Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
<dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be>
-Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com>
+Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com>
Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
Sarangdhar Joshi <spjoshi@codeaurora.org>
Sascha Hauer <s.hauer@pengutronix.de>
S.Çağlar Onur <caglar@pardus.org.tr>
+Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com>
Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
Sebastian Reichel <sre@kernel.org> <sre@debian.org>
Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
+Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+Uwe Kleine-König <ukleinek@strlen.de>
Uwe Kleine-König <ukl@pengutronix.de>
Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
E: andersen@codepoet.org
W: https://www.codepoet.org/
P: 1024D/30D39057 1BC4 2742 E885 E4DE 9301 0C82 5F9B 643E 30D3 9057
-D: Maintainer of ide-cd and Uniform CD-ROM driver,
+D: Maintainer of ide-cd and Uniform CD-ROM driver,
D: ATAPI CD-Changer support, Major 2.1.x CD-ROM update.
S: 352 North 525 East
S: Springville, Utah 84663
E: pbd@op.net
D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+)
D: Various bugfixes and changes to sound drivers
-S: USA
+S: USA
N: Carlos Henrique Bauer
E: chbauer@acm.org
S: Portland, Oregon
S: USA
+N: Jason Cooper
+D: ARM/Marvell SOC co-maintainer
+D: irqchip co-maintainer
+D: MVEBU PCI DRIVER co-maintainer
+
N: Robin Cornelius
E: robincornelius@users.sourceforge.net
D: Ralink rt2x00 WLAN driver
D: AX25-HOWTO, HAM-HOWTO, IPX-HOWTO, NET-2-HOWTO
D: ax25-utils maintainer.
+N: Kamil Debski
+E: kamil@wypas.org
+D: Samsung S5P 2D graphics acceleration and Multi Format Codec drivers
+D: Samsung USB2 phy drivers
+D: PWM fan driver
+
N: Helge Deller
E: deller@gmx.de
W: http://www.parisc-linux.org/
E: dfrasnel@alphalinux.org
W: http://www.alphalinux.org/
P: 1024/3EF87611 B9 F1 44 50 D3 E8 C2 80 DA E5 55 AA 56 7C 42 DA
-D: DEC Alpha hacker
+D: DEC Alpha hacker
D: Miscellaneous bug squisher
N: Jim Freeman
S: New South Wales, 2121
S: Australia
-N: Carlos E. Gorges
+N: Carlos E. Gorges
E: carlos@techlinux.com.br
D: fix smp support on cmpci driver
P: 2048G/EA3C4B19 FF31 33A6 0362 4915 B7EB E541 17D0 0379 EA3C 4B19
E: wgreathouse@myfavoritei.com
D: Current Belkin USB Serial Adapter F5U103 hacker
D: Kernel hacker, embedded systems
-S: 7802 Fitzwater Road
+S: 7802 Fitzwater Road
S: Brecksville, OH 44141-1334
S: USA
E: grant@torque.net
W: http://www.torque.net/linux-pp.html
D: original author of ppa driver for parallel port ZIP drive
-D: original architect of the parallel-port sharing scheme
+D: original architect of the parallel-port sharing scheme
D: PARIDE subsystem: drivers for parallel port IDE & ATAPI devices
S: 44 St. Joseph Street, Suite 506
S: Toronto, Ontario, M4Y 2W4
E: benh@kernel.crashing.org
D: Various parts of PPC/PPC64 & PowerMac
S: 312/107 Canberra Avenue
-S: Griffith, ACT 2603
+S: Griffith, ACT 2603
S: Australia
N: Andreas Herrmann
N: Bernhard Kaindl
E: bkaindl@netway.at
E: edv@bartelt.via.at
-D: Author of a menu based configuration tool, kmenu, which
+D: Author of a menu based configuration tool, kmenu, which
D: is the predecessor of 'make menuconfig' and 'make xconfig'.
D: digiboard driver update(modularisation work and 2.1.x upd)
S: Tallak 95
S: Santa Clara, CA 95051
S: USA
+N: Kukjin Kim
+E: kgene@kernel.org
+D: Samsung S3C, S5P and Exynos ARM architectures
+
+N: Sangbeom Kim
+E: sbkim73@samsung.com
+D: Samsung SoC Audio (ASoC) drivers
+D: Samsung PMIC (RTC, regulators, MFD) drivers
+
N: Russell King
E: rmk@arm.linux.org.uk
D: Linux/arm integrator, maintainer & hacker
D: IP transparent proxy support
S: X/OS Experts in Open Systems BV
S: Kruislaan 419
-S: 1098 VA Amsterdam
+S: 1098 VA Amsterdam
S: The Netherlands
N: Goran Koruga
N: Andrzej M. Krzysztofowicz
E: ankry@mif.pg.gda.pl
-D: Some 8-bit XT disk driver and devfs hacking
+D: Some 8-bit XT disk driver and devfs hacking
D: Aladdin 1533/1543(C) chipset IDE
D: PIIX chipset IDE
S: ul. Matemblewska 1B/10
D: Logical Volume Manager
S: Bartningstr. 12
S: 64289 Darmstadt
-S: Germany
+S: Germany
N: Mark W. McClelland
E: mmcclell@bigfoot.com
P: 1024/04B6E8F5 6C 77 33 CA CC D6 22 03 AB AB 15 A3 AE AD 39 7D
D: Kernel hacker. PostgreSQL hacker. Software watchdog daemon.
D: Maintainer of several Debian packages
-S: Th.-Heuss-Str. 61
+S: Th.-Heuss-Str. 61
S: D-41812 Erkelenz
S: Germany
W: http://www.i-Connect.Net/~mike/
D: Developer and maintainer of the EATA-DMA SCSI driver
D: Co-developer EATA-PIO SCSI driver
-D: /proc/scsi and assorted other snippets
+D: /proc/scsi and assorted other snippets
S: Zum Schiersteiner Grund 2
S: 55127 Mainz
S: Germany
N: Venkatesh Pallipadi (Venki)
D: x86/HPET
+N: Kyungmin Park
+E: kyungmin.park@samsung.com
+D: Samsung S5Pv210 and Exynos4210 mobile platforms
+
N: David Parsons
E: orc@pell.chi.il.us
D: improved memory detection code.
S: Chandler, Arizona 85249
S: USA
-N: Frederic Potter
+N: Frederic Potter
E: fpotter@cirpack.com
D: Some PCI kernel support
S: 76131 Karlsruhe
S: Germany
-N: James Simmons
+N: James Simmons
E: jsimmons@infradead.org
-E: jsimmons@users.sf.net
+E: jsimmons@users.sf.net
D: Frame buffer device maintainer
D: input layer development
D: tty/console layer
-D: various mipsel devices
-S: 115 Carmel Avenue
+D: various mipsel devices
+S: 115 Carmel Avenue
S: El Cerrito CA 94530
-S: USA
+S: USA
N: Jaspreet Singh
E: jaspreet@sangoma.com
W: www.sangoma.com
-D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards
+D: WANPIPE drivers & API Support for Sangoma S508/FT1 cards
S: Sangoma Technologies Inc.,
S: 1001 Denison Street
S: Suite 101
E: csmall@triode.apana.org.au
E: vk2xlz@gonzo.vk2xlz.ampr.org (packet radio)
D: Gracilis PackeTwin device driver
-D: RSPF daemon
+D: RSPF daemon
S: 10 Stockalls Place
S: Minto, NSW, 2566
S: Australia
E: tsusheng@scf.usc.edu
D: IGMP(Internet Group Management Protocol) version 2
S: 2F 14 ALY 31 LN 166 SEC 1 SHIH-PEI RD
-S: Taipei
+S: Taipei
S: Taiwan 112
S: Republic of China
S: 24335 Delta Drive
D: patches for ghostscript, worked on color 'ls', etc.
S: 301 15th Street S.
S: Moorhead, Minnesota 56560
-S: USA
+S: USA
N: Jos Vos
E: jos@xos.nl
D: Various IP firewall updates, ipfwadm
S: X/OS Experts in Open Systems BV
S: Kruislaan 419
-S: 1098 VA Amsterdam
+S: 1098 VA Amsterdam
S: The Netherlands
N: Jeroen Vreeken
N: Victor Yodaiken
E: yodaiken@fsmlabs.com
D: RTLinux (RealTime Linux)
-S: POB 1822
+S: POB 1822
S: Socorro NM, 87801
S: USA
S: France
# Don't add your name here, unless you really _are_ after Marc
-# alphabetically. Leonard used to be very proud of being the
+# alphabetically. Leonard used to be very proud of being the
# last entry, and he'll get positively pissed if he can't even
# be second-to-last. (and this file really _is_ supposed to be
# in alphabetic order)
layout of the files below for details on how to do this.)
obsolete/
- This directory documents interfaces that are still remaining in
+ This directory documents interfaces that are still remaining in
the kernel, but are marked to be removed at some later point in
time. The description of the interface will document the reason
why it is obsolete and when it can be expected to be removed.
be changed further.
+Note:
+ The fields should be use a simple notation, compatible with ReST markup.
+ Also, the file **should not** have a top-level index, like::
+
+ ===
+ foo
+ ===
+
How things move between levels:
Interfaces in stable may move to obsolete, as long as the proper
system. Device DAX is strict, precise and predictable.
Specifically this interface:
- 1/ Guarantees fault granularity with respect to a given
- page size (pte, pmd, or pud) set at configuration time.
+ 1. Guarantees fault granularity with respect to a given
+ page size (pte, pmd, or pud) set at configuration time.
- 2/ Enforces deterministic behavior by being strict about
- what fault scenarios are supported.
+ 2. Enforces deterministic behavior by being strict about
+ what fault scenarios are supported.
The /sys/class/dax/ interface enumerates all the
device-dax instances in the system. The ABI is
setting reported by the mouse. This number has to be further
processed to receive the real dpi value:
+ ===== ====
VALUE DPI
+ ===== ====
1 400
2 800
4 1600
+ ===== ====
This file is readonly.
Has never been used. If bookkeeping is done, it's done in userland tools.
GPIOs are identified as they are inside the kernel, using integers in
the range 0..INT_MAX. See Documentation/admin-guide/gpio for more information.
+ ::
+
/sys/class/gpio
/export ... asks the kernel to export a GPIO to userspace
/unexport ... to return a GPIO to the kernel
devfs has been unmaintained for a number of years, has unfixable
races, contains a naming policy within the kernel that is
against the LSB, and can be replaced by using udev.
+
The files fs/devfs/*, include/linux/devfs_fs*.h were removed,
along with the assorted devfs function calls throughout the
kernel tree.
to implement sensible device security policies, and its low level
of abstraction that required userspace clients to duplicate much
of the kernel's ieee1394 core functionality.
+
Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
firewire-core.
claim just control over a single rfkill instance.
This file was scheduled to be removed in 2012, and was removed
in 2016.
-Values: 0: Kernel handles events
+Values: 0: Kernel handles events
performance issues in its first generation. Any video1394 user had
to use raw1394 + libraw1394 too because video1394 did not provide
asynchronous I/O for device discovery and configuration.
+
Replaced by /dev/fw*, i.e. the <linux/firewire-cdev.h> ABI of
firewire-core.
Each /dev/fw* is associated with one IEEE 1394 node, which can
be remote or local nodes. Operations on a /dev/fw* file have
different scope:
+
- The 1394 node which is associated with the file:
+
- Asynchronous request transmission
- Get the Configuration ROM
- Query node ID
- Query maximum speed of the path between this node
and local node
+
- The 1394 bus (i.e. "card") to which the node is attached to:
+
- Isochronous stream transmission and reception
- Asynchronous stream transmission and reception
- Asynchronous broadcast request transmission
manager
- Query cycle time
- Bus reset initiation, bus reset event reception
+
- All 1394 buses:
+
- Allocation of IEEE 1212 address ranges on the local
link layers, reception of inbound requests to such
an address range, asynchronous response transmission
userland implement different access permission models, some
operations are restricted to /dev/fw* files that are associated
with a local node:
+
- Addition of descriptors or directories to the local
nodes' Configuration ROM
- PHY packet transmission and reception
The following file operations are supported:
open(2)
- Currently the only useful flags are O_RDWR.
+ Currently the only useful flags are O_RDWR.
ioctl(2)
- Initiate various actions. Some take immediate effect, others
- are performed asynchronously while or after the ioctl returns.
- See the inline documentation in <linux/firewire-cdev.h> for
- descriptions of all ioctls.
+ Initiate various actions. Some take immediate effect, others
+ are performed asynchronously while or after the ioctl returns.
+ See the inline documentation in <linux/firewire-cdev.h> for
+ descriptions of all ioctls.
poll(2), select(2), epoll_wait(2) etc.
- Watch for events to become available to be read.
+ Watch for events to become available to be read.
read(2)
- Receive various events. There are solicited events like
- outbound asynchronous transaction completion or isochronous
- buffer completion, and unsolicited events such as bus resets,
- request reception, or PHY packet reception. Always use a read
- buffer which is large enough to receive the largest event that
- could ever arrive. See <linux/firewire-cdev.h> for descriptions
- of all event types and for which ioctls affect reception of
- events.
+ Receive various events. There are solicited events like
+ outbound asynchronous transaction completion or isochronous
+ buffer completion, and unsolicited events such as bus resets,
+ request reception, or PHY packet reception. Always use a read
+ buffer which is large enough to receive the largest event that
+ could ever arrive. See <linux/firewire-cdev.h> for descriptions
+ of all event types and for which ioctls affect reception of
+ events.
mmap(2)
- Allocate a DMA buffer for isochronous reception or transmission
- and map it into the process address space. The arguments should
- be used as follows: addr = NULL, length = the desired buffer
- size, i.e. number of packets times size of largest packet,
- prot = at least PROT_READ for reception and at least PROT_WRITE
- for transmission, flags = MAP_SHARED, fd = the handle to the
- /dev/fw*, offset = 0.
+ Allocate a DMA buffer for isochronous reception or transmission
+ and map it into the process address space. The arguments should
+ be used as follows: addr = NULL, length = the desired buffer
+ size, i.e. number of packets times size of largest packet,
+ prot = at least PROT_READ for reception and at least PROT_WRITE
+ for transmission, flags = MAP_SHARED, fd = the handle to the
+ /dev/fw*, offset = 0.
Isochronous reception works in packet-per-buffer fashion except
for multichannel reception which works in buffer-fill mode.
munmap(2)
- Unmap the isochronous I/O buffer from the process address space.
+ Unmap the isochronous I/O buffer from the process address space.
close(2)
- Besides stopping and freeing I/O contexts that were associated
- with the file descriptor, back out any changes to the local
- nodes' Configuration ROM. Deallocate isochronous channels and
- bandwidth at the IRM that were marked for kernel-assisted
- re- and deallocation.
-
-Users: libraw1394
- libdc1394
- libhinawa
+ Besides stopping and freeing I/O contexts that were associated
+ with the file descriptor, back out any changes to the local
+ nodes' Configuration ROM. Deallocate isochronous channels and
+ bandwidth at the IRM that were marked for kernel-assisted
+ re- and deallocation.
+
+Users: libraw1394;
+ libdc1394;
+ libhinawa;
tools like linux-firewire-utils, fwhack, ...
-What: /sys/firmware/acpi/pm_profile
+What: /sys/firmware/acpi/pm_profile
Date: 03-Nov-2011
KernelVersion: v3.2
Contact: linux-acpi@vger.kernel.org
-Description: The ACPI pm_profile sysfs interface exports the platform
+Description: The ACPI pm_profile sysfs interface exports the platform
power management (and performance) requirement expectations
as provided by BIOS. The integer value is directly passed as
retrieved from the FADT ACPI table.
-Values: For possible values see ACPI specification:
+
+Values: For possible values see ACPI specification:
5.2.9 Fixed ACPI Description Table (FADT)
Field: Preferred_PM_Profile
Currently these values are defined by spec:
- 0 Unspecified
- 1 Desktop
- 2 Mobile
- 3 Workstation
- 4 Enterprise Server
- 5 SOHO Server
- 6 Appliance PC
- 7 Performance Server
+
+ == =================
+ 0 Unspecified
+ 1 Desktop
+ 2 Mobile
+ 3 Workstation
+ 4 Enterprise Server
+ 5 SOHO Server
+ 6 Appliance PC
+ 7 Performance Server
>7 Reserved
+ == =================
IEEE 1394 node device attribute.
Read-only and immutable.
Values: 1: The sysfs entry represents a local node (a controller card).
+
0: The sysfs entry represents a remote node.
Read-only attribute, immutable during the target's lifetime.
Format, as exposed by firewire-sbp2 since 2.6.22, May 2007:
Colon-separated hexadecimal string representations of
+
u64 EUI-64 : u24 directory_ID : u16 LUN
+
without 0x prefixes, without whitespace. The former sbp2 driver
(removed in 2.6.37 after being superseded by firewire-sbp2) used
a somewhat shorter format which was not as close to SAM.
Note: This file is only present if CONFIG_NVMEM_SYSFS
is enabled
- ex:
- hexdump /sys/bus/nvmem/devices/qfprom0/nvmem
+ ex::
- 0000000 0000 0000 0000 0000 0000 0000 0000 0000
- *
- 00000a0 db10 2240 0000 e000 0c00 0c00 0000 0c00
- 0000000 0000 0000 0000 0000 0000 0000 0000 0000
- ...
- *
- 0001000
+ hexdump /sys/bus/nvmem/devices/qfprom0/nvmem
+
+ 0000000 0000 0000 0000 0000 0000 0000 0000 0000
+ *
+ 00000a0 db10 2240 0000 e000 0c00 0c00 0000 0c00
+ 0000000 0000 0000 0000 0000 0000 0000 0000 0000
+ ...
+ *
+ 0001000
Tools can use this file and the connected_duration file to
compute the percentage of time that a device has been active.
- For example,
- echo $((100 * `cat active_duration` / `cat connected_duration`))
+ For example::
+
+ echo $((100 * `cat active_duration` / `cat connected_duration`))
+
will give an integer percentage. Note that this does not
account for counter wrap.
Users:
Description: VCPU (sub)channel is affinitized to
Users: tools/hv/lsvmbus and other debugging tools
-What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/cpu
-Date: September. 2017
-KernelVersion: 4.14
-Contact: Stephen Hemminger <sthemmin@microsoft.com>
-Description: VCPU (sub)channel is affinitized to
-Users: tools/hv/lsvmbus and other debugging tools
-
What: /sys/bus/vmbus/devices/<UUID>/channels/<N>/in_mask
Date: September. 2017
KernelVersion: 4.14
control systems are attached/generate presence for as short as
100 ms - hence the tens-to-hundreds milliseconds scan intervals
are required.
+
see Documentation/w1/w1-generic.rst for detailed information.
Users: any user space application which wants to know bus scanning
interval
Contact: Richard Purdie <rpurdie@rpsys.net>
Description:
Control BACKLIGHT power, values are FB_BLANK_* from fb.h
+
- FB_BLANK_UNBLANK (0) : power on.
- FB_BLANK_POWERDOWN (4) : power off
Users: HAL
KernelVersion: v2.6.12
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===========================================
node_type: (RO) Node type (CA, RNIC, usNIC, usNIC UDP,
switch or router)
node_guid: (RO) Node GUID
sys_image_guid: (RO) System image GUID
+ =============== ===========================================
What: /sys/class/infiniband/<device>/node_desc
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===============================================
lid: (RO) Port LID
rate: (RO) Port data rate (active width * active
cap_mask: (RO) Port capability mask. 2 bits here are
settable- IsCommunicationManagementSupported
- (set when CM module is loaded) and IsSM (set via
- open of issmN file).
+ (set when CM module is loaded) and IsSM (set
+ via open of issmN file).
+ =============== ===============================================
What: /sys/class/infiniband/<device>/ports/<port-num>/link_layer
KernelVersion: v2.6.12
Contact: linux-rdma@vger.kernel.org
Description:
- Errors info:
- -----------
+ **Errors info**:
symbol_error: (RO) Total number of minor link errors detected on
one or more physical lanes.
intervention. It can also indicate hardware issues or extremely
poor link signal integrity
- Data info:
- ---------
+ **Data info**:
port_xmit_data: (RO) Total number of data octets, divided by 4
(lanes), transmitted on all VLs. This is 64 bit counter
transmitted on all VLs from the port. This may include multicast
packets with errors.
- Misc info:
- ---------
+ **Misc info**:
port_xmit_discards: (RO) Total number of outbound packets
discarded by the port because the port is down or congested.
two umad devices and two issm devices, while a switch will have
one device of each type (for switch port 0).
+ ======= =====================================
ibdev: (RO) Show Infiniband (IB) device name
port: (RO) Display port number
+ ======= =====================================
What: /sys/class/infiniband_mad/abi_version
KernelVersion: v2.6.14
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===========================================
ibdev: (RO) Display Infiniband (IB) device name
abi_version: (RO) Show ABI version of IB device specific
interfaces.
+ =============== ===========================================
What: /sys/class/infiniband_verbs/abi_version
KernelVersion: v2.6.12
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ================================================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host Channel Adapter type: MT23108, MT25208
(MT23108 compat mode), MT25208 or MT25204
board_id: (RO) Manufacturing board ID
+ =============== ================================================
sysfs interface for Mellanox ConnectX HCA IB driver (mlx4)
KernelVersion: v2.6.24
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===============================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host channel adapter type
board_id: (RO) Manufacturing board ID
+ =============== ===============================
What: /sys/class/infiniband/mlx4_X/iov/ports/<port-num>/gids/<n>
example, ports/1/pkeys/10 contains the value at index 10 in port
1's P_Key table.
+ ======================= ==========================================
gids/<n>: (RO) The physical port gids n = 0..127
admin_guids/<n>: (RW) Allows examining or changing the
guest, whenever it uses its pkey index
1, will actually be using the real pkey
index 10.
+ ======================= ==========================================
What: /sys/class/infiniband/mlx4_X/iov/<pci-slot-num>/ports/<m>/smi_enabled
Enabling QP0 on VFs for selected VF/port. By default, no VFs are
enabled for QP0 operation.
- smi_enabled: (RO) Indicates whether smi is currently enabled
- for the indicated VF/port
+ ================= ==== ===========================================
+ smi_enabled: (RO) Indicates whether smi is currently enabled
+ for the indicated VF/port
- enable_smi_admin:(RW) Used by the admin to request that smi
- capability be enabled or disabled for the
- indicated VF/port. 0 = disable, 1 = enable.
+ enable_smi_admin: (RW) Used by the admin to request that smi
+ capability be enabled or disabled for the
+ indicated VF/port. 0 = disable, 1 = enable.
+ ================= ==== ===========================================
The requested enablement will occur at the next reset of the VF
(e.g. driver restart on the VM which owns the VF).
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== =============================================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Driver short name. Should normally match
board_id: (RO) Manufacturing board id. (Vendor + device
information)
+ =============== =============================================
sysfs interface for Intel IB driver qib
KernelVersion: v2.6.35
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ======================================================
version: (RO) Display version information of installed software
and drivers.
chip_reset: (WO) Reset the chip if possible by writing
"reset" to this file. Only allowed if no user
contexts are open that use chip resources.
+ =============== ======================================================
What: /sys/class/infiniband/qibX/ports/N/sl2vl/[0-15]
Description:
Per-port congestion control. Both are binary attributes.
- cc_table_bin: (RO) Congestion control table size followed by
+ =============== ================================================
+ cc_table_bin (RO) Congestion control table size followed by
table entries.
- cc_settings_bin:(RO) Congestion settings: port control, control
+ cc_settings_bin (RO) Congestion settings: port control, control
map and an array of 16 entries for the
congestion entries - increase, timer, event log
trigger threshold and the minimum injection rate
delay.
+ =============== ================================================
What: /sys/class/infiniband/qibX/ports/N/linkstate/loopback
What: /sys/class/infiniband/qibX/ports/N/linkstate/led_override
Description:
[to be documented]
+ =============== ===============================================
loopback: (WO)
led_override: (WO)
hrtbt_enable: (RW)
errors. Possible states are- "Initted",
"Present", "IB_link_up", "IB_configured" or
"Fatal_Hardware_Error".
+ =============== ===============================================
What: /sys/class/infiniband/qibX/ports/N/diag_counters/rc_resends
What: /sys/class/infiniband/qibX/ports/N/diag_counters/seq_naks
linux-rdma@vger.kernel.org
Description:
+ =============== ===============================================
board_id: (RO) Manufacturing board id
config: (RO) Report the configuration for this PF
iface: (RO) Shows which network interface this usNIC
entry is associated to (visible with ifconfig).
+ =============== ===============================================
What: /sys/class/infiniband/usnic_X/qpn/summary
What: /sys/class/infiniband/usnic_X/qpn/context
KernelVersion: v4.6
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== =============================================
hw_rev: (RO) Hardware revision number
board_id: (RO) Manufacturing board id
available.
tempsense: (RO) Thermal sense information
+ =============== =============================================
What: /sys/class/infiniband/hfi1_X/ports/N/CCMgtA/cc_settings_bin
Description:
Per-port congestion control.
- cc_table_bin: (RO) CCA tables used by PSM2 Congestion control
+ =============== ================================================
+ cc_table_bin (RO) CCA tables used by PSM2 Congestion control
table size followed by table entries. Binary
attribute.
- cc_settings_bin:(RO) Congestion settings: port control, control
+ cc_settings_bin (RO) Congestion settings: port control, control
map and an array of 16 entries for the
congestion entries - increase, timer, event log
trigger threshold and the minimum injection rate
delay. Binary attribute.
- cc_prescan: (RW) enable prescanning for faster BECN
+ cc_prescan (RW) enable prescanning for faster BECN
response. Write "on" to enable and "off" to
disable.
+ =============== ================================================
What: /sys/class/infiniband/hfi1_X/ports/N/sc2vl/[0-31]
What: /sys/class/infiniband/hfi1_X/ports/N/sl2sc/[0-31]
KernelVersion: v4.6
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ===================================================
sc2vl/: (RO) 32 files (0 - 31) used to translate sl->vl
sl2sc/: (RO) 32 files (0 - 31) used to translate sl->sc
vl2mtu/: (RO) 16 files (0 - 15) used to determine MTU for vl
+ =============== ===================================================
What: /sys/class/infiniband/hfi1_X/sdma_N/cpu_list
Description:
sdma<N>/ contains one directory per sdma engine (0 - 15)
+ =============== ==============================================
cpu_list: (RW) List of cpus for user-process to sdma
engine assignment.
vl: (RO) Displays the virtual lane (vl) the sdma
engine maps to.
+ =============== ==============================================
This interface gives the user control on the affinity settings
for the device. As an example, to set an sdma engine irq
affinity and thread affinity of a user processes to use the
sdma engine, which is "near" in terms of NUMA configuration, or
- physical cpu location, the user will do:
+ physical cpu location, the user will do::
- echo "3" > /proc/irq/<N>/smp_affinity_list
- echo "4-7" > /sys/devices/.../sdma3/cpu_list
- cat /sys/devices/.../sdma3/vl
- 0
- echo "8" > /proc/irq/<M>/smp_affinity_list
- echo "9-12" > /sys/devices/.../sdma4/cpu_list
- cat /sys/devices/.../sdma4/vl
- 1
+ echo "3" > /proc/irq/<N>/smp_affinity_list
+ echo "4-7" > /sys/devices/.../sdma3/cpu_list
+ cat /sys/devices/.../sdma3/vl
+ 0
+ echo "8" > /proc/irq/<M>/smp_affinity_list
+ echo "9-12" > /sys/devices/.../sdma4/cpu_list
+ cat /sys/devices/.../sdma4/vl
+ 1
to make sure that when a process runs on cpus 4,5,6, or 7, and
uses vl=0, then sdma engine 3 is selected by the driver, and
KernelVersion: v4.10
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== ========================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Show HCA type (I40IW)
board_id: (RO) I40IW board ID
+ =============== ==== ========================
sysfs interface for QLogic qedr NIC Driver
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== ========================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Display HCA type
+ =============== ==== ========================
sysfs interface for VMware Paravirtual RDMA driver
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== =====================================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host channel adapter type
board_id: (RO) Display PVRDMA manufacturing board ID
+ =============== ==== =====================================
sysfs interface for Broadcom NetXtreme-E RoCE driver
KernelVersion: v4.11
Contact: linux-rdma@vger.kernel.org
Description:
+ =============== ==== =========================
hw_rev: (RO) Hardware revision number
hca_type: (RO) Host channel adapter type
+ =============== ==== =========================
For details to this subsystem look at Documentation/driver-api/rfkill.rst.
-For the deprecated /sys/class/rfkill/*/claim knobs of this interface look in
+For the deprecated ``/sys/class/rfkill/*/claim`` knobs of this interface look in
Documentation/ABI/removed/sysfs-class-rfkill.
What: /sys/class/rfkill
Contact: linux-wireless@vger.kernel.org
Description: Whether the soft blocked state is initialised from non-volatile
storage at startup.
-Values: A numeric value.
- 0: false
- 1: true
+Values: A numeric value:
+
+ - 0: false
+ - 1: true
What: /sys/class/rfkill/rfkill[0-9]+/state
through this interface. There will likely be another attempt to
remove it in the future.
Values: A numeric value.
+
0: RFKILL_STATE_SOFT_BLOCKED
transmitter is turned off by software
1: RFKILL_STATE_UNBLOCKED
Contact: linux-wireless@vger.kernel.org
Description: Current hardblock state. This file is read only.
Values: A numeric value.
+
0: inactive
The transmitter is (potentially) active.
1: active
Contact: linux-wireless@vger.kernel.org
Description: Current softblock state. This file is read and write.
Values: A numeric value.
+
0: inactive
The transmitter is (potentially) active.
+
1: active
The transmitter is turned off by software.
Contact: linux-integrity@vger.kernel.org
Description: The "caps" property contains TPM manufacturer and version info.
- Example output:
+ Example output::
- Manufacturer: 0x53544d20
- TCG version: 1.2
- Firmware version: 8.16
+ Manufacturer: 0x53544d20
+ TCG version: 1.2
+ Firmware version: 8.16
Manufacturer is a hex dump of the 4 byte manufacturer info
space in a TPM. TCG version shows the TCG TPM spec level that
any longer than necessary before starting to poll for a
result.
- Example output:
+ Example output::
- 3015000 4508000 180995000 [original]
+ 3015000 4508000 180995000 [original]
Here the short, medium and long durations are displayed in
usecs. "[original]" indicates that the values are displayed
values may be constantly changing, the output is only valid
for a snapshot in time.
- Example output:
+ Example output::
- PCR-00: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-01: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-02: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-03: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- PCR-04: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
- ...
+ PCR-00: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-01: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-02: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-03: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ PCR-04: 3A 3F 78 0F 11 A4 B4 99 69 FC AA 80 CD 6E 39 57 C3 3B 22 75
+ ...
The number of PCRs and hex bytes needed to represent a PCR
value will vary depending on TPM chip version. For TPM 1.1 and
ated at TPM manufacture time and exists for the life of the
chip.
- Example output:
-
- Algorithm: 00 00 00 01
- Encscheme: 00 03
- Sigscheme: 00 01
- Parameters: 00 00 08 00 00 00 00 02 00 00 00 00
- Modulus length: 256
- Modulus:
- B4 76 41 82 C9 20 2C 10 18 40 BC 8B E5 44 4C 6C
- 3A B2 92 0C A4 9B 2A 83 EB 5C 12 85 04 48 A0 B6
- 1E E4 81 84 CE B2 F2 45 1C F0 85 99 61 02 4D EB
- 86 C4 F7 F3 29 60 52 93 6B B2 E5 AB 8B A9 09 E3
- D7 0E 7D CA 41 BF 43 07 65 86 3C 8C 13 7A D0 8B
- 82 5E 96 0B F8 1F 5F 34 06 DA A2 52 C1 A9 D5 26
- 0F F4 04 4B D9 3F 2D F2 AC 2F 74 64 1F 8B CD 3E
- 1E 30 38 6C 70 63 69 AB E2 50 DF 49 05 2E E1 8D
- 6F 78 44 DA 57 43 69 EE 76 6C 38 8A E9 8E A3 F0
- A7 1F 3C A8 D0 12 15 3E CA 0E BD FA 24 CD 33 C6
- 47 AE A4 18 83 8E 22 39 75 93 86 E6 FD 66 48 B6
- 10 AD 94 14 65 F9 6A 17 78 BD 16 53 84 30 BF 70
- E0 DC 65 FD 3C C6 B0 1E BF B9 C1 B5 6C EF B1 3A
- F8 28 05 83 62 26 11 DC B4 6B 5A 97 FF 32 26 B6
- F7 02 71 CF 15 AE 16 DD D1 C1 8E A8 CF 9B 50 7B
- C3 91 FF 44 1E CF 7C 39 FE 17 77 21 20 BD CE 9B
-
- Possible values:
-
- Algorithm: TPM_ALG_RSA (1)
- Encscheme: TPM_ES_RSAESPKCSv15 (2)
+ Example output::
+
+ Algorithm: 00 00 00 01
+ Encscheme: 00 03
+ Sigscheme: 00 01
+ Parameters: 00 00 08 00 00 00 00 02 00 00 00 00
+ Modulus length: 256
+ Modulus:
+ B4 76 41 82 C9 20 2C 10 18 40 BC 8B E5 44 4C 6C
+ 3A B2 92 0C A4 9B 2A 83 EB 5C 12 85 04 48 A0 B6
+ 1E E4 81 84 CE B2 F2 45 1C F0 85 99 61 02 4D EB
+ 86 C4 F7 F3 29 60 52 93 6B B2 E5 AB 8B A9 09 E3
+ D7 0E 7D CA 41 BF 43 07 65 86 3C 8C 13 7A D0 8B
+ 82 5E 96 0B F8 1F 5F 34 06 DA A2 52 C1 A9 D5 26
+ 0F F4 04 4B D9 3F 2D F2 AC 2F 74 64 1F 8B CD 3E
+ 1E 30 38 6C 70 63 69 AB E2 50 DF 49 05 2E E1 8D
+ 6F 78 44 DA 57 43 69 EE 76 6C 38 8A E9 8E A3 F0
+ A7 1F 3C A8 D0 12 15 3E CA 0E BD FA 24 CD 33 C6
+ 47 AE A4 18 83 8E 22 39 75 93 86 E6 FD 66 48 B6
+ 10 AD 94 14 65 F9 6A 17 78 BD 16 53 84 30 BF 70
+ E0 DC 65 FD 3C C6 B0 1E BF B9 C1 B5 6C EF B1 3A
+ F8 28 05 83 62 26 11 DC B4 6B 5A 97 FF 32 26 B6
+ F7 02 71 CF 15 AE 16 DD D1 C1 8E A8 CF 9B 50 7B
+ C3 91 FF 44 1E CF 7C 39 FE 17 77 21 20 BD CE 9B
+
+ Possible values::
+
+ Algorithm: TPM_ALG_RSA (1)
+ Encscheme: TPM_ES_RSAESPKCSv15 (2)
TPM_ES_RSAESOAEP_SHA1_MGF1 (3)
- Sigscheme: TPM_SS_NONE (1)
- Parameters, a byte string of 3 u32 values:
+ Sigscheme: TPM_SS_NONE (1)
+ Parameters, a byte string of 3 u32 values:
Key Length (bits): 00 00 08 00 (2048)
Num primes: 00 00 00 02 (2)
Exponent Size: 00 00 00 00 (0 means the
default exp)
- Modulus Length: 256 (bytes)
- Modulus: The 256 byte Endorsement Key modulus
+ Modulus Length: 256 (bytes)
+ Modulus: The 256 byte Endorsement Key modulus
What: /sys/class/tpm/tpmX/device/temp_deactivated
Date: April 2006
timeouts is defined by the TPM interface spec that the chip
conforms to.
- Example output:
+ Example output::
- 750000 750000 750000 750000 [original]
+ 750000 750000 750000 750000 [original]
The four timeout values are shown in usecs, with a trailing
"[original]" or "[adjusted]" depending on whether the values
Description: The "tpm_version_major" property shows the TCG spec major version
implemented by the TPM device.
- Example output:
+ Example output::
- 2
+ 2
-# Note: This documents additional properties of any device beyond what
-# is documented in Documentation/admin-guide/sysfs-rules.rst
+Note:
+ This documents additional properties of any device beyond what
+ is documented in Documentation/admin-guide/sysfs-rules.rst
What: /sys/devices/*/of_node
Date: February 2015
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/cap
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: Capabilities the DMA supports.Currently there are DMA_PQ, DMA_PQ_VAL,
DMA_XOR,DMA_XOR_VAL,DMA_INTERRUPT.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_active
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: The number of descriptors active in the ring.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/ring_size
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: Descriptor ring size, total number of descriptors available.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/version
Date: December 3, 2009
KernelVersion: 2.6.32
Contact: dmaengine@vger.kernel.org
Description: Version of ioatdma device.
-What: sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
+What: /sys/devices/pciXXXX:XX/0000:XX:XX.X/dma/dma<n>chan<n>/quickdata/intr_coalesce
Date: August 8, 2017
KernelVersion: 4.14
Contact: dmaengine@vger.kernel.org
resets. Three registers are used by the FSBL and
other Xilinx software products: GLOBAL_GEN_STORAGE{4:6}.
- Usage:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
- # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ Usage::
+
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+
+ Example::
- Example:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
- # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
+ # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/ggs0
Users: Xilinx
software products: PERS_GLOB_GEN_STORAGE{4:7}.
Register is reset only by a POR reset.
- Usage:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
- # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ Usage::
+
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ # echo <value> > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+
+ Example::
- Example:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
- # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
+ # echo 0x1234ABCD > /sys/devices/platform/firmware\:zynqmp-firmware/pggs0
Users: Xilinx
Following are available shutdown scopes(subtypes):
- subsystem: Only the APU along with all of its peripherals
+ subsystem:
+ Only the APU along with all of its peripherals
not used by other processing units will be
shut down. This may result in the FPD power
domain being shut down provided that no other
processing unit uses FPD peripherals or DRAM.
- ps_only: The complete PS will be shut down, including the
+ ps_only:
+ The complete PS will be shut down, including the
RPU, PMU, etc. Only the PL domain (FPGA)
remains untouched.
- system: The complete system/device is shut down.
+ system:
+ The complete system/device is shut down.
- Usage:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
- # echo <scope> > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ Usage::
+
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ # echo <scope> > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+
+ Example::
- Example:
- # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
- # echo "subsystem" > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ # cat /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
+ # echo "subsystem" > /sys/devices/platform/firmware\:zynqmp-firmware/shutdown_scope
Users: Xilinx
system restart.
Usage:
- Set healthy bit
- # echo 1 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
- Unset healthy bit
- # echo 0 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
+ Set healthy bit::
+
+ # echo 1 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
+
+ Unset healthy bit::
+
+ # echo 0 > /sys/devices/platform/firmware\:zynqmp-firmware/health_status
Users: Xilinx
One can request ib_srp to connect to a new target by writing
a comma-separated list of login parameters to this sysfs
attribute. The supported parameters are:
+
* id_ext, a 16-digit hexadecimal number specifying the eight
byte identifier extension in the 16-byte SRP target port
identifier. The target port identifier is sent by ib_srp
speakup if for example
the say screen command is used before the
entire screen is read.
+
With no_interrupt set to one, if the say
screen command is used, and one then types on the keyboard,
speakup will continue to say the whole screen regardless until
Again, these are part of the help system. For instance, if you
had pressed speakup + keypad 3, you would hear:
"speakup keypad 3 is go to bottom edge."
+
The speakup key is depressed, so the name of the key state is
speakup.
+
This part of the message comes from the states collection.
What: /sys/accessibility/speakup/i18n/characters
Contact: speakup@linux-speakup.org
Description: Controls if punctuation is spoken by speakup, or by the
synthesizer.
+
For example, speakup speaks ">" as "greater", while
the espeak synthesizer used by the soft driver speaks "greater
than". Zero lets speakup speak the punctuation. One lets the
directory has a name of the form "<key>-<vendor guid>"
and contains the following files:
+ =============== ========================================
attributes: A read-only text file enumerating the
EFI variable flags. Potential values
include:
size: As ASCII representation of the size of
the variable's value.
+ =============== ========================================
In addition, two other magic binary files are provided
in the top-level directory and are used for adding and
removing variables:
+ =============== ========================================
new_var: Takes a "struct efi_variable" and
instructs the EFI firmware to create a
new variable.
instructs the EFI firmware to remove any
variable that has a matching vendor GUID
and variable key name.
+ =============== ========================================
This is only for the powerpc/powernv platform.
+ =============== ===============================================
initiate_dump: When '1' is written to it,
we will initiate a dump.
Read this file for supported commands.
and ID of the dump, use the id and type files.
Do not rely on any particular size of dump
type or dump id.
+ =============== ===============================================
Each dump has the following files:
+
+ =============== ===============================================
id: An ASCII representation of the dump ID
in hex (e.g. '0x01')
type: An ASCII representation of the type of
inaccessible.
Reading this file will get a list of
supported actions.
+ =============== ===============================================
For each log entry (directory), there are the following
files:
+ ============== ================================================
id: An ASCII representation of the ID of the
error log, in hex - e.g. "0x01".
entry will be removed from sysfs.
Reading this file will list the supported
operations (currently just acknowledge).
+ ============== ================================================
Space separated list of supported guest system types. Each type
is in the format: <class>-<major>.<minor>-<arch>
With:
+
+ ======== ============================================
<class>: "xen" -- x86: paravirtualized, arm: standard
"hvm" -- x86 only: fully virtualized
<major>: major guest interface version
"x86_64": 64 bit x86 guest
"armv7l": 32 bit arm guest
"aarch64": 64 bit arm guest
+ ======== ============================================
What: /sys/hypervisor/properties/changeset
Date: March 2009
+What: vDSO
+Date: July 2011
+KernelVersion: 3.0
+Contact: Andy Lutomirski <luto@kernel.org>
+Description:
+
On some architectures, when the kernel loads any userspace program it
maps an ELF DSO into that program's address space. This DSO is called
the vDSO and it often contains useful and highly-optimized alternatives
ABI of those symbols is considered stable. It may vary across architectures,
though.
-(As of this writing, this ABI documentation as been confirmed for x86_64.
+Note:
+ As of this writing, this ABI documentation as been confirmed for x86_64.
The maintainers of the other vDSO-using architectures should confirm
- that it is correct for their architecture.)
+ that it is correct for their architecture.
This group contains the configuration for user defined ACPI
tables. The attributes of a user define table are:
- aml - a binary attribute that the user can use to
+ aml
+ - a binary attribute that the user can use to
fill in the ACPI aml definitions. Once the aml
data is written to this file and the file is
closed the table will be loaded and ACPI devices
The rest of the attributes are read-only and are valid only
after the table has been loaded by filling the aml entry:
- signature - ASCII table signature
- length - length of table in bytes, including the header
- revision - ACPI Specification minor version number
- oem_id - ASCII OEM identification
- oem_table_id - ASCII OEM table identification
- oem_revision - OEM revision number
- asl_compiler_id - ASCII ASL compiler vendor ID
- asl_compiler_revision - ASL compiler version
+ signature
+ - ASCII table signature
+
+ length
+ - length of table in bytes, including the header
+
+ revision
+ - ACPI Specification minor version number
+
+ oem_id
+ - ASCII OEM identification
+
+ oem_table_id
+ - ASCII OEM table identification
+
+ oem_revision
+ - OEM revision number
+
+ asl_compiler_id
+ - ASCII ASL compiler vendor ID
+
+ asl_compiler_revision
+ - ASL compiler version
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_video/<link>
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_net/<link>
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_sound/<card>
Description:
The attributes:
- create_card write '1' to this attribute to trigger the
+ create_card
+ write '1' to this attribute to trigger the
registration of the sound card with the ALSA
subsystem.
Description:
The attributes:
- buffer_size configure the buffer size for this channel
+ buffer_size
+ configure the buffer size for this channel
- subbuffer_size configure the sub-buffer size for this channel
+ subbuffer_size
+ configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
- num_buffers configure number of buffers used for this
+ num_buffers
+ configure number of buffers used for this
channel
- datatype configure type of data that will travel over
+ datatype
+ configure type of data that will travel over
this channel
- direction configure whether this link will be an input
+ direction
+ configure whether this link will be an input
or output
- dbr_size configure DBR data buffer size (this is used
+ dbr_size
+ configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
transmitted via USB (this is used for USB
communication only)
- device name of the device the link is to be attached to
+ device
+ name of the device the link is to be attached to
- channel name of the channel the link is to be attached to
+ channel
+ name of the channel the link is to be attached to
- comp_params pass parameters needed by some components
+ comp_params
+ pass parameters needed by some components
- create_link write '1' to this attribute to trigger the
+ create_link
+ write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
- destroy_link write '1' to this attribute to destroy an
+ destroy_link
+ write '1' to this attribute to destroy an
active link
This interfaces can be used to show spear's PCIe device capability.
Nodes are only visible when configfs is mounted. To mount configfs
- in /config directory use:
- # mount -t configfs none /config/
+ in /config directory use::
- For nth PCIe Device Controller
- /config/pcie-gadget.n/
- link ... used to enable ltssm and read its status.
- int_type ...used to configure and read type of supported
- interrupt
- no_of_msi ... used to configure number of MSI vector needed and
+ # mount -t configfs none /config/
+
+ For nth PCIe Device Controller /config/pcie-gadget.n/:
+
+ =============== ======================================================
+ link used to enable ltssm and read its status.
+ int_type used to configure and read type of supported interrupt
+ no_of_msi used to configure number of MSI vector needed and
to read no of MSI granted.
- inta ... write 1 to assert INTA and 0 to de-assert.
- send_msi ... write MSI vector to be sent.
- vendor_id ... used to write and read vendor id (hex)
- device_id ... used to write and read device id (hex)
- bar0_size ... used to write and read bar0_size
- bar0_address ... used to write and read bar0 mapped area in hex.
- bar0_rw_offset ... used to write and read offset of bar0 where
- bar0_data will be written or read.
- bar0_data ... used to write and read data at bar0_rw_offset.
+ inta write 1 to assert INTA and 0 to de-assert.
+ send_msi write MSI vector to be sent.
+ vendor_id used to write and read vendor id (hex)
+ device_id used to write and read device id (hex)
+ bar0_size used to write and read bar0_size
+ bar0_address used to write and read bar0 mapped area in hex.
+ bar0_rw_offset used to write and read offset of bar0 where bar0_data
+ will be written or read.
+ bar0_data used to write and read data at bar0_rw_offset.
+ =============== ======================================================
The attributes of a gadget:
- UDC - bind a gadget to UDC/unbind a gadget;
- write UDC's name found in /sys/class/udc/*
- to bind a gadget, empty string "" to unbind.
-
- max_speed - maximum speed the driver supports. Valid
- names are super-speed-plus, super-speed,
- high-speed, full-speed, and low-speed.
-
- bDeviceClass - USB device class code
- bDeviceSubClass - USB device subclass code
- bDeviceProtocol - USB device protocol code
- bMaxPacketSize0 - maximum endpoint 0 packet size
- bcdDevice - bcd device release number
- bcdUSB - bcd USB specification version number
- idProduct - product ID
- idVendor - vendor ID
+ ================ ============================================
+ UDC bind a gadget to UDC/unbind a gadget;
+ write UDC's name found in /sys/class/udc/*
+ to bind a gadget, empty string "" to unbind.
+
+ max_speed maximum speed the driver supports. Valid
+ names are super-speed-plus, super-speed,
+ high-speed, full-speed, and low-speed.
+
+ bDeviceClass USB device class code
+ bDeviceSubClass USB device subclass code
+ bDeviceProtocol USB device protocol code
+ bMaxPacketSize0 maximum endpoint 0 packet size
+ bcdDevice bcd device release number
+ bcdUSB bcd USB specification version number
+ idProduct product ID
+ idVendor vendor ID
+ ================ ============================================
What: /config/usb-gadget/gadget/configs
Date: Jun 2013
Description:
The attributes of a configuration:
- bmAttributes - configuration characteristics
- MaxPower - maximum power consumption from the bus
+ ================ ======================================
+ bmAttributes configuration characteristics
+ MaxPower maximum power consumption from the bus
+ ================ ======================================
What: /config/usb-gadget/gadget/configs/config/strings
Date: Jun 2013
Description:
The attributes:
- configuration - configuration description
+ ================ =========================
+ configuration configuration description
+ ================ =========================
What: /config/usb-gadget/gadget/functions
The attributes:
- compatible_id - 8-byte string for "Compatible ID"
- sub_compatible_id - 8-byte string for "Sub Compatible ID"
+ ================= =====================================
+ compatible_id 8-byte string for "Compatible ID"
+ sub_compatible_id 8-byte string for "Sub Compatible ID"
+ ================= =====================================
What: /config/usb-gadget/gadget/functions/<func>.<inst>/interface.<n>/<property>
Date: May 2014
The attributes:
- type - value 1..7 for interpreting the data
- 1: unicode string
- 2: unicode string with environment variable
- 3: binary
- 4: little-endian 32-bit
- 5: big-endian 32-bit
- 6: unicode string with a symbolic link
- 7: multiple unicode strings
- data - blob of data to be interpreted depending on
+ ===== ===============================================
+ type value 1..7 for interpreting the data
+
+ - 1: unicode string
+ - 2: unicode string with environment variable
+ - 3: binary
+ - 4: little-endian 32-bit
+ - 5: big-endian 32-bit
+ - 6: unicode string with a symbolic link
+ - 7: multiple unicode strings
+ data blob of data to be interpreted depending on
type
+ ===== ===============================================
What: /config/usb-gadget/gadget/strings
Date: Jun 2013
Description:
The attributes:
- serialnumber - gadget's serial number (string)
- product - gadget's product description
- manufacturer - gadget's manufacturer description
+ ============ =================================
+ serialnumber gadget's serial number (string)
+ product gadget's product description
+ manufacturer gadget's manufacturer description
+ ============ =================================
What: /config/usb-gadget/gadget/os_desc
Date: May 2014
Description:
This group contains "OS String" extension handling attributes.
- use - flag turning "OS Desctiptors" support on/off
- b_vendor_code - one-byte value used for custom per-device and
+ ============= ===============================================
+ use flag turning "OS Desctiptors" support on/off
+ b_vendor_code one-byte value used for custom per-device and
per-interface requests
- qw_sign - an identifier to be reported as "OS String"
+ qw_sign an identifier to be reported as "OS String"
proper
+ ============= ===============================================
Description:
The attributes:
- ifname - network device interface name associated with
+ ifname
+ - network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult
+ - queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr
+ - MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr
+ - MAC address of device's end of this
Ethernet over USB link
Description:
The attributes:
- ifname - network device interface name associated with
+ ========== =============================================
+ ifname network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr MAC address of device's end of this
Ethernet over USB link
+ ========== =============================================
Description:
The attributes:
- protocol - HID protocol to use
- report_desc - blob corresponding to HID report descriptors
+ ============= ============================================
+ protocol HID protocol to use
+ report_desc blob corresponding to HID report descriptors
except the data passed through /dev/hidg<N>
- report_length - HID report length
- subclass - HID device subclass to use
+ report_length HID report length
+ subclass HID device subclass to use
+ ============= ============================================
Description:
The attributes:
- qlen - depth of loopback queue
- buflen - buffer length
+ ======= =======================
+ qlen depth of loopback queue
+ buflen buffer length
+ ======= =======================
Description:
The attributes:
- stall - Set to permit function to halt bulk endpoints.
+ =========== ==============================================
+ stall Set to permit function to halt bulk endpoints.
Disabled on some USB devices known not to work
correctly. You should set it to true.
- num_buffers - Number of pipeline buffers. Valid numbers
+ num_buffers Number of pipeline buffers. Valid numbers
are 2..4. Available only if
CONFIG_USB_GADGET_DEBUG_FILES is set.
+ =========== ==============================================
What: /config/usb-gadget/gadget/functions/mass_storage.name/lun.name
Date: Oct 2013
Description:
The attributes:
- file - The path to the backing file for the LUN.
+ =========== ==============================================
+ file The path to the backing file for the LUN.
Required if LUN is not marked as removable.
- ro - Flag specifying access to the LUN shall be
+ ro Flag specifying access to the LUN shall be
read-only. This is implied if CD-ROM emulation
is enabled as well as when it was impossible
to open "filename" in R/W mode.
- removable - Flag specifying that LUN shall be indicated as
+ removable Flag specifying that LUN shall be indicated as
being removable.
- cdrom - Flag specifying that LUN shall be reported as
+ cdrom Flag specifying that LUN shall be reported as
being a CD-ROM.
- nofua - Flag specifying that FUA flag
+ nofua Flag specifying that FUA flag
in SCSI WRITE(10,12)
+ =========== ==============================================
Description:
The attributes:
- index - index value for the USB MIDI adapter
- id - ID string for the USB MIDI adapter
- buflen - MIDI buffer length
- qlen - USB read request queue length
- in_ports - number of MIDI input ports
- out_ports - number of MIDI output ports
+ ========== ====================================
+ index index value for the USB MIDI adapter
+ id ID string for the USB MIDI adapter
+ buflen MIDI buffer length
+ qlen USB read request queue length
+ in_ports number of MIDI input ports
+ out_ports number of MIDI output ports
+ ========== ====================================
Description:
The attributes:
- pnp_string - Data to be passed to the host in pnp string
- q_len - Number of requests per endpoint
+ ========== ===========================================
+ pnp_string Data to be passed to the host in pnp string
+ q_len Number of requests per endpoint
+ ========== ===========================================
Description:
The attributes:
- ifname - network device interface name associated with
+ ========= =============================================
+ ifname network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr MAC address of device's end of this
Ethernet over USB link
- class - USB interface class, default is 02 (hex)
- subclass - USB interface subclass, default is 06 (hex)
- protocol - USB interface protocol, default is 00 (hex)
+ class USB interface class, default is 02 (hex)
+ subclass USB interface subclass, default is 06 (hex)
+ protocol USB interface protocol, default is 00 (hex)
+ ========= =============================================
Description:
The attributes:
- pattern - 0 (all zeros), 1 (mod63), 2 (none)
- isoc_interval - 1..16
- isoc_maxpacket - 0 - 1023 (fs), 0 - 1024 (hs/ss)
- isoc_mult - 0..2 (hs/ss only)
- isoc_maxburst - 0..15 (ss only)
- buflen - buffer length
- bulk_qlen - depth of queue for bulk
- iso_qlen - depth of queue for iso
+ ============== ==================================
+ pattern 0 (all zeros), 1 (mod63), 2 (none)
+ isoc_interval 1..16
+ isoc_maxpacket 0 - 1023 (fs), 0 - 1024 (hs/ss)
+ isoc_mult 0..2 (hs/ss only)
+ isoc_maxburst 0..15 (ss only)
+ buflen buffer length
+ bulk_qlen depth of queue for bulk
+ iso_qlen depth of queue for iso
+ ============== ==================================
Description:
The attributes:
- ifname - network device interface name associated with
+ ========== =============================================
+ ifname network device interface name associated with
this function instance
- qmult - queue length multiplier for high and
+ qmult queue length multiplier for high and
super speed
- host_addr - MAC address of host's end of this
+ host_addr MAC address of host's end of this
Ethernet over USB link
- dev_addr - MAC address of device's end of this
+ dev_addr MAC address of device's end of this
Ethernet over USB link
+ ========== =============================================
Description:
The attributes:
- c_chmask - capture channel mask
- c_srate - capture sampling rate
- c_ssize - capture sample size (bytes)
- p_chmask - playback channel mask
- p_srate - playback sampling rate
- p_ssize - playback sample size (bytes)
- req_number - the number of pre-allocated request
- for both capture and playback
+ ========== ===================================
+ c_chmask capture channel mask
+ c_srate capture sampling rate
+ c_ssize capture sample size (bytes)
+ p_chmask playback channel mask
+ p_srate playback sampling rate
+ p_ssize playback sample size (bytes)
+ req_number the number of pre-allocated request
+ for both capture and playback
+ ========== ===================================
Description:
The attributes:
- c_chmask - capture channel mask
- c_srate - capture sampling rate
- c_ssize - capture sample size (bytes)
- p_chmask - playback channel mask
- p_srate - playback sampling rate
- p_ssize - playback sample size (bytes)
+ ========= ============================
+ c_chmask capture channel mask
+ c_srate capture sampling rate
+ c_ssize capture sample size (bytes)
+ p_chmask playback channel mask
+ p_srate playback sampling rate
+ p_ssize playback sample size (bytes)
+ ========= ============================
KernelVersion: 4.0
Description: UVC function directory
- streaming_maxburst - 0..15 (ss only)
- streaming_maxpacket - 1..1023 (fs), 1..3072 (hs/ss)
- streaming_interval - 1..16
+ =================== =============================
+ streaming_maxburst 0..15 (ss only)
+ streaming_maxpacket 1..1023 (fs), 1..3072 (hs/ss)
+ streaming_interval 1..16
+ =================== =============================
What: /config/usb-gadget/gadget/functions/uvc.name/control
Date: Dec 2014
Description: Control descriptors
All attributes read only:
- bInterfaceNumber - USB interface number for this
- streaming interface
+
+ ================ =============================
+ bInterfaceNumber USB interface number for this
+ streaming interface
+ ================ =============================
What: /config/usb-gadget/gadget/functions/uvc.name/control/class
Date: Dec 2014
Description: Default output terminal descriptors
All attributes read only:
- iTerminal - index of string descriptor
- bSourceID - id of the terminal to which this terminal
+
+ ============== =============================================
+ iTerminal index of string descriptor
+ bSourceID id of the terminal to which this terminal
is connected
- bAssocTerminal - id of the input terminal to which this output
+ bAssocTerminal id of the input terminal to which this output
terminal is associated
- wTerminalType - terminal type
- bTerminalID - a non-zero id of this terminal
+ wTerminalType terminal type
+ bTerminalID a non-zero id of this terminal
+ ============== =============================================
What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera
Date: Dec 2014
Description: Default camera terminal descriptors
All attributes read only:
- bmControls - bitmap specifying which controls are
- supported for the video stream
- wOcularFocalLength - the value of Locular
- wObjectiveFocalLengthMax- the value of Lmin
- wObjectiveFocalLengthMin- the value of Lmax
- iTerminal - index of string descriptor
- bAssocTerminal - id of the output terminal to which
- this terminal is connected
- wTerminalType - terminal type
- bTerminalID - a non-zero id of this terminal
+
+ ======================== ====================================
+ bmControls bitmap specifying which controls are
+ supported for the video stream
+ wOcularFocalLength the value of Locular
+ wObjectiveFocalLengthMax the value of Lmin
+ wObjectiveFocalLengthMin the value of Lmax
+ iTerminal index of string descriptor
+ bAssocTerminal id of the output terminal to which
+ this terminal is connected
+ wTerminalType terminal type
+ bTerminalID a non-zero id of this terminal
+ ======================== ====================================
What: /config/usb-gadget/gadget/functions/uvc.name/control/processing
Date: Dec 2014
Description: Default processing unit descriptors
All attributes read only:
- iProcessing - index of string descriptor
- bmControls - bitmap specifying which controls are
+
+ =============== ========================================
+ iProcessing index of string descriptor
+ bmControls bitmap specifying which controls are
supported for the video stream
- wMaxMultiplier - maximum digital magnification x100
- bSourceID - id of the terminal to which this unit is
+ wMaxMultiplier maximum digital magnification x100
+ bSourceID id of the terminal to which this unit is
connected
- bUnitID - a non-zero id of this unit
+ bUnitID a non-zero id of this unit
+ =============== ========================================
What: /config/usb-gadget/gadget/functions/uvc.name/control/header
Date: Dec 2014
Description: Streaming descriptors
All attributes read only:
- bInterfaceNumber - USB interface number for this
- streaming interface
+
+ ================ =============================
+ bInterfaceNumber USB interface number for this
+ streaming interface
+ ================ =============================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class
Date: Dec 2014
Description: Default color matching descriptors
All attributes read only:
- bMatrixCoefficients - matrix used to compute luma and
- chroma values from the color primaries
- bTransferCharacteristics- optoelectronic transfer
- characteristic of the source picutre,
- also called the gamma function
- bColorPrimaries - color primaries and the reference
- white
+
+ ======================== ======================================
+ bMatrixCoefficients matrix used to compute luma and
+ chroma values from the color primaries
+ bTransferCharacteristics optoelectronic transfer
+ characteristic of the source picutre,
+ also called the gamma function
+ bColorPrimaries color primaries and the reference
+ white
+ ======================== ======================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg
Date: Dec 2014
All attributes read only,
except bmaControls and bDefaultFrameIndex:
- bFormatIndex - unique id for this format descriptor;
+
+ =================== =====================================
+ bFormatIndex unique id for this format descriptor;
only defined after parent header is
linked into the streaming class;
read-only
- bmaControls - this format's data for bmaControls in
+ bmaControls this format's data for bmaControls in
the streaming header
- bmInterfaceFlags - specifies interlace information,
+ bmInterfaceFlags specifies interlace information,
read-only
- bAspectRatioY - the X dimension of the picture aspect
+ bAspectRatioY the X dimension of the picture aspect
ratio, read-only
- bAspectRatioX - the Y dimension of the picture aspect
+ bAspectRatioX the Y dimension of the picture aspect
ratio, read-only
- bmFlags - characteristics of this format,
+ bmFlags characteristics of this format,
read-only
- bDefaultFrameIndex - optimum frame index for this stream
+ bDefaultFrameIndex optimum frame index for this stream
+ =================== =====================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name/name
Date: Dec 2014
KernelVersion: 4.0
Description: Specific MJPEG frame descriptors
- bFrameIndex - unique id for this framedescriptor;
- only defined after parent format is
- linked into the streaming header;
- read-only
- dwFrameInterval - indicates how frame interval can be
- programmed; a number of values
- separated by newline can be specified
- dwDefaultFrameInterval - the frame interval the device would
- like to use as default
- dwMaxVideoFrameBufferSize- the maximum number of bytes the
- compressor will produce for a video
- frame or still image
- dwMaxBitRate - the maximum bit rate at the shortest
- frame interval in bps
- dwMinBitRate - the minimum bit rate at the longest
- frame interval in bps
- wHeight - height of decoded bitmap frame in px
- wWidth - width of decoded bitmam frame in px
- bmCapabilities - still image support, fixed frame-rate
- support
+ ========================= =====================================
+ bFrameIndex unique id for this framedescriptor;
+ only defined after parent format is
+ linked into the streaming header;
+ read-only
+ dwFrameInterval indicates how frame interval can be
+ programmed; a number of values
+ separated by newline can be specified
+ dwDefaultFrameInterval the frame interval the device would
+ like to use as default
+ dwMaxVideoFrameBufferSize the maximum number of bytes the
+ compressor will produce for a video
+ frame or still image
+ dwMaxBitRate the maximum bit rate at the shortest
+ frame interval in bps
+ dwMinBitRate the minimum bit rate at the longest
+ frame interval in bps
+ wHeight height of decoded bitmap frame in px
+ wWidth width of decoded bitmam frame in px
+ bmCapabilities still image support, fixed frame-rate
+ support
+ ========================= =====================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed
Date: Dec 2014
KernelVersion: 4.0
Description: Specific uncompressed format descriptors
- bFormatIndex - unique id for this format descriptor;
+ ================== =======================================
+ bFormatIndex unique id for this format descriptor;
only defined after parent header is
linked into the streaming class;
read-only
- bmaControls - this format's data for bmaControls in
+ bmaControls this format's data for bmaControls in
the streaming header
- bmInterfaceFlags - specifies interlace information,
+ bmInterfaceFlags specifies interlace information,
read-only
- bAspectRatioY - the X dimension of the picture aspect
+ bAspectRatioY the X dimension of the picture aspect
ratio, read-only
- bAspectRatioX - the Y dimension of the picture aspect
+ bAspectRatioX the Y dimension of the picture aspect
ratio, read-only
- bDefaultFrameIndex - optimum frame index for this stream
- bBitsPerPixel - number of bits per pixel used to
+ bDefaultFrameIndex optimum frame index for this stream
+ bBitsPerPixel number of bits per pixel used to
specify color in the decoded video
frame
- guidFormat - globally unique id used to identify
+ guidFormat globally unique id used to identify
stream-encoding format
+ ================== =======================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name/name
Date: Dec 2014
KernelVersion: 4.0
Description: Specific uncompressed frame descriptors
- bFrameIndex - unique id for this framedescriptor;
- only defined after parent format is
- linked into the streaming header;
- read-only
- dwFrameInterval - indicates how frame interval can be
- programmed; a number of values
- separated by newline can be specified
- dwDefaultFrameInterval - the frame interval the device would
- like to use as default
- dwMaxVideoFrameBufferSize- the maximum number of bytes the
- compressor will produce for a video
- frame or still image
- dwMaxBitRate - the maximum bit rate at the shortest
- frame interval in bps
- dwMinBitRate - the minimum bit rate at the longest
- frame interval in bps
- wHeight - height of decoded bitmap frame in px
- wWidth - width of decoded bitmam frame in px
- bmCapabilities - still image support, fixed frame-rate
- support
+ ========================= =====================================
+ bFrameIndex unique id for this framedescriptor;
+ only defined after parent format is
+ linked into the streaming header;
+ read-only
+ dwFrameInterval indicates how frame interval can be
+ programmed; a number of values
+ separated by newline can be specified
+ dwDefaultFrameInterval the frame interval the device would
+ like to use as default
+ dwMaxVideoFrameBufferSize the maximum number of bytes the
+ compressor will produce for a video
+ frame or still image
+ dwMaxBitRate the maximum bit rate at the shortest
+ frame interval in bps
+ dwMinBitRate the minimum bit rate at the longest
+ frame interval in bps
+ wHeight height of decoded bitmap frame in px
+ wWidth width of decoded bitmam frame in px
+ bmCapabilities still image support, fixed frame-rate
+ support
+ ========================= =====================================
What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header
Date: Dec 2014
Description: Specific streaming header descriptors
All attributes read only:
- bTriggerUsage - how the host software will respond to
+
+ ==================== =====================================
+ bTriggerUsage how the host software will respond to
a hardware trigger interrupt event
- bTriggerSupport - flag specifying if hardware
+ bTriggerSupport flag specifying if hardware
triggering is supported
- bStillCaptureMethod - method of still image caputre
+ bStillCaptureMethod method of still image caputre
supported
- bTerminalLink - id of the output terminal to which
+ bTerminalLink id of the output terminal to which
the video endpoint of this interface
is connected
- bmInfo - capabilities of this video streaming
+ bmInfo capabilities of this video streaming
interface
+ ==================== =====================================
What: /sys/class/udc/udc.name/device/gadget/video4linux/video.name/function_name
Date: May 2018
commands.
Note that the output of 'error-inj' shall be valid as input to 'error-inj'.
-So this must work:
+So this must work::
$ cat error-inj >einj.txt
$ cat einj.txt >error-inj
The user can supply a bitmask value, each bit represents
a different engine to disable/enable its clock gating feature.
The bitmask is composed of 20 bits:
- 0 - 7 : DMA channels
- 8 - 11 : MME engines
- 12 - 19 : TPC engines
+
+ ======= ============
+ 0 - 7 DMA channels
+ 8 - 11 MME engines
+ 12 - 19 TPC engines
+ ======= ============
+
The bit's location of a specific engine can be determined
using (1 << GAUDI_ENGINE_ID_*). GAUDI_ENGINE_ID_* values
are defined in uapi habanalabs.h file in enum gaudi_engine_id
the generic Linux user-space PCI mapping) because the DDR bar
is very small compared to the DDR memory and only the driver can
move the bar before and after the transaction.
+
If the IOMMU is disabled, it also allows the root user to read
or write from the host a device VA of a host mapped memory
the generic Linux user-space PCI mapping) because the DDR bar
is very small compared to the DDR memory and only the driver can
move the bar before and after the transaction.
+
If the IOMMU is disabled, it also allows the root user to read
or write from the host a device VA of a host mapped memory
General information like which GPE is assigned to the EC and whether
the global lock should get used.
Knowing the EC GPE one can watch the amount of HW events related to
-the EC here (XY -> GPE number from /sys/kernel/debug/ec/*/gpe):
+the EC here (XY -> GPE number from `/sys/kernel/debug/ec/*/gpe`):
/sys/firmware/acpi/interrupts/gpeXY
The io file is binary and a userspace tool located here:
should get used to read out the 256 Embedded Controller registers
or writing to them.
-CAUTION: Do not write to the Embedded Controller if you don't know
-what you are doing! Rebooting afterwards also is a good idea.
-This can influence the way your machine is cooled and fans may
-not get switched on again after you did a wrong write.
+CAUTION:
+ Do not write to the Embedded Controller if you don't know
+ what you are doing! Rebooting afterwards also is a good idea.
+ This can influence the way your machine is cooled and fans may
+ not get switched on again after you did a wrong write.
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Read input from the shift registers, in hexadecimal.
+Description: (Read) Read input from the shift registers, in hexadecimal.
Returns N+1 bytes, where N is the number of Moxtet connected
modules. The first byte is from the CPU board itself.
- Example: 101214
- 10: CPU board with SD card
- 12: 2 = PCIe module, 1 = IRQ not active
- 14: 4 = Peridot module, 1 = IRQ not active
+
+ Example::
+
+ 101214
+
+ == =======================================
+ 10 CPU board with SD card
+ 12 2 = PCIe module, 1 = IRQ not active
+ 14 4 = Peridot module, 1 = IRQ not active
+ == =======================================
What: /sys/kernel/debug/moxtet/output
Date: March 2019
Description: (RW) Read last written value to the shift registers, in
hexadecimal, or write values to the shift registers, also
in hexadecimal.
- Example: 0102
- 01: 01 was last written, or is to be written, to the
- first module's shift register
- 02: the same for second module
+
+ Example::
+
+ 0102
+
+ == ================================================
+ 01 01 was last written, or is to be written, to the
+ first module's shift register
+ 02 the same for second module
+ == ================================================
Contact: Kent Yoder <key@linux.vnet.ibm.com>
Description:
- These debugfs interfaces are built by the nx-crypto driver, built in
+These debugfs interfaces are built by the nx-crypto driver, built in
arch/powerpc/crypto/nx.
Error Detection
===============
errors:
-- A u32 providing a total count of errors since the driver was loaded. The
-only errors counted here are those returned from the hcall, H_COP_OP.
+ A u32 providing a total count of errors since the driver was loaded. The
+ only errors counted here are those returned from the hcall, H_COP_OP.
last_error:
-- The most recent non-zero return code from the H_COP_OP hcall. -EBUSY is not
-recorded here (the hcall will retry until -EBUSY goes away).
+ The most recent non-zero return code from the H_COP_OP hcall. -EBUSY is not
+ recorded here (the hcall will retry until -EBUSY goes away).
last_error_pid:
-- The process ID of the process who received the most recent error from the
-hcall.
+ The process ID of the process who received the most recent error from the
+ hcall.
Device Use
==========
aes_bytes:
-- The total number of bytes encrypted using AES in any of the driver's
-supported modes.
+ The total number of bytes encrypted using AES in any of the driver's
+ supported modes.
aes_ops:
-- The total number of AES operations submitted to the hardware.
+ The total number of AES operations submitted to the hardware.
sha256_bytes:
-- The total number of bytes hashed by the hardware using SHA-256.
+ The total number of bytes hashed by the hardware using SHA-256.
sha256_ops:
-- The total number of SHA-256 operations submitted to the hardware.
+ The total number of SHA-256 operations submitted to the hardware.
sha512_bytes:
-- The total number of bytes hashed by the hardware using SHA-512.
+ The total number of bytes hashed by the hardware using SHA-512.
sha512_ops:
-- The total number of SHA-512 operations submitted to the hardware.
+ The total number of SHA-512 operations submitted to the hardware.
Contact: Thomas Maier <balagi@justmail.de>
Description:
-debugfs interface
------------------
-
The pktcdvd module (packet writing driver) creates
these files in debugfs:
/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
- info (0444) Lots of driver statistics and infos.
-Example:
--------
+ ==== ====== ====================================
+ info 0444 Lots of driver statistics and infos.
+ ==== ====== ====================================
+
+Example::
-cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
+ cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
Date: Jun 2020
KernelVersion: 5.8
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (W) Message to sign with the ECDSA private key stored in
- device's OTP. The message must be exactly 64 bytes (since
- this is intended for SHA-512 hashes).
- (R) The resulting signature, 136 bytes. This contains the R and
- S values of the ECDSA signature, both in big-endian format.
+Description:
+
+ ======= ===========================================================
+ (Write) Message to sign with the ECDSA private key stored in
+ device's OTP. The message must be exactly 64 bytes
+ (since this is intended for SHA-512 hashes).
+ (Read) The resulting signature, 136 bytes. This contains the
+ R and S values of the ECDSA signature, both in
+ big-endian format.
+ ======= ===========================================================
for writing, two for the type and at least a single byte of
data.
- Example:
- // Request EC info type 3 (EC firmware build date)
- // Corresponds with sending type 0x00f0 with
- // MBOX = [38, 00, 03, 00]
- $ echo 00 f0 38 00 03 00 > /sys/kernel/debug/wilco_ec/raw
- // View the result. The decoded ASCII result "12/21/18" is
- // included after the raw hex.
- // Corresponds with MBOX = [00, 00, 31, 32, 2f, 32, 31, 38, ...]
- $ cat /sys/kernel/debug/wilco_ec/raw
- 00 00 31 32 2f 32 31 2f 31 38 00 38 00 01 00 2f 00 ..12/21/18.8...
+ Example::
+
+ // Request EC info type 3 (EC firmware build date)
+ // Corresponds with sending type 0x00f0 with
+ // MBOX = [38, 00, 03, 00]
+ $ echo 00 f0 38 00 03 00 > /sys/kernel/debug/wilco_ec/raw
+ // View the result. The decoded ASCII result "12/21/18" is
+ // included after the raw hex.
+ // Corresponds with MBOX = [00, 00, 31, 32, 2f, 32, 31, 38, ...]
+ $ cat /sys/kernel/debug/wilco_ec/raw
+ 00 00 31 32 2f 32 31 2f 31 38 00 38 00 01 00 2f 00 ..12/21/18.8...
Note that the first 16 bytes of the received MBOX[] will be
printed, even if some of the data is junk, and skipping bytes
<uapi/linux/wmi.h>
1) To perform an SMBIOS call from userspace, you'll need to
- first determine the minimum size of the calling interface
- buffer for your machine.
- Platforms that contain larger buffers can return larger
- objects from the system firmware.
- Commonly this size is either 4k or 32k.
+ first determine the minimum size of the calling interface
+ buffer for your machine.
+ Platforms that contain larger buffers can return larger
+ objects from the system firmware.
+ Commonly this size is either 4k or 32k.
- To determine the size of the buffer read() a u64 dword from
- the WMI character device /dev/wmi/dell-smbios.
+ To determine the size of the buffer read() a u64 dword from
+ the WMI character device /dev/wmi/dell-smbios.
2) After you've determined the minimum size of the calling
- interface buffer, you can allocate a structure that represents
- the structure documented above.
+ interface buffer, you can allocate a structure that represents
+ the structure documented above.
3) In the 'length' object store the size of the buffer you
- determined above and allocated.
+ determined above and allocated.
4) In this buffer object, prepare as necessary for the SMBIOS
- call you're interested in. Typically SMBIOS buffers have
- "class", "select", and "input" defined to values that coincide
- with the data you are interested in.
- Documenting class/select/input values is outside of the scope
- of this documentation. Check with the libsmbios project for
- further documentation on these values.
+ call you're interested in. Typically SMBIOS buffers have
+ "class", "select", and "input" defined to values that coincide
+ with the data you are interested in.
+ Documenting class/select/input values is outside of the scope
+ of this documentation. Check with the libsmbios project for
+ further documentation on these values.
6) Run the call by using ioctl() as described in the header.
to the kernel's printk buffer.
Injecting messages:
+
Every write() to the opened device node places a log entry in
the kernel's printk buffer.
the messages can always be reliably determined.
Accessing the buffer:
+
Every read() from the opened device node receives one record
of the kernel's printk buffer.
if needed, without limiting the interface to a single reader.
The device supports seek with the following parameters:
+
SEEK_SET, 0
seek to the first entry in the buffer
SEEK_END, 0
readable context of the message, for reliable processing in
userspace.
- Example:
- 7,160,424069,-;pci_root PNP0A03:00: host bridge window [io 0x0000-0x0cf7] (ignored)
- SUBSYSTEM=acpi
- DEVICE=+acpi:PNP0A03:00
- 6,339,5140900,-;NET: Registered protocol family 10
- 30,340,5690716,-;udevd[80]: starting version 181
+ Example::
+
+ 7,160,424069,-;pci_root PNP0A03:00: host bridge window [io 0x0000-0x0cf7] (ignored)
+ SUBSYSTEM=acpi
+ DEVICE=+acpi:PNP0A03:00
+ 6,339,5140900,-;NET: Registered protocol family 10
+ 30,340,5690716,-;udevd[80]: starting version 181
The DEVICE= key uniquely identifies devices the following way:
- b12:8 - block dev_t
- c127:3 - char dev_t
- n8 - netdev ifindex
- +sound:card0 - subsystem:devname
+
+ ============ =================
+ b12:8 block dev_t
+ c127:3 char dev_t
+ n8 netdev ifindex
+ +sound:card0 subsystem:devname
+ ============ =================
The flags field carries '-' by default. A 'c' indicates a
fragment of a line. Note, that these hints about continuation
echoing a value to <securityfs>/evm made up of the
following bits:
+ === ==================================================
Bit Effect
+ === ==================================================
0 Enable HMAC validation and creation
1 Enable digital signature validation
2 Permit modification of EVM-protected metadata at
runtime. Not supported if HMAC validation and
creation is enabled.
31 Disable further runtime modification of EVM policy
+ === ==================================================
- For example:
+ For example::
- echo 1 ><securityfs>/evm
+ echo 1 ><securityfs>/evm
will enable HMAC validation and creation
- echo 0x80000003 ><securityfs>/evm
+ ::
+
+ echo 0x80000003 ><securityfs>/evm
will enable HMAC and digital signature validation and
HMAC creation and disable all further modification of policy.
- echo 0x80000006 ><securityfs>/evm
+ ::
+
+ echo 0x80000006 ><securityfs>/evm
will enable digital signature validation, permit
modification of EVM-protected metadata and
Shows the set of extended attributes used to calculate or
validate the EVM signature, and allows additional attributes
to be added at runtime. Any signatures generated after
- additional attributes are added (and on files posessing those
+ additional attributes are added (and on files possessing those
additional attributes) will only be valid if the same
additional attributes are configured on system boot. Writing
a single period (.) will lock the xattr list from any further
The following file operations are supported:
open(2)
- Currently the only useful flags are O_RDWR.
+ Currently the only useful flags are O_RDWR.
ioctl(2)
- Initiate various actions.
- See the inline documentation in [include/uapi]<linux/gpio.h>
- for descriptions of all ioctls.
+ Initiate various actions.
+
+ See the inline documentation in [include/uapi]<linux/gpio.h>
+ for descriptions of all ioctls.
close(2)
- Stops and free up the I/O contexts that was associated
- with the file descriptor.
+ Stops and free up the I/O contexts that was associated
+ with the file descriptor.
Users: TBD
IMA appraisal, if configured, uses these file measurements
for local measurement appraisal.
- rule format: action [condition ...]
+ ::
- action: measure | dont_measure | appraise | dont_appraise |
- audit | hash | dont_hash
- condition:= base | lsm [option]
+ rule format: action [condition ...]
+
+ action: measure | dont_measure | appraise | dont_appraise |
+ audit | hash | dont_hash
+ condition:= base | lsm [option]
base: [[func=] [mask=] [fsmagic=] [fsuuid=] [uid=]
[euid=] [fowner=] [fsname=]]
lsm: [[subj_user=] [subj_role=] [subj_type=]
[obj_user=] [obj_role=] [obj_type=]]
option: [[appraise_type=]] [template=] [permit_directio]
[appraise_flag=] [keyrings=]
- base: func:= [BPRM_CHECK][MMAP_CHECK][CREDS_CHECK][FILE_CHECK][MODULE_CHECK]
- [FIRMWARE_CHECK]
+ base:
+ func:= [BPRM_CHECK][MMAP_CHECK][CREDS_CHECK][FILE_CHECK]MODULE_CHECK]
+ [FIRMWARE_CHECK]
[KEXEC_KERNEL_CHECK] [KEXEC_INITRAMFS_CHECK]
[KEXEC_CMDLINE] [KEY_CHECK]
mask:= [[^]MAY_READ] [[^]MAY_WRITE] [[^]MAY_APPEND]
uid:= decimal value
euid:= decimal value
fowner:= decimal value
- lsm: are LSM specific
- option: appraise_type:= [imasig] [imasig|modsig]
+ lsm: are LSM specific
+ option:
+ appraise_type:= [imasig] [imasig|modsig]
appraise_flag:= [check_blacklist]
Currently, blacklist check is only for files signed with appended
signature.
(eg, ima-ng). Only valid when action is "measure".
pcr:= decimal value
- default policy:
+ default policy:
# PROC_SUPER_MAGIC
dont_measure fsmagic=0x9fa0
dont_appraise fsmagic=0x9fa0
Examples of LSM specific definitions:
- SELinux:
+ SELinux::
+
dont_measure obj_type=var_log_t
dont_appraise obj_type=var_log_t
dont_measure obj_type=auditd_log_t
measure subj_user=system_u func=FILE_CHECK mask=MAY_READ
measure subj_role=system_r func=FILE_CHECK mask=MAY_READ
- Smack:
+ Smack::
+
measure subj_user=_ func=FILE_CHECK mask=MAY_READ
- Example of measure rules using alternate PCRs:
+ Example of measure rules using alternate PCRs::
measure func=KEXEC_KERNEL_CHECK pcr=4
measure func=KEXEC_INITRAMFS_CHECK pcr=5
of block devices. Each line contains the following 14
fields:
- 1 - major number
- 2 - minor mumber
- 3 - device name
- 4 - reads completed successfully
- 5 - reads merged
- 6 - sectors read
- 7 - time spent reading (ms)
- 8 - writes completed
- 9 - writes merged
- 10 - sectors written
- 11 - time spent writing (ms)
- 12 - I/Os currently in progress
- 13 - time spent doing I/Os (ms)
- 14 - weighted time spent doing I/Os (ms)
+ == ===================================
+ 1 major number
+ 2 minor mumber
+ 3 device name
+ 4 reads completed successfully
+ 5 reads merged
+ 6 sectors read
+ 7 time spent reading (ms)
+ 8 writes completed
+ 9 writes merged
+ 10 sectors written
+ 11 time spent writing (ms)
+ 12 I/Os currently in progress
+ 13 time spent doing I/Os (ms)
+ 14 weighted time spent doing I/Os (ms)
+ == ===================================
Kernel 4.18+ appends four more fields for discard
tracking putting the total at 18:
- 15 - discards completed successfully
- 16 - discards merged
- 17 - sectors discarded
- 18 - time spent discarding
+ == ===================================
+ 15 discards completed successfully
+ 16 discards merged
+ 17 sectors discarded
+ 18 time spent discarding
+ == ===================================
Kernel 5.5+ appends two more fields for flush requests:
- 19 - flush requests completed successfully
- 20 - time spent flushing
+ == =====================================
+ 19 flush requests completed successfully
+ 20 time spent flushing
+ == =====================================
For more details refer to Documentation/admin-guide/iostats.rst
For more details, see Documentation/filesystems/proc.rst
and the procfs man page.
- Typical output looks like this:
+ Typical output looks like this::
- 00100000-ff709000 ---p 00000000 00:00 0 [rollup]
- Size: 1192 kB
- KernelPageSize: 4 kB
- MMUPageSize: 4 kB
- Rss: 884 kB
- Pss: 385 kB
- Pss_Anon: 301 kB
- Pss_File: 80 kB
- Pss_Shmem: 4 kB
- Shared_Clean: 696 kB
- Shared_Dirty: 0 kB
- Private_Clean: 120 kB
- Private_Dirty: 68 kB
- Referenced: 884 kB
- Anonymous: 68 kB
- LazyFree: 0 kB
- AnonHugePages: 0 kB
- ShmemPmdMapped: 0 kB
- Shared_Hugetlb: 0 kB
- Private_Hugetlb: 0 kB
- Swap: 0 kB
- SwapPss: 0 kB
- Locked: 385 kB
+ 00100000-ff709000 ---p 00000000 00:00 0 [rollup]
+ Size: 1192 kB
+ KernelPageSize: 4 kB
+ MMUPageSize: 4 kB
+ Rss: 884 kB
+ Pss: 385 kB
+ Pss_Anon: 301 kB
+ Pss_File: 80 kB
+ Pss_Shmem: 4 kB
+ Shared_Clean: 696 kB
+ Shared_Dirty: 0 kB
+ Private_Clean: 120 kB
+ Private_Dirty: 68 kB
+ Referenced: 884 kB
+ Anonymous: 68 kB
+ LazyFree: 0 kB
+ AnonHugePages: 0 kB
+ ShmemPmdMapped: 0 kB
+ Shared_Hugetlb: 0 kB
+ Private_Hugetlb: 0 kB
+ Swap: 0 kB
+ SwapPss: 0 kB
+ Locked: 385 kB
provide a generic interface to show records captured in
the dying moments. In the case of a panic the last part
of the console log is captured, but other interesting
- data can also be saved.
+ data can also be saved::
- # mount -t pstore -o kmsg_bytes=8000 - /sys/fs/pstore
+ # mount -t pstore -o kmsg_bytes=8000 - /sys/fs/pstore
- $ ls -l /sys/fs/pstore/
- total 0
- -r--r--r-- 1 root root 7896 Nov 30 15:38 dmesg-erst-1
+ $ ls -l /sys/fs/pstore/
+ total 0
+ -r--r--r-- 1 root root 7896 Nov 30 15:38 dmesg-erst-1
Different users of this interface will result in different
filename prefixes. Currently two are defined:
- "dmesg" - saved console log
- "mce" - architecture dependent data from fatal h/w error
+ - "dmesg" - saved console log
+ - "mce" - architecture dependent data from fatal h/w error
Once the information in a file has been read, removing
the file will signal to the underlying persistent storage
- device that it can reclaim the space for later re-use.
+ device that it can reclaim the space for later re-use::
- $ rm /sys/fs/pstore/dmesg-erst-1
+ $ rm /sys/fs/pstore/dmesg-erst-1
The expectation is that all files in /sys/fs/pstore/
will be saved elsewhere and erased from persistent store
backends are available, the preferred backend may be
set by passing the pstore.backend= argument to the kernel at
boot time.
-
Description:
The /sys/block/<disk>/stat files displays the I/O
statistics of disk <disk>. They contain 11 fields:
- 1 - reads completed successfully
- 2 - reads merged
- 3 - sectors read
- 4 - time spent reading (ms)
- 5 - writes completed
- 6 - writes merged
- 7 - sectors written
- 8 - time spent writing (ms)
- 9 - I/Os currently in progress
- 10 - time spent doing I/Os (ms)
- 11 - weighted time spent doing I/Os (ms)
- 12 - discards completed
- 13 - discards merged
- 14 - sectors discarded
- 15 - time spent discarding (ms)
- 16 - flush requests completed
- 17 - time spent flushing (ms)
+
+ == ==============================================
+ 1 reads completed successfully
+ 2 reads merged
+ 3 sectors read
+ 4 time spent reading (ms)
+ 5 writes completed
+ 6 writes merged
+ 7 sectors written
+ 8 time spent writing (ms)
+ 9 I/Os currently in progress
+ 10 time spent doing I/Os (ms)
+ 11 weighted time spent doing I/Os (ms)
+ 12 discards completed
+ 13 discards merged
+ 14 sectors discarded
+ 15 time spent discarding (ms)
+ 16 flush requests completed
+ 17 time spent flushing (ms)
+ == ==============================================
+
For more details refer Documentation/admin-guide/iostats.rst
It has the following valid values:
+ == ========================================================
0 OFF - the LED is not activated on activity
1 BLINK_ON - the LED blinks on every 10ms when activity is
detected.
2 BLINK_OFF - the LED is on when idle, and blinks off
every 10ms when activity is detected.
+ == ========================================================
Note that the user must turn sw_activity OFF it they wish to
control the activity LED via the em_message file.
is using the device. When "force" is used, the device is also unmapped
when device is in use. All I/Os that are in progress will fail.
- Example:
+ Example::
- # echo "normal" > /sys/block/rnbd0/rnbd/unmap_device
+ # echo "normal" > /sys/block/rnbd0/rnbd/unmap_device
What: /sys/block/rnbd<N>/rnbd/state
Date: Feb 2020
This attribute indicates the full path of ACPI namespace
object associated with the device object. For example,
\_SB_.PCI0.
+
This file is not present for device objects representing
fixed ACPI hardware features (like power and sleep
buttons).
The return value is a decimal integer representing the device's
status bitmap:
- Bit [0] – Set if the device is present.
- Bit [1] – Set if the device is enabled and decoding its
- resources.
- Bit [2] – Set if the device should be shown in the UI.
- Bit [3] – Set if the device is functioning properly (cleared if
- device failed its diagnostics).
- Bit [4] – Set if the battery is present.
- Bits [31:5] – Reserved (must be cleared)
+ =========== ==================================================
+ Bit [0] Set if the device is present.
+ Bit [1] Set if the device is enabled and decoding its
+ resources.
+ Bit [2] Set if the device should be shown in the UI.
+ Bit [3] Set if the device is functioning properly (cleared
+ if device failed its diagnostics).
+ Bit [4] Set if the battery is present.
+ Bits [31:5] Reserved (must be cleared)
+ =========== ==================================================
If bit [0] is clear, then bit 1 must also be clear (a device
that is not present cannot be enabled).
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Indicate if the CTI hardware is powered.
+Description: (Read) Indicate if the CTI hardware is powered.
What: /sys/bus/coresight/devices/<cti-name>/ctmid
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Display the associated CTM ID
+Description: (Read) Display the associated CTM ID
What: /sys/bus/coresight/devices/<cti-name>/nr_trigger_cons
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Number of devices connected to triggers on this CTI
+Description: (Read) Number of devices connected to triggers on this CTI
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/name
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Name of connected device <N>
+Description: (Read) Name of connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/in_signals
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Input trigger signals from connected device <N>
+Description: (Read) Input trigger signals from connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/in_types
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Functional types for the input trigger signals
+Description: (Read) Functional types for the input trigger signals
from connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/out_signals
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Output trigger signals to connected device <N>
+Description: (Read) Output trigger signals to connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/out_types
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Functional types for the output trigger signals
+Description: (Read) Functional types for the output trigger signals
to connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/regs/inout_sel
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Write the INTACK register.
+Description: (Write) Write the INTACK register.
What: /sys/bus/coresight/devices/<cti-name>/regs/appset
Date: March 2020
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Write APPCLEAR register to deactivate channel.
+Description: (Write) Write APPCLEAR register to deactivate channel.
What: /sys/bus/coresight/devices/<cti-name>/regs/apppulse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Write APPPULSE to pulse a channel active for one clock
+Description: (Write) Write APPPULSE to pulse a channel active for one clock
cycle.
What: /sys/bus/coresight/devices/<cti-name>/regs/chinstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Read current status of channel inputs.
+Description: (Read) Read current status of channel inputs.
What: /sys/bus/coresight/devices/<cti-name>/regs/choutstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) read current status of channel outputs.
+Description: (Read) read current status of channel outputs.
What: /sys/bus/coresight/devices/<cti-name>/regs/triginstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) read current status of input trigger signals
+Description: (Read) read current status of input trigger signals
What: /sys/bus/coresight/devices/<cti-name>/regs/trigoutstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) read current status of output trigger signals.
+Description: (Read) read current status of output trigger signals.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigin_attach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Attach a CTI input trigger to a CTM channel.
+Description: (Write) Attach a CTI input trigger to a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigin_detach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Detach a CTI input trigger from a CTM channel.
+Description: (Write) Detach a CTI input trigger from a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_attach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Attach a CTI output trigger to a CTM channel.
+Description: (Write) Attach a CTI output trigger to a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_detach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Detach a CTI output trigger from a CTM channel.
+Description: (Write) Detach a CTI output trigger from a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_gate_enable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (RW) Enable CTIGATE for single channel (W) or list enabled
+Description: (RW) Enable CTIGATE for single channel (Write) or list enabled
channels through the gate (R).
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_gate_disable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Disable CTIGATE for single channel.
+Description: (Write) Disable CTIGATE for single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_set
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Activate a single channel.
+Description: (Write) Activate a single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_clear
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Deactivate a single channel.
+Description: (Write) Deactivate a single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_pulse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Pulse a single channel - activate for a single clock cycle.
+Description: (Write) Pulse a single channel - activate for a single clock cycle.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_filtered
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) List of output triggers filtered across all connections.
+Description: (Read) List of output triggers filtered across all connections.
What: /sys/bus/coresight/devices/<cti-name>/channels/trig_filter_enable
Date: March 2020
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) show channels with at least one attached trigger signal.
+Description: (Read) show channels with at least one attached trigger signal.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_free
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) show channels with no attached trigger signals.
+Description: (Read) show channels with no attached trigger signals.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_sel
Date: March 2020
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Read to see input triggers connected to selected view
+Description: (Read) Read to see input triggers connected to selected view
channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_out
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (R) Read to see output triggers connected to selected view
+Description: (Read) Read to see output triggers connected to selected view
channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_reset
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
-Description: (W) Clear all channel / trigger programming.
+Description: (Write) Clear all channel / trigger programming.
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
Description: (RW) Add/remove a sink from a trace path. There can be multiple
source for a single sink.
- ex: echo 1 > /sys/bus/coresight/devices/20010000.etb/enable_sink
+
+ ex::
+
+ echo 1 > /sys/bus/coresight/devices/20010000.etb/enable_sink
What: /sys/bus/coresight/devices/<memory_map>.etb/trigger_cntr
Date: November 2014
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Defines the depth, in words, of the trace RAM in powers of
+Description: (Read) Defines the depth, in words, of the trace RAM in powers of
2. The value is read directly from HW register RDP, 0x004.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/sts
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB status register. The value
+Description: (Read) Shows the value held by the ETB status register. The value
is read directly from HW register STS, 0x00C.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/rrp
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB RAM Read Pointer register
+Description: (Read) Shows the value held by the ETB RAM Read Pointer register
that is used to read entries from the Trace RAM over the APB
interface. The value is read directly from HW register RRP,
0x014.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB RAM Write Pointer register
+Description: (Read) Shows the value held by the ETB RAM Write Pointer register
that is used to sets the write pointer to write entries from
the CoreSight bus into the Trace RAM. The value is read directly
from HW register RWP, 0x018.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Similar to "trigger_cntr" above except that this value is
+Description: (Read) Similar to "trigger_cntr" above except that this value is
read directly from HW register TRG, 0x01C.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/ctl
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB Control register. The value
+Description: (Read) Shows the value held by the ETB Control register. The value
is read directly from HW register CTL, 0x020.
What: /sys/bus/coresight/devices/<memory_map>.etb/mgmt/ffsr
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB Formatter and Flush Status
+Description: (Read) Shows the value held by the ETB Formatter and Flush Status
register. The value is read directly from HW register FFSR,
0x300.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the ETB Formatter and Flush Control
+Description: (Read) Shows the value held by the ETB Formatter and Flush Control
register. The value is read directly from HW register FFCR,
0x304.
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Provides the number of address comparators pairs accessible
+Description: (Read) Provides the number of address comparators pairs accessible
on a trace unit, as specified by bit 3:0 of register ETMCCR.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/nr_cntr
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Provides the number of counters accessible on a trace unit,
+Description: (Read) Provides the number of counters accessible on a trace unit,
as specified by bit 15:13 of register ETMCCR.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/nr_ctxid_cmp
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Provides the number of context ID comparator available on a
+Description: (Read) Provides the number of context ID comparator available on a
trace unit, as specified by bit 25:24 of register ETMCCR.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/reset
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (W) Cancels all configuration on a trace unit and set it back
+Description: (Write) Cancels all configuration on a trace unit and set it back
to its boot configuration.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/seq_12_event
Date: November 2014
KernelVersion: 3.19
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Holds the current state of the sequencer.
+Description: (Read) Holds the current state of the sequencer.
What: /sys/bus/coresight/devices/<memory_map>.[etm|ptm]/sync_freq
Date: November 2014
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) The CPU this tracing entity is associated with.
+Description: (Read) The CPU this tracing entity is associated with.
What: /sys/bus/coresight/devices/etm<N>/nr_pe_cmp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of PE comparator inputs that are
+Description: (Read) Indicates the number of PE comparator inputs that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_addr_cmp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of address comparator pairs that are
+Description: (Read) Indicates the number of address comparator pairs that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_cntr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of counters that are available for
+Description: (Read) Indicates the number of counters that are available for
tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_ext_inp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates how many external inputs are implemented.
+Description: (Read) Indicates how many external inputs are implemented.
What: /sys/bus/coresight/devices/etm<N>/numcidc
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of Context ID comparators that are
+Description: (Read) Indicates the number of Context ID comparators that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/numvmidc
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of VMID comparators that are available
+Description: (Read) Indicates the number of VMID comparators that are available
for tracing.
What: /sys/bus/coresight/devices/etm<N>/nrseqstate
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of sequencer states that are
+Description: (Read) Indicates the number of sequencer states that are
implemented.
What: /sys/bus/coresight/devices/etm<N>/nr_resource
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of resource selection pairs that are
+Description: (Read) Indicates the number of resource selection pairs that are
available for tracing.
What: /sys/bus/coresight/devices/etm<N>/nr_ss_cmp
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the number of single-shot comparator controls that
+Description: (Read) Indicates the number of single-shot comparator controls that
are available for tracing.
What: /sys/bus/coresight/devices/etm<N>/reset
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (W) Cancels all configuration on a trace unit and set it back
+Description: (Write) Cancels all configuration on a trace unit and set it back
to its boot configuration.
What: /sys/bus/coresight/devices/etm<N>/mode
Date: December 2019
KernelVersion: 5.5
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the current settings for the selected address
+Description: (Read) Print the current settings for the selected address
comparator.
What: /sys/bus/coresight/devices/etm<N>/sshot_idx
Date: December 2019
KernelVersion: 5.5
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the current value of the selected single shot
+Description: (Read) Print the current value of the selected single shot
status register.
What: /sys/bus/coresight/devices/etm<N>/sshot_pe_ctrl
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the OS Lock Status Register (0x304).
+Description: (Read) Print the content of the OS Lock Status Register (0x304).
The value it taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpdcr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Power Down Control Register
+Description: (Read) Print the content of the Power Down Control Register
(0x310). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpdsr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Power Down Status Register
+Description: (Read) Print the content of the Power Down Status Register
(0x314). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trclsr
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the SW Lock Status Register
+Description: (Read) Print the content of the SW Lock Status Register
(0xFB4). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcauthstatus
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Authentication Status Register
+Description: (Read) Print the content of the Authentication Status Register
(0xFB8). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcdevid
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Device ID Register
+Description: (Read) Print the content of the Device ID Register
(0xFC8). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcdevtype
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Device Type Register
+Description: (Read) Print the content of the Device Type Register
(0xFCC). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr0
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID0 Register
+Description: (Read) Print the content of the Peripheral ID0 Register
(0xFE0). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr1
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID1 Register
+Description: (Read) Print the content of the Peripheral ID1 Register
(0xFE4). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr2
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID2 Register
+Description: (Read) Print the content of the Peripheral ID2 Register
(0xFE8). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcpidr3
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the Peripheral ID3 Register
+Description: (Read) Print the content of the Peripheral ID3 Register
(0xFEC). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trcconfig
Date: February 2016
KernelVersion: 4.07
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the trace configuration register
+Description: (Read) Print the content of the trace configuration register
(0x010) as currently set by SW.
What: /sys/bus/coresight/devices/etm<N>/mgmt/trctraceid
Date: February 2016
KernelVersion: 4.07
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Print the content of the trace ID register (0x040).
+Description: (Read) Print the content of the trace ID register (0x040).
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr0
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the tracing capabilities of the trace unit (0x1E0).
+Description: (Read) Returns the tracing capabilities of the trace unit (0x1E0).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr1
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the tracing capabilities of the trace unit (0x1E4).
+Description: (Read) Returns the tracing capabilities of the trace unit (0x1E4).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr2
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the maximum size of the data value, data address,
+Description: (Read) Returns the maximum size of the data value, data address,
VMID, context ID and instuction address in the trace unit
(0x1E8). The value is taken directly from the HW.
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the value associated with various resources
+Description: (Read) Returns the value associated with various resources
available to the trace unit. See the Trace Macrocell
architecture specification for more details (0x1E8).
The value is taken directly from the HW.
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns how many resources the trace unit supports (0x1F0).
+Description: (Read) Returns how many resources the trace unit supports (0x1F0).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr5
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns how many resources the trace unit supports (0x1F4).
+Description: (Read) Returns how many resources the trace unit supports (0x1F4).
The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr8
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the maximum speculation depth of the instruction
+Description: (Read) Returns the maximum speculation depth of the instruction
trace stream. (0x180). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr9
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of P0 right-hand keys that the trace unit
+Description: (Read) Returns the number of P0 right-hand keys that the trace unit
can use (0x184). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr10
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of P1 right-hand keys that the trace unit
+Description: (Read) Returns the number of P1 right-hand keys that the trace unit
can use (0x188). The value is taken directly from the HW.
What: /sys/bus/coresight/devices/etm<N>/trcidr/trcidr11
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of special P1 right-hand keys that the
+Description: (Read) Returns the number of special P1 right-hand keys that the
trace unit can use (0x18C). The value is taken directly from
the HW.
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of conditional P1 right-hand keys that
+Description: (Read) Returns the number of conditional P1 right-hand keys that
the trace unit can use (0x190). The value is taken directly
from the HW.
Date: April 2015
KernelVersion: 4.01
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Returns the number of special conditional P1 right-hand keys
+Description: (Read) Returns the number of special conditional P1 right-hand keys
that the trace unit can use (0x194). The value is taken
directly from the HW.
Date: April 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) List various control and status registers. The specific
+Description: (Read) List various control and status registers. The specific
layout and content is driver specific.
What: /sys/bus/coresight/devices/<memory_map>.stm/traceid
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Defines the size, in 32-bit words, of the local RAM buffer.
+Description: (Read) Defines the size, in 32-bit words, of the local RAM buffer.
The value is read directly from HW register RSZ, 0x004.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/sts
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC status register. The value
+Description: (Read) Shows the value held by the TMC status register. The value
is read directly from HW register STS, 0x00C.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/rrp
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC RAM Read Pointer register
+Description: (Read) Shows the value held by the TMC RAM Read Pointer register
that is used to read entries from the Trace RAM over the APB
interface. The value is read directly from HW register RRP,
0x014.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC RAM Write Pointer register
+Description: (Read) Shows the value held by the TMC RAM Write Pointer register
that is used to sets the write pointer to write entries from
the CoreSight bus into the Trace RAM. The value is read directly
from HW register RWP, 0x018.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Similar to "trigger_cntr" above except that this value is
+Description: (Read) Similar to "trigger_cntr" above except that this value is
read directly from HW register TRG, 0x01C.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ctl
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Control register. The value
+Description: (Read) Shows the value held by the TMC Control register. The value
is read directly from HW register CTL, 0x020.
What: /sys/bus/coresight/devices/<memory_map>.tmc/mgmt/ffsr
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Formatter and Flush Status
+Description: (Read) Shows the value held by the TMC Formatter and Flush Status
register. The value is read directly from HW register FFSR,
0x300.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Formatter and Flush Control
+Description: (Read) Shows the value held by the TMC Formatter and Flush Control
register. The value is read directly from HW register FFCR,
0x304.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Shows the value held by the TMC Mode register, which
+Description: (Read) Shows the value held by the TMC Mode register, which
indicate the mode the device has been configured to enact. The
The value is read directly from the MODE register, 0x028.
Date: March 2016
KernelVersion: 4.7
Contact: Mathieu Poirier <mathieu.poirier@linaro.org>
-Description: (R) Indicates the capabilities of the Coresight TMC.
+Description: (Read) Indicates the capabilities of the Coresight TMC.
The value is read directly from the DEVID register, 0xFC8,
What: /sys/bus/coresight/devices/<memory_map>.tmc/buffer_size
Description: Contains the ids of the channel paths used by this
subchannel, as reported by the channel subsystem
during subchannel recognition.
+
Note: This is an I/O-subchannel specific attribute.
Users: s390-tools, HAL
channel subsystem when last queried by the common I/O
layer (this implies that this attribute is not necessarily
in sync with the values current in the channel subsystem).
+
Note: This is an I/O-subchannel specific attribute.
Users: s390-tools, HAL
opt-out of driver binding using a driver_override name such as
"none". Only a single driver may be specified in the override,
there is no support for parsing delimiters.
+
Note that unlike the mechanism of the same name for pci, this
file does not allow to override basic matching rules. I.e.,
the driver must still match the subchannel type of the device.
Contact: Xu Yilun <yilun.xu@intel.com>
Description: Read-only. It returns type of DFL FIU of the device. Now DFL
supports 2 FIU types, 0 for FME, 1 for PORT.
+
Format: 0x%x
What: /sys/bus/dfl/devices/dfl_dev.X/feature_id
Contact: Xu Yilun <yilun.xu@intel.com>
Description: Read-only. It returns feature identifier local to its DFL FIU
type.
+
Format: 0x%x
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
- below.
+ below::
event = "config:0-11" - event ID
evtype = "config:12-15" - event type
portid = "config:16-23" - event source
- For example,
+ For example::
fab_mmio_read = "event=0x06,evtype=0x02,portid=0xff"
All supported performance monitoring events are listed below.
- Basic events (evtype=0x00)
+ Basic events (evtype=0x00)::
clock = "event=0x00,evtype=0x00,portid=0xff"
- Cache events (evtype=0x01)
+ Cache events (evtype=0x01)::
cache_read_hit = "event=0x00,evtype=0x01,portid=0xff"
cache_read_miss = "event=0x01,evtype=0x01,portid=0xff"
cache_rx_req_stall = "event=0x09,evtype=0x01,portid=0xff"
cache_eviction = "event=0x0a,evtype=0x01,portid=0xff"
- Fabric events (evtype=0x02)
+ Fabric events (evtype=0x02)::
fab_pcie0_read = "event=0x00,evtype=0x02,portid=0xff"
fab_pcie0_write = "event=0x01,evtype=0x02,portid=0xff"
fab_port_mmio_read = "event=0x06,evtype=0x02,portid=?"
fab_port_mmio_write = "event=0x07,evtype=0x02,portid=?"
- VTD events (evtype=0x03)
+ VTD events (evtype=0x03)::
vtd_port_read_transaction = "event=0x00,evtype=0x03,portid=?"
vtd_port_write_transaction = "event=0x01,evtype=0x03,portid=?"
vtd_port_devtlb_2m_fill = "event=0x05,evtype=0x03,portid=?"
vtd_port_devtlb_1g_fill = "event=0x06,evtype=0x03,portid=?"
- VTD SIP events (evtype=0x04)
+ VTD SIP events (evtype=0x04)::
vtd_sip_iotlb_4k_hit = "event=0x00,evtype=0x04,portid=0xff"
vtd_sip_iotlb_2m_hit = "event=0x01,evtype=0x04,portid=0xff"
name/value pairs.
Userspace must be prepared for the possibility that attributes
- define overlapping bit ranges. For example:
+ define overlapping bit ranges. For example::
+
attr1 = 'config:0-23'
attr2 = 'config:0-7'
attr3 = 'config:12-35'
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
- below.
+ below::
chip = "config:16-31"
core = "config:16-31"
offset = "config:32-63"
vcpu = "config:16-31"
- For example,
+ For example::
- PM_PB_CYC = "domain=1,offset=0x80,chip=?,lpar=0x0"
+ PM_PB_CYC = "domain=1,offset=0x80,chip=?,lpar=0x0"
In this event, '?' after chip specifies that
this value will be provided by user while running this event.
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
- below.
+ below::
counter_info_version = "config:16-23"
length = "config:24-31"
secondary_index = "config:0-15"
starting_index = "config:32-63"
- For example,
+ For example::
- processor_core_utilization_instructions_completed = "request=0x94,
+ processor_core_utilization_instructions_completed = "request=0x94,
phys_processor_idx=?,counter_info_version=0x8,
length=8,offset=0x18"
'0' if the hypervisor is configured to forbid access to event
counters being accumulated by other guests and to physical
domain event counters.
+
'1' if that access is allowed.
What: /sys/bus/event_source/devices/hv_gpci/interface/ga
KernelVersion: TBD
Contact: Robert Love <robert.w.love@intel.com>, devel@open-fcoe.org
Description: The FCoE bus. Attributes in this directory are control interfaces.
+
Attributes:
- ctlr_create: 'FCoE Controller' instance creation interface. Writing an
+ ctlr_create:
+ 'FCoE Controller' instance creation interface. Writing an
<ifname> to this file will allocate and populate sysfs with a
fcoe_ctlr_device (ctlr_X). The user can then configure any
per-port settings and finally write to the fcoe_ctlr_device's
'start' attribute to begin the kernel's discovery and login
process.
- ctlr_destroy: 'FCoE Controller' instance removal interface. Writing a
+ ctlr_destroy:
+ 'FCoE Controller' instance removal interface. Writing a
fcoe_ctlr_device's sysfs name to this file will log the
fcoe_ctlr_device out of the fabric or otherwise connected
FCoE devices. It will also free all kernel memory allocated
Attributes:
- fcf_dev_loss_tmo: Device loss timeout period (see below). Changing
+ fcf_dev_loss_tmo:
+ Device loss timeout period (see below). Changing
this value will change the dev_loss_tmo for all
FCFs discovered by this controller.
- mode: Display or change the FCoE Controller's mode. Possible
+ mode:
+ Display or change the FCoE Controller's mode. Possible
modes are 'Fabric' and 'VN2VN'. If a FCoE Controller
is started in 'Fabric' mode then FIP FCF discovery is
initiated and ultimately a fabric login is attempted.
FIP VN2VN discovery and login is performed. A FCoE
Controller only supports one mode at a time.
- enabled: Whether an FCoE controller is enabled or disabled.
+ enabled:
+ Whether an FCoE controller is enabled or disabled.
0 if disabled, 1 if enabled. Writing either 0 or 1
to this file will enable or disable the FCoE controller.
- lesb/link_fail: Link Error Status Block (LESB) link failure count.
+ lesb/link_fail:
+ Link Error Status Block (LESB) link failure count.
- lesb/vlink_fail: Link Error Status Block (LESB) virtual link
+ lesb/vlink_fail:
+ Link Error Status Block (LESB) virtual link
failure count.
- lesb/miss_fka: Link Error Status Block (LESB) missed FCoE
+ lesb/miss_fka:
+ Link Error Status Block (LESB) missed FCoE
Initialization Protocol (FIP) Keep-Alives (FKA).
- lesb/symb_err: Link Error Status Block (LESB) symbolic error count.
+ lesb/symb_err:
+ Link Error Status Block (LESB) symbolic error count.
- lesb/err_block: Link Error Status Block (LESB) block error count.
+ lesb/err_block:
+ Link Error Status Block (LESB) block error count.
- lesb/fcs_error: Link Error Status Block (LESB) Fibre Channel
+ lesb/fcs_error:
+ Link Error Status Block (LESB) Fibre Channel
Services error count.
Notes: ctlr_X (global increment starting at 0)
Fibre Channel frames into a FC fabric. It can also take
outbound FC frames and pack them in Ethernet packets to
be sent to their destination on the Ethernet segment.
+
Attributes:
- fabric_name: Identifies the fabric that the FCF services.
+ fabric_name:
+ Identifies the fabric that the FCF services.
- switch_name: Identifies the FCF.
+ switch_name:
+ Identifies the FCF.
- priority: The switch's priority amongst other FCFs on the same
+ priority:
+ The switch's priority amongst other FCFs on the same
fabric.
- selected: 1 indicates that the switch has been selected for use;
+ selected:
+ 1 indicates that the switch has been selected for use;
0 indicates that the switch will not be used.
- fc_map: The Fibre Channel MAP
+ fc_map:
+ The Fibre Channel MAP
- vfid: The Virtual Fabric ID
+ vfid:
+ The Virtual Fabric ID
- mac: The FCF's MAC address
+ mac:
+ The FCF's MAC address
- fka_period: The FIP Keep-Alive period
+ fka_period:
+ The FIP Keep-Alive period
fabric_state: The internal kernel state
- "Unknown" - Initialization value
- "Disconnected" - No link to the FCF/fabric
- "Connected" - Host is connected to the FCF
- "Deleted" - FCF is being removed from the system
+
+ - "Unknown" - Initialization value
+ - "Disconnected" - No link to the FCF/fabric
+ - "Connected" - Host is connected to the FCF
+ - "Deleted" - FCF is being removed from the system
dev_loss_tmo: The device loss timeout period for this FCF.
the driver to attempt to bind to the device found at
this location. The format for the location is Object.Id
and is the same as found in /sys/bus/fsl-mc/devices/.
- For example:
- # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/bind
+
+ For example::
+
+ # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/bind
What: /sys/bus/fsl-mc/drivers/.../unbind
Date: December 2016
driver to attempt to unbind from the device found at
this location. The format for the location is Object.Id
and is the same as found in /sys/bus/fsl-mc/devices/.
- For example:
- # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/unbind
+
+ For example::
+
+ # echo dpni.2 > /sys/bus/fsl-mc/drivers/fsl_dpaa2_eth/unbind
Contact: Minkyu Kang <mk7.kang@samsung.com>
Description:
show what device is attached
- NONE - no device
- USB - USB device is attached
- UART - UART is attached
- CHARGER - Charger is attaced
- JIG - JIG is attached
+
+ ======= ======================
+ NONE no device
+ USB USB device is attached
+ UART UART is attached
+ CHARGER Charger is attaced
+ JIG JIG is attached
+ ======= ======================
What: /sys/bus/i2c/devices/.../switch
Date: February 2011
Contact: Minkyu Kang <mk7.kang@samsung.com>
Description:
show or set the state of manual switch
- VAUDIO - switch to VAUDIO path
- UART - switch to UART path
- AUDIO - switch to AUDIO path
- DHOST - switch to DHOST path
- AUTO - switch automatically by device
+
+ ======= ==============================
+ VAUDIO switch to VAUDIO path
+ UART switch to UART path
+ AUDIO switch to AUDIO path
+ DHOST switch to DHOST path
+ AUTO switch automatically by device
+ ======= ==============================
Value that exists only for mux devices that can be
written to control the behaviour of the multiplexer on
idle. Possible values:
- -2 - disconnect on idle, i.e. deselect the last used
- channel, which is useful when there is a device
- with an address that conflicts with another
- device on another mux on the same parent bus.
- -1 - leave the mux as-is, which is the most optimal
- setting in terms of I2C operations and is the
- default mode.
- 0..<nchans> - set the mux to a predetermined channel,
- which is useful if there is one channel that is
- used almost always, and you want to reduce the
- latency for normal operations after rare
- transactions on other channels
+
+ =========== ===============================================
+ -2 disconnect on idle, i.e. deselect the last used
+ channel, which is useful when there is a device
+ with an address that conflicts with another
+ device on another mux on the same parent bus.
+ -1 leave the mux as-is, which is the most optimal
+ setting in terms of I2C operations and is the
+ default mode.
+ 0..<nchans> set the mux to a predetermined channel,
+ which is useful if there is one channel that is
+ used almost always, and you want to reduce the
+ latency for normal operations after rare
+ transactions on other channels
+ =========== ===============================================
by space. Modes can be "hdr-ddr", "hdr-tsp" and "hdr-tsl".
See the I3C specification for more details about these HDR
modes.
+
This entry describes the HDRCAP of the master controller
driving the bus.
Expose the HDR (High Data Rate) capabilities of a device.
Returns a list of supported HDR mode, each element is separated
by space. Modes can be "hdr-ddr", "hdr-tsp" and "hdr-tsl".
+
See the I3C specification for more details about these HDR
modes.
based on hardware generated events (e.g. data ready) or
provided by a separate driver for other hardware (e.g.
periodic timer, GPIO or high resolution timer).
+
Contains trigger type specific elements. These do not
generalize well and hence are not documented in this file.
X is the IIO index of the trigger.
Description:
When the internal sampling clock can only take a specific set of
frequencies, we can specify the available values with:
+
- a small discrete set of values like "0 2 4 6 8"
- a range with minimum, step and maximum frequencies like
"[min step max]"
<type>[Y][_name]_<raw|input>_thresh_falling_value may take
different values, but the device can only enable both thresholds
or neither.
+
Note the driver will assume the last p events requested are
to be enabled where p is how many it supports (which may vary
depending on the exact set requested. So if you want to be
<type>[Y][_name]_<raw|input>_roc_falling_value may take
different values, but the device can only enable both rate of
change thresholds or neither.
+
Note the driver will assume the last p events requested are
to be enabled where p is however many it supports (which may
vary depending on the exact set requested. So if you want to be
Specifies the value of threshold that the device is comparing
against for the events enabled by
<type>Y[_name]_thresh[_rising|falling]_en.
+
If separate attributes exist for the two directions, but
direction is not specified for this attribute, then a single
threshold value applies to both directions.
+
The raw or input element of the name indicates whether the
value is in raw device units or in processed units (as _raw
and _input do on sysfs direct channel read attributes).
If separate attributes exist for the two directions, but
direction is not specified for this attribute, then a single
hysteresis value applies to both directions.
+
For falling events the hysteresis is added to the _value attribute for
this event to get the upper threshold for when the event goes back to
normal, for rising events the hysteresis is subtracted from the _value
Specifies the value of rate of change threshold that the
device is comparing against for the events enabled by
<type>[Y][_name]_roc[_rising|falling]_en.
+
If separate attributes exist for the two directions,
but direction is not specified for this attribute,
then a single threshold value applies to both directions.
Proximity measurement indicating that some
object is near the sensor, usually by observing
reflectivity of infrared or ultrasound emitted.
+
Often these sensors are unit less and as such conversion
to SI units is not possible. Higher proximity measurements
indicate closer objects, and vice versa. Units after
Description:
A single positive integer specifying the maximum number of scan
elements to wait for.
+
Poll will block until the watermark is reached.
+
Blocking read will wait until the minimum between the requested
read amount or the low water mark is available.
+
Non-blocking read will retrieve the available samples from the
buffer even if there are less samples then watermark level. This
allows the application to block on poll with a timeout and read
device settings allows it (e.g. if a trigger is set that samples
data differently that the hardware fifo does then hardware fifo
will not enabled).
+
If the hardware fifo is enabled and the level of the hardware
fifo reaches the hardware fifo watermark level the device will
flush its hardware fifo to the device buffer. Doing a non
blocking read on the device when no samples are present in the
device buffer will also force a flush.
+
When the hardware fifo is enabled there is no need to use a
trigger to use buffer mode since the watermark settings
guarantees that the hardware fifo is flushed to the device
A single positive integer specifying the minimum watermark level
for the hardware fifo of this device. If the device does not
have a hardware fifo this entry is not present.
+
If the user sets buffer/watermark to a value less than this one,
then the hardware watermark will remain unset.
A single positive integer specifying the maximum watermark level
for the hardware fifo of this device. If the device does not
have a hardware fifo this entry is not present.
+
If the user sets buffer/watermark to a value greater than this
one, then the hardware watermark will be capped at this value.
levels for the hardware fifo. This entry is optional and if it
is not present it means that all the values between
hwfifo_watermark_min and hwfifo_watermark_max are supported.
+
If the user sets buffer/watermark to a value greater than
hwfifo_watermak_min but not equal to any of the values in this
list, the driver will chose an appropriate value for the
Contact: linux-iio@vger.kernel.org
Description:
'1' (enable) or '0' (disable) specifying the enable
- of heater function. Same reading values apply
+ of heater function. Same reading values apply.
+
This ABI is especially applicable for humidity sensors
to heatup the device and get rid of any condensation
in some humidity environment
Mounting matrix for IIO sensors. This is a rotation matrix which
informs userspace about sensor chip's placement relative to the
main hardware it is mounted on.
+
Main hardware placement is defined according to the local
reference frame related to the physical quantity the sensor
measures.
+
Given that the rotation matrix is defined in a board specific
way (platform data and / or device-tree), the main hardware
reference frame definition is left to the implementor's choice
(see below for a magnetometer example).
+
Applications should apply this rotation matrix to samples so
that when main hardware reference frame is aligned onto local
reference frame, then sensor chip reference frame is also
perfectly aligned with it.
+
Matrix is a 3x3 unitary matrix and typically looks like
[0, 1, 0; 1, 0, 0; 0, 0, -1]. Identity matrix
[1, 0, 0; 0, 1, 0; 0, 0, 1] means sensor chip and main hardware
For example, a mounting matrix for a magnetometer sensor informs
userspace about sensor chip's ORIENTATION relative to the main
hardware.
+
More specifically, main hardware orientation is defined with
respect to the LOCAL EARTH GEOMAGNETIC REFERENCE FRAME where :
+
* Y is in the ground plane and positive towards magnetic North ;
* X is in the ground plane, perpendicular to the North axis and
positive towards the East ;
An implementor might consider that for a hand-held device, a
'natural' orientation would be 'front facing camera at the top'.
The main hardware reference frame could then be described as :
+
* Y is in the plane of the screen and is positive towards the
top of the screen ;
* X is in the plane of the screen, perpendicular to Y axis, and
positive towards the right hand side of the screen ;
* Z is perpendicular to the screen plane and positive out of the
screen.
+
Another example for a quadrotor UAV might be :
+
* Y is in the plane of the propellers and positive towards the
front-view camera;
* X is in the plane of the propellers, perpendicular to Y axis,
This interface is deprecated; please use the Counter subsystem.
A list of possible counting directions which are:
+
- "up" : counter device is increasing.
- "down": counter device is decreasing.
Description:
The DAC is used to find the peak level of an alternating
voltage input signal by a binary search using the output
- of a comparator wired to an interrupt pin. Like so:
+ of a comparator wired to an interrupt pin. Like so::
+
_
| \
input +------>-------|+ \
| irq|------<-------'
| |
'-------'
+
The boolean invert attribute (0/1) should be set when the
input signal is centered around the maximum value of the
dac instead of zero. The envelope detector will search
from below in this case and will also invert the result.
+
The edge/level of the interrupt is also switched to its
opposite value.
is separately set for "GND-Open" and "Supply-Open" modes.
Channels 0..31 have common low threshold values, but could have different
sensing_modes.
+
The low voltage threshold range is between 2..21V.
Hysteresis between low and high thresholds can not be lower then 2 and
can not be odd.
+
If falling threshold results hysteresis to odd value then rising
threshold is automatically subtracted by one.
this value then the threshold rising event is pushed.
Depending on in_voltageY_sensing_mode the high voltage threshold
is separately set for "GND-Open" and "Supply-Open" modes.
+
Channels 0..31 have common high threshold values, but could have different
sensing_modes.
+
The high voltage threshold range is between 3..22V.
Hysteresis between low and high thresholds can not be lower then 2 and
can not be odd.
+
If rising threshold results hysteresis to odd value then falling
threshold is automatically appended by one.
The STM32 ADC can be configured to use external trigger sources
(e.g. timers, pwm or exti gpio). Then, it can be tuned to start
conversions on external trigger by either:
+
- "rising-edge"
- "falling-edge"
- "both-edges".
+
Reading returns current trigger polarity.
+
Writing value before enabling conversions sets trigger polarity.
What: /sys/bus/iio/devices/triggerX/trigger_polarity_available
Contact: linux-iio@vger.kernel.org
Description:
Writing '1' will perform a FOC (Fast Online Calibration). The
- corresponding calibration offsets can be read from *_calibbias
+ corresponding calibration offsets can be read from `*_calibbias`
entries.
What: /sys/bus/iio/devices/iio:deviceX/location
Contact: arnaud.pouliquen@st.com
Description:
For audio purpose only.
+
Used by audio driver to set/get the spi input frequency.
+
This is mandatory if DFSDM is slave on SPI bus, to
provide information on the SPI clock frequency during runtime
Notice that the SPI frequency should be a multiple of sample
frequency to ensure the precision.
- if DFSDM input is SPI master
+
+ if DFSDM input is SPI master:
+
Reading SPI clkout frequency,
error on writing
+
If DFSDM input is SPI Slave:
+
Reading returns value previously set.
Writing value before starting conversions.
first object echoed in meters. Default value is 6.020.
This setting limits the time the driver is waiting for a
echo.
+
Showing the range of available values is represented as the
minimum value, the step and the maximum value, all enclosed
in square brackets.
- Example:
- [0.043 0.043 11.008]
+
+ Example::
+
+ [0.043 0.043 11.008]
Contact: linux-iio@vger.kernel.org
Description:
Reading returns either '1' or '0'.
+
'1' means that the clock in question is present.
+
'0' means that the clock is missing.
What: /sys/bus/iio/devices/iio:deviceX/pllY_locked
KernelVersion:
Contact: linux-iio@vger.kernel.org
Description:
- Reading returns the datasheet name for channel Y:
+ Reading returns the datasheet name for channel Y::
- out_altvoltage0_name: RF8x
- out_altvoltage1_name: RFAUX8x
- out_altvoltage2_name: RF16x
- out_altvoltage3_name: RF32x
+ out_altvoltage0_name: RF8x
+ out_altvoltage1_name: RFAUX8x
+ out_altvoltage2_name: RF16x
+ out_altvoltage3_name: RF32x
What: /sys/bus/iio/devices/iio:deviceX/out_altvoltageY_powerdown
KernelVersion:
Get measured values from the ADC for these stages. Y is the
specific stage number corresponding to datasheet stage names
as follows:
- 1 -> LED2
- 2 -> ALED2/LED3
- 3 -> LED1
- 4 -> ALED1/LED4
+
+ == ==========
+ 1 LED2
+ 2 ALED2/LED3
+ 3 LED1
+ 4 ALED1/LED4
+ == ==========
+
Note that channels 5 and 6 represent LED2-ALED2 and LED1-ALED1
respectively which simply helper channels containing the
calculated difference in the value of stage 1 - 2 and 3 - 4.
Scheme 0 has wider dynamic range, Scheme 1 proximity detection
is less affected by the ambient IR noise variation.
- 0 Sensing IR from LED and ambient
- 1 Sensing IR from LED with ambient IR rejection
+ == =============================================
+ 0 Sensing IR from LED and ambient
+ 1 Sensing IR from LED with ambient IR rejection
+ == =============================================
Contact: fabrice.gasnier@st.com
Description:
Configure the device counter quadrature modes:
+
- non-quadrature:
Encoder IN1 input servers as the count input (up
direction).
+
- quadrature:
Encoder IN1 and IN2 inputs are mixed to get direction
and count.
Contact: fabrice.gasnier@st.com
Description:
Configure the device encoder/counter active edge:
+
- rising-edge
- falling-edge
- both-edges
In non-quadrature mode, device counts up on active edge.
+
In quadrature mode, encoder counting scenarios are as follows:
- ----------------------------------------------------------------
+
+ +---------+----------+--------------------+--------------------+
| Active | Level on | IN1 signal | IN2 signal |
- | edge | opposite |------------------------------------------
+ | edge | opposite +----------+---------+----------+---------+
| | signal | Rising | Falling | Rising | Falling |
- ----------------------------------------------------------------
- | Rising | High -> | Down | - | Up | - |
- | edge | Low -> | Up | - | Down | - |
- ----------------------------------------------------------------
- | Falling | High -> | - | Up | - | Down |
- | edge | Low -> | - | Down | - | Up |
- ----------------------------------------------------------------
- | Both | High -> | Down | Up | Up | Down |
- | edges | Low -> | Up | Down | Down | Up |
- ----------------------------------------------------------------
+ +---------+----------+----------+---------+----------+---------+
+ | Rising | High -> | Down | - | Up | - |
+ | edge | Low -> | Up | - | Down | - |
+ +---------+----------+----------+---------+----------+---------+
+ | Falling | High -> | - | Up | - | Down |
+ | edge | Low -> | - | Down | - | Up |
+ +---------+----------+----------+---------+----------+---------+
+ | Both | High -> | Down | Up | Up | Down |
+ | edges | Low -> | Up | Down | Down | Up |
+ +---------+----------+----------+---------+----------+---------+
Description:
Current configuration and available configurations
for the bias current.
- normal - Normal measurement configurations (default)
- positivebias - Positive bias configuration
- negativebias - Negative bias configuration
- disabled - Only available on HMC5983. Disables magnetic
+
+ ============ ============================================
+ normal Normal measurement configurations (default)
+ positivebias Positive bias configuration
+ negativebias Negative bias configuration
+ disabled Only available on HMC5983. Disables magnetic
sensor and enables temperature sensor.
- Note: The effect of this configuration may vary
- according to the device. For exact documentation
- check the device's datasheet.
+ ============ ============================================
+
+ Note:
+ The effect of this configuration may vary
+ according to the device. For exact documentation
+ check the device's datasheet.
Open-circuit fault. The detection of open-circuit faults,
such as those caused by broken thermocouple wires.
Reading returns either '1' or '0'.
- '1' = An open circuit such as broken thermocouple wires
- has been detected.
- '0' = No open circuit or broken thermocouple wires are detected
+
+ === =======================================================
+ '1' An open circuit such as broken thermocouple wires
+ has been detected.
+ '0' No open circuit or broken thermocouple wires are detected
+ === =======================================================
What: /sys/bus/iio/devices/iio:deviceX/fault_ovuv
KernelVersion: 5.1
cables by integrated MOSFETs at the T+ and T- inputs, and the
BIAS output. These MOSFETs turn off when the input voltage is
negative or greater than VDD.
+
Reading returns either '1' or '0'.
- '1' = The input voltage is negative or greater than VDD.
- '0' = The input voltage is positive and less than VDD (normal
- state).
+
+ === =======================================================
+ '1' The input voltage is negative or greater than VDD.
+ '0' The input voltage is positive and less than VDD (normal
+ state).
+ === =======================================================
Contact: benjamin.gaignard@st.com
Description:
Reading returns the list possible master modes which are:
- - "reset" : The UG bit from the TIMx_EGR register is
+
+
+ - "reset"
+ The UG bit from the TIMx_EGR register is
used as trigger output (TRGO).
- - "enable" : The Counter Enable signal CNT_EN is used
+ - "enable"
+ The Counter Enable signal CNT_EN is used
as trigger output.
- - "update" : The update event is selected as trigger output.
+ - "update"
+ The update event is selected as trigger output.
For instance a master timer can then be used
as a prescaler for a slave timer.
- - "compare_pulse" : The trigger output send a positive pulse
- when the CC1IF flag is to be set.
- - "OC1REF" : OC1REF signal is used as trigger output.
- - "OC2REF" : OC2REF signal is used as trigger output.
- - "OC3REF" : OC3REF signal is used as trigger output.
- - "OC4REF" : OC4REF signal is used as trigger output.
+ - "compare_pulse"
+ The trigger output send a positive pulse
+ when the CC1IF flag is to be set.
+ - "OC1REF"
+ OC1REF signal is used as trigger output.
+ - "OC2REF"
+ OC2REF signal is used as trigger output.
+ - "OC3REF"
+ OC3REF signal is used as trigger output.
+ - "OC4REF"
+ OC4REF signal is used as trigger output.
+
Additional modes (on TRGO2 only):
- - "OC5REF" : OC5REF signal is used as trigger output.
- - "OC6REF" : OC6REF signal is used as trigger output.
+
+ - "OC5REF"
+ OC5REF signal is used as trigger output.
+ - "OC6REF"
+ OC6REF signal is used as trigger output.
- "compare_pulse_OC4REF":
- OC4REF rising or falling edges generate pulses.
+ OC4REF rising or falling edges generate pulses.
- "compare_pulse_OC6REF":
- OC6REF rising or falling edges generate pulses.
+ OC6REF rising or falling edges generate pulses.
- "compare_pulse_OC4REF_r_or_OC6REF_r":
- OC4REF or OC6REF rising edges generate pulses.
+ OC4REF or OC6REF rising edges generate pulses.
- "compare_pulse_OC4REF_r_or_OC6REF_f":
- OC4REF rising or OC6REF falling edges generate pulses.
+ OC4REF rising or OC6REF falling edges generate
+ pulses.
- "compare_pulse_OC5REF_r_or_OC6REF_r":
- OC5REF or OC6REF rising edges generate pulses.
+ OC5REF or OC6REF rising edges generate pulses.
- "compare_pulse_OC5REF_r_or_OC6REF_f":
- OC5REF rising or OC6REF falling edges generate pulses.
-
- +-----------+ +-------------+ +---------+
- | Prescaler +-> | Counter | +-> | Master | TRGO(2)
- +-----------+ +--+--------+-+ |-> | Control +-->
- | | || +---------+
- +--v--------+-+ OCxREF || +---------+
- | Chx compare +----------> | Output | ChX
- +-----------+-+ | | Control +-->
- . | | +---------+
- . | | .
- +-----------v-+ OC6REF | .
- | Ch6 compare +---------+>
- +-------------+
-
- Example with: "compare_pulse_OC4REF_r_or_OC6REF_r":
-
- X
- X X
- X . . X
- X . . X
- X . . X
- count X . . . . X
- . . . .
- . . . .
- +---------------+
- OC4REF | . . |
- +-+ . . +-+
- . +---+ .
- OC6REF . | | .
- +-------+ +-------+
- +-+ +-+
- TRGO2 | | | |
- +-+ +---+ +---------+
+ OC5REF rising or OC6REF falling edges generate
+ pulses.
+
+ ::
+
+ +-----------+ +-------------+ +---------+
+ | Prescaler +-> | Counter | +-> | Master | TRGO(2)
+ +-----------+ +--+--------+-+ |-> | Control +-->
+ | | || +---------+
+ +--v--------+-+ OCxREF || +---------+
+ | Chx compare +----------> | Output | ChX
+ +-----------+-+ | | Control +-->
+ . | | +---------+
+ . | | .
+ +-----------v-+ OC6REF | .
+ | Ch6 compare +---------+>
+ +-------------+
+
+ Example with: "compare_pulse_OC4REF_r_or_OC6REF_r"::
+
+ X
+ X X
+ X . . X
+ X . . X
+ X . . X
+ count X . . . . X
+ . . . .
+ . . . .
+ +---------------+
+ OC4REF | . . |
+ +-+ . . +-+
+ . +---+ .
+ OC6REF . | | .
+ +-------+ +-------+
+ +-+ +-+
+ TRGO2 | | | |
+ +-+ +---+ +---------+
What: /sys/bus/iio/devices/triggerX/master_mode
KernelVersion: 4.11
Configure the device counter enable modes, in all case
counting direction is set by in_count0_count_direction
attribute and the counter is clocked by the internal clock.
+
always:
Counter is always ON.
KernelVersion: 4.3
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RO) Output port type:
- 0: not present,
- 1: MSU (Memory Storage Unit)
- 2: CTP (Common Trace Port)
- 4: PTI (MIPI PTI).
+
+ == =========================
+ 0 not present,
+ 1 MSU (Memory Storage Unit)
+ 2 CTP (Common Trace Port)
+ 4 PTI (MIPI PTI).
+ == =========================
What: /sys/bus/intel_th/devices/<intel_th_id>-gth/outputs/[0-7]_drop
Date: June 2015
KernelVersion: 4.3
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RW) Configure MSC operating mode:
+
- "single", for contiguous buffer mode (high-order alloc);
- "multi", for multiblock mode;
- "ExI", for DCI handler mode;
- "debug", for debug mode;
- any of the currently loaded buffer sinks.
+
If operating mode changes, existing buffer is deallocated,
provided there are no active users and tracing is not enabled,
otherwise the write will fail.
KernelVersion: 4.3
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RW) Configure MSC buffer size for "single" or "multi" modes.
+
In single mode, this is a single number of pages, has to be
power of 2. In multiblock mode, this is a comma-separated list
of numbers of pages for each window to be allocated. Number of
windows is not limited.
+
Writing to this file deallocates existing buffer (provided
there are no active users and tracing is not enabled) and then
allocates a new one.
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to read back the configured direction of the channel.
- The following strings will be accepted:
+ The following strings will be accepted::
+
'tx',
'rx'
Users:
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to read back the configured data type of the channel.
- The following strings will be accepted:
+ The following strings will be accepted::
+
'control',
'async',
'sync',
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Moxtet module description. Format: string
+Description: (Read) Moxtet module description. Format: string
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_id
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Moxtet module ID. Format: %x
+Description: (Read) Moxtet module ID. Format: %x
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_name
Date: March 2019
KernelVersion: 5.3
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Moxtet module name. Format: string
+Description: (Read) Moxtet module name. Format: string
-For all of the nmem device attributes under nfit/*, see the 'NVDIMM Firmware
+For all of the nmem device attributes under ``nfit/*``, see the 'NVDIMM Firmware
Interface Table (NFIT)' section in the ACPI specification
(http://www.uefi.org/specifications) for more details.
+What: nvdimm
+Date: July 2020
+KernelVersion: 5.8
+Contact: Dan Williams <dan.j.williams@intel.com>
+Description:
+
The libnvdimm sub-system implements a common sysfs interface for
platform nvdimm resources. See Documentation/driver-api/nvdimm/.
at 'Documentation/powerpc/papr_hcalls.rst' . Below are
the flags reported in this sysfs file:
- * "not_armed" : Indicates that NVDIMM contents will not
+ * "not_armed"
+ Indicates that NVDIMM contents will not
survive a power cycle.
- * "flush_fail" : Indicates that NVDIMM contents
+ * "flush_fail"
+ Indicates that NVDIMM contents
couldn't be flushed during last
shut-down event.
- * "restore_fail": Indicates that NVDIMM contents
+ * "restore_fail"
+ Indicates that NVDIMM contents
couldn't be restored during NVDIMM
initialization.
- * "encrypted" : NVDIMM contents are encrypted.
- * "smart_notify": There is health event for the NVDIMM.
- * "scrubbed" : Indicating that contents of the
+ * "encrypted"
+ NVDIMM contents are encrypted.
+ * "smart_notify"
+ There is health event for the NVDIMM.
+ * "scrubbed"
+ Indicating that contents of the
NVDIMM have been scrubbed.
- * "locked" : Indicating that NVDIMM contents cant
+ * "locked"
+ Indicating that NVDIMM contents cant
be modified until next power cycle.
What: /sys/bus/nd/devices/nmemX/papr/perf_stats
* "MedWDur " : Media Write Duration
* "CchRHCnt" : Cache Read Hit Count
* "CchWHCnt" : Cache Write Hit Count
- * "FastWCnt" : Fast Write Count
\ No newline at end of file
+ * "FastWCnt" : Fast Write Count
this location. This is useful for overriding default
bindings. The format for the location is: DDDD:BB:DD.F.
That is Domain:Bus:Device.Function and is the same as
- found in /sys/bus/pci/devices/. For example:
- # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
+ found in /sys/bus/pci/devices/. For example::
+
+ # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/bind
+
(Note: kernels before 2.6.28 may require echo -n).
What: /sys/bus/pci/drivers/.../unbind
this location. This may be useful when overriding default
bindings. The format for the location is: DDDD:BB:DD.F.
That is Domain:Bus:Device.Function and is the same as
- found in /sys/bus/pci/devices/. For example:
- # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
+ found in /sys/bus/pci/devices/. For example::
+
+ # echo 0000:00:19.0 > /sys/bus/pci/drivers/foo/unbind
+
(Note: kernels before 2.6.28 may require echo -n).
What: /sys/bus/pci/drivers/.../new_id
Class, Class Mask, and Private Driver Data. The Vendor ID
and Device ID fields are required, the rest are optional.
Upon successfully adding an ID, the driver will probe
- for the device and attempt to bind to it. For example:
- # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
+ for the device and attempt to bind to it. For example::
+
+ # echo "8086 10f5" > /sys/bus/pci/drivers/foo/new_id
What: /sys/bus/pci/drivers/.../remove_id
Date: February 2009
required, the rest are optional. After successfully
removing an ID, the driver will no longer support the
device. This is useful to ensure auto probing won't
- match the driver to the device. For example:
- # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
+ match the driver to the device. For example::
+
+ # echo "8086 10f5" > /sys/bus/pci/drivers/foo/remove_id
What: /sys/bus/pci/rescan
Date: January 2009
-==========================
PCIe Device AER statistics
-==========================
+--------------------------
+
These attributes show up under all the devices that are AER capable. These
statistical counters indicate the errors "as seen/reported by the device".
Note that this may mean that if an endpoint is causing problems, the AER
PCI device using ERR_COR. Note that since multiple errors may
be reported using a single ERR_COR message, thus
TOTAL_ERR_COR at the end of the file may not match the actual
- total of all the errors in the file. Sample output:
--------------------------------------------------------------------------
-localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
-Receiver Error 2
-Bad TLP 0
-Bad DLLP 0
-RELAY_NUM Rollover 0
-Replay Timer Timeout 0
-Advisory Non-Fatal 0
-Corrected Internal Error 0
-Header Log Overflow 0
-TOTAL_ERR_COR 2
--------------------------------------------------------------------------
+ total of all the errors in the file. Sample output::
+
+ localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
+ Receiver Error 2
+ Bad TLP 0
+ Bad DLLP 0
+ RELAY_NUM Rollover 0
+ Replay Timer Timeout 0
+ Advisory Non-Fatal 0
+ Corrected Internal Error 0
+ Header Log Overflow 0
+ TOTAL_ERR_COR 2
What: /sys/bus/pci/devices/<dev>/aer_dev_fatal
Date: July 2018
PCI device using ERR_FATAL. Note that since multiple errors may
be reported using a single ERR_FATAL message, thus
TOTAL_ERR_FATAL at the end of the file may not match the actual
- total of all the errors in the file. Sample output:
--------------------------------------------------------------------------
-localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
-Undefined 0
-Data Link Protocol 0
-Surprise Down Error 0
-Poisoned TLP 0
-Flow Control Protocol 0
-Completion Timeout 0
-Completer Abort 0
-Unexpected Completion 0
-Receiver Overflow 0
-Malformed TLP 0
-ECRC 0
-Unsupported Request 0
-ACS Violation 0
-Uncorrectable Internal Error 0
-MC Blocked TLP 0
-AtomicOp Egress Blocked 0
-TLP Prefix Blocked Error 0
-TOTAL_ERR_FATAL 0
--------------------------------------------------------------------------
+ total of all the errors in the file. Sample output::
+
+ localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
+ Undefined 0
+ Data Link Protocol 0
+ Surprise Down Error 0
+ Poisoned TLP 0
+ Flow Control Protocol 0
+ Completion Timeout 0
+ Completer Abort 0
+ Unexpected Completion 0
+ Receiver Overflow 0
+ Malformed TLP 0
+ ECRC 0
+ Unsupported Request 0
+ ACS Violation 0
+ Uncorrectable Internal Error 0
+ MC Blocked TLP 0
+ AtomicOp Egress Blocked 0
+ TLP Prefix Blocked Error 0
+ TOTAL_ERR_FATAL 0
What: /sys/bus/pci/devices/<dev>/aer_dev_nonfatal
Date: July 2018
PCI device using ERR_NONFATAL. Note that since multiple errors
may be reported using a single ERR_FATAL message, thus
TOTAL_ERR_NONFATAL at the end of the file may not match the
- actual total of all the errors in the file. Sample output:
--------------------------------------------------------------------------
-localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
-Undefined 0
-Data Link Protocol 0
-Surprise Down Error 0
-Poisoned TLP 0
-Flow Control Protocol 0
-Completion Timeout 0
-Completer Abort 0
-Unexpected Completion 0
-Receiver Overflow 0
-Malformed TLP 0
-ECRC 0
-Unsupported Request 0
-ACS Violation 0
-Uncorrectable Internal Error 0
-MC Blocked TLP 0
-AtomicOp Egress Blocked 0
-TLP Prefix Blocked Error 0
-TOTAL_ERR_NONFATAL 0
--------------------------------------------------------------------------
+ actual total of all the errors in the file. Sample output::
+
+ localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
+ Undefined 0
+ Data Link Protocol 0
+ Surprise Down Error 0
+ Poisoned TLP 0
+ Flow Control Protocol 0
+ Completion Timeout 0
+ Completer Abort 0
+ Unexpected Completion 0
+ Receiver Overflow 0
+ Malformed TLP 0
+ ECRC 0
+ Unsupported Request 0
+ ACS Violation 0
+ Uncorrectable Internal Error 0
+ MC Blocked TLP 0
+ AtomicOp Egress Blocked 0
+ TLP Prefix Blocked Error 0
+ TOTAL_ERR_NONFATAL 0
-============================
PCIe Rootport AER statistics
-============================
+----------------------------
+
These attributes show up under only the rootports (or root complex event
collectors) that are AER capable. These indicate the number of error messages as
"reported to" the rootport. Please note that the rootports also transmit
Description:
Version of AudioDSP firmware ASoC catpt driver is
communicating with.
+
Format: %d.%d.%d.%d, type:major:minor:build.
What: /sys/devices/pci0000:00/<dev>/fw_info
number returns the port to normal operation.
For example: To force the high-speed device attached to
- port 4 on bus 2 to run at full speed:
+ port 4 on bus 2 to run at full speed::
echo 4 >/sys/bus/usb/devices/usb2/../companion
- To return the port to high-speed operation:
+ To return the port to high-speed operation::
echo -4 >/sys/bus/usb/devices/usb2/../companion
an individual subdirectory with the following name format of
device_name "nn:d:iiii", where:
- nn - two-digit hexadecimal ID of RapidIO network where the
+ ==== ========================================================
+ nn two-digit hexadecimal ID of RapidIO network where the
device resides
- d - device type: 'e' - for endpoint or 's' - for switch
- iiii - four-digit device destID for endpoints, or switchID for
+ d device type: 'e' - for endpoint or 's' - for switch
+ iiii four-digit device destID for endpoints, or switchID for
switches
+ ==== ========================================================
For example, below is a list of device directories that
represents a typical RapidIO network with one switch, one host,
and two agent endpoints, as it is seen by the enumerating host
- (with destID = 1):
+ (with destID = 1)::
- /sys/bus/rapidio/devices/00:e:0000
- /sys/bus/rapidio/devices/00:e:0002
- /sys/bus/rapidio/devices/00:s:0001
+ /sys/bus/rapidio/devices/00:e:0000
+ /sys/bus/rapidio/devices/00:e:0002
+ /sys/bus/rapidio/devices/00:s:0001
- NOTE: An enumerating or discovering endpoint does not create a
- sysfs entry for itself, this is why an endpoint with destID=1 is
- not shown in the list.
+ NOTE:
+ An enumerating or discovering endpoint does not create a
+ sysfs entry for itself, this is why an endpoint with destID=1
+ is not shown in the list.
Attributes Common for All RapidIO Devices
-----------------------------------------
Usage: <mon ip addr> <options> <pool name> <rbd image name> [<snap name>]
+ Example::
+
$ echo "192.168.0.1 name=admin rbd foo" > /sys/bus/rbd/add
The snapshot name can be "-" or omitted to map the image
Usage: <dev-id> [force]
+ Example::
+
$ echo 2 > /sys/bus/rbd/remove
Optional "force" argument which when passed will wait for
KernelVersion: v2.6.37
Contact: Sage Weil <sage@newdream.net>
Description:
- size: (RO) The size (in bytes) of the mapped block
+
+ ============== ================================================
+ size (RO) The size (in bytes) of the mapped block
device.
- major: (RO) The block device major number.
+ major (RO) The block device major number.
- client_id: (RO) The ceph unique client id that was assigned
+ client_id (RO) The ceph unique client id that was assigned
for this specific session.
- pool: (RO) The name of the storage pool where this rbd
+ pool (RO) The name of the storage pool where this rbd
image resides. An rbd image name is unique
within its pool.
- name: (RO) The name of the rbd image.
+ name (RO) The name of the rbd image.
- refresh: (WO) Writing to this file will reread the image
+ refresh (WO) Writing to this file will reread the image
header data and set all relevant data structures
accordingly.
- current_snap: (RO) The current snapshot for which the device
+ current_snap (RO) The current snapshot for which the device
is mapped.
+ ============== ================================================
What: /sys/bus/rbd/devices/<dev-id>/pool_id
KernelVersion: v3.7
Contact: Sage Weil <sage@newdream.net>
Description:
- image_id: (RO) The unique id for the rbd image. (For rbd
+ ========= ===============================================
+ image_id (RO) The unique id for the rbd image. (For rbd
image format 1 this is empty.)
- features: (RO) A hexadecimal encoding of the feature bits
+ features (RO) A hexadecimal encoding of the feature bits
for this image.
+ ========= ===============================================
What: /sys/bus/rbd/devices/<dev-id>/parent
KernelVersion: v4.9
Contact: Sage Weil <sage@newdream.net>
Description:
- snap_id: (RO) The current snapshot's id.
+ ============ ================================================
+ snap_id (RO) The current snapshot's id.
- config_info: (RO) The string written into
+ config_info (RO) The string written into
/sys/bus/rbd/add{,_single_major}.
- cluster_fsid: (RO) The ceph cluster UUID.
+ cluster_fsid (RO) The ceph cluster UUID.
- client_addr: (RO) The ceph unique client
+ client_addr (RO) The ceph unique client
entity_addr_t (address + nonce). The format is
<address>:<port>/<nonce>: '1.2.3.4:1234/5678' or
'[1:2:3:4:5:6:7:8]:1234/5678'.
+ ============ ================================================
When the file contains a "1" the bus is operated and periodically
does a push-pull cycle to write and read data from the
connected devices.
+
When writing a "0" or "1" the bus moves to the described state.
What: /sys/bus/siox/devices/siox-X/device_add
to add a new device dynamically. <type> is the name that is used to match
to a driver (similar to the platform bus). <inbytes> and <outbytes> define
the length of the input and output shift register in bytes respectively.
+
<statustype> defines the 4 bit device type that is check to identify connection
problems.
+
The new device is added to the end of the existing chain.
What: /sys/bus/siox/devices/siox-X/device_remove
Description: This attribute holds current Thunderbolt security level
set by the system BIOS. Possible values are:
- none: All devices are automatically authorized
- user: Devices are only authorized based on writing
- appropriate value to the authorized attribute
- secure: Require devices that support secure connect at
- minimum. User needs to authorize each device.
- dponly: Automatically tunnel Display port (and USB). No
- PCIe tunnels are created.
- usbonly: Automatically tunnel USB controller of the
+ ======= ==================================================
+ none All devices are automatically authorized
+ user Devices are only authorized based on writing
+ appropriate value to the authorized attribute
+ secure Require devices that support secure connect at
+ minimum. User needs to authorize each device.
+ dponly Automatically tunnel Display port (and USB). No
+ PCIe tunnels are created.
+ usbonly Automatically tunnel USB controller of the
connected Thunderbolt dock (and Display Port). All
PCIe links downstream of the dock are removed.
+ ======= ==================================================
What: /sys/bus/thunderbolt/devices/.../authorized
Date: Sep 2017
yet authorized.
Possible values are supported:
- 1: The device will be authorized and connected
+
+ == ===========================================
+ 1 The device will be authorized and connected
+ == ===========================================
When key attribute contains 32 byte hex string the possible
values are:
- 1: The 32 byte hex string is added to the device NVM and
- the device is authorized.
- 2: Send a challenge based on the 32 byte hex string. If the
- challenge response from device is valid, the device is
- authorized. In case of failure errno will be ENOKEY if
- the device did not contain a key at all, and
- EKEYREJECTED if the challenge response did not match.
+
+ == ========================================================
+ 1 The 32 byte hex string is added to the device NVM and
+ the device is authorized.
+ 2 Send a challenge based on the 32 byte hex string. If the
+ challenge response from device is valid, the device is
+ authorized. In case of failure errno will be ENOKEY if
+ the device did not contain a key at all, and
+ EKEYREJECTED if the challenge response did not match.
+ == ========================================================
What: /sys/bus/thunderbolt/devices/.../boot
Date: Jun 2018
verification fails an error code is returned instead.
This file will accept writing values "1" or "2"
+
- Writing "1" will flush the image to the storage
- area and authenticate the image in one action.
+ area and authenticate the image in one action.
- Writing "2" will run some basic validation on the image
- and flush it to the storage area.
+ and flush it to the storage area.
When read holds status of the last authentication
operation if an error occurred during the process. This
question. Following directories are already reserved by
the Apple XDomain specification:
- network: IP/ethernet over Thunderbolt
- targetdm: Target disk mode protocol over Thunderbolt
- extdisp: External display mode protocol over Thunderbolt
+ ======== ===============================================
+ network IP/ethernet over Thunderbolt
+ targetdm Target disk mode protocol over Thunderbolt
+ extdisp External display mode protocol over Thunderbolt
+ ======== ===============================================
What: /sys/bus/thunderbolt/devices/<xdomain>.<service>/modalias
Date: Jan 2018
image when the device is disconnected from the host system.
This file will accept writing values "1" or "2"
+
- Writing "1" will flush the image to the storage
- area and prepare the device for authentication on disconnect.
+ area and prepare the device for authentication on disconnect.
- Writing "2" will run some basic validation on the image
- and flush it to the storage area.
+ and flush it to the storage area.
by writing INTERFACE to /sys/bus/usb/drivers_probe
This allows to avoid side-effects with drivers
that need multiple interfaces.
+
A deauthorized interface cannot be probed or claimed.
What: /sys/bus/usb/devices/usbX/interface_authorized_default
table at compile time. The format for the device ID is:
idVendor idProduct bInterfaceClass RefIdVendor RefIdProduct
The vendor ID and device ID fields are required, the
- rest is optional. The Ref* tuple can be used to tell the
+ rest is optional. The `Ref*` tuple can be used to tell the
driver to use the same driver_data for the new device as
it is used for the reference device.
Upon successfully adding an ID, the driver will probe
- for the device and attempt to bind to it. For example:
- # echo "8086 10f5" > /sys/bus/usb/drivers/foo/new_id
+ for the device and attempt to bind to it. For example::
+
+ # echo "8086 10f5" > /sys/bus/usb/drivers/foo/new_id
Here add a new device (0458:7045) using driver_data from
- an already supported device (0458:704c):
- # echo "0458 7045 0 0458 704c" > /sys/bus/usb/drivers/foo/new_id
+ an already supported device (0458:704c)::
+
+ # echo "0458 7045 0 0458 704c" > /sys/bus/usb/drivers/foo/new_id
Reading from this file will list all dynamically added
device IDs in the same format, with one entry per
- line. For example:
- # cat /sys/bus/usb/drivers/foo/new_id
- 8086 10f5
- dead beef 06
- f00d cafe
+ line. For example::
+
+ # cat /sys/bus/usb/drivers/foo/new_id
+ 8086 10f5
+ dead beef 06
+ f00d cafe
The list will be truncated at PAGE_SIZE bytes due to
sysfs restrictions.
advance, and behaves well according to the specification.
This attribute is a bit-field that controls the behavior of
a specific port:
+
- Bit 0 of this field selects the "old" enumeration scheme,
as it is considerably faster (it only causes one USB reset
instead of 2).
+
The old enumeration scheme can also be selected globally
using /sys/module/usbcore/parameters/old_scheme_first, but
it is often not desirable as the new scheme was introduced to
poll() for monitoring changes to this value in user space.
Any time this value changes the corresponding hub device will send a
- udev event with the following attributes:
+ udev event with the following attributes::
- OVER_CURRENT_PORT=/sys/bus/usb/devices/.../(hub interface)/portX
- OVER_CURRENT_COUNT=[current value of this sysfs attribute]
+ OVER_CURRENT_PORT=/sys/bus/usb/devices/.../(hub interface)/portX
+ OVER_CURRENT_COUNT=[current value of this sysfs attribute]
What: /sys/bus/usb/devices/.../(hub interface)/portX/usb3_lpm_permit
Date: November 2015
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the devices display mode.
For a 6 character display the values are
+
MSB 0x06; LSB 0x3F, and
+
for an 8 character display the values are
+
MSB 0x08; LSB 0xFF.
What: /sys/bus/usb/.../textmode
Contact: Harrison Metzger <harrisonmetz@gmail.com>
Description: Controls the decimal places on the device.
To set the nth decimal place, give this field
- the value of 10 ** n. Assume this field has
+ the value of ``10 ** n``. Assume this field has
the value k and has 1 or more decimal places set,
to set the mth place (where m is not already set),
- change this fields value to k + 10 ** m.
+ change this fields value to ``k + 10 ** m``.
Writing UUID to this file will create mediated device of
type <type-id> for parent device <device>. This is a
write-only file.
- For example:
- # echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1001" > \
+ For example::
+
+ # echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1001" > \
/sys/devices/foo/mdev_supported_types/foo-1/create
What: /sys/.../mdev_supported_types/<type-id>/devices/
Writing '1' to this file destroys the mediated device. The
vendor driver can fail the remove() callback if that device
is active and the vendor driver doesn't support hot unplug.
- Example:
- # echo 1 > /sys/bus/mdev/devices/<UUID>/remove
+ Example::
+
+ # echo 1 > /sys/bus/mdev/devices/<UUID>/remove
the "erase" command on the on-board flash of the connected
micro.
-What: /sys/class/c2port/c2portX/flash_erase
-Date: October 2008
-Contact: Rodolfo Giometti <giometti@linux.it>
-Description:
- The /sys/class/c2port/c2portX/flash_erase file show the
- on-board flash size of the connected micro.
-
What: /sys/class/c2port/c2portX/reset
Date: October 2008
Contact: Rodolfo Giometti <giometti@linux.it>
non-linear
The brightness changes non-linearly with each step. Brightness
controls should use a linear mapping for a linear perception.
+
+What: /sys/class/backlight/<backlight>/ambient_light_level
+Date: Apr, 2010
+KernelVersion: v2.6.35
+Contact: Michael Hennerich <michael.hennerich@analog.com>
+Description:
+ (RO) Get conversion value of the light sensor.
+
+ The value is automatically updated every 80 ms when the
+ light sensor is enabled.
+
+ The value range is device-driver specific:
+
+ For ADP8870:
+
+ It returns integer between 0 (dark) and 8000 (max ambient
+ brightness).
+
+ For ADP8860:
+
+ It returns a 13-bits integer.
+
+What: /sys/class/backlight/<backlight>/ambient_light_zone
+Date: Apr, 2010
+KernelVersion: v2.6.35
+Contact: Michael Hennerich <michael.hennerich@analog.com>,
+ device-drivers-devel@blackfin.uclinux.org
+
+Description:
+ (RW) Read or write the specific brightness level at which the
+ backlight operates.
+
+ The value meaning is device-driver specific:
+
+ For ADP8860:
+
+ == ==========================
+ 0 Off: Backlight set to 0 mA
+ 1 Level 1: daylight
+ 2 Level 2: bright
+ 3 Level 3: dark
+ == ==========================
+
+ For ADP8870:
+
+ == ==========================
+ 0 Off: Backlight set to 0 mA
+ 1 Level 1: daylight
+ 2 Level 2: bright
+ 3 Level 3: office
+ 4 Level 4: indoor
+ 5 Level 5: dark
+ == ==========================
+
+ Writing 0 returns to normal/automatic ambient light level
+ operation.
+
+ It can be enabled by writing the value stored in
+ /sys/class/backlight/<backlight>/max_brightness to
+ /sys/class/backlight/<backlight>/brightness.
dark (level 3). By default the brightness operates at the daylight brightness
level.
-What: /sys/class/backlight/<backlight>/ambient_light_level
-Date: Apr, 2010
-KernelVersion: v2.6.35
-Contact: Michael Hennerich <michael.hennerich@analog.com>
-Description:
- (RO) 13-bit conversion value for the first light sensor—high
- byte (Bit 12 to Bit 8). The value is updated every 80 ms (when
- the light sensor is enabled).
-
-
-What: /sys/class/backlight/<backlight>/ambient_light_zone
-Date: Apr, 2010
-KernelVersion: v2.6.35
-Contact: Michael Hennerich <michael.hennerich@analog.com>
-Description:
- (RW) Read or write the specific level at which the backlight
- operates. Value "0" enables automatic ambient light sensing, and
- values "1", "2" or "3" set the control to daylight, office or
- dark respectively.
+See also /sys/class/backlight/<backlight>/ambient_light_level and
+/sys/class/backlight/<backlight>/ambient_light_zone.
What: /sys/class/backlight/<backlight>/l1_daylight_max
+See also /sys/class/backlight/<backlight>/ambient_light_level and
+/sys/class/backlight/<backlight>/ambient_light_zone.
+
What: /sys/class/backlight/<backlight>/<ambient light zone>_max
What: /sys/class/backlight/<backlight>/l1_daylight_max
What: /sys/class/backlight/<backlight>/l2_bright_max
set to 0. Full off when the backlight is disabled.
This file will also show the dim brightness level stored for
this <ambient light zone>.
-
-What: /sys/class/backlight/<backlight>/ambient_light_level
-Date: May 2011
-KernelVersion: 3.0
-Contact: device-drivers-devel@blackfin.uclinux.org
-Description:
- Get conversion value of the light sensor.
- This value is updated every 80 ms (when the light sensor
- is enabled). Returns integer between 0 (dark) and
- 8000 (max ambient brightness)
-
-What: /sys/class/backlight/<backlight>/ambient_light_zone
-Date: May 2011
-KernelVersion: 3.0
-Contact: device-drivers-devel@blackfin.uclinux.org
-Description:
- Get/Set current ambient light zone. Reading returns
- integer between 1..5 (1 = daylight, 2 = bright, ..., 5 = dark).
- Writing a value between 1..5 forces the backlight controller
- to enter the corresponding ambient light zone.
- Writing 0 returns to normal/automatic ambient light level
- operation. The ambient light sensing feature on these devices
- is an extension to the API documented in
- Documentation/ABI/stable/sysfs-class-backlight.
- It can be enabled by writing the value stored in
- /sys/class/backlight/<backlight>/max_brightness to
- /sys/class/backlight/<backlight>/brightness.
Get the ALS output channel used as input in
ALS-current-control mode (0, 1), where:
- 0 - out_current0 (backlight 0)
- 1 - out_current1 (backlight 1)
+ == ==========================
+ 0 out_current0 (backlight 0)
+ 1 out_current1 (backlight 1)
+ == ==========================
What: /sys/class/backlight/<backlight>/als_en
Date: May 2012
Description:
Set the brightness-mapping mode (0, 1), where:
- 0 - exponential mode
- 1 - linear mode
+ == ================
+ 0 exponential mode
+ 1 linear mode
+ == ================
What: /sys/class/backlight/<backlight>/pwm
Date: April 2012
Description:
Set the PWM-input control mask (5 bits), where:
- bit 5 - PWM-input enabled in Zone 4
- bit 4 - PWM-input enabled in Zone 3
- bit 3 - PWM-input enabled in Zone 2
- bit 2 - PWM-input enabled in Zone 1
- bit 1 - PWM-input enabled in Zone 0
- bit 0 - PWM-input enabled
+ ===== ===========================
+ bit 5 PWM-input enabled in Zone 4
+ bit 4 PWM-input enabled in Zone 3
+ bit 3 PWM-input enabled in Zone 2
+ bit 2 PWM-input enabled in Zone 1
+ bit 1 PWM-input enabled in Zone 0
+ bit 0 PWM-input enabled
+ ===== ===========================
filesystems which do not provide their own BDI.
Files under /sys/class/bdi/<bdi>/
----------------------------------
read_ahead_kb (read-write)
KernelVersion: 4.2
Description:
Tell the EC to reboot in various ways. Options are:
- "cancel": Cancel a pending reboot.
- "ro": Jump to RO without rebooting.
- "rw": Jump to RW without rebooting.
- "cold": Cold reboot.
- "disable-jump": Disable jump until next reboot.
- "hibernate": Hibernate the EC.
- "at-shutdown": Reboot after an AP shutdown.
+
+ - "cancel": Cancel a pending reboot.
+ - "ro": Jump to RO without rebooting.
+ - "rw": Jump to RW without rebooting.
+ - "cold": Cold reboot.
+ - "disable-jump": Disable jump until next reboot.
+ - "hibernate": Hibernate the EC.
+ - "at-shutdown": Reboot after an AP shutdown.
What: /sys/class/chromeos/<ec-device-name>/version
Date: August 2015
when performing the START_WORK ioctl. Only applicable when
running under hashed page table mmu.
Possible values:
- none: No prefaulting (default)
- work_element_descriptor: Treat the work element
- descriptor as an effective address and
- prefault what it points to.
- all: all segments process calling START_WORK maps.
+
+ ======================= ======================================
+ none No prefaulting (default)
+ work_element_descriptor Treat the work element
+ descriptor as an effective address and
+ prefault what it points to.
+ all all segments process calling
+ START_WORK maps.
+ ======================= ======================================
+
Users: https://github.com/ibm-capi/libcxl
What: /sys/class/cxl/<afu>/reset
card. A power cycle is required to load the image.
"none" could be useful for debugging because the trace arrays
are preserved.
+
"user" and "factory" means PERST will cause either the user or
user or factory image to be loaded.
Default is to reload on PERST whichever image the card has
Description: read/write
Trust that when an image is reloaded via PERST, it will not
have changed.
- 0 = don't trust, the image may be different (default)
- 1 = trust that the image will not change.
+
+ == =================================================
+ 0 don't trust, the image may be different (default)
+ 1 trust that the image will not change.
+ == =================================================
Users: https://github.com/ibm-capi/libcxl
What: /sys/class/cxl/<card>/psl_timebase_synced
driver should provide the list of available frequencies
with its profile. If need to reset the statistics of devfreq
behavior on a specific device, enter 0(zero) to 'trans_stat'
- as following:
+ as following::
+
echo 0 > /sys/class/devfreq/.../trans_stat
What: /sys/class/devfreq/.../userspace/set_freq
This work timer is used by devfreq workqueue in order to
monitor the device status such as utilization. The user
can change the work timer on runtime according to their demand
- as following:
+ as following::
+
echo deferrable > /sys/class/devfreq/.../timer
echo delayed > /sys/class/devfreq/.../timer
This will be one of the following strings:
- 'consumer unbind'
- 'supplier unbind'
- 'never'
+ - 'consumer unbind'
+ - 'supplier unbind'
+ - 'never'
'consumer unbind' means the device link will be removed when
the consumer's driver is unbound from the consumer device.
This will be one of the following strings:
- '0' - Does not affect runtime power management
- '1' - Affects runtime power management
+ === ========================================
+ '0' Does not affect runtime power management
+ '1' Affects runtime power management
+ === ========================================
What: /sys/class/devlink/.../status
Date: May 2020
This will be one of the following strings:
- 'not tracked'
- 'dormant'
- 'available'
- 'consumer probing'
- 'active'
- 'supplier unbinding'
- 'unknown'
+ - 'not tracked'
+ - 'dormant'
+ - 'available'
+ - 'consumer probing'
+ - 'active'
+ - 'supplier unbinding'
+ - 'unknown'
'not tracked' means this device link does not track the status
and has no impact on the binding, unbinding and syncing the
This will be one of the following strings:
+ === ================================
'0'
- '1' - Affects runtime power management
+ '1' Affects runtime power management
+ === ================================
'0' means the device link can affect other device behaviors
like binding/unbinding, suspend/resume, runtime power
callback.
If the default callback for showing function is used, the
- format is like this:
- # cat state
- USB_OTG=1
- HDMI=0
- TA=1
- EAR_JACK=0
- #
+ format is like this::
+
+ # cat state
+ USB_OTG=1
+ HDMI=0
+ TA=1
+ EAR_JACK=0
+ #
+
In this example, the extcon device has USB_OTG and TA
cables attached and HDMI and EAR_JACK cables detached.
In order to update the state of an extcon device, enter a hex
- state number starting with 0x:
- # echo 0xHEX > state
+ state number starting with 0x::
+
+ # echo 0xHEX > state
This updates the whole state of the extcon device.
Inputs of all the methods are required to meet the
Description:
Shows the relations of mutually exclusiveness. For example,
if the mutually_exclusive array of extcon device is
- {0x3, 0x5, 0xC, 0x0}, then the output is:
- # ls mutually_exclusive/
- 0x3
- 0x5
- 0xc
- #
+ {0x3, 0x5, 0xC, 0x0}, then the output is::
+
+ # ls mutually_exclusive/
+ 0x3
+ 0x5
+ 0xc
+ #
Note that mutually_exclusive is a sub-directory of the extcon
device and the file names under the mutually_exclusive
* firmware request = firmware class request in progress
* firmware request error = firmware request failed
* write init = preparing FPGA for programming
- * write init error = Error while preparing FPGA for
- programming
+ * write init error = Error while preparing FPGA for programming
* write = FPGA ready to receive image data
* write error = Error while programming
* write complete = Doing post programming steps
programming errors to userspace. This is a list of strings for
the supported status.
- * reconfig operation error - invalid operations detected by
+ * reconfig operation error - invalid operations detected by
reconfiguration hardware.
e.g. start reconfiguration
with errors not cleared
The GNSS receiver type. The currently identified types reflect
the protocol(s) supported by the receiver:
+ ====== ===========
"NMEA" NMEA 0183
"SiRF" SiRF Binary
"UBX" UBX
+ ====== ===========
Note that also non-"NMEA" type receivers typically support a
subset of NMEA 0183 with vendor extensions (e.g. to allow
KernelVersion: 2.6.17
Contact: Richard Purdie <rpurdie@rpsys.net>
Description:
- Set the brightness of the LED. Most LEDs don't
- have hardware brightness support, so will just be turned on for
- non-zero brightness settings. The value is between 0 and
+ Set the brightness of the LED.
+
+ Most LEDs don't have hardware brightness support, so will
+ just be turned on for non-zero brightness settings.
+
+ .. Note::
+
+ For multicolor LEDs, writing to this file will update all
+ LEDs within the group to a calculated percentage of what
+ each color LED intensity is set to.
+
+ The percentage is calculated for each grouped LED via
+ the equation below::
+
+ led_brightness = brightness * multi_intensity/max_brightness
+
+ For additional details please refer to
+ Documentation/leds/leds-class-multicolor.rst.
+
+ The value is between 0 and
/sys/class/leds/<led>/max_brightness.
Writing 0 to this file clears active trigger.
Writing non-zero to this file while trigger is active changes the
top brightness trigger is going to use.
+
+
What: /sys/class/leds/<led>/max_brightness
Date: March 2006
KernelVersion: 2.6.17
Description:
Set the trigger for this LED. A trigger is a kernel based source
of LED events.
+
You can change triggers in a similar manner to the way an IO
scheduler is chosen. Trigger specific parameters can appear in
/sys/class/leds/<led> once a given trigger is selected. For
- their documentation see sysfs-class-led-trigger-*.
+ their documentation see `sysfs-class-led-trigger-*`.
What: /sys/class/leds/<led>/inverted
Date: January 2011
-What: /sys/class/leds/<led>/hw_pattern
-Date: September 2019
-KernelVersion: 5.5
-Description:
- Specify a hardware pattern for the EL15203000 LED.
- The LEDs board supports only predefined patterns by firmware
- for specific LEDs.
-
- Breathing mode for Screen frame light tube:
- "0 4000 1 4000"
-
- ^
- |
- Max-| ---
- | / \
- | / \
- | / \ /
- | / \ /
- Min-|- ---
- |
- 0------4------8--> time (sec)
-
- Cascade mode for Pipe LED:
- "1 800 2 800 4 800 8 800 16 800"
-
- ^
- |
- 0 On -|----+ +----+ +---
- | | | | |
- Off-| +-------------------+ +-------------------+
- |
- 1 On -| +----+ +----+
- | | | | |
- Off |----+ +-------------------+ +------------------
- |
- 2 On -| +----+ +----+
- | | | | |
- Off-|---------+ +-------------------+ +-------------
- |
- 3 On -| +----+ +----+
- | | | | |
- Off-|--------------+ +-------------------+ +--------
- |
- 4 On -| +----+ +----+
- | | | | |
- Off-|-------------------+ +-------------------+ +---
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
- Inverted cascade mode for Pipe LED:
- "30 800 29 800 27 800 23 800 15 800"
-
- ^
- |
- 0 On -| +-------------------+ +-------------------+
- | | | | |
- Off-|----+ +----+ +---
- |
- 1 On -|----+ +-------------------+ +------------------
- | | | | |
- Off | +----+ +----+
- |
- 2 On -|---------+ +-------------------+ +-------------
- | | | | |
- Off-| +----+ +----+
- |
- 3 On -|--------------+ +-------------------+ +--------
- | | | | |
- Off-| +----+ +----+
- |
- 4 On -|-------------------+ +-------------------+ +---
- | | | | |
- Off-| +----+ +----+
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
- Bounce mode for Pipe LED:
- "1 800 2 800 4 800 8 800 16 800 16 800 8 800 4 800 2 800 1 800"
-
- ^
- |
- 0 On -|----+ +--------
- | | |
- Off-| +---------------------------------------+
- |
- 1 On -| +----+ +----+
- | | | | |
- Off |----+ +-----------------------------+ +--------
- |
- 2 On -| +----+ +----+
- | | | | |
- Off-|---------+ +-------------------+ +-------------
- |
- 3 On -| +----+ +----+
- | | | | |
- Off-|--------------+ +---------+ +------------------
- |
- 4 On -| +---------+
- | | |
- Off-|-------------------+ +-----------------------
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
- Inverted bounce mode for Pipe LED:
- "30 800 29 800 27 800 23 800 15 800 15 800 23 800 27 800 29 800 30 800"
-
- ^
- |
- 0 On -| +---------------------------------------+
- | | |
- Off-|----+ +--------
- |
- 1 On -|----+ +-----------------------------+ +--------
- | | | | |
- Off | +----+ +----+
- |
- 2 On -|---------+ +-------------------+ +-------------
- | | | | |
- Off-| +----+ +----+
- |
- 3 On -|--------------+ +---------+ +------------------
- | | | | |
- Off-| +----+ +----+
- |
- 4 On -|-------------------+ +-----------------------
- | | |
- Off-| +---------+
- |
- 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
-
What: /sys/class/leds/<led>/repeat
Date: September 2019
KernelVersion: 5.5
Set the ALS output channel to use as input in
ALS-current-control mode (1, 2), where:
- 1 - out_current1
- 2 - out_current2
+ == ============
+ 1 out_current1
+ 2 out_current2
+ == ============
What: /sys/class/leds/<led>/als_en
Date: May 2012
Description:
Set the pattern generator fall and rise times (0..7), where:
- 0 - 2048 us
- 1 - 262 ms
- 2 - 524 ms
- 3 - 1.049 s
- 4 - 2.097 s
- 5 - 4.194 s
- 6 - 8.389 s
- 7 - 16.78 s
+ == =======
+ 0 2048 us
+ 1 262 ms
+ 2 524 ms
+ 3 1.049 s
+ 4 2.097 s
+ 5 4.194 s
+ 6 8.389 s
+ 7 16.78 s
+ == =======
What: /sys/class/leds/<led>/id
Date: April 2012
Description:
Set the brightness-mapping mode (0, 1), where:
- 0 - exponential mode
- 1 - linear mode
+ == ================
+ 0 exponential mode
+ 1 linear mode
+ == ================
What: /sys/class/leds/<led>/pwm
Date: April 2012
Description:
Set the PWM-input control mask (5 bits), where:
- bit 5 - PWM-input enabled in Zone 4
- bit 4 - PWM-input enabled in Zone 3
- bit 3 - PWM-input enabled in Zone 2
- bit 2 - PWM-input enabled in Zone 1
- bit 1 - PWM-input enabled in Zone 0
- bit 0 - PWM-input enabled
+ ===== ===========================
+ bit 5 PWM-input enabled in Zone 4
+ bit 4 PWM-input enabled in Zone 3
+ bit 3 PWM-input enabled in Zone 2
+ bit 2 PWM-input enabled in Zone 1
+ bit 1 PWM-input enabled in Zone 0
+ bit 0 PWM-input enabled
+ ===== ===========================
+++ /dev/null
-What: /sys/class/leds/<led>/hw_pattern
-Date: September 2018
-KernelVersion: 4.20
-Description:
- Specify a hardware pattern for the SC27XX LED. For the SC27XX
- LED controller, it only supports 4 stages to make a single
- hardware pattern, which is used to configure the rise time,
- high time, fall time and low time for the breathing mode.
-
- For the breathing mode, the SC27XX LED only expects one brightness
- for the high stage. To be compatible with the hardware pattern
- format, we should set brightness as 0 for rise stage, fall
- stage and low stage.
-
- Min stage duration: 125 ms
- Max stage duration: 31875 ms
-
- Since the stage duration step is 125 ms, the duration should be
- a multiplier of 125, like 125ms, 250ms, 375ms, 500ms ... 31875ms.
-
- Thus the format of the hardware pattern values should be:
- "0 rise_duration brightness high_duration 0 fall_duration 0 low_duration".
Flash faults are re-read after strobing the flash. Possible
flash faults:
- * led-over-voltage - flash controller voltage to the flash LED
+ * led-over-voltage
+ flash controller voltage to the flash LED
has exceeded the limit specific to the flash controller
- * flash-timeout-exceeded - the flash strobe was still on when
+ * flash-timeout-exceeded
+ the flash strobe was still on when
the timeout set by the user has expired; not all flash
controllers may set this in all such conditions
- * controller-over-temperature - the flash controller has
+ * controller-over-temperature
+ the flash controller has
overheated
- * controller-short-circuit - the short circuit protection
+ * controller-short-circuit
+ the short circuit protection
of the flash controller has been triggered
- * led-power-supply-over-current - current in the LED power
+ * led-power-supply-over-current
+ current in the LED power
supply has exceeded the limit specific to the flash
controller
- * indicator-led-fault - the flash controller has detected
+ * indicator-led-fault
+ the flash controller has detected
a short or open circuit condition on the indicator LED
- * led-under-voltage - flash controller voltage to the flash
+ * led-under-voltage
+ flash controller voltage to the flash
LED has been below the minimum limit specific to
the flash
- * controller-under-voltage - the input voltage of the flash
+ * controller-under-voltage
+ the input voltage of the flash
controller is below the limit under which strobing the
flash at full current will not be possible;
the condition persists until this flag is no longer set
- * led-over-temperature - the temperature of the LED has exceeded
+ * led-over-temperature
+ the temperature of the LED has exceeded
its allowed upper limit
-What: /sys/class/leds/<led>/brightness
-Date: March 2020
-KernelVersion: 5.9
-Contact: Dan Murphy <dmurphy@ti.com>
-Description: read/write
- Writing to this file will update all LEDs within the group to a
- calculated percentage of what each color LED intensity is set
- to. The percentage is calculated for each grouped LED via the
- equation below:
-
- led_brightness = brightness * multi_intensity/max_brightness
-
- For additional details please refer to
- Documentation/leds/leds-class-multicolor.rst.
-
- The value of the LED is from 0 to
- /sys/class/leds/<led>/max_brightness.
What: /sys/class/leds/<led>/multi_index
Date: March 2020
as an array of strings as they are indexed in the
multi_intensity file.
+ For additional details please refer to
+ Documentation/leds/leds-class-multicolor.rst.
+
What: /sys/class/leds/<led>/multi_intensity
Date: March 2020
KernelVersion: 5.9
This file contains array of integers. Order of components is
described by the multi_index array. The maximum intensity should
not exceed /sys/class/leds/<led>/max_brightness.
+
+ For additional details please refer to
+ Documentation/leds/leds-class-multicolor.rst.
Contact: linux-leds@vger.kernel.org
Description:
Signal the link state of the named network device.
+
If set to 0 (default), the LED's normal state is off.
+
If set to 1, the LED's normal state reflects the link state
of the named network device.
Setting this value also immediately changes the LED state.
+
What: /sys/class/leds/<led>/tx
Date: Dec 2017
KernelVersion: 4.16
Contact: linux-leds@vger.kernel.org
Description:
Signal transmission of data on the named network device.
+
If set to 0 (default), the LED will not blink on transmission.
+
If set to 1, the LED will blink for the milliseconds specified
in interval to signal transmission.
Contact: linux-leds@vger.kernel.org
Description:
Signal reception of data on the named network device.
+
If set to 0 (default), the LED will not blink on reception.
+
If set to 1, the LED will blink for the milliseconds specified
in interval to signal reception.
Since different LED hardware can have different semantics of
hardware patterns, each driver is expected to provide its own
- description for the hardware patterns in their ABI documentation
- file.
+ description for the hardware patterns in their documentation
+ file at Documentation/leds/.
What: /sys/class/leds/<led>/repeat
Date: September 2018
selected for the USB port trigger. Selecting ports makes trigger
observing them for any connected devices and lighting on LED if
there are any.
+
Echoing "1" value selects USB port. Echoing "0" unselects it.
Current state can be also read.
of one LED will update the mode of its two sibling devices as
well. Possible values are:
- 0 - normal
- 1 - audio
- 2 - breathing
+ == =========
+ 0 normal
+ 1 audio
+ 2 breathing
+ == =========
Normal: LEDs are fully on when enabled
Audio: LEDs brightness depends on sound level
When read, this entry provides the current state of an Intel
MIC device in the context of the card OS. Possible values that
will be read are:
- "ready" - The MIC device is ready to boot the card OS. On
- reading this entry after an OSPM resume, a "boot" has to be
- written to this entry if the card was previously shutdown
- during OSPM suspend.
- "booting" - The MIC device has initiated booting a card OS.
- "online" - The MIC device has completed boot and is online
- "shutting_down" - The card OS is shutting down.
- "resetting" - A reset has been initiated for the MIC device
- "reset_failed" - The MIC device has failed to reset.
+
+
+ =============== ===============================================
+ "ready" The MIC device is ready to boot the card OS.
+ On reading this entry after an OSPM resume,
+ a "boot" has to be written to this entry if
+ the card was previously shutdown during OSPM
+ suspend.
+ "booting" The MIC device has initiated booting a card OS.
+ "online" The MIC device has completed boot and is online
+ "shutting_down" The card OS is shutting down.
+ "resetting" A reset has been initiated for the MIC device
+ "reset_failed" The MIC device has failed to reset.
+ =============== ===============================================
When written, this sysfs entry triggers different state change
operations depending upon the current state of the card OS.
Acceptable values are:
- "boot" - Boot the card OS image specified by the combination
- of firmware, ramdisk, cmdline and bootmode
- sysfs entries.
- "reset" - Initiates device reset.
- "shutdown" - Initiates card OS shutdown.
+
+
+ ========== ===================================================
+ "boot" Boot the card OS image specified by the combination
+ of firmware, ramdisk, cmdline and bootmode
+ sysfs entries.
+ "reset" Initiates device reset.
+ "shutdown" Initiates card OS shutdown.
+ ========== ===================================================
What: /sys/class/mic/mic(x)/shutdown_status
Date: October 2013
OS can shutdown because of various reasons. When read, this
entry provides the status on why the card OS was shutdown.
Possible values are:
- "nop" - shutdown status is not applicable, when the card OS is
- "online"
- "crashed" - Shutdown because of a HW or SW crash.
- "halted" - Shutdown because of a halt command.
- "poweroff" - Shutdown because of a poweroff command.
- "restart" - Shutdown because of a restart command.
+
+ ========== ===================================================
+ "nop" shutdown status is not applicable, when the card OS
+ is "online"
+ "crashed" Shutdown because of a HW or SW crash.
+ "halted" Shutdown because of a halt command.
+ "poweroff" Shutdown because of a poweroff command.
+ "restart" Shutdown because of a restart command.
+ ========== ===================================================
What: /sys/class/mic/mic(x)/cmdline
Date: October 2013
Contact: netdev@vger.kernel.org
Description:
Indicates the name assignment type. Possible values are:
- 1: enumerated by the kernel, possibly in an unpredictable way
- 2: predictably named by the kernel
- 3: named by userspace
- 4: renamed
+
+ == ==========================================================
+ 1 enumerated by the kernel, possibly in an unpredictable way
+ 2 predictably named by the kernel
+ 3 named by userspace
+ 4 renamed
+ == ==========================================================
What: /sys/class/net/<iface>/addr_assign_type
Date: July 2010
Contact: netdev@vger.kernel.org
Description:
Indicates the address assignment type. Possible values are:
- 0: permanent address
- 1: randomly generated
- 2: stolen from another device
- 3: set using dev_set_mac_address
+
+ == =============================
+ 0 permanent address
+ 1 randomly generated
+ 2 stolen from another device
+ 3 set using dev_set_mac_address
+ == =============================
What: /sys/class/net/<iface>/addr_len
Date: April 2005
Default value 0 does not forward any link local frames.
Restricted bits:
- 0: 01-80-C2-00-00-00 Bridge Group Address used for STP
- 1: 01-80-C2-00-00-01 (MAC Control) 802.3 used for MAC PAUSE
- 2: 01-80-C2-00-00-02 (Link Aggregation) 802.3ad
+
+ == ========================================================
+ 0 01-80-C2-00-00-00 Bridge Group Address used for STP
+ 1 01-80-C2-00-00-01 (MAC Control) 802.3 used for MAC PAUSE
+ 2 01-80-C2-00-00-02 (Link Aggregation) 802.3ad
+ == ========================================================
Any values not setting these bits can be used. Take special
care when forwarding control frames e.g. 802.1X-PAE or LLDP.
Description:
Indicates the current physical link state of the interface.
Posssible values are:
- 0: physical link is down
- 1: physical link is up
+
+ == =====================
+ 0 physical link is down
+ 1 physical link is up
+ == =====================
Note: some special devices, e.g: bonding and team drivers will
allow this attribute to be written to force a link state for
Description:
Indicates whether the interface is under test. Possible
values are:
- 0: interface is not being tested
- 1: interface is being tested
+
+ == =============================
+ 0 interface is not being tested
+ 1 interface is being tested
+ == =============================
When an interface is under test, it cannot be expected
to pass packets as normal.
-What: /sys/clas/net/<iface>/duplex
+What: /sys/class/net/<iface>/duplex
Date: October 2009
KernelVersion: 2.6.33
Contact: netdev@vger.kernel.org
Description:
Indicates the interface latest or current duplex value. Possible
values are:
- half: half duplex
- full: full duplex
+
+ ==== ===========
+ half half duplex
+ full full duplex
+ ==== ===========
Note: This attribute is only valid for interfaces that implement
the ethtool get_link_ksettings method (mostly Ethernet).
Indicates the interface link mode, as a decimal number. This
attribute should be used in conjunction with 'dormant' attribute
to determine the interface usability. Possible values:
- 0: default link mode
- 1: dormant link mode
+
+ == =================
+ 0 default link mode
+ 1 dormant link mode
+ == =================
What: /sys/class/net/<iface>/mtu
Date: April 2005
Contact: netdev@vger.kernel.org
Description:
Indicates the interface RFC2863 operational state as a string.
+
Possible values are:
+
"unknown", "notpresent", "down", "lowerlayerdown", "testing",
"dormant", "up".
KernelVersion: 3.16
Contact: Bjørn Mork <bjorn@mork.no>
Description:
- Bit 0: 16-bit NTB supported (set to 1)
- Bit 1: 32-bit NTB supported
- Bits 2 – 15: reserved (reset to zero; must be ignored by host)
+ - Bit 0: 16-bit NTB supported (set to 1)
+ - Bit 1: 32-bit NTB supported
+ - Bits 2 – 15: reserved (reset to zero; must be ignored by host)
What: /sys/class/net/<iface>/cdc_ncm/dwNtbInMaxSize
Date: May 2014
Ethernet driver during bus enumeration, encoded in string.
This interface mode is used to configure the Ethernet MAC with the
appropriate mode for its data lines to the PHY hardware.
+
Possible values are:
+
<empty> (not available), mii, gmii, sgmii, tbi, rev-mii,
rmii, rgmii, rgmii-id, rgmii-rxid, rgmii-txid, rtbi, smii
xgmii, moca, qsgmii, trgmii, 1000base-x, 2500base-x, rxaui,
Description: read only
Number of contexts for the AFU, in the format <n>/<max>
where:
- n: number of currently active contexts, for debug
- max: maximum number of contexts supported by the AFU
+
+ ==== ===============================================
+ n number of currently active contexts, for debug
+ max maximum number of contexts supported by the AFU
+ ==== ===============================================
What: /sys/class/ocxl/<afu name>/pp_mmio_size
Date: January 2018
Description: read/write
Control whether the FPGA is reloaded on a link reset. Enabled
through a vendor-specific logic block on the FPGA.
- 0 Do not reload FPGA image from flash
- 1 Reload FPGA image from flash
- unavailable
- The device does not support this capability
+
+ =========== ===========================================
+ 0 Do not reload FPGA image from flash
+ 1 Reload FPGA image from flash
+ unavailable The device does not support this capability
+ =========== ===========================================
Contact: Thomas Maier <balagi@justmail.de>
Description:
- add: (WO) Write a block device id (major:minor) to
+ ========== ==============================================
+ add (WO) Write a block device id (major:minor) to
create a new pktcdvd device and map it to the
block device.
- remove: (WO) Write the pktcdvd device id (major:minor)
+ remove (WO) Write the pktcdvd device id (major:minor)
to remove the pktcdvd device.
- device_map: (RO) Shows the device mapping in format:
+ device_map (RO) Shows the device mapping in format:
pktcdvd[0-7] <pktdevid> <blkdevid>
+ ========== ==============================================
What: /sys/class/pktcdvd/pktcdvd[0-7]/dev
KernelVersion: 2.6.20
Contact: Thomas Maier <balagi@justmail.de>
Description:
- size: (RO) Contains the size of the bio write queue.
+ ============== ================================================
+ size (RO) Contains the size of the bio write queue.
- congestion_off: (RW) If bio write queue size is below this mark,
+ congestion_off (RW) If bio write queue size is below this mark,
accept new bio requests from the block layer.
- congestion_on: (RW) If bio write queue size is higher as this
+ congestion_on (RW) If bio write queue size is higher as this
mark, do no longer accept bio write requests
from the block layer and wait till the pktcdvd
device has processed enough bio's so that bio
write queue size is below congestion off mark.
A value of <= 0 disables congestion control.
+ ============== ================================================
Example:
--------
-To use the pktcdvd sysfs interface directly, you can do:
-
-# create a new pktcdvd device mapped to /dev/hdc
-echo "22:0" >/sys/class/pktcdvd/add
-cat /sys/class/pktcdvd/device_map
-# assuming device pktcdvd0 was created, look at stat's
-cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
-# print the device id of the mapped block device
-fgrep pktcdvd0 /sys/class/pktcdvd/device_map
-# remove device, using pktcdvd0 device id 253:0
-echo "253:0" >/sys/class/pktcdvd/remove
+To use the pktcdvd sysfs interface directly, you can do::
+
+ # create a new pktcdvd device mapped to /dev/hdc
+ echo "22:0" >/sys/class/pktcdvd/add
+ cat /sys/class/pktcdvd/device_map
+ # assuming device pktcdvd0 was created, look at stat's
+ cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
+ # print the device id of the mapped block device
+ fgrep pktcdvd0 /sys/class/pktcdvd/device_map
+ # remove device, using pktcdvd0 device id 253:0
+ echo "253:0" >/sys/class/pktcdvd/remove
-===== General Properties =====
+**General Properties**
What: /sys/class/power_supply/<supply_name>/manufacturer
Date: May 2007
Access: Read
Valid values: "Battery", "UPS", "Mains", "USB", "Wireless"
-===== Battery Properties =====
+**Battery and USB properties**
+
+What: /sys/class/power_supply/<supply_name>/current_avg
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports an average IBAT current reading for the battery, over
+ a fixed period. Normally devices will provide a fixed interval
+ in which they average readings to smooth out the reported
+ value.
+
+ USB:
+
+ Reports an average IBUS current reading over a fixed period.
+ Normally devices will provide a fixed interval in which they
+ average readings to smooth out the reported value.
+
+ Access: Read
+
+ Valid values: Represented in microamps. Negative values are
+ used for discharging batteries, positive values for charging
+ batteries and for USB IBUS current.
+
+What: /sys/class/power_supply/<supply_name>/current_max
+Date: October 2010
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the maximum IBAT current allowed into the battery.
+
+ USB:
+
+ Reports the maximum IBUS current the supply can support.
+
+ Access: Read
+ Valid values: Represented in microamps
+
+What: /sys/class/power_supply/<supply_name>/current_now
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+
+ Battery:
+
+ Reports an instant, single IBAT current reading for the
+ battery. This value is not averaged/smoothed.
+
+ Access: Read
+
+ USB:
+
+ Reports the IBUS current supplied now. This value is generally
+ read-only reporting, unless the 'online' state of the supply
+ is set to be programmable, in which case this value can be set
+ within the reported min/max range.
+
+ Access: Read, Write
+
+ Valid values: Represented in microamps. Negative values are
+ used for discharging batteries, positive values for charging
+ batteries and for USB IBUS current.
+
+What: /sys/class/power_supply/<supply_name>/temp
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the current TBAT battery temperature reading.
+
+ USB:
+
+ Reports the current supply temperature reading. This would
+ normally be the internal temperature of the device itself
+ (e.g TJUNC temperature of an IC)
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_alert_max
+Date: July 2012
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Maximum TBAT temperature trip-wire value where the supply will
+ notify user-space of the event.
+
+ USB:
+
+ Maximum supply temperature trip-wire value where the supply
+ will notify user-space of the event.
+
+ This is normally used for the charging scenario where
+ user-space needs to know if the temperature has crossed an
+ upper threshold so it can take appropriate action (e.g. warning
+ user that the temperature is critically high, and charging has
+ stopped).
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_alert_min
+Date: July 2012
+Contact: linux-pm@vger.kernel.org
+Description:
+
+ Battery:
+
+ Minimum TBAT temperature trip-wire value where the supply will
+ notify user-space of the event.
+
+ USB:
+
+ Minimum supply temperature trip-wire value where the supply
+ will notify user-space of the event.
+
+ This is normally used for the charging scenario where user-space
+ needs to know if the temperature has crossed a lower threshold
+ so it can take appropriate action (e.g. warning user that
+ temperature level is high, and charging current has been
+ reduced accordingly to remedy the situation).
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_max
+Date: July 2014
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the maximum allowed TBAT battery temperature for
+ charging.
+
+ USB:
+
+ Reports the maximum allowed supply temperature for operation.
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/temp_min
+Date: July 2014
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the minimum allowed TBAT battery temperature for
+ charging.
+
+ USB:
+
+ Reports the minimum allowed supply temperature for operation.
+
+ Access: Read
+
+ Valid values: Represented in 1/10 Degrees Celsius
+
+What: /sys/class/power_supply/<supply_name>/voltage_max,
+Date: January 2008
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the maximum safe VBAT voltage permitted for the
+ battery, during charging.
+
+ USB:
+
+ Reports the maximum VBUS voltage the supply can support.
+
+ Access: Read
+
+ Valid values: Represented in microvolts
+
+What: /sys/class/power_supply/<supply_name>/voltage_min,
+Date: January 2008
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports the minimum safe VBAT voltage permitted for the
+ battery, during discharging.
+
+ USB:
+
+ Reports the minimum VBUS voltage the supply can support.
+
+ Access: Read
+
+ Valid values: Represented in microvolts
+
+What: /sys/class/power_supply/<supply_name>/voltage_now,
+Date: May 2007
+Contact: linux-pm@vger.kernel.org
+Description:
+ Battery:
+
+ Reports an instant, single VBAT voltage reading for the
+ battery. This value is not averaged/smoothed.
+
+ Access: Read
+
+ USB:
+
+ Reports the VBUS voltage supplied now. This value is generally
+ read-only reporting, unless the 'online' state of the supply
+ is set to be programmable, in which case this value can be set
+ within the reported min/max range.
+
+ Access: Read, Write
+
+ Valid values: Represented in microvolts
+
+**Battery Properties**
What: /sys/class/power_supply/<supply_name>/capacity
Date: May 2007
Contact: linux-pm@vger.kernel.org
Description:
Fine grain representation of battery capacity.
+
Access: Read
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_alert_max
low).
Access: Read, Write
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_alert_min
critically low).
Access: Read, Write
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_error_margin
completely useless.
Access: Read
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/capacity_level
Coarse representation of battery capacity.
Access: Read
- Valid values: "Unknown", "Critical", "Low", "Normal", "High",
- "Full"
-
-What: /sys/class/power_supply/<supply_name>/current_avg
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an average IBAT current reading for the battery, over a
- fixed period. Normally devices will provide a fixed interval in
- which they average readings to smooth out the reported value.
-
- Access: Read
- Valid values: Represented in microamps. Negative values are used
- for discharging batteries, positive values for charging batteries.
-What: /sys/class/power_supply/<supply_name>/current_max
-Date: October 2010
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum IBAT current allowed into the battery.
-
- Access: Read
- Valid values: Represented in microamps
-
-What: /sys/class/power_supply/<supply_name>/current_now
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an instant, single IBAT current reading for the battery.
- This value is not averaged/smoothed.
-
- Access: Read
- Valid values: Represented in microamps. Negative values are used
- for discharging batteries, positive values for charging batteries.
+ Valid values:
+ "Unknown", "Critical", "Low", "Normal", "High",
+ "Full"
What: /sys/class/power_supply/<supply_name>/charge_control_limit
Date: Oct 2012
throttling for thermal cooling or improving battery health.
Access: Read, Write
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/charge_control_limit_max
Maximum legal value for the charge_control_limit property.
Access: Read
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/charge_control_start_threshold
stop.
Access: Read, Write
+
Valid values: 0 - 100 (percent)
What: /sys/class/power_supply/<supply_name>/charge_type
different algorithm.
Access: Read, Write
- Valid values: "Unknown", "N/A", "Trickle", "Fast", "Standard",
+
+ Valid values:
+ "Unknown", "N/A", "Trickle", "Fast", "Standard",
"Adaptive", "Custom"
What: /sys/class/power_supply/<supply_name>/charge_term_current
when the battery is considered full and charging should end.
Access: Read
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/health
functionality.
Access: Read
- Valid values: "Unknown", "Good", "Overheat", "Dead",
+
+ Valid values:
+ "Unknown", "Good", "Overheat", "Dead",
"Over voltage", "Unspecified failure", "Cold",
"Watchdog timer expire", "Safety timer expire",
"Over current", "Calibration required", "Warm",
for a battery charge cycle.
Access: Read
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/present
Reports whether a battery is present or not in the system.
Access: Read
+
Valid values:
+
+ == =======
0: Absent
1: Present
+ == =======
What: /sys/class/power_supply/<supply_name>/status
Date: May 2007
used to enable/disable charging to the battery.
Access: Read, Write
- Valid values: "Unknown", "Charging", "Discharging",
+
+ Valid values:
+ "Unknown", "Charging", "Discharging",
"Not charging", "Full"
What: /sys/class/power_supply/<supply_name>/technology
Describes the battery technology supported by the supply.
Access: Read
- Valid values: "Unknown", "NiMH", "Li-ion", "Li-poly", "LiFe",
- "NiCd", "LiMn"
-
-What: /sys/class/power_supply/<supply_name>/temp
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the current TBAT battery temperature reading.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_max
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Maximum TBAT temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- battery charging scenario where user-space needs to know the
- battery temperature has crossed an upper threshold so it can
- take appropriate action (e.g. warning user that battery level is
- critically high, and charging has stopped).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_min
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Minimum TBAT temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- battery charging scenario where user-space needs to know the
- battery temperature has crossed a lower threshold so it can take
- appropriate action (e.g. warning user that battery level is
- high, and charging current has been reduced accordingly to
- remedy the situation).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_max
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum allowed TBAT battery temperature for
- charging.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-What: /sys/class/power_supply/<supply_name>/temp_min
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the minimum allowed TBAT battery temperature for
- charging.
+ Valid values:
+ "Unknown", "NiMH", "Li-ion", "Li-poly", "LiFe",
+ "NiCd", "LiMn"
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
What: /sys/class/power_supply/<supply_name>/voltage_avg,
Date: May 2007
which they average readings to smooth out the reported value.
Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_max,
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum safe VBAT voltage permitted for the battery,
- during charging.
-
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_min,
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the minimum safe VBAT voltage permitted for the battery,
- during discharging.
- Access: Read
Valid values: Represented in microvolts
-What: /sys/class/power_supply/<supply_name>/voltage_now,
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an instant, single VBAT voltage reading for the battery.
- This value is not averaged/smoothed.
-
- Access: Read
- Valid values: Represented in microvolts
-
-===== USB Properties =====
-
-What: /sys/class/power_supply/<supply_name>/current_avg
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports an average IBUS current reading over a fixed period.
- Normally devices will provide a fixed interval in which they
- average readings to smooth out the reported value.
-
- Access: Read
- Valid values: Represented in microamps
-
-
-What: /sys/class/power_supply/<supply_name>/current_max
-Date: October 2010
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum IBUS current the supply can support.
-
- Access: Read
- Valid values: Represented in microamps
-
-What: /sys/class/power_supply/<supply_name>/current_now
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the IBUS current supplied now. This value is generally
- read-only reporting, unless the 'online' state of the supply
- is set to be programmable, in which case this value can be set
- within the reported min/max range.
-
- Access: Read, Write
- Valid values: Represented in microamps
+**USB Properties**
What: /sys/class/power_supply/<supply_name>/input_current_limit
Date: July 2014
solved using power limit use input_current_limit.
Access: Read, Write
+
Valid values: Represented in microamps
What: /sys/class/power_supply/<supply_name>/input_voltage_limit
solved using power limit use input_voltage_limit.
Access: Read, Write
+
Valid values: Represented in microvolts
What: /sys/class/power_supply/<supply_name>/input_power_limit
limit only for problems that can be solved using power limit.
Access: Read, Write
+
Valid values: Represented in microwatts
What: /sys/class/power_supply/<supply_name>/online,
USB supply so voltage and current can be controlled).
Access: Read, Write
+
Valid values:
+
+ == ==================================================
0: Offline
1: Online Fixed - Fixed Voltage Supply
2: Online Programmable - Programmable Voltage Supply
-
-What: /sys/class/power_supply/<supply_name>/temp
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the current supply temperature reading. This would
- normally be the internal temperature of the device itself (e.g
- TJUNC temperature of an IC)
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_max
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Maximum supply temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- charging scenario where user-space needs to know the supply
- temperature has crossed an upper threshold so it can take
- appropriate action (e.g. warning user that the supply
- temperature is critically high, and charging has stopped to
- remedy the situation).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_alert_min
-Date: July 2012
-Contact: linux-pm@vger.kernel.org
-Description:
- Minimum supply temperature trip-wire value where the supply will
- notify user-space of the event. This is normally used for the
- charging scenario where user-space needs to know the supply
- temperature has crossed a lower threshold so it can take
- appropriate action (e.g. warning user that the supply
- temperature is high, and charging current has been reduced
- accordingly to remedy the situation).
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_max
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum allowed supply temperature for operation.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
-
-What: /sys/class/power_supply/<supply_name>/temp_min
-Date: July 2014
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the mainimum allowed supply temperature for operation.
-
- Access: Read
- Valid values: Represented in 1/10 Degrees Celsius
+ == ==================================================
What: /sys/class/power_supply/<supply_name>/usb_type
Date: March 2018
is attached.
Access: Read-Only
- Valid values: "Unknown", "SDP", "DCP", "CDP", "ACA", "C", "PD",
- "PD_DRP", "PD_PPS", "BrickID"
-
-What: /sys/class/power_supply/<supply_name>/voltage_max
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the maximum VBUS voltage the supply can support.
-
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_min
-Date: January 2008
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the minimum VBUS voltage the supply can support.
- Access: Read
- Valid values: Represented in microvolts
-
-What: /sys/class/power_supply/<supply_name>/voltage_now
-Date: May 2007
-Contact: linux-pm@vger.kernel.org
-Description:
- Reports the VBUS voltage supplied now. This value is generally
- read-only reporting, unless the 'online' state of the supply
- is set to be programmable, in which case this value can be set
- within the reported min/max range.
-
- Access: Read, Write
- Valid values: Represented in microvolts
+ Valid values:
+ "Unknown", "SDP", "DCP", "CDP", "ACA", "C", "PD",
+ "PD_DRP", "PD_PPS", "BrickID"
-===== Device Specific Properties =====
+**Device Specific Properties**
What: /sys/class/power/ds2760-battery.*/charge_now
Date: May 2010
will drop to 0 A) and will trigger interrupt.
Valid values:
+
- 5, 6 or 7 (hours),
- 0: disabled.
will drop to 0 A) and will trigger interrupt.
Valid values:
+
- 4 - 16 (hours), step by 2 (rounded down)
- 0: disabled.
interrupt and start top-off charging mode.
Valid values:
+
- 100000 - 200000 (microamps), step by 25000 (rounded down)
- 200000 - 350000 (microamps), step by 50000 (rounded down)
- 0: disabled.
will drop to 0 A) and will trigger interrupt.
Valid values:
+
- 0 - 70 (minutes), step by 10 (rounded down)
What: /sys/class/power_supply/bq24257-charger/ovp_voltage
device datasheet for details.
Valid values:
+
- 6000000, 6500000, 7000000, 8000000, 9000000, 9500000, 10000000,
10500000 (all uV)
lower than the set value. See device datasheet for details.
Valid values:
+
- 4200000, 4280000, 4360000, 4440000, 4520000, 4600000, 4680000,
4760000 (all uV)
the charger operates normally. See device datasheet for details.
Valid values:
+
- 1: enabled
- 0: disabled
from the system. See device datasheet for details.
Valid values:
+
- 1: enabled
- 0: disabled
manufactured.
Access: Read
+
Valid values: Reported as integer
What: /sys/class/power_supply/<supply_name>/manufacture_month
Reports the month when the device has been manufactured.
Access: Read
+
Valid values: 1-12
What: /sys/class/power_supply/<supply_name>/manufacture_day
Represents a battery impedance compensation to accelerate charging.
Access: Read, Write
+
Valid values: Represented in milli-ohms. Valid range is [0, 140].
Writing to this can disable charging.
Possible values are:
- "auto" - draw power as appropriate for detected
- power source and battery status.
- "off" - do not draw any power.
- "continuous"
- - activate mode described as "linear" in
- TWL data sheets. This uses whatever
- current is available and doesn't switch off
- when voltage drops.
- This is useful for unstable power sources
- such as bicycle dynamo, but care should
- be taken that battery is not over-charged.
+ ============= ===========================================
+ "auto" draw power as appropriate for detected
+ power source and battery status.
+ "off" do not draw any power.
+ "continuous" activate mode described as "linear" in
+ TWL data sheets. This uses whatever
+ current is available and doesn't switch off
+ when voltage drops.
+
+ This is useful for unstable power sources
+ such as bicycle dynamo, but care should
+ be taken that battery is not over-charged.
+ ============= ===========================================
What: /sys/class/power_supply/twl4030_ac/mode
Description:
Writing to this can disable charging.
Possible values are:
- "auto" - draw power as appropriate for detected
- power source and battery status.
- "off" - do not draw any power.
+
+ ====== ===========================================
+ "auto" draw power as appropriate for detected
+ power source and battery status.
+ "off" do not draw any power.
+ ====== ===========================================
Description:
What charging algorithm to use:
- Standard: Fully charges battery at a standard rate.
- Adaptive: Battery settings adaptively optimized based on
+ Standard:
+ Fully charges battery at a standard rate.
+ Adaptive:
+ Battery settings adaptively optimized based on
typical battery usage pattern.
- Fast: Battery charges over a shorter period.
- Trickle: Extends battery lifespan, intended for users who
+ Fast:
+ Battery charges over a shorter period.
+ Trickle:
+ Extends battery lifespan, intended for users who
primarily use their Chromebook while connected to AC.
- Custom: A low and high threshold percentage is specified.
+ Custom:
+ A low and high threshold percentage is specified.
Charging begins when level drops below
charge_control_start_threshold, and ceases when
level is above charge_control_end_threshold.
- Long Life: Customized charge rate for last longer battery life.
+ Long Life:
+ Customized charge rate for last longer battery life.
On Wilco device this mode is pre-configured in the factory
through EC's private PID. Swiching to a different mode will
be denied by Wilco EC when Long Life mode is enabled.
The /sys/class/rapidio_port subdirectory contains individual
subdirectories named as "rapidioN" where N = mport ID registered
with RapidIO subsystem.
+
NOTE: An mport ID is not a RapidIO destination ID assigned to a
given local mport device.
Alexandre Bounine <alexandre.bounine@idt.com>
Description:
(RO) reports RapidIO common transport system size:
+
0 = small (8-bit destination ID, max. 256 devices),
+
1 = large (16-bit destination ID, max. 65536 devices).
What: /sys/class/rapidio_port/rapidioN/port_destid
Contact: Matt Porter <mporter@kernel.crashing.org>,
Alexandre Bounine <alexandre.bounine@idt.com>
Description:
- (RO) reports RapidIO destination ID assigned to the given
- RapidIO mport device. If value 0xFFFFFFFF is returned this means
- that no valid destination ID have been assigned to the mport
- (yet). Normally, before enumeration/discovery have been executed
- only fabric enumerating mports have a valid destination ID
- assigned to them using "hdid=..." rapidio module parameter.
+
+(RO) reports RapidIO destination ID assigned to the given
+RapidIO mport device. If value 0xFFFFFFFF is returned this means
+that no valid destination ID have been assigned to the mport
+(yet). Normally, before enumeration/discovery have been executed
+only fabric enumerating mports have a valid destination ID
+assigned to them using "hdid=..." rapidio module parameter.
After enumeration or discovery was performed for a given mport device,
the corresponding subdirectory will also contain subdirectories for each
child RapidIO device connected to the mport.
The example below shows mport device subdirectory with several child RapidIO
-devices attached to it.
-
-[rio@rapidio ~]$ ls /sys/class/rapidio_port/rapidio0/ -l
-total 0
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0001
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0004
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0007
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0002
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0003
-drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0005
-lrwxrwxrwx 1 root root 0 Feb 11 15:11 device -> ../../../0000:01:00.0
--r--r--r-- 1 root root 4096 Feb 11 15:11 port_destid
-drwxr-xr-x 2 root root 0 Feb 11 15:11 power
-lrwxrwxrwx 1 root root 0 Feb 11 15:04 subsystem -> ../../../../../../class/rapidio_port
--r--r--r-- 1 root root 4096 Feb 11 15:11 sys_size
--rw-r--r-- 1 root root 4096 Feb 11 15:04 uevent
+devices attached to it::
+
+ [rio@rapidio ~]$ ls /sys/class/rapidio_port/rapidio0/ -l
+ total 0
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0001
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0004
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:e:0007
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0002
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0003
+ drwxr-xr-x 3 root root 0 Feb 11 15:10 00:s:0005
+ lrwxrwxrwx 1 root root 0 Feb 11 15:11 device -> ../../../0000:01:00.0
+ -r--r--r-- 1 root root 4096 Feb 11 15:11 port_destid
+ drwxr-xr-x 2 root root 0 Feb 11 15:11 power
+ lrwxrwxrwx 1 root root 0 Feb 11 15:04 subsystem -> ../../../../../../class/rapidio_port
+ -r--r--r-- 1 root root 4096 Feb 11 15:11 sys_size
+ -rw-r--r-- 1 root root 4096 Feb 11 15:04 uevent
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Reading this file returns a list of available protocols,
- something like:
+ something like::
+
"rc5 [rc6] nec jvc [sony]"
+
Enabled protocols are shown in [] brackets.
+
Writing "+proto" will add a protocol to the list of enabled
protocols.
+
Writing "-proto" will remove a protocol from the list of enabled
protocols.
+
Writing "proto" will enable only "proto".
+
Writing "none" will disable all protocols.
+
Write fails with EINVAL if an invalid protocol combination or
unknown protocol name is used.
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Sets the scancode filter expected value.
+
Use in combination with /sys/class/rc/rcN/filter_mask to set the
expected value of the bits set in the filter mask.
If the hardware supports it then scancodes which do not match
the filter will be ignored. Otherwise the write will fail with
an error.
+
This value may be reset to 0 if the current protocol is altered.
What: /sys/class/rc/rcN/filter_mask
of the scancode which should be compared against the expected
value. A value of 0 disables the filter to allow all valid
scancodes to be processed.
+
If the hardware supports it then scancodes which do not match
the filter will be ignored. Otherwise the write will fail with
an error.
+
This value may be reset to 0 if the current protocol is altered.
What: /sys/class/rc/rcN/wakeup_protocols
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Reading this file returns a list of available protocols to use
- for the wakeup filter, something like:
+ for the wakeup filter, something like::
+
"rc-5 nec nec-x rc-6-0 rc-6-6a-24 [rc-6-6a-32] rc-6-mce"
+
Note that protocol variants are listed, so "nec", "sony",
"rc-5", "rc-6" have their different bit length encodings
listed if available.
+
The enabled wakeup protocol is shown in [] brackets.
+
Only one protocol can be selected at a time.
+
Writing "proto" will use "proto" for wakeup events.
+
Writing "none" will disable wakeup.
+
Write fails with EINVAL if an invalid protocol combination or
unknown protocol name is used, or if wakeup is not supported by
the hardware.
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Sets the scancode wakeup filter expected value.
+
Use in combination with /sys/class/rc/rcN/wakeup_filter_mask to
set the expected value of the bits set in the wakeup filter mask
to trigger a system wake event.
+
If the hardware supports it and wakeup_filter_mask is not 0 then
scancodes which match the filter will wake the system from e.g.
suspend to RAM or power off.
+
Otherwise the write will fail with an error.
+
This value may be reset to 0 if the wakeup protocol is altered.
What: /sys/class/rc/rcN/wakeup_filter_mask
Contact: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Description:
Sets the scancode wakeup filter mask of bits to compare.
+
Use in combination with /sys/class/rc/rcN/wakeup_filter to set
the bits of the scancode which should be compared against the
expected value to trigger a system wake event.
+
If the hardware supports it and wakeup_filter_mask is not 0 then
scancodes which match the filter will wake the system from e.g.
suspend to RAM or power off.
+
Otherwise the write will fail with an error.
+
This value may be reset to 0 if the wakeup protocol is altered.
This will be one of the following strings:
- off
- on
- error
- fast
- normal
- idle
- standby
+ - off
+ - on
+ - error
+ - fast
+ - normal
+ - idle
+ - standby
"off" means the regulator is not supplying power to the
system.
This will be one of the following strings:
- 'voltage'
- 'current'
- 'unknown'
+ - 'voltage'
+ - 'current'
+ - 'unknown'
'voltage' means the regulator output voltage can be controlled
by software.
The opmode value can be one of the following strings:
- 'fast'
- 'normal'
- 'idle'
- 'standby'
- 'unknown'
+ - 'fast'
+ - 'normal'
+ - 'idle'
+ - 'standby'
+ - 'unknown'
The modes are described in include/linux/regulator/consumer.h
This will be one of the following strings:
- 'enabled'
- 'disabled'
- 'unknown'
+ - 'enabled'
+ - 'disabled'
+ - 'unknown'
'enabled' means the regulator is in bypass mode.
Reports the state of the remote processor, which will be one of:
- "offline"
- "suspended"
- "running"
- "crashed"
- "invalid"
+ - "offline"
+ - "suspended"
+ - "running"
+ - "crashed"
+ - "invalid"
"offline" means the remote processor is powered off.
Writing this file controls the state of the remote processor.
The following states can be written:
- "start"
- "stop"
+ - "start"
+ - "stop"
Writing "start" will attempt to start the processor running the
firmware indicated by, or written to,
Description: Provide information about RNBD-client.
All sysfs files that are not read-only provide the usage information on read:
- Example:
- # cat /sys/class/rnbd-client/ctl/map_device
+ Example::
- > Usage: echo "sessname=<name of the rtrs session> path=<[srcaddr,]dstaddr>
- > [path=<[srcaddr,]dstaddr>] device_path=<full path on remote side>
- > [access_mode=<ro|rw|migration>] > map_device
- >
- > addr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]
+ # cat /sys/class/rnbd-client/ctl/map_device
+
+ > Usage: echo "sessname=<name of the rtrs session> path=<[srcaddr,]dstaddr>
+ > [path=<[srcaddr,]dstaddr>] device_path=<full path on remote side>
+ > [access_mode=<ro|rw|migration>] > map_device
+ >
+ > addr ::= [ ip:<ipv4> | ip:<ipv6> | gid:<gid> ]
What: /sys/class/rnbd-client/ctl/map_device
Date: Feb 2020
KernelVersion: 5.7
Contact: Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
-Description: Expected format is the following:
+Description: Expected format is the following::
- sessname=<name of the rtrs session>
- path=<[srcaddr,]dstaddr> [path=<[srcaddr,]dstaddr> ...]
- device_path=<full path on remote side>
- [access_mode=<ro|rw|migration>]
+ sessname=<name of the rtrs session>
+ path=<[srcaddr,]dstaddr> [path=<[srcaddr,]dstaddr> ...]
+ device_path=<full path on remote side>
+ [access_mode=<ro|rw|migration>]
Where:
- sessname: accepts a string not bigger than 256 chars, which identifies
- a given session on the client and on the server.
- I.e. "clt_hostname-srv_hostname" could be a natural choice.
+ sessname:
+ accepts a string not bigger than 256 chars, which identifies
+ a given session on the client and on the server.
+ I.e. "clt_hostname-srv_hostname" could be a natural choice.
+
+ path:
+ describes a connection between the client and the server by
+ specifying destination and, when required, the source address.
+ The addresses are to be provided in the following format::
- path: describes a connection between the client and the server by
- specifying destination and, when required, the source address.
- The addresses are to be provided in the following format:
+ ip:<IPv6>
+ ip:<IPv4>
+ gid:<GID>
- ip:<IPv6>
- ip:<IPv4>
- gid:<GID>
+ for example::
- for example:
+ path=ip:10.0.0.66
- path=ip:10.0.0.66
The single addr is treated as the destination.
The connection will be established to this server from any client IP address.
- path=ip:10.0.0.66,ip:10.0.1.66
+ ::
+
+ path=ip:10.0.0.66,ip:10.0.1.66
+
First addr is the source address and the second is the destination.
If multiple "path=" options are specified multiple connection
will be established and data will be sent according to
the selected multipath policy (see RTRS mp_policy sysfs entry description).
- device_path: Path to the block device on the server side. Path is specified
- relative to the directory on server side configured in the
- 'dev_search_path' module parameter of the rnbd_server.
- The rnbd_server prepends the <device_path> received from client
- with <dev_search_path> and tries to open the
- <dev_search_path>/<device_path> block device. On success,
- a /dev/rnbd<N> device file, a /sys/block/rnbd_client/rnbd<N>/
- directory and an entry in /sys/class/rnbd-client/ctl/devices
- will be created.
+ device_path:
+ Path to the block device on the server side. Path is specified
+ relative to the directory on server side configured in the
+ 'dev_search_path' module parameter of the rnbd_server.
+ The rnbd_server prepends the <device_path> received from client
+ with <dev_search_path> and tries to open the
+ <dev_search_path>/<device_path> block device. On success,
+ a /dev/rnbd<N> device file, a /sys/block/rnbd_client/rnbd<N>/
+ directory and an entry in /sys/class/rnbd-client/ctl/devices
+ will be created.
If 'dev_search_path' contains '%SESSNAME%', then each session can
have different devices namespace, e.g. server was configured with
client has this string "sessname=blya device_path=sda", then server
will try to open: /run/rnbd-devs/blya/sda.
- access_mode: the access_mode parameter specifies if the device is to be
- mapped as "ro" read-only or "rw" read-write. The server allows
- a device to be exported in rw mode only once. The "migration"
- access mode has to be specified if a second mapping in read-write
- mode is desired.
+ access_mode:
+ the access_mode parameter specifies if the device is to be
+ mapped as "ro" read-only or "rw" read-write. The server allows
+ a device to be exported in rw mode only once. The "migration"
+ access mode has to be specified if a second mapping in read-write
+ mode is desired.
By default "rw" is used.
is the same as the device name. By extracting the last part of the
path the path to the device /dev/<dev-name> can be build.
- o /dev/block/$(cat /sys/class/rnbd-client/ctl/devices/<device_id>/dev)
+ * /dev/block/$(cat /sys/class/rnbd-client/ctl/devices/<device_id>/dev)
How to find the <device_id> of the device is described on the next
section.
The <device_id> of each device is created as follows:
- If the 'device_path' provided during mapping contains slashes ("/"),
- they are replaced by exclamation mark ("!") and used as as the
- <device_id>. Otherwise, the <device_id> will be the same as the
- "device_path" provided.
+ they are replaced by exclamation mark ("!") and used as as the
+ <device_id>. Otherwise, the <device_id> will be the same as the
+ "device_path" provided.
calibrate the AB8500.s 32KHz Real Time Clock.
Every 60 seconds the AB8500 will correct the RTC's value
by adding to it the value of this attribute.
+
The range of the attribute is -127 to +127 in units of
30.5 micro-seconds (half-parts-per-million of the 32KHz clock)
Users: The /vendor/st-ericsson/base_utilities/core/rtc_calibration
KernelVersion: 5.7
Contact: Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
Description: RW, adds a new path (connection) to an existing session. Expected format is the
- following:
+ following::
- <[source addr,]destination addr>
- *addr ::= [ ip:<ipv4|ipv6> | gid:<gid> ]
+ <[source addr,]destination addr>
+ *addr ::= [ ip:<ipv4|ipv6> | gid:<gid> ]
What: /sys/class/rtrs-client/<session-name>/max_reconnect_attempts
Date: Feb 2020
Description: Multipath policy specifies which path should be selected on each IO:
round-robin (0):
- select path in per CPU round-robin manner.
+ select path in per CPU round-robin manner.
min-inflight (1):
- select path with minimum inflights.
+ select path with minimum inflights.
What: /sys/class/rtrs-client/<session-name>/paths/
Date: Feb 2020
not the case, the processing of an I/O response could be processed on a
different CPU than where it was originally submitted. This file shows
how many interrupts where generated on a non expected CPU.
- "from:" is the CPU on which the IRQ was expected, but not generated.
- "to:" is the CPU on which the IRQ was generated, but not expected.
+
+ "from:"
+ is the CPU on which the IRQ was expected, but not generated.
+ "to:"
+ is the CPU on which the IRQ was generated, but not expected.
What: /sys/class/rtrs-client/<session-name>/paths/<src@dst>/stats/reconnects
Date: Feb 2020
KernelVersion: 5.7
Contact: Jack Wang <jinpu.wang@cloud.ionos.com> Danil Kipnis <danil.kipnis@cloud.ionos.com>
Description: Contains statistics regarding rdma operations and inflight operations.
- The output consists of 6 values:
+ The output consists of 6 values::
- <read-count> <read-total-size> <write-count> <write-total-size> \
- <inflights> <failovered>
+ <read-count> <read-total-size> <write-count> \
+ <write-total-size> <inflights> <failovered>
management) on top, which makes it match the Windows IRST (Intel
Rapid Storage Technology) driver settings. This setting is also
close to min_power, except that:
+
a) It does not use host-initiated slumber mode, but it does
- allow device-initiated slumber
+ allow device-initiated slumber
b) It does not enable low power device sleep mode (DevSlp).
What: /sys/class/scsi_host/hostX/em_message
protocol, writes and reads correspond to the LED message format
as defined in the AHCI spec.
- The user must turn sw_activity (under /sys/block/*/device/) OFF
- it they wish to control the activity LED via the em_message
+ The user must turn sw_activity (under `/sys/block/*/device/`)
+ OFF it they wish to control the activity LED via the em_message
file.
em_message_type: (RO) Displays the current enclosure management
attribute will not return until the operation has finished.
Valid values:
- - source (The port will behave as source only DFP port)
- - sink (The port will behave as sink only UFP port)
- - dual (The port will behave as dual-role-data and
+
+ ====== ==============================================
+ source (The port will behave as source only DFP port)
+ sink (The port will behave as sink only UFP port)
+ dual (The port will behave as dual-role-data and
dual-role-power port)
+ ====== ==============================================
What: /sys/class/typec/<port>/vconn_source
Date: April 2017
generates uevent KOBJ_CHANGE.
Valid values:
+
- "no" when the port is not the VCONN Source
- "yes" when the port is the VCONN Source
power operation mode should show "usb_power_delivery".
Valid values:
+
- default
- 1.5A
- 3.0A
Contact: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Description:
Shows type of the plug on the cable:
+
- type-a - Standard A
- type-b - Standard B
- type-c
<channel> <type> [<bpst offset>]
to start (or stop) scanning on a channel. <type> is one of:
- 0 - scan
- 1 - scan outside BP
- 2 - scan while inactive
- 3 - scanning disabled
- 4 - scan (with start time of <bpst offset>)
+
+ == =======================================
+ 0 scan
+ 1 scan outside BP
+ 2 scan while inactive
+ 3 scanning disabled
+ 4 scan (with start time of <bpst offset>)
+ == =======================================
What: /sys/class/uwb_rc/uwbN/mac_address
Date: July 2008
h/w strapping (for WDT2 only).
At alternate flash the 'access_cs0' sysfs node provides:
- ast2400: a way to get access to the primary SPI flash
+
+ ast2400:
+ a way to get access to the primary SPI flash
chip at CS0 after booting from the alternate
chip at CS1.
- ast2500: a way to restore the normal address mapping
+ ast2500:
+ a way to restore the normal address mapping
from (CS0->CS1, CS1->CS0) to (CS0->CS0,
CS1->CS1).
the form "<major>:<minor>". These links point to the
corresponding sysfs path for the given device.
- Example:
- $ readlink /sys/dev/block/8:32
- ../../block/sdc
+ Example::
+
+ $ readlink /sys/dev/block/8:32
+ ../../block/sdc
Entries in /sys/dev/char and /sys/dev/block will be
dynamically created and destroyed as devices enter and
block.
For example, on 4-die Xeon platform with up to 6 IIO stacks per
die and, therefore, 6 IIO PMON blocks per die, the mapping of
- IIO PMON block 0 exposes as the following:
+ IIO PMON block 0 exposes as the following::
- $ ls /sys/devices/uncore_iio_0/die*
- -r--r--r-- /sys/devices/uncore_iio_0/die0
- -r--r--r-- /sys/devices/uncore_iio_0/die1
- -r--r--r-- /sys/devices/uncore_iio_0/die2
- -r--r--r-- /sys/devices/uncore_iio_0/die3
+ $ ls /sys/devices/uncore_iio_0/die*
+ -r--r--r-- /sys/devices/uncore_iio_0/die0
+ -r--r--r-- /sys/devices/uncore_iio_0/die1
+ -r--r--r-- /sys/devices/uncore_iio_0/die2
+ -r--r--r-- /sys/devices/uncore_iio_0/die3
- $ tail /sys/devices/uncore_iio_0/die*
- ==> /sys/devices/uncore_iio_0/die0 <==
- 0000:00
- ==> /sys/devices/uncore_iio_0/die1 <==
- 0000:40
- ==> /sys/devices/uncore_iio_0/die2 <==
- 0000:80
- ==> /sys/devices/uncore_iio_0/die3 <==
- 0000:c0
+ $ tail /sys/devices/uncore_iio_0/die*
+ ==> /sys/devices/uncore_iio_0/die0 <==
+ 0000:00
+ ==> /sys/devices/uncore_iio_0/die1 <==
+ 0000:40
+ ==> /sys/devices/uncore_iio_0/die2 <==
+ 0000:80
+ ==> /sys/devices/uncore_iio_0/die3 <==
+ 0000:c0
- Which means:
- IIO PMU 0 on die 0 belongs to PCI RP on bus 0x00, domain 0x0000
- IIO PMU 0 on die 1 belongs to PCI RP on bus 0x40, domain 0x0000
- IIO PMU 0 on die 2 belongs to PCI RP on bus 0x80, domain 0x0000
- IIO PMU 0 on die 3 belongs to PCI RP on bus 0xc0, domain 0x0000
+ Which means::
+
+ IIO PMU 0 on die 0 belongs to PCI RP on bus 0x00, domain 0x0000
+ IIO PMU 0 on die 1 belongs to PCI RP on bus 0x40, domain 0x0000
+ IIO PMU 0 on die 2 belongs to PCI RP on bus 0x80, domain 0x0000
+ IIO PMU 0 on die 3 belongs to PCI RP on bus 0xc0, domain 0x0000
online/offline state of the memory section. When written,
root can toggle the the online/offline state of a removable
memory section (see removable file description above)
- using the following commands.
- # echo online > /sys/devices/system/memory/memoryX/state
- # echo offline > /sys/devices/system/memory/memoryX/state
+ using the following commands::
+
+ # echo online > /sys/devices/system/memory/memoryX/state
+ # echo offline > /sys/devices/system/memory/memoryX/state
For example, if /sys/devices/system/memory/memory22/removable
contains a value of 1 and
/sys/devices/system/memory/memory22/state contains the
string "online" the following command can be executed by
- by root to offline that section.
- # echo offline > /sys/devices/system/memory/memory22/state
+ by root to offline that section::
+
+ # echo offline > /sys/devices/system/memory/memory22/state
+
Users: hotplug memory remove tools
http://www.ibm.com/developerworks/wikis/display/LinuxP/powerpc-utils
For example, the following symbolic link is created for
memory section 9 on node0:
+
/sys/devices/system/memory/memory9/node0 -> ../../node/node0
points to the corresponding /sys/devices/system/memory/memoryY
memory section directory. For example, the following symbolic
link is created for memory section 9 on node0.
+
/sys/devices/system/node/node0/memory9 -> ../../memory/memory9
(RO) Hexadecimal bitmask of the TAD attributes are reported by
the platform firmware (see ACPI 6.2, section 9.18.2):
+ ======= ======================================================
BIT(0): AC wakeup implemented if set
BIT(1): DC wakeup implemented if set
BIT(2): Get/set real time features implemented if set
BIT(6): The AC timer wakes up from S5 if set
BIT(7): The DC timer wakes up from S4 if set
BIT(8): The DC timer wakes up from S5 if set
+ ======= ======================================================
The other bits are reserved.
timer status with the following meaning of bits (see ACPI 6.2,
Section 9.18.5):
+ ======= ======================================================
Bit(0): The timer has expired if set.
Bit(1): The timer has woken up the system from a sleep state
(S3 or S4/S5 if supported) if set.
+ ======= ======================================================
The other bits are reserved.
Contact: Fabien Chouteau <fabien.chouteau@barco.com>
Description:
Show the suspend state of an USB composite gadget.
- 1 -> suspended
- 0 -> resumed
+
+ - 1 -> suspended
+ - 0 -> resumed
(_UDC_ is the name of the USB Device Controller driver)
Storage mode.
Possible values are:
- 1 -> ignore the FUA flag
- 0 -> obey the FUA flag
+
+ - 1 -> ignore the FUA flag
+ - 0 -> obey the FUA flag
The protection has information embedded whether it blocks reads,
writes or both.
The result is:
- 0 -> the DPS is not keylocked
- 1 -> the DPS is keylocked
+
+ - 0 -> the DPS is not keylocked
+ - 1 -> the DPS is keylocked
+
Users: None identified so far.
What: /sys/devices/platform/docg3/f[0-3]_dps[01]_protection_key
Entering the correct value toggle the lock, and can be observed
through f[0-3]_dps[01]_is_keylocked.
Possible values are:
+
- 8 bytes
+
Typical values are:
+
- "00000000"
- "12345678"
+
Users: None identified so far.
Contact: openipmi-developer@lists.sourceforge.net
Description:
- idles: (RO) Number of times the interface was
+ ====================== ========================================
+ idles (RO) Number of times the interface was
idle while being polled.
- watchdog_pretimeouts: (RO) Number of watchdog pretimeouts.
+ watchdog_pretimeouts (RO) Number of watchdog pretimeouts.
- complete_transactions: (RO) Number of completed messages.
+ complete_transactions (RO) Number of completed messages.
- events: (RO) Number of IPMI events received from
+ events (RO) Number of IPMI events received from
the hardware.
- interrupts: (RO) Number of interrupts the driver
+ interrupts (RO) Number of interrupts the driver
handled.
- hosed_count: (RO) Number of times the hardware didn't
+ hosed_count (RO) Number of times the hardware didn't
follow the state machine.
- long_timeouts: (RO) Number of times the driver
+ long_timeouts (RO) Number of times the driver
requested a timer while nothing was in
progress.
- flag_fetches: (RO) Number of times the driver
+ flag_fetches (RO) Number of times the driver
requested flags from the hardware.
- attentions: (RO) Number of time the driver got an
+ attentions (RO) Number of time the driver got an
ATTN from the hardware.
- incoming_messages: (RO) Number of asynchronous messages
+ incoming_messages (RO) Number of asynchronous messages
received.
- short_timeouts: (RO) Number of times the driver
+ short_timeouts (RO) Number of times the driver
requested a timer while an operation was
in progress.
+ ====================== ========================================
What: /sys/devices/platform/ipmi_si.*/interrupts_enabled
KernelVersion: v4.15
Contact: openipmi-developer@lists.sourceforge.net
Description:
- hosed: (RO) Number of times the hardware didn't
+ ====================== ========================================
+ hosed (RO) Number of times the hardware didn't
follow the state machine.
- alerts: (RO) Number of alerts received.
+ alerts (RO) Number of alerts received.
- sent_messages: (RO) Number of total messages sent.
+ sent_messages (RO) Number of total messages sent.
- sent_message_parts: (RO) Number of message parts sent.
+ sent_message_parts (RO) Number of message parts sent.
Messages may be broken into parts if
they are long.
- received_messages: (RO) Number of message responses
+ received_messages (RO) Number of message responses
received.
- received_message_parts: (RO) Number of message fragments
+ received_message_parts (RO) Number of message fragments
received.
- events: (RO) Number of received events.
+ events (RO) Number of received events.
- watchdog_pretimeouts: (RO) Number of watchdog pretimeouts.
+ watchdog_pretimeouts (RO) Number of watchdog pretimeouts.
- flag_fetches: (RO) Number of times a flag fetch was
+ flag_fetches (RO) Number of times a flag fetch was
requested.
- send_retries: (RO) Number of time a message was
+ send_retries (RO) Number of time a message was
retried.
- receive_retries: (RO) Number of times the receive of a
+ receive_retries (RO) Number of times the receive of a
message was retried.
- send_errors: (RO) Number of times the send of a
+ send_errors (RO) Number of times the send of a
message failed.
- receive_errors: (RO) Number of errors in receiving
+ receive_errors (RO) Number of errors in receiving
messages.
+ ====================== ========================================
to overlay planes.
Selects the composition mode for the overlay. Possible values
- are
+ are:
- 0 - Alpha Blending
- 1 - ROP3
+ - 0 - Alpha Blending
+ - 1 - ROP3
What: /sys/devices/platform/sh_mobile_lcdc_fb.[0-3]/graphics/fb[0-9]/ovl_position
Date: May 2012
to overlay planes.
Stores the x,y overlay position on the display in pixels. The
- position format is `[0-9]+,[0-9]+'.
+ position format is `[0-9]+,[0-9]+`.
What: /sys/devices/platform/sh_mobile_lcdc_fb.[0-3]/graphics/fb[0-9]/ovl_rop3
Date: May 2012
b[15:0]
inform firmware the current software execution
stage.
+
+ == ===========================================
0 the first stage bootloader didn't run or
didn't reach the point of launching second
stage bootloader.
2 both first and second stage bootloader ran
and the operating system launch was
attempted.
+ == ===========================================
b[16]
+ == ===========================================
1 firmware to reset current image retry
counter.
0 no action.
+ == ===========================================
b[17]
+ == ===========================================
1 firmware to clear RSU log
0 no action.
+ == ===========================================
b[18]
this is negative logic
+
+ == ===========================================
1 no action
0 firmware record the notify code defined
in b[15:0].
+ == ===========================================
What: /sys/devices/platform/stratix10-rsu.0/dcmf0
Date: June 2020
The processor idle states which are available for use have the
following attributes:
- name: (RO) Name of the idle state (string).
+ ======== ==== =================================================
+ name: (RO) Name of the idle state (string).
latency: (RO) The latency to exit out of this idle state (in
- microseconds).
+ microseconds).
- power: (RO) The power consumed while in this idle state (in
- milliwatts).
+ power: (RO) The power consumed while in this idle state (in
+ milliwatts).
- time: (RO) The total time spent in this idle state (in microseconds).
+ time: (RO) The total time spent in this idle state
+ (in microseconds).
- usage: (RO) Number of times this state was entered (a count).
+ usage: (RO) Number of times this state was entered (a count).
- above: (RO) Number of times this state was entered, but the
- observed CPU idle duration was too short for it (a count).
+ above: (RO) Number of times this state was entered, but the
+ observed CPU idle duration was too short for it
+ (a count).
- below: (RO) Number of times this state was entered, but the
- observed CPU idle duration was too long for it (a count).
+ below: (RO) Number of times this state was entered, but the
+ observed CPU idle duration was too long for it
+ (a count).
+ ======== ==== =================================================
What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc
Date: February 2008
This switch controls the boost setting for the whole system.
Boosting allows the CPU and the firmware to run at a frequency
beyound it's nominal limit.
+
More details can be found in
Documentation/admin-guide/pm/cpufreq.rst
Description: Parameters for the CPU cache attributes
allocation_policy:
- - WriteAllocate: allocate a memory location to a cache line
- on a cache miss because of a write
- - ReadAllocate: allocate a memory location to a cache line
+ - WriteAllocate:
+ allocate a memory location to a cache line
+ on a cache miss because of a write
+ - ReadAllocate:
+ allocate a memory location to a cache line
on a cache miss because of a read
- - ReadWriteAllocate: both writeallocate and readallocate
+ - ReadWriteAllocate:
+ both writeallocate and readallocate
- attributes: LEGACY used only on IA64 and is same as write_policy
+ attributes:
+ LEGACY used only on IA64 and is same as write_policy
- coherency_line_size: the minimum amount of data in bytes that gets
+ coherency_line_size:
+ the minimum amount of data in bytes that gets
transferred from memory to cache
- level: the cache hierarchy in the multi-level cache configuration
+ level:
+ the cache hierarchy in the multi-level cache configuration
- number_of_sets: total number of sets in the cache, a set is a
+ number_of_sets:
+ total number of sets in the cache, a set is a
collection of cache lines with the same cache index
- physical_line_partition: number of physical cache line per cache tag
+ physical_line_partition:
+ number of physical cache line per cache tag
- shared_cpu_list: the list of logical cpus sharing the cache
+ shared_cpu_list:
+ the list of logical cpus sharing the cache
- shared_cpu_map: logical cpu mask containing the list of cpus sharing
+ shared_cpu_map:
+ logical cpu mask containing the list of cpus sharing
the cache
- size: the total cache size in kB
+ size:
+ the total cache size in kB
type:
- Instruction: cache that only holds instructions
- Data: cache that only caches data
- Unified: cache that holds both data and instructions
- ways_of_associativity: degree of freedom in placing a particular block
- of memory in the cache
+ ways_of_associativity:
+ degree of freedom in placing a particular block
+ of memory in the cache
write_policy:
- - WriteThrough: data is written to both the cache line
+ - WriteThrough:
+ data is written to both the cache line
and to the block in the lower-level memory
- - WriteBack: data is written only to the cache line and
+ - WriteBack:
+ data is written only to the cache line and
the modified cache line is written to main
memory only when it is replaced
throttle attributes exported in the 'throttle_stats' directory:
- turbo_stat : This file gives the total number of times the max
- frequency is throttled to lower frequency in turbo (at and above
- nominal frequency) range of frequencies.
+ frequency is throttled to lower frequency in turbo (at and above
+ nominal frequency) range of frequencies.
- sub_turbo_stat : This file gives the total number of times the
- max frequency is throttled to lower frequency in sub-turbo(below
- nominal frequency) range of frequencies.
+ max frequency is throttled to lower frequency in sub-turbo(below
+ nominal frequency) range of frequencies.
- unthrottle : This file gives the total number of times the max
- frequency is unthrottled after being throttled.
+ frequency is unthrottled after being throttled.
- powercap : This file gives the total number of times the max
- frequency is throttled due to 'Power Capping'.
+ frequency is throttled due to 'Power Capping'.
- overtemp : This file gives the total number of times the max
- frequency is throttled due to 'CPU Over Temperature'.
+ frequency is throttled due to 'CPU Over Temperature'.
- supply_fault : This file gives the total number of times the
- max frequency is throttled due to 'Power Supply Failure'.
+ max frequency is throttled due to 'Power Supply Failure'.
- overcurrent : This file gives the total number of times the
- max frequency is throttled due to 'Overcurrent'.
+ max frequency is throttled due to 'Overcurrent'.
- occ_reset : This file gives the total number of times the max
- frequency is throttled due to 'OCC Reset'.
+ frequency is throttled due to 'OCC Reset'.
The sysfs attributes representing different throttle reasons like
powercap, overtemp, supply_fault, overcurrent and occ_reset map to
Date: June 2016
Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org>
Description: AArch64 CPU registers
+
'identification' directory exposes the CPU ID registers for
- identifying model and revision of the CPU.
+ identifying model and revision of the CPU.
What: /sys/devices/system/cpu/cpu#/cpu_capacity
Date: December 2016
vulnerabilities. The output of those files reflects the
state of the CPUs in the system. Possible output values:
+ ================ ==============================================
"Not affected" CPU is not affected by the vulnerability
"Vulnerable" CPU is affected and no mitigation in effect
"Mitigation: $M" CPU is affected and mitigation $M is in effect
+ ================ ==============================================
See also: Documentation/admin-guide/hw-vuln/index.rst
control: Read/write interface to control SMT. Possible
values:
+ ================ =========================================
"on" SMT is enabled
"off" SMT is disabled
"forceoff" SMT is force disabled. Cannot be changed.
"notsupported" SMT is not supported by the CPU
"notimplemented" SMT runtime toggling is not
implemented for the architecture
+ ================ =========================================
If control status is "forceoff" or "notsupported" writes
are rejected.
Facility in POWER9 and newer processors. i.e., it is a Secure
Virtual Machine.
-What: /sys/devices/system/cpu/cpuX/purr
+What: /sys/devices/system/cpu/cpuX/purr
Date: Apr 2005
Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
Description: PURR ticks for this CPU since the system boot.
Description: The state file allows a means by which to change in and
out of Premium Real-Time Mode (PRTM), as well as the
ability to query the current state.
- 0 => PRTM off
- 1 => PRTM enabled
+
+ - 0 => PRTM off
+ - 1 => PRTM enabled
+
Users: The ibm-prtm userspace daemon uses this interface.
if DDR power rails will be kept powered during system suspend.
("on"/"1" = enabled, "off"/"0" = disabled).
Two types of power switches (or control signals) can be used:
+
A. With a momentary power switch (or pulse signal), DDR
Backup Mode is enabled by default when available, as the
PMIC will be configured only during system suspend.
B. With a toggle power switch (or level signal), the
following steps must be followed exactly:
+
1. Configure PMIC for backup mode, to change the role of
the accessory power switch from a power switch to a
wake-up switch,
3. Suspend system,
4. Switch accessory power switch on, to resume the
system.
+
DDR Backup Mode must be explicitly enabled by the user,
to invoke step 1.
+
See also Documentation/devicetree/bindings/mfd/bd9571mwv.txt.
Users: User space applications for embedded boards equipped with a
BD9571MWV PMIC.
Date: May 2014
Contact: klebers@linux.vnet.ibm.com
Description: Interface to trigger a PCIe card reset to reload the bitstream.
+
+ ::
+
sudo sh -c 'echo 1 > \
/sys/class/genwqe/genwqe0_card/reload_bitstream'
+
If successfully, the card will come back with the bitstream set
on 'next_bitstream'.
What: /sys/class/genwqe/genwqe<n>_card/device/sriov_numvfs
Date: Oct 2013
Contact: haver@linux.vnet.ibm.com
-Description: Enable VFs (1..15):
+Description: Enable VFs (1..15)::
+
sudo sh -c 'echo 15 > \
/sys/bus/pci/devices/0000\:1b\:00.0/sriov_numvfs'
- Disable VFs:
+
+ Disable VFs::
+
Write a 0 into the same sysfs entry.
Contact: linux-input@vger.kernel.org
Description: This controls if mouse clicks should be generated if the trackpoint is quickly pressed. How fast this press has to be
is being controlled by press_speed.
+
Values are 0 or 1.
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/dragging
Date: July 2011
Contact: linux-input@vger.kernel.org
Description: If this setting is enabled, it is possible to do dragging by pressing the trackpoint. This requires press_to_select to be enabled.
+
Values are 0 or 1.
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/release_to_select
Contact: linux-input@vger.kernel.org
Description: This setting controls if the mouse click events generated by pressing the trackpoint (if press_to_select is enabled) generate
a left or right mouse button click.
+
Values are 0 or 1.
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/sensitivity
Date: July 2011
Contact: linux-input@vger.kernel.org
Description: This setting controls how fast the trackpoint needs to be pressed to generate a mouse click if press_to_select is enabled.
+
Values are decimal integers from 1 (slowest) to 255 (fastest).
+
Applies to Thinkpad USB Keyboard with TrackPoint.
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/fn_lock
Date: July 2014
Contact: linux-input@vger.kernel.org
Description: This setting controls whether Fn Lock is enabled on the keyboard (i.e. if F1 is Mute or F1)
+
Values are 0 or 1
+
Applies to ThinkPad Compact (USB|Bluetooth) Keyboard with TrackPoint.
Contact: Michal Malý <madcatxster@devoid-pointer.net>
Description: Displays a set of alternate modes supported by a wheel. Each
mode is listed as follows:
+
Tag: Mode Name
+
Currently active mode is marked with an asterisk. List also
contains an abstract item "native" which always denotes the
native mode of the wheel. Echoing the mode tag switches the
This entry is not created for devices that have only one mode.
Currently supported mode switches:
- Driving Force Pro:
+
+ Driving Force Pro::
+
DF-EX --> DFP
- G25:
+ G25::
+
DF-EX --> DFP --> G25
- G27:
+ G27::
+
DF-EX <*> DFP <-> G25 <-> G27
DF-EX <*--------> G25 <-> G27
DF-EX <*----------------> G27
- G29:
+ G29::
+
DF-EX <*> DFP <-> G25 <-> G27 <-> G29
DF-EX <*--------> G25 <-> G27 <-> G29
DF-EX <*----------------> G27 <-> G29
DF-EX <*------------------------> G29
- DFGT:
+ DFGT::
+
DF-EX <*> DFP <-> DFGT
DF-EX <*--------> DFGT
Description:
Threholds to override activation slack.
- activation_width: (RW) Width threshold to immediately
+ ================= =====================================
+ activation_width (RW) Width threshold to immediately
start processing touch events.
- activation_height: (RW) Height threshold to immediately
+ activation_height (RW) Height threshold to immediately
start processing touch events.
-
+ ================= =====================================
What: /sys/bus/hid/drivers/ntrig/<dev>/min_width
What: /sys/bus/hid/drivers/ntrig/<dev>/min_height
Description:
Minimum size contact accepted.
- min_width: (RW) Minimum touch contact width to decide
+ ========== ===========================================
+ min_width (RW) Minimum touch contact width to decide
activation and activity.
- min_height: (RW) Minimum touch contact height to decide
+ min_height (RW) Minimum touch contact height to decide
activation and activity.
+ ========== ===========================================
What: /sys/bus/hid/drivers/ntrig/<dev>/sensor_physical_width
Contact: Stefan Achatz <erazor_de@users.sourceforge.net>
Description: It is possible to switch the dpi setting of the mouse with the
press of a button.
+
When read, this file returns the raw number of the actual dpi
setting reported by the mouse. This number has to be further
processed to receive the real dpi value:
+ ===== =====
VALUE DPI
+ ===== =====
1 800
2 1200
3 1600
4 2000
5 2400
6 3200
+ ===== =====
This file is readonly.
Users: http://roccat.sourceforge.net
Date: March 2010
Contact: Stefan Achatz <erazor_de@users.sourceforge.net>
Description: When read, this file returns the number of the actual profile.
+
This file is readonly.
Users: http://roccat.sourceforge.net
further usage in other programs. To receive the real version
number the decimal point has to be shifted 2 positions to the
left. E.g. a returned value of 138 means 1.38
+
This file is readonly.
Users: http://roccat.sourceforge.net
press of a button. A profile holds information like button
mappings, sensitivity, the colors of the 5 leds and light
effects.
+
When read, these files return the respective profile. The
returned data is 975 bytes in size.
+
When written, this file lets one write the respective profile
data back to the mouse. The data has to be 975 bytes long.
+
The mouse will reject invalid data, whereas the profile number
stored in the profile doesn't need to fit the number of the
store.
Description: When read, this file returns the settings stored in the mouse.
The size of the data is 36 bytes and holds information like the
startup_profile, tcu state and calibration_data.
+
When written, this file lets write settings back to the mouse.
The data has to be 36 bytes long. The mouse will reject invalid
data.
Date: March 2010
Contact: Stefan Achatz <erazor_de@users.sourceforge.net>
Description: The integer value of this attribute ranges from 1 to 5.
+
When read, this attribute returns the number of the profile
that's active when the mouse is powered on.
+
When written, this file sets the number of the startup profile
and the mouse activates this profile immediately.
Users: http://roccat.sourceforge.net
calibrate the laser power to fit the mousepad surface.
When read, this file returns the current state of the TCU,
where 0 means off and 1 means on.
+
Writing 0 in this file will switch the TCU off.
+
Writing 1 in this file will start the calibration which takes
around 6 seconds to complete and activates the TCU.
+
Users: http://roccat.sourceforge.net
What: /sys/bus/usb/devices/<busnum>-<devnum>:<config num>.<interface num>/<hid-bus>:<vendor-id>:<product-id>.<num>/kone/roccatkone<minor>/weight
and its value can be read out. When read, this file returns the
raw value returned by the mouse which eases further processing
in other software.
+
The values map to the weights as follows:
+ ===== ======
VALUE WEIGHT
+ ===== ======
0 none
1 5g
2 10g
3 15g
4 20g
+ ===== ======
This file is readonly.
Users: http://roccat.sourceforge.net
the official Nintendo Nunchuck extension and classic is the
Nintendo Classic Controller extension. The motionp extension can
be combined with the other two.
+
Starting with kernel-version 3.11 Motion Plus hotplugging is
supported and if detected, it's no longer reported as static
extension. You will get uevent notifications for the motion-plus
Other strings for each device-type are available and may be
added if new device-specific detections are added.
Currently supported are:
- gen10: First Wii Remote generation
- gen20: Second Wii Remote Plus generation (builtin MP)
+
+ ============= =======================================
+ gen10: First Wii Remote generation
+ gen20: Second Wii Remote Plus generation
+ (builtin MP)
balanceboard: Wii Balance Board
+ ============= =======================================
What: /sys/bus/hid/drivers/wiimote/<dev>/bboard_calib
Date: May 2013
First, 0kg values for all 4 sensors are written, followed by the
17kg values for all 4 sensors and last the 34kg values for all 4
sensors.
+
Calibration data is already applied by the kernel to all input
values but may be used by user-space to perform other
transformations.
is prefixed with a +/-. Each value is a signed 16bit number.
Data is encoded as decimal numbers and specifies the offsets of
the analog sticks of the pro-controller.
+
Calibration data is already applied by the kernel to all input
values but may be used by user-space to perform other
transformations.
+
Calibration data is detected by the kernel during device setup.
You can write "scan\n" into this file to re-trigger calibration.
You can also write data directly in the form "x1:y1 x2:y2" to
Description: Reports the firmware version provided by the touchscreen, for example "00_T6" on a EXC80H60
Access: Read
+
Valid values: Represented as string
What: /sys/bus/i2c/devices/xxx/model
Description: Reports the model identification provided by the touchscreen, for example "Orion_1320" on a EXC80H60
Access: Read
+
Valid values: Represented as string
Description: read-only access to the efuse on the Ingenic JZ4780 SoC
The SoC has a one time programmable 8K efuse that is
split into segments. The driver supports read only.
- The segments are
+ The segments are:
+
+ ===== ======== =================
0x000 64 bit Random Number
0x008 128 bit Ingenic Chip ID
0x018 128 bit Customer ID
0x1E0 8 bit Protect Segment
0x1E1 2296 bit HDMI Key
0x300 2048 bit Security boot key
+ ===== ======== =================
+
Users: any user space application which wants to read the Chip
and Customer ID
the format of DDDD:BB:DD.F-REG:SIZE:MASK will allow the guest
to write and read from the PCI device. That is Domain:Bus:
Device.Function-Register:Size:Mask (Domain is optional).
- For example:
- #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
+ For example::
+
+ #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
+
will allow the guest to read and write to the configuration
register 0x0E.
their fans quiet at all costs. Reading from this file
will show the current performance level. Writing to the
file can change this value.
+
Valid options:
- "silent"
- "normal"
- "overclock"
+ - "silent"
+ - "normal"
+ - "overclock"
+
Note that not all laptops support all of these options.
Specifically, not all support the "overclock" option,
and it's still unknown if this value even changes
Description: Max battery charge level can be modified, battery cycle
life can be extended by reducing the max battery charge
level.
- 0 means normal battery mode (100% charge)
- 1 means battery life extender mode (80% charge)
+
+ - 0 means normal battery mode (100% charge)
+ - 1 means battery life extender mode (80% charge)
What: /sys/devices/platform/samsung/usb_charge
Date: December 1, 2011
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the keyboard backlight operation mode, valid
values are:
+
* 0x1 -> FN-Z
* 0x2 -> AUTO (also called TIMER)
* 0x8 -> ON
* 0x10 -> OFF
+
Note that from kernel 3.16 onwards this file accepts all listed
parameters, kernel 3.15 only accepts the first two (FN-Z and
AUTO).
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This files controls the status of the touchpad and pointing
stick (if available), valid values are:
+
* 0 -> OFF
* 1 -> ON
+
Users: KToshiba
What: /sys/devices/LNXSYSTM:00/LNXSYBUS:00/TOS{1900,620{0,7,8}}:00/available_kbd_modes
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file shows the supported keyboard backlight modes
the system supports, which can be:
+
* 0x1 -> FN-Z
* 0x2 -> AUTO (also called TIMER)
* 0x8 -> ON
* 0x10 -> OFF
+
Note that not all keyboard types support the listed modes.
See the entry named "available_kbd_modes"
Users: KToshiba
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file shows the current keyboard backlight type,
which can be:
+
* 1 -> Type 1, supporting modes FN-Z and AUTO
* 2 -> Type 2, supporting modes TIMER, ON and OFF
Users: KToshiba
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the USB Sleep & Charge charging mode, which
can be:
+
* 0 -> Disabled (0x00)
* 1 -> Alternate (0x09)
* 2 -> Auto (0x21)
* 3 -> Typical (0x11)
+
Note that from kernel 4.1 onwards this file accepts all listed
values, kernel 4.0 only supports the first three.
Note that this feature only works when connected to power, if
Description: This file controls the USB Sleep Functions under battery, and
set the level at which point they will be disabled, accepted
values can be:
+
* 0 -> Disabled
* 1-100 -> Battery level to disable sleep functions
+
Currently it prints two values, the first one indicates if the
feature is enabled or disabled, while the second one shows the
current battery level set.
KernelVersion: 4.0
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the USB Rapid Charge state, which can be:
+
* 0 -> Disabled
* 1 -> Enabled
+
Note that toggling this value requires a reboot for changes to
take effect.
Users: KToshiba
KernelVersion: 4.0
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the Sleep & Music state, which values can be:
+
* 0 -> Disabled
* 1 -> Enabled
+
Note that this feature only works when connected to power, if
you want to use it under battery, see the entry named
"sleep_functions_on_battery"
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the state of the internal fan, valid
values are:
+
* 0 -> OFF
* 1 -> ON
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the Special Functions (hotkeys) operation
mode, valid values are:
+
* 0 -> Normal Operation
* 1 -> Special Functions
+
In the "Normal Operation" mode, the F{1-12} keys are as usual
and the hotkeys are accessed via FN-F{1-12}.
In the "Special Functions" mode, the F{1-12} keys trigger the
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls whether the laptop should turn ON whenever
the LID is opened, valid values are:
+
* 0 -> Disabled
* 1 -> Enabled
+
Note that toggling this value requires a reboot for changes to
take effect.
Users: KToshiba
KernelVersion: 4.0
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the USB 3 functionality, valid values are:
+
* 0 -> Disabled (Acts as a regular USB 2)
* 1 -> Enabled (Full USB 3 functionality)
+
Note that toggling this value requires a reboot for changes to
take effect.
Users: KToshiba
Reading this file prints two values, the first is the actual cooling method
and the second is the maximum cooling method supported.
When the maximum cooling method is ONE, valid values are:
+
* 0 -> Maximum Performance
* 1 -> Battery Optimized
+
When the maximum cooling method is TWO, valid values are:
+
* 0 -> Maximum Performance
* 1 -> Performance
* 2 -> Battery Optimized
+
Users: KToshiba
Contact: Azael Avalos <coproscefalo@gmail.com>
Description: This file controls the built-in accelerometer protection level,
valid values are:
+
* 0 -> Disabled
* 1 -> Low
* 2 -> Medium
* 3 -> High
+
The default potection value is set to 2 (Medium).
Users: KToshiba
Description: This file shows the device type. This is one of the UFS
device descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/device_class
Description: This file shows the device class. This is one of the UFS
device descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/device_sub_class
Description: This file shows the UFS storage subclass. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/protocol
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/number_of_luns
Description: This file shows number of logical units. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/number_of_wluns
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/boot_enable
enabled for boot. This is one of the UFS device descriptor
parameters. The full information about the descriptor could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/descriptor_access_enable
of the boot sequence. This is one of the UFS device descriptor
parameters. The full information about the descriptor could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/initial_power_mode
device initialization or hardware reset. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/high_priority_lun
Description: This file shows the high priority lun. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/secure_removal_type
Description: This file shows the secure removal type. This is one of
the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/support_security_lun
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/bkops_termination_latency
latency. This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/initial_active_icc_level
Description: This file shows the initial active ICC level. This is one
of the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/specification_version
Description: This file shows the specification version. This is one
of the UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/manufacturing_date
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/manufacturer_id
Description: This file shows the manufacturee ID. This is one of the
UFS device descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/rtt_capability
supported by the device. This is one of the UFS device
descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/rtc_update
clock update. This is one of the UFS device descriptor
parameters. The full information about the descriptor
could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/ufs_features
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be
found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/ffu_timeout
Description: This file shows the FFU timeout. This is one of the
UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/queue_depth
Description: This file shows the device queue depth. This is one of the
UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/device_version
Description: This file shows the device version. This is one of the
UFS device descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/number_of_secure_wpa
supported by the device. This is one of the UFS device
descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/psa_max_data_size
This is one of the UFS device descriptor parameters.
The full information about the descriptor could be found
at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/psa_state_timeout
in PSA state. This is one of the UFS device descriptor
parameters. The full information about the descriptor could
be found at UFS specifications 2.1.
+
The file is read only.
This is one of the UFS interconnect descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/interconnect_descriptor/mphy_version
This is one of the UFS interconnect descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_number_of_luns
supported by the UFS device. This is one of the UFS
geometry descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/segment_size
Description: This file shows the segment size. This is one of the UFS
geometry descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/allocation_unit_size
Description: This file shows the allocation unit size. This is one of
the UFS geometry descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/min_addressable_block_size
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/optimal_read_block_size
of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/optimal_write_block_size
of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_in_buffer_size
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_out_buffer_size
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at UFS
specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/rpmb_rw_size
in Security Protocol In/Out. This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/dyn_capacity_resource_policy
is one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/data_ordering
This is one of the UFS geometry descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/max_number_of_contexts
are supported by the device. This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/sys_data_tag_unit_size
Description: This file shows system data tag unit size. This is one of
the UFS geometry descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/sys_data_tag_resource_size
This is one of the UFS geometry descriptor parameters.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/secure_removal_types
one of the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/memory_types
the UFS geometry descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/*_memory_max_alloc_units
enhanced type 1-4). This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/*_memory_capacity_adjustment_factor
enhanced type 1-4). This is one of the UFS geometry
descriptor parameters. The full information about the
descriptor could be found at UFS specifications 2.1.
+
The file is read only.
of the UFS health descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/health_descriptor/life_time_estimation_a
(method a). This is one of the UFS health descriptor
parameters. The full information about the descriptor
could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/health_descriptor/life_time_estimation_b
(method b). This is one of the UFS health descriptor
parameters. The full information about the descriptor
could be found at UFS specifications 2.1.
+
The file is read only.
active ICC levels from 0 to 15. This is one of the UFS
power descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
Description: This file contains a device manufactureer name string.
The full information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/product_name
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file contains a product name string. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/oem_id
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file contains a OEM ID string. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/serial_number
Description: This file contains a device serial number string. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/string_descriptors/product_revision
Description: This file contains a product revision string. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
Description: This file shows boot LUN information. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/lun_write_protect
Description: This file shows LUN write protection status. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/lun_queue_depth
Description: This file shows LUN queue depth. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/psa_sensitive
Description: This file shows PSA sensitivity. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/lun_memory_type
Description: This file shows LUN memory type. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/data_reliability
occurs during a write operation. This is one of the UFS
unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/logical_block_size
(calculated as an exponent with base 2). This is one of
the UFS unit descriptor parameters. The full information about
the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/logical_block_count
This is one of the UFS unit descriptor parameters. The full
information about the descriptor could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/erase_block_size
Description: This file shows the erase block size. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/provisioning_type
Description: This file shows the thin provisioning type. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/physical_memory_resourse_count
Description: This file shows the total physical memory resources. This is
one of the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/context_capabilities
Description: This file shows the context capabilities. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/large_unit_granularity
Description: This file shows the granularity of the LUN. This is one of
the UFS unit descriptor parameters. The full information
about the descriptor could be found at UFS specifications 2.1.
+
The file is read only.
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file shows the device init status. The full information
about the flag could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/permanent_wpe
Description: This file shows whether permanent write protection is enabled.
The full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/power_on_wpe
logical units configured as power on write protected. The
full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/bkops_enable
Description: This file shows whether the device background operations are
enabled. The full information about the flag could be
found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/life_span_mode_enable
Description: This file shows whether the device life span mode is enabled.
The full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/phy_resource_removal
Description: This file shows whether physical resource removal is enable.
The full information about the flag could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/busy_rtc
Description: This file shows whether the device is executing internal
operation related to real time clock. The full information
about the flag could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/disable_fw_update
Description: This file shows whether the device FW update is permanently
disabled. The full information about the flag could be found
at UFS specifications 2.1.
+
The file is read only.
Description: This file provides the boot lun enabled UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/current_power_mode
Description: This file provides the current power mode UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/active_icc_level
Description: This file provides the active icc level UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/ooo_data_enabled
Description: This file provides the out of order data transfer enabled UFS
device attribute. The full information about the attribute
could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/bkops_status
Description: This file provides the background operations status UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/purge_status
Description: This file provides the purge operation status UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/max_data_in_size
Description: This file shows the maximum data size in a DATA IN
UPIU. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/max_data_out_size
Description: This file shows the maximum number of bytes that can be
requested with a READY TO TRANSFER UPIU. The full information
about the attribute could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/reference_clock_frequency
Description: This file provides the reference clock frequency UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/configuration_descriptor_lock
outstanding RTTs in device that is allowed. The full
information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/exception_event_control
Description: This file provides the exception event control UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/exception_event_status
Description: This file provides the exception event status UFS device
attribute. The full information about the attribute could
be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/ffu_status
Description: This file provides the ffu status UFS device attribute.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/psa_state
Contact: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Description: This file show the PSA feature status. The full information
about the attribute could be found at UFS specifications 2.1.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/psa_data_size
load to all logical units in pre-soldering state.
The full information about the attribute could be found at
UFS specifications 2.1.
+
The file is read only.
to be removed from the physical memory resources pool of
the particular logical unit. The full information about
the attribute could be found at UFS specifications 2.1.
+
The file is read only.
Description: This entry could be used to set or show the UFS device
runtime power management level. The current driver
implementation supports 6 levels with next target states:
- 0 - an UFS device will stay active, an UIC link will
- stay active
- 1 - an UFS device will stay active, an UIC link will
- hibernate
- 2 - an UFS device will moved to sleep, an UIC link will
- stay active
- 3 - an UFS device will moved to sleep, an UIC link will
- hibernate
- 4 - an UFS device will be powered off, an UIC link will
- hibernate
- 5 - an UFS device will be powered off, an UIC link will
- be powered off
+
+ == ====================================================
+ 0 an UFS device will stay active, an UIC link will
+ stay active
+ 1 an UFS device will stay active, an UIC link will
+ hibernate
+ 2 an UFS device will moved to sleep, an UIC link will
+ stay active
+ 3 an UFS device will moved to sleep, an UIC link will
+ hibernate
+ 4 an UFS device will be powered off, an UIC link will
+ hibernate
+ 5 an UFS device will be powered off, an UIC link will
+ be powered off
+ == ====================================================
What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_dev_state
Date: February 2018
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target power mode of an UFS device
for the chosen runtime power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_link_state
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target state of an UFS UIC link
for the chosen runtime power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/spm_lvl
Description: This entry could be used to set or show the UFS device
system power management level. The current driver
implementation supports 6 levels with next target states:
- 0 - an UFS device will stay active, an UIC link will
- stay active
- 1 - an UFS device will stay active, an UIC link will
- hibernate
- 2 - an UFS device will moved to sleep, an UIC link will
- stay active
- 3 - an UFS device will moved to sleep, an UIC link will
- hibernate
- 4 - an UFS device will be powered off, an UIC link will
- hibernate
- 5 - an UFS device will be powered off, an UIC link will
- be powered off
+
+ == ====================================================
+ 0 an UFS device will stay active, an UIC link will
+ stay active
+ 1 an UFS device will stay active, an UIC link will
+ hibernate
+ 2 an UFS device will moved to sleep, an UIC link will
+ stay active
+ 3 an UFS device will moved to sleep, an UIC link will
+ hibernate
+ 4 an UFS device will be powered off, an UIC link will
+ hibernate
+ 5 an UFS device will be powered off, an UIC link will
+ be powered off
+ == ====================================================
What: /sys/bus/platform/drivers/ufshcd/*/spm_target_dev_state
Date: February 2018
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target power mode of an UFS device
for the chosen system power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/spm_target_link_state
Contact: Subhash Jadavani <subhashj@codeaurora.org>
Description: This entry shows the target state of an UFS UIC link
for the chosen system power management level.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_presv_us_en
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows if preserve user-space was configured
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_shared_alloc_units
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the shared allocated units of WB buffer
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_type
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the configured WB type.
0x1 for shared buffer mode. 0x0 for dedicated buffer mode.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_buff_cap_adj
buffer mode.
The value of this parameter is 3 for TLC NAND when SLC mode
is used as WriteBooster Buffer. 2 for MLC NAND.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_max_alloc_units
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the Maximum total WriteBooster Buffer size
which is supported by the entire device.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_max_wb_luns
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the maximum number of luns that can support
WriteBooster.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_sup_red_type
preserve user space type.
02h: Device can be configured in either user space
reduction type or preserve user space type.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_sup_wb_type
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: The supportability of WriteBooster Buffer type.
- 00h: LU based WriteBooster Buffer configuration
- 01h: Single shared WriteBooster Buffer
- configuration
- 02h: Supporting both LU based WriteBooster
- Buffer and Single shared WriteBooster Buffer
- configuration
+
+ === ==========================================================
+ 00h LU based WriteBooster Buffer configuration
+ 01h Single shared WriteBooster Buffer configuration
+ 02h Supporting both LU based WriteBooster.
+ Buffer and Single shared WriteBooster Buffer configuration
+ === ==========================================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_enable
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the status of WriteBooster.
- 0: WriteBooster is not enabled.
- 1: WriteBooster is enabled
+
+ == ============================
+ 0 WriteBooster is not enabled.
+ 1 WriteBooster is enabled
+ == ============================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_flush_en
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows if flush is enabled.
- 0: Flush operation is not performed.
- 1: Flush operation is performed.
+
+ == =================================
+ 0 Flush operation is not performed.
+ 1 Flush operation is performed.
+ == =================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_flush_during_h8
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: Flush WriteBooster Buffer during hibernate state.
- 0: Device is not allowed to flush the
- WriteBooster Buffer during link hibernate
- state.
- 1: Device is allowed to flush the
- WriteBooster Buffer during link hibernate
- state
+
+ == =================================================
+ 0 Device is not allowed to flush the
+ WriteBooster Buffer during link hibernate state.
+ 1 Device is allowed to flush the
+ WriteBooster Buffer during link hibernate state.
+ == =================================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_avail_buf
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the amount of unused WriteBooster buffer
available.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_cur_buf
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the amount of unused current buffer.
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_flush_status
Date: June 2020
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the flush operation status.
- 00h: idle
- 01h: Flush operation in progress
- 02h: Flush operation stopped prematurely.
- 03h: Flush operation completed successfully
- 04h: Flush operation general failure
+
+
+ === ======================================
+ 00h idle
+ 01h Flush operation in progress
+ 02h Flush operation stopped prematurely.
+ 03h Flush operation completed successfully
+ 04h Flush operation general failure
+ === ======================================
+
The file is read only.
What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_life_time_est
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows an indication of the WriteBooster Buffer
lifetime based on the amount of performed program/erase cycles
- 01h: 0% - 10% WriteBooster Buffer life time used
+
+ === =============================================
+ 01h 0% - 10% WriteBooster Buffer life time used
...
- 0Ah: 90% - 100% WriteBooster Buffer life time used
+ 0Ah 90% - 100% WriteBooster Buffer life time used
+ === =============================================
+
The file is read only.
What: /sys/class/scsi_device/*/device/unit_descriptor/wb_buf_alloc_units
Contact: Asutosh Das <asutoshd@codeaurora.org>
Description: This entry shows the configured size of WriteBooster buffer.
0400h corresponds to 4GB.
+
The file is read only.
Description: When written, this file sets the I2C speed on the connected
DS28E17 chip. When read, it reads the current setting from
the DS28E17 chip.
+
Valid values: 100, 400, 900 [kBaud].
+
Default 100, can be set by w1_ds28e17.speed= module parameter.
Users: w1_ds28e17 driver
the busy timeout for I2C operations on the connected DS28E17
chip. When read, returns the current setting.
Valid values: 1 to 9.
+
Default 1, can be set by w1_ds28e17.stretch= module parameter.
Users: w1_ds28e17 driver
device data to its embedded EEPROM, either restore data
embedded in device EEPROM. Be aware that devices support
limited EEPROM writing cycles (typical 50k)
+
* 'save': save device RAM to EEPROM
* 'restore': restore EEPROM data in device RAM
+
Users: any user space application which wants to communicate with
w1_term device
Contact: Akira Shimahara <akira215corp@gmail.com>
Description:
(RO) return the power status by asking the device
+
* '0': device parasite powered
* '1': device externally powered
* '-xx': xx is kernel error when reading power status
+
Users: any user space application which wants to communicate with
w1_term device
will be changed only in device RAM, so it will be cleared when
power is lost. Trigger a 'save' to EEPROM command to keep
values after power-on. Read or write are :
+
* '9..14': device resolution in bit
- or resolution to set in bit
+ or resolution to set in bit
* '-xx': xx is kernel error when reading the resolution
* Anything else: do nothing
+
Some DS18B20 clones are fixed in 12-bit resolution, so the
actual resolution is read back from the chip and verified. Error
is reported if the results differ.
Contact: Akira Shimahara <akira215corp@gmail.com>
Description:
(RO) return the temperature in 1/1000 degC.
+
* If a bulk read has been triggered, it will directly
- return the temperature computed when the bulk read
- occurred, if available. If not yet available, nothing
- is returned (a debug kernel message is sent), you
- should retry later on.
+ return the temperature computed when the bulk read
+ occurred, if available. If not yet available, nothing
+ is returned (a debug kernel message is sent), you
+ should retry later on.
* If no bulk read has been triggered, it will trigger
- a conversion and send the result. Note that the
- conversion duration depend on the resolution (if
- device support this feature). It takes 94ms in 9bits
- resolution, 750ms for 12bits.
+ a conversion and send the result. Note that the
+ conversion duration depend on the resolution (if
+ device support this feature). It takes 94ms in 9bits
+ resolution, 750ms for 12bits.
+
Users: any user space application which wants to communicate with
w1_term device
(RW) return the temperature in 1/1000 degC.
*read*: return 2 lines with the hexa output data sent on the
bus, return the CRC check and temperature in 1/1000 degC
- *write* :
+ *write*:
+
* '0' : save the 2 or 3 bytes to the device EEPROM
- (i.e. TH, TL and config register)
+ (i.e. TH, TL and config register)
* '9..14' : set the device resolution in RAM
- (if supported)
+ (if supported)
* Anything else: do nothing
+
refer to Documentation/w1/slaves/w1_therm.rst for detailed
information.
Users: any user space application which wants to communicate with
Contact: Akira Shimahara <akira215corp@gmail.com>
Description:
(RW) trigger a bulk read conversion. read the status
+
*read*:
- * '-1': conversion in progress on at least 1 sensor
- * '1' : conversion complete but at least one sensor
+ * '-1':
+ conversion in progress on at least 1 sensor
+ * '1' :
+ conversion complete but at least one sensor
value has not been read yet
- * '0' : no bulk operation. Reading temperature will
+ * '0' :
+ no bulk operation. Reading temperature will
trigger a conversion on each device
- *write*: 'trigger': trigger a bulk read on all supporting
+
+ *write*:
+ 'trigger': trigger a bulk read on all supporting
devices on the bus
+
Note that if a bulk read is sent but one sensor is not read
immediately, the next access to temperature on this device
will return the temperature measured at the time of issue
reset to default (datasheet) conversion time for a new
resolution.
- *read*: Actual conversion time in milliseconds. *write*:
- '0': Set the default conversion time from the datasheet.
- '1': Measure and set the conversion time. Make a single
+ *read*:
+ Actual conversion time in milliseconds.
+
+ *write*:
+ * '0':
+ Set the default conversion time from the datasheet.
+ * '1':
+ Measure and set the conversion time. Make a single
temperature conversion, measure an actual value.
Increase it by 20% for temperature range. A new
conversion time can be obtained by reading this
same attribute.
- other positive value:
+ * other positive value:
Set the conversion time in milliseconds.
Users: An application using the w1_term device
(RW) Control optional driver settings.
Bit masks to read/write (bitwise OR):
- 1: Enable check for conversion success. If byte 6 of
+ == ============================================================
+ 1 Enable check for conversion success. If byte 6 of
scratchpad memory is 0xC after conversion, and
temperature reads 85.00 (powerup value) or 127.94
(insufficient power) - return a conversion error.
- 2: Enable poll for conversion completion. Generate read cycles
+ 2 Enable poll for conversion completion. Generate read cycles
after the conversion start and wait for 1's. In parasite
power mode this feature is not available.
+ == ============================================================
+
+ *read*:
+ Currently selected features.
- *read*: Currently selected features.
- *write*: Select features.
+ *write*:
+ Select features.
Users: An application using the w1_term device
When the Wacom Intuos 4 is connected over Bluetooth, the
image has to contain 256 bytes (64x32 px 1 bit colour).
The format is also scrambled, like in the USB mode, and it can
- be summarized by converting 76543210 into GECA6420.
+ be summarized by converting::
+
+ 76543210 into GECA6420.
HGFEDCBA HFDB7531
What: /sys/bus/hid/devices/<bus>:<vid>:<pid>.<n>/wacom_remote/unpair_remote
image: The image bitmap. Currently a 32-bit BMP.
status: 1 if the image is valid, 0 if firmware invalidated it.
type: 0 indicates image is in BMP format.
+
+ ======== ===================================================
version: The version of the BGRT. Currently 1.
xoffset: The number of pixels between the left of the screen
and the left edge of the image.
yoffset: The number of pixels between the top of the screen
and the top edge of the image.
+ ======== ===================================================
What: /sys/firmware/acpi/hotplug/
Date: February 2013
The following setting is available to user space for each
hotplug profile:
+ ======== =======================================================
enabled: If set, the ACPI core will handle notifications of
- hotplug events associated with the given class of
- devices and will allow those devices to be ejected with
- the help of the _EJ0 control method. Unsetting it
- effectively disables hotplug for the correspoinding
- class of devices.
+ hotplug events associated with the given class of
+ devices and will allow those devices to be ejected with
+ the help of the _EJ0 control method. Unsetting it
+ effectively disables hotplug for the correspoinding
+ class of devices.
+ ======== =======================================================
The value of the above attribute is an integer number: 1 (set)
or 0 (unset). Attempts to write any other values to it will
To figure out where all the SCI's are coming from,
/sys/firmware/acpi/interrupts contains a file listing
every possible source, and the count of how many
- times it has triggered.
-
- $ cd /sys/firmware/acpi/interrupts
- $ grep . *
- error: 0
- ff_gbl_lock: 0 enable
- ff_pmtimer: 0 invalid
- ff_pwr_btn: 0 enable
- ff_rt_clk: 2 disable
- ff_slp_btn: 0 invalid
- gpe00: 0 invalid
- gpe01: 0 enable
- gpe02: 108 enable
- gpe03: 0 invalid
- gpe04: 0 invalid
- gpe05: 0 invalid
- gpe06: 0 enable
- gpe07: 0 enable
- gpe08: 0 invalid
- gpe09: 0 invalid
- gpe0A: 0 invalid
- gpe0B: 0 invalid
- gpe0C: 0 invalid
- gpe0D: 0 invalid
- gpe0E: 0 invalid
- gpe0F: 0 invalid
- gpe10: 0 invalid
- gpe11: 0 invalid
- gpe12: 0 invalid
- gpe13: 0 invalid
- gpe14: 0 invalid
- gpe15: 0 invalid
- gpe16: 0 invalid
- gpe17: 1084 enable
- gpe18: 0 enable
- gpe19: 0 invalid
- gpe1A: 0 invalid
- gpe1B: 0 invalid
- gpe1C: 0 invalid
- gpe1D: 0 invalid
- gpe1E: 0 invalid
- gpe1F: 0 invalid
- gpe_all: 1192
- sci: 1194
- sci_not: 0
-
- sci - The number of times the ACPI SCI
- has been called and claimed an interrupt.
-
- sci_not - The number of times the ACPI SCI
- has been called and NOT claimed an interrupt.
-
- gpe_all - count of SCI caused by GPEs.
-
- gpeXX - count for individual GPE source
-
- ff_gbl_lock - Global Lock
-
- ff_pmtimer - PM Timer
-
- ff_pwr_btn - Power Button
-
- ff_rt_clk - Real Time Clock
-
- ff_slp_btn - Sleep Button
-
- error - an interrupt that can't be accounted for above.
-
- invalid: it's either a GPE or a Fixed Event that
- doesn't have an event handler.
-
- disable: the GPE/Fixed Event is valid but disabled.
-
- enable: the GPE/Fixed Event is valid and enabled.
-
- Root has permission to clear any of these counters. Eg.
- # echo 0 > gpe11
-
- All counters can be cleared by clearing the total "sci":
- # echo 0 > sci
+ times it has triggered::
+
+ $ cd /sys/firmware/acpi/interrupts
+ $ grep . *
+ error: 0
+ ff_gbl_lock: 0 enable
+ ff_pmtimer: 0 invalid
+ ff_pwr_btn: 0 enable
+ ff_rt_clk: 2 disable
+ ff_slp_btn: 0 invalid
+ gpe00: 0 invalid
+ gpe01: 0 enable
+ gpe02: 108 enable
+ gpe03: 0 invalid
+ gpe04: 0 invalid
+ gpe05: 0 invalid
+ gpe06: 0 enable
+ gpe07: 0 enable
+ gpe08: 0 invalid
+ gpe09: 0 invalid
+ gpe0A: 0 invalid
+ gpe0B: 0 invalid
+ gpe0C: 0 invalid
+ gpe0D: 0 invalid
+ gpe0E: 0 invalid
+ gpe0F: 0 invalid
+ gpe10: 0 invalid
+ gpe11: 0 invalid
+ gpe12: 0 invalid
+ gpe13: 0 invalid
+ gpe14: 0 invalid
+ gpe15: 0 invalid
+ gpe16: 0 invalid
+ gpe17: 1084 enable
+ gpe18: 0 enable
+ gpe19: 0 invalid
+ gpe1A: 0 invalid
+ gpe1B: 0 invalid
+ gpe1C: 0 invalid
+ gpe1D: 0 invalid
+ gpe1E: 0 invalid
+ gpe1F: 0 invalid
+ gpe_all: 1192
+ sci: 1194
+ sci_not: 0
+
+ =========== ==================================================
+ sci The number of times the ACPI SCI
+ has been called and claimed an interrupt.
+
+ sci_not The number of times the ACPI SCI
+ has been called and NOT claimed an interrupt.
+
+ gpe_all count of SCI caused by GPEs.
+
+ gpeXX count for individual GPE source
+
+ ff_gbl_lock Global Lock
+
+ ff_pmtimer PM Timer
+
+ ff_pwr_btn Power Button
+
+ ff_rt_clk Real Time Clock
+
+ ff_slp_btn Sleep Button
+
+ error an interrupt that can't be accounted for above.
+
+ invalid it's either a GPE or a Fixed Event that
+ doesn't have an event handler.
+
+ disable the GPE/Fixed Event is valid but disabled.
+
+ enable the GPE/Fixed Event is valid and enabled.
+ =========== ==================================================
+
+ Root has permission to clear any of these counters. Eg.::
+
+ # echo 0 > gpe11
+
+ All counters can be cleared by clearing the total "sci"::
+
+ # echo 0 > sci
None of these counters has an effect on the function
of the system, they are simply statistics.
Let's take power button fixed event for example, please kill acpid
and other user space applications so that the machine won't shutdown
- when pressing the power button.
- # cat ff_pwr_btn
- 0 enabled
- # press the power button for 3 times;
- # cat ff_pwr_btn
- 3 enabled
- # echo disable > ff_pwr_btn
- # cat ff_pwr_btn
- 3 disabled
- # press the power button for 3 times;
- # cat ff_pwr_btn
- 3 disabled
- # echo enable > ff_pwr_btn
- # cat ff_pwr_btn
- 4 enabled
- /*
- * this is because the status bit is set even if the enable bit is cleared,
- * and it triggers an ACPI fixed event when the enable bit is set again
- */
- # press the power button for 3 times;
- # cat ff_pwr_btn
- 7 enabled
- # echo disable > ff_pwr_btn
- # press the power button for 3 times;
- # echo clear > ff_pwr_btn /* clear the status bit */
- # echo disable > ff_pwr_btn
- # cat ff_pwr_btn
- 7 enabled
+ when pressing the power button::
+
+ # cat ff_pwr_btn
+ 0 enabled
+ # press the power button for 3 times;
+ # cat ff_pwr_btn
+ 3 enabled
+ # echo disable > ff_pwr_btn
+ # cat ff_pwr_btn
+ 3 disabled
+ # press the power button for 3 times;
+ # cat ff_pwr_btn
+ 3 disabled
+ # echo enable > ff_pwr_btn
+ # cat ff_pwr_btn
+ 4 enabled
+ /*
+ * this is because the status bit is set even if the enable
+ * bit is cleared, and it triggers an ACPI fixed event when
+ * the enable bit is set again
+ */
+ # press the power button for 3 times;
+ # cat ff_pwr_btn
+ 7 enabled
+ # echo disable > ff_pwr_btn
+ # press the power button for 3 times;
+ # echo clear > ff_pwr_btn /* clear the status bit */
+ # echo disable > ff_pwr_btn
+ # cat ff_pwr_btn
+ 7 enabled
doesn't matter), they will be represented in sysfs as
entries "T-0" through "T-(N-1)":
- Example entry directories:
+ Example entry directories::
/sys/firmware/dmi/entries/17-0
/sys/firmware/dmi/entries/17-1
Each DMI entry in sysfs has the common header values
exported as attributes:
- handle : The 16bit 'handle' that is assigned to this
+ ======== =================================================
+ handle The 16bit 'handle' that is assigned to this
entry by the firmware. This handle may be
referred to by other entries.
- length : The length of the entry, as presented in the
+ length The length of the entry, as presented in the
entry itself. Note that this is _not the
total count of bytes associated with the
- entry_. This value represents the length of
+ entry. This value represents the length of
the "formatted" portion of the entry. This
"formatted" region is sometimes followed by
the "unformatted" region composed of nul
terminated strings, with termination signalled
by a two nul characters in series.
- raw : The raw bytes of the entry. This includes the
+ raw The raw bytes of the entry. This includes the
"formatted" portion of the entry, the
"unformatted" strings portion of the entry,
and the two terminating nul characters.
- type : The type of the entry. This value is the same
+ type The type of the entry. This value is the same
as found in the directory name. It indicates
how the rest of the entry should be interpreted.
- instance: The instance ordinal of the entry for the
+ instance The instance ordinal of the entry for the
given type. This value is the same as found
in the parent directory name.
- position: The ordinal position (zero-based) of the entry
+ position The ordinal position (zero-based) of the entry
within the entirety of the DMI entry table.
+ ======== =================================================
- === Entry Specialization ===
+ **Entry Specialization**
Some entry types may have other information available in
sysfs. Not all types are specialized.
- --- Type 15 - System Event Log ---
+ **Type 15 - System Event Log**
This entry allows the firmware to export a log of
events the system has taken. This information is
typically backed by nvram, but the implementation
details are abstracted by this table. This entry's data
- is exported in the directory:
+ is exported in the directory::
- /sys/firmware/dmi/entries/15-0/system_event_log
+ /sys/firmware/dmi/entries/15-0/system_event_log
and has the following attributes (documented in the
SMBIOS / DMI specification under "System Event Log (Type 15)":
- area_length
- header_start_offset
- data_start_offset
- access_method
- status
- change_token
- access_method_address
- header_format
- per_log_type_descriptor_length
- type_descriptors_supported_count
+ - area_length
+ - header_start_offset
+ - data_start_offset
+ - access_method
+ - status
+ - change_token
+ - access_method_address
+ - header_format
+ - per_log_type_descriptor_length
+ - type_descriptors_supported_count
As well, the kernel exports the binary attribute:
- raw_event_log : The raw binary bits of the event log
+ ============= ====================================
+ raw_event_log The raw binary bits of the event log
as described by the DMI entry.
+ ============= ====================================
Date: February 2015
Contact: Peter Jones <pjones@redhat.com>
Description: What kind of firmware entry this is:
- 0 - Unknown
- 1 - System Firmware
- 2 - Device Firmware
- 3 - UEFI Driver
+
+ == ===============
+ 0 Unknown
+ 1 System Firmware
+ 2 Device Firmware
+ 3 UEFI Driver
+ == ===============
What: /sys/firmware/efi/esrt/entries/entry$N/fw_class
Date: February 2015
Contact: Peter Jones <pjones@redhat.com>
Description: The result of the last firmware update attempt for the
firmware resource entry.
- 0 - Success
- 1 - Insufficient resources
- 2 - Incorrect version
- 3 - Invalid format
- 4 - Authentication error
- 5 - AC power event
- 6 - Battery power event
+
+ == ======================
+ 0 Success
+ 1 Insufficient resources
+ 2 Incorrect version
+ 3 Invalid format
+ 4 Authentication error
+ 5 AC power event
+ 6 Battery power event
+ == ======================
/sys/firmware/efi/runtime-map/ is the directory the kernel
exports that information in.
- subdirectories are named with the number of the memory range:
+ subdirectories are named with the number of the memory range::
/sys/firmware/efi/runtime-map/0
/sys/firmware/efi/runtime-map/1
Each subdirectory contains five files:
- attribute : The attributes of the memory range.
- num_pages : The size of the memory range in pages.
- phys_addr : The physical address of the memory range.
- type : The type of the memory range.
- virt_addr : The virtual address of the memory range.
+ ========= =========================================
+ attribute The attributes of the memory range.
+ num_pages The size of the memory range in pages.
+ phys_addr The physical address of the memory range.
+ type The type of the memory range.
+ virt_addr The virtual address of the memory range.
+ ========= =========================================
Above values are all hexadecimal numbers with the '0x' prefix.
Users: Kexec
This directory has the same layout (and
underlying implementation as /sys/firmware/efi/vars.
- See Documentation/ABI/*/sysfs-firmware-efi-vars
+ See `Documentation/ABI/*/sysfs-firmware-efi-vars`
for more information on how to interact with
this structure.
the raw memory map to userspace.
The structure is as follows: Under /sys/firmware/memmap there
- are subdirectories with the number of the entry as their name:
+ are subdirectories with the number of the entry as their name::
/sys/firmware/memmap/0
/sys/firmware/memmap/1
Each directory contains three files:
- start : The start address (as hexadecimal number with the
+ ======== =====================================================
+ start The start address (as hexadecimal number with the
'0x' prefix).
- end : The end address, inclusive (regardless whether the
+ end The end address, inclusive (regardless whether the
firmware provides inclusive or exclusive ranges).
- type : Type of the entry as string. See below for a list of
+ type Type of the entry as string. See below for a list of
valid types.
+ ======== =====================================================
- So, for example:
+ So, for example::
/sys/firmware/memmap/0/start
/sys/firmware/memmap/0/end
- reserved
Following shell snippet can be used to display that memory
- map in a human-readable format:
+ map in a human-readable format::
- -------------------- 8< ----------------------------------------
#!/bin/bash
cd /sys/firmware/memmap
for dir in * ; do
type=$(cat $dir/type)
printf "%016x-%016x (%s)\n" $start $[ $end +1] "$type"
done
- -------------------- >8 ----------------------------------------
to the fw_cfg device can be found in "docs/specs/fw_cfg.txt"
in the QEMU source tree.
- === SysFS fw_cfg Interface ===
+ **SysFS fw_cfg Interface**
The fw_cfg sysfs interface described in this document is only
intended to display discoverable blobs (i.e., those registered
/sys/firmware/qemu_fw_cfg/rev
- --- Discoverable fw_cfg blobs by selector key ---
+ **Discoverable fw_cfg blobs by selector key**
All discoverable blobs listed in the fw_cfg file directory are
displayed as entries named after their unique selector key
Each such fw_cfg sysfs entry has the following values exported
as attributes:
- name : The 56-byte nul-terminated ASCII string used as the
+ ==== ====================================================
+ name The 56-byte nul-terminated ASCII string used as the
blob's 'file name' in the fw_cfg directory.
- size : The length of the blob, as given in the fw_cfg
+ size The length of the blob, as given in the fw_cfg
directory.
- key : The value of the blob's selector key as given in the
+ key The value of the blob's selector key as given in the
fw_cfg directory. This value is the same as used in
the parent directory name.
- raw : The raw bytes of the blob, obtained by selecting the
+ raw The raw bytes of the blob, obtained by selecting the
entry via the control register, and reading a number
of bytes equal to the blob size from the data
register.
+ ==== ====================================================
- --- Listing fw_cfg blobs by file name ---
+ **Listing fw_cfg blobs by file name**
While the fw_cfg device does not impose any specific naming
convention on the blobs registered in the file directory,
QEMU developers have traditionally used path name semantics
- to give each blob a descriptive name. For example:
+ to give each blob a descriptive name. For example::
"bootorder"
"genroms/kvmvapic.bin"
of directories matching the path name components of fw_cfg
blob names, ending in symlinks to the by_key entry for each
"basename", as illustrated below (assume current directory is
- /sys/firmware):
+ /sys/firmware)::
qemu_fw_cfg/by_name/bootorder -> ../by_key/38
qemu_fw_cfg/by_name/etc/e820 -> ../../by_key/35
http://simplefirmware.org/documentation
While the tables are used by the kernel, user-space
- can observe them this way:
+ can observe them this way::
- # cd /sys/firmware/sfi/tables
- # cat $TABLENAME > $TABLENAME.bin
+ # cd /sys/firmware/sfi/tables
+ # cat $TABLENAME > $TABLENAME.bin
The /sys/firmware/sgi_uv directory contains information
about the SGI UV platform.
- Under that directory are a number of files:
+ Under that directory are a number of files::
partition_id
coherence_id
SGI UV systems can be partitioned into multiple physical
machines, which each partition running a unique copy
of the operating system. Each partition will have a unique
- partition id. To display the partition id, use the command:
+ partition id. To display the partition id, use the command::
cat /sys/firmware/sgi_uv/partition_id
A partitioned SGI UV system can have one or more coherence
domain. The coherence id indicates which coherence domain
this partition is in. To display the coherence id, use the
- command:
+ command::
cat /sys/firmware/sgi_uv/coherence_id
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Board version burned into eFuses of this Turris Mox board.
+Description: (Read) Board version burned into eFuses of this Turris Mox board.
Format: %i
What: /sys/firmware/turris-mox-rwtm/mac_address*
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) MAC addresses burned into eFuses of this Turris Mox board.
+Description: (Read) MAC addresses burned into eFuses of this Turris Mox board.
Format: %pM
What: /sys/firmware/turris-mox-rwtm/pubkey
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) ECDSA public key (in pubkey hex compressed form) computed
+Description: (Read) ECDSA public key (in pubkey hex compressed form) computed
as pair to the ECDSA private key burned into eFuses of this
Turris Mox Board.
Format: string
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) RAM size in MiB of this Turris Mox board as was detected
+Description: (Read) RAM size in MiB of this Turris Mox board as was detected
during manufacturing and burned into eFuses. Can be 512 or 1024.
Format: %i
Date: August 2019
KernelVersion: 5.4
Contact: Marek Behún <marek.behun@nic.cz>
-Description: (R) Serial number burned into eFuses of this Turris Mox device.
+Description: (Read) Serial number burned into eFuses of this Turris Mox device.
Format: %016X
parameter will have their blocks allocated out of a
block group specific preallocation pool, so that small
files are packed closely together. Each large file
- will have its blocks allocated out of its own unique
- preallocation pool.
+ will have its blocks allocated out of its own unique
+ preallocation pool.
What: /sys/fs/ext4/<disk>/inode_readahead_blks
Date: March 2008
Date: July 2013
Contact: "Namjae Jeon" <namjae.jeon@samsung.com>
Description: Controls the victim selection policy for garbage collection.
- Setting gc_idle = 0(default) will disable this option. Setting
- gc_idle = 1 will select the Cost Benefit approach & setting
- gc_idle = 2 will select the greedy approach & setting
- gc_idle = 3 will select the age-threshold based approach.
+ Setting gc_idle = 0(default) will disable this option. Setting:
+
+ =========== ===============================================
+ gc_idle = 1 will select the Cost Benefit approach & setting
+ gc_idle = 2 will select the greedy approach & setting
+ gc_idle = 3 will select the age-threshold based approach.
+ =========== ===============================================
What: /sys/fs/f2fs/<disk>/reclaim_segments
Date: October 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description: Controls the in-place-update policy.
updates in f2fs. User can set:
- 0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
- 0x04: F2FS_IPU_UTIL, 0x08: F2FS_IPU_SSR_UTIL,
- 0x10: F2FS_IPU_FSYNC, 0x20: F2FS_IPU_ASYNC,
- 0x40: F2FS_IPU_NOCACHE.
+
+ ==== =================
+ 0x01 F2FS_IPU_FORCE
+ 0x02 F2FS_IPU_SSR
+ 0x04 F2FS_IPU_UTIL
+ 0x08 F2FS_IPU_SSR_UTIL
+ 0x10 F2FS_IPU_FSYNC
+ 0x20 F2FS_IPU_ASYNC,
+ 0x40 F2FS_IPU_NOCACHE
+ ==== =================
+
Refer segment.h for details.
What: /sys/fs/f2fs/<disk>/min_ipu_util
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Give a way to attach REQ_META|FUA to data writes
given temperature-based bits. Now the bits indicate:
- * REQ_META | REQ_FUA |
- * 5 | 4 | 3 | 2 | 1 | 0 |
- * Cold | Warm | Hot | Cold | Warm | Hot |
+
+ +-------------------+-------------------+
+ | REQ_META | REQ_FUA |
+ +------+------+-----+------+------+-----+
+ | 5 | 4 | 3 | 2 | 1 | 0 |
+ +------+------+-----+------+------+-----+
+ | Cold | Warm | Hot | Cold | Warm | Hot |
+ +------+------+-----+------+------+-----+
What: /sys/fs/f2fs/<disk>/node_io_flag
Date: June 2020
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Give a way to attach REQ_META|FUA to node writes
given temperature-based bits. Now the bits indicate:
- * REQ_META | REQ_FUA |
- * 5 | 4 | 3 | 2 | 1 | 0 |
- * Cold | Warm | Hot | Cold | Warm | Hot |
+
+ +-------------------+-------------------+
+ | REQ_META | REQ_FUA |
+ +------+------+-----+------+------+-----+
+ | 5 | 4 | 3 | 2 | 1 | 0 |
+ +------+------+-----+------+------+-----+
+ | Cold | Warm | Hot | Cold | Warm | Hot |
+ +------+------+-----+------+------+-----+
What: /sys/fs/f2fs/<disk>/iostat_period_ms
Date: April 2020
Contact: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Description: If running under Xen:
Describes mode that Xen's performance-monitoring unit (PMU)
- uses. Accepted values are
- "off" -- PMU is disabled
- "self" -- The guest can profile itself
- "hv" -- The guest can profile itself and, if it is
+ uses. Accepted values are:
+
+ ====== ============================================
+ "off" PMU is disabled
+ "self" The guest can profile itself
+ "hv" The guest can profile itself and, if it is
privileged (e.g. dom0), the hypervisor
- "all" -- The guest can profile itself, the hypervisor
+ "all" The guest can profile itself, the hypervisor
and all other guests. Only available to
privileged guests.
+ ====== ============================================
What: /sys/hypervisor/pmu/pmu_features
Date: August 2015
representation of setup_data type. "data" file is the binary
representation of setup_data payload.
- The whole boot_params directory structure is like below:
- /sys/kernel/boot_params
- |__ data
- |__ setup_data
- | |__ 0
- | | |__ data
- | | |__ type
- | |__ 1
- | |__ data
- | |__ type
- |__ version
+ The whole boot_params directory structure is like below::
+
+ /sys/kernel/boot_params
+ |__ data
+ |__ setup_data
+ | |__ 0
+ | | |__ data
+ | | |__ type
+ | |__ 1
+ | |__ data
+ | |__ type
+ |__ version
Users: Kexec
of the hugepages supported by the kernel/CPU combination.
Under these directories are a number of files:
- nr_hugepages
- nr_overcommit_hugepages
- free_hugepages
- surplus_hugepages
- resv_hugepages
+
+ - nr_hugepages
+ - nr_overcommit_hugepages
+ - free_hugepages
+ - surplus_hugepages
+ - resv_hugepages
+
See Documentation/admin-guide/mm/hugetlbpage.rst for details.
in a tree.
run: write 0 to disable ksm, read 0 while ksm is disabled.
- write 1 to run ksm, read 1 while ksm is running.
- write 2 to disable ksm and unmerge all its pages.
+
+ - write 1 to run ksm, read 1 while ksm is running.
+ - write 2 to disable ksm and unmerge all its pages.
sleep_millisecs: how many milliseconds ksm should sleep between
scans.
number of objects per slab. If a slab cannot be allocated
because of fragmentation, SLUB will retry with the minimum order
possible depending on its characteristics.
+
When debug_guardpage_minorder=N (N > 0) parameter is specified
(see Documentation/admin-guide/kernel-parameters.rst), the minimum possible
order is used and this sysfs entry can not be used to change
new slab has not been possible at the cache's order and instead
fallen back to its minimum possible order. It can be written to
clear the current count.
+
Available when CONFIG_SLUB_STATS is enabled.
What: /sys/kernel/slab/cache/partial
slab from a remote node as opposed to allocating a new slab on
the local node. This reduces the amount of wasted memory over
the entire system but can be expensive.
+
Available when CONFIG_NUMA is enabled.
What: /sys/kernel/slab/cache/sanity_checks
Contact: Kirill Smelkov <kirr@mns.spb.ru>
Description: Maximum time allowed for periodic transfers per microframe (μs)
- [ USB 2.0 sets maximum allowed time for periodic transfers per
+ Note:
+ USB 2.0 sets maximum allowed time for periodic transfers per
microframe to be 80%, that is 100 microseconds out of 125
microseconds (full microframe).
However there are cases, when 80% max isochronous bandwidth is
too limiting. For example two video streams could require 110
microseconds of isochronous bandwidth per microframe to work
- together. ]
+ together.
Through this setting it is possible to raise the limit so that
the host controller would allow allocating more than 100
KernelVersion:»·3.3
Contact: Kay Sievers <kay.sievers@vrfy.org>
Description: Module taint flags:
- P - proprietary module
- O - out-of-tree module
- F - force-loaded module
- C - staging driver module
- E - unsigned module
+ == =====================
+ P proprietary module
+ O out-of-tree module
+ F force-loaded module
+ C staging driver module
+ E unsigned module
+ == =====================
Contact: "Corentin Chary" <corentincj@iksaif.net>
Description:
This file allows display switching. The value
- is composed by 4 bits and defined as follow:
- 4321
- |||`- LCD
- ||`-- CRT
- |`--- TV
- `---- DVI
- Ex: - 0 (0000b) means no display
+ is composed by 4 bits and defined as follow::
+
+ 4321
+ |||`- LCD
+ ||`-- CRT
+ |`--- TV
+ `---- DVI
+
+ Ex:
+ - 0 (0000b) means no display
- 3 (0011b) CRT+LCD.
What: /sys/devices/platform/asus_laptop/gps
Description:
Some models like the W1N have a LED display that can be
used to display several items of information.
- To control the LED display, use the following :
+ To control the LED display, use the following::
+
echo 0x0T000DDD > /sys/devices/platform/asus_laptop/
+
where T control the 3 letters display, and DDD the 3 digits display.
The DDD table can be found in Documentation/admin-guide/laptops/asus-laptop.rst
Description:
Change CPU clock configuration (write-only).
There are three available clock configuration:
+
* 0 -> Super Performance Mode
* 1 -> High Performance Mode
* 2 -> Power Saving Mode
In order to use an extended can_id add the
CAN_EFF_FLAG (0x80000000U) to the can_id. Example:
- - standard id 0x7ff:
- echo 0x7ff > /sys/class/net/can0/mb0_id
+ - standard id 0x7ff::
- - extended id 0x1fffffff:
- echo 0x9fffffff > /sys/class/net/can0/mb0_id
+ echo 0x7ff > /sys/class/net/can0/mb0_id
+
+ - extended id 0x1fffffff::
+
+ echo 0x9fffffff > /sys/class/net/can0/mb0_id
this file. To disable a trigger, write its name preceded
by '-' instead.
- For example, to enable the keyboard as trigger run:
+ For example, to enable the keyboard as trigger run::
+
echo +keyboard > /sys/class/leds/dell::kbd_backlight/start_triggers
- To disable it:
+
+ To disable it::
+
echo -keyboard > /sys/class/leds/dell::kbd_backlight/start_triggers
Note that not all the available triggers can be configured.
with any the above units. If no unit is specified, the value
is assumed to be expressed in seconds.
- For example, to set the timeout to 10 minutes run:
+ For example, to set the timeout to 10 minutes run::
+
echo 10m > /sys/class/leds/dell::kbd_backlight/stop_timeout
Note that when this file is read, the returned value might be
For example the token ID "5" would be available
as the following attributes:
- 0005_location
- 0005_value
+ - 0005_location
+ - 0005_value
Tokens will vary from machine to machine, and
only tokens available on that machine will be
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. Read this file to get the name of hwmon device, it
supports values:
- 'dfl_fme_thermal' - thermal hwmon device name
- 'dfl_fme_power' - power hwmon device name
+
+ ================= =========================
+ 'dfl_fme_thermal' thermal hwmon device name
+ 'dfl_fme_power' power hwmon device name
+ ================= =========================
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/temp1_input
Date: October 2019
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-Only. Read this file to get the policy of hardware threshold1
(see 'temp1_max'). It only supports two values (policies):
- 0 - AP2 state (90% throttling)
- 1 - AP1 state (50% throttling)
+
+ == ==========================
+ 0 AP2 state (90% throttling)
+ 1 AP1 state (50% throttling)
+ == ==========================
What: /sys/bus/platform/devices/dfl-fme.0/hwmon/hwmonX/power1_input
Date: October 2019
Contact: linux-acpi@vger.kernel.org
Description:
(RO) Display the platform power source
+
+ ========= ============================
bits[3:0] Current power source
- 0x00 = DC
- 0x01 = AC
- 0x02 = USB
- 0x03 = Wireless Charger
+ - 0x00 = DC
+ - 0x01 = AC
+ - 0x02 = USB
+ - 0x03 = Wireless Charger
bits[7:4] Power source sequence number
+ ========= ============================
What: /sys/bus/platform/devices/INT3407:00/dptf_power/battery_steady_power
Date: Jul, 2016
Contact: "Corentin Chary" <corentincj@iksaif.net>
Description:
This file allows display switching.
+
- 1 = LCD
- 2 = CRT
- 3 = LCD+CRT
+
If you run X11, you should use xrandr instead.
What: /sys/devices/platform/eeepc/camera
Description:
Change CPU clock configuration.
On the Eee PC 1000H there are three available clock configuration:
+
* 0 -> Super Performance Mode
* 1 -> High Performance Mode
* 2 -> Power Saving Mode
+
On Eee PC 701 there is only 2 available clock configurations.
Available configuration are listed in available_cpufv file.
Reading this file will show the raw hexadecimal value which
- is defined as follow:
- | 8 bit | 8 bit |
- | `---- Current mode
- `------------ Availables modes
+ is defined as follow::
+
+ | 8 bit | 8 bit |
+ | `---- Current mode
+ `------------ Availables modes
+
For example, 0x301 means: mode 1 selected, 3 available modes.
What: /sys/devices/platform/eeepc/available_cpufv
Description:
Reading the file will give you a list of masters which can be
selected for a demultiplexed bus. The format is
- "<index>:<name>". Example from a Renesas Lager board:
+ "<index>:<name>". Example from a Renesas Lager board::
- 0:/i2c@e6500000 1:/i2c@e6508000
+ 0:/i2c@e6500000 1:/i2c@e6508000
What: /sys/devices/platform/<i2c-demux-name>/current_master
Date: January 2016
Description:
Change fan mode
There are four available modes:
+
* 0 -> Super Silent Mode
* 1 -> Standard Mode
* 2 -> Dust Cleaning
Contact: "Oleg Keri <ezhi99@gmail.com>"
Description:
Control fn-lock mode.
+
* 1 -> Switched On
* 0 -> Switched Off
- For example:
- # echo "0" > \
- /sys/bus/pci/devices/0000:00:1f.0/PNP0C09:00/VPC2004:00/fn_lock
+ For example::
+
+ # echo "0" > \
+ /sys/bus/pci/devices/0000:00:1f.0/PNP0C09:00/VPC2004:00/fn_lock
of 0 and userspace can signal SBL to update firmware,
on next reboot, by writing a value of 1.
There are two available states:
+
* 0 -> Skip firmware update while rebooting
* 1 -> Attempt firmware update on next reboot
Thunderbolt controllers to turn on or off when no
devices are connected (write-only)
There are two available states:
+
* 0 -> Force power disabled
* 1 -> Force power enabled
Description:
Name of the UART device at which the WL128x chip
is connected. example: "/dev/ttyS0".
+
The device name flows down to architecture specific board
initialization file from the SFI/ATAGS bootloader
firmware. The name exposed is read from the user-space
Description:
The Life-cycle state of the SoC, which could be one of the
following values.
- Production - Production state and can be updated to secure
- GA Secured - Secure chip and not able to change state
- GA Non-Secured - Non-Secure chip and not able to change state
- RMA - Return Merchandise Authorization
+
+ ============== =============================================
+ Production Production state and can be updated to secure
+ GA Secured Secure chip and not able to change state
+ GA Non-Secured Non-Secure chip and not able to change state
+ RMA Return Merchandise Authorization
+ ============== =============================================
What: /sys/bus/platform/devices/MLNXBF04:00/post_reset_wdog
Date: Oct 2019
Contact: "Liming Sun <lsun@mellanox.com>"
Description:
The source of the boot stream for the next reset. It could be
- one of the following values.
- external - boot from external source (USB or PCIe)
- emmc - boot from the onchip eMMC
- emmc_legacy - boot from the onchip eMMC in legacy (slow) mode
+ one of the following values:
+
+ =========== ===============================================
+ external boot from external source (USB or PCIe)
+ emmc boot from the onchip eMMC
+ emmc_legacy boot from the onchip eMMC in legacy (slow) mode
+ =========== ===============================================
What: /sys/bus/platform/devices/MLNXBF04:00/second_reset_action
Date: Oct 2019
Update the source of the boot stream after next reset. It could
be one of the following values and will be applied after next
reset.
- external - boot from external source (USB or PCIe)
- emmc - boot from the onchip eMMC
- emmc_legacy - boot from the onchip eMMC in legacy (slow) mode
- swap_emmc - swap the primary / secondary boot partition
- none - cancel the action
+
+ =========== ===============================================
+ external boot from external source (USB or PCIe)
+ emmc boot from the onchip eMMC
+ emmc_legacy boot from the onchip eMMC in legacy (slow) mode
+ swap_emmc swap the primary / secondary boot partition
+ none cancel the action
+ =========== ===============================================
What: /sys/bus/platform/devices/MLNXBF04:00/secure_boot_fuse_state
Date: Oct 2019
Contact: "Liming Sun <lsun@mellanox.com>"
Description:
The state of eFuse versions with the following values.
- InUse - burnt, valid and currently in use
- Used - burnt and valid
- Free - not burnt and free to use
- Skipped - not burnt but not free (skipped)
- Wasted - burnt and invalid
- Invalid - not burnt but marked as valid (error state).
+
+ ======= ===============================================
+ InUse burnt, valid and currently in use
+ Used burnt and valid
+ Free not burnt and free to use
+ Skipped not burnt but not free (skipped)
+ Wasted burnt and invalid
+ Invalid not burnt but marked as valid (error state).
+ ======= ===============================================
The file can show/change the phy mode for role swap of usb.
Write the following strings to change the mode:
- "host" - switching mode from peripheral to host.
- "peripheral" - switching mode from host to peripheral.
+
+ - "host" - switching mode from peripheral to host.
+ - "peripheral" - switching mode from host to peripheral.
Read the file, then it shows the following strings:
- "host" - The mode is host now.
- "peripheral" - The mode is peripheral now.
+
+ - "host" - The mode is host now.
+ - "peripheral" - The mode is peripheral now.
The file can show/change the drd mode of usb.
Write the following string to change the mode:
- "host" - switching mode from peripheral to host.
- "peripheral" - switching mode from host to peripheral.
+
+ - "host" - switching mode from peripheral to host.
+ - "peripheral" - switching mode from host to peripheral.
Read the file, then it shows the following strings:
- "host" - The mode is host now.
- "peripheral" - The mode is peripheral now.
+
+ - "host" - The mode is host now.
+ - "peripheral" - The mode is peripheral now.
Description:
LPE Firmware version for SST driver on all atom
plaforms (BYT/CHT/Merrifield/BSW).
- If the FW has never been loaded it will display:
+ If the FW has never been loaded it will display::
+
"FW not yet loaded"
- If FW has been loaded it will display:
+
+ If FW has been loaded it will display::
+
"v01.aa.bb.cc"
+
aa: Major version is reflecting SoC version:
+
+ === =============
0d: BYT FW
0b: BSW FW
07: Merrifield FW
+ === =============
+
bb: Minor version
+
cc: Build version
Description:
Current status of the device.
Allowed values:
- 1 - Device is available and can be exported
- 2 - Device is currently exported
- 3 - Fatal error occurred during communication
- with peer
+
+ == ==========================================
+ 1 Device is available and can be exported
+ 2 Device is currently exported
+ 3 Fatal error occurred during communication
+ with peer
+ == ==========================================
What: /sys/devices/platform/usbip-vudc.%d/usbip_sockfd
Date: April 2016
which affects charging via the special USB PowerShare port
(marked with a small lightning bolt or battery icon) when in
low power states:
+
- In S0, the port will always provide power.
- In S0ix, if usb_charge is enabled, then power will be
supplied to the port when on AC or if battery is > 50%.
suspend-to-disk mechanism. Reading from this file returns
the name of the method by which the system will be put to
sleep on the next suspend. There are four methods supported:
+
'firmware' - means that the memory image will be saved to disk
by some firmware, in which case we also assume that the
firmware will handle the system suspend.
+
'platform' - the memory image will be saved by the kernel and
the system will be put to sleep by the platform driver (e.g.
ACPI or other PM registers).
+
'shutdown' - the memory image will be saved by the kernel and
the system will be powered off.
+
'reboot' - the memory image will be saved by the kernel and
the system will be rebooted.
The suspend-to-disk method may be chosen by writing to this
file one of the accepted strings:
- 'firmware'
- 'platform'
- 'shutdown'
- 'reboot'
- 'testproc'
- 'test'
+ - 'firmware'
+ - 'platform'
+ - 'shutdown'
+ - 'reboot'
+ - 'testproc'
+ - 'test'
It will only change to 'firmware' or 'platform' if the system
supports that.
string representing a nonzero integer into it.
To use this debugging feature you should attempt to suspend
- the machine, then reboot it and run
+ the machine, then reboot it and run::
- dmesg -s 1000000 | grep 'hash matches'
+ dmesg -s 1000000 | grep 'hash matches'
If you do not get any matches (or they appear to be false
positives), it is possible that the last PM event point
wakeup sources created with the help of /sys/power/wake_lock.
When a string is written to /sys/power/wake_unlock, it will be
assumed to represent the name of a wakeup source to deactivate.
+
If a wakeup source object of that name exists and is active at
the moment, it will be deactivated.
/sys/kernel/profiling is the runtime equivalent
of the boot-time profile= option.
- You can get the same effect running:
+ You can get the same effect running::
echo 2 > /sys/kernel/profiling
pin offered by the PTP hardware clock. The file name
is the hardware dependent pin name. Reading from this
file produces two numbers, the assigned function (see
- the PTP_PF_ enumeration values in linux/ptp_clock.h)
+ the `PTP_PF_` enumeration values in linux/ptp_clock.h)
and the channel number. The function and channel
assignment may be changed by two writing numbers into
the file.
Enable passing additional variables for synthetic uevents that
are generated by writing /sys/.../uevent file.
- Recognized extended format is ACTION [UUID [KEY=VALUE ...].
+ Recognized extended format is::
- The ACTION is compulsory - it is the name of the uevent action
- ("add", "change", "remove"). There is no change compared to
- previous functionality here. The rest of the extended format
- is optional.
+ ACTION [UUID [KEY=VALUE ...]
+
+ The ACTION is compulsory - it is the name of the uevent
+ action (``add``, ``change``, ``remove``). There is no change
+ compared to previous functionality here. The rest of the
+ extended format is optional.
You need to pass UUID first before any KEY=VALUE pairs.
- The UUID must be in "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
+ The UUID must be in ``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``
format where 'x' is a hex digit. The UUID is considered to be
a transaction identifier so it's possible to use the same UUID
value for one or more synthetic uevents in which case we
logically group these uevents together for any userspace
listeners. The UUID value appears in uevent as
- "SYNTH_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" environment
+ ``SYNTH_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx`` environment
variable.
If UUID is not passed in, the generated synthetic uevent gains
- "SYNTH_UUID=0" environment variable automatically.
+ ``SYNTH_UUID=0`` environment variable automatically.
The KEY=VALUE pairs can contain alphanumeric characters only.
+
It's possible to define zero or more pairs - each pair is then
delimited by a space character ' '. Each pair appears in
- synthetic uevent as "SYNTH_ARG_KEY=VALUE". That means the KEY
- name gains "SYNTH_ARG_" prefix to avoid possible collisions
+ synthetic uevent as ``SYNTH_ARG_KEY=VALUE``. That means the KEY
+ name gains ``SYNTH_ARG_`` prefix to avoid possible collisions
with existing variables.
- Example of valid sequence written to the uevent file:
+ Example of valid sequence written to the uevent file::
add fe4d7c9d-b8c6-4a70-9ef1-3d8a58d18eed A=1 B=abc
- This generates synthetic uevent including these variables:
+ This generates synthetic uevent including these variables::
ACTION=add
SYNTH_ARG_A=1
SYNTH_ARG_B=abc
SYNTH_UUID=fe4d7c9d-b8c6-4a70-9ef1-3d8a58d18eed
+
Users:
udev, userspace tools generating synthetic uevents
7. Device is unplugged.
References:
- [WUSB-AM] Association Models Supplement to the
+ [WUSB-AM]
+ Association Models Supplement to the
Certified Wireless Universal Serial Bus
Specification, version 1.0.
KernelVersion: 5.6
Contact: linux-usb@vger.kernel.org
Description: There are two USB charger states:
- USB_CHARGER_ABSENT
- USB_CHARGER_PRESENT
+
+ - USB_CHARGER_ABSENT
+ - USB_CHARGER_PRESENT
+
There are five USB charger types:
- USB_CHARGER_UNKNOWN_TYPE: Charger type is unknown
- USB_CHARGER_SDP_TYPE: Standard Downstream Port
- USB_CHARGER_CDP_TYPE: Charging Downstream Port
- USB_CHARGER_DCP_TYPE: Dedicated Charging Port
- USB_CHARGER_ACA_TYPE: Accessory Charging Adapter
+
+ ======================== ==========================
+ USB_CHARGER_UNKNOWN_TYPE Charger type is unknown
+ USB_CHARGER_SDP_TYPE Standard Downstream Port
+ USB_CHARGER_CDP_TYPE Charging Downstream Port
+ USB_CHARGER_DCP_TYPE Dedicated Charging Port
+ USB_CHARGER_ACA_TYPE Accessory Charging Adapter
+ ======================== ==========================
+
https://www.usb.org/document-library/battery-charging-v12-spec-and-adopters-agreement
- Here are two examples taken using udevadm monitor -p when
- USB charger is online:
- UDEV change /devices/soc0/usbphynop1 (platform)
- ACTION=change
- DEVPATH=/devices/soc0/usbphynop1
- DRIVER=usb_phy_generic
- MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
- OF_COMPATIBLE_0=usb-nop-xceiv
- OF_COMPATIBLE_N=1
- OF_FULLNAME=/usbphynop1
- OF_NAME=usbphynop1
- SEQNUM=2493
- SUBSYSTEM=platform
- USB_CHARGER_STATE=USB_CHARGER_PRESENT
- USB_CHARGER_TYPE=USB_CHARGER_SDP_TYPE
- USEC_INITIALIZED=227422826
-
- USB charger is offline:
- KERNEL change /devices/soc0/usbphynop1 (platform)
- ACTION=change
- DEVPATH=/devices/soc0/usbphynop1
- DRIVER=usb_phy_generic
- MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
- OF_COMPATIBLE_0=usb-nop-xceiv
- OF_COMPATIBLE_N=1
- OF_FULLNAME=/usbphynop1
- OF_NAME=usbphynop1
- SEQNUM=2494
- SUBSYSTEM=platform
- USB_CHARGER_STATE=USB_CHARGER_ABSENT
- USB_CHARGER_TYPE=USB_CHARGER_UNKNOWN_TYPE
+ Here are two examples taken using ``udevadm monitor -p`` when
+ USB charger is online::
+
+ UDEV change /devices/soc0/usbphynop1 (platform)
+ ACTION=change
+ DEVPATH=/devices/soc0/usbphynop1
+ DRIVER=usb_phy_generic
+ MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
+ OF_COMPATIBLE_0=usb-nop-xceiv
+ OF_COMPATIBLE_N=1
+ OF_FULLNAME=/usbphynop1
+ OF_NAME=usbphynop1
+ SEQNUM=2493
+ SUBSYSTEM=platform
+ USB_CHARGER_STATE=USB_CHARGER_PRESENT
+ USB_CHARGER_TYPE=USB_CHARGER_SDP_TYPE
+ USEC_INITIALIZED=227422826
+
+ USB charger is offline::
+
+ KERNEL change /devices/soc0/usbphynop1 (platform)
+ ACTION=change
+ DEVPATH=/devices/soc0/usbphynop1
+ DRIVER=usb_phy_generic
+ MODALIAS=of:Nusbphynop1T(null)Cusb-nop-xceiv
+ OF_COMPATIBLE_0=usb-nop-xceiv
+ OF_COMPATIBLE_N=1
+ OF_FULLNAME=/usbphynop1
+ OF_NAME=usbphynop1
+ SEQNUM=2494
+ SUBSYSTEM=platform
+ USB_CHARGER_STATE=USB_CHARGER_ABSENT
+ USB_CHARGER_TYPE=USB_CHARGER_UNKNOWN_TYPE
longer functional a uevent will be raised. The uevent will
contain ACTION=offline and ERROR=DEAD.
- Here is an example taken using udevadm monitor -p:
+ Here is an example taken using udevadm monitor -p::
- KERNEL[130.428945] offline /devices/pci0000:00/0000:00:10.0/usb2 (usb)
- ACTION=offline
- BUSNUM=002
- DEVNAME=/dev/bus/usb/002/001
- DEVNUM=001
- DEVPATH=/devices/pci0000:00/0000:00:10.0/usb2
- DEVTYPE=usb_device
- DRIVER=usb
- ERROR=DEAD
- MAJOR=189
- MINOR=128
- PRODUCT=1d6b/2/414
- SEQNUM=2168
- SUBSYSTEM=usb
- TYPE=9/0/1
+ KERNEL[130.428945] offline /devices/pci0000:00/0000:00:10.0/usb2 (usb)
+ ACTION=offline
+ BUSNUM=002
+ DEVNAME=/dev/bus/usb/002/001
+ DEVNUM=001
+ DEVPATH=/devices/pci0000:00/0000:00:10.0/usb2
+ DEVTYPE=usb_device
+ DRIVER=usb
+ ERROR=DEAD
+ MAJOR=189
+ MINOR=128
+ PRODUCT=1d6b/2/414
+ SEQNUM=2168
+ SUBSYSTEM=usb
+ TYPE=9/0/1
Users: chromium-os-dev@chromium.org
If unsure, select 'N'.
+config WARN_ABI_ERRORS
+ bool "Warn if there are errors at ABI files"
+ depends on COMPILE_TEST
+ help
+ The files under Documentation/ABI should follow what's
+ described at Documentation/ABI/README. Yet, as they're manually
+ written, it would be possible that some of those files would
+ have errors that would break them for being parsed by
+ scripts/get_abi.pl. Add a check to verify them.
+ If unsure, select 'N'.
$(shell $(srctree)/scripts/documentation-file-ref-check --warn)
endif
+# Check for broken ABI files
+ifeq ($(CONFIG_WARN_ABI_ERRORS),y)
+$(shell $(srctree)/scripts/get_abi.pl validate --dir $(srctree)/Documentation/ABI)
+endif
+
# You can set these variables from the command line.
SPHINXBUILD = sphinx-build
SPHINXOPTS =
PDFLATEX = xelatex
LATEXOPTS = -interaction=batchmode
+ifeq ($(KBUILD_VERBOSE),0)
+SPHINXOPTS += "-q"
+endif
+
# User-friendly check for sphinx-build
HAVE_SPHINX := $(shell if which $(SPHINXBUILD) >/dev/null 2>&1; then echo 1; else echo 0; fi)
privileges, such as allowing a user to set up user namespace UID/GID mappings.
Note on GID policies and setgroups()
-==================
+====================================
In v5.9 we are adding support for limiting CAP_SETGID privileges as was done
previously for CAP_SETUID. However, for compatibility with common sandboxing
related code conventions in userspace, we currently allow arbitrary
--- /dev/null
+ABI obsolete symbols
+====================
+
+Documents interfaces that are still remaining in the kernel, but are
+marked to be removed at some later point in time.
+
+The description of the interface will document the reason why it is
+obsolete and when it can be expected to be removed.
+
+.. kernel-abi:: $srctree/Documentation/ABI/obsolete
+ :rst:
--- /dev/null
+ABI removed symbols
+===================
+
+.. kernel-abi:: $srctree/Documentation/ABI/removed
+ :rst:
--- /dev/null
+ABI stable symbols
+==================
+
+Documents the interfaces that the developer has defined to be stable.
+
+Userspace programs are free to use these interfaces with no
+restrictions, and backward compatibility for them will be guaranteed
+for at least 2 years.
+
+Most interfaces (like syscalls) are expected to never change and always
+be available.
+
+.. kernel-abi:: $srctree/Documentation/ABI/stable
+ :rst:
--- /dev/null
+ABI testing symbols
+===================
+
+Documents interfaces that are felt to be stable,
+as the main development of this interface has been completed.
+
+The interface can be changed to add new features, but the
+current interface will not break by doing this, unless grave
+errors or security problems are found in them.
+
+Userspace programs can start to rely on these interfaces, but they must
+be aware of changes that can occur before these interfaces move to
+be marked stable.
+
+Programs that use these interfaces are strongly encouraged to add their
+name to the description of these interfaces, so that the kernel
+developers can easily notify them if any changes occur.
+
+.. kernel-abi:: $srctree/Documentation/ABI/testing
+ :rst:
--- /dev/null
+=====================
+Linux ABI description
+=====================
+
+.. toctree::
+ :maxdepth: 2
+
+ abi-stable
+ abi-testing
+ abi-obsolete
+ abi-removed
==============================
Since the boot configuration file is loaded with initrd, it will be added
-to the end of the initrd (initramfs) image file with size, checksum and
-12-byte magic word as below.
+to the end of the initrd (initramfs) image file with padding, size,
+checksum and 12-byte magic word as below.
-[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n]
+[initrd][bootconfig][padding][size(le32)][checksum(le32)][#BOOTCONFIG\n]
+
+The size and checksum fields are unsigned 32bit little endian value.
+
+When the boot configuration is added to the initrd image, the total
+file size is aligned to 4 bytes. To fill the gap, null characters
+(``\0``) will be added. Thus the ``size`` is the length of the bootconfig
+file + padding bytes.
The Linux kernel decodes the last part of the initrd image in memory to
get the boot configuration data.
Because of this "piggyback" method, there is no need to change or
-update the boot loader and the kernel image itself.
+update the boot loader and the kernel image itself as long as the boot
+loader passes the correct initrd file size. If by any chance, the boot
+loader passes a longer size, the kernel feils to find the bootconfig data.
To do this operation, Linux kernel provides "bootconfig" command under
tools/bootconfig, which allows admin to apply or delete the config file
contain 256 key-value pairs. In most cases, the number of config items
will be under 100 entries and smaller than 8KB, so it would be enough.
If the node number exceeds 1024, parser returns an error even if the file
-size is smaller than 32KB.
+size is smaller than 32KB. (Note that this maximum size is not including
+the padding null characters.)
Anyway, since bootconfig command verifies it when appending a boot config
to initrd image, user can notice it before boot.
devices
sysctl/index
+ abi
+
This section describes CPU vulnerabilities and their mitigations.
.. toctree::
mds=off [X86]
tsx_async_abort=off [X86]
kvm.nx_huge_pages=off [X86]
+ no_entry_flush [PPC]
+ no_uaccess_flush [PPC]
Exceptions:
This does not have any effect on
noefi Disable EFI runtime services support.
+ no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
+
noexec [IA-64]
noexec [X86]
nospec_store_bypass_disable
[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+ no_uaccess_flush
+ [PPC] Don't flush the L1-D cache after accessing user data.
+
noxsave [BUGS=X86] Disables x86 extended register state save
and restore using xsave. The kernel will fallback to
enabling legacy floating-point and sse state.
statistics of the given idle state. That information is exposed by the kernel
via ``sysfs``.
-For each CPU in the system, there is a :file:`/sys/devices/system/cpu<N>/cpuidle/`
+For each CPU in the system, there is a :file:`/sys/devices/system/cpu/cpu<N>/cpuidle/`
directory in ``sysfs``, where the number ``<N>`` is assigned to the given
CPU at the initialization time. That directory contains a set of subdirectories
called :file:`state0`, :file:`state1` and so on, up to the number of idle state
residency.
``below``
- Total number of times this idle state had been asked for, but cerainly
+ Total number of times this idle state had been asked for, but certainly
a deeper idle state would have been a better match for the observed idle
duration.
0: 0 1 2 3 4 5 6 7
RSS hash key:
84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
+
netdev_tstamp_prequeue
----------------------
* User Manual
http://dl.linux-sunxi.org/A64/Allwinner%20A64%20User%20Manual%20v1.0.pdf
+
+ - Allwinner H6
+
+ * Datasheet
+
+ https://linux-sunxi.org/images/5/5c/Allwinner_H6_V200_Datasheet_V1.1.pdf
+
+ * User Manual
+
+ https://linux-sunxi.org/images/4/46/Allwinner_H6_V200_User_Manual_V1.1.pdf
system call) are not checked if the user thread tag checking mode is
``PR_MTE_TCF_NONE`` or ``PR_MTE_TCF_ASYNC``. If the tag checking mode is
``PR_MTE_TCF_SYNC``, the kernel makes a best effort to check its user
-address accesses, however it cannot always guarantee it.
+address accesses, however it cannot always guarantee it. Kernel accesses
+to user addresses are always performed with an effective ``PSTATE.TCO``
+value of zero, regardless of the user configuration.
Excluding Tags in the ``IRG``, ``ADDG`` and ``SUBG`` instructions
-----------------------------------------------------------------
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Neoverse-N1 | #1349291 | N/A |
# ones.
extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include',
'kfigure', 'sphinx.ext.ifconfig', 'automarkup',
- 'maintainers_include', 'sphinx.ext.autosectionlabel' ]
+ 'maintainers_include', 'sphinx.ext.autosectionlabel',
+ 'kernel_abi']
#
# cdomain is badly broken in Sphinx 3+. Leaving it out generates *most*
support for Sphinx v3.0 and above is brand new. Be prepared for
possible issues in the generated output.
''')
- if minor > 0 or patch >= 2:
+ if (major > 3) or (minor > 0 or patch >= 2):
# Sphinx c function parser is more pedantic with regards to type
# checking. Due to that, having macros at c:function cause problems.
# Those needed to be scaped by using c_id_attributes[] array
pass::
ok 28 - kmalloc_double_kzfree
+
or, if kmalloc failed::
# kmalloc_large_oob_right: ASSERTION FAILED at lib/test_kasan.c:163
Expected ptr is not null, but is
not ok 4 - kmalloc_large_oob_right
+
or, if a KASAN report was expected, but not found::
# kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629
re-run kunit_tool.
5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This
may help clean up any residual config items which could be causing problems.
-6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be
+6. Finally, try running KUnit outside UML. KUnit and KUnit tests can be
built into any kernel, or can be built as a module and loaded at runtime.
Doing so should allow you to determine if UML is causing the issue you're
seeing. When tests are built-in, they will execute when the kernel boots, and
config MISC_EXAMPLE_TEST
bool "Test for my example"
- depends on MISC_EXAMPLE && KUNIT
+ depends on MISC_EXAMPLE && KUNIT=y
and the following to ``drivers/misc/Makefile``:
.. code-block:: none
- config FOO_KUNIT_TEST
- tristate "KUnit test for foo" if !KUNIT_ALL_TESTS
- depends on KUNIT
- default KUNIT_ALL_TESTS
- help
- This builds unit tests for foo.
+ config FOO_KUNIT_TEST
+ tristate "KUnit test for foo" if !KUNIT_ALL_TESTS
+ depends on KUNIT
+ default KUNIT_ALL_TESTS
+ help
+ This builds unit tests for foo.
- For more information on KUnit and unit tests in general, please refer
- to the KUnit documentation in Documentation/dev-tools/kunit
+ For more information on KUnit and unit tests in general, please refer
+ to the KUnit documentation in Documentation/dev-tools/kunit/.
- If unsure, say N
+ If unsure, say N.
Test File and Module Names
the second parameter, in this case, is what the value is expected to be; the
last value is what the value actually is. If ``add`` passes all of these
expectations, the test case, ``add_test_basic`` will pass; if any one of these
-expectations fail, the test case will fail.
+expectations fails, the test case will fail.
It is important to understand that a test case *fails* when any expectation is
violated; however, the test will continue running, potentially trying other
kunit_test_suite(example_test_suite);
In the above example the test suite, ``example_test_suite``, would run the test
-cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``,
+cases ``example_test_foo``, ``example_test_bar``, and ``example_test_baz``;
each would have ``example_test_init`` called immediately before it and would
have ``example_test_exit`` called immediately after it.
``kunit_test_suite(example_test_suite)`` registers the test suite with the
such that the definition of that function can be changed without affecting the
rest of the code base. In the kernel this primarily comes from two constructs,
classes, structs that contain function pointers that are provided by the
-implementer, and architecture specific functions which have definitions selected
+implementer, and architecture-specific functions which have definitions selected
at compile time.
Classes
By default KUnit uses UML as a way to provide dependencies for code under test.
Under most circumstances KUnit's usage of UML should be treated as an
implementation detail of how KUnit works under the hood. Nevertheless, there
-are instances where being able to run architecture specific code or test
+are instances where being able to run architecture-specific code or test
against real hardware is desirable. For these reasons KUnit supports running on
other architectures.
...will run the tests.
+.. note::
+ Note that you should make sure your test depends on ``KUNIT=y`` in Kconfig
+ if the test does not support module build. Otherwise, it will trigger
+ compile errors if ``CONFIG_KUNIT`` is ``m``.
+
Writing new tests for other architectures
-----------------------------------------
hardware state in between test cases; if this is not possible, you may only be
able to run one test case per invocation.
-.. TODO(brendanhiggins@google.com): Add an actual example of an architecture
+.. TODO(brendanhiggins@google.com): Add an actual example of an architecture-
dependent KUnit test.
KUnit debugfs representation
- enum:
- ucrobotics,bubblegum-96 # uCRobotics Bubblegum-96
- const: actions,s900
+
+additionalProperties: true
- altr,socfpga-arria5
- altr,socfpga-arria10
- const: altr,socfpga
+
+additionalProperties: true
+
...
- amazon,al-alpine-v3-evp
- const: amazon,al-alpine-v3
+additionalProperties: true
+
...
- enum:
- amlogic,ad401
- const: amlogic,a1
+
+additionalProperties: true
+
...
- compatible
- core-module@10000000
+additionalProperties: true
+
...
- compatible
- soc
+additionalProperties: true
+
...
- compatible
- core-module@10000000
+additionalProperties: true
+
...
required:
- arm,hbi
+additionalProperties: true
+
...
- const: atmel,samv71
- const: atmel,samv7
+additionalProperties: true
+
...
- const: lsi,axm5516-amarillo
- const: lsi,axm5516
+additionalProperties: true
+
...
- raspberrypi,3-compute-module-lite
- const: brcm,bcm2837
+additionalProperties: true
+
...
- brcm,bcm28155-ap
- const: brcm,bcm11351
+additionalProperties: true
+
...
- brcm,bcm21664-garnet
- const: brcm,bcm21664
+additionalProperties: true
+
...
- brcm,bcm23550-sparrow
- const: brcm,bcm23550
+additionalProperties: true
+
...
- const: brcm,brcm53012
- const: brcm,brcm53016
- const: brcm,bcm4708
+
+additionalProperties: true
+
...
- brcm,bcm58305
- const: brcm,cygnus
+additionalProperties: true
+
...
- const: brcm,bcm53342
- const: brcm,hr2
+additionalProperties: true
+
...
- brcm,ns2-xmc
- const: brcm,ns2
+additionalProperties: true
+
...
- brcm,bcm88312
- const: brcm,nsp
+additionalProperties: true
+
...
- brcm,bcm958802a802x
- const: brcm,stingray
+additionalProperties: true
+
...
- cavium,thunderx2-cn9900
- const: brcm,vulcan-soc
+additionalProperties: true
+
...
- enum:
- bitmain,sophon-edge
- const: bitmain,bm1880
+
+additionalProperties: true
+
...
- enum:
- calxeda,highbank
- calxeda,ecx-2000
+
+additionalProperties: true
compatible:
const: cnxt,cx92755
+additionalProperties: true
+
...
- fsl,s32v234-evb # S32V234-EVB2 Customer Evaluation Board
- const: fsl,s32v234
+additionalProperties: true
+
...
items:
- const: H836ASDJ
- const: hisilicon,sd5203
+
+additionalProperties: true
+
...
- enum:
- intel,keembay-evm
- const: intel,keembay
+
+additionalProperties: true
+
...
- enum:
- gateworks,gw2358
- const: intel,ixp43x
+
+additionalProperties: true
- description: TI-SCI processor id for the remote processor device
- description: TI-SCI host id to which processor control ownership
should be transferred to
+
+additionalProperties: true
- const: marvell,cn9130
- const: marvell,armada-ap807-quad
- const: marvell,armada-ap807
+
+additionalProperties: true
- const: google,krane-sku176
- const: google,krane
- const: mediatek,mt8183
+
+additionalProperties: true
+
...
- compatible
- axi@600000000
+additionalProperties: true
+
...
- const: moxa,moxart-uc-7112-lx
- const: moxa,moxart
+additionalProperties: true
...
- enum:
- dell,wyse-ariel
- const: marvell,mmp3
+
+additionalProperties: true
+
...
- enum:
- 70mai,midrived08 # 70mai midrive d08
- const: mstar,mercury5
+
+additionalProperties: true
- ea,ea3250
- phytec,phy3250
- const: nxp,lpc3250
+
+additionalProperties: true
...
- qcom,sm8250-mtp
- const: qcom,sm8250
+additionalProperties: true
+
...
- xunlong,orangepi-i96 # Orange Pi i96
- const: rda,8810pl
+additionalProperties: true
+
...
- enum:
- realtek,mjolnir # Realtek Mjolnir EVB
- const: realtek,rtd1619
+
+additionalProperties: true
+
...
- renesas,rzn1d400-db # RZN1D-DB (RZ/N1D Demo Board for the RZ/N1D 400 pins package)
- const: renesas,r9a06g032
+additionalProperties: true
+
...
items:
- const: zkmagic,a95x-z2
- const: rockchip,rk3318
+
+additionalProperties: true
+
...
required:
- compatible
+
+additionalProperties: true
- items:
- const: sirf,prima2-cb
- const: sirf,prima2
+
+additionalProperties: true
+
...
- enum:
- socionext,milbeaut-m10v-evb
- const: socionext,sc2000a
+
+additionalProperties: true
+
...
- enum:
- socionext,uniphier-pxs3-ref
- const: socionext,uniphier-pxs3
+
+additionalProperties: true
- st,spear320
- st,spear1310
- st,spear1340
+
+additionalProperties: true
+
...
- sprd,sp9863a-1h10
- const: sprd,sc9863a
+additionalProperties: true
+
...
- st,stih407
- st,stih410
- st,stih418
+
+additionalProperties: true
+
...
- const: st,stm32mp157
- description: Odyssey STM32MP1 SoM based Boards
items:
- - enum:
- - seeed,stm32mp157c-odyssey
- - const: seeed,stm32mp157c-odyssey-som
- - const: st,stm32mp157
+ - enum:
+ - seeed,stm32mp157c-odyssey
+ - const: seeed,stm32mp157c-odyssey-som
+ - const: st,stm32mp157
+
+additionalProperties: true
+
...
items:
- const: xunlong,orangepi-zero-plus2-h3
- const: allwinner,sun8i-h3
+
+additionalProperties: true
- enum:
- nvidia,tegra234-vdk
- const: nvidia,tegra234
+
+additionalProperties: true
- description: K3 J7200 SoC
items:
- const: ti,j7200
+
+additionalProperties: true
+
...
- ti,nspire-tp
# Clickpad models
- ti,nspire-clp
+
+additionalProperties: true
+
...
- enbw,cmc # EnBW AM1808 based CMC board
- lego,ev3 # LEGO MINDSTORMS EV3 (AM1808 based)
- const: ti,da850
+
+additionalProperties: true
+
...
- enum:
- toshiba,tmpv7708-rm-mbrc # TMPV7708 RM main board
- const: toshiba,tmpv7708
+
+additionalProperties: true
+
...
items:
- const: samsung,golden
- const: st-ericsson,u8500
+
+additionalProperties: true
- wm,wm8650
- wm,wm8750
- wm,wm8850
+
+additionalProperties: true
+
- const: xlnx,zynqmp-zcu111
- const: xlnx,zynqmp
+additionalProperties: true
+
...
- zte,zx296718-evb
- const: zte,zx296718
+additionalProperties: true
+
...
please refer the following document to know more about the binding rules
for these system controllers:
-Documentation/devicetree/bindings/arm/hisilicon/hisilicon.txt
+Documentation/devicetree/bindings/arm/hisilicon/hisilicon.yaml
Required Properties:
};
can@53fc8000 {
- compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan";
+ compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan";
reg = <0x53fc8000 0x4000>;
interrupts = <82>;
clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, <&clks IMX5_CLK_CAN1_SERIAL_GATE>;
resets:
maxItems: 1
+ wifi-2.4ghz-coexistence:
+ type: boolean
+ description: >
+ Should the pixel frequencies in the WiFi frequencies range be
+ avoided?
+
required:
- compatible
- reg
title: Toshiba TC358775 DSI to LVDS bridge bindings
maintainers:
- - Vinay Simha BN <simhavcs@gmail.com>
+ - Vinay Simha BN <simhavcs@gmail.com>
description: |
- This binding supports DSI to LVDS bridge TC358775
+ This binding supports DSI to LVDS bridge TC358775
- MIPI DSI-RX Data 4-lane, CLK 1-lane with data rates up to 800 Mbps/lane.
- Video frame size:
- Up to 1600x1200 24-bit/pixel resolution for single-link LVDS display panel
- limited by 135 MHz LVDS speed
- Up to WUXGA (1920x1200 24-bit pixels) resolution for dual-link LVDS display
- panel, limited by 270 MHz LVDS speed.
+ MIPI DSI-RX Data 4-lane, CLK 1-lane with data rates up to 800 Mbps/lane.
+ Video frame size:
+ Up to 1600x1200 24-bit/pixel resolution for single-link LVDS display panel
+ limited by 135 MHz LVDS speed
+ Up to WUXGA (1920x1200 24-bit pixels) resolution for dual-link LVDS display
+ panel, limited by 270 MHz LVDS speed.
properties:
compatible:
vdd-supply:
maxItems: 1
- description: 1.2V LVDS Power Supply
+ description: 1.2V LVDS Power Supply
vddio-supply:
maxItems: 1
- port@1
required:
- - compatible
- - reg
- - vdd-supply
- - vddio-supply
- - stby-gpios
- - reset-gpios
- - ports
+ - compatible
+ - reg
+ - vdd-supply
+ - vddio-supply
+ - stby-gpios
+ - reset-gpios
+ - ports
+
+additionalProperties: false
examples:
- - |
+ - |
#include <dt-bindings/gpio/gpio.h>
/* For single-link LVDS display panel */
};
};
- - |
+ - |
/* For dual-link LVDS display panel */
i2c@78b8000 {
compatible:
items:
- enum:
- - bananapi,lhr050h41
- - feixin,k101-im2byl02
-
+ - bananapi,lhr050h41
+ - feixin,k101-im2byl02
- const: ilitek,ili9881c
backlight: true
reset-gpios: true
+ 'mantix,tp-rstn-gpios':
+ description: second reset line that triggers DSI config load
+
backlight: true
required:
avee-supply = <®_avee>;
vddi-supply = <®_1v8_p>;
reset-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>;
+ mantix,tp-rstn-gpios = <&gpio1 24 GPIO_ACTIVE_LOW>;
backlight = <&backlight>;
};
};
- "#address-cells"
- "#size-cells"
+additionalProperties: false
examples:
- |
-Aspeed AST2500 SoC EDAC node
+Aspeed BMC SoC EDAC node
-The Aspeed AST2500 SoC supports DDR3 and DDR4 memory with and without ECC (error
+The Aspeed BMC SoC supports DDR3 and DDR4 memory with and without ECC (error
correction check).
The memory controller supports SECDED (single bit error correction, double bit
Required properties:
-- compatible: should be "aspeed,ast2500-sdram-edac"
+- compatible: should be one of
+ - "aspeed,ast2400-sdram-edac"
+ - "aspeed,ast2500-sdram-edac"
+ - "aspeed,ast2600-sdram-edac"
- reg: sdram controller register set should be <0x1e6e0000 0x174>
- interrupts: should be AVIC interrupt #0
at25,byte-len:
$ref: /schemas/types.yaml#/definitions/uint32
description:
- Total eeprom size in bytes. Deprecated, use "size" property instead.
+ Total eeprom size in bytes. Deprecated, use "size" property instead.
deprecated: true
at25,addr-mode:
$ref: /schemas/types.yaml#/definitions/uint32
description:
- Addr-mode flags, as defined in include/linux/spi/eeprom.h.
- Deprecated, use "address-width" property instead.
+ Addr-mode flags, as defined in include/linux/spi/eeprom.h.
+ Deprecated, use "address-width" property instead.
deprecated: true
at25,page-size:
gpio-controller: true
gpio-line-names:
- minItems: 1
- maxItems: 8
+ minItems: 1
+ maxItems: 8
required:
- compatible
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+
+$id: http://devicetree.org/schemas/i2c/google,cros-ec-i2c-tunnel.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: I2C bus that tunnels through the ChromeOS EC (cros-ec)
+
+maintainers:
+ - Doug Anderson <dianders@chromium.org>
+ - Benson Leung <bleung@chromium.org>
+ - Enric Balletbo i Serra <enric.balletbo@collabora.com>
+
+description: |
+ On some ChromeOS board designs we've got a connection to the EC
+ (embedded controller) but no direct connection to some devices on the
+ other side of the EC (like a battery and PMIC). To get access to
+ those devices we need to tunnel our i2c commands through the EC.
+
+ The node for this device should be under a cros-ec node like
+ google,cros-ec-spi or google,cros-ec-i2c.
+
+allOf:
+ - $ref: i2c-controller.yaml#
+
+properties:
+ compatible:
+ const: google,cros-ec-i2c-tunnel
+
+ google,remote-bus:
+ description: The EC bus we'd like to talk to.
+ $ref: /schemas/types.yaml#/definitions/uint32
+
+required:
+ - compatible
+ - google,remote-bus
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ spi0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cros-ec@0 {
+ compatible = "google,cros-ec-spi";
+ reg = <0>;
+ spi-max-frequency = <5000000>;
+
+ i2c-tunnel {
+ compatible = "google,cros-ec-i2c-tunnel";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ google,remote-bus = <0>;
+
+ battery: sbs-battery@b {
+ compatible = "sbs,sbs-battery";
+ reg = <0xb>;
+ sbs,poll-retry-count = <1>;
+ };
+ };
+ };
+ };
+++ /dev/null
-I2C bus that tunnels through the ChromeOS EC (cros-ec)
-======================================================
-On some ChromeOS board designs we've got a connection to the EC (embedded
-controller) but no direct connection to some devices on the other side of
-the EC (like a battery and PMIC). To get access to those devices we need
-to tunnel our i2c commands through the EC.
-
-The node for this device should be under a cros-ec node like google,cros-ec-spi
-or google,cros-ec-i2c.
-
-
-Required properties:
-- compatible: google,cros-ec-i2c-tunnel
-- google,remote-bus: The EC bus we'd like to talk to.
-
-Optional child nodes:
-- One node per I2C device connected to the tunnelled I2C bus.
-
-
-Example:
- cros-ec@0 {
- compatible = "google,cros-ec-spi";
-
- ...
-
- i2c-tunnel {
- compatible = "google,cros-ec-i2c-tunnel";
- #address-cells = <1>;
- #size-cells = <0>;
-
- google,remote-bus = <0>;
-
- battery: sbs-battery@b {
- compatible = "sbs,sbs-battery";
- reg = <0xb>;
- sbs,poll-retry-count = <1>;
- };
- };
- }
compatible:
oneOf:
- enum:
- - ingenic,jz4770-i2c
- - ingenic,x1000-i2c
+ - ingenic,jz4770-i2c
+ - ingenic,x1000-i2c
- items:
- - const: ingenic,jz4780-i2c
- - const: ingenic,jz4770-i2c
+ - const: ingenic,jz4780-i2c
+ - const: ingenic,jz4770-i2c
reg:
maxItems: 1
vref-supply = <&adc_vref>;
};
};
-...
\ No newline at end of file
+...
+
spi-max-frequency: true
spi-cpol: true
- spi-cpha : true
+
+ spi-cpha: true
"#io-channel-cells":
const: 1
adc-reserved-channels:
$ref: /schemas/types.yaml#/definitions/uint32
description:
- Bitmask of reserved channels, i.e. channels that cannot be
- used by the OS.
+ Bitmask of reserved channels, i.e. channels that cannot be
+ used by the OS.
clocks:
maxItems: 1
gpios:
description:
- GPIO used for controlling the reset pin
+ GPIO used for controlling the reset pin
maxItems: 1
spi-max-frequency: true
- reg
- vref-supply
+additionalProperties: false
+
examples:
- |
i2c {
- compatible
- reg
+additionalProperties: false
+
examples:
- |
i2c0 {
+++ /dev/null
-ChromeOS EC Keyboard
-
-Google's ChromeOS EC Keyboard is a simple matrix keyboard implemented on
-a separate EC (Embedded Controller) device. It provides a message for reading
-key scans from the EC. These are then converted into keycodes for processing
-by the kernel.
-
-This binding is based on matrix-keymap.txt and extends/modifies it as follows:
-
-Required properties:
-- compatible: "google,cros-ec-keyb"
-
-Optional properties:
-- google,needs-ghost-filter: True to enable a ghost filter for the matrix
-keyboard. This is recommended if the EC does not have its own logic or
-hardware for this.
-
-
-Example:
-
-cros-ec-keyb {
- compatible = "google,cros-ec-keyb";
- keypad,num-rows = <8>;
- keypad,num-columns = <13>;
- google,needs-ghost-filter;
- /*
- * Keymap entries take the form of 0xRRCCKKKK where
- * RR=Row CC=Column KKKK=Key Code
- * The values below are for a US keyboard layout and
- * are taken from the Linux driver. Note that the
- * 102ND key is not used for US keyboards.
- */
- linux,keymap = <
- /* CAPSLCK F1 B F10 */
- 0x0001003a 0x0002003b 0x00030030 0x00040044
- /* N = R_ALT ESC */
- 0x00060031 0x0008000d 0x000a0064 0x01010001
- /* F4 G F7 H */
- 0x0102003e 0x01030022 0x01040041 0x01060023
- /* ' F9 BKSPACE L_CTRL */
- 0x01080028 0x01090043 0x010b000e 0x0200001d
- /* TAB F3 T F6 */
- 0x0201000f 0x0202003d 0x02030014 0x02040040
- /* ] Y 102ND [ */
- 0x0205001b 0x02060015 0x02070056 0x0208001a
- /* F8 GRAVE F2 5 */
- 0x02090042 0x03010029 0x0302003c 0x03030006
- /* F5 6 - \ */
- 0x0304003f 0x03060007 0x0308000c 0x030b002b
- /* R_CTRL A D F */
- 0x04000061 0x0401001e 0x04020020 0x04030021
- /* S K J ; */
- 0x0404001f 0x04050025 0x04060024 0x04080027
- /* L ENTER Z C */
- 0x04090026 0x040b001c 0x0501002c 0x0502002e
- /* V X , M */
- 0x0503002f 0x0504002d 0x05050033 0x05060032
- /* L_SHIFT / . SPACE */
- 0x0507002a 0x05080035 0x05090034 0x050B0039
- /* 1 3 4 2 */
- 0x06010002 0x06020004 0x06030005 0x06040003
- /* 8 7 0 9 */
- 0x06050009 0x06060008 0x0608000b 0x0609000a
- /* L_ALT DOWN RIGHT Q */
- 0x060a0038 0x060b006c 0x060c006a 0x07010010
- /* E R W I */
- 0x07020012 0x07030013 0x07040011 0x07050017
- /* U R_SHIFT P O */
- 0x07060016 0x07070036 0x07080019 0x07090018
- /* UP LEFT */
- 0x070b0067 0x070c0069>;
-};
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+
+$id: http://devicetree.org/schemas/input/google,cros-ec-keyb.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ChromeOS EC Keyboard
+
+maintainers:
+ - Simon Glass <sjg@chromium.org>
+ - Benson Leung <bleung@chromium.org>
+ - Enric Balletbo i Serra <enric.balletbo@collabora.com>
+
+description: |
+ Google's ChromeOS EC Keyboard is a simple matrix keyboard
+ implemented on a separate EC (Embedded Controller) device. It provides
+ a message for reading key scans from the EC. These are then converted
+ into keycodes for processing by the kernel.
+
+allOf:
+ - $ref: "/schemas/input/matrix-keymap.yaml#"
+
+properties:
+ compatible:
+ const: google,cros-ec-keyb
+
+ google,needs-ghost-filter:
+ description:
+ Enable a ghost filter for the matrix keyboard. This is recommended
+ if the EC does not have its own logic or hardware for this.
+ type: boolean
+
+required:
+ - compatible
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ cros-ec-keyb {
+ compatible = "google,cros-ec-keyb";
+ keypad,num-rows = <8>;
+ keypad,num-columns = <13>;
+ google,needs-ghost-filter;
+ /*
+ * Keymap entries take the form of 0xRRCCKKKK where
+ * RR=Row CC=Column KKKK=Key Code
+ * The values below are for a US keyboard layout and
+ * are taken from the Linux driver. Note that the
+ * 102ND key is not used for US keyboards.
+ */
+ linux,keymap = <
+ /* CAPSLCK F1 B F10 */
+ 0x0001003a 0x0002003b 0x00030030 0x00040044
+ /* N = R_ALT ESC */
+ 0x00060031 0x0008000d 0x000a0064 0x01010001
+ /* F4 G F7 H */
+ 0x0102003e 0x01030022 0x01040041 0x01060023
+ /* ' F9 BKSPACE L_CTRL */
+ 0x01080028 0x01090043 0x010b000e 0x0200001d
+ /* TAB F3 T F6 */
+ 0x0201000f 0x0202003d 0x02030014 0x02040040
+ /* ] Y 102ND [ */
+ 0x0205001b 0x02060015 0x02070056 0x0208001a
+ /* F8 GRAVE F2 5 */
+ 0x02090042 0x03010029 0x0302003c 0x03030006
+ /* F5 6 - \ */
+ 0x0304003f 0x03060007 0x0308000c 0x030b002b
+ /* R_CTRL A D F */
+ 0x04000061 0x0401001e 0x04020020 0x04030021
+ /* S K J ; */
+ 0x0404001f 0x04050025 0x04060024 0x04080027
+ /* L ENTER Z C */
+ 0x04090026 0x040b001c 0x0501002c 0x0502002e
+ /* V X , M */
+ 0x0503002f 0x0504002d 0x05050033 0x05060032
+ /* L_SHIFT / . SPACE */
+ 0x0507002a 0x05080035 0x05090034 0x050B0039
+ /* 1 3 4 2 */
+ 0x06010002 0x06020004 0x06030005 0x06040003
+ /* 8 7 0 9 */
+ 0x06050009 0x06060008 0x0608000b 0x0609000a
+ /* L_ALT DOWN RIGHT Q */
+ 0x060a0038 0x060b006c 0x060c006a 0x07010010
+ /* E R W I */
+ 0x07020012 0x07030013 0x07040011 0x07050017
+ /* U R_SHIFT P O */
+ 0x07060016 0x07070036 0x07080019 0x07090018
+ /* UP LEFT */
+ 0x070b0067 0x070c0069>;
+ };
instances.
required:
- - compatible
- - reg
- - interrupts
- - interrupt-names
- - interrupt-controller
- - "#interrupt-cells"
+ - compatible
+ - reg
+ - interrupts
+ - interrupt-names
+ - interrupt-controller
+ - "#interrupt-cells"
additionalProperties: false
| | vint | bit | | 0 |.....|63| vintx |
| +--------------+ +------------+ |
| |
+ | Unmap |
+ | +--------------+ |
+ Unmapped events ---->| | umapidx |-------------------------> Globalevents
+ | +--------------+ |
+ | |
+-----------------------------------------+
Configuration of these Intmap registers that maps global events to vint is
- description: |
"limit" specifies the limit for translation
+ ti,unmapped-event-sources:
+ $ref: /schemas/types.yaml#definitions/phandle-array
+ description:
+ Array of phandles to DMA controllers where the unmapped events originate.
+
required:
- compatible
- reg
- ti,sci-dev-id
- ti,interrupt-ranges
+unevaluatedProperties: false
+
examples:
- |
bus {
- ti,sci-dev-id
- ti,interrupt-ranges
+unevaluatedProperties: false
+
examples:
- |
main_gpio_intr: interrupt-controller0 {
that a LED can be made so bright that it gets damaged or causes damage
due to restrictions in a specific system, such as mounting conditions.
$ref: /schemas/types.yaml#definitions/uint32
+
+additionalProperties: true
LED_COLOR_ID available, add a new one.
$ref: /schemas/types.yaml#definitions/uint32
minimum: 0
- maximum: 8
+ maximum: 9
function-enumerator:
description:
modules. This is achieved by adding multi-led nodes layer to the
monochrome LED bindings.
The nodes and properties defined in this document are unique to the multicolor
- LED class. Common LED nodes and properties are inherited from the common.txt
+ LED class. Common LED nodes and properties are inherited from the common.yaml
within this documentation directory.
patternProperties:
description: Represents the LEDs that are to be grouped.
properties:
color:
- const: 8 # LED_COLOR_ID_MULTI
description: |
- For multicolor LED support this property should be defined as
- LED_COLOR_ID_MULTI which can be found in include/linux/leds/common.h.
+ For multicolor LED support this property should be defined as either
+ LED_COLOR_ID_RGB or LED_COLOR_ID_MULTI which can be found in
+ include/linux/leds/common.h.
+ enum: [ 8, 9 ]
$ref: "common.yaml#"
vled-supply:
description: LED supply.
+ '#address-cells':
+ const: 1
+
+ '#size-cells':
+ const: 0
+
patternProperties:
'^multi-led@[0-9a-f]$':
type: object
- compatible
- reg
+additionalProperties: false
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_LOW>;
clocks = <&infracfg CLK_INFRA_GCE>;
clock-names = "gce";
- #mbox-cells = <3>;
+ #mbox-cells = <2>;
};
Example for a client device:
compatible:
items:
- enum:
- - dell,wyse-ariel-ec # Dell Wyse Ariel board (3020)
+ - dell,wyse-ariel-ec # Dell Wyse Ariel board (3020)
- const: ene,kb3930
reg:
maxItems: 1
whether this nvram is present or not.
type: boolean
+ mtk,rpmsg-name:
+ description:
+ Must be defined if the cros-ec is a rpmsg device for a Mediatek
+ ARM Cortex M4 Co-processor. Contains the name pf the rpmsg
+ device. Used to match the subnode to the rpmsg device announced by
+ the SCP.
+ $ref: "/schemas/types.yaml#/definitions/string"
+
spi-max-frequency:
description: Maximum SPI frequency of the device in Hz.
wakeup-source:
description: Button can wake-up the system.
+ '#address-cells':
+ const: 1
+
+ '#size-cells':
+ const: 0
+
+ typec:
+ $ref: "/schemas/chrome/google,cros-ec-typec.yaml#"
+
+ ec-pwm:
+ $ref: "/schemas/pwm/google,cros-ec-pwm.yaml#"
+
+ keyboard-controller:
+ $ref: "/schemas/input/google,cros-ec-keyb.yaml#"
+
+ codecs:
+ type: object
+ additionalProperties: false
+
+ properties:
+ '#address-cells':
+ const: 2
+
+ '#size-cells':
+ const: 1
+
+ patternProperties:
+ "^ec-codec@[a-f0-9]+$":
+ type: object
+ $ref: "/schemas/sound/google,cros-ec-codec.yaml#"
+
+ required:
+ - "#address-cells"
+ - "#size-cells"
+
+patternProperties:
+ "^i2c-tunnel[0-9]*$":
+ type: object
+ $ref: "/schemas/i2c/google,cros-ec-i2c-tunnel.yaml#"
+
+ "^regulator@[0-9]+$":
+ type: object
+ $ref: "/schemas/regulator/google,cros-ec-regulator.yaml#"
+
+ "^extcon[0-9]*$":
+ type: object
+ $ref: "/schemas/extcon/extcon-usbc-cros-ec.yaml#"
+
required:
- compatible
items:
- const: yna,cu2000-neo
- const: ingenic,x2000e
+
+additionalProperties: true
+
...
- description: Virtual Loongson64 Quad Core + VirtIO
items:
- const: loongson,loongson64v-4core-virtio
+
+additionalProperties: true
+
...
clock-output-names:
oneOf:
- items:
- - const: clk_out_sd0
- - const: clk_in_sd0
+ - const: clk_out_sd0
+ - const: clk_in_sd0
- items:
- - const: clk_out_sd1
- - const: clk_in_sd1
+ - const: clk_out_sd1
+ - const: clk_in_sd1
properties:
compatible:
- clocks
- clock-names
+unevaluatedProperties: false
+
examples:
- |
#include <dt-bindings/interrupt-controller/arm-gic.h>
%YAML 1.2
---
$id: "http://devicetree.org/schemas/mmc/sdhci-am654.yaml#"
-$schema : "http://devicetree.org/meta-schemas/core.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: TI AM654 MMC Controller
ti,driver-strength-ohm:
description: DLL drive strength in ohms
$ref: "/schemas/types.yaml#/definitions/uint32"
- oneOf:
- - enum:
- - 33
- - 40
- - 50
- - 66
- - 100
+ enum:
+ - 33
+ - 40
+ - 50
+ - 66
+ - 100
ti,strobe-sel:
description: strobe select delay for HS400 speed mode.
- clock-names
- ti,otap-del-sel-legacy
+unevaluatedProperties: false
+
examples:
- |
#include <dt-bindings/interrupt-controller/irq.h>
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/can-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: CAN Controller Generic Binding
+
+maintainers:
+ - Marc Kleine-Budde <mkl@pengutronix.de>
+
+properties:
+ $nodename:
+ pattern: "^can(@.*)?$"
+
+additionalProperties: true
+
+...
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/fsl,flexcan.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title:
+ Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
+
+maintainers:
+ - Marc Kleine-Budde <mkl@pengutronix.de>
+
+allOf:
+ - $ref: can-controller.yaml#
+
+properties:
+ compatible:
+ oneOf:
+ - enum:
+ - fsl,imx8qm-flexcan
+ - fsl,imx8mp-flexcan
+ - fsl,imx6q-flexcan
+ - fsl,imx28-flexcan
+ - fsl,imx25-flexcan
+ - fsl,p1010-flexcan
+ - fsl,vf610-flexcan
+ - fsl,ls1021ar2-flexcan
+ - fsl,lx2160ar1-flexcan
+ - items:
+ - enum:
+ - fsl,imx53-flexcan
+ - fsl,imx35-flexcan
+ - const: fsl,imx25-flexcan
+ - items:
+ - enum:
+ - fsl,imx7d-flexcan
+ - fsl,imx6ul-flexcan
+ - fsl,imx6sx-flexcan
+ - const: fsl,imx6q-flexcan
+ - items:
+ - enum:
+ - fsl,ls1028ar1-flexcan
+ - const: fsl,lx2160ar1-flexcan
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ maxItems: 1
+
+ clocks:
+ maxItems: 2
+
+ clock-names:
+ items:
+ - const: ipg
+ - const: per
+
+ clock-frequency:
+ description: |
+ The oscillator frequency driving the flexcan device, filled in by the
+ boot loader. This property should only be used the used operating system
+ doesn't support the clocks and clock-names property.
+
+ xceiver-supply:
+ description: Regulator that powers the CAN transceiver.
+
+ big-endian:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description: |
+ This means the registers of FlexCAN controller are big endian. This is
+ optional property.i.e. if this property is not present in device tree
+ node then controller is assumed to be little endian. If this property is
+ present then controller is assumed to be big endian.
+
+ fsl,stop-mode:
+ description: |
+ Register bits of stop mode control.
+
+ The format should be as follows:
+ <gpr req_gpr req_bit>
+ gpr is the phandle to general purpose register node.
+ req_gpr is the gpr register offset of CAN stop request.
+ req_bit is the bit offset of CAN stop request.
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ items:
+ items:
+ - description: The 'gpr' is the phandle to general purpose register node.
+ - description: The 'req_gpr' is the gpr register offset of CAN stop request.
+ maximum: 0xff
+ - description: The 'req_bit' is the bit offset of CAN stop request.
+ maximum: 0x1f
+
+ fsl,clk-source:
+ description: |
+ Select the clock source to the CAN Protocol Engine (PE). It's SoC
+ implementation dependent. Refer to RM for detailed definition. If this
+ property is not set in device tree node then driver selects clock source 1
+ by default.
+ 0: clock source 0 (oscillator clock)
+ 1: clock source 1 (peripheral clock)
+ $ref: /schemas/types.yaml#/definitions/uint32
+ default: 1
+ minimum: 0
+ maximum: 1
+
+ wakeup-source:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Enable CAN remote wakeup.
+
+required:
+ - compatible
+ - reg
+ - interrupts
+
+additionalProperties: false
+
+examples:
+ - |
+ can@1c000 {
+ compatible = "fsl,p1010-flexcan";
+ reg = <0x1c000 0x1000>;
+ interrupts = <48 0x2>;
+ interrupt-parent = <&mpic>;
+ clock-frequency = <200000000>;
+ fsl,clk-source = <0>;
+ };
+ - |
+ #include <dt-bindings/interrupt-controller/irq.h>
+
+ can@2090000 {
+ compatible = "fsl,imx6q-flexcan";
+ reg = <0x02090000 0x4000>;
+ interrupts = <0 110 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clks 1>, <&clks 2>;
+ clock-names = "ipg", "per";
+ fsl,stop-mode = <&gpr 0x34 28>;
+ };
+++ /dev/null
-Flexcan CAN controller on Freescale's ARM and PowerPC system-on-a-chip (SOC).
-
-Required properties:
-
-- compatible : Should be "fsl,<processor>-flexcan"
-
- where <processor> is imx8qm, imx6q, imx28, imx53, imx35, imx25, p1010,
- vf610, ls1021ar2, lx2160ar1, ls1028ar1.
-
- The ls1028ar1 must be followed by lx2160ar1, e.g.
- - "fsl,ls1028ar1-flexcan", "fsl,lx2160ar1-flexcan"
-
- An implementation should also claim any of the following compatibles
- that it is fully backwards compatible with:
-
- - fsl,p1010-flexcan
-
-- reg : Offset and length of the register set for this device
-- interrupts : Interrupt tuple for this device
-
-Optional properties:
-
-- clock-frequency : The oscillator frequency driving the flexcan device
-
-- xceiver-supply: Regulator that powers the CAN transceiver
-
-- big-endian: This means the registers of FlexCAN controller are big endian.
- This is optional property.i.e. if this property is not present in
- device tree node then controller is assumed to be little endian.
- if this property is present then controller is assumed to be big
- endian.
-
-- fsl,stop-mode: register bits of stop mode control, the format is
- <&gpr req_gpr req_bit>.
- gpr is the phandle to general purpose register node.
- req_gpr is the gpr register offset of CAN stop request.
- req_bit is the bit offset of CAN stop request.
-
-- fsl,clk-source: Select the clock source to the CAN Protocol Engine (PE).
- It's SoC Implementation dependent. Refer to RM for detailed
- definition. If this property is not set in device tree node
- then driver selects clock source 1 by default.
- 0: clock source 0 (oscillator clock)
- 1: clock source 1 (peripheral clock)
-
-- wakeup-source: enable CAN remote wakeup
-
-Example:
-
- can@1c000 {
- compatible = "fsl,p1010-flexcan";
- reg = <0x1c000 0x1000>;
- interrupts = <48 0x2>;
- interrupt-parent = <&mpic>;
- clock-frequency = <200000000>; // filled in by bootloader
- fsl,clk-source = <0>; // select clock source 0 for PE
- };
spi-max-frequency = <10000000>;
bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>;
interrupt-parent = <&gpio1>;
- interrupts = <14 GPIO_ACTIVE_LOW>;
+ interrupts = <14 IRQ_TYPE_LEVEL_LOW>;
device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>;
reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>;
- clocks
- clock-names
+unevaluatedProperties: false
+
examples:
# FIXME: Remove defines and include the correct header file
# once it is available in mainline.
clock-frequency = <100000>;
interrupt-parent = <&gpio1>;
- interrupts = <29 GPIO_ACTIVE_HIGH>;
+ interrupts = <29 IRQ_TYPE_LEVEL_HIGH>;
enable-gpios = <&gpio0 30 GPIO_ACTIVE_HIGH>;
firmware-gpios = <&gpio0 31 GPIO_ACTIVE_HIGH>;
clock-frequency = <400000>;
interrupt-parent = <&gpio1>;
- interrupts = <17 GPIO_ACTIVE_HIGH>;
+ interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
required:
- reg
+unevaluatedProperties: false
+
examples:
- |
mdio0 {
reg-names:
oneOf:
- items:
- - const: dbi
- - const: dbi2
- - const: link
- - const: addr_space
+ - const: dbi
+ - const: dbi2
+ - const: link
+ - const: addr_space
- items:
- - const: dbi
- - const: dbi2
- - const: link
- - const: addr_space
- - const: atu
+ - const: dbi
+ - const: dbi2
+ - const: link
+ - const: addr_space
+ - const: atu
clocks:
maxItems: 2
clock-names:
oneOf:
- items: # for PXs2
- - const: link
+ - const: link
- items: # for others
- - const: link
- - const: phy
+ - const: link
+ - const: phy
resets:
maxItems: 2
title: OMAP USB2 PHY
maintainers:
- - Kishon Vijay Abraham I <kishon@ti.com>
- - Roger Quadros <rogerq@ti.com>
+ - Kishon Vijay Abraham I <kishon@ti.com>
+ - Roger Quadros <rogerq@ti.com>
properties:
compatible:
oneOf:
- items:
- - enum:
- - ti,dra7x-usb2
- - ti,dra7x-usb2-phy2
- - ti,am654-usb2
- - enum:
- - ti,omap-usb2
+ - enum:
+ - ti,dra7x-usb2
+ - ti,dra7x-usb2-phy2
+ - ti,am654-usb2
+ - enum:
+ - ti,omap-usb2
- items:
- - const: ti,am437x-usb2
+ - const: ti,am437x-usb2
- items:
- - const: ti,omap-usb2
+ - const: ti,omap-usb2
reg:
maxItems: 1
- clocks
- clock-names
+additionalProperties: false
+
examples:
- |
usb0_phy: phy@4100000 {
items:
oneOf:
- enum: [lcd0_d18_mfp, rmii_crs_dv_mfp, rmii_txd0_mfp,
- rmii_txd1_mfp, rmii_txen_mfp, rmii_rxen_mfp, rmii_rxd1_mfp,
- rmii_rxd0_mfp, rmii_ref_clk_mfp, i2s_d0_mfp, i2s_pcm1_mfp,
- i2s0_pcm0_mfp, i2s1_pcm0_mfp, i2s_d1_mfp, ks_in2_mfp,
- ks_in1_mfp, ks_in0_mfp, ks_in3_mfp, ks_out0_mfp,
- ks_out1_mfp, ks_out2_mfp, lvds_o_pn_mfp, dsi_dn0_mfp,
- dsi_dp2_mfp, lcd0_d17_mfp, dsi_dp3_mfp, dsi_dn3_mfp,
- dsi_dp0_mfp, lvds_ee_pn_mfp, spi0_i2c_pcm_mfp,
- spi0_i2s_pcm_mfp, dsi_dnp1_cp_mfp, lvds_e_pn_mfp,
- dsi_dn2_mfp, uart2_rtsb_mfp, uart2_ctsb_mfp, uart3_rtsb_mfp,
- uart3_ctsb_mfp, sd0_d0_mfp, sd0_d1_mfp, sd0_d2_d3_mfp,
- sd1_d0_d3_mfp, sd0_cmd_mfp, sd0_clk_mfp, sd1_cmd_mfp,
- uart0_rx_mfp, clko_25m_mfp, csi_cn_cp_mfp, sens0_ckout_mfp,
- uart0_tx_mfp, i2c0_mfp, csi_dn_dp_mfp, sen0_pclk_mfp,
- pcm1_in_mfp, pcm1_clk_mfp, pcm1_sync_mfp, pcm1_out_mfp,
- dnand_data_wr_mfp, dnand_acle_ce0_mfp, nand_ceb2_mfp,
- nand_ceb3_mfp]
+ rmii_txd1_mfp, rmii_txen_mfp, rmii_rxen_mfp, rmii_rxd1_mfp,
+ rmii_rxd0_mfp, rmii_ref_clk_mfp, i2s_d0_mfp, i2s_pcm1_mfp,
+ i2s0_pcm0_mfp, i2s1_pcm0_mfp, i2s_d1_mfp, ks_in2_mfp,
+ ks_in1_mfp, ks_in0_mfp, ks_in3_mfp, ks_out0_mfp,
+ ks_out1_mfp, ks_out2_mfp, lvds_o_pn_mfp, dsi_dn0_mfp,
+ dsi_dp2_mfp, lcd0_d17_mfp, dsi_dp3_mfp, dsi_dn3_mfp,
+ dsi_dp0_mfp, lvds_ee_pn_mfp, spi0_i2c_pcm_mfp,
+ spi0_i2s_pcm_mfp, dsi_dnp1_cp_mfp, lvds_e_pn_mfp,
+ dsi_dn2_mfp, uart2_rtsb_mfp, uart2_ctsb_mfp, uart3_rtsb_mfp,
+ uart3_ctsb_mfp, sd0_d0_mfp, sd0_d1_mfp, sd0_d2_d3_mfp,
+ sd1_d0_d3_mfp, sd0_cmd_mfp, sd0_clk_mfp, sd1_cmd_mfp,
+ uart0_rx_mfp, clko_25m_mfp, csi_cn_cp_mfp, sens0_ckout_mfp,
+ uart0_tx_mfp, i2c0_mfp, csi_dn_dp_mfp, sen0_pclk_mfp,
+ pcm1_in_mfp, pcm1_clk_mfp, pcm1_sync_mfp, pcm1_out_mfp,
+ dnand_data_wr_mfp, dnand_acle_ce0_mfp, nand_ceb2_mfp,
+ nand_ceb3_mfp]
minItems: 1
maxItems: 32
Specify the alternative function to be configured for the
given gpio pin groups.
enum: [nor, eth_rmii, eth_smii, spi0, spi1, spi2, spi3, sens0,
- sens1, uart0, uart1, uart2, uart3, uart4, uart5, uart6, i2s0,
- i2s1, pcm1, pcm0, ks, jtag, pwm0, pwm1, pwm2, pwm3, pwm4, pwm5,
- p0, sd0, sd1, sd2, i2c0, i2c1, i2c3, dsi, lvds, usb30, clko_25m,
- mipi_csi, nand, spdif, ts, lcd0]
+ sens1, uart0, uart1, uart2, uart3, uart4, uart5, uart6, i2s0,
+ i2s1, pcm1, pcm0, ks, jtag, pwm0, pwm1, pwm2, pwm3, pwm4, pwm5,
+ p0, sd0, sd1, sd2, i2c0, i2c1, i2c3, dsi, lvds, usb30, clko_25m,
+ mipi_csi, nand, spdif, ts, lcd0]
required:
- groups
items:
oneOf:
- enum: [sirq_drv, rmii_txd01_txen_drv, rmii_rxer_drv,
- rmii_crs_drv, rmii_rxd10_drv, rmii_ref_clk_drv,
- smi_mdc_mdio_drv, i2s_d0_drv, i2s_bclk0_drv, i2s3_drv,
- i2s13_drv, pcm1_drv, ks_in_drv, ks_out_drv, lvds_all_drv,
- lcd_dsi_drv, dsi_drv, sd0_d0_d3_drv, sd1_d0_d3_drv,
- sd0_cmd_drv, sd0_clk_drv, sd1_cmd_drv, sd1_clk_drv,
- spi0_all_drv, uart0_rx_drv, uart0_tx_drv, uart2_all_drv,
- i2c0_all_drv, i2c12_all_drv, sens0_pclk_drv,
- sens0_ckout_drv, uart3_all_drv]
+ rmii_crs_drv, rmii_rxd10_drv, rmii_ref_clk_drv,
+ smi_mdc_mdio_drv, i2s_d0_drv, i2s_bclk0_drv, i2s3_drv,
+ i2s13_drv, pcm1_drv, ks_in_drv, ks_out_drv, lvds_all_drv,
+ lcd_dsi_drv, dsi_drv, sd0_d0_d3_drv, sd1_d0_d3_drv,
+ sd0_cmd_drv, sd0_clk_drv, sd1_cmd_drv, sd1_clk_drv,
+ spi0_all_drv, uart0_rx_drv, uart0_tx_drv, uart2_all_drv,
+ i2c0_all_drv, i2c12_all_drv, sens0_pclk_drv,
+ sens0_ckout_drv, uart3_all_drv]
minItems: 1
maxItems: 32
items:
oneOf:
- enum: [dnand_dqs, dnand_dqsn, eth_txd0, eth_txd1, eth_txen,
- eth_rxer, eth_crs_dv, eth_rxd1, eth_rxd0, eth_ref_clk,
- eth_mdc, eth_mdio, sirq0, sirq1, sirq2, i2s_d0, i2s_bclk0,
- i2s_lrclk0, i2s_mclk0, i2s_d1, i2s_bclk1, i2s_lrclk1,
- i2s_mclk1, ks_in0, ks_in1, ks_in2, ks_in3, ks_out0, ks_out1,
- ks_out2, lvds_oep, lvds_oen, lvds_odp, lvds_odn, lvds_ocp,
- lvds_ocn, lvds_obp, lvds_obn, lvds_oap, lvds_oan, lvds_eep,
- lvds_een, lvds_edp, lvds_edn, lvds_ecp, lvds_ecn, lvds_ebp,
- lvds_ebn, lvds_eap, lvds_ean, lcd0_d18, lcd0_d17, dsi_dp3,
- dsi_dn3, dsi_dp1, dsi_dn1, dsi_cp, dsi_cn, dsi_dp0, dsi_dn0,
- dsi_dp2, dsi_dn2, sd0_d0, sd0_d1, sd0_d2, sd0_d3, sd1_d0,
- sd1_d1, sd1_d2, sd1_d3, sd0_cmd, sd0_clk, sd1_cmd, sd1_clk,
- spi0_sclk, spi0_ss, spi0_miso, spi0_mosi, uart0_rx,
- uart0_tx, i2c0_sclk, i2c0_sdata, sensor0_pclk,
- sensor0_ckout, dnand_ale, dnand_cle, dnand_ceb0, dnand_ceb1,
- dnand_ceb2, dnand_ceb3, uart2_rx, uart2_tx, uart2_rtsb,
- uart2_ctsb, uart3_rx, uart3_tx, uart3_rtsb, uart3_ctsb,
- pcm1_in, pcm1_clk, pcm1_sync, pcm1_out, i2c1_sclk,
- i2c1_sdata, i2c2_sclk, i2c2_sdata, csi_dn0, csi_dp0,
- csi_dn1, csi_dp1, csi_dn2, csi_dp2, csi_dn3, csi_dp3,
- csi_cn, csi_cp, dnand_d0, dnand_d1, dnand_d2, dnand_d3,
- dnand_d4, dnand_d5, dnand_d6, dnand_d7, dnand_rb, dnand_rdb,
- dnand_rdbn, dnand_wrb, porb, clko_25m, bsel, pkg0, pkg1,
- pkg2, pkg3]
+ eth_rxer, eth_crs_dv, eth_rxd1, eth_rxd0, eth_ref_clk,
+ eth_mdc, eth_mdio, sirq0, sirq1, sirq2, i2s_d0, i2s_bclk0,
+ i2s_lrclk0, i2s_mclk0, i2s_d1, i2s_bclk1, i2s_lrclk1,
+ i2s_mclk1, ks_in0, ks_in1, ks_in2, ks_in3, ks_out0, ks_out1,
+ ks_out2, lvds_oep, lvds_oen, lvds_odp, lvds_odn, lvds_ocp,
+ lvds_ocn, lvds_obp, lvds_obn, lvds_oap, lvds_oan, lvds_eep,
+ lvds_een, lvds_edp, lvds_edn, lvds_ecp, lvds_ecn, lvds_ebp,
+ lvds_ebn, lvds_eap, lvds_ean, lcd0_d18, lcd0_d17, dsi_dp3,
+ dsi_dn3, dsi_dp1, dsi_dn1, dsi_cp, dsi_cn, dsi_dp0, dsi_dn0,
+ dsi_dp2, dsi_dn2, sd0_d0, sd0_d1, sd0_d2, sd0_d3, sd1_d0,
+ sd1_d1, sd1_d2, sd1_d3, sd0_cmd, sd0_clk, sd1_cmd, sd1_clk,
+ spi0_sclk, spi0_ss, spi0_miso, spi0_mosi, uart0_rx,
+ uart0_tx, i2c0_sclk, i2c0_sdata, sensor0_pclk,
+ sensor0_ckout, dnand_ale, dnand_cle, dnand_ceb0, dnand_ceb1,
+ dnand_ceb2, dnand_ceb3, uart2_rx, uart2_tx, uart2_rtsb,
+ uart2_ctsb, uart3_rx, uart3_tx, uart3_rtsb, uart3_ctsb,
+ pcm1_in, pcm1_clk, pcm1_sync, pcm1_out, i2c1_sclk,
+ i2c1_sdata, i2c2_sclk, i2c2_sdata, csi_dn0, csi_dp0,
+ csi_dn1, csi_dp1, csi_dn2, csi_dp2, csi_dn3, csi_dp3,
+ csi_cn, csi_cp, dnand_d0, dnand_d1, dnand_d2, dnand_d3,
+ dnand_d4, dnand_d5, dnand_d6, dnand_d7, dnand_rb, dnand_rdb,
+ dnand_rdbn, dnand_wrb, porb, clko_25m, bsel, pkg0, pkg1,
+ pkg2, pkg3]
minItems: 1
maxItems: 64
required:
- pinmux
- additionalProperties: false
+ additionalProperties: false
required:
- compatible
Specify the alternative function to be configured for the specified
pins. Functions are only valid for gpio pins.
enum: [ gpio, cci_i2c0, blsp_uim1, blsp_uim2, blsp_uim3, blsp_uim5,
- blsp_i2c1, blsp_i2c2, blsp_i2c3, blsp_i2c5, blsp_spi1,
- blsp_spi2, blsp_spi3, blsp_spi5, blsp_uart1, blsp_uart2,
- blsp_uart3, blsp_uart5, cam_mclk0, cam_mclk1, wlan ]
+ blsp_i2c1, blsp_i2c2, blsp_i2c3, blsp_i2c5, blsp_spi1,
+ blsp_spi2, blsp_spi3, blsp_spi5, blsp_uart1, blsp_uart2,
+ blsp_uart3, blsp_uart5, cam_mclk0, cam_mclk1, wlan ]
drive-strength:
enum: [2, 4, 6, 8, 10, 12, 14, 16]
Function to mux.
$ref: "/schemas/types.yaml#/definitions/string"
enum: [i2c0, i2c1, i2c2, i2c3, i2c4, i2c5, i2c6, i2c7, i2c8,
- spi0, spi1, spi2, spi3, spi4, spi5, spi6,
- uart0, uart1, uart2, uart3, pwm, pcmif_out, pcmif_in]
+ spi0, spi1, spi2, spi3, spi4, spi5, spi6,
+ uart0, uart1, uart2, uart3, pwm, pcmif_out, pcmif_in]
groups:
description:
Name of the pin group to use for the functions.
$ref: "/schemas/types.yaml#/definitions/string"
enum: [i2c0_grp, i2c1_grp, i2c2_grp, i2c3_grp, i2c4_grp,
- i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp,
- spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp,
- spi1_grp, spi2_grp, spi3_grp, spi4_grp, spi5_grp, spi6_grp,
- uart0_grp, uart1_grp, uart2_grp, uart3_grp,
- pwm0_gpio4_grp, pwm0_gpio8_grp, pwm0_gpio12_grp,
- pwm0_gpio16_grp, pwm1_gpio5_grp, pwm1_gpio9_grp,
- pwm1_gpio13_grp, pwm1_gpio17_grp, pwm2_gpio6_grp,
- pwm2_gpio10_grp, pwm2_gpio14_grp, pwm2_gpio18_grp,
- pwm3_gpio7_grp, pwm3_gpio11_grp, pwm3_gpio15_grp,
- pwm3_gpio19_grp, pcmif_out_grp, pcmif_in_grp]
+ i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp,
+ spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp,
+ spi1_grp, spi2_grp, spi3_grp, spi4_grp, spi5_grp, spi6_grp,
+ uart0_grp, uart1_grp, uart2_grp, uart3_grp,
+ pwm0_gpio4_grp, pwm0_gpio8_grp, pwm0_gpio12_grp,
+ pwm0_gpio16_grp, pwm1_gpio5_grp, pwm1_gpio9_grp,
+ pwm1_gpio13_grp, pwm1_gpio17_grp, pwm2_gpio6_grp,
+ pwm2_gpio10_grp, pwm2_gpio14_grp, pwm2_gpio18_grp,
+ pwm3_gpio7_grp, pwm3_gpio11_grp, pwm3_gpio15_grp,
+ pwm3_gpio19_grp, pcmif_out_grp, pcmif_in_grp]
drive-strength:
enum: [2, 4, 6, 8, 16, 24, 32]
properties:
mode-normal:
- $ref: /schemas/types.yaml#/definitions/uint32
- description: |
- Default value to set on a reboot if no command was provided.
+ $ref: /schemas/types.yaml#/definitions/uint32
+ description:
+ Default value to set on a reboot if no command was provided.
patternProperties:
"^mode-.*$":
$ref: /schemas/types.yaml#/definitions/uint32
+additionalProperties: false
+
examples:
- |
reboot-mode {
oneOf:
- const: ingenic,jz4740-battery
- items:
- - enum:
- - ingenic,jz4725b-battery
- - ingenic,jz4770-battery
- - const: ingenic,jz4740-battery
+ - enum:
+ - ingenic,jz4725b-battery
+ - ingenic,jz4770-battery
+ - const: ingenic,jz4740-battery
io-channels:
maxItems: 1
then:
properties:
summit,mains-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 1000000,
- 1500000, 1800000, 2000000]
+ enum: [ 300000, 500000, 700000, 1000000,
+ 1500000, 1800000, 2000000]
summit,usb-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 1000000,
- 1500000, 1800000, 2000000]
+ enum: [ 300000, 500000, 700000, 1000000,
+ 1500000, 1800000, 2000000]
summit,charge-current-compensation-microamp:
enum: [200000, 450000, 600000, 900000]
else:
properties:
summit,mains-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 900000, 1200000,
- 1500000, 1800000, 2000000, 2200000, 2500000]
+ enum: [ 300000, 500000, 700000, 900000, 1200000,
+ 1500000, 1800000, 2000000, 2200000, 2500000]
summit,usb-current-limit-microamp:
- enum: [ 300000, 500000, 700000, 900000, 1200000,
- 1500000, 1800000, 2000000, 2200000, 2500000]
+ enum: [ 300000, 500000, 700000, 900000, 1200000,
+ 1500000, 1800000, 2000000, 2200000, 2500000]
summit,charge-current-compensation-microamp:
enum: [250000, 700000, 900000, 1200000]
- enable-gpios
- mps,fb-voltage-divider
+unevaluatedProperties: false
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
- compatible
- reg
+additionalProperties: false
+
examples:
- |
i2c {
properties:
compatible:
items:
- - enum:
- - sifive,fu540-c000-ccache
+ - enum:
+ - sifive,fu540-c000-ccache
required:
- compatible
- sifive,hifive-unleashed-a00
- const: sifive,fu540-c000
- const: sifive,fu540
+
+additionalProperties: true
+
...
- const: fsl,imx21-rnga
- items:
- enum:
- - fsl,imx6sl-rngb
- - fsl,imx6sll-rngb
- - fsl,imx6ull-rngb
+ - fsl,imx6sl-rngb
+ - fsl,imx6sll-rngb
+ - fsl,imx6ull-rngb
- const: fsl,imx25-rngb
- const: fsl,imx35-rngc
- const: fsl,imx21-uart
- items:
- enum:
- - fsl,imx25-uart
- - fsl,imx27-uart
- - fsl,imx31-uart
- - fsl,imx35-uart
- - fsl,imx50-uart
- - fsl,imx51-uart
- - fsl,imx53-uart
- - fsl,imx6q-uart
+ - fsl,imx25-uart
+ - fsl,imx27-uart
+ - fsl,imx31-uart
+ - fsl,imx35-uart
+ - fsl,imx50-uart
+ - fsl,imx51-uart
+ - fsl,imx53-uart
+ - fsl,imx6q-uart
- const: fsl,imx21-uart
- items:
- enum:
- - fsl,imx6sl-uart
- - fsl,imx6sll-uart
- - fsl,imx6sx-uart
+ - fsl,imx6sl-uart
+ - fsl,imx6sll-uart
+ - fsl,imx6sx-uart
- const: fsl,imx6q-uart
- const: fsl,imx21-uart
- items:
- enum:
- - fsl,imx6ul-uart
- - fsl,imx7d-uart
- - fsl,imx8mm-uart
- - fsl,imx8mn-uart
- - fsl,imx8mp-uart
- - fsl,imx8mq-uart
+ - fsl,imx6ul-uart
+ - fsl,imx7d-uart
+ - fsl,imx8mm-uart
+ - fsl,imx8mn-uart
+ - fsl,imx8mp-uart
+ - fsl,imx8mq-uart
- const: fsl,imx6q-uart
reg:
description: |
Google's ChromeOS EC codec is a digital mic codec provided by the
- Embedded Controller (EC) and is controlled via a host-command interface.
- An EC codec node should only be found as a sub-node of the EC node (see
- Documentation/devicetree/bindings/mfd/google,cros-ec.yaml).
+ Embedded Controller (EC) and is controlled via a host-command
+ interface. An EC codec node should only be found inside the "codecs"
+ subnode of a cros-ec node.
+ (see Documentation/devicetree/bindings/mfd/google,cros-ec.yaml).
properties:
compatible:
#size-cells = <0>;
cros-ec@0 {
compatible = "google,cros-ec-spi";
- #address-cells = <2>;
- #size-cells = <1>;
reg = <0>;
- cros_ec_codec: ec-codec@10500000 {
- compatible = "google,cros-ec-codec";
- #sound-dai-cells = <1>;
- reg = <0x0 0x10500000 0x80000>;
- memory-region = <&reserved_mem>;
+
+ codecs {
+ #address-cells = <2>;
+ #size-cells = <1>;
+
+ cros_ec_codec: ec-codec@10500000 {
+ compatible = "google,cros-ec-codec";
+ #sound-dai-cells = <1>;
+ reg = <0x0 0x10500000 0x80000>;
+ memory-region = <&reserved_mem>;
+ };
+
};
};
};
- Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
description:
- The Microchip Sony/Philips Digital Interface Receiver is a
- serial port compliant with the IEC-60958 standard.
+ The Microchip Sony/Philips Digital Interface Receiver is a serial port
+ compliant with the IEC-60958 standard.
properties:
"#sound-dai-cells":
- Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
description:
- The Microchip Sony/Philips Digital Interface Transmitter is a
- serial port compliant with the IEC-60958 standard.
+ The Microchip Sony/Philips Digital Interface Transmitter is a serial port
+ compliant with the IEC-60958 standard.
properties:
"#sound-dai-cells":
reg:
maxItems: 2
description: LPAIF core registers
+
reg-names:
- maxItems: 2
+ maxItems: 2
+
clocks:
minItems: 3
maxItems: 6
interrupts:
maxItems: 2
description: LPAIF DMA buffer interrupt
+
interrupt-names:
maxItems: 2
+
qcom,adsp:
$ref: /schemas/types.yaml#/definitions/phandle
description: Phandle for the audio DSP node
properties:
clock-names:
oneOf:
- - items: #for I2S
- - const: pcnoc-sway-clk
- - const: audio-core
- - const: mclk0
- - const: pcnoc-mport-clk
- - const: mi2s-bit-clk0
- - const: mi2s-bit-clk1
- - items: #for HDMI
- - const: pcnoc-sway-clk
- - const: audio-core
- - const: pcnoc-mport-clk
+ - items: #for I2S
+ - const: pcnoc-sway-clk
+ - const: audio-core
+ - const: mclk0
+ - const: pcnoc-mport-clk
+ - const: mi2s-bit-clk0
+ - const: mi2s-bit-clk1
+ - items: #for HDMI
+ - const: pcnoc-sway-clk
+ - const: audio-core
+ - const: pcnoc-mport-clk
reg-names:
anyOf:
- items: #for I2S
- - const: lpass-lpaif
+ - const: lpass-lpaif
- items: #for I2S and HDMI
- - const: lpass-hdmiif
- - const: lpass-lpaif
+ - const: lpass-hdmiif
+ - const: lpass-lpaif
interrupt-names:
anyOf:
- items: #for I2S
- - const: lpass-irq-lpaif
+ - const: lpass-irq-lpaif
- items: #for I2S and HDMI
- - const: lpass-irq-lpaif
- - const: lpass-irq-hdmi
+ - const: lpass-irq-lpaif
+ - const: lpass-irq-hdmi
required:
- iommus
- power-domains
required:
- compatible
+additionalProperties: false
+
examples:
- |
#include <dt-bindings/gpio/gpio.h>
- reg : The I2C address of the device.
+Optional properties:
+
+- realtek,power-up-delay-ms
+ Set a delay time for flush work to be completed,
+ this value is adjustable depending on platform.
Example:
rt1015: codec@28 {
compatible = "realtek,rt1015";
reg = <0x28>;
+ realtek,power-up-delay-ms = <50>;
};
- const: allwinner,sun4i-a10-system-control
- const: allwinner,sun8i-a23-system-control
- const: allwinner,sun8i-h3-system-control
+ - items:
+ - const: allwinner,sun8i-v3s-system-control
+ - const: allwinner,sun8i-h3-system-control
- items:
- const: allwinner,sun8i-r40-system-control
- const: allwinner,sun4i-a10-system-control
compatible:
items:
- enum:
- - arm,sp804
- - hisilicon,sp804
+ - arm,sp804
+ - hisilicon,sp804
- const: arm,primecell
interrupts:
clock is used for all clock inputs.
oneOf:
- items:
- - description: clock for timer 1
- - description: clock for timer 2
- - description: bus clock
+ - description: clock for timer 1
+ - description: clock for timer 2
+ - description: bus clock
- items:
- - description: unified clock for both timers and the bus
+ - description: unified clock for both timers and the bus
clock-names: true
# The original binding did not specify any clock names, and there is no
enum: [super-speed, high-speed, full-speed]
phys:
- minItems: 1
- maxItems: 2
+ minItems: 1
+ maxItems: 2
phy-names:
minItems: 1
properties:
compatible:
- const: ti,hd3ss3220
+ const: ti,hd3ss3220
reg:
maxItems: 1
- const: fsl,imx21-owire
- items:
- enum:
- - fsl,imx27-owire
- - fsl,imx50-owire
- - fsl,imx51-owire
- - fsl,imx53-owire
+ - fsl,imx27-owire
+ - fsl,imx50-owire
+ - fsl,imx51-owire
+ - fsl,imx53-owire
- const: fsl,imx21-owire
reg:
Because the generator is implemented in a separate file, it can be
reused elsewhere in the media subsystem.
- Currently vidtv supports working with 3 PSI tables: PAT, PMT and
- SDT.
+ Currently vidtv supports working with 5 PSI tables: PAT, PMT,
+ SDT, NIT and EIT.
The specification for PAT and PMT can be found in *ISO 13818-1:
- Systems*, while the specification for the SDT can be found in *ETSI
+ Systems*, while the specification for the SDT, NIT, EIT can be found in *ETSI
EN 300 468: Specification for Service Information (SI) in DVB
systems*.
#. Their programs will be concatenated to populate the PAT
+ #. Their events will be concatenated to populate the EIT
+
#. For each program in the PAT, a PMT section will be created
#. The PMT section for a channel will be assigned its streams.
The first step to check whether the demod loaded successfully is to run::
$ dvb-fe-tool
+ Device Dummy demod for DVB-T/T2/C/S/S2 (/dev/dvb/adapter0/frontend0) capabilities:
+ CAN_FEC_1_2
+ CAN_FEC_2_3
+ CAN_FEC_3_4
+ CAN_FEC_4_5
+ CAN_FEC_5_6
+ CAN_FEC_6_7
+ CAN_FEC_7_8
+ CAN_FEC_8_9
+ CAN_FEC_AUTO
+ CAN_GUARD_INTERVAL_AUTO
+ CAN_HIERARCHY_AUTO
+ CAN_INVERSION_AUTO
+ CAN_QAM_16
+ CAN_QAM_32
+ CAN_QAM_64
+ CAN_QAM_128
+ CAN_QAM_256
+ CAN_QAM_AUTO
+ CAN_QPSK
+ CAN_TRANSMISSION_MODE_AUTO
+ DVB API Version 5.11, Current v5 delivery system: DVBC/ANNEX_A
+ Supported delivery systems:
+ DVBT
+ DVBT2
+ [DVBC/ANNEX_A]
+ DVBS
+ DVBS2
+ Frequency range for the current standard:
+ From: 51.0 MHz
+ To: 2.15 GHz
+ Step: 62.5 kHz
+ Tolerance: 29.5 MHz
+ Symbol rate ranges for the current standard:
+ From: 1.00 MBauds
+ To: 45.0 MBauds
This should return what is currently set up at the demod struct, i.e.::
here's an example::
[Channel]
- FREQUENCY = 330000000
+ FREQUENCY = 474000000
MODULATION = QAM/AUTO
SYMBOL_RATE = 6940000
INNER_FEC = AUTO
Assuming this channel is named 'channel.conf', you can then run::
$ dvbv5-scan channel.conf
+ dvbv5-scan ~/vidtv.conf
+ ERROR command BANDWIDTH_HZ (5) not found during retrieve
+ Cannot calc frequency shift. Either bandwidth/symbol-rate is unavailable (yet).
+ Scanning frequency #1 330000000
+ (0x00) Signal= -68.00dBm
+ Scanning frequency #2 474000000
+ Lock (0x1f) Signal= -34.45dBm C/N= 33.74dB UCB= 0
+ Service Beethoven, provider LinuxTV.org: digital television
For more information on dvb-scan, check its documentation online here:
`dvb-scan Documentation <https://www.linuxtv.org/wiki/index.php/Dvbscan>`_.
dvbv5-zap is a command line tool that can be used to record MPEG-TS to disk. The
typical use is to tune into a channel and put it into record mode. The example
-below - which is taken from the documentation - illustrates that::
+below - which is taken from the documentation - illustrates that\ [1]_::
- $ dvbv5-zap -c dvb_channel.conf "trilhas sonoras" -r
- using demux '/dev/dvb/adapter0/demux0'
+ $ dvbv5-zap -c dvb_channel.conf "beethoven" -o music.ts -P -t 10
+ using demux 'dvb0.demux0'
reading channels from file 'dvb_channel.conf'
- service has pid type 05: 204
- tuning to 573000000 Hz
- audio pid 104
- dvb_set_pesfilter 104
- Lock (0x1f) Quality= Good Signal= 100.00% C/N= -13.80dB UCB= 70 postBER= 3.14x10^-3 PER= 0
- DVR interface '/dev/dvb/adapter0/dvr0' can now be opened
+ tuning to 474000000 Hz
+ pass all PID's to TS
+ dvb_set_pesfilter 8192
+ dvb_dev_set_bufsize: buffer set to 6160384
+ Lock (0x1f) Quality= Good Signal= -34.66dBm C/N= 33.41dB UCB= 0 postBER= 0 preBER= 1.05x10^-3 PER= 0
+ Lock (0x1f) Quality= Good Signal= -34.57dBm C/N= 33.46dB UCB= 0 postBER= 0 preBER= 1.05x10^-3 PER= 0
+ Record to file 'music.ts' started
+ received 24587768 bytes (2401 Kbytes/sec)
+ Lock (0x1f) Quality= Good Signal= -34.42dBm C/N= 33.89dB UCB= 0 postBER= 0 preBER= 2.44x10^-3 PER= 0
+
+.. [1] In this example, it records 10 seconds with all program ID's stored
+ at the music.ts file.
+
-The channel can be watched by playing the contents of the DVR interface, with
-some player that recognizes the MPEG-TS format, such as *mplayer* or *vlc*.
+The channel can be watched by playing the contents of the stream with some
+player that recognizes the MPEG-TS format, such as ``mplayer`` or ``vlc``.
By playing the contents of the stream one can visually inspect the workings of
-vidtv, e.g.::
+vidtv, e.g., to play a recorded TS file with::
+
+ $ mplayer music.ts
+
+or, alternatively, running this command on one terminal::
+
+ $ dvbv5-zap -c dvb_channel.conf "beethoven" -P -r &
+
+And, on a second terminal, playing the contents from DVR interface with::
$ mplayer /dev/dvb/adapter0/dvr0
- Updating the error statistics accordingly (e.g. BER, etc).
- Simulating some noise in the encoded data.
+
+Functions and structs used within vidtv
+---------------------------------------
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_bridge.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_channel.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_demod.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_encoder.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_mux.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_pes.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_psi.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_s302m.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_ts.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_tuner.h
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_common.c
+
+.. kernel-doc:: drivers/media/test-drivers/vidtv/vidtv_tuner.c
.. kernel-doc:: fs/dax.c
:export:
-.. kernel-doc:: fs/direct-io.c
- :export:
-
.. kernel-doc:: fs/libfs.c
:export:
There is a helper function to create device related seq_file::
- struct dentry *debugfs_create_devm_seqfile(struct device *dev,
+ void debugfs_create_devm_seqfile(struct device *dev,
const char *name,
struct dentry *parent,
int (*read_fn)(struct seq_file *s,
- s\_padding2
-
* - 0x54
+ - \_\_be32
+ - s\_num\_fc\_blocks
+ - Number of fast commit blocks in the journal.
+ * - 0x58
- \_\_u32
- s\_padding[42]
-
- This journal uses v3 of the checksum on-disk format. This is the same as
v2, but the journal block tag size is fixed regardless of the size of
block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+ * - 0x20
+ - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT)
.. _jbd2_checksum_type:
- Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
points to the two block groups that contain backup superblocks
(COMPAT\_SPARSE\_SUPER2).
+ * - 0x400
+ - Fast commits supported. Although fast commits blocks are
+ backward incompatible, fast commit blocks are not always
+ present in the journal. If fast commit blocks are present in
+ the journal, JBD2 incompat feature
+ (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets
+ set (COMPAT\_FAST\_COMMIT).
.. _super_incompat:
~~~~~~~~~~~~
JBD2 to also allows you to perform file-system specific delta commits known as
-fast commits. In order to use fast commits, you first need to call
-:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal
-area should be reserved for fast commits. Along with that, you will also need
-to set following callbacks that perform correspodning work:
+fast commits. In order to use fast commits, you will need to set following
+callbacks that perform correspodning work:
`journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and
fast commit.
For most platforms, both the _LID method and the lid notifications are
reliable. However, there are exceptions. In order to work with these
-exceptional buggy platforms, special restrictions and expections should be
+exceptional buggy platforms, special restrictions and exceptions should be
taken into account. This document describes the restrictions and the
-expections of the Linux ACPI lid device driver.
+exceptions of the Linux ACPI lid device driver.
Restrictions of the returning value of the _LID control method
trigger some system power saving operations on Windows. Since it is fully
tested, it is reliable from all AML tables.
-Expections for the userspace users of the ACPI lid device driver
+Exceptions for the userspace users of the ACPI lid device driver
================================================================
The ACPI button driver exports the lid state to the userspace via the
C. button.lid_init_state=ignore:
When this option is specified, the ACPI button driver never reports the
initial lid state and there is a compensation mechanism implemented to
- ensure that the reliable "closed" notifications can always be delievered
+ ensure that the reliable "closed" notifications can always be delivered
to the userspace by always pairing "closed" input events with complement
"opened" input events. But there is still no guarantee that the "opened"
notifications can be delivered to the userspace when the lid is actually
Name (_CRS, ResourceTemplate ()
{
- GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly,
+ GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly,
"\\_SB.GPO0", 0, ResourceConsumer) {15}
- GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly,
+ GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly,
"\\_SB.GPO0", 0, ResourceConsumer) {27, 31}
})
pin
Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
active_low
- If 1 the GPIO is marked as active_low.
+ If 1, the GPIO is marked as active_low.
Since ACPI GpioIo() resource does not have a field saying whether it is
active low or high, the "active_low" argument can be used here. Setting
it to 1 marks the GPIO as active low.
+Note, active_low in _DSD does not make sense for GpioInt() resource and
+must be 0. GpioInt() resource has its own means of defining it.
+
In our Bluetooth example the "reset-gpios" refers to the second GpioIo()
resource, second pin in that resource with the GPIO number of 31.
+The GpioIo() resource unfortunately doesn't explicitly provide an initial
+state of the output pin which driver should use during its initialization.
+
+Linux tries to use common sense here and derives the state from the bias
+and polarity settings. The table below shows the expectations:
+
+========= ============= ==============
+Pull Bias Polarity Requested...
+========= ============= ==============
+Implicit x AS IS (assumed firmware configured for us)
+Explicit x (no _DSD) as Pull Bias (Up == High, Down == Low),
+ assuming non-active (Polarity = !Pull Bias)
+Down Low as low, assuming active
+Down High as low, assuming non-active
+Up Low as high, assuming non-active
+Up High as high, assuming active
+========= ============= ==============
+
+That said, for our above example the both GPIOs, since the bias setting
+is explicit and _DSD is present, will be treated as active with a high
+polarity and Linux will configure the pins in this state until a driver
+reprograms them differently.
+
It is possible to leave holes in the array of GPIOs. This is useful in
cases like with SPI host controllers where some chip selects may be
implemented as GPIOs and some as native signals. For example a SPI host
Package () {
"gpio-line-names",
Package () {
- "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", "MUX7_IO",
- "LVL_C_A1", "MUX0_IO", "SPI1_MISO"
+ "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD",
+ "MUX7_IO", "LVL_C_A1", "MUX0_IO", "SPI1_MISO",
}
}
mapping between those names and the ACPI GPIO resources corresponding to them.
To do that, the driver needs to define a mapping table as a NULL-terminated
-array of struct acpi_gpio_mapping objects that each contain a name, a pointer
+array of struct acpi_gpio_mapping objects that each contains a name, a pointer
to an array of line data (struct acpi_gpio_params) objects and the size of that
array. Each struct acpi_gpio_params object consists of three fields,
crs_entry_index, line_index, active_low, representing the index of the target
static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
{ "reset-gpios", &reset_gpio, 1 },
{ "shutdown-gpios", &shutdown_gpio, 1 },
- { },
+ { }
};
Next, the mapping table needs to be passed as the second argument to
-acpi_dev_add_driver_gpios() that will register it with the ACPI device object
-pointed to by its first argument. That should be done in the driver's .probe()
-routine. On removal, the driver should unregister its GPIO mapping table by
+acpi_dev_add_driver_gpios() or its managed analogue that will
+register it with the ACPI device object pointed to by its first
+argument. That should be done in the driver's .probe() routine.
+On removal, the driver should unregister its GPIO mapping table by
calling acpi_dev_remove_driver_gpios() on the ACPI device object where that
table was previously registered.
but since there is no way to know the mapping between "reset" and
the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT).
-The driver author can solve this by passing the mapping explictly
-(the recommended way and documented in the above chapter).
+The driver author can solve this by passing the mapping explicitly
+(this is the recommended way and it's documented in the above chapter).
The ACPI GPIO mapping tables should not contaminate drivers that are not
knowing about which exact device they are servicing on. It implies that
-the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain
+the ACPI GPIO mapping tables are hardly linked to an ACPI ID and certain
objects, as listed in the above chapter, of the device in question.
Getting GPIO descriptor
Be aware that gpiod_get_index() in cases 1 and 2, assuming that there
are two versions of ACPI device description provided and no mapping is
present in the driver, will return different resources. That's why a
-certain driver has to handle them carefully as explained in previous
+certain driver has to handle them carefully as explained in the previous
chapter.
[ 0.188903] exdebug-0398 ex_trace_point : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
Developers can utilize these special log entries to track the AML
-interpretion, thus can aid issue debugging and performance tuning. Note
+interpretation, thus can aid issue debugging and performance tuning. Note
that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
"AML tracer" logs.
===================
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
- :doc: AMDGPU XGMI Support
-
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
- :internal:
AMDGPU RAS Support
==================
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
:doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
-.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
- :internal:
-
Sample Code
-----------
Sample code for testing error injection can be found here:
integrated 12 bit SAR ADC, accessed using a PMBus interface.
The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
Sysfs entries
mcp3021
menf21bmc
mlxreg-fan
+ mp2975
nct6683
nct6775
nct7802
vendor dual-loop, digital, multi-phase controller MP2975.
This device:
+
- Supports up to two power rail.
- Provides 8 pulse-width modulations (PWMs), and can be configured up
to 8-phase operation for rail 1 and up to 4-phase operation for rail
10-mV DAC, IMVP9 mode with 5-mV DAC.
Device supports:
+
- SVID interface.
- AVSBus interface.
Device complaint with:
+
- PMBus rev 1.3 interface.
Device supports direct format for reading output current, output voltage,
The below VID modes are supported: VR12, VR13, IMVP9.
The driver provides the next attributes for the current:
+
- for current in: input, maximum alarm;
- for current out input, maximum alarm and highest values;
- for phase current: input and label.
-attributes.
+ attributes.
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- 'k' is number of configured phases (from 1 to 8);
- indexes 1, 1*n for "iin";
**curr[1-{2n+k}]_label**
The driver provides the next attributes for the voltage:
+
- for voltage in: input, high critical threshold, high critical alarm, all only
from page 0;
- for voltage out: input, low and high critical thresholds, low and high
critical alarms, from pages 0 and 1;
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- indexes 1 for "iin";
- indexes n+1, n+2 for "vout";
**in[2-{n+1}1_lcrit_alarm**
The driver provides the next attributes for the power:
+
- for power in alarm and input.
- for power out: highest and input.
+
The driver exports the following attributes via the 'sysfs' files, where
+
- 'n' is number of telemetry pages (from 1 to 2);
- indexes 1 for "pin";
- indexes n+1, n+2 for "pout";
They can be enabled individually. The full list of the parameters: ::
make CC=clang LD=ld.lld AR=llvm-ar NM=llvm-nm STRIP=llvm-strip \
- OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump OBJSIZE=llvm-size \
- READELF=llvm-readelf HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar \
- HOSTLD=ld.lld
+ OBJCOPY=llvm-objcopy OBJDUMP=llvm-objdump READELF=llvm-readelf \
+ HOSTCC=clang HOSTCXX=clang++ HOSTAR=llvm-ar HOSTLD=ld.lld
Currently, the integrated assembler is disabled by default. You can pass
``LLVM_IAS=1`` to enable it.
uleds
leds-blinkm
+ leds-el15203000
leds-lm3556
leds-lp3944
leds-lp5521
leds-lp5562
leds-lp55xx
leds-mlxcpld
+ leds-sc27xx
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
+Kernel driver for Crane EL15203000
+==================================
+
+/sys/class/leds/<led>/hw_pattern
+--------------------------------
+
+Specify a hardware pattern for the EL15203000 LED.
+
+The LEDs board supports only predefined patterns by firmware
+for specific LEDs.
+
+Breathing mode for Screen frame light tube::
+
+ "0 4000 1 4000"
+
+ ^
+ |
+ Max-| ---
+ | / \
+ | / \
+ | / \ /
+ | / \ /
+ Min-|- ---
+ |
+ 0------4------8--> time (sec)
+
+Cascade mode for Pipe LED::
+
+ "1 800 2 800 4 800 8 800 16 800"
+
+ ^
+ |
+ 0 On -|----+ +----+ +---
+ | | | | |
+ Off-| +-------------------+ +-------------------+
+ |
+ 1 On -| +----+ +----+
+ | | | | |
+ Off |----+ +-------------------+ +------------------
+ |
+ 2 On -| +----+ +----+
+ | | | | |
+ Off-|---------+ +-------------------+ +-------------
+ |
+ 3 On -| +----+ +----+
+ | | | | |
+ Off-|--------------+ +-------------------+ +--------
+ |
+ 4 On -| +----+ +----+
+ | | | | |
+ Off-|-------------------+ +-------------------+ +---
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
+
+Inverted cascade mode for Pipe LED::
+
+ "30 800 29 800 27 800 23 800 15 800"
+
+ ^
+ |
+ 0 On -| +-------------------+ +-------------------+
+ | | | | |
+ Off-|----+ +----+ +---
+ |
+ 1 On -|----+ +-------------------+ +------------------
+ | | | | |
+ Off | +----+ +----+
+ |
+ 2 On -|---------+ +-------------------+ +-------------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 3 On -|--------------+ +-------------------+ +--------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 4 On -|-------------------+ +-------------------+ +---
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
+
+Bounce mode for Pipe LED::
+
+ "1 800 2 800 4 800 8 800 16 800 16 800 8 800 4 800 2 800 1 800"
+
+ ^
+ |
+ 0 On -|----+ +--------
+ | | |
+ Off-| +---------------------------------------+
+ |
+ 1 On -| +----+ +----+
+ | | | | |
+ Off |----+ +-----------------------------+ +--------
+ |
+ 2 On -| +----+ +----+
+ | | | | |
+ Off-|---------+ +-------------------+ +-------------
+ |
+ 3 On -| +----+ +----+
+ | | | | |
+ Off-|--------------+ +---------+ +------------------
+ |
+ 4 On -| +---------+
+ | | |
+ Off-|-------------------+ +-----------------------
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
+
+Inverted bounce mode for Pipe LED::
+
+ "30 800 29 800 27 800 23 800 15 800 15 800 23 800 27 800 29 800 30 800"
+
+ ^
+ |
+ 0 On -| +---------------------------------------+
+ | | |
+ Off-|----+ +--------
+ |
+ 1 On -|----+ +-----------------------------+ +--------
+ | | | | |
+ Off | +----+ +----+
+ |
+ 2 On -|---------+ +-------------------+ +-------------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 3 On -|--------------+ +---------+ +------------------
+ | | | | |
+ Off-| +----+ +----+
+ |
+ 4 On -|-------------------+ +-----------------------
+ | | |
+ Off-| +---------+
+ |
+ 0---0.8--1.6--2.4--3.2---4---4.8--5.6--6.4--7.2---8--> time (sec)
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================
+Kernel driver for Spreadtrum SC27XX
+===================================
+
+/sys/class/leds/<led>/hw_pattern
+--------------------------------
+
+Specify a hardware pattern for the SC27XX LED. For the SC27XX
+LED controller, it only supports 4 stages to make a single
+hardware pattern, which is used to configure the rise time,
+high time, fall time and low time for the breathing mode.
+
+For the breathing mode, the SC27XX LED only expects one brightness
+for the high stage. To be compatible with the hardware pattern
+format, we should set brightness as 0 for rise stage, fall
+stage and low stage.
+
+- Min stage duration: 125 ms
+- Max stage duration: 31875 ms
+
+Since the stage duration step is 125 ms, the duration should be
+a multiplier of 125, like 125ms, 250ms, 375ms, 500ms ... 31875ms.
+
+Thus the format of the hardware pattern values should be:
+"0 rise_duration brightness high_duration 0 fall_duration 0 low_duration".
(4 usages * n STATEs + 1) categories:
where the 4 usages can be:
+
- 'ever held in STATE context'
- 'ever held as readlock in STATE context'
- 'ever held with STATE enabled'
where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
now they include:
+
- hardirq
- softirq
where the last 1 category is:
+
- 'ever used' [ == !unused ]
When locking rules are violated, these usage bits are presented in the
+--------------+-------------+--------------+
| | irq enabled | irq disabled |
+--------------+-------------+--------------+
- | ever in irq | ? | - |
+ | ever in irq | '?' | '-' |
+--------------+-------------+--------------+
- | never in irq | + | . |
+ | never in irq | '+' | '.' |
+--------------+-------------+--------------+
The character '-' suggests irq is disabled because if otherwise the
BD_MUTEX_PARTITION
};
-mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
+ mutex_lock_nested(&bdev->bd_contains->bd_mutex, BD_MUTEX_PARTITION);
In this case the locking is done on a bdev object that is known to be a
partition.
----------------
The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes.
-Exceeding this number will trigger the following lockdep warning:
+Exceeding this number will trigger the following lockdep warning::
(DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
The difference between recursive readers and non-recursive readers is because:
recursive readers get blocked only by a write lock *holder*, while non-recursive
-readers could get blocked by a write lock *waiter*. Considering the follow example:
+readers could get blocked by a write lock *waiter*. Considering the follow
+example::
TASK A: TASK B:
Block condition matrix, Y means the row blocks the column, and N means otherwise.
- | E | r | R |
+---+---+---+---+
- E | Y | Y | Y |
+ | | E | r | R |
+ +---+---+---+---+
+ | E | Y | Y | Y |
+ +---+---+---+---+
+ | r | Y | Y | N |
+---+---+---+---+
- r | Y | Y | N |
+ | R | Y | Y | N |
+---+---+---+---+
- R | Y | Y | N |
(W: writers, r: non-recursive readers, R: recursive readers)
acquired recursively. Unlike non-recursive read locks, recursive read locks
only get blocked by current write lock *holders* other than write lock
-*waiters*, for example:
+*waiters*, for example::
TASK A: TASK B:
even true for two non-recursive read locks). A non-recursive lock can block the
corresponding recursive lock, and vice versa.
-A deadlock case with recursive locks involved is as follow:
+A deadlock case with recursive locks involved is as follow::
TASK A: TASK B:
dependencies, but we can show that 4 types of lock dependencies are enough for
deadlock detection.
-For each lock dependency:
+For each lock dependency::
L1 -> L2
With the above combination for simplification, there are 4 types of dependency edges
in the lockdep graph:
-1) -(ER)->: exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
+1) -(ER)->:
+ exclusive writer to recursive reader dependency, "X -(ER)-> Y" means
X -> Y and X is a writer and Y is a recursive reader.
-2) -(EN)->: exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
+2) -(EN)->:
+ exclusive writer to non-recursive locker dependency, "X -(EN)-> Y" means
X -> Y and X is a writer and Y is either a writer or non-recursive reader.
-3) -(SR)->: shared reader to recursive reader dependency, "X -(SR)-> Y" means
+3) -(SR)->:
+ shared reader to recursive reader dependency, "X -(SR)-> Y" means
X -> Y and X is a reader (recursive or not) and Y is a recursive reader.
-4) -(SN)->: shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
+4) -(SN)->:
+ shared reader to non-recursive locker dependency, "X -(SN)-> Y" means
X -> Y and X is a reader (recursive or not) and Y is either a writer or
non-recursive reader.
-Note that given two locks, they may have multiple dependencies between them, for example:
+Note that given two locks, they may have multiple dependencies between them,
+for example::
TASK A:
Proof for sufficiency (Lemma 1):
-Let's say we have a strong circle:
+Let's say we have a strong circle::
L1 -> L2 ... -> Ln -> L1
-, which means we have dependencies:
+, which means we have dependencies::
L1 -> L2
L2 -> L3
for a lock held by P1. Let's name the lock Px is waiting as Lx, so since P1 is waiting
for L1 and holding Ln, so we will have Ln -> L1 in the dependency graph. Similarly,
we have L1 -> L2, L2 -> L3, ..., Ln-1 -> Ln in the dependency graph, which means we
-have a circle:
+have a circle::
Ln -> L1 -> L2 -> ... -> Ln
isl29003
lis3lv02d
max6875
- mic/index
pci-endpoint-test
spear-pcie-gadget
uacce
+++ /dev/null
-=============================================
-Intel Many Integrated Core (MIC) architecture
-=============================================
-
-.. toctree::
- :maxdepth: 1
-
- mic_overview
- scif_overview
-
-.. only:: subproject and html
-
- Indices
- =======
-
- * :ref:`genindex`
+++ /dev/null
-======================================================
-Intel Many Integrated Core (MIC) architecture overview
-======================================================
-
-An Intel MIC X100 device is a PCIe form factor add-in coprocessor
-card based on the Intel Many Integrated Core (MIC) architecture
-that runs a Linux OS. It is a PCIe endpoint in a platform and therefore
-implements the three required standard address spaces i.e. configuration,
-memory and I/O. The host OS loads a device driver as is typical for
-PCIe devices. The card itself runs a bootstrap after reset that
-transfers control to the card OS downloaded from the host driver. The
-host driver supports OSPM suspend and resume operations. It shuts down
-the card during suspend and reboots the card OS during resume.
-The card OS as shipped by Intel is a Linux kernel with modifications
-for the X100 devices.
-
-Since it is a PCIe card, it does not have the ability to host hardware
-devices for networking, storage and console. We provide these devices
-on X100 coprocessors thus enabling a self-bootable equivalent
-environment for applications. A key benefit of our solution is that it
-leverages the standard virtio framework for network, disk and console
-devices, though in our case the virtio framework is used across a PCIe
-bus. A Virtio Over PCIe (VOP) driver allows creating user space
-backends or devices on the host which are used to probe virtio drivers
-for these devices on the MIC card. The existing VRINGH infrastructure
-in the kernel is used to access virtio rings from the host. The card
-VOP driver allows card virtio drivers to communicate with their user
-space backends on the host via a device page. Ring 3 apps on the host
-can add, remove and configure virtio devices. A thin MIC specific
-virtio_config_ops is implemented which is borrowed heavily from
-previous similar implementations in lguest and s390.
-
-MIC PCIe card has a dma controller with 8 channels. These channels are
-shared between the host s/w and the card s/w. 0 to 3 are used by host
-and 4 to 7 by card. As the dma device doesn't show up as PCIe device,
-a virtual bus called mic bus is created and virtual dma devices are
-created on it by the host/card drivers. On host the channels are private
-and used only by the host driver to transfer data for the virtio devices.
-
-The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a
-low level communications API across PCIe currently implemented for MIC.
-More details are available at scif_overview.txt.
-
-The Coprocessor State Management (COSM) driver on the host allows for
-boot, shutdown and reset of Intel MIC devices. It communicates with a COSM
-"client" driver on the MIC cards over SCIF to perform these functions.
-
-Here is a block diagram of the various components described above. The
-virtio backends are situated on the host rather than the card given better
-single threaded performance for the host compared to MIC, the ability of
-the host to initiate DMA's to/from the card using the MIC DMA engine and
-the fact that the virtio block storage backend can only be on the host::
-
- +----------+ | +----------+
- | Card OS | | | Host OS |
- +----------+ | +----------+
- |
- +-------+ +--------+ +------+ | +---------+ +--------+ +--------+
- | Virtio| |Virtio | |Virtio| | |Virtio | |Virtio | |Virtio |
- | Net | |Console | |Block | | |Net | |Console | |Block |
- | Driver| |Driver | |Driver| | |backend | |backend | |backend |
- +---+---+ +---+----+ +--+---+ | +---------+ +----+---+ +--------+
- | | | | | | |
- | | | |User | | |
- | | | |------|------------|--+------|-------
- +---------+---------+ |Kernel |
- | | |
- +---------+ +---+----+ +------+ | +------+ +------+ +--+---+ +-------+
- |MIC DMA | | VOP | | SCIF | | | SCIF | | COSM | | VOP | |MIC DMA|
- +---+-----+ +---+----+ +--+---+ | +--+---+ +--+---+ +------+ +----+--+
- | | | | | | |
- +---+-----+ +---+----+ +--+---+ | +--+---+ +--+---+ +------+ +----+--+
- |MIC | | VOP | |SCIF | | |SCIF | | COSM | | VOP | | MIC |
- |HW Bus | | HW Bus| |HW Bus| | |HW Bus| | Bus | |HW Bus| |HW Bus |
- +---------+ +--------+ +--+---+ | +--+---+ +------+ +------+ +-------+
- | | | | | | |
- | +-----------+--+ | | | +---------------+ |
- | |Intel MIC | | | | |Intel MIC | |
- | |Card Driver | | | | |Host Driver | |
- +---+--------------+------+ | +----+---------------+-----+
- | | |
- +-------------------------------------------------------------+
- | |
- | PCIe Bus |
- +-------------------------------------------------------------+
+++ /dev/null
-========================================
-Symmetric Communication Interface (SCIF)
-========================================
-
-The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a low
-level communications API across PCIe currently implemented for MIC. Currently
-SCIF provides inter-node communication within a single host platform, where a
-node is a MIC Coprocessor or Xeon based host. SCIF abstracts the details of
-communicating over the PCIe bus while providing an API that is symmetric
-across all the nodes in the PCIe network. An important design objective for SCIF
-is to deliver the maximum possible performance given the communication
-abilities of the hardware. SCIF has been used to implement an offload compiler
-runtime and OFED support for MPI implementations for MIC coprocessors.
-
-SCIF API Components
-===================
-
-The SCIF API has the following parts:
-
-1. Connection establishment using a client server model
-2. Byte stream messaging intended for short messages
-3. Node enumeration to determine online nodes
-4. Poll semantics for detection of incoming connections and messages
-5. Memory registration to pin down pages
-6. Remote memory mapping for low latency CPU accesses via mmap
-7. Remote DMA (RDMA) for high bandwidth DMA transfers
-8. Fence APIs for RDMA synchronization
-
-SCIF exposes the notion of a connection which can be used by peer processes on
-nodes in a SCIF PCIe "network" to share memory "windows" and to communicate. A
-process in a SCIF node initiates a SCIF connection to a peer process on a
-different node via a SCIF "endpoint". SCIF endpoints support messaging APIs
-which are similar to connection oriented socket APIs. Connected SCIF endpoints
-can also register local memory which is followed by data transfer using either
-DMA, CPU copies or remote memory mapping via mmap. SCIF supports both user and
-kernel mode clients which are functionally equivalent.
-
-SCIF Performance for MIC
-========================
-
-DMA bandwidth comparison between the TCP (over ethernet over PCIe) stack versus
-SCIF shows the performance advantages of SCIF for HPC applications and
-runtimes::
-
- Comparison of TCP and SCIF based BW
-
- Throughput (GB/sec)
- 8 + PCIe Bandwidth ******
- + TCP ######
- 7 + ************************************** SCIF %%%%%%
- | %%%%%%%%%%%%%%%%%%%
- 6 + %%%%
- | %%
- | %%%
- 5 + %%
- | %%
- 4 + %%
- | %%
- 3 + %%
- | %
- 2 + %%
- | %%
- | %
- 1 +
- + ######################################
- 0 +++---+++--+--+-+--+--+-++-+--+-++-+--+-++-+-
- 1 10 100 1000 10000 100000
- Transfer Size (KBytes)
-
-SCIF allows memory sharing via mmap(..) between processes on different PCIe
-nodes and thus provides bare-metal PCIe latency. The round trip SCIF mmap
-latency from the host to an x100 MIC for an 8 byte message is 0.44 usecs.
-
-SCIF has a user space library which is a thin IOCTL wrapper providing a user
-space API similar to the kernel API in scif.h. The SCIF user space library
-is distributed @ https://software.intel.com/en-us/mic-developer
-
-Here is some pseudo code for an example of how two applications on two PCIe
-nodes would typically use the SCIF API::
-
- Process A (on node A) Process B (on node B)
-
- /* get online node information */
- scif_get_node_ids(..) scif_get_node_ids(..)
- scif_open(..) scif_open(..)
- scif_bind(..) scif_bind(..)
- scif_listen(..)
- scif_accept(..) scif_connect(..)
- /* SCIF connection established */
-
- /* Send and receive short messages */
- scif_send(..)/scif_recv(..) scif_send(..)/scif_recv(..)
-
- /* Register memory */
- scif_register(..) scif_register(..)
-
- /* RDMA */
- scif_readfrom(..)/scif_writeto(..) scif_readfrom(..)/scif_writeto(..)
-
- /* Fence DMAs */
- scif_fence_signal(..) scif_fence_signal(..)
-
- mmap(..) mmap(..)
-
- /* Access remote registered memory */
-
- /* Close the endpoints */
- scif_close(..) scif_close(..)
that both the name (as reported by ``fw.app.name``) and version are
required to uniquely identify the package.
* - ``fw.app.bundle_id``
+ - running
- 0xc0000001
- Unique identifier for the DDP package loaded in the device. Also
referred to as the DDP Track ID. Can be used to uniquely identify
SAE J1939 defines a higher layer protocol on CAN. It implements a more
sophisticated addressing scheme and extends the maximum packet size above 8
bytes. Several derived specifications exist, which differ from the original
-J1939 on the application level, like MilCAN A, NMEA2000 and especially
+J1939 on the application level, like MilCAN A, NMEA2000, and especially
ISO-11783 (ISOBUS). This last one specifies the so-called ETP (Extended
-Transport Protocol) which is has been included in this implementation. This
+Transport Protocol), which has been included in this implementation. This
results in a maximum packet size of ((2 ^ 24) - 1) * 7 bytes == 111 MiB.
Specifications used
addressing and transport methods used by J1939.
* **Addressing:** when a process on an ECU communicates via J1939, it should
- not necessarily know its source address. Although at least one process per
+ not necessarily know its source address. Although, at least one process per
ECU should know the source address. Other processes should be able to reuse
that address. This way, address parameters for different processes
cooperating for the same ECU, are not duplicated. This way of working is
- closely related to the UNIX concept where programs do just one thing, and do
+ closely related to the UNIX concept, where programs do just one thing and do
it well.
* **Dynamic addressing:** Address Claiming in J1939 is time critical.
- Furthermore data transport should be handled properly during the address
+ Furthermore, data transport should be handled properly during the address
negotiation. Putting this functionality in the kernel eliminates it as a
requirement for _every_ user space process that communicates via J1939. This
results in a consistent J1939 bus with proper addressing.
The J1939 sockets operate on CAN network devices (see SocketCAN). Any J1939
user space library operating on CAN raw sockets will still operate properly.
-Since such library does not communicate with the in-kernel implementation, care
+Since such a library does not communicate with the in-kernel implementation, care
must be taken that these two do not interfere. In practice, this means they
cannot share ECU addresses. A single ECU (or virtual ECU) address is used by
the library exclusively, or by the in-kernel system exclusively.
8 bits : PS (PDU Specific)
In J1939-21 distinction is made between PDU1 format (where PF < 240) and PDU2
-format (where PF >= 240). Furthermore, when using PDU2 format, the PS-field
+format (where PF >= 240). Furthermore, when using the PDU2 format, the PS-field
contains a so-called Group Extension, which is part of the PGN. When using PDU2
format, the Group Extension is set in the PS-field.
On the other hand, when using PDU1 format, the PS-field contains a so-called
Destination Address, which is _not_ part of the PGN. When communicating a PGN
-from user space to kernel (or visa versa) and PDU2 format is used, the PS-field
+from user space to kernel (or vice versa) and PDU2 format is used, the PS-field
of the PGN shall be set to zero. The Destination Address shall be set
elsewhere.
Both static and dynamic addressing methods can be used.
-For static addresses, no extra checks are made by the kernel, and provided
+For static addresses, no extra checks are made by the kernel and provided
addresses are considered right. This responsibility is for the OEM or system
integrator.
For dynamic addressing, so-called Address Claiming, extra support is foreseen
-in the kernel. In J1939 any ECU is known by it's 64-bit NAME. At the moment of
+in the kernel. In J1939 any ECU is known by its 64-bit NAME. At the moment of
a successful address claim, the kernel keeps track of both NAME and source
address being claimed. This serves as a base for filter schemes. By default,
-packets with a destination that is not locally, will be rejected.
+packets with a destination that is not locally will be rejected.
Mixed mode packets (from a static to a dynamic address or vice versa) are
allowed. The BSD sockets define separate API calls for getting/setting the
---------
On CAN, you first need to open a socket for communicating over a CAN network.
-To use J1939, #include <linux/can/j1939.h>. From there, <linux/can.h> will be
+To use J1939, ``#include <linux/can/j1939.h>``. From there, ``<linux/can.h>`` will be
included too. To open a socket, use:
.. code-block:: C
s = socket(PF_CAN, SOCK_DGRAM, CAN_J1939);
-J1939 does use SOCK_DGRAM sockets. In the J1939 specification, connections are
+J1939 does use ``SOCK_DGRAM`` sockets. In the J1939 specification, connections are
mentioned in the context of transport protocol sessions. These still deliver
-packets to the other end (using several CAN packets). SOCK_STREAM is not
+packets to the other end (using several CAN packets). ``SOCK_STREAM`` is not
supported.
-After the successful creation of the socket, you would normally use the bind(2)
-and/or connect(2) system call to bind the socket to a CAN interface. After
-binding and/or connecting the socket, you can read(2) and write(2) from/to the
-socket or use send(2), sendto(2), sendmsg(2) and the recv*() counterpart
+After the successful creation of the socket, you would normally use the ``bind(2)``
+and/or ``connect(2)`` system call to bind the socket to a CAN interface. After
+binding and/or connecting the socket, you can ``read(2)`` and ``write(2)`` from/to the
+socket or use ``send(2)``, ``sendto(2)``, ``sendmsg(2)`` and the ``recv*()`` counterpart
operations on the socket as usual. There are also J1939 specific socket options
described below.
-In order to send data, a bind(2) must have been successful. bind(2) assigns a
+In order to send data, a ``bind(2)`` must have been successful. ``bind(2)`` assigns a
local address to a socket.
-Different from CAN is that the payload data is just the data that get send,
-without it's header info. The header info is derived from the sockaddr supplied
-to bind(2), connect(2), sendto(2) and recvfrom(2). A write(2) with size 4 will
+Different from CAN is that the payload data is just the data that get sends,
+without its header info. The header info is derived from the sockaddr supplied
+to ``bind(2)``, ``connect(2)``, ``sendto(2)`` and ``recvfrom(2)``. A ``write(2)`` with size 4 will
result in a packet with 4 bytes.
The sockaddr structure has extensions for use with J1939 as specified below:
} can_addr;
}
-can_family & can_ifindex serve the same purpose as for other SocketCAN sockets.
+``can_family`` & ``can_ifindex`` serve the same purpose as for other SocketCAN sockets.
-can_addr.j1939.pgn specifies the PGN (max 0x3ffff). Individual bits are
+``can_addr.j1939.pgn`` specifies the PGN (max 0x3ffff). Individual bits are
specified above.
-can_addr.j1939.name contains the 64-bit J1939 NAME.
+``can_addr.j1939.name`` contains the 64-bit J1939 NAME.
-can_addr.j1939.addr contains the address.
+``can_addr.j1939.addr`` contains the address.
-The bind(2) system call assigns the local address, i.e. the source address when
-sending packages. If a PGN during bind(2) is set, it's used as a RX filter.
-I.e. only packets with a matching PGN are received. If an ADDR or NAME is set
+The ``bind(2)`` system call assigns the local address, i.e. the source address when
+sending packages. If a PGN during ``bind(2)`` is set, it's used as a RX filter.
+I.e. only packets with a matching PGN are received. If an ADDR or NAME is set
it is used as a receive filter, too. It will match the destination NAME or ADDR
of the incoming packet. The NAME filter will work only if appropriate Address
Claiming for this name was done on the CAN bus and registered/cached by the
kernel.
-On the other hand connect(2) assigns the remote address, i.e. the destination
-address. The PGN from connect(2) is used as the default PGN when sending
+On the other hand ``connect(2)`` assigns the remote address, i.e. the destination
+address. The PGN from ``connect(2)`` is used as the default PGN when sending
packets. If ADDR or NAME is set it will be used as the default destination ADDR
-or NAME. Further a set ADDR or NAME during connect(2) is used as a receive
+or NAME. Further a set ADDR or NAME during ``connect(2)`` is used as a receive
filter. It will match the source NAME or ADDR of the incoming packet.
-Both write(2) and send(2) will send a packet with local address from bind(2) and
-the remote address from connect(2). Use sendto(2) to overwrite the destination
+Both ``write(2)`` and ``send(2)`` will send a packet with local address from ``bind(2)`` and the
+remote address from ``connect(2)``. Use ``sendto(2)`` to overwrite the destination
address.
-If can_addr.j1939.name is set (!= 0) the NAME is looked up by the kernel and
-the corresponding ADDR is used. If can_addr.j1939.name is not set (== 0),
-can_addr.j1939.addr is used.
+If ``can_addr.j1939.name`` is set (!= 0) the NAME is looked up by the kernel and
+the corresponding ADDR is used. If ``can_addr.j1939.name`` is not set (== 0),
+``can_addr.j1939.addr`` is used.
When creating a socket, reasonable defaults are set. Some options can be
-modified with setsockopt(2) & getsockopt(2).
+modified with ``setsockopt(2)`` & ``getsockopt(2)``.
RX path related options:
-- SO_J1939_FILTER - configure array of filters
-- SO_J1939_PROMISC - disable filters set by bind(2) and connect(2)
+- ``SO_J1939_FILTER`` - configure array of filters
+- ``SO_J1939_PROMISC`` - disable filters set by ``bind(2)`` and ``connect(2)``
By default no broadcast packets can be send or received. To enable sending or
-receiving broadcast packets use the socket option SO_BROADCAST:
+receiving broadcast packets use the socket option ``SO_BROADCAST``:
.. code-block:: C
+---------------------------+
TX path related options:
-SO_J1939_SEND_PRIO - change default send priority for the socket
+``SO_J1939_SEND_PRIO`` - change default send priority for the socket
Message Flags during send() and Related System Calls
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-send(2), sendto(2) and sendmsg(2) take a 'flags' argument. Currently
+``send(2)``, ``sendto(2)`` and ``sendmsg(2)`` take a 'flags' argument. Currently
supported flags are:
-* MSG_DONTWAIT, i.e. non-blocking operation.
+* ``MSG_DONTWAIT``, i.e. non-blocking operation.
recvmsg(2)
^^^^^^^^^^
-In most cases recvmsg(2) is needed if you want to extract more information than
-recvfrom(2) can provide. For example package priority and timestamp. The
+In most cases ``recvmsg(2)`` is needed if you want to extract more information than
+``recvfrom(2)`` can provide. For example package priority and timestamp. The
Destination Address, name and packet priority (if applicable) are attached to
-the msghdr in the recvmsg(2) call. They can be extracted using cmsg(3) macros,
-with cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR,
-SCM_J1939_DEST_NAME or SCM_J1939_PRIO. The returned data is a uint8_t for
-priority and dst_addr, and uint64_t for dst_name.
+the msghdr in the ``recvmsg(2)`` call. They can be extracted using ``cmsg(3)`` macros,
+with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``,
+``SCM_J1939_DEST_NAME`` or ``SCM_J1939_PRIO``. The returned data is a ``uint8_t`` for
+``priority`` and ``dst_addr``, and ``uint64_t`` for ``dst_name``.
.. code-block:: C
Distinction has to be made between using the claimed address and doing an
address claim. To use an already claimed address, one has to fill in the
-j1939.name member and provide it to bind(2). If the name had claimed an address
+``j1939.name`` member and provide it to ``bind(2)``. If the name had claimed an address
earlier, all further messages being sent will use that address. And the
-j1939.addr member will be ignored.
+``j1939.addr`` member will be ignored.
An exception on this is PGN 0x0ee00. This is the "Address Claim/Cannot Claim
-Address" message and the kernel will use the j1939.addr member for that PGN if
+Address" message and the kernel will use the ``j1939.addr`` member for that PGN if
necessary.
To claim an address following code example can be used:
If another ECU claims the address, the kernel will mark the NAME-SA expired.
No socket bound to the NAME can send packets (other than address claims). To
-claim another address, some socket bound to NAME, must bind(2) again, but with
-only j1939.addr changed to the new SA, and must then send a valid address claim
+claim another address, some socket bound to NAME, must ``bind(2)`` again, but with
+only ``j1939.addr`` changed to the new SA, and must then send a valid address claim
packet. This restarts the state machine in the kernel (and any other
participant on the bus) for this NAME.
-can-utils also include the jacd tool, so it can be used as code example or as
+``can-utils`` also include the ``j1939acd`` tool, so it can be used as code example or as
default Address Claiming daemon.
Send Examples
bind(sock, (struct sockaddr *)&baddr, sizeof(baddr));
-Now, the socket 'sock' is bound to the SA 0x20. Since no connect(2) was called,
-at this point we can use only sendto(2) or sendmsg(2).
+Now, the socket 'sock' is bound to the SA 0x20. Since no ``connect(2)`` was called,
+at this point we can use only ``sendto(2)`` or ``sendmsg(2)``.
Send:
.can_family = AF_CAN,
.can_addr.j1939 = {
.name = J1939_NO_NAME;
- .pgn = 0x30,
- .addr = 0x12300,
+ .addr = 0x30,
+ .pgn = 0x12300,
},
};
Q: How can I tell whether it got merged?
A: Start by looking at the main patchworks queue for netdev:
- http://patchwork.ozlabs.org/project/netdev/list/
+ https://patchwork.kernel.org/project/netdevbpf/list/
The "State" field will tell you exactly where things are at with your
patch.
There is a patchworks queue that you can see here:
- http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
+ https://patchwork.kernel.org/bundle/netdev/stable/?state=*
It contains the patches which Dave has selected, but not yet handed off
to Greg. If Greg already has the patch, then it will be here:
minimum, your changes should survive an ``allyesconfig`` and an
``allmodconfig`` build without new warnings or failures.
+Q: How do I post corresponding changes to user space components?
+----------------------------------------------------------------
+A: User space code exercising kernel features should be posted
+alongside kernel patches. This gives reviewers a chance to see
+how any new interface is used and how well it works.
+
+When user space tools reside in the kernel repo itself all changes
+should generally come as one series. If series becomes too large
+or the user space project is not reviewed on netdev include a link
+to a public repo where user space patches can be seen.
+
+In case user space tooling lives in a separate repository but is
+reviewed on netdev (e.g. patches to `iproute2` tools) kernel and
+user space patches should form separate series (threads) when posted
+to the mailing list, e.g.::
+
+ [PATCH net-next 0/3] net: some feature cover letter
+ └─ [PATCH net-next 1/3] net: some feature prep
+ └─ [PATCH net-next 2/3] net: some feature do it
+ └─ [PATCH net-next 3/3] selftest: net: some feature
+
+ [PATCH iproute2-next] ip: add support for some feature
+
+Posting as one thread is discouraged because it confuses patchwork
+(as of patchwork 2.2.2).
+
Q: Any other tips to help ensure my net/net-next patch gets OK'd?
-----------------------------------------------------------------
A: Attention to detail. Re-read your own work as if you were the
speeds (see below.)
``PHY_INTERFACE_MODE_2500BASEX``
- This defines a variant of 1000BASE-X which is clocked 2.5 times faster,
- than the 802.3 standard giving a fixed bit rate of 3.125Gbaud.
+ This defines a variant of 1000BASE-X which is clocked 2.5 times as fast
+ as the 802.3 standard, giving a fixed bit rate of 3.125Gbaud.
``PHY_INTERFACE_MODE_SGMII``
This is used for Cisco SGMII, which is a modification of 1000BASE-X
translated to netlink attributes when dumped. Drivers must not overwrite
the statistics they don't report with 0.
-.. kernel-doc:: include/linux/ethtool.h
- :identifiers: ethtool_pause_stats
+- ethtool_pause_stats()
submission guidelines as described in
:ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
after first checking the stable networking queue at
- https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive=
+ https://patchwork.kernel.org/bundle/netdev/stable/?state=*
to ensure the requested patch is not already queued up.
- Security patches should not be handled (solely) by the -stable review
process but should follow the procedures in
import re
from itertools import chain
+#
+# Python 2 lacks re.ASCII...
+#
+try:
+ ascii_p3 = re.ASCII
+except AttributeError:
+ ascii_p3 = 0
+
#
# Regex nastiness. Of course.
# Try to identify "function()" that's not already marked up some
# :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
# bit tries to restrict matches to things that won't create trouble.
#
-RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=re.ASCII)
+RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)
#
# Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
#
RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
- flags=re.ASCII)
+ flags=ascii_p3)
#
# Sphinx 3 uses a different C role for each one of struct, union, enum and
# typedef
#
-RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
-RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=re.ASCII)
+RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
+RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
#
# Detects a reference to a documentation page of the form Documentation/... with
--- /dev/null
+# -*- coding: utf-8; mode: python -*-
+# coding=utf-8
+# SPDX-License-Identifier: GPL-2.0
+#
+u"""
+ kernel-abi
+ ~~~~~~~~~~
+
+ Implementation of the ``kernel-abi`` reST-directive.
+
+ :copyright: Copyright (C) 2016 Markus Heiser
+ :copyright: Copyright (C) 2016-2020 Mauro Carvalho Chehab
+ :maintained-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
+ :license: GPL Version 2, June 1991 see Linux/COPYING for details.
+
+ The ``kernel-abi`` (:py:class:`KernelCmd`) directive calls the
+ scripts/get_abi.pl script to parse the Kernel ABI files.
+
+ Overview of directive's argument and options.
+
+ .. code-block:: rst
+
+ .. kernel-abi:: <ABI directory location>
+ :debug:
+
+ The argument ``<ABI directory location>`` is required. It contains the
+ location of the ABI files to be parsed.
+
+ ``debug``
+ Inserts a code-block with the *raw* reST. Sometimes it is helpful to see
+ what reST is generated.
+
+"""
+
+import codecs
+import os
+import subprocess
+import sys
+import re
+import kernellog
+
+from os import path
+
+from docutils import nodes, statemachine
+from docutils.statemachine import ViewList
+from docutils.parsers.rst import directives, Directive
+from docutils.utils.error_reporting import ErrorString
+
+#
+# AutodocReporter is only good up to Sphinx 1.7
+#
+import sphinx
+
+Use_SSI = sphinx.__version__[:3] >= '1.7'
+if Use_SSI:
+ from sphinx.util.docutils import switch_source_input
+else:
+ from sphinx.ext.autodoc import AutodocReporter
+
+__version__ = '1.0'
+
+def setup(app):
+
+ app.add_directive("kernel-abi", KernelCmd)
+ return dict(
+ version = __version__
+ , parallel_read_safe = True
+ , parallel_write_safe = True
+ )
+
+class KernelCmd(Directive):
+
+ u"""KernelABI (``kernel-abi``) directive"""
+
+ required_arguments = 1
+ optional_arguments = 2
+ has_content = False
+ final_argument_whitespace = True
+
+ option_spec = {
+ "debug" : directives.flag,
+ "rst" : directives.unchanged
+ }
+
+ def run(self):
+
+ doc = self.state.document
+ if not doc.settings.file_insertion_enabled:
+ raise self.warning("docutils: file insertion disabled")
+
+ env = doc.settings.env
+ cwd = path.dirname(doc.current_source)
+ cmd = "get_abi.pl rest --enable-lineno --dir "
+ cmd += self.arguments[0]
+
+ if 'rst' in self.options:
+ cmd += " --rst-source"
+
+ srctree = path.abspath(os.environ["srctree"])
+
+ fname = cmd
+
+ # extend PATH with $(srctree)/scripts
+ path_env = os.pathsep.join([
+ srctree + os.sep + "scripts",
+ os.environ["PATH"]
+ ])
+ shell_env = os.environ.copy()
+ shell_env["PATH"] = path_env
+ shell_env["srctree"] = srctree
+
+ lines = self.runCmd(cmd, shell=True, cwd=cwd, env=shell_env)
+ nodeList = self.nestedParse(lines, self.arguments[0])
+ return nodeList
+
+ def runCmd(self, cmd, **kwargs):
+ u"""Run command ``cmd`` and return it's stdout as unicode."""
+
+ try:
+ proc = subprocess.Popen(
+ cmd
+ , stdout = subprocess.PIPE
+ , stderr = subprocess.PIPE
+ , **kwargs
+ )
+ out, err = proc.communicate()
+
+ out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8')
+
+ if proc.returncode != 0:
+ raise self.severe(
+ u"command '%s' failed with return code %d"
+ % (cmd, proc.returncode)
+ )
+ except OSError as exc:
+ raise self.severe(u"problems with '%s' directive: %s."
+ % (self.name, ErrorString(exc)))
+ return out
+
+ def nestedParse(self, lines, fname):
+ content = ViewList()
+ node = nodes.section()
+
+ if "debug" in self.options:
+ code_block = "\n\n.. code-block:: rst\n :linenos:\n"
+ for l in lines.split("\n"):
+ code_block += "\n " + l
+ lines = code_block + "\n\n"
+
+ line_regex = re.compile("^#define LINENO (\S+)\#([0-9]+)$")
+ ln = 0
+ n = 0
+ f = fname
+
+ for line in lines.split("\n"):
+ n = n + 1
+ match = line_regex.search(line)
+ if match:
+ new_f = match.group(1)
+
+ # Sphinx parser is lazy: it stops parsing contents in the
+ # middle, if it is too big. So, handle it per input file
+ if new_f != f and content:
+ self.do_parse(content, node)
+ content = ViewList()
+
+ f = new_f
+
+ # sphinx counts lines from 0
+ ln = int(match.group(2)) - 1
+ else:
+ content.append(line, f, ln)
+
+ kernellog.info(self.state.document.settings.env.app, "%s: parsed %i lines" % (fname, n))
+
+ if content:
+ self.do_parse(content, node)
+
+ return node.children
+
+ def do_parse(self, content, node):
+ if Use_SSI:
+ with switch_source_input(self.state, content):
+ self.state.nested_parse(content, 0, node, match_titles=1)
+ else:
+ buf = self.state.memo.title_styles, self.state.memo.section_level, self.state.memo.reporter
+
+ self.state.memo.title_styles = []
+ self.state.memo.section_level = 0
+ self.state.memo.reporter = AutodocReporter(content, self.state.memo.reporter)
+ try:
+ self.state.nested_parse(content, 0, node, match_titles=1)
+ finally:
+ self.state.memo.title_styles, self.state.memo.section_level, self.state.memo.reporter = buf
else:
app.verbose(message)
-
+def info(app, message):
+ if UseLogging:
+ logger.info(message)
+ else:
+ app.info(message)
:ref:`Documentation/translations/it_IT/networking/netdev-FAQ.rst <it_netdev-FAQ>`;
ma solo dopo aver verificato al seguente indirizzo che la patch non sia
già in coda:
- https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive=
+ https://patchwork.kernel.org/bundle/netdev/stable/?state=*
- Una patch di sicurezza non dovrebbero essere gestite (solamente) dal processo
di revisione -stable, ma dovrebbe seguire le procedure descritte in
:ref:`Documentation/translations/it_IT/admin-guide/security-bugs.rst <it_securitybugs>`.
spec_ctrl
accelerators/ocxl
ioctl/index
+ iommu
media/index
.. only:: subproject and html
instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
KVM_EXIT_X86_WRMSR exit notifications.
-8.25 KVM_X86_SET_MSR_FILTER
+8.27 KVM_X86_SET_MSR_FILTER
---------------------------
:Architectures: x86
trap and emulate MSRs that are outside of the scope of KVM as well as
limit the attack surface on KVM's MSR emulation code.
-
-8.26 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_CPUID
-----------------------------
Architectures: x86
async pf acknowledgment msr
0x4b564d07.
+KVM_FEATURE_MSI_EXT_DEST_ID 15 guest checks this feature bit
+ before using extended destination
+ ID bits in MSI address bits 11-5.
+
KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24 host will warn if no guest-side
per-cpu warps are expected in
kvmclock
+------------------+
| VMALLOC area | VMALLOC_START 0xc0000000 128MB - 64KB
+------------------+ VMALLOC_END
- | Cache aliasing | TLBTEMP_BASE_1 0xc7ff0000 DCACHE_WAY_SIZE
+ +------------------+
+ | Cache aliasing | TLBTEMP_BASE_1 0xc8000000 DCACHE_WAY_SIZE
| remap area 1 |
+------------------+
| Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE
+------------------+
| VMALLOC area | VMALLOC_START 0xa0000000 128MB - 64KB
+------------------+ VMALLOC_END
- | Cache aliasing | TLBTEMP_BASE_1 0xa7ff0000 DCACHE_WAY_SIZE
+ +------------------+
+ | Cache aliasing | TLBTEMP_BASE_1 0xa8000000 DCACHE_WAY_SIZE
| remap area 1 |
+------------------+
| Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE
+------------------+
| VMALLOC area | VMALLOC_START 0x90000000 128MB - 64KB
+------------------+ VMALLOC_END
- | Cache aliasing | TLBTEMP_BASE_1 0x97ff0000 DCACHE_WAY_SIZE
+ +------------------+
+ | Cache aliasing | TLBTEMP_BASE_1 0x98000000 DCACHE_WAY_SIZE
| remap area 1 |
+------------------+
| Cache aliasing | TLBTEMP_BASE_2 DCACHE_WAY_SIZE
L: amd-gfx@lists.freedesktop.org
S: Supported
T: git git://people.freedesktop.org/~agd5f/linux
-F: drivers/gpu/drm/amd/powerplay/
+F: drivers/gpu/drm/amd/pm/powerplay/
AMD SEATTLE DEVICE TREE SUPPORT
M: Brijesh Singh <brijeshkumar.singh@amd.com>
L: linux-iio@vger.kernel.org
S: Supported
W: http://ez.analog.com/community/linux-device-drivers
-F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt
+F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml
F: drivers/iio/adc/ad7768-1.c
ANALOG DEVICES INC AD7780 DRIVER
L: netdev@vger.kernel.org
S: Supported
W: https://www.marvell.com/
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst
F: drivers/net/ethernet/aquantia/atlantic/
ARM/Allwinner sunXi SoC support
M: Maxime Ripard <mripard@kernel.org>
M: Chen-Yu Tsai <wens@csie.org>
+R: Jernej Skrabec <jernej.skrabec@siol.net>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
ARM/CORESIGHT FRAMEWORK AND DRIVERS
M: Mathieu Poirier <mathieu.poirier@linaro.org>
-R: Suzuki K Poulose <suzuki.poulose@arm.com>
+M: Suzuki K Poulose <suzuki.poulose@arm.com>
R: Mike Leach <mike.leach@linaro.org>
+R: Leo Yan <leo.yan@linaro.org>
L: coresight@lists.linaro.org (moderated for non-subscribers)
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/coresight/linux.git
F: Documentation/ABI/testing/sysfs-bus-coresight-devices-*
F: Documentation/devicetree/bindings/arm/coresight-cpu-debug.txt
F: Documentation/devicetree/bindings/arm/coresight-cti.yaml
ARM/LPC32XX SOC SUPPORT
M: Vladimir Zapolskiy <vz@mleia.com>
-M: Sylvain Lemieux <slemieux.tyco@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://github.com/vzapolskiy/linux-lpc32xx.git
S: Maintained
ARM/Marvell Dove/MV78xx0/Orion SOC support
-M: Jason Cooper <jason@lakedaemon.net>
M: Andrew Lunn <andrew@lunn.ch>
M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
M: Gregory Clement <gregory.clement@bootlin.com>
F: drivers/soc/dove/
ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K, CN9130 SOC support
-M: Jason Cooper <jason@lakedaemon.net>
M: Andrew Lunn <andrew@lunn.ch>
M: Gregory Clement <gregory.clement@bootlin.com>
M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
F: sound/soc/rockchip/
N: rockchip
-ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
-M: Kukjin Kim <kgene@kernel.org>
+ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES
M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org
N: s3c64xx
N: s5pv210
-ARM/SAMSUNG MOBILE MACHINE SUPPORT
-M: Kyungmin Park <kyungmin.park@samsung.com>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Maintained
-F: arch/arm/mach-s5pv210/
-
ARM/SAMSUNG S5P SERIES 2D GRAPHICS ACCELERATION (G2D) SUPPORT
-M: Kyungmin Park <kyungmin.park@samsung.com>
-M: Kamil Debski <kamil@wypas.org>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-arm-kernel@lists.infradead.org
L: linux-media@vger.kernel.org
F: drivers/media/platform/s5p-jpeg/
ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT
-M: Kyungmin Park <kyungmin.park@samsung.com>
-M: Kamil Debski <kamil@wypas.org>
-M: Jeongtae Park <jtp.park@samsung.com>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-arm-kernel@lists.infradead.org
L: linux-media@vger.kernel.org
ARM/SOCFPGA EDAC SUPPORT
M: Dinh Nguyen <dinguyen@kernel.org>
S: Maintained
-F: drivers/edac/altera_edac.
+F: drivers/edac/altera_edac.[ch]
ARM/SPREADTRUM SoC SUPPORT
M: Orson Zhai <orsonzhai@gmail.com>
N: visconti
ARM/UNIPHIER ARCHITECTURE
-M: Masahiro Yamada <yamada.masahiro@socionext.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-uniphier.git
+S: Orphan
F: Documentation/devicetree/bindings/arm/socionext/uniphier.yaml
F: Documentation/devicetree/bindings/gpio/socionext,uniphier-gpio.yaml
F: Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml
BPF (Safe dynamic programs and tools)
M: Alexei Starovoitov <ast@kernel.org>
M: Daniel Borkmann <daniel@iogearbox.net>
+M: Andrii Nakryiko <andrii@kernel.org>
R: Martin KaFai Lau <kafai@fb.com>
R: Song Liu <songliubraving@fb.com>
R: Yonghong Song <yhs@fb.com>
-R: Andrii Nakryiko <andrii@kernel.org>
R: John Fastabend <john.fastabend@gmail.com>
R: KP Singh <kpsingh@chromium.org>
L: netdev@vger.kernel.org
F: arch/x86/net/
X: arch/x86/net/bpf_jit_comp32.c
+BPF LSM (Security Audit and Enforcement using BPF)
+M: KP Singh <kpsingh@chromium.org>
+R: Florent Revest <revest@chromium.org>
+R: Brendan Jackman <jackmanb@chromium.org>
+L: bpf@vger.kernel.org
+S: Maintained
+F: Documentation/bpf/bpf_lsm.rst
+F: include/linux/bpf_lsm.h
+F: kernel/bpf/bpf_lsm.c
+F: security/bpf/
+
BROADCOM B44 10/100 ETHERNET DRIVER
M: Michael Chan <michael.chan@broadcom.com>
L: netdev@vger.kernel.org
M: Arend van Spriel <arend.vanspriel@broadcom.com>
M: Franky Lin <franky.lin@broadcom.com>
M: Hante Meuleman <hante.meuleman@broadcom.com>
-M: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
-M: Wright Feng <wright.feng@cypress.com>
+M: Chi-hsien Lin <chi-hsien.lin@infineon.com>
+M: Wright Feng <wright.feng@infineon.com>
+M: Chung-hsien Hsu <chung-hsien.hsu@infineon.com>
L: linux-wireless@vger.kernel.org
L: brcm80211-dev-list.pdl@broadcom.com
-L: brcm80211-dev-list@cypress.com
+L: SHA-cyfmac-dev-list@infineon.com
S: Supported
F: drivers/net/wireless/broadcom/brcm80211/
L: linux-usb@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
-F: Documentation/devicetree/bindings/usb/cdns-usb3.txt
+F: Documentation/devicetree/bindings/usb/cdns,usb3.yaml
F: drivers/usb/cdns3/
CADET FM/AM RADIO RECEIVER DRIVER
C: irc://chat.freenode.net/clangbuiltlinux
F: Documentation/kbuild/llvm.rst
F: scripts/clang-tools/
+F: scripts/lld-version.sh
K: \b(?i:clang|llvm)\b
CLEANCACHE API
F: drivers/media/dvb-frontends/cxd2820r*
CXGB3 ETHERNET DRIVER (CXGB3)
-M: Vishal Kulkarni <vishal@chelsio.com>
+M: Raju Rangoju <rajur@chelsio.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.chelsio.com
F: drivers/net/ethernet/chelsio/inline_crypto/
CXGB4 ETHERNET DRIVER (CXGB4)
-M: Vishal Kulkarni <vishal@chelsio.com>
+M: Raju Rangoju <rajur@chelsio.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.chelsio.com
F: include/uapi/rdma/cxgb4-abi.h
CXGB4VF ETHERNET DRIVER (CXGB4VF)
-M: Vishal Kulkarni <vishal@gmail.com>
+M: Raju Rangoju <rajur@chelsio.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.chelsio.com
F: drivers/media/platform/sti/delta
DENALI NAND DRIVER
-M: Masahiro Yamada <yamada.masahiro@socionext.com>
L: linux-mtd@lists.infradead.org
-S: Supported
+S: Orphan
F: drivers/mtd/nand/raw/denali*
DESIGNWARE EDMA CORE IP DRIVER
M: Tony Luck <tony.luck@intel.com>
L: linux-edac@vger.kernel.org
S: Maintained
-F: drivers/edac/skx_*.c
+F: drivers/edac/skx_*.[ch]
EDAC-TI
M: Tero Kristo <t-kristo@ti.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git
F: Documentation/filesystems/ext4/
F: fs/ext4/
+F: include/trace/events/ext4.h
Extended Verification Module (EVM)
M: Mimi Zohar <zohar@linux.ibm.com>
M: john.garry@huawei.com
S: Maintained
W: http://www.hisilicon.com
-F: Documentation/devicetree/bindings/arm/hisilicon/hisilicon-low-pin-count.txt
+F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml
F: drivers/bus/hisi_lpc.c
HISILICON NETWORK SUBSYSTEM 3 DRIVER (HNS3)
W: http://www.intel.com/support/feedback.htm
W: http://e1000.sourceforge.net/
Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git
F: Documentation/networking/device_drivers/ethernet/intel/
F: drivers/net/ethernet/intel/
F: drivers/net/ethernet/intel/*/
W: https://01.org/linux-acpi
F: drivers/platform/x86/intel_menlow.c
-INTEL MIC DRIVERS (mic)
-M: Sudeep Dutt <sudeep.dutt@intel.com>
-M: Ashutosh Dixit <ashutosh.dixit@intel.com>
-S: Supported
-W: https://github.com/sudeepdutt/mic
-W: http://software.intel.com/en-us/mic-developer
-F: Documentation/misc-devices/mic/
-F: drivers/dma/mic_x100_dma.c
-F: drivers/dma/mic_x100_dma.h
-F: drivers/misc/mic/
-F: include/linux/mic_bus.h
-F: include/linux/scif.h
-F: include/uapi/linux/mic_common.h
-F: include/uapi/linux/mic_ioctl.h
-F: include/uapi/linux/scif_ioctl.h
-
INTEL P-Unit IPC DRIVER
M: Zha Qipeng <qipeng.zha@intel.com>
L: platform-driver-x86@vger.kernel.org
F: drivers/net/wireless/intel/iwlegacy/
INTEL WIRELESS WIFI LINK (iwlwifi)
-M: Johannes Berg <johannes.berg@intel.com>
-M: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
M: Luca Coelho <luciano.coelho@intel.com>
-M: Intel Linux Wireless <linuxwifi@intel.com>
L: linux-wireless@vger.kernel.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi
IOMMU DRIVERS
M: Joerg Roedel <joro@8bytes.org>
+M: Will Deacon <will@kernel.org>
L: iommu@lists.linux-foundation.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
IRQCHIP DRIVERS
M: Thomas Gleixner <tglx@linutronix.de>
-M: Jason Cooper <jason@lakedaemon.net>
M: Marc Zyngier <maz@kernel.org>
L: linux-kernel@vger.kernel.org
S: Maintained
F: arch/s390/include/asm/gmap.h
F: arch/s390/include/asm/kvm*
F: arch/s390/include/uapi/asm/kvm*
+F: arch/s390/kernel/uv.c
F: arch/s390/kvm/
F: arch/s390/mm/gmap.c
F: tools/testing/selftests/kvm/*/s390x/
F: arch/mips/lantiq
F: drivers/soc/lantiq
-LAPB module
-L: linux-x25@vger.kernel.org
-S: Orphan
-F: Documentation/networking/lapb-module.rst
-F: include/*/lapb.h
-F: net/lapb/
-
LASI 53c700 driver for PARISC
M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
L: linux-scsi@vger.kernel.org
F: drivers/input/touchscreen/melfas_mip4.c
MELLANOX BLUEFIELD I2C DRIVER
-M: Khalil Blaiech <kblaiech@mellanox.com>
+M: Khalil Blaiech <kblaiech@nvidia.com>
L: linux-i2c@vger.kernel.org
S: Supported
F: drivers/i2c/busses/i2c-mlxbf.c
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx4/en_*
MELLANOX ETHERNET DRIVER (mlx5e)
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx5/core/en_*
MELLANOX ETHERNET INNOVA DRIVERS
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx5/core/accel/*
F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/*
F: drivers/net/ethernet/mellanox/mlx5/core/fpga/*
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlxsw/
F: tools/testing/selftests/drivers/net/mlxsw/
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlxfw/
MELLANOX HARDWARE PLATFORM SUPPORT
L: linux-rdma@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlx4/
F: include/linux/mlx4/
L: linux-rdma@vger.kernel.org
S: Supported
W: http://www.mellanox.com
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: Documentation/networking/device_drivers/ethernet/mellanox/
F: drivers/net/ethernet/mellanox/mlx5/core/
F: include/linux/mlx5/
L: netdev@vger.kernel.org
S: Maintained
W: http://www.linuxfoundation.org/en/Net
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
F: Documentation/devicetree/bindings/net/
L: netdev@vger.kernel.org
S: Maintained
W: http://www.linuxfoundation.org/en/Net
-Q: http://patchwork.ozlabs.org/project/netdev/list/
+Q: https://patchwork.kernel.org/project/netdevbpf/list/
B: mailto:netdev@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
M: Ilias Apalodimas <ilias.apalodimas@linaro.org>
L: netdev@vger.kernel.org
S: Supported
+F: Documentation/networking/page_pool.rst
F: include/net/page_pool.h
+F: include/trace/events/page_pool.h
F: net/core/page_pool.c
PANASONIC LAPTOP ACPI EXTRAS DRIVER
PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support)
M: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
-M: Jason Cooper <jason@lakedaemon.net>
L: linux-pci@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: include/trace/events/pwc.h
PWM FAN DRIVER
-M: Kamil Debski <kamil@wypas.org>
M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-hwmon@vger.kernel.org
S: Supported
F: drivers/mailbox/qcom-ipcc.c
F: include/dt-bindings/mailbox/qcom-ipcc.h
+QUALCOMM IPQ4019 VQMMC REGULATOR DRIVER
+M: Robert Marko <robert.marko@sartura.hr>
+M: Luka Perkov <luka.perkov@sartura.hr>
+L: linux-arm-msm@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/regulator/vqmmc-ipq4019-regulator.yaml
+F: drivers/regulator/vqmmc-ipq4019-regulator.c
+
QUALCOMM RMNET DRIVER
M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
M: Sean Tranchetti <stranche@codeaurora.org>
F: drivers/net/wireless/realtek/rtlwifi/
REALTEK WIRELESS DRIVER (rtw88)
-M: Yan-Hsuan Chuang <yhchuang@realtek.com>
+M: Yan-Hsuan Chuang <tony0620emma@gmail.com>
L: linux-wireless@vger.kernel.org
S: Maintained
F: drivers/net/wireless/realtek/rtw88/
R: Sergei Shtylyov <sergei.shtylyov@gmail.com>
L: netdev@vger.kernel.org
L: linux-renesas-soc@vger.kernel.org
-F: Documentation/devicetree/bindings/net/renesas,*.txt
F: Documentation/devicetree/bindings/net/renesas,*.yaml
F: drivers/net/ethernet/renesas/
F: include/linux/sh_eth.h
S390 IUCV NETWORK LAYER
M: Julian Wiedmann <jwi@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
-M: Ursula Braun <ubraun@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
S390 NETWORK DRIVERS
M: Julian Wiedmann <jwi@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
-M: Ursula Braun <ubraun@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
SAMSUNG AUDIO (ASoC) DRIVERS
M: Krzysztof Kozlowski <krzk@kernel.org>
-M: Sangbeom Kim <sbkim73@samsung.com>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Supported
F: drivers/platform/x86/samsung-laptop.c
SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS
-M: Sangbeom Kim <sbkim73@samsung.com>
M: Krzysztof Kozlowski <krzk@kernel.org>
M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-kernel@vger.kernel.org
F: drivers/nfc/s3fwrn5
SAMSUNG S5C73M3 CAMERA DRIVER
-M: Kyungmin Park <kyungmin.park@samsung.com>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-media@vger.kernel.org
S: Supported
F: drivers/media/i2c/s5c73m3/*
SAMSUNG S5K5BAF CAMERA DRIVER
-M: Kyungmin Park <kyungmin.park@samsung.com>
M: Andrzej Hajda <a.hajda@samsung.com>
L: linux-media@vger.kernel.org
S: Supported
F: drivers/crypto/s5p-sss.c
SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS
-M: Kyungmin Park <kyungmin.park@samsung.com>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: linux-media@vger.kernel.org
S: Supported
F: include/linux/platform_data/clk-s3c2410.h
SAMSUNG SPI DRIVERS
-M: Kukjin Kim <kgene@kernel.org>
M: Krzysztof Kozlowski <krzk@kernel.org>
M: Andi Shyti <andi@etezian.org>
L: linux-spi@vger.kernel.org
F: drivers/thermal/samsung/
SAMSUNG USB2 PHY DRIVER
-M: Kamil Debski <kamil@wypas.org>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: linux-kernel@vger.kernel.org
S: Supported
F: include/linux/slimbus.h
SFC NETWORK DRIVER
-M: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
-M: Edward Cree <ecree@solarflare.com>
-M: Martin Habets <mhabets@solarflare.com>
+M: Edward Cree <ecree.xilinx@gmail.com>
+M: Martin Habets <habetsm.xilinx@gmail.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/sfc/
F: drivers/misc/sgi-xp/
SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
-M: Ursula Braun <ubraun@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
M: Binghui Wang <wangbinghui@hisilicon.com>
L: linux-usb@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/phy/phy-hi3660-usb3.txt
+F: Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml
F: drivers/phy/hisilicon/phy-hi3660-usb3.c
USB ISP116X DRIVER
S: Supported
F: drivers/usb/class/usblp.c
+USB RAW GADGET DRIVER
+R: Andrey Konovalov <andreyknvl@gmail.com>
+L: linux-usb@vger.kernel.org
+S: Maintained
+F: Documentation/usb/raw-gadget.rst
+F: drivers/usb/gadget/legacy/raw_gadget.c
+F: include/uapi/linux/usb/raw_gadget.h
+
USB QMI WWAN NETWORK DRIVER
M: Bjørn Mork <bjorn@mork.no>
L: netdev@vger.kernel.org
S: Maintained
N: axp[128]
-X.25 NETWORK LAYER
-M: Andrew Hendry <andrew.hendry@gmail.com>
+X.25 STACK
+M: Martin Schiller <ms@dev.tdt.de>
L: linux-x25@vger.kernel.org
-S: Odd Fixes
+S: Maintained
+F: Documentation/networking/lapb-module.rst
F: Documentation/networking/x25*
+F: drivers/net/wan/hdlc_x25.c
+F: drivers/net/wan/lapbether.c
+F: include/*/lapb.h
F: include/net/x25*
+F: include/uapi/linux/x25.h
+F: net/lapb/
F: net/x25/
X86 ARCHITECTURE (32-BIT AND 64-BIT)
L: bpf@vger.kernel.org
S: Supported
F: include/net/xdp.h
+F: include/net/xdp_priv.h
F: include/trace/events/xdp.h
F: kernel/bpf/cpumap.c
F: kernel/bpf/devmap.c
F: net/core/xdp.c
-N: xdp
-K: xdp
+F: samples/bpf/xdp*
+F: tools/testing/selftests/bpf/*xdp*
+F: tools/testing/selftests/bpf/*/*xdp*
+F: drivers/net/ethernet/*/*/*/*/*xdp*
+F: drivers/net/ethernet/*/*/*xdp*
+K: (?:\b|_)xdp(?:\b|_)
XDP SOCKETS (AF_XDP)
M: Björn Töpel <bjorn.topel@intel.com>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Maintained
+F: Documentation/networking/af_xdp.rst
F: include/net/xdp_sock*
F: include/net/xsk_buff_pool.h
F: include/uapi/linux/if_xdp.h
+F: include/uapi/linux/xdp_diag.h
+F: include/net/netns/xdp.h
F: net/xdp/
F: samples/bpf/xdpsock*
F: tools/lib/bpf/xsk*
VERSION = 5
PATCHLEVEL = 10
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc7
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
OBJCOPY = llvm-objcopy
OBJDUMP = llvm-objdump
READELF = llvm-readelf
-OBJSIZE = llvm-size
STRIP = llvm-strip
else
CC = $(CROSS_COMPILE)gcc
OBJCOPY = $(CROSS_COMPILE)objcopy
OBJDUMP = $(CROSS_COMPILE)objdump
READELF = $(CROSS_COMPILE)readelf
-OBJSIZE = $(CROSS_COMPILE)size
STRIP = $(CROSS_COMPILE)strip
endif
PAHOLE = pahole
CLANG_FLAGS :=
export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
+export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL
export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD
export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
DEBUG_CFLAGS += -g
endif
+ifneq ($(LLVM_IAS),1)
KBUILD_AFLAGS += -Wa,-gdwarf-2
+endif
ifdef CONFIG_DEBUG_INFO_DWARF4
DEBUG_CFLAGS += -gdwarf-4
KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init)
# change __FILE__ to the relative path from the srctree
-KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
+KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
# ensure -fcf-protection is disabled when using retpoline as it is
# incompatible with -mindirect-branch=thunk-extern
LDFLAGS_vmlinux += --pack-dyn-relocs=relr
endif
+# We never want expected sections to be placed heuristically by the
+# linker. All sections should be explicitly named in the linker script.
+ifdef CONFIG_LD_ORPHAN_WARN
+LDFLAGS_vmlinux += --orphan-handling=warn
+endif
+
# Align the bit size of userspace programs with the kernel
KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
bool
depends on HAVE_STATIC_CALL
+config ARCH_WANT_LD_ORPHAN_WARN
+ bool
+ help
+ An arch should select this symbol once all linker sections are explicitly
+ included, size-asserted, or discarded in the linker scripts. This is
+ important because we never want expected sections to be placed heuristically
+ by the linker, since the locations of such sections can change between linker
+ versions.
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
void arch_cpu_idle(void)
{
wtint(0);
- local_irq_enable();
+ raw_local_irq_enable();
}
void arch_cpu_idle_dead(void)
x <<= 2;
r -= 2;
}
- if (!(x & 0x80000000u)) {
- x <<= 1;
+ if (!(x & 0x80000000u))
r -= 1;
- }
return r;
}
#ifdef CONFIG_ARC_HAS_PAE40
#define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE)
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
#else
#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE)
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
#endif
/**************************************************************************
sr r5, [ARC_REG_LPB_CTRL]
1:
#endif /* CONFIG_ARC_LPB_DISABLE */
-#endif
+
+ /* On HSDK, CCMs need to remapped super early */
+#ifdef CONFIG_ARC_SOC_HSDK
+ mov r6, 0x60000000
+ lr r5, [ARC_REG_ICCM_BUILD]
+ breq r5, 0, 1f
+ sr r6, [ARC_REG_AUX_ICCM]
+1:
+ lr r5, [ARC_REG_DCCM_BUILD]
+ breq r5, 0, 2f
+ sr r6, [ARC_REG_AUX_DCCM]
+2:
+#endif /* CONFIG_ARC_SOC_HSDK */
+
+#endif /* CONFIG_ISA_ARCV2 */
+
; Config DSP_CTRL properly, so kernel may use integer multiply,
; multiply-accumulate, and divide operations
DSP_EARLY_INIT
#ifdef CONFIG_ARC_DW2_UNWIND
-static void seed_unwind_frame_info(struct task_struct *tsk,
- struct pt_regs *regs,
- struct unwind_frame_info *frame_info)
+static int
+seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs,
+ struct unwind_frame_info *frame_info)
{
- /*
- * synchronous unwinding (e.g. dump_stack)
- * - uses current values of SP and friends
- */
- if (tsk == NULL && regs == NULL) {
+ if (regs) {
+ /*
+ * Asynchronous unwinding of intr/exception
+ * - Just uses the pt_regs passed
+ */
+ frame_info->task = tsk;
+
+ frame_info->regs.r27 = regs->fp;
+ frame_info->regs.r28 = regs->sp;
+ frame_info->regs.r31 = regs->blink;
+ frame_info->regs.r63 = regs->ret;
+ frame_info->call_frame = 0;
+ } else if (tsk == NULL || tsk == current) {
+ /*
+ * synchronous unwinding (e.g. dump_stack)
+ * - uses current values of SP and friends
+ */
unsigned long fp, sp, blink, ret;
frame_info->task = current;
frame_info->regs.r31 = blink;
frame_info->regs.r63 = ret;
frame_info->call_frame = 0;
- } else if (regs == NULL) {
+ } else {
/*
- * Asynchronous unwinding of sleeping task
- * - Gets SP etc from task's pt_regs (saved bottom of kernel
- * mode stack of task)
+ * Asynchronous unwinding of a likely sleeping task
+ * - first ensure it is actually sleeping
+ * - if so, it will be in __switch_to, kernel mode SP of task
+ * is safe-kept and BLINK at a well known location in there
*/
+ if (tsk->state == TASK_RUNNING)
+ return -1;
+
frame_info->task = tsk;
frame_info->regs.r27 = TSK_K_FP(tsk);
frame_info->regs.r28 += 60;
frame_info->call_frame = 0;
- } else {
- /*
- * Asynchronous unwinding of intr/exception
- * - Just uses the pt_regs passed
- */
- frame_info->task = tsk;
-
- frame_info->regs.r27 = regs->fp;
- frame_info->regs.r28 = regs->sp;
- frame_info->regs.r31 = regs->blink;
- frame_info->regs.r63 = regs->ret;
- frame_info->call_frame = 0;
}
+ return 0;
}
#endif
int (*consumer_fn) (unsigned int, void *), void *arg)
{
#ifdef CONFIG_ARC_DW2_UNWIND
- int ret = 0;
+ int ret = 0, cnt = 0;
unsigned int address;
struct unwind_frame_info frame_info;
- seed_unwind_frame_info(tsk, regs, &frame_info);
+ if (seed_unwind_frame_info(tsk, regs, &frame_info))
+ return 0;
while (1) {
address = UNW_PC(&frame_info);
break;
frame_info.regs.r63 = frame_info.regs.r31;
+
+ if (cnt++ > 128) {
+ printk("unwinder looping too long, aborting !\n");
+ return 0;
+ }
}
return address; /* return the last address it saw */
* -Changes related to MMU v2 (Rel 4.8)
*
* Vineetg: Aug 29th 2008
- * -In TLB Flush operations (Metal Fix MMU) there is a explict command to
+ * -In TLB Flush operations (Metal Fix MMU) there is a explicit command to
* flush Micro-TLBS. If TLB Index Reg is invalid prior to TLBIVUTLB cmd,
* it fails. Thus need to load it with ANY valid value before invoking
* TLBIVUTLB cmd
*
* Vineetg: Aug 21th 2008:
* -Reduced the duration of IRQ lockouts in TLB Flush routines
- * -Multiple copies of TLB erase code seperated into a "single" function
+ * -Multiple copies of TLB erase code separated into a "single" function
* -In TLB Flush routines, interrupt disabling moved UP to retrieve ASID
* in interrupt-safe region.
*
*
* Although J-TLB is 2 way set assoc, ARC700 caches J-TLB into uTLBS which has
* much higher associativity. u-D-TLB is 8 ways, u-I-TLB is 4 ways.
- * Given this, the thrasing problem should never happen because once the 3
+ * Given this, the thrashing problem should never happen because once the 3
* J-TLB entries are created (even though 3rd will knock out one of the prev
* two), the u-D-TLB and u-I-TLB will have what is required to accomplish memcpy
*
* There was however an obscure hardware bug, where uTLB flush would
* fail when a prior probe for J-TLB (both totally unrelated) would
* return lkup err - because the entry didn't exist in MMU.
- * The Workround was to set Index reg with some valid value, prior to
+ * The Workaround was to set Index reg with some valid value, prior to
* flush. This was fixed in MMU v3
*/
unsigned int idx;
}
/*
- * Flush the entrie MM for userland. The fastest way is to move to Next ASID
+ * Flush the entire MM for userland. The fastest way is to move to Next ASID
*/
noinline void local_flush_tlb_mm(struct mm_struct *mm)
{
* Difference between this and Kernel Range Flush is
* -Here the fastest way (if range is too large) is to move to next ASID
* without doing any explicit Shootdown
- * -In case of kernel Flush, entry has to be shot down explictly
+ * -In case of kernel Flush, entry has to be shot down explicitly
*/
void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end)
* Super Page size is configurable in hardware (4K to 16M), but fixed once
* RTL builds.
*
- * The exact THP size a Linx configuration will support is a function of:
+ * The exact THP size a Linux configuration will support is a function of:
* - MMU page size (typical 8K, RTL fixed)
* - software page walker address split between PGD:PTE:PFN (typical
* 11:8:13, but can be changed with 1 line)
#endif
-/* Read the Cache Build Confuration Registers, Decode them and save into
+/* Read the Cache Build Configuration Registers, Decode them and save into
* the cpuinfo structure for later use.
* No Validation is done here, simply read/convert the BCRs
*/
pr_info("%s", arc_mmu_mumbojumbo(0, str, sizeof(str)));
/*
- * Can't be done in processor.h due to header include depenedencies
+ * Can't be done in processor.h due to header include dependencies
*/
BUILD_BUG_ON(!IS_ALIGNED((CONFIG_ARC_KVADDR_SIZE << 20), PMD_SIZE));
/*
* stack top size sanity check,
- * Can't be done in processor.h due to header include depenedencies
+ * Can't be done in processor.h due to header include dependencies
*/
BUILD_BUG_ON(!IS_ALIGNED(STACK_TOP, PMD_SIZE));
* the duplicate one.
* -Knob to be verbose abt it.(TODO: hook them up to debugfs)
*/
-volatile int dup_pd_silent; /* Be slient abt it or complain (default) */
+volatile int dup_pd_silent; /* Be silent abt it or complain (default) */
void do_tlb_overlap_fault(unsigned long cause, unsigned long address,
struct pt_regs *regs)
/***********************************************************************
* Diagnostic Routines
- * -Called from Low Level TLB Hanlders if things don;t look good
+ * -Called from Low Level TLB Handlers if things don;t look good
**********************************************************************/
#ifdef CONFIG_ARC_DBG_TLB_PARANOIA
#define ARC_CCM_UNUSED_ADDR 0x60000000
-static void __init hsdk_init_per_cpu(unsigned int cpu)
-{
- /*
- * By default ICCM is mapped to 0x7z while this area is used for
- * kernel virtual mappings, so move it to currently unused area.
- */
- if (cpuinfo_arc700[cpu].iccm.sz)
- write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR);
-
- /*
- * By default DCCM is mapped to 0x8z while this area is used by kernel,
- * so move it to currently unused area.
- */
- if (cpuinfo_arc700[cpu].dccm.sz)
- write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR);
-}
#define ARC_PERIPHERAL_BASE 0xf0000000
#define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000)
MACHINE_START(SIMULATION, "hsdk")
.dt_compat = hsdk_compat,
.init_early = hsdk_init_early,
- .init_per_cpu = hsdk_init_per_cpu,
MACHINE_END
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
select ARCH_WANT_IPC_PARSE_VERSION
+ select ARCH_WANT_LD_ORPHAN_WARN
select BINFMT_FLAT_ARGVP_ENVP_ON_STACK
select BUILDTIME_TABLE_SORT if MMU
select CLONE_BACKWARDS
KBUILD_LDFLAGS_MODULE += --be8
endif
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
-
GZFLAGS :=-9
#KBUILD_CFLAGS +=-pipe
# Delete all temporary local symbols
LDFLAGS_vmlinux += -X
# Report orphan sections
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+ifdef CONFIG_LD_ORPHAN_WARN
+LDFLAGS_vmlinux += --orphan-handling=warn
+endif
# Next argument is a linker script
LDFLAGS_vmlinux += -T
@ issued from HYP mode take us to the correct handler code. We
@ will disable the MMU before jumping to the kernel proper.
@
+ ARM( bic r1, r1, #(1 << 30) ) @ clear HSCTLR.TE
+ THUMB( orr r1, r1, #(1 << 30) ) @ set HSCTLR.TE
+ mcr p15, 4, r1, c1, c0, 0
adr r0, __hyp_reentry_vectors
mcr p15, 4, r0, c12, c0, 0 @ set HYP vector base (HVBAR)
isb
ranges = <0x0 0x100000 0x8000>;
mac_sw: switch@0 {
- compatible = "ti,am4372-cpsw","ti,cpsw-switch";
+ compatible = "ti,am4372-cpsw-switch", "ti,cpsw-switch";
reg = <0x0 0x4000>;
ranges = <0 0 0x4000>;
clocks = <&cpsw_125mhz_gclk>, <&dpll_clksel_mac_clk>;
always-on;
};
+ edac: sdram@1e6e0000 {
+ compatible = "aspeed,ast2600-sdram-edac", "syscon";
+ reg = <0x1e6e0000 0x174>;
+ interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
ahb {
compatible = "simple-bus";
#address-cells = <1>;
interrupts = <GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "int0", "int1";
- clocks = <&mcan_clk>, <&l3_iclk_div>;
- clock-names = "cclk", "hclk";
+ clocks = <&l3_iclk_div>, <&mcan_clk>;
+ clock-names = "hclk", "cclk";
bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>;
};
};
};
&clock {
- clocks = <&clock CLK_XUSBXTI>;
assigned-clocks = <&clock CLK_FOUT_EPLL>;
assigned-clock-rates = <45158401>;
};
MX50_PAD_CSPI_MISO__CSPI_MISO 0x00
MX50_PAD_CSPI_MOSI__CSPI_MOSI 0x00
MX50_PAD_CSPI_SS0__GPIO4_11 0xc4
- MX50_PAD_ECSPI1_MOSI__CSPI_SS1 0xf4
+ MX50_PAD_ECSPI1_MOSI__GPIO4_13 0x84
>;
};
#size-cells = <0>;
/* Microchip KSZ9031RNX PHY */
- rgmii_phy: ethernet-phy@4 {
- reg = <4>;
+ rgmii_phy: ethernet-phy@0 {
+ reg = <0>;
interrupts-extended = <&gpio1 28 IRQ_TYPE_LEVEL_LOW>;
reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
reset-assert-us = <10000>;
&fec {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_enet>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
/delete-property/ #size-cells;
spi-slave;
status = "okay";
- ready-gpio = <&gpio 125 GPIO_ACTIVE_HIGH>;
+ ready-gpios = <&gpio 125 GPIO_ACTIVE_HIGH>;
slave {
compatible = "olpc,xo1.75-ec";
spi-cpha;
- cmd-gpio = <&gpio 155 GPIO_ACTIVE_HIGH>;
+ cmd-gpios = <&gpio 155 GPIO_ACTIVE_HIGH>;
};
};
interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&soc_clocks MMP2_CLK_CCIC0>;
clock-names = "axi";
+ power-domains = <&soc_clocks MMP3_POWER_DOMAIN_CAMERA>;
#clock-cells = <0>;
clock-output-names = "mclk";
status = "disabled";
interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&soc_clocks MMP2_CLK_CCIC1>;
clock-names = "axi";
+ power-domains = <&soc_clocks MMP3_POWER_DOMAIN_CAMERA>;
#clock-cells = <0>;
clock-output-names = "mclk";
status = "disabled";
states = <1800000 0x1>,
<2900000 0x0>;
};
+
+ vin: vin {
+ compatible = "regulator-fixed";
+ regulator-name = "vin";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-always-on;
+ };
};
&adc {
regulators {
compatible = "st,stpmic1-regulators";
+ buck1-supply = <&vin>;
+ buck2-supply = <&vin>;
+ buck3-supply = <&vin>;
+ buck4-supply = <&vin>;
ldo1-supply = <&v3v3>;
ldo2-supply = <&v3v3>;
ldo3-supply = <&vdd_ddr>;
+ ldo4-supply = <&vin>;
ldo5-supply = <&v3v3>;
ldo6-supply = <&v3v3>;
+ vref_ddr-supply = <&vin>;
+ boost-supply = <&vin>;
pwr_sw1-supply = <&bst_out>;
pwr_sw2-supply = <&bst_out>;
linux,code = <KEY_A>;
gpios = <&gpiof 3 GPIO_ACTIVE_LOW>;
};
+
+ /*
+ * The EXTi IRQ line 0 is shared with PMIC,
+ * so mark this as polled GPIO key.
+ */
+ button-2 {
+ label = "TA3-GPIO-C";
+ linux,code = <KEY_C>;
+ gpios = <&gpiog 0 GPIO_ACTIVE_LOW>;
+ };
};
gpio-keys {
wakeup-source;
};
- button-2 {
- label = "TA3-GPIO-C";
- linux,code = <KEY_C>;
- gpios = <&gpioi 11 GPIO_ACTIVE_LOW>;
- wakeup-source;
- };
-
button-3 {
label = "TA4-GPIO-D";
linux,code = <KEY_D>;
led-0 {
label = "green:led5";
- gpios = <&gpiog 2 GPIO_ACTIVE_HIGH>;
+ gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>;
default-state = "off";
};
gpio = <&gpiog 3 GPIO_ACTIVE_LOW>;
regulator-always-on;
regulator-boot-on;
+ vin-supply = <&vdd>;
};
};
vdda: ldo1 {
regulator-name = "vdda";
+ regulator-always-on;
regulator-min-microvolt = <2900000>;
regulator-max-microvolt = <2900000>;
interrupts = <IT_CURLIM_LDO1 0>;
};
};
+&dts {
+ status = "okay";
+};
+
&i2c4 {
pinctrl-names = "default";
pinctrl-0 = <&i2c4_pins_a>;
dais = <&sai2a_port &sai2b_port &i2s2_port>;
status = "okay";
};
+
+ vin: vin {
+ compatible = "regulator-fixed";
+ regulator-name = "vin";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-always-on;
+ };
};
&adc {
regulators {
compatible = "st,stpmic1-regulators";
+ buck1-supply = <&vin>;
+ buck2-supply = <&vin>;
+ buck3-supply = <&vin>;
+ buck4-supply = <&vin>;
ldo1-supply = <&v3v3>;
+ ldo2-supply = <&vin>;
ldo3-supply = <&vdd_ddr>;
+ ldo4-supply = <&vin>;
+ ldo5-supply = <&vin>;
ldo6-supply = <&v3v3>;
+ vref_ddr-supply = <&vin>;
+ boost-supply = <&vin>;
pwr_sw1-supply = <&bst_out>;
pwr_sw2-supply = <&bst_out>;
trips {
cpu_alert0: cpu-alert0 {
/* milliCelsius */
- temperature = <850000>;
+ temperature = <85000>;
hysteresis = <2000>;
type = "passive";
};
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_gmac_3v3>;
status = "okay";
};
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_sw>;
phy-handle = <&rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
allwinner,rx-delay-ps = <700>;
allwinner,tx-delay-ps = <700>;
status = "okay";
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_dldo4>;
phy-handle = <&rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
};
};
-&emac {
- /* LEDs changed to active high on the plus */
- /delete-property/ allwinner,leds-active-low;
-};
-
&mmc1 {
vmmc-supply = <®_vcc3v3>;
bus-width = <4>;
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_dc1sw>;
status = "okay";
};
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_cldo1>;
status = "okay";
};
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-supply = <®_cldo1>;
status = "okay";
};
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
};
};
+&mdio1 {
+ clock-frequency = <5000000>;
+};
&iomuxc {
pinctrl_gpio_e6185_eeprom_sel: pinctrl-gpio-e6185-eeprom-spi0 {
CONFIG_SPI_IMX=y
CONFIG_SPI_SPIDEV=y
CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_MXC=y
CONFIG_W1=y
CONFIG_W1_MASTER_MXC=y
CONFIG_W1_SLAVE_THERM=y
CONFIG_GPIO_PCF857X=y
CONFIG_GPIO_STMPE=y
CONFIG_GPIO_74X164=y
+CONFIG_GPIO_MXC=y
CONFIG_POWER_RESET=y
CONFIG_POWER_RESET_SYSCON=y
CONFIG_POWER_RESET_SYSCON_POWEROFF=y
CONFIG_SPI_ORION=y
CONFIG_GPIO_ASPEED=m
CONFIG_GPIO_ASPEED_SGPIO=y
+CONFIG_GPIO_MXC=y
CONFIG_POWER_RESET=y
CONFIG_POWER_RESET_GPIO=y
CONFIG_POWER_RESET_QNAP=y
CONFIG_GPIO_TPS6586X=y
CONFIG_GPIO_TPS65910=y
CONFIG_GPIO_TWL4030=y
+CONFIG_GPIO_MXC=y
CONFIG_POWER_AVS=y
CONFIG_ROCKCHIP_IODOMAIN=y
CONFIG_POWER_RESET_AS3722=y
CONFIG_BINFMT_MISC=y
CONFIG_CMA=y
CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_PGTABLE_MAPPING=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
unsigned long val, void *data);
/* optinsn template addresses */
-extern __visible kprobe_opcode_t optprobe_template_entry;
-extern __visible kprobe_opcode_t optprobe_template_val;
-extern __visible kprobe_opcode_t optprobe_template_call;
-extern __visible kprobe_opcode_t optprobe_template_end;
-extern __visible kprobe_opcode_t optprobe_template_sub_sp;
-extern __visible kprobe_opcode_t optprobe_template_add_sp;
-extern __visible kprobe_opcode_t optprobe_template_restore_begin;
-extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn;
-extern __visible kprobe_opcode_t optprobe_template_restore_end;
+extern __visible kprobe_opcode_t optprobe_template_entry[];
+extern __visible kprobe_opcode_t optprobe_template_val[];
+extern __visible kprobe_opcode_t optprobe_template_call[];
+extern __visible kprobe_opcode_t optprobe_template_end[];
+extern __visible kprobe_opcode_t optprobe_template_sub_sp[];
+extern __visible kprobe_opcode_t optprobe_template_add_sp[];
+extern __visible kprobe_opcode_t optprobe_template_restore_begin[];
+extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[];
+extern __visible kprobe_opcode_t optprobe_template_restore_end[];
#define MAX_OPTIMIZED_LENGTH 4
#define MAX_OPTINSN_SIZE \
- ((unsigned long)&optprobe_template_end - \
- (unsigned long)&optprobe_template_entry)
+ ((unsigned long)optprobe_template_end - \
+ (unsigned long)optprobe_template_entry)
#define RELATIVEJUMP_SIZE 4
struct arch_optimized_insn {
#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t))
#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32))
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
+
/*
* PMD_SHIFT determines the size of the area a second-level page table can map
* PGDIR_SHIFT determines what a third-level page table entry can map
#define PTE_HWTABLE_OFF (0)
#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64))
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
+
/*
* PGDIR_SHIFT determines the size a top-level page table entry can map.
*/
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
arm_pm_idle();
else
cpu_do_idle();
- local_irq_enable();
+ raw_local_irq_enable();
}
void arch_cpu_idle_prepare(void)
ARM_DISCARD
#ifndef CONFIG_SMP_ON_UP
*(.alt.smp.init)
+#endif
+#ifndef CONFIG_ARM_UNWIND
+ *(.ARM.exidx) *(.ARM.exidx.*)
+ *(.ARM.extab) *(.ARM.extab.*)
#endif
}
/*
* MMU is disabled, use the physical address of the coherency
- * base address. However, if the coherency fabric isn't mapped
- * (i.e its virtual address is zero), it means coherency is
- * not enabled, so we return 0.
+ * base address, (or 0x0 if the coherency fabric is not mapped)
*/
- ldr r1, =coherency_base
- cmp r1, #0
- beq 2f
adr r1, 3f
ldr r3, [r1]
ldr r1, [r1, r3]
.dev_id = "ohci",
.table = {
/* Power GPIO on the I2C-attached TPS65010 */
- GPIO_LOOKUP("i2c-tps65010", 1, "power", GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("tps65010", 0, "power", GPIO_ACTIVE_HIGH),
GPIO_LOOKUP(OMAP_GPIO_LABEL, 9, "overcurrent",
GPIO_ACTIVE_HIGH),
},
depends on ARCH_MULTI_V6
select ARCH_OMAP2PLUS
select CPU_V6
- select PM_GENERIC_DOMAINS if PM
select SOC_HAS_OMAP2_SDRC
config ARCH_OMAP3
select OMAP_DM_TIMER
select OMAP_GPMC
select PINCTRL
+ select PM_GENERIC_DOMAINS if PM
+ select PM_GENERIC_DOMAINS_OF if PM
select RESET_CONTROLLER
select SOC_BUS
select TI_SYSC
if (mpuss_can_lose_context) {
error = cpu_cluster_pm_enter();
if (error) {
- omap_set_pwrdm_state(mpu_pd, PWRDM_POWER_ON);
- goto cpu_cluster_pm_out;
+ index = 0;
+ cx = state_ptr + index;
+ pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state);
+ omap_set_pwrdm_state(mpu_pd, cx->mpu_state);
+ mpuss_can_lose_context = 0;
}
}
}
omap4_enter_lowpower(dev->cpu, cx->cpu_state);
cpu_done[dev->cpu] = true;
-cpu_cluster_pm_out:
/* Wakeup CPU1 only if it is not offlined */
if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) {
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
- unsigned long start = PHYS_PFN(range_start);
- unsigned long end = PHYS_PFN(range_end);
+ unsigned long start = PFN_UP(range_start);
+ unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
"optprobe_template_end:\n");
#define TMPL_VAL_IDX \
- ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry)
#define TMPL_CALL_IDX \
- ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry)
#define TMPL_END_IDX \
- ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry)
#define TMPL_ADD_SP \
- ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry)
#define TMPL_SUB_SP \
- ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry)
#define TMPL_RESTORE_BEGIN \
- ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry)
#define TMPL_RESTORE_ORIGN_INSN \
- ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry)
#define TMPL_RESTORE_END \
- ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry)
+ ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry)
/*
* ARM can always optimize an instruction when using ARM ISA, except
}
/* Copy arch-dep-instance from template. */
- memcpy(code, (unsigned long *)&optprobe_template_entry,
+ memcpy(code, (unsigned long *)optprobe_template_entry,
TMPL_END_IDX * sizeof(kprobe_opcode_t));
/* Adjust buffer according to instruction. */
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
+ select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARM_AMBA
select ARM_ARCH_TIMER
If unsure, say Y.
+config ARM64_ERRATUM_1508412
+ bool "Cortex-A77: 1508412: workaround deadlock on sequence of NC/Device load and store exclusive or PAR read"
+ default y
+ help
+ This option adds a workaround for Arm Cortex-A77 erratum 1508412.
+
+ Affected Cortex-A77 cores (r0p0, r1p0) could deadlock on a sequence
+ of a store-exclusive or read of PAR_EL1 and a load with device or
+ non-cacheable memory attributes. The workaround depends on a firmware
+ counterpart.
+
+ KVM guests must also have the workaround implemented or they can
+ deadlock the system.
+
+ Work around the issue by inserting DMB SY barriers around PAR_EL1
+ register reads and warning KVM users. The DMB barrier is sufficient
+ to prevent a speculative PAR_EL1 read.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
config NODES_SHIFT
int "Maximum NUMA Nodes (as a power of 2)"
range 1 10
- default "2"
+ default "4"
depends on NEED_MULTIPLE_NODES
help
Specify the maximum number of NUMA Nodes available on the target
config ARCH_BERLIN
bool "Marvell Berlin SoC Family"
select DW_APB_ICTL
+ select DW_APB_TIMER_OF
select GPIOLIB
select PINCTRL
help
endif
endif
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
-
ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
$(warning LSE atomics not supported by binutils)
&emac {
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_dc1sw>;
status = "okay";
&emac {
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_gmac_3v3>;
status = "okay";
&emac {
pinctrl-names = "default";
pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-txid";
phy-handle = <&ext_rgmii_phy>;
status = "okay";
};
status = "okay";
port {
- #address-cells = <1>;
- #size-cells = <0>;
-
csi_ep: endpoint {
remote-endpoint = <&ov5640_ep>;
bus-width = <8>;
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
/delete-property/ allwinner,leds-active-low;
status = "okay";
};
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <®_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
&emac {
pinctrl-names = "default";
pinctrl-0 = <&ext_rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_aldo2>;
status = "okay";
&emac {
pinctrl-names = "default";
pinctrl-0 = <&ext_rgmii_pins>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
phy-handle = <&ext_rgmii_phy>;
phy-supply = <®_gmac_3v3>;
allwinner,rx-delay-ps = <200>;
flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00a";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00a";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb {
+ status = "okay";
+ dr_mode = "otg";
+ vbus-supply = <&usb_pwr>;
+};
#size-cells = <2>;
ranges;
+ usb: usb@ffe09080 {
+ compatible = "amlogic,meson-axg-usb-ctrl";
+ reg = <0x0 0xffe09080 0x0 0x20>;
+ interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clocks = <&clkc CLKID_USB>, <&clkc CLKID_USB1_DDR_BRIDGE>;
+ clock-names = "usb_ctrl", "ddr";
+ resets = <&reset RESET_USB_OTG>;
+
+ dr_mode = "otg";
+
+ phys = <&usb2_phy1>;
+ phy-names = "usb2-phy1";
+
+ dwc2: usb@ff400000 {
+ compatible = "amlogic,meson-g12a-usb", "snps,dwc2";
+ reg = <0x0 0xff400000 0x0 0x40000>;
+ interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc CLKID_USB1>;
+ clock-names = "otg";
+ phys = <&usb2_phy1>;
+ dr_mode = "peripheral";
+ g-rx-fifo-size = <192>;
+ g-np-tx-fifo-size = <128>;
+ g-tx-fifo-size = <128 128 16 16 16>;
+ };
+
+ dwc3: usb@ff500000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0xff500000 0x0 0x100000>;
+ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ maximum-speed = "high-speed";
+ snps,dis_u2_susphy_quirk;
+ };
+ };
+
ethmac: ethernet@ff3f0000 {
compatible = "amlogic,meson-axg-dwmac",
"snps,dwmac-3.70a",
"timing-adjustment";
rx-fifo-depth = <4096>;
tx-fifo-depth = <2048>;
+ resets = <&reset RESET_ETHERNET>;
+ reset-names = "stmmaceth";
status = "disabled";
};
clock-names = "core", "clkin0", "clkin1";
resets = <&reset RESET_SD_EMMC_C>;
};
+
+ usb2_phy1: phy@9020 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x9020 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ };
};
sram: sram@fffc0000 {
};
ethmac: ethernet@ff3f0000 {
- compatible = "amlogic,meson-axg-dwmac",
+ compatible = "amlogic,meson-g12a-dwmac",
"snps,dwmac-3.70a",
"snps,dwmac";
reg = <0x0 0xff3f0000 0x0 0x10000>,
"timing-adjustment";
rx-fifo-depth = <4096>;
tx-fifo-depth = <2048>;
+ resets = <&reset RESET_ETHERNET>;
+ reset-names = "stmmaceth";
status = "disabled";
mdio0: mdio {
hwrng: rng@218 {
compatible = "amlogic,meson-rng";
reg = <0x0 0x218 0x0 0x4>;
+ clocks = <&clkc CLKID_RNG0>;
+ clock-names = "core";
};
};
regulator-min-microvolt = <680000>;
regulator-max-microvolt = <1040000>;
- pwms = <&pwm_AO_cd 1 1500 0>;
+ pwms = <&pwm_ab 0 1500 0>;
};
&vddcpu_b {
#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/meson-gxbb-power.h>
+#include <dt-bindings/reset/amlogic,meson-gxbb-reset.h>
#include <dt-bindings/thermal/thermal.h>
/ {
interrupt-names = "macirq";
rx-fifo-depth = <4096>;
tx-fifo-depth = <2048>;
+ resets = <&reset RESET_ETHERNET>;
+ reset-names = "stmmaceth";
power-domains = <&pwrc PWRC_GXBB_ETHERNET_MEM_ID>;
status = "disabled";
};
usb {
compatible = "simple-bus";
dma-ranges;
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0x0 0x0 0x68500000 0x00400000>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>;
usbphy0: usb-phy@0 {
compatible = "brcm,sr-usb-combo-phy";
- reg = <0x00000000 0x100>;
+ reg = <0x0 0x00000000 0x0 0x100>;
#phy-cells = <1>;
status = "disabled";
};
xhci0: usb@1000 {
compatible = "generic-xhci";
- reg = <0x00001000 0x1000>;
+ reg = <0x0 0x00001000 0x0 0x1000>;
interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usbphy0 1>, <&usbphy0 0>;
phy-names = "phy0", "phy1";
bdc0: usb@2000 {
compatible = "brcm,bdc-v0.16";
- reg = <0x00002000 0x1000>;
+ reg = <0x0 0x00002000 0x0 0x1000>;
interrupts = <GIC_SPI 259 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usbphy0 0>, <&usbphy0 1>;
phy-names = "phy0", "phy1";
usbphy1: usb-phy@10000 {
compatible = "brcm,sr-usb-combo-phy";
- reg = <0x00010000 0x100>;
+ reg = <0x0 0x00010000 0x0 0x100>;
#phy-cells = <1>;
status = "disabled";
};
usbphy2: usb-phy@20000 {
compatible = "brcm,sr-usb-hs-phy";
- reg = <0x00020000 0x100>;
+ reg = <0x0 0x00020000 0x0 0x100>;
#phy-cells = <0>;
status = "disabled";
};
xhci1: usb@11000 {
compatible = "generic-xhci";
- reg = <0x00011000 0x1000>;
+ reg = <0x0 0x00011000 0x0 0x1000>;
interrupts = <GIC_SPI 263 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usbphy1 1>, <&usbphy2>, <&usbphy1 0>;
phy-names = "phy0", "phy1", "phy2";
bdc1: usb@21000 {
compatible = "brcm,bdc-v0.16";
- reg = <0x00021000 0x1000>;
+ reg = <0x0 0x00021000 0x0 0x1000>;
interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usbphy2>;
phy-names = "phy0";
&enetc_port0 {
phy-handle = <&phy0>;
phy-connection-type = "sgmii";
+ managed = "in-band-status";
status = "okay";
mdio {
compatible = "fsl,ls1028a-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x1c>;
#fsl,rcpm-wakeup-cells = <7>;
+ little-endian;
};
ftm_alarm0: timer@2800000 {
compatible = "fsl,ls1088a-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x18>;
#fsl,rcpm-wakeup-cells = <6>;
+ little-endian;
};
ftm_alarm0: timer@2800000 {
compatible = "fsl,ls208xa-rcpm", "fsl,qoriq-rcpm-2.1+";
reg = <0x0 0x1e34040 0x0 0x18>;
#fsl,rcpm-wakeup-cells = <6>;
+ little-endian;
};
ftm_alarm0: timer@2800000 {
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
host-wakeup-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>;
device-wakeup-gpios = <&gpio2 7 GPIO_ACTIVE_HIGH>;
clocks = <&osc_32k>;
+ max-speed = <4000000>;
clock-names = "extclk";
};
};
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio2>;
- /*
- * The interrupt is not correct. It should be level low,
- * however with internal pull up this causes IRQ storm.
- */
- interrupts = <8 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
rohm,reset-snvs-powered;
#clock-cells = <0>;
pinctrl_pmic: pmicirqgrp {
fsl,pins = <
- MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x41
+ MX8MM_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141
>;
};
opp-1600000000 {
opp-hz = /bits/ 64 <1600000000>;
- opp-microvolt = <900000>;
+ opp-microvolt = <950000>;
opp-supported-hw = <0xc>, <0x7>;
clock-latency-ns = <150000>;
opp-suspend;
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
pmic: pmic@25 {
compatible = "nxp,pca9450b";
reg = <0x25>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio1>;
interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
interrupt-parent = <&gpio2>;
- /*
- * The interrupt is not correct. It should be level low,
- * however with internal pull up this causes IRQ storm.
- */
- interrupts = <8 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <8 IRQ_TYPE_LEVEL_LOW>;
rohm,reset-snvs-powered;
regulators {
pinctrl_pmic: pmicirqgrp {
fsl,pins = <
- MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x101
+ MX8MN_IOMUXC_SD1_DATA6_GPIO2_IO8 0x141
>;
};
#index-cells = <1>;
reg = <0x32e40200 0x200>;
};
-
- usbotg2: usb@32e50000 {
- compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb";
- reg = <0x32e50000 0x200>;
- interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>;
- clock-names = "usb1_ctrl_root_clk";
- assigned-clocks = <&clk IMX8MN_CLK_USB_BUS>,
- <&clk IMX8MN_CLK_USB_CORE_REF>;
- assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>,
- <&clk IMX8MN_SYS_PLL1_100M>;
- fsl,usbphy = <&usbphynop2>;
- fsl,usbmisc = <&usbmisc2 0>;
- status = "disabled";
- };
-
- usbmisc2: usbmisc@32e50200 {
- compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc";
- #index-cells = <1>;
- reg = <0x32e50200 0x200>;
- };
-
};
dma_apbh: dma-controller@33000000 {
assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
clock-names = "main_clk";
};
-
- usbphynop2: usbphynop2 {
- compatible = "usb-nop-xceiv";
- clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
- assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
- assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
- clock-names = "main_clk";
- };
};
clock-names = "fmanclk";
fsl,qman-channel-range = <0x800 0x10>;
ptimer-handle = <&ptp_timer0>;
+ dma-coherent;
muram@0 {
compatible = "fsl,fman-muram";
flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "mt25qu02g";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
compatible = "globalscale,espressobin-v7-emmc", "globalscale,espressobin-v7",
"globalscale,espressobin", "marvell,armada3720",
"marvell,armada3710";
+
+ aliases {
+ /* ethernet1 is wan port */
+ ethernet1 = &switch0port3;
+ ethernet3 = &switch0port1;
+ };
};
&switch0 {
ports {
- port@1 {
+ switch0port1: port@1 {
reg = <1>;
label = "lan1";
phy-handle = <&switch0phy0>;
};
- port@3 {
+ switch0port3: port@3 {
reg = <3>;
label = "wan";
phy-handle = <&switch0phy2>;
model = "Globalscale Marvell ESPRESSOBin Board V7";
compatible = "globalscale,espressobin-v7", "globalscale,espressobin",
"marvell,armada3720", "marvell,armada3710";
+
+ aliases {
+ /* ethernet1 is wan port */
+ ethernet1 = &switch0port3;
+ ethernet3 = &switch0port1;
+ };
};
&switch0 {
ports {
- port@1 {
+ switch0port1: port@1 {
reg = <1>;
label = "lan1";
phy-handle = <&switch0phy0>;
};
- port@3 {
+ switch0port3: port@3 {
reg = <3>;
label = "wan";
phy-handle = <&switch0phy2>;
/ {
aliases {
ethernet0 = ð0;
+ /* for dsa slave device */
+ ethernet1 = &switch0port1;
+ ethernet2 = &switch0port2;
+ ethernet3 = &switch0port3;
serial0 = &uart0;
serial1 = &uart1;
};
#address-cells = <1>;
#size-cells = <0>;
- port@0 {
+ switch0port0: port@0 {
reg = <0>;
label = "cpu";
ethernet = <ð0>;
};
};
- port@1 {
+ switch0port1: port@1 {
reg = <1>;
label = "wan";
phy-handle = <&switch0phy0>;
};
- port@2 {
+ switch0port2: port@2 {
reg = <2>;
label = "lan0";
phy-handle = <&switch0phy1>;
};
- port@3 {
+ switch0port3: port@3 {
reg = <3>;
label = "lan1";
phy-handle = <&switch0phy2>;
model = "NVIDIA Jetson TX2 Developer Kit";
compatible = "nvidia,p2771-0000", "nvidia,tegra186";
- aconnect {
- status = "okay";
-
- dma-controller@2930000 {
- status = "okay";
- };
-
- interrupt-controller@2a40000 {
- status = "okay";
- };
- };
-
i2c@3160000 {
power-monitor@42 {
compatible = "ti,ina3221";
status = "okay";
};
- serial@c280000 {
+ serial@3100000 {
status = "okay";
};
hsp_aon: hsp@c150000 {
compatible = "nvidia,tegra194-hsp", "nvidia,tegra186-hsp";
- reg = <0x0c150000 0xa0000>;
+ reg = <0x0c150000 0x90000>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
vin-supply = <&vdd_5v0_sys>;
};
- vdd_usb_vbus_otg: regulator@11 {
- compatible = "regulator-fixed";
- regulator-name = "USB_VBUS_EN0";
- regulator-min-microvolt = <5000000>;
- regulator-max-microvolt = <5000000>;
- gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>;
- enable-active-high;
- vin-supply = <&vdd_5v0_sys>;
- };
-
vdd_hdmi: regulator@10 {
compatible = "regulator-fixed";
regulator-name = "VDD_HDMI_5V0";
enable-active-high;
vin-supply = <&vdd_3v3_sys>;
};
+
+ vdd_usb_vbus_otg: regulator@14 {
+ compatible = "regulator-fixed";
+ regulator-name = "USB_VBUS_EN0";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ gpio = <&gpio TEGRA_GPIO(CC, 4) GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ vin-supply = <&vdd_5v0_sys>;
+ };
};
compatible = "nvidia,tegra234-vdk", "nvidia,tegra234";
aliases {
- sdhci3 = "/cbb@0/sdhci@3460000";
+ mmc3 = "/bus@0/mmc@3460000";
serial0 = &uarta;
};
stdout-path = "serial0:115200n8";
};
- cbb@0 {
+ bus@0 {
serial@3100000 {
status = "okay";
};
- sdhci@3460000 {
+ mmc@3460000 {
status = "okay";
bus-width = <8>;
non-removable;
};
soc: soc {
- #address-cells = <1>;
- #size-cells = <1>;
- ranges = <0 0 0 0xffffffff>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges = <0 0 0 0 0x0 0xffffffff>;
dma-ranges;
compatible = "simple-bus";
prng: qrng@e1000 {
compatible = "qcom,prng-ee";
- reg = <0xe3000 0x1000>;
+ reg = <0x0 0xe3000 0x0 0x1000>;
clocks = <&gcc GCC_PRNG_AHB_CLK>;
clock-names = "core";
};
cryptobam: dma@704000 {
compatible = "qcom,bam-v1.7.0";
- reg = <0x00704000 0x20000>;
+ reg = <0x0 0x00704000 0x0 0x20000>;
interrupts = <GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gcc GCC_CRYPTO_AHB_CLK>;
clock-names = "bam_clk";
crypto: crypto@73a000 {
compatible = "qcom,crypto-v5.1";
- reg = <0x0073a000 0x6000>;
+ reg = <0x0 0x0073a000 0x0 0x6000>;
clocks = <&gcc GCC_CRYPTO_AHB_CLK>,
<&gcc GCC_CRYPTO_AXI_CLK>,
<&gcc GCC_CRYPTO_CLK>;
tlmm: pinctrl@1000000 {
compatible = "qcom,ipq6018-pinctrl";
- reg = <0x01000000 0x300000>;
+ reg = <0x0 0x01000000 0x0 0x300000>;
interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
gpio-controller;
#gpio-cells = <2>;
gcc: gcc@1800000 {
compatible = "qcom,gcc-ipq6018";
- reg = <0x01800000 0x80000>;
+ reg = <0x0 0x01800000 0x0 0x80000>;
clocks = <&xo>, <&sleep_clk>;
clock-names = "xo", "sleep_clk";
#clock-cells = <1>;
tcsr_mutex_regs: syscon@1905000 {
compatible = "syscon";
- reg = <0x01905000 0x8000>;
+ reg = <0x0 0x01905000 0x0 0x8000>;
};
tcsr_q6: syscon@1945000 {
compatible = "syscon";
- reg = <0x01945000 0xe000>;
+ reg = <0x0 0x01945000 0x0 0xe000>;
};
blsp_dma: dma@7884000 {
compatible = "qcom,bam-v1.7.0";
- reg = <0x07884000 0x2b000>;
+ reg = <0x0 0x07884000 0x0 0x2b000>;
interrupts = <GIC_SPI 238 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gcc GCC_BLSP1_AHB_CLK>;
clock-names = "bam_clk";
blsp1_uart3: serial@78b1000 {
compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm";
- reg = <0x078b1000 0x200>;
+ reg = <0x0 0x078b1000 0x0 0x200>;
interrupts = <GIC_SPI 306 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gcc GCC_BLSP1_UART3_APPS_CLK>,
<&gcc GCC_BLSP1_AHB_CLK>;
compatible = "qcom,spi-qup-v2.2.1";
#address-cells = <1>;
#size-cells = <0>;
- reg = <0x078b5000 0x600>;
+ reg = <0x0 0x078b5000 0x0 0x600>;
interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
spi-max-frequency = <50000000>;
clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>,
compatible = "qcom,spi-qup-v2.2.1";
#address-cells = <1>;
#size-cells = <0>;
- reg = <0x078b6000 0x600>;
+ reg = <0x0 0x078b6000 0x0 0x600>;
interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
spi-max-frequency = <50000000>;
clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>,
compatible = "qcom,i2c-qup-v2.2.1";
#address-cells = <1>;
#size-cells = <0>;
- reg = <0x078b6000 0x600>;
+ reg = <0x0 0x078b6000 0x0 0x600>;
interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gcc GCC_BLSP1_AHB_CLK>,
<&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>;
compatible = "qcom,i2c-qup-v2.2.1";
#address-cells = <1>;
#size-cells = <0>;
- reg = <0x078b7000 0x600>;
+ reg = <0x0 0x078b7000 0x0 0x600>;
interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&gcc GCC_BLSP1_AHB_CLK>,
<&gcc GCC_BLSP1_QUP3_I2C_APPS_CLK>;
compatible = "qcom,msm-qgic2";
interrupt-controller;
#interrupt-cells = <0x3>;
- reg = <0x0b000000 0x1000>, /*GICD*/
- <0x0b002000 0x1000>, /*GICC*/
- <0x0b001000 0x1000>, /*GICH*/
- <0x0b004000 0x1000>; /*GICV*/
+ reg = <0x0 0x0b000000 0x0 0x1000>, /*GICD*/
+ <0x0 0x0b002000 0x0 0x1000>, /*GICC*/
+ <0x0 0x0b001000 0x0 0x1000>, /*GICH*/
+ <0x0 0x0b004000 0x0 0x1000>; /*GICV*/
interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_HIGH>;
};
watchdog@b017000 {
compatible = "qcom,kpss-wdt";
interrupts = <GIC_SPI 3 IRQ_TYPE_EDGE_RISING>;
- reg = <0x0b017000 0x40>;
+ reg = <0x0 0x0b017000 0x0 0x40>;
clocks = <&sleep_clk>;
timeout-sec = <10>;
};
apcs_glb: mailbox@b111000 {
compatible = "qcom,ipq6018-apcs-apps-global";
- reg = <0x0b111000 0x1000>;
+ reg = <0x0 0x0b111000 0x0 0x1000>;
#clock-cells = <1>;
clocks = <&a53pll>, <&xo>;
clock-names = "pll", "xo";
a53pll: clock@b116000 {
compatible = "qcom,ipq6018-a53pll";
- reg = <0x0b116000 0x40>;
+ reg = <0x0 0x0b116000 0x0 0x40>;
#clock-cells = <0>;
clocks = <&xo>;
clock-names = "xo";
};
timer@b120000 {
- #address-cells = <1>;
- #size-cells = <1>;
+ #address-cells = <2>;
+ #size-cells = <2>;
ranges;
compatible = "arm,armv7-timer-mem";
- reg = <0x0b120000 0x1000>;
+ reg = <0x0 0x0b120000 0x0 0x1000>;
clock-frequency = <19200000>;
frame@b120000 {
frame-number = <0>;
interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0x0b121000 0x1000>,
- <0x0b122000 0x1000>;
+ reg = <0x0 0x0b121000 0x0 0x1000>,
+ <0x0 0x0b122000 0x0 0x1000>;
};
frame@b123000 {
frame-number = <1>;
interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0xb123000 0x1000>;
+ reg = <0x0 0xb123000 0x0 0x1000>;
status = "disabled";
};
frame@b124000 {
frame-number = <2>;
interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0x0b124000 0x1000>;
+ reg = <0x0 0x0b124000 0x0 0x1000>;
status = "disabled";
};
frame@b125000 {
frame-number = <3>;
interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0x0b125000 0x1000>;
+ reg = <0x0 0x0b125000 0x0 0x1000>;
status = "disabled";
};
frame@b126000 {
frame-number = <4>;
interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0x0b126000 0x1000>;
+ reg = <0x0 0x0b126000 0x0 0x1000>;
status = "disabled";
};
frame@b127000 {
frame-number = <5>;
interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0x0b127000 0x1000>;
+ reg = <0x0 0x0b127000 0x0 0x1000>;
status = "disabled";
};
frame@b128000 {
frame-number = <6>;
interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>;
- reg = <0x0b128000 0x1000>;
+ reg = <0x0 0x0b128000 0x0 0x1000>;
status = "disabled";
};
};
q6v5_wcss: remoteproc@cd00000 {
compatible = "qcom,ipq8074-wcss-pil";
- reg = <0x0cd00000 0x4040>,
- <0x004ab000 0x20>;
+ reg = <0x0 0x0cd00000 0x0 0x4040>,
+ <0x0 0x004ab000 0x0 0x20>;
reg-names = "qdsp6",
"rmb";
interrupts-extended = <&intc GIC_SPI 325 IRQ_TYPE_EDGE_RISING>,
clock-frequency = <0>;
};
+ audio_clk_b: audio_clk_b {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <0>;
+ };
+
audio_clk_c: audio_clk_c {
compatible = "fixed-clock";
#clock-cells = <0>;
interrupts = <RK_PB2 IRQ_TYPE_LEVEL_LOW>;
pinctrl-names = "default";
pinctrl-0 = <&pmic_int>;
- rockchip,system-power-controller;
wakeup-source;
#clock-cells = <1>;
clock-output-names = "rk808-clkout1", "xin32k";
gmac_clk: gmac-clock {
compatible = "fixed-clock";
clock-frequency = <125000000>;
- clock-output-names = "gmac_clk";
+ clock-output-names = "gmac_clkin";
#clock-cells = <0>;
};
label = "red:diy";
gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
default-state = "off";
- linux,default-trigger = "mmc1";
+ linux,default-trigger = "mmc2";
};
yellow_led: led-2 {
label = "yellow:yellow-led";
gpios = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>;
default-state = "off";
- linux,default-trigger = "mmc0";
+ linux,default-trigger = "mmc1";
};
};
i2c6 = &i2c6;
i2c7 = &i2c7;
i2c8 = &i2c8;
+ mmc0 = &sdio0;
+ mmc1 = &sdmmc;
+ mmc2 = &sdhci;
serial0 = &uart0;
serial1 = &uart1;
serial2 = &uart2;
CONFIG_GPIO_DWAPB=y
CONFIG_GPIO_MB86S7X=y
CONFIG_GPIO_MPC8XXX=y
+CONFIG_GPIO_MXC=y
CONFIG_GPIO_PL061=y
CONFIG_GPIO_RCAR=y
CONFIG_GPIO_UNIPHIER=y
* #imm16 values used for BRK instruction generation
* 0x004: for installing kprobes
* 0x005: for installing uprobes
+ * 0x006: for kprobe software single-step
* Allowed values for kgdb are 0x400 - 0x7ff
* 0x100: for triggering a fault on purpose (reserved)
* 0x400: for dynamic BRK instruction
*/
#define KPROBES_BRK_IMM 0x004
#define UPROBES_BRK_IMM 0x005
+#define KPROBES_BRK_SS_IMM 0x006
#define FAULT_BRK_IMM 0x100
#define KGDB_DYN_DBG_BRK_IMM 0x400
#define KGDB_COMPILED_DBG_BRK_IMM 0x401
#define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
#define ICACHE_POLICY_VPIPT 0
+#define ICACHE_POLICY_RESERVED 1
#define ICACHE_POLICY_VIPT 2
#define ICACHE_POLICY_PIPT 3
#define ARM64_HAS_ARMv8_4_TTL 55
#define ARM64_HAS_TLB_RANGE 56
#define ARM64_MTE 57
+#define ARM64_WORKAROUND_1508412 58
-#define ARM64_NCAPS 58
+#define ARM64_NCAPS 59
#endif /* __ASM_CPUCAPS_H */
/*
* CPU feature detected at boot time based on feature of one or more CPUs.
* All possible conflicts for a late CPU are ignored.
+ * NOTE: this means that a late CPU with the feature will *not* cause the
+ * capability to be advertised by cpus_have_*cap()!
*/
#define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \
(ARM64_CPUCAP_SCOPE_LOCAL_CPU | \
return false;
}
+static __always_inline bool is_vhe_hyp_code(void)
+{
+ /* Only defined for code run in VHE hyp context */
+ return __is_defined(__KVM_VHE_HYPERVISOR__);
+}
+
+static __always_inline bool is_nvhe_hyp_code(void)
+{
+ /* Only defined for code run in NVHE hyp context */
+ return __is_defined(__KVM_NVHE_HYPERVISOR__);
+}
+
+static __always_inline bool is_hyp_code(void)
+{
+ return is_vhe_hyp_code() || is_nvhe_hyp_code();
+}
+
extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
extern struct static_key_false arm64_const_caps_ready;
}
/*
- * Test for a capability, possibly with a runtime check.
+ * Test for a capability without a runtime check.
*
- * Before capabilities are finalized, this behaves as cpus_have_cap().
+ * Before capabilities are finalized, this will BUG().
* After capabilities are finalized, this is patched to avoid a runtime check.
*
* @num must be a compile-time constant.
*/
-static __always_inline bool cpus_have_const_cap(int num)
+static __always_inline bool cpus_have_final_cap(int num)
{
if (system_capabilities_finalized())
return __cpus_have_const_cap(num);
else
- return cpus_have_cap(num);
+ BUG();
}
/*
- * Test for a capability without a runtime check.
+ * Test for a capability, possibly with a runtime check for non-hyp code.
*
- * Before capabilities are finalized, this will BUG().
+ * For hyp code, this behaves the same as cpus_have_final_cap().
+ *
+ * For non-hyp code:
+ * Before capabilities are finalized, this behaves as cpus_have_cap().
* After capabilities are finalized, this is patched to avoid a runtime check.
*
* @num must be a compile-time constant.
*/
-static __always_inline bool cpus_have_final_cap(int num)
+static __always_inline bool cpus_have_const_cap(int num)
{
- if (system_capabilities_finalized())
+ if (is_hyp_code())
+ return cpus_have_final_cap(num);
+ else if (system_capabilities_finalized())
return __cpus_have_const_cap(num);
else
- BUG();
+ return cpus_have_cap(num);
}
static inline void cpus_set_cap(unsigned int num)
#define ARM_CPU_PART_CORTEX_A55 0xD05
#define ARM_CPU_PART_CORTEX_A76 0xD0B
#define ARM_CPU_PART_NEOVERSE_N1 0xD0C
+#define ARM_CPU_PART_CORTEX_A77 0xD0D
#define APM_CPU_PART_POTENZA 0x000
#define QCOM_CPU_PART_FALKOR_V1 0x800
#define QCOM_CPU_PART_FALKOR 0xC00
#define QCOM_CPU_PART_KRYO 0x200
+#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800
+#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801
#define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803
#define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804
#define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805
#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
+#define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
+#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
#define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
#define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
{
unsigned long flags = regs->pstate & DAIF_MASK;
+ if (interrupts_enabled(regs))
+ trace_hardirqs_on();
+
/*
* We can't use local_daif_restore(regs->pstate) here as
* system_has_prio_mask_debugging() won't restore the I bit if it can
/* kprobes BRK opcodes with ESR encoding */
#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
+#define BRK64_OPCODE_KPROBES_SS (AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5))
/* uprobes BRK opcodes with ESR encoding */
#define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
return esr;
}
+asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs);
+asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs);
asmlinkage void enter_from_user_mode(void);
+asmlinkage void exit_to_user_mode(void);
+void arm64_enter_nmi(struct pt_regs *regs);
+void arm64_exit_nmi(struct pt_regs *regs);
void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
void do_undefinstr(struct pt_regs *regs);
void do_bti(struct pt_regs *regs);
#include <linux/percpu.h>
#define __ARCH_WANT_KPROBES_INSN_SLOT
-#define MAX_INSN_SIZE 1
+#define MAX_INSN_SIZE 2
#define flush_insn_slot(p) do { } while (0)
#define kretprobe_blacklist_size 0
*/
unsigned long *pmu_filter;
unsigned int pmuver;
+
+ u8 pfr0_csv2;
};
struct kvm_vcpu_fault_info {
#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2)
#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2)
#define cp14_DBGDCCINT (MDCCINT_EL1 * 2)
+#define cp14_DBGVCR (DBGVCR32_EL2 * 2)
#define NR_COPRO_REGS (NR_SYS_REGS * 2)
#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID))
#define pte_valid_not_user(pte) \
((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
-#define pte_valid_young(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
#define pte_valid_user(pte) \
((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
* Could the pte be present in the TLB? We must check mm_tlb_flush_pending
* so that we don't erroneously return false for pages that have been
* remapped as PROT_NONE but are yet to be flushed from the TLB.
+ * Note that we can't make any assumptions based on the state of the access
+ * flag, since ptep_clear_flush_young() elides a DSB when invalidating the
+ * TLB.
*/
#define pte_accessible(mm, pte) \
- (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
+ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
/*
* p??_access_permitted() is true for valid user mappings (subject to the
return pmd;
}
-static inline pte_t pte_wrprotect(pte_t pte)
-{
- pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
- pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
- return pte;
-}
-
static inline pte_t pte_mkwrite(pte_t pte)
{
pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
return pte;
}
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+ /*
+ * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
+ * clear), set the PTE_DIRTY bit.
+ */
+ if (pte_hw_dirty(pte))
+ pte = pte_mkdirty(pte);
+
+ pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+ return pte;
+}
+
static inline pte_t pte_mkold(pte_t pte)
{
return clear_pte_bit(pte, __pgprot(PTE_AF));
pte = READ_ONCE(*ptep);
do {
old_pte = pte;
- /*
- * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY
- * clear), set the PTE_DIRTY bit.
- */
- if (pte_hw_dirty(pte))
- pte = pte_mkdirty(pte);
pte = pte_wrprotect(pte);
pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
pte_val(old_pte), pte_val(pte));
#ifndef _ARM_PROBES_H
#define _ARM_PROBES_H
+#include <asm/insn.h>
+
typedef u32 probe_opcode_t;
typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
/* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */
u64 pmr_save;
u64 stackframe[2];
+
+ /* Only valid for some EL1 exceptions. */
+ u64 lockdep_hardirqs;
+ u64 exit_rcu;
};
static inline bool in_syscall(struct pt_regs const *regs)
#define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1)
#define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4)
+#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7)
+
#define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0)
#define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0)
#define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2)
#define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3)
+#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7)
+
/* Definitions for system register interface to AMU for ARMv8.4 onwards */
#define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2))
#define SYS_AMCR_EL0 SYS_AM_EL0(2, 0)
#define SYS_TFSR_EL1_TF0_SHIFT 0
#define SYS_TFSR_EL1_TF1_SHIFT 1
#define SYS_TFSR_EL1_TF0 (UL(1) << SYS_TFSR_EL1_TF0_SHIFT)
-#define SYS_TFSR_EL1_TF1 (UK(2) << SYS_TFSR_EL1_TF1_SHIFT)
+#define SYS_TFSR_EL1_TF1 (UL(1) << SYS_TFSR_EL1_TF1_SHIFT)
/* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
#define SYS_MPIDR_SAFE_VAL (BIT(31))
#include <linux/build_bug.h>
#include <linux/types.h>
+#include <asm/alternative.h>
#define __DEFINE_MRS_MSR_S_REGNUM \
" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
write_sysreg_s(__scs_new, sysreg); \
} while (0)
+#define read_sysreg_par() ({ \
+ u64 par; \
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
+ par = read_sysreg(par_el1); \
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
+ par; \
+})
+
#endif
#endif /* __ASM_SYSREG_H */
static __always_inline bool has_vhe(void)
{
/*
- * The following macros are defined for code specic to VHE/nVHE.
- * If has_vhe() is inlined into those compilation units, it can
- * be determined statically. Otherwise fall back to caps.
+ * Code only run in VHE/NVHE hyp context can assume VHE is present or
+ * absent. Otherwise fall back to caps.
*/
- if (__is_defined(__KVM_VHE_HYPERVISOR__))
+ if (is_vhe_hyp_code())
return true;
- else if (__is_defined(__KVM_NVHE_HYPERVISOR__))
+ else if (is_nvhe_hyp_code())
return false;
else
return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN);
MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
/* Brahma-B53 r0p[0] */
MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+ /* Kryo2XX Silver rAp4 */
+ MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4),
{},
};
#endif
.matches = has_neoverse_n1_erratum_1542419,
.cpu_enable = cpu_enable_trap_ctr_access,
},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1508412
+ {
+ /* we depend on the firmware portion for correctness */
+ .desc = "ARM erratum 1508412 (kernel portion)",
+ .capability = ARM64_WORKAROUND_1508412,
+ ERRATA_MIDR_RANGE(MIDR_CORTEX_A77,
+ 0, 0,
+ 1, 0),
+ },
#endif
{
}
MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+ MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD),
+ MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{ /* sentinel */ }
static struct cpuinfo_arm64 boot_cpu_data;
static const char *icache_policy_str[] = {
- [0 ... ICACHE_POLICY_PIPT] = "RESERVED/UNKNOWN",
+ [ICACHE_POLICY_VPIPT] = "VPIPT",
+ [ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN",
[ICACHE_POLICY_VIPT] = "VIPT",
[ICACHE_POLICY_PIPT] = "PIPT",
- [ICACHE_POLICY_VPIPT] = "VPIPT",
};
unsigned long __icache_flags;
case ICACHE_POLICY_VPIPT:
set_bit(ICACHEF_VPIPT, &__icache_flags);
break;
- default:
+ case ICACHE_POLICY_RESERVED:
case ICACHE_POLICY_VIPT:
/* Assume aliasing */
set_bit(ICACHEF_ALIASING, &__icache_flags);
+ break;
}
pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
* correctly at this alignment, we must ensure that .text is
* placed at a 4k boundary in the Image to begin with.
*/
- .align 12
+ .balign SEGMENT_ALIGN
efi_header_end:
.endm
#include <asm/mmu.h>
#include <asm/sysreg.h>
-static void notrace el1_abort(struct pt_regs *regs, unsigned long esr)
+/*
+ * This is intended to match the logic in irqentry_enter(), handling the kernel
+ * mode transitions only.
+ */
+static void noinstr enter_from_kernel_mode(struct pt_regs *regs)
+{
+ regs->exit_rcu = false;
+
+ if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ rcu_irq_enter();
+ trace_hardirqs_off_finish();
+
+ regs->exit_rcu = true;
+ return;
+ }
+
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ rcu_irq_enter_check_tick();
+ trace_hardirqs_off_finish();
+}
+
+/*
+ * This is intended to match the logic in irqentry_exit(), handling the kernel
+ * mode transitions only, and with preemption handled elsewhere.
+ */
+static void noinstr exit_to_kernel_mode(struct pt_regs *regs)
+{
+ lockdep_assert_irqs_disabled();
+
+ if (interrupts_enabled(regs)) {
+ if (regs->exit_rcu) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ rcu_irq_exit();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+ return;
+ }
+
+ trace_hardirqs_on();
+ } else {
+ if (regs->exit_rcu)
+ rcu_irq_exit();
+ }
+}
+
+void noinstr arm64_enter_nmi(struct pt_regs *regs)
+{
+ regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
+
+ __nmi_enter();
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ lockdep_hardirq_enter();
+ rcu_nmi_enter();
+
+ trace_hardirqs_off_finish();
+ ftrace_nmi_enter();
+}
+
+void noinstr arm64_exit_nmi(struct pt_regs *regs)
+{
+ bool restore = regs->lockdep_hardirqs;
+
+ ftrace_nmi_exit();
+ if (restore) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ }
+
+ rcu_nmi_exit();
+ lockdep_hardirq_exit();
+ if (restore)
+ lockdep_hardirqs_on(CALLER_ADDR0);
+ __nmi_exit();
+}
+
+asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
+ arm64_enter_nmi(regs);
+ else
+ enter_from_kernel_mode(regs);
+}
+
+asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
+ arm64_exit_nmi(regs);
+ else
+ exit_to_kernel_mode(regs);
+}
+
+static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
far = untagged_addr(far);
do_mem_abort(far, esr, regs);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_abort);
-static void notrace el1_pc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_sp_pc_abort(far, esr, regs);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_pc);
-static void notrace el1_undef(struct pt_regs *regs)
+static void noinstr el1_undef(struct pt_regs *regs)
{
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_undefinstr(regs);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_undef);
-static void notrace el1_inv(struct pt_regs *regs, unsigned long esr)
+static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr)
{
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
bad_mode(regs, 0, esr);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_inv);
-static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
+static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
+{
+ regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
+
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ rcu_nmi_enter();
+
+ trace_hardirqs_off_finish();
+}
+
+static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
+{
+ bool restore = regs->lockdep_hardirqs;
+
+ if (restore) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ }
+
+ rcu_nmi_exit();
+ if (restore)
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ arm64_enter_el1_dbg(regs);
do_debug_exception(far, esr, regs);
+ arm64_exit_el1_dbg(regs);
}
-NOKPROBE_SYMBOL(el1_dbg);
-static void notrace el1_fpac(struct pt_regs *regs, unsigned long esr)
+static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr)
{
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_ptrauth_fault(regs, esr);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_fpac);
-asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
el1_inv(regs, esr);
}
}
-NOKPROBE_SYMBOL(el1_sync_handler);
-static void notrace el0_da(struct pt_regs *regs, unsigned long esr)
+asmlinkage void noinstr enter_from_user_mode(void)
+{
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ CT_WARN_ON(ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+ trace_hardirqs_off_finish();
+}
+
+asmlinkage void noinstr exit_to_user_mode(void)
+{
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ user_enter_irqoff();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+static void noinstr el0_da(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
far = untagged_addr(far);
do_mem_abort(far, esr, regs);
}
-NOKPROBE_SYMBOL(el0_da);
-static void notrace el0_ia(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
if (!is_ttbr0_addr(far))
arm64_apply_bp_hardening();
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_mem_abort(far, esr, regs);
}
-NOKPROBE_SYMBOL(el0_ia);
-static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_fpsimd_acc(esr, regs);
}
-NOKPROBE_SYMBOL(el0_fpsimd_acc);
-static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sve_acc(esr, regs);
}
-NOKPROBE_SYMBOL(el0_sve_acc);
-static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_fpsimd_exc(esr, regs);
}
-NOKPROBE_SYMBOL(el0_fpsimd_exc);
-static void notrace el0_sys(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sysinstr(esr, regs);
}
-NOKPROBE_SYMBOL(el0_sys);
-static void notrace el0_pc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
if (!is_ttbr0_addr(instruction_pointer(regs)))
arm64_apply_bp_hardening();
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sp_pc_abort(far, esr, regs);
}
-NOKPROBE_SYMBOL(el0_pc);
-static void notrace el0_sp(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sp_pc_abort(regs->sp, esr, regs);
}
-NOKPROBE_SYMBOL(el0_sp);
-static void notrace el0_undef(struct pt_regs *regs)
+static void noinstr el0_undef(struct pt_regs *regs)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_undefinstr(regs);
}
-NOKPROBE_SYMBOL(el0_undef);
-static void notrace el0_bti(struct pt_regs *regs)
+static void noinstr el0_bti(struct pt_regs *regs)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_bti(regs);
}
-NOKPROBE_SYMBOL(el0_bti);
-static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
bad_el0_sync(regs, 0, esr);
}
-NOKPROBE_SYMBOL(el0_inv);
-static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr)
{
/* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */
unsigned long far = read_sysreg(far_el1);
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
- user_exit_irqoff();
+ enter_from_user_mode();
do_debug_exception(far, esr, regs);
local_daif_restore(DAIF_PROCCTX_NOIRQ);
}
-NOKPROBE_SYMBOL(el0_dbg);
-static void notrace el0_svc(struct pt_regs *regs)
+static void noinstr el0_svc(struct pt_regs *regs)
{
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ enter_from_user_mode();
do_el0_svc(regs);
}
-NOKPROBE_SYMBOL(el0_svc);
-static void notrace el0_fpac(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_ptrauth_fault(regs, esr);
}
-NOKPROBE_SYMBOL(el0_fpac);
-asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
el0_inv(regs, esr);
}
}
-NOKPROBE_SYMBOL(el0_sync_handler);
#ifdef CONFIG_COMPAT
-static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_cp15instr(esr, regs);
}
-NOKPROBE_SYMBOL(el0_cp15);
-static void notrace el0_svc_compat(struct pt_regs *regs)
+static void noinstr el0_svc_compat(struct pt_regs *regs)
{
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ enter_from_user_mode();
do_el0_svc_compat(regs);
}
-NOKPROBE_SYMBOL(el0_svc_compat);
-asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
el0_inv(regs, esr);
}
}
-NOKPROBE_SYMBOL(el0_sync_compat_handler);
#endif /* CONFIG_COMPAT */
#include <asm/unistd.h>
/*
- * Context tracking subsystem. Used to instrument transitions
- * between user and kernel mode.
+ * Context tracking and irqflag tracing need to instrument transitions between
+ * user and kernel mode.
*/
- .macro ct_user_exit_irqoff
-#ifdef CONFIG_CONTEXT_TRACKING
+ .macro user_exit_irqoff
+#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
bl enter_from_user_mode
#endif
.endm
- .macro ct_user_enter
-#ifdef CONFIG_CONTEXT_TRACKING
- bl context_tracking_user_enter
+ .macro user_enter_irqoff
+#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
+ bl exit_to_user_mode
#endif
.endm
alternative_else_nop_endif
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
- .if \el == 0
- ct_user_enter
- .endif
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
alternative_if_not ARM64_HAS_PAN
br x30
#endif
.else
+ /* Ensure any device/NC reads complete */
+ alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
+
eret
.endif
sb
gic_prio_irq_setup pmr=x20, tmp=x1
enable_da_f
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- test_irqs_unmasked res=x0, pmr=x20
- cbz x0, 1f
- bl asm_nmi_enter
-1:
-#endif
-
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_off
-#endif
+ mov x0, sp
+ bl enter_el1_irq_or_nmi
irq_handler
1:
#endif
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- /*
- * When using IRQ priority masking, we can get spurious interrupts while
- * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a
- * section with interrupts disabled. Skip tracing in those cases.
- */
- test_irqs_unmasked res=x0, pmr=x20
- cbz x0, 1f
- bl asm_nmi_exit
-1:
-#endif
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- test_irqs_unmasked res=x0, pmr=x20
- cbnz x0, 1f
-#endif
- bl trace_hardirqs_on
-1:
-#endif
+ mov x0, sp
+ bl exit_el1_irq_or_nmi
kernel_exit 1
SYM_CODE_END(el1_irq)
kernel_entry 0
el0_irq_naked:
gic_prio_irq_setup pmr=x20, tmp=x0
- ct_user_exit_irqoff
+ user_exit_irqoff
enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_off
-#endif
-
tbz x22, #55, 1f
bl do_el0_irq_bp_hardening
1:
irq_handler
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_on
-#endif
b ret_to_user
SYM_CODE_END(el0_irq)
el0_error_naked:
mrs x25, esr_el1
gic_prio_kentry_setup tmp=x2
- ct_user_exit_irqoff
+ user_exit_irqoff
enable_dbg
mov x0, sp
mov x1, x25
SYM_CODE_START_LOCAL(ret_to_user)
disable_daif
gic_prio_kentry_setup tmp=x3
- ldr x1, [tsk, #TSK_TI_FLAGS]
- and x2, x1, #_TIF_WORK_MASK
+#ifdef CONFIG_TRACE_IRQFLAGS
+ bl trace_hardirqs_off
+#endif
+ ldr x19, [tsk, #TSK_TI_FLAGS]
+ and x2, x19, #_TIF_WORK_MASK
cbnz x2, work_pending
finish_ret_to_user:
+ user_enter_irqoff
/* Ignore asynchronous tag check faults in the uaccess routines */
clear_mte_async_tcf
- enable_step_tsk x1, x2
+ enable_step_tsk x19, x2
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
bl stackleak_erase
#endif
*/
work_pending:
mov x0, sp // 'regs'
+ mov x1, x19
bl do_notify_resume
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_on // enabled while in userspace
-#endif
- ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step
+ ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step
b finish_ret_to_user
SYM_CODE_END(ret_to_user)
/* Kernel symbols needed for cpus_have_final/const_caps checks. */
KVM_NVHE_ALIAS(arm64_const_caps_ready);
KVM_NVHE_ALIAS(cpu_hwcap_keys);
-KVM_NVHE_ALIAS(cpu_hwcaps);
/* Static keys which are set if a vGIC trap should be handled in hyp. */
KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
local_daif_restore(DAIF_PROCCTX_NOIRQ);
}
}
-
-/*
- * Stubs to make nmi_enter/exit() code callable from ASM
- */
-asmlinkage void notrace asm_nmi_enter(void)
-{
- nmi_enter();
-}
-NOKPROBE_SYMBOL(asm_nmi_enter);
-
-asmlinkage void notrace asm_nmi_exit(void)
-{
- nmi_exit();
-}
-NOKPROBE_SYMBOL(asm_nmi_exit);
u64 flags, value;
bool be_image, be_kernel;
struct kexec_buf kbuf;
- unsigned long text_offset;
+ unsigned long text_offset, kernel_segment_number;
struct kexec_segment *kernel_segment;
int ret;
/* Adjust kernel segment with TEXT_OFFSET */
kbuf.memsz += text_offset;
- ret = kexec_add_buffer(&kbuf);
- if (ret)
+ kernel_segment_number = image->nr_segments;
+
+ /*
+ * The location of the kernel segment may make it impossible to satisfy
+ * the other segment requirements, so we try repeatedly to find a
+ * location that will work.
+ */
+ while ((ret = kexec_add_buffer(&kbuf)) == 0) {
+ /* Try to load additional data */
+ kernel_segment = &image->segment[kernel_segment_number];
+ ret = load_other_segments(image, kernel_segment->mem,
+ kernel_segment->memsz, initrd,
+ initrd_len, cmdline);
+ if (!ret)
+ break;
+
+ /*
+ * We couldn't find space for the other segments; erase the
+ * kernel segment and try the next available hole.
+ */
+ image->nr_segments -= 1;
+ kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz;
+ kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
+ }
+
+ if (ret) {
+ pr_err("Could not find any suitable kernel location!");
return ERR_PTR(ret);
+ }
- kernel_segment = &image->segment[image->nr_segments - 1];
+ kernel_segment = &image->segment[kernel_segment_number];
kernel_segment->mem += text_offset;
kernel_segment->memsz -= text_offset;
image->start = kernel_segment->mem;
kernel_segment->mem, kbuf.bufsz,
kernel_segment->memsz);
- /* Load additional data */
- ret = load_other_segments(image,
- kernel_segment->mem, kernel_segment->memsz,
- initrd, initrd_len, cmdline);
-
- return ERR_PTR(ret);
+ return NULL;
}
#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
return ret;
}
+/*
+ * Tries to add the initrd and DTB to the image. If it is not possible to find
+ * valid locations, this function will undo changes to the image and return non
+ * zero.
+ */
int load_other_segments(struct kimage *image,
unsigned long kernel_load_addr,
unsigned long kernel_size,
{
struct kexec_buf kbuf;
void *headers, *dtb = NULL;
- unsigned long headers_sz, initrd_load_addr = 0, dtb_len;
+ unsigned long headers_sz, initrd_load_addr = 0, dtb_len,
+ orig_segments = image->nr_segments;
int ret = 0;
kbuf.image = image;
return 0;
out_err:
+ image->nr_segments = orig_segments;
vfree(dtb);
return ret;
}
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
static void __kprobes
post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
-static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode)
-{
- void *addrs[1];
- u32 insns[1];
-
- addrs[0] = addr;
- insns[0] = opcode;
-
- return aarch64_insn_patch_text(addrs, insns, 1);
-}
-
static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
{
+ kprobe_opcode_t *addr = p->ainsn.api.insn;
+ void *addrs[] = {addr, addr + 1};
+ u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS};
+
/* prepare insn slot */
- patch_text(p->ainsn.api.insn, p->opcode);
+ aarch64_insn_patch_text(addrs, insns, 2);
- flush_icache_range((uintptr_t) (p->ainsn.api.insn),
- (uintptr_t) (p->ainsn.api.insn) +
- MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+ flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE));
/*
* Needs restoring of return address after stepping xol.
/* arm kprobe: install breakpoint in text */
void __kprobes arch_arm_kprobe(struct kprobe *p)
{
- patch_text(p->addr, BRK64_OPCODE_KPROBES);
+ void *addr = p->addr;
+ u32 insn = BRK64_OPCODE_KPROBES;
+
+ aarch64_insn_patch_text(&addr, &insn, 1);
}
/* disarm kprobe: remove breakpoint from text */
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
- patch_text(p->addr, p->opcode);
+ void *addr = p->addr;
+
+ aarch64_insn_patch_text(&addr, &p->opcode, 1);
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
}
/*
- * Interrupts need to be disabled before single-step mode is set, and not
- * reenabled until after single-step mode ends.
- * Without disabling interrupt on local CPU, there is a chance of
- * interrupt occurrence in the period of exception return and start of
- * out-of-line single-step, that result in wrongly single stepping
- * into the interrupt handler.
+ * Mask all of DAIF while executing the instruction out-of-line, to keep things
+ * simple and avoid nesting exceptions. Interrupts do have to be disabled since
+ * the kprobe state is per-CPU and doesn't get migrated.
*/
static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
kcb->saved_irqflag = regs->pstate & DAIF_MASK;
- regs->pstate |= PSR_I_BIT;
- /* Unmask PSTATE.D for enabling software step exceptions. */
- regs->pstate &= ~PSR_D_BIT;
+ regs->pstate |= DAIF_MASK;
}
static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
slot = (unsigned long)p->ainsn.api.insn;
set_ss_context(kcb, slot); /* mark pending ss */
-
- /* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
- kernel_enable_single_step(regs);
instruction_pointer_set(regs, slot);
} else {
/* insn simulation */
}
/* call post handler */
kcb->kprobe_status = KPROBE_HIT_SSDONE;
- if (cur->post_handler) {
- /* post_handler can hit breakpoint and single step
- * again, so we enable D-flag for recursive exception.
- */
+ if (cur->post_handler)
cur->post_handler(cur, regs, 0);
- }
reset_current_kprobe();
}
if (!instruction_pointer(regs))
BUG();
- kernel_disable_single_step();
-
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
else
* pre-handler and it returned non-zero, it will
* modify the execution path and no need to single
* stepping. Let's just reset current kprobe and exit.
- *
- * pre_handler can hit a breakpoint and can step thru
- * before return, keep PSTATE D-flag enabled until
- * pre_handler return back.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
setup_singlestep(p, regs, kcb, 0);
}
static int __kprobes
-kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
+kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
int retval;
if (retval == DBG_HOOK_HANDLED) {
kprobes_restore_local_irqflag(kcb, regs);
- kernel_disable_single_step();
-
post_kprobe_handler(kcb, regs);
}
return retval;
}
-static struct step_hook kprobes_step_hook = {
- .fn = kprobe_single_step_handler,
+static struct break_hook kprobes_break_ss_hook = {
+ .imm = KPROBES_BRK_SS_IMM,
+ .fn = kprobe_breakpoint_ss_handler,
};
static int __kprobes
int __init arch_init_kprobes(void)
{
register_kernel_break_hook(&kprobes_break_hook);
- register_kernel_step_hook(&kprobes_step_hook);
+ register_kernel_break_hook(&kprobes_break_ss_hook);
return 0;
}
void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
-static void __cpu_do_idle(void)
+static void noinstr __cpu_do_idle(void)
{
dsb(sy);
wfi();
}
-static void __cpu_do_idle_irqprio(void)
+static void noinstr __cpu_do_idle_irqprio(void)
{
unsigned long pmr;
unsigned long daif_bits;
* ensure that interrupts are not masked at the PMR (because the core will
* not wake up if we block the wake up signal in the interrupt controller).
*/
-void cpu_do_idle(void)
+void noinstr cpu_do_idle(void)
{
if (system_uses_irq_prio_masking())
__cpu_do_idle_irqprio();
/*
* This is our default idle handler.
*/
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
{
/*
* This should do all the clock switching and wait for interrupt
* tricks
*/
cpu_do_idle();
- local_irq_enable();
+ raw_local_irq_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
bool prev32, next32;
u64 val;
- if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) &&
- cpus_have_const_cap(ARM64_WORKAROUND_1418040)))
+ if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040))
return;
prev32 = is_compat_thread(task_thread_info(prev));
next32 = is_compat_thread(task_thread_info(next));
- if (prev32 == next32)
+ if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
return;
val = read_sysreg(cntkctl_el1);
MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
+ MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
{ /* sentinel */ }
return SPECTRE_VULNERABLE;
}
-#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED (1)
-
static enum mitigation_state spectre_v2_get_cpu_fw_mitigation_state(void)
{
int ret;
static void cpu_psci_cpu_die(unsigned int cpu)
{
- int ret;
/*
* There are no known implementations of PSCI actually using the
* power state field, pass a sensible default for now.
u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
PSCI_0_2_POWER_STATE_TYPE_SHIFT;
- ret = psci_ops.cpu_off(state);
-
- pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
+ psci_ops.cpu_off(state);
}
static int cpu_psci_cpu_kill(unsigned int cpu)
#include <linux/uaccess.h>
#include <asm/alternative.h>
+#include <asm/exception.h>
#include <asm/kprobes.h>
#include <asm/mmu.h>
#include <asm/ptrace.h>
}
-asmlinkage __kprobes notrace unsigned long
+asmlinkage noinstr unsigned long
__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
{
unsigned long ret;
- nmi_enter();
+ arm64_enter_nmi(regs);
ret = _sdei_handler(regs, arg);
- nmi_exit();
+ arm64_exit_nmi(regs);
return ret;
}
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
+ rcu_cpu_starting(cpu);
preempt_disable();
trace_hardirqs_off();
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
+ rcu_report_dead(cpu);
if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
update_cpu_boot_status(CPU_KILL_ME);
cortex_a76_erratum_1463225_svc_handler();
local_daif_restore(DAIF_PROCCTX);
- user_exit();
if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) {
/*
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
+#include <asm/exception.h>
#include <asm/extable.h>
#include <asm/insn.h>
#include <asm/kprobes.h>
* bad_mode handles the impossible case in the exception vector. This is always
* fatal.
*/
-asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
+asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
{
+ arm64_enter_nmi(regs);
+
console_verbose();
pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
__aligned(16);
-asmlinkage void handle_bad_stack(struct pt_regs *regs)
+asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
{
unsigned long tsk_stk = (unsigned long)current->stack;
unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
unsigned int esr = read_sysreg(esr_el1);
unsigned long far = read_sysreg(far_el1);
+ arm64_enter_nmi(regs);
+
console_verbose();
pr_emerg("Insufficient stack space to handle exception!");
}
}
-asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr)
{
- nmi_enter();
+ arm64_enter_nmi(regs);
/* non-RAS errors are not containable */
if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
arm64_serror_panic(regs, esr);
- nmi_exit();
-}
-
-asmlinkage void enter_from_user_mode(void)
-{
- CT_WARN_ON(ct_state() != CONTEXT_USER);
- user_exit_irqoff();
+ arm64_exit_nmi(regs);
}
-NOKPROBE_SYMBOL(enter_from_user_mode);
/* GENERIC_BUG traps */
CC_COMPAT ?= $(CC)
CC_COMPAT += $(CC_COMPAT_CLANG_FLAGS)
+
+ifneq ($(LLVM),)
+LD_COMPAT ?= $(LD)
+else
+LD_COMPAT ?= $(CROSS_COMPILE_COMPAT)ld
+endif
else
CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc
+LD_COMPAT ?= $(CROSS_COMPILE_COMPAT)ld
endif
cc32-option = $(call try-run,\
$(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
cc32-disable-warning = $(call try-run,\
$(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
-cc32-ldoption = $(call try-run,\
- $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
cc32-as-instr = $(call try-run,\
printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
VDSO_CFLAGS += $(dmbinstr)
VDSO_AFLAGS += $(dmbinstr)
-VDSO_LDFLAGS := $(VDSO_CPPFLAGS)
# From arm vDSO Makefile
-VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
-VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
-VDSO_LDFLAGS += -nostdlib -shared -mfloat-abi=soft
-VDSO_LDFLAGS += -Wl,--hash-style=sysv
-VDSO_LDFLAGS += -Wl,--build-id=sha1
-VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd)
+VDSO_LDFLAGS += -Bsymbolic --no-undefined -soname=linux-vdso.so.1
+VDSO_LDFLAGS += -z max-page-size=4096 -z common-page-size=4096
+VDSO_LDFLAGS += -nostdlib -shared --hash-style=sysv --build-id=sha1
# Borrow vdsomunge.c from the arm vDSO
cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
quiet_cmd_vdsold = LD32 $@
- cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
- -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
+ cmd_vdsold = $(LD_COMPAT) $(VDSO_LDFLAGS) \
+ -T $(filter %.lds,$^) $(filter %.o,$^) -o $@
quiet_cmd_vdsocc = CC32 $@
cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
quiet_cmd_vdsocc_gettimeofday = CC32 $@
* explicitly check instead of blindly discarding.
*/
.plt : {
- *(.plt) *(.plt.*) *(.iplt) *(.igot)
+ *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
}
ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;
}
+static void set_default_csv2(struct kvm *kvm)
+{
+ /*
+ * The default is to expose CSV2 == 1 if the HW isn't affected.
+ * Although this is a per-CPU feature, we make it global because
+ * asymmetric systems are just a nuisance.
+ *
+ * Userspace can override this as long as it doesn't promise
+ * the impossible.
+ */
+ if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
+ kvm->arch.pfr0_csv2 = 1;
+}
+
/**
* kvm_arch_init_vm - initializes a VM data structure
* @kvm: pointer to the KVM struct
/* The maximum number of VCPUs is limited by the host's GIC model */
kvm->arch.max_vcpus = kvm_arm_default_max_vcpus();
+ set_default_csv2(kvm);
+
return ret;
out_free_stage2_pgd:
kvm_free_stage2_pgd(&kvm->arch.mmu);
preempt_enable();
+ /*
+ * The ARMv8 architecture doesn't give the hypervisor
+ * a mechanism to prevent a guest from dropping to AArch32 EL0
+ * if implemented by the CPU. If we spot the guest in such
+ * state and that we decided it wasn't supposed to do so (like
+ * with the asymmetric AArch32 case), return to userspace with
+ * a fatal error.
+ */
+ if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) {
+ /*
+ * As we have caught the guest red-handed, decide that
+ * it isn't fit for purpose anymore by making the vcpu
+ * invalid. The VMM can try and fix it by issuing a
+ * KVM_ARM_VCPU_INIT if it really wants to.
+ */
+ vcpu->arch.target = -1;
+ ret = ARM_EXCEPTION_IL;
+ }
+
ret = handle_exit(vcpu, ret);
}
return -ENODEV;
}
- if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE))
+ if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) ||
+ cpus_have_final_cap(ARM64_WORKAROUND_1508412))
kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
"Only trusted guests should be used on this system.\n");
* We do need to save/restore PAR_EL1 though, as we haven't
* saved the guest context yet, and we may return early...
*/
- par = read_sysreg(par_el1);
+ par = read_sysreg_par();
if (!__kvm_at("s1e1r", far))
- tmp = read_sysreg(par_el1);
+ tmp = read_sysreg_par();
else
tmp = SYS_PAR_EL1_F; /* back to the guest */
write_sysreg(par, par_el1);
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
handle_tx2_tvm(vcpu))
- return true;
+ goto guest;
/*
* We trap the first access to the FP/SIMD to save the host context
* Similarly for trapped SVE accesses.
*/
if (__hyp_handle_fpsimd(vcpu))
- return true;
+ goto guest;
if (__hyp_handle_ptrauth(vcpu))
- return true;
+ goto guest;
if (!__populate_fault_info(vcpu))
- return true;
+ goto guest;
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
int ret = __vgic_v2_perform_cpuif_access(vcpu);
if (ret == 1)
- return true;
+ goto guest;
/* Promote an illegal access to an SError.*/
if (ret == -1)
int ret = __vgic_v3_perform_cpuif_access(vcpu);
if (ret == 1)
- return true;
+ goto guest;
}
exit:
/* Return to the host kernel and handle the exit */
return false;
+
+guest:
+ /* Re-enter the guest */
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412));
+ return true;
}
static inline void __kvm_unexpected_el2_exception(void)
ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
ctxt_sys_reg(ctxt, AMAIR_EL1) = read_sysreg_el1(SYS_AMAIR);
ctxt_sys_reg(ctxt, CNTKCTL_EL1) = read_sysreg_el1(SYS_CNTKCTL);
- ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg(par_el1);
+ ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg_par();
ctxt_sys_reg(ctxt, TPIDR_EL1) = read_sysreg(tpidr_el1);
ctxt_sys_reg(ctxt, SP_EL1) = read_sysreg(sp_el1);
get_host_ctxt x0, x1
- ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
-
/* Store the host regs x2 and x3 */
stp x2, x3, [x0, #CPU_XREG_OFFSET(2)]
cmp x0, #HVC_STUB_HCALL_NR
b.lo __kvm_handle_stub_hvc
- /* Set tpidr_el2 for use by HYP to free a register */
- msr tpidr_el2, x2
-
- mov x2, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init)
- cmp x0, x2
- b.eq 1f
+ // We only actively check bits [24:31], and everything
+ // else has to be zero, which we check at build time.
+#if (KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) & 0xFFFFFFFF00FFFFFF)
+#error Unexpected __KVM_HOST_SMCCC_FUNC___kvm_hyp_init value
+#endif
+
+ ror x0, x0, #24
+ eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 24) & 0xF)
+ ror x0, x0, #4
+ eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 28) & 0xF)
+ cbz x0, 1f
mov x0, #SMCCC_RET_NOT_SUPPORTED
eret
-1: phys_to_ttbr x0, x1
+1:
+ /* Set tpidr_el2 for use by HYP to free a register */
+ msr tpidr_el2, x2
+
+ phys_to_ttbr x0, x1
alternative_if ARM64_HAS_CNP
orr x0, x0, #TTBR_CNP_BIT
alternative_else_nop_endif
SECTIONS {
HYP_SECTION(.text)
+ /*
+ * .hyp..data..percpu needs to be page aligned to maintain the same
+ * alignment for when linking into vmlinux.
+ */
+ . = ALIGN(PAGE_SIZE);
HYP_SECTION_NAME(.data..percpu) : {
PERCPU_INPUT(L1_CACHE_BYTES)
}
{
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
- u64 par = read_sysreg(par_el1);
+ u64 par = read_sysreg_par();
bool restore_host = true;
struct kvm_cpu_context *host_ctxt;
struct kvm_vcpu *vcpu;
struct tlb_inv_context cxt;
/* Switch to requested VMID */
- mmu = kern_hyp_va(mmu);
__tlb_switch_to_guest(mmu, &cxt);
__tlbi(vmalle1);
static bool stage2_pte_cacheable(kvm_pte_t pte)
{
- u64 memattr = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR, pte);
+ u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
return memattr == PAGE_S2_MEMATTR(NORMAL);
}
u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
- pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL | __GFP_ZERO);
+ pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
if (!pgt->pgd)
return -ENOMEM;
{
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
- u64 par = read_sysreg(par_el1);
+ u64 par = read_sysreg_par();
__hyp_call_panic(spsr, elr, par);
unreachable();
val = SMCCC_RET_SUCCESS;
break;
case SPECTRE_UNAFFECTED:
- val = SMCCC_RET_NOT_REQUIRED;
+ val = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
break;
}
break;
vma_shift = PAGE_SHIFT;
}
- if (vma_shift == PUD_SHIFT &&
- !fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
- vma_shift = PMD_SHIFT;
-
- if (vma_shift == PMD_SHIFT &&
- !fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
- force_pte = true;
+ switch (vma_shift) {
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SHIFT:
+ if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
+ break;
+ fallthrough;
+#endif
+ case CONT_PMD_SHIFT:
+ vma_shift = PMD_SHIFT;
+ fallthrough;
+ case PMD_SHIFT:
+ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE))
+ break;
+ fallthrough;
+ case CONT_PTE_SHIFT:
vma_shift = PAGE_SHIFT;
+ force_pte = true;
+ fallthrough;
+ case PAGE_SHIFT:
+ break;
+ default:
+ WARN_ONCE(1, "Unknown vma_shift %d", vma_shift);
}
vma_pagesize = 1UL << vma_shift;
if (kvm_is_device_pfn(pfn)) {
device = true;
+ force_pte = true;
} else if (logging_active && !write_fault) {
/*
* Only actually map the page as writable if this was a write
case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break;
case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break;
case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break;
- case PAR_EL1: *val = read_sysreg_s(SYS_PAR_EL1); break;
+ case PAR_EL1: *val = read_sysreg_par(); break;
case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break;
case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break;
case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break;
{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \
access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
-static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
- const struct sys_reg_desc *r)
+static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
{
kvm_inject_undefined(vcpu);
}
/* Macro to expand the AMU counter and type registers*/
-#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
-#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu }
-#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
-#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu }
-
-static bool trap_ptrauth(struct kvm_vcpu *vcpu,
- struct sys_reg_params *p,
- const struct sys_reg_desc *rd)
-{
- /*
- * If we land here, that is because we didn't fixup the access on exit
- * by allowing the PtrAuth sysregs. The only way this happens is when
- * the guest does not have PtrAuth support enabled.
- */
- kvm_inject_undefined(vcpu);
-
- return false;
-}
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access }
+#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access }
+#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access }
static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
- return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+ return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN;
}
+/*
+ * If we land here on a PtrAuth access, that is because we didn't
+ * fixup the access on exit by allowing the PtrAuth sysregs. The only
+ * way this happens is when the guest does not have PtrAuth support
+ * enabled.
+ */
#define __PTRAUTH_KEY(k) \
- { SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k, \
+ { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \
.visibility = ptrauth_visibility}
#define PTRAUTH_KEY(k) \
if (!vcpu_has_sve(vcpu))
val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
- if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) &&
- arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED)
- val |= (1UL << ID_AA64PFR0_CSV2_SHIFT);
+ val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT);
+ val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT);
} else if (id == SYS_ID_AA64PFR1_EL1) {
val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT);
} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
return val;
}
+static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
+{
+ u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
+ (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+
+ switch (id) {
+ case SYS_ID_AA64ZFR0_EL1:
+ if (!vcpu_has_sve(vcpu))
+ return REG_RAZ;
+ break;
+ }
+
+ return 0;
+}
+
/* cpufeature ID register access trap handlers */
static bool __access_id_reg(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
- return __access_id_reg(vcpu, p, r, false);
+ bool raz = sysreg_visible_as_raz(vcpu, r);
+
+ return __access_id_reg(vcpu, p, r, raz);
}
static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
if (vcpu_has_sve(vcpu))
return 0;
- return REG_HIDDEN_USER | REG_HIDDEN_GUEST;
-}
-
-/* Visibility overrides for SVE-specific ID registers */
-static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *rd)
-{
- if (vcpu_has_sve(vcpu))
- return 0;
-
- return REG_HIDDEN_USER;
+ return REG_HIDDEN;
}
-/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */
-static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu)
-{
- if (!vcpu_has_sve(vcpu))
- return 0;
-
- return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1);
-}
-
-static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
- struct sys_reg_params *p,
- const struct sys_reg_desc *rd)
-{
- if (p->is_write)
- return write_to_read_only(vcpu, p, rd);
-
- p->regval = guest_id_aa64zfr0_el1(vcpu);
- return true;
-}
-
-static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *rd,
- const struct kvm_one_reg *reg, void __user *uaddr)
-{
- u64 val;
-
- if (WARN_ON(!vcpu_has_sve(vcpu)))
- return -ENOENT;
-
- val = guest_id_aa64zfr0_el1(vcpu);
- return reg_to_user(uaddr, &val, reg->id);
-}
-
-static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *rd,
- const struct kvm_one_reg *reg, void __user *uaddr)
+static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *rd,
+ const struct kvm_one_reg *reg, void __user *uaddr)
{
const u64 id = sys_reg_to_index(rd);
int err;
u64 val;
-
- if (WARN_ON(!vcpu_has_sve(vcpu)))
- return -ENOENT;
+ u8 csv2;
err = reg_from_user(&val, uaddr, id);
if (err)
return err;
- /* This is what we mean by invariant: you can't change it. */
- if (val != guest_id_aa64zfr0_el1(vcpu))
+ /*
+ * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as
+ * it doesn't promise more than what is actually provided (the
+ * guest could otherwise be covered in ectoplasmic residue).
+ */
+ csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT);
+ if (csv2 > 1 ||
+ (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED))
return -EINVAL;
+ /* We can only differ with CSV2, and anything else is an error */
+ val ^= read_id_reg(vcpu, rd, false);
+ val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT);
+ if (val)
+ return -EINVAL;
+
+ vcpu->kvm->arch.pfr0_csv2 = csv2;
+
return 0;
}
static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
const struct kvm_one_reg *reg, void __user *uaddr)
{
- return __get_id_reg(vcpu, rd, uaddr, false);
+ bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+ return __get_id_reg(vcpu, rd, uaddr, raz);
}
static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
const struct kvm_one_reg *reg, void __user *uaddr)
{
- return __set_id_reg(vcpu, rd, uaddr, false);
+ bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+ return __set_id_reg(vcpu, rd, uaddr, raz);
}
static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
return true;
}
-static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
- const struct sys_reg_desc *r)
-{
- kvm_inject_undefined(vcpu);
- return false;
-}
-
/* sys_reg_desc initialiser for known cpufeature ID registers */
#define ID_SANITISED(name) { \
SYS_DESC(SYS_##name), \
.access = access_id_reg, \
.get_user = get_id_reg, \
.set_user = set_id_reg, \
+ .visibility = id_visibility, \
}
/*
/* AArch64 ID registers */
/* CRm=4 */
- ID_SANITISED(ID_AA64PFR0_EL1),
+ { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg,
+ .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, },
ID_SANITISED(ID_AA64PFR1_EL1),
ID_UNALLOCATED(4,2),
ID_UNALLOCATED(4,3),
- { SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility },
+ ID_SANITISED(ID_AA64ZFR0_EL1),
ID_UNALLOCATED(4,5),
ID_UNALLOCATED(4,6),
ID_UNALLOCATED(4,7),
{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
- { SYS_DESC(SYS_RGSR_EL1), access_mte_regs },
- { SYS_DESC(SYS_GCR_EL1), access_mte_regs },
+ { SYS_DESC(SYS_RGSR_EL1), undef_access },
+ { SYS_DESC(SYS_GCR_EL1), undef_access },
{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
- { SYS_DESC(SYS_TFSR_EL1), access_mte_regs },
- { SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs },
+ { SYS_DESC(SYS_TFSR_EL1), undef_access },
+ { SYS_DESC(SYS_TFSRE0_EL1), undef_access },
{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
{ SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
+ { SYS_DESC(SYS_SCXTNUM_EL1), undef_access },
+
{ SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
{ SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr },
{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
- { SYS_DESC(SYS_AMCR_EL0), access_amu },
- { SYS_DESC(SYS_AMCFGR_EL0), access_amu },
- { SYS_DESC(SYS_AMCGCR_EL0), access_amu },
- { SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
- { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+ { SYS_DESC(SYS_SCXTNUM_EL0), undef_access },
+
+ { SYS_DESC(SYS_AMCR_EL0), undef_access },
+ { SYS_DESC(SYS_AMCFGR_EL0), undef_access },
+ { SYS_DESC(SYS_AMCGCR_EL0), undef_access },
+ { SYS_DESC(SYS_AMUSERENR_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access },
+ { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access },
AMU_AMEVCNTR0_EL0(0),
AMU_AMEVCNTR0_EL0(1),
AMU_AMEVCNTR0_EL0(2),
{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
DBG_BCR_BVR_WCR_WVR(1),
/* DBGDCCINT */
- { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT },
/* DBGDSCRext */
- { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext },
DBG_BCR_BVR_WCR_WVR(2),
/* DBGDTR[RT]Xint */
{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
DBG_BCR_BVR_WCR_WVR(6),
/* DBGVCR */
- { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+ { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR },
DBG_BCR_BVR_WCR_WVR(7),
DBG_BCR_BVR_WCR_WVR(8),
DBG_BCR_BVR_WCR_WVR(9),
trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
/* Check for regs disabled by runtime config */
- if (sysreg_hidden_from_guest(vcpu, r)) {
+ if (sysreg_hidden(vcpu, r)) {
kvm_inject_undefined(vcpu);
return;
}
return get_invariant_sys_reg(reg->id, uaddr);
/* Check for regs disabled by runtime config */
- if (sysreg_hidden_from_user(vcpu, r))
+ if (sysreg_hidden(vcpu, r))
return -ENOENT;
if (r->get_user)
return set_invariant_sys_reg(reg->id, uaddr);
/* Check for regs disabled by runtime config */
- if (sysreg_hidden_from_user(vcpu, r))
+ if (sysreg_hidden(vcpu, r))
return -ENOENT;
if (r->set_user)
if (!(rd->reg || rd->get_user))
return 0;
- if (sysreg_hidden_from_user(vcpu, rd))
+ if (sysreg_hidden(vcpu, rd))
return 0;
if (!copy_reg_to_user(rd, uind))
const struct sys_reg_desc *rd);
};
-#define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */
-#define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */
+#define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */
+#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */
static __printf(2, 3)
inline void print_sys_reg_msg(const struct sys_reg_params *p,
__vcpu_sys_reg(vcpu, r->reg) = r->val;
}
-static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *r)
+static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
{
if (likely(!r->visibility))
return false;
- return r->visibility(vcpu, r) & REG_HIDDEN_GUEST;
+ return r->visibility(vcpu, r) & REG_HIDDEN;
}
-static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *r)
+static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
{
if (likely(!r->visibility))
return false;
- return r->visibility(vcpu, r) & REG_HIDDEN_USER;
+ return r->visibility(vcpu, r) & REG_RAZ;
}
static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
return extract_bytes(value, addr & 7, len);
}
+static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu,
+ gpa_t addr, unsigned int len)
+{
+ unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+ int target_vcpu_id = vcpu->vcpu_id;
+ u64 value;
+
+ value = (u64)(mpidr & GENMASK(23, 0)) << 32;
+ value |= ((target_vcpu_id & 0xffff) << 8);
+
+ if (vgic_has_its(vcpu->kvm))
+ value |= GICR_TYPER_PLPIS;
+
+ /* reporting of the Last bit is not supported for userspace */
+ return extract_bytes(value, addr & 7, len);
+}
+
static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
REGISTER_DESC_WITH_LENGTH(GICR_IIDR,
vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4,
VGIC_ACCESS_32bit),
- REGISTER_DESC_WITH_LENGTH(GICR_TYPER,
- vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8,
+ REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER,
+ vgic_mmio_read_v3r_typer, vgic_mmio_write_wi,
+ vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8,
VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_LENGTH(GICR_WAKER,
vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
stp \reg1, \reg2, [\ptr], \val
.endm
- .weak memcpy
SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_PI(memcpy)
+SYM_FUNC_START_WEAK_PI(memcpy)
#include "copy_template.S"
ret
SYM_FUNC_END_PI(memcpy)
D_l .req x13
D_h .req x14
- .weak memmove
SYM_FUNC_START_ALIAS(__memmove)
-SYM_FUNC_START_PI(memmove)
+SYM_FUNC_START_WEAK_PI(memmove)
cmp dstin, src
b.lo __memcpy
add tmp1, src, count
tmp3w .req w9
tmp3 .req x9
- .weak memset
SYM_FUNC_START_ALIAS(__memset)
-SYM_FUNC_START_PI(memset)
+SYM_FUNC_START_WEAK_PI(memset)
mov dst, dstin /* Preserve return value. */
and A_lw, val, #255
orr A_lw, A_lw, A_lw, lsl #8
local_irq_save(flags);
asm volatile("at s1e1r, %0" :: "r" (addr));
isb();
- par = read_sysreg(par_el1);
+ par = read_sysreg_par();
local_irq_restore(flags);
/*
*/
static void debug_exception_enter(struct pt_regs *regs)
{
- /*
- * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
- * already disabled to preserve the last enabled/disabled addresses.
- */
- if (interrupts_enabled(regs))
- trace_hardirqs_off();
-
- if (user_mode(regs)) {
- RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
- } else {
- /*
- * We might have interrupted pretty much anything. In
- * fact, if we're a debug exception, we can even interrupt
- * NMI processing. We don't want this code makes in_nmi()
- * to return true, but we need to notify RCU.
- */
- rcu_nmi_enter();
- }
-
preempt_disable();
/* This code is a bit fragile. Test it. */
static void debug_exception_exit(struct pt_regs *regs)
{
preempt_enable_no_resched();
-
- if (!user_mode(regs))
- rcu_nmi_exit();
-
- if (interrupts_enabled(regs))
- trace_hardirqs_on();
}
NOKPROBE_SYMBOL(debug_exception_exit);
free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
}
+static bool inside_linear_region(u64 start, u64 size)
+{
+ /*
+ * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
+ * accommodating both its ends but excluding PAGE_END. Max physical
+ * range which can be mapped inside this linear mapping range, must
+ * also be derived from its end points.
+ */
+ return start >= __pa(_PAGE_OFFSET(vabits_actual)) &&
+ (start + size - 1) <= __pa(PAGE_END - 1);
+}
+
int arch_add_memory(int nid, u64 start, u64 size,
struct mhp_params *params)
{
int ret, flags = 0;
+ if (!inside_linear_region(start, size)) {
+ pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size);
+ return -EINVAL;
+ }
+
if (rodata_full || debug_pagealloc_enabled())
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
#ifdef CONFIG_CPU_PM_STOP
asm volatile("stop\n");
#endif
- local_irq_enable();
+ raw_local_irq_enable();
}
#endif
*/
void arch_cpu_idle(void)
{
- local_irq_enable();
+ raw_local_irq_enable();
__asm__("sleep");
}
{
__vmwait();
/* interrupts wake us up, but irqs are still disabled */
- local_irq_enable();
+ raw_local_irq_enable();
}
/*
#endif
#endif /* CONFIG_SPARSEMEM */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int memory_add_physaddr_to_nid(u64 addr);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+
#endif /* _ASM_IA64_SPARSEMEM_H */
if (mark_idle)
(*mark_idle)(1);
- safe_halt();
+ raw_safe_halt();
if (mark_idle)
(*mark_idle)(0);
void arch_cpu_idle(void)
{
- local_irq_enable();
+ raw_local_irq_enable();
}
{
struct clk_init_data id;
struct clk_hw *h;
+ struct clk *clk;
h = kzalloc(sizeof(*h), GFP_KERNEL);
if (!h)
id.ops = &alchemy_clkops_cpu;
h->init = &id;
- return clk_register(NULL, h);
+ clk = clk_register(NULL, h);
+ if (IS_ERR(clk)) {
+ pr_err("failed to register clock\n");
+ kfree(h);
+ }
+
+ return clk;
}
/* AUXPLLs ************************************************************/
#if defined(CONFIG_XPA)
+#define MAX_POSSIBLE_PHYSMEM_BITS 40
#define pte_pfn(x) (((unsigned long)((x).pte_high >> _PFN_SHIFT)) | (unsigned long)((x).pte_low << _PAGE_PRESENT_SHIFT))
static inline pte_t
pfn_pte(unsigned long pfn, pgprot_t prot)
#elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
#define pte_pfn(x) ((unsigned long)((x).pte_high >> 6))
static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
#else
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
#ifdef CONFIG_CPU_VR41XX
#define pte_pfn(x) ((unsigned long)((x).pte >> (PAGE_SHIFT + 2)))
#define pfn_pte(pfn, prot) __pte(((pfn) << (PAGE_SHIFT + 2)) | pgprot_val(prot))
{
unsigned long cfg = read_c0_conf();
write_c0_conf(cfg | R30XX_CONF_HALT);
- local_irq_enable();
+ raw_local_irq_enable();
}
static void __cpuidle r39xx_wait(void)
{
if (!need_resched())
write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
- local_irq_enable();
+ raw_local_irq_enable();
}
void __cpuidle r4k_wait(void)
{
- local_irq_enable();
+ raw_local_irq_enable();
__r4k_wait();
}
" .set arch=r4000 \n"
" wait \n"
" .set pop \n");
- local_irq_enable();
+ raw_local_irq_enable();
}
/*
" wait \n"
" mtc0 $1, $12 # stalls until W stage \n"
" .set pop \n");
- local_irq_enable();
+ raw_local_irq_enable();
}
/*
if (cpu_wait)
cpu_wait();
else
- local_irq_enable();
+ raw_local_irq_enable();
}
#ifdef CONFIG_CPU_IDLE
static void __init bootmem_init(void)
{
phys_addr_t ramstart, ramend;
- phys_addr_t start, end;
- u64 i;
+ unsigned long start, end;
+ int i;
ramstart = memblock_start_of_DRAM();
ramend = memblock_end_of_DRAM();
min_low_pfn = ARCH_PFN_OFFSET;
max_pfn = PFN_DOWN(ramend);
- for_each_mem_range(i, &start, &end) {
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) {
/*
* Skip highmem here so we get an accurate max_low_pfn if low
* memory stops short of high memory.
}
return mask == PM_HUGE_MASK;
}
+EXPORT_SYMBOL(has_transparent_hugepage);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
void arch_cpu_idle(void)
{
- local_irq_enable();
+ raw_local_irq_enable();
}
/*
*/
void arch_cpu_idle(void)
{
- local_irq_enable();
+ raw_local_irq_enable();
if (mfspr(SPR_UPR) & SPR_UPR_PMP)
mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME);
}
void __cpuidle arch_cpu_idle(void)
{
- local_irq_enable();
+ raw_local_irq_enable();
/* nop on real hardware, qemu will idle sleep. */
asm volatile("or %%r10,%%r10,%%r10\n":::);
select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
+ select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
select BUILDTIME_TABLE_SORT
LDFLAGS_vmlinux-y := -Bstatic
LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y)
-LDFLAGS_vmlinux += $(call ld-option,--orphan-handling=warn)
ifdef CONFIG_PPC64
ifeq ($(call cc-option-yn,-mcmodel=medium),y)
cpu-as-$(CONFIG_40x) += -Wa,-m405
cpu-as-$(CONFIG_44x) += -Wa,-m440
cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec)
-cpu-as-$(CONFIG_E200) += -Wa,-me200
cpu-as-$(CONFIG_E500) += -Wa,-me500
# When using '-many -mpower4' gas will first try and find a matching power4
*/
#ifdef CONFIG_PTE_64BIT
#define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
#else
#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
#endif
/*
#endif
.endm
+#ifdef CONFIG_PPC_KUAP
.macro kuap_check_amr gpr1, gpr2
#ifdef CONFIG_PPC_KUAP_DEBUG
BEGIN_MMU_FTR_SECTION_NESTED(67)
END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
#endif
.endm
+#endif
.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr
#ifdef CONFIG_PPC_KUAP
#else /* !__ASSEMBLY__ */
+#include <linux/jump_label.h>
+
+DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
+
#ifdef CONFIG_PPC_KUAP
#include <asm/mmu.h>
static inline unsigned long get_kuap(void)
{
+ /*
+ * We return AMR_KUAP_BLOCKED when we don't support KUAP because
+ * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to
+ * cause restore_user_access to do a flush.
+ *
+ * This has no effect in terms of actually blocking things on hash,
+ * so it doesn't break anything.
+ */
if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
- return 0;
+ return AMR_KUAP_BLOCKED;
return mfspr(SPRN_AMR);
}
isync();
}
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+ return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
+ (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
+ "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
+}
+#else /* CONFIG_PPC_KUAP */
+static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr) { }
+
+static inline unsigned long kuap_get_and_check_amr(void)
+{
+ return 0UL;
+}
+
+static inline unsigned long get_kuap(void)
+{
+ return AMR_KUAP_BLOCKED;
+}
+
+static inline void set_kuap(unsigned long value) { }
+#endif /* !CONFIG_PPC_KUAP */
+
static __always_inline void allow_user_access(void __user *to, const void __user *from,
unsigned long size, unsigned long dir)
{
unsigned long size, unsigned long dir)
{
set_kuap(AMR_KUAP_BLOCKED);
+ if (static_branch_unlikely(&uaccess_flush_key))
+ do_uaccess_flush();
}
static inline unsigned long prevent_user_access_return(void)
unsigned long flags = get_kuap();
set_kuap(AMR_KUAP_BLOCKED);
+ if (static_branch_unlikely(&uaccess_flush_key))
+ do_uaccess_flush();
return flags;
}
static inline void restore_user_access(unsigned long flags)
{
set_kuap(flags);
+ if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED)
+ do_uaccess_flush();
}
-
-static inline bool
-bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
-{
- return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
- (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
- "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
-}
-#else /* CONFIG_PPC_KUAP */
-static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
-{
-}
-
-static inline void kuap_check_amr(void)
-{
-}
-
-static inline unsigned long kuap_get_and_check_amr(void)
-{
- return 0;
-}
-#endif /* CONFIG_PPC_KUAP */
-
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
static inline void radix_init_pseries(void) { };
#endif
+#ifdef CONFIG_HOTPLUG_CPU
+#define arch_clear_mm_cpumask_cpu(cpu, mm) \
+ do { \
+ if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \
+ atomic_dec(&(mm)->context.active_cpus); \
+ cpumask_clear_cpu(cpu, mm_cpumask(mm)); \
+ } \
+ } while (0)
+
+void cleanup_cpu_mmu_context(void);
+#endif
+
static inline int get_user_context(mm_context_t *ctx, unsigned long ea)
{
int index = ea >> MAX_EA_BITS_PER_CONTEXT;
nop; \
nop
+#define ENTRY_FLUSH_SLOT \
+ ENTRY_FLUSH_FIXUP_SECTION; \
+ nop; \
+ nop; \
+ nop;
+
/*
* r10 must be free to use, r13 must be paca
*/
#define INTERRUPT_TO_KERNEL \
- STF_ENTRY_BARRIER_SLOT
+ STF_ENTRY_BARRIER_SLOT; \
+ ENTRY_FLUSH_SLOT
/*
* Macros for annotating the expected destination of (h)rfid
RFSCV; \
b rfscv_flush_fallback
+#else /* __ASSEMBLY__ */
+/* Prototype for function defined in exceptions-64s.S */
+void do_uaccess_flush(void);
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_EXCEPTION_H */
FTR_ENTRY_OFFSET 955b-956b; \
.popsection;
+#define UACCESS_FLUSH_FIXUP_SECTION \
+959: \
+ .pushsection __uaccess_flush_fixup,"a"; \
+ .align 2; \
+960: \
+ FTR_ENTRY_OFFSET 959b-960b; \
+ .popsection;
+
+#define ENTRY_FLUSH_FIXUP_SECTION \
+957: \
+ .pushsection __entry_flush_fixup,"a"; \
+ .align 2; \
+958: \
+ FTR_ENTRY_OFFSET 957b-958b; \
+ .popsection;
+
#define RFI_FLUSH_FIXUP_SECTION \
951: \
.pushsection __rfi_flush_fixup,"a"; \
#include <linux/types.h>
extern long stf_barrier_fallback;
+extern long entry_flush_fallback;
extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup;
+extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
#define KUAP_CURRENT_WRITE 8
#define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE)
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
#include <asm/book3s/64/kup-radix.h>
#endif
#ifdef CONFIG_PPC_8xx
.macro kuap_check current, gpr
.endm
+.macro kuap_check_amr gpr1, gpr2
+.endm
+
#endif
#else /* !__ASSEMBLY__ */
void setup_kuap(bool disabled);
#else
static inline void setup_kuap(bool disabled) { }
+
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+ return false;
+}
+
+static inline void kuap_check_amr(void) { }
+
+/*
+ * book3s/64/kup-radix.h defines these functions for the !KUAP case to flush
+ * the L1D cache after user accesses. Only include the empty stubs for other
+ * platforms.
+ */
+#ifndef CONFIG_PPC_BOOK3S_64
static inline void allow_user_access(void __user *to, const void __user *from,
unsigned long size, unsigned long dir) { }
static inline void prevent_user_access(void __user *to, const void __user *from,
unsigned long size, unsigned long dir) { }
static inline unsigned long prevent_user_access_return(void) { return 0UL; }
static inline void restore_user_access(unsigned long flags) { }
-static inline bool
-bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
-{
- return false;
-}
+#endif /* CONFIG_PPC_BOOK3S_64 */
#endif /* CONFIG_PPC_KUAP */
static inline void allow_read_from_user(const void __user *from, unsigned long size)
#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
#endif
+#ifdef CONFIG_MEMORY_HOTPLUG
+extern int create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot);
+#endif
+
#endif /* __KERNEL__ */
#endif /* _ASM_MMZONE_H_ */
static inline bool
bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
{
- return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
+ return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000),
"Bug: fault blocked by AP register !");
}
* respectively NA for All or X for Supervisor and no access for User.
* Then we use the APG to say whether accesses are according to Page rules or
* "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
- */
-#define MI_APG_INIT 0x40000000
-
-/*
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MI_APG_KUEP 0x60000000
+ * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say
+ * "all User" rules, that will lead to NA for all.
+ * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED
+ * 0 => Kernel => 11 (all accesses performed according as user iaw page definition)
+ * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition)
+ * 2 => User => 11 (all accesses performed according as user iaw page definition)
+ * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT
+ * => 10 (all accesses performed according to swaped page definition) for KUEP
+ * 4-15 => Not Used
+ */
+#define MI_APG_INIT 0xdc000000
+#define MI_APG_KUEP 0xde000000
/* The effective page number register. When read, contains the information
* about the last instruction TLB miss. When MI_RPN is written, bits in
#define MD_Ks 0x80000000 /* Should not be set */
#define MD_Kp 0x40000000 /* Should always be set */
-/*
- * All pages' PP data bits are set to either 000 or 011 or 001, which means
- * respectively RW for Supervisor and no access for User, or RO for
- * Supervisor and no access for user and NA for ALL.
- * Then we use the APG to say whether accesses are according to Page rules or
- * "all Supervisor" rules (Access to all)
- * Therefore, we define 2 APG groups. lsb is _PMD_USER
- * 0 => Kernel => 01 (all accesses performed according to page definition)
- * 1 => User => 00 (all accesses performed as supervisor iaw page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_INIT 0x40000000
-
-/*
- * 0 => No user => 01 (all accesses performed according to page definition)
- * 1 => User => 10 (all accesses performed according to swaped page definition)
- * 2-15 => Not Used
- */
-#define MD_APG_KUAP 0x60000000
+/* See explanation above at the definition of MI_APG_INIT */
+#define MD_APG_INIT 0xdc000000
+#define MD_APG_KUAP 0xde000000
/* The effective page number register. When read, contains the information
* about the last instruction TLB miss. When MD_RPN is written, bits in
*/
#if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
#define PTE_RPN_MASK (~((1ULL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
#else
#define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
#endif
/*
* into the TLB.
*/
#define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */
-#define _PAGE_SPECIAL 0x0020 /* SW entry */
+#define _PAGE_ACCESSED 0x0020 /* Copied to L1 APG 1 entry in I/DTLB */
#define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */
-#define _PAGE_ACCESSED 0x0080 /* software: page referenced */
+#define _PAGE_SPECIAL 0x0080 /* SW entry */
#define _PAGE_NA 0x0200 /* Supervisor NA, User no access */
#define _PAGE_RO 0x0600 /* Supervisor RO, User no access */
#define _PMD_PRESENT 0x0001
#define _PMD_PRESENT_MASK _PMD_PRESENT
-#define _PMD_BAD 0x0fd0
+#define _PMD_BAD 0x0f90
#define _PMD_PAGE_MASK 0x000c
#define _PMD_PAGE_8M 0x000c
#define _PMD_PAGE_512K 0x0004
-#define _PMD_USER 0x0020 /* APG 1 */
+#define _PMD_ACCESSED 0x0020 /* APG 1 */
+#define _PMD_USER 0x0040 /* APG 2 */
#define _PTE_NONE_MASK 0
// Software required to flush link stack on context switch
#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull
+// The L1-D cache should be flushed when entering the kernel
+#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull
+
+// The L1-D cache should be flushed after user accesses from the kernel
+#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull
// Features enabled by default
#define SEC_FTR_DEFAULT \
(SEC_FTR_L1D_FLUSH_HV | \
SEC_FTR_L1D_FLUSH_PR | \
SEC_FTR_BNDS_CHK_SPEC_BAR | \
+ SEC_FTR_L1D_FLUSH_ENTRY | \
+ SEC_FTR_L1D_FLUSH_UACCESS | \
SEC_FTR_FAVOUR_SECURITY)
#endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
};
void setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_entry_flush(bool enable);
+void setup_uaccess_flush(bool enable);
void do_rfi_flush_fixups(enum l1d_flush_type types);
#ifdef CONFIG_PPC_BARRIER_NOSPEC
void setup_barrier_nospec(void);
#else
static inline void setup_barrier_nospec(void) { };
#endif
+void do_uaccess_flush_fixups(enum l1d_flush_type types);
+void do_entry_flush_fixups(enum l1d_flush_type types);
void do_barrier_nospec_fixups(bool enable);
extern bool barrier_nospec_enabled;
#endif /* CONFIG_SPARSEMEM */
#ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
- int nid, pgprot_t prot);
extern int remove_section_mapping(unsigned long start, unsigned long end);
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
#ifdef CONFIG_NUMA
extern int hot_add_scn_to_nid(unsigned long scn_addr);
}
#endif /* CONFIG_NUMA */
#endif /* CONFIG_MEMORY_HOTPLUG */
-
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_SPARSEMEM_H */
struct device;
struct device_node;
+struct drmem_lmb;
#ifdef CONFIG_NUMA
*/
return (nid < 0) ? 0 : nid;
}
+
+int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+
#else
static inline int early_cpu_to_node(int cpu) { return 0; }
return 0;
}
-#endif /* CONFIG_NUMA */
+static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
+{
+ return first_online_node;
+}
-struct drmem_lmb;
-int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+#endif /* CONFIG_NUMA */
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
extern int find_and_online_cpu_nid(int cpu);
* are no aliasing issues.
*/
#define __put_user_asm_goto(x, addr, label, op) \
- asm volatile goto( \
+ asm_volatile_goto( \
"1: " op "%U1%X1 %0,%1 # put_user\n" \
EX_TABLE(1b, %l2) \
: \
__put_user_asm_goto(x, ptr, label, "std")
#else /* __powerpc64__ */
#define __put_user_asm2_goto(x, addr, label) \
- asm volatile goto( \
+ asm_volatile_goto( \
"1: stw%X1 %0, %1\n" \
"2: stw%X1 %L0, %L1\n" \
EX_TABLE(1b, %l2) \
{
struct pci_io_addr_range *piar;
struct rb_node *n;
+ unsigned long flags;
- spin_lock(&pci_io_addr_cache_root.piar_lock);
+ spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) {
piar = rb_entry(n, struct pci_io_addr_range, rb_node);
(piar->flags & IORESOURCE_IO) ? "i/o" : "mem",
&piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev));
}
- spin_unlock(&pci_io_addr_cache_root.piar_lock);
+ spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
return 0;
}
* Vectors for the FWNMI option. Share common code.
*/
TRAMP_REAL_BEGIN(system_reset_fwnmi)
- /* XXX: fwnmi guest could run a nested/PR guest, so why no test? */
- __IKVM_REAL(system_reset)=0
GEN_INT_ENTRY system_reset, virt=0
#endif /* CONFIG_PPC_PSERIES */
* If none is found, do a Linux page fault. Linux page faults can happen in
* kernel mode due to user copy operations of course.
*
+ * KVM: The KVM HDSI handler may perform a load with MSR[DR]=1 in guest
+ * MMU context, which may cause a DSI in the host, which must go to the
+ * KVM handler. MSR[IR] is not enabled, so the real-mode handler will
+ * always be used regardless of AIL setting.
+ *
* - Radix MMU
* The hardware loads from the Linux page table directly, so a fault goes
* immediately to Linux page fault.
IVEC=0x300
IDAR=1
IDSISR=1
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_SKIP=1
IKVM_REAL=1
-#endif
INT_DEFINE_END(data_access)
EXC_REAL_BEGIN(data_access, 0x300, 0x80)
* ppc64_bolted_size (first segment). The kernel handler must avoid stomping
* on user-handler data structures.
*
+ * KVM: Same as 0x300, DSLB must test for KVM guest.
+ *
* A dedicated save area EXSLB is used (XXX: but it actually need not be
* these days, we could use EXGEN).
*/
IAREA=PACA_EXSLB
IRECONCILE=0
IDAR=1
-#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
IKVM_SKIP=1
IKVM_REAL=1
-#endif
INT_DEFINE_END(data_access_slb)
EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
.endr
blr
-TRAMP_REAL_BEGIN(rfi_flush_fallback)
- SET_SCRATCH0(r13);
- GET_PACA(r13);
- std r1,PACA_EXRFI+EX_R12(r13)
- ld r1,PACAKSAVE(r13)
- std r9,PACA_EXRFI+EX_R9(r13)
- std r10,PACA_EXRFI+EX_R10(r13)
- std r11,PACA_EXRFI+EX_R11(r13)
- mfctr r9
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
ld r11,PACA_L1D_FLUSH_SIZE(r13)
srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
sync
/*
- * The load adresses are at staggered offsets within cachelines,
+ * The load addresses are at staggered offsets within cachelines,
* which suits some pipelines better (on others it should not
* hurt).
*/
ld r11,(0x80 + 8)*7(r10)
addi r10,r10,0x80*8
bdnz 1b
+.endm
+TRAMP_REAL_BEGIN(entry_flush_fallback)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ blr
+
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r1,PACA_EXRFI+EX_R12(r13)
+ ld r1,PACAKSAVE(r13)
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
std r10,PACA_EXRFI+EX_R10(r13)
std r11,PACA_EXRFI+EX_R11(r13)
mfctr r9
- ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
- ld r11,PACA_L1D_FLUSH_SIZE(r13)
- srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
- mtctr r11
- DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
- /* order ld/st prior to dcbt stop all streams with flushing */
- sync
-
- /*
- * The load adresses are at staggered offsets within cachelines,
- * which suits some pipelines better (on others it should not
- * hurt).
- */
-1:
- ld r11,(0x80 + 8)*0(r10)
- ld r11,(0x80 + 8)*1(r10)
- ld r11,(0x80 + 8)*2(r10)
- ld r11,(0x80 + 8)*3(r10)
- ld r11,(0x80 + 8)*4(r10)
- ld r11,(0x80 + 8)*5(r10)
- ld r11,(0x80 + 8)*6(r10)
- ld r11,(0x80 + 8)*7(r10)
- addi r10,r10,0x80*8
- bdnz 1b
-
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
RFSCV
USE_TEXT_SECTION()
- MASKED_INTERRUPT
- MASKED_INTERRUPT hsrr=1
+
+_GLOBAL(do_uaccess_flush)
+ UACCESS_FLUSH_FIXUP_SECTION
+ nop
+ nop
+ nop
+ blr
+ L1D_DISPLACEMENT_FLUSH
+ blr
+_ASM_NOKPROBE_SYMBOL(do_uaccess_flush)
+EXPORT_SYMBOL(do_uaccess_flush)
+
+
+MASKED_INTERRUPT
+MASKED_INTERRUPT hsrr=1
#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
kvmppc_skip_interrupt:
rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
lwz r11, 0(r11) /* Get Linux PTE */
-#ifdef CONFIG_SWAP
li r9, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
- li r9, _PAGE_PRESENT
-#endif
andc. r9, r9, r11 /* Check permission */
bne 5f
rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */
lwz r11, 0(r11) /* Get Linux PTE */
-#ifdef CONFIG_SWAP
li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
- li r9, _PAGE_PRESENT | _PAGE_EXEC
-#endif
andc. r9, r9, r11 /* Check permission */
bne 5f
InstructionTLBMiss:
mtspr SPRN_SPRG_SCRATCH0, r10
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
mtspr SPRN_SPRG_SCRATCH1, r11
-#endif
/* If we are faulting a kernel address, we have to use the
* kernel page tables.
3:
mtcr r11
#endif
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
mtspr SPRN_MD_TWC, r11
-#else
- lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */
- mtspr SPRN_MI_TWC, r10 /* Set segment attributes */
- mtspr SPRN_MD_TWC, r10
-#endif
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
-#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT)
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
mtspr SPRN_MI_TWC, r11
-#endif
-#ifdef CONFIG_SWAP
- rlwinm r11, r10, 32-5, _PAGE_PRESENT
- and r11, r11, r10
- rlwimi r10, r11, 0, _PAGE_PRESENT
-#endif
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 20 and 23 must be clear.
* Software indicator bits 22, 24, 25, 26, and 27 must be
/* Restore registers */
0: mfspr r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS)
mfspr r11, SPRN_SPRG_SCRATCH1
-#endif
rfi
patch_site 0b, patch__itlbmiss_exit_1
addi r10, r10, 1
stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0)
mfspr r10, SPRN_SPRG_SCRATCH0
-#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP)
mfspr r11, SPRN_SPRG_SCRATCH1
-#endif
rfi
#endif
mfspr r10, SPRN_MD_TWC
lwz r10, 0(r10) /* Get the pte */
- /* Insert the Guarded flag into the TWC from the Linux PTE.
+ /* Insert Guarded and Accessed flags into the TWC from the Linux PTE.
* It is bit 27 of both the Linux PTE and the TWC (at least
* I got that right :-). It will be better when we can put
* this into the Linux pgd/pmd and load it in the operation
* above.
*/
- rlwimi r11, r10, 0, _PAGE_GUARDED
+ rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED
rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K
mtspr SPRN_MD_TWC, r11
- /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
- * We also need to know if the insn is a load/store, so:
- * Clear _PAGE_PRESENT and load that which will
- * trap into DTLB Error with store bit set accordinly.
- */
- /* PRESENT=0x1, ACCESSED=0x20
- * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
- * r10 = (r10 & ~PRESENT) | r11;
- */
-#ifdef CONFIG_SWAP
- rlwinm r11, r10, 32-5, _PAGE_PRESENT
- and r11, r11, r10
- rlwimi r10, r11, 0, _PAGE_PRESENT
-#endif
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 24, 25, 26, and 27 must be
* set. All other Linux PTE bits control the behavior
li r9, 4 /* up to 4 pages of 8M */
mtctr r9
lis r9, KERNELBASE@h /* Create vaddr for TLB */
- li r10, MI_PS8MEG | MI_SVALID /* Set 8M byte page */
+ li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID
li r11, MI_BOOTINIT /* Create RPN for address 0 */
1:
mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */
#ifdef CONFIG_PIN_TLB_TEXT
LOAD_REG_IMMEDIATE(r5, 28 << 8)
LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
- LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
LOAD_REG_ADDR(r9, _sinittext)
li r0, 4
LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM)
#ifdef CONFIG_PIN_TLB_DATA
LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
- LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG)
+ LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
#ifdef CONFIG_PIN_TLB_IMMR
li r0, 3
#else
#endif
#ifdef CONFIG_PIN_TLB_IMMR
LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID)
- LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED)
+ LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED)
mfspr r8, SPRN_IMMR
rlwinm r8, r8, 0, 0xfff80000
ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \
bl initial_bats
bl load_segment_registers
BEGIN_MMU_FTR_SECTION
+ bl reloc_offset
bl early_hash_table
END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
#if defined(CONFIG_BOOTX_TEXT)
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
-#else
- li r1,_PAGE_PRESENT | _PAGE_EXEC
-#endif
#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
li r1, _PAGE_PRESENT | _PAGE_ACCESSED
-#else
- li r1, _PAGE_PRESENT
-#endif
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
-#ifdef CONFIG_SWAP
li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
-#else
- li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
-#endif
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
ori r6, r6, 3 /* 256kB table */
mtspr SPRN_SDR1, r6
lis r6, early_hash@h
- lis r3, Hash@ha
+ addis r3, r3, Hash@ha
stw r6, Hash@l(r3)
blr
* interrupts enabled, some don't.
*/
if (irqs_disabled())
- local_irq_enable();
+ raw_local_irq_enable();
} else {
- local_irq_enable();
+ raw_local_irq_enable();
/*
* Go into low thread priority and possibly
* low power mode.
static enum l1d_flush_type enabled_flush_types;
static void *l1d_flush_fallback_area;
static bool no_rfi_flush;
+static bool no_entry_flush;
+static bool no_uaccess_flush;
bool rfi_flush;
+bool entry_flush;
+bool uaccess_flush;
+DEFINE_STATIC_KEY_FALSE(uaccess_flush_key);
+EXPORT_SYMBOL(uaccess_flush_key);
static int __init handle_no_rfi_flush(char *p)
{
}
early_param("no_rfi_flush", handle_no_rfi_flush);
+static int __init handle_no_entry_flush(char *p)
+{
+ pr_info("entry-flush: disabled on command line.");
+ no_entry_flush = true;
+ return 0;
+}
+early_param("no_entry_flush", handle_no_entry_flush);
+
+static int __init handle_no_uaccess_flush(char *p)
+{
+ pr_info("uaccess-flush: disabled on command line.");
+ no_uaccess_flush = true;
+ return 0;
+}
+early_param("no_uaccess_flush", handle_no_uaccess_flush);
+
/*
* The RFI flush is not KPTI, but because users will see doco that says to use
* nopti we hijack that option here to also disable the RFI flush.
rfi_flush = enable;
}
+void entry_flush_enable(bool enable)
+{
+ if (enable) {
+ do_entry_flush_fixups(enabled_flush_types);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ do_entry_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ entry_flush = enable;
+}
+
+void uaccess_flush_enable(bool enable)
+{
+ if (enable) {
+ do_uaccess_flush_fixups(enabled_flush_types);
+ static_branch_enable(&uaccess_flush_key);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ static_branch_disable(&uaccess_flush_key);
+ do_uaccess_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ uaccess_flush = enable;
+}
+
static void __ref init_fallback_flush(void)
{
u64 l1d_size, limit;
enabled_flush_types = types;
- if (!no_rfi_flush && !cpu_mitigations_off())
+ if (!cpu_mitigations_off() && !no_rfi_flush)
rfi_flush_enable(enable);
}
+void setup_entry_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_entry_flush)
+ entry_flush_enable(enable);
+}
+
+void setup_uaccess_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_uaccess_flush)
+ uaccess_flush_enable(enable);
+}
+
#ifdef CONFIG_DEBUG_FS
static int rfi_flush_set(void *data, u64 val)
{
DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+static int entry_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != entry_flush)
+ entry_flush_enable(enable);
+
+ return 0;
+}
+
+static int entry_flush_get(void *data, u64 *val)
+{
+ *val = entry_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+
+static int uaccess_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != uaccess_flush)
+ uaccess_flush_enable(enable);
+
+ return 0;
+}
+
+static int uaccess_flush_get(void *data, u64 *val)
+{
+ *val = uaccess_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n");
+
static __init int rfi_flush_debugfs_init(void)
{
debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+ debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
+ debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
return 0;
}
device_initcall(rfi_flush_debugfs_init);
/* Activate a secondary processor. */
void start_secondary(void *unused)
{
- unsigned int cpu = smp_processor_id();
+ unsigned int cpu = raw_smp_processor_id();
mmgrab(&init_mm);
current->active_mm = &init_mm;
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
+ rcu_cpu_starting(cpu);
preempt_disable();
cpu_callin_map[cpu] = 1;
#include <linux/err.h>
#include <asm/asm-prototypes.h>
-#include <asm/book3s/64/kup-radix.h>
+#include <asm/kup.h>
#include <asm/cputime.h>
#include <asm/hw_irq.h>
#include <asm/kprobes.h>
__stop___stf_entry_barrier_fixup = .;
}
+ . = ALIGN(8);
+ __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) {
+ __start___uaccess_flush_fixup = .;
+ *(__uaccess_flush_fixup)
+ __stop___uaccess_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
+ __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
+ __start___entry_flush_fixup = .;
+ *(__entry_flush_fixup)
+ __stop___entry_flush_fixup = .;
+ }
+
. = ALIGN(8);
__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
__start___stf_exit_barrier_fixup = .;
static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu)
{
/* We have a block of xive->nr_servers VPs. We just need to check
- * raw vCPU ids are below the expected limit for this guest's
- * core stride ; kvmppc_pack_vcpu_id() will pack them down to an
- * index that can be safely used to compute a VP id that belongs
- * to the VP block.
+ * packed vCPU ids are below that.
*/
- return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode;
+ return kvmppc_pack_vcpu_id(xive->kvm, cpu) < xive->nr_servers;
}
int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp)
}
state = &sb->irq_state[src];
+
+ /* Some sanity checking */
+ if (!state->valid) {
+ pr_devel("%s: source %lx invalid !\n", __func__, irq);
+ return VM_FAULT_SIGBUS;
+ }
+
kvmppc_xive_select_irq(state, &hw_num, &xd);
arch_spin_lock(&sb->lock);
do_stf_exit_barrier_fixups(types);
}
+void do_uaccess_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[4], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___uaccess_flush_fixup);
+ end = PTRRELOC(&__stop___uaccess_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+ instrs[3] = 0x4e800020; /* blr */
+
+ i = 0;
+ if (types == L1D_FLUSH_FALLBACK) {
+ instrs[3] = 0x60000000; /* nop */
+ /* fallthrough to fallback flush */
+ }
+
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+
+ patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
+ patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+ patch_instruction((struct ppc_inst *)(dest + 3), ppc_inst(instrs[3]));
+ }
+
+ printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
+ (types == L1D_FLUSH_NONE) ? "no" :
+ (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" :
+ (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG)
+ ? "ori+mttrig type"
+ : "ori type" :
+ (types & L1D_FLUSH_MTTRIG) ? "mttrig type"
+ : "unknown");
+}
+
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[3], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___entry_flush_fixup);
+ end = PTRRELOC(&__stop___entry_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+
+ i = 0;
+ if (types == L1D_FLUSH_FALLBACK) {
+ instrs[i++] = 0x7d4802a6; /* mflr r10 */
+ instrs[i++] = 0x60000000; /* branch patched below */
+ instrs[i++] = 0x7d4803a6; /* mtlr r10 */
+ }
+
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+
+ if (types == L1D_FLUSH_FALLBACK)
+ patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback,
+ BRANCH_SET_LINK);
+ else
+ patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
+
+ patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+ }
+
+ printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
+ (types == L1D_FLUSH_NONE) ? "no" :
+ (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" :
+ (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG)
+ ? "ori+mttrig type"
+ : "ori type" :
+ (types & L1D_FLUSH_MTTRIG) ? "mttrig type"
+ : "unknown");
+}
+
void do_rfi_flush_fixups(enum l1d_flush_type types)
{
unsigned int instrs[3], *dest;
rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
- : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+ : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "i"(r)
: "memory");
}
asm volatile("ptesync": : :"memory");
/*
- * Flush the first set of the TLB, and any caching of partition table
- * entries. Then flush the remaining sets of the TLB. Hash mode uses
- * partition scoped TLB translations.
+ * Flush the partition table cache if this is HV mode.
*/
- tlbiel_hash_set_isa300(0, is, 0, 2, 0);
- for (set = 1; set < num_sets; set++)
- tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+ if (early_cpu_has_feature(CPU_FTR_HVMODE))
+ tlbiel_hash_set_isa300(0, is, 0, 2, 0);
/*
- * Now invalidate the process table cache.
+ * Now invalidate the process table cache. UPRT=0 HPT modes (what
+ * current hardware implements) do not use the process table, but
+ * add the flushes anyway.
*
* From ISA v3.0B p. 1078:
* The following forms are invalid.
*/
tlbiel_hash_set_isa300(0, is, 0, 2, 1);
+ /*
+ * Then flush the sets of the TLB proper. Hash mode uses
+ * partition scoped TLB translations, which may be flushed
+ * in !HV mode.
+ */
+ for (set = 0; set < num_sets; set++)
+ tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+
ppc_after_tlbiel_barrier();
asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/slab.h>
+#include <linux/cpu.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
isync();
}
#endif
+
+/**
+ * cleanup_cpu_mmu_context - Clean up MMU details for this CPU (newly offlined)
+ *
+ * This clears the CPU from mm_cpumask for all processes, and then flushes the
+ * local TLB to ensure TLB coherency in case the CPU is onlined again.
+ *
+ * KVM guest translations are not necessarily flushed here. If KVM started
+ * using mm_cpumask or the Linux APIs which do, this would have to be resolved.
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+void cleanup_cpu_mmu_context(void)
+{
+ int cpu = smp_processor_id();
+
+ clear_tasks_mm_cpumask(cpu);
+ tlbiel_all();
+}
+#endif
#include <asm/rtas.h>
#include <asm/kasan.h>
#include <asm/svm.h>
+#include <asm/mmzone.h>
#include <mm/mmu_decl.h>
of_node_put(cpu);
}
- if (likely(nid > 0))
- node_set_online(nid);
+ node_set_online(nid);
}
get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
/* If this is a valid record, create the sample */
struct perf_output_handle handle;
- if (perf_output_begin(&handle, event, header.size))
+ if (perf_output_begin(&handle, &data, event, header.size))
return;
perf_output_sample(&handle, &header, &data, event);
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
mpic_cpu_set_priority(0xf);
+ cleanup_cpu_mmu_context();
+
return 0;
}
security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
}
-static void pnv_setup_rfi_flush(void)
+static void pnv_setup_security_mitigations(void)
{
struct device_node *np, *fw_features;
enum l1d_flush_type type;
type = L1D_FLUSH_ORI;
}
+ /*
+ * If we are non-Power9 bare metal, we don't need to flush on kernel
+ * entry or after user access: they fix a P9 specific vulnerability.
+ */
+ if (!pvr_version_is(PVR_POWER9)) {
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
+ }
+
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
(security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \
security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
setup_rfi_flush(type, enable);
setup_count_cache_flush();
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+ setup_entry_flush(enable);
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+ setup_uaccess_flush(enable);
+
+ setup_stf_barrier();
}
static void __init pnv_check_guarded_cores(void)
{
set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
- pnv_setup_rfi_flush();
- setup_stf_barrier();
+ pnv_setup_security_mitigations();
/* Initialize SMP */
pnv_smp_init();
add_preferred_console("hvc", 0, NULL);
if (!radix_enabled()) {
+ size_t size = sizeof(struct slb_entry) * mmu_slb_size;
int i;
/* Allocate per cpu area to save old slb contents during MCE */
- for_each_possible_cpu(i)
- paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i));
+ for_each_possible_cpu(i) {
+ paca_ptrs[i]->mce_faulty_slbs =
+ memblock_alloc_node(size,
+ __alignof__(struct slb_entry),
+ cpu_to_node(i));
+ }
}
}
xive_smp_disable_cpu();
else
xics_migrate_irqs_away();
+
+ cleanup_cpu_mmu_context();
+
return 0;
}
xive_smp_disable_cpu();
else
xics_migrate_irqs_away();
+
+ cleanup_cpu_mmu_context();
+
return 0;
}
cpus_read_unlock();
- /* Possibly switch to a new RFI flush type */
- pseries_setup_rfi_flush();
+ /* Possibly switch to a new L1 flush type */
+ pseries_setup_security_mitigations();
/* Reinitialise system information for hv-24x7 */
read_24x7_sys_info();
return hwirq;
}
- virq = irq_create_mapping(NULL, hwirq);
+ virq = irq_create_mapping_affinity(NULL, hwirq,
+ entry->affinity);
if (!virq) {
pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);
int dlpar_workqueue_init(void);
-void pseries_setup_rfi_flush(void);
+void pseries_setup_security_mitigations(void);
void pseries_lpar_read_hblkrm_characteristics(void);
#endif /* _PSERIES_PSERIES_H */
security_ftr_clear(SEC_FTR_BNDS_CHK_SPEC_BAR);
}
-void pseries_setup_rfi_flush(void)
+void pseries_setup_security_mitigations(void)
{
struct h_cpu_char_result result;
enum l1d_flush_type types;
setup_rfi_flush(types, enable);
setup_count_cache_flush();
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+ setup_entry_flush(enable);
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+ setup_uaccess_flush(enable);
+
+ setup_stf_barrier();
}
#ifdef CONFIG_PCI_IOV
fwnmi_init();
- pseries_setup_rfi_flush();
- setup_stf_barrier();
+ pseries_setup_security_mitigations();
pseries_lpar_read_hblkrm_characteristics();
/* By default, only probe PCI (can be overridden by rtas_pci) */
#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 34
+
#endif /* _ASM_RISCV_PGTABLE_32_H */
do { \
long __kr_err; \
\
- __put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
+ __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
goto err_label; \
} while (0)
#ifndef __ASSEMBLY__
+#include <asm/barrier.h>
+
static inline void cpu_relax(void)
{
#ifdef __riscv_muldiv
-/* SPDX-License-Identifier: GPL-2.0 */
+// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2013 Linaro Limited
* Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
.word 0
#endif
.balign 8
+#ifdef CONFIG_RISCV_M_MODE
+ /* Image load offset (0MB) from start of RAM for M-mode */
+ .dword 0
+#else
#if __riscv_xlen == 64
/* Image load offset(2MB) from start of RAM */
.dword 0x200000
#else
/* Image load offset(4MB) from start of RAM */
.dword 0x400000
+#endif
#endif
/* Effective size of kernel image */
.dword _end - _start
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
void arch_cpu_idle(void)
{
wait_for_interrupt();
- local_irq_enable();
+ raw_local_irq_enable();
}
void show_regs(struct pt_regs *regs)
*cmdline_p = boot_command_line;
early_ioremap_setup();
+ jump_label_init();
parse_early_param();
efi_init();
# SPDX-License-Identifier: GPL-2.0-only
vdso.lds
*.tmp
+vdso-syms.S
SYSCFLAGS_vdso.so.dbg = $(c_flags)
$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE
$(call if_changed,vdsold)
+SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
+ -Wl,--build-id=sha1 -Wl,--hash-style=both
# We also create a special relocatable object that should mirror the symbol
# table and layout of the linked DSO. With ld --just-symbols we can then
# refer to these symbols in the kernel code rather than hand-coded addresses.
-
-SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
- -Wl,--build-id=sha1 -Wl,--hash-style=both
-$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
- $(call if_changed,vdsold)
-
-LDFLAGS_vdso-syms.o := -r --just-symbols
-$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE
- $(call if_changed,ld)
+$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE
+ $(call if_changed,so2s)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
$(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \
rm $@.tmp
+# Extracts symbol offsets from the VDSO, converting them into an assembly file
+# that contains the same symbols at the same offsets.
+quiet_cmd_so2s = SO2S $@
+ cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@
+
# install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com>
+
+sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \
+| grep '^\.'
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
int index;
+ unsigned long pfn;
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs))
* of a task switch.
*/
index = pgd_index(addr);
- pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
+ pfn = csr_read(CSR_SATP) & SATP_PPN;
+ pgd = (pgd_t *)pfn_to_virt(pfn) + index;
pgd_k = init_mm.pgd + index;
if (!pgd_present(*pgd_k)) {
void __init setup_bootmem(void)
{
- phys_addr_t mem_size = 0;
- phys_addr_t total_mem = 0;
- phys_addr_t mem_start, start, end = 0;
+ phys_addr_t mem_start = 0;
+ phys_addr_t start, end = 0;
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
u64 i;
/* Find the memory region containing the kernel */
for_each_mem_range(i, &start, &end) {
phys_addr_t size = end - start;
- if (!total_mem)
+ if (!mem_start)
mem_start = start;
if (start <= vmlinux_start && vmlinux_end <= end)
BUG_ON(size == 0);
- total_mem = total_mem + size;
}
/*
- * Remove memblock from the end of usable area to the
- * end of region
+ * The maximal physical memory size is -PAGE_OFFSET.
+ * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed
+ * as it is unusable by kernel.
*/
- mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
- if (mem_start + mem_size < end)
- memblock_remove(mem_start + mem_size,
- end - mem_start - mem_size);
+ memblock_enforce_memory_limit(mem_start - PAGE_OFFSET);
/* Reserve from the start of the kernel to the end of the kernel */
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
#define NUM_EARLY_PMDS (1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE)
#endif
pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE);
+pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);
static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
{
load_pa + (va - PAGE_OFFSET),
map_size, PAGE_KERNEL_EXEC);
+#ifndef __PAGETABLE_PMD_FOLDED
+ /* Setup early PMD for DTB */
+ create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
+ (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE);
+ /* Create two consecutive PMD mappings for FDT early scan */
+ pa = dtb_pa & ~(PMD_SIZE - 1);
+ create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
+ pa, PMD_SIZE, PAGE_KERNEL);
+ create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
+ pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
+ dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
+#else
/* Create two consecutive PGD mappings for FDT early scan */
pa = dtb_pa & ~(PGDIR_SIZE - 1);
create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE,
pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL);
dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1));
+#endif
dtb_early_pa = dtb_pa;
/*
+CONFIG_UAPI_HEADER_TEST=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_WATCH_QUEUE=y
CONFIG_FRONTSWAP=y
CONFIG_CMA_DEBUG=y
CONFIG_CMA_DEBUGFS=y
+CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
CONFIG_PCI=y
# CONFIG_PCIEASPM is not set
CONFIG_PCI_DEBUG=y
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
CONFIG_CRYPTO_GCM=y
CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_CORDIC=m
CONFIG_CRC32_SELFTEST=y
CONFIG_CRC4=m
CONFIG_FAULT_INJECTION=y
CONFIG_FAILSLAB=y
CONFIG_FAIL_PAGE_ALLOC=y
+CONFIG_FAULT_INJECTION_USERCOPY=y
CONFIG_FAIL_MAKE_REQUEST=y
CONFIG_FAIL_IO_TIMEOUT=y
CONFIG_FAIL_FUTEX=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
+CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
-CONFIG_ZSMALLOC=m
+CONFIG_ZSMALLOC=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
-# CONFIG_NET_DROP_MONITOR is not set
CONFIG_PCI=y
# CONFIG_PCIEASPM is not set
CONFIG_HOTPLUG_PCI=y
CONFIG_UEVENT_HELPER=y
CONFIG_DEVTMPFS=y
CONFIG_CONNECTOR=y
-CONFIG_ZRAM=m
+CONFIG_ZRAM=y
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_DRBD=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
CONFIG_CRYPTO_GCM=y
CONFIG_CRYPTO_CHACHA20POLY1305=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CRYPTO_DEV_VIRTIO=m
CONFIG_CORDIC=m
CONFIG_PRIME_NUMBERS=m
CONFIG_CRC4=m
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
CONFIG_CRASH_DUMP=y
-# CONFIG_SECCOMP is not set
# CONFIG_PFAULT is not set
# CONFIG_S390_HYPFS_FS is not set
# CONFIG_VIRTUALIZATION is not set
# CONFIG_S390_GUEST is not set
+# CONFIG_SECCOMP is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
return !!(pud_val(pud) & _REGION3_ENTRY_LARGE);
}
-static inline unsigned long pud_pfn(pud_t pud)
-{
- unsigned long origin_mask;
-
- origin_mask = _REGION_ENTRY_ORIGIN;
- if (pud_large(pud))
- origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
- return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
-}
-
#define pmd_leaf pmd_large
static inline int pmd_large(pmd_t pmd)
{
return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY;
}
-static inline unsigned long pmd_pfn(pmd_t pmd)
-{
- unsigned long origin_mask;
-
- origin_mask = _SEGMENT_ENTRY_ORIGIN;
- if (pmd_large(pmd))
- origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
- return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT;
-}
-
#define pmd_write pmd_write
static inline int pmd_write(pmd_t pmd)
{
#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
-#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
#define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
#define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
+static inline unsigned long pmd_deref(pmd_t pmd)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _SEGMENT_ENTRY_ORIGIN;
+ if (pmd_large(pmd))
+ origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE;
+ return pmd_val(pmd) & origin_mask;
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+ return pmd_deref(pmd) >> PAGE_SHIFT;
+}
+
+static inline unsigned long pud_deref(pud_t pud)
+{
+ unsigned long origin_mask;
+
+ origin_mask = _REGION_ENTRY_ORIGIN;
+ if (pud_large(pud))
+ origin_mask = _REGION3_ENTRY_ORIGIN_LARGE;
+ return pud_val(pud) & origin_mask;
+}
+
+static inline unsigned long pud_pfn(pud_t pud)
+{
+ return pud_deref(pud) >> PAGE_SHIFT;
+}
+
/*
* The pgd_offset function *always* adds the index for the top-level
* region/segment table. This is done to get a sequence like the
* final .boot.data section, which should be identical in the decompressor and
* the decompressed kernel (that is checked during the build).
*/
-#define __bootdata(var) __section(".boot.data.var") var
+#define __bootdata(var) __section(".boot.data." #var) var
/*
* .boot.preserved.data is similar to .boot.data, but it is not part of the
* .init section and thus will be preserved for later use in the decompressed
* kernel.
*/
-#define __bootdata_preserved(var) __section(".boot.preserved.data.var") var
+#define __bootdata_preserved(var) __section(".boot.preserved.data." #var) var
extern unsigned long __sdma, __edma;
extern unsigned long __stext_dma, __etext_dma;
/* stack_frame offsets */
OFFSET(__SF_BACKCHAIN, stack_frame, back_chain);
OFFSET(__SF_GPRS, stack_frame, gprs);
- OFFSET(__SF_EMPTY, stack_frame, empty1);
- OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[0]);
- OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[1]);
- OFFSET(__SF_SIE_REASON, stack_frame, empty1[2]);
- OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[3]);
+ OFFSET(__SF_EMPTY, stack_frame, empty1[0]);
+ OFFSET(__SF_SIE_CONTROL, stack_frame, empty1[1]);
+ OFFSET(__SF_SIE_SAVEAREA, stack_frame, empty1[2]);
+ OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]);
+ OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]);
BLANK();
OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
BLANK();
- /* constants used by the vdso */
- DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME);
- DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC);
- DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
- DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
- DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
- DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
- BLANK();
/* idle data offsets */
OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit);
#endif
LOCKDEP_SYS_EXIT
.Lsysc_tif:
+ DISABLE_INTS
TSTMSK __PT_FLAGS(%r11),_PIF_WORK
jnz .Lsysc_work
TSTMSK __TI_flags(%r12),_TIF_WORK
# One of the work bits is on. Find out which one.
#
.Lsysc_work:
+ ENABLE_INTS
TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED
jo .Lsysc_reschedule
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
jo .Lio_restore
-#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS)
- tmhh %r8,0x300
- jz 1f
TRACE_IRQS_OFF
-1:
-#endif
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
.Lio_loop:
lgr %r2,%r11 # pass pointer to pt_regs
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lio_work
.Lio_restore:
-#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS)
- tm __PT_PSW(%r11),3
- jno 0f
TRACE_IRQS_ON
-0:
-#endif
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lio_exit_kernel
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
jo .Lio_restore
-#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS)
- tmhh %r8,0x300
- jz 1f
TRACE_IRQS_OFF
-1:
-#endif
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
lghi %r3,EXT_INTERRUPT
* %r4
*/
load_fpu_regs:
+ stnsm __SF_EMPTY(%r15),0xfc
lg %r4,__LC_CURRENT
aghi %r4,__TASK_thread
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
.Lload_fpu_regs_done:
ni __LC_CPU_FLAGS+7,255-_CIF_FPU
.Lload_fpu_regs_exit:
+ ssm __SF_EMPTY(%r15)
BR_EX %r14
.Lload_fpu_regs_end:
ENDPROC(load_fpu_regs)
PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
clear_cpu_flag(CIF_NOHZ_DELAY);
- local_irq_save(flags);
+ raw_local_irq_save(flags);
/* Call the assembler magic in entry.S */
psw_idle(idle, psw_mask);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
/* Account time spent with enabled wait psw loaded as idle time. */
raw_write_seqcount_begin(&idle->seqcount);
void arch_cpu_idle(void)
{
enabled_wait();
- local_irq_enable();
+ raw_local_irq_enable();
}
void arch_cpu_idle_exit(void)
rcu_read_lock();
perf_prepare_sample(&header, data, event, regs);
- if (perf_output_begin(&handle, event, header.size))
+ if (perf_output_begin(&handle, data, event, header.size))
goto out;
/* Update the process ID (see also kernel/events/core.c) */
}
arch_initcall(init_cpum_sampling_pmu);
-core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644);
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
/*
* Use the regs from the first interruption and let
static void smp_init_secondary(void)
{
- int cpu = smp_processor_id();
+ int cpu = raw_smp_processor_id();
S390_lowcore.last_update_clock = get_tod_clock();
restore_access_regs(S390_lowcore.access_regs_save_area);
set_cpu_flag(CIF_ASCE_PRIMARY);
set_cpu_flag(CIF_ASCE_SECONDARY);
cpu_init();
+ rcu_cpu_starting(cpu);
preempt_disable();
init_cpu_timer();
vtime_init();
.paddr = paddr
};
- if (uv_call(0, (u64)&uvcb))
+ if (uv_call(0, (u64)&uvcb)) {
+ /*
+ * Older firmware uses 107/d as an indication of a non secure
+ * page. Let us emulate the newer variant (no-op).
+ */
+ if (uvcb.header.rc == 0x107 && uvcb.header.rrc == 0xd)
+ return 0;
return -EINVAL;
+ }
return 0;
}
struct kvm_s390_pv_unp unp = {};
r = -EINVAL;
- if (!kvm_s390_pv_is_protected(kvm))
+ if (!kvm_s390_pv_is_protected(kvm) || !mm_is_protected(kvm->mm))
break;
r = -EFAULT;
vcpu->arch.sie_block->pp = 0;
vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
vcpu->arch.sie_block->todpr = 0;
- vcpu->arch.sie_block->cpnc = 0;
}
}
regs->etoken = 0;
regs->etoken_extension = 0;
- regs->diag318 = 0;
}
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
return -EIO;
}
kvm->arch.gmap->guest_handle = uvcb.guest_handle;
- atomic_set(&kvm->mm->context.is_protected, 1);
return 0;
}
*rrc = uvcb.header.rrc;
KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x",
*rc, *rrc);
+ if (!cc)
+ atomic_set(&kvm->mm->context.is_protected, 1);
return cc ? -EINVAL : 0;
}
static void __udelay_disabled(unsigned long long usecs)
{
- unsigned long cr0, cr0_new, psw_mask, flags;
+ unsigned long cr0, cr0_new, psw_mask;
struct s390_idle_data idle;
u64 end;
psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT;
set_clock_comparator(end);
set_cpu_flag(CIF_IGNORE_IRQ);
- local_irq_save(flags);
psw_idle(&idle, psw_mask);
- local_irq_restore(flags);
+ trace_hardirqs_off();
clear_cpu_flag(CIF_IGNORE_IRQ);
set_clock_comparator(S390_lowcore.clock_comparator);
__ctl_load(cr0, 0, 0);
#include <linux/sched/mm.h>
void s390_reset_acc(struct mm_struct *mm)
{
+ if (!mm_is_protected(mm))
+ return;
/*
* we might be called during
* reset: we walk the pages and clear
if (ret)
break;
+ /* the PCI function will be scanned once function 0 appears */
+ if (!zdev->zbus->bus)
+ break;
+
pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn);
if (!pdev)
break;
{
struct msi_desc *entry = irq_get_msi_desc(data->irq);
struct msi_msg msg = entry->msg;
+ int cpu_addr = smp_cpu_get_cpu_address(cpumask_first(dest));
msg.address_lo &= 0xff0000ff;
- msg.address_lo |= (cpumask_first(dest) << 8);
+ msg.address_lo |= (cpu_addr << 8);
pci_write_msi_msg(data->irq, &msg);
return IRQ_SET_MASK_OK;
unsigned long bit;
struct msi_desc *msi;
struct msi_msg msg;
+ int cpu_addr;
int rc, irq;
zdev->aisb = -1UL;
handle_percpu_irq);
msg.data = hwirq - bit;
if (irq_delivery == DIRECTED) {
+ if (msi->affinity)
+ cpu = cpumask_first(&msi->affinity->mask);
+ else
+ cpu = 0;
+ cpu_addr = smp_cpu_get_cpu_address(cpu);
+
msg.address_lo = zdev->msi_addr & 0xff0000ff;
- msg.address_lo |= msi->affinity ?
- (cpumask_first(&msi->affinity->mask) << 8) : 0;
+ msg.address_lo |= (cpu_addr << 8);
+
for_each_possible_cpu(cpu) {
airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
}
void default_idle(void)
{
set_bl_bit();
- local_irq_enable();
+ raw_local_irq_enable();
/* Isn't this racy ? */
cpu_sleep();
clear_bl_bit();
register unsigned int address = (unsigned int)leon3_irqctrl_regs;
/* Interrupts need to be enabled to not hang the CPU */
- local_irq_enable();
+ raw_local_irq_enable();
__asm__ __volatile__ (
"wr %%g0, %%asr19\n"
static void pmc_leon_idle(void)
{
/* Interrupts need to be enabled to not hang the CPU */
- local_irq_enable();
+ raw_local_irq_enable();
/* For systems without power-down, this will be no-op */
__asm__ __volatile__ ("wr %g0, %asr19\n\t");
{
if (sparc_idle)
(*sparc_idle)();
- local_irq_enable();
+ raw_local_irq_enable();
}
/* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */
{
if (tlb_type != hypervisor) {
touch_nmi_watchdog();
- local_irq_enable();
+ raw_local_irq_enable();
} else {
unsigned long pstate;
- local_irq_enable();
+ raw_local_irq_enable();
/* The sun4v sleeping code requires that we have PSTATE.IE cleared over
* the cpu sleep hypervisor call.
} while (0)
#ifdef CONFIG_3_LEVEL_PGTABLES
-#define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x))
+
+#define __pmd_free_tlb(tlb, pmd, address) \
+do { \
+ pgtable_pmd_page_dtor(virt_to_page(pmd)); \
+ tlb_remove_page((tlb),virt_to_page(pmd)); \
+} while (0) \
+
#endif
#endif
{
cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
um_idle_sleep();
- local_irq_enable();
+ raw_local_irq_enable();
}
int __cant_sleep(void) {
* on some systems.
*/
-void __section(".__syscall_stub")
+void __attribute__ ((__section__ (".__syscall_stub")))
stub_clone_handler(void)
{
struct stub_data *data = (struct stub_data *) STUB_DATA;
select ARCH_WANT_DEFAULT_BPF_JIT if X86_64
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANT_HUGE_PMD_SHARE
+ select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANTS_THP_SWAP if X86_64
select BUILDTIME_TABLE_SORT
select CLKEVT_I8253
LDFLAGS_vmlinux += -z max-page-size=0x200000
endif
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
# Compressed kernel should be built as PIE since it may be loaded at any
# address by the bootloader.
LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker)
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+ifdef CONFIG_LD_ORPHAN_WARN
+LDFLAGS_vmlinux += --orphan-handling=warn
+endif
LDFLAGS_vmlinux += -T
hostprogs := mkpiggy
add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
/* Load the new page-table. */
+ sev_verify_cbit(top_level_pgt);
write_cr3(top_level_pgt);
}
SYM_FUNC_END(get_sev_encryption_bit)
.code64
+
+#include "../../kernel/sev_verify_cbit.S"
+
SYM_FUNC_START(set_sev_encryption_mask)
#ifdef CONFIG_AMD_MEM_ENCRYPT
push %rbp
bts %rax, sme_me_mask(%rip) /* Create the encryption mask */
+ /*
+ * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in
+ * get_sev_encryption_bit() because this function is 32-bit code and
+ * shared between 64-bit and 32-bit boot path.
+ */
+ movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */
+ rdmsr
+
+ /* Store MSR value in sev_status */
+ shlq $32, %rdx
+ orq %rdx, %rax
+ movq %rax, sev_status(%rip)
+
.Lno_sev_mask:
movq %rbp, %rsp /* Restore original stack pointer */
#ifdef CONFIG_AMD_MEM_ENCRYPT
.balign 8
-SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sme_me_mask, .quad 0)
+SYM_DATA(sev_status, .quad 0)
+SYM_DATA(sev_check_data, .quad 0)
#endif
void boot_stage1_vc(void);
void boot_stage2_vc(void);
+unsigned long sev_verify_cbit(unsigned long cr3);
+
#endif /* BOOT_COMPRESSED_MISC_H */
*/
static bool insn_has_rep_prefix(struct insn *insn)
{
+ insn_byte_t p;
int i;
insn_get_prefixes(insn);
- for (i = 0; i < insn->prefixes.nbytes; i++) {
- insn_byte_t p = insn->prefixes.bytes[i];
-
+ for_each_insn_prefix(insn, i, p) {
if (p == 0xf2 || p == 0xf3)
return true;
}
dctx->s[1] = get_unaligned_le32(&inp[4]);
dctx->s[2] = get_unaligned_le32(&inp[8]);
dctx->s[3] = get_unaligned_le32(&inp[12]);
+ acc += POLY1305_BLOCK_SIZE;
dctx->sset = true;
}
}
440 common process_madvise sys_process_madvise
#
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64. These syscalls have numbers 512-547.
+# Do not add new syscalls to this range. Numbers 548 and above are available
+# for non-x32 use.
#
512 x32 rt_sigaction compat_sys_rt_sigaction
513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn
545 x32 execveat compat_sys_execveat
546 x32 preadv2 compat_sys_preadv64v2
547 x32 pwritev2 compat_sys_pwritev64v2
+# This is the end of the legacy x32 range. Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
u64 pebs_enabled = cpuc->pebs_enabled;
handled++;
- x86_pmu.drain_pebs(regs);
+ x86_pmu.drain_pebs(regs, &data);
status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
/*
x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
+ if (version >= 5) {
+ x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated;
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ pr_cont(" AnyThread deprecated, ");
+ }
+
/*
* Install the hw-cache-events table:
*/
x86_pmu.intel_ctrl |=
((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+ /* AnyThread may be deprecated on arch perfmon v5 or later */
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ x86_pmu.format_attrs = intel_arch_formats_attr;
+
if (x86_pmu.event_constraints) {
/*
* event on fixed counter2 (REF_CYCLES) only works on this
MODULE_LICENSE("GPL");
#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \
-static ssize_t __cstate_##_var##_show(struct kobject *kobj, \
- struct kobj_attribute *attr, \
+static ssize_t __cstate_##_var##_show(struct device *dev, \
+ struct device_attribute *attr, \
char *page) \
{ \
BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
return sprintf(page, _format "\n"); \
} \
-static struct kobj_attribute format_attr_##_var = \
+static struct device_attribute format_attr_##_var = \
__ATTR(_name, 0444, __cstate_##_var##_show, NULL)
static ssize_t cstate_get_attr_cpumask(struct device *dev,
rcu_read_lock();
perf_prepare_sample(&header, &data, event, ®s);
- if (perf_output_begin(&handle, event, header.size *
- (top - base - skip)))
+ if (perf_output_begin(&handle, &data, event,
+ header.size * (top - base - skip)))
goto unlock;
for (at = base; at < top; at++) {
static inline void intel_pmu_drain_pebs_buffer(void)
{
- x86_pmu.drain_pebs(NULL);
+ struct perf_sample_data data;
+
+ x86_pmu.drain_pebs(NULL, &data);
}
/*
return 0;
}
-static void __intel_pmu_pebs_event(struct perf_event *event,
- struct pt_regs *iregs,
- void *base, void *top,
- int bit, int count,
- void (*setup_sample)(struct perf_event *,
- struct pt_regs *,
- void *,
- struct perf_sample_data *,
- struct pt_regs *))
+static __always_inline void
+__intel_pmu_pebs_event(struct perf_event *event,
+ struct pt_regs *iregs,
+ struct perf_sample_data *data,
+ void *base, void *top,
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- struct perf_sample_data data;
struct x86_perf_regs perf_regs;
struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
- struct pt_regs dummy_iregs;
+ static struct pt_regs dummy_iregs;
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
/*
iregs = &dummy_iregs;
while (count > 1) {
- setup_sample(event, iregs, at, &data, regs);
- perf_event_output(event, &data, regs);
+ setup_sample(event, iregs, at, data, regs);
+ perf_event_output(event, data, regs);
at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_sample(event, iregs, at, &data, regs);
+ setup_sample(event, iregs, at, data, regs);
if (iregs == &dummy_iregs) {
/*
* The PEBS records may be drained in the non-overflow context,
* last record the same as other PEBS records, and doesn't
* invoke the generic overflow handler.
*/
- perf_event_output(event, &data, regs);
+ perf_event_output(event, data, regs);
} else {
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, regs))
+ if (perf_event_overflow(event, data, regs))
x86_pmu_stop(event, 0);
}
}
-static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
setup_pebs_fixed_sample_data);
}
}
}
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
* that caused the PEBS record. It's called collision.
* If collision happened, the record will be dropped.
*/
- if (p->status != (1ULL << bit)) {
+ if (pebs_status != (1ULL << bit)) {
for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
if (error[bit]) {
perf_log_lost_samples(event, error[bit]);
- if (perf_event_account_interrupt(event))
+ if (iregs && perf_event_account_interrupt(event))
x86_pmu_stop(event, 0);
}
if (counts[bit]) {
- __intel_pmu_pebs_event(event, iregs, base,
+ __intel_pmu_pebs_event(event, iregs, data, base,
top, bit, counts[bit],
setup_pebs_fixed_sample_data);
}
}
}
-static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
{
short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (WARN_ON_ONCE(!event->attr.precise_ip))
continue;
- __intel_pmu_pebs_event(event, iregs, base,
+ __intel_pmu_pebs_event(event, iregs, data, base,
top, bit, counts[bit],
setup_pebs_adaptive_sample_data);
}
return map;
}
-ssize_t uncore_event_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
+ssize_t uncore_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
struct uncore_event_desc *event =
container_of(attr, struct uncore_event_desc, attr);
#define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS 2
struct uncore_event_desc {
- struct kobj_attribute attr;
+ struct device_attribute attr;
const char *config;
};
struct pci2phy_map *__find_pci2phy_map(int segment);
int uncore_pcibus_to_physid(struct pci_bus *bus);
-ssize_t uncore_event_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf);
+ssize_t uncore_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf);
static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev)
{
}
#define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format) \
-static ssize_t __uncore_##_var##_show(struct kobject *kobj, \
- struct kobj_attribute *attr, \
+static ssize_t __uncore_##_var##_show(struct device *dev, \
+ struct device_attribute *attr, \
char *page) \
{ \
BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
return sprintf(page, _format "\n"); \
} \
-static struct kobj_attribute format_attr_##_var = \
+static struct device_attribute format_attr_##_var = \
__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
static inline bool uncore_pmc_fixed(int idx)
static struct freerunning_counters snb_uncore_imc_freerunning[] = {
[SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
0x0, 0x0, 1, 32 },
- [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
+ [SNB_PCI_UNCORE_IMC_DATA_WRITES] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE,
0x0, 0x0, 1, 32 },
[SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE,
0x0, 0x0, 1, 32 },
u64 pebs_baseline:1;
u64 perf_metrics:1;
u64 pebs_output_pt_available:1;
+ u64 anythread_deprecated:1;
};
u64 capabilities;
};
int pebs_record_size;
int pebs_buffer_size;
int max_pebs_events;
- void (*drain_pebs)(struct pt_regs *regs);
+ void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
unsigned long large_pebs_flags;
* any other bit is reserved
*/
#define RAPL_EVENT_MASK 0xFFULL
-
-#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \
-static ssize_t __rapl_##_var##_show(struct kobject *kobj, \
- struct kobj_attribute *attr, \
- char *page) \
-{ \
- BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
- return sprintf(page, _format "\n"); \
-} \
-static struct kobj_attribute format_attr_##_var = \
- __ATTR(_name, 0444, __rapl_##_var##_show, NULL)
-
#define RAPL_CNTR_WIDTH 32
#define RAPL_EVENT_ATTR_STR(_name, v, str) \
.attrs = attrs_empty,
};
-DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+PMU_FORMAT_ATTR(event, "config:0-7");
static struct attribute *rapl_formats_attr[] = {
&format_attr_event.attr,
NULL,
pr_info("Hyper-V: Using enlightened APIC (%s mode)",
x2apic_enabled() ? "x2apic" : "xapic");
/*
- * With x2apic, architectural x2apic MSRs are equivalent to the
- * respective synthetic MSRs, so there's no need to override
- * the apic accessors. The only exception is
- * hv_apic_eoi_write, because it benefits from lazy EOI when
- * available, but it works for both xapic and x2apic modes.
+ * When in x2apic mode, don't use the Hyper-V specific APIC
+ * accessors since the field layout in the ICR register is
+ * different in x2apic mode. Furthermore, the architectural
+ * x2apic MSRs function just as well as the Hyper-V
+ * synthetic APIC MSRs, so there's no benefit in having
+ * separate Hyper-V accessors for x2apic mode. The only
+ * exception is hv_apic_eoi_write, because it benefits from
+ * lazy EOI when available, but the same accessor works for
+ * both xapic and x2apic because the field layout is the same.
*/
apic_set_eoi_write(hv_apic_eoi_write);
if (!x2apic_enabled()) {
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+/**
+ * for_each_insn_prefix() -- Iterate prefixes in the instruction
+ * @insn: Pointer to struct insn.
+ * @idx: Index storage.
+ * @prefix: Prefix byte.
+ *
+ * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
+ * and the index is stored in @idx (note that this @idx is just for a cursor,
+ * do not change it.)
+ * Since prefixes.nbytes can be bigger than 4 if some prefixes
+ * are repeated, it cannot be used for looping over the prefixes.
+ */
+#define for_each_insn_prefix(insn, idx, prefix) \
+ for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+
#define POP_SS_OPCODE 0x1f
#define MOV_SREG_OPCODE 0x8e
int cpuid_nent;
struct kvm_cpuid_entry2 *cpuid_entries;
+ unsigned long cr3_lm_rsvd_bits;
int maxphyaddr;
int max_tdp_level;
int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_extint(struct kvm_vcpu *v);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
{
- trace_hardirqs_on();
-
mds_idle_clear_cpu_buffers();
/* "mwait %eax, %ecx;" */
asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
struct {
unsigned int num_counters_fixed:5;
unsigned int bit_width_fixed:8;
- unsigned int reserved:19;
+ unsigned int reserved1:2;
+ unsigned int anythread_deprecated:1;
+ unsigned int reserved2:16;
} split;
unsigned int full;
};
#endif
#endif /* CONFIG_SPARSEMEM */
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+extern int phys_to_target_node(phys_addr_t start);
+#define phys_to_target_node phys_to_target_node
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_SPARSEMEM_H */
#ifndef _ASM_X86_UV_UV_H
#define _ASM_X86_UV_UV_H
-#include <asm/tlbflush.h>
-
enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC};
-struct cpumask;
-struct mm_struct;
-struct flush_tlb_info;
-
#ifdef CONFIG_X86_UV
#include <linux/efi.h>
static inline int is_uv_hubbed(int uv) { return 0; }
static inline void uv_cpu_init(void) { }
static inline void uv_system_init(void) { }
-static inline const struct cpumask *
-uv_flush_tlb_others(const struct cpumask *cpumask,
- const struct flush_tlb_info *info)
-{ return cpumask; }
#endif /* X86_UV */
#define KVM_FEATURE_POLL_CONTROL 12
#define KVM_FEATURE_PV_SCHED_YIELD 13
#define KVM_FEATURE_ASYNC_PF_INT 14
+#define KVM_FEATURE_MSI_EXT_DEST_ID 15
#define KVM_HINTS_REALTIME 0
temp_mm_state_t temp_state;
lockdep_assert_irqs_disabled();
+
+ /*
+ * Make sure not to be in TLB lazy mode, as otherwise we'll end up
+ * with a stale address space WITHOUT being in lazy mode after
+ * restoring the previous mm.
+ */
+ if (this_cpu_read(cpu_tlbstate.is_lazy))
+ leave_mm(smp_processor_id());
+
temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
switch_mm_irqs_off(NULL, mm, current);
static int uv_node_id;
/* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */
-static u8 uv_archtype[UV_AT_SIZE];
+static u8 uv_archtype[UV_AT_SIZE + 1];
static u8 oem_id[ACPI_OEM_ID_SIZE + 1];
static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
/* UV4/4A only have a revision difference */
case UV4_HUB_PART_NUMBER:
uv_min_hub_revision_id = node_id.s.revision
- + UV4_HUB_REVISION_BASE;
+ + UV4_HUB_REVISION_BASE - 1;
uv_hub_type_set(UV4);
if (uv_min_hub_revision_id == UV4A_HUB_REVISION_BASE)
uv_hub_type_set(UV4|UV4A);
{
/* Relies on 'to' being NULL chars so result will be NULL terminated */
strncpy(to, from, len-1);
+
+ /* Trim trailing spaces */
+ (void)strim(to);
}
/* Find UV arch type entry in UVsystab */
if (n > 0 && n < sizeof(uv_ate->archtype)) {
pr_info("UV: UVarchtype received from BIOS\n");
- uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype);
+ uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype);
return 1;
}
return 0;
return ret;
}
-static int __init uv_set_system_type(char *_oem_id)
+static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id)
{
/* Save OEM_ID passed from ACPI MADT */
uv_stringify(sizeof(oem_id), oem_id, _oem_id);
if (!early_get_arch_type())
/* If not use OEM ID for UVarchtype */
- uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id);
+ uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id);
/* Check if not hubbed */
if (strncmp(uv_archtype, "SGI", 3) != 0) {
/* (Not hubless), not a UV */
return 0;
+ /* Is UV hubless system */
+ uv_hubless_system = 0x01;
+
+ /* UV5 Hubless */
+ if (strncmp(uv_archtype, "NSGI5", 5) == 0)
+ uv_hubless_system |= 0x20;
+
/* UV4 Hubless: CH */
- if (strncmp(uv_archtype, "NSGI4", 5) == 0)
- uv_hubless_system = 0x11;
+ else if (strncmp(uv_archtype, "NSGI4", 5) == 0)
+ uv_hubless_system |= 0x10;
/* UV3 Hubless: UV300/MC990X w/o hub */
else
- uv_hubless_system = 0x9;
+ uv_hubless_system |= 0x8;
+
+ /* Copy APIC type */
+ uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n",
oem_id, oem_table_id, uv_system_type, uv_hubless_system);
uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
/* If not UV, return. */
- if (likely(uv_set_system_type(_oem_id) == 0))
+ if (uv_set_system_type(_oem_id, _oem_table_id) == 0)
return 0;
/* Save and Decode OEM Table ID */
if (boot_cpu_has(X86_FEATURE_IBPB)) {
setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
+ spectre_v2_user_ibpb = mode;
switch (cmd) {
case SPECTRE_V2_USER_CMD_FORCE:
case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
static_branch_enable(&switch_mm_always_ibpb);
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
break;
case SPECTRE_V2_USER_CMD_PRCTL:
case SPECTRE_V2_USER_CMD_AUTO:
pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
static_key_enabled(&switch_mm_always_ibpb) ?
"always-on" : "conditional");
-
- spectre_v2_user_ibpb = mode;
}
/*
return 0;
}
+static bool is_spec_ib_user_controlled(void)
+{
+ return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
+ spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP;
+}
+
static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
{
switch (ctrl) {
if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
return 0;
+
/*
- * Indirect branch speculation is always disabled in strict
- * mode. It can neither be enabled if it was force-disabled
- * by a previous prctl call.
+ * With strict mode for both IBPB and STIBP, the instruction
+ * code paths avoid checking this task flag and instead,
+ * unconditionally run the instruction. However, STIBP and IBPB
+ * are independent and either can be set to conditionally
+ * enabled regardless of the mode of the other.
+ *
+ * If either is set to conditional, allow the task flag to be
+ * updated, unless it was force-disabled by a previous prctl
+ * call. Currently, this is possible on an AMD CPU which has the
+ * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the
+ * kernel is booted with 'spectre_v2_user=seccomp', then
+ * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and
+ * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED.
*/
- if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+ if (!is_spec_ib_user_controlled() ||
task_spec_ib_force_disable(task))
return -EPERM;
+
task_clear_spec_ib_disable(task);
task_update_spec_tif(task);
break;
if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
return -EPERM;
- if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+
+ if (!is_spec_ib_user_controlled())
return 0;
+
task_set_spec_ib_disable(task);
if (ctrl == PR_SPEC_FORCE_DISABLE)
task_set_spec_ib_force_disable(task);
if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE &&
spectre_v2_user_stibp == SPECTRE_V2_USER_NONE)
return PR_SPEC_ENABLE;
- else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
- return PR_SPEC_DISABLE;
- else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL ||
- spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
- spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) {
+ else if (is_spec_ib_user_controlled()) {
if (task_spec_ib_force_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE;
if (task_spec_ib_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
- } else
+ } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED)
+ return PR_SPEC_DISABLE;
+ else
return PR_SPEC_NOT_AFFECTED;
}
* When there's any problem use only local no_way_out state.
*/
if (!lmce) {
- if (mce_end(order) < 0)
- no_way_out = worst >= MCE_PANIC_SEVERITY;
+ if (mce_end(order) < 0) {
+ if (!no_way_out)
+ no_way_out = worst >= MCE_PANIC_SEVERITY;
+ }
} else {
/*
* If there was a fatal machine check we should have
return find_matching_signature(mc, csig, cpf);
}
-/*
- * Given CPU signature and a microcode patch, this function finds if the
- * microcode patch has matching family and model with the CPU.
- *
- * %true - if there's a match
- * %false - otherwise
- */
-static bool microcode_matches(struct microcode_header_intel *mc_header,
- unsigned long sig)
-{
- unsigned long total_size = get_totalsize(mc_header);
- unsigned long data_size = get_datasize(mc_header);
- struct extended_sigtable *ext_header;
- unsigned int fam_ucode, model_ucode;
- struct extended_signature *ext_sig;
- unsigned int fam, model;
- int ext_sigcount, i;
-
- fam = x86_family(sig);
- model = x86_model(sig);
-
- fam_ucode = x86_family(mc_header->sig);
- model_ucode = x86_model(mc_header->sig);
-
- if (fam == fam_ucode && model == model_ucode)
- return true;
-
- /* Look for ext. headers: */
- if (total_size <= data_size + MC_HEADER_SIZE)
- return false;
-
- ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE;
- ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
- ext_sigcount = ext_header->count;
-
- for (i = 0; i < ext_sigcount; i++) {
- fam_ucode = x86_family(ext_sig->sig);
- model_ucode = x86_model(ext_sig->sig);
-
- if (fam == fam_ucode && model == model_ucode)
- return true;
-
- ext_sig++;
- }
- return false;
-}
-
static struct ucode_patch *memdup_patch(void *data, unsigned int size)
{
struct ucode_patch *p;
return p;
}
-static void save_microcode_patch(void *data, unsigned int size)
+static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size)
{
struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
struct ucode_patch *iter, *tmp, *p = NULL;
if (!p)
return;
+ if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf))
+ return;
+
/*
* Save for early loading. On 32-bit, that needs to be a physical
* address as the APs are running from physical addresses, before
size -= mc_size;
- if (!microcode_matches(mc_header, uci->cpu_sig.sig)) {
+ if (!find_matching_signature(data, uci->cpu_sig.sig,
+ uci->cpu_sig.pf)) {
data += mc_size;
continue;
}
if (save) {
- save_microcode_patch(data, mc_size);
+ save_microcode_patch(uci, data, mc_size);
goto next;
}
* Save this microcode patch. It will be loaded early when a CPU is
* hot-added or resumes.
*/
-static void save_mc_for_early(u8 *mc, unsigned int size)
+static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size)
{
/* Synchronization during CPU hotplug. */
static DEFINE_MUTEX(x86_cpu_microcode_mutex);
mutex_lock(&x86_cpu_microcode_mutex);
- save_microcode_patch(mc, size);
+ save_microcode_patch(uci, mc, size);
show_saved_mc();
mutex_unlock(&x86_cpu_microcode_mutex);
* permanent memory. So it will be loaded early when a CPU is hot added
* or resumes.
*/
- save_mc_for_early(new_mc, new_mc_size);
+ save_mc_for_early(uci, new_mc, new_mc_size);
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
if (d) {
cpumask_set_cpu(cpu, &d->cpu_mask);
+ if (r->cache.arch_has_per_cpu_cfg)
+ rdt_domain_reconfigure_cdp(r);
return;
}
r->rid == RDT_RESOURCE_L2CODE) {
r->cache.arch_has_sparse_bitmaps = false;
r->cache.arch_has_empty_bitmaps = false;
+ r->cache.arch_has_per_cpu_cfg = false;
} else if (r->rid == RDT_RESOURCE_MBA) {
r->msr_base = MSR_IA32_MBA_THRTL_BASE;
r->msr_update = mba_wrmsr_intel;
r->rid == RDT_RESOURCE_L2CODE) {
r->cache.arch_has_sparse_bitmaps = true;
r->cache.arch_has_empty_bitmaps = true;
+ r->cache.arch_has_per_cpu_cfg = true;
} else if (r->rid == RDT_RESOURCE_MBA) {
r->msr_base = MSR_IA32_MBA_BW_BASE;
r->msr_update = mba_wrmsr_amd;
* executing entities
* @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid.
* @arch_has_empty_bitmaps: True if the '0' bitmap is valid.
+ * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache
+ * level has CPU scope.
*/
struct rdt_cache {
unsigned int cbm_len;
unsigned int shareable_bits;
bool arch_has_sparse_bitmaps;
bool arch_has_empty_bitmaps;
+ bool arch_has_per_cpu_cfg;
};
/**
return ret ?: nbytes;
}
+/**
+ * rdtgroup_remove - the helper to remove resource group safely
+ * @rdtgrp: resource group to remove
+ *
+ * On resource group creation via a mkdir, an extra kernfs_node reference is
+ * taken to ensure that the rdtgroup structure remains accessible for the
+ * rdtgroup_kn_unlock() calls where it is removed.
+ *
+ * Drop the extra reference here, then free the rdtgroup structure.
+ *
+ * Return: void
+ */
+static void rdtgroup_remove(struct rdtgroup *rdtgrp)
+{
+ kernfs_put(rdtgrp->kn);
+ kfree(rdtgrp);
+}
+
struct task_move_callback {
struct callback_head work;
struct rdtgroup *rdtgrp;
(rdtgrp->flags & RDT_DELETED)) {
current->closid = 0;
current->rmid = 0;
- kfree(rdtgrp);
+ rdtgroup_remove(rdtgrp);
}
if (unlikely(current->flags & PF_EXITING))
if (IS_ERR(kn_subdir))
return PTR_ERR(kn_subdir);
- kernfs_get(kn_subdir);
ret = rdtgroup_kn_set_ugid(kn_subdir);
if (ret)
return ret;
kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
if (IS_ERR(kn_info))
return PTR_ERR(kn_info);
- kernfs_get(kn_info);
ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
if (ret)
goto out_destroy;
}
- /*
- * This extra ref will be put in kernfs_remove() and guarantees
- * that @rdtgrp->kn is always accessible.
- */
- kernfs_get(kn_info);
-
ret = rdtgroup_kn_set_ugid(kn_info);
if (ret)
goto out_destroy;
if (dest_kn)
*dest_kn = kn;
- /*
- * This extra ref will be put in kernfs_remove() and guarantees
- * that @rdtgrp->kn is always accessible.
- */
- kernfs_get(kn);
-
ret = rdtgroup_kn_set_ugid(kn);
if (ret)
goto out_destroy;
r_l = &rdt_resources_all[level];
list_for_each_entry(d, &r_l->domains, list) {
- /* Pick one CPU from each domain instance to update MSR */
- cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+ if (r_l->cache.arch_has_per_cpu_cfg)
+ /* Pick all the CPUs in the domain instance */
+ for_each_cpu(cpu, &d->cpu_mask)
+ cpumask_set_cpu(cpu, cpu_mask);
+ else
+ /* Pick one CPU from each domain instance to update MSR */
+ cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
}
cpu = get_cpu();
/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
rdtgroup_pseudo_lock_remove(rdtgrp);
kernfs_unbreak_active_protection(kn);
- kernfs_put(rdtgrp->kn);
- kfree(rdtgrp);
+ rdtgroup_remove(rdtgrp);
} else {
kernfs_unbreak_active_protection(kn);
}
&kn_mongrp);
if (ret < 0)
goto out_info;
- kernfs_get(kn_mongrp);
ret = mkdir_mondata_all(rdtgroup_default.kn,
&rdtgroup_default, &kn_mondata);
if (ret < 0)
goto out_mongrp;
- kernfs_get(kn_mondata);
rdtgroup_default.mon.mon_data_kn = kn_mondata;
}
if (atomic_read(&sentry->waitcount) != 0)
sentry->flags = RDT_DELETED;
else
- kfree(sentry);
+ rdtgroup_remove(sentry);
}
}
if (atomic_read(&rdtgrp->waitcount) != 0)
rdtgrp->flags = RDT_DELETED;
else
- kfree(rdtgrp);
+ rdtgroup_remove(rdtgrp);
}
/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
update_closid_rmid(cpu_online_mask, &rdtgroup_default);
if (IS_ERR(kn))
return PTR_ERR(kn);
- /*
- * This extra ref will be put in kernfs_remove() and guarantees
- * that kn is always accessible.
- */
- kernfs_get(kn);
ret = rdtgroup_kn_set_ugid(kn);
if (ret)
goto out_destroy;
/*
* kernfs_remove() will drop the reference count on "kn" which
* will free it. But we still need it to stick around for the
- * rdtgroup_kn_unlock(kn} call below. Take one extra reference
- * here, which will be dropped inside rdtgroup_kn_unlock().
+ * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
+ * which will be dropped by kernfs_put() in rdtgroup_remove().
*/
kernfs_get(kn);
out_idfree:
free_rmid(rdtgrp->mon.rmid);
out_destroy:
+ kernfs_put(rdtgrp->kn);
kernfs_remove(rdtgrp->kn);
out_free_rgrp:
kfree(rdtgrp);
{
kernfs_remove(rgrp->kn);
free_rmid(rgrp->mon.rmid);
- kfree(rgrp);
+ rdtgroup_remove(rgrp);
}
/*
WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
list_del(&rdtgrp->mon.crdtgrp_list);
- /*
- * one extra hold on this, will drop when we kfree(rdtgrp)
- * in rdtgroup_kn_unlock()
- */
- kernfs_get(kn);
kernfs_remove(rdtgrp->kn);
return 0;
rdtgrp->flags = RDT_DELETED;
list_del(&rdtgrp->rdtgroup_list);
- /*
- * one extra hold on this, will drop when we kfree(rdtgrp)
- * in rdtgroup_kn_unlock()
- */
- kernfs_get(kn);
kernfs_remove(rdtgrp->kn);
return 0;
}
if (!user_mode(regs))
return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
+ /* The user space code from other tasks cannot be accessed. */
+ if (regs != task_pt_regs(current))
+ return -EPERM;
/*
* Make sure userspace isn't trying to trick us into dumping kernel
* memory by pointing the userspace instruction pointer at it.
if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
return -EINVAL;
+ /*
+ * Even if named copy_from_user_nmi() this can be invoked from
+ * other contexts and will not try to resolve a pagefault, which is
+ * the correct thing to do here as this code can be called from any
+ * context.
+ */
return copy_from_user_nmi(buf, (void __user *)src, nbytes);
}
u8 opcodes[OPCODE_BUFSIZE];
unsigned long prologue = regs->ip - PROLOGUE_SIZE;
- if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
- printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
- loglvl, prologue);
- } else {
+ switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
+ case 0:
printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
__stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1);
+ break;
+ case -EPERM:
+ /* No access to the user space stack of other tasks. Ignore. */
+ break;
+ default:
+ printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
+ loglvl, prologue);
+ break;
}
}
/* Setup early boot stage 4-/5-level pagetables. */
addq phys_base(%rip), %rax
+
+ /*
+ * For SEV guests: Verify that the C-bit is correct. A malicious
+ * hypervisor could lie about the C-bit position to perform a ROP
+ * attack on the guest by writing to the unencrypted stack and wait for
+ * the next RET instruction.
+ * %rsi carries pointer to realmode data and is callee-clobbered. Save
+ * and restore it.
+ */
+ pushq %rsi
+ movq %rax, %rdi
+ call sev_verify_cbit
+ popq %rsi
+
+ /* Switch to new page-table */
movq %rax, %cr3
/* Ensure I am executing from virtual addresses */
SYM_CODE_END(secondary_startup_64)
#include "verify_cpu.S"
+#include "sev_verify_cbit.S"
#ifdef CONFIG_HOTPLUG_CPU
/*
params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch;
/* Copying screen_info will do? */
- memcpy(¶ms->screen_info, &boot_params.screen_info,
- sizeof(struct screen_info));
+ memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info));
/* Fill in memsize later */
params->screen_info.ext_mem_k = 0;
}
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
return PERF_SAMPLE_REGS_ABI_64;
}
+static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs);
+
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
+ struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs);
struct pt_regs *user_regs = task_pt_regs(current);
+ if (!in_nmi()) {
+ regs_user->regs = user_regs;
+ regs_user->abi = perf_reg_abi(current);
+ return;
+ }
+
/*
* If we're in an NMI that interrupted task_pt_regs setup, then
* we can't sample user regs at all. This check isn't really
*/
void __cpuidle default_idle(void)
{
- safe_halt();
+ raw_safe_halt();
}
#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
EXPORT_SYMBOL(default_idle);
/*
* AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
* states (local apic timer and TSC stop).
+ *
+ * XXX this function is completely buggered vs RCU and tracing.
*/
static void amd_e400_idle(void)
{
* The switch back from broadcast mode needs to be called with
* interrupts disabled.
*/
- local_irq_disable();
+ raw_local_irq_disable();
tick_broadcast_exit();
- local_irq_enable();
+ raw_local_irq_enable();
}
/*
if (!need_resched())
__sti_mwait(0, 0);
else
- local_irq_enable();
+ raw_local_irq_enable();
} else {
- local_irq_enable();
+ raw_local_irq_enable();
}
__current_clr_polling();
}
goto fail;
regs->dx = val >> 32;
+ /*
+ * This is a VC handler and the #VC is only raised when SEV-ES is
+ * active, which means SEV must be active too. Do sanity checks on the
+ * CPUID results to make sure the hypervisor does not trick the kernel
+ * into the no-sev path. This could map sensitive data unencrypted and
+ * make it accessible to the hypervisor.
+ *
+ * In particular, check for:
+ * - Hypervisor CPUID bit
+ * - Availability of CPUID leaf 0x8000001f
+ * - SEV CPUID bit.
+ *
+ * The hypervisor might still report the wrong C-bit position, but this
+ * can't be checked here.
+ */
+
+ if ((fn == 1 && !(regs->cx & BIT(31))))
+ /* Hypervisor bit */
+ goto fail;
+ else if (fn == 0x80000000 && (regs->ax < 0x8000001f))
+ /* SEV leaf check */
+ goto fail;
+ else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
+ /* SEV bit */
+ goto fail;
+
/* Skip over the CPUID two-byte opcode */
regs->ip += 2;
return ES_EXCEPTION;
}
-static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
- unsigned long vaddr, phys_addr_t *paddr)
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+ unsigned long vaddr, phys_addr_t *paddr)
{
unsigned long va = (unsigned long)vaddr;
unsigned int level;
if (user_mode(ctxt->regs))
ctxt->fi.error_code |= X86_PF_USER;
- return false;
+ return ES_EXCEPTION;
}
+ if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+ /* Emulated MMIO to/from encrypted memory not supported */
+ return ES_UNSUPPORTED;
+
pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
pa |= va & ~page_level_mask(level);
*paddr = pa;
- return true;
+ return ES_OK;
}
/* Include code shared with pre-decompression boot stage */
{
u64 exit_code, exit_info_1, exit_info_2;
unsigned long ghcb_pa = __pa(ghcb);
+ enum es_result res;
phys_addr_t paddr;
void __user *ref;
exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
- if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) {
- if (!read)
+ res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+ if (res != ES_OK) {
+ if (res == ES_EXCEPTION && !read)
ctxt->fi.error_code |= X86_PF_WRITE;
- return ES_EXCEPTION;
+ return res;
}
exit_info_1 = paddr;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sev_verify_cbit.S - Code for verification of the C-bit position reported
+ * by the Hypervisor when running with SEV enabled.
+ *
+ * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de)
+ *
+ * sev_verify_cbit() is called before switching to a new long-mode page-table
+ * at boot.
+ *
+ * Verify that the C-bit position is correct by writing a random value to
+ * an encrypted memory location while on the current page-table. Then it
+ * switches to the new page-table to verify the memory content is still the
+ * same. After that it switches back to the current page-table and when the
+ * check succeeded it returns. If the check failed the code invalidates the
+ * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to
+ * make sure no interrupt or exception can get the CPU out of the hlt loop.
+ *
+ * New page-table pointer is expected in %rdi (first parameter)
+ *
+ */
+SYM_FUNC_START(sev_verify_cbit)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /* First check if a C-bit was detected */
+ movq sme_me_mask(%rip), %rsi
+ testq %rsi, %rsi
+ jz 3f
+
+ /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */
+ movq sev_status(%rip), %rsi
+ testq %rsi, %rsi
+ jz 3f
+
+ /* Save CR4 in %rsi */
+ movq %cr4, %rsi
+
+ /* Disable Global Pages */
+ movq %rsi, %rdx
+ andq $(~X86_CR4_PGE), %rdx
+ movq %rdx, %cr4
+
+ /*
+ * Verified that running under SEV - now get a random value using
+ * RDRAND. This instruction is mandatory when running as an SEV guest.
+ *
+ * Don't bail out of the loop if RDRAND returns errors. It is better to
+ * prevent forward progress than to work with a non-random value here.
+ */
+1: rdrand %rdx
+ jnc 1b
+
+ /* Store value to memory and keep it in %rdx */
+ movq %rdx, sev_check_data(%rip)
+
+ /* Backup current %cr3 value to restore it later */
+ movq %cr3, %rcx
+
+ /* Switch to new %cr3 - This might unmap the stack */
+ movq %rdi, %cr3
+
+ /*
+ * Compare value in %rdx with memory location. If C-bit is incorrect
+ * this would read the encrypted data and make the check fail.
+ */
+ cmpq %rdx, sev_check_data(%rip)
+
+ /* Restore old %cr3 */
+ movq %rcx, %cr3
+
+ /* Restore previous CR4 */
+ movq %rsi, %cr4
+
+ /* Check CMPQ result */
+ je 3f
+
+ /*
+ * The check failed, prevent any forward progress to prevent ROP
+ * attacks, invalidate the stack and go into a hlt loop.
+ */
+ xorq %rsp, %rsp
+ subq $0x1000, %rsp
+2: hlt
+ jmp 2b
+3:
+#endif
+ /* Return page-table pointer */
+ movq %rdi, %rax
+ ret
+SYM_FUNC_END(sev_verify_cbit)
if (!tboot_enabled())
return 0;
- if (intel_iommu_tboot_noforce)
- return 1;
-
- if (no_iommu || swiotlb || dmar_disabled)
+ if (no_iommu || dmar_disabled)
pr_warn("Forcing Intel-IOMMU to enabled\n");
dmar_disabled = 0;
-#ifdef CONFIG_SWIOTLB
- swiotlb = 0;
-#endif
no_iommu = 0;
return 1;
set_debugreg(DR6_RESERVED, 6);
dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
- /*
- * Clear the virtual DR6 value, ptrace routines will set bits here for
- * things we want signals for.
- */
- current->thread.virtual_dr6 = 0;
-
- /*
- * The SDM says "The processor clears the BTF flag when it
- * generates a debug exception." Clear TIF_BLOCKSTEP to keep
- * TIF_BLOCKSTEP in sync with the hardware BTF flag.
- */
- clear_thread_flag(TIF_BLOCKSTEP);
-
return dr6;
}
*/
WARN_ON_ONCE(user_mode(regs));
+ if (test_thread_flag(TIF_BLOCKSTEP)) {
+ /*
+ * The SDM says "The processor clears the BTF flag when it
+ * generates a debug exception." but PTRACE_BLOCKSTEP requested
+ * it for userspace, but we just took a kernel #DB, so re-set
+ * BTF.
+ */
+ unsigned long debugctl;
+
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ debugctl |= DEBUGCTLMSR_BTF;
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ }
+
/*
* Catch SYSENTER with TF set and clear DR_STEP. If this hit a
* watchpoint at the same time then that will still be handled.
irqentry_enter_from_user_mode(regs);
instrumentation_begin();
+ /*
+ * Start the virtual/ptrace DR6 value with just the DR_STEP mask
+ * of the real DR6. ptrace_triggered() will set the DR_TRAPn bits.
+ *
+ * Userspace expects DR_STEP to be visible in ptrace_get_debugreg(6)
+ * even if it is not the result of PTRACE_SINGLESTEP.
+ */
+ current->thread.virtual_dr6 = (dr6 & DR_STEP);
+
+ /*
+ * The SDM says "The processor clears the BTF flag when it
+ * generates a debug exception." Clear TIF_BLOCKSTEP to keep
+ * TIF_BLOCKSTEP in sync with the hardware BTF flag.
+ */
+ clear_thread_flag(TIF_BLOCKSTEP);
+
/*
* If dr6 has no reason to give us about the origin of this trap,
* then it's very likely the result of an icebp/int01 trap.
unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
{
- struct task_struct *task = state->task;
-
if (unwind_done(state))
return NULL;
if (state->regs)
return &state->regs->ip;
- if (task != current && state->sp == task->thread.sp) {
- struct inactive_task_frame *frame = (void *)task->thread.sp;
- return &frame->ret_addr;
- }
-
if (state->sp)
return (unsigned long *)state->sp - 1;
} else {
struct inactive_task_frame *frame = (void *)task->thread.sp;
- state->sp = task->thread.sp;
+ state->sp = task->thread.sp + sizeof(*frame);
state->bp = READ_ONCE_NOCHECK(frame->bp);
state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
state->signal = (void *)state->ip == ret_from_fork;
static bool is_prefix_bad(struct insn *insn)
{
+ insn_byte_t p;
int i;
- for (i = 0; i < insn->prefixes.nbytes; i++) {
+ for_each_insn_prefix(insn, i, p) {
insn_attr_t attr;
- attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+ attr = inat_get_opcode_attribute(p);
switch (attr) {
case INAT_MAKE_PREFIX(INAT_PFX_ES):
case INAT_MAKE_PREFIX(INAT_PFX_CS):
static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
{
u8 opc1 = OPCODE1(insn);
+ insn_byte_t p;
int i;
switch (opc1) {
* Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix.
* No one uses these insns, reject any branch insns with such prefix.
*/
- for (i = 0; i < insn->prefixes.nbytes; i++) {
- if (insn->prefixes.bytes[i] == 0x66)
+ for_each_insn_prefix(insn, i, p) {
+ if (p == 0x66)
return -ENOTSUPP;
}
return 0;
}
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+
+ /*
+ * save the feature bitmap to avoid cpuid lookup for every PV
+ * operation
+ */
+ if (best)
+ vcpu->arch.pv_cpuid.features = best->eax;
+}
+
void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
- /*
- * save the feature bitmap to avoid cpuid lookup for every PV
- * operation
- */
- if (best)
- vcpu->arch.pv_cpuid.features = best->eax;
-
if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
if (best)
vcpu->arch.guest_supported_xcr0 =
(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
+ kvm_update_pv_runtime(vcpu);
+
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
kvm_mmu_reset_context(vcpu);
vcpu->arch.cr4_guest_rsvd_bits =
__cr4_reserved_bits(guest_cpuid_has, vcpu);
+ vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
+
/* Invoke the vendor callback only after the above state is updated. */
kvm_x86_ops.vcpu_after_set_cpuid(vcpu);
}
edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
edx.split.bit_width_fixed = cap.bit_width_fixed;
- edx.split.reserved = 0;
+ edx.split.anythread_deprecated = 1;
+ edx.split.reserved1 = 0;
+ edx.split.reserved2 = 0;
entry->eax = eax.full;
entry->ebx = cap.events_mask;
void kvm_set_cpu_caps(void);
void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu);
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
return X86EMUL_CONTINUE;
}
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+ /* emulating clflushopt regardless of cpuid */
+ return X86EMUL_CONTINUE;
+}
+
static int em_movsxd(struct x86_emulate_ctxt *ctxt)
{
ctxt->dst.val = (s32) ctxt->src.val;
};
static const struct gprefix pfx_0f_ae_7 = {
- I(SrcMem | ByteOp, em_clflush), N, N, N,
+ I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
};
static const struct group_dual group15 = { {
* check if there is pending interrupt from
* non-APIC source without intack.
*/
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
- u8 accept = kvm_apic_accept_pic_intr(v);
-
- if (accept) {
- if (irqchip_split(v->kvm))
- return pending_userspace_extint(v);
- else
- return v->kvm->arch.vpic->output;
- } else
- return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
{
/*
- * FIXME: interrupt.injected represents an interrupt that it's
+ * FIXME: interrupt.injected represents an interrupt whose
* side-effects have already been applied (e.g. bit from IRR
* already moved to ISR). Therefore, it is incorrect to rely
* on interrupt.injected to know if there is a pending
if (!lapic_in_kernel(v))
return v->arch.interrupt.injected;
+ if (!kvm_apic_accept_pic_intr(v))
+ return 0;
+
+ if (irqchip_split(v->kvm))
+ return pending_userspace_extint(v);
+ else
+ return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
if (kvm_cpu_has_extint(v))
return 1;
*/
int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
{
- /*
- * FIXME: interrupt.injected represents an interrupt that it's
- * side-effects have already been applied (e.g. bit from IRR
- * already moved to ISR). Therefore, it is incorrect to rely
- * on interrupt.injected to know if there is a pending
- * interrupt in the user-mode LAPIC.
- * This leads to nVMX/nSVM not be able to distinguish
- * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
- * pending interrupt or should re-inject an injected
- * interrupt.
- */
- if (!lapic_in_kernel(v))
- return v->arch.interrupt.injected;
-
if (kvm_cpu_has_extint(v))
return 1;
*/
static int kvm_cpu_get_extint(struct kvm_vcpu *v)
{
- if (kvm_cpu_has_extint(v)) {
- if (irqchip_split(v->kvm)) {
- int vector = v->arch.pending_external_vector;
-
- v->arch.pending_external_vector = -1;
- return vector;
- } else
- return kvm_pic_read_irq(v->kvm); /* PIC */
- } else
+ if (!kvm_cpu_has_extint(v)) {
+ WARN_ON(!lapic_in_kernel(v));
return -1;
+ }
+
+ if (!lapic_in_kernel(v))
+ return v->arch.interrupt.nr;
+
+ if (irqchip_split(v->kvm)) {
+ int vector = v->arch.pending_external_vector;
+
+ v->arch.pending_external_vector = -1;
+ return vector;
+ } else
+ return kvm_pic_read_irq(v->kvm); /* PIC */
}
/*
*/
int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
{
- int vector;
-
- if (!lapic_in_kernel(v))
- return v->arch.interrupt.nr;
-
- vector = kvm_cpu_get_extint(v);
-
+ int vector = kvm_cpu_get_extint(v);
if (vector != -1)
return vector; /* PIC */
struct kvm_lapic *apic = vcpu->arch.apic;
u32 ppr;
- if (!kvm_apic_hw_enabled(apic))
+ if (!kvm_apic_present(vcpu))
return -1;
__apic_update_ppr(apic, &ppr);
{
u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
- gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
+ gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)
& shadow_nonpresent_or_rsvd_mask;
return gpa >> PAGE_SHIFT;
static u64 restore_acc_track_spte(u64 spte)
{
u64 new_spte = spte;
- u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift)
- & shadow_acc_track_saved_bits_mask;
+ u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
+ & SHADOW_ACC_TRACK_SAVED_BITS_MASK;
WARN_ON_ONCE(spte_ad_enabled(spte));
WARN_ON_ONCE(!is_access_track_spte(spte));
new_spte &= ~shadow_acc_track_mask;
- new_spte &= ~(shadow_acc_track_saved_bits_mask <<
- shadow_acc_track_saved_bits_shift);
+ new_spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+ SHADOW_ACC_TRACK_SAVED_BITS_SHIFT);
new_spte |= saved_bits;
return new_spte;
} else {
rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
- while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
- desc = desc->more;
+ while (desc->sptes[PTE_LIST_EXT-1]) {
count += PTE_LIST_EXT;
- }
- if (desc->sptes[PTE_LIST_EXT-1]) {
- desc->more = mmu_alloc_pte_list_desc(vcpu);
+
+ if (!desc->more) {
+ desc->more = mmu_alloc_pte_list_desc(vcpu);
+ desc = desc->more;
+ break;
+ }
desc = desc->more;
}
for (i = 0; desc->sptes[i]; ++i)
{
u64 sptes[PT64_ROOT_MAX_LEVEL];
struct rsvd_bits_validate *rsvd_check;
- int root = vcpu->arch.mmu->root_level;
+ int root = vcpu->arch.mmu->shadow_root_level;
int leaf;
int level;
bool reserved = false;
mask |= shadow_mmio_value | access;
mask |= gpa | shadow_nonpresent_or_rsvd_mask;
mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
- << shadow_nonpresent_or_rsvd_mask_len;
+ << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
return mask;
}
!spte_can_locklessly_be_made_writable(spte),
"kvm: Writable SPTE is not locklessly dirty-trackable\n");
- WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask <<
- shadow_acc_track_saved_bits_shift),
+ WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+ SHADOW_ACC_TRACK_SAVED_BITS_SHIFT),
"kvm: Access Tracking saved bit locations are not zero\n");
- spte |= (spte & shadow_acc_track_saved_bits_mask) <<
- shadow_acc_track_saved_bits_shift;
+ spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) <<
+ SHADOW_ACC_TRACK_SAVED_BITS_SHIFT;
spte &= ~shadow_acc_track_mask;
return spte;
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask)
{
BUG_ON((u64)(unsigned)access_mask != access_mask);
- WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+ WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN));
WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
shadow_mmio_access_mask = access_mask;
low_phys_bits = boot_cpu_data.x86_phys_bits;
if (boot_cpu_has_bug(X86_BUG_L1TF) &&
!WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
- 52 - shadow_nonpresent_or_rsvd_mask_len)) {
+ 52 - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)) {
low_phys_bits = boot_cpu_data.x86_cache_bits
- - shadow_nonpresent_or_rsvd_mask_len;
+ - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
shadow_nonpresent_or_rsvd_mask =
rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
}
*/
extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
+/*
+ * The number of high-order 1 bits to use in the mask above.
+ */
+#define SHADOW_NONPRESENT_OR_RSVD_MASK_LEN 5
+
/*
* The mask/shift to use for saving the original R/X bits when marking the PTE
* as not-present for access tracking purposes. We do not save the W bit as the
* PTEs being access tracked also need to be dirty tracked, so the W bit will be
* restored only when a write is attempted to the page.
*/
-static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK |
- PT64_EPT_EXECUTABLE_MASK;
-static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT;
-
-/*
- * The number of high-order 1 bits to use in the mask above.
- */
-static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
+#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (PT64_EPT_READABLE_MASK | \
+ PT64_EPT_EXECUTABLE_MASK)
+#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT PT64_SECOND_AVAIL_BITS_SHIFT
/*
* In some cases, we need to preserve the GFN of a non-present or reserved
{
struct kvm_mmu_page *sp;
+ if (!kvm->arch.tdp_mmu_enabled)
+ return false;
+ if (WARN_ON(!VALID_PAGE(hpa)))
+ return false;
+
sp = to_shadow_page(hpa);
+ if (WARN_ON(!sp))
+ return false;
return sp->tdp_mmu_page && sp->root_count;
}
* Its safe to read more than we are asked, caller should ensure that
* destination has enough space.
*/
- src_paddr = round_down(src_paddr, 16);
offset = src_paddr & 15;
+ src_paddr = round_down(src_paddr, 16);
sz = round_up(sz + offset, 16);
return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
svm->avic_is_running = true;
svm->msrpm = svm_vcpu_alloc_msrpm();
- if (!svm->msrpm)
+ if (!svm->msrpm) {
+ err = -ENOMEM;
goto error_free_vmcb_page;
+ }
svm_vcpu_init_msrpm(vcpu, svm->msrpm);
static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_cpuid_entry2 *best;
vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
boot_cpu_has(X86_FEATURE_XSAVE) &&
/* Check again if INVPCID interception if required */
svm_check_invpcid(svm);
+ /* For sev guests, the memory encryption bit is not reserved in CR3. */
+ if (sev_guest(vcpu->kvm)) {
+ best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
+ if (best)
+ vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
+ }
+
if (!kvm_vcpu_apicv_active(vcpu))
return;
};
const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
+__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
{
vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
-
}
#endif
vp_ap->enlighten_vmentry = 1;
}
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
+__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
#else /* !IS_ENABLED(CONFIG_HYPERV) */
static inline void evmcs_write64(unsigned long field, u64 value) {}
static inline void evmcs_write32(unsigned long field, u32 value) {}
static inline u32 evmcs_read32(unsigned long field) { return 0; }
static inline u16 evmcs_read16(unsigned long field) { return 0; }
static inline void evmcs_load(u64 phys_addr) {}
-static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
static inline void evmcs_touch_msr_bitmap(void) {}
#endif /* IS_ENABLED(CONFIG_HYPERV) */
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
- if (static_branch_unlikely(&enable_evmcs))
+#if IS_ENABLED(CONFIG_HYPERV)
+ if (enlightened_vmcs)
evmcs_sanitize_exec_ctrls(vmcs_conf);
+#endif
return 0;
}
static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx;
- unsigned long *msr_bitmap;
int i, cpu, err;
BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
- msr_bitmap = vmx->vmcs01.msr_bitmap;
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
/*
* When called, it means the previous get/set msr reached an invalid msr.
- * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want
- * to fail the caller.
+ * Return true if we want to ignore/silent this failed msr access.
*/
-static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
- u64 data, bool write)
+static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
+ u64 data, bool write)
{
const char *op = write ? "wrmsr" : "rdmsr";
if (ignore_msrs) {
if (report_ignored_msrs)
- vcpu_unimpl(vcpu, "ignored %s: 0x%x data 0x%llx\n",
- op, msr, data);
+ kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
+ op, msr, data);
/* Mask the error */
- return 0;
+ return true;
} else {
- vcpu_debug_ratelimited(vcpu, "unhandled %s: 0x%x data 0x%llx\n",
- op, msr, data);
- return -ENOENT;
+ kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
+ op, msr, data);
+ return false;
}
}
}
if (is_long_mode(vcpu) &&
- (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
+ (cr3 & vcpu->arch.cr3_lm_rsvd_bits))
return 1;
else if (is_pae_paging(vcpu) &&
!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
if (r == KVM_MSR_RET_INVALID) {
/* Unconditionally clear the output for simplicity */
*data = 0;
- r = kvm_msr_ignored_check(vcpu, index, 0, false);
+ if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ r = 0;
}
if (r)
struct msr_data msr;
if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
- return -EPERM;
+ return KVM_MSR_RET_FILTERED;
switch (index) {
case MSR_FS_BASE:
int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
if (ret == KVM_MSR_RET_INVALID)
- ret = kvm_msr_ignored_check(vcpu, index, data, true);
+ if (kvm_msr_ignored_check(vcpu, index, data, true))
+ ret = 0;
return ret;
}
int ret;
if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
- return -EPERM;
+ return KVM_MSR_RET_FILTERED;
msr.index = index;
msr.host_initiated = host_initiated;
if (ret == KVM_MSR_RET_INVALID) {
/* Unconditionally clear *data for simplicity */
*data = 0;
- ret = kvm_msr_ignored_check(vcpu, index, 0, false);
+ if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ ret = 0;
}
return ret;
static u64 kvm_msr_reason(int r)
{
switch (r) {
- case -ENOENT:
+ case KVM_MSR_RET_INVALID:
return KVM_MSR_EXIT_REASON_UNKNOWN;
- case -EPERM:
+ case KVM_MSR_RET_FILTERED:
return KVM_MSR_EXIT_REASON_FILTER;
default:
return KVM_MSR_EXIT_REASON_INVAL;
struct kvm_arch *ka = &vcpu->kvm->arch;
if (vcpu->vcpu_id == 0 && !host_initiated) {
- if (ka->boot_vcpu_runs_old_kvmclock && old_msr)
+ if (ka->boot_vcpu_runs_old_kvmclock != old_msr)
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
ka->boot_vcpu_runs_old_kvmclock = old_msr;
/* Values other than LBR and BTF are vendor-specific,
thus reserved and should throw a #GP */
return 1;
- }
- vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
- __func__, data);
+ } else if (report_ignored_msrs)
+ vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
+ __func__, data);
break;
case 0x200 ... 0x2ff:
return kvm_mtrr_set_msr(vcpu, msr, data);
msr_info->data = vcpu->arch.efer;
break;
case MSR_KVM_WALL_CLOCK:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+ return 1;
+
+ msr_info->data = vcpu->kvm->arch.wall_clock;
+ break;
case MSR_KVM_WALL_CLOCK_NEW:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+ return 1;
+
msr_info->data = vcpu->kvm->arch.wall_clock;
break;
case MSR_KVM_SYSTEM_TIME:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+ return 1;
+
+ msr_info->data = vcpu->arch.time;
+ break;
case MSR_KVM_SYSTEM_TIME_NEW:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+ return 1;
+
msr_info->data = vcpu->arch.time;
break;
case MSR_KVM_ASYNC_PF_EN:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ return 1;
+
msr_info->data = vcpu->arch.apf.msr_en_val;
break;
case MSR_KVM_ASYNC_PF_INT:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
+ return 1;
+
msr_info->data = vcpu->arch.apf.msr_int_val;
break;
case MSR_KVM_ASYNC_PF_ACK:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ return 1;
+
msr_info->data = 0;
break;
case MSR_KVM_STEAL_TIME:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
+ return 1;
+
msr_info->data = vcpu->arch.st.msr_val;
break;
case MSR_KVM_PV_EOI_EN:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
+ return 1;
+
msr_info->data = vcpu->arch.pv_eoi.msr_val;
break;
case MSR_KVM_POLL_CONTROL:
+ if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
+ return 1;
+
msr_info->data = vcpu->arch.msr_kvm_poll_control;
break;
case MSR_IA32_P5_MC_ADDR:
static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
{
+ /*
+ * We can accept userspace's request for interrupt injection
+ * as long as we have a place to store the interrupt number.
+ * The actual injection will happen when the CPU is able to
+ * deliver the interrupt.
+ */
+ if (kvm_cpu_has_extint(vcpu))
+ return false;
+
+ /* Acknowledging ExtINT does not happen if LINT0 is masked. */
return (!lapic_in_kernel(vcpu) ||
kvm_apic_accept_pic_intr(vcpu));
}
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
{
return kvm_arch_interrupt_allowed(vcpu) &&
- !kvm_cpu_has_interrupt(vcpu) &&
- !kvm_event_needs_reinjection(vcpu) &&
kvm_cpu_accept_dm_intr(vcpu);
}
case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
vcpu->arch.pv_cpuid.enforce = cap->args[0];
+ if (vcpu->arch.pv_cpuid.enforce)
+ kvm_update_pv_runtime(vcpu);
return 0;
int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
-#define KVM_MSR_RET_INVALID 2
+/*
+ * Internal error codes that are used to indicate that MSR emulation encountered
+ * an error that should result in #GP in the guest, unless userspace
+ * handles it.
+ */
+#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */
+#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */
#define __cr4_reserved_bits(__cpu_has, __c) \
({ \
*/
bool insn_has_rep_prefix(struct insn *insn)
{
+ insn_byte_t p;
int i;
insn_get_prefixes(insn);
- for (i = 0; i < insn->prefixes.nbytes; i++) {
- insn_byte_t p = insn->prefixes.bytes[i];
-
+ for_each_insn_prefix(insn, i, p) {
if (p == 0xf2 || p == 0xf3)
return true;
}
{
int idx = INAT_SEG_REG_DEFAULT;
int num_overrides = 0, i;
+ insn_byte_t p;
insn_get_prefixes(insn);
/* Look for any segment override prefixes. */
- for (i = 0; i < insn->prefixes.nbytes; i++) {
+ for_each_insn_prefix(insn, i, p) {
insn_attr_t attr;
- attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+ attr = inat_get_opcode_attribute(p);
switch (attr) {
case INAT_MAKE_PREFIX(INAT_PFX_CS):
idx = INAT_SEG_REG_CS;
* to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
*/
-.weak memcpy
-
/*
* memcpy - Copy a memory block.
*
* rax original destination
*/
SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
* Output:
* rax: dest
*/
-.weak memmove
-
-SYM_FUNC_START_ALIAS(memmove)
+SYM_FUNC_START_WEAK(memmove)
SYM_FUNC_START(__memmove)
mov %rdi, %rax
#include <asm/alternative-asm.h>
#include <asm/export.h>
-.weak memset
-
/*
* ISO C memset - set a memory block to a byte value. This function uses fast
* string to get better performance than the original function. The code is
*
* rax original destination
*/
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
SYM_FUNC_START(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
*/
u64 sme_me_mask __section(".data") = 0;
u64 sev_status __section(".data") = 0;
+u64 sev_check_data __section(".data") = 0;
EXPORT_SYMBOL(sme_me_mask);
DEFINE_STATIC_KEY_FALSE(sev_enable_key);
EXPORT_SYMBOL_GPL(sev_enable_key);
return meminfo_to_nid(&numa_reserved_meminfo, start);
}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
int memory_add_physaddr_to_nid(u64 start)
{
nid = numa_meminfo.blk[0].nid;
return nid;
}
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif
gfp_mask = GFP_KERNEL | __GFP_ZERO;
efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
if (!efi_pgd)
- return -ENOMEM;
+ goto fail;
pgd = efi_pgd + pgd_index(EFI_VA_END);
p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
- if (!p4d) {
- free_page((unsigned long)efi_pgd);
- return -ENOMEM;
- }
+ if (!p4d)
+ goto free_pgd;
pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
- if (!pud) {
- if (pgtable_l5_enabled())
- free_page((unsigned long) pgd_page_vaddr(*pgd));
- free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
- return -ENOMEM;
- }
+ if (!pud)
+ goto free_p4d;
efi_mm.pgd = efi_pgd;
mm_init_cpumask(&efi_mm);
init_new_context(NULL, &efi_mm);
return 0;
+
+free_p4d:
+ if (pgtable_l5_enabled())
+ free_page((unsigned long)pgd_page_vaddr(*pgd));
+free_pgd:
+ free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+fail:
+ return -ENOMEM;
}
/*
#include <sysdep/mcontext.h>
#include <sys/ucontext.h>
-void __section(".__syscall_stub")
+void __attribute__ ((__section__ (".__syscall_stub")))
stub_segv_handler(int sig, siginfo_t *info, void *p)
{
ucontext_t *uc = p;
void xen_uninit_lock_cpu(int cpu)
{
+ int irq;
+
if (!xen_pvspin)
return;
- unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
+ /*
+ * When booting the kernel with 'mitigations=auto,nosmt', the secondary
+ * CPUs are not activated, and lock_kicker_irq is not initialized.
+ */
+ irq = per_cpu(lock_kicker_irq, cpu);
+ if (irq == -1)
+ return;
+
+ unbind_from_irqhandler(irq, NULL);
per_cpu(lock_kicker_irq, cpu) = -1;
kfree(per_cpu(irq_name, cpu));
per_cpu(irq_name, cpu) = NULL;
*/
#define VMALLOC_START (XCHAL_KSEG_CACHED_VADDR - 0x10000000)
#define VMALLOC_END (VMALLOC_START + 0x07FEFFFF)
-#define TLBTEMP_BASE_1 (VMALLOC_END + 1)
+#define TLBTEMP_BASE_1 (VMALLOC_START + 0x08000000)
#define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
#define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE)
return -EFAULT;
}
#else
-long strncpy_from_user(char *dst, const char *src, long count);
+long strncpy_from_user(char *dst, const char __user *src, long count);
#endif
/*
kvaddr = TLBTEMP_BASE_1 +
(page_to_phys(page) & DCACHE_ALIAS_MASK);
+ preempt_disable();
__invalidate_dcache_page_alias(kvaddr,
page_to_phys(page));
+ preempt_enable();
}
}
}
if (!alias && !mapping)
return;
+ preempt_disable();
virt = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK);
__flush_invalidate_dcache_page_alias(virt, phys);
if (mapping)
__invalidate_icache_page_alias(virt, phys);
+ preempt_enable();
}
/* There shouldn't be an entry in the cache for this page anymore. */
unsigned long phys = page_to_phys(pfn_to_page(pfn));
unsigned long virt = TLBTEMP_BASE_1 + (address & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_page_alias(virt, phys);
__invalidate_icache_page_alias(virt, phys);
+ preempt_enable();
}
EXPORT_SYMBOL(local_flush_cache_page);
unsigned long phys = page_to_phys(page);
unsigned long tmp;
+ preempt_disable();
tmp = TLBTEMP_BASE_1 + (phys & DCACHE_ALIAS_MASK);
__flush_invalidate_dcache_page_alias(tmp, phys);
tmp = TLBTEMP_BASE_1 + (addr & DCACHE_ALIAS_MASK);
__flush_invalidate_dcache_page_alias(tmp, phys);
__invalidate_icache_page_alias(tmp, phys);
+ preempt_enable();
clear_bit(PG_arch_1, &page->flags);
}
if (alias) {
unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_page_alias(t, phys);
+ preempt_enable();
}
/* Copy data */
if (alias) {
unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_range((unsigned long) dst, len);
if ((vma->vm_flags & VM_EXEC) != 0)
__invalidate_icache_page_alias(t, phys);
+ preempt_enable();
} else if ((vma->vm_flags & VM_EXEC) != 0) {
__flush_dcache_range((unsigned long)dst,len);
if (alias) {
unsigned long t = TLBTEMP_BASE_1 + (vaddr & DCACHE_ALIAS_MASK);
+ preempt_disable();
__flush_invalidate_dcache_page_alias(t, phys);
+ preempt_enable();
}
memcpy(dst, src, len);
/* set highmem page free */
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
&range_start, &range_end, NULL) {
- unsigned long start = PHYS_PFN(range_start);
- unsigned long end = PHYS_PFN(range_end);
+ unsigned long start = PFN_UP(range_start);
+ unsigned long end = PFN_DOWN(range_end);
/* Ignore complete lowmem entries */
if (end <= max_low)
ssize_t size, left;
unsigned len, i;
size_t offset;
+ int ret = 0;
if (WARN_ON_ONCE(!max_append_sectors))
return 0;
len = min_t(size_t, PAGE_SIZE - offset, left);
if (bio_add_hw_page(q, bio, page, len, offset,
- max_append_sectors, &same_page) != len)
- return -EINVAL;
+ max_append_sectors, &same_page) != len) {
+ ret = -EINVAL;
+ break;
+ }
if (same_page)
put_page(page);
offset = 0;
}
- iov_iter_advance(iter, size);
- return 0;
+ iov_iter_advance(iter, size - left);
+ return ret;
}
/**
goto fail;
}
+ if (radix_tree_preload(GFP_KERNEL)) {
+ blkg_free(new_blkg);
+ ret = -ENOMEM;
+ goto fail;
+ }
+
rcu_read_lock();
spin_lock_irq(&q->queue_lock);
blkg = blkg_lookup_check(pos, pol, q);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
- goto fail_unlock;
+ blkg_free(new_blkg);
+ goto fail_preloaded;
}
if (blkg) {
blkg = blkg_create(pos, q, new_blkg);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
- goto fail_unlock;
+ goto fail_preloaded;
}
}
+ radix_tree_preload_end();
+
if (pos == blkcg)
goto success;
}
ctx->body = input;
return 0;
+fail_preloaded:
+ radix_tree_preload_end();
fail_unlock:
spin_unlock_irq(&q->queue_lock);
rcu_read_unlock();
blkg_iostat_set(&blkg->iostat.cur, &tmp);
u64_stats_update_end(&blkg->iostat.sync);
}
+ disk_put_part(part);
}
}
return;
}
+ /*
+ * Flush request has to be marked as IDLE when it is really ended
+ * because its .end_io() is called from timeout code path too for
+ * avoiding use-after-free.
+ */
+ WRITE_ONCE(flush_rq->state, MQ_RQ_IDLE);
if (fq->rq_status != BLK_STS_OK)
error = fq->rq_status;
static inline unsigned get_max_io_size(struct request_queue *q,
struct bio *bio)
{
- unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+ unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0);
unsigned max_sectors = sectors;
unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
t->io_min = max(t->io_min, b->io_min);
t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
- t->chunk_sectors = lcm_not_zero(t->chunk_sectors, b->chunk_sectors);
+
+ /* Set non-power-of-2 compatible chunk_sectors boundary */
+ if (b->chunk_sectors)
+ t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors);
/* Physical block size a multiple of the logical block size? */
if (t->physical_block_size & (t->logical_block_size - 1)) {
* Set disk capacity and notify if the size is not currently
* zero and will not be set to zero
*/
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
bool update_bdev)
{
sector_t capacity = get_capacity(disk);
char *envp[] = { "RESIZE=1", NULL };
kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+ return true;
}
+
+ return false;
}
EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
spin_lock_init(&ksm->idle_slots_lock);
slot_hashtable_size = roundup_pow_of_two(num_slots);
+ /*
+ * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2
+ * buckets. This only makes a difference when there is only 1 keyslot.
+ */
+ if (slot_hashtable_size < 2)
+ slot_hashtable_size = 2;
+
ksm->log_slot_ht_size = ilog2(slot_hashtable_size);
ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size,
sizeof(ksm->slot_hashtable[0]),
obj-$(CONFIG_SSB) += ssb/
obj-$(CONFIG_BCMA) += bcma/
obj-$(CONFIG_VHOST_RING) += vhost/
+obj-$(CONFIG_VHOST_IOTLB) += vhost/
obj-$(CONFIG_VHOST) += vhost/
obj-$(CONFIG_VLYNQ) += vlynq/
obj-$(CONFIG_GREYBUS) += greybus/
mark_cut_flag = 0;
synth_printf("%s\n", spk_msg_get(MSG_CUT));
- speakup_clear_selection();
ret = speakup_set_selection(tty);
switch (ret) {
struct tty_struct *tty;
};
-void speakup_clear_selection(void)
-{
- console_lock();
- clear_selection();
- console_unlock();
-}
-
static void __speakup_set_selection(struct work_struct *work)
{
struct speakup_selection_work *ssw =
goto unref;
}
+ console_lock();
+ clear_selection();
+ console_unlock();
+
set_selection_kernel(&sel, tty);
unref:
void speakup_start_ttys(void);
void synth_buffer_add(u16 ch);
void synth_buffer_clear(void);
-void speakup_clear_selection(void);
int speakup_set_selection(struct tty_struct *tty);
void speakup_cancel_selection(void);
int speakup_paste_selection(struct tty_struct *tty);
{
struct spk_ldisc_data *ldisc_data;
+ if (tty != speakup_tty)
+ /* Somebody tried to use this line discipline outside speakup */
+ return -ENODEV;
+
if (!tty->ops->write)
return -EOPNOTSUPP;
- speakup_tty = tty;
ldisc_data = kmalloc(sizeof(*ldisc_data), GFP_KERNEL);
if (!ldisc_data)
init_completion(&ldisc_data->completion);
ldisc_data->buf_free = true;
- speakup_tty->disc_data = ldisc_data;
+ tty->disc_data = ldisc_data;
return 0;
}
tty_unlock(tty);
+ mutex_lock(&speakup_tty_mutex);
+ speakup_tty = tty;
ret = tty_set_ldisc(tty, N_SPEAKUP);
if (ret)
- pr_err("speakup: Failed to set N_SPEAKUP on tty\n");
+ speakup_tty = NULL;
+ mutex_unlock(&speakup_tty_mutex);
+
+ if (!ret)
+ /* Success */
+ return 0;
+
+ pr_err("speakup: Failed to set N_SPEAKUP on tty\n");
+
+ tty_lock(tty);
+ if (tty->ops->close)
+ tty->ops->close(tty, NULL);
+ tty_unlock(tty);
+
+ tty_kclose(tty);
return ret;
}
struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data;
char rv;
- if (wait_for_completion_timeout(&ldisc_data->completion,
+ if (!timeout) {
+ if (!try_wait_for_completion(&ldisc_data->completion))
+ return 0xff;
+ } else if (wait_for_completion_timeout(&ldisc_data->completion,
usecs_to_jiffies(timeout)) == 0) {
- if (timeout)
- pr_warn("spk_ttyio: timeout (%d) while waiting for input\n",
- timeout);
+ pr_warn("spk_ttyio: timeout (%d) while waiting for input\n",
+ timeout);
return 0xff;
}
E_NEW_DEFAULT,
};
+/*
+ * Note: add new members at the end, speakupmap.h depends on the values of the
+ * enum starting from SPELL_DELAY (see inc_dec_var)
+ */
enum var_id_t {
VERSION = 0, SYNTH, SILENT, SYNTH_DIRECT,
KEYMAP, CHARS,
SAY_CONTROL, SAY_WORD_CTL, NO_INTERRUPT, KEY_ECHO,
SPELL_DELAY, PUNC_LEVEL, READING_PUNC,
ATTRIB_BLEEP, BLEEPS,
- RATE, PITCH, INFLECTION, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG,
+ RATE, PITCH, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG,
DIRECT, PAUSE,
- CAPS_START, CAPS_STOP, CHARTAB,
+ CAPS_START, CAPS_STOP, CHARTAB, INFLECTION,
MAXVARS
};
ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value;
level = device->brightness->levels[bqc_value +
- ACPI_VIDEO_FIRST_LEVEL];
+ ACPI_VIDEO_FIRST_LEVEL];
} else {
level = bqc_value;
}
goto out_free_levels;
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "found %d brightness levels\n",
- br->count - ACPI_VIDEO_FIRST_LEVEL));
+ "found %d brightness levels\n",
+ br->count - ACPI_VIDEO_FIRST_LEVEL));
return 0;
out_free_levels:
if (rc)
return rc;
+ /* IO space doesn't need mapping */
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+ return 0;
+
if (!acpi_os_map_generic_address(reg))
return -ENXIO;
* iort_set_fwnode() - Create iort_fwnode and use it to register
* iommu data in the iort_fwnode_list
*
- * @node: IORT table node associated with the IOMMU
+ * @iort_node: IORT table node associated with the IOMMU
* @fwnode: fwnode associated with the IORT node
*
* Returns: 0 on success
/**
* iort_get_device_domain() - Find MSI domain related to a device
* @dev: The device.
- * @req_id: Requester ID for the device.
+ * @id: Requester ID for the device.
+ * @bus_token: irq domain bus token.
*
* Returns: the MSI domain for this device, NULL otherwise
*/
*
* @dev: device to configure
* @dma_addr: device DMA address result pointer
- * @size: DMA range size result pointer
+ * @dma_size: DMA range size result pointer
*/
void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
{
/**
* iort_add_platform_device() - Allocate a platform device for IORT node
* @node: Pointer to device ACPI IORT node
+ * @ops: Pointer to IORT device config struct
*
* Returns: 0 on success, <0 failure
*/
*/
if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) ||
(test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) &&
- (battery->capacity_now <= battery->alarm)))
+ (battery->capacity_now <= battery->alarm)))
acpi_pm_wakeup_event(&battery->device->dev);
return result;
/* Please keep this list sorted alphabetically by vendor and model */
static const struct dmi_system_id dmi_lid_quirks[] = {
- {
- /*
- * Acer Switch 10 SW5-012. _LID method messes with home and
- * power button GPIO IRQ settings causing an interrupt storm on
- * both GPIOs. This is unfixable without a DSDT override, so we
- * have to disable the lid-switch functionality altogether :|
- */
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
- DMI_MATCH(DMI_PRODUCT_NAME, "Aspire SW5-012"),
- },
- .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_DISABLED,
- },
{
/* GP-electronic T701, _LID method points to a floating GPIO */
.matches = {
*/
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
- DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E2215T"),
+ },
+ .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
+ },
+ {
+ /*
+ * Medion Akoya E2228T, notification of the LID device only
+ * happens on close, not on open and _LID always returns closed.
+ */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MEDION"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E2228T"),
},
.driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN,
},
* between them).
*/
list_for_each_entry_reverse(dd, &ds->dependent_devices, list)
- dock_hotplug_event(dd, ACPI_NOTIFY_EJECT_REQUEST, false);
+ dock_hotplug_event(dd, ACPI_NOTIFY_EJECT_REQUEST,
+ DOCK_CALL_HANDLER);
list_for_each_entry_reverse(dd, &ds->dependent_devices, list)
acpi_bus_trim(dd->adev);
static const struct acpi_device_id pch_fivr_device_ids[] = {
{"INTC1045", 0},
+ {"INTC1049", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids);
{"INT3532", 0},
{"INTC1047", 0},
{"INTC1050", 0},
+ {"INTC1060", 0},
+ {"INTC1061", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
{"INT340A"},
{"INT340B"},
{"INTC1040"},
+ {"INTC1041"},
{"INTC1043"},
{"INTC1044"},
{"INTC1045"},
+ {"INTC1046"},
{"INTC1047"},
+ {"INTC1048"},
+ {"INTC1049"},
+ {"INTC1060"},
+ {"INTC1061"},
{""},
};
event.type = type;
event.data = data;
return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event)
- == NOTIFY_BAD) ? -EINVAL : 0;
+ == NOTIFY_BAD) ? -EINVAL : 0;
}
EXPORT_SYMBOL(acpi_notifier_call_chain);
switch (gsi) {
case 0 ... 255:
- sprintf(ev_name, "_%c%02hhX",
+ sprintf(ev_name, "_%c%02X",
trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi);
if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle)))
{"PNP0C0B", 0},
{"INT3404", 0},
{"INTC1044", 0},
+ {"INTC1048", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, fan_device_ids);
struct acpi_fan_fps *fps = &fan->fps[i];
snprintf(fps->name, ACPI_FPS_NAME_LEN, "state%d", i);
+ sysfs_attr_init(&fps->dev_attr.attr);
fps->dev_attr.show = show_state;
fps->dev_attr.store = NULL;
fps->dev_attr.attr.name = fps->name;
void acpi_power_add_remove_device(struct acpi_device *adev, bool add);
int acpi_power_wakeup_list_init(struct list_head *list, int *system_level);
int acpi_device_sleep_wake(struct acpi_device *dev,
- int enable, int sleep_state, int dev_state);
+ int enable, int sleep_state, int dev_state);
int acpi_power_get_inferred_state(struct acpi_device *device, int *state);
int acpi_power_on_resources(struct acpi_device *device, int state);
int acpi_power_transition(struct acpi_device *device, int state);
le16_to_cpu(nfit_dcr->dcr->code));
break;
}
- if (rc != ENXIO)
+ if (rc != -ENXIO)
break;
}
mutex_unlock(&acpi_desc->init_mutex);
* these commands.
*/
enum nfit_aux_cmds {
- NFIT_CMD_TRANSLATE_SPA = 5,
- NFIT_CMD_ARS_INJECT_SET = 7,
- NFIT_CMD_ARS_INJECT_CLEAR = 8,
- NFIT_CMD_ARS_INJECT_GET = 9,
+ NFIT_CMD_TRANSLATE_SPA = 5,
+ NFIT_CMD_ARS_INJECT_SET = 7,
+ NFIT_CMD_ARS_INJECT_CLEAR = 8,
+ NFIT_CMD_ARS_INJECT_GET = 9,
};
static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
nfit_blk->bdw_offset = nfit_mem->bdw->offset;
mmio = &nfit_blk->mmio[BDW];
mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address,
- nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
+ nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr));
if (!mmio->addr.base) {
dev_dbg(dev, "%s failed to map bdw\n",
nvdimm_name(nvdimm));
* configure the IRQ assigned to this slot|dev|pin. The 'source_index'
* indicates which resource descriptor in the resource template (of
* the link device) this interrupt is allocated from.
- *
+ *
* NOTE: Don't query the Link Device for IRQ information at this time
* because Link Device enumeration may not have occurred yet
* (e.g. exists somewhere 'below' this _PRT entry in the ACPI
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
* Copyright (C) 2002 Dominik Brodowski <devel@brodo.de>
*
- * TBD:
- * 1. Support more than one IRQ resource entry per link device (index).
+ * TBD:
+ * 1. Support more than one IRQ resource entry per link device (index).
* 2. Implement start/stop mechanism and use ACPI Bus Driver facilities
* for IRQ management (e.g. start()->_SRS).
*/
}
}
- /*
- * Query and parse _CRS to get the current IRQ assignment.
+ /*
+ * Query and parse _CRS to get the current IRQ assignment.
*/
status = acpi_walk_resources(link->device->handle, METHOD_NAME__CRS,
/*
* "acpi_irq_balance" (default in APIC mode) enables ACPI to use PIC Interrupt
* Link Devices to move the PIRQs around to minimize sharing.
- *
+ *
* "acpi_irq_nobalance" (default in PIC mode) tells ACPI not to move any PIC IRQs
* that the BIOS has already set to active. This is necessary because
* ACPI has no automatic means of knowing what ISA IRQs are used. Note that
*
* Note that PCI IRQ routers have a list of possible IRQs,
* which may not include the IRQs this table says are available.
- *
+ *
* Since this heuristic can't tell the difference between a link
* that no device will attach to, vs. a link which may be shared
* by multiple active devices -- it is not optimal.
{
if (!memcmp(f->oem_id, mcfg_oem_id, ACPI_OEM_ID_SIZE) &&
!memcmp(f->oem_table_id, mcfg_oem_table_id,
- ACPI_OEM_TABLE_ID_SIZE) &&
+ ACPI_OEM_TABLE_ID_SIZE) &&
f->oem_revision == mcfg_oem_revision &&
f->segment == segment &&
resource_contains(&f->bus_range, bus_range))
* 1. via "Device Specific (D-State) Control"
* 2. via "Power Resource Control".
* The code below deals with ACPI Power Resources control.
- *
+ *
* An ACPI "power resource object" represents a software controllable power
* plane, clock plane, or other resource depended on by a device.
*
* -ENODEV if the execution of either _DSW or _PSW has failed
*/
int acpi_device_sleep_wake(struct acpi_device *dev,
- int enable, int sleep_state, int dev_state)
+ int enable, int sleep_state, int dev_state)
{
union acpi_object in_arg[3];
struct acpi_object_list arg_list = { 3, in_arg };
/*
* Prepare a wakeup device, two steps (Ref ACPI 2.0:P229):
- * 1. Power on the power resources required for the wakeup device
+ * 1. Power on the power resources required for the wakeup device
* 2. Execute _DSW (Device Sleep Wake) or (deprecated in ACPI 3.0) _PSW (Power
* State Wake) for the device, if present
*/
(u32) px->control, (u32) px->status));
/*
- * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
+ * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq
*/
if (!px->core_frequency ||
((u32)(px->core_frequency * 1000) !=
goto err_ret;
/*
- * Now that we have _PSD data from all CPUs, lets setup P-state
+ * Now that we have _PSD data from all CPUs, lets setup P-state
* domain info.
*/
for_each_possible_cpu(i) {
if (match_pdomain->domain != pdomain->domain)
continue;
- match_pr->performance->shared_type =
+ match_pr->performance->shared_type =
pr->performance->shared_type;
cpumask_copy(match_pr->performance->shared_cpu_map,
pr->performance->shared_cpu_map);
state_readers[i].mode,
ACPI_SBS_BATTERY,
state_readers[i].command,
- (u8 *)battery +
+ (u8 *)battery +
state_readers[i].offset);
if (result)
goto end;
EXPORT_SYMBOL_GPL(acpi_smbus_write);
int acpi_smbus_register_callback(struct acpi_smb_hc *hc,
- smbus_alarm_callback callback, void *context)
+ smbus_alarm_callback callback, void *context)
{
mutex_lock(&hc->lock);
hc->callback = callback;
typedef void (*smbus_alarm_callback)(void *context);
extern int acpi_smbus_read(struct acpi_smb_hc *hc, u8 protocol, u8 address,
- u8 command, u8 * data);
+ u8 command, u8 *data);
extern int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 slave_address,
- u8 command, u8 * data, u8 length);
+ u8 command, u8 *data, u8 length);
extern int acpi_smbus_register_callback(struct acpi_smb_hc *hc,
- smbus_alarm_callback callback, void *context);
+ smbus_alarm_callback callback, void *context);
extern int acpi_smbus_unregister_callback(struct acpi_smb_hc *hc);
}
/**
- * acpi_dma_configure - Set-up DMA configuration for the device.
+ * acpi_dma_configure_id - Set-up DMA configuration for the device.
* @dev: The pointer to the device
* @attr: device dma attributes
* @input_id: input device id const value pointer
DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"),
},
},
- {
- .callback = video_detect_force_video,
- .ident = "ThinkPad X201T",
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
- },
- },
+ {
+ .callback = video_detect_force_video,
+ .ident = "ThinkPad X201T",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"),
+ },
+ },
/* The native backlight controls do not work on some older machines */
{
if (!dev->wakeup.flags.valid
|| sleep_state > (u32) dev->wakeup.sleep_state
|| !(device_may_wakeup(&dev->dev)
- || dev->wakeup.prepare_count))
+ || dev->wakeup.prepare_count))
continue;
if (device_may_wakeup(&dev->dev))
if (!dev->wakeup.flags.valid
|| sleep_state > (u32) dev->wakeup.sleep_state
|| !(device_may_wakeup(&dev->dev)
- || dev->wakeup.prepare_count))
+ || dev->wakeup.prepare_count))
continue;
acpi_set_gpe_wake_mask(dev->wakeup.gpe_device, dev->wakeup.gpe_number,
pp->dhfis_bits &= ~done_mask;
pp->dmafis_bits &= ~done_mask;
pp->sdbfis_bits |= done_mask;
- ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask);
+ ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask);
if (!ap->qc_active) {
DPRINTK("over\n");
if (push_scqe(card, vc, scq, &scqe, skb) != 0) {
atomic_inc(&vcc->stats->tx_err);
+ dma_unmap_single(&card->pcidev->dev, NS_PRV_DMA(skb), skb->len,
+ DMA_TO_DEVICE);
dev_kfree_skb_any(skb);
return -EIO;
}
dev_dbg(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_drop_link(link->consumer);
+ pm_runtime_drop_link(link);
list_del_rcu(&link->s_node);
list_del_rcu(&link->c_node);
dev_info(link->consumer, "Dropping the link to %s\n",
dev_name(link->supplier));
- if (link->flags & DL_FLAG_PM_RUNTIME)
- pm_runtime_drop_link(link->consumer);
+ pm_runtime_drop_link(link);
list_del(&link->s_node);
list_del(&link->c_node);
*/
void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
{
+ struct device *parent = dev->parent;
struct fwnode_handle *fn = dev->fwnode;
if (fwnode) {
} else {
if (fwnode_is_primary(fn)) {
dev->fwnode = fn->secondary;
- fn->secondary = NULL;
+ if (!(parent && fn == parent->fwnode))
+ fn->secondary = ERR_PTR(-ENODEV);
} else {
dev->fwnode = NULL;
}
drv = dev->driver;
if (drv) {
+ pm_runtime_get_sync(dev);
+
while (device_links_busy(dev)) {
__device_driver_unlock(dev, parent);
* have released the driver successfully while this one
* was waiting, so check for that.
*/
- if (dev->driver != drv)
+ if (dev->driver != drv) {
+ pm_runtime_put(dev);
return;
+ }
}
- pm_runtime_get_sync(dev);
- pm_runtime_clean_up_links(dev);
-
driver_sysfs_remove(dev);
if (dev->bus)
pm_runtime_reinit(dev);
}
-/**
- * pm_runtime_clean_up_links - Prepare links to consumers for driver removal.
- * @dev: Device whose driver is going to be removed.
- *
- * Check links from this device to any consumers and if any of them have active
- * runtime PM references to the device, drop the usage counter of the device
- * (as many times as needed).
- *
- * Links with the DL_FLAG_MANAGED flag unset are ignored.
- *
- * Since the device is guaranteed to be runtime-active at the point this is
- * called, nothing else needs to be done here.
- *
- * Moreover, this is called after device_links_busy() has returned 'false', so
- * the status of each link is guaranteed to be DL_STATE_SUPPLIER_UNBIND and
- * therefore rpm_active can't be manipulated concurrently.
- */
-void pm_runtime_clean_up_links(struct device *dev)
-{
- struct device_link *link;
- int idx;
-
- idx = device_links_read_lock();
-
- list_for_each_entry_rcu(link, &dev->links.consumers, s_node,
- device_links_read_lock_held()) {
- if (!(link->flags & DL_FLAG_MANAGED))
- continue;
-
- while (refcount_dec_not_one(&link->rpm_active))
- pm_runtime_put_noidle(dev);
- }
-
- device_links_read_unlock(idx);
-}
-
/**
* pm_runtime_get_suppliers - Resume and reference-count supplier devices.
* @dev: Consumer device.
spin_unlock_irq(&dev->power.lock);
}
-void pm_runtime_drop_link(struct device *dev)
+static void pm_runtime_drop_link_count(struct device *dev)
{
spin_lock_irq(&dev->power.lock);
WARN_ON(dev->power.links_count == 0);
spin_unlock_irq(&dev->power.lock);
}
+/**
+ * pm_runtime_drop_link - Prepare for device link removal.
+ * @link: Device link going away.
+ *
+ * Drop the link count of the consumer end of @link and decrement the supplier
+ * device's runtime PM usage counter as many times as needed to drop all of the
+ * PM runtime reference to it from the consumer.
+ */
+void pm_runtime_drop_link(struct device_link *link)
+{
+ if (!(link->flags & DL_FLAG_PM_RUNTIME))
+ return;
+
+ pm_runtime_drop_link_count(link->consumer);
+
+ while (refcount_dec_not_one(&link->rpm_active))
+ pm_runtime_put(link->supplier);
+}
+
static bool pm_runtime_need_not_resume(struct device *dev)
{
return atomic_read(&dev->power.usage_count) <= 1 &&
bd_set_nr_sectors(bdev, size);
- set_capacity_revalidate_and_notify(lo->lo_disk, size, false);
+ if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false))
+ kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
}
static inline int
}
}
-static void nbd_size_update(struct nbd_device *nbd)
+static void nbd_size_update(struct nbd_device *nbd, bool start)
{
struct nbd_config *config = nbd->config;
struct block_device *bdev = bdget_disk(nbd->disk, 0);
if (bdev) {
if (bdev->bd_disk) {
bd_set_nr_sectors(bdev, nr_sectors);
- set_blocksize(bdev, config->blksize);
+ if (start)
+ set_blocksize(bdev, config->blksize);
} else
set_bit(GD_NEED_PART_SCAN, &nbd->disk->state);
bdput(bdev);
config->blksize = blocksize;
config->bytesize = blocksize * nr_blocks;
if (nbd->task_recv != NULL)
- nbd_size_update(nbd);
+ nbd_size_update(nbd, false);
}
static void nbd_complete_rq(struct request *req)
args->index = i;
queue_work(nbd->recv_workq, &args->work);
}
- nbd_size_update(nbd);
+ nbd_size_update(nbd, true);
return error;
}
if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) &&
bdev->bd_openers == 0)
nbd_disconnect_and_put(nbd);
+ bdput(bdev);
nbd_config_put(nbd);
nbd_put(nbd);
unsigned int nr_zones_closed;
struct blk_zone *zones;
sector_t zone_size_sects;
+ spinlock_t zone_lock;
+ unsigned long *zone_locks;
unsigned long size; /* device size in MB */
unsigned long completion_nsec; /* time in ns to complete a request */
// SPDX-License-Identifier: GPL-2.0
#include <linux/vmalloc.h>
+#include <linux/bitmap.h>
#include "null_blk.h"
#define CREATE_TRACE_POINTS
if (!dev->zones)
return -ENOMEM;
+ /*
+ * With memory backing, the zone_lock spinlock needs to be temporarily
+ * released to avoid scheduling in atomic context. To guarantee zone
+ * information protection, use a bitmap to lock zones with
+ * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing
+ * implies that the queue is marked with BLK_MQ_F_BLOCKING.
+ */
+ spin_lock_init(&dev->zone_lock);
+ if (dev->memory_backed) {
+ dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
+ if (!dev->zone_locks) {
+ kvfree(dev->zones);
+ return -ENOMEM;
+ }
+ }
+
if (dev->zone_nr_conv >= dev->nr_zones) {
dev->zone_nr_conv = dev->nr_zones - 1;
pr_info("changed the number of conventional zones to %u",
void null_free_zoned_dev(struct nullb_device *dev)
{
+ bitmap_free(dev->zone_locks);
kvfree(dev->zones);
}
+static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
+{
+ if (dev->memory_backed)
+ wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
+ spin_lock_irq(&dev->zone_lock);
+}
+
+static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
+{
+ spin_unlock_irq(&dev->zone_lock);
+
+ if (dev->memory_backed)
+ clear_and_wake_up_bit(zno, dev->zone_locks);
+}
+
int null_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct nullb *nullb = disk->private_data;
struct nullb_device *dev = nullb->dev;
- unsigned int first_zone, i;
+ unsigned int first_zone, i, zno;
struct blk_zone zone;
int error;
nr_zones = min(nr_zones, dev->nr_zones - first_zone);
trace_nullb_report_zones(nullb, nr_zones);
- for (i = 0; i < nr_zones; i++) {
+ zno = first_zone;
+ for (i = 0; i < nr_zones; i++, zno++) {
/*
* Stacked DM target drivers will remap the zone information by
* modifying the zone information passed to the report callback.
* So use a local copy to avoid corruption of the device zone
* array.
*/
- memcpy(&zone, &dev->zones[first_zone + i],
- sizeof(struct blk_zone));
+ null_lock_zone(dev, zno);
+ memcpy(&zone, &dev->zones[zno], sizeof(struct blk_zone));
+ null_unlock_zone(dev, zno);
+
error = cb(&zone, i, data);
if (error)
return error;
return nr_zones;
}
+/*
+ * This is called in the case of memory backing from null_process_cmd()
+ * with the target zone already locked.
+ */
size_t null_zone_valid_read_len(struct nullb *nullb,
sector_t sector, unsigned int len)
{
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+ null_lock_zone(dev, zno);
+
switch (zone->cond) {
case BLK_ZONE_COND_FULL:
/* Cannot write to a full zone */
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
case BLK_ZONE_COND_EMPTY:
case BLK_ZONE_COND_CLOSED:
ret = null_check_zone_resources(dev, zone);
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
break;
case BLK_ZONE_COND_IMP_OPEN:
case BLK_ZONE_COND_EXP_OPEN:
break;
default:
/* Invalid zone condition */
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
}
/*
else
cmd->rq->__sector = sector;
} else if (sector != zone->wp) {
- return BLK_STS_IOERR;
+ ret = BLK_STS_IOERR;
+ goto unlock;
}
- if (zone->wp + nr_sectors > zone->start + zone->capacity)
- return BLK_STS_IOERR;
+ if (zone->wp + nr_sectors > zone->start + zone->capacity) {
+ ret = BLK_STS_IOERR;
+ goto unlock;
+ }
if (zone->cond == BLK_ZONE_COND_CLOSED) {
dev->nr_zones_closed--;
if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
zone->cond = BLK_ZONE_COND_IMP_OPEN;
+ /*
+ * Memory backing allocation may sleep: release the zone_lock spinlock
+ * to avoid scheduling in atomic context. Zone operation atomicity is
+ * still guaranteed through the zone_locks bitmap.
+ */
+ if (dev->memory_backed)
+ spin_unlock_irq(&dev->zone_lock);
ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+ if (dev->memory_backed)
+ spin_lock_irq(&dev->zone_lock);
+
if (ret != BLK_STS_OK)
- return ret;
+ goto unlock;
zone->wp += nr_sectors;
if (zone->wp == zone->start + zone->capacity) {
dev->nr_zones_imp_open--;
zone->cond = BLK_ZONE_COND_FULL;
}
- return BLK_STS_OK;
+ ret = BLK_STS_OK;
+
+unlock:
+ null_unlock_zone(dev, zno);
+
+ return ret;
}
static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zone)
sector_t sector)
{
struct nullb_device *dev = cmd->nq->dev;
- unsigned int zone_no = null_zone_no(dev, sector);
- struct blk_zone *zone = &dev->zones[zone_no];
- blk_status_t ret = BLK_STS_OK;
+ unsigned int zone_no;
+ struct blk_zone *zone;
+ blk_status_t ret;
size_t i;
+ if (op == REQ_OP_ZONE_RESET_ALL) {
+ for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
+ null_lock_zone(dev, i);
+ zone = &dev->zones[i];
+ if (zone->cond != BLK_ZONE_COND_EMPTY) {
+ null_reset_zone(dev, zone);
+ trace_nullb_zone_op(cmd, i, zone->cond);
+ }
+ null_unlock_zone(dev, i);
+ }
+ return BLK_STS_OK;
+ }
+
+ zone_no = null_zone_no(dev, sector);
+ zone = &dev->zones[zone_no];
+
+ null_lock_zone(dev, zone_no);
+
switch (op) {
- case REQ_OP_ZONE_RESET_ALL:
- for (i = dev->zone_nr_conv; i < dev->nr_zones; i++)
- null_reset_zone(dev, &dev->zones[i]);
- break;
case REQ_OP_ZONE_RESET:
ret = null_reset_zone(dev, zone);
break;
ret = null_finish_zone(dev, zone);
break;
default:
- return BLK_STS_NOTSUPP;
+ ret = BLK_STS_NOTSUPP;
+ break;
}
if (ret == BLK_STS_OK)
trace_nullb_zone_op(cmd, zone_no, zone->cond);
+ null_unlock_zone(dev, zone_no);
+
return ret;
}
blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
sector_t sector, sector_t nr_sectors)
{
+ struct nullb_device *dev = cmd->nq->dev;
+ unsigned int zno = null_zone_no(dev, sector);
+ blk_status_t sts;
+
switch (op) {
case REQ_OP_WRITE:
- return null_zone_write(cmd, sector, nr_sectors, false);
+ sts = null_zone_write(cmd, sector, nr_sectors, false);
+ break;
case REQ_OP_ZONE_APPEND:
- return null_zone_write(cmd, sector, nr_sectors, true);
+ sts = null_zone_write(cmd, sector, nr_sectors, true);
+ break;
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_RESET_ALL:
case REQ_OP_ZONE_OPEN:
case REQ_OP_ZONE_CLOSE:
case REQ_OP_ZONE_FINISH:
- return null_zone_mgmt(cmd, op, sector);
+ sts = null_zone_mgmt(cmd, op, sector);
+ break;
default:
- return null_process_cmd(cmd, op, sector, nr_sectors);
+ null_lock_zone(dev, zno);
+ sts = null_process_cmd(cmd, op, sector, nr_sectors);
+ null_unlock_zone(dev, zno);
}
+
+ return sts;
}
#define ACE_FSM_NUM_STATES 11
/* Set flag to exit FSM loop and reschedule tasklet */
-static inline void ace_fsm_yield(struct ace_device *ace)
+static inline void ace_fsm_yieldpoll(struct ace_device *ace)
{
- dev_dbg(ace->dev, "ace_fsm_yield()\n");
tasklet_schedule(&ace->fsm_tasklet);
ace->fsm_continue_flag = 0;
}
+static inline void ace_fsm_yield(struct ace_device *ace)
+{
+ dev_dbg(ace->dev, "%s()\n", __func__);
+ ace_fsm_yieldpoll(ace);
+}
+
/* Set flag to exit FSM loop and wait for IRQ to reschedule tasklet */
static inline void ace_fsm_yieldirq(struct ace_device *ace)
{
dev_dbg(ace->dev, "ace_fsm_yieldirq()\n");
- if (!ace->irq)
- /* No IRQ assigned, so need to poll */
- tasklet_schedule(&ace->fsm_tasklet);
- ace->fsm_continue_flag = 0;
+ if (ace->irq > 0)
+ ace->fsm_continue_flag = 0;
+ else
+ ace_fsm_yieldpoll(ace);
}
static bool ace_has_next_request(struct request_queue *q)
ACE_CTRL_DATABUFRDYIRQ | ACE_CTRL_ERRORIRQ);
/* Now we can hook up the irq handler */
- if (ace->irq) {
+ if (ace->irq > 0) {
rc = request_irq(ace->irq, ace_interrupt, 0, "systemace", ace);
if (rc) {
/* Failure - fall back to polled mode */
dev_err(ace->dev, "request_irq failed\n");
- ace->irq = 0;
+ ace->irq = rc;
}
}
tasklet_kill(&ace->fsm_tasklet);
- if (ace->irq)
+ if (ace->irq > 0)
free_irq(ace->irq, ace);
iounmap(ace->baseaddr);
int rc;
dev_dbg(dev, "ace_alloc(%p)\n", dev);
- if (!physaddr) {
- rc = -ENODEV;
- goto err_noreg;
- }
-
/* Allocate and initialize the ace device structure */
ace = kzalloc(sizeof(struct ace_device), GFP_KERNEL);
if (!ace) {
dev_set_drvdata(dev, NULL);
kfree(ace);
err_alloc:
-err_noreg:
dev_err(dev, "could not initialize device, err=%i\n", rc);
return rc;
}
static int ace_probe(struct platform_device *dev)
{
- resource_size_t physaddr = 0;
int bus_width = ACE_BUS_WIDTH_16; /* FIXME: should not be hard coded */
+ resource_size_t physaddr;
+ struct resource *res;
u32 id = dev->id;
- int irq = 0;
+ int irq;
int i;
dev_dbg(&dev->dev, "ace_probe(%p)\n", dev);
if (of_find_property(dev->dev.of_node, "8-bit", NULL))
bus_width = ACE_BUS_WIDTH_8;
- for (i = 0; i < dev->num_resources; i++) {
- if (dev->resource[i].flags & IORESOURCE_MEM)
- physaddr = dev->resource[i].start;
- if (dev->resource[i].flags & IORESOURCE_IRQ)
- irq = dev->resource[i].start;
- }
+ res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -EINVAL;
+
+ physaddr = res->start;
+ if (!physaddr)
+ return -ENODEV;
+
+ irq = platform_get_irq_optional(dev, 0);
/* Call the bus-independent setup code */
return ace_alloc(&dev->dev, id, physaddr, irq, bus_width);
struct intel_tlv {
u8 type;
u8 len;
- u8 val[0];
+ u8 val[];
} __packed;
struct intel_version_tlv {
u32 sysc_mask, syss_done, rstval;
int syss_offset, error = 0;
+ if (ddata->cap->regbits->srst_shift < 0)
+ return 0;
+
syss_offset = ddata->offsets[SYSC_SYSSTATUS];
sysc_mask = BIT(ddata->cap->regbits->srst_shift);
return error;
}
}
- error = sysc_wait_softreset(ddata);
- if (error)
- dev_warn(ddata->dev, "OCP softreset timed out\n");
+ /*
+ * Some modules like i2c and hdq1w have unusable reset status unless
+ * the module reset quirk is enabled. Skip status check on enable.
+ */
+ if (!(ddata->cfg.quirks & SYSC_MODULE_QUIRK_ENA_RESETDONE)) {
+ error = sysc_wait_softreset(ddata);
+ if (error)
+ dev_warn(ddata->dev, "OCP softreset timed out\n");
+ }
if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET)
sysc_disable_opt_clocks(ddata);
SYSC_QUIRK("hdmi", 0, 0, 0x10, -ENODEV, 0x50030200, 0xffffffff,
SYSC_QUIRK_OPT_CLKS_NEEDED),
SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff,
- SYSC_MODULE_QUIRK_HDQ1W),
+ SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE),
SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x0000000a, 0xffffffff,
- SYSC_MODULE_QUIRK_HDQ1W),
+ SYSC_MODULE_QUIRK_HDQ1W | SYSC_MODULE_QUIRK_ENA_RESETDONE),
SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000036, 0x000000ff,
- SYSC_MODULE_QUIRK_I2C),
+ SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x0000003c, 0x000000ff,
- SYSC_MODULE_QUIRK_I2C),
+ SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
SYSC_QUIRK("i2c", 0, 0, 0x20, 0x10, 0x00000040, 0x000000ff,
- SYSC_MODULE_QUIRK_I2C),
+ SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
SYSC_QUIRK("i2c", 0, 0, 0x10, 0x90, 0x5040000a, 0xfffff0f0,
- SYSC_MODULE_QUIRK_I2C),
+ SYSC_MODULE_QUIRK_I2C | SYSC_MODULE_QUIRK_ENA_RESETDONE),
SYSC_QUIRK("gpu", 0x50000000, 0x14, -ENODEV, -ENODEV, 0x00010201, 0xffffffff, 0),
SYSC_QUIRK("gpu", 0x50000000, 0xfe00, 0xfe10, -ENODEV, 0x40000000 , 0xffffffff,
SYSC_MODULE_QUIRK_SGX),
if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) &&
(ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE))
- return -EBUSY;
+ return -ENXIO;
return 0;
}
log_size = log_tbl->size;
memunmap(log_tbl);
+ if (!log_size) {
+ pr_warn("UEFI TPM log area empty\n");
+ return -EIO;
+ }
+
log_tbl = memremap(efi.tpm_log, sizeof(*log_tbl) + log_size,
MEMREMAP_WB);
if (!log_tbl) {
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/kernel.h>
+#include <linux/dmi.h>
#include "tpm.h"
#include "tpm_tis_core.h"
return container_of(data, struct tpm_tis_tcg_phy, priv);
}
-static bool interrupts = true;
-module_param(interrupts, bool, 0444);
+static int interrupts = -1;
+module_param(interrupts, int, 0444);
MODULE_PARM_DESC(interrupts, "Enable interrupts");
static bool itpm;
MODULE_PARM_DESC(force, "Force device probe rather than using ACPI entry");
#endif
+static int tpm_tis_disable_irq(const struct dmi_system_id *d)
+{
+ if (interrupts == -1) {
+ pr_notice("tpm_tis: %s detected: disabling interrupts.\n", d->ident);
+ interrupts = 0;
+ }
+
+ return 0;
+}
+
+static const struct dmi_system_id tpm_tis_dmi_table[] = {
+ {
+ .callback = tpm_tis_disable_irq,
+ .ident = "ThinkPad T490s",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"),
+ },
+ },
+ {}
+};
+
#if defined(CONFIG_PNP) && defined(CONFIG_ACPI)
static int has_hid(struct acpi_device *dev, const char *hid)
{
int irq = -1;
int rc;
+ dmi_check_system(tpm_tis_dmi_table);
+
rc = check_acpi_tpm2(dev);
if (rc)
return rc;
/*
* Allocate DMA memory from ancestor. When a virtio
* device is created by remoteproc, the DMA memory is
- * associated with the grandparent device:
- * vdev => rproc => platform-dev.
+ * associated with the parent device:
+ * virtioY => remoteprocX#vdevYbuffer.
*/
- if (!vdev->dev.parent || !vdev->dev.parent->parent)
+ buf->dev = vdev->dev.parent;
+ if (!buf->dev)
goto free_buf;
- buf->dev = vdev->dev.parent->parent;
/* Increase device refcnt to avoid freeing it */
get_device(buf->dev);
hws[IMX8MM_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mm_a53_core_sels, ARRAY_SIZE(imx8mm_a53_core_sels));
/* BUS */
- hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800);
+ hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800);
hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mm_enet_axi_sels, base + 0x8880);
- hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
+ hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980);
hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00);
hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite_bus("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80);
hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80);
hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00);
hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80);
- hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00);
- hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
+ hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mm_noc_sels, base + 0x8d00);
+ hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
/* AHB */
- hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
+ hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100);
/* IPG */
hws[IMX8MN_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mn_a53_core_sels, ARRAY_SIZE(imx8mn_a53_core_sels));
/* BUS */
- hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
+ hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mn_enet_axi_sels, base + 0x8880);
hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900);
hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00);
hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80);
hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00);
hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80);
- hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00);
+ hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mn_noc_sels, base + 0x8d00);
- hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
+ hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100);
hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
/* CORE SEL */
hws[IMX8MP_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", ccm_base + 0x9880, 24, 1, imx8mp_a53_core_sels, ARRAY_SIZE(imx8mp_a53_core_sels));
- hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
+ hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880);
- hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
+ hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980);
hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00);
hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80);
hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite_bus("hdmi_axi", imx8mp_media_axi_sels, ccm_base + 0x8b80);
hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00);
hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80);
- hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
- hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
+ hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
+ hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_bus_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite_bus("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00);
hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite_bus("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80);
- hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
+ hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100);
hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200);
hws[IMX8MQ_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mq_a53_core_sels, ARRAY_SIZE(imx8mq_a53_core_sels));
/* BUS */
- hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
+ hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mq_enet_axi_sels, base + 0x8880);
hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900);
hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980);
hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80);
hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00);
hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80);
- hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00);
- hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
+ hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mq_noc_sels, base + 0x8d00);
+ hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
/* AHB */
/* AHB clock is used by the AHB bus therefore marked as critical */
- hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
+ hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100);
/* IPG */
IMX_COMPOSITE_BUS, \
CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE)
+#define imx8m_clk_hw_composite_bus_critical(name, parent_names, reg) \
+ imx8m_clk_hw_composite_flags(name, parent_names, ARRAY_SIZE(parent_names), reg, \
+ IMX_COMPOSITE_BUS, \
+ CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE | CLK_IS_CRITICAL)
+
#define imx8m_clk_hw_composite_core(name, parent_names, reg) \
imx8m_clk_hw_composite_flags(name, parent_names, \
ARRAY_SIZE(parent_names), reg, \
void *data;
};
-#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw)
+static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw)
+{
+ return container_of(hw, struct clk_regmap, hw);
+}
/**
* struct clk_regmap_gate_data - regmap backed gate specific data
unsigned int enable_mask;
bool enable_is_inverted;
};
-#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw)
+
+static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw)
+{
+ return container_of(hw, struct clk_regmap, hw);
+}
int clk_is_enabled_regmap(struct clk_hw *hw);
int clk_enable_regmap(struct clk_hw *hw);
.reg_bits = 32,
.val_bits = 32,
.reg_stride = 4,
- .max_register = 0x24,
+ .max_register = QUPRD,
};
static const struct regmap_config ti_eqep_regmap16_config = {
.reg_bits = 16,
.val_bits = 16,
.reg_stride = 2,
- .max_register = 0x1e,
+ .max_register = QCPRDLAT,
};
static int ti_eqep_probe(struct platform_device *pdev)
config CPU_FREQ_DEFAULT_GOV_ONDEMAND
bool "ondemand"
+ depends on !(X86_INTEL_PSTATE && SMP)
select CPU_FREQ_GOV_ONDEMAND
select CPU_FREQ_GOV_PERFORMANCE
help
config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
bool "conservative"
+ depends on !(X86_INTEL_PSTATE && SMP)
select CPU_FREQ_GOV_CONSERVATIVE
select CPU_FREQ_GOV_PERFORMANCE
help
}
}
+/**
+ * cpufreq_driver_test_flags - Test cpufreq driver's flags against given ones.
+ * @flags: Flags to test against the current cpufreq driver's flags.
+ *
+ * Assumes that the driver is there, so callers must ensure that this is the
+ * case.
+ */
+bool cpufreq_driver_test_flags(u16 flags)
+{
+ return !!(cpufreq_driver->flags & flags);
+}
+
/**
* cpufreq_get_current_driver - return current driver's name
*
* exactly same freq is called again and so we can save on few function
* calls.
*/
- if (target_freq == policy->cur)
+ if (target_freq == policy->cur &&
+ !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS))
return 0;
/* Save last value to restore later on errors */
return -EINVAL;
/* Platform doesn't want dynamic frequency switching ? */
- if (policy->governor->dynamic_switching &&
+ if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING &&
cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) {
struct cpufreq_governor *gov = cpufreq_fallback_governor();
}
}
+ policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET);
+
return 0;
}
#define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_) \
{ \
.name = _name_, \
- .dynamic_switching = true, \
+ .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, \
.owner = THIS_MODULE, \
.init = cpufreq_dbs_governor_init, \
.exit = cpufreq_dbs_governor_exit, \
static struct cpufreq_governor cpufreq_gov_performance = {
.name = "performance",
.owner = THIS_MODULE,
+ .flags = CPUFREQ_GOV_STRICT_TARGET,
.limits = cpufreq_gov_performance_limits,
};
.name = "powersave",
.limits = cpufreq_gov_powersave_limits,
.owner = THIS_MODULE,
+ .flags = CPUFREQ_GOV_STRICT_TARGET,
};
MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
case EPS_BRAND_C3:
pr_cont("C3\n");
return -ENODEV;
- break;
}
/* Enable Enhanced PowerSaver */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
}
static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate,
- bool fast_switch)
+ bool strict, bool fast_switch)
{
u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev;
* field in it, so opportunistically update the max too if needed.
*/
value &= ~HWP_MAX_PERF(~0L);
- value |= HWP_MAX_PERF(cpu->max_perf_ratio);
+ value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio);
if (value == prev)
return;
pstate_funcs.get_val(cpu, target_pstate));
}
-static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate,
- bool fast_switch)
+static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy,
+ int target_pstate, bool fast_switch)
{
+ struct cpudata *cpu = all_cpu_data[policy->cpu];
int old_pstate = cpu->pstate.current_pstate;
target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
- if (target_pstate != old_pstate) {
+ if (hwp_active) {
+ intel_cpufreq_adjust_hwp(cpu, target_pstate,
+ policy->strict_target, fast_switch);
+ cpu->pstate.current_pstate = target_pstate;
+ } else if (target_pstate != old_pstate) {
+ intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch);
cpu->pstate.current_pstate = target_pstate;
- if (hwp_active)
- intel_cpufreq_adjust_hwp(cpu, target_pstate,
- fast_switch);
- else
- intel_cpufreq_adjust_perf_ctl(cpu, target_pstate,
- fast_switch);
}
intel_cpufreq_trace(cpu, fast_switch ? INTEL_PSTATE_TRACE_FAST_SWITCH :
break;
}
- target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false);
+ target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false);
freqs.new = target_pstate * cpu->pstate.scaling;
target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
- target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true);
+ target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true);
return target_pstate * cpu->pstate.scaling;
}
hwp_mode_bdw = id->driver_data;
intel_pstate.attr = hwp_cpufreq_attrs;
intel_cpufreq.attr = hwp_cpufreq_attrs;
+ intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
if (!default_driver)
default_driver = &intel_pstate;
break;
default:
return;
- break;
}
if (min_vid_speed >= highest_speed)
return;
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/clk-provider.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
#include <linux/cpumask.h>
static int scmi_cpufreq_probe(struct scmi_device *sdev)
{
int ret;
+ struct device *dev = &sdev->dev;
handle = sdev->handle;
if (!handle || !handle->perf_ops)
return -ENODEV;
+#ifdef CONFIG_COMMON_CLK
+ /* dummy clock provider as needed by OPP if clocks property is used */
+ if (of_find_property(dev->of_node, "#clock-cells", NULL))
+ devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, NULL);
+#endif
+
ret = cpufreq_register_driver(&scmi_cpufreq_driver);
if (ret) {
- dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n",
+ dev_err(dev, "%s: registering cpufreq failed, err: %d\n",
__func__, ret);
}
return pentium3_get_frequency(processor);
default:
return 0;
- };
+ }
return 0;
}
EXPORT_SYMBOL_GPL(speedstep_get_frequency);
struct tegra186_cpufreq_cluster {
const struct tegra186_cpufreq_cluster_info *info;
struct cpufreq_frequency_table *table;
+ u32 ref_clk_khz;
+ u32 div;
};
struct tegra186_cpufreq_data {
static unsigned int tegra186_cpufreq_get(unsigned int cpu)
{
- struct cpufreq_frequency_table *tbl;
+ struct tegra186_cpufreq_data *data = cpufreq_get_driver_data();
struct cpufreq_policy *policy;
void __iomem *edvd_reg;
unsigned int i, freq = 0;
if (!policy)
return 0;
- tbl = policy->freq_table;
edvd_reg = policy->driver_data;
ndiv = readl(edvd_reg) & EDVD_CORE_VOLT_FREQ_F_MASK;
- for (i = 0; tbl[i].frequency != CPUFREQ_TABLE_END; i++) {
- if ((tbl[i].driver_data & EDVD_CORE_VOLT_FREQ_F_MASK) == ndiv) {
- freq = tbl[i].frequency;
- break;
+ for (i = 0; i < data->num_clusters; i++) {
+ struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+ int core;
+
+ for (core = 0; core < ARRAY_SIZE(cluster->info->cpus); core++) {
+ if (cluster->info->cpus[core] != policy->cpu)
+ continue;
+
+ freq = (cluster->ref_clk_khz * ndiv) / cluster->div;
+ goto out;
}
}
+out:
cpufreq_cpu_put(policy);
return freq;
static struct cpufreq_frequency_table *init_vhint_table(
struct platform_device *pdev, struct tegra_bpmp *bpmp,
- unsigned int cluster_id)
+ struct tegra186_cpufreq_cluster *cluster)
{
struct cpufreq_frequency_table *table;
struct mrq_cpu_vhint_request req;
memset(&req, 0, sizeof(req));
req.addr = phys;
- req.cluster_id = cluster_id;
+ req.cluster_id = cluster->info->bpmp_cluster_id;
memset(&msg, 0, sizeof(msg));
msg.mrq = MRQ_CPU_VHINT;
goto free;
}
+ cluster->ref_clk_khz = data->ref_clk_hz / 1000;
+ cluster->div = data->pdiv * data->mdiv;
+
for (i = data->vfloor, j = 0; i <= data->vceil; i++) {
struct cpufreq_frequency_table *point;
u16 ndiv = data->ndiv[i];
point = &table[j++];
point->driver_data = edvd_val;
- point->frequency = data->ref_clk_hz * ndiv / data->pdiv /
- data->mdiv / 1000;
+ point->frequency = (cluster->ref_clk_khz * ndiv) / cluster->div;
}
table[j].frequency = CPUFREQ_TABLE_END;
struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
cluster->info = &tegra186_clusters[i];
- cluster->table = init_vhint_table(
- pdev, bpmp, cluster->info->bpmp_cluster_id);
+ cluster->table = init_vhint_table(pdev, bpmp, cluster);
if (IS_ERR(cluster->table)) {
err = PTR_ERR(cluster->table);
goto put_bpmp;
}
local_fiq_disable();
- tegra_pm_set_cpu_in_lp2();
+ RCU_NONIDLE(tegra_pm_set_cpu_in_lp2());
cpu_pm_enter();
switch (index) {
}
cpu_pm_exit();
- tegra_pm_clear_cpu_in_lp2();
+ RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2());
local_fiq_enable();
return err ?: index;
*
* This file add support for MD5 and SHA1/SHA224/SHA256/SHA384/SHA512.
*
- * You could find the datasheet in Documentation/arm/sunxi/README
+ * You could find the datasheet in Documentation/arm/sunxi.rst
*/
#include <linux/dma-mapping.h>
#include <linux/pm_runtime.h>
*
* This file handle the PRNG
*
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
*/
#include "sun8i-ce.h"
#include <linux/dma-mapping.h>
*
* This file handle the TRNG
*
- * You could find a link for the datasheet in Documentation/arm/sunxi/README
+ * You could find a link for the datasheet in Documentation/arm/sunxi.rst
*/
#include "sun8i-ce.h"
#include <linux/dma-mapping.h>
Say M if unsure.
config DEV_DAX_HMEM_DEVICES
- depends on NUMA_KEEP_MEMINFO # for phys_to_target_node()
depends on DEV_DAX_HMEM && DAX=y
def_bool y
help
Enable support for the Intel(R) IOP Series RAID engines.
-config INTEL_MIC_X100_DMA
- tristate "Intel MIC X100 DMA Driver"
- depends on 64BIT && X86 && INTEL_MIC_BUS
- select DMA_ENGINE
- help
- This enables DMA support for the Intel Many Integrated Core
- (MIC) family of PCIe form factor coprocessor X100 devices that
- run a 64 bit Linux OS. This driver will be used by both MIC
- host and card drivers.
-
- If you are building host kernel with a MIC device or a card
- kernel for a MIC device, then say M (recommended) or Y, else
- say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
config K3_DMA
tristate "Hisilicon K3 DMA support"
depends on ARCH_HI3xxx || ARCH_HISI || COMPILE_TEST
obj-$(CONFIG_INTEL_IOATDMA) += ioat/
obj-$(CONFIG_INTEL_IDXD) += idxd/
obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
-obj-$(CONFIG_INTEL_MIC_X100_DMA) += mic_x100_dma.o
obj-$(CONFIG_K3_DMA) += k3dma.o
obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
static int __dma_async_device_channel_register(struct dma_device *device,
struct dma_chan *chan)
{
- int rc = 0;
+ int rc;
chan->local = alloc_percpu(typeof(*chan->local));
if (!chan->local)
- goto err_out;
+ return -ENOMEM;
chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL);
if (!chan->dev) {
- free_percpu(chan->local);
- chan->local = NULL;
- goto err_out;
+ rc = -ENOMEM;
+ goto err_free_local;
}
/*
if (chan->chan_id < 0) {
pr_err("%s: unable to alloc ida for chan: %d\n",
__func__, chan->chan_id);
- goto err_out;
+ rc = chan->chan_id;
+ goto err_free_dev;
}
chan->dev->device.class = &dma_devclass;
mutex_lock(&device->chan_mutex);
ida_free(&device->chan_ida, chan->chan_id);
mutex_unlock(&device->chan_mutex);
- err_out:
- free_percpu(chan->local);
+ err_free_dev:
kfree(chan->dev);
+ err_free_local:
+ free_percpu(chan->local);
return rc;
}
resource_size_t start;
start = pci_resource_start(pdev, IDXD_WQ_BAR);
- start = start + wq->id * IDXD_PORTAL_SIZE;
+ start += idxd_get_wq_portal_full_offset(wq->id, IDXD_PORTAL_LIMITED);
wq->dportal = devm_ioremap(dev, start, IDXD_PORTAL_SIZE);
if (!wq->dportal)
int i, wq_offset;
lockdep_assert_held(&idxd->dev_lock);
- memset(&wq->wqcfg, 0, sizeof(wq->wqcfg));
+ memset(wq->wqcfg, 0, idxd->wqcfg_size);
wq->type = IDXD_WQT_NONE;
wq->size = 0;
wq->group = NULL;
clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
memset(wq->name, 0, WQ_NAME_SIZE);
- for (i = 0; i < 8; i++) {
- wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32);
+ for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
+ wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
iowrite32(0, idxd->reg_base + wq_offset);
dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
wq->id, i, wq_offset,
if (!wq->group)
return 0;
- memset(&wq->wqcfg, 0, sizeof(union wqcfg));
+ memset(wq->wqcfg, 0, idxd->wqcfg_size);
/* byte 0-3 */
- wq->wqcfg.wq_size = wq->size;
+ wq->wqcfg->wq_size = wq->size;
if (wq->size == 0) {
dev_warn(dev, "Incorrect work queue size: 0\n");
}
/* bytes 4-7 */
- wq->wqcfg.wq_thresh = wq->threshold;
+ wq->wqcfg->wq_thresh = wq->threshold;
/* byte 8-11 */
- wq->wqcfg.priv = !!(wq->type == IDXD_WQT_KERNEL);
- wq->wqcfg.mode = 1;
-
- wq->wqcfg.priority = wq->priority;
+ wq->wqcfg->priv = !!(wq->type == IDXD_WQT_KERNEL);
+ wq->wqcfg->mode = 1;
+ wq->wqcfg->priority = wq->priority;
/* bytes 12-15 */
- wq->wqcfg.max_xfer_shift = ilog2(wq->max_xfer_bytes);
- wq->wqcfg.max_batch_shift = ilog2(wq->max_batch_size);
+ wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
+ wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size);
dev_dbg(dev, "WQ %d CFGs\n", wq->id);
- for (i = 0; i < 8; i++) {
- wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32);
- iowrite32(wq->wqcfg.bits[i], idxd->reg_base + wq_offset);
+ for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
+ wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
+ iowrite32(wq->wqcfg->bits[i], idxd->reg_base + wq_offset);
dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
wq->id, i, wq_offset,
ioread32(idxd->reg_base + wq_offset));
u32 priority;
enum idxd_wq_state state;
unsigned long flags;
- union wqcfg wqcfg;
+ union wqcfg *wqcfg;
u32 vec_ptr; /* interrupt steering */
struct dsa_hw_desc **hw_descs;
int num_descs;
int max_wq_size;
int token_limit;
int nr_tokens; /* non-reserved tokens */
+ unsigned int wqcfg_size;
union sw_err_reg sw_err;
wait_queue_head_t cmd_waitq;
wq->idxd_cdev.minor = -1;
wq->max_xfer_bytes = idxd->max_xfer_bytes;
wq->max_batch_size = idxd->max_batch_size;
+ wq->wqcfg = devm_kzalloc(dev, idxd->wqcfg_size, GFP_KERNEL);
+ if (!wq->wqcfg)
+ return -ENOMEM;
}
for (i = 0; i < idxd->max_engines; i++) {
dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size);
idxd->max_wqs = idxd->hw.wq_cap.num_wqs;
dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs);
+ idxd->wqcfg_size = 1 << (idxd->hw.wq_cap.wqcfg_size + IDXD_WQCFG_MIN);
+ dev_dbg(dev, "wqcfg size: %u\n", idxd->wqcfg_size);
/* reading operation capabilities */
for (i = 0; i < 4; i++) {
#define IDXD_MMIO_BAR 0
#define IDXD_WQ_BAR 2
-#define IDXD_PORTAL_SIZE 0x4000
+#define IDXD_PORTAL_SIZE PAGE_SIZE
/* MMIO Device BAR0 Registers */
#define IDXD_VER_OFFSET 0x00
struct {
u64 total_wq_size:16;
u64 num_wqs:8;
- u64 rsvd:24;
+ u64 wqcfg_size:4;
+ u64 rsvd:20;
u64 shared_mode:1;
u64 dedicated_mode:1;
u64 rsvd2:1;
u64 bits;
} __packed;
#define IDXD_WQCAP_OFFSET 0x20
+#define IDXD_WQCFG_MIN 5
union group_cap_reg {
struct {
};
u32 bits[8];
} __packed;
+
+/*
+ * This macro calculates the offset into the WQCFG register
+ * idxd - struct idxd *
+ * n - wq id
+ * ofs - the index of the 32b dword for the config register
+ *
+ * The WQCFG register block is divided into groups per each wq. The n index
+ * allows us to move to the register group that's for that particular wq.
+ * Each register is 32bits. The ofs gives us the number of register to access.
+ */
+#define WQCFG_OFFSET(_idxd_dev, n, ofs) \
+({\
+ typeof(_idxd_dev) __idxd_dev = (_idxd_dev); \
+ (__idxd_dev)->wqcfg_offset + (n) * (__idxd_dev)->wqcfg_size + sizeof(u32) * (ofs); \
+})
+
+#define WQCFG_STRIDES(_idxd_dev) ((_idxd_dev)->wqcfg_size / sizeof(u32))
+
#endif
if (idxd->state != IDXD_DEV_ENABLED)
return -EIO;
- portal = wq->dportal + idxd_get_wq_portal_offset(IDXD_PORTAL_UNLIMITED);
+ portal = wq->dportal;
/*
* The wmb() flushes writes to coherent DMA data before possibly
* triggering a DMA read. The wmb() is necessary even on UP because
#define DCA2_TAG_MAP_BYTE3 0x82
#define DCA2_TAG_MAP_BYTE4 0x82
-/* verify if tag map matches expected values */
-static inline int dca2_tag_map_valid(u8 *tag_map)
-{
- return ((tag_map[0] == DCA2_TAG_MAP_BYTE0) &&
- (tag_map[1] == DCA2_TAG_MAP_BYTE1) &&
- (tag_map[2] == DCA2_TAG_MAP_BYTE2) &&
- (tag_map[3] == DCA2_TAG_MAP_BYTE3) &&
- (tag_map[4] == DCA2_TAG_MAP_BYTE4));
-}
-
/*
* "Legacy" DCA systems do not implement the DCA register set in the
* I/OAT device. Software needs direct support for their tag mappings.
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC X100 DMA Driver.
- *
- * Adapted from IOAT dma driver.
- */
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/seq_file.h>
-#include <linux/vmalloc.h>
-
-#include "mic_x100_dma.h"
-
-#define MIC_DMA_MAX_XFER_SIZE_CARD (1 * 1024 * 1024 -\
- MIC_DMA_ALIGN_BYTES)
-#define MIC_DMA_MAX_XFER_SIZE_HOST (1 * 1024 * 1024 >> 1)
-#define MIC_DMA_DESC_TYPE_SHIFT 60
-#define MIC_DMA_MEMCPY_LEN_SHIFT 46
-#define MIC_DMA_STAT_INTR_SHIFT 59
-
-/* high-water mark for pushing dma descriptors */
-static int mic_dma_pending_level = 4;
-
-/* Status descriptor is used to write a 64 bit value to a memory location */
-enum mic_dma_desc_format_type {
- MIC_DMA_MEMCPY = 1,
- MIC_DMA_STATUS,
-};
-
-static inline u32 mic_dma_hw_ring_inc(u32 val)
-{
- return (val + 1) % MIC_DMA_DESC_RX_SIZE;
-}
-
-static inline u32 mic_dma_hw_ring_dec(u32 val)
-{
- return val ? val - 1 : MIC_DMA_DESC_RX_SIZE - 1;
-}
-
-static inline void mic_dma_hw_ring_inc_head(struct mic_dma_chan *ch)
-{
- ch->head = mic_dma_hw_ring_inc(ch->head);
-}
-
-/* Prepare a memcpy desc */
-static inline void mic_dma_memcpy_desc(struct mic_dma_desc *desc,
- dma_addr_t src_phys, dma_addr_t dst_phys, u64 size)
-{
- u64 qw0, qw1;
-
- qw0 = src_phys;
- qw0 |= (size >> MIC_DMA_ALIGN_SHIFT) << MIC_DMA_MEMCPY_LEN_SHIFT;
- qw1 = MIC_DMA_MEMCPY;
- qw1 <<= MIC_DMA_DESC_TYPE_SHIFT;
- qw1 |= dst_phys;
- desc->qw0 = qw0;
- desc->qw1 = qw1;
-}
-
-/* Prepare a status desc. with @data to be written at @dst_phys */
-static inline void mic_dma_prep_status_desc(struct mic_dma_desc *desc, u64 data,
- dma_addr_t dst_phys, bool generate_intr)
-{
- u64 qw0, qw1;
-
- qw0 = data;
- qw1 = (u64) MIC_DMA_STATUS << MIC_DMA_DESC_TYPE_SHIFT | dst_phys;
- if (generate_intr)
- qw1 |= (1ULL << MIC_DMA_STAT_INTR_SHIFT);
- desc->qw0 = qw0;
- desc->qw1 = qw1;
-}
-
-static void mic_dma_cleanup(struct mic_dma_chan *ch)
-{
- struct dma_async_tx_descriptor *tx;
- u32 tail;
- u32 last_tail;
-
- spin_lock(&ch->cleanup_lock);
- tail = mic_dma_read_cmp_cnt(ch);
- /*
- * This is the barrier pair for smp_wmb() in fn.
- * mic_dma_tx_submit_unlock. It's required so that we read the
- * updated cookie value from tx->cookie.
- */
- smp_rmb();
- for (last_tail = ch->last_tail; tail != last_tail;) {
- tx = &ch->tx_array[last_tail];
- if (tx->cookie) {
- dma_cookie_complete(tx);
- dmaengine_desc_get_callback_invoke(tx, NULL);
- tx->callback = NULL;
- }
- last_tail = mic_dma_hw_ring_inc(last_tail);
- }
- /* finish all completion callbacks before incrementing tail */
- smp_mb();
- ch->last_tail = last_tail;
- spin_unlock(&ch->cleanup_lock);
-}
-
-static u32 mic_dma_ring_count(u32 head, u32 tail)
-{
- u32 count;
-
- if (head >= tail)
- count = (tail - 0) + (MIC_DMA_DESC_RX_SIZE - head);
- else
- count = tail - head;
- return count - 1;
-}
-
-/* Returns the num. of free descriptors on success, -ENOMEM on failure */
-static int mic_dma_avail_desc_ring_space(struct mic_dma_chan *ch, int required)
-{
- struct device *dev = mic_dma_ch_to_device(ch);
- u32 count;
-
- count = mic_dma_ring_count(ch->head, ch->last_tail);
- if (count < required) {
- mic_dma_cleanup(ch);
- count = mic_dma_ring_count(ch->head, ch->last_tail);
- }
-
- if (count < required) {
- dev_dbg(dev, "Not enough desc space");
- dev_dbg(dev, "%s %d required=%u, avail=%u\n",
- __func__, __LINE__, required, count);
- return -ENOMEM;
- } else {
- return count;
- }
-}
-
-/* Program memcpy descriptors into the descriptor ring and update s/w head ptr*/
-static int mic_dma_prog_memcpy_desc(struct mic_dma_chan *ch, dma_addr_t src,
- dma_addr_t dst, size_t len)
-{
- size_t current_transfer_len;
- size_t max_xfer_size = to_mic_dma_dev(ch)->max_xfer_size;
- /* 3 is added to make sure we have enough space for status desc */
- int num_desc = len / max_xfer_size + 3;
- int ret;
-
- if (len % max_xfer_size)
- num_desc++;
-
- ret = mic_dma_avail_desc_ring_space(ch, num_desc);
- if (ret < 0)
- return ret;
- do {
- current_transfer_len = min(len, max_xfer_size);
- mic_dma_memcpy_desc(&ch->desc_ring[ch->head],
- src, dst, current_transfer_len);
- mic_dma_hw_ring_inc_head(ch);
- len -= current_transfer_len;
- dst = dst + current_transfer_len;
- src = src + current_transfer_len;
- } while (len > 0);
- return 0;
-}
-
-/* It's a h/w quirk and h/w needs 2 status descriptors for every status desc */
-static void mic_dma_prog_intr(struct mic_dma_chan *ch)
-{
- mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
- ch->status_dest_micpa, false);
- mic_dma_hw_ring_inc_head(ch);
- mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
- ch->status_dest_micpa, true);
- mic_dma_hw_ring_inc_head(ch);
-}
-
-/* Wrapper function to program memcpy descriptors/status descriptors */
-static int mic_dma_do_dma(struct mic_dma_chan *ch, int flags, dma_addr_t src,
- dma_addr_t dst, size_t len)
-{
- if (len && -ENOMEM == mic_dma_prog_memcpy_desc(ch, src, dst, len)) {
- return -ENOMEM;
- } else {
- /* 3 is the maximum number of status descriptors */
- int ret = mic_dma_avail_desc_ring_space(ch, 3);
-
- if (ret < 0)
- return ret;
- }
-
- /* Above mic_dma_prog_memcpy_desc() makes sure we have enough space */
- if (flags & DMA_PREP_FENCE) {
- mic_dma_prep_status_desc(&ch->desc_ring[ch->head], 0,
- ch->status_dest_micpa, false);
- mic_dma_hw_ring_inc_head(ch);
- }
-
- if (flags & DMA_PREP_INTERRUPT)
- mic_dma_prog_intr(ch);
-
- return 0;
-}
-
-static inline void mic_dma_issue_pending(struct dma_chan *ch)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-
- spin_lock(&mic_ch->issue_lock);
- /*
- * Write to head triggers h/w to act on the descriptors.
- * On MIC, writing the same head value twice causes
- * a h/w error. On second write, h/w assumes we filled
- * the entire ring & overwrote some of the descriptors.
- */
- if (mic_ch->issued == mic_ch->submitted)
- goto out;
- mic_ch->issued = mic_ch->submitted;
- /*
- * make descriptor updates visible before advancing head,
- * this is purposefully not smp_wmb() since we are also
- * publishing the descriptor updates to a dma device
- */
- wmb();
- mic_dma_write_reg(mic_ch, MIC_DMA_REG_DHPR, mic_ch->issued);
-out:
- spin_unlock(&mic_ch->issue_lock);
-}
-
-static inline void mic_dma_update_pending(struct mic_dma_chan *ch)
-{
- if (mic_dma_ring_count(ch->issued, ch->submitted)
- > mic_dma_pending_level)
- mic_dma_issue_pending(&ch->api_ch);
-}
-
-static dma_cookie_t mic_dma_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(tx->chan);
- dma_cookie_t cookie;
-
- dma_cookie_assign(tx);
- cookie = tx->cookie;
- /*
- * We need an smp write barrier here because another CPU might see
- * an update to submitted and update h/w head even before we
- * assigned a cookie to this tx.
- */
- smp_wmb();
- mic_ch->submitted = mic_ch->head;
- spin_unlock(&mic_ch->prep_lock);
- mic_dma_update_pending(mic_ch);
- return cookie;
-}
-
-static inline struct dma_async_tx_descriptor *
-allocate_tx(struct mic_dma_chan *ch)
-{
- u32 idx = mic_dma_hw_ring_dec(ch->head);
- struct dma_async_tx_descriptor *tx = &ch->tx_array[idx];
-
- dma_async_tx_descriptor_init(tx, &ch->api_ch);
- tx->tx_submit = mic_dma_tx_submit_unlock;
- return tx;
-}
-
-/* Program a status descriptor with dst as address and value to be written */
-static struct dma_async_tx_descriptor *
-mic_dma_prep_status_lock(struct dma_chan *ch, dma_addr_t dst, u64 src_val,
- unsigned long flags)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- int result;
-
- spin_lock(&mic_ch->prep_lock);
- result = mic_dma_avail_desc_ring_space(mic_ch, 4);
- if (result < 0)
- goto error;
- mic_dma_prep_status_desc(&mic_ch->desc_ring[mic_ch->head], src_val, dst,
- false);
- mic_dma_hw_ring_inc_head(mic_ch);
- result = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
- if (result < 0)
- goto error;
-
- return allocate_tx(mic_ch);
-error:
- dev_err(mic_dma_ch_to_device(mic_ch),
- "Error enqueueing dma status descriptor, error=%d\n", result);
- spin_unlock(&mic_ch->prep_lock);
- return NULL;
-}
-
-/*
- * Prepare a memcpy descriptor to be added to the ring.
- * Note that the temporary descriptor adds an extra overhead of copying the
- * descriptor to ring. So, we copy directly to the descriptor ring
- */
-static struct dma_async_tx_descriptor *
-mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest,
- dma_addr_t dma_src, size_t len, unsigned long flags)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- struct device *dev = mic_dma_ch_to_device(mic_ch);
- int result;
-
- if (!len && !flags)
- return NULL;
-
- spin_lock(&mic_ch->prep_lock);
- result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len);
- if (result >= 0)
- return allocate_tx(mic_ch);
- dev_err(dev, "Error enqueueing dma, error=%d\n", result);
- spin_unlock(&mic_ch->prep_lock);
- return NULL;
-}
-
-static struct dma_async_tx_descriptor *
-mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- int ret;
-
- spin_lock(&mic_ch->prep_lock);
- ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0);
- if (!ret)
- return allocate_tx(mic_ch);
- spin_unlock(&mic_ch->prep_lock);
- return NULL;
-}
-
-/* Return the status of the transaction */
-static enum dma_status
-mic_dma_tx_status(struct dma_chan *ch, dma_cookie_t cookie,
- struct dma_tx_state *txstate)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
-
- if (DMA_COMPLETE != dma_cookie_status(ch, cookie, txstate))
- mic_dma_cleanup(mic_ch);
-
- return dma_cookie_status(ch, cookie, txstate);
-}
-
-static irqreturn_t mic_dma_thread_fn(int irq, void *data)
-{
- mic_dma_cleanup((struct mic_dma_chan *)data);
- return IRQ_HANDLED;
-}
-
-static irqreturn_t mic_dma_intr_handler(int irq, void *data)
-{
- struct mic_dma_chan *ch = ((struct mic_dma_chan *)data);
-
- mic_dma_ack_interrupt(ch);
- return IRQ_WAKE_THREAD;
-}
-
-static int mic_dma_alloc_desc_ring(struct mic_dma_chan *ch)
-{
- u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring);
- struct device *dev = &to_mbus_device(ch)->dev;
-
- desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES);
- ch->desc_ring = kzalloc(desc_ring_size, GFP_KERNEL);
-
- if (!ch->desc_ring)
- return -ENOMEM;
-
- ch->desc_ring_micpa = dma_map_single(dev, ch->desc_ring,
- desc_ring_size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, ch->desc_ring_micpa))
- goto map_error;
-
- ch->tx_array = vzalloc(array_size(MIC_DMA_DESC_RX_SIZE,
- sizeof(*ch->tx_array)));
- if (!ch->tx_array)
- goto tx_error;
- return 0;
-tx_error:
- dma_unmap_single(dev, ch->desc_ring_micpa, desc_ring_size,
- DMA_BIDIRECTIONAL);
-map_error:
- kfree(ch->desc_ring);
- return -ENOMEM;
-}
-
-static void mic_dma_free_desc_ring(struct mic_dma_chan *ch)
-{
- u64 desc_ring_size = MIC_DMA_DESC_RX_SIZE * sizeof(*ch->desc_ring);
-
- vfree(ch->tx_array);
- desc_ring_size = ALIGN(desc_ring_size, MIC_DMA_ALIGN_BYTES);
- dma_unmap_single(&to_mbus_device(ch)->dev, ch->desc_ring_micpa,
- desc_ring_size, DMA_BIDIRECTIONAL);
- kfree(ch->desc_ring);
- ch->desc_ring = NULL;
-}
-
-static void mic_dma_free_status_dest(struct mic_dma_chan *ch)
-{
- dma_unmap_single(&to_mbus_device(ch)->dev, ch->status_dest_micpa,
- L1_CACHE_BYTES, DMA_BIDIRECTIONAL);
- kfree(ch->status_dest);
-}
-
-static int mic_dma_alloc_status_dest(struct mic_dma_chan *ch)
-{
- struct device *dev = &to_mbus_device(ch)->dev;
-
- ch->status_dest = kzalloc(L1_CACHE_BYTES, GFP_KERNEL);
- if (!ch->status_dest)
- return -ENOMEM;
- ch->status_dest_micpa = dma_map_single(dev, ch->status_dest,
- L1_CACHE_BYTES, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(dev, ch->status_dest_micpa)) {
- kfree(ch->status_dest);
- ch->status_dest = NULL;
- return -ENOMEM;
- }
- return 0;
-}
-
-static int mic_dma_check_chan(struct mic_dma_chan *ch)
-{
- if (mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR) ||
- mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) & MIC_DMA_CHAN_QUIESCE) {
- mic_dma_disable_chan(ch);
- mic_dma_chan_mask_intr(ch);
- dev_err(mic_dma_ch_to_device(ch),
- "%s %d error setting up mic dma chan %d\n",
- __func__, __LINE__, ch->ch_num);
- return -EBUSY;
- }
- return 0;
-}
-
-static int mic_dma_chan_setup(struct mic_dma_chan *ch)
-{
- if (MIC_DMA_CHAN_MIC == ch->owner)
- mic_dma_chan_set_owner(ch);
- mic_dma_disable_chan(ch);
- mic_dma_chan_mask_intr(ch);
- mic_dma_write_reg(ch, MIC_DMA_REG_DCHERRMSK, 0);
- mic_dma_chan_set_desc_ring(ch);
- ch->last_tail = mic_dma_read_reg(ch, MIC_DMA_REG_DTPR);
- ch->head = ch->last_tail;
- ch->issued = 0;
- mic_dma_chan_unmask_intr(ch);
- mic_dma_enable_chan(ch);
- return mic_dma_check_chan(ch);
-}
-
-static void mic_dma_chan_destroy(struct mic_dma_chan *ch)
-{
- mic_dma_disable_chan(ch);
- mic_dma_chan_mask_intr(ch);
-}
-
-static int mic_dma_setup_irq(struct mic_dma_chan *ch)
-{
- ch->cookie =
- to_mbus_hw_ops(ch)->request_threaded_irq(to_mbus_device(ch),
- mic_dma_intr_handler, mic_dma_thread_fn,
- "mic dma_channel", ch, ch->ch_num);
- return PTR_ERR_OR_ZERO(ch->cookie);
-}
-
-static inline void mic_dma_free_irq(struct mic_dma_chan *ch)
-{
- to_mbus_hw_ops(ch)->free_irq(to_mbus_device(ch), ch->cookie, ch);
-}
-
-static int mic_dma_chan_init(struct mic_dma_chan *ch)
-{
- int ret = mic_dma_alloc_desc_ring(ch);
-
- if (ret)
- goto ring_error;
- ret = mic_dma_alloc_status_dest(ch);
- if (ret)
- goto status_error;
- ret = mic_dma_chan_setup(ch);
- if (ret)
- goto chan_error;
- return ret;
-chan_error:
- mic_dma_free_status_dest(ch);
-status_error:
- mic_dma_free_desc_ring(ch);
-ring_error:
- return ret;
-}
-
-static int mic_dma_drain_chan(struct mic_dma_chan *ch)
-{
- struct dma_async_tx_descriptor *tx;
- int err = 0;
- dma_cookie_t cookie;
-
- tx = mic_dma_prep_memcpy_lock(&ch->api_ch, 0, 0, 0, DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- goto error;
- }
-
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie))
- err = -ENOMEM;
- else
- err = dma_sync_wait(&ch->api_ch, cookie);
- if (err) {
- dev_err(mic_dma_ch_to_device(ch), "%s %d TO chan 0x%x\n",
- __func__, __LINE__, ch->ch_num);
- err = -EIO;
- }
-error:
- mic_dma_cleanup(ch);
- return err;
-}
-
-static inline void mic_dma_chan_uninit(struct mic_dma_chan *ch)
-{
- mic_dma_chan_destroy(ch);
- mic_dma_cleanup(ch);
- mic_dma_free_status_dest(ch);
- mic_dma_free_desc_ring(ch);
-}
-
-static int mic_dma_init(struct mic_dma_device *mic_dma_dev,
- enum mic_dma_chan_owner owner)
-{
- int i, first_chan = mic_dma_dev->start_ch;
- struct mic_dma_chan *ch;
- int ret;
-
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- ch = &mic_dma_dev->mic_ch[i];
- ch->ch_num = i;
- ch->owner = owner;
- spin_lock_init(&ch->cleanup_lock);
- spin_lock_init(&ch->prep_lock);
- spin_lock_init(&ch->issue_lock);
- ret = mic_dma_setup_irq(ch);
- if (ret)
- goto error;
- }
- return 0;
-error:
- for (i = i - 1; i >= first_chan; i--)
- mic_dma_free_irq(ch);
- return ret;
-}
-
-static void mic_dma_uninit(struct mic_dma_device *mic_dma_dev)
-{
- int i, first_chan = mic_dma_dev->start_ch;
- struct mic_dma_chan *ch;
-
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- ch = &mic_dma_dev->mic_ch[i];
- mic_dma_free_irq(ch);
- }
-}
-
-static int mic_dma_alloc_chan_resources(struct dma_chan *ch)
-{
- int ret = mic_dma_chan_init(to_mic_dma_chan(ch));
- if (ret)
- return ret;
- return MIC_DMA_DESC_RX_SIZE;
-}
-
-static void mic_dma_free_chan_resources(struct dma_chan *ch)
-{
- struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch);
- mic_dma_drain_chan(mic_ch);
- mic_dma_chan_uninit(mic_ch);
-}
-
-/* Set the fn. handlers and register the dma device with dma api */
-static int mic_dma_register_dma_device(struct mic_dma_device *mic_dma_dev,
- enum mic_dma_chan_owner owner)
-{
- int i, first_chan = mic_dma_dev->start_ch;
-
- dma_cap_zero(mic_dma_dev->dma_dev.cap_mask);
- /*
- * This dma engine is not capable of host memory to host memory
- * transfers
- */
- dma_cap_set(DMA_MEMCPY, mic_dma_dev->dma_dev.cap_mask);
-
- if (MIC_DMA_CHAN_HOST == owner)
- dma_cap_set(DMA_PRIVATE, mic_dma_dev->dma_dev.cap_mask);
- mic_dma_dev->dma_dev.device_alloc_chan_resources =
- mic_dma_alloc_chan_resources;
- mic_dma_dev->dma_dev.device_free_chan_resources =
- mic_dma_free_chan_resources;
- mic_dma_dev->dma_dev.device_tx_status = mic_dma_tx_status;
- mic_dma_dev->dma_dev.device_prep_dma_memcpy = mic_dma_prep_memcpy_lock;
- mic_dma_dev->dma_dev.device_prep_dma_imm_data =
- mic_dma_prep_status_lock;
- mic_dma_dev->dma_dev.device_prep_dma_interrupt =
- mic_dma_prep_interrupt_lock;
- mic_dma_dev->dma_dev.device_issue_pending = mic_dma_issue_pending;
- mic_dma_dev->dma_dev.copy_align = MIC_DMA_ALIGN_SHIFT;
- INIT_LIST_HEAD(&mic_dma_dev->dma_dev.channels);
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- mic_dma_dev->mic_ch[i].api_ch.device = &mic_dma_dev->dma_dev;
- dma_cookie_init(&mic_dma_dev->mic_ch[i].api_ch);
- list_add_tail(&mic_dma_dev->mic_ch[i].api_ch.device_node,
- &mic_dma_dev->dma_dev.channels);
- }
- return dmaenginem_async_device_register(&mic_dma_dev->dma_dev);
-}
-
-/*
- * Initializes dma channels and registers the dma device with the
- * dma engine api.
- */
-static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev,
- enum mic_dma_chan_owner owner)
-{
- struct mic_dma_device *mic_dma_dev;
- int ret;
- struct device *dev = &mbdev->dev;
-
- mic_dma_dev = devm_kzalloc(dev, sizeof(*mic_dma_dev), GFP_KERNEL);
- if (!mic_dma_dev) {
- ret = -ENOMEM;
- goto alloc_error;
- }
- mic_dma_dev->mbdev = mbdev;
- mic_dma_dev->dma_dev.dev = dev;
- mic_dma_dev->mmio = mbdev->mmio_va;
- if (MIC_DMA_CHAN_HOST == owner) {
- mic_dma_dev->start_ch = 0;
- mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_HOST;
- } else {
- mic_dma_dev->start_ch = 4;
- mic_dma_dev->max_xfer_size = MIC_DMA_MAX_XFER_SIZE_CARD;
- }
- ret = mic_dma_init(mic_dma_dev, owner);
- if (ret)
- goto init_error;
- ret = mic_dma_register_dma_device(mic_dma_dev, owner);
- if (ret)
- goto reg_error;
- return mic_dma_dev;
-reg_error:
- mic_dma_uninit(mic_dma_dev);
-init_error:
- mic_dma_dev = NULL;
-alloc_error:
- dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret);
- return mic_dma_dev;
-}
-
-static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev)
-{
- mic_dma_uninit(mic_dma_dev);
-}
-
-/* DEBUGFS CODE */
-static int mic_dma_reg_show(struct seq_file *s, void *pos)
-{
- struct mic_dma_device *mic_dma_dev = s->private;
- int i, chan_num, first_chan = mic_dma_dev->start_ch;
- struct mic_dma_chan *ch;
-
- seq_printf(s, "SBOX_DCR: %#x\n",
- mic_dma_mmio_read(&mic_dma_dev->mic_ch[first_chan],
- MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR));
- seq_puts(s, "DMA Channel Registers\n");
- seq_printf(s, "%-10s| %-10s %-10s %-10s %-10s %-10s",
- "Channel", "DCAR", "DTPR", "DHPR", "DRAR_HI", "DRAR_LO");
- seq_printf(s, " %-11s %-14s %-10s\n", "DCHERR", "DCHERRMSK", "DSTAT");
- for (i = first_chan; i < first_chan + MIC_DMA_NUM_CHAN; i++) {
- ch = &mic_dma_dev->mic_ch[i];
- chan_num = ch->ch_num;
- seq_printf(s, "%-10i| %-#10x %-#10x %-#10x %-#10x",
- chan_num,
- mic_dma_read_reg(ch, MIC_DMA_REG_DCAR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DTPR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DHPR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_HI));
- seq_printf(s, " %-#10x %-#10x %-#14x %-#10x\n",
- mic_dma_read_reg(ch, MIC_DMA_REG_DRAR_LO),
- mic_dma_read_reg(ch, MIC_DMA_REG_DCHERR),
- mic_dma_read_reg(ch, MIC_DMA_REG_DCHERRMSK),
- mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT));
- }
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_dma_reg);
-
-/* Debugfs parent dir */
-static struct dentry *mic_dma_dbg;
-
-static int mic_dma_driver_probe(struct mbus_device *mbdev)
-{
- struct mic_dma_device *mic_dma_dev;
- enum mic_dma_chan_owner owner;
-
- if (MBUS_DEV_DMA_MIC == mbdev->id.device)
- owner = MIC_DMA_CHAN_MIC;
- else
- owner = MIC_DMA_CHAN_HOST;
-
- mic_dma_dev = mic_dma_dev_reg(mbdev, owner);
- dev_set_drvdata(&mbdev->dev, mic_dma_dev);
-
- if (mic_dma_dbg) {
- mic_dma_dev->dbg_dir = debugfs_create_dir(dev_name(&mbdev->dev),
- mic_dma_dbg);
- debugfs_create_file("mic_dma_reg", 0444, mic_dma_dev->dbg_dir,
- mic_dma_dev, &mic_dma_reg_fops);
- }
- return 0;
-}
-
-static void mic_dma_driver_remove(struct mbus_device *mbdev)
-{
- struct mic_dma_device *mic_dma_dev;
-
- mic_dma_dev = dev_get_drvdata(&mbdev->dev);
- debugfs_remove_recursive(mic_dma_dev->dbg_dir);
- mic_dma_dev_unreg(mic_dma_dev);
-}
-
-static struct mbus_device_id id_table[] = {
- {MBUS_DEV_DMA_MIC, MBUS_DEV_ANY_ID},
- {MBUS_DEV_DMA_HOST, MBUS_DEV_ANY_ID},
- {0},
-};
-
-static struct mbus_driver mic_dma_driver = {
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = mic_dma_driver_probe,
- .remove = mic_dma_driver_remove,
-};
-
-static int __init mic_x100_dma_init(void)
-{
- int rc = mbus_register_driver(&mic_dma_driver);
- if (rc)
- return rc;
- mic_dma_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
- return 0;
-}
-
-static void __exit mic_x100_dma_exit(void)
-{
- debugfs_remove_recursive(mic_dma_dbg);
- mbus_unregister_driver(&mic_dma_driver);
-}
-
-module_init(mic_x100_dma_init);
-module_exit(mic_x100_dma_exit);
-
-MODULE_DEVICE_TABLE(mbus, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 DMA Driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC X100 DMA Driver.
- *
- * Adapted from IOAT dma driver.
- */
-#ifndef _MIC_X100_DMA_H_
-#define _MIC_X100_DMA_H_
-
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/mic_bus.h>
-
-#include "dmaengine.h"
-
-/*
- * MIC has a total of 8 dma channels.
- * Four channels are assigned for host SW use & the remaining for MIC SW.
- * MIC DMA transfer size & addresses need to be 64 byte aligned.
- */
-#define MIC_DMA_MAX_NUM_CHAN 8
-#define MIC_DMA_NUM_CHAN 4
-#define MIC_DMA_ALIGN_SHIFT DMAENGINE_ALIGN_64_BYTES
-#define MIC_DMA_ALIGN_BYTES (1 << MIC_DMA_ALIGN_SHIFT)
-#define MIC_DMA_DESC_RX_SIZE (128 * 1024 - 4)
-
-/*
- * Register descriptions
- * All the registers are 32 bit registers.
- * DCR is a global register and all others are per-channel.
- * DCR - bits 0, 2, 4, 6, 8, 10, 12, 14 - enable bits for channels 0 to 7
- * bits 1, 3, 5, 7, 9, 11, 13, 15 - owner bits for channels 0 to 7
- * DCAR - bit 24 & 25 interrupt masks for mic owned & host owned channels
- * DHPR - head of the descriptor ring updated by s/w
- * DTPR - tail of the descriptor ring updated by h/w
- * DRAR_LO - lower 32 bits of descriptor ring's mic address
- * DRAR_HI - 3:0 - remaining 4 bits of descriptor ring's mic address
- * 20:4 descriptor ring size
- * 25:21 mic smpt entry number
- * DSTAT - 16:0 h/w completion count; 31:28 dma engine status
- * DCHERR - this register is non-zero on error
- * DCHERRMSK - interrupt mask register
- */
-#define MIC_DMA_HW_CMP_CNT_MASK 0x1ffff
-#define MIC_DMA_CHAN_QUIESCE 0x20000000
-#define MIC_DMA_SBOX_BASE 0x00010000
-#define MIC_DMA_SBOX_DCR 0x0000A280
-#define MIC_DMA_SBOX_CH_BASE 0x0001A000
-#define MIC_DMA_SBOX_CHAN_OFF 0x40
-#define MIC_DMA_SBOX_DCAR_IM0 (0x1 << 24)
-#define MIC_DMA_SBOX_DCAR_IM1 (0x1 << 25)
-#define MIC_DMA_SBOX_DRARHI_SYS_MASK (0x1 << 26)
-#define MIC_DMA_REG_DCAR 0
-#define MIC_DMA_REG_DHPR 4
-#define MIC_DMA_REG_DTPR 8
-#define MIC_DMA_REG_DRAR_LO 20
-#define MIC_DMA_REG_DRAR_HI 24
-#define MIC_DMA_REG_DSTAT 32
-#define MIC_DMA_REG_DCHERR 44
-#define MIC_DMA_REG_DCHERRMSK 48
-
-/* HW dma desc */
-struct mic_dma_desc {
- u64 qw0;
- u64 qw1;
-};
-
-enum mic_dma_chan_owner {
- MIC_DMA_CHAN_MIC = 0,
- MIC_DMA_CHAN_HOST
-};
-
-/*
- * mic_dma_chan - channel specific information
- * @ch_num: channel number
- * @owner: owner of this channel
- * @last_tail: cached value of descriptor ring tail
- * @head: index of next descriptor in desc_ring
- * @issued: hardware notification point
- * @submitted: index that will be used to submit descriptors to h/w
- * @api_ch: dma engine api channel
- * @desc_ring: dma descriptor ring
- * @desc_ring_micpa: mic physical address of desc_ring
- * @status_dest: destination for status (fence) descriptor
- * @status_dest_micpa: mic address for status_dest,
- * DMA controller uses this address
- * @tx_array: array of async_tx
- * @cleanup_lock: lock held when processing completed tx
- * @prep_lock: lock held in prep_memcpy & released in tx_submit
- * @issue_lock: lock used to synchronize writes to head
- * @cookie: mic_irq cookie used with mic irq request
- */
-struct mic_dma_chan {
- int ch_num;
- enum mic_dma_chan_owner owner;
- u32 last_tail;
- u32 head;
- u32 issued;
- u32 submitted;
- struct dma_chan api_ch;
- struct mic_dma_desc *desc_ring;
- dma_addr_t desc_ring_micpa;
- u64 *status_dest;
- dma_addr_t status_dest_micpa;
- struct dma_async_tx_descriptor *tx_array;
- spinlock_t cleanup_lock;
- spinlock_t prep_lock;
- spinlock_t issue_lock;
- struct mic_irq *cookie;
-};
-
-/*
- * struct mic_dma_device - per mic device
- * @mic_ch: dma channels
- * @dma_dev: underlying dma device
- * @mbdev: mic bus dma device
- * @mmio: virtual address of the mmio space
- * @dbg_dir: debugfs directory
- * @start_ch: first channel number that can be used
- * @max_xfer_size: maximum transfer size per dma descriptor
- */
-struct mic_dma_device {
- struct mic_dma_chan mic_ch[MIC_DMA_MAX_NUM_CHAN];
- struct dma_device dma_dev;
- struct mbus_device *mbdev;
- void __iomem *mmio;
- struct dentry *dbg_dir;
- int start_ch;
- size_t max_xfer_size;
-};
-
-static inline struct mic_dma_chan *to_mic_dma_chan(struct dma_chan *ch)
-{
- return container_of(ch, struct mic_dma_chan, api_ch);
-}
-
-static inline struct mic_dma_device *to_mic_dma_dev(struct mic_dma_chan *ch)
-{
- return
- container_of((const typeof(((struct mic_dma_device *)0)->mic_ch)*)
- (ch - ch->ch_num), struct mic_dma_device, mic_ch);
-}
-
-static inline struct mbus_device *to_mbus_device(struct mic_dma_chan *ch)
-{
- return to_mic_dma_dev(ch)->mbdev;
-}
-
-static inline struct mbus_hw_ops *to_mbus_hw_ops(struct mic_dma_chan *ch)
-{
- return to_mbus_device(ch)->hw_ops;
-}
-
-static inline struct device *mic_dma_ch_to_device(struct mic_dma_chan *ch)
-{
- return to_mic_dma_dev(ch)->dma_dev.dev;
-}
-
-static inline void __iomem *mic_dma_chan_to_mmio(struct mic_dma_chan *ch)
-{
- return to_mic_dma_dev(ch)->mmio;
-}
-
-static inline u32 mic_dma_read_reg(struct mic_dma_chan *ch, u32 reg)
-{
- return ioread32(mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE +
- ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg);
-}
-
-static inline void mic_dma_write_reg(struct mic_dma_chan *ch, u32 reg, u32 val)
-{
- iowrite32(val, mic_dma_chan_to_mmio(ch) + MIC_DMA_SBOX_CH_BASE +
- ch->ch_num * MIC_DMA_SBOX_CHAN_OFF + reg);
-}
-
-static inline u32 mic_dma_mmio_read(struct mic_dma_chan *ch, u32 offset)
-{
- return ioread32(mic_dma_chan_to_mmio(ch) + offset);
-}
-
-static inline void mic_dma_mmio_write(struct mic_dma_chan *ch, u32 val,
- u32 offset)
-{
- iowrite32(val, mic_dma_chan_to_mmio(ch) + offset);
-}
-
-static inline u32 mic_dma_read_cmp_cnt(struct mic_dma_chan *ch)
-{
- return mic_dma_read_reg(ch, MIC_DMA_REG_DSTAT) &
- MIC_DMA_HW_CMP_CNT_MASK;
-}
-
-static inline void mic_dma_chan_set_owner(struct mic_dma_chan *ch)
-{
- u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
- u32 chan_num = ch->ch_num;
-
- dcr = (dcr & ~(0x1 << (chan_num * 2))) | (ch->owner << (chan_num * 2));
- mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static inline void mic_dma_enable_chan(struct mic_dma_chan *ch)
-{
- u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-
- dcr |= 2 << (ch->ch_num << 1);
- mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static inline void mic_dma_disable_chan(struct mic_dma_chan *ch)
-{
- u32 dcr = mic_dma_mmio_read(ch, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-
- dcr &= ~(2 << (ch->ch_num << 1));
- mic_dma_mmio_write(ch, dcr, MIC_DMA_SBOX_BASE + MIC_DMA_SBOX_DCR);
-}
-
-static void mic_dma_chan_set_desc_ring(struct mic_dma_chan *ch)
-{
- u32 drar_hi;
- dma_addr_t desc_ring_micpa = ch->desc_ring_micpa;
-
- drar_hi = (MIC_DMA_DESC_RX_SIZE & 0x1ffff) << 4;
- if (MIC_DMA_CHAN_MIC == ch->owner) {
- drar_hi |= (desc_ring_micpa >> 32) & 0xf;
- } else {
- drar_hi |= MIC_DMA_SBOX_DRARHI_SYS_MASK;
- drar_hi |= ((desc_ring_micpa >> 34)
- & 0x1f) << 21;
- drar_hi |= (desc_ring_micpa >> 32) & 0x3;
- }
- mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_LO, (u32) desc_ring_micpa);
- mic_dma_write_reg(ch, MIC_DMA_REG_DRAR_HI, drar_hi);
-}
-
-static inline void mic_dma_chan_mask_intr(struct mic_dma_chan *ch)
-{
- u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR);
-
- if (MIC_DMA_CHAN_MIC == ch->owner)
- dcar |= MIC_DMA_SBOX_DCAR_IM0;
- else
- dcar |= MIC_DMA_SBOX_DCAR_IM1;
- mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar);
-}
-
-static inline void mic_dma_chan_unmask_intr(struct mic_dma_chan *ch)
-{
- u32 dcar = mic_dma_read_reg(ch, MIC_DMA_REG_DCAR);
-
- if (MIC_DMA_CHAN_MIC == ch->owner)
- dcar &= ~MIC_DMA_SBOX_DCAR_IM0;
- else
- dcar &= ~MIC_DMA_SBOX_DCAR_IM1;
- mic_dma_write_reg(ch, MIC_DMA_REG_DCAR, dcar);
-}
-
-static void mic_dma_ack_interrupt(struct mic_dma_chan *ch)
-{
- if (MIC_DMA_CHAN_MIC == ch->owner) {
- /* HW errata */
- mic_dma_chan_mask_intr(ch);
- mic_dma_chan_unmask_intr(ch);
- }
- to_mbus_hw_ops(ch)->ack_interrupt(to_mbus_device(ch), ch->ch_num);
-}
-#endif
* If burst size is smaller than bus width then make sure we only
* transfer one at a time to avoid a burst stradling an MFIFO entry.
*/
- if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width)
+ if (burst * 8 < pl330->pcfg.data_bus_width)
desc->rqcfg.brst_len = 1;
desc->bytes_requested = len;
#define XUDMA_GET_PUT_RESOURCE(res) \
struct udma_##res *xudma_##res##_get(struct udma_dev *ud, int id) \
{ \
- return __udma_reserve_##res(ud, false, id); \
+ return __udma_reserve_##res(ud, UDMA_TP_NORMAL, id); \
} \
EXPORT_SYMBOL(xudma_##res##_get); \
\
}
}
+/* Currently used by omap2 & 3 to block deeper SoC idle states */
+static bool omap_dma_busy(struct omap_dmadev *od)
+{
+ struct omap_chan *c;
+ int lch = -1;
+
+ while (1) {
+ lch = find_next_bit(od->lch_bitmap, od->lch_count, lch + 1);
+ if (lch >= od->lch_count)
+ break;
+ c = od->lch_map[lch];
+ if (!c)
+ continue;
+ if (omap_dma_chan_read(c, CCR) & CCR_ENABLE)
+ return true;
+ }
+
+ return false;
+}
+
/* Currently only used for omap2. For omap1, also a check for lcd_dma is needed */
static int omap_dma_busy_notifier(struct notifier_block *nb,
unsigned long cmd, void *v)
{
struct omap_dmadev *od;
- struct omap_chan *c;
- int lch = -1;
od = container_of(nb, struct omap_dmadev, nb);
switch (cmd) {
case CPU_CLUSTER_PM_ENTER:
- while (1) {
- lch = find_next_bit(od->lch_bitmap, od->lch_count,
- lch + 1);
- if (lch >= od->lch_count)
- break;
- c = od->lch_map[lch];
- if (!c)
- continue;
- if (omap_dma_chan_read(c, CCR) & CCR_ENABLE)
- return NOTIFY_BAD;
- }
+ if (omap_dma_busy(od))
+ return NOTIFY_BAD;
break;
case CPU_CLUSTER_PM_ENTER_FAILED:
case CPU_CLUSTER_PM_EXIT:
switch (cmd) {
case CPU_CLUSTER_PM_ENTER:
+ if (omap_dma_busy(od))
+ return NOTIFY_BAD;
omap_dma_context_save(od);
break;
case CPU_CLUSTER_PM_ENTER_FAILED:
#define to_dma_tx_descriptor(tx) \
container_of(tx, struct xilinx_dma_tx_descriptor, async_tx)
#define xilinx_dma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \
- readl_poll_timeout(chan->xdev->regs + chan->ctrl_offset + reg, val, \
- cond, delay_us, timeout_us)
+ readl_poll_timeout_atomic(chan->xdev->regs + chan->ctrl_offset + reg, \
+ val, cond, delay_us, timeout_us)
/* IO accessors */
static inline u32 dma_read(struct xilinx_dma_chan *chan, u32 reg)
{
struct xilinx_cdma_tx_segment *cdma_seg;
struct xilinx_axidma_tx_segment *axidma_seg;
+ struct xilinx_aximcdma_tx_segment *aximcdma_seg;
struct xilinx_cdma_desc_hw *cdma_hw;
struct xilinx_axidma_desc_hw *axidma_hw;
+ struct xilinx_aximcdma_desc_hw *aximcdma_hw;
struct list_head *entry;
u32 residue = 0;
cdma_hw = &cdma_seg->hw;
residue += (cdma_hw->control - cdma_hw->status) &
chan->xdev->max_buffer_len;
- } else {
+ } else if (chan->xdev->dma_config->dmatype ==
+ XDMA_TYPE_AXIDMA) {
axidma_seg = list_entry(entry,
struct xilinx_axidma_tx_segment,
node);
axidma_hw = &axidma_seg->hw;
residue += (axidma_hw->control - axidma_hw->status) &
chan->xdev->max_buffer_len;
+ } else {
+ aximcdma_seg =
+ list_entry(entry,
+ struct xilinx_aximcdma_tx_segment,
+ node);
+ aximcdma_hw = &aximcdma_seg->hw;
+ residue +=
+ (aximcdma_hw->control - aximcdma_hw->status) &
+ chan->xdev->max_buffer_len;
}
}
upper_32_bits(chan->seg_p + sizeof(*chan->seg_mv) *
((i + 1) % XILINX_DMA_NUM_DESCS));
chan->seg_mv[i].phys = chan->seg_p +
- sizeof(*chan->seg_v) * i;
+ sizeof(*chan->seg_mv) * i;
list_add_tail(&chan->seg_mv[i].node,
&chan->free_seg_list);
}
static void xilinx_mcdma_start_transfer(struct xilinx_dma_chan *chan)
{
struct xilinx_dma_tx_descriptor *head_desc, *tail_desc;
- struct xilinx_axidma_tx_segment *tail_segment;
+ struct xilinx_aximcdma_tx_segment *tail_segment;
u32 reg;
/*
tail_desc = list_last_entry(&chan->pending_list,
struct xilinx_dma_tx_descriptor, node);
tail_segment = list_last_entry(&tail_desc->segments,
- struct xilinx_axidma_tx_segment, node);
+ struct xilinx_aximcdma_tx_segment, node);
reg = dma_ctrl_read(chan, XILINX_MCDMA_CHAN_CR_OFFSET(chan->tdest));
struct xilinx_vdma_tx_segment *tail_segment;
struct xilinx_dma_tx_descriptor *tail_desc;
struct xilinx_axidma_tx_segment *axidma_tail_segment;
+ struct xilinx_aximcdma_tx_segment *aximcdma_tail_segment;
struct xilinx_cdma_tx_segment *cdma_tail_segment;
if (list_empty(&chan->pending_list))
struct xilinx_cdma_tx_segment,
node);
cdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
- } else {
+ } else if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
axidma_tail_segment = list_last_entry(&tail_desc->segments,
struct xilinx_axidma_tx_segment,
node);
axidma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
+ } else {
+ aximcdma_tail_segment =
+ list_last_entry(&tail_desc->segments,
+ struct xilinx_aximcdma_tx_segment,
+ node);
+ aximcdma_tail_segment->hw.next_desc = (u32)desc->async_tx.phys;
}
/*
chan->stop_transfer = xilinx_dma_stop_transfer;
}
- /* check if SG is enabled (only for AXIDMA and CDMA) */
+ /* check if SG is enabled (only for AXIDMA, AXIMCDMA, and CDMA) */
if (xdev->dma_config->dmatype != XDMA_TYPE_VDMA) {
- if (dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
- XILINX_DMA_DMASR_SG_MASK)
+ if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA ||
+ dma_ctrl_read(chan, XILINX_DMA_REG_DMASR) &
+ XILINX_DMA_DMASR_SG_MASK)
chan->has_sg = true;
dev_dbg(chan->dev, "ch %d: SG %s\n", chan->id,
chan->has_sg ? "enabled" : "disabled");
Support for error detection and correction on Freescale memory
controllers on Layerscape SoCs.
-config EDAC_MV64X60
- tristate "Marvell MV64x60"
- depends on MV64X60
- help
- Support for error detection and correction on the Marvell
- MV64360 and MV64460 chipsets.
-
config EDAC_PASEMI
tristate "PA Semi PWRficient"
depends on PPC_PASEMI && PCI
health, you should probably say 'Y' here.
config EDAC_ASPEED
- tristate "Aspeed AST 2500 SoC"
- depends on MACH_ASPEED_G5
+ tristate "Aspeed AST BMC SoC"
+ depends on ARCH_ASPEED
help
- Support for error detection and correction on the Aspeed AST 2500 SoC.
+ Support for error detection and correction on the Aspeed AST BMC SoC.
First, ECC must be configured in the bootloader. Then, this driver
will expose error counters via the EDAC kernel framework.
i10nm_edac-y := skx_common.o i10nm_base.o
obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o
-obj-$(CONFIG_EDAC_MV64X60) += mv64x60_edac.o
obj-$(CONFIG_EDAC_CELL) += cell_edac.o
obj-$(CONFIG_EDAC_PPC4XX) += ppc4xx_edac.o
obj-$(CONFIG_EDAC_AMD8111) += amd8111_edac.o
/* Per-node stuff */
static struct ecc_settings **ecc_stngs;
+/* Device for the PCI component */
+static struct device *pci_ctl_dev;
+
/*
* Valid scrub rates for the K8 hardware memory scrubber. We map the scrubbing
* bandwidth to a valid bit pattern. The 'set' operation finds the 'matching-
case 0x20:
case 0x21:
return 0;
- break;
case 0x22:
case 0x23:
return 1;
- break;
default:
return err_sym >> 4;
- break;
}
/* x8 symbols */
else
WARN(1, KERN_ERR "Invalid error symbol: 0x%x\n",
err_sym);
return -1;
- break;
-
case 0x11:
return 0;
- break;
case 0x12:
return 1;
- break;
default:
return err_sym >> 3;
- break;
}
return -1;
}
return -ENODEV;
}
+ if (!pci_ctl_dev)
+ pci_ctl_dev = &pvt->F0->dev;
+
edac_dbg(1, "F0: %s\n", pci_name(pvt->F0));
edac_dbg(1, "F3: %s\n", pci_name(pvt->F3));
edac_dbg(1, "F6: %s\n", pci_name(pvt->F6));
return -ENODEV;
}
+ if (!pci_ctl_dev)
+ pci_ctl_dev = &pvt->F2->dev;
+
edac_dbg(1, "F1: %s\n", pci_name(pvt->F1));
edac_dbg(1, "F2: %s\n", pci_name(pvt->F2));
edac_dbg(1, "F3: %s\n", pci_name(pvt->F3));
static void setup_pci_device(void)
{
- struct mem_ctl_info *mci;
- struct amd64_pvt *pvt;
-
if (pci_ctl)
return;
- mci = edac_mc_find(0);
- if (!mci)
- return;
-
- pvt = mci->pvt_info;
- if (pvt->umc)
- pci_ctl = edac_pci_create_generic_ctl(&pvt->F0->dev, EDAC_MOD_STR);
- else
- pci_ctl = edac_pci_create_generic_ctl(&pvt->F2->dev, EDAC_MOD_STR);
+ pci_ctl = edac_pci_create_generic_ctl(pci_ctl_dev, EDAC_MOD_STR);
if (!pci_ctl) {
pr_warn("%s(): Unable to create PCI control\n", __func__);
pr_warn("%s(): PCI error report via EDAC not set\n", __func__);
return 0;
err_pci:
+ pci_ctl_dev = NULL;
+
msrs_free(msrs);
msrs = NULL;
kfree(ecc_stngs);
ecc_stngs = NULL;
+ pci_ctl_dev = NULL;
+
msrs_free(msrs);
msrs = NULL;
}
static void amd76x_check(struct mem_ctl_info *mci)
{
struct amd76x_error_info info;
- edac_dbg(3, "\n");
amd76x_get_error_info(mci, &info);
amd76x_process_error_info(mci, &info, 1);
}
int rc;
/* retrieve info about physical memory from device tree */
- np = of_find_node_by_path("/memory");
+ np = of_find_node_by_name(NULL, "memory");
if (!np) {
dev_err(mci->pdev, "dt: missing /memory node\n");
return -ENODEV;
static const struct of_device_id aspeed_of_match[] = {
+ { .compatible = "aspeed,ast2400-sdram-edac" },
{ .compatible = "aspeed,ast2500-sdram-edac" },
+ { .compatible = "aspeed,ast2600-sdram-edac" },
{},
};
+MODULE_DEVICE_TABLE(of, aspeed_of_match);
static struct platform_driver aspeed_driver = {
.driver = {
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Stefan Schaeckeler <sschaeck@cisco.com>");
-MODULE_DESCRIPTION("Aspeed AST2500 EDAC driver");
+MODULE_DESCRIPTION("Aspeed BMC SoC EDAC driver");
MODULE_VERSION("1.0");
{
struct e752x_error_info info;
- edac_dbg(3, "\n");
e752x_get_error_info(mci, &info);
e752x_process_error_info(mci, &info, 1);
}
{
struct e7xxx_error_info info;
- edac_dbg(3, "\n");
e7xxx_get_error_info(mci, &info);
e7xxx_process_error_info(mci, &info, 1);
}
extern void edac_device_free_ctl_info(struct edac_device_ctl_info *ctl_info);
/**
- * edac_device_add_device: Insert the 'edac_dev' structure into the
+ * edac_device_add_device - Insert the 'edac_dev' structure into the
* edac_device global list and create sysfs entries associated with
* edac_device structure.
*
extern int edac_device_add_device(struct edac_device_ctl_info *edac_dev);
/**
- * edac_device_del_device:
- * Remove sysfs entries for specified edac_device structure and
- * then remove edac_device structure from global list
+ * edac_device_del_device - Remove sysfs entries for specified edac_device
+ * structure and then remove edac_device structure from global list
*
* @dev:
* Pointer to struct &device representing the edac device
extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev);
/**
- * Log correctable errors.
+ * edac_device_handle_ce_count - Log correctable errors.
*
* @edac_dev: pointer to struct &edac_device_ctl_info
* @inst_nr: number of the instance where the CE error happened
const char *msg);
/**
- * Log uncorrectable errors.
+ * edac_device_handle_ue_count - Log uncorrectable errors.
*
* @edac_dev: pointer to struct &edac_device_ctl_info
* @inst_nr: number of the instance where the CE error happened
[MEM_RDDR4] = "Registered-DDR4",
[MEM_LPDDR4] = "Low-Power-DDR4-RAM",
[MEM_LRDDR4] = "Load-Reduced-DDR4-RAM",
+ [MEM_DDR5] = "Unbuffered-DDR5",
[MEM_NVDIMM] = "Non-volatile-RAM",
[MEM_WIO2] = "Wide-IO-2",
};
*/
#include <linux/kernel.h>
+#include <linux/io.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include <asm/mce.h>
#include "edac_module.h"
#include "skx_common.h"
-#define I10NM_REVISION "v0.0.3"
+#define I10NM_REVISION "v0.0.4"
#define EDAC_MOD_STR "i10nm_edac"
/* Debug macros */
#define i10nm_printk(level, fmt, arg...) \
edac_printk(level, "i10nm", fmt, ##arg)
-#define I10NM_GET_SCK_BAR(d, reg) \
+#define I10NM_GET_SCK_BAR(d, reg) \
pci_read_config_dword((d)->uracu, 0xd0, &(reg))
#define I10NM_GET_IMC_BAR(d, i, reg) \
pci_read_config_dword((d)->uracu, 0xd8 + (i) * 4, &(reg))
#define I10NM_GET_DIMMMTR(m, i, j) \
- (*(u32 *)((m)->mbase + 0x2080c + (i) * 0x4000 + (j) * 4))
+ readl((m)->mbase + 0x2080c + (i) * (m)->chan_mmio_sz + (j) * 4)
#define I10NM_GET_MCDDRTCFG(m, i, j) \
- (*(u32 *)((m)->mbase + 0x20970 + (i) * 0x4000 + (j) * 4))
+ readl((m)->mbase + 0x20970 + (i) * (m)->chan_mmio_sz + (j) * 4)
+#define I10NM_GET_MCMTR(m, i) \
+ readl((m)->mbase + 0x20ef8 + (i) * (m)->chan_mmio_sz)
+#define I10NM_GET_AMAP(m, i) \
+ readl((m)->mbase + 0x20814 + (i) * (m)->chan_mmio_sz)
#define I10NM_GET_SCK_MMIO_BASE(reg) (GET_BITFIELD(reg, 0, 28) << 23)
#define I10NM_GET_IMC_MMIO_OFFSET(reg) (GET_BITFIELD(reg, 0, 10) << 12)
.type = I10NM,
.decs_did = 0x3452,
.busno_cfg_offset = 0xcc,
+ .ddr_chan_mmio_sz = 0x4000,
};
static struct res_config i10nm_cfg1 = {
.type = I10NM,
.decs_did = 0x3452,
.busno_cfg_offset = 0xd0,
+ .ddr_chan_mmio_sz = 0x4000,
+};
+
+static struct res_config spr_cfg = {
+ .type = SPR,
+ .decs_did = 0x3252,
+ .busno_cfg_offset = 0xd0,
+ .ddr_chan_mmio_sz = 0x8000,
+ .support_ddr5 = true,
};
static const struct x86_cpu_id i10nm_cpuids[] = {
X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x0, 0x3), &i10nm_cfg0),
X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0xf), &i10nm_cfg1),
X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x0, 0xf), &i10nm_cfg1),
+ X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SAPPHIRERAPIDS_X, X86_STEPPINGS(0x0, 0xf), &spr_cfg),
{}
};
MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids);
{
u32 mcmtr;
- mcmtr = *(u32 *)(imc->mbase + 0x20ef8 + chan * 0x4000);
+ mcmtr = I10NM_GET_MCMTR(imc, chan);
edac_dbg(1, "ch%d mcmtr reg %x\n", chan, mcmtr);
return !!GET_BITFIELD(mcmtr, 2, 2);
}
-static int i10nm_get_dimm_config(struct mem_ctl_info *mci)
+static int i10nm_get_dimm_config(struct mem_ctl_info *mci,
+ struct res_config *cfg)
{
struct skx_pvt *pvt = mci->pvt_info;
struct skx_imc *imc = pvt->imc;
+ u32 mtr, amap, mcddrtcfg;
struct dimm_info *dimm;
- u32 mtr, mcddrtcfg;
int i, j, ndimms;
for (i = 0; i < I10NM_NUM_CHANNELS; i++) {
continue;
ndimms = 0;
+ amap = I10NM_GET_AMAP(imc, i);
for (j = 0; j < I10NM_NUM_DIMMS; j++) {
dimm = edac_get_dimm(mci, i, j, 0);
mtr = I10NM_GET_DIMMMTR(imc, i, j);
mtr, mcddrtcfg, imc->mc, i, j);
if (IS_DIMM_PRESENT(mtr))
- ndimms += skx_get_dimm_info(mtr, 0, 0, dimm,
- imc, i, j);
+ ndimms += skx_get_dimm_info(mtr, 0, amap, dimm,
+ imc, i, j, cfg);
else if (IS_NVDIMM_PRESENT(mcddrtcfg, j))
ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
EDAC_MOD_STR);
d->imc[i].lmc = i;
d->imc[i].src_id = src_id;
d->imc[i].node_id = node_id;
+ d->imc[i].chan_mmio_sz = cfg->ddr_chan_mmio_sz;
rc = skx_register_mci(&d->imc[i], d->imc[i].mdev,
"Intel_10nm Socket", EDAC_MOD_STR,
- i10nm_get_dimm_config);
+ i10nm_get_dimm_config, cfg);
if (rc < 0)
goto fail;
}
{
struct i3000_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
i3000_get_error_info(mci, &info);
i3000_process_error_info(mci, &info, 1);
}
{
struct i3200_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
i3200_get_and_clear_error_info(mci, &info);
i3200_process_error_info(mci, &info);
}
static void i5000_check_error(struct mem_ctl_info *mci)
{
struct i5000_error_info info;
- edac_dbg(4, "MC%d\n", mci->mc_idx);
+
i5000_get_error_info(mci, &info);
i5000_process_error_info(mci, &info, 1);
}
static void i5400_check_error(struct mem_ctl_info *mci)
{
struct i5400_error_info info;
- edac_dbg(4, "MC%d\n", mci->mc_idx);
+
i5400_get_error_info(mci, &info);
i5400_process_error_info(mci, &info);
}
{
struct i82443bxgx_edacmc_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
i82443bxgx_edacmc_get_error_info(mci, &info);
i82443bxgx_edacmc_process_error_info(mci, &info, 1);
}
{
struct i82860_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
i82860_get_error_info(mci, &info);
i82860_process_error_info(mci, &info, 1);
}
{
struct i82875p_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
i82875p_get_error_info(mci, &info);
i82875p_process_error_info(mci, &info, 1);
}
{
struct i82975x_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
i82975x_get_error_info(mci, &info);
i82975x_process_error_info(mci, &info, 1);
}
{
struct ie31200_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
ie31200_get_and_clear_error_info(mci, &info);
ie31200_process_error_info(mci, &info);
}
+++ /dev/null
-/*
- * Marvell MV64x60 Memory Controller kernel module for PPC platforms
- *
- * Author: Dave Jiang <djiang@mvista.com>
- *
- * 2006-2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- *
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/edac.h>
-#include <linux/gfp.h>
-
-#include "edac_module.h"
-#include "mv64x60_edac.h"
-
-static const char *mv64x60_ctl_name = "MV64x60";
-static int edac_dev_idx;
-static int edac_pci_idx;
-static int edac_mc_idx;
-
-/*********************** PCI err device **********************************/
-#ifdef CONFIG_PCI
-static void mv64x60_pci_check(struct edac_pci_ctl_info *pci)
-{
- struct mv64x60_pci_pdata *pdata = pci->pvt_info;
- u32 cause;
-
- cause = readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE);
- if (!cause)
- return;
-
- printk(KERN_ERR "Error in PCI %d Interface\n", pdata->pci_hose);
- printk(KERN_ERR "Cause register: 0x%08x\n", cause);
- printk(KERN_ERR "Address Low: 0x%08x\n",
- readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_LO));
- printk(KERN_ERR "Address High: 0x%08x\n",
- readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ADDR_HI));
- printk(KERN_ERR "Attribute: 0x%08x\n",
- readl(pdata->pci_vbase + MV64X60_PCI_ERROR_ATTR));
- printk(KERN_ERR "Command: 0x%08x\n",
- readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CMD));
- writel(~cause, pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE);
-
- if (cause & MV64X60_PCI_PE_MASK)
- edac_pci_handle_pe(pci, pci->ctl_name);
-
- if (!(cause & MV64X60_PCI_PE_MASK))
- edac_pci_handle_npe(pci, pci->ctl_name);
-}
-
-static irqreturn_t mv64x60_pci_isr(int irq, void *dev_id)
-{
- struct edac_pci_ctl_info *pci = dev_id;
- struct mv64x60_pci_pdata *pdata = pci->pvt_info;
- u32 val;
-
- val = readl(pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE);
- if (!val)
- return IRQ_NONE;
-
- mv64x60_pci_check(pci);
-
- return IRQ_HANDLED;
-}
-
-/*
- * Bit 0 of MV64x60_PCIx_ERR_MASK does not exist on the 64360 and because of
- * errata FEr-#11 and FEr-##16 for the 64460, it should be 0 on that chip as
- * well. IOW, don't set bit 0.
- */
-
-/* Erratum FEr PCI-#16: clear bit 0 of PCI SERRn Mask reg. */
-static int __init mv64x60_pci_fixup(struct platform_device *pdev)
-{
- struct resource *r;
- void __iomem *pci_serr;
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- if (!r) {
- printk(KERN_ERR "%s: Unable to get resource for "
- "PCI err regs\n", __func__);
- return -ENOENT;
- }
-
- pci_serr = ioremap(r->start, resource_size(r));
- if (!pci_serr)
- return -ENOMEM;
-
- writel(readl(pci_serr) & ~0x1, pci_serr);
- iounmap(pci_serr);
-
- return 0;
-}
-
-static int mv64x60_pci_err_probe(struct platform_device *pdev)
-{
- struct edac_pci_ctl_info *pci;
- struct mv64x60_pci_pdata *pdata;
- struct resource *r;
- int res = 0;
-
- if (!devres_open_group(&pdev->dev, mv64x60_pci_err_probe, GFP_KERNEL))
- return -ENOMEM;
-
- pci = edac_pci_alloc_ctl_info(sizeof(*pdata), "mv64x60_pci_err");
- if (!pci)
- return -ENOMEM;
-
- pdata = pci->pvt_info;
-
- pdata->pci_hose = pdev->id;
- pdata->name = "mv64x60_pci_err";
- platform_set_drvdata(pdev, pci);
- pci->dev = &pdev->dev;
- pci->dev_name = dev_name(&pdev->dev);
- pci->mod_name = EDAC_MOD_STR;
- pci->ctl_name = pdata->name;
-
- if (edac_op_state == EDAC_OPSTATE_POLL)
- pci->edac_check = mv64x60_pci_check;
-
- pdata->edac_idx = edac_pci_idx++;
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!r) {
- printk(KERN_ERR "%s: Unable to get resource for "
- "PCI err regs\n", __func__);
- res = -ENOENT;
- goto err;
- }
-
- if (!devm_request_mem_region(&pdev->dev,
- r->start,
- resource_size(r),
- pdata->name)) {
- printk(KERN_ERR "%s: Error while requesting mem region\n",
- __func__);
- res = -EBUSY;
- goto err;
- }
-
- pdata->pci_vbase = devm_ioremap(&pdev->dev,
- r->start,
- resource_size(r));
- if (!pdata->pci_vbase) {
- printk(KERN_ERR "%s: Unable to setup PCI err regs\n", __func__);
- res = -ENOMEM;
- goto err;
- }
-
- res = mv64x60_pci_fixup(pdev);
- if (res < 0) {
- printk(KERN_ERR "%s: PCI fixup failed\n", __func__);
- goto err;
- }
-
- writel(0, pdata->pci_vbase + MV64X60_PCI_ERROR_CAUSE);
- writel(0, pdata->pci_vbase + MV64X60_PCI_ERROR_MASK);
- writel(MV64X60_PCIx_ERR_MASK_VAL,
- pdata->pci_vbase + MV64X60_PCI_ERROR_MASK);
-
- if (edac_pci_add_device(pci, pdata->edac_idx) > 0) {
- edac_dbg(3, "failed edac_pci_add_device()\n");
- goto err;
- }
-
- if (edac_op_state == EDAC_OPSTATE_INT) {
- pdata->irq = platform_get_irq(pdev, 0);
- res = devm_request_irq(&pdev->dev,
- pdata->irq,
- mv64x60_pci_isr,
- 0,
- "[EDAC] PCI err",
- pci);
- if (res < 0) {
- printk(KERN_ERR "%s: Unable to request irq %d for "
- "MV64x60 PCI ERR\n", __func__, pdata->irq);
- res = -ENODEV;
- goto err2;
- }
- printk(KERN_INFO EDAC_MOD_STR " acquired irq %d for PCI Err\n",
- pdata->irq);
- }
-
- devres_remove_group(&pdev->dev, mv64x60_pci_err_probe);
-
- /* get this far and it's successful */
- edac_dbg(3, "success\n");
-
- return 0;
-
-err2:
- edac_pci_del_device(&pdev->dev);
-err:
- edac_pci_free_ctl_info(pci);
- devres_release_group(&pdev->dev, mv64x60_pci_err_probe);
- return res;
-}
-
-static int mv64x60_pci_err_remove(struct platform_device *pdev)
-{
- struct edac_pci_ctl_info *pci = platform_get_drvdata(pdev);
-
- edac_dbg(0, "\n");
-
- edac_pci_del_device(&pdev->dev);
-
- edac_pci_free_ctl_info(pci);
-
- return 0;
-}
-
-static struct platform_driver mv64x60_pci_err_driver = {
- .probe = mv64x60_pci_err_probe,
- .remove = mv64x60_pci_err_remove,
- .driver = {
- .name = "mv64x60_pci_err",
- }
-};
-
-#endif /* CONFIG_PCI */
-
-/*********************** SRAM err device **********************************/
-static void mv64x60_sram_check(struct edac_device_ctl_info *edac_dev)
-{
- struct mv64x60_sram_pdata *pdata = edac_dev->pvt_info;
- u32 cause;
-
- cause = readl(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE);
- if (!cause)
- return;
-
- printk(KERN_ERR "Error in internal SRAM\n");
- printk(KERN_ERR "Cause register: 0x%08x\n", cause);
- printk(KERN_ERR "Address Low: 0x%08x\n",
- readl(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_LO));
- printk(KERN_ERR "Address High: 0x%08x\n",
- readl(pdata->sram_vbase + MV64X60_SRAM_ERR_ADDR_HI));
- printk(KERN_ERR "Data Low: 0x%08x\n",
- readl(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_LO));
- printk(KERN_ERR "Data High: 0x%08x\n",
- readl(pdata->sram_vbase + MV64X60_SRAM_ERR_DATA_HI));
- printk(KERN_ERR "Parity: 0x%08x\n",
- readl(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY));
- writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE);
-
- edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name);
-}
-
-static irqreturn_t mv64x60_sram_isr(int irq, void *dev_id)
-{
- struct edac_device_ctl_info *edac_dev = dev_id;
- struct mv64x60_sram_pdata *pdata = edac_dev->pvt_info;
- u32 cause;
-
- cause = readl(pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE);
- if (!cause)
- return IRQ_NONE;
-
- mv64x60_sram_check(edac_dev);
-
- return IRQ_HANDLED;
-}
-
-static int mv64x60_sram_err_probe(struct platform_device *pdev)
-{
- struct edac_device_ctl_info *edac_dev;
- struct mv64x60_sram_pdata *pdata;
- struct resource *r;
- int res = 0;
-
- if (!devres_open_group(&pdev->dev, mv64x60_sram_err_probe, GFP_KERNEL))
- return -ENOMEM;
-
- edac_dev = edac_device_alloc_ctl_info(sizeof(*pdata),
- "sram", 1, NULL, 0, 0, NULL, 0,
- edac_dev_idx);
- if (!edac_dev) {
- devres_release_group(&pdev->dev, mv64x60_sram_err_probe);
- return -ENOMEM;
- }
-
- pdata = edac_dev->pvt_info;
- pdata->name = "mv64x60_sram_err";
- edac_dev->dev = &pdev->dev;
- platform_set_drvdata(pdev, edac_dev);
- edac_dev->dev_name = dev_name(&pdev->dev);
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!r) {
- printk(KERN_ERR "%s: Unable to get resource for "
- "SRAM err regs\n", __func__);
- res = -ENOENT;
- goto err;
- }
-
- if (!devm_request_mem_region(&pdev->dev,
- r->start,
- resource_size(r),
- pdata->name)) {
- printk(KERN_ERR "%s: Error while request mem region\n",
- __func__);
- res = -EBUSY;
- goto err;
- }
-
- pdata->sram_vbase = devm_ioremap(&pdev->dev,
- r->start,
- resource_size(r));
- if (!pdata->sram_vbase) {
- printk(KERN_ERR "%s: Unable to setup SRAM err regs\n",
- __func__);
- res = -ENOMEM;
- goto err;
- }
-
- /* setup SRAM err registers */
- writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE);
-
- edac_dev->mod_name = EDAC_MOD_STR;
- edac_dev->ctl_name = pdata->name;
-
- if (edac_op_state == EDAC_OPSTATE_POLL)
- edac_dev->edac_check = mv64x60_sram_check;
-
- pdata->edac_idx = edac_dev_idx++;
-
- if (edac_device_add_device(edac_dev) > 0) {
- edac_dbg(3, "failed edac_device_add_device()\n");
- goto err;
- }
-
- if (edac_op_state == EDAC_OPSTATE_INT) {
- pdata->irq = platform_get_irq(pdev, 0);
- res = devm_request_irq(&pdev->dev,
- pdata->irq,
- mv64x60_sram_isr,
- 0,
- "[EDAC] SRAM err",
- edac_dev);
- if (res < 0) {
- printk(KERN_ERR
- "%s: Unable to request irq %d for "
- "MV64x60 SRAM ERR\n", __func__, pdata->irq);
- res = -ENODEV;
- goto err2;
- }
-
- printk(KERN_INFO EDAC_MOD_STR " acquired irq %d for SRAM Err\n",
- pdata->irq);
- }
-
- devres_remove_group(&pdev->dev, mv64x60_sram_err_probe);
-
- /* get this far and it's successful */
- edac_dbg(3, "success\n");
-
- return 0;
-
-err2:
- edac_device_del_device(&pdev->dev);
-err:
- devres_release_group(&pdev->dev, mv64x60_sram_err_probe);
- edac_device_free_ctl_info(edac_dev);
- return res;
-}
-
-static int mv64x60_sram_err_remove(struct platform_device *pdev)
-{
- struct edac_device_ctl_info *edac_dev = platform_get_drvdata(pdev);
-
- edac_dbg(0, "\n");
-
- edac_device_del_device(&pdev->dev);
- edac_device_free_ctl_info(edac_dev);
-
- return 0;
-}
-
-static struct platform_driver mv64x60_sram_err_driver = {
- .probe = mv64x60_sram_err_probe,
- .remove = mv64x60_sram_err_remove,
- .driver = {
- .name = "mv64x60_sram_err",
- }
-};
-
-/*********************** CPU err device **********************************/
-static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev)
-{
- struct mv64x60_cpu_pdata *pdata = edac_dev->pvt_info;
- u32 cause;
-
- cause = readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) &
- MV64x60_CPU_CAUSE_MASK;
- if (!cause)
- return;
-
- printk(KERN_ERR "Error on CPU interface\n");
- printk(KERN_ERR "Cause register: 0x%08x\n", cause);
- printk(KERN_ERR "Address Low: 0x%08x\n",
- readl(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_LO));
- printk(KERN_ERR "Address High: 0x%08x\n",
- readl(pdata->cpu_vbase[0] + MV64x60_CPU_ERR_ADDR_HI));
- printk(KERN_ERR "Data Low: 0x%08x\n",
- readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_LO));
- printk(KERN_ERR "Data High: 0x%08x\n",
- readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_DATA_HI));
- printk(KERN_ERR "Parity: 0x%08x\n",
- readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY));
- writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE);
-
- edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name);
-}
-
-static irqreturn_t mv64x60_cpu_isr(int irq, void *dev_id)
-{
- struct edac_device_ctl_info *edac_dev = dev_id;
- struct mv64x60_cpu_pdata *pdata = edac_dev->pvt_info;
- u32 cause;
-
- cause = readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE) &
- MV64x60_CPU_CAUSE_MASK;
- if (!cause)
- return IRQ_NONE;
-
- mv64x60_cpu_check(edac_dev);
-
- return IRQ_HANDLED;
-}
-
-static int mv64x60_cpu_err_probe(struct platform_device *pdev)
-{
- struct edac_device_ctl_info *edac_dev;
- struct resource *r;
- struct mv64x60_cpu_pdata *pdata;
- int res = 0;
-
- if (!devres_open_group(&pdev->dev, mv64x60_cpu_err_probe, GFP_KERNEL))
- return -ENOMEM;
-
- edac_dev = edac_device_alloc_ctl_info(sizeof(*pdata),
- "cpu", 1, NULL, 0, 0, NULL, 0,
- edac_dev_idx);
- if (!edac_dev) {
- devres_release_group(&pdev->dev, mv64x60_cpu_err_probe);
- return -ENOMEM;
- }
-
- pdata = edac_dev->pvt_info;
- pdata->name = "mv64x60_cpu_err";
- edac_dev->dev = &pdev->dev;
- platform_set_drvdata(pdev, edac_dev);
- edac_dev->dev_name = dev_name(&pdev->dev);
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!r) {
- printk(KERN_ERR "%s: Unable to get resource for "
- "CPU err regs\n", __func__);
- res = -ENOENT;
- goto err;
- }
-
- if (!devm_request_mem_region(&pdev->dev,
- r->start,
- resource_size(r),
- pdata->name)) {
- printk(KERN_ERR "%s: Error while requesting mem region\n",
- __func__);
- res = -EBUSY;
- goto err;
- }
-
- pdata->cpu_vbase[0] = devm_ioremap(&pdev->dev,
- r->start,
- resource_size(r));
- if (!pdata->cpu_vbase[0]) {
- printk(KERN_ERR "%s: Unable to setup CPU err regs\n", __func__);
- res = -ENOMEM;
- goto err;
- }
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- if (!r) {
- printk(KERN_ERR "%s: Unable to get resource for "
- "CPU err regs\n", __func__);
- res = -ENOENT;
- goto err;
- }
-
- if (!devm_request_mem_region(&pdev->dev,
- r->start,
- resource_size(r),
- pdata->name)) {
- printk(KERN_ERR "%s: Error while requesting mem region\n",
- __func__);
- res = -EBUSY;
- goto err;
- }
-
- pdata->cpu_vbase[1] = devm_ioremap(&pdev->dev,
- r->start,
- resource_size(r));
- if (!pdata->cpu_vbase[1]) {
- printk(KERN_ERR "%s: Unable to setup CPU err regs\n", __func__);
- res = -ENOMEM;
- goto err;
- }
-
- /* setup CPU err registers */
- writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE);
- writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK);
- writel(0x000000ff, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_MASK);
-
- edac_dev->mod_name = EDAC_MOD_STR;
- edac_dev->ctl_name = pdata->name;
- if (edac_op_state == EDAC_OPSTATE_POLL)
- edac_dev->edac_check = mv64x60_cpu_check;
-
- pdata->edac_idx = edac_dev_idx++;
-
- if (edac_device_add_device(edac_dev) > 0) {
- edac_dbg(3, "failed edac_device_add_device()\n");
- goto err;
- }
-
- if (edac_op_state == EDAC_OPSTATE_INT) {
- pdata->irq = platform_get_irq(pdev, 0);
- res = devm_request_irq(&pdev->dev,
- pdata->irq,
- mv64x60_cpu_isr,
- 0,
- "[EDAC] CPU err",
- edac_dev);
- if (res < 0) {
- printk(KERN_ERR
- "%s: Unable to request irq %d for MV64x60 "
- "CPU ERR\n", __func__, pdata->irq);
- res = -ENODEV;
- goto err2;
- }
-
- printk(KERN_INFO EDAC_MOD_STR
- " acquired irq %d for CPU Err\n", pdata->irq);
- }
-
- devres_remove_group(&pdev->dev, mv64x60_cpu_err_probe);
-
- /* get this far and it's successful */
- edac_dbg(3, "success\n");
-
- return 0;
-
-err2:
- edac_device_del_device(&pdev->dev);
-err:
- devres_release_group(&pdev->dev, mv64x60_cpu_err_probe);
- edac_device_free_ctl_info(edac_dev);
- return res;
-}
-
-static int mv64x60_cpu_err_remove(struct platform_device *pdev)
-{
- struct edac_device_ctl_info *edac_dev = platform_get_drvdata(pdev);
-
- edac_dbg(0, "\n");
-
- edac_device_del_device(&pdev->dev);
- edac_device_free_ctl_info(edac_dev);
- return 0;
-}
-
-static struct platform_driver mv64x60_cpu_err_driver = {
- .probe = mv64x60_cpu_err_probe,
- .remove = mv64x60_cpu_err_remove,
- .driver = {
- .name = "mv64x60_cpu_err",
- }
-};
-
-/*********************** DRAM err device **********************************/
-
-static void mv64x60_mc_check(struct mem_ctl_info *mci)
-{
- struct mv64x60_mc_pdata *pdata = mci->pvt_info;
- u32 reg;
- u32 err_addr;
- u32 sdram_ecc;
- u32 comp_ecc;
- u32 syndrome;
-
- reg = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR);
- if (!reg)
- return;
-
- err_addr = reg & ~0x3;
- sdram_ecc = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_RCVD);
- comp_ecc = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CALC);
- syndrome = sdram_ecc ^ comp_ecc;
-
- /* first bit clear in ECC Err Reg, 1 bit error, correctable by HW */
- if (!(reg & 0x1))
- edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
- err_addr >> PAGE_SHIFT,
- err_addr & PAGE_MASK, syndrome,
- 0, 0, -1,
- mci->ctl_name, "");
- else /* 2 bit error, UE */
- edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
- err_addr >> PAGE_SHIFT,
- err_addr & PAGE_MASK, 0,
- 0, 0, -1,
- mci->ctl_name, "");
-
- /* clear the error */
- writel(0, pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR);
-}
-
-static irqreturn_t mv64x60_mc_isr(int irq, void *dev_id)
-{
- struct mem_ctl_info *mci = dev_id;
- struct mv64x60_mc_pdata *pdata = mci->pvt_info;
- u32 reg;
-
- reg = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR);
- if (!reg)
- return IRQ_NONE;
-
- /* writing 0's to the ECC err addr in check function clears irq */
- mv64x60_mc_check(mci);
-
- return IRQ_HANDLED;
-}
-
-static void get_total_mem(struct mv64x60_mc_pdata *pdata)
-{
- struct device_node *np = NULL;
- const unsigned int *reg;
-
- np = of_find_node_by_type(NULL, "memory");
- if (!np)
- return;
-
- reg = of_get_property(np, "reg", NULL);
-
- pdata->total_mem = reg[1];
-}
-
-static void mv64x60_init_csrows(struct mem_ctl_info *mci,
- struct mv64x60_mc_pdata *pdata)
-{
- struct csrow_info *csrow;
- struct dimm_info *dimm;
-
- u32 devtype;
- u32 ctl;
-
- get_total_mem(pdata);
-
- ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_CONFIG);
-
- csrow = mci->csrows[0];
- dimm = csrow->channels[0]->dimm;
-
- dimm->nr_pages = pdata->total_mem >> PAGE_SHIFT;
- dimm->grain = 8;
-
- dimm->mtype = (ctl & MV64X60_SDRAM_REGISTERED) ? MEM_RDDR : MEM_DDR;
-
- devtype = (ctl >> 20) & 0x3;
- switch (devtype) {
- case 0x0:
- dimm->dtype = DEV_X32;
- break;
- case 0x2: /* could be X8 too, but no way to tell */
- dimm->dtype = DEV_X16;
- break;
- case 0x3:
- dimm->dtype = DEV_X4;
- break;
- default:
- dimm->dtype = DEV_UNKNOWN;
- break;
- }
-
- dimm->edac_mode = EDAC_SECDED;
-}
-
-static int mv64x60_mc_err_probe(struct platform_device *pdev)
-{
- struct mem_ctl_info *mci;
- struct edac_mc_layer layers[2];
- struct mv64x60_mc_pdata *pdata;
- struct resource *r;
- u32 ctl;
- int res = 0;
-
- if (!devres_open_group(&pdev->dev, mv64x60_mc_err_probe, GFP_KERNEL))
- return -ENOMEM;
-
- layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
- layers[0].size = 1;
- layers[0].is_virt_csrow = true;
- layers[1].type = EDAC_MC_LAYER_CHANNEL;
- layers[1].size = 1;
- layers[1].is_virt_csrow = false;
- mci = edac_mc_alloc(edac_mc_idx, ARRAY_SIZE(layers), layers,
- sizeof(struct mv64x60_mc_pdata));
- if (!mci) {
- printk(KERN_ERR "%s: No memory for CPU err\n", __func__);
- devres_release_group(&pdev->dev, mv64x60_mc_err_probe);
- return -ENOMEM;
- }
-
- pdata = mci->pvt_info;
- mci->pdev = &pdev->dev;
- platform_set_drvdata(pdev, mci);
- pdata->name = "mv64x60_mc_err";
- mci->dev_name = dev_name(&pdev->dev);
- pdata->edac_idx = edac_mc_idx++;
-
- r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!r) {
- printk(KERN_ERR "%s: Unable to get resource for "
- "MC err regs\n", __func__);
- res = -ENOENT;
- goto err;
- }
-
- if (!devm_request_mem_region(&pdev->dev,
- r->start,
- resource_size(r),
- pdata->name)) {
- printk(KERN_ERR "%s: Error while requesting mem region\n",
- __func__);
- res = -EBUSY;
- goto err;
- }
-
- pdata->mc_vbase = devm_ioremap(&pdev->dev,
- r->start,
- resource_size(r));
- if (!pdata->mc_vbase) {
- printk(KERN_ERR "%s: Unable to setup MC err regs\n", __func__);
- res = -ENOMEM;
- goto err;
- }
-
- ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_CONFIG);
- if (!(ctl & MV64X60_SDRAM_ECC)) {
- /* Non-ECC RAM? */
- printk(KERN_WARNING "%s: No ECC DIMMs discovered\n", __func__);
- res = -ENODEV;
- goto err;
- }
-
- edac_dbg(3, "init mci\n");
- mci->mtype_cap = MEM_FLAG_RDDR | MEM_FLAG_DDR;
- mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
- mci->edac_cap = EDAC_FLAG_SECDED;
- mci->mod_name = EDAC_MOD_STR;
- mci->ctl_name = mv64x60_ctl_name;
-
- if (edac_op_state == EDAC_OPSTATE_POLL)
- mci->edac_check = mv64x60_mc_check;
-
- mci->ctl_page_to_phys = NULL;
-
- mci->scrub_mode = SCRUB_SW_SRC;
-
- mv64x60_init_csrows(mci, pdata);
-
- /* setup MC registers */
- writel(0, pdata->mc_vbase + MV64X60_SDRAM_ERR_ADDR);
- ctl = readl(pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL);
- ctl = (ctl & 0xff00ffff) | 0x10000;
- writel(ctl, pdata->mc_vbase + MV64X60_SDRAM_ERR_ECC_CNTL);
-
- res = edac_mc_add_mc(mci);
- if (res) {
- edac_dbg(3, "failed edac_mc_add_mc()\n");
- goto err;
- }
-
- if (edac_op_state == EDAC_OPSTATE_INT) {
- /* acquire interrupt that reports errors */
- pdata->irq = platform_get_irq(pdev, 0);
- res = devm_request_irq(&pdev->dev,
- pdata->irq,
- mv64x60_mc_isr,
- 0,
- "[EDAC] MC err",
- mci);
- if (res < 0) {
- printk(KERN_ERR "%s: Unable to request irq %d for "
- "MV64x60 DRAM ERR\n", __func__, pdata->irq);
- res = -ENODEV;
- goto err2;
- }
-
- printk(KERN_INFO EDAC_MOD_STR " acquired irq %d for MC Err\n",
- pdata->irq);
- }
-
- /* get this far and it's successful */
- edac_dbg(3, "success\n");
-
- return 0;
-
-err2:
- edac_mc_del_mc(&pdev->dev);
-err:
- devres_release_group(&pdev->dev, mv64x60_mc_err_probe);
- edac_mc_free(mci);
- return res;
-}
-
-static int mv64x60_mc_err_remove(struct platform_device *pdev)
-{
- struct mem_ctl_info *mci = platform_get_drvdata(pdev);
-
- edac_dbg(0, "\n");
-
- edac_mc_del_mc(&pdev->dev);
- edac_mc_free(mci);
- return 0;
-}
-
-static struct platform_driver mv64x60_mc_err_driver = {
- .probe = mv64x60_mc_err_probe,
- .remove = mv64x60_mc_err_remove,
- .driver = {
- .name = "mv64x60_mc_err",
- }
-};
-
-static struct platform_driver * const drivers[] = {
- &mv64x60_mc_err_driver,
- &mv64x60_cpu_err_driver,
- &mv64x60_sram_err_driver,
-#ifdef CONFIG_PCI
- &mv64x60_pci_err_driver,
-#endif
-};
-
-static int __init mv64x60_edac_init(void)
-{
-
- printk(KERN_INFO "Marvell MV64x60 EDAC driver " MV64x60_REVISION "\n");
- printk(KERN_INFO "\t(C) 2006-2007 MontaVista Software\n");
-
- /* make sure error reporting method is sane */
- switch (edac_op_state) {
- case EDAC_OPSTATE_POLL:
- case EDAC_OPSTATE_INT:
- break;
- default:
- edac_op_state = EDAC_OPSTATE_INT;
- break;
- }
-
- return platform_register_drivers(drivers, ARRAY_SIZE(drivers));
-}
-module_init(mv64x60_edac_init);
-
-static void __exit mv64x60_edac_exit(void)
-{
- platform_unregister_drivers(drivers, ARRAY_SIZE(drivers));
-}
-module_exit(mv64x60_edac_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Montavista Software, Inc.");
-module_param(edac_op_state, int, 0444);
-MODULE_PARM_DESC(edac_op_state,
- "EDAC Error Reporting state: 0=Poll, 2=Interrupt");
+++ /dev/null
-/*
- * EDAC defs for Marvell MV64x60 bridge chip
- *
- * Author: Dave Jiang <djiang@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- *
- */
-#ifndef _MV64X60_EDAC_H_
-#define _MV64X60_EDAC_H_
-
-#define MV64x60_REVISION " Ver: 2.0.0"
-#define EDAC_MOD_STR "MV64x60_edac"
-
-#define mv64x60_printk(level, fmt, arg...) \
- edac_printk(level, "MV64x60", fmt, ##arg)
-
-#define mv64x60_mc_printk(mci, level, fmt, arg...) \
- edac_mc_chipset_printk(mci, level, "MV64x60", fmt, ##arg)
-
-/* CPU Error Report Registers */
-#define MV64x60_CPU_ERR_ADDR_LO 0x00 /* 0x0070 */
-#define MV64x60_CPU_ERR_ADDR_HI 0x08 /* 0x0078 */
-#define MV64x60_CPU_ERR_DATA_LO 0x00 /* 0x0128 */
-#define MV64x60_CPU_ERR_DATA_HI 0x08 /* 0x0130 */
-#define MV64x60_CPU_ERR_PARITY 0x10 /* 0x0138 */
-#define MV64x60_CPU_ERR_CAUSE 0x18 /* 0x0140 */
-#define MV64x60_CPU_ERR_MASK 0x20 /* 0x0148 */
-
-#define MV64x60_CPU_CAUSE_MASK 0x07ffffff
-
-/* SRAM Error Report Registers */
-#define MV64X60_SRAM_ERR_CAUSE 0x08 /* 0x0388 */
-#define MV64X60_SRAM_ERR_ADDR_LO 0x10 /* 0x0390 */
-#define MV64X60_SRAM_ERR_ADDR_HI 0x78 /* 0x03f8 */
-#define MV64X60_SRAM_ERR_DATA_LO 0x18 /* 0x0398 */
-#define MV64X60_SRAM_ERR_DATA_HI 0x20 /* 0x03a0 */
-#define MV64X60_SRAM_ERR_PARITY 0x28 /* 0x03a8 */
-
-/* SDRAM Controller Registers */
-#define MV64X60_SDRAM_CONFIG 0x00 /* 0x1400 */
-#define MV64X60_SDRAM_ERR_DATA_HI 0x40 /* 0x1440 */
-#define MV64X60_SDRAM_ERR_DATA_LO 0x44 /* 0x1444 */
-#define MV64X60_SDRAM_ERR_ECC_RCVD 0x48 /* 0x1448 */
-#define MV64X60_SDRAM_ERR_ECC_CALC 0x4c /* 0x144c */
-#define MV64X60_SDRAM_ERR_ADDR 0x50 /* 0x1450 */
-#define MV64X60_SDRAM_ERR_ECC_CNTL 0x54 /* 0x1454 */
-#define MV64X60_SDRAM_ERR_ECC_ERR_CNT 0x58 /* 0x1458 */
-
-#define MV64X60_SDRAM_REGISTERED 0x20000
-#define MV64X60_SDRAM_ECC 0x40000
-
-#ifdef CONFIG_PCI
-/*
- * Bit 0 of MV64x60_PCIx_ERR_MASK does not exist on the 64360 and because of
- * errata FEr-#11 and FEr-##16 for the 64460, it should be 0 on that chip as
- * well. IOW, don't set bit 0.
- */
-#define MV64X60_PCIx_ERR_MASK_VAL 0x00a50c24
-
-/* Register offsets from PCIx error address low register */
-#define MV64X60_PCI_ERROR_ADDR_LO 0x00
-#define MV64X60_PCI_ERROR_ADDR_HI 0x04
-#define MV64X60_PCI_ERROR_ATTR 0x08
-#define MV64X60_PCI_ERROR_CMD 0x10
-#define MV64X60_PCI_ERROR_CAUSE 0x18
-#define MV64X60_PCI_ERROR_MASK 0x1c
-
-#define MV64X60_PCI_ERR_SWrPerr 0x0002
-#define MV64X60_PCI_ERR_SRdPerr 0x0004
-#define MV64X60_PCI_ERR_MWrPerr 0x0020
-#define MV64X60_PCI_ERR_MRdPerr 0x0040
-
-#define MV64X60_PCI_PE_MASK (MV64X60_PCI_ERR_SWrPerr | \
- MV64X60_PCI_ERR_SRdPerr | \
- MV64X60_PCI_ERR_MWrPerr | \
- MV64X60_PCI_ERR_MRdPerr)
-
-struct mv64x60_pci_pdata {
- int pci_hose;
- void __iomem *pci_vbase;
- char *name;
- int irq;
- int edac_idx;
-};
-
-#endif /* CONFIG_PCI */
-
-struct mv64x60_mc_pdata {
- void __iomem *mc_vbase;
- int total_mem;
- char *name;
- int irq;
- int edac_idx;
-};
-
-struct mv64x60_cpu_pdata {
- void __iomem *cpu_vbase[2];
- char *name;
- int irq;
- int edac_idx;
-};
-
-struct mv64x60_sram_pdata {
- void __iomem *sram_vbase;
- char *name;
- int irq;
- int edac_idx;
-};
-
-#endif
{
struct r82600_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
r82600_get_error_info(mci, &info);
r82600_process_error_info(mci, &info, 1);
}
return !!GET_BITFIELD(mcmtr, 2, 2);
}
-static int skx_get_dimm_config(struct mem_ctl_info *mci)
+static int skx_get_dimm_config(struct mem_ctl_info *mci, struct res_config *cfg)
{
struct skx_pvt *pvt = mci->pvt_info;
u32 mtr, mcmtr, amap, mcddrtcfg;
pci_read_config_dword(imc->chan[i].cdev,
0x80 + 4 * j, &mtr);
if (IS_DIMM_PRESENT(mtr)) {
- ndimms += skx_get_dimm_info(mtr, mcmtr, amap, dimm, imc, i, j);
+ ndimms += skx_get_dimm_info(mtr, mcmtr, amap, dimm, imc, i, j, cfg);
} else if (IS_NVDIMM_PRESENT(mcddrtcfg, j)) {
ndimms += skx_get_nvdimm_info(dimm, imc, i, j,
EDAC_MOD_STR);
d->imc[i].node_id = node_id;
rc = skx_register_mci(&d->imc[i], d->imc[i].chan[0].cdev,
"Skylake Socket", EDAC_MOD_STR,
- skx_get_dimm_config);
+ skx_get_dimm_config, cfg);
if (rc < 0)
goto fail;
}
#define numcol(reg) skx_get_dimm_attr(reg, 0, 1, 10, 0, 2, "cols")
int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
- struct skx_imc *imc, int chan, int dimmno)
+ struct skx_imc *imc, int chan, int dimmno,
+ struct res_config *cfg)
{
- int banks = 16, ranks, rows, cols, npages;
+ int banks, ranks, rows, cols, npages;
+ enum mem_type mtype;
u64 size;
ranks = numrank(mtr);
rows = numrow(mtr);
cols = numcol(mtr);
+ if (cfg->support_ddr5 && (amap & 0x8)) {
+ banks = 32;
+ mtype = MEM_DDR5;
+ } else {
+ banks = 16;
+ mtype = MEM_DDR4;
+ }
+
/*
* Compute size in 8-byte (2^3) words, then shift to MiB (2^20)
*/
dimm->nr_pages = npages;
dimm->grain = 32;
dimm->dtype = get_width(mtr);
- dimm->mtype = MEM_DDR4;
+ dimm->mtype = mtype;
dimm->edac_mode = EDAC_SECDED; /* likely better than this */
snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u",
imc->src_id, imc->lmc, chan, dimmno);
int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev,
const char *ctl_name, const char *mod_str,
- get_dimm_config_f get_dimm_config)
+ get_dimm_config_f get_dimm_config,
+ struct res_config *cfg)
{
struct mem_ctl_info *mci;
struct edac_mc_layer layers[2];
}
mci->mtype_cap = MEM_FLAG_DDR4 | MEM_FLAG_NVDIMM;
+ if (cfg->support_ddr5)
+ mci->mtype_cap |= MEM_FLAG_DDR5;
mci->edac_ctl_cap = EDAC_FLAG_NONE;
mci->edac_cap = EDAC_FLAG_NONE;
mci->mod_name = mod_str;
mci->dev_name = pci_name(pdev);
mci->ctl_page_to_phys = NULL;
- rc = get_dimm_config(mci);
+ rc = get_dimm_config(mci, cfg);
if (rc < 0)
goto fail;
struct mem_ctl_info *mci;
struct pci_dev *mdev; /* for i10nm CPU */
void __iomem *mbase; /* for i10nm CPU */
+ int chan_mmio_sz; /* for i10nm CPU */
u8 mc; /* system wide mc# */
u8 lmc; /* socket relative mc# */
u8 src_id, node_id;
enum type {
SKX,
- I10NM
+ I10NM,
+ SPR
};
enum {
unsigned int decs_did;
/* Default bus number configuration register offset */
int busno_cfg_offset;
+ /* Per DDR channel memory-mapped I/O size */
+ int ddr_chan_mmio_sz;
+ bool support_ddr5;
};
-typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci);
+typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci,
+ struct res_config *cfg);
typedef bool (*skx_decode_f)(struct decoded_addr *res);
typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len);
int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm);
int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
- struct skx_imc *imc, int chan, int dimmno);
+ struct skx_imc *imc, int chan, int dimmno,
+ struct res_config *cfg);
int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc,
int chan, int dimmno, const char *mod_str);
int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev,
const char *ctl_name, const char *mod_str,
- get_dimm_config_f get_dimm_config);
+ get_dimm_config_f get_dimm_config,
+ struct res_config *cfg);
int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
void *data);
#ifdef CONFIG_EDAC_DEBUG
if (priv->p_data->quirks & DDR_ECC_DATA_POISON_SUPPORT) {
- if (edac_create_sysfs_attributes(mci)) {
+ rc = edac_create_sysfs_attributes(mci);
+ if (rc) {
edac_printk(KERN_ERR, EDAC_MC,
"Failed to create sysfs entries\n");
goto free_edac_mc;
{
struct x38_error_info info;
- edac_dbg(1, "MC%d\n", mci->mc_idx);
x38_get_and_clear_error_info(mci, &info);
x38_process_error_info(mci, &info);
}
protocols_imp[tot_num_ret + loop] = *(list + loop);
tot_num_ret += loop_num_ret;
+
+ scmi_reset_rx_to_maxsz(handle, t);
} while (loop_num_ret);
scmi_xfer_put(handle, t);
}
tot_rate_cnt += num_returned;
+
+ scmi_reset_rx_to_maxsz(handle, t);
/*
* check for both returned and remaining to avoid infinite
* loop due to buggy firmware
struct scmi_xfer *xfer);
int scmi_xfer_get_init(const struct scmi_handle *h, u8 msg_id, u8 prot_id,
size_t tx_size, size_t rx_size, struct scmi_xfer **p);
+void scmi_reset_rx_to_maxsz(const struct scmi_handle *handle,
+ struct scmi_xfer *xfer);
int scmi_handle_put(const struct scmi_handle *handle);
struct scmi_handle *scmi_handle_get(struct device *dev);
void scmi_set_handle(struct scmi_device *scmi_dev);
return ret;
}
+void scmi_reset_rx_to_maxsz(const struct scmi_handle *handle,
+ struct scmi_xfer *xfer)
+{
+ struct scmi_info *info = handle_to_scmi_info(handle);
+
+ xfer->rx.len = info->desc->max_msg_size;
+}
+
#define SCMI_MAX_RESPONSE_TIMEOUT (2 * MSEC_PER_SEC)
/**
"finalized PENDING handler - key:%X\n",
hndl->key);
ret = scmi_event_handler_enable_events(hndl);
+ if (ret) {
+ dev_dbg(ni->handle->dev,
+ "purging INVALID handler - key:%X\n",
+ hndl->key);
+ scmi_put_active_handler(ni, hndl);
+ }
} else {
ret = scmi_valid_pending_handler(ni, hndl);
- }
- if (ret) {
- dev_dbg(ni->handle->dev,
- "purging PENDING handler - key:%X\n",
- hndl->key);
- /* this hndl can be only a pending one */
- scmi_put_handler_unlocked(ni, hndl);
+ if (ret) {
+ dev_dbg(ni->handle->dev,
+ "purging PENDING handler - key:%X\n",
+ hndl->key);
+ /* this hndl can be only a pending one */
+ scmi_put_handler_unlocked(ni, hndl);
+ }
}
}
mutex_unlock(&ni->pending_mtx);
ni->gid = gid;
ni->handle = handle;
- ni->notify_wq = alloc_workqueue("scmi_notify",
+ ni->notify_wq = alloc_workqueue(dev_name(handle->dev),
WQ_UNBOUND | WQ_FREEZABLE | WQ_SYSFS,
0);
if (!ni->notify_wq)
}
tot_opp_cnt += num_returned;
+
+ scmi_reset_rx_to_maxsz(handle, t);
/*
* check for both returned and remaining to avoid infinite
* loop due to buggy firmware
#define EXPLICIT_RESET_ASSERT BIT(1)
#define ASYNCHRONOUS_RESET BIT(2)
__le32 reset_state;
-#define ARCH_RESET_TYPE BIT(31)
-#define COLD_RESET_STATE BIT(0)
-#define ARCH_COLD_RESET (ARCH_RESET_TYPE | COLD_RESET_STATE)
+#define ARCH_COLD_RESET 0
};
struct scmi_msg_reset_notify {
}
desc_index += num_returned;
+
+ scmi_reset_rx_to_maxsz(handle, t);
/*
* check for both returned and remaining to avoid infinite
* loop due to buggy firmware
const struct scmi_desc scmi_smc_desc = {
.ops = &scmi_smc_ops,
.max_rx_timeout_ms = 30,
- .max_msg = 1,
+ .max_msg = 20,
.max_msg_size = 128,
};
config EFI_EARLYCON
def_bool y
- depends on SERIAL_EARLYCON && !ARM && !IA64
+ depends on EFI && SERIAL_EARLYCON && !ARM && !IA64
select FONT_SUPPORT
select ARCH_USE_MEMREMAP_PROT
if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) {
- efivar_ssdt_load();
error = generic_ops_register();
if (error)
goto err_put;
+ efivar_ssdt_load();
platform_device_register_simple("efivars", 0, NULL, 0);
}
#include <linux/of_platform.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
+#include <linux/hashtable.h>
#include <linux/firmware/xlnx-zynqmp.h>
#include "zynqmp-debug.h"
+/* Max HashMap Order for PM API feature check (1<<7 = 128) */
+#define PM_API_FEATURE_CHECK_MAX_ORDER 7
+
static bool feature_check_enabled;
-static u32 zynqmp_pm_features[PM_API_MAX];
+DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER);
+
+/**
+ * struct pm_api_feature_data - PM API Feature data
+ * @pm_api_id: PM API Id, used as key to index into hashmap
+ * @feature_status: status of PM API feature: valid, invalid
+ * @hentry: hlist_node that hooks this entry into hashtable
+ */
+struct pm_api_feature_data {
+ u32 pm_api_id;
+ int feature_status;
+ struct hlist_node hentry;
+};
static const struct mfd_cell firmware_devs[] = {
{
int ret;
u32 ret_payload[PAYLOAD_ARG_CNT];
u64 smc_arg[2];
+ struct pm_api_feature_data *feature_data;
if (!feature_check_enabled)
return 0;
- /* Return value if feature is already checked */
- if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED)
- return zynqmp_pm_features[api_id];
+ /* Check for existing entry in hash table for given api */
+ hash_for_each_possible(pm_api_features_map, feature_data, hentry,
+ api_id) {
+ if (feature_data->pm_api_id == api_id)
+ return feature_data->feature_status;
+ }
+
+ /* Add new entry if not present */
+ feature_data = kmalloc(sizeof(*feature_data), GFP_KERNEL);
+ if (!feature_data)
+ return -ENOMEM;
+ feature_data->pm_api_id = api_id;
smc_arg[0] = PM_SIP_SVC | PM_FEATURE_CHECK;
smc_arg[1] = api_id;
ret = do_fw_call(smc_arg[0], smc_arg[1], 0, ret_payload);
- if (ret) {
- zynqmp_pm_features[api_id] = PM_FEATURE_INVALID;
- return PM_FEATURE_INVALID;
- }
+ if (ret)
+ ret = -EOPNOTSUPP;
+ else
+ ret = ret_payload[1];
- zynqmp_pm_features[api_id] = ret_payload[1];
+ feature_data->feature_status = ret;
+ hash_add(pm_api_features_map, &feature_data->hentry, api_id);
- return zynqmp_pm_features[api_id];
+ return ret;
}
/**
* Make sure to stay in x0 register
*/
u64 smc_arg[4];
+ int ret;
- if (zynqmp_pm_feature(pm_api_id) == PM_FEATURE_INVALID)
- return -ENOTSUPP;
+ /* Check if feature is supported or not */
+ ret = zynqmp_pm_feature(pm_api_id);
+ if (ret < 0)
+ return ret;
smc_arg[0] = PM_SIP_SVC | pm_api_id;
smc_arg[1] = ((u64)arg1 << 32) | arg0;
*/
int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type)
{
- return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SET_SD_TAPDELAY,
+ return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, IOCTL_SD_DLL_RESET,
type, 0, NULL);
}
EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset);
static int zynqmp_firmware_remove(struct platform_device *pdev)
{
+ struct pm_api_feature_data *feature_data;
+ int i;
+
mfd_remove_devices(&pdev->dev);
zynqmp_pm_api_debugfs_exit();
+ hash_for_each(pm_api_features_map, i, feature_data, hentry) {
+ hash_del(&feature_data->hentry);
+ kfree(feature_data);
+ }
+
return 0;
}
tristate "FPGA Device Feature List (DFL) support"
select FPGA_BRIDGE
select FPGA_REGION
+ depends on HAS_IOMEM
help
Device Feature List (DFL) defines a feature list structure that
creates a linked list of feature headers within the MMIO space
static const struct aspeed_bank_props ast2600_bank_props[] = {
/* input output */
+ {4, 0xffffffff, 0x00ffffff}, /* Q/R/S/T */
{5, 0xffffffff, 0xffffff00}, /* U/V/W/X */
{6, 0x0000ffff, 0x0000ffff}, /* Y/Z */
{ },
#ifdef CONFIG_PM_SLEEP
static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable)
{
- struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d);
- struct dwapb_gpio *gpio = igc->private;
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct dwapb_gpio *gpio = to_dwapb_gpio(gc);
struct dwapb_context *ctx = gpio->ports[0].ctx;
irq_hw_number_t bit = irqd_to_hwirq(d);
{
struct device *dev = bank->chip.parent;
void __iomem *base = bank->base;
- u32 nowake;
+ u32 mask, nowake;
bank->saved_datain = readl_relaxed(base + bank->regs->datain);
if (!bank->enabled_non_wakeup_gpios)
goto update_gpio_context_count;
+ /* Check for pending EDGE_FALLING, ignore EDGE_BOTH */
+ mask = bank->enabled_non_wakeup_gpios & bank->context.fallingdetect;
+ mask &= ~bank->context.risingdetect;
+ bank->saved_datain |= mask;
+
+ /* Check for pending EDGE_RISING, ignore EDGE_BOTH */
+ mask = bank->enabled_non_wakeup_gpios & bank->context.risingdetect;
+ mask &= ~bank->context.fallingdetect;
+ bank->saved_datain &= ~mask;
+
if (!may_lose_context)
goto update_gpio_context_count;
#include <linux/spinlock.h>
#include <linux/types.h>
+/*
+ * PLX PEX8311 PCI LCS_INTCSR Interrupt Control/Status
+ *
+ * Bit: Description
+ * 0: Enable Interrupt Sources (Bit 0)
+ * 1: Enable Interrupt Sources (Bit 1)
+ * 2: Generate Internal PCI Bus Internal SERR# Interrupt
+ * 3: Mailbox Interrupt Enable
+ * 4: Power Management Interrupt Enable
+ * 5: Power Management Interrupt
+ * 6: Slave Read Local Data Parity Check Error Enable
+ * 7: Slave Read Local Data Parity Check Error Status
+ * 8: Internal PCI Wire Interrupt Enable
+ * 9: PCI Express Doorbell Interrupt Enable
+ * 10: PCI Abort Interrupt Enable
+ * 11: Local Interrupt Input Enable
+ * 12: Retry Abort Enable
+ * 13: PCI Express Doorbell Interrupt Active
+ * 14: PCI Abort Interrupt Active
+ * 15: Local Interrupt Input Active
+ * 16: Local Interrupt Output Enable
+ * 17: Local Doorbell Interrupt Enable
+ * 18: DMA Channel 0 Interrupt Enable
+ * 19: DMA Channel 1 Interrupt Enable
+ * 20: Local Doorbell Interrupt Active
+ * 21: DMA Channel 0 Interrupt Active
+ * 22: DMA Channel 1 Interrupt Active
+ * 23: Built-In Self-Test (BIST) Interrupt Active
+ * 24: Direct Master was the Bus Master during a Master or Target Abort
+ * 25: DMA Channel 0 was the Bus Master during a Master or Target Abort
+ * 26: DMA Channel 1 was the Bus Master during a Master or Target Abort
+ * 27: Target Abort after internal 256 consecutive Master Retrys
+ * 28: PCI Bus wrote data to LCS_MBOX0
+ * 29: PCI Bus wrote data to LCS_MBOX1
+ * 30: PCI Bus wrote data to LCS_MBOX2
+ * 31: PCI Bus wrote data to LCS_MBOX3
+ */
+#define PLX_PEX8311_PCI_LCS_INTCSR 0x68
+#define INTCSR_INTERNAL_PCI_WIRE BIT(8)
+#define INTCSR_LOCAL_INPUT BIT(11)
+
/**
* struct idio_24_gpio_reg - GPIO device registers structure
* @out0_7: Read: FET Outputs 0-7
struct idio_24_gpio {
struct gpio_chip chip;
raw_spinlock_t lock;
+ __u8 __iomem *plx;
struct idio_24_gpio_reg __iomem *reg;
unsigned long irq_mask;
};
unsigned long flags;
const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
unsigned char new_irq_mask;
- const unsigned long bank_offset = bit_offset/8 * 8;
+ const unsigned long bank_offset = bit_offset / 8;
unsigned char cos_enable_state;
raw_spin_lock_irqsave(&idio24gpio->lock, flags);
- idio24gpio->irq_mask &= BIT(bit_offset);
- new_irq_mask = idio24gpio->irq_mask >> bank_offset;
+ idio24gpio->irq_mask &= ~BIT(bit_offset);
+ new_irq_mask = idio24gpio->irq_mask >> bank_offset * 8;
if (!new_irq_mask) {
cos_enable_state = ioread8(&idio24gpio->reg->cos_enable);
unsigned long flags;
unsigned char prev_irq_mask;
const unsigned long bit_offset = irqd_to_hwirq(data) - 24;
- const unsigned long bank_offset = bit_offset/8 * 8;
+ const unsigned long bank_offset = bit_offset / 8;
unsigned char cos_enable_state;
raw_spin_lock_irqsave(&idio24gpio->lock, flags);
- prev_irq_mask = idio24gpio->irq_mask >> bank_offset;
+ prev_irq_mask = idio24gpio->irq_mask >> bank_offset * 8;
idio24gpio->irq_mask |= BIT(bit_offset);
if (!prev_irq_mask) {
struct device *const dev = &pdev->dev;
struct idio_24_gpio *idio24gpio;
int err;
+ const size_t pci_plx_bar_index = 1;
const size_t pci_bar_index = 2;
const char *const name = pci_name(pdev);
struct gpio_irq_chip *girq;
return err;
}
- err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name);
+ err = pcim_iomap_regions(pdev, BIT(pci_plx_bar_index) | BIT(pci_bar_index), name);
if (err) {
dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err);
return err;
}
+ idio24gpio->plx = pcim_iomap_table(pdev)[pci_plx_bar_index];
idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index];
idio24gpio->chip.label = name;
/* Software board reset */
iowrite8(0, &idio24gpio->reg->soft_reset);
+ /*
+ * enable PLX PEX8311 internal PCI wire interrupt and local interrupt
+ * input
+ */
+ iowrite8((INTCSR_INTERNAL_PCI_WIRE | INTCSR_LOCAL_INPUT) >> 8,
+ idio24gpio->plx + PLX_PEX8311_PCI_LCS_INTCSR + 1);
err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio);
if (err) {
return PTR_ERR(chip->regs);
ngpio = of_irq_count(node);
- if (ngpio >= SIFIVE_GPIO_MAX) {
+ if (ngpio > SIFIVE_GPIO_MAX) {
dev_err(dev, "Too many GPIO interrupts (max=%d)\n",
SIFIVE_GPIO_MAX);
return -ENXIO;
struct gpio_device;
-#ifdef CONFIG_GPIO_CDEV
-
int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt);
void gpiolib_cdev_unregister(struct gpio_device *gdev);
-#else
-
-static inline int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt)
-{
- return 0;
-}
-
-static inline void gpiolib_cdev_unregister(struct gpio_device *gdev)
-{
-}
-
-#endif /* CONFIG_GPIO_CDEV */
-
#endif /* GPIOLIB_CDEV_H */
kfree(gdev);
}
+#ifdef CONFIG_GPIO_CDEV
+#define gcdev_register(gdev, devt) gpiolib_cdev_register((gdev), (devt))
+#define gcdev_unregister(gdev) gpiolib_cdev_unregister((gdev))
+#else
+/*
+ * gpiolib_cdev_register() indirectly calls device_add(), which is still
+ * required even when cdev is not selected.
+ */
+#define gcdev_register(gdev, devt) device_add(&(gdev)->dev)
+#define gcdev_unregister(gdev) device_del(&(gdev)->dev)
+#endif
+
static int gpiochip_setup_dev(struct gpio_device *gdev)
{
int ret;
- ret = gpiolib_cdev_register(gdev, gpio_devt);
+ ret = gcdev_register(gdev, gpio_devt);
if (ret)
return ret;
return 0;
err_remove_device:
- gpiolib_cdev_unregister(gdev);
+ gcdev_unregister(gdev);
return ret;
}
* be removed, else it will be dangling until the last user is
* gone.
*/
- gpiolib_cdev_unregister(gdev);
+ gcdev_unregister(gdev);
put_device(&gdev->dev);
}
EXPORT_SYMBOL_GPL(gpiochip_remove);
MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin");
#define AMDGPU_RESUME_MS 2000
return amdgpu_asic_supports_baco(adev);
}
+/*
+ * VRAM access helper functions
+ */
+
/**
- * VRAM access helper functions.
- *
* amdgpu_device_vram_access - read/write a buffer in vram
*
* @adev: amdgpu_device pointer
/**
* amdgpu_invalid_rreg - dummy reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
*
* Dummy register read function. Used for register blocks
/**
* amdgpu_invalid_wreg - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
* @v: value to write to the register
*
/**
* amdgpu_invalid_rreg64 - dummy 64 bit reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
*
* Dummy register read function. Used for register blocks
/**
* amdgpu_invalid_wreg64 - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @reg: offset of register
* @v: value to write to the register
*
/**
* amdgpu_block_invalid_rreg - dummy reg read function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @block: offset of instance
* @reg: offset of register
*
/**
* amdgpu_block_invalid_wreg - dummy reg write function
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @block: offset of instance
* @reg: offset of register
* @v: value to write to the register
/**
* amdgpu_device_asic_init - Wrapper for atom asic_init
*
- * @dev: drm_device pointer
+ * @adev: amdgpu_device pointer
*
* Does any asic specific work and then calls atom asic init.
*/
/**
* amdgpu_device_vram_scratch_init - allocate the VRAM scratch page
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Allocates a scratch page of VRAM for use by various things in the
* driver.
/**
* amdgpu_device_vram_scratch_fini - Free the VRAM scratch page
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Frees the VRAM scratch page.
*/
chip_name = "arcturus";
break;
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
case CHIP_NAVI10:
chip_name = "navi10";
/**
* amdgpu_device_has_dc_support - check if dc is supported
*
- * @adev: amdgpu_device_pointer
+ * @adev: amdgpu_device pointer
*
* Returns true for supported, false for not supported
*/
/**
* amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @from_hypervisor: request from hypervisor
*
* do VF FLR and reinitialize Asic
/**
* amdgpu_device_has_job_running - check if there is any job in mirror list
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* check if there is any job in mirror list
*/
/**
* amdgpu_device_should_recover_gpu - check if we should try GPU recovery
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
*
* Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover
* a hung GPU.
/**
* amdgpu_device_gpu_recover - reset the asic and recover scheduler
*
- * @adev: amdgpu device pointer
+ * @adev: amdgpu_device pointer
* @job: which job trigger hang
*
* Attempt to reset the GPU if it has hung (all asics).
bool need_emergency_restart = false;
bool audio_suspended = false;
- /**
+ /*
* Special case: RAS triggered and full reset isn't supported
*/
need_emergency_restart = amdgpu_ras_need_emergency_restart(adev);
if (!amdgpu_device_supports_baco(adev_to_drm(adev)))
return -ENOTSUPP;
- if (ras && ras->supported)
+ if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt)
adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
return amdgpu_dpm_baco_enter(adev);
if (ret)
return ret;
- if (ras && ras->supported)
+ if (ras && ras->supported && adev->nbio.funcs->enable_doorbell_interrupt)
adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
return 0;
{0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
{0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU},
/* Arcturus */
- {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
- {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT},
+ {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
+ {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
+ {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
+ {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS},
/* Navi10 */
{0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
+ {0x1002, 0x731E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
/* Navi14 */
{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
struct ww_acquire_ctx ticket;
struct list_head list, duplicates;
uint64_t va_flags;
+ uint64_t vm_size;
int r = 0;
if (args->va_address < AMDGPU_VA_RESERVED_SIZE) {
args->va_address &= AMDGPU_GMC_HOLE_MASK;
+ vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
+ vm_size -= AMDGPU_VA_RESERVED_SIZE;
+ if (args->va_address + args->map_size > vm_size) {
+ dev_dbg(&dev->pdev->dev,
+ "va_address 0x%llx is in top reserved area 0x%llx\n",
+ args->va_address + args->map_size, vm_size);
+ return -EINVAL;
+ }
+
if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) {
dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n",
args->flags);
/**
* amdgpu_gtt_mgr_init - init GTT manager and DRM MM
*
- * @man: TTM memory type manager
- * @p_size: maximum size of GTT
+ * @adev: amdgpu_device pointer
+ * @gtt_size: maximum size of GTT
*
* Allocate and initialize the GTT manager.
*/
/**
* amdgpu_gtt_mgr_fini - free and destroy GTT manager
*
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
*
* Destroy and free the GTT manager, returns -EBUSY if ranges are still
* allocated inside it.
psp->asd_feature_version = le32_to_cpu(desc->fw_version);
psp->asd_ucode_size = le32_to_cpu(desc->size_bytes);
psp->asd_start_addr = ucode_start_addr;
+ psp->asd_fw = psp->ta_fw;
break;
case TA_FW_TYPE_PSP_XGMI:
psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version);
static int amdgpu_ttm_init_on_chip(struct amdgpu_device *adev,
unsigned int type,
- uint64_t size)
+ uint64_t size_in_page)
{
return ttm_range_man_init(&adev->mman.bdev, type,
- false, size >> PAGE_SHIFT);
+ false, size_in_page);
}
/**
unsigned harvest_config;
/* store image width to adjust nb memory state */
unsigned decode_image_width;
+ uint32_t keyselect;
};
int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
#define FIRMWARE_RAVEN2 "amdgpu/raven2_vcn.bin"
#define FIRMWARE_ARCTURUS "amdgpu/arcturus_vcn.bin"
#define FIRMWARE_RENOIR "amdgpu/renoir_vcn.bin"
+#define FIRMWARE_GREEN_SARDINE "amdgpu/green_sardine_vcn.bin"
#define FIRMWARE_NAVI10 "amdgpu/navi10_vcn.bin"
#define FIRMWARE_NAVI14 "amdgpu/navi14_vcn.bin"
#define FIRMWARE_NAVI12 "amdgpu/navi12_vcn.bin"
MODULE_FIRMWARE(FIRMWARE_RAVEN2);
MODULE_FIRMWARE(FIRMWARE_ARCTURUS);
MODULE_FIRMWARE(FIRMWARE_RENOIR);
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE);
MODULE_FIRMWARE(FIRMWARE_NAVI10);
MODULE_FIRMWARE(FIRMWARE_NAVI14);
MODULE_FIRMWARE(FIRMWARE_NAVI12);
adev->vcn.indirect_sram = true;
break;
case CHIP_RENOIR:
- fw_name = FIRMWARE_RENOIR;
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ fw_name = FIRMWARE_RENOIR;
+ else
+ fw_name = FIRMWARE_GREEN_SARDINE;
+
if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
adev->vcn.indirect_sram = true;
#define AMDGPU_MMHUB_0 1
#define AMDGPU_MMHUB_1 2
-/* hardcode that limit for now */
-#define AMDGPU_VA_RESERVED_SIZE (1ULL << 20)
+/* Reserve 2MB at top/bottom of address space for kernel use */
+#define AMDGPU_VA_RESERVED_SIZE (2ULL << 20)
/* max vmids dedicated for process */
#define AMDGPU_VM_MAX_RESERVED_VMID 1
/**
* amdgpu_vram_mgr_init - init VRAM manager and DRM MM
*
- * @man: TTM memory type manager
- * @p_size: maximum size of VRAM
+ * @adev: amdgpu_device pointer
*
* Allocate and initialize the VRAM manager.
*/
/**
* amdgpu_vram_mgr_fini - free and destroy VRAM manager
*
- * @man: TTM memory type manager
+ * @adev: amdgpu_device pointer
*
* Destroy and free the VRAM manager, returns -EBUSY if ranges are still
* allocated inside it.
/**
* amdgpu_vram_mgr_vis_size - Calculate visible node size
*
- * @adev: amdgpu device structure
+ * @adev: amdgpu_device pointer
* @node: MM node structure
*
* Calculate how many bytes of the MM node are inside visible VRAM
switch (adev->asic_type) {
case CHIP_BONAIRE:
- case CHIP_HAWAII:
/* disable baco reset until it works */
/* smu7_asic_get_baco_capability(adev, &baco_reset); */
baco_reset = false;
break;
+ case CHIP_HAWAII:
+ baco_reset = cik_asic_supports_baco(adev);
+ break;
default:
baco_reset = false;
break;
{
u32 srbm_soft_reset = 0;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- u32 tmp = RREG32(mmSRBM_STATUS2);
+ u32 tmp;
- if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) {
- /* sdma0 */
- tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
- tmp |= SDMA0_F32_CNTL__HALT_MASK;
- WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
- srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
- }
- if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) {
- /* sdma1 */
- tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
- tmp |= SDMA0_F32_CNTL__HALT_MASK;
- WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
- srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
- }
+ /* sdma0 */
+ tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET);
+ tmp |= SDMA0_F32_CNTL__HALT_MASK;
+ WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp);
+ srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK;
+
+ /* sdma1 */
+ tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET);
+ tmp |= SDMA0_F32_CNTL__HALT_MASK;
+ WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp);
+ srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK;
if (srbm_soft_reset) {
tmp = RREG32(mmSRBM_SOFT_RESET);
#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3
#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK 0x00000008L
+#define mmCGTT_SPI_CS_CLK_CTRL 0x507c
+#define mmCGTT_SPI_CS_CLK_CTRL_BASE_IDX 1
+
MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
MODULE_FIRMWARE("amdgpu/navi10_me.bin");
static const struct soc15_reg_golden golden_settings_gc_10_3[] =
{
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CS_CLK_CTRL, 0x78000000, 0x78000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_PS_CLK_CTRL, 0xff7f0fff, 0x78000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0 ,mmGCEA_SDP_TAG_RESERVE0, 0xffffffff, 0x10100100),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCEA_SDP_TAG_RESERVE1, 0xffffffff, 0x17000088),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x1ff1ffff, 0x00000500),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003fffff, 0x00280400),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
MODULE_FIRMWARE("amdgpu/renoir_mec2.bin");
MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_ce.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_pfp.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_me.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_mec2.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin");
+
#define mmTCP_CHAN_STEER_0_ARCT 0x0b03
#define mmTCP_CHAN_STEER_0_ARCT_BASE_IDX 0
#define mmTCP_CHAN_STEER_1_ARCT 0x0b04
chip_name = "arcturus";
break;
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
default:
BUG();
adev->virt.ops = &xgpu_nv_virt_ops;
}
+static bool nv_is_headless_sku(struct pci_dev *pdev)
+{
+ if ((pdev->device == 0x731E &&
+ (pdev->revision == 0xC6 || pdev->revision == 0xC7)) ||
+ (pdev->device == 0x7340 && pdev->revision == 0xC9))
+ return true;
+ return false;
+}
+
int nv_set_ip_blocks(struct amdgpu_device *adev)
{
int r;
if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
!amdgpu_sriov_vf(adev))
amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
- amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+ if (!nv_is_headless_sku(adev->pdev))
+ amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
if (adev->enable_mes)
amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
MODULE_FIRMWARE("amdgpu/renoir_asd.bin");
MODULE_FIRMWARE("amdgpu/renoir_ta.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin");
/* address block */
#define smnMP1_FIRMWARE_FLAGS 0x3010024
switch (adev->asic_type) {
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
default:
BUG();
MODULE_FIRMWARE("amdgpu/raven2_sdma.bin");
MODULE_FIRMWARE("amdgpu/arcturus_sdma.bin");
MODULE_FIRMWARE("amdgpu/renoir_sdma.bin");
+MODULE_FIRMWARE("amdgpu/green_sardine_sdma.bin");
#define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK 0x000000F8L
#define SDMA0_POWER_CNTL__ON_OFF_STATUS_DURATION_TIME_MASK 0xFC000000L
chip_name = "arcturus";
break;
case CHIP_RENOIR:
- chip_name = "renoir";
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ chip_name = "renoir";
+ else
+ chip_name = "green_sardine";
break;
default:
BUG();
adev->pg_flags = AMD_PG_SUPPORT_SDMA |
AMD_PG_SUPPORT_MMHUB |
- AMD_PG_SUPPORT_VCN |
- AMD_PG_SUPPORT_VCN_DPG;
+ AMD_PG_SUPPORT_VCN;
} else {
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
break;
case CHIP_RENOIR:
adev->asic_funcs = &soc15_asic_funcs;
- adev->apu_flags |= AMD_APU_IS_RENOIR;
+ if (adev->pdev->device == 0x1636)
+ adev->apu_flags |= AMD_APU_IS_RENOIR;
+ else
+ adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
+
+ if (adev->apu_flags & AMD_APU_IS_RENOIR)
+ adev->external_rev_id = adev->rev_id + 0x91;
+ else
+ adev->external_rev_id = adev->rev_id + 0xa1;
adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
AMD_CG_SUPPORT_GFX_MGLS |
AMD_CG_SUPPORT_GFX_3D_CGCG |
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_JPEG |
AMD_PG_SUPPORT_VCN_DPG;
- adev->external_rev_id = adev->rev_id + 0x91;
break;
default:
/* FIXME: not supported yet */
*/
static int uvd_v3_1_fw_validate(struct amdgpu_device *adev)
{
- void *ptr;
- uint32_t ucode_len, i;
- uint32_t keysel;
-
- ptr = adev->uvd.inst[0].cpu_addr;
- ptr += 192 + 16;
- memcpy(&ucode_len, ptr, 4);
- ptr += ucode_len;
- memcpy(&keysel, ptr, 4);
+ int i;
+ uint32_t keysel = adev->uvd.keyselect;
WREG32(mmUVD_FW_START, keysel);
struct amdgpu_ring *ring;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int r;
+ void *ptr;
+ uint32_t ucode_len;
/* UVD TRAP */
r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
if (r)
return r;
+ /* Retrieval firmware validate key */
+ ptr = adev->uvd.inst[0].cpu_addr;
+ ptr += 192 + 16;
+ memcpy(&ucode_len, ptr, 4);
+ ptr += ucode_len;
+ memcpy(&adev->uvd.keyselect, ptr, 4);
+
r = amdgpu_uvd_entity_init(adev);
return r;
tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_CNTL, tmp);
+ /* Stall DPG before WPTR/RPTR reset */
+ WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
+ UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
+ ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
+
/* set the write pointer delay */
WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR_CNTL, 0);
WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR,
lower_32_bits(ring->wptr));
+ /* Unstall DPG */
+ WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
+ 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
+
return 0;
}
UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+ /* Stall DPG before WPTR/RPTR reset */
+ WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
+ UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
+ ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
+
/* Restore */
ring = &adev->vcn.inst[inst_idx].ring_enc[0];
+ ring->wptr = 0;
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr);
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4);
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
ring = &adev->vcn.inst[inst_idx].ring_enc[1];
+ ring->wptr = 0;
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr);
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4);
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR,
- RREG32_SOC15(VCN, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF);
+ /* Unstall DPG */
+ WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
+ 0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS,
UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
{
struct amdgpu_device *adev = ring->adev;
- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
- WREG32_SOC15(VCN, ring->me, mmUVD_SCRATCH2,
- lower_32_bits(ring->wptr) | 0x80000000);
-
if (ring->use_doorbell) {
adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
}
pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL);
- memcpy(pcrat_image, crat_table, crat_table->length);
if (!pcrat_image)
return -ENOMEM;
+ memcpy(pcrat_image, crat_table, crat_table->length);
*crat_image = pcrat_image;
*size = crat_table->length;
config DEBUG_KERNEL_DC
bool "Enable kgdb break in DC"
depends on DRM_AMD_DC
+ depends on KGDB
help
Choose this option if you want to hit kdgb_break in assert.
#define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin"
MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB);
#endif
+#define FIRMWARE_GREEN_SARDINE_DMUB "amdgpu/green_sardine_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE_DMUB);
#define FIRMWARE_RAVEN_DMCU "amdgpu/raven_dmcu.bin"
MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU);
{
struct drm_device *dev = connector->dev;
struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_comressor_info *compressor = &adev->dm.compressor;
+ struct dm_compressor_info *compressor = &adev->dm.compressor;
struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector);
struct drm_display_mode *mode;
unsigned long max_size = 0;
case CHIP_RAVEN:
case CHIP_RENOIR:
init_data.flags.gpu_vm_support = true;
+ if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+ init_data.flags.disable_dmcu = true;
break;
default:
break;
amdgpu_dm_init_color_mod();
#ifdef CONFIG_DRM_AMD_DC_HDCP
- if (adev->asic_type >= CHIP_RAVEN) {
+ if (adev->dm.dc->caps.max_links > 0 && adev->asic_type >= CHIP_RAVEN) {
adev->dm.hdcp_workqueue = hdcp_create_workqueue(adev, &init_params.cp_psp, adev->dm.dc);
if (!adev->dm.hdcp_workqueue)
case CHIP_RENOIR:
dmub_asic = DMUB_ASIC_DCN21;
fw_name_dmub = FIRMWARE_RENOIR_DMUB;
+ if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id))
+ fw_name_dmub = FIRMWARE_GREEN_SARDINE_DMUB;
break;
#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
case CHIP_SIENNA_CICHLID:
bool mode_set_reset_required = false;
drm_atomic_helper_update_legacy_modeset_state(dev, state);
- drm_atomic_helper_calc_timestamping_constants(state);
dm_state = dm_atomic_get_new_state(state);
if (dm_state && dm_state->context) {
}
}
+ drm_atomic_helper_calc_timestamping_constants(state);
+
/* update changed items */
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
* @bo_ptr: Pointer to the buffer object
* @gpu_addr: MMIO gpu addr
*/
-struct dm_comressor_info {
+struct dm_compressor_info {
void *cpu_addr;
struct amdgpu_bo *bo_ptr;
uint64_t gpu_addr;
* @soc_bounding_box: SOC bounding box values provided by gpu_info FW
* @cached_state: Caches device atomic state for suspend/resume
* @cached_dc_state: Cached state of content streams
- * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
+ * @compressor: Frame buffer compression buffer. See &struct dm_compressor_info
* @force_timing_sync: set via debugfs. When set, indicates that all connected
* displays will be forced to synchronize.
*/
struct drm_atomic_state *cached_state;
struct dc_state *cached_dc_state;
- struct dm_comressor_info compressor;
+ struct dm_compressor_info compressor;
const struct firmware *fw_dmcu;
uint32_t dmcu_fw_version;
rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
break;
}
+
+ if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) {
+ rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
+ break;
+ }
if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) {
rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
break;
new_clocks->dppclk_khz = 100000;
}
- if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
- if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz)
+ /*
+ * Temporally ignore thew 0 cases for disp and dpp clks.
+ * We may have a new feature that requires 0 clks in the future.
+ */
+ if (new_clocks->dppclk_khz == 0 || new_clocks->dispclk_khz == 0) {
+ new_clocks->dppclk_khz = clk_mgr_base->clks.dppclk_khz;
+ new_clocks->dispclk_khz = clk_mgr_base->clks.dispclk_khz;
+ }
+
+ if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr_base->clks.dppclk_khz)) {
+ if (clk_mgr_base->clks.dppclk_khz > new_clocks->dppclk_khz)
dpp_clock_lowered = true;
clk_mgr_base->clks.dppclk_khz = new_clocks->dppclk_khz;
update_dppclk = true;
struct dc_state *dc_create_state(struct dc *dc)
{
- struct dc_state *context = kzalloc(sizeof(struct dc_state),
- GFP_KERNEL);
+ struct dc_state *context = kvzalloc(sizeof(struct dc_state),
+ GFP_KERNEL);
if (!context)
return NULL;
dc_version = DCN_VERSION_1_01;
if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev))
dc_version = DCN_VERSION_2_1;
+ if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev))
+ dc_version = DCN_VERSION_2_1;
break;
#endif
static const struct clock_source_funcs dcn3_clk_src_funcs = {
.cs_power_down = dce110_clock_source_power_down,
.program_pix_clk = dcn3_program_pix_clk,
- .get_pix_clk_dividers = dcn3_get_pix_clk_dividers
+ .get_pix_clk_dividers = dcn3_get_pix_clk_dividers,
+ .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz
};
#endif
/*****************************************/
if (split[i]) {
if (odm) {
- if (split[i] == 4 && old_pipe->next_odm_pipe->next_odm_pipe)
+ if (split[i] == 4 && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe)
old_index = old_pipe->next_odm_pipe->next_odm_pipe->pipe_idx;
else if (old_pipe->next_odm_pipe)
old_index = old_pipe->next_odm_pipe->pipe_idx;
} else {
- if (split[i] == 4 && old_pipe->bottom_pipe->bottom_pipe &&
+ if (split[i] == 4 && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe &&
old_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
old_index = old_pipe->bottom_pipe->bottom_pipe->pipe_idx;
else if (old_pipe->bottom_pipe &&
goto validate_fail;
newly_split[pipe_4to1->pipe_idx] = true;
- if (odm && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe)
+ if (odm && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe
+ && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe)
old_index = old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe->pipe_idx;
- else if (!odm && old_pipe->bottom_pipe->bottom_pipe->bottom_pipe &&
- old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
+ else if (!odm && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe &&
+ old_pipe->bottom_pipe->bottom_pipe->bottom_pipe &&
+ old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state)
old_index = old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->pipe_idx;
else
old_index = -1;
ddc_data_regs_dcn2(4),
ddc_data_regs_dcn2(5),
ddc_data_regs_dcn2(6),
+ {
+ DDC_GPIO_VGA_REG_LIST(DATA),
+ .ddc_setup = 0,
+ .phy_aux_cntl = 0,
+ .dc_gpio_aux_ctrl_5 = 0
+ }
};
static const struct ddc_registers ddc_clk_regs_dcn[] = {
ddc_clk_regs_dcn2(4),
ddc_clk_regs_dcn2(5),
ddc_clk_regs_dcn2(6),
+ {
+ DDC_GPIO_VGA_REG_LIST(CLK),
+ .ddc_setup = 0,
+ .phy_aux_cntl = 0,
+ .dc_gpio_aux_ctrl_5 = 0
+ }
};
static const struct ddc_sh_mask ddc_shift[] = {
enum gpio_mode mode)
{
if (gpio->pin) {
- ASSERT_CRITICAL(false);
+ BREAK_TO_DEBUGGER();
return GPIO_RESULT_ALREADY_OPENED;
}
// No action if allocation failed during gpio construct
if (!gpio->hw_container.ddc) {
- ASSERT_CRITICAL(false);
+ BREAK_TO_DEBUGGER();
return GPIO_RESULT_NON_SPECIFIC_ERROR;
}
gpio->mode = mode;
pflip_int_entry(1),
pflip_int_entry(2),
pflip_int_entry(3),
- [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(),
- [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(),
+ pflip_int_entry(4),
+ pflip_int_entry(5),
[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
gpio_pad_int_entry(0),
gpio_pad_int_entry(1),
pflip_int_entry(1),
pflip_int_entry(2),
pflip_int_entry(3),
- [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(),
- [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(),
+ pflip_int_entry(4),
+ pflip_int_entry(5),
[DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(),
gpio_pad_int_entry(0),
gpio_pad_int_entry(1),
* general debug capabilities
*
*/
-#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)
-#define ASSERT_CRITICAL(expr) do { \
- if (WARN_ON(!(expr))) { \
- kgdb_breakpoint(); \
- } \
-} while (0)
+#ifdef CONFIG_DEBUG_KERNEL_DC
+#define dc_breakpoint() kgdb_breakpoint()
#else
-#define ASSERT_CRITICAL(expr) do { \
- if (WARN_ON(!(expr))) { \
- ; \
- } \
-} while (0)
+#define dc_breakpoint() do {} while (0)
#endif
-#if defined(CONFIG_DEBUG_KERNEL_DC)
-#define ASSERT(expr) ASSERT_CRITICAL(expr)
+#define ASSERT_CRITICAL(expr) do { \
+ if (WARN_ON(!(expr))) \
+ dc_breakpoint(); \
+ } while (0)
-#else
-#define ASSERT(expr) WARN_ON_ONCE(!(expr))
-#endif
+#define ASSERT(expr) do { \
+ if (WARN_ON_ONCE(!(expr))) \
+ dc_breakpoint(); \
+ } while (0)
-#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB))
#define BREAK_TO_DEBUGGER() \
do { \
DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__); \
- kgdb_breakpoint(); \
+ dc_breakpoint(); \
} while (0)
-#else
-#define BREAK_TO_DEBUGGER() DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__)
-#endif
#define DC_ERR(...) do { \
dm_error(__VA_ARGS__); \
#if defined(CONFIG_DRM_AMD_DC_DCN3_0)
#define ASICREV_IS_SIENNA_CICHLID_P(eChipRev) ((eChipRev >= NV_SIENNA_CICHLID_P_A0))
#endif
+#define GREEN_SARDINE_A0 0xA1
+#ifndef ASICREV_IS_GREEN_SARDINE
+#define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF))
+#endif
/*
* ASIC chip ID
AMD_APU_IS_RAVEN2 = 0x00000002UL,
AMD_APU_IS_PICASSO = 0x00000004UL,
AMD_APU_IS_RENOIR = 0x00000008UL,
+ AMD_APU_IS_GREEN_SARDINE = 0x00000010UL,
};
/**
bool (*is_hw_avfs_present)(struct pp_hwmgr *hwmgr);
int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting);
int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */
+ int (*stop_smc)(struct pp_hwmgr *hwmgr);
};
struct pp_hwmgr_func {
extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw);
+extern int smum_stop_smc(struct pp_hwmgr *hwmgr);
+
#endif
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
{ CMD_DELAY_MS, 0, 0, 0, 20, 0 },
- { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 },
+ { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
- { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c },
+ { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
- { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 },
+ { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
};
static const struct baco_cmd_entry clean_baco_tbl[] =
{
{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+ { CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 },
{ CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 }
};
PP_ASSERT_WITH_CODE((tmp_result == 0),
"Failed to reset to default!", result = tmp_result);
+ tmp_result = smum_stop_smc(hwmgr);
+ PP_ASSERT_WITH_CODE((tmp_result == 0),
+ "Failed to stop smc!", result = tmp_result);
+
tmp_result = smu7_force_switch_to_arbf0(hwmgr);
PP_ASSERT_WITH_CODE((tmp_result == 0),
"Failed to force to switch arbf0!", result = tmp_result);
data->current_profile_setting.sclk_down_hyst = 100;
data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
data->current_profile_setting.bupdate_mclk = 1;
- if (adev->gmc.vram_width == 256) {
- data->current_profile_setting.mclk_up_hyst = 10;
- data->current_profile_setting.mclk_down_hyst = 60;
- data->current_profile_setting.mclk_activity = 25;
- } else if (adev->gmc.vram_width == 128) {
- data->current_profile_setting.mclk_up_hyst = 5;
- data->current_profile_setting.mclk_down_hyst = 16;
- data->current_profile_setting.mclk_activity = 20;
- } else if (adev->gmc.vram_width == 64) {
- data->current_profile_setting.mclk_up_hyst = 3;
- data->current_profile_setting.mclk_down_hyst = 16;
- data->current_profile_setting.mclk_activity = 20;
+ if (hwmgr->chip_id >= CHIP_POLARIS10) {
+ if (adev->gmc.vram_width == 256) {
+ data->current_profile_setting.mclk_up_hyst = 10;
+ data->current_profile_setting.mclk_down_hyst = 60;
+ data->current_profile_setting.mclk_activity = 25;
+ } else if (adev->gmc.vram_width == 128) {
+ data->current_profile_setting.mclk_up_hyst = 5;
+ data->current_profile_setting.mclk_down_hyst = 16;
+ data->current_profile_setting.mclk_activity = 20;
+ } else if (adev->gmc.vram_width == 64) {
+ data->current_profile_setting.mclk_up_hyst = 3;
+ data->current_profile_setting.mclk_down_hyst = 16;
+ data->current_profile_setting.mclk_activity = 20;
+ }
+ } else {
+ data->current_profile_setting.mclk_up_hyst = 0;
+ data->current_profile_setting.mclk_down_hyst = 100;
+ data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
}
hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D];
hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D;
static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr)
{
- return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
- CGS_IND_REG__SMC, FEATURE_STATUS,
- VOLTAGE_CONTROLLER_ON))
- ? true : false;
+ return ci_is_smc_ram_running(hwmgr);
}
static int ci_smu_init(struct pp_hwmgr *hwmgr)
return 0;
}
+static void ci_reset_smc(struct pp_hwmgr *hwmgr)
+{
+ PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+ SMC_SYSCON_RESET_CNTL,
+ rst_reg, 1);
+}
+
+
+static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr)
+{
+ PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC,
+ SMC_SYSCON_CLOCK_CNTL_0,
+ ck_disable, 1);
+}
+
+static int ci_stop_smc(struct pp_hwmgr *hwmgr)
+{
+ ci_reset_smc(hwmgr);
+ ci_stop_smc_clock(hwmgr);
+
+ return 0;
+}
+
const struct pp_smumgr_func ci_smu_funcs = {
.name = "ci_smu",
.smu_init = ci_smu_init,
.is_dpm_running = ci_is_dpm_running,
.update_dpm_settings = ci_update_dpm_settings,
.update_smc_table = ci_update_smc_table,
+ .stop_smc = ci_stop_smc,
};
return -EINVAL;
}
+
+int smum_stop_smc(struct pp_hwmgr *hwmgr)
+{
+ if (hwmgr->smumgr_funcs->stop_smc)
+ return hwmgr->smumgr_funcs->stop_smc(hwmgr);
+
+ return 0;
+}
return ret;
}
- /*
- * Set initialized values (get from vbios) to dpm tables context such as
- * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each
- * type of clks.
- */
- ret = smu_set_default_dpm_table(smu);
- if (ret) {
- dev_err(adev->dev, "Failed to setup default dpm clock tables!\n");
- return ret;
- }
-
ret = smu_notify_display_change(smu);
if (ret)
return ret;
if (!speed)
return -EINVAL;
- switch (smu_v11_0_get_fan_control_mode(smu)) {
- case AMD_FAN_CTRL_AUTO:
- return navi10_get_smu_metrics_data(smu,
- METRICS_CURR_FANSPEED,
- speed);
- default:
- return smu_v11_0_get_fan_speed_rpm(smu, speed);
- }
+ return navi10_get_smu_metrics_data(smu,
+ METRICS_CURR_FANSPEED,
+ speed);
}
static int navi10_get_fan_parameters(struct smu_context *smu)
.functionality = navi10_i2c_func,
};
-static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control)
-{
- struct amdgpu_device *adev = to_amdgpu_device(control);
- int res;
-
- control->owner = THIS_MODULE;
- control->class = I2C_CLASS_SPD;
- control->dev.parent = &adev->pdev->dev;
- control->algo = &navi10_i2c_algo;
- snprintf(control->name, sizeof(control->name), "AMDGPU SMU");
-
- res = i2c_add_adapter(control);
- if (res)
- DRM_ERROR("Failed to register hw i2c, err: %d\n", res);
-
- return res;
-}
-
-static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control)
-{
- i2c_del_adapter(control);
-}
-
static ssize_t navi10_get_gpu_metrics(struct smu_context *smu,
void **table)
{
.set_default_dpm_table = navi10_set_default_dpm_table,
.dpm_set_vcn_enable = navi10_dpm_set_vcn_enable,
.dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable,
- .i2c_init = navi10_i2c_control_init,
- .i2c_fini = navi10_i2c_control_fini,
.print_clk_levels = navi10_print_clk_levels,
.force_clk_levels = navi10_force_clk_levels,
.populate_umd_state_clk = navi10_populate_umd_state_clk,
if (!speed)
return -EINVAL;
- switch (smu_v11_0_get_fan_control_mode(smu)) {
- case AMD_FAN_CTRL_AUTO:
- return sienna_cichlid_get_smu_metrics_data(smu,
- METRICS_CURR_FANSPEED,
- speed);
- default:
- return smu_v11_0_get_fan_speed_rpm(smu, speed);
- }
+ return sienna_cichlid_get_smu_metrics_data(smu,
+ METRICS_CURR_FANSPEED,
+ speed);
}
static int sienna_cichlid_get_fan_parameters(struct smu_context *smu)
if (ret)
return ret;
- crystal_clock_freq = amdgpu_asic_get_xclk(adev);
+ /*
+ * crystal_clock_freq div by 4 is required since the fan control
+ * module refers to 25MHz
+ */
+
+ crystal_clock_freq = amdgpu_asic_get_xclk(adev) / 4;
tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
WREG32_SOC15(THM, 0, mmCG_TACH_CTRL,
REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_TACH_CTRL),
case DRM_MODE_DPMS_SUSPEND:
if (ast->tx_chip_type == AST_TX_DP501)
ast_set_dp501_video_output(crtc->dev, 1);
- ast_crtc_load_lut(ast, crtc);
break;
case DRM_MODE_DPMS_OFF:
if (ast->tx_chip_type == AST_TX_DP501)
return 0;
}
+static void
+ast_crtc_helper_atomic_flush(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state)
+{
+ struct ast_private *ast = to_ast_private(crtc->dev);
+ struct ast_crtc_state *ast_crtc_state = to_ast_crtc_state(crtc->state);
+ struct ast_crtc_state *old_ast_crtc_state = to_ast_crtc_state(old_crtc_state);
+
+ /*
+ * The gamma LUT has to be reloaded after changing the primary
+ * plane's color format.
+ */
+ if (old_ast_crtc_state->format != ast_crtc_state->format)
+ ast_crtc_load_lut(ast, crtc);
+}
+
static void
ast_crtc_helper_atomic_enable(struct drm_crtc *crtc,
struct drm_crtc_state *old_crtc_state)
static const struct drm_crtc_helper_funcs ast_crtc_helper_funcs = {
.atomic_check = ast_crtc_helper_atomic_check,
+ .atomic_flush = ast_crtc_helper_atomic_flush,
.atomic_enable = ast_crtc_helper_atomic_enable,
.atomic_disable = ast_crtc_helper_atomic_disable,
};
if DRM_CDNS_MHDP8546
config DRM_CDNS_MHDP8546_J721E
- depends on ARCH_K3_J721E_SOC || COMPILE_TEST
+ depends on ARCH_K3 || COMPILE_TEST
bool "J721E Cadence DPI/DP wrapper support"
default y
help
{
enum drm_connector_status result;
- mutex_lock(&hdmi->mutex);
- hdmi->force = DRM_FORCE_UNSPECIFIED;
- dw_hdmi_update_power(hdmi);
- dw_hdmi_update_phy_mask(hdmi);
- mutex_unlock(&hdmi->mutex);
-
result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data);
mutex_lock(&hdmi->mutex);
* drm_dp_downstream_is_type() - is the downstream facing port of certain type?
* @dpcd: DisplayPort configuration data
* @port_cap: port capabilities
+ * @type: port type to be checked. Can be:
+ * %DP_DS_PORT_TYPE_DP, %DP_DS_PORT_TYPE_VGA, %DP_DS_PORT_TYPE_DVI,
+ * %DP_DS_PORT_TYPE_HDMI, %DP_DS_PORT_TYPE_NON_EDID,
+ * %DP_DS_PORT_TYPE_DP_DUALMODE or %DP_DS_PORT_TYPE_WIRELESS.
*
* Caveat: Only works with DPCD 1.1+ port caps.
*
/**
* drm_dp_downstream_mode() - return a mode for downstream facing port
+ * @dev: DRM device
* @dpcd: DisplayPort configuration data
* @port_cap: port capabilities
*
/**
* drm_dp_subconnector_type() - get DP branch device type
- *
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
*/
enum drm_mode_subconnector
drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
/**
* drm_mode_set_dp_subconnector_property - set subconnector for DP connector
+ * @connector: connector to set property on
+ * @status: connector status
+ * @dpcd: DisplayPort configuration data
+ * @port_cap: port capabilities
*
* Called by a driver on every detect event.
*/
/**
* drm_display_mode_from_cea_vic() - return a mode for CEA VIC
* @dev: DRM device
- * @vic: CEA VIC of the mode
+ * @video_code: CEA VIC of the mode
*
* Creates a new mode matching the specified CEA VIC.
*
*/
drm_gem_object_get(obj);
+ vma->vm_private_data = obj;
+
if (obj->funcs && obj->funcs->mmap) {
ret = obj->funcs->mmap(obj, vma);
if (ret) {
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
}
- vma->vm_private_data = obj;
-
return 0;
}
EXPORT_SYMBOL(drm_gem_mmap_obj);
/* Remove the fake offset */
vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
- if (obj->import_attach)
+ if (obj->import_attach) {
+ /* Drop the reference drm_gem_mmap_obj() acquired.*/
+ drm_gem_object_put(obj);
+ vma->vm_private_data = NULL;
+
return dma_buf_mmap(obj->dma_buf, vma, 0);
+ }
shmem = to_drm_gem_shmem_obj(obj);
unsigned int c = 0;
if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN)
- pl_flag = TTM_PL_FLAG_TOPDOWN;
+ invariant_flags = TTM_PL_FLAG_TOPDOWN;
gbo->placement.placement = gbo->placements;
gbo->placement.busy_placement = gbo->placements;
/**
* drm_prime_pages_to_sg - converts a page array into an sg list
+ * @dev: DRM device
* @pages: pointer to the array of page pointers to convert
* @nr_pages: length of the page vector
*
# SPDX-License-Identifier: GPL-2.0-only
config DRM_EXYNOS
tristate "DRM Support for Samsung SoC Exynos Series"
- depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST)
+ depends on OF && DRM && COMMON_CLK
+ depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST
depends on MMU
select DRM_KMS_HELPER
select VIDEOMODE_HELPERS
{
struct drm_psb_private *dev_priv = dev->dev_private;
unsigned long irqflags;
+ unsigned int i;
spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R);
PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
- if (dev->vblank[0].enabled)
- psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
- else
- psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[1].enabled)
- psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
- else
- psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[2].enabled)
- psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
- else
- psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+ for (i = 0; i < dev->num_crtcs; ++i) {
+ if (dev->vblank[i].enabled)
+ psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+ else
+ psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+ }
if (dev_priv->ops->hotplug_enable)
dev_priv->ops->hotplug_enable(dev, true);
{
struct drm_psb_private *dev_priv = dev->dev_private;
unsigned long irqflags;
+ unsigned int i;
spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags);
PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM);
- if (dev->vblank[0].enabled)
- psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[1].enabled)
- psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE);
-
- if (dev->vblank[2].enabled)
- psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE);
+ for (i = 0; i < dev->num_crtcs; ++i) {
+ if (dev->vblank[i].enabled)
+ psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE);
+ }
dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG |
_PSB_IRQ_MSVDX_FLAG |
val & PLANE_CTL_FLIP_HORIZONTAL)
plane_config->rotation |= DRM_MODE_REFLECT_X;
+ /* 90/270 degree rotation would require extra work */
+ if (drm_rotation_90_or_270(plane_config->rotation))
+ goto error;
+
base = intel_de_read(dev_priv, PLANE_SURF(pipe, plane_id)) & 0xfffff000;
plane_config->base = base;
case 10 ... 11:
bpp = 10 * 3;
break;
- case 12:
+ case 12 ... 16:
bpp = 12 * 3;
break;
default:
+ MISSING_CASE(conn_state->max_bpc);
return -EINVAL;
}
if (!HAS_GMCH(i915))
sanitize_watermarks(i915);
- /*
- * Force all active planes to recompute their states. So that on
- * mode_setcrtc after probe, all the intel_plane_state variables
- * are already calculated and there is no assert_plane warnings
- * during bootup.
- */
- ret = intel_initial_commit(dev);
- if (ret)
- drm_dbg_kms(&i915->drm, "Initial commit in probe failed.\n");
-
return 0;
}
{
int ret;
- intel_overlay_setup(i915);
-
if (!HAS_DISPLAY(i915))
return 0;
+ /*
+ * Force all active planes to recompute their states. So that on
+ * mode_setcrtc after probe, all the intel_plane_state variables
+ * are already calculated and there is no assert_plane warnings
+ * during bootup.
+ */
+ ret = intel_initial_commit(&i915->drm);
+ if (ret)
+ return ret;
+
+ intel_overlay_setup(i915);
+
ret = intel_fbdev_init(&i915->drm);
if (ret)
return ret;
return;
intel_connector = to_intel_connector(connector);
- dig_port = enc_to_dig_port(intel_attached_encoder(intel_connector));
+ dig_port = enc_to_dig_port(to_intel_encoder(new_state->best_encoder));
if (dev_priv->psr.dp != &dig_port->dp)
return;
if (!obj)
return -ENOENT;
- /*
- * Already in the desired write domain? Nothing for us to do!
- *
- * We apply a little bit of cunning here to catch a broader set of
- * no-ops. If obj->write_domain is set, we must be in the same
- * obj->read_domains, and only that domain. Therefore, if that
- * obj->write_domain matches the request read_domains, we are
- * already in the same read/write domain and can skip the operation,
- * without having to further check the requested write_domain.
- */
- if (READ_ONCE(obj->write_domain) == read_domains) {
- err = 0;
- goto out;
- }
-
/*
* Try to flush the object off the GPU without holding the lock.
* We will repeat the flush holding the lock in the normal manner
if (err)
goto out;
+ /*
+ * Already in the desired write domain? Nothing for us to do!
+ *
+ * We apply a little bit of cunning here to catch a broader set of
+ * no-ops. If obj->write_domain is set, we must be in the same
+ * obj->read_domains, and only that domain. Therefore, if that
+ * obj->write_domain matches the request read_domains, we are
+ * already in the same read/write domain and can skip the operation,
+ * without having to further check the requested write_domain.
+ */
+ if (READ_ONCE(obj->write_domain) == read_domains)
+ goto out_unpin;
+
err = i915_gem_object_lock_interruptible(obj, NULL);
if (err)
goto out_unpin;
void (*truncate)(struct drm_i915_gem_object *obj);
void (*writeback)(struct drm_i915_gem_object *obj);
+ int (*pread)(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pread *arg);
int (*pwrite)(struct drm_i915_gem_object *obj,
const struct drm_i915_gem_pwrite *arg);
vaddr, dma);
}
+static int
+phys_pwrite(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pwrite *args)
+{
+ void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+ char __user *user_data = u64_to_user_ptr(args->data_ptr);
+ int err;
+
+ err = i915_gem_object_wait(obj,
+ I915_WAIT_INTERRUPTIBLE |
+ I915_WAIT_ALL,
+ MAX_SCHEDULE_TIMEOUT);
+ if (err)
+ return err;
+
+ /*
+ * We manually control the domain here and pretend that it
+ * remains coherent i.e. in the GTT domain, like shmem_pwrite.
+ */
+ i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
+
+ if (copy_from_user(vaddr, user_data, args->size))
+ return -EFAULT;
+
+ drm_clflush_virt_range(vaddr, args->size);
+ intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
+
+ i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
+ return 0;
+}
+
+static int
+phys_pread(struct drm_i915_gem_object *obj,
+ const struct drm_i915_gem_pread *args)
+{
+ void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
+ char __user *user_data = u64_to_user_ptr(args->data_ptr);
+ int err;
+
+ err = i915_gem_object_wait(obj,
+ I915_WAIT_INTERRUPTIBLE,
+ MAX_SCHEDULE_TIMEOUT);
+ if (err)
+ return err;
+
+ drm_clflush_virt_range(vaddr, args->size);
+ if (copy_to_user(user_data, vaddr, args->size))
+ return -EFAULT;
+
+ return 0;
+}
+
static void phys_release(struct drm_i915_gem_object *obj)
{
fput(obj->base.filp);
.get_pages = i915_gem_object_get_pages_phys,
.put_pages = i915_gem_object_put_pages_phys,
+ .pread = phys_pread,
+ .pwrite = phys_pwrite,
+
.release = phys_release,
};
#include "i915_trace.h"
#include "intel_breadcrumbs.h"
#include "intel_context.h"
+#include "intel_engine_pm.h"
#include "intel_gt_pm.h"
#include "intel_gt_requests.h"
-static void irq_enable(struct intel_engine_cs *engine)
+static bool irq_enable(struct intel_engine_cs *engine)
{
if (!engine->irq_enable)
- return;
+ return false;
/* Caller disables interrupts */
spin_lock(&engine->gt->irq_lock);
engine->irq_enable(engine);
spin_unlock(&engine->gt->irq_lock);
+
+ return true;
}
static void irq_disable(struct intel_engine_cs *engine)
static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
{
- lockdep_assert_held(&b->irq_lock);
-
- if (!b->irq_engine || b->irq_armed)
- return;
-
- if (!intel_gt_pm_get_if_awake(b->irq_engine->gt))
+ /*
+ * Since we are waiting on a request, the GPU should be busy
+ * and should have its own rpm reference.
+ */
+ if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt)))
return;
/*
*/
WRITE_ONCE(b->irq_armed, true);
- /*
- * Since we are waiting on a request, the GPU should be busy
- * and should have its own rpm reference. This is tracked
- * by i915->gt.awake, we can forgo holding our own wakref
- * for the interrupt as before i915->gt.awake is released (when
- * the driver is idle) we disarm the breadcrumbs.
- */
-
- if (!b->irq_enabled++)
- irq_enable(b->irq_engine);
+ /* Requests may have completed before we could enable the interrupt. */
+ if (!b->irq_enabled++ && irq_enable(b->irq_engine))
+ irq_work_queue(&b->irq_work);
}
-static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
+static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
{
- lockdep_assert_held(&b->irq_lock);
-
- if (!b->irq_engine || !b->irq_armed)
+ if (!b->irq_engine)
return;
+ spin_lock(&b->irq_lock);
+ if (!b->irq_armed)
+ __intel_breadcrumbs_arm_irq(b);
+ spin_unlock(&b->irq_lock);
+}
+
+static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
+{
GEM_BUG_ON(!b->irq_enabled);
if (!--b->irq_enabled)
irq_disable(b->irq_engine);
intel_gt_pm_put_async(b->irq_engine->gt);
}
+static void intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
+{
+ spin_lock(&b->irq_lock);
+ if (b->irq_armed)
+ __intel_breadcrumbs_disarm_irq(b);
+ spin_unlock(&b->irq_lock);
+}
+
static void add_signaling_context(struct intel_breadcrumbs *b,
struct intel_context *ce)
{
- intel_context_get(ce);
- list_add_tail(&ce->signal_link, &b->signalers);
- if (list_is_first(&ce->signal_link, &b->signalers))
- __intel_breadcrumbs_arm_irq(b);
+ lockdep_assert_held(&ce->signal_lock);
+
+ spin_lock(&b->signalers_lock);
+ list_add_rcu(&ce->signal_link, &b->signalers);
+ spin_unlock(&b->signalers_lock);
}
-static void remove_signaling_context(struct intel_breadcrumbs *b,
+static bool remove_signaling_context(struct intel_breadcrumbs *b,
struct intel_context *ce)
{
- list_del(&ce->signal_link);
- intel_context_put(ce);
+ lockdep_assert_held(&ce->signal_lock);
+
+ if (!list_empty(&ce->signals))
+ return false;
+
+ spin_lock(&b->signalers_lock);
+ list_del_rcu(&ce->signal_link);
+ spin_unlock(&b->signalers_lock);
+
+ return true;
}
static inline bool __request_completed(const struct i915_request *rq)
intel_engine_add_retire(b->irq_engine, tl);
}
-static bool __signal_request(struct i915_request *rq, struct list_head *signals)
+static bool __signal_request(struct i915_request *rq)
{
- clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+ GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
if (!__dma_fence_signal(&rq->fence)) {
i915_request_put(rq);
return false;
}
- list_add_tail(&rq->signal_link, signals);
return true;
}
+static struct llist_node *
+slist_add(struct llist_node *node, struct llist_node *head)
+{
+ node->next = head;
+ return node;
+}
+
static void signal_irq_work(struct irq_work *work)
{
struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work);
const ktime_t timestamp = ktime_get();
- struct intel_context *ce, *cn;
- struct list_head *pos, *next;
- LIST_HEAD(signal);
-
- spin_lock(&b->irq_lock);
+ struct llist_node *signal, *sn;
+ struct intel_context *ce;
- if (list_empty(&b->signalers))
- __intel_breadcrumbs_disarm_irq(b);
+ signal = NULL;
+ if (unlikely(!llist_empty(&b->signaled_requests)))
+ signal = llist_del_all(&b->signaled_requests);
- list_splice_init(&b->signaled_requests, &signal);
+ /*
+ * Keep the irq armed until the interrupt after all listeners are gone.
+ *
+ * Enabling/disabling the interrupt is rather costly, roughly a couple
+ * of hundred microseconds. If we are proactive and enable/disable
+ * the interrupt around every request that wants a breadcrumb, we
+ * quickly drown in the extra orders of magnitude of latency imposed
+ * on request submission.
+ *
+ * So we try to be lazy, and keep the interrupts enabled until no
+ * more listeners appear within a breadcrumb interrupt interval (that
+ * is until a request completes that no one cares about). The
+ * observation is that listeners come in batches, and will often
+ * listen to a bunch of requests in succession. Though note on icl+,
+ * interrupts are always enabled due to concerns with rc6 being
+ * dysfunctional with per-engine interrupt masking.
+ *
+ * We also try to avoid raising too many interrupts, as they may
+ * be generated by userspace batches and it is unfortunately rather
+ * too easy to drown the CPU under a flood of GPU interrupts. Thus
+ * whenever no one appears to be listening, we turn off the interrupts.
+ * Fewer interrupts should conserve power -- at the very least, fewer
+ * interrupt draw less ire from other users of the system and tools
+ * like powertop.
+ */
+ if (!signal && READ_ONCE(b->irq_armed) && list_empty(&b->signalers))
+ intel_breadcrumbs_disarm_irq(b);
- list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) {
- GEM_BUG_ON(list_empty(&ce->signals));
+ rcu_read_lock();
+ list_for_each_entry_rcu(ce, &b->signalers, signal_link) {
+ struct i915_request *rq;
- list_for_each_safe(pos, next, &ce->signals) {
- struct i915_request *rq =
- list_entry(pos, typeof(*rq), signal_link);
+ list_for_each_entry_rcu(rq, &ce->signals, signal_link) {
+ bool release;
- GEM_BUG_ON(!check_signal_order(ce, rq));
if (!__request_completed(rq))
break;
+ if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL,
+ &rq->fence.flags))
+ break;
+
/*
* Queue for execution after dropping the signaling
* spinlock as the callback chain may end up adding
* more signalers to the same context or engine.
*/
- __signal_request(rq, &signal);
- }
+ spin_lock(&ce->signal_lock);
+ list_del_rcu(&rq->signal_link);
+ release = remove_signaling_context(b, ce);
+ spin_unlock(&ce->signal_lock);
- /*
- * We process the list deletion in bulk, only using a list_add
- * (not list_move) above but keeping the status of
- * rq->signal_link known with the I915_FENCE_FLAG_SIGNAL bit.
- */
- if (!list_is_first(pos, &ce->signals)) {
- /* Advance the list to the first incomplete request */
- __list_del_many(&ce->signals, pos);
- if (&ce->signals == pos) { /* now empty */
+ if (__signal_request(rq))
+ /* We own signal_node now, xfer to local list */
+ signal = slist_add(&rq->signal_node, signal);
+
+ if (release) {
add_retire(b, ce->timeline);
- remove_signaling_context(b, ce);
+ intel_context_put(ce);
}
}
}
+ rcu_read_unlock();
- spin_unlock(&b->irq_lock);
-
- list_for_each_safe(pos, next, &signal) {
+ llist_for_each_safe(signal, sn, signal) {
struct i915_request *rq =
- list_entry(pos, typeof(*rq), signal_link);
+ llist_entry(signal, typeof(*rq), signal_node);
struct list_head cb_list;
spin_lock(&rq->lock);
i915_request_put(rq);
}
+
+ if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers))
+ intel_breadcrumbs_arm_irq(b);
}
struct intel_breadcrumbs *
if (!b)
return NULL;
- spin_lock_init(&b->irq_lock);
+ b->irq_engine = irq_engine;
+
+ spin_lock_init(&b->signalers_lock);
INIT_LIST_HEAD(&b->signalers);
- INIT_LIST_HEAD(&b->signaled_requests);
+ init_llist_head(&b->signaled_requests);
+ spin_lock_init(&b->irq_lock);
init_irq_work(&b->irq_work, signal_irq_work);
- b->irq_engine = irq_engine;
-
return b;
}
void intel_breadcrumbs_park(struct intel_breadcrumbs *b)
{
- unsigned long flags;
-
- if (!READ_ONCE(b->irq_armed))
- return;
-
- spin_lock_irqsave(&b->irq_lock, flags);
- __intel_breadcrumbs_disarm_irq(b);
- spin_unlock_irqrestore(&b->irq_lock, flags);
-
- if (!list_empty(&b->signalers))
- irq_work_queue(&b->irq_work);
+ /* Kick the work once more to drain the signalers */
+ irq_work_sync(&b->irq_work);
+ while (unlikely(READ_ONCE(b->irq_armed))) {
+ local_irq_disable();
+ signal_irq_work(&b->irq_work);
+ local_irq_enable();
+ cond_resched();
+ }
+ GEM_BUG_ON(!list_empty(&b->signalers));
}
void intel_breadcrumbs_free(struct intel_breadcrumbs *b)
{
+ irq_work_sync(&b->irq_work);
+ GEM_BUG_ON(!list_empty(&b->signalers));
+ GEM_BUG_ON(b->irq_armed);
kfree(b);
}
-static void insert_breadcrumb(struct i915_request *rq,
- struct intel_breadcrumbs *b)
+static void insert_breadcrumb(struct i915_request *rq)
{
+ struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs;
struct intel_context *ce = rq->context;
struct list_head *pos;
* its signal completion.
*/
if (__request_completed(rq)) {
- if (__signal_request(rq, &b->signaled_requests))
+ if (__signal_request(rq) &&
+ llist_add(&rq->signal_node, &b->signaled_requests))
irq_work_queue(&b->irq_work);
return;
}
if (list_empty(&ce->signals)) {
+ intel_context_get(ce);
add_signaling_context(b, ce);
pos = &ce->signals;
} else {
break;
}
}
- list_add(&rq->signal_link, pos);
+ list_add_rcu(&rq->signal_link, pos);
GEM_BUG_ON(!check_signal_order(ce, rq));
+ GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags));
set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
- /* Check after attaching to irq, interrupt may have already fired. */
- if (__request_completed(rq))
- irq_work_queue(&b->irq_work);
+ /*
+ * Defer enabling the interrupt to after HW submission and recheck
+ * the request as it may have completed and raised the interrupt as
+ * we were attaching it into the lists.
+ */
+ irq_work_queue(&b->irq_work);
}
bool i915_request_enable_breadcrumb(struct i915_request *rq)
{
- struct intel_breadcrumbs *b;
+ struct intel_context *ce = rq->context;
/* Serialises with i915_request_retire() using rq->lock */
if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
return true;
- /*
- * rq->engine is locked by rq->engine->active.lock. That however
- * is not known until after rq->engine has been dereferenced and
- * the lock acquired. Hence we acquire the lock and then validate
- * that rq->engine still matches the lock we hold for it.
- *
- * Here, we are using the breadcrumb lock as a proxy for the
- * rq->engine->active.lock, and we know that since the breadcrumb
- * will be serialised within i915_request_submit/i915_request_unsubmit,
- * the engine cannot change while active as long as we hold the
- * breadcrumb lock on that engine.
- *
- * From the dma_fence_enable_signaling() path, we are outside of the
- * request submit/unsubmit path, and so we must be more careful to
- * acquire the right lock.
- */
- b = READ_ONCE(rq->engine)->breadcrumbs;
- spin_lock(&b->irq_lock);
- while (unlikely(b != READ_ONCE(rq->engine)->breadcrumbs)) {
- spin_unlock(&b->irq_lock);
- b = READ_ONCE(rq->engine)->breadcrumbs;
- spin_lock(&b->irq_lock);
- }
-
- /*
- * Now that we are finally serialised with request submit/unsubmit,
- * [with b->irq_lock] and with i915_request_retire() [via checking
- * SIGNALED with rq->lock] confirm the request is indeed active. If
- * it is no longer active, the breadcrumb will be attached upon
- * i915_request_submit().
- */
+ spin_lock(&ce->signal_lock);
if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
- insert_breadcrumb(rq, b);
-
- spin_unlock(&b->irq_lock);
+ insert_breadcrumb(rq);
+ spin_unlock(&ce->signal_lock);
return true;
}
void i915_request_cancel_breadcrumb(struct i915_request *rq)
{
- struct intel_breadcrumbs *b = rq->engine->breadcrumbs;
+ struct intel_context *ce = rq->context;
+ bool release;
- /*
- * We must wait for b->irq_lock so that we know the interrupt handler
- * has released its reference to the intel_context and has completed
- * the DMA_FENCE_FLAG_SIGNALED_BIT/I915_FENCE_FLAG_SIGNAL dance (if
- * required).
- */
- spin_lock(&b->irq_lock);
- if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) {
- struct intel_context *ce = rq->context;
+ if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
+ return;
- list_del(&rq->signal_link);
- if (list_empty(&ce->signals))
- remove_signaling_context(b, ce);
+ spin_lock(&ce->signal_lock);
+ list_del_rcu(&rq->signal_link);
+ release = remove_signaling_context(rq->engine->breadcrumbs, ce);
+ spin_unlock(&ce->signal_lock);
+ if (release)
+ intel_context_put(ce);
- clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
- i915_request_put(rq);
- }
- spin_unlock(&b->irq_lock);
+ i915_request_put(rq);
}
static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p)
drm_printf(p, "Signals:\n");
- spin_lock_irq(&b->irq_lock);
- list_for_each_entry(ce, &b->signalers, signal_link) {
- list_for_each_entry(rq, &ce->signals, signal_link) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(ce, &b->signalers, signal_link) {
+ list_for_each_entry_rcu(rq, &ce->signals, signal_link)
drm_printf(p, "\t[%llx:%llx%s] @ %dms\n",
rq->fence.context, rq->fence.seqno,
i915_request_completed(rq) ? "!" :
i915_request_started(rq) ? "*" :
"",
jiffies_to_msecs(jiffies - rq->emitted_jiffies));
- }
}
- spin_unlock_irq(&b->irq_lock);
+ rcu_read_unlock();
}
void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine,
* the overhead of waking that client is much preferred.
*/
struct intel_breadcrumbs {
- spinlock_t irq_lock; /* protects the lists used in hardirq context */
-
/* Not all breadcrumbs are attached to physical HW */
struct intel_engine_cs *irq_engine;
+ spinlock_t signalers_lock; /* protects the list of signalers */
struct list_head signalers;
- struct list_head signaled_requests;
+ struct llist_head signaled_requests;
+ spinlock_t irq_lock; /* protects the interrupt from hardirq context */
struct irq_work irq_work; /* for use from inside irq_lock */
-
unsigned int irq_enabled;
-
bool irq_armed;
};
return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL);
}
-void intel_context_free(struct intel_context *ce)
+static void rcu_context_free(struct rcu_head *rcu)
{
+ struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);
+
kmem_cache_free(global.slab_ce, ce);
}
+void intel_context_free(struct intel_context *ce)
+{
+ call_rcu(&ce->rcu, rcu_context_free);
+}
+
struct intel_context *
intel_context_create(struct intel_engine_cs *engine)
{
}
void
-intel_context_init(struct intel_context *ce,
- struct intel_engine_cs *engine)
+intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
{
GEM_BUG_ON(!engine->cops);
GEM_BUG_ON(!engine->gt->vm);
ce->vm = i915_vm_get(engine->gt->vm);
- INIT_LIST_HEAD(&ce->signal_link);
+ /* NB ce->signal_link/lock is used under RCU */
+ spin_lock_init(&ce->signal_lock);
INIT_LIST_HEAD(&ce->signals);
mutex_init(&ce->pin_mutex);
struct i915_gem_context;
struct i915_gem_ww_ctx;
struct i915_vma;
+struct intel_breadcrumbs;
struct intel_context;
struct intel_ring;
};
struct intel_context {
- struct kref ref;
+ /*
+ * Note: Some fields may be accessed under RCU.
+ *
+ * Unless otherwise noted a field can safely be assumed to be protected
+ * by strong reference counting.
+ */
+ union {
+ struct kref ref; /* no kref_get_unless_zero()! */
+ struct rcu_head rcu;
+ };
struct intel_engine_cs *engine;
struct intel_engine_cs *inflight;
struct i915_address_space *vm;
struct i915_gem_context __rcu *gem_context;
- struct list_head signal_link;
- struct list_head signals;
+ /*
+ * @signal_lock protects the list of requests that need signaling,
+ * @signals. While there are any requests that need signaling,
+ * we add the context to the breadcrumbs worker, and remove it
+ * upon completion/cancellation of the last request.
+ */
+ struct list_head signal_link; /* Accessed under RCU */
+ struct list_head signals; /* Guarded by signal_lock */
+ spinlock_t signal_lock; /* protects signals, the list of requests */
struct i915_vma *state;
struct intel_ring *ring;
}
static inline u32 *
-__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
+__gen8_emit_write_rcs(u32 *cs, u32 value, u32 offset, u32 flags0, u32 flags1)
{
- /* We're using qword write, offset should be aligned to 8 bytes. */
- GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
-
- /* w/a for post sync ops following a GPGPU operation we
- * need a prior CS_STALL, which is emitted by the flush
- * following the batch.
- */
*cs++ = GFX_OP_PIPE_CONTROL(6) | flags0;
- *cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB;
- *cs++ = gtt_offset;
+ *cs++ = flags1 | PIPE_CONTROL_QW_WRITE;
+ *cs++ = offset;
*cs++ = 0;
*cs++ = value;
- /* We're thrashing one dword of HWS. */
- *cs++ = 0;
+ *cs++ = 0; /* We're thrashing one extra dword. */
return cs;
}
static inline u32*
gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
{
- return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags);
+ /* We're using qword write, offset should be aligned to 8 bytes. */
+ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+ return __gen8_emit_write_rcs(cs,
+ value,
+ gtt_offset,
+ 0,
+ flags | PIPE_CONTROL_GLOBAL_GTT_IVB);
}
static inline u32*
gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1)
{
- return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1);
+ /* We're using qword write, offset should be aligned to 8 bytes. */
+ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
+
+ return __gen8_emit_write_rcs(cs,
+ value,
+ gtt_offset,
+ flags0,
+ flags1 | PIPE_CONTROL_GLOBAL_GTT_IVB);
+}
+
+static inline u32 *
+__gen8_emit_flush_dw(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
+{
+ *cs++ = (MI_FLUSH_DW + 1) | flags;
+ *cs++ = gtt_offset;
+ *cs++ = 0;
+ *cs++ = value;
+
+ return cs;
}
static inline u32 *
/* Offset should be aligned to 8 bytes for both (QW/DW) write types */
GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8));
- *cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags;
- *cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT;
- *cs++ = 0;
- *cs++ = value;
-
- return cs;
+ return __gen8_emit_flush_dw(cs,
+ value,
+ gtt_offset | MI_FLUSH_DW_USE_GTT,
+ flags | MI_FLUSH_DW_OP_STOREDW);
}
static inline void __intel_engine_reset(struct intel_engine_cs *engine,
* instances.
*/
if ((INTEL_GEN(i915) >= 11 &&
- engine->gt->info.vdbox_sfc_access & engine->mask) ||
+ (engine->gt->info.vdbox_sfc_access &
+ BIT(engine->instance))) ||
(INTEL_GEN(i915) >= 9 && engine->instance == 0))
engine->uabi_capabilities |=
I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC;
struct virtual_engine {
struct intel_engine_cs base;
struct intel_context context;
+ struct rcu_work rcu;
/*
* We allow only a single request through the virtual engine at a time
.destroy = execlists_context_destroy,
};
+static u32 hwsp_offset(const struct i915_request *rq)
+{
+ const struct intel_timeline_cacheline *cl;
+
+ /* Before the request is executed, the timeline/cachline is fixed */
+
+ cl = rcu_dereference_protected(rq->hwsp_cacheline, 1);
+ if (cl)
+ return cl->ggtt_offset;
+
+ return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset;
+}
+
static int gen8_emit_init_breadcrumb(struct i915_request *rq)
{
u32 *cs;
*cs++ = MI_NOOP;
*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
- *cs++ = i915_request_timeline(rq)->hwsp_offset;
+ *cs++ = hwsp_offset(rq);
*cs++ = 0;
*cs++ = rq->fence.seqno - 1;
return gen8_emit_wa_tail(request, cs);
}
-static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs)
+static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
{
- u32 addr = i915_request_active_timeline(request)->hwsp_offset;
-
- return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0);
+ return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
}
static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
cs = gen8_emit_ggtt_write_rcs(cs,
request->fence.seqno,
- i915_request_active_timeline(request)->hwsp_offset,
+ hwsp_offset(request),
PIPE_CONTROL_FLUSH_ENABLE |
PIPE_CONTROL_CS_STALL);
{
cs = gen8_emit_ggtt_write_rcs(cs,
request->fence.seqno,
- i915_request_active_timeline(request)->hwsp_offset,
+ hwsp_offset(request),
PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_TILE_CACHE_FLUSH |
PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs)
{
- return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs));
+ /* XXX Stalling flush before seqno write; post-sync not */
+ cs = emit_xcs_breadcrumb(rq, __gen8_emit_flush_dw(cs, 0, 0, 0));
+ return gen12_emit_fini_breadcrumb_tail(rq, cs);
}
static u32 *
{
cs = gen12_emit_ggtt_write_rcs(cs,
request->fence.seqno,
- i915_request_active_timeline(request)->hwsp_offset,
+ hwsp_offset(request),
PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
PIPE_CONTROL_CS_STALL |
PIPE_CONTROL_TILE_CACHE_FLUSH |
return &ve->base.execlists.default_priolist.requests[0];
}
-static void virtual_context_destroy(struct kref *kref)
+static void rcu_virtual_context_destroy(struct work_struct *wrk)
{
struct virtual_engine *ve =
- container_of(kref, typeof(*ve), context.ref);
+ container_of(wrk, typeof(*ve), rcu.work);
unsigned int n;
- GEM_BUG_ON(!list_empty(virtual_queue(ve)));
- GEM_BUG_ON(ve->request);
GEM_BUG_ON(ve->context.inflight);
+ /* Preempt-to-busy may leave a stale request behind. */
+ if (unlikely(ve->request)) {
+ struct i915_request *old;
+
+ spin_lock_irq(&ve->base.active.lock);
+
+ old = fetch_and_zero(&ve->request);
+ if (old) {
+ GEM_BUG_ON(!i915_request_completed(old));
+ __i915_request_submit(old);
+ i915_request_put(old);
+ }
+
+ spin_unlock_irq(&ve->base.active.lock);
+ }
+
+ /*
+ * Flush the tasklet in case it is still running on another core.
+ *
+ * This needs to be done before we remove ourselves from the siblings'
+ * rbtrees as in the case it is running in parallel, it may reinsert
+ * the rb_node into a sibling.
+ */
+ tasklet_kill(&ve->base.execlists.tasklet);
+
+ /* Decouple ourselves from the siblings, no more access allowed. */
for (n = 0; n < ve->num_siblings; n++) {
struct intel_engine_cs *sibling = ve->siblings[n];
struct rb_node *node = &ve->nodes[sibling->id].rb;
- unsigned long flags;
if (RB_EMPTY_NODE(node))
continue;
- spin_lock_irqsave(&sibling->active.lock, flags);
+ spin_lock_irq(&sibling->active.lock);
/* Detachment is lazily performed in the execlists tasklet */
if (!RB_EMPTY_NODE(node))
rb_erase_cached(node, &sibling->execlists.virtual);
- spin_unlock_irqrestore(&sibling->active.lock, flags);
+ spin_unlock_irq(&sibling->active.lock);
}
GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet));
+ GEM_BUG_ON(!list_empty(virtual_queue(ve)));
if (ve->context.state)
__execlists_context_fini(&ve->context);
intel_context_fini(&ve->context);
+ intel_breadcrumbs_free(ve->base.breadcrumbs);
intel_engine_free_request_pool(&ve->base);
kfree(ve->bonds);
kfree(ve);
}
+static void virtual_context_destroy(struct kref *kref)
+{
+ struct virtual_engine *ve =
+ container_of(kref, typeof(*ve), context.ref);
+
+ GEM_BUG_ON(!list_empty(&ve->context.signals));
+
+ /*
+ * When destroying the virtual engine, we have to be aware that
+ * it may still be in use from an hardirq/softirq context causing
+ * the resubmission of a completed request (background completion
+ * due to preempt-to-busy). Before we can free the engine, we need
+ * to flush the submission code and tasklets that are still potentially
+ * accessing the engine. Flushing the tasklets requires process context,
+ * and since we can guard the resubmit onto the engine with an RCU read
+ * lock, we can delegate the free of the engine to an RCU worker.
+ */
+ INIT_RCU_WORK(&ve->rcu, rcu_virtual_context_destroy);
+ queue_rcu_work(system_wq, &ve->rcu);
+}
+
static void virtual_engine_initial_hint(struct virtual_engine *ve)
{
int swp;
GEN9_MOCS_ENTRIES,
MOCS_ENTRY(I915_MOCS_CACHED,
LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3),
- L3_3_WB)
+ L3_3_WB),
+
+ /*
+ * mocs:63
+ * - used by the L3 for all of its evictions.
+ * Thus it is expected to allow LLC cacheability to enable coherent
+ * flows to be maintained.
+ * - used to force L3 uncachable cycles.
+ * Thus it is expected to make the surface L3 uncacheable.
+ */
+ MOCS_ENTRY(63,
+ LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
+ L3_1_UC)
};
/* NOTE: the LE_TGT_CACHE is not used on Broxton */
* only, __init_mocs_table() take care to program unused index with
* this entry.
*/
- MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
- L3_3_WB),
+ MOCS_ENTRY(I915_MOCS_PTE,
+ LE_0_PAGETABLE | LE_TC_0_PAGETABLE,
+ L3_1_UC),
GEN11_MOCS_ENTRIES,
/* Implicitly enable L1 - HDC:L1 + L3 + LLC */
static void gen11_rc6_enable(struct intel_rc6 *rc6)
{
- struct intel_uncore *uncore = rc6_to_uncore(rc6);
+ struct intel_gt *gt = rc6_to_gt(rc6);
+ struct intel_uncore *uncore = gt->uncore;
struct intel_engine_cs *engine;
enum intel_engine_id id;
+ u32 pg_enable;
+ int i;
/* 2b: Program RC6 thresholds.*/
set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
GEN6_RC_CTL_RC6_ENABLE |
GEN6_RC_CTL_EI_MODE(1);
- set(uncore, GEN9_PG_ENABLE,
- GEN9_RENDER_PG_ENABLE |
- GEN9_MEDIA_PG_ENABLE |
- GEN11_MEDIA_SAMPLER_PG_ENABLE);
+ pg_enable =
+ GEN9_RENDER_PG_ENABLE |
+ GEN9_MEDIA_PG_ENABLE |
+ GEN11_MEDIA_SAMPLER_PG_ENABLE;
+
+ if (INTEL_GEN(gt->i915) >= 12) {
+ for (i = 0; i < I915_MAX_VCS; i++)
+ if (HAS_ENGINE(gt, _VCS(i)))
+ pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) |
+ VDN_MFX_POWERGATE_ENABLE(i));
+ }
+
+ set(uncore, GEN9_PG_ENABLE, pg_enable);
}
static void gen9_rc6_enable(struct intel_rc6 *rc6)
adj = -2;
rps->last_adj = adj;
rps->cur_freq = max_t(int, rps->cur_freq + adj, rps->min_freq);
+ if (rps->cur_freq < rps->efficient_freq) {
+ rps->cur_freq = rps->efficient_freq;
+ rps->last_adj = 0;
+ }
GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq);
}
return cl;
}
-static void cacheline_acquire(struct intel_timeline_cacheline *cl)
+static void cacheline_acquire(struct intel_timeline_cacheline *cl,
+ u32 ggtt_offset)
{
- if (cl)
- i915_active_acquire(&cl->active);
+ if (!cl)
+ return;
+
+ cl->ggtt_offset = ggtt_offset;
+ i915_active_acquire(&cl->active);
}
static void cacheline_release(struct intel_timeline_cacheline *cl)
GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
tl->fence_context, tl->hwsp_offset);
- cacheline_acquire(tl->hwsp_cacheline);
+ cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset);
if (atomic_fetch_inc(&tl->pin_count)) {
cacheline_release(tl->hwsp_cacheline);
__i915_vma_unpin(tl->hwsp_ggtt);
GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
tl->fence_context, tl->hwsp_offset);
- cacheline_acquire(cl);
+ cacheline_acquire(cl, tl->hwsp_offset);
tl->hwsp_cacheline = cl;
*seqno = timeline_advance(tl);
if (err)
goto out;
- *hwsp = i915_ggtt_offset(cl->hwsp->vma) +
- ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
-
+ *hwsp = cl->ggtt_offset;
out:
i915_active_release(&cl->active);
return err;
struct intel_timeline_hwsp *hwsp;
void *vaddr;
+ u32 ggtt_offset;
+
struct rcu_head rcu;
};
return;
}
- if (wal->list)
+ if (wal->list) {
memcpy(list, wal->list, sizeof(*wa) * wal->count);
+ kfree(wal->list);
+ }
wal->list = list;
}
return PTR_ERR(page);
vaddr = kmap(page);
- if (write)
+ if (write) {
memcpy(vaddr + offset_in_page(off), ptr, this);
- else
+ set_page_dirty(page);
+ } else {
memcpy(ptr, vaddr + offset_in_page(off), this);
+ }
+ mark_page_accessed(page);
kunmap(page);
put_page(page);
/* let the virtual display supports DP1.2 */
static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = {
- 0x12, 0x014, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+ 0x12, 0x014, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
};
static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
#define F_CMD_ACCESS (1 << 3)
/* This reg has been accessed by a VM */
#define F_ACCESSED (1 << 4)
-/* This reg has been accessed through GPU commands */
+/* This reg could be accessed by unaligned address */
#define F_UNALIGN (1 << 6)
/* This reg is in GVT's mmio save-restor list and in hardware
* logical context image
const struct intel_engine_cs *engine =
intel_gvt_render_mmio_to_engine(vgpu->gvt, offset);
- if (!intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
+ if (value != 0 &&
+ !intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) {
gvt_vgpu_err("write invalid HWSP address, reg:0x%x, value:0x%x\n",
offset, value);
return -EINVAL;
return 0;
}
+/**
+ * FixMe:
+ * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did:
+ * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.)
+ * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing
+ * these MI_BATCH_BUFFER.
+ * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT
+ * PML4 PTE: PAT(0) PCD(1) PWT(1).
+ * The performance is still expected to be low, will need further improvement.
+ */
+static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset,
+ void *p_data, unsigned int bytes)
+{
+ u64 pat =
+ GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(1, 0) |
+ GEN8_PPAT(2, 0) |
+ GEN8_PPAT(3, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+ GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+ vgpu_vreg(vgpu, offset) = lower_32_bits(pat);
+
+ return 0;
+}
+
static int guc_status_read(struct intel_vgpu *vgpu,
unsigned int offset, void *p_data,
unsigned int bytes)
MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write);
- MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS);
+ MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT);
MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS);
MMIO_D(GAMTARBMODE, D_BDW_PLUS);
NULL, NULL);
MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL);
- MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
+ MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT);
return 0;
}
MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
MMIO_D(GEN6_GFXPAUSE, D_BXT);
MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(RENDER_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(GEN6_BSD_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(BLT_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
+ MMIO_F(GEN8_RING_CS_GPR(VEBOX_RING_BASE, 0), 0x40, F_CMD_ACCESS,
+ 0, 0, D_BXT, NULL, NULL);
MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
+ MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write);
+
return 0;
}
/* Take a module reference as mdev core doesn't take
* a reference for vendor driver.
*/
- if (!try_module_get(THIS_MODULE))
+ if (!try_module_get(THIS_MODULE)) {
+ ret = -ENODEV;
goto undo_group;
+ }
ret = kvmgt_guest_init(mdev);
if (ret)
i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->vm));
for_each_engine(engine, vgpu->gvt->gt, id)
- intel_context_unpin(s->shadow[id]);
+ intel_context_put(s->shadow[id]);
kmem_cache_destroy(s->workloads);
}
ce->ring = __intel_context_ring_size(ring_size);
}
- ret = intel_context_pin(ce);
- intel_context_put(ce);
- if (ret)
- goto out_shadow_ctx;
-
s->shadow[i] = ce;
}
if (IS_ERR(s->shadow[i]))
break;
- intel_context_unpin(s->shadow[i]);
intel_context_put(s->shadow[i]);
}
i915_vm_put(&ppgtt->vm);
{
struct intel_vgpu_submission *s = &workload->vgpu->submission;
+ intel_context_unpin(s->shadow[workload->engine->id]);
release_shadow_batch_buffer(workload);
release_shadow_wa_ctx(&workload->wa_ctx);
return ERR_PTR(ret);
}
+ ret = intel_context_pin(s->shadow[engine->id]);
+ if (ret) {
+ intel_vgpu_destroy_workload(workload);
+ return ERR_PTR(ret);
+ }
+
return workload;
}
if (IS_BROADWELL(dev_priv))
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
- else
+ /* FixMe: Re-enable APL/BXT once vfio_edid enabled */
+ else if (!IS_BROXTON(dev_priv))
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
if (ret)
goto out_clean_sched_policy;
return ret;
}
-static int
-i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
- struct drm_i915_gem_pwrite *args,
- struct drm_file *file)
-{
- void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
- char __user *user_data = u64_to_user_ptr(args->data_ptr);
-
- /*
- * We manually control the domain here and pretend that it
- * remains coherent i.e. in the GTT domain, like shmem_pwrite.
- */
- i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU);
-
- if (copy_from_user(vaddr, user_data, args->size))
- return -EFAULT;
-
- drm_clflush_virt_range(vaddr, args->size);
- intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt);
-
- i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
- return 0;
-}
-
static int
i915_gem_create(struct drm_file *file,
struct intel_memory_region *mr,
trace_i915_gem_object_pread(obj, args->offset, args->size);
+ ret = -ENODEV;
+ if (obj->ops->pread)
+ ret = obj->ops->pread(obj, args);
+ if (ret != -ENODEV)
+ goto out;
+
ret = i915_gem_object_wait(obj,
I915_WAIT_INTERRUPTIBLE,
MAX_SCHEDULE_TIMEOUT);
if (ret == -EFAULT || ret == -ENOSPC) {
if (i915_gem_object_has_struct_page(obj))
ret = i915_gem_shmem_pwrite(obj, args);
- else
- ret = i915_gem_phys_pwrite(obj, args, file);
}
i915_gem_object_unpin_pages(obj);
GEN5_FEATURES,
PLATFORM(INTEL_IRONLAKE),
.is_mobile = 1,
+ .has_rps = true,
.display.has_fbc = 1,
};
DRM_I915_PERF_RECORD_OA_REPORT_LOST);
if (ret)
return ret;
- intel_uncore_write(uncore, oastatus_reg,
- oastatus & ~GEN8_OASTATUS_REPORT_LOST);
+
+ intel_uncore_rmw(uncore, oastatus_reg,
+ GEN8_OASTATUS_COUNTER_OVERFLOW |
+ GEN8_OASTATUS_REPORT_LOST,
+ IS_GEN_RANGE(uncore->i915, 8, 10) ?
+ (GEN8_OASTATUS_HEAD_POINTER_WRAP |
+ GEN8_OASTATUS_TAIL_POINTER_WRAP) : 0);
}
return gen8_append_oa_reports(stream, buf, count, offset);
#define GEN7_OASTATUS2_MEM_SELECT_GGTT (1 << 0) /* 0: PPGTT, 1: GGTT */
#define GEN8_OASTATUS _MMIO(0x2b08)
+#define GEN8_OASTATUS_TAIL_POINTER_WRAP (1 << 17)
+#define GEN8_OASTATUS_HEAD_POINTER_WRAP (1 << 16)
#define GEN8_OASTATUS_OVERRUN_STATUS (1 << 3)
#define GEN8_OASTATUS_COUNTER_OVERFLOW (1 << 2)
#define GEN8_OASTATUS_OABUFFER_OVERFLOW (1 << 1)
#define GEN9_PWRGT_MEDIA_STATUS_MASK (1 << 0)
#define GEN9_PWRGT_RENDER_STATUS_MASK (1 << 1)
-#define POWERGATE_ENABLE _MMIO(0xa210)
-#define VDN_HCP_POWERGATE_ENABLE(n) BIT(((n) * 2) + 3)
-#define VDN_MFX_POWERGATE_ENABLE(n) BIT(((n) * 2) + 4)
-
#define GTFIFODBG _MMIO(0x120000)
#define GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV (0x1f << 20)
#define GT_FIFO_FREE_ENTRIES_CHV (0x7f << 13)
#define GEN9_MEDIA_PG_IDLE_HYSTERESIS _MMIO(0xA0C4)
#define GEN9_RENDER_PG_IDLE_HYSTERESIS _MMIO(0xA0C8)
#define GEN9_PG_ENABLE _MMIO(0xA210)
-#define GEN9_RENDER_PG_ENABLE REG_BIT(0)
-#define GEN9_MEDIA_PG_ENABLE REG_BIT(1)
-#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2)
+#define GEN9_RENDER_PG_ENABLE REG_BIT(0)
+#define GEN9_MEDIA_PG_ENABLE REG_BIT(1)
+#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2)
+#define VDN_HCP_POWERGATE_ENABLE(n) REG_BIT(3 + 2 * (n))
+#define VDN_MFX_POWERGATE_ENABLE(n) REG_BIT(4 + 2 * (n))
#define GEN8_PUSHBUS_CONTROL _MMIO(0xA248)
#define GEN8_PUSHBUS_ENABLE _MMIO(0xA250)
#define GEN8_PUSHBUS_SHIFT _MMIO(0xA25C)
struct intel_context *context;
struct intel_ring *ring;
struct intel_timeline __rcu *timeline;
+
struct list_head signal_link;
+ struct llist_node signal_node;
/*
* The rcu epoch of when this request was allocated. Used to judiciously
{
struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
- if (vw->pinned)
+ if (vw->pinned) {
__i915_gem_object_unpin_pages(vw->pinned);
+ i915_gem_object_put(vw->pinned);
+ }
i915_vm_free_pt_stash(vw->vm, &vw->stash);
i915_vm_put(vw->vm);
if (vma->obj) {
__i915_gem_object_pin_pages(vma->obj);
- work->pinned = vma->obj;
+ work->pinned = i915_gem_object_get(vma->obj);
}
} else {
vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags);
min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
}
- if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+ if (size > mem->mm.size)
return -E2BIG;
n_pages = size >> ilog2(mem->mm.chunk_size);
static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
{
- u32 vd_pg_enable = 0;
- unsigned int i;
-
/* Wa_1409120013:tgl */
I915_WRITE(ILK_DPFC_CHICKEN,
ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
- /* This is not a WA. Enable VD HCP & MFX_ENC powergate */
- for (i = 0; i < I915_MAX_VCS; i++) {
- if (HAS_ENGINE(&dev_priv->gt, _VCS(i)))
- vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) |
- VDN_MFX_POWERGATE_ENABLE(i);
- }
-
- I915_WRITE(POWERGATE_ENABLE,
- I915_READ(POWERGATE_ENABLE) | vd_pg_enable);
-
/* Wa_1409825376:tgl (pre-prod)*/
if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1))
I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) |
struct intel_context *ce;
ce = intel_context_create(engine);
- if (IS_ERR(ce))
+ if (IS_ERR(ce)) {
+ err = PTR_ERR(ce);
goto out;
+ }
err = intel_context_pin(ce);
if (err) {
struct intel_context *ce;
ce = intel_context_create(engine);
- if (IS_ERR(ce))
+ if (IS_ERR(ce)) {
+ err = PTR_ERR(ce);
goto out;
+ }
err = intel_context_pin(ce);
if (err) {
return err;
}
+static int igt_mock_splintered_region(void *arg)
+{
+ struct intel_memory_region *mem = arg;
+ struct drm_i915_private *i915 = mem->i915;
+ struct drm_i915_gem_object *obj;
+ unsigned int expected_order;
+ LIST_HEAD(objects);
+ u64 size;
+ int err = 0;
+
+ /*
+ * Sanity check we can still allocate everything even if the
+ * mm.max_order != mm.size. i.e our starting address space size is not a
+ * power-of-two.
+ */
+
+ size = (SZ_4G - 1) & PAGE_MASK;
+ mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0);
+ if (IS_ERR(mem))
+ return PTR_ERR(mem);
+
+ if (mem->mm.size != size) {
+ pr_err("%s size mismatch(%llu != %llu)\n",
+ __func__, mem->mm.size, size);
+ err = -EINVAL;
+ goto out_put;
+ }
+
+ expected_order = get_order(rounddown_pow_of_two(size));
+ if (mem->mm.max_order != expected_order) {
+ pr_err("%s order mismatch(%u != %u)\n",
+ __func__, mem->mm.max_order, expected_order);
+ err = -EINVAL;
+ goto out_put;
+ }
+
+ obj = igt_object_create(mem, &objects, size, 0);
+ if (IS_ERR(obj)) {
+ err = PTR_ERR(obj);
+ goto out_close;
+ }
+
+ close_objects(mem, &objects);
+
+ /*
+ * While we should be able allocate everything without any flag
+ * restrictions, if we consider I915_BO_ALLOC_CONTIGUOUS then we are
+ * actually limited to the largest power-of-two for the region size i.e
+ * max_order, due to the inner workings of the buddy allocator. So make
+ * sure that does indeed hold true.
+ */
+
+ obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS);
+ if (!IS_ERR(obj)) {
+ pr_err("%s too large contiguous allocation was not rejected\n",
+ __func__);
+ err = -EINVAL;
+ goto out_close;
+ }
+
+ obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size),
+ I915_BO_ALLOC_CONTIGUOUS);
+ if (IS_ERR(obj)) {
+ pr_err("%s largest possible contiguous allocation failed\n",
+ __func__);
+ err = PTR_ERR(obj);
+ goto out_close;
+ }
+
+out_close:
+ close_objects(mem, &objects);
+out_put:
+ intel_memory_region_put(mem);
+ return err;
+}
+
static int igt_gpu_write_dw(struct intel_context *ce,
struct i915_vma *vma,
u32 dword,
static const struct i915_subtest tests[] = {
SUBTEST(igt_mock_fill),
SUBTEST(igt_mock_contiguous),
+ SUBTEST(igt_mock_splintered_region),
};
struct intel_memory_region *mem;
struct drm_i915_private *i915;
struct drm_i915_private *i915 = mem->i915;
struct drm_i915_gem_object *obj;
- if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+ if (size > mem->mm.size)
return ERR_PTR(-E2BIG);
obj = i915_gem_object_alloc();
return 0;
}
-static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder)
-{
-}
-
static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder)
{
struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder);
static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = {
.enable = dw_hdmi_imx_encoder_enable,
- .disable = dw_hdmi_imx_encoder_disable,
.atomic_check = dw_hdmi_imx_atomic_check,
};
hdmi->dev = &pdev->dev;
encoder = &hdmi->encoder;
- encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
- /*
- * If we failed to find the CRTC(s) which this encoder is
- * supposed to be connected to, it's because the CRTC has
- * not been registered yet. Defer probing, and hope that
- * the required CRTC is added later.
- */
- if (encoder->possible_crtcs == 0)
- return -EPROBE_DEFER;
+ ret = imx_drm_encoder_parse_of(drm, encoder, dev->of_node);
+ if (ret)
+ return ret;
ret = dw_hdmi_imx_parse_dt(hdmi);
if (ret < 0)
#include <drm/drm_fb_helper.h>
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_managed.h>
#include <drm/drm_of.h>
#include <drm/drm_plane_helper.h>
#include <drm/drm_probe_helper.h>
drm->mode_config.allow_fb_modifiers = true;
drm->mode_config.normalize_zpos = true;
- drm_mode_config_init(drm);
+ ret = drmm_mode_config_init(drm);
+ if (ret)
+ return ret;
ret = drm_vblank_init(drm, MAX_CRTC);
if (ret)
drm_kms_helper_poll_fini(drm);
component_unbind_all(drm->dev, drm);
err_kms:
- drm_mode_config_cleanup(drm);
drm_dev_put(drm);
return ret;
component_unbind_all(drm->dev, drm);
- drm_mode_config_cleanup(drm);
+ drm_dev_put(drm);
dev_set_drvdata(dev, NULL);
-
- drm_dev_put(drm);
}
static const struct component_master_ops imx_drm_ops = {
struct i2c_adapter *ddc;
int chno;
void *edid;
- int edid_len;
struct drm_display_mode mode;
int mode_valid;
u32 bus_format;
}
if (!channel->ddc) {
+ int edid_len;
+
/* if no DDC available, fallback to hardcoded EDID */
dev_dbg(dev, "no ddc available\n");
- edidp = of_get_property(child, "edid",
- &channel->edid_len);
+ edidp = of_get_property(child, "edid", &edid_len);
if (edidp) {
- channel->edid = kmemdup(edidp,
- channel->edid_len,
- GFP_KERNEL);
+ channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL);
} else if (!channel->panel) {
/* fallback to display-timings node */
ret = of_get_drm_display_mode(child,
#include <linux/platform_device.h>
#include <linux/regmap.h>
#include <linux/regulator/consumer.h>
-#include <linux/spinlock.h>
#include <linux/videodev2.h>
#include <video/imx-ipu-v3.h>
struct drm_connector connector;
struct drm_encoder encoder;
struct device *dev;
- spinlock_t lock; /* register lock */
- bool enabled;
int mode;
int di_hsync_pin;
int di_vsync_pin;
return container_of(e, struct imx_tve, encoder);
}
-static void tve_lock(void *__tve)
-__acquires(&tve->lock)
-{
- struct imx_tve *tve = __tve;
-
- spin_lock(&tve->lock);
-}
-
-static void tve_unlock(void *__tve)
-__releases(&tve->lock)
-{
- struct imx_tve *tve = __tve;
-
- spin_unlock(&tve->lock);
-}
-
static void tve_enable(struct imx_tve *tve)
{
- if (!tve->enabled) {
- tve->enabled = true;
- clk_prepare_enable(tve->clk);
- regmap_update_bits(tve->regmap, TVE_COM_CONF_REG,
- TVE_EN, TVE_EN);
- }
+ clk_prepare_enable(tve->clk);
+ regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, TVE_EN);
/* clear interrupt status register */
regmap_write(tve->regmap, TVE_STAT_REG, 0xffffffff);
static void tve_disable(struct imx_tve *tve)
{
- if (tve->enabled) {
- tve->enabled = false;
- regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
- clk_disable_unprepare(tve->clk);
- }
+ regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0);
+ clk_disable_unprepare(tve->clk);
}
static int tve_setup_tvout(struct imx_tve *tve)
.readable_reg = imx_tve_readable_reg,
- .lock = tve_lock,
- .unlock = tve_unlock,
+ .fast_io = true,
.max_register = 0xdc,
};
[TVE_MODE_VGA] = "vga",
};
-static const int of_get_tve_mode(struct device_node *np)
+static int of_get_tve_mode(struct device_node *np)
{
const char *bm;
int ret, i;
memset(tve, 0, sizeof(*tve));
tve->dev = dev;
- spin_lock_init(&tve->lock);
ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0);
if (ddc_node) {
struct drm_bridge bridge;
struct device *dev;
void *edid;
- int edid_len;
u32 bus_format;
u32 bus_flags;
struct drm_display_mode mode;
return container_of(c, struct imx_parallel_display, connector);
}
-static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e)
-{
- return container_of(e, struct imx_parallel_display, encoder);
-}
-
static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b)
{
return container_of(b, struct imx_parallel_display, bridge);
struct device_node *np = dev->of_node;
const u8 *edidp;
struct imx_parallel_display *imxpd;
+ int edid_len;
int ret;
u32 bus_format = 0;
const char *fmt;
if (ret && ret != -ENODEV)
return ret;
- edidp = of_get_property(np, "edid", &imxpd->edid_len);
+ edidp = of_get_property(np, "edid", &edid_len);
if (edidp)
- imxpd->edid = kmemdup(edidp, imxpd->edid_len, GFP_KERNEL);
+ imxpd->edid = devm_kmemdup(dev, edidp, edid_len, GFP_KERNEL);
ret = of_property_read_string(np, "interface-pix-fmt", &fmt);
if (!ret) {
return 0;
}
-static void imx_pd_unbind(struct device *dev, struct device *master,
- void *data)
-{
- struct imx_parallel_display *imxpd = dev_get_drvdata(dev);
-
- kfree(imxpd->edid);
-}
-
static const struct component_ops imx_pd_ops = {
.bind = imx_pd_bind,
- .unbind = imx_pd_unbind,
};
static int imx_pd_probe(struct platform_device *pdev)
match);
if (ret) {
dev_err(dev, "failed to add component master\n");
- goto clk_disable;
+ /*
+ * The EPOD regulator is already disabled at this point so some
+ * special errorpath code is needed
+ */
+ clk_disable_unprepare(mcde->mcde_clk);
+ regulator_disable(mcde->vana);
+ return ret;
}
return 0;
return 0;
}
-static void mtk_dpi_encoder_destroy(struct drm_encoder *encoder)
-{
- drm_encoder_cleanup(encoder);
-}
-
-static const struct drm_encoder_funcs mtk_dpi_encoder_funcs = {
- .destroy = mtk_dpi_encoder_destroy,
-};
-
static int mtk_dpi_bridge_attach(struct drm_bridge *bridge,
enum drm_bridge_attach_flags flags)
{
u32 horizontal_sync_active_byte;
u32 horizontal_backporch_byte;
u32 horizontal_frontporch_byte;
+ u32 horizontal_front_back_byte;
+ u32 data_phy_cycles_byte;
u32 dsi_tmp_buf_bpp, data_phy_cycles;
+ u32 delta;
struct mtk_phy_timing *timing = &dsi->phy_timing;
struct videomode *vm = &dsi->vm;
horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10);
if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)
- horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp;
+ horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp - 10;
else
horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) *
- dsi_tmp_buf_bpp;
+ dsi_tmp_buf_bpp - 10;
data_phy_cycles = timing->lpx + timing->da_hs_prepare +
- timing->da_hs_zero + timing->da_hs_exit;
-
- if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
- if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
- data_phy_cycles * dsi->lanes + 18) {
- horizontal_frontporch_byte =
- vm->hfront_porch * dsi_tmp_buf_bpp -
- (data_phy_cycles * dsi->lanes + 18) *
- vm->hfront_porch /
- (vm->hfront_porch + vm->hback_porch);
-
- horizontal_backporch_byte =
- horizontal_backporch_byte -
- (data_phy_cycles * dsi->lanes + 18) *
- vm->hback_porch /
- (vm->hfront_porch + vm->hback_porch);
- } else {
- DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
- horizontal_frontporch_byte = vm->hfront_porch *
- dsi_tmp_buf_bpp;
- }
+ timing->da_hs_zero + timing->da_hs_exit + 3;
+
+ delta = dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST ? 18 : 12;
+
+ horizontal_frontporch_byte = vm->hfront_porch * dsi_tmp_buf_bpp;
+ horizontal_front_back_byte = horizontal_frontporch_byte + horizontal_backporch_byte;
+ data_phy_cycles_byte = data_phy_cycles * dsi->lanes + delta;
+
+ if (horizontal_front_back_byte > data_phy_cycles_byte) {
+ horizontal_frontporch_byte -= data_phy_cycles_byte *
+ horizontal_frontporch_byte /
+ horizontal_front_back_byte;
+
+ horizontal_backporch_byte -= data_phy_cycles_byte *
+ horizontal_backporch_byte /
+ horizontal_front_back_byte;
} else {
- if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp >
- data_phy_cycles * dsi->lanes + 12) {
- horizontal_frontporch_byte =
- vm->hfront_porch * dsi_tmp_buf_bpp -
- (data_phy_cycles * dsi->lanes + 12) *
- vm->hfront_porch /
- (vm->hfront_porch + vm->hback_porch);
- horizontal_backporch_byte = horizontal_backporch_byte -
- (data_phy_cycles * dsi->lanes + 12) *
- vm->hback_porch /
- (vm->hfront_porch + vm->hback_porch);
- } else {
- DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
- horizontal_frontporch_byte = vm->hfront_porch *
- dsi_tmp_buf_bpp;
- }
+ DRM_WARN("HFP + HBP less than d-phy, FPS will under 60Hz\n");
}
writel(horizontal_sync_active_byte, dsi->regs + DSI_HSA_WC);
#include <drm/drm_fb_cma_helper.h>
#include <drm/drm_fourcc.h>
#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
#include <drm/drm_plane.h>
#include <drm/drm_plane_helper.h>
#include <drm/drm_vblank.h>
writel(ctrl, mxsfb->base + LCDC_AS_CTRL);
}
+static bool mxsfb_format_mod_supported(struct drm_plane *plane,
+ uint32_t format,
+ uint64_t modifier)
+{
+ return modifier == DRM_FORMAT_MOD_LINEAR;
+}
+
static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = {
+ .prepare_fb = drm_gem_fb_prepare_fb,
.atomic_check = mxsfb_plane_atomic_check,
.atomic_update = mxsfb_plane_primary_atomic_update,
};
static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = {
+ .prepare_fb = drm_gem_fb_prepare_fb,
.atomic_check = mxsfb_plane_atomic_check,
.atomic_update = mxsfb_plane_overlay_atomic_update,
};
static const struct drm_plane_funcs mxsfb_plane_funcs = {
+ .format_mod_supported = mxsfb_format_mod_supported,
.update_plane = drm_atomic_helper_update_plane,
.disable_plane = drm_atomic_helper_disable_plane,
.destroy = drm_plane_cleanup,
struct nv50_core **);
int core507d_init(struct nv50_core *);
void core507d_ntfy_init(struct nouveau_bo *, u32);
+int core507d_read_caps(struct nv50_disp *disp);
int core507d_caps_init(struct nouveau_drm *, struct nv50_disp *);
int core507d_ntfy_wait_done(struct nouveau_bo *, u32, struct nvif_device *);
int core507d_update(struct nv50_core *, u32 *, bool);
int core827d_new(struct nouveau_drm *, s32, struct nv50_core **);
int core907d_new(struct nouveau_drm *, s32, struct nv50_core **);
+int core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp);
extern const struct nv50_outp_func dac907d;
extern const struct nv50_outp_func sor907d;
}
int
-core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+core507d_read_caps(struct nv50_disp *disp)
{
struct nvif_push *push = disp->core->chan.push;
int ret;
- if ((ret = PUSH_WAIT(push, 2)))
+ ret = PUSH_WAIT(push, 6);
+ if (ret)
return ret;
+ PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL,
+ NVDEF(NV507D, SET_NOTIFIER_CONTROL, MODE, WRITE) |
+ NVVAL(NV507D, SET_NOTIFIER_CONTROL, OFFSET, NV50_DISP_CORE_NTFY >> 2) |
+ NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, ENABLE));
+
PUSH_MTHD(push, NV507D, GET_CAPABILITIES, 0x00000000);
+
+ PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL,
+ NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE));
+
return PUSH_KICK(push);
}
+int
+core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+{
+ struct nv50_core *core = disp->core;
+ struct nouveau_bo *bo = disp->sync;
+ s64 time;
+ int ret;
+
+ NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1,
+ NVDEF(NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, FALSE));
+
+ ret = core507d_read_caps(disp);
+ if (ret < 0)
+ return ret;
+
+ time = nvif_msec(core->chan.base.device, 2000ULL,
+ if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY,
+ NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, ==, TRUE))
+ break;
+ usleep_range(1, 2);
+ );
+ if (time < 0)
+ NV_ERROR(drm, "core caps notifier timeout\n");
+
+ return 0;
+}
+
int
core507d_init(struct nv50_core *core)
{
#include "core.h"
#include "head.h"
+#include <nvif/push507c.h>
+#include <nvif/timer.h>
+
+#include <nvhw/class/cl907d.h>
+
+#include "nouveau_bo.h"
+
+int
+core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp)
+{
+ struct nv50_core *core = disp->core;
+ struct nouveau_bo *bo = disp->sync;
+ s64 time;
+ int ret;
+
+ NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV907D_CORE_NOTIFIER_3, CAPABILITIES_4,
+ NVDEF(NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, FALSE));
+
+ ret = core507d_read_caps(disp);
+ if (ret < 0)
+ return ret;
+
+ time = nvif_msec(core->chan.base.device, 2000ULL,
+ if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY,
+ NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, ==, TRUE))
+ break;
+ usleep_range(1, 2);
+ );
+ if (time < 0)
+ NV_ERROR(drm, "core caps notifier timeout\n");
+
+ return 0;
+}
+
static const struct nv50_core_func
core907d = {
.init = core507d_init,
.ntfy_init = core507d_ntfy_init,
- .caps_init = core507d_caps_init,
+ .caps_init = core907d_caps_init,
.ntfy_wait_done = core507d_ntfy_wait_done,
.update = core507d_update,
.head = &head907d,
core917d = {
.init = core507d_init,
.ntfy_init = core507d_ntfy_init,
- .caps_init = core507d_caps_init,
+ .caps_init = core907d_caps_init,
.ntfy_wait_done = core507d_ntfy_wait_done,
.update = core507d_update,
.head = &head917d,
* DAC
*****************************************************************************/
static void
-nv50_dac_disable(struct drm_encoder *encoder)
+nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nv50_core *core = nv50_disp(encoder->dev)->core;
}
static void
-nv50_dac_enable(struct drm_encoder *encoder)
+nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
static const struct drm_encoder_helper_funcs
nv50_dac_help = {
.atomic_check = nv50_outp_atomic_check,
- .enable = nv50_dac_enable,
- .disable = nv50_dac_disable,
+ .atomic_enable = nv50_dac_enable,
+ .atomic_disable = nv50_dac_disable,
.detect = nv50_dac_detect
};
}
static void
-nv50_msto_enable(struct drm_encoder *encoder)
+nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nv50_head *head = nv50_head(encoder->crtc);
struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state);
}
static void
-nv50_msto_disable(struct drm_encoder *encoder)
+nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nv50_msto *msto = nv50_msto(encoder);
struct nv50_mstc *mstc = msto->mstc;
static const struct drm_encoder_helper_funcs
nv50_msto_help = {
- .disable = nv50_msto_disable,
- .enable = nv50_msto_enable,
+ .atomic_disable = nv50_msto_disable,
+ .atomic_enable = nv50_msto_enable,
.atomic_check = nv50_msto_atomic_check,
};
}
static void
-nv50_sor_enable(struct drm_encoder *encoder,
- struct drm_atomic_state *state)
+nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
}
static void
-nv50_pior_disable(struct drm_encoder *encoder)
+nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nv50_core *core = nv50_disp(encoder->dev)->core;
}
static void
-nv50_pior_enable(struct drm_encoder *encoder)
+nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state)
{
struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
}
core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh);
- nv_encoder->crtc = encoder->crtc;
+ nv_encoder->crtc = &nv_crtc->base;
}
static const struct drm_encoder_helper_funcs
nv50_pior_help = {
.atomic_check = nv50_pior_atomic_check,
- .enable = nv50_pior_enable,
- .disable = nv50_pior_disable,
+ .atomic_enable = nv50_pior_enable,
+ .atomic_disable = nv50_pior_disable,
};
static void
#define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_DONE_TRUE 0x00000001
#define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_R0 15:1
#define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_TIMESTAMP 29:16
-
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1 0x00000001
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE 0:0
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_FALSE 0x00000000
+#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_TRUE 0x00000001
// class methods
#define NV507D_UPDATE (0x00000080)
#ifndef _cl907d_h_
#define _cl907d_h_
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4 0x00000004
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE 0:0
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_FALSE 0x00000000
+#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_TRUE 0x00000001
#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20 0x00000014
#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18 0:0
#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18_FALSE 0x00000000
if (domain & NOUVEAU_GEM_DOMAIN_VRAM) {
struct nvif_mmu *mmu = &drm->client.mmu;
- const u8 type = mmu->type[drm->ttm.type_vram].type;
pl[*n].mem_type = TTM_PL_VRAM;
pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED;
/* Some BARs do not support being ioremapped WC */
if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA &&
- type & NVIF_MEM_UNCACHED)
+ mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED)
pl[*n].flags &= ~TTM_PL_FLAG_WC;
(*n)++;
}
reg->bus.offset = handle;
- ret = 0;
}
+ ret = 0;
break;
default:
ret = -EINVAL;
nouveau_connector_set_edid(struct nouveau_connector *nv_connector,
struct edid *edid)
{
- struct edid *old_edid = nv_connector->edid;
+ if (nv_connector->edid != edid) {
+ struct edid *old_edid = nv_connector->edid;
- drm_connector_update_edid_property(&nv_connector->base, edid);
- kfree(old_edid);
- nv_connector->edid = edid;
+ drm_connector_update_edid_property(&nv_connector->base, edid);
+ kfree(old_edid);
+ nv_connector->edid = edid;
+ }
}
static enum drm_connector_status
/* Try retrieving EDID via DDC */
if (!drm->vbios.fp_no_ddc) {
status = nouveau_connector_detect(connector, force);
- if (status == connector_status_connected)
+ if (status == connector_status_connected) {
+ edid = nv_connector->edid;
goto out;
+ }
}
/* On some laptops (Sony, i'm looking at you) there appears to
return 112000 * duallink_scale;
}
-enum drm_mode_status
-nouveau_conn_mode_clock_valid(const struct drm_display_mode *mode,
- const unsigned min_clock,
- const unsigned max_clock,
- unsigned int *clock_out)
-{
- unsigned int clock = mode->clock;
-
- if ((mode->flags & DRM_MODE_FLAG_3D_MASK) ==
- DRM_MODE_FLAG_3D_FRAME_PACKING)
- clock *= 2;
-
- if (clock < min_clock)
- return MODE_CLOCK_LOW;
- if (clock > max_clock)
- return MODE_CLOCK_HIGH;
-
- if (clock_out)
- *clock_out = clock;
-
- return MODE_OK;
-}
-
static enum drm_mode_status
nouveau_connector_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
struct nouveau_connector *nv_connector = nouveau_connector(connector);
struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder;
struct drm_encoder *encoder = to_drm_encoder(nv_encoder);
- unsigned min_clock = 25000, max_clock = min_clock;
+ unsigned int min_clock = 25000, max_clock = min_clock, clock = mode->clock;
switch (nv_encoder->dcb->type) {
case DCB_OUTPUT_LVDS:
return MODE_BAD;
}
- return nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
- NULL);
+ if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+ clock *= 2;
+
+ if (clock < min_clock)
+ return MODE_CLOCK_LOW;
+ if (clock > max_clock)
+ return MODE_CLOCK_HIGH;
+
+ return MODE_OK;
}
static struct drm_encoder *
const struct drm_display_mode *mode,
unsigned *out_clock)
{
- const unsigned min_clock = 25000;
- unsigned max_clock, ds_clock, clock;
- enum drm_mode_status ret;
+ const unsigned int min_clock = 25000;
+ unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock;
+ const u8 bpp = connector->display_info.bpc * 3;
if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace)
return MODE_NO_INTERLACE;
- max_clock = outp->dp.link_nr * outp->dp.link_bw;
- ds_clock = drm_dp_downstream_max_dotclock(outp->dp.dpcd,
- outp->dp.downstream_ports);
- if (ds_clock)
- max_clock = min(max_clock, ds_clock);
+ if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
+ clock *= 2;
+
+ max_rate = outp->dp.link_nr * outp->dp.link_bw;
+ mode_rate = DIV_ROUND_UP(clock * bpp, 8);
+ if (mode_rate > max_rate)
+ return MODE_CLOCK_HIGH;
+
+ ds_max_dotclock = drm_dp_downstream_max_dotclock(outp->dp.dpcd, outp->dp.downstream_ports);
+ if (ds_max_dotclock && clock > ds_max_dotclock)
+ return MODE_CLOCK_HIGH;
+
+ if (clock < min_clock)
+ return MODE_CLOCK_LOW;
- clock = mode->clock * (connector->display_info.bpc * 3) / 10;
- ret = nouveau_conn_mode_clock_valid(mode, min_clock, max_clock,
- &clock);
if (out_clock)
*out_clock = clock;
- return ret;
+
+ return MODE_OK;
}
* to the caller, instead of a normal nouveau_bo ttm reference. */
ret = drm_gem_object_init(drm->dev, &nvbo->bo.base, size);
if (ret) {
- nouveau_bo_ref(NULL, &nvbo);
+ drm_gem_object_release(&nvbo->bo.base);
+ kfree(nvbo);
return ret;
}
NV_PRINTK(err, cli, "validating bo list\n");
validate_fini(op, chan, NULL, NULL);
return ret;
+ } else if (ret > 0) {
+ *apply_relocs = true;
}
- *apply_relocs = ret;
+
return 0;
}
nouveau_bo_wr32(nvbo, r->reloc_bo_offset >> 2, data);
}
- u_free(reloc);
return ret;
}
break;
}
}
- u_free(reloc);
}
out_prevalid:
+ if (!IS_ERR(reloc))
+ u_free(reloc);
u_free(bo);
u_free(push);
struct nouveau_cli *cli = nouveau_cli(file_priv);
struct drm_nouveau_svm_bind *args = data;
unsigned target, cmd, priority;
- unsigned long addr, end, size;
+ unsigned long addr, end;
struct mm_struct *mm;
args->va_start &= PAGE_MASK;
- args->va_end &= PAGE_MASK;
+ args->va_end = ALIGN(args->va_end, PAGE_SIZE);
/* Sanity check arguments */
if (args->reserved0 || args->reserved1)
return -EINVAL;
if (args->va_start >= args->va_end)
return -EINVAL;
- if (!args->npages)
- return -EINVAL;
cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT;
cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK;
if (args->stride)
return -EINVAL;
- size = ((unsigned long)args->npages) << PAGE_SHIFT;
- if ((args->va_start + size) <= args->va_start)
- return -EINVAL;
- if ((args->va_start + size) > args->va_end)
- return -EINVAL;
-
/*
* Ok we are ask to do something sane, for now we only support migrate
* commands but we will add things like memory policy (what to do on
return -EINVAL;
}
- for (addr = args->va_start, end = args->va_start + size; addr < end;) {
+ for (addr = args->va_start, end = args->va_end; addr < end;) {
struct vm_area_struct *vma;
unsigned long next;
}
}
+/* returns true if the GPU is in the CPU native byte order */
static inline bool
nvkm_device_endianness(struct nvkm_device *device)
{
- u32 boot1 = nvkm_rd32(device, 0x000004) & 0x01000001;
#ifdef __BIG_ENDIAN
- if (!boot1)
- return false;
+ const bool big_endian = true;
#else
- if (boot1)
- return false;
+ const bool big_endian = false;
#endif
+
+ /* Read NV_PMC_BOOT_1, and assume non-functional endian switch if it
+ * doesn't contain the expected values.
+ */
+ u32 pmc_boot_1 = nvkm_rd32(device, 0x000004);
+ if (pmc_boot_1 && pmc_boot_1 != 0x01000001)
+ return !big_endian; /* Assume GPU is LE in this case. */
+
+ /* 0 means LE and 0x01000001 means BE GPU. Condition is true when
+ * GPU/CPU endianness don't match.
+ */
+ if (big_endian == !pmc_boot_1) {
+ nvkm_wr32(device, 0x000004, 0x01000001);
+ nvkm_rd32(device, 0x000000);
+ if (nvkm_rd32(device, 0x000004) != (big_endian ? 0x01000001 : 0x00000000))
+ return !big_endian; /* Assume GPU is LE on any unexpected read-back. */
+ }
+
+ /* CPU/GPU endianness should (hopefully) match. */
return true;
}
if (detect) {
/* switch mmio to cpu's native endianness */
if (!nvkm_device_endianness(device)) {
- nvkm_wr32(device, 0x000004, 0x01000001);
- nvkm_rd32(device, 0x000000);
- if (!nvkm_device_endianness(device)) {
- nvdev_error(device,
- "GPU not supported on big-endian\n");
- ret = -ENOSYS;
- goto done;
- }
+ nvdev_error(device,
+ "Couldn't switch GPU to CPUs endianess\n");
+ ret = -ENOSYS;
+ goto done;
}
boot0 = nvkm_rd32(device, 0x000000);
sdi->pixelclock = adjusted_mode->clock * 1000;
}
-static void sdi_bridge_enable(struct drm_bridge *bridge,
- struct drm_bridge_state *bridge_state)
+static void sdi_bridge_enable(struct drm_bridge *bridge)
{
struct sdi_device *sdi = drm_bridge_to_sdi(bridge);
struct dispc_clock_info dispc_cinfo;
regulator_disable(sdi->vdds_sdi_reg);
}
-static void sdi_bridge_disable(struct drm_bridge *bridge,
- struct drm_bridge_state *bridge_state)
+static void sdi_bridge_disable(struct drm_bridge *bridge)
{
struct sdi_device *sdi = drm_bridge_to_sdi(bridge);
.mode_valid = sdi_bridge_mode_valid,
.mode_fixup = sdi_bridge_mode_fixup,
.mode_set = sdi_bridge_mode_set,
- .atomic_enable = sdi_bridge_enable,
- .atomic_disable = sdi_bridge_disable,
+ .enable = sdi_bridge_enable,
+ .disable = sdi_bridge_disable,
};
static void sdi_bridge_init(struct sdi_device *sdi)
struct mantix {
struct device *dev;
struct drm_panel panel;
+
struct gpio_desc *reset_gpio;
+ struct gpio_desc *tp_rstn_gpio;
struct regulator *avdd;
struct regulator *avee;
{
struct mantix *ctx = panel_to_mantix(panel);
+ gpiod_set_value_cansleep(ctx->tp_rstn_gpio, 1);
+ usleep_range(5000, 6000);
+ gpiod_set_value_cansleep(ctx->reset_gpio, 1);
+
regulator_disable(ctx->avee);
regulator_disable(ctx->avdd);
/* T11 */
return ret;
}
- /* T3+T5 */
- usleep_range(10000, 12000);
-
- gpiod_set_value_cansleep(ctx->reset_gpio, 1);
- usleep_range(5150, 7000);
-
+ /* T3 + T4 + time for voltage to become stable: */
+ usleep_range(6000, 7000);
gpiod_set_value_cansleep(ctx->reset_gpio, 0);
+ gpiod_set_value_cansleep(ctx->tp_rstn_gpio, 0);
/* T6 */
msleep(50);
if (!mode) {
dev_err(ctx->dev, "Failed to add mode %ux%u@%u\n",
default_mode.hdisplay, default_mode.vdisplay,
- drm_mode_vrefresh(mode));
+ drm_mode_vrefresh(&default_mode));
return -ENOMEM;
}
if (!ctx)
return -ENOMEM;
- ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+ ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(ctx->reset_gpio)) {
dev_err(dev, "cannot get reset gpio\n");
return PTR_ERR(ctx->reset_gpio);
}
+ ctx->tp_rstn_gpio = devm_gpiod_get(dev, "mantix,tp-rstn", GPIOD_OUT_HIGH);
+ if (IS_ERR(ctx->tp_rstn_gpio)) {
+ dev_err(dev, "cannot get tp-rstn gpio\n");
+ return PTR_ERR(ctx->tp_rstn_gpio);
+ }
+
mipi_dsi_set_drvdata(dsi, ctx);
ctx->dev = dev;
lcd->spi = spi;
mutex_init(&lcd->mutex);
- lcd->reset_gpio = devm_gpiod_get(&spi->dev, "reset", GPIOD_OUT_LOW);
+ lcd->reset_gpio = devm_gpiod_get(&spi->dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(lcd->reset_gpio)) {
dev_err(&spi->dev, "failed to get reset GPIO\n");
return PTR_ERR(lcd->reset_gpio);
err_out1:
pm_runtime_disable(pfdev->dev);
panfrost_device_fini(pfdev);
+ pm_runtime_set_suspended(pfdev->dev);
err_out0:
drm_dev_put(ddev);
return err;
panfrost_gem_shrinker_cleanup(ddev);
pm_runtime_get_sync(pfdev->dev);
- panfrost_device_fini(pfdev);
- pm_runtime_put_sync_suspend(pfdev->dev);
pm_runtime_disable(pfdev->dev);
+ panfrost_device_fini(pfdev);
+ pm_runtime_set_suspended(pfdev->dev);
drm_dev_put(ddev);
return 0;
kref_put(&mapping->refcount, panfrost_gem_mapping_release);
}
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo)
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo)
{
struct panfrost_gem_mapping *mapping;
- mutex_lock(&bo->mappings.lock);
list_for_each_entry(mapping, &bo->mappings.list, node)
panfrost_gem_teardown_mapping(mapping);
- mutex_unlock(&bo->mappings.lock);
}
int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
struct panfrost_file_priv *priv);
void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping);
-void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo);
+void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo);
void panfrost_gem_shrinker_init(struct drm_device *dev);
void panfrost_gem_shrinker_cleanup(struct drm_device *dev);
{
struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
struct panfrost_gem_object *bo = to_panfrost_bo(obj);
+ bool ret = false;
if (atomic_read(&bo->gpu_usecount))
return false;
- if (!mutex_trylock(&shmem->pages_lock))
+ if (!mutex_trylock(&bo->mappings.lock))
return false;
- panfrost_gem_teardown_mappings(bo);
+ if (!mutex_trylock(&shmem->pages_lock))
+ goto unlock_mappings;
+
+ panfrost_gem_teardown_mappings_locked(bo);
drm_gem_shmem_purge_locked(obj);
+ ret = true;
mutex_unlock(&shmem->pages_lock);
- return true;
+
+unlock_mappings:
+ mutex_unlock(&bo->mappings.lock);
+ return ret;
}
static unsigned long
struct device_node *port, *endpoint;
int ret = 0, child_count = 0;
const char *name;
- u32 endpoint_id;
+ u32 endpoint_id = 0;
lvds->drm_dev = drm_dev;
port = of_graph_get_port_by_id(dev->of_node, 1);
*
* XXX(hch): this has no business in a driver and needs to move
* to the device tree.
+ *
+ * If we have two subsequent calls to dma_direct_set_offset
+ * returns -EINVAL. Unfortunately, this happens when we have two
+ * backends in the system, and will result in the driver
+ * reporting an error while it has been setup properly before.
+ * Ignore EINVAL, but it should really be removed eventually.
*/
ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G);
- if (ret)
+ if (ret && ret != -EINVAL)
return ret;
}
struct drm_framebuffer *fb = state->fb;
const struct drm_format_info *format = fb->format;
uint64_t modifier = fb->modifier;
+ unsigned int ch1_phase_idx;
u32 out_fmt_val;
u32 in_fmt_val, in_mod_val, in_ps_val;
unsigned int i;
* I have no idea what this does exactly, but it seems to be
* related to the scaler FIR filter phase parameters.
*/
+ ch1_phase_idx = (format->num_planes > 1) ? 1 : 0;
regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZPHASE_REG,
- frontend->data->ch_phase[0].horzphase);
+ frontend->data->ch_phase[0]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZPHASE_REG,
- frontend->data->ch_phase[1].horzphase);
+ frontend->data->ch_phase[ch1_phase_idx]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE0_REG,
- frontend->data->ch_phase[0].vertphase[0]);
+ frontend->data->ch_phase[0]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE0_REG,
- frontend->data->ch_phase[1].vertphase[0]);
+ frontend->data->ch_phase[ch1_phase_idx]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE1_REG,
- frontend->data->ch_phase[0].vertphase[1]);
+ frontend->data->ch_phase[0]);
regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE1_REG,
- frontend->data->ch_phase[1].vertphase[1]);
+ frontend->data->ch_phase[ch1_phase_idx]);
/*
* Checking the input format is sufficient since we currently only
};
static const struct sun4i_frontend_data sun4i_a10_frontend = {
- .ch_phase = {
- {
- .horzphase = 0,
- .vertphase = { 0, 0 },
- },
- {
- .horzphase = 0xfc000,
- .vertphase = { 0xfc000, 0xfc000 },
- },
- },
+ .ch_phase = { 0x000, 0xfc000 },
.has_coef_rdy = true,
};
static const struct sun4i_frontend_data sun8i_a33_frontend = {
- .ch_phase = {
- {
- .horzphase = 0x400,
- .vertphase = { 0x400, 0x400 },
- },
- {
- .horzphase = 0x400,
- .vertphase = { 0x400, 0x400 },
- },
- },
+ .ch_phase = { 0x400, 0xfc400 },
.has_coef_access_ctrl = true,
};
struct sun4i_frontend_data {
bool has_coef_access_ctrl;
bool has_coef_rdy;
-
- struct {
- u32 horzphase;
- u32 vertphase[2];
- } ch_phase[2];
+ u32 ch_phase[2];
};
struct sun4i_frontend {
phy_node = of_parse_phandle(dev->of_node, "phys", 0);
if (!phy_node) {
dev_err(dev, "Can't found PHY phandle\n");
+ ret = -EINVAL;
goto err_disable_clk_tmds;
}
if (!fpriv)
return -ENOMEM;
- idr_init(&fpriv->contexts);
+ idr_init_base(&fpriv->contexts, 1);
mutex_init(&fpriv->lock);
filp->driver_priv = fpriv;
if (!output->ddc) {
err = -EPROBE_DEFER;
- of_node_put(ddc);
return err;
}
}
struct tegra_sor_ops {
const char *name;
int (*probe)(struct tegra_sor *sor);
- int (*remove)(struct tegra_sor *sor);
void (*audio_enable)(struct tegra_sor *sor);
void (*audio_disable)(struct tegra_sor *sor);
};
.atomic_check = tegra_sor_encoder_atomic_check,
};
+static void tegra_sor_disable_regulator(void *data)
+{
+ struct regulator *reg = data;
+
+ regulator_disable(reg);
+}
+
+static int tegra_sor_enable_regulator(struct tegra_sor *sor, struct regulator *reg)
+{
+ int err;
+
+ err = regulator_enable(reg);
+ if (err)
+ return err;
+
+ return devm_add_action_or_reset(sor->dev, tegra_sor_disable_regulator, reg);
+}
+
static int tegra_sor_hdmi_probe(struct tegra_sor *sor)
{
int err;
return PTR_ERR(sor->avdd_io_supply);
}
- err = regulator_enable(sor->avdd_io_supply);
+ err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply);
if (err < 0) {
dev_err(sor->dev, "failed to enable AVDD I/O supply: %d\n",
err);
return PTR_ERR(sor->vdd_pll_supply);
}
- err = regulator_enable(sor->vdd_pll_supply);
+ err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply);
if (err < 0) {
dev_err(sor->dev, "failed to enable VDD PLL supply: %d\n",
err);
return PTR_ERR(sor->hdmi_supply);
}
- err = regulator_enable(sor->hdmi_supply);
+ err = tegra_sor_enable_regulator(sor, sor->hdmi_supply);
if (err < 0) {
dev_err(sor->dev, "failed to enable HDMI supply: %d\n", err);
return err;
return 0;
}
-static int tegra_sor_hdmi_remove(struct tegra_sor *sor)
-{
- regulator_disable(sor->hdmi_supply);
- regulator_disable(sor->vdd_pll_supply);
- regulator_disable(sor->avdd_io_supply);
-
- return 0;
-}
-
static const struct tegra_sor_ops tegra_sor_hdmi_ops = {
.name = "HDMI",
.probe = tegra_sor_hdmi_probe,
- .remove = tegra_sor_hdmi_remove,
.audio_enable = tegra_sor_hdmi_audio_enable,
.audio_disable = tegra_sor_hdmi_audio_disable,
};
if (IS_ERR(sor->avdd_io_supply))
return PTR_ERR(sor->avdd_io_supply);
- err = regulator_enable(sor->avdd_io_supply);
+ err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply);
if (err < 0)
return err;
if (IS_ERR(sor->vdd_pll_supply))
return PTR_ERR(sor->vdd_pll_supply);
- err = regulator_enable(sor->vdd_pll_supply);
+ err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply);
if (err < 0)
return err;
return 0;
}
-static int tegra_sor_dp_remove(struct tegra_sor *sor)
-{
- regulator_disable(sor->vdd_pll_supply);
- regulator_disable(sor->avdd_io_supply);
-
- return 0;
-}
-
static const struct tegra_sor_ops tegra_sor_dp_ops = {
.name = "DP",
.probe = tegra_sor_dp_probe,
- .remove = tegra_sor_dp_remove,
};
static int tegra_sor_init(struct host1x_client *client)
if (err < 0) {
dev_err(sor->dev, "failed to deassert SOR reset: %d\n",
err);
+ clk_disable_unprepare(sor->clk);
return err;
}
}
err = clk_prepare_enable(sor->clk_safe);
- if (err < 0)
+ if (err < 0) {
+ clk_disable_unprepare(sor->clk);
return err;
+ }
err = clk_prepare_enable(sor->clk_dp);
- if (err < 0)
+ if (err < 0) {
+ clk_disable_unprepare(sor->clk_safe);
+ clk_disable_unprepare(sor->clk);
return err;
+ }
return 0;
}
return err;
err = tegra_output_probe(&sor->output);
- if (err < 0) {
- dev_err(&pdev->dev, "failed to probe output: %d\n", err);
- return err;
- }
+ if (err < 0)
+ return dev_err_probe(&pdev->dev, err,
+ "failed to probe output\n");
if (sor->ops && sor->ops->probe) {
err = sor->ops->probe(sor);
if (err < 0) {
dev_err(&pdev->dev, "failed to probe %s: %d\n",
sor->ops->name, err);
- goto output;
+ goto remove;
}
}
rpm_disable:
pm_runtime_disable(&pdev->dev);
remove:
- if (sor->ops && sor->ops->remove)
- sor->ops->remove(sor);
-output:
tegra_output_remove(&sor->output);
return err;
}
pm_runtime_disable(&pdev->dev);
- if (sor->ops && sor->ops->remove) {
- err = sor->ops->remove(sor);
- if (err < 0)
- dev_err(&pdev->dev, "failed to remove SOR: %d\n", err);
- }
-
tegra_output_remove(&sor->output);
return 0;
ret = v3d_job_init(v3d, file_priv, &bin->base,
v3d_job_free, args->in_sync_bcl);
if (ret) {
- kfree(bin);
v3d_job_put(&render->base);
kfree(bin);
return ret;
}
if (IS_ERR(cma_obj)) {
- struct drm_printer p = drm_info_printer(vc4->dev->dev);
+ struct drm_printer p = drm_info_printer(vc4->base.dev);
DRM_ERROR("Failed to allocate from CMA:\n");
vc4_bo_stats_print(&p, vc4);
return ERR_PTR(-ENOMEM);
{
struct vc4_dev *vc4 =
container_of(work, struct vc4_dev, bo_cache.time_work);
- struct drm_device *dev = vc4->dev;
+ struct drm_device *dev = &vc4->base;
mutex_lock(&vc4->bo_lock);
vc4_bo_cache_free_old(dev);
return 0;
}
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused);
int vc4_bo_cache_init(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work);
timer_setup(&vc4->bo_cache.time_timer, vc4_bo_cache_time_timer, 0);
- return 0;
+ return drmm_add_action_or_reset(dev, vc4_bo_cache_destroy, NULL);
}
-void vc4_bo_cache_destroy(struct drm_device *dev)
+static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
int i;
dev->coherent_dma_mask = DMA_BIT_MASK(32);
- vc4 = devm_kzalloc(dev, sizeof(*vc4), GFP_KERNEL);
- if (!vc4)
- return -ENOMEM;
-
/* If VC4 V3D is missing, don't advertise render nodes. */
node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL);
if (!node || !of_device_is_available(node))
vc4_drm_driver.driver_features &= ~DRIVER_RENDER;
of_node_put(node);
- drm = drm_dev_alloc(&vc4_drm_driver, dev);
- if (IS_ERR(drm))
- return PTR_ERR(drm);
+ vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base);
+ if (IS_ERR(vc4))
+ return PTR_ERR(vc4);
+
+ drm = &vc4->base;
platform_set_drvdata(pdev, drm);
- vc4->dev = drm;
- drm->dev_private = vc4;
INIT_LIST_HEAD(&vc4->debugfs_list);
mutex_init(&vc4->bin_bo_lock);
ret = vc4_bo_cache_init(drm);
if (ret)
- goto dev_put;
+ return ret;
- drm_mode_config_init(drm);
+ ret = drmm_mode_config_init(drm);
+ if (ret)
+ return ret;
- vc4_gem_init(drm);
+ ret = vc4_gem_init(drm);
+ if (ret)
+ return ret;
ret = component_bind_all(dev, drm);
if (ret)
- goto gem_destroy;
+ return ret;
ret = vc4_plane_create_additional_planes(drm);
if (ret)
unbind_all:
component_unbind_all(dev, drm);
-gem_destroy:
- vc4_gem_destroy(drm);
- vc4_bo_cache_destroy(drm);
-dev_put:
- drm_dev_put(drm);
+
return ret;
}
static void vc4_drm_unbind(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
- struct vc4_dev *vc4 = to_vc4_dev(drm);
drm_dev_unregister(drm);
drm_atomic_helper_shutdown(drm);
-
- drm_mode_config_cleanup(drm);
-
- drm_atomic_private_obj_fini(&vc4->load_tracker);
- drm_atomic_private_obj_fini(&vc4->ctm_manager);
-
- drm_dev_put(drm);
}
static const struct component_master_ops vc4_drm_ops = {
#include <drm/drm_device.h>
#include <drm/drm_encoder.h>
#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_managed.h>
#include <drm/drm_mm.h>
#include <drm/drm_modeset_lock.h>
};
struct vc4_dev {
- struct drm_device *dev;
+ struct drm_device base;
struct vc4_hvs *hvs;
struct vc4_v3d *v3d;
struct drm_modeset_lock ctm_state_lock;
struct drm_private_obj ctm_manager;
+ struct drm_private_obj hvs_channels;
struct drm_private_obj load_tracker;
/* List of vc4_debugfs_info_entry for adding to debugfs once
static inline struct vc4_dev *
to_vc4_dev(struct drm_device *dev)
{
- return (struct vc4_dev *)dev->dev_private;
+ return container_of(dev, struct vc4_dev, base);
}
struct vc4_bo {
static inline struct vc4_bo *
to_vc4_bo(struct drm_gem_object *bo)
{
- return (struct vc4_bo *)bo;
+ return container_of(to_drm_gem_cma_obj(bo), struct vc4_bo, base);
}
struct vc4_fence {
static inline struct vc4_fence *
to_vc4_fence(struct dma_fence *fence)
{
- return (struct vc4_fence *)fence;
+ return container_of(fence, struct vc4_fence, base);
}
struct vc4_seqno_cb {
static inline struct vc4_plane *
to_vc4_plane(struct drm_plane *plane)
{
- return (struct vc4_plane *)plane;
+ return container_of(plane, struct vc4_plane, base);
}
enum vc4_scaling_mode {
static inline struct vc4_plane_state *
to_vc4_plane_state(struct drm_plane_state *state)
{
- return (struct vc4_plane_state *)state;
+ return container_of(state, struct vc4_plane_state, base);
}
enum vc4_encoder_type {
static inline struct vc4_crtc *
to_vc4_crtc(struct drm_crtc *crtc)
{
- return (struct vc4_crtc *)crtc;
+ return container_of(crtc, struct vc4_crtc, base);
}
static inline const struct vc4_crtc_data *
unsigned int top;
unsigned int bottom;
} margins;
+
+ /* Transitional state below, only valid during atomic commits */
+ bool update_muxing;
};
#define VC4_HVS_CHANNEL_DISABLED ((unsigned int)-1)
static inline struct vc4_crtc_state *
to_vc4_crtc_state(struct drm_crtc_state *crtc_state)
{
- return (struct vc4_crtc_state *)crtc_state;
+ return container_of(crtc_state, struct vc4_crtc_state, base);
}
#define V3D_READ(offset) readl(vc4->v3d->regs + offset)
struct sg_table *sgt);
void *vc4_prime_vmap(struct drm_gem_object *obj);
int vc4_bo_cache_init(struct drm_device *dev);
-void vc4_bo_cache_destroy(struct drm_device *dev);
int vc4_bo_inc_usecnt(struct vc4_bo *bo);
void vc4_bo_dec_usecnt(struct vc4_bo *bo);
void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo);
extern const struct dma_fence_ops vc4_fence_ops;
/* vc4_gem.c */
-void vc4_gem_init(struct drm_device *dev);
-void vc4_gem_destroy(struct drm_device *dev);
+int vc4_gem_init(struct drm_device *dev);
int vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
int vc4_wait_seqno_ioctl(struct drm_device *dev, void *data,
struct vc4_dev *vc4 =
container_of(work, struct vc4_dev, hangcheck.reset_work);
- vc4_save_hang_state(vc4->dev);
+ vc4_save_hang_state(&vc4->base);
- vc4_reset(vc4->dev);
+ vc4_reset(&vc4->base);
}
static void
vc4_hangcheck_elapsed(struct timer_list *t)
{
struct vc4_dev *vc4 = from_timer(vc4, t, hangcheck.timer);
- struct drm_device *dev = vc4->dev;
+ struct drm_device *dev = &vc4->base;
uint32_t ct0ca, ct1ca;
unsigned long irqflags;
struct vc4_exec_info *bin_exec, *render_exec;
list_del(&exec->head);
spin_unlock_irqrestore(&vc4->job_lock, irqflags);
- vc4_complete_exec(vc4->dev, exec);
+ vc4_complete_exec(&vc4->base, exec);
spin_lock_irqsave(&vc4->job_lock, irqflags);
}
return 0;
fail:
- vc4_complete_exec(vc4->dev, exec);
+ vc4_complete_exec(&vc4->base, exec);
return ret;
}
-void
-vc4_gem_init(struct drm_device *dev)
+static void vc4_gem_destroy(struct drm_device *dev, void *unused);
+int vc4_gem_init(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
INIT_LIST_HEAD(&vc4->purgeable.list);
mutex_init(&vc4->purgeable.lock);
+
+ return drmm_add_action_or_reset(dev, vc4_gem_destroy, NULL);
}
-void
-vc4_gem_destroy(struct drm_device *dev)
+static void vc4_gem_destroy(struct drm_device *dev, void *unused)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
{
}
+#define WIFI_2_4GHz_CH1_MIN_FREQ 2400000000ULL
+#define WIFI_2_4GHz_CH1_MAX_FREQ 2422000000ULL
+
+static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder,
+ struct drm_crtc_state *crtc_state,
+ struct drm_connector_state *conn_state)
+{
+ struct drm_display_mode *mode = &crtc_state->adjusted_mode;
+ struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+ unsigned long long pixel_rate = mode->clock * 1000;
+ unsigned long long tmds_rate;
+
+ if (vc4_hdmi->variant->unsupported_odd_h_timings &&
+ ((mode->hdisplay % 2) || (mode->hsync_start % 2) ||
+ (mode->hsync_end % 2) || (mode->htotal % 2)))
+ return -EINVAL;
+
+ /*
+ * The 1440p@60 pixel rate is in the same range than the first
+ * WiFi channel (between 2.4GHz and 2.422GHz with 22MHz
+ * bandwidth). Slightly lower the frequency to bring it out of
+ * the WiFi range.
+ */
+ tmds_rate = pixel_rate * 10;
+ if (vc4_hdmi->disable_wifi_frequencies &&
+ (tmds_rate >= WIFI_2_4GHz_CH1_MIN_FREQ &&
+ tmds_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) {
+ mode->clock = 238560;
+ pixel_rate = mode->clock * 1000;
+ }
+
+ if (pixel_rate > vc4_hdmi->variant->max_pixel_clock)
+ return -EINVAL;
+
+ return 0;
+}
+
static enum drm_mode_status
vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder,
const struct drm_display_mode *mode)
{
struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder);
+ if (vc4_hdmi->variant->unsupported_odd_h_timings &&
+ ((mode->hdisplay % 2) || (mode->hsync_start % 2) ||
+ (mode->hsync_end % 2) || (mode->htotal % 2)))
+ return MODE_H_ILLEGAL;
+
if ((mode->clock * 1000) > vc4_hdmi->variant->max_pixel_clock)
return MODE_CLOCK_HIGH;
}
static const struct drm_encoder_helper_funcs vc4_hdmi_encoder_helper_funcs = {
+ .atomic_check = vc4_hdmi_encoder_atomic_check,
.mode_valid = vc4_hdmi_encoder_mode_valid,
.disable = vc4_hdmi_encoder_disable,
.enable = vc4_hdmi_encoder_enable,
struct snd_soc_dai *dai)
{
struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
+ struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
struct device *dev = &vc4_hdmi->pdev->dev;
u32 audio_packet_config, channel_mask;
u32 channel_map;
HDMI_WRITE(HDMI_AUDIO_PACKET_CONFIG, audio_packet_config);
vc4_hdmi_set_n_cts(vc4_hdmi);
+ vc4_hdmi_set_audio_infoframe(encoder);
+
return 0;
}
struct snd_soc_dai *dai)
{
struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai);
- struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base;
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
- vc4_hdmi_set_audio_infoframe(encoder);
vc4_hdmi->audio.streaming = true;
if (vc4_hdmi->variant->phy_rng_enable)
};
static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = {
+ .name = "vc4-hdmi-codec-dai-component",
.controls = vc4_hdmi_audio_controls,
.num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls),
.dapm_widgets = vc4_hdmi_audio_widgets,
vc4_hdmi->hpd_active_low = hpd_gpio_flags & OF_GPIO_ACTIVE_LOW;
}
+ vc4_hdmi->disable_wifi_frequencies =
+ of_property_read_bool(dev->of_node, "wifi-2.4ghz-coexistence");
+
pm_runtime_enable(dev);
drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_TMDS);
PHY_LANE_2,
PHY_LANE_CK,
},
+ .unsupported_odd_h_timings = true,
.init_resources = vc5_hdmi_init_resources,
.csc_setup = vc5_hdmi_csc_setup,
PHY_LANE_CK,
PHY_LANE_2,
},
+ .unsupported_odd_h_timings = true,
.init_resources = vc5_hdmi_init_resources,
.csc_setup = vc5_hdmi_csc_setup,
*/
enum vc4_hdmi_phy_channel phy_lane_mapping[4];
+ /* The BCM2711 cannot deal with odd horizontal pixel timings */
+ bool unsupported_odd_h_timings;
+
/* Callback to get the resources (memory region, interrupts,
* clocks, etc) for that variant.
*/
int hpd_gpio;
bool hpd_active_low;
+ /*
+ * On some systems (like the RPi4), some modes are in the same
+ * frequency range than the WiFi channels (1440p@60Hz for
+ * example). Should we take evasive actions because that system
+ * has a wifi adapter?
+ */
+ bool disable_wifi_frequencies;
+
struct cec_adapter *cec_adap;
struct cec_msg cec_rx_msg;
bool cec_tx_ok;
{
struct platform_device *pdev = to_platform_device(dev);
struct drm_device *drm = dev_get_drvdata(master);
- struct vc4_dev *vc4 = drm->dev_private;
+ struct vc4_dev *vc4 = to_vc4_dev(drm);
struct vc4_hvs *hvs = NULL;
int ret;
u32 dispctrl;
void *data)
{
struct drm_device *drm = dev_get_drvdata(master);
- struct vc4_dev *vc4 = drm->dev_private;
+ struct vc4_dev *vc4 = to_vc4_dev(drm);
struct vc4_hvs *hvs = vc4->hvs;
if (drm_mm_node_allocated(&vc4->hvs->mitchell_netravali_filter))
#include "vc4_drv.h"
#include "vc4_regs.h"
+#define HVS_NUM_CHANNELS 3
+
struct vc4_ctm_state {
struct drm_private_state base;
struct drm_color_ctm *ctm;
return container_of(priv, struct vc4_ctm_state, base);
}
+struct vc4_hvs_state {
+ struct drm_private_state base;
+ unsigned int unassigned_channels;
+};
+
+static struct vc4_hvs_state *
+to_vc4_hvs_state(struct drm_private_state *priv)
+{
+ return container_of(priv, struct vc4_hvs_state, base);
+}
+
struct vc4_load_tracker_state {
struct drm_private_state base;
u64 hvs_load;
struct drm_private_obj *manager)
{
struct drm_device *dev = state->dev;
- struct vc4_dev *vc4 = dev->dev_private;
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
struct drm_private_state *priv_state;
int ret;
.atomic_destroy_state = vc4_ctm_destroy_state,
};
+static void vc4_ctm_obj_fini(struct drm_device *dev, void *unused)
+{
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+ drm_atomic_private_obj_fini(&vc4->ctm_manager);
+}
+
+static int vc4_ctm_obj_init(struct vc4_dev *vc4)
+{
+ struct vc4_ctm_state *ctm_state;
+
+ drm_modeset_lock_init(&vc4->ctm_state_lock);
+
+ ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
+ if (!ctm_state)
+ return -ENOMEM;
+
+ drm_atomic_private_obj_init(&vc4->base, &vc4->ctm_manager, &ctm_state->base,
+ &vc4_ctm_state_funcs);
+
+ return drmm_add_action_or_reset(&vc4->base, vc4_ctm_obj_fini, NULL);
+}
+
/* Converts a DRM S31.32 value to the HW S0.9 format. */
static u16 vc4_ctm_s31_32_to_s0_9(u64 in)
{
VC4_SET_FIELD(ctm_state->fifo, SCALER_OLEDOFFS_DISPFIFO));
}
+static struct vc4_hvs_state *
+vc4_hvs_get_global_state(struct drm_atomic_state *state)
+{
+ struct vc4_dev *vc4 = to_vc4_dev(state->dev);
+ struct drm_private_state *priv_state;
+
+ priv_state = drm_atomic_get_private_obj_state(state, &vc4->hvs_channels);
+ if (IS_ERR(priv_state))
+ return ERR_CAST(priv_state);
+
+ return to_vc4_hvs_state(priv_state);
+}
+
static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4,
struct drm_atomic_state *state)
{
{
struct drm_crtc_state *crtc_state;
struct drm_crtc *crtc;
- unsigned char dsp2_mux = 0;
- unsigned char dsp3_mux = 3;
- unsigned char dsp4_mux = 3;
- unsigned char dsp5_mux = 3;
+ unsigned char mux;
unsigned int i;
u32 reg;
struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state);
struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
- if (!crtc_state->active)
+ if (!vc4_state->update_muxing)
continue;
switch (vc4_crtc->data->hvs_output) {
case 2:
- dsp2_mux = (vc4_state->assigned_channel == 2) ? 0 : 1;
+ mux = (vc4_state->assigned_channel == 2) ? 0 : 1;
+ reg = HVS_READ(SCALER_DISPECTRL);
+ HVS_WRITE(SCALER_DISPECTRL,
+ (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) |
+ VC4_SET_FIELD(mux, SCALER_DISPECTRL_DSP2_MUX));
break;
case 3:
- dsp3_mux = vc4_state->assigned_channel;
+ if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED)
+ mux = 3;
+ else
+ mux = vc4_state->assigned_channel;
+
+ reg = HVS_READ(SCALER_DISPCTRL);
+ HVS_WRITE(SCALER_DISPCTRL,
+ (reg & ~SCALER_DISPCTRL_DSP3_MUX_MASK) |
+ VC4_SET_FIELD(mux, SCALER_DISPCTRL_DSP3_MUX));
break;
case 4:
- dsp4_mux = vc4_state->assigned_channel;
+ if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED)
+ mux = 3;
+ else
+ mux = vc4_state->assigned_channel;
+
+ reg = HVS_READ(SCALER_DISPEOLN);
+ HVS_WRITE(SCALER_DISPEOLN,
+ (reg & ~SCALER_DISPEOLN_DSP4_MUX_MASK) |
+ VC4_SET_FIELD(mux, SCALER_DISPEOLN_DSP4_MUX));
+
break;
case 5:
- dsp5_mux = vc4_state->assigned_channel;
+ if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED)
+ mux = 3;
+ else
+ mux = vc4_state->assigned_channel;
+
+ reg = HVS_READ(SCALER_DISPDITHER);
+ HVS_WRITE(SCALER_DISPDITHER,
+ (reg & ~SCALER_DISPDITHER_DSP5_MUX_MASK) |
+ VC4_SET_FIELD(mux, SCALER_DISPDITHER_DSP5_MUX));
break;
default:
break;
}
}
-
- reg = HVS_READ(SCALER_DISPECTRL);
- HVS_WRITE(SCALER_DISPECTRL,
- (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) |
- VC4_SET_FIELD(dsp2_mux, SCALER_DISPECTRL_DSP2_MUX));
-
- reg = HVS_READ(SCALER_DISPCTRL);
- HVS_WRITE(SCALER_DISPCTRL,
- (reg & ~SCALER_DISPCTRL_DSP3_MUX_MASK) |
- VC4_SET_FIELD(dsp3_mux, SCALER_DISPCTRL_DSP3_MUX));
-
- reg = HVS_READ(SCALER_DISPEOLN);
- HVS_WRITE(SCALER_DISPEOLN,
- (reg & ~SCALER_DISPEOLN_DSP4_MUX_MASK) |
- VC4_SET_FIELD(dsp4_mux, SCALER_DISPEOLN_DSP4_MUX));
-
- reg = HVS_READ(SCALER_DISPDITHER);
- HVS_WRITE(SCALER_DISPDITHER,
- (reg & ~SCALER_DISPDITHER_DSP5_MUX_MASK) |
- VC4_SET_FIELD(dsp5_mux, SCALER_DISPDITHER_DSP5_MUX));
}
static void
.atomic_destroy_state = vc4_load_tracker_destroy_state,
};
-#define NUM_OUTPUTS 6
-#define NUM_CHANNELS 3
+static void vc4_load_tracker_obj_fini(struct drm_device *dev, void *unused)
+{
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
-static int
-vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+ if (!vc4->load_tracker_available)
+ return;
+
+ drm_atomic_private_obj_fini(&vc4->load_tracker);
+}
+
+static int vc4_load_tracker_obj_init(struct vc4_dev *vc4)
{
- unsigned long unassigned_channels = GENMASK(NUM_CHANNELS - 1, 0);
- struct drm_crtc_state *old_crtc_state, *new_crtc_state;
- struct drm_crtc *crtc;
- int i, ret;
+ struct vc4_load_tracker_state *load_state;
- /*
- * Since the HVS FIFOs are shared across all the pixelvalves and
- * the TXP (and thus all the CRTCs), we need to pull the current
- * state of all the enabled CRTCs so that an update to a single
- * CRTC still keeps the previous FIFOs enabled and assigned to
- * the same CRTCs, instead of evaluating only the CRTC being
- * modified.
- */
- list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
- struct drm_crtc_state *crtc_state;
+ if (!vc4->load_tracker_available)
+ return 0;
- if (!crtc->state->enable)
- continue;
+ load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
+ if (!load_state)
+ return -ENOMEM;
- crtc_state = drm_atomic_get_crtc_state(state, crtc);
- if (IS_ERR(crtc_state))
- return PTR_ERR(crtc_state);
- }
+ drm_atomic_private_obj_init(&vc4->base, &vc4->load_tracker,
+ &load_state->base,
+ &vc4_load_tracker_state_funcs);
+
+ return drmm_add_action_or_reset(&vc4->base, vc4_load_tracker_obj_fini, NULL);
+}
+
+static struct drm_private_state *
+vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj)
+{
+ struct vc4_hvs_state *old_state = to_vc4_hvs_state(obj->state);
+ struct vc4_hvs_state *state;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return NULL;
+
+ __drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+ state->unassigned_channels = old_state->unassigned_channels;
+
+ return &state->base;
+}
+
+static void vc4_hvs_channels_destroy_state(struct drm_private_obj *obj,
+ struct drm_private_state *state)
+{
+ struct vc4_hvs_state *hvs_state = to_vc4_hvs_state(state);
+
+ kfree(hvs_state);
+}
+
+static const struct drm_private_state_funcs vc4_hvs_state_funcs = {
+ .atomic_duplicate_state = vc4_hvs_channels_duplicate_state,
+ .atomic_destroy_state = vc4_hvs_channels_destroy_state,
+};
+
+static void vc4_hvs_channels_obj_fini(struct drm_device *dev, void *unused)
+{
+ struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+ drm_atomic_private_obj_fini(&vc4->hvs_channels);
+}
+
+static int vc4_hvs_channels_obj_init(struct vc4_dev *vc4)
+{
+ struct vc4_hvs_state *state;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ state->unassigned_channels = GENMASK(HVS_NUM_CHANNELS - 1, 0);
+ drm_atomic_private_obj_init(&vc4->base, &vc4->hvs_channels,
+ &state->base,
+ &vc4_hvs_state_funcs);
+
+ return drmm_add_action_or_reset(&vc4->base, vc4_hvs_channels_obj_fini, NULL);
+}
+
+/*
+ * The BCM2711 HVS has up to 7 outputs connected to the pixelvalves and
+ * the TXP (and therefore all the CRTCs found on that platform).
+ *
+ * The naive (and our initial) implementation would just iterate over
+ * all the active CRTCs, try to find a suitable FIFO, and then remove it
+ * from the pool of available FIFOs. However, there are a few corner
+ * cases that need to be considered:
+ *
+ * - When running in a dual-display setup (so with two CRTCs involved),
+ * we can update the state of a single CRTC (for example by changing
+ * its mode using xrandr under X11) without affecting the other. In
+ * this case, the other CRTC wouldn't be in the state at all, so we
+ * need to consider all the running CRTCs in the DRM device to assign
+ * a FIFO, not just the one in the state.
+ *
+ * - To fix the above, we can't use drm_atomic_get_crtc_state on all
+ * enabled CRTCs to pull their CRTC state into the global state, since
+ * a page flip would start considering their vblank to complete. Since
+ * we don't have a guarantee that they are actually active, that
+ * vblank might never happen, and shouldn't even be considered if we
+ * want to do a page flip on a single CRTC. That can be tested by
+ * doing a modetest -v first on HDMI1 and then on HDMI0.
+ *
+ * - Since we need the pixelvalve to be disabled and enabled back when
+ * the FIFO is changed, we should keep the FIFO assigned for as long
+ * as the CRTC is enabled, only considering it free again once that
+ * CRTC has been disabled. This can be tested by booting X11 on a
+ * single display, and changing the resolution down and then back up.
+ */
+static int vc4_pv_muxing_atomic_check(struct drm_device *dev,
+ struct drm_atomic_state *state)
+{
+ struct vc4_hvs_state *hvs_new_state;
+ struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+ struct drm_crtc *crtc;
+ unsigned int i;
+
+ hvs_new_state = vc4_hvs_get_global_state(state);
+ if (!hvs_new_state)
+ return -EINVAL;
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+ struct vc4_crtc_state *old_vc4_crtc_state =
+ to_vc4_crtc_state(old_crtc_state);
struct vc4_crtc_state *new_vc4_crtc_state =
to_vc4_crtc_state(new_crtc_state);
struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
unsigned int matching_channels;
- if (old_crtc_state->enable && !new_crtc_state->enable)
- new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED;
-
- if (!new_crtc_state->enable)
+ /* Nothing to do here, let's skip it */
+ if (old_crtc_state->enable == new_crtc_state->enable)
continue;
- if (new_vc4_crtc_state->assigned_channel != VC4_HVS_CHANNEL_DISABLED) {
- unassigned_channels &= ~BIT(new_vc4_crtc_state->assigned_channel);
+ /* Muxing will need to be modified, mark it as such */
+ new_vc4_crtc_state->update_muxing = true;
+
+ /* If we're disabling our CRTC, we put back our channel */
+ if (!new_crtc_state->enable) {
+ hvs_new_state->unassigned_channels |= BIT(old_vc4_crtc_state->assigned_channel);
+ new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED;
continue;
}
* the future, we will need to have something smarter,
* but it works so far.
*/
- matching_channels = unassigned_channels & vc4_crtc->data->hvs_available_channels;
+ matching_channels = hvs_new_state->unassigned_channels & vc4_crtc->data->hvs_available_channels;
if (matching_channels) {
unsigned int channel = ffs(matching_channels) - 1;
new_vc4_crtc_state->assigned_channel = channel;
- unassigned_channels &= ~BIT(channel);
+ hvs_new_state->unassigned_channels &= ~BIT(channel);
} else {
return -EINVAL;
}
}
+ return 0;
+}
+
+static int
+vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+ int ret;
+
+ ret = vc4_pv_muxing_atomic_check(dev, state);
+ if (ret)
+ return ret;
+
ret = vc4_ctm_atomic_check(dev, state);
if (ret < 0)
return ret;
int vc4_kms_load(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
- struct vc4_ctm_state *ctm_state;
- struct vc4_load_tracker_state *load_state;
bool is_vc5 = of_device_is_compatible(dev->dev->of_node,
"brcm,bcm2711-vc5");
int ret;
dev->mode_config.async_page_flip = true;
dev->mode_config.allow_fb_modifiers = true;
- drm_modeset_lock_init(&vc4->ctm_state_lock);
-
- ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL);
- if (!ctm_state)
- return -ENOMEM;
-
- drm_atomic_private_obj_init(dev, &vc4->ctm_manager, &ctm_state->base,
- &vc4_ctm_state_funcs);
+ ret = vc4_ctm_obj_init(vc4);
+ if (ret)
+ return ret;
- if (vc4->load_tracker_available) {
- load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
- if (!load_state) {
- drm_atomic_private_obj_fini(&vc4->ctm_manager);
- return -ENOMEM;
- }
+ ret = vc4_load_tracker_obj_init(vc4);
+ if (ret)
+ return ret;
- drm_atomic_private_obj_init(dev, &vc4->load_tracker,
- &load_state->base,
- &vc4_load_tracker_state_funcs);
- }
+ ret = vc4_hvs_channels_obj_init(vc4);
+ if (ret)
+ return ret;
drm_mode_config_reset(dev);
int vc4_v3d_get_bin_slot(struct vc4_dev *vc4)
{
- struct drm_device *dev = vc4->dev;
+ struct drm_device *dev = &vc4->base;
unsigned long irqflags;
int slot;
uint64_t seqno = 0;
INIT_LIST_HEAD(&list);
while (true) {
- struct vc4_bo *bo = vc4_bo_create(vc4->dev, size, true,
+ struct vc4_bo *bo = vc4_bo_create(&vc4->base, size, true,
VC4_BO_TYPE_BIN);
if (IS_ERR(bo)) {
struct vc4_v3d *v3d = dev_get_drvdata(dev);
struct vc4_dev *vc4 = v3d->vc4;
- vc4_irq_uninstall(vc4->dev);
+ vc4_irq_uninstall(&vc4->base);
clk_disable_unprepare(v3d->clk);
if (ret != 0)
return ret;
- vc4_v3d_init_hw(vc4->dev);
+ vc4_v3d_init_hw(&vc4->base);
/* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */
- enable_irq(vc4->dev->irq);
- vc4_irq_postinstall(vc4->dev);
+ enable_irq(vc4->base.irq);
+ vc4_irq_postinstall(&vc4->base);
return 0;
}
}
EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace);
-bool ipu_pixelformat_is_planar(u32 pixelformat)
-{
- switch (pixelformat) {
- case V4L2_PIX_FMT_YUV420:
- case V4L2_PIX_FMT_YVU420:
- case V4L2_PIX_FMT_YUV422P:
- case V4L2_PIX_FMT_NV12:
- case V4L2_PIX_FMT_NV21:
- case V4L2_PIX_FMT_NV16:
- case V4L2_PIX_FMT_NV61:
- return true;
- }
-
- return false;
-}
-EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar);
-
-enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code)
-{
- switch (mbus_code & 0xf000) {
- case 0x1000:
- return IPUV3_COLORSPACE_RGB;
- case 0x2000:
- return IPUV3_COLORSPACE_YUV;
- default:
- return IPUV3_COLORSPACE_UNKNOWN;
- }
-}
-EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace);
-
-int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
-{
- switch (pixelformat) {
- case V4L2_PIX_FMT_YUV420:
- case V4L2_PIX_FMT_YVU420:
- case V4L2_PIX_FMT_YUV422P:
- case V4L2_PIX_FMT_NV12:
- case V4L2_PIX_FMT_NV21:
- case V4L2_PIX_FMT_NV16:
- case V4L2_PIX_FMT_NV61:
- /*
- * for the planar YUV formats, the stride passed to
- * cpmem must be the stride in bytes of the Y plane.
- * And all the planar YUV formats have an 8-bit
- * Y component.
- */
- return (8 * pixel_stride) >> 3;
- case V4L2_PIX_FMT_RGB565:
- case V4L2_PIX_FMT_YUYV:
- case V4L2_PIX_FMT_UYVY:
- return (16 * pixel_stride) >> 3;
- case V4L2_PIX_FMT_BGR24:
- case V4L2_PIX_FMT_RGB24:
- return (24 * pixel_stride) >> 3;
- case V4L2_PIX_FMT_BGR32:
- case V4L2_PIX_FMT_RGB32:
- case V4L2_PIX_FMT_XBGR32:
- case V4L2_PIX_FMT_XRGB32:
- return (32 * pixel_stride) >> 3;
- default:
- break;
- }
-
- return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(ipu_stride_to_bytes);
-
int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
bool hflip, bool vflip)
{
#define CP_2WHEEL_MOUSE_HACK 0x02
#define CP_2WHEEL_MOUSE_HACK_ON 0x04
+#define VA_INVAL_LOGICAL_BOUNDARY 0x08
+
/*
* Some USB barcode readers from cypress have usage min and usage max in
* the wrong order
*/
-static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+static __u8 *cp_rdesc_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- unsigned long quirks = (unsigned long)hid_get_drvdata(hdev);
unsigned int i;
- if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX))
- return rdesc;
-
if (*rsize < 4)
return rdesc;
return rdesc;
}
+static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc,
+ unsigned int *rsize)
+{
+ /*
+ * Varmilo VA104M (with VID Cypress and device ID 07B1) incorrectly
+ * reports Logical Minimum of its Consumer Control device as 572
+ * (0x02 0x3c). Fix this by setting its Logical Minimum to zero.
+ */
+ if (*rsize == 25 &&
+ rdesc[0] == 0x05 && rdesc[1] == 0x0c &&
+ rdesc[2] == 0x09 && rdesc[3] == 0x01 &&
+ rdesc[6] == 0x19 && rdesc[7] == 0x00 &&
+ rdesc[11] == 0x16 && rdesc[12] == 0x3c && rdesc[13] == 0x02) {
+ hid_info(hdev,
+ "fixing up varmilo VA104M consumer control report descriptor\n");
+ rdesc[12] = 0x00;
+ rdesc[13] = 0x00;
+ }
+ return rdesc;
+}
+
+static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+ unsigned int *rsize)
+{
+ unsigned long quirks = (unsigned long)hid_get_drvdata(hdev);
+
+ if (quirks & CP_RDESC_SWAPPED_MIN_MAX)
+ rdesc = cp_rdesc_fixup(hdev, rdesc, rsize);
+ if (quirks & VA_INVAL_LOGICAL_BOUNDARY)
+ rdesc = va_logical_boundary_fixup(hdev, rdesc, rsize);
+
+ return rdesc;
+}
+
static int cp_input_mapped(struct hid_device *hdev, struct hid_input *hi,
struct hid_field *field, struct hid_usage *usage,
unsigned long **bit, int *max)
.driver_data = CP_RDESC_SWAPPED_MIN_MAX },
{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE),
.driver_data = CP_2WHEEL_MOUSE_HACK },
+ { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1),
+ .driver_data = VA_INVAL_LOGICAL_BOUNDARY },
{ }
};
MODULE_DEVICE_TABLE(hid, cp_devices);
#define USB_DEVICE_ID_CYPRESS_BARCODE_4 0xed81
#define USB_DEVICE_ID_CYPRESS_TRUETOUCH 0xc001
+#define USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1 0X07b1
+
#define USB_VENDOR_ID_DATA_MODUL 0x7374
#define USB_VENDOR_ID_DATA_MODUL_EASYMAXTOUCH 0x1201
#define USB_VENDOR_ID_FRUCTEL 0x25B6
#define USB_DEVICE_ID_GAMETEL_MT_MODE 0x0002
+#define USB_VENDOR_ID_GAMEVICE 0x27F8
+#define USB_DEVICE_ID_GAMEVICE_GV186 0x0BBE
+#define USB_DEVICE_ID_GAMEVICE_KISHI 0x0BBF
+
#define USB_VENDOR_ID_GAMERON 0x0810
#define USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR 0x0001
#define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR 0x0002
#define USB_DEVICE_ID_PENPOWER 0x00f4
#define USB_VENDOR_ID_GREENASIA 0x0e8f
+#define USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR 0x3010
#define USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD 0x3013
#define USB_VENDOR_ID_GRETAGMACBETH 0x0971
#define USB_VENDOR_ID_LOGITECH 0x046d
#define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
#define USB_DEVICE_ID_LOGITECH_T651 0xb00c
+#define USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD 0xb309
#define USB_DEVICE_ID_LOGITECH_C007 0xc007
#define USB_DEVICE_ID_LOGITECH_C077 0xc077
#define USB_DEVICE_ID_LOGITECH_RECEIVER 0xc101
#define USB_VENDOR_ID_UGTIZER 0x2179
#define USB_DEVICE_ID_UGTIZER_TABLET_GP0610 0x0053
+#define USB_DEVICE_ID_UGTIZER_TABLET_GT5040 0x0077
#define USB_VENDOR_ID_VIEWSONIC 0x0543
#define USB_DEVICE_ID_VIEWSONIC_PD1011 0xe621
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ASUSTEK,
USB_DEVICE_ID_ASUSTEK_T100CHI_KEYBOARD),
HID_BATTERY_QUIRK_IGNORE },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
+ USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD),
+ HID_BATTERY_QUIRK_IGNORE },
{}
};
#include "hid-ids.h"
+#define QUIRK_TOUCHPAD_ON_OFF_REPORT BIT(0)
+
+static __u8 *ite_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize)
+{
+ unsigned long quirks = (unsigned long)hid_get_drvdata(hdev);
+
+ if (quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) {
+ if (*rsize == 188 && rdesc[162] == 0x81 && rdesc[163] == 0x02) {
+ hid_info(hdev, "Fixing up ITE keyboard report descriptor\n");
+ rdesc[163] = HID_MAIN_ITEM_RELATIVE;
+ }
+ }
+
+ return rdesc;
+}
+
+static int ite_input_mapping(struct hid_device *hdev,
+ struct hid_input *hi, struct hid_field *field,
+ struct hid_usage *usage, unsigned long **bit,
+ int *max)
+{
+
+ unsigned long quirks = (unsigned long)hid_get_drvdata(hdev);
+
+ if ((quirks & QUIRK_TOUCHPAD_ON_OFF_REPORT) &&
+ (usage->hid & HID_USAGE_PAGE) == 0x00880000) {
+ if (usage->hid == 0x00880078) {
+ /* Touchpad on, userspace expects F22 for this */
+ hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F22);
+ return 1;
+ }
+ if (usage->hid == 0x00880079) {
+ /* Touchpad off, userspace expects F23 for this */
+ hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_F23);
+ return 1;
+ }
+ return -1;
+ }
+
+ return 0;
+}
+
static int ite_event(struct hid_device *hdev, struct hid_field *field,
struct hid_usage *usage, __s32 value)
{
return 0;
}
+static int ite_probe(struct hid_device *hdev, const struct hid_device_id *id)
+{
+ int ret;
+
+ hid_set_drvdata(hdev, (void *)id->driver_data);
+
+ ret = hid_open_report(hdev);
+ if (ret)
+ return ret;
+
+ return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+}
+
static const struct hid_device_id ite_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) },
{ HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) },
/* ITE8595 USB kbd ctlr, with Synaptics touchpad connected to it. */
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_SYNAPTICS,
- USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012) },
+ USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012),
+ .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT },
/* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_SYNAPTICS,
static struct hid_driver ite_driver = {
.name = "itetech",
.id_table = ite_devices,
+ .probe = ite_probe,
+ .report_fixup = ite_report_fixup,
+ .input_mapping = ite_input_mapping,
.event = ite_event,
};
module_hid_driver(ite_driver);
0x25, 0x01, /* LOGICAL_MAX (1) */
0x75, 0x01, /* REPORT_SIZE (1) */
0x95, 0x04, /* REPORT_COUNT (4) */
- 0x81, 0x06, /* INPUT */
+ 0x81, 0x02, /* INPUT (Data,Var,Abs) */
0xC0, /* END_COLLECTION */
0xC0, /* END_COLLECTION */
};
schedule_work(&djrcv_dev->work);
}
+/*
+ * Some quad/bluetooth keyboards have a builtin touchpad in this case we see
+ * only 1 paired device with a device_type of REPORT_TYPE_KEYBOARD. For the
+ * touchpad to work we must also forward mouse input reports to the dj_hiddev
+ * created for the keyboard (instead of forwarding them to a second paired
+ * device with a device_type of REPORT_TYPE_MOUSE as we normally would).
+ */
+static const u16 kbd_builtin_touchpad_ids[] = {
+ 0xb309, /* Dinovo Edge */
+ 0xb30c, /* Dinovo Mini */
+};
+
static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev,
struct hidpp_event *hidpp_report,
struct dj_workitem *workitem)
{
struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev);
+ int i, id;
workitem->type = WORKITEM_TYPE_PAIRED;
workitem->device_type = hidpp_report->params[HIDPP_PARAM_DEVICE_INFO] &
workitem->reports_supported |= STD_KEYBOARD | MULTIMEDIA |
POWER_KEYS | MEDIA_CENTER |
HIDPP;
+ id = (workitem->quad_id_msb << 8) | workitem->quad_id_lsb;
+ for (i = 0; i < ARRAY_SIZE(kbd_builtin_touchpad_ids); i++) {
+ if (id == kbd_builtin_touchpad_ids[i]) {
+ workitem->reports_supported |= STD_MOUSE;
+ break;
+ }
+ }
break;
case REPORT_TYPE_MOUSE:
workitem->reports_supported |= STD_MOUSE | HIDPP;
#define HIDPP_CAPABILITY_BATTERY_LEVEL_STATUS BIT(3)
#define HIDPP_CAPABILITY_BATTERY_VOLTAGE BIT(4)
+#define lg_map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c))
+
/*
* There are two hidpp protocols in use, the first version hidpp10 is known
* as register access protocol or RAP, the second version hidpp20 is known as
return g920_ff_set_autocenter(hidpp, data);
}
+/* -------------------------------------------------------------------------- */
+/* Logitech Dinovo Mini keyboard with builtin touchpad */
+/* -------------------------------------------------------------------------- */
+#define DINOVO_MINI_PRODUCT_ID 0xb30c
+
+static int lg_dinovo_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+ struct hid_field *field, struct hid_usage *usage,
+ unsigned long **bit, int *max)
+{
+ if ((usage->hid & HID_USAGE_PAGE) != HID_UP_LOGIVENDOR)
+ return 0;
+
+ switch (usage->hid & HID_USAGE) {
+ case 0x00d: lg_map_key_clear(KEY_MEDIA); break;
+ default:
+ return 0;
+ }
+ return 1;
+}
+
/* -------------------------------------------------------------------------- */
/* HID++1.0 devices which use HID++ reports for their wheels */
/* -------------------------------------------------------------------------- */
field->application != HID_GD_MOUSE)
return m560_input_mapping(hdev, hi, field, usage, bit, max);
+ if (hdev->product == DINOVO_MINI_PRODUCT_ID)
+ return lg_dinovo_input_mapping(hdev, hi, field, usage, bit, max);
+
return 0;
}
LDJ_DEVICE(0x405e), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
{ /* Mouse Logitech MX Anywhere 2 */
LDJ_DEVICE(0x404a), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
+ { LDJ_DEVICE(0x4072), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
{ LDJ_DEVICE(0xb013), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
{ LDJ_DEVICE(0xb018), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
{ LDJ_DEVICE(0xb01f), .driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
{ /* Keyboard MX5000 (Bluetooth-receiver in HID proxy mode) */
LDJ_DEVICE(0xb305),
.driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS },
+ { /* Dinovo Edge (Bluetooth-receiver in HID proxy mode) */
+ LDJ_DEVICE(0xb309),
+ .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS },
{ /* Keyboard MX5500 (Bluetooth-receiver in HID proxy mode) */
LDJ_DEVICE(0xb30b),
.driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS },
{ /* MX5000 keyboard over Bluetooth */
HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305),
.driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS },
+ { /* Dinovo Edge keyboard over Bluetooth */
+ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb309),
+ .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS },
{ /* MX5500 keyboard over Bluetooth */
HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b),
.driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS },
MCP2221_ALT_F_NOT_GPIOD = 0xEF,
};
+/* MCP GPIO direction encoding */
+enum {
+ MCP2221_DIR_OUT = 0x00,
+ MCP2221_DIR_IN = 0x01,
+};
+
+#define MCP_NGPIO 4
+
+/* MCP GPIO set command layout */
+struct mcp_set_gpio {
+ u8 cmd;
+ u8 dummy;
+ struct {
+ u8 change_value;
+ u8 value;
+ u8 change_direction;
+ u8 direction;
+ } gpio[MCP_NGPIO];
+} __packed;
+
+/* MCP GPIO get command layout */
+struct mcp_get_gpio {
+ u8 cmd;
+ u8 dummy;
+ struct {
+ u8 direction;
+ u8 value;
+ } gpio[MCP_NGPIO];
+} __packed;
+
/*
* There is no way to distinguish responses. Therefore next command
* is sent only after response to previous has been received. Mutex
mcp->txbuf[0] = MCP2221_GPIO_GET;
- mcp->gp_idx = (offset + 1) * 2;
+ mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].value);
mutex_lock(&mcp->lock);
ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1);
memset(mcp->txbuf, 0, 18);
mcp->txbuf[0] = MCP2221_GPIO_SET;
- mcp->gp_idx = ((offset + 1) * 4) - 1;
+ mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].value);
mcp->txbuf[mcp->gp_idx - 1] = 1;
mcp->txbuf[mcp->gp_idx] = !!value;
memset(mcp->txbuf, 0, 18);
mcp->txbuf[0] = MCP2221_GPIO_SET;
- mcp->gp_idx = (offset + 1) * 5;
+ mcp->gp_idx = offsetof(struct mcp_set_gpio, gpio[offset].direction);
mcp->txbuf[mcp->gp_idx - 1] = 1;
mcp->txbuf[mcp->gp_idx] = val;
struct mcp2221 *mcp = gpiochip_get_data(gc);
mutex_lock(&mcp->lock);
- ret = mcp_gpio_dir_set(mcp, offset, 0);
+ ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_IN);
mutex_unlock(&mcp->lock);
return ret;
struct mcp2221 *mcp = gpiochip_get_data(gc);
mutex_lock(&mcp->lock);
- ret = mcp_gpio_dir_set(mcp, offset, 1);
+ ret = mcp_gpio_dir_set(mcp, offset, MCP2221_DIR_OUT);
mutex_unlock(&mcp->lock);
/* Can't configure as output, bailout early */
mcp->txbuf[0] = MCP2221_GPIO_GET;
- mcp->gp_idx = (offset + 1) * 2;
+ mcp->gp_idx = offsetof(struct mcp_get_gpio, gpio[offset].direction);
mutex_lock(&mcp->lock);
ret = mcp_send_data_req_status(mcp, mcp->txbuf, 1);
if (ret)
return ret;
- if (mcp->gpio_dir)
+ if (mcp->gpio_dir == MCP2221_DIR_IN)
return GPIO_LINE_DIRECTION_IN;
return GPIO_LINE_DIRECTION_OUT;
mcp->status = -ENOENT;
} else {
mcp->status = !!data[mcp->gp_idx];
- mcp->gpio_dir = !!data[mcp->gp_idx + 1];
+ mcp->gpio_dir = data[mcp->gp_idx + 1];
}
break;
default:
mcp->gc->get_direction = mcp_gpio_get_direction;
mcp->gc->set = mcp_gpio_set;
mcp->gc->get = mcp_gpio_get;
- mcp->gc->ngpio = 4;
+ mcp->gc->ngpio = MCP_NGPIO;
mcp->gc->base = -1;
mcp->gc->can_sleep = 1;
mcp->gc->parent = &hdev->dev;
{ HID_USB_DEVICE(USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_FUTABA, USB_DEVICE_ID_LED_DISPLAY), HID_QUIRK_NO_INIT_REPORTS },
+ { HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_SAT_ADAPTOR), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD), HID_QUIRK_MULTI_INPUT },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_GV186),
+ HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
+ { HID_USB_DEVICE(USB_VENDOR_ID_GAMEVICE, USB_DEVICE_ID_GAMEVICE_KISHI),
+ HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
{ HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_DRIVING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FIGHTING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_HAPP, USB_DEVICE_ID_UGCI_FLYING), HID_QUIRK_BADPAD | HID_QUIRK_MULTI_INPUT },
return 1;
ptr = raw_data;
- ptr++; /* Skip report id */
+ if (report->id)
+ ptr++; /* Skip report id */
spin_lock_irqsave(&pdata->lock, flags);
USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER,
USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER,
+ USB_DEVICE_ID_UGTIZER_TABLET_GT5040) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_TABLET_G5) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
break;
case VID_PID(USB_VENDOR_ID_UGTIZER,
USB_DEVICE_ID_UGTIZER_TABLET_GP0610):
+ case VID_PID(USB_VENDOR_ID_UGTIZER,
+ USB_DEVICE_ID_UGTIZER_TABLET_GT5040):
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540):
case VID_PID(USB_VENDOR_ID_UGEE,
}
}
+static void i2c_hid_acpi_shutdown(struct device *dev)
+{
+ acpi_device_set_power(ACPI_COMPANION(dev), ACPI_STATE_D3_COLD);
+}
+
static const struct acpi_device_id i2c_hid_acpi_match[] = {
{"ACPI0C50", 0 },
{"PNP0C50", 0 },
static inline void i2c_hid_acpi_fix_up_power(struct device *dev) {}
static inline void i2c_hid_acpi_enable_wakeup(struct device *dev) {}
+
+static inline void i2c_hid_acpi_shutdown(struct device *dev) {}
#endif
#ifdef CONFIG_OF
i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
free_irq(client->irq, ihid);
+
+ i2c_hid_acpi_shutdown(&client->dev);
}
#ifdef CONFIG_PM_SLEEP
/*
* Hyper-V does not provide a way to change the connect CPU once
- * it is set; we must prevent the connect CPU from going offline.
+ * it is set; we must prevent the connect CPU from going offline
+ * while the VM is running normally. But in the panic or kexec()
+ * path where the vmbus is already disconnected, the CPU must be
+ * allowed to shut down.
*/
- if (cpu == VMBUS_CONNECT_CPU)
+ if (cpu == VMBUS_CONNECT_CPU &&
+ vmbus_connection.conn_state == CONNECTED)
return -EBUSY;
/*
/* Refuse to balloon below the floor. */
if (avail_pages < num_pages || avail_pages - num_pages < floor) {
- pr_warn("Balloon request will be partially fulfilled. %s\n",
+ pr_info("Balloon request will be partially fulfilled. %s\n",
avail_pages < num_pages ? "Not enough memory." :
"Balloon floor reached.");
enum hwmon_sensor_types type,
u32 attr, int channel)
{
- return 0444;
+ return 0440;
}
static int energy_accumulator(void *p)
#include <linux/hwmon.h>
#include <linux/workqueue.h>
#include <linux/err.h>
+#include <linux/bits.h>
/* data port used by Apple SMC */
#define APPLESMC_DATA_PORT 0x300
#define APPLESMC_MAX_DATA_LENGTH 32
-/* wait up to 128 ms for a status change. */
-#define APPLESMC_MIN_WAIT 0x0010
-#define APPLESMC_RETRY_WAIT 0x0100
-#define APPLESMC_MAX_WAIT 0x20000
+/* Apple SMC status bits */
+#define SMC_STATUS_AWAITING_DATA BIT(0) /* SMC has data waiting to be read */
+#define SMC_STATUS_IB_CLOSED BIT(1) /* Will ignore any input */
+#define SMC_STATUS_BUSY BIT(2) /* Command in progress */
+
+/* Initial wait is 8us */
+#define APPLESMC_MIN_WAIT 0x0008
#define APPLESMC_READ_CMD 0x10
#define APPLESMC_WRITE_CMD 0x11
static struct workqueue_struct *applesmc_led_wq;
/*
- * wait_read - Wait for a byte to appear on SMC port. Callers must
- * hold applesmc_lock.
+ * Wait for specific status bits with a mask on the SMC.
+ * Used before all transactions.
+ * This does 10 fast loops of 8us then exponentially backs off for a
+ * minimum total wait of 262ms. Depending on usleep_range this could
+ * run out past 500ms.
*/
-static int wait_read(void)
+
+static int wait_status(u8 val, u8 mask)
{
- unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
u8 status;
int us;
+ int i;
- for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
- usleep_range(us, us * 16);
+ us = APPLESMC_MIN_WAIT;
+ for (i = 0; i < 24 ; i++) {
status = inb(APPLESMC_CMD_PORT);
- /* read: wait for smc to settle */
- if (status & 0x01)
+ if ((status & mask) == val)
return 0;
- /* timeout: give up */
- if (time_after(jiffies, end))
- break;
+ usleep_range(us, us * 2);
+ if (i > 9)
+ us <<= 1;
}
-
- pr_warn("wait_read() fail: 0x%02x\n", status);
return -EIO;
}
-/*
- * send_byte - Write to SMC port, retrying when necessary. Callers
- * must hold applesmc_lock.
- */
+/* send_byte - Write to SMC data port. Callers must hold applesmc_lock. */
+
static int send_byte(u8 cmd, u16 port)
{
- u8 status;
- int us;
- unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC;
+ int status;
+
+ status = wait_status(0, SMC_STATUS_IB_CLOSED);
+ if (status)
+ return status;
+ /*
+ * This needs to be a separate read looking for bit 0x04
+ * after bit 0x02 falls. If consolidated with the wait above
+ * this extra read may not happen if status returns both
+ * simultaneously and this would appear to be required.
+ */
+ status = wait_status(SMC_STATUS_BUSY, SMC_STATUS_BUSY);
+ if (status)
+ return status;
outb(cmd, port);
- for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) {
- usleep_range(us, us * 16);
- status = inb(APPLESMC_CMD_PORT);
- /* write: wait for smc to settle */
- if (status & 0x02)
- continue;
- /* ready: cmd accepted, return */
- if (status & 0x04)
- return 0;
- /* timeout: give up */
- if (time_after(jiffies, end))
- break;
- /* busy: long wait and resend */
- udelay(APPLESMC_RETRY_WAIT);
- outb(cmd, port);
- }
-
- pr_warn("send_byte(0x%02x, 0x%04x) fail: 0x%02x\n", cmd, port, status);
- return -EIO;
+ return 0;
}
+/* send_command - Write a command to the SMC. Callers must hold applesmc_lock. */
+
static int send_command(u8 cmd)
{
- return send_byte(cmd, APPLESMC_CMD_PORT);
+ int ret;
+
+ ret = wait_status(0, SMC_STATUS_IB_CLOSED);
+ if (ret)
+ return ret;
+ outb(cmd, APPLESMC_CMD_PORT);
+ return 0;
+}
+
+/*
+ * Based on logic from the Apple driver. This is issued before any interaction
+ * If busy is stuck high, issue a read command to reset the SMC state machine.
+ * If busy is stuck high after the command then the SMC is jammed.
+ */
+
+static int smc_sane(void)
+{
+ int ret;
+
+ ret = wait_status(0, SMC_STATUS_BUSY);
+ if (!ret)
+ return ret;
+ ret = send_command(APPLESMC_READ_CMD);
+ if (ret)
+ return ret;
+ return wait_status(0, SMC_STATUS_BUSY);
}
static int send_argument(const char *key)
{
u8 status, data = 0;
int i;
+ int ret;
+
+ ret = smc_sane();
+ if (ret)
+ return ret;
if (send_command(cmd) || send_argument(key)) {
pr_warn("%.4s: read arg fail\n", key);
}
for (i = 0; i < len; i++) {
- if (wait_read()) {
+ if (wait_status(SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY,
+ SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY)) {
pr_warn("%.4s: read data[%d] fail\n", key, i);
return -EIO;
}
for (i = 0; i < 16; i++) {
udelay(APPLESMC_MIN_WAIT);
status = inb(APPLESMC_CMD_PORT);
- if (!(status & 0x01))
+ if (!(status & SMC_STATUS_AWAITING_DATA))
break;
data = inb(APPLESMC_DATA_PORT);
}
if (i)
pr_warn("flushed %d bytes, last value is: %d\n", i, data);
- return 0;
+ return wait_status(0, SMC_STATUS_BUSY);
}
static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len)
{
int i;
+ int ret;
+
+ ret = smc_sane();
+ if (ret)
+ return ret;
if (send_command(cmd) || send_argument(key)) {
pr_warn("%s: write arg fail\n", key);
}
}
- return 0;
+ return wait_status(0, SMC_STATUS_BUSY);
}
static int read_register_count(unsigned int *count)
switch (idx) {
case MAX20730_DEBUGFS_VOUT_MIN:
ret = VOLT_FROM_REG(data->mfr_voutmin * 10000);
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n",
- ret / 10000, ret % 10000);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n",
+ ret / 10000, ret % 10000);
break;
case MAX20730_DEBUGFS_FREQUENCY:
val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_FSW_MASK)
ret = 800;
else
ret = 900;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_PG_DELAY:
val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_TSTAT_MASK)
case MAX20730_DEBUGFS_OC_PROTECT_MODE:
ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_OCPM_MASK)
>> MAX20730_MFR_DEVSET2_OCPM_BIT_POS;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_SS_TIMING:
val = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_SS_MASK)
case MAX20730_DEBUGFS_IMAX:
ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_IMAX_MASK)
>> MAX20730_MFR_DEVSET2_IMAX_BIT_POS;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_OPERATION:
ret = i2c_smbus_read_byte_data(psu->client, PMBUS_OPERATION);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_ON_OFF_CONFIG:
ret = i2c_smbus_read_byte_data(psu->client, PMBUS_ON_OFF_CONFIG);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_SMBALERT_MASK:
ret = i2c_smbus_read_word_data(psu->client,
PMBUS_SMB_ALERT_MASK);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_VOUT_MODE:
ret = i2c_smbus_read_byte_data(psu->client, PMBUS_VOUT_MODE);
if (ret < 0)
return ret;
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret);
break;
case MAX20730_DEBUGFS_VOUT_COMMAND:
ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_COMMAND);
return ret;
ret = VOLT_FROM_REG(ret * 10000);
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX,
- "%d.%d\n", ret / 10000, ret % 10000);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX,
+ "%d.%d\n", ret / 10000, ret % 10000);
break;
case MAX20730_DEBUGFS_VOUT_MAX:
ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_MAX);
return ret;
ret = VOLT_FROM_REG(ret * 10000);
- len = snprintf(tbuf, DEBUG_FS_DATA_MAX,
- "%d.%d\n", ret / 10000, ret % 10000);
+ len = scnprintf(tbuf, DEBUG_FS_DATA_MAX,
+ "%d.%d\n", ret / 10000, ret % 10000);
break;
default:
len = strlcpy(tbuf, "Invalid\n", DEBUG_FS_DATA_MAX);
struct i2c_client *client = to_i2c_client(dev->parent);
struct pmbus_sensor *sensor = to_pmbus_sensor(devattr);
struct pmbus_data *data = i2c_get_clientdata(client);
+ ssize_t ret;
+ mutex_lock(&data->update_lock);
pmbus_update_sensor_data(client, sensor);
if (sensor->data < 0)
- return sensor->data;
-
- return snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor));
+ ret = sensor->data;
+ else
+ ret = snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor));
+ mutex_unlock(&data->update_lock);
+ return ret;
}
static ssize_t pmbus_set_sensor(struct device *dev,
int val;
struct i2c_client *client = to_i2c_client(dev->parent);
struct pmbus_samples_reg *reg = to_samples_reg(devattr);
+ struct pmbus_data *data = i2c_get_clientdata(client);
+ mutex_lock(&data->update_lock);
val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg);
+ mutex_unlock(&data->update_lock);
if (val < 0)
return val;
static void sample_timer(struct timer_list *t)
{
struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer);
+ unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start);
int pulses;
- u64 tmp;
- pulses = atomic_read(&ctx->pulses);
- atomic_sub(pulses, &ctx->pulses);
- tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60;
- do_div(tmp, ctx->pulses_per_revolution * 1000);
- ctx->rpm = tmp;
+ if (delta) {
+ pulses = atomic_read(&ctx->pulses);
+ atomic_sub(pulses, &ctx->pulses);
+ ctx->rpm = (unsigned int)(pulses * 1000 * 60) /
+ (ctx->pulses_per_revolution * delta);
+
+ ctx->sample_start = ktime_get();
+ }
- ctx->sample_start = ktime_get();
mod_timer(&ctx->rpm_timer, jiffies + HZ);
}
module_init(coresight_init);
module_exit(coresight_exit);
+MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>");
MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>");
MODULE_DESCRIPTION("Arm CoreSight tracer driver");
}
eattr->var = con;
con->con_attrs[attr_idx] = &eattr->attr.attr;
+ /*
+ * Initialize the dynamically allocated attribute
+ * to avoid LOCKDEP splat. See include/linux/sysfs.h
+ * for more details.
+ */
+ sysfs_attr_init(con->con_attrs[attr_idx]);
+
return 0;
}
u32 id;
int cpu = event->cpu;
cpumask_t *mask;
- struct coresight_device *sink;
+ struct coresight_device *sink = NULL;
struct etm_event_data *event_data = NULL;
event_data = alloc_event_data(cpu);
config I2C_MLXBF
tristate "Mellanox BlueField I2C controller"
- depends on ARM64
+ depends on MELLANOX_PLATFORM && ARM64
+ select I2C_SLAVE
help
Enabling this option will add I2C SMBus support for Mellanox BlueField
system.
u32 raw_stat, stat, enabled, tmp;
u8 val = 0, slave_activity;
- regmap_read(dev->map, DW_IC_INTR_STAT, &stat);
regmap_read(dev->map, DW_IC_ENABLE, &enabled);
regmap_read(dev->map, DW_IC_RAW_INTR_STAT, &raw_stat);
regmap_read(dev->map, DW_IC_STATUS, &tmp);
if (!enabled || !(raw_stat & ~DW_IC_INTR_ACTIVITY) || !dev->slave)
return 0;
+ stat = i2c_dw_read_clear_intrbits_slave(dev);
dev_dbg(dev->dev,
"%#x STATUS SLAVE_ACTIVITY=%#x : RAW_INTR_STAT=%#x : INTR_STAT=%#x\n",
enabled, slave_activity, raw_stat, stat);
- if ((stat & DW_IC_INTR_RX_FULL) && (stat & DW_IC_INTR_STOP_DET))
- i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED, &val);
+ if (stat & DW_IC_INTR_RX_FULL) {
+ if (dev->status != STATUS_WRITE_IN_PROGRESS) {
+ dev->status = STATUS_WRITE_IN_PROGRESS;
+ i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_REQUESTED,
+ &val);
+ }
+
+ regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
+ val = tmp;
+ if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED,
+ &val))
+ dev_vdbg(dev->dev, "Byte %X acked!", val);
+ }
if (stat & DW_IC_INTR_RD_REQ) {
if (slave_activity) {
- if (stat & DW_IC_INTR_RX_FULL) {
- regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
- val = tmp;
-
- if (!i2c_slave_event(dev->slave,
- I2C_SLAVE_WRITE_RECEIVED,
- &val)) {
- dev_vdbg(dev->dev, "Byte %X acked!",
- val);
- }
- regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
- } else {
- regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
- regmap_read(dev->map, DW_IC_CLR_RX_UNDER, &tmp);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
- }
+ regmap_read(dev->map, DW_IC_CLR_RD_REQ, &tmp);
+
+ dev->status = STATUS_READ_IN_PROGRESS;
if (!i2c_slave_event(dev->slave,
I2C_SLAVE_READ_REQUESTED,
&val))
if (!i2c_slave_event(dev->slave, I2C_SLAVE_READ_PROCESSED,
&val))
regmap_read(dev->map, DW_IC_CLR_RX_DONE, &tmp);
-
- i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
- return 1;
}
- if (stat & DW_IC_INTR_RX_FULL) {
- regmap_read(dev->map, DW_IC_DATA_CMD, &tmp);
- val = tmp;
- if (!i2c_slave_event(dev->slave, I2C_SLAVE_WRITE_RECEIVED,
- &val))
- dev_vdbg(dev->dev, "Byte %X acked!", val);
- } else {
+ if (stat & DW_IC_INTR_STOP_DET) {
+ dev->status = STATUS_IDLE;
i2c_slave_event(dev->slave, I2C_SLAVE_STOP, &val);
- stat = i2c_dw_read_clear_intrbits_slave(dev);
}
return 1;
struct dw_i2c_dev *dev = dev_id;
int ret;
- i2c_dw_read_clear_intrbits_slave(dev);
ret = i2c_dw_irq_handler_slave(dev);
if (ret > 0)
complete(&dev->cmd_complete);
dma->chan_using = NULL;
}
+static void i2c_imx_clear_irq(struct imx_i2c_struct *i2c_imx, unsigned int bits)
+{
+ unsigned int temp;
+
+ /*
+ * i2sr_clr_opcode is the value to clear all interrupts. Here we want to
+ * clear only <bits>, so we write ~i2sr_clr_opcode with just <bits>
+ * toggled. This is required because i.MX needs W0C and Vybrid uses W1C.
+ */
+ temp = ~i2c_imx->hwdata->i2sr_clr_opcode ^ bits;
+ imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR);
+}
+
static int i2c_imx_bus_busy(struct imx_i2c_struct *i2c_imx, int for_busy, bool atomic)
{
unsigned long orig_jiffies = jiffies;
/* check for arbitration lost */
if (temp & I2SR_IAL) {
- temp &= ~I2SR_IAL;
- imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR);
+ i2c_imx_clear_irq(i2c_imx, I2SR_IAL);
return -EAGAIN;
}
*/
readb_poll_timeout_atomic(addr, regval, regval & I2SR_IIF, 5, 1000 + 100);
i2c_imx->i2csr = regval;
- imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+ i2c_imx_clear_irq(i2c_imx, I2SR_IIF | I2SR_IAL);
} else {
wait_event_timeout(i2c_imx->queue, i2c_imx->i2csr & I2SR_IIF, HZ / 10);
}
dev_dbg(&i2c_imx->adapter.dev, "<%s> Timeout\n", __func__);
return -ETIMEDOUT;
}
+
+ /* check for arbitration lost */
+ if (i2c_imx->i2csr & I2SR_IAL) {
+ dev_dbg(&i2c_imx->adapter.dev, "<%s> Arbitration lost\n", __func__);
+ i2c_imx_clear_irq(i2c_imx, I2SR_IAL);
+
+ i2c_imx->i2csr = 0;
+ return -EAGAIN;
+ }
+
dev_dbg(&i2c_imx->adapter.dev, "<%s> TRX complete\n", __func__);
i2c_imx->i2csr = 0;
return 0;
/* Stop I2C transaction */
dev_dbg(&i2c_imx->adapter.dev, "<%s>\n", __func__);
temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
+ if (!(temp & I2CR_MSTA))
+ i2c_imx->stopped = 1;
temp &= ~(I2CR_MSTA | I2CR_MTX);
if (i2c_imx->dma)
temp &= ~I2CR_DMAEN;
if (temp & I2SR_IIF) {
/* save status register */
i2c_imx->i2csr = temp;
- temp &= ~I2SR_IIF;
- temp |= (i2c_imx->hwdata->i2sr_clr_opcode & I2SR_IIF);
- imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2SR);
+ i2c_imx_clear_irq(i2c_imx, I2SR_IIF);
wake_up(&i2c_imx->queue);
return IRQ_HANDLED;
}
*/
dev_dbg(dev, "<%s> clear MSTA\n", __func__);
temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
+ if (!(temp & I2CR_MSTA))
+ i2c_imx->stopped = 1;
temp &= ~(I2CR_MSTA | I2CR_MTX);
imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
- i2c_imx_bus_busy(i2c_imx, 0, false);
+ if (!i2c_imx->stopped)
+ i2c_imx_bus_busy(i2c_imx, 0, false);
} else {
/*
* For i2c master receiver repeat restart operation like:
dev_dbg(&i2c_imx->adapter.dev,
"<%s> clear MSTA\n", __func__);
temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
+ if (!(temp & I2CR_MSTA))
+ i2c_imx->stopped = 1;
temp &= ~(I2CR_MSTA | I2CR_MTX);
imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
- i2c_imx_bus_busy(i2c_imx, 0, atomic);
+ if (!i2c_imx->stopped)
+ i2c_imx_bus_busy(i2c_imx, 0, atomic);
} else {
/*
* For i2c master receiver repeat restart operation like:
* Master. Default value is set to 400MHz.
*/
#define MLXBF_I2C_TYU_PLL_OUT_FREQ (400 * 1000 * 1000)
-/* Reference clock for Bluefield 1 - 156 MHz. */
-#define MLXBF_I2C_TYU_PLL_IN_FREQ (156 * 1000 * 1000)
-/* Reference clock for BlueField 2 - 200 MHz. */
-#define MLXBF_I2C_YU_PLL_IN_FREQ (200 * 1000 * 1000)
+/* Reference clock for Bluefield - 156 MHz. */
+#define MLXBF_I2C_PLL_IN_FREQ (156 * 1000 * 1000)
/* Constant used to determine the PLL frequency. */
#define MLNXBF_I2C_COREPLL_CONST 16384
#define MLXBF_I2C_FREQUENCY_1GHZ 1000000000
-static void mlxbf_i2c_write(void __iomem *io, int reg, u32 val)
-{
- writel(val, io + reg);
-}
-
-static u32 mlxbf_i2c_read(void __iomem *io, int reg)
-{
- return readl(io + reg);
-}
-
-/*
- * This function is used to read data from Master GW Data Descriptor.
- * Data bytes in the Master GW Data Descriptor are shifted left so the
- * data starts at the MSB of the descriptor registers as set by the
- * underlying hardware. TYU_READ_DATA enables byte swapping while
- * reading data bytes, and MUST be called by the SMBus read routines
- * to copy data from the 32 * 32-bit HW Data registers a.k.a Master GW
- * Data Descriptor.
- */
-static u32 mlxbf_i2c_read_data(void __iomem *io, int reg)
-{
- return (u32)be32_to_cpu(mlxbf_i2c_read(io, reg));
-}
-
-/*
- * This function is used to write data to the Master GW Data Descriptor.
- * Data copied to the Master GW Data Descriptor MUST be shifted left so
- * the data starts at the MSB of the descriptor registers as required by
- * the underlying hardware. TYU_WRITE_DATA enables byte swapping when
- * writing data bytes, and MUST be called by the SMBus write routines to
- * copy data to the 32 * 32-bit HW Data registers a.k.a Master GW Data
- * Descriptor.
- */
-static void mlxbf_i2c_write_data(void __iomem *io, int reg, u32 val)
-{
- mlxbf_i2c_write(io, reg, (u32)cpu_to_be32(val));
-}
-
/*
* Function to poll a set of bits at a specific address; it checks whether
* the bits are equal to zero when eq_zero is set to 'true', and not equal
timeout = (timeout / MLXBF_I2C_POLL_FREQ_IN_USEC) + 1;
do {
- bits = mlxbf_i2c_read(io, addr) & mask;
+ bits = readl(io + addr) & mask;
if (eq_zero ? bits == 0 : bits != 0)
return eq_zero ? 1 : bits;
udelay(MLXBF_I2C_POLL_FREQ_IN_USEC);
MLXBF_I2C_SMBUS_TIMEOUT);
/* Read cause status bits. */
- cause_status_bits = mlxbf_i2c_read(priv->mst_cause->io,
- MLXBF_I2C_CAUSE_ARBITER);
+ cause_status_bits = readl(priv->mst_cause->io +
+ MLXBF_I2C_CAUSE_ARBITER);
cause_status_bits &= MLXBF_I2C_CAUSE_MASTER_ARBITER_BITS_MASK;
/*
* Parse both Cause and Master GW bits, then return transaction status.
*/
- master_status_bits = mlxbf_i2c_read(priv->smbus->io,
- MLXBF_I2C_SMBUS_MASTER_STATUS);
+ master_status_bits = readl(priv->smbus->io +
+ MLXBF_I2C_SMBUS_MASTER_STATUS);
master_status_bits &= MLXBF_I2C_SMBUS_MASTER_STATUS_MASK;
if (mlxbf_i2c_smbus_transaction_success(master_status_bits,
aligned_length = round_up(length, 4);
- /* Copy data bytes from 4-byte aligned source buffer. */
+ /*
+ * Copy data bytes from 4-byte aligned source buffer.
+ * Data copied to the Master GW Data Descriptor MUST be shifted
+ * left so the data starts at the MSB of the descriptor registers
+ * as required by the underlying hardware. Enable byte swapping
+ * when writing data bytes to the 32 * 32-bit HW Data registers
+ * a.k.a Master GW Data Descriptor.
+ */
for (offset = 0; offset < aligned_length; offset += sizeof(u32)) {
data32 = *((u32 *)(data + offset));
- mlxbf_i2c_write_data(priv->smbus->io, addr + offset, data32);
+ iowrite32be(data32, priv->smbus->io + addr + offset);
}
}
mask = sizeof(u32) - 1;
+ /*
+ * Data bytes in the Master GW Data Descriptor are shifted left
+ * so the data starts at the MSB of the descriptor registers as
+ * set by the underlying hardware. Enable byte swapping while
+ * reading data bytes from the 32 * 32-bit HW Data registers
+ * a.k.a Master GW Data Descriptor.
+ */
+
for (offset = 0; offset < (length & ~mask); offset += sizeof(u32)) {
- data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset);
+ data32 = ioread32be(priv->smbus->io + addr + offset);
*((u32 *)(data + offset)) = data32;
}
if (!(length & mask))
return;
- data32 = mlxbf_i2c_read_data(priv->smbus->io, addr + offset);
+ data32 = ioread32be(priv->smbus->io + addr + offset);
for (byte = 0; byte < (length & mask); byte++) {
data[offset + byte] = data32 & GENMASK(7, 0);
command |= rol32(pec_en, MLXBF_I2C_MASTER_SEND_PEC_SHIFT);
/* Clear status bits. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_STATUS, 0x0);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_STATUS);
/* Set the cause data. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0);
+ writel(~0x0, priv->smbus->io + MLXBF_I2C_CAUSE_OR_CLEAR);
/* Zero PEC byte. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_PEC, 0x0);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_PEC);
/* Zero byte count. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_RS_BYTES, 0x0);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_RS_BYTES);
/* GW activation. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_GW, command);
+ writel(command, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_GW);
/*
* Poll master status and check status bits. An ACK is sent when
* needs to be 'manually' reset. This should be removed in
* next tag integration.
*/
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_MASTER_FSM,
- MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK);
+ writel(MLXBF_I2C_SMBUS_MASTER_FSM_PS_STATE_MASK,
+ priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_FSM);
}
return ret;
timer |= mlxbf_i2c_set_timer(priv, timings->scl_low,
false, MLXBF_I2C_MASK_16,
MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH,
- timer);
+ writel(timer, priv->smbus->io +
+ MLXBF_I2C_SMBUS_TIMER_SCL_LOW_SCL_HIGH);
timer = mlxbf_i2c_set_timer(priv, timings->sda_rise, false,
MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_0);
MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_16);
timer |= mlxbf_i2c_set_timer(priv, timings->scl_fall, false,
MLXBF_I2C_MASK_8, MLXBF_I2C_SHIFT_24);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE,
- timer);
+ writel(timer, priv->smbus->io +
+ MLXBF_I2C_SMBUS_TIMER_FALL_RISE_SPIKE);
timer = mlxbf_i2c_set_timer(priv, timings->hold_start, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
timer |= mlxbf_i2c_set_timer(priv, timings->hold_data, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_THOLD, timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_THOLD);
timer = mlxbf_i2c_set_timer(priv, timings->setup_start, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
timer |= mlxbf_i2c_set_timer(priv, timings->setup_stop, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP, timer);
+ writel(timer, priv->smbus->io +
+ MLXBF_I2C_SMBUS_TIMER_TSETUP_START_STOP);
timer = mlxbf_i2c_set_timer(priv, timings->setup_data, true,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA,
- timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_TIMER_TSETUP_DATA);
timer = mlxbf_i2c_set_timer(priv, timings->buf, false,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_0);
timer |= mlxbf_i2c_set_timer(priv, timings->thigh_max, false,
MLXBF_I2C_MASK_16, MLXBF_I2C_SHIFT_16);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_THIGH_MAX_TBUF,
- timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_THIGH_MAX_TBUF);
timer = timings->timeout;
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT,
- timer);
+ writel(timer, priv->smbus->io + MLXBF_I2C_SMBUS_SCL_LOW_TIMEOUT);
}
enum mlxbf_i2c_timings_config {
return -EFAULT;
gpio_res->io = devm_ioremap(dev, params->start, size);
- if (IS_ERR(gpio_res->io)) {
+ if (!gpio_res->io) {
devm_release_mem_region(dev, params->start, size);
- return PTR_ERR(gpio_res->io);
+ return -ENOMEM;
}
return 0;
return -EFAULT;
corepll_res->io = devm_ioremap(dev, params->start, size);
- if (IS_ERR(corepll_res->io)) {
+ if (!corepll_res->io) {
devm_release_mem_region(dev, params->start, size);
- return PTR_ERR(corepll_res->io);
+ return -ENOMEM;
}
return 0;
* platform firmware; disabling the bus might compromise the system
* functionality.
*/
- config_reg = mlxbf_i2c_read(gpio_res->io,
- MLXBF_I2C_GPIO_0_FUNC_EN_0);
+ config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0);
config_reg = MLXBF_I2C_GPIO_SMBUS_GW_ASSERT_PINS(priv->bus,
config_reg);
- mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FUNC_EN_0,
- config_reg);
+ writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FUNC_EN_0);
- config_reg = mlxbf_i2c_read(gpio_res->io,
- MLXBF_I2C_GPIO_0_FORCE_OE_EN);
+ config_reg = readl(gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN);
config_reg = MLXBF_I2C_GPIO_SMBUS_GW_RESET_PINS(priv->bus,
config_reg);
- mlxbf_i2c_write(gpio_res->io, MLXBF_I2C_GPIO_0_FORCE_OE_EN,
- config_reg);
+ writel(config_reg, gpio_res->io + MLXBF_I2C_GPIO_0_FORCE_OE_EN);
mutex_unlock(gpio_res->lock);
u32 corepll_val;
u16 core_f;
- pad_frequency = MLXBF_I2C_TYU_PLL_IN_FREQ;
+ pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
- corepll_val = mlxbf_i2c_read(corepll_res->io,
- MLXBF_I2C_CORE_PLL_REG1);
+ corepll_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
/* Get Core PLL configuration bits. */
core_f = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT) &
u8 core_od, core_r;
u32 core_f;
- pad_frequency = MLXBF_I2C_YU_PLL_IN_FREQ;
+ pad_frequency = MLXBF_I2C_PLL_IN_FREQ;
- corepll_reg1_val = mlxbf_i2c_read(corepll_res->io,
- MLXBF_I2C_CORE_PLL_REG1);
- corepll_reg2_val = mlxbf_i2c_read(corepll_res->io,
- MLXBF_I2C_CORE_PLL_REG2);
+ corepll_reg1_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1);
+ corepll_reg2_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG2);
/* Get Core PLL configuration bits */
core_f = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT) &
* (7-bit address, 1 status bit (1 if enabled, 0 if not)).
*/
for (reg = 0; reg < reg_cnt; reg++) {
- slave_reg = mlxbf_i2c_read(priv->smbus->io,
+ slave_reg = readl(priv->smbus->io +
MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4);
/*
* Each register holds 4 slave addresses. So, we have to keep
/* Enable the slave address and update the register. */
slave_reg |= (1 << MLXBF_I2C_SMBUS_SLAVE_ADDR_EN_BIT) << (byte * 8);
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg);
+ writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG +
+ reg * 0x4);
return 0;
}
* (7-bit address, 1 status bit (1 if enabled, 0 if not)).
*/
for (reg = 0; reg < reg_cnt; reg++) {
- slave_reg = mlxbf_i2c_read(priv->smbus->io,
+ slave_reg = readl(priv->smbus->io +
MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4);
/* Check whether the address slots are empty. */
/* Cleanup the slave address slot. */
slave_reg &= ~(GENMASK(7, 0) << (slave_byte * 8));
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG + reg * 0x4, slave_reg);
+ writel(slave_reg, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_ADDR_CFG +
+ reg * 0x4);
return 0;
}
return -EFAULT;
coalesce_res->io = ioremap(params->start, size);
- if (IS_ERR(coalesce_res->io)) {
+ if (!coalesce_res->io) {
release_mem_region(params->start, size);
- return PTR_ERR(coalesce_res->io);
+ return -ENOMEM;
}
priv->coalesce = coalesce_res;
int ret;
/* Reset FSM. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_FSM, 0);
+ writel(0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_FSM);
/*
* Enable slave cause interrupt bits. Drive
* masters issue a Read and Write, respectively. But, clear all
* interrupts first.
*/
- mlxbf_i2c_write(priv->slv_cause->io,
- MLXBF_I2C_CAUSE_OR_CLEAR, ~0);
+ writel(~0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
int_reg = MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE;
int_reg |= MLXBF_I2C_CAUSE_WRITE_SUCCESS;
- mlxbf_i2c_write(priv->slv_cause->io,
- MLXBF_I2C_CAUSE_OR_EVTEN0, int_reg);
+ writel(int_reg, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_EVTEN0);
/* Finally, set the 'ready' bit to start handling transactions. */
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+ writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
/* Initialize the cause coalesce resource. */
ret = mlxbf_i2c_init_coalesce(pdev, priv);
MLXBF_I2C_CAUSE_YU_SLAVE_BIT :
priv->bus + MLXBF_I2C_CAUSE_TYU_SLAVE_BIT;
- coalesce0_reg = mlxbf_i2c_read(priv->coalesce->io,
- MLXBF_I2C_CAUSE_COALESCE_0);
+ coalesce0_reg = readl(priv->coalesce->io + MLXBF_I2C_CAUSE_COALESCE_0);
is_set = coalesce0_reg & (1 << slave_shift);
if (!is_set)
return false;
/* Check the source of the interrupt, i.e. whether a Read or Write. */
- cause_reg = mlxbf_i2c_read(priv->slv_cause->io,
- MLXBF_I2C_CAUSE_ARBITER);
+ cause_reg = readl(priv->slv_cause->io + MLXBF_I2C_CAUSE_ARBITER);
if (cause_reg & MLXBF_I2C_CAUSE_READ_WAIT_FW_RESPONSE)
*read = true;
else if (cause_reg & MLXBF_I2C_CAUSE_WRITE_SUCCESS)
*write = true;
/* Clear cause bits. */
- mlxbf_i2c_write(priv->slv_cause->io, MLXBF_I2C_CAUSE_OR_CLEAR, ~0x0);
+ writel(~0x0, priv->slv_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR);
return true;
}
* address, if supplied.
*/
if (recv_bytes > 0) {
- data32 = mlxbf_i2c_read_data(priv->smbus->io,
- MLXBF_I2C_SLAVE_DATA_DESC_ADDR);
+ data32 = ioread32be(priv->smbus->io +
+ MLXBF_I2C_SLAVE_DATA_DESC_ADDR);
/* Parse the received bytes. */
switch (recv_bytes) {
control32 |= rol32(write_size, MLXBF_I2C_SLAVE_WRITE_BYTES_SHIFT);
control32 |= rol32(pec_en, MLXBF_I2C_SLAVE_SEND_PEC_SHIFT);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_GW, control32);
+ writel(control32, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_GW);
/*
* Wait until the transfer is completed; the driver will wait
mlxbf_smbus_slave_wait_for_idle(priv, MLXBF_I2C_SMBUS_TIMEOUT);
/* Release the Slave GW. */
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC);
+ writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
return 0;
}
i2c_slave_event(slave, I2C_SLAVE_STOP, &value);
/* Release the Slave GW. */
- mlxbf_i2c_write(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_PEC, 0x0);
- mlxbf_i2c_write(priv->smbus->io, MLXBF_I2C_SMBUS_SLAVE_READY, 0x1);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_PEC);
+ writel(0x1, priv->smbus->io + MLXBF_I2C_SMBUS_SLAVE_READY);
return ret;
}
* slave, if the higher 8 bits are sent then the slave expect N bytes
* from the master.
*/
- rw_bytes_reg = mlxbf_i2c_read(priv->smbus->io,
- MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
+ rw_bytes_reg = readl(priv->smbus->io +
+ MLXBF_I2C_SMBUS_SLAVE_RS_MASTER_BYTES);
recv_bytes = (rw_bytes_reg >> 8) & GENMASK(7, 0);
/*
MODULE_DEVICE_TABLE(of, mlxbf_i2c_dt_ids);
+#ifdef CONFIG_ACPI
static const struct acpi_device_id mlxbf_i2c_acpi_ids[] = {
{ "MLNXBF03", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_1] },
{ "MLNXBF23", (kernel_ulong_t)&mlxbf_i2c_chip[MLXBF_I2C_CHIP_TYPE_2] },
return ret;
}
+#else
+static int mlxbf_i2c_acpi_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
+{
+ return -ENOENT;
+}
+#endif /* CONFIG_ACPI */
static int mlxbf_i2c_of_probe(struct device *dev, struct mlxbf_i2c_priv *priv)
{
.driver = {
.name = "i2c-mlxbf",
.of_match_table = mlxbf_i2c_dt_ids,
+#ifdef CONFIG_ACPI
.acpi_match_table = ACPI_PTR(mlxbf_i2c_acpi_ids),
+#endif /* CONFIG_ACPI */
},
};
module_exit(mlxbf_i2c_exit);
MODULE_DESCRIPTION("Mellanox BlueField I2C bus driver");
-MODULE_AUTHOR("Khalil Blaiech <kblaiech@mellanox.com>");
+MODULE_AUTHOR("Khalil Blaiech <kblaiech@nvidia.com>");
MODULE_LICENSE("GPL v2");
{
u16 control_reg;
+ writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
+ udelay(50);
+ writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+
mtk_i2c_writew(i2c, I2C_SOFT_RST, OFFSET_SOFTRESET);
/* Set ioconfig */
mtk_i2c_writew(i2c, control_reg, OFFSET_CONTROL);
mtk_i2c_writew(i2c, I2C_DELAY_LEN, OFFSET_DELAY_LEN);
-
- writel(I2C_DMA_HARD_RST, i2c->pdmabase + OFFSET_RST);
- udelay(50);
- writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
}
static const struct i2c_spec_values *mtk_i2c_get_spec(unsigned int speed)
if (unlikely(val & CCI_IRQ_STATUS_0_I2C_M1_ERROR)) {
if (val & CCI_IRQ_STATUS_0_I2C_M1_Q0_NACK_ERR ||
val & CCI_IRQ_STATUS_0_I2C_M1_Q1_NACK_ERR)
- cci->master[0].status = -ENXIO;
+ cci->master[1].status = -ENXIO;
else
- cci->master[0].status = -EIO;
+ cci->master[1].status = -EIO;
writel(CCI_HALT_REQ_I2C_M1_Q0Q1, cci->base + CCI_HALT_REQ);
ret = IRQ_HANDLED;
if (ret || qup->bus_err || qup->qup_err) {
reinit_completion(&qup->xfer);
- if (qup_i2c_change_state(qup, QUP_RUN_STATE)) {
+ ret = qup_i2c_change_state(qup, QUP_RUN_STATE);
+ if (ret) {
dev_err(qup->dev, "change to run state timed out");
goto desc_err;
}
int sr;
bool send_stop;
bool stop_after_dma;
+ bool atomic_xfer;
struct resource *res;
struct dma_chan *dma_tx;
ret = iic_rd(pd, ICDR);
break;
case OP_RX_STOP: /* enable DTE interrupt, issue stop */
- iic_wr(pd, ICIC,
- ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
+ if (!pd->atomic_xfer)
+ iic_wr(pd, ICIC,
+ ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK);
break;
case OP_RX_STOP_DATA: /* enable DTE interrupt, read data, issue stop */
- iic_wr(pd, ICIC,
- ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
+ if (!pd->atomic_xfer)
+ iic_wr(pd, ICIC,
+ ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE);
ret = iic_rd(pd, ICDR);
iic_wr(pd, ICCR, ICCR_ICE | ICCR_RACK);
break;
if (wakeup) {
pd->sr |= SW_DONE;
- wake_up(&pd->wait);
+ if (!pd->atomic_xfer)
+ wake_up(&pd->wait);
}
/* defeat write posting to avoid spurious WAIT interrupts */
pd->pos = -1;
pd->sr = 0;
+ if (pd->atomic_xfer)
+ return;
+
pd->dma_buf = i2c_get_dma_safe_msg_buf(pd->msg, 8);
if (pd->dma_buf)
sh_mobile_i2c_xfer_dma(pd);
return i ? 0 : -ETIMEDOUT;
}
-static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter,
- struct i2c_msg *msgs,
- int num)
+static int sh_mobile_xfer(struct sh_mobile_i2c_data *pd,
+ struct i2c_msg *msgs, int num)
{
- struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
struct i2c_msg *msg;
int err = 0;
int i;
- long timeout;
+ long time_left;
/* Wake up device and enable clock */
pm_runtime_get_sync(pd->dev);
if (do_start)
i2c_op(pd, OP_START);
- /* The interrupt handler takes care of the rest... */
- timeout = wait_event_timeout(pd->wait,
- pd->sr & (ICSR_TACK | SW_DONE),
- adapter->timeout);
-
- /* 'stop_after_dma' tells if DMA transfer was complete */
- i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg, pd->stop_after_dma);
+ if (pd->atomic_xfer) {
+ unsigned long j = jiffies + pd->adap.timeout;
+
+ time_left = time_before_eq(jiffies, j);
+ while (time_left &&
+ !(pd->sr & (ICSR_TACK | SW_DONE))) {
+ unsigned char sr = iic_rd(pd, ICSR);
+
+ if (sr & (ICSR_AL | ICSR_TACK |
+ ICSR_WAIT | ICSR_DTE)) {
+ sh_mobile_i2c_isr(0, pd);
+ udelay(150);
+ } else {
+ cpu_relax();
+ }
+ time_left = time_before_eq(jiffies, j);
+ }
+ } else {
+ /* The interrupt handler takes care of the rest... */
+ time_left = wait_event_timeout(pd->wait,
+ pd->sr & (ICSR_TACK | SW_DONE),
+ pd->adap.timeout);
+
+ /* 'stop_after_dma' tells if DMA xfer was complete */
+ i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg,
+ pd->stop_after_dma);
+ }
- if (!timeout) {
+ if (!time_left) {
dev_err(pd->dev, "Transfer request timed out\n");
if (pd->dma_direction != DMA_NONE)
sh_mobile_i2c_cleanup_dma(pd);
return err ?: num;
}
+static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter,
+ struct i2c_msg *msgs,
+ int num)
+{
+ struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
+
+ pd->atomic_xfer = false;
+ return sh_mobile_xfer(pd, msgs, num);
+}
+
+static int sh_mobile_i2c_xfer_atomic(struct i2c_adapter *adapter,
+ struct i2c_msg *msgs,
+ int num)
+{
+ struct sh_mobile_i2c_data *pd = i2c_get_adapdata(adapter);
+
+ pd->atomic_xfer = true;
+ return sh_mobile_xfer(pd, msgs, num);
+}
+
static u32 sh_mobile_i2c_func(struct i2c_adapter *adapter)
{
return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING;
}
static const struct i2c_algorithm sh_mobile_i2c_algorithm = {
- .functionality = sh_mobile_i2c_func,
- .master_xfer = sh_mobile_i2c_xfer,
+ .functionality = sh_mobile_i2c_func,
+ .master_xfer = sh_mobile_i2c_xfer,
+ .master_xfer_atomic = sh_mobile_i2c_xfer_atomic,
};
static const struct i2c_adapter_quirks sh_mobile_i2c_quirks = {
struct cpuidle_state *state = &drv->states[index];
unsigned long eax = flg2MWAIT(state->flags);
unsigned long ecx = 1; /* break on interrupt flag */
- bool tick;
-
- if (!static_cpu_has(X86_FEATURE_ARAT)) {
- /*
- * Switch over to one-shot tick broadcast if the target C-state
- * is deeper than C1.
- */
- if ((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) {
- tick = true;
- tick_broadcast_enter();
- } else {
- tick = false;
- }
- }
mwait_idle_with_hints(eax, ecx);
- if (!static_cpu_has(X86_FEATURE_ARAT) && tick)
- tick_broadcast_exit();
-
return index;
}
return false;
}
+static bool __init intel_idle_state_needs_timer_stop(struct cpuidle_state *state)
+{
+ unsigned long eax = flg2MWAIT(state->flags);
+
+ if (boot_cpu_has(X86_FEATURE_ARAT))
+ return false;
+
+ /*
+ * Switch over to one-shot tick broadcast if the target C-state
+ * is deeper than C1.
+ */
+ return !!((eax >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK);
+}
+
#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
#include <acpi/processor.h>
struct acpi_processor_cx *cx;
struct cpuidle_state *state;
- if (intel_idle_max_cstate_reached(cstate))
+ if (intel_idle_max_cstate_reached(cstate - 1))
break;
cx = &acpi_state_table.states[cstate];
if (disabled_states_mask & BIT(cstate))
state->flags |= CPUIDLE_FLAG_OFF;
+ if (intel_idle_state_needs_timer_stop(state))
+ state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+
state->enter = intel_idle;
state->enter_s2idle = intel_idle_s2idle;
}
!(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_ALWAYS_ENABLE)))
drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF;
+ if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count]))
+ drv->states[drv->state_count].flags |= CPUIDLE_FLAG_TIMER_STOP;
+
drv->state_count++;
}
KX_MAX_CHIPS /* this must be last */
};
+enum kx_acpi_type {
+ ACPI_GENERIC,
+ ACPI_SMO8500,
+ ACPI_KIOX010A,
+};
+
struct kxcjk1013_data {
struct i2c_client *client;
struct iio_trigger *dready_trig;
bool motion_trigger_on;
int64_t timestamp;
enum kx_chipset chipset;
- bool is_smo8500_device;
+ enum kx_acpi_type acpi_type;
};
enum kxcjk1013_axis {
{19163, 1, 0},
{38326, 0, 1} };
+#ifdef CONFIG_ACPI
+enum kiox010a_fn_index {
+ KIOX010A_SET_LAPTOP_MODE = 1,
+ KIOX010A_SET_TABLET_MODE = 2,
+};
+
+static int kiox010a_dsm(struct device *dev, int fn_index)
+{
+ acpi_handle handle = ACPI_HANDLE(dev);
+ guid_t kiox010a_dsm_guid;
+ union acpi_object *obj;
+
+ if (!handle)
+ return -ENODEV;
+
+ guid_parse("1f339696-d475-4e26-8cad-2e9f8e6d7a91", &kiox010a_dsm_guid);
+
+ obj = acpi_evaluate_dsm(handle, &kiox010a_dsm_guid, 1, fn_index, NULL);
+ if (!obj)
+ return -EIO;
+
+ ACPI_FREE(obj);
+ return 0;
+}
+#endif
+
static int kxcjk1013_set_mode(struct kxcjk1013_data *data,
enum kxcjk1013_mode mode)
{
{
int ret;
+#ifdef CONFIG_ACPI
+ if (data->acpi_type == ACPI_KIOX010A) {
+ /* Make sure the kbd and touchpad on 2-in-1s using 2 KXCJ91008-s work */
+ kiox010a_dsm(&data->client->dev, KIOX010A_SET_LAPTOP_MODE);
+ }
+#endif
+
ret = i2c_smbus_read_byte_data(data->client, KXCJK1013_REG_WHO_AM_I);
if (ret < 0) {
dev_err(&data->client->dev, "Error reading who_am_i\n");
static const char *kxcjk1013_match_acpi_device(struct device *dev,
enum kx_chipset *chipset,
- bool *is_smo8500_device)
+ enum kx_acpi_type *acpi_type)
{
const struct acpi_device_id *id;
return NULL;
if (strcmp(id->id, "SMO8500") == 0)
- *is_smo8500_device = true;
+ *acpi_type = ACPI_SMO8500;
+ else if (strcmp(id->id, "KIOX010A") == 0)
+ *acpi_type = ACPI_KIOX010A;
*chipset = (enum kx_chipset)id->driver_data;
} else if (ACPI_HANDLE(&client->dev)) {
name = kxcjk1013_match_acpi_device(&client->dev,
&data->chipset,
- &data->is_smo8500_device);
+ &data->acpi_type);
} else
return -ENODEV;
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->info = &kxcjk1013_info;
- if (client->irq > 0 && !data->is_smo8500_device) {
+ if (client->irq > 0 && data->acpi_type != ACPI_SMO8500) {
ret = devm_request_threaded_irq(&client->dev, client->irq,
kxcjk1013_data_rdy_trig_poll,
kxcjk1013_event_handler,
#define JZ4725B_ADC_BATTERY_HIGH_VREF_BITS 10
#define JZ4740_ADC_BATTERY_HIGH_VREF (7500 * 0.986)
#define JZ4740_ADC_BATTERY_HIGH_VREF_BITS 12
-#define JZ4770_ADC_BATTERY_VREF 6600
+#define JZ4770_ADC_BATTERY_VREF 1200
#define JZ4770_ADC_BATTERY_VREF_BITS 12
#define JZ_ADC_IRQ_AUX BIT(0)
mutex_unlock(&adc->lock);
}
-static void ingenic_adc_enable(struct ingenic_adc *adc,
- int engine,
- bool enabled)
+static void ingenic_adc_enable_unlocked(struct ingenic_adc *adc,
+ int engine,
+ bool enabled)
{
u8 val;
- mutex_lock(&adc->lock);
val = readb(adc->base + JZ_ADC_REG_ENABLE);
if (enabled)
val &= ~BIT(engine);
writeb(val, adc->base + JZ_ADC_REG_ENABLE);
+}
+
+static void ingenic_adc_enable(struct ingenic_adc *adc,
+ int engine,
+ bool enabled)
+{
+ mutex_lock(&adc->lock);
+ ingenic_adc_enable_unlocked(adc, engine, enabled);
mutex_unlock(&adc->lock);
}
static int ingenic_adc_capture(struct ingenic_adc *adc,
int engine)
{
+ u32 cfg;
u8 val;
int ret;
- ingenic_adc_enable(adc, engine, true);
+ /*
+ * Disable CMD_SEL temporarily, because it causes wrong VBAT readings,
+ * probably due to the switch of VREF. We must keep the lock here to
+ * avoid races with the buffer enable/disable functions.
+ */
+ mutex_lock(&adc->lock);
+ cfg = readl(adc->base + JZ_ADC_REG_CFG);
+ writel(cfg & ~JZ_ADC_REG_CFG_CMD_SEL, adc->base + JZ_ADC_REG_CFG);
+
+ ingenic_adc_enable_unlocked(adc, engine, true);
ret = readb_poll_timeout(adc->base + JZ_ADC_REG_ENABLE, val,
!(val & BIT(engine)), 250, 1000);
if (ret)
- ingenic_adc_enable(adc, engine, false);
+ ingenic_adc_enable_unlocked(adc, engine, false);
+
+ writel(cfg, adc->base + JZ_ADC_REG_CFG);
+ mutex_unlock(&adc->lock);
return ret;
}
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/mod_devicetable.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <linux/iopoll.h>
#include <linux/io.h>
#include <linux/iio/iio.h>
goto err_disable_clk;
}
+ adc_dev->dev_comp = device_get_match_data(&pdev->dev);
+
mutex_init(&adc_dev->lock);
mt6577_auxadc_mod_reg(adc_dev->reg_base + MT6577_AUXADC_MISC,
* struct stm32_adc_common_regs - stm32 common registers
* @csr: common status register offset
* @ccr: common control register offset
- * @eoc1_msk: adc1 end of conversion flag in @csr
- * @eoc2_msk: adc2 end of conversion flag in @csr
- * @eoc3_msk: adc3 end of conversion flag in @csr
+ * @eoc_msk: array of eoc (end of conversion flag) masks in csr for adc1..n
+ * @ovr_msk: array of ovr (overrun flag) masks in csr for adc1..n
* @ier: interrupt enable register offset for each adc
* @eocie_msk: end of conversion interrupt enable mask in @ier
*/
struct stm32_adc_common_regs {
u32 csr;
u32 ccr;
- u32 eoc1_msk;
- u32 eoc2_msk;
- u32 eoc3_msk;
+ u32 eoc_msk[STM32_ADC_MAX_ADCS];
+ u32 ovr_msk[STM32_ADC_MAX_ADCS];
u32 ier;
u32 eocie_msk;
};
static const struct stm32_adc_common_regs stm32f4_adc_common_regs = {
.csr = STM32F4_ADC_CSR,
.ccr = STM32F4_ADC_CCR,
- .eoc1_msk = STM32F4_EOC1 | STM32F4_OVR1,
- .eoc2_msk = STM32F4_EOC2 | STM32F4_OVR2,
- .eoc3_msk = STM32F4_EOC3 | STM32F4_OVR3,
+ .eoc_msk = { STM32F4_EOC1, STM32F4_EOC2, STM32F4_EOC3},
+ .ovr_msk = { STM32F4_OVR1, STM32F4_OVR2, STM32F4_OVR3},
.ier = STM32F4_ADC_CR1,
- .eocie_msk = STM32F4_EOCIE | STM32F4_OVRIE,
+ .eocie_msk = STM32F4_EOCIE,
};
/* STM32H7 common registers definitions */
static const struct stm32_adc_common_regs stm32h7_adc_common_regs = {
.csr = STM32H7_ADC_CSR,
.ccr = STM32H7_ADC_CCR,
- .eoc1_msk = STM32H7_EOC_MST | STM32H7_OVR_MST,
- .eoc2_msk = STM32H7_EOC_SLV | STM32H7_OVR_SLV,
+ .eoc_msk = { STM32H7_EOC_MST, STM32H7_EOC_SLV},
+ .ovr_msk = { STM32H7_OVR_MST, STM32H7_OVR_SLV},
.ier = STM32H7_ADC_IER,
- .eocie_msk = STM32H7_EOCIE | STM32H7_OVRIE,
+ .eocie_msk = STM32H7_EOCIE,
};
static const unsigned int stm32_adc_offset[STM32_ADC_MAX_ADCS] = {
{
struct stm32_adc_priv *priv = irq_desc_get_handler_data(desc);
struct irq_chip *chip = irq_desc_get_chip(desc);
+ int i;
u32 status;
chained_irq_enter(chip, desc);
* before invoking the interrupt handler (e.g. call ISR only for
* IRQ-enabled ADCs).
*/
- if (status & priv->cfg->regs->eoc1_msk &&
- stm32_adc_eoc_enabled(priv, 0))
- generic_handle_irq(irq_find_mapping(priv->domain, 0));
-
- if (status & priv->cfg->regs->eoc2_msk &&
- stm32_adc_eoc_enabled(priv, 1))
- generic_handle_irq(irq_find_mapping(priv->domain, 1));
-
- if (status & priv->cfg->regs->eoc3_msk &&
- stm32_adc_eoc_enabled(priv, 2))
- generic_handle_irq(irq_find_mapping(priv->domain, 2));
+ for (i = 0; i < priv->cfg->num_irqs; i++) {
+ if ((status & priv->cfg->regs->eoc_msk[i] &&
+ stm32_adc_eoc_enabled(priv, i)) ||
+ (status & priv->cfg->regs->ovr_msk[i]))
+ generic_handle_irq(irq_find_mapping(priv->domain, i));
+ }
chained_irq_exit(chip, desc);
};
* @start_conv: routine to start conversions
* @stop_conv: routine to stop conversions
* @unprepare: optional unprepare routine (disable, power-down)
+ * @irq_clear: routine to clear irqs
* @smp_cycles: programmable sampling time (ADC clock cycles)
*/
struct stm32_adc_cfg {
void (*start_conv)(struct iio_dev *, bool dma);
void (*stop_conv)(struct iio_dev *);
void (*unprepare)(struct iio_dev *);
+ void (*irq_clear)(struct iio_dev *indio_dev, u32 msk);
const unsigned int *smp_cycles;
};
STM32F4_ADON | STM32F4_DMA | STM32F4_DDS);
}
+static void stm32f4_adc_irq_clear(struct iio_dev *indio_dev, u32 msk)
+{
+ struct stm32_adc *adc = iio_priv(indio_dev);
+
+ stm32_adc_clr_bits(adc, adc->cfg->regs->isr_eoc.reg, msk);
+}
+
static void stm32h7_adc_start_conv(struct iio_dev *indio_dev, bool dma)
{
struct stm32_adc *adc = iio_priv(indio_dev);
stm32_adc_clr_bits(adc, STM32H7_ADC_CFGR, STM32H7_DMNGT_MASK);
}
+static void stm32h7_adc_irq_clear(struct iio_dev *indio_dev, u32 msk)
+{
+ struct stm32_adc *adc = iio_priv(indio_dev);
+ /* On STM32H7 IRQs are cleared by writing 1 into ISR register */
+ stm32_adc_set_bits(adc, adc->cfg->regs->isr_eoc.reg, msk);
+}
+
static int stm32h7_adc_exit_pwr_down(struct iio_dev *indio_dev)
{
struct stm32_adc *adc = iio_priv(indio_dev);
}
}
+static void stm32_adc_irq_clear(struct iio_dev *indio_dev, u32 msk)
+{
+ struct stm32_adc *adc = iio_priv(indio_dev);
+
+ adc->cfg->irq_clear(indio_dev, msk);
+}
+
static irqreturn_t stm32_adc_threaded_isr(int irq, void *data)
{
struct iio_dev *indio_dev = data;
struct stm32_adc *adc = iio_priv(indio_dev);
const struct stm32_adc_regspec *regs = adc->cfg->regs;
u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg);
+ u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg);
- if (status & regs->isr_ovr.mask)
+ /* Check ovr status right now, as ovr mask should be already disabled */
+ if (status & regs->isr_ovr.mask) {
+ /*
+ * Clear ovr bit to avoid subsequent calls to IRQ handler.
+ * This requires to stop ADC first. OVR bit state in ISR,
+ * is propaged to CSR register by hardware.
+ */
+ adc->cfg->stop_conv(indio_dev);
+ stm32_adc_irq_clear(indio_dev, regs->isr_ovr.mask);
dev_err(&indio_dev->dev, "Overrun, stopping: restart needed\n");
+ return IRQ_HANDLED;
+ }
- return IRQ_HANDLED;
+ if (!(status & mask))
+ dev_err_ratelimited(&indio_dev->dev,
+ "Unexpected IRQ: IER=0x%08x, ISR=0x%08x\n",
+ mask, status);
+
+ return IRQ_NONE;
}
static irqreturn_t stm32_adc_isr(int irq, void *data)
struct stm32_adc *adc = iio_priv(indio_dev);
const struct stm32_adc_regspec *regs = adc->cfg->regs;
u32 status = stm32_adc_readl(adc, regs->isr_eoc.reg);
+ u32 mask = stm32_adc_readl(adc, regs->ier_eoc.reg);
+
+ if (!(status & mask))
+ return IRQ_WAKE_THREAD;
if (status & regs->isr_ovr.mask) {
/*
.start_conv = stm32f4_adc_start_conv,
.stop_conv = stm32f4_adc_stop_conv,
.smp_cycles = stm32f4_adc_smp_cycles,
+ .irq_clear = stm32f4_adc_irq_clear,
};
static const struct stm32_adc_cfg stm32h7_adc_cfg = {
.prepare = stm32h7_adc_prepare,
.unprepare = stm32h7_adc_unprepare,
.smp_cycles = stm32h7_adc_smp_cycles,
+ .irq_clear = stm32h7_adc_irq_clear,
};
static const struct stm32_adc_cfg stm32mp1_adc_cfg = {
.prepare = stm32h7_adc_prepare,
.unprepare = stm32h7_adc_unprepare,
.smp_cycles = stm32h7_adc_smp_cycles,
+ .irq_clear = stm32h7_adc_irq_clear,
};
static const struct of_device_id stm32_adc_of_match[] = {
struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent);
struct cros_ec_dev *ec = sensor_hub->ec;
struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev);
- u32 ver_mask;
+ u32 ver_mask, temp;
int frequencies[ARRAY_SIZE(state->frequencies) / 2] = { 0 };
int ret, i;
&frequencies[2],
&state->fifo_max_event_count);
} else {
- frequencies[1] = state->resp->info_3.min_frequency;
- frequencies[2] = state->resp->info_3.max_frequency;
- state->fifo_max_event_count =
- state->resp->info_3.fifo_max_event_count;
+ if (state->resp->info_3.max_frequency == 0) {
+ get_default_min_max_freq(state->resp->info.type,
+ &frequencies[1],
+ &frequencies[2],
+ &temp);
+ } else {
+ frequencies[1] = state->resp->info_3.min_frequency;
+ frequencies[2] = state->resp->info_3.max_frequency;
+ }
+ state->fifo_max_event_count = state->resp->info_3.fifo_max_event_count;
}
for (i = 0; i < ARRAY_SIZE(frequencies); i++) {
state->frequencies[2 * i] = frequencies[i] / 1000;
static void st_lsm6dsx_shub_wait_complete(struct st_lsm6dsx_hw *hw)
{
struct st_lsm6dsx_sensor *sensor;
- u32 odr;
+ u32 odr, timeout;
sensor = iio_priv(hw->iio_devs[ST_LSM6DSX_ID_ACC]);
odr = (hw->enable_mask & BIT(ST_LSM6DSX_ID_ACC)) ? sensor->odr : 12500;
- msleep((2000000U / odr) + 1);
+ /* set 10ms as minimum timeout for i2c slave configuration */
+ timeout = max_t(u32, 2000000U / odr + 1, 10);
+ msleep(timeout);
}
/*
config VCNL4035
tristate "VCNL4035 combined ALS and proximity sensor"
+ select IIO_BUFFER
select IIO_TRIGGERED_BUFFER
select REGMAP_I2C
depends on I2C
This allows the user to config the default GID type that the CM
uses for each device, when initiaing new connections.
+config INFINIBAND_VIRT_DMA
+ def_bool !HIGHMEM
+
if INFINIBAND_USER_ACCESS || !INFINIBAND_USER_ACCESS
source "drivers/infiniband/hw/mthca/Kconfig"
source "drivers/infiniband/hw/qib/Kconfig"
atomic_set(&cm_id_priv->work_count, -1);
refcount_set(&cm_id_priv->refcount, 1);
- ret = xa_alloc_cyclic_irq(&cm.local_id_table, &id, NULL, xa_limit_32b,
- &cm.local_id_next, GFP_KERNEL);
+ ret = xa_alloc_cyclic(&cm.local_id_table, &id, NULL, xa_limit_32b,
+ &cm.local_id_next, GFP_KERNEL);
if (ret < 0)
goto error;
cm_id_priv->id.local_id = (__force __be32)id ^ cm.random_id_operand;
*/
static void cm_finalize_id(struct cm_id_private *cm_id_priv)
{
- xa_store_irq(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id),
- cm_id_priv, GFP_KERNEL);
+ xa_store(&cm.local_id_table, cm_local_id(cm_id_priv->id.local_id),
+ cm_id_priv, GFP_ATOMIC);
}
struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
spin_unlock(&cm.lock);
spin_unlock_irq(&cm_id_priv->lock);
- xa_erase_irq(&cm.local_id_table, cm_local_id(cm_id->local_id));
+ xa_erase(&cm.local_id_table, cm_local_id(cm_id->local_id));
cm_deref_id(cm_id_priv);
wait_for_completion(&cm_id_priv->comp);
while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
cm.remote_id_table = RB_ROOT;
cm.remote_qp_table = RB_ROOT;
cm.remote_sidr_table = RB_ROOT;
- xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
+ xa_init_flags(&cm.local_id_table, XA_FLAGS_ALLOC);
get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand);
INIT_LIST_HEAD(&cm.timewait_list);
/*
* The FSM uses a funny double locking where state is protected by both
* the handler_mutex and the spinlock. State is not allowed to change
- * away from a handler_mutex protected value without also holding
+ * to/from a handler_mutex protected value without also holding
* handler_mutex.
*/
- if (comp == RDMA_CM_CONNECT)
+ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT)
lockdep_assert_held(&id_priv->handler_mutex);
spin_lock_irqsave(&id_priv->lock, flags);
return ret;
}
-int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+/**
+ * rdma_connect_locked - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Same as rdma_connect() but can only be called from the
+ * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback.
+ */
+int rdma_connect_locked(struct rdma_cm_id *id,
+ struct rdma_conn_param *conn_param)
{
struct rdma_id_private *id_priv =
container_of(id, struct rdma_id_private, id);
int ret;
- mutex_lock(&id_priv->handler_mutex);
- if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) {
- ret = -EINVAL;
- goto err_unlock;
- }
+ if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT))
+ return -EINVAL;
if (!id->qp) {
id_priv->qp_num = conn_param->qp_num;
ret = -ENOSYS;
if (ret)
goto err_state;
- mutex_unlock(&id_priv->handler_mutex);
return 0;
err_state:
cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED);
-err_unlock:
+ return ret;
+}
+EXPORT_SYMBOL(rdma_connect_locked);
+
+/**
+ * rdma_connect - Initiate an active connection request.
+ * @id: Connection identifier to connect.
+ * @conn_param: Connection information used for connected QPs.
+ *
+ * Users must have resolved a route for the rdma_cm_id to connect with by having
+ * called rdma_resolve_route before calling this routine.
+ *
+ * This call will either connect to a remote QP or obtain remote QP information
+ * for unconnected rdma_cm_id's. The actual operation is based on the
+ * rdma_cm_id's port space.
+ */
+int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
+{
+ struct rdma_id_private *id_priv =
+ container_of(id, struct rdma_id_private, id);
+ int ret;
+
+ mutex_lock(&id_priv->handler_mutex);
+ ret = rdma_connect_locked(id, conn_param);
mutex_unlock(&id_priv->handler_mutex);
return ret;
}
if (!rdma_is_port_valid(ib_dev, port_num))
return -EINVAL;
- if (!rdma_ib_or_roce(ib_dev, port_num))
- return -EOPNOTSUPP;
-
gid_attr = rdma_get_gid_attr(ib_dev, port_num, gid_index);
if (IS_ERR(gid_attr))
return PTR_ERR(gid_attr);
& CCE_REVISION_SW_MASK);
/* alloc netdev data */
- if (hfi1_netdev_alloc(dd))
+ ret = hfi1_netdev_alloc(dd);
+ if (ret)
goto bail_cleanup;
ret = set_up_context_variables(dd);
/*
+ * Copyright(c) 2020 Cornelis Networks, Inc.
* Copyright(c) 2015-2020 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
spin_lock_init(&fd->tid_lock);
spin_lock_init(&fd->invalid_lock);
fd->rec_cpu_num = -1; /* no cpu affinity by default */
- fd->mm = current->mm;
- mmgrab(fd->mm);
fd->dd = dd;
fp->private_data = fd;
return 0;
deallocate_ctxt(uctxt);
done:
- mmdrop(fdata->mm);
if (atomic_dec_and_test(&dd->user_refcount))
complete(&dd->user_comp);
#ifndef _HFI1_KERNEL_H
#define _HFI1_KERNEL_H
/*
+ * Copyright(c) 2020 Cornelis Networks, Inc.
* Copyright(c) 2015-2020 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
u32 invalid_tid_idx;
/* protect invalid_tids array and invalid_tid_idx */
spinlock_t invalid_lock;
- struct mm_struct *mm;
};
extern struct xarray hfi1_dev_table;
/*
+ * Copyright(c) 2020 Cornelis Networks, Inc.
* Copyright(c) 2016 - 2017 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
#include <linux/rculist.h>
#include <linux/mmu_notifier.h>
#include <linux/interval_tree_generic.h>
+#include <linux/sched/mm.h>
#include "mmu_rb.h"
#include "trace.h"
-struct mmu_rb_handler {
- struct mmu_notifier mn;
- struct rb_root_cached root;
- void *ops_arg;
- spinlock_t lock; /* protect the RB tree */
- struct mmu_rb_ops *ops;
- struct mm_struct *mm;
- struct list_head lru_list;
- struct work_struct del_work;
- struct list_head del_list;
- struct workqueue_struct *wq;
-};
-
static unsigned long mmu_node_start(struct mmu_rb_node *);
static unsigned long mmu_node_last(struct mmu_rb_node *);
static int mmu_notifier_range_start(struct mmu_notifier *,
return PAGE_ALIGN(node->addr + node->len) - 1;
}
-int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm,
+int hfi1_mmu_rb_register(void *ops_arg,
struct mmu_rb_ops *ops,
struct workqueue_struct *wq,
struct mmu_rb_handler **handler)
{
- struct mmu_rb_handler *handlr;
+ struct mmu_rb_handler *h;
int ret;
- handlr = kmalloc(sizeof(*handlr), GFP_KERNEL);
- if (!handlr)
+ h = kmalloc(sizeof(*h), GFP_KERNEL);
+ if (!h)
return -ENOMEM;
- handlr->root = RB_ROOT_CACHED;
- handlr->ops = ops;
- handlr->ops_arg = ops_arg;
- INIT_HLIST_NODE(&handlr->mn.hlist);
- spin_lock_init(&handlr->lock);
- handlr->mn.ops = &mn_opts;
- handlr->mm = mm;
- INIT_WORK(&handlr->del_work, handle_remove);
- INIT_LIST_HEAD(&handlr->del_list);
- INIT_LIST_HEAD(&handlr->lru_list);
- handlr->wq = wq;
-
- ret = mmu_notifier_register(&handlr->mn, handlr->mm);
+ h->root = RB_ROOT_CACHED;
+ h->ops = ops;
+ h->ops_arg = ops_arg;
+ INIT_HLIST_NODE(&h->mn.hlist);
+ spin_lock_init(&h->lock);
+ h->mn.ops = &mn_opts;
+ INIT_WORK(&h->del_work, handle_remove);
+ INIT_LIST_HEAD(&h->del_list);
+ INIT_LIST_HEAD(&h->lru_list);
+ h->wq = wq;
+
+ ret = mmu_notifier_register(&h->mn, current->mm);
if (ret) {
- kfree(handlr);
+ kfree(h);
return ret;
}
- *handler = handlr;
+ *handler = h;
return 0;
}
struct list_head del_list;
/* Unregister first so we don't get any more notifications. */
- mmu_notifier_unregister(&handler->mn, handler->mm);
+ mmu_notifier_unregister(&handler->mn, handler->mn.mm);
/*
* Make sure the wq delete handler is finished running. It will not
int ret = 0;
trace_hfi1_mmu_rb_insert(mnode->addr, mnode->len);
+
+ if (current->mm != handler->mn.mm)
+ return -EPERM;
+
spin_lock_irqsave(&handler->lock, flags);
node = __mmu_rb_search(handler, mnode->addr, mnode->len);
if (node) {
__mmu_int_rb_remove(mnode, &handler->root);
list_del(&mnode->list); /* remove from LRU list */
}
+ mnode->handler = handler;
unlock:
spin_unlock_irqrestore(&handler->lock, flags);
return ret;
unsigned long flags;
bool ret = false;
+ if (current->mm != handler->mn.mm)
+ return ret;
+
spin_lock_irqsave(&handler->lock, flags);
node = __mmu_rb_search(handler, addr, len);
if (node) {
unsigned long flags;
bool stop = false;
+ if (current->mm != handler->mn.mm)
+ return;
+
INIT_LIST_HEAD(&del_list);
spin_lock_irqsave(&handler->lock, flags);
{
unsigned long flags;
+ if (current->mm != handler->mn.mm)
+ return;
+
/* Validity of handler and node pointers has been checked by caller. */
trace_hfi1_mmu_rb_remove(node->addr, node->len);
spin_lock_irqsave(&handler->lock, flags);
/*
+ * Copyright(c) 2020 Cornelis Networks, Inc.
* Copyright(c) 2016 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
unsigned long len;
unsigned long __last;
struct rb_node node;
+ struct mmu_rb_handler *handler;
struct list_head list;
};
void *evict_arg, bool *stop);
};
-int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm,
+struct mmu_rb_handler {
+ struct mmu_notifier mn;
+ struct rb_root_cached root;
+ void *ops_arg;
+ spinlock_t lock; /* protect the RB tree */
+ struct mmu_rb_ops *ops;
+ struct list_head lru_list;
+ struct work_struct del_work;
+ struct list_head del_list;
+ struct workqueue_struct *wq;
+};
+
+int hfi1_mmu_rb_register(void *ops_arg,
struct mmu_rb_ops *ops,
struct workqueue_struct *wq,
struct mmu_rb_handler **handler);
/*
+ * Copyright(c) 2020 Cornelis Networks, Inc.
* Copyright(c) 2015-2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
{
struct page **pages;
struct hfi1_devdata *dd = fd->uctxt->dd;
+ struct mm_struct *mm;
if (mapped) {
pci_unmap_single(dd->pcidev, node->dma_addr,
node->npages * PAGE_SIZE, PCI_DMA_FROMDEVICE);
pages = &node->pages[idx];
+ mm = mm_from_tid_node(node);
} else {
pages = &tidbuf->pages[idx];
+ mm = current->mm;
}
- hfi1_release_user_pages(fd->mm, pages, npages, mapped);
+ hfi1_release_user_pages(mm, pages, npages, mapped);
fd->tid_n_pinned -= npages;
}
* pages, accept the amount pinned so far and program only that.
* User space knows how to deal with partially programmed buffers.
*/
- if (!hfi1_can_pin_pages(dd, fd->mm, fd->tid_n_pinned, npages)) {
+ if (!hfi1_can_pin_pages(dd, current->mm, fd->tid_n_pinned, npages)) {
kfree(pages);
return -ENOMEM;
}
- pinned = hfi1_acquire_user_pages(fd->mm, vaddr, npages, true, pages);
+ pinned = hfi1_acquire_user_pages(current->mm, vaddr, npages, true, pages);
if (pinned <= 0) {
kfree(pages);
return pinned;
if (fd->use_mn) {
ret = mmu_interval_notifier_insert(
- &node->notifier, fd->mm,
+ &node->notifier, current->mm,
tbuf->vaddr + (pageidx * PAGE_SIZE), npages * PAGE_SIZE,
&tid_mn_ops);
if (ret)
#ifndef _HFI1_USER_EXP_RCV_H
#define _HFI1_USER_EXP_RCV_H
/*
+ * Copyright(c) 2020 - Cornelis Networks, Inc.
* Copyright(c) 2015 - 2017 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
int hfi1_user_exp_rcv_invalid(struct hfi1_filedata *fd,
struct hfi1_tid_info *tinfo);
+static inline struct mm_struct *mm_from_tid_node(struct tid_rb_node *node)
+{
+ return node->notifier.mm;
+}
+
#endif /* _HFI1_USER_EXP_RCV_H */
/*
+ * Copyright(c) 2020 - Cornelis Networks, Inc.
* Copyright(c) 2015 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
atomic_set(&pq->n_reqs, 0);
init_waitqueue_head(&pq->wait);
atomic_set(&pq->n_locked, 0);
- pq->mm = fd->mm;
iowait_init(&pq->busy, 0, NULL, NULL, defer_packet_queue,
activate_packet_queue, NULL, NULL);
cq->nentries = hfi1_sdma_comp_ring_size;
- ret = hfi1_mmu_rb_register(pq, pq->mm, &sdma_rb_ops, dd->pport->hfi1_wq,
+ ret = hfi1_mmu_rb_register(pq, &sdma_rb_ops, dd->pport->hfi1_wq,
&pq->handler);
if (ret) {
dd_dev_err(dd, "Failed to register with MMU %d", ret);
npages -= node->npages;
retry:
- if (!hfi1_can_pin_pages(pq->dd, pq->mm,
+ if (!hfi1_can_pin_pages(pq->dd, current->mm,
atomic_read(&pq->n_locked), npages)) {
cleared = sdma_cache_evict(pq, npages);
if (cleared >= npages)
goto retry;
}
- pinned = hfi1_acquire_user_pages(pq->mm,
+ pinned = hfi1_acquire_user_pages(current->mm,
((unsigned long)iovec->iov.iov_base +
(node->npages * PAGE_SIZE)), npages, 0,
pages + node->npages);
return pinned;
}
if (pinned != npages) {
- unpin_vector_pages(pq->mm, pages, node->npages, pinned);
+ unpin_vector_pages(current->mm, pages, node->npages, pinned);
return -EFAULT;
}
kfree(node->pages);
static void unpin_sdma_pages(struct sdma_mmu_node *node)
{
if (node->npages) {
- unpin_vector_pages(node->pq->mm, node->pages, 0, node->npages);
+ unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0,
+ node->npages);
atomic_sub(node->npages, &node->pq->n_locked);
}
}
#ifndef _HFI1_USER_SDMA_H
#define _HFI1_USER_SDMA_H
/*
+ * Copyright(c) 2020 - Cornelis Networks, Inc.
* Copyright(c) 2015 - 2018 Intel Corporation.
*
* This file is provided under a dual BSD/GPLv2 license. When using or
unsigned long unpinned;
struct mmu_rb_handler *handler;
atomic_t n_locked;
- struct mm_struct *mm;
};
struct hfi1_user_sdma_comp_q {
struct iovec *iovec, unsigned long dim,
unsigned long *count);
+static inline struct mm_struct *mm_from_sdma_node(struct sdma_mmu_node *node)
+{
+ return node->rb.handler->mn.mm;
+}
+
#endif /* _HFI1_USER_SDMA_H */
roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1);
roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_L_INV_EN_S, 1);
+ roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, 1);
roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, 0);
roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_MR_MW_S, 1);
V2_QPC_BYTE_28_AT_M,
V2_QPC_BYTE_28_AT_S);
qp_attr->retry_cnt = roce_get_field(context.byte_212_lsn,
- V2_QPC_BYTE_212_RETRY_CNT_M,
- V2_QPC_BYTE_212_RETRY_CNT_S);
+ V2_QPC_BYTE_212_RETRY_NUM_INIT_M,
+ V2_QPC_BYTE_212_RETRY_NUM_INIT_S);
qp_attr->rnr_retry = roce_get_field(context.byte_244_rnr_rxack,
- V2_QPC_BYTE_244_RNR_CNT_M,
- V2_QPC_BYTE_244_RNR_CNT_S);
+ V2_QPC_BYTE_244_RNR_NUM_INIT_M,
+ V2_QPC_BYTE_244_RNR_NUM_INIT_S);
done:
qp_attr->cur_qp_state = qp_attr->qp_state;
__le32 rsv_uars_rsv_qps;
};
#define V2_QUERY_PF_CAPS_D_NUM_SRQS_S 0
-#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(20, 0)
+#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(19, 0)
#define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_S 20
#define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_M GENMASK(21, 20)
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." __stringify(DRV_VERSION_BUILD)
-static int push_mode;
-module_param(push_mode, int, 0644);
-MODULE_PARM_DESC(push_mode, "Low latency mode: 0=disabled (default), 1=enabled)");
-
static int debug;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "debug flags: 0=disabled (default), 0x7fffffff=all");
if (status)
goto exit;
iwdev->obj_next = iwdev->obj_mem;
- iwdev->push_mode = push_mode;
init_waitqueue_head(&iwdev->vchnl_waitq);
init_waitqueue_head(&dev->vf_reqs);
*/
static int i40iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
{
- struct i40iw_ucontext *ucontext;
- u64 db_addr_offset, push_offset, pfn;
-
- ucontext = to_ucontext(context);
- if (ucontext->iwdev->sc_dev.is_pf) {
- db_addr_offset = I40IW_DB_ADDR_OFFSET;
- push_offset = I40IW_PUSH_OFFSET;
- if (vma->vm_pgoff)
- vma->vm_pgoff += I40IW_PF_FIRST_PUSH_PAGE_INDEX - 1;
- } else {
- db_addr_offset = I40IW_VF_DB_ADDR_OFFSET;
- push_offset = I40IW_VF_PUSH_OFFSET;
- if (vma->vm_pgoff)
- vma->vm_pgoff += I40IW_VF_FIRST_PUSH_PAGE_INDEX - 1;
- }
+ struct i40iw_ucontext *ucontext = to_ucontext(context);
+ u64 dbaddr;
- vma->vm_pgoff += db_addr_offset >> PAGE_SHIFT;
-
- if (vma->vm_pgoff == (db_addr_offset >> PAGE_SHIFT)) {
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- } else {
- if ((vma->vm_pgoff - (push_offset >> PAGE_SHIFT)) % 2)
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- else
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
- }
+ if (vma->vm_pgoff || vma->vm_end - vma->vm_start != PAGE_SIZE)
+ return -EINVAL;
- pfn = vma->vm_pgoff +
- (pci_resource_start(ucontext->iwdev->ldev->pcidev, 0) >>
- PAGE_SHIFT);
+ dbaddr = I40IW_DB_ADDR_OFFSET + pci_resource_start(ucontext->iwdev->ldev->pcidev, 0);
- return rdma_user_mmap_io(context, vma, pfn, PAGE_SIZE,
- vma->vm_page_prot, NULL);
+ return rdma_user_mmap_io(context, vma, dbaddr >> PAGE_SHIFT, PAGE_SIZE,
+ pgprot_noncached(vma->vm_page_prot), NULL);
}
/**
int err;
dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
- err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
+ err = register_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+ &dev->port[port_num].roce.nb);
if (err) {
dev->port[port_num].roce.nb.notifier_call = NULL;
return err;
static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u8 port_num)
{
if (dev->port[port_num].roce.nb.notifier_call) {
- unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
+ unregister_netdevice_notifier_net(mlx5_core_net(dev->mdev),
+ &dev->port[port_num].roce.nb);
dev->port[port_num].roce.nb.notifier_call = NULL;
}
}
}
mailbox = mthca_alloc_mailbox(dev, GFP_KERNEL);
- if (IS_ERR(mailbox))
+ if (IS_ERR(mailbox)) {
+ err = PTR_ERR(mailbox);
goto err_out_arm;
+ }
cq_context = mailbox->buf;
}
spin_lock_irq(&dev->cq_table.lock);
- if (mthca_array_set(&dev->cq_table.cq,
- cq->cqn & (dev->limits.num_cqs - 1),
- cq)) {
+ err = mthca_array_set(&dev->cq_table.cq,
+ cq->cqn & (dev->limits.num_cqs - 1), cq);
+ if (err) {
spin_unlock_irq(&dev->cq_table.lock);
goto err_out_free_mr;
}
listener->qed_handle);
cm_id->rem_ref(cm_id);
+ kfree(listener);
return rc;
}
}
ret = ib_device_set_netdev(&dev->ib_dev, dev->netdev, 1);
if (ret)
- return ret;
+ goto err_srq_free;
spin_lock_init(&dev->srq_tbl_lock);
rdma_set_device_sysfs_group(&dev->ib_dev, &pvrdma_attr_group);
u8 subnet_timeout;
u8 init_type_reply;
u8 active_width;
- u16 active_speed;
+ u8 active_speed;
u8 phys_state;
u8 reserved[2];
};
# SPDX-License-Identifier: GPL-2.0-only
config INFINIBAND_RDMAVT
tristate "RDMA verbs transport library"
- depends on X86_64 && ARCH_DMA_ADDR_T_64BIT
+ depends on INFINIBAND_VIRT_DMA
+ depends on X86_64
depends on PCI
select DMA_VIRT_OPS
help
int rvt_register_device(struct rvt_dev_info *rdi)
{
int ret = 0, i;
+ u64 dma_mask;
if (!rdi)
return -EINVAL;
/* DMA Operations */
rdi->ibdev.dev.dma_parms = rdi->ibdev.dev.parent->dma_parms;
- dma_set_coherent_mask(&rdi->ibdev.dev,
- rdi->ibdev.dev.parent->coherent_dma_mask);
+ dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+ ret = dma_coerce_mask_and_coherent(&rdi->ibdev.dev, dma_mask);
+ if (ret)
+ goto bail_wss;
/* Protection Domain */
spin_lock_init(&rdi->n_pds_lock);
config RDMA_RXE
tristate "Software RDMA over Ethernet (RoCE) driver"
depends on INET && PCI && INFINIBAND
- depends on !64BIT || ARCH_DMA_ADDR_T_64BIT
+ depends on INFINIBAND_VIRT_DMA
select NET_UDP_TUNNEL
select CRYPTO_CRC32
select DMA_VIRT_OPS
int rxe_av_chk_attr(struct rxe_dev *rxe, struct rdma_ah_attr *attr)
{
+ const struct ib_global_route *grh = rdma_ah_read_grh(attr);
struct rxe_port *port;
+ int type;
port = &rxe->port;
if (rdma_ah_get_ah_flags(attr) & IB_AH_GRH) {
- u8 sgid_index = rdma_ah_read_grh(attr)->sgid_index;
+ if (grh->sgid_index > port->attr.gid_tbl_len) {
+ pr_warn("invalid sgid index = %d\n",
+ grh->sgid_index);
+ return -EINVAL;
+ }
- if (sgid_index > port->attr.gid_tbl_len) {
- pr_warn("invalid sgid index = %d\n", sgid_index);
+ type = rdma_gid_attr_network_type(grh->sgid_attr);
+ if (type < RDMA_NETWORK_IPV4 ||
+ type > RDMA_NETWORK_IPV6) {
+ pr_warn("invalid network type for rdma_rxe = %d\n",
+ type);
return -EINVAL;
}
}
void rxe_av_fill_ip_info(struct rxe_av *av, struct rdma_ah_attr *attr)
{
const struct ib_gid_attr *sgid_attr = attr->grh.sgid_attr;
+ int ibtype;
+ int type;
rdma_gid2ip((struct sockaddr *)&av->sgid_addr, &sgid_attr->gid);
rdma_gid2ip((struct sockaddr *)&av->dgid_addr,
&rdma_ah_read_grh(attr)->dgid);
- av->network_type = rdma_gid_attr_network_type(sgid_attr);
+
+ ibtype = rdma_gid_attr_network_type(sgid_attr);
+
+ switch (ibtype) {
+ case RDMA_NETWORK_IPV4:
+ type = RXE_NETWORK_TYPE_IPV4;
+ break;
+ case RDMA_NETWORK_IPV6:
+ type = RXE_NETWORK_TYPE_IPV4;
+ break;
+ default:
+ /* not reached - checked in rxe_av_chk_attr */
+ type = 0;
+ break;
+ }
+
+ av->network_type = type;
}
struct rxe_av *rxe_get_av(struct rxe_pkt_info *pkt)
if (IS_ERR(attr))
return NULL;
- if (av->network_type == RXE_NETWORK_TYPE_IPV6)
+ if (av->network_type == RXE_NETWORK_TYPE_IPV4)
hdr_len = ETH_HLEN + sizeof(struct udphdr) +
sizeof(struct iphdr);
else
int err;
struct ib_device *dev = &rxe->ib_dev;
struct crypto_shash *tfm;
+ u64 dma_mask;
strlcpy(dev->node_desc, "rxe", sizeof(dev->node_desc));
rxe->ndev->dev_addr);
dev->dev.dma_parms = &rxe->dma_parms;
dma_set_max_seg_size(&dev->dev, UINT_MAX);
- dma_set_coherent_mask(&dev->dev, dma_get_required_mask(&dev->dev));
+ dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+ err = dma_coerce_mask_and_coherent(&dev->dev, dma_mask);
+ if (err)
+ return err;
dev->uverbs_cmd_mask = BIT_ULL(IB_USER_VERBS_CMD_GET_CONTEXT)
| BIT_ULL(IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)
config RDMA_SIW
tristate "Software RDMA over TCP/IP (iWARP) driver"
depends on INET && INFINIBAND && LIBCRC32C
+ depends on INFINIBAND_VIRT_DMA
select DMA_VIRT_OPS
help
This driver implements the iWARP RDMA transport over
struct siw_device *sdev = NULL;
struct ib_device *base_dev;
struct device *parent = netdev->dev.parent;
+ u64 dma_mask;
int rv;
if (!parent) {
base_dev->dev.parent = parent;
base_dev->dev.dma_parms = &sdev->dma_parms;
dma_set_max_seg_size(&base_dev->dev, UINT_MAX);
- dma_set_coherent_mask(&base_dev->dev,
- dma_get_required_mask(&base_dev->dev));
+ dma_mask = IS_ENABLED(CONFIG_64BIT) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32);
+ if (dma_coerce_mask_and_coherent(&base_dev->dev, dma_mask))
+ goto error;
+
base_dev->num_comp_vectors = num_possible_cpus();
xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1);
conn_param.private_data = (void *)&req_hdr;
conn_param.private_data_len = sizeof(struct iser_cm_hdr);
- ret = rdma_connect(cma_id, &conn_param);
+ ret = rdma_connect_locked(cma_id, &conn_param);
if (ret) {
iser_err("failure connecting: %d\n", ret);
goto failure;
uuid_copy(&msg.sess_uuid, &sess->s.uuid);
uuid_copy(&msg.paths_uuid, &clt->paths_uuid);
- err = rdma_connect(con->c.cm_id, ¶m);
+ err = rdma_connect_locked(con->c.cm_id, ¶m);
if (err)
- rtrs_err(clt, "rdma_connect(): %d\n", err);
+ rtrs_err(clt, "rdma_connect_locked(): %d\n", err);
return err;
}
/**
* srpt_unregister_mad_agent - unregister MAD callback functions
* @sdev: SRPT HCA pointer.
+ * @port_cnt: number of ports with registered MAD
*
* Note: It is safe to call this function more than once for the same device.
*/
-static void srpt_unregister_mad_agent(struct srpt_device *sdev)
+static void srpt_unregister_mad_agent(struct srpt_device *sdev, int port_cnt)
{
struct ib_port_modify port_modify = {
.clr_port_cap_mask = IB_PORT_DEVICE_MGMT_SUP,
struct srpt_port *sport;
int i;
- for (i = 1; i <= sdev->device->phys_port_cnt; i++) {
+ for (i = 1; i <= port_cnt; i++) {
sport = &sdev->port[i - 1];
WARN_ON(sport->port != i);
if (sport->mad_agent) {
if (ret) {
pr_err("MAD registration failed for %s-%d.\n",
dev_name(&sdev->device->dev), i);
- goto err_event;
+ i--;
+ goto err_port;
}
}
pr_debug("added %s.\n", dev_name(&device->dev));
return 0;
-err_event:
+err_port:
+ srpt_unregister_mad_agent(sdev, i);
ib_unregister_event_handler(&sdev->event_handler);
err_cm:
if (sdev->cm_id)
struct srpt_device *sdev = client_data;
int i;
- srpt_unregister_mad_agent(sdev);
+ srpt_unregister_mad_agent(sdev, sdev->device->phys_port_cnt);
ib_unregister_event_handler(&sdev->event_handler);
* @rdma_cm: See below.
* @rdma_cm.cm_id: RDMA CM ID associated with the channel.
* @cq: IB completion queue for this channel.
+ * @cq_size: Number of CQEs in @cq.
* @zw_cqe: Zero-length write CQE.
* @rcu: RCU head.
* @kref: kref for this channel.
{ 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 },
{ 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 },
{ 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 },
+ { 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 },
{ 0x12ab, 0x0004, "Honey Bee Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x12ab, 0x0301, "PDP AFTERGLOW AX.1", 0, XTYPE_XBOX360 },
{ 0x12ab, 0x0303, "Mortal Kombat Klassic FightStick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
XPAD_XBOXONE_VENDOR(0x0f0d), /* Hori Controllers */
XPAD_XBOX360_VENDOR(0x1038), /* SteelSeries Controllers */
XPAD_XBOX360_VENDOR(0x11c9), /* Nacon GC100XF */
+ XPAD_XBOX360_VENDOR(0x1209), /* Ardwiino Controllers */
XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */
XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */
switch (data) {
case SUNKBD_RET_RESET:
- schedule_work(&sunkbd->tq);
+ if (sunkbd->enabled)
+ schedule_work(&sunkbd->tq);
sunkbd->reset = -1;
break;
}
/*
- * sunkbd_reinit() sets leds and beeps to a state the computer remembers they
- * were in.
+ * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers
+ * they were in.
*/
-static void sunkbd_reinit(struct work_struct *work)
+static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd)
{
- struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
-
- wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ);
-
serio_write(sunkbd->serio, SUNKBD_CMD_SETLED);
serio_write(sunkbd->serio,
(!!test_bit(LED_CAPSL, sunkbd->dev->led) << 3) |
SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd));
}
+
+/*
+ * sunkbd_reinit() wait for the keyboard reset to complete and restores state
+ * of leds and beeps.
+ */
+
+static void sunkbd_reinit(struct work_struct *work)
+{
+ struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
+
+ /*
+ * It is OK that we check sunkbd->enabled without pausing serio,
+ * as we only want to catch true->false transition that will
+ * happen once and we will be woken up for it.
+ */
+ wait_event_interruptible_timeout(sunkbd->wait,
+ sunkbd->reset >= 0 || !sunkbd->enabled,
+ HZ);
+
+ if (sunkbd->reset >= 0 && sunkbd->enabled)
+ sunkbd_set_leds_beeps(sunkbd);
+}
+
static void sunkbd_enable(struct sunkbd *sunkbd, bool enable)
{
serio_pause_rx(sunkbd->serio);
sunkbd->enabled = enable;
serio_continue_rx(sunkbd->serio);
+
+ if (!enable) {
+ wake_up_interruptible(&sunkbd->wait);
+ cancel_work_sync(&sunkbd->tq);
+ }
}
/*
struct input_dev *input_dev;
const struct adxl34x_platform_data *pdata;
int err, range, i;
- unsigned char revid;
+ int revid;
if (!irq) {
dev_err(dev, "no IRQ?\n");
#include <linux/module.h>
#include <linux/input.h>
#include <linux/init.h>
+#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
int (*iap_reset)(struct i2c_client *client);
int (*prepare_fw_update)(struct i2c_client *client, u16 ic_type,
- u8 iap_version);
+ u8 iap_version, u16 fw_page_size);
int (*write_fw_block)(struct i2c_client *client, u16 fw_page_size,
const u8 *page, u16 checksum, int idx);
int (*finish_fw_update)(struct i2c_client *client,
u16 sw_checksum = 0, fw_checksum = 0;
error = data->ops->prepare_fw_update(client, data->ic_type,
- data->iap_version);
+ data->iap_version,
+ data->fw_page_size);
if (error)
return error;
return 0;
}
-static int elan_read_write_iap_type(struct i2c_client *client)
+static int elan_read_write_iap_type(struct i2c_client *client, u16 fw_page_size)
{
int error;
u16 constant;
do {
error = elan_i2c_write_cmd(client, ETP_I2C_IAP_TYPE_CMD,
- ETP_I2C_IAP_TYPE_REG);
+ fw_page_size / 2);
if (error) {
dev_err(&client->dev,
"cannot write iap type: %d\n", error);
constant = le16_to_cpup((__le16 *)val);
dev_dbg(&client->dev, "iap type reg: 0x%04x\n", constant);
- if (constant == ETP_I2C_IAP_TYPE_REG)
+ if (constant == fw_page_size / 2)
return 0;
} while (--retry > 0);
}
static int elan_i2c_prepare_fw_update(struct i2c_client *client, u16 ic_type,
- u8 iap_version)
+ u8 iap_version, u16 fw_page_size)
{
struct device *dev = &client->dev;
int error;
}
if (ic_type >= 0x0D && iap_version >= 1) {
- error = elan_read_write_iap_type(client);
+ error = elan_read_write_iap_type(client, fw_page_size);
if (error)
return error;
}
}
static int elan_smbus_prepare_fw_update(struct i2c_client *client, u16 ic_type,
- u8 iap_version)
+ u8 iap_version, u16 fw_page_size)
{
struct device *dev = &client->dev;
int len;
DMI_MATCH(DMI_SYS_VENDOR, "PEGATRON CORPORATION"),
DMI_MATCH(DMI_PRODUCT_NAME, "C15B"),
},
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ByteSpeed LLC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "ByteSpeed Laptop C15B"),
+ },
},
{ }
};
MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]");
#endif
+static bool i8042_present;
static bool i8042_bypass_aux_irq_test;
static char i8042_kbd_firmware_id[128];
static char i8042_aux_firmware_id[128];
unsigned long flags;
int retval;
+ if (!i8042_present)
+ return -1;
+
spin_lock_irqsave(&i8042_lock, flags);
retval = __i8042_command(param, command);
spin_unlock_irqrestore(&i8042_lock, flags);
if (error)
goto err_free_ports;
- if (aux_enable())
+ error = aux_enable();
+ if (error)
goto err_free_irq;
i8042_aux_irq_registered = true;
err = i8042_platform_init();
if (err)
- return err;
+ return (err == -ENODEV) ? 0 : err;
err = i8042_controller_check();
if (err)
goto err_platform_exit;
+ /* Set this before creating the dev to allow i8042_command to work right away */
+ i8042_present = true;
+
pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0);
if (IS_ERR(pdev)) {
err = PTR_ERR(pdev);
static void __exit i8042_exit(void)
{
+ if (!i8042_present)
+ return;
+
platform_device_unregister(i8042_platform_device);
platform_driver_unregister(&i8042_driver);
i8042_platform_exit();
config TOUCHSCREEN_ADC
tristate "Generic ADC based resistive touchscreen"
depends on IIO
+ select IIO_BUFFER
select IIO_BUFFER_CB
help
Say Y here if you want to use the generic ADC
msleep(MXT_FW_RESET_TIME);
}
- error = mxt_acquire_irq(data);
+ error = mxt_check_retrigen(data);
if (error)
return error;
- error = mxt_check_retrigen(data);
+ error = mxt_acquire_irq(data);
if (error)
return error;
}
node->avg_bw = node->init_avg;
node->peak_bw = node->init_peak;
+ if (provider->aggregate)
+ provider->aggregate(node, 0, node->init_avg, node->init_peak,
+ &node->avg_bw, &node->peak_bw);
provider->set(node, node);
node->avg_bw = 0;
node->peak_bw = 0;
count++;
count += of_count_icc_providers(child);
}
- of_node_put(np);
return count;
}
int qcom_icc_set(struct icc_node *src, struct icc_node *dst)
{
struct qcom_icc_provider *qp;
+ struct qcom_icc_node *qn;
struct icc_node *node;
if (!src)
node = src;
qp = to_qcom_provider(node->provider);
+ qn = node->data;
+
+ qn->sum_avg[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->sum_avg[QCOM_ICC_BUCKET_AMC],
+ node->avg_bw);
+ qn->max_peak[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->max_peak[QCOM_ICC_BUCKET_AMC],
+ node->peak_bw);
qcom_icc_bcm_voter_commit(qp->voter);
DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8916_MASTER_SDCC_2, 8, -1, -1, MSM8916_PNOC_INT_1);
DEFINE_QNODE(mas_qdss_bam, MSM8916_MASTER_QDSS_BAM, 8, -1, -1, MSM8916_SNOC_QDSS_INT);
DEFINE_QNODE(mas_qdss_etr, MSM8916_MASTER_QDSS_ETR, 8, -1, -1, MSM8916_SNOC_QDSS_INT);
-DEFINE_QNODE(mas_snoc_cfg, MSM8916_MASTER_SNOC_CFG, 4, 20, -1, MSM8916_SNOC_QDSS_INT);
+DEFINE_QNODE(mas_snoc_cfg, MSM8916_MASTER_SNOC_CFG, 4, -1, -1, MSM8916_SNOC_QDSS_INT);
DEFINE_QNODE(mas_spdm, MSM8916_MASTER_SPDM, 4, -1, -1, MSM8916_PNOC_MAS_0);
DEFINE_QNODE(mas_tcu0, MSM8916_MASTER_TCU0, 8, -1, -1, MSM8916_SLAVE_EBI_CH0, MSM8916_BIMC_SNOC_MAS, MSM8916_SLAVE_AMPSS_L2);
DEFINE_QNODE(mas_tcu1, MSM8916_MASTER_TCU1, 8, -1, -1, MSM8916_SLAVE_EBI_CH0, MSM8916_BIMC_SNOC_MAS, MSM8916_SLAVE_AMPSS_L2);
DEFINE_QNODE(pcnoc_snoc_slv, MSM8916_PNOC_SNOC_SLV, 8, -1, 45, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC, MSM8916_SNOC_INT_1);
DEFINE_QNODE(qdss_int, MSM8916_SNOC_QDSS_INT, 8, -1, -1, MSM8916_SNOC_INT_0, MSM8916_SNOC_INT_BIMC);
DEFINE_QNODE(slv_apps_l2, MSM8916_SLAVE_AMPSS_L2, 8, -1, -1, 0);
-DEFINE_QNODE(slv_apss, MSM8916_SLAVE_APSS, 4, -1, 20, 0);
+DEFINE_QNODE(slv_apss, MSM8916_SLAVE_APSS, 4, -1, -1, 0);
DEFINE_QNODE(slv_audio, MSM8916_SLAVE_LPASS, 4, -1, -1, 0);
DEFINE_QNODE(slv_bimc_cfg, MSM8916_SLAVE_BIMC_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_blsp_1, MSM8916_SLAVE_BLSP_1, 4, -1, -1, 0);
DEFINE_QNODE(slv_boot_rom, MSM8916_SLAVE_BOOT_ROM, 4, -1, -1, 0);
DEFINE_QNODE(slv_camera_cfg, MSM8916_SLAVE_CAMERA_CFG, 4, -1, -1, 0);
-DEFINE_QNODE(slv_cats_0, MSM8916_SLAVE_CATS_128, 16, -1, 106, 0);
-DEFINE_QNODE(slv_cats_1, MSM8916_SLAVE_OCMEM_64, 8, -1, 107, 0);
+DEFINE_QNODE(slv_cats_0, MSM8916_SLAVE_CATS_128, 16, -1, -1, 0);
+DEFINE_QNODE(slv_cats_1, MSM8916_SLAVE_OCMEM_64, 8, -1, -1, 0);
DEFINE_QNODE(slv_clk_ctl, MSM8916_SLAVE_CLK_CTL, 4, -1, -1, 0);
DEFINE_QNODE(slv_crypto_0_cfg, MSM8916_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_dehr_cfg, MSM8916_SLAVE_DEHR_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_security, MSM8916_SLAVE_SECURITY, 4, -1, -1, 0);
DEFINE_QNODE(slv_snoc_cfg, MSM8916_SLAVE_SNOC_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_spdm, MSM8916_SLAVE_SPDM, 4, -1, -1, 0);
-DEFINE_QNODE(slv_srvc_snoc, MSM8916_SLAVE_SRVC_SNOC, 8, -1, 29, 0);
+DEFINE_QNODE(slv_srvc_snoc, MSM8916_SLAVE_SRVC_SNOC, 8, -1, -1, 0);
DEFINE_QNODE(slv_tcsr, MSM8916_SLAVE_TCSR, 4, -1, -1, 0);
DEFINE_QNODE(slv_tlmm, MSM8916_SLAVE_TLMM, 4, -1, -1, 0);
DEFINE_QNODE(slv_usb_hs, MSM8916_SLAVE_USB_HS, 4, -1, -1, 0);
DEFINE_QNODE(snoc_bimc_1_mas, MSM8916_SNOC_BIMC_1_MAS, 16, -1, -1, MSM8916_SNOC_BIMC_1_SLV);
DEFINE_QNODE(snoc_bimc_1_slv, MSM8916_SNOC_BIMC_1_SLV, 8, -1, -1, MSM8916_SLAVE_EBI_CH0);
DEFINE_QNODE(snoc_int_0, MSM8916_SNOC_INT_0, 8, 99, 130, MSM8916_SLAVE_QDSS_STM, MSM8916_SLAVE_IMEM, MSM8916_SNOC_PNOC_MAS);
-DEFINE_QNODE(snoc_int_1, MSM8916_SNOC_INT_1, 8, 100, 131, MSM8916_SLAVE_APSS, MSM8916_SLAVE_CATS_128, MSM8916_SLAVE_OCMEM_64);
+DEFINE_QNODE(snoc_int_1, MSM8916_SNOC_INT_1, 8, -1, -1, MSM8916_SLAVE_APSS, MSM8916_SLAVE_CATS_128, MSM8916_SLAVE_OCMEM_64);
DEFINE_QNODE(snoc_int_bimc, MSM8916_SNOC_INT_BIMC, 8, 101, 132, MSM8916_SNOC_BIMC_0_MAS);
DEFINE_QNODE(snoc_pcnoc_mas, MSM8916_SNOC_PNOC_MAS, 8, -1, -1, MSM8916_SNOC_PNOC_SLV);
DEFINE_QNODE(snoc_pcnoc_slv, MSM8916_SNOC_PNOC_SLV, 8, -1, -1, MSM8916_PNOC_INT_0);
do_div(rate, src_qn->buswidth);
+ rate = min_t(u32, rate, INT_MAX);
+
if (src_qn->rate == rate)
return 0;
return 0;
}
+static int msm8974_get_bw(struct icc_node *node, u32 *avg, u32 *peak)
+{
+ *avg = 0;
+ *peak = 0;
+
+ return 0;
+}
+
static int msm8974_icc_probe(struct platform_device *pdev)
{
const struct msm8974_icc_desc *desc;
provider->aggregate = icc_std_aggregate;
provider->xlate = of_icc_xlate_onecell;
provider->data = data;
+ provider->get_bw = msm8974_get_bw;
ret = icc_provider_add(provider);
if (ret) {
.driver = {
.name = "qnoc-msm8974",
.of_match_table = msm8974_noc_of_match,
+ .sync_state = icc_sync_state,
},
};
module_platform_driver(msm8974_noc_driver);
}
DEFINE_QNODE(mas_apps_proc, QCS404_MASTER_AMPSS_M0, 8, 0, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV);
-DEFINE_QNODE(mas_oxili, QCS404_MASTER_GRAPHICS_3D, 8, 6, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV);
-DEFINE_QNODE(mas_mdp, QCS404_MASTER_MDP_PORT0, 8, 8, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV);
+DEFINE_QNODE(mas_oxili, QCS404_MASTER_GRAPHICS_3D, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV);
+DEFINE_QNODE(mas_mdp, QCS404_MASTER_MDP_PORT0, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV);
DEFINE_QNODE(mas_snoc_bimc_1, QCS404_SNOC_BIMC_1_MAS, 8, 76, -1, QCS404_SLAVE_EBI_CH0);
DEFINE_QNODE(mas_tcu_0, QCS404_MASTER_TCU_0, 8, -1, -1, QCS404_SLAVE_EBI_CH0, QCS404_BIMC_SNOC_SLV);
DEFINE_QNODE(mas_spdm, QCS404_MASTER_SPDM, 4, -1, -1, QCS404_PNOC_INT_3);
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
DEFINE_QBCM(bcm_sh0, "SH0", true, &qns_llcc);
DEFINE_QBCM(bcm_mm0, "MM0", false, &qns_mem_noc_hf);
DEFINE_QBCM(bcm_sh1, "SH1", false, &qns_apps_io);
-DEFINE_QBCM(bcm_mm1, "MM1", false, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qxm_camnoc_hf0, &qxm_camnoc_hf1, &qxm_mdp0, &qxm_mdp1);
+DEFINE_QBCM(bcm_mm1, "MM1", true, &qxm_camnoc_hf0_uncomp, &qxm_camnoc_hf1_uncomp, &qxm_camnoc_sf_uncomp, &qxm_camnoc_hf0, &qxm_camnoc_hf1, &qxm_mdp0, &qxm_mdp1);
DEFINE_QBCM(bcm_sh2, "SH2", false, &qns_memnoc_snoc);
DEFINE_QBCM(bcm_mm2, "MM2", false, &qns2_mem_noc);
DEFINE_QBCM(bcm_sh3, "SH3", false, &acm_tcu);
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
.driver = {
.name = "qnoc-sm8150",
.of_match_table = qnoc_of_match,
+ .sync_state = icc_sync_state,
},
};
module_platform_driver(qnoc_driver);
return ret;
}
+ for (i = 0; i < qp->num_bcms; i++)
+ qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
+
for (i = 0; i < num_nodes; i++) {
size_t j;
}
data->num_nodes = num_nodes;
- for (i = 0; i < qp->num_bcms; i++)
- qcom_icc_bcm_init(qp->bcms[i], &pdev->dev);
-
platform_set_drvdata(pdev, qp);
return 0;
.driver = {
.name = "qnoc-sm8250",
.of_match_table = qnoc_of_match,
+ .sync_state = icc_sync_state,
},
};
module_platform_driver(qnoc_driver);
/* Only true if all IOMMUs support device IOTLBs */
extern bool amd_iommu_iotlb_sup;
-#define MAX_IRQS_PER_TABLE 256
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define MAX_IRQS_PER_TABLE 512
#define IRQ_TABLE_ALIGNMENT 128
struct irq_remap_table {
#include <asm/iommu_table.h>
#include <asm/io_apic.h>
#include <asm/irq_remapping.h>
+#include <asm/set_memory.h>
#include <linux/crash_dump.h>
free_pages((unsigned long)iommu->cmd_buf, get_order(CMD_BUFFER_SIZE));
}
+static void *__init iommu_alloc_4k_pages(struct amd_iommu *iommu,
+ gfp_t gfp, size_t size)
+{
+ int order = get_order(size);
+ void *buf = (void *)__get_free_pages(gfp, order);
+
+ if (buf &&
+ iommu_feature(iommu, FEATURE_SNP) &&
+ set_memory_4k((unsigned long)buf, (1 << order))) {
+ free_pages((unsigned long)buf, order);
+ buf = NULL;
+ }
+
+ return buf;
+}
+
/* allocates the memory where the IOMMU will log its events to */
static int __init alloc_event_buffer(struct amd_iommu *iommu)
{
- iommu->evt_buf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(EVT_BUFFER_SIZE));
+ iommu->evt_buf = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+ EVT_BUFFER_SIZE);
return iommu->evt_buf ? 0 : -ENOMEM;
}
/* allocates the memory where the IOMMU will log its events to */
static int __init alloc_ppr_log(struct amd_iommu *iommu)
{
- iommu->ppr_log = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(PPR_LOG_SIZE));
+ iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+ PPR_LOG_SIZE);
return iommu->ppr_log ? 0 : -ENOMEM;
}
static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
{
- iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL);
+ iommu->cmd_sem = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO, 1);
return iommu->cmd_sem ? 0 : -ENOMEM;
}
{
struct qcom_smmu *qsmmu;
+ /* Check to make sure qcom_scm has finished probing */
+ if (!qcom_scm_is_available())
+ return ERR_PTR(-EPROBE_DEFER);
+
qsmmu = devm_kzalloc(smmu->dev, sizeof(*qsmmu), GFP_KERNEL);
if (!qsmmu)
return ERR_PTR(-ENOMEM);
dmar_iommu_notify_scope_dev(info);
}
+static inline void vf_inherit_msi_domain(struct pci_dev *pdev)
+{
+ struct pci_dev *physfn = pci_physfn(pdev);
+
+ dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&physfn->dev));
+}
+
static int dmar_pci_bus_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
/* Only care about add/remove events for physical functions.
* For VFs we actually do the lookup based on the corresponding
* PF in device_to_iommu() anyway. */
- if (pdev->is_virtfn)
+ if (pdev->is_virtfn) {
+ /*
+ * Ensure that the VF device inherits the irq domain of the
+ * PF device. Ideally the device would inherit the domain
+ * from the bus, but DMAR can have multiple units per bus
+ * which makes this impossible. The VF 'bus' could inherit
+ * from the PF device, but that's yet another x86'sism to
+ * inflict on everybody else.
+ */
+ if (action == BUS_NOTIFY_ADD_DEVICE)
+ vf_inherit_msi_domain(pdev);
return NOTIFY_DONE;
+ }
+
if (action != BUS_NOTIFY_ADD_DEVICE &&
action != BUS_NOTIFY_REMOVED_DEVICE)
return NOTIFY_DONE;
warn_invalid_dmar(phys_addr, " returns all ones");
goto unmap;
}
- iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
+ if (ecap_vcs(iommu->ecap))
+ iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
/* the registers might be more than one page */
map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
* (used when kernel is launched w/ TXT)
*/
static int force_on = 0;
-int intel_iommu_tboot_noforce;
+static int intel_iommu_tboot_noforce;
static int no_platform_optin;
#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
if (ecap_prs(iommu->ecap))
intel_svm_finish_prq(iommu);
}
- if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap))
+ if (vccap_pasid(iommu->vccap))
ioasid_unregister_allocator(&iommu->pasid_allocator);
#endif
{
struct device_domain_info *info;
+ if (unlikely(!dev || !dev->iommu))
+ return NULL;
+
if (unlikely(attach_deferred(dev)))
return NULL;
* is active. All vIOMMU allocators will eventually be calling the same
* host allocator.
*/
- if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap))
+ if (!vccap_pasid(iommu->vccap))
return;
pr_info("Register custom PASID allocator\n");
* page aligned, we don't need to use a bounce page.
*/
if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) {
- tlb_addr = swiotlb_tbl_map_single(dev,
- phys_to_dma_unencrypted(dev, io_tlb_start),
- paddr, size, aligned_size, dir, attrs);
+ tlb_addr = swiotlb_tbl_map_single(dev, paddr, size,
+ aligned_size, dir, attrs);
if (tlb_addr == DMA_MAPPING_ERROR) {
goto swiotlb_error;
} else {
* Intel IOMMU is required for a TXT/tboot launch or platform
* opt in, so enforce that.
*/
- force_on = tboot_force_iommu() || platform_optin_force_iommu();
+ force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) ||
+ platform_optin_force_iommu();
if (iommu_init_mempool()) {
if (force_on)
struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
struct intel_svm_dev *sdev = NULL;
struct dmar_domain *dmar_domain;
+ struct device_domain_info *info;
struct intel_svm *svm = NULL;
int ret = 0;
if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
return -EINVAL;
+ info = get_domain_info(dev);
+ if (!info)
+ return -EINVAL;
+
dmar_domain = to_dmar_domain(domain);
mutex_lock(&pasid_mutex);
goto out;
}
sdev->dev = dev;
+ sdev->sid = PCI_DEVID(info->bus, info->devfn);
/* Only count users if device has aux domains */
if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
resp.qw0 = QI_PGRP_PASID(req->pasid) |
QI_PGRP_DID(req->rid) |
QI_PGRP_PASID_P(req->pasid_present) |
- QI_PGRP_PDP(req->pasid_present) |
+ QI_PGRP_PDP(req->priv_data_present) |
QI_PGRP_RESP_CODE(result) |
QI_PGRP_RESP_TYPE;
resp.qw1 = QI_PGRP_IDX(req->prg_index) |
*/
iommu_alloc_default_domain(group, dev);
- if (group->default_domain)
+ if (group->default_domain) {
ret = __iommu_attach_device(group->default_domain, dev);
+ if (ret) {
+ iommu_group_put(group);
+ goto err_release;
+ }
+ }
iommu_create_device_direct_mappings(group, dev);
iommu_group_put(group);
- if (ret)
- goto err_release;
-
if (ops->probe_finalize)
ops->probe_finalize(dev);
static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
{
- u32 mask;
+ u64 mask;
int i;
if (data->version != IOMMU_GPASID_BIND_VERSION_1)
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_IPI if SYS_SUPPORTS_MULTITHREADING
select IRQ_DOMAIN
- select IRQ_DOMAIN_HIERARCHY if GENERIC_IRQ_IPI
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config CLPS711X_IRQCHIP
config MIPS_GIC
bool
select GENERIC_IRQ_IPI
- select IRQ_DOMAIN_HIERARCHY
select MIPS_CM
config INGENIC_IRQ
config MST_IRQ
bool "MStar Interrupt Controller"
+ depends on ARCH_MEDIATEK || ARCH_MSTARV7 || COMPILE_TEST
default ARCH_MEDIATEK
select IRQ_DOMAIN
select IRQ_DOMAIN_HIERARCHY
#define BITS_PER_MBOX 32
-static void bcm2836_arm_irqchip_smp_init(void)
+static void __init bcm2836_arm_irqchip_smp_init(void)
{
struct irq_fwspec ipi_fwspec = {
.fwnode = intc.domain->fwnode,
#define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0)
#define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1)
#define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2)
-#define ITS_FLAGS_SAVE_SUSPEND_STATE (1ULL << 3)
#define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0)
#define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1)
list_for_each_entry(its, &its_nodes, entry) {
void __iomem *base;
- if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE))
- continue;
-
base = its->base;
its->ctlr_save = readl_relaxed(base + GITS_CTLR);
err = its_force_quiescent(base);
list_for_each_entry_continue_reverse(its, &its_nodes, entry) {
void __iomem *base;
- if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE))
- continue;
-
base = its->base;
writel_relaxed(its->ctlr_save, base + GITS_CTLR);
}
void __iomem *base;
int i;
- if (!(its->flags & ITS_FLAGS_SAVE_SUSPEND_STATE))
- continue;
-
base = its->base;
/*
* don't restore it since writing to CBASER or BASER<n>
* registers is undefined according to the GIC v3 ITS
* Specification.
+ *
+ * Firmware resuming with the ITS enabled is terminally broken.
*/
+ WARN_ON(readl_relaxed(base + GITS_CTLR) & GITS_CTLR_ENABLE);
ret = its_force_quiescent(base);
if (ret) {
pr_err("ITS@%pa: failed to quiesce on resume: %d\n",
ctlr |= GITS_CTLR_ImDe;
writel_relaxed(ctlr, its->base + GITS_CTLR);
- if (GITS_TYPER_HCC(typer))
- its->flags |= ITS_FLAGS_SAVE_SUSPEND_STATE;
-
err = its_init_domain(handle, its);
if (err)
goto out_free_tables;
.free = irq_domain_free_irqs_common,
};
-int __init
-mst_intc_of_init(struct device_node *dn, struct device_node *parent)
+static int __init mst_intc_of_init(struct device_node *dn,
+ struct device_node *parent)
{
struct irq_domain *domain, *domain_parent;
struct mst_intc_chip_data *cd;
};
struct intc_irqpin_config {
- unsigned int irlm_bit;
- unsigned needs_irlm:1;
+ int irlm_bit; /* -1 if non-existent */
};
static unsigned long intc_irqpin_read32(void __iomem *iomem)
static const struct intc_irqpin_config intc_irqpin_irlm_r8a777x = {
.irlm_bit = 23, /* ICR0.IRLM0 */
- .needs_irlm = 1,
};
static const struct intc_irqpin_config intc_irqpin_rmobile = {
- .needs_irlm = 0,
+ .irlm_bit = -1,
};
static const struct of_device_id intc_irqpin_dt_ids[] = {
}
/* configure "individual IRQ mode" where needed */
- if (config && config->needs_irlm) {
+ if (config && config->irlm_bit >= 0) {
if (io[INTC_IRQPIN_REG_IRLM])
intc_irqpin_read_modify_write(p, INTC_IRQPIN_REG_IRLM,
config->irlm_bit, 1, 1);
struct irq_data *d, int enable)
{
int cpu;
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
writel(enable, priv->regs + PRIORITY_BASE + d->hwirq * PRIORITY_PER_ID);
for_each_cpu(cpu, mask) {
{
struct cpumask amask;
unsigned int cpu;
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
cpumask_and(&amask, &priv->lmask, cpu_online_mask);
cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
static void plic_irq_mask(struct irq_data *d)
{
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
plic_irq_toggle(&priv->lmask, d, 0);
}
{
unsigned int cpu;
struct cpumask amask;
- struct plic_priv *priv = irq_get_chip_data(d->irq);
+ struct plic_priv *priv = irq_data_get_irq_chip_data(d);
cpumask_and(&amask, &priv->lmask, mask_val);
return -EINVAL;
plic_irq_toggle(&priv->lmask, d, 0);
- plic_irq_toggle(cpumask_of(cpu), d, 1);
+ plic_irq_toggle(cpumask_of(cpu), d, !irqd_irq_masked(d));
irq_data_update_effective_affinity(d, cpumask_of(cpu));
if (fwspec->param_count != 2)
return -EINVAL;
*hwirq = fwspec->param[0];
- *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+ *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK;
}
return 0;
}
{ .exti = 25, .irq_parent = 107, .chip = &stm32_exti_h_chip_direct },
{ .exti = 30, .irq_parent = 52, .chip = &stm32_exti_h_chip_direct },
{ .exti = 47, .irq_parent = 93, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 48, .irq_parent = 138, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 50, .irq_parent = 139, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 52, .irq_parent = 140, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 53, .irq_parent = 141, .chip = &stm32_exti_h_chip_direct },
{ .exti = 54, .irq_parent = 135, .chip = &stm32_exti_h_chip_direct },
{ .exti = 61, .irq_parent = 100, .chip = &stm32_exti_h_chip_direct },
{ .exti = 65, .irq_parent = 144, .chip = &stm32_exti_h_chip },
* @base: Base address of the memory mapped IO registers
* @pdev: Pointer to platform device.
* @ti_sci_id: TI-SCI device identifier
+ * @unmapped_cnt: Number of @unmapped_dev_ids entries
+ * @unmapped_dev_ids: Pointer to an array of TI-SCI device identifiers of
+ * unmapped event sources.
+ * Unmapped Events are not part of the Global Event Map and
+ * they are converted to Global event within INTA to be
+ * received by the same INTA to generate an interrupt.
+ * In case an interrupt request comes for a device which is
+ * generating Unmapped Event, we must use the INTA's TI-SCI
+ * device identifier in place of the source device
+ * identifier to let sysfw know where it has to program the
+ * Global Event number.
*/
struct ti_sci_inta_irq_domain {
const struct ti_sci_handle *sci;
void __iomem *base;
struct platform_device *pdev;
u32 ti_sci_id;
+
+ int unmapped_cnt;
+ u16 *unmapped_dev_ids;
};
#define to_vint_desc(e, i) container_of(e, struct ti_sci_inta_vint_desc, \
events[i])
+static u16 ti_sci_inta_get_dev_id(struct ti_sci_inta_irq_domain *inta, u32 hwirq)
+{
+ u16 dev_id = HWIRQ_TO_DEVID(hwirq);
+ int i;
+
+ if (inta->unmapped_cnt == 0)
+ return dev_id;
+
+ /*
+ * For devices sending Unmapped Events we must use the INTA's TI-SCI
+ * device identifier number to be able to convert it to a Global Event
+ * and map it to an interrupt.
+ */
+ for (i = 0; i < inta->unmapped_cnt; i++) {
+ if (dev_id == inta->unmapped_dev_ids[i]) {
+ dev_id = inta->ti_sci_id;
+ break;
+ }
+ }
+
+ return dev_id;
+}
+
/**
* ti_sci_inta_irq_handler() - Chained IRQ handler for the vint irqs
* @desc: Pointer to irq_desc corresponding to the irq
u16 dev_id, dev_index;
int err;
- dev_id = HWIRQ_TO_DEVID(hwirq);
+ dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
dev_index = HWIRQ_TO_IRQID(hwirq);
event_desc = &vint_desc->events[free_bit];
{
struct ti_sci_inta_vint_desc *vint_desc;
struct ti_sci_inta_irq_domain *inta;
+ u16 dev_id;
vint_desc = to_vint_desc(event_desc, event_desc->vint_bit);
inta = vint_desc->domain->host_data;
+ dev_id = ti_sci_inta_get_dev_id(inta, hwirq);
/* free event irq */
mutex_lock(&inta->vint_mutex);
inta->sci->ops.rm_irq_ops.free_event_map(inta->sci,
- HWIRQ_TO_DEVID(hwirq),
- HWIRQ_TO_IRQID(hwirq),
+ dev_id, HWIRQ_TO_IRQID(hwirq),
inta->ti_sci_id,
vint_desc->vint_id,
event_desc->global_event,
.chip = &ti_sci_inta_msi_irq_chip,
};
+static int ti_sci_inta_get_unmapped_sources(struct ti_sci_inta_irq_domain *inta)
+{
+ struct device *dev = &inta->pdev->dev;
+ struct device_node *node = dev_of_node(dev);
+ struct of_phandle_iterator it;
+ int count, err, ret, i;
+
+ count = of_count_phandle_with_args(node, "ti,unmapped-event-sources", NULL);
+ if (count <= 0)
+ return 0;
+
+ inta->unmapped_dev_ids = devm_kcalloc(dev, count,
+ sizeof(*inta->unmapped_dev_ids),
+ GFP_KERNEL);
+ if (!inta->unmapped_dev_ids)
+ return -ENOMEM;
+
+ i = 0;
+ of_for_each_phandle(&it, err, node, "ti,unmapped-event-sources", NULL, 0) {
+ u32 dev_id;
+
+ ret = of_property_read_u32(it.node, "ti,sci-dev-id", &dev_id);
+ if (ret) {
+ dev_err(dev, "ti,sci-dev-id read failure for %pOFf\n", it.node);
+ of_node_put(it.node);
+ return ret;
+ }
+ inta->unmapped_dev_ids[i++] = dev_id;
+ }
+
+ inta->unmapped_cnt = count;
+
+ return 0;
+}
+
static int ti_sci_inta_irq_domain_probe(struct platform_device *pdev)
{
struct irq_domain *parent_domain, *domain, *msi_domain;
if (IS_ERR(inta->base))
return PTR_ERR(inta->base);
+ ret = ti_sci_inta_get_unmapped_sources(inta);
+ if (ret)
+ return ret;
+
domain = irq_domain_add_linear(dev_of_node(dev),
ti_sci_get_num_resources(inta->vint),
&ti_sci_inta_irq_domain_ops, inta);
return cache->sectors_per_block_shift >= 0;
}
-/* gcc on ARM generates spurious references to __udivdi3 and __umoddi3 */
-#if defined(CONFIG_ARM) && __GNUC__ == 4 && __GNUC_MINOR__ <= 6
-__always_inline
-#endif
static dm_block_t block_div(dm_block_t b, uint32_t n)
{
do_div(b, n);
int r;
if (a->alg_string) {
- *hash = crypto_alloc_shash(a->alg_string, 0, 0);
+ *hash = crypto_alloc_shash(a->alg_string, 0, CRYPTO_ALG_ALLOCATES_MEMORY);
if (IS_ERR(*hash)) {
*error = error_alg;
r = PTR_ERR(*hash);
struct journal_completion comp;
comp.ic = ic;
- ic->journal_crypt = crypto_alloc_skcipher(ic->journal_crypt_alg.alg_string, 0, 0);
+ ic->journal_crypt = crypto_alloc_skcipher(ic->journal_crypt_alg.alg_string, 0, CRYPTO_ALG_ALLOCATES_MEMORY);
if (IS_ERR(ic->journal_crypt)) {
*error = "Invalid journal cipher";
r = PTR_ERR(ic->journal_crypt);
#include <linux/mutex.h>
#include <linux/delay.h>
#include <linux/atomic.h>
-#include <linux/lcm.h>
#include <linux/blk-mq.h>
#include <linux/mount.h>
#include <linux/dax.h>
void dm_table_event(struct dm_table *t)
{
- /*
- * You can no longer call dm_table_event() from interrupt
- * context, use a bottom half instead.
- */
- BUG_ON(in_interrupt());
-
mutex_lock(&_event_lock);
if (t->event_fn)
t->event_fn(t->event_context);
zone_sectors = ti_limits.chunk_sectors;
}
- /* Stack chunk_sectors if target-specific splitting is required */
- if (ti->max_io_len)
- ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len,
- ti_limits.chunk_sectors);
/* Set I/O hints portion of queue limits */
if (ti->type->io_hints)
ti->type->io_hints(ti, &ti_limits);
#else
static int persistent_memory_claim(struct dm_writecache *wc)
{
- BUG();
+ return -EOPNOTSUPP;
}
#endif
struct wc_memory_superblock s;
static struct dm_arg _args[] = {
- {0, 10, "Invalid number of feature args"},
+ {0, 16, "Invalid number of feature args"},
};
as.argc = argc;
extra_args += 2;
if (wc->autocommit_time_set)
extra_args += 2;
+ if (wc->max_age != MAX_AGE_UNSPECIFIED)
+ extra_args += 2;
if (wc->cleaner)
extra_args++;
if (wc->writeback_fua_set)
return -EAGAIN;
map = dm_get_live_table(md, &srcu_idx);
- if (!map)
- return -EIO;
+ if (!map) {
+ ret = -EIO;
+ goto out;
+ }
do {
struct dm_target *tgt;
static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
struct block_device **bdev)
- __acquires(md->io_barrier)
{
struct dm_target *tgt;
struct dm_table *map;
}
static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx)
- __releases(md->io_barrier)
{
dm_put_live_table(md, srcu_idx);
}
sector_t max_len;
/*
- * Does the target need to split even further?
- * - q->limits.chunk_sectors reflects ti->max_io_len so
- * blk_max_size_offset() provides required splitting.
- * - blk_max_size_offset() also respects q->limits.max_sectors
+ * Does the target need to split IO even further?
+ * - varied (per target) IO splitting is a tenet of DM; this
+ * explains why stacked chunk_sectors based splitting via
+ * blk_max_size_offset() isn't possible here. So pass in
+ * ti->max_io_len to override stacked chunk_sectors.
*/
- max_len = blk_max_size_offset(ti->table->md->queue,
- target_offset);
- if (len > max_len)
- len = max_len;
+ if (ti->max_io_len) {
+ max_len = blk_max_size_offset(ti->table->md->queue,
+ target_offset, ti->max_io_len);
+ if (len > max_len)
+ len = max_len;
+ }
return len;
}
* ->zero_page_range() is mandatory dax operation. If we are
* here, something is wrong.
*/
- dm_put_live_table(md, srcu_idx);
goto out;
}
ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages);
-
out:
dm_put_live_table(md, srcu_idx);
depends on MTK_IOMMU || COMPILE_TEST
depends on VIDEO_DEV && VIDEO_V4L2
depends on ARCH_MEDIATEK || COMPILE_TEST
+ depends on VIDEO_MEDIATEK_VPU || MTK_SCP
+ # The two following lines ensure we have the same state ("m" or "y") as
+ # our dependencies, to avoid missing symbols during link.
+ depends on VIDEO_MEDIATEK_VPU || !VIDEO_MEDIATEK_VPU
+ depends on MTK_SCP || !MTK_SCP
select VIDEOBUF2_DMA_CONTIG
select V4L2_MEM2MEM_DEV
- select VIDEO_MEDIATEK_VPU
- select MTK_SCP
+ select VIDEO_MEDIATEK_VCODEC_VPU if VIDEO_MEDIATEK_VPU
+ select VIDEO_MEDIATEK_VCODEC_SCP if MTK_SCP
help
- Mediatek video codec driver provides HW capability to
- encode and decode in a range of video formats
- This driver rely on VPU driver to communicate with VPU.
+ Mediatek video codec driver provides HW capability to
+ encode and decode in a range of video formats on MT8173
+ and MT8183.
+
+ Note that support for MT8173 requires VIDEO_MEDIATEK_VPU to
+ also be selected. Support for MT8183 depends on MTK_SCP.
+
+ To compile this driver as modules, choose M here: the
+ modules will be called mtk-vcodec-dec and mtk-vcodec-enc.
+
+config VIDEO_MEDIATEK_VCODEC_VPU
+ bool
- To compile this driver as modules, choose M here: the
- modules will be called mtk-vcodec-dec and mtk-vcodec-enc.
+config VIDEO_MEDIATEK_VCODEC_SCP
+ bool
config VIDEO_MEM2MEM_DEINTERLACE
tristate "Deinterlace support"
* Suspend/resume support.
*/
+#ifdef CONFIG_PM
static int mmpcam_runtime_resume(struct device *dev)
{
struct mmp_camera *cam = dev_get_drvdata(dev);
return mccic_resume(&cam->mcam);
return 0;
}
+#endif
static const struct dev_pm_ops mmpcam_pm_ops = {
SET_RUNTIME_PM_OPS(mmpcam_runtime_suspend, mmpcam_runtime_resume, NULL)
mtk-vcodec-common-y := mtk_vcodec_intr.o \
mtk_vcodec_util.o \
- mtk_vcodec_fw.o
+ mtk_vcodec_fw.o \
+
+ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_VPU),)
+mtk-vcodec-common-y += mtk_vcodec_fw_vpu.o
+endif
+
+ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP),)
+mtk-vcodec-common-y += mtk_vcodec_fw_scp.o
+endif
}
dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
- dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, VPU_RST_DEC);
+ dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, DECODER);
if (IS_ERR(dev->fw_handler))
return PTR_ERR(dev->fw_handler);
}
dma_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
- dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, VPU_RST_ENC);
+ dev->fw_handler = mtk_vcodec_fw_select(dev, fw_type, ENCODER);
if (IS_ERR(dev->fw_handler))
return PTR_ERR(dev->fw_handler);
// SPDX-License-Identifier: GPL-2.0
#include "mtk_vcodec_fw.h"
+#include "mtk_vcodec_fw_priv.h"
#include "mtk_vcodec_util.h"
#include "mtk_vcodec_drv.h"
-struct mtk_vcodec_fw_ops {
- int (*load_firmware)(struct mtk_vcodec_fw *fw);
- unsigned int (*get_vdec_capa)(struct mtk_vcodec_fw *fw);
- unsigned int (*get_venc_capa)(struct mtk_vcodec_fw *fw);
- void * (*map_dm_addr)(struct mtk_vcodec_fw *fw, u32 dtcm_dmem_addr);
- int (*ipi_register)(struct mtk_vcodec_fw *fw, int id,
- mtk_vcodec_ipi_handler handler, const char *name, void *priv);
- int (*ipi_send)(struct mtk_vcodec_fw *fw, int id, void *buf,
- unsigned int len, unsigned int wait);
-};
-
-struct mtk_vcodec_fw {
- enum mtk_vcodec_fw_type type;
- const struct mtk_vcodec_fw_ops *ops;
- struct platform_device *pdev;
- struct mtk_scp *scp;
-};
-
-static int mtk_vcodec_vpu_load_firmware(struct mtk_vcodec_fw *fw)
-{
- return vpu_load_firmware(fw->pdev);
-}
-
-static unsigned int mtk_vcodec_vpu_get_vdec_capa(struct mtk_vcodec_fw *fw)
-{
- return vpu_get_vdec_hw_capa(fw->pdev);
-}
-
-static unsigned int mtk_vcodec_vpu_get_venc_capa(struct mtk_vcodec_fw *fw)
-{
- return vpu_get_venc_hw_capa(fw->pdev);
-}
-
-static void *mtk_vcodec_vpu_map_dm_addr(struct mtk_vcodec_fw *fw,
- u32 dtcm_dmem_addr)
-{
- return vpu_mapping_dm_addr(fw->pdev, dtcm_dmem_addr);
-}
-
-static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id,
- mtk_vcodec_ipi_handler handler,
- const char *name, void *priv)
-{
- /*
- * The handler we receive takes a void * as its first argument. We
- * cannot change this because it needs to be passed down to the rproc
- * subsystem when SCP is used. VPU takes a const argument, which is
- * more constrained, so the conversion below is safe.
- */
- ipi_handler_t handler_const = (ipi_handler_t)handler;
-
- return vpu_ipi_register(fw->pdev, id, handler_const, name, priv);
-}
-
-static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf,
- unsigned int len, unsigned int wait)
-{
- return vpu_ipi_send(fw->pdev, id, buf, len);
-}
-
-static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = {
- .load_firmware = mtk_vcodec_vpu_load_firmware,
- .get_vdec_capa = mtk_vcodec_vpu_get_vdec_capa,
- .get_venc_capa = mtk_vcodec_vpu_get_venc_capa,
- .map_dm_addr = mtk_vcodec_vpu_map_dm_addr,
- .ipi_register = mtk_vcodec_vpu_set_ipi_register,
- .ipi_send = mtk_vcodec_vpu_ipi_send,
-};
-
-static int mtk_vcodec_scp_load_firmware(struct mtk_vcodec_fw *fw)
-{
- return rproc_boot(scp_get_rproc(fw->scp));
-}
-
-static unsigned int mtk_vcodec_scp_get_vdec_capa(struct mtk_vcodec_fw *fw)
-{
- return scp_get_vdec_hw_capa(fw->scp);
-}
-
-static unsigned int mtk_vcodec_scp_get_venc_capa(struct mtk_vcodec_fw *fw)
-{
- return scp_get_venc_hw_capa(fw->scp);
-}
-
-static void *mtk_vcodec_vpu_scp_dm_addr(struct mtk_vcodec_fw *fw,
- u32 dtcm_dmem_addr)
-{
- return scp_mapping_dm_addr(fw->scp, dtcm_dmem_addr);
-}
-
-static int mtk_vcodec_scp_set_ipi_register(struct mtk_vcodec_fw *fw, int id,
- mtk_vcodec_ipi_handler handler,
- const char *name, void *priv)
-{
- return scp_ipi_register(fw->scp, id, handler, priv);
-}
-
-static int mtk_vcodec_scp_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf,
- unsigned int len, unsigned int wait)
-{
- return scp_ipi_send(fw->scp, id, buf, len, wait);
-}
-
-static const struct mtk_vcodec_fw_ops mtk_vcodec_rproc_msg = {
- .load_firmware = mtk_vcodec_scp_load_firmware,
- .get_vdec_capa = mtk_vcodec_scp_get_vdec_capa,
- .get_venc_capa = mtk_vcodec_scp_get_venc_capa,
- .map_dm_addr = mtk_vcodec_vpu_scp_dm_addr,
- .ipi_register = mtk_vcodec_scp_set_ipi_register,
- .ipi_send = mtk_vcodec_scp_ipi_send,
-};
-
-static void mtk_vcodec_reset_handler(void *priv)
-{
- struct mtk_vcodec_dev *dev = priv;
- struct mtk_vcodec_ctx *ctx;
-
- mtk_v4l2_err("Watchdog timeout!!");
-
- mutex_lock(&dev->dev_mutex);
- list_for_each_entry(ctx, &dev->ctx_list, list) {
- ctx->state = MTK_STATE_ABORT;
- mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT",
- ctx->id);
- }
- mutex_unlock(&dev->dev_mutex);
-}
-
struct mtk_vcodec_fw *mtk_vcodec_fw_select(struct mtk_vcodec_dev *dev,
enum mtk_vcodec_fw_type type,
- enum rst_id rst_id)
+ enum mtk_vcodec_fw_use fw_use)
{
- const struct mtk_vcodec_fw_ops *ops;
- struct mtk_vcodec_fw *fw;
- struct platform_device *fw_pdev = NULL;
- struct mtk_scp *scp = NULL;
-
switch (type) {
case VPU:
- ops = &mtk_vcodec_vpu_msg;
- fw_pdev = vpu_get_plat_device(dev->plat_dev);
- if (!fw_pdev) {
- mtk_v4l2_err("firmware device is not ready");
- return ERR_PTR(-EINVAL);
- }
- vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_reset_handler,
- dev, rst_id);
- break;
+ return mtk_vcodec_fw_vpu_init(dev, fw_use);
case SCP:
- ops = &mtk_vcodec_rproc_msg;
- scp = scp_get(dev->plat_dev);
- if (!scp) {
- mtk_v4l2_err("could not get vdec scp handle");
- return ERR_PTR(-EPROBE_DEFER);
- }
- break;
+ return mtk_vcodec_fw_scp_init(dev);
default:
mtk_v4l2_err("invalid vcodec fw type");
return ERR_PTR(-EINVAL);
}
-
- fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL);
- if (!fw)
- return ERR_PTR(-EINVAL);
-
- fw->type = type;
- fw->ops = ops;
- fw->pdev = fw_pdev;
- fw->scp = scp;
-
- return fw;
}
EXPORT_SYMBOL_GPL(mtk_vcodec_fw_select);
void mtk_vcodec_fw_release(struct mtk_vcodec_fw *fw)
{
- switch (fw->type) {
- case VPU:
- put_device(&fw->pdev->dev);
- break;
- case SCP:
- scp_put(fw->scp);
- break;
- }
+ fw->ops->release(fw);
}
EXPORT_SYMBOL_GPL(mtk_vcodec_fw_release);
SCP,
};
+enum mtk_vcodec_fw_use {
+ DECODER,
+ ENCODER,
+};
+
struct mtk_vcodec_fw;
typedef void (*mtk_vcodec_ipi_handler) (void *data,
struct mtk_vcodec_fw *mtk_vcodec_fw_select(struct mtk_vcodec_dev *dev,
enum mtk_vcodec_fw_type type,
- enum rst_id rst_id);
+ enum mtk_vcodec_fw_use fw_use);
void mtk_vcodec_fw_release(struct mtk_vcodec_fw *fw);
int mtk_vcodec_fw_load_firmware(struct mtk_vcodec_fw *fw);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _MTK_VCODEC_FW_PRIV_H_
+#define _MTK_VCODEC_FW_PRIV_H_
+
+#include "mtk_vcodec_fw.h"
+
+struct mtk_vcodec_dev;
+
+struct mtk_vcodec_fw {
+ enum mtk_vcodec_fw_type type;
+ const struct mtk_vcodec_fw_ops *ops;
+ struct platform_device *pdev;
+ struct mtk_scp *scp;
+};
+
+struct mtk_vcodec_fw_ops {
+ int (*load_firmware)(struct mtk_vcodec_fw *fw);
+ unsigned int (*get_vdec_capa)(struct mtk_vcodec_fw *fw);
+ unsigned int (*get_venc_capa)(struct mtk_vcodec_fw *fw);
+ void *(*map_dm_addr)(struct mtk_vcodec_fw *fw, u32 dtcm_dmem_addr);
+ int (*ipi_register)(struct mtk_vcodec_fw *fw, int id,
+ mtk_vcodec_ipi_handler handler, const char *name,
+ void *priv);
+ int (*ipi_send)(struct mtk_vcodec_fw *fw, int id, void *buf,
+ unsigned int len, unsigned int wait);
+ void (*release)(struct mtk_vcodec_fw *fw);
+};
+
+#if IS_ENABLED(CONFIG_VIDEO_MEDIATEK_VCODEC_VPU)
+struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev,
+ enum mtk_vcodec_fw_use fw_use);
+#else
+static inline struct mtk_vcodec_fw *
+mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev,
+ enum mtk_vcodec_fw_use fw_use)
+{
+ return ERR_PTR(-ENODEV);
+}
+#endif /* CONFIG_VIDEO_MEDIATEK_VCODEC_VPU */
+
+#if IS_ENABLED(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP)
+struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev);
+#else
+static inline struct mtk_vcodec_fw *
+mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev)
+{
+ return ERR_PTR(-ENODEV);
+}
+#endif /* CONFIG_VIDEO_MEDIATEK_VCODEC_SCP */
+
+#endif /* _MTK_VCODEC_FW_PRIV_H_ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include "mtk_vcodec_fw_priv.h"
+#include "mtk_vcodec_util.h"
+#include "mtk_vcodec_drv.h"
+
+static int mtk_vcodec_scp_load_firmware(struct mtk_vcodec_fw *fw)
+{
+ return rproc_boot(scp_get_rproc(fw->scp));
+}
+
+static unsigned int mtk_vcodec_scp_get_vdec_capa(struct mtk_vcodec_fw *fw)
+{
+ return scp_get_vdec_hw_capa(fw->scp);
+}
+
+static unsigned int mtk_vcodec_scp_get_venc_capa(struct mtk_vcodec_fw *fw)
+{
+ return scp_get_venc_hw_capa(fw->scp);
+}
+
+static void *mtk_vcodec_vpu_scp_dm_addr(struct mtk_vcodec_fw *fw,
+ u32 dtcm_dmem_addr)
+{
+ return scp_mapping_dm_addr(fw->scp, dtcm_dmem_addr);
+}
+
+static int mtk_vcodec_scp_set_ipi_register(struct mtk_vcodec_fw *fw, int id,
+ mtk_vcodec_ipi_handler handler,
+ const char *name, void *priv)
+{
+ return scp_ipi_register(fw->scp, id, handler, priv);
+}
+
+static int mtk_vcodec_scp_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf,
+ unsigned int len, unsigned int wait)
+{
+ return scp_ipi_send(fw->scp, id, buf, len, wait);
+}
+
+static void mtk_vcodec_scp_release(struct mtk_vcodec_fw *fw)
+{
+ scp_put(fw->scp);
+}
+
+static const struct mtk_vcodec_fw_ops mtk_vcodec_rproc_msg = {
+ .load_firmware = mtk_vcodec_scp_load_firmware,
+ .get_vdec_capa = mtk_vcodec_scp_get_vdec_capa,
+ .get_venc_capa = mtk_vcodec_scp_get_venc_capa,
+ .map_dm_addr = mtk_vcodec_vpu_scp_dm_addr,
+ .ipi_register = mtk_vcodec_scp_set_ipi_register,
+ .ipi_send = mtk_vcodec_scp_ipi_send,
+ .release = mtk_vcodec_scp_release,
+};
+
+struct mtk_vcodec_fw *mtk_vcodec_fw_scp_init(struct mtk_vcodec_dev *dev)
+{
+ struct mtk_vcodec_fw *fw;
+ struct mtk_scp *scp;
+
+ scp = scp_get(dev->plat_dev);
+ if (!scp) {
+ mtk_v4l2_err("could not get vdec scp handle");
+ return ERR_PTR(-EPROBE_DEFER);
+ }
+
+ fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL);
+ fw->type = SCP;
+ fw->ops = &mtk_vcodec_rproc_msg;
+ fw->scp = scp;
+
+ return fw;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include "mtk_vcodec_fw_priv.h"
+#include "mtk_vcodec_util.h"
+#include "mtk_vcodec_drv.h"
+
+static int mtk_vcodec_vpu_load_firmware(struct mtk_vcodec_fw *fw)
+{
+ return vpu_load_firmware(fw->pdev);
+}
+
+static unsigned int mtk_vcodec_vpu_get_vdec_capa(struct mtk_vcodec_fw *fw)
+{
+ return vpu_get_vdec_hw_capa(fw->pdev);
+}
+
+static unsigned int mtk_vcodec_vpu_get_venc_capa(struct mtk_vcodec_fw *fw)
+{
+ return vpu_get_venc_hw_capa(fw->pdev);
+}
+
+static void *mtk_vcodec_vpu_map_dm_addr(struct mtk_vcodec_fw *fw,
+ u32 dtcm_dmem_addr)
+{
+ return vpu_mapping_dm_addr(fw->pdev, dtcm_dmem_addr);
+}
+
+static int mtk_vcodec_vpu_set_ipi_register(struct mtk_vcodec_fw *fw, int id,
+ mtk_vcodec_ipi_handler handler,
+ const char *name, void *priv)
+{
+ /*
+ * The handler we receive takes a void * as its first argument. We
+ * cannot change this because it needs to be passed down to the rproc
+ * subsystem when SCP is used. VPU takes a const argument, which is
+ * more constrained, so the conversion below is safe.
+ */
+ ipi_handler_t handler_const = (ipi_handler_t)handler;
+
+ return vpu_ipi_register(fw->pdev, id, handler_const, name, priv);
+}
+
+static int mtk_vcodec_vpu_ipi_send(struct mtk_vcodec_fw *fw, int id, void *buf,
+ unsigned int len, unsigned int wait)
+{
+ return vpu_ipi_send(fw->pdev, id, buf, len);
+}
+
+static void mtk_vcodec_vpu_release(struct mtk_vcodec_fw *fw)
+{
+ put_device(&fw->pdev->dev);
+}
+
+static void mtk_vcodec_vpu_reset_handler(void *priv)
+{
+ struct mtk_vcodec_dev *dev = priv;
+ struct mtk_vcodec_ctx *ctx;
+
+ mtk_v4l2_err("Watchdog timeout!!");
+
+ mutex_lock(&dev->dev_mutex);
+ list_for_each_entry(ctx, &dev->ctx_list, list) {
+ ctx->state = MTK_STATE_ABORT;
+ mtk_v4l2_debug(0, "[%d] Change to state MTK_STATE_ABORT",
+ ctx->id);
+ }
+ mutex_unlock(&dev->dev_mutex);
+}
+
+static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = {
+ .load_firmware = mtk_vcodec_vpu_load_firmware,
+ .get_vdec_capa = mtk_vcodec_vpu_get_vdec_capa,
+ .get_venc_capa = mtk_vcodec_vpu_get_venc_capa,
+ .map_dm_addr = mtk_vcodec_vpu_map_dm_addr,
+ .ipi_register = mtk_vcodec_vpu_set_ipi_register,
+ .ipi_send = mtk_vcodec_vpu_ipi_send,
+ .release = mtk_vcodec_vpu_release,
+};
+
+struct mtk_vcodec_fw *mtk_vcodec_fw_vpu_init(struct mtk_vcodec_dev *dev,
+ enum mtk_vcodec_fw_use fw_use)
+{
+ struct platform_device *fw_pdev;
+ struct mtk_vcodec_fw *fw;
+ enum rst_id rst_id;
+
+ switch (fw_use) {
+ case ENCODER:
+ rst_id = VPU_RST_ENC;
+ break;
+ case DECODER:
+ default:
+ rst_id = VPU_RST_DEC;
+ break;
+ }
+
+ fw_pdev = vpu_get_plat_device(dev->plat_dev);
+ if (!fw_pdev) {
+ mtk_v4l2_err("firmware device is not ready");
+ return ERR_PTR(-EINVAL);
+ }
+ vpu_wdt_reg_handler(fw_pdev, mtk_vcodec_vpu_reset_handler, dev, rst_id);
+
+ fw = devm_kzalloc(&dev->plat_dev->dev, sizeof(*fw), GFP_KERNEL);
+ fw->type = VPU;
+ fw->ops = &mtk_vcodec_vpu_msg;
+ fw->pdev = fw_pdev;
+
+ return fw;
+}
u32 header_mode;
- u32 profile;
- u32 level;
+ struct {
+ u32 h264;
+ u32 mpeg4;
+ u32 hevc;
+ u32 vp8;
+ u32 vp9;
+ } profile;
+ struct {
+ u32 h264;
+ u32 mpeg4;
+ u32 hevc;
+ u32 vp9;
+ } level;
};
struct venus_buffer {
return 0;
opp_dl_add_err:
- dev_pm_domain_detach(core->opp_pmdomain, true);
+ dev_pm_opp_detach_genpd(core->opp_table);
opp_attach_err:
if (core->pd_dl_venus) {
device_link_del(core->pd_dl_venus);
if (core->opp_dl_venus)
device_link_del(core->opp_dl_venus);
- dev_pm_domain_detach(core->opp_pmdomain, true);
+ dev_pm_opp_detach_genpd(core->opp_table);
}
static int core_get_v4(struct device *dev)
struct hfi_quantization quant;
struct hfi_quantization_range quant_range;
u32 ptype, rate_control, bitrate;
+ u32 profile, level;
int ret;
ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2);
if (ret)
return ret;
- ret = venus_helper_set_profile_level(inst, ctr->profile, ctr->level);
+ switch (inst->hfi_codec) {
+ case HFI_VIDEO_CODEC_H264:
+ profile = ctr->profile.h264;
+ level = ctr->level.h264;
+ break;
+ case HFI_VIDEO_CODEC_MPEG4:
+ profile = ctr->profile.mpeg4;
+ level = ctr->level.mpeg4;
+ break;
+ case HFI_VIDEO_CODEC_VP8:
+ profile = ctr->profile.vp8;
+ level = 0;
+ break;
+ case HFI_VIDEO_CODEC_VP9:
+ profile = ctr->profile.vp9;
+ level = ctr->level.vp9;
+ break;
+ case HFI_VIDEO_CODEC_HEVC:
+ profile = ctr->profile.hevc;
+ level = ctr->level.hevc;
+ break;
+ case HFI_VIDEO_CODEC_MPEG2:
+ default:
+ profile = 0;
+ level = 0;
+ break;
+ }
+
+ ret = venus_helper_set_profile_level(inst, profile, level);
if (ret)
return ret;
ctr->h264_entropy_mode = ctrl->val;
break;
case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE:
+ ctr->profile.mpeg4 = ctrl->val;
+ break;
case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
+ ctr->profile.h264 = ctrl->val;
+ break;
case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
+ ctr->profile.hevc = ctrl->val;
+ break;
case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
- ctr->profile = ctrl->val;
+ ctr->profile.vp8 = ctrl->val;
break;
case V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL:
+ ctr->level.mpeg4 = ctrl->val;
+ break;
case V4L2_CID_MPEG_VIDEO_H264_LEVEL:
+ ctr->level.h264 = ctrl->val;
+ break;
case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
- ctr->level = ctrl->val;
+ ctr->level.hevc = ctrl->val;
break;
case V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP:
ctr->h264_i_qp = ctrl->val;
* validate the existing APIs in the media subsystem. It can also aid
* developers working on userspace applications.
*
- * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner' and 'dvb_vidtv_demod'.
+ * When this module is loaded, it will attempt to modprobe 'dvb_vidtv_tuner'
+ * and 'dvb_vidtv_demod'.
*
* Copyright (C) 2020 Daniel W. S. Almeida
*/
+#include <linux/dev_printk.h>
#include <linux/moduleparam.h>
#include <linux/mutex.h>
#include <linux/platform_device.h>
-#include <linux/dev_printk.h>
#include <linux/time.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include "vidtv_bridge.h"
+#include "vidtv_common.h"
#include "vidtv_demod.h"
-#include "vidtv_tuner.h"
-#include "vidtv_ts.h"
#include "vidtv_mux.h"
-#include "vidtv_common.h"
+#include "vidtv_ts.h"
+#include "vidtv_tuner.h"
-//#define MUX_BUF_MAX_SZ
-//#define MUX_BUF_MIN_SZ
+#define MUX_BUF_MIN_SZ 90164
+#define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10)
#define TUNER_DEFAULT_ADDR 0x68
#define DEMOD_DEFAULT_ADDR 0x60
+#define VIDTV_DEFAULT_NETWORK_ID 0xff44
+#define VIDTV_DEFAULT_NETWORK_NAME "LinuxTV.org"
+#define VIDTV_DEFAULT_TS_ID 0x4081
-/* LNBf fake parameters: ranges used by an Universal (extended) European LNBf */
-#define LNB_CUT_FREQUENCY 11700000
-#define LNB_LOW_FREQ 9750000
-#define LNB_HIGH_FREQ 10600000
-
+/*
+ * The LNBf fake parameters here are the ranges used by an
+ * Universal (extended) European LNBf, which is likely the most common LNBf
+ * found on Satellite digital TV system nowadays.
+ */
+#define LNB_CUT_FREQUENCY 11700000 /* high IF frequency */
+#define LNB_LOW_FREQ 9750000 /* low IF frequency */
+#define LNB_HIGH_FREQ 10600000 /* transition frequency */
static unsigned int drop_tslock_prob_on_low_snr;
module_param(drop_tslock_prob_on_low_snr, uint, 0);
static unsigned int pcr_period_msec = 40;
module_param(pcr_period_msec, uint, 0);
-MODULE_PARM_DESC(pcr_period_msec, "How often to send PCR packets. Default: 40ms");
+MODULE_PARM_DESC(pcr_period_msec,
+ "How often to send PCR packets. Default: 40ms");
static unsigned int mux_rate_kbytes_sec = 4096;
module_param(mux_rate_kbytes_sec, uint, 0);
static unsigned int mux_buf_sz_pkts;
module_param(mux_buf_sz_pkts, uint, 0);
-MODULE_PARM_DESC(mux_buf_sz_pkts, "Size for the internal mux buffer in multiples of 188 bytes");
-
-#define MUX_BUF_MIN_SZ 90164
-#define MUX_BUF_MAX_SZ (MUX_BUF_MIN_SZ * 10)
+MODULE_PARM_DESC(mux_buf_sz_pkts,
+ "Size for the internal mux buffer in multiples of 188 bytes");
static u32 vidtv_bridge_mux_buf_sz_for_mux_rate(void)
{
u32 max_elapsed_time_msecs = VIDTV_MAX_SLEEP_USECS / USEC_PER_MSEC;
- u32 nbytes_expected;
u32 mux_buf_sz = mux_buf_sz_pkts * TS_PACKET_LEN;
+ u32 nbytes_expected;
nbytes_expected = mux_rate_kbytes_sec;
nbytes_expected *= max_elapsed_time_msecs;
FE_HAS_LOCK);
}
-static void
-vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts)
+/*
+ * called on a separate thread by the mux when new packets become available
+ */
+static void vidtv_bridge_on_new_pkts_avail(void *priv, u8 *buf, u32 npkts)
{
- /*
- * called on a separate thread by the mux when new packets become
- * available
- */
- struct vidtv_dvb *dvb = (struct vidtv_dvb *)priv;
+ struct vidtv_dvb *dvb = priv;
/* drop packets if we lose the lock */
if (vidtv_bridge_check_demod_lock(dvb, 0))
static int vidtv_start_streaming(struct vidtv_dvb *dvb)
{
- struct vidtv_mux_init_args mux_args = {0};
+ struct vidtv_mux_init_args mux_args = {
+ .mux_rate_kbytes_sec = mux_rate_kbytes_sec,
+ .on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail,
+ .pcr_period_usecs = pcr_period_msec * USEC_PER_MSEC,
+ .si_period_usecs = si_period_msec * USEC_PER_MSEC,
+ .pcr_pid = pcr_pid,
+ .transport_stream_id = VIDTV_DEFAULT_TS_ID,
+ .network_id = VIDTV_DEFAULT_NETWORK_ID,
+ .network_name = VIDTV_DEFAULT_NETWORK_NAME,
+ .priv = dvb,
+ };
struct device *dev = &dvb->pdev->dev;
u32 mux_buf_sz;
return 0;
}
- mux_buf_sz = (mux_buf_sz_pkts) ? mux_buf_sz_pkts : vidtv_bridge_mux_buf_sz_for_mux_rate();
+ if (mux_buf_sz_pkts)
+ mux_buf_sz = mux_buf_sz_pkts;
+ else
+ mux_buf_sz = vidtv_bridge_mux_buf_sz_for_mux_rate();
- mux_args.mux_rate_kbytes_sec = mux_rate_kbytes_sec;
- mux_args.on_new_packets_available_cb = vidtv_bridge_on_new_pkts_avail;
- mux_args.mux_buf_sz = mux_buf_sz;
- mux_args.pcr_period_usecs = pcr_period_msec * 1000;
- mux_args.si_period_usecs = si_period_msec * 1000;
- mux_args.pcr_pid = pcr_pid;
- mux_args.transport_stream_id = VIDTV_DEFAULT_TS_ID;
- mux_args.priv = dvb;
+ mux_args.mux_buf_sz = mux_buf_sz;
dvb->streaming = true;
- dvb->mux = vidtv_mux_init(dvb->fe[0], dev, mux_args);
+ dvb->mux = vidtv_mux_init(dvb->fe[0], dev, &mux_args);
+ if (!dvb->mux)
+ return -ENOMEM;
vidtv_mux_start_thread(dvb->mux);
dev_dbg_ratelimited(dev, "Started streaming\n");
{
struct dvb_demux *demux = feed->demux;
struct vidtv_dvb *dvb = demux->priv;
- int rc;
int ret;
+ int rc;
if (!demux->dmx.frontend)
return -EINVAL;
static struct dvb_frontend *vidtv_get_frontend_ptr(struct i2c_client *c)
{
- /* the demod will set this when its probe function runs */
struct vidtv_demod_state *state = i2c_get_clientdata(c);
+ /* the demod will set this when its probe function runs */
return &state->frontend;
}
struct i2c_msg msgs[],
int num)
{
+ /*
+ * Right now, this virtual driver doesn't really send or receive
+ * messages from I2C. A real driver will require an implementation
+ * here.
+ */
return 0;
}
static int vidtv_bridge_probe_demod(struct vidtv_dvb *dvb, u32 n)
{
- struct vidtv_demod_config cfg = {};
-
- cfg.drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr;
- cfg.recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr;
-
+ struct vidtv_demod_config cfg = {
+ .drop_tslock_prob_on_low_snr = drop_tslock_prob_on_low_snr,
+ .recover_tslock_prob_on_good_snr = recover_tslock_prob_on_good_snr,
+ };
dvb->i2c_client_demod[n] = dvb_module_probe("dvb_vidtv_demod",
NULL,
&dvb->i2c_adapter,
static int vidtv_bridge_probe_tuner(struct vidtv_dvb *dvb, u32 n)
{
- struct vidtv_tuner_config cfg = {};
+ struct vidtv_tuner_config cfg = {
+ .fe = dvb->fe[n],
+ .mock_power_up_delay_msec = mock_power_up_delay_msec,
+ .mock_tune_delay_msec = mock_tune_delay_msec,
+ };
u32 freq;
int i;
- cfg.fe = dvb->fe[n];
- cfg.mock_power_up_delay_msec = mock_power_up_delay_msec;
- cfg.mock_tune_delay_msec = mock_tune_delay_msec;
-
/* TODO: check if the frequencies are at a valid range */
memcpy(cfg.vidtv_valid_dvb_t_freqs,
static int vidtv_bridge_dvb_init(struct vidtv_dvb *dvb)
{
- int ret;
- int i;
- int j;
+ int ret, i, j;
ret = vidtv_bridge_i2c_register_adap(dvb);
if (ret < 0)
#include <linux/i2c.h>
#include <linux/platform_device.h>
#include <linux/types.h>
+
#include <media/dmxdev.h>
#include <media/dvb_demux.h>
#include <media/dvb_frontend.h>
+
#include "vidtv_mux.h"
/**
* @adapter: Represents a DTV adapter. See 'dvb_register_adapter'.
* @demux: The demux used by the dvb_dmx_swfilter_packets() call.
* @dmx_dev: Represents a demux device.
- * @dmx_frontend: The frontends associated with the demux.
+ * @dmx_fe: The frontends associated with the demux.
* @i2c_adapter: The i2c_adapter associated with the bridge driver.
* @i2c_client_demod: The i2c_clients associated with the demodulator modules.
* @i2c_client_tuner: The i2c_clients associated with the tuner modules.
* When vidtv boots, it will create some hardcoded channels.
* Their services will be concatenated to populate the SDT.
* Their programs will be concatenated to populate the PAT
+ * Their events will be concatenated to populate the EIT
* For each program in the PAT, a PMT section will be created
* The PMT section for a channel will be assigned its streams.
* Every stream will have its corresponding encoder polled to produce TS packets
* Copyright (C) 2020 Daniel W. S. Almeida
*/
-#include <linux/types.h>
-#include <linux/slab.h>
#include <linux/dev_printk.h>
#include <linux/ratelimit.h>
+#include <linux/slab.h>
+#include <linux/types.h>
#include "vidtv_channel.h"
-#include "vidtv_psi.h"
+#include "vidtv_common.h"
#include "vidtv_encoder.h"
#include "vidtv_mux.h"
-#include "vidtv_common.h"
+#include "vidtv_psi.h"
#include "vidtv_s302m.h"
static void vidtv_channel_encoder_destroy(struct vidtv_encoder *e)
{
- struct vidtv_encoder *curr = e;
struct vidtv_encoder *tmp = NULL;
+ struct vidtv_encoder *curr = e;
while (curr) {
/* forward the call to the derived type */
}
#define ENCODING_ISO8859_15 "\x0b"
+#define TS_NIT_PID 0x10
+/*
+ * init an audio only channel with a s302m encoder
+ */
struct vidtv_channel
*vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id)
{
- /*
- * init an audio only channel with a s302m encoder
- */
- const u16 s302m_service_id = 0x880;
- const u16 s302m_program_num = 0x880;
- const u16 s302m_program_pid = 0x101; /* packet id for PMT*/
- const u16 s302m_es_pid = 0x111; /* packet id for the ES */
const __be32 s302m_fid = cpu_to_be32(VIDTV_S302M_FORMAT_IDENTIFIER);
-
- char *name = ENCODING_ISO8859_15 "Beethoven";
+ char *event_text = ENCODING_ISO8859_15 "Bagatelle No. 25 in A minor for solo piano, also known as F\xfcr Elise, composed by Ludwig van Beethoven";
+ char *event_name = ENCODING_ISO8859_15 "Ludwig van Beethoven: F\xfcr Elise";
+ struct vidtv_s302m_encoder_init_args encoder_args = {};
+ char *iso_language_code = ENCODING_ISO8859_15 "eng";
char *provider = ENCODING_ISO8859_15 "LinuxTV.org";
+ char *name = ENCODING_ISO8859_15 "Beethoven";
+ const u16 s302m_es_pid = 0x111; /* packet id for the ES */
+ const u16 s302m_program_pid = 0x101; /* packet id for PMT*/
+ const u16 s302m_service_id = 0x880;
+ const u16 s302m_program_num = 0x880;
+ const u16 s302m_beethoven_event_id = 1;
+ struct vidtv_channel *s302m;
- struct vidtv_channel *s302m = kzalloc(sizeof(*s302m), GFP_KERNEL);
- struct vidtv_s302m_encoder_init_args encoder_args = {};
+ s302m = kzalloc(sizeof(*s302m), GFP_KERNEL);
+ if (!s302m)
+ return NULL;
s302m->name = kstrdup(name, GFP_KERNEL);
+ if (!s302m->name)
+ goto free_s302m;
- s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id);
+ s302m->service = vidtv_psi_sdt_service_init(NULL, s302m_service_id, false, true);
+ if (!s302m->service)
+ goto free_name;
s302m->service->descriptor = (struct vidtv_psi_desc *)
vidtv_psi_service_desc_init(NULL,
- DIGITAL_TELEVISION_SERVICE,
+ DIGITAL_RADIO_SOUND_SERVICE,
name,
provider);
+ if (!s302m->service->descriptor)
+ goto free_service;
s302m->transport_stream_id = transport_stream_id;
s302m->program = vidtv_psi_pat_program_init(NULL,
s302m_service_id,
s302m_program_pid);
+ if (!s302m->program)
+ goto free_service;
s302m->program_num = s302m_program_num;
s302m->streams = vidtv_psi_pmt_stream_init(NULL,
STREAM_PRIVATE_DATA,
s302m_es_pid);
+ if (!s302m->streams)
+ goto free_program;
s302m->streams->descriptor = (struct vidtv_psi_desc *)
vidtv_psi_registration_desc_init(NULL,
s302m_fid,
NULL,
0);
+ if (!s302m->streams->descriptor)
+ goto free_streams;
+
encoder_args.es_pid = s302m_es_pid;
s302m->encoders = vidtv_s302m_encoder_init(encoder_args);
+ if (!s302m->encoders)
+ goto free_streams;
+
+ s302m->events = vidtv_psi_eit_event_init(NULL, s302m_beethoven_event_id);
+ if (!s302m->events)
+ goto free_encoders;
+ s302m->events->descriptor = (struct vidtv_psi_desc *)
+ vidtv_psi_short_event_desc_init(NULL,
+ iso_language_code,
+ event_name,
+ event_text);
+ if (!s302m->events->descriptor)
+ goto free_events;
if (head) {
while (head->next)
}
return s302m;
+
+free_events:
+ vidtv_psi_eit_event_destroy(s302m->events);
+free_encoders:
+ vidtv_s302m_encoder_destroy(s302m->encoders);
+free_streams:
+ vidtv_psi_pmt_stream_destroy(s302m->streams);
+free_program:
+ vidtv_psi_pat_program_destroy(s302m->program);
+free_service:
+ vidtv_psi_sdt_service_destroy(s302m->service);
+free_name:
+ kfree(s302m->name);
+free_s302m:
+ kfree(s302m);
+
+ return NULL;
+}
+
+static struct vidtv_psi_table_eit_event
+*vidtv_channel_eit_event_cat_into_new(struct vidtv_mux *m)
+{
+ /* Concatenate the events */
+ const struct vidtv_channel *cur_chnl = m->channels;
+ struct vidtv_psi_table_eit_event *curr = NULL;
+ struct vidtv_psi_table_eit_event *head = NULL;
+ struct vidtv_psi_table_eit_event *tail = NULL;
+ struct vidtv_psi_desc *desc = NULL;
+ u16 event_id;
+
+ if (!cur_chnl)
+ return NULL;
+
+ while (cur_chnl) {
+ curr = cur_chnl->events;
+
+ if (!curr)
+ dev_warn_ratelimited(m->dev,
+ "No events found for channel %s\n",
+ cur_chnl->name);
+
+ while (curr) {
+ event_id = be16_to_cpu(curr->event_id);
+ tail = vidtv_psi_eit_event_init(tail, event_id);
+ if (!tail) {
+ vidtv_psi_eit_event_destroy(head);
+ return NULL;
+ }
+
+ desc = vidtv_psi_desc_clone(curr->descriptor);
+ vidtv_psi_desc_assign(&tail->descriptor, desc);
+
+ if (!head)
+ head = tail;
+
+ curr = curr->next;
+ }
+
+ cur_chnl = cur_chnl->next;
+ }
+
+ return head;
}
static struct vidtv_psi_table_sdt_service
if (!curr)
dev_warn_ratelimited(m->dev,
- "No services found for channel %s\n", cur_chnl->name);
+ "No services found for channel %s\n",
+ cur_chnl->name);
while (curr) {
service_id = be16_to_cpu(curr->service_id);
- tail = vidtv_psi_sdt_service_init(tail, service_id);
+ tail = vidtv_psi_sdt_service_init(tail,
+ service_id,
+ curr->EIT_schedule,
+ curr->EIT_present_following);
+ if (!tail)
+ goto free;
desc = vidtv_psi_desc_clone(curr->descriptor);
+ if (!desc)
+ goto free_tail;
vidtv_psi_desc_assign(&tail->descriptor, desc);
if (!head)
}
return head;
+
+free_tail:
+ vidtv_psi_sdt_service_destroy(tail);
+free:
+ vidtv_psi_sdt_service_destroy(head);
+ return NULL;
}
static struct vidtv_psi_table_pat_program*
tail = vidtv_psi_pat_program_init(tail,
serv_id,
pid);
+ if (!tail) {
+ vidtv_psi_pat_program_destroy(head);
+ return NULL;
+ }
if (!head)
head = tail;
cur_chnl = cur_chnl->next;
}
+ /* Add the NIT table */
+ vidtv_psi_pat_program_init(tail, 0, TS_NIT_PID);
return head;
}
+/*
+ * Match channels to their respective PMT sections, then assign the
+ * streams
+ */
static void
vidtv_channel_pmt_match_sections(struct vidtv_channel *channels,
struct vidtv_psi_table_pmt **sections,
u32 nsections)
{
- /*
- * Match channels to their respective PMT sections, then assign the
- * streams
- */
struct vidtv_psi_table_pmt *curr_section = NULL;
- struct vidtv_channel *cur_chnl = channels;
-
- struct vidtv_psi_table_pmt_stream *s = NULL;
struct vidtv_psi_table_pmt_stream *head = NULL;
struct vidtv_psi_table_pmt_stream *tail = NULL;
-
+ struct vidtv_psi_table_pmt_stream *s = NULL;
+ struct vidtv_channel *cur_chnl = channels;
struct vidtv_psi_desc *desc = NULL;
- u32 j;
- u16 curr_id;
u16 e_pid; /* elementary stream pid */
+ u16 curr_id;
+ u32 j;
while (cur_chnl) {
for (j = 0; j < nsections; ++j) {
head = tail;
desc = vidtv_psi_desc_clone(s->descriptor);
- vidtv_psi_desc_assign(&tail->descriptor, desc);
+ vidtv_psi_desc_assign(&tail->descriptor,
+ desc);
s = s->next;
}
}
}
-void vidtv_channel_si_init(struct vidtv_mux *m)
+static void
+vidtv_channel_destroy_service_list(struct vidtv_psi_desc_service_list_entry *e)
+{
+ struct vidtv_psi_desc_service_list_entry *tmp;
+
+ while (e) {
+ tmp = e;
+ e = e->next;
+ kfree(tmp);
+ }
+}
+
+static struct vidtv_psi_desc_service_list_entry
+*vidtv_channel_build_service_list(struct vidtv_psi_table_sdt_service *s)
+{
+ struct vidtv_psi_desc_service_list_entry *curr_e = NULL;
+ struct vidtv_psi_desc_service_list_entry *head_e = NULL;
+ struct vidtv_psi_desc_service_list_entry *prev_e = NULL;
+ struct vidtv_psi_desc *desc = s->descriptor;
+ struct vidtv_psi_desc_service *s_desc;
+
+ while (s) {
+ while (desc) {
+ if (s->descriptor->type != SERVICE_DESCRIPTOR)
+ goto next_desc;
+
+ s_desc = (struct vidtv_psi_desc_service *)desc;
+
+ curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL);
+ if (!curr_e) {
+ vidtv_channel_destroy_service_list(head_e);
+ return NULL;
+ }
+
+ curr_e->service_id = s->service_id;
+ curr_e->service_type = s_desc->service_type;
+
+ if (!head_e)
+ head_e = curr_e;
+ if (prev_e)
+ prev_e->next = curr_e;
+
+ prev_e = curr_e;
+
+next_desc:
+ desc = desc->next;
+ }
+ s = s->next;
+ }
+ return head_e;
+}
+
+int vidtv_channel_si_init(struct vidtv_mux *m)
{
+ struct vidtv_psi_desc_service_list_entry *service_list = NULL;
struct vidtv_psi_table_pat_program *programs = NULL;
struct vidtv_psi_table_sdt_service *services = NULL;
+ struct vidtv_psi_table_eit_event *events = NULL;
m->si.pat = vidtv_psi_pat_table_init(m->transport_stream_id);
+ if (!m->si.pat)
+ return -ENOMEM;
- m->si.sdt = vidtv_psi_sdt_table_init(m->transport_stream_id);
+ m->si.sdt = vidtv_psi_sdt_table_init(m->network_id,
+ m->transport_stream_id);
+ if (!m->si.sdt)
+ goto free_pat;
programs = vidtv_channel_pat_prog_cat_into_new(m);
+ if (!programs)
+ goto free_sdt;
services = vidtv_channel_sdt_serv_cat_into_new(m);
+ if (!services)
+ goto free_programs;
+
+ events = vidtv_channel_eit_event_cat_into_new(m);
+ if (!events)
+ goto free_services;
+
+ /* look for a service descriptor for every service */
+ service_list = vidtv_channel_build_service_list(services);
+ if (!service_list)
+ goto free_events;
+
+ /* use these descriptors to build the NIT */
+ m->si.nit = vidtv_psi_nit_table_init(m->network_id,
+ m->transport_stream_id,
+ m->network_name,
+ service_list);
+ if (!m->si.nit)
+ goto free_service_list;
+
+ m->si.eit = vidtv_psi_eit_table_init(m->network_id,
+ m->transport_stream_id,
+ programs->service_id);
+ if (!m->si.eit)
+ goto free_nit;
/* assemble all programs and assign to PAT */
vidtv_psi_pat_program_assign(m->si.pat, programs);
/* assemble all services and assign to SDT */
vidtv_psi_sdt_service_assign(m->si.sdt, services);
- m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat, m->pcr_pid);
+ /* assemble all events and assign to EIT */
+ vidtv_psi_eit_event_assign(m->si.eit, events);
+
+ m->si.pmt_secs = vidtv_psi_pmt_create_sec_for_each_pat_entry(m->si.pat,
+ m->pcr_pid);
+ if (!m->si.pmt_secs)
+ goto free_eit;
vidtv_channel_pmt_match_sections(m->channels,
m->si.pmt_secs,
- m->si.pat->programs);
+ m->si.pat->num_pmt);
+
+ vidtv_channel_destroy_service_list(service_list);
+
+ return 0;
+
+free_eit:
+ vidtv_psi_eit_table_destroy(m->si.eit);
+free_nit:
+ vidtv_psi_nit_table_destroy(m->si.nit);
+free_service_list:
+ vidtv_channel_destroy_service_list(service_list);
+free_events:
+ vidtv_psi_eit_event_destroy(events);
+free_services:
+ vidtv_psi_sdt_service_destroy(services);
+free_programs:
+ vidtv_psi_pat_program_destroy(programs);
+free_sdt:
+ vidtv_psi_sdt_table_destroy(m->si.sdt);
+free_pat:
+ vidtv_psi_pat_table_destroy(m->si.pat);
+ return 0;
}
void vidtv_channel_si_destroy(struct vidtv_mux *m)
{
u32 i;
- u16 num_programs = m->si.pat->programs;
vidtv_psi_pat_table_destroy(m->si.pat);
- for (i = 0; i < num_programs; ++i)
+ for (i = 0; i < m->si.pat->num_pmt; ++i)
vidtv_psi_pmt_table_destroy(m->si.pmt_secs[i]);
kfree(m->si.pmt_secs);
vidtv_psi_sdt_table_destroy(m->si.sdt);
+ vidtv_psi_nit_table_destroy(m->si.nit);
+ vidtv_psi_eit_table_destroy(m->si.eit);
}
-void vidtv_channels_init(struct vidtv_mux *m)
+int vidtv_channels_init(struct vidtv_mux *m)
{
/* this is the place to add new 'channels' for vidtv */
m->channels = vidtv_channel_s302m_init(NULL, m->transport_stream_id);
+
+ if (!m->channels)
+ return -ENOMEM;
+
+ return 0;
}
void vidtv_channels_destroy(struct vidtv_mux *m)
vidtv_psi_pat_program_destroy(curr->program);
vidtv_psi_pmt_stream_destroy(curr->streams);
vidtv_channel_encoder_destroy(curr->encoders);
+ vidtv_psi_eit_event_destroy(curr->events);
tmp = curr;
curr = curr->next;
* When vidtv boots, it will create some hardcoded channels.
* Their services will be concatenated to populate the SDT.
* Their programs will be concatenated to populate the PAT
+ * Their events will be concatenated to populate the EIT
* For each program in the PAT, a PMT section will be created
* The PMT section for a channel will be assigned its streams.
* Every stream will have its corresponding encoder polled to produce TS packets
#define VIDTV_CHANNEL_H
#include <linux/types.h>
-#include "vidtv_psi.h"
+
#include "vidtv_encoder.h"
#include "vidtv_mux.h"
+#include "vidtv_psi.h"
/**
* struct vidtv_channel - A 'channel' abstraction
* Every stream will have its corresponding encoder polled to produce TS packets
* These packets may be interleaved by the mux and then delivered to the bridge
*
+ * @name: name of the channel
* @transport_stream_id: a number to identify the TS, chosen at will.
* @service: A _single_ service. Will be concatenated into the SDT.
* @program_num: The link between PAT, PMT and SDT.
* Will be concatenated into the PAT.
* @streams: A stream loop used to populate the PMT section for 'program'
* @encoders: A encoder loop. There must be one encoder for each stream.
+ * @events: Optional event information. This will feed into the EIT.
* @next: Optionally chain this channel.
*/
struct vidtv_channel {
struct vidtv_psi_table_pat_program *program;
struct vidtv_psi_table_pmt_stream *streams;
struct vidtv_encoder *encoders;
+ struct vidtv_psi_table_eit_event *events;
struct vidtv_channel *next;
};
* vidtv_channel_si_init - Init the PSI tables from the channels in the mux
* @m: The mux containing the channels.
*/
-void vidtv_channel_si_init(struct vidtv_mux *m);
+int vidtv_channel_si_init(struct vidtv_mux *m);
void vidtv_channel_si_destroy(struct vidtv_mux *m);
/**
* vidtv_channels_init - Init hardcoded, fake 'channels'.
* @m: The mux to store the channels into.
*/
-void vidtv_channels_init(struct vidtv_mux *m);
+int vidtv_channels_init(struct vidtv_mux *m);
struct vidtv_channel
*vidtv_channel_s302m_init(struct vidtv_channel *head, u16 transport_stream_id);
void vidtv_channels_destroy(struct vidtv_mux *m);
#define CLOCK_UNIT_27MHZ 27000000
#define VIDTV_SLEEP_USECS 10000
#define VIDTV_MAX_SLEEP_USECS (2 * VIDTV_SLEEP_USECS)
-#define VIDTV_DEFAULT_TS_ID 0x744
u32 vidtv_memcpy(void *to,
size_t to_offset,
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/workqueue.h>
+
#include <media/dvb_frontend.h>
#include "vidtv_demod.h"
c->cnr.stat[0].svalue = state->tuner_cnr;
c->cnr.stat[0].svalue -= prandom_u32_max(state->tuner_cnr / 50);
-
}
static int vidtv_demod_read_status(struct dvb_frontend *fe,
#define VIDTV_DEMOD_H
#include <linux/dvb/frontend.h>
+
#include <media/dvb_frontend.h>
/**
* modulation and fec_inner
* @modulation: see enum fe_modulation
* @fec: see enum fe_fec_rate
+ * @cnr_ok: S/N threshold to consider the signal as OK. Below that, there's
+ * a chance of losing sync.
+ * @cnr_good: S/N threshold to consider the signal strong.
*
* This struct matches values for 'good' and 'ok' CNRs given the combination
* of modulation and fec_inner in use. We might simulate some noise if the
* struct vidtv_demod_state - The demodulator state
* @frontend: The frontend structure allocated by the demod.
* @config: The config used to init the demod.
- * @poll_snr: The task responsible for periodically checking the simulated
- * signal quality, eventually dropping or reacquiring the TS lock.
* @status: the demod status.
- * @cold_start: Whether the demod has not been init yet.
- * @poll_snr_thread_running: Whether the task responsible for periodically
- * checking the simulated signal quality is running.
- * @poll_snr_thread_restart: Whether we should restart the poll_snr task.
+ * @tuner_cnr: current S/N ratio for the signal carrier
*/
struct vidtv_demod_state {
struct dvb_frontend frontend;
struct vidtv_access_unit *next;
};
-/* Some musical notes, used by a tone generator */
+/* Some musical notes, used by a tone generator. Values are in Hz */
enum musical_notes {
NOTE_SILENT = 0,
* @encoder_buf_sz: The encoder buffer size, in bytes
* @encoder_buf_offset: Our byte position in the encoder buffer.
* @sample_count: How many samples we have encoded in total.
+ * @access_units: encoder payload units, used for clock references
* @src_buf: The source of raw data to be encoded, encoder might set a
* default if null.
+ * @src_buf_sz: size of @src_buf.
* @src_buf_offset: Our position in the source buffer.
* @is_video_encoder: Whether this a video encoder (as opposed to audio)
* @ctx: Encoder-specific state.
* @stream_id: Examples: Audio streams (0xc0-0xdf), Video streams
* (0xe0-0xef).
- * @es_id: The TS PID to use for the elementary stream in this encoder.
+ * @es_pid: The TS PID to use for the elementary stream in this encoder.
* @encode: Prepare enough AUs for the given amount of time.
* @clear: Clear the encoder output.
* @sync: Attempt to synchronize with this encoder.
u32 encoder_buf_offset;
u64 sample_count;
- int last_duration;
- int note_offset;
- enum musical_notes last_tone;
struct vidtv_access_unit *access_units;
* Copyright (C) 2020 Daniel W. S. Almeida
*/
-#include <linux/types.h>
-#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/dev_printk.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
-#include <linux/dev_printk.h>
+#include <linux/math64.h>
#include <linux/ratelimit.h>
-#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/types.h>
#include <linux/vmalloc.h>
-#include <linux/math64.h>
-#include "vidtv_mux.h"
-#include "vidtv_ts.h"
-#include "vidtv_pes.h"
-#include "vidtv_encoder.h"
#include "vidtv_channel.h"
#include "vidtv_common.h"
+#include "vidtv_encoder.h"
+#include "vidtv_mux.h"
+#include "vidtv_pes.h"
#include "vidtv_psi.h"
+#include "vidtv_ts.h"
static struct vidtv_mux_pid_ctx
*vidtv_mux_get_pid_ctx(struct vidtv_mux *m, u16 pid)
struct vidtv_mux_pid_ctx *ctx;
ctx = vidtv_mux_get_pid_ctx(m, pid);
-
if (ctx)
- goto end;
+ return ctx;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return NULL;
- ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
ctx->pid = pid;
ctx->cc = 0;
hash_add(m->pid_ctx, &ctx->h, pid);
-end:
return ctx;
}
-static void vidtv_mux_pid_ctx_init(struct vidtv_mux *m)
+static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m)
+{
+ struct vidtv_mux_pid_ctx *ctx;
+ struct hlist_node *tmp;
+ int bkt;
+
+ hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) {
+ hash_del(&ctx->h);
+ kfree(ctx);
+ }
+}
+
+static int vidtv_mux_pid_ctx_init(struct vidtv_mux *m)
{
struct vidtv_psi_table_pat_program *p = m->si.pat->program;
u16 pid;
hash_init(m->pid_ctx);
/* push the pcr pid ctx */
- vidtv_mux_create_pid_ctx_once(m, m->pcr_pid);
- /* push the null packet pid ctx */
- vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID);
+ if (!vidtv_mux_create_pid_ctx_once(m, m->pcr_pid))
+ return -ENOMEM;
+ /* push the NULL packet pid ctx */
+ if (!vidtv_mux_create_pid_ctx_once(m, TS_NULL_PACKET_PID))
+ goto free;
/* push the PAT pid ctx */
- vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID);
+ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_PAT_PID))
+ goto free;
/* push the SDT pid ctx */
- vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID);
+ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_SDT_PID))
+ goto free;
+ /* push the NIT pid ctx */
+ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_NIT_PID))
+ goto free;
+ /* push the EIT pid ctx */
+ if (!vidtv_mux_create_pid_ctx_once(m, VIDTV_EIT_PID))
+ goto free;
/* add a ctx for all PMT sections */
while (p) {
vidtv_mux_create_pid_ctx_once(m, pid);
p = p->next;
}
-}
-static void vidtv_mux_pid_ctx_destroy(struct vidtv_mux *m)
-{
- int bkt;
- struct vidtv_mux_pid_ctx *ctx;
- struct hlist_node *tmp;
+ return 0;
- hash_for_each_safe(m->pid_ctx, bkt, tmp, ctx, h) {
- hash_del(&ctx->h);
- kfree(ctx);
- }
+free:
+ vidtv_mux_pid_ctx_destroy(m);
+ return -ENOMEM;
}
static void vidtv_mux_update_clk(struct vidtv_mux *m)
static u32 vidtv_mux_push_si(struct vidtv_mux *m)
{
+ struct vidtv_psi_pat_write_args pat_args = {
+ .buf = m->mux_buf,
+ .buf_sz = m->mux_buf_sz,
+ .pat = m->si.pat,
+ };
+ struct vidtv_psi_pmt_write_args pmt_args = {
+ .buf = m->mux_buf,
+ .buf_sz = m->mux_buf_sz,
+ .pcr_pid = m->pcr_pid,
+ };
+ struct vidtv_psi_sdt_write_args sdt_args = {
+ .buf = m->mux_buf,
+ .buf_sz = m->mux_buf_sz,
+ .sdt = m->si.sdt,
+ };
+ struct vidtv_psi_nit_write_args nit_args = {
+ .buf = m->mux_buf,
+ .buf_sz = m->mux_buf_sz,
+ .nit = m->si.nit,
+
+ };
+ struct vidtv_psi_eit_write_args eit_args = {
+ .buf = m->mux_buf,
+ .buf_sz = m->mux_buf_sz,
+ .eit = m->si.eit,
+ };
u32 initial_offset = m->mux_buf_offset;
-
struct vidtv_mux_pid_ctx *pat_ctx;
struct vidtv_mux_pid_ctx *pmt_ctx;
struct vidtv_mux_pid_ctx *sdt_ctx;
-
- struct vidtv_psi_pat_write_args pat_args = {};
- struct vidtv_psi_pmt_write_args pmt_args = {};
- struct vidtv_psi_sdt_write_args sdt_args = {};
-
- u32 nbytes; /* the number of bytes written by this function */
+ struct vidtv_mux_pid_ctx *nit_ctx;
+ struct vidtv_mux_pid_ctx *eit_ctx;
+ u32 nbytes;
u16 pmt_pid;
u32 i;
pat_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_PAT_PID);
sdt_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_SDT_PID);
+ nit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_NIT_PID);
+ eit_ctx = vidtv_mux_get_pid_ctx(m, VIDTV_EIT_PID);
- pat_args.buf = m->mux_buf;
pat_args.offset = m->mux_buf_offset;
- pat_args.pat = m->si.pat;
- pat_args.buf_sz = m->mux_buf_sz;
pat_args.continuity_counter = &pat_ctx->cc;
- m->mux_buf_offset += vidtv_psi_pat_write_into(pat_args);
+ m->mux_buf_offset += vidtv_psi_pat_write_into(&pat_args);
- for (i = 0; i < m->si.pat->programs; ++i) {
+ for (i = 0; i < m->si.pat->num_pmt; ++i) {
pmt_pid = vidtv_psi_pmt_get_pid(m->si.pmt_secs[i],
m->si.pat);
pmt_ctx = vidtv_mux_get_pid_ctx(m, pmt_pid);
- pmt_args.buf = m->mux_buf;
pmt_args.offset = m->mux_buf_offset;
pmt_args.pmt = m->si.pmt_secs[i];
pmt_args.pid = pmt_pid;
- pmt_args.buf_sz = m->mux_buf_sz;
pmt_args.continuity_counter = &pmt_ctx->cc;
- pmt_args.pcr_pid = m->pcr_pid;
/* write each section into buffer */
- m->mux_buf_offset += vidtv_psi_pmt_write_into(pmt_args);
+ m->mux_buf_offset += vidtv_psi_pmt_write_into(&pmt_args);
}
- sdt_args.buf = m->mux_buf;
sdt_args.offset = m->mux_buf_offset;
- sdt_args.sdt = m->si.sdt;
- sdt_args.buf_sz = m->mux_buf_sz;
sdt_args.continuity_counter = &sdt_ctx->cc;
- m->mux_buf_offset += vidtv_psi_sdt_write_into(sdt_args);
+ m->mux_buf_offset += vidtv_psi_sdt_write_into(&sdt_args);
+
+ nit_args.offset = m->mux_buf_offset;
+ nit_args.continuity_counter = &nit_ctx->cc;
+
+ m->mux_buf_offset += vidtv_psi_nit_write_into(&nit_args);
+
+ eit_args.offset = m->mux_buf_offset;
+ eit_args.continuity_counter = &eit_ctx->cc;
+
+ m->mux_buf_offset += vidtv_psi_eit_write_into(&eit_args);
nbytes = m->mux_buf_offset - initial_offset;
static u32 vidtv_mux_packetize_access_units(struct vidtv_mux *m,
struct vidtv_encoder *e)
{
- u32 nbytes = 0;
-
- struct pes_write_args args = {};
- u32 initial_offset = m->mux_buf_offset;
+ struct pes_write_args args = {
+ .dest_buf = m->mux_buf,
+ .dest_buf_sz = m->mux_buf_sz,
+ .pid = be16_to_cpu(e->es_pid),
+ .encoder_id = e->id,
+ .stream_id = be16_to_cpu(e->stream_id),
+ .send_pts = true, /* forbidden value '01'... */
+ .send_dts = false, /* ...for PTS_DTS flags */
+ };
struct vidtv_access_unit *au = e->access_units;
-
+ u32 initial_offset = m->mux_buf_offset;
+ struct vidtv_mux_pid_ctx *pid_ctx;
+ u32 nbytes = 0;
u8 *buf = NULL;
- struct vidtv_mux_pid_ctx *pid_ctx = vidtv_mux_create_pid_ctx_once(m,
- be16_to_cpu(e->es_pid));
- args.dest_buf = m->mux_buf;
- args.dest_buf_sz = m->mux_buf_sz;
- args.pid = be16_to_cpu(e->es_pid);
- args.encoder_id = e->id;
+ /* see SMPTE 302M clause 6.4 */
+ if (args.encoder_id == S302M) {
+ args.send_dts = false;
+ args.send_pts = true;
+ }
+
+ pid_ctx = vidtv_mux_create_pid_ctx_once(m, be16_to_cpu(e->es_pid));
args.continuity_counter = &pid_ctx->cc;
- args.stream_id = be16_to_cpu(e->stream_id);
- args.send_pts = true;
while (au) {
buf = e->encoder_buf + au->offset;
args.pts = au->pts;
args.pcr = m->timing.clk;
- m->mux_buf_offset += vidtv_pes_write_into(args);
+ m->mux_buf_offset += vidtv_pes_write_into(&args);
au = au->next;
}
static u32 vidtv_mux_poll_encoders(struct vidtv_mux *m)
{
- u32 nbytes = 0;
- u32 au_nbytes;
struct vidtv_channel *cur_chnl = m->channels;
struct vidtv_encoder *e = NULL;
+ u32 nbytes = 0;
+ u32 au_nbytes;
while (cur_chnl) {
e = cur_chnl->encoders;
static u32 vidtv_mux_pad_with_nulls(struct vidtv_mux *m, u32 npkts)
{
- struct null_packet_write_args args = {};
+ struct null_packet_write_args args = {
+ .dest_buf = m->mux_buf,
+ .buf_sz = m->mux_buf_sz,
+ .dest_offset = m->mux_buf_offset,
+ };
u32 initial_offset = m->mux_buf_offset;
- u32 nbytes; /* the number of bytes written by this function */
- u32 i;
struct vidtv_mux_pid_ctx *ctx;
+ u32 nbytes;
+ u32 i;
ctx = vidtv_mux_get_pid_ctx(m, TS_NULL_PACKET_PID);
- args.dest_buf = m->mux_buf;
- args.buf_sz = m->mux_buf_sz;
args.continuity_counter = &ctx->cc;
- args.dest_offset = m->mux_buf_offset;
for (i = 0; i < npkts; ++i) {
m->mux_buf_offset += vidtv_ts_null_write_into(args);
struct vidtv_mux,
mpeg_thread);
struct dtv_frontend_properties *c = &m->fe->dtv_property_cache;
+ u32 tot_bits = 0;
u32 nbytes;
u32 npkts;
- u32 tot_bits = 0;
while (m->streaming) {
nbytes = 0;
struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe,
struct device *dev,
- struct vidtv_mux_init_args args)
+ struct vidtv_mux_init_args *args)
{
- struct vidtv_mux *m = kzalloc(sizeof(*m), GFP_KERNEL);
+ struct vidtv_mux *m;
+
+ m = kzalloc(sizeof(*m), GFP_KERNEL);
+ if (!m)
+ return NULL;
m->dev = dev;
m->fe = fe;
- m->timing.pcr_period_usecs = args.pcr_period_usecs;
- m->timing.si_period_usecs = args.si_period_usecs;
+ m->timing.pcr_period_usecs = args->pcr_period_usecs;
+ m->timing.si_period_usecs = args->si_period_usecs;
+
+ m->mux_rate_kbytes_sec = args->mux_rate_kbytes_sec;
- m->mux_rate_kbytes_sec = args.mux_rate_kbytes_sec;
+ m->on_new_packets_available_cb = args->on_new_packets_available_cb;
- m->on_new_packets_available_cb = args.on_new_packets_available_cb;
+ m->mux_buf = vzalloc(args->mux_buf_sz);
+ if (!m->mux_buf)
+ goto free_mux;
- m->mux_buf = vzalloc(args.mux_buf_sz);
- m->mux_buf_sz = args.mux_buf_sz;
+ m->mux_buf_sz = args->mux_buf_sz;
- m->pcr_pid = args.pcr_pid;
- m->transport_stream_id = args.transport_stream_id;
- m->priv = args.priv;
+ m->pcr_pid = args->pcr_pid;
+ m->transport_stream_id = args->transport_stream_id;
+ m->priv = args->priv;
+ m->network_id = args->network_id;
+ m->network_name = kstrdup(args->network_name, GFP_KERNEL);
m->timing.current_jiffies = get_jiffies_64();
- if (args.channels)
- m->channels = args.channels;
+ if (args->channels)
+ m->channels = args->channels;
else
- vidtv_channels_init(m);
+ if (vidtv_channels_init(m) < 0)
+ goto free_mux_buf;
/* will alloc data for pmt_sections after initializing pat */
- vidtv_channel_si_init(m);
+ if (vidtv_channel_si_init(m) < 0)
+ goto free_channels;
INIT_WORK(&m->mpeg_thread, vidtv_mux_tick);
- vidtv_mux_pid_ctx_init(m);
+ if (vidtv_mux_pid_ctx_init(m) < 0)
+ goto free_channel_si;
return m;
+
+free_channel_si:
+ vidtv_channel_si_destroy(m);
+free_channels:
+ vidtv_channels_destroy(m);
+free_mux_buf:
+ vfree(m->mux_buf);
+free_mux:
+ kfree(m);
+ return NULL;
}
void vidtv_mux_destroy(struct vidtv_mux *m)
vidtv_mux_pid_ctx_destroy(m);
vidtv_channel_si_destroy(m);
vidtv_channels_destroy(m);
+ kfree(m->network_name);
vfree(m->mux_buf);
kfree(m);
}
#ifndef VIDTV_MUX_H
#define VIDTV_MUX_H
-#include <linux/types.h>
#include <linux/hashtable.h>
+#include <linux/types.h>
#include <linux/workqueue.h>
+
#include <media/dvb_frontend.h>
#include "vidtv_psi.h"
* @pat: The PAT in use by the muxer.
* @pmt_secs: The PMT sections in use by the muxer. One for each program in the PAT.
* @sdt: The SDT in use by the muxer.
+ * @nit: The NIT in use by the muxer.
+ * @eit: the EIT in use by the muxer.
*/
struct vidtv_mux_si {
/* the SI tables */
struct vidtv_psi_table_pat *pat;
struct vidtv_psi_table_pmt **pmt_secs; /* the PMT sections */
struct vidtv_psi_table_sdt *sdt;
+ struct vidtv_psi_table_nit *nit;
+ struct vidtv_psi_table_eit *eit;
};
/**
/**
* struct vidtv_mux - A muxer abstraction loosely based in libavcodec/mpegtsenc.c
- * @mux_rate_kbytes_sec: The bit rate for the TS, in kbytes.
+ * @fe: The frontend structure allocated by the muxer.
+ * @dev: pointer to struct device.
* @timing: Keeps track of timing related information.
+ * @mux_rate_kbytes_sec: The bit rate for the TS, in kbytes.
* @pid_ctx: A hash table to keep track of per-PID metadata.
* @on_new_packets_available_cb: A callback to inform of new TS packets ready.
* @mux_buf: A pointer to a buffer for this muxer. TS packets are stored there
* @pcr_pid: The TS PID used for the PSI packets. All channels will share the
* same PCR.
* @transport_stream_id: The transport stream ID
+ * @network_id: The network ID
+ * @network_name: The network name
* @priv: Private data.
*/
struct vidtv_mux {
u16 pcr_pid;
u16 transport_stream_id;
+ u16 network_id;
+ char *network_name;
void *priv;
};
* same PCR.
* @transport_stream_id: The transport stream ID
* @channels: an optional list of channels to use
+ * @network_id: The network ID
+ * @network_name: The network name
* @priv: Private data.
*/
struct vidtv_mux_init_args {
u16 pcr_pid;
u16 transport_stream_id;
struct vidtv_channel *channels;
+ u16 network_id;
+ char *network_name;
void *priv;
};
struct vidtv_mux *vidtv_mux_init(struct dvb_frontend *fe,
struct device *dev,
- struct vidtv_mux_init_args args);
+ struct vidtv_mux_init_args *args);
void vidtv_mux_destroy(struct vidtv_mux *m);
void vidtv_mux_start_thread(struct vidtv_mux *m);
#include <linux/types.h>
#include <linux/printk.h>
#include <linux/ratelimit.h>
-#include <asm/byteorder.h>
#include "vidtv_pes.h"
#include "vidtv_common.h"
return len;
}
-static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args args)
+static u32 vidtv_pes_write_header_stuffing(struct pes_header_write_args *args)
{
/*
* This is a fixed 8-bit value equal to '0xFF' that can be inserted
* It is discarded by the decoder. No more than 32 stuffing bytes shall
* be present in one PES packet header.
*/
- if (args.n_pes_h_s_bytes > PES_HEADER_MAX_STUFFING_BYTES) {
+ if (args->n_pes_h_s_bytes > PES_HEADER_MAX_STUFFING_BYTES) {
pr_warn_ratelimited("More than %d stuffing bytes in PES packet header\n",
PES_HEADER_MAX_STUFFING_BYTES);
- args.n_pes_h_s_bytes = PES_HEADER_MAX_STUFFING_BYTES;
+ args->n_pes_h_s_bytes = PES_HEADER_MAX_STUFFING_BYTES;
}
- return vidtv_memset(args.dest_buf,
- args.dest_offset,
- args.dest_buf_sz,
+ return vidtv_memset(args->dest_buf,
+ args->dest_offset,
+ args->dest_buf_sz,
TS_FILL_BYTE,
- args.n_pes_h_s_bytes);
+ args->n_pes_h_s_bytes);
}
-static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args args)
+static u32 vidtv_pes_write_pts_dts(struct pes_header_write_args *args)
{
u32 nbytes = 0; /* the number of bytes written by this function */
u64 mask2;
u64 mask3;
- if (!args.send_pts && args.send_dts)
+ if (!args->send_pts && args->send_dts)
return 0;
mask1 = GENMASK_ULL(32, 30);
mask3 = GENMASK_ULL(14, 0);
/* see ISO/IEC 13818-1 : 2000 p. 32 */
- if (args.send_pts && args.send_dts) {
- pts_dts.pts1 = (0x3 << 4) | ((args.pts & mask1) >> 29) | 0x1;
- pts_dts.pts2 = cpu_to_be16(((args.pts & mask2) >> 14) | 0x1);
- pts_dts.pts3 = cpu_to_be16(((args.pts & mask3) << 1) | 0x1);
+ if (args->send_pts && args->send_dts) {
+ pts_dts.pts1 = (0x3 << 4) | ((args->pts & mask1) >> 29) | 0x1;
+ pts_dts.pts2 = cpu_to_be16(((args->pts & mask2) >> 14) | 0x1);
+ pts_dts.pts3 = cpu_to_be16(((args->pts & mask3) << 1) | 0x1);
- pts_dts.dts1 = (0x1 << 4) | ((args.dts & mask1) >> 29) | 0x1;
- pts_dts.dts2 = cpu_to_be16(((args.dts & mask2) >> 14) | 0x1);
- pts_dts.dts3 = cpu_to_be16(((args.dts & mask3) << 1) | 0x1);
+ pts_dts.dts1 = (0x1 << 4) | ((args->dts & mask1) >> 29) | 0x1;
+ pts_dts.dts2 = cpu_to_be16(((args->dts & mask2) >> 14) | 0x1);
+ pts_dts.dts3 = cpu_to_be16(((args->dts & mask3) << 1) | 0x1);
op = &pts_dts;
op_sz = sizeof(pts_dts);
- } else if (args.send_pts) {
- pts.pts1 = (0x1 << 5) | ((args.pts & mask1) >> 29) | 0x1;
- pts.pts2 = cpu_to_be16(((args.pts & mask2) >> 14) | 0x1);
- pts.pts3 = cpu_to_be16(((args.pts & mask3) << 1) | 0x1);
+ } else if (args->send_pts) {
+ pts.pts1 = (0x1 << 5) | ((args->pts & mask1) >> 29) | 0x1;
+ pts.pts2 = cpu_to_be16(((args->pts & mask2) >> 14) | 0x1);
+ pts.pts3 = cpu_to_be16(((args->pts & mask3) << 1) | 0x1);
op = &pts;
op_sz = sizeof(pts);
}
/* copy PTS/DTS optional */
- nbytes += vidtv_memcpy(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ nbytes += vidtv_memcpy(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
op,
op_sz);
return nbytes;
}
-static u32 vidtv_pes_write_h(struct pes_header_write_args args)
+static u32 vidtv_pes_write_h(struct pes_header_write_args *args)
{
u32 nbytes = 0; /* the number of bytes written by this function */
struct vidtv_mpeg_pes pes_header = {};
struct vidtv_pes_optional pes_optional = {};
- struct pes_header_write_args pts_dts_args = args;
- u32 stream_id = (args.encoder_id == S302M) ? PRIVATE_STREAM_1_ID : args.stream_id;
+ struct pes_header_write_args pts_dts_args;
+ u32 stream_id = (args->encoder_id == S302M) ? PRIVATE_STREAM_1_ID : args->stream_id;
u16 pes_opt_bitfield = 0x01 << 15;
pes_header.bitfield = cpu_to_be32((PES_START_CODE_PREFIX << 8) | stream_id);
- pes_header.length = cpu_to_be16(vidtv_pes_op_get_len(args.send_pts,
- args.send_dts) +
- args.access_unit_len);
+ pes_header.length = cpu_to_be16(vidtv_pes_op_get_len(args->send_pts,
+ args->send_dts) +
+ args->access_unit_len);
- if (args.send_pts && args.send_dts)
+ if (args->send_pts && args->send_dts)
pes_opt_bitfield |= (0x3 << 6);
- else if (args.send_pts)
+ else if (args->send_pts)
pes_opt_bitfield |= (0x1 << 7);
pes_optional.bitfield = cpu_to_be16(pes_opt_bitfield);
- pes_optional.length = vidtv_pes_op_get_len(args.send_pts, args.send_dts) +
- args.n_pes_h_s_bytes -
+ pes_optional.length = vidtv_pes_op_get_len(args->send_pts, args->send_dts) +
+ args->n_pes_h_s_bytes -
sizeof(struct vidtv_pes_optional);
/* copy header */
- nbytes += vidtv_memcpy(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ nbytes += vidtv_memcpy(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
&pes_header,
sizeof(pes_header));
/* copy optional header bits */
- nbytes += vidtv_memcpy(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ nbytes += vidtv_memcpy(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
&pes_optional,
sizeof(pes_optional));
/* copy the timing information */
- pts_dts_args.dest_offset = args.dest_offset + nbytes;
- nbytes += vidtv_pes_write_pts_dts(pts_dts_args);
+ pts_dts_args = *args;
+ pts_dts_args.dest_offset = args->dest_offset + nbytes;
+ nbytes += vidtv_pes_write_pts_dts(&pts_dts_args);
/* write any PES header stuffing */
nbytes += vidtv_pes_write_header_stuffing(args);
return nbytes;
}
-u32 vidtv_pes_write_into(struct pes_write_args args)
+u32 vidtv_pes_write_into(struct pes_write_args *args)
{
- u32 unaligned_bytes = (args.dest_offset % TS_PACKET_LEN);
- struct pes_ts_header_write_args ts_header_args = {};
- struct pes_header_write_args pes_header_args = {};
- u32 remaining_len = args.access_unit_len;
+ u32 unaligned_bytes = (args->dest_offset % TS_PACKET_LEN);
+ struct pes_ts_header_write_args ts_header_args = {
+ .dest_buf = args->dest_buf,
+ .dest_buf_sz = args->dest_buf_sz,
+ .pid = args->pid,
+ .pcr = args->pcr,
+ .continuity_counter = args->continuity_counter,
+ };
+ struct pes_header_write_args pes_header_args = {
+ .dest_buf = args->dest_buf,
+ .dest_buf_sz = args->dest_buf_sz,
+ .encoder_id = args->encoder_id,
+ .send_pts = args->send_pts,
+ .pts = args->pts,
+ .send_dts = args->send_dts,
+ .dts = args->dts,
+ .stream_id = args->stream_id,
+ .n_pes_h_s_bytes = args->n_pes_h_s_bytes,
+ .access_unit_len = args->access_unit_len,
+ };
+ u32 remaining_len = args->access_unit_len;
bool wrote_pes_header = false;
- u64 last_pcr = args.pcr;
+ u64 last_pcr = args->pcr;
bool need_pcr = true;
u32 available_space;
u32 payload_size;
pr_warn_ratelimited("buffer is misaligned, while starting PES\n");
/* forcibly align and hope for the best */
- nbytes += vidtv_memset(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ nbytes += vidtv_memset(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
TS_FILL_BYTE,
TS_PACKET_LEN - unaligned_bytes);
}
- if (args.send_dts && !args.send_pts) {
- pr_warn_ratelimited("forbidden value '01' for PTS_DTS flags\n");
- args.send_pts = true;
- args.pts = args.dts;
- }
-
- /* see SMPTE 302M clause 6.4 */
- if (args.encoder_id == S302M) {
- args.send_dts = false;
- args.send_pts = true;
- }
-
while (remaining_len) {
available_space = TS_PAYLOAD_LEN;
/*
* the space needed for the TS header _and_ for the PES header
*/
if (!wrote_pes_header)
- available_space -= vidtv_pes_h_get_len(args.send_pts,
- args.send_dts);
+ available_space -= vidtv_pes_h_get_len(args->send_pts,
+ args->send_dts);
/*
* if the encoder has inserted stuffing bytes in the PES
* header, account for them.
*/
- available_space -= args.n_pes_h_s_bytes;
+ available_space -= args->n_pes_h_s_bytes;
/* Take the extra adaptation into account if need to send PCR */
if (need_pcr) {
}
/* write ts header */
- ts_header_args.dest_buf = args.dest_buf;
- ts_header_args.dest_offset = args.dest_offset + nbytes;
- ts_header_args.dest_buf_sz = args.dest_buf_sz;
- ts_header_args.pid = args.pid;
- ts_header_args.pcr = args.pcr;
- ts_header_args.continuity_counter = args.continuity_counter;
- ts_header_args.wrote_pes_header = wrote_pes_header;
- ts_header_args.n_stuffing_bytes = stuff_bytes;
+ ts_header_args.dest_offset = args->dest_offset + nbytes;
+ ts_header_args.wrote_pes_header = wrote_pes_header;
+ ts_header_args.n_stuffing_bytes = stuff_bytes;
nbytes += vidtv_pes_write_ts_h(ts_header_args, need_pcr,
&last_pcr);
if (!wrote_pes_header) {
/* write the PES header only once */
- pes_header_args.dest_buf = args.dest_buf;
-
- pes_header_args.dest_offset = args.dest_offset +
- nbytes;
-
- pes_header_args.dest_buf_sz = args.dest_buf_sz;
- pes_header_args.encoder_id = args.encoder_id;
- pes_header_args.send_pts = args.send_pts;
- pes_header_args.pts = args.pts;
- pes_header_args.send_dts = args.send_dts;
- pes_header_args.dts = args.dts;
- pes_header_args.stream_id = args.stream_id;
- pes_header_args.n_pes_h_s_bytes = args.n_pes_h_s_bytes;
- pes_header_args.access_unit_len = args.access_unit_len;
-
- nbytes += vidtv_pes_write_h(pes_header_args);
- wrote_pes_header = true;
+ pes_header_args.dest_offset = args->dest_offset +
+ nbytes;
+ nbytes += vidtv_pes_write_h(&pes_header_args);
+ wrote_pes_header = true;
}
/* write as much of the payload as we possibly can */
- nbytes += vidtv_memcpy(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
- args.from,
+ nbytes += vidtv_memcpy(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
+ args->from,
payload_size);
- args.from += payload_size;
+ args->from += payload_size;
remaining_len -= payload_size;
}
#ifndef VIDTV_PES_H
#define VIDTV_PES_H
-#include <asm/byteorder.h>
#include <linux/types.h>
#include "vidtv_common.h"
* @dest_buf_sz: The size of the dest_buffer
* @pid: The PID to use for the TS packets.
* @continuity_counter: Incremented on every new TS packet.
- * @n_pes_h_s_bytes: Padding bytes. Might be used by an encoder if needed, gets
+ * @wrote_pes_header: Flag to indicate that the PES header was written
+ * @n_stuffing_bytes: Padding bytes. Might be used by an encoder if needed, gets
* discarded by the decoder.
+ * @pcr: counter driven by a 27Mhz clock.
*/
struct pes_ts_header_write_args {
void *dest_buf;
* @dts: DTS value to send.
* @n_pes_h_s_bytes: Padding bytes. Might be used by an encoder if needed, gets
* discarded by the decoder.
+ * @pcr: counter driven by a 27Mhz clock.
*/
struct pes_write_args {
void *dest_buf;
* equal to the size of the access unit, since we need space for PES headers, TS headers
* and padding bytes, if any.
*/
-u32 vidtv_pes_write_into(struct pes_write_args args);
+u32 vidtv_pes_write_into(struct pes_write_args *args);
#endif // VIDTV_PES_H
* technically be broken into one or more sections, we do not do this here,
* hence 'table' and 'section' are interchangeable for vidtv.
*
- * This code currently supports three tables: PAT, PMT and SDT. These are the
- * bare minimum to get userspace to recognize our MPEG transport stream. It can
- * be extended to support more PSI tables in the future.
- *
* Copyright (C) 2020 Daniel W. S. Almeida
*/
#define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/slab.h>
+#include <linux/bcd.h>
#include <linux/crc32.h>
-#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/ktime.h>
#include <linux/printk.h>
#include <linux/ratelimit.h>
+#include <linux/slab.h>
#include <linux/string.h>
-#include <asm/byteorder.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/types.h>
-#include "vidtv_psi.h"
#include "vidtv_common.h"
+#include "vidtv_psi.h"
#include "vidtv_ts.h"
#define CRC_SIZE_IN_BYTES 4
#define MAX_VERSION_NUM 32
+#define INITIAL_CRC 0xffffffff
+#define ISO_LANGUAGE_CODE_LEN 3
static const u32 CRC_LUT[256] = {
/* from libdvbv5 */
0xbcb4666d, 0xb8757bda, 0xb5365d03, 0xb1f740b4
};
-static inline u32 dvb_crc32(u32 crc, u8 *data, u32 len)
+static u32 dvb_crc32(u32 crc, u8 *data, u32 len)
{
/* from libdvbv5 */
while (len--)
h->version++;
}
-static inline u16 vidtv_psi_sdt_serv_get_desc_loop_len(struct vidtv_psi_table_sdt_service *s)
-{
- u16 mask;
- u16 ret;
-
- mask = GENMASK(11, 0);
-
- ret = be16_to_cpu(s->bitfield) & mask;
- return ret;
-}
-
-static inline u16 vidtv_psi_pmt_stream_get_desc_loop_len(struct vidtv_psi_table_pmt_stream *s)
-{
- u16 mask;
- u16 ret;
-
- mask = GENMASK(9, 0);
-
- ret = be16_to_cpu(s->bitfield2) & mask;
- return ret;
-}
-
-static inline u16 vidtv_psi_pmt_get_desc_loop_len(struct vidtv_psi_table_pmt *p)
-{
- u16 mask;
- u16 ret;
-
- mask = GENMASK(9, 0);
-
- ret = be16_to_cpu(p->bitfield2) & mask;
- return ret;
-}
-
-static inline u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h)
+static u16 vidtv_psi_get_sec_len(struct vidtv_psi_table_header *h)
{
u16 mask;
u16 ret;
return ret;
}
-inline u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p)
+u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p)
{
u16 mask;
u16 ret;
return ret;
}
-inline u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s)
+u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s)
{
u16 mask;
u16 ret;
return ret;
}
-static inline void vidtv_psi_set_desc_loop_len(__be16 *bitfield, u16 new_len, u8 desc_len_nbits)
+static void vidtv_psi_set_desc_loop_len(__be16 *bitfield, u16 new_len,
+ u8 desc_len_nbits)
{
- u16 mask;
__be16 new;
+ u16 mask;
mask = GENMASK(15, desc_len_nbits);
h->bitfield = new;
}
-static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args args)
+/*
+ * Packetize PSI sections into TS packets:
+ * push a TS header (4bytes) every 184 bytes
+ * manage the continuity_counter
+ * add stuffing (i.e. padding bytes) after the CRC
+ */
+static u32 vidtv_psi_ts_psi_write_into(struct psi_write_args *args)
{
- /*
- * Packetize PSI sections into TS packets:
- * push a TS header (4bytes) every 184 bytes
- * manage the continuity_counter
- * add stuffing (i.e. padding bytes) after the CRC
- */
-
- u32 nbytes_past_boundary = (args.dest_offset % TS_PACKET_LEN);
+ struct vidtv_mpeg_ts ts_header = {
+ .sync_byte = TS_SYNC_BYTE,
+ .bitfield = cpu_to_be16((args->new_psi_section << 14) | args->pid),
+ .scrambling = 0,
+ .payload = 1,
+ .adaptation_field = 0, /* no adaptation field */
+ };
+ u32 nbytes_past_boundary = (args->dest_offset % TS_PACKET_LEN);
bool aligned = (nbytes_past_boundary == 0);
- struct vidtv_mpeg_ts ts_header = {};
-
- /* number of bytes written by this function */
- u32 nbytes = 0;
- /* how much there is left to write */
- u32 remaining_len = args.len;
- /* how much we can be written in this packet */
+ u32 remaining_len = args->len;
u32 payload_write_len = 0;
- /* where we are in the source */
u32 payload_offset = 0;
+ u32 nbytes = 0;
- const u16 PAYLOAD_START = args.new_psi_section;
-
- if (!args.crc && !args.is_crc)
+ if (!args->crc && !args->is_crc)
pr_warn_ratelimited("Missing CRC for chunk\n");
- if (args.crc)
- *args.crc = dvb_crc32(*args.crc, args.from, args.len);
+ if (args->crc)
+ *args->crc = dvb_crc32(*args->crc, args->from, args->len);
- if (args.new_psi_section && !aligned) {
+ if (args->new_psi_section && !aligned) {
pr_warn_ratelimited("Cannot write a new PSI section in a misaligned buffer\n");
/* forcibly align and hope for the best */
- nbytes += vidtv_memset(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ nbytes += vidtv_memset(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
TS_FILL_BYTE,
TS_PACKET_LEN - nbytes_past_boundary);
}
while (remaining_len) {
- nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN;
+ nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN;
aligned = (nbytes_past_boundary == 0);
if (aligned) {
/* if at a packet boundary, write a new TS header */
- ts_header.sync_byte = TS_SYNC_BYTE;
- ts_header.bitfield = cpu_to_be16((PAYLOAD_START << 14) | args.pid);
- ts_header.scrambling = 0;
- ts_header.continuity_counter = *args.continuity_counter;
- ts_header.payload = 1;
- /* no adaptation field */
- ts_header.adaptation_field = 0;
-
- /* copy the header */
- nbytes += vidtv_memcpy(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ ts_header.continuity_counter = *args->continuity_counter;
+
+ nbytes += vidtv_memcpy(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
&ts_header,
sizeof(ts_header));
/*
* This will trigger a discontinuity if the buffer is full,
* effectively dropping the packet.
*/
- vidtv_ts_inc_cc(args.continuity_counter);
+ vidtv_ts_inc_cc(args->continuity_counter);
}
/* write the pointer_field in the first byte of the payload */
- if (args.new_psi_section)
- nbytes += vidtv_memset(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ if (args->new_psi_section)
+ nbytes += vidtv_memset(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
0x0,
1);
/* write as much of the payload as possible */
- nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN;
+ nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN;
payload_write_len = min(TS_PACKET_LEN - nbytes_past_boundary, remaining_len);
- nbytes += vidtv_memcpy(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
- args.from + payload_offset,
+ nbytes += vidtv_memcpy(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
+ args->from + payload_offset,
payload_write_len);
/* 'payload_write_len' written from a total of 'len' requested*/
* fill the rest of the packet if there is any remaining space unused
*/
- nbytes_past_boundary = (args.dest_offset + nbytes) % TS_PACKET_LEN;
+ nbytes_past_boundary = (args->dest_offset + nbytes) % TS_PACKET_LEN;
- if (args.is_crc)
- nbytes += vidtv_memset(args.dest_buf,
- args.dest_offset + nbytes,
- args.dest_buf_sz,
+ if (args->is_crc)
+ nbytes += vidtv_memset(args->dest_buf,
+ args->dest_offset + nbytes,
+ args->dest_buf_sz,
TS_FILL_BYTE,
TS_PACKET_LEN - nbytes_past_boundary);
return nbytes;
}
-static u32 table_section_crc32_write_into(struct crc32_write_args args)
+static u32 table_section_crc32_write_into(struct crc32_write_args *args)
{
+ struct psi_write_args psi_args = {
+ .dest_buf = args->dest_buf,
+ .from = &args->crc,
+ .len = CRC_SIZE_IN_BYTES,
+ .dest_offset = args->dest_offset,
+ .pid = args->pid,
+ .new_psi_section = false,
+ .continuity_counter = args->continuity_counter,
+ .is_crc = true,
+ .dest_buf_sz = args->dest_buf_sz,
+ };
+
/* the CRC is the last entry in the section */
- u32 nbytes = 0;
- struct psi_write_args psi_args = {};
- psi_args.dest_buf = args.dest_buf;
- psi_args.from = &args.crc;
- psi_args.len = CRC_SIZE_IN_BYTES;
- psi_args.dest_offset = args.dest_offset;
- psi_args.pid = args.pid;
- psi_args.new_psi_section = false;
- psi_args.continuity_counter = args.continuity_counter;
- psi_args.is_crc = true;
- psi_args.dest_buf_sz = args.dest_buf_sz;
+ return vidtv_psi_ts_psi_write_into(&psi_args);
+}
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+static void vidtv_psi_desc_chain(struct vidtv_psi_desc *head, struct vidtv_psi_desc *desc)
+{
+ if (head) {
+ while (head->next)
+ head = head->next;
- return nbytes;
+ head->next = desc;
+ }
}
struct vidtv_psi_desc_service *vidtv_psi_service_desc_init(struct vidtv_psi_desc *head,
u32 provider_name_len = provider_name ? strlen(provider_name) : 0;
desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return NULL;
desc->type = SERVICE_DESCRIPTOR;
if (provider_name && provider_name_len)
desc->provider_name = kstrdup(provider_name, GFP_KERNEL);
- if (head) {
- while (head->next)
- head = head->next;
-
- head->next = (struct vidtv_psi_desc *)desc;
- }
+ vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc);
return desc;
}
struct vidtv_psi_desc_registration *desc;
desc = kzalloc(sizeof(*desc) + sizeof(format_id) + additional_info_len, GFP_KERNEL);
+ if (!desc)
+ return NULL;
desc->type = REGISTRATION_DESCRIPTOR;
additional_ident_info,
additional_info_len);
- if (head) {
- while (head->next)
- head = head->next;
+ vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc);
+ return desc;
+}
- head->next = (struct vidtv_psi_desc *)desc;
+struct vidtv_psi_desc_network_name
+*vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name)
+{
+ u32 network_name_len = network_name ? strlen(network_name) : 0;
+ struct vidtv_psi_desc_network_name *desc;
+
+ desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return NULL;
+
+ desc->type = NETWORK_NAME_DESCRIPTOR;
+
+ desc->length = network_name_len;
+
+ if (network_name && network_name_len)
+ desc->network_name = kstrdup(network_name, GFP_KERNEL);
+
+ vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc);
+ return desc;
+}
+
+struct vidtv_psi_desc_service_list
+*vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head,
+ struct vidtv_psi_desc_service_list_entry *entry)
+{
+ struct vidtv_psi_desc_service_list_entry *curr_e = NULL;
+ struct vidtv_psi_desc_service_list_entry *head_e = NULL;
+ struct vidtv_psi_desc_service_list_entry *prev_e = NULL;
+ struct vidtv_psi_desc_service_list *desc;
+ u16 length = 0;
+
+ desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return NULL;
+
+ desc->type = SERVICE_LIST_DESCRIPTOR;
+
+ while (entry) {
+ curr_e = kzalloc(sizeof(*curr_e), GFP_KERNEL);
+ if (!curr_e) {
+ while (head_e) {
+ curr_e = head_e;
+ head_e = head_e->next;
+ kfree(curr_e);
+ }
+ kfree(desc);
+ return NULL;
+ }
+
+ curr_e->service_id = entry->service_id;
+ curr_e->service_type = entry->service_type;
+
+ length += sizeof(struct vidtv_psi_desc_service_list_entry) -
+ sizeof(struct vidtv_psi_desc_service_list_entry *);
+
+ if (!head_e)
+ head_e = curr_e;
+ if (prev_e)
+ prev_e->next = curr_e;
+
+ prev_e = curr_e;
+ entry = entry->next;
}
+ desc->length = length;
+ desc->service_list = head_e;
+
+ vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc);
+ return desc;
+}
+
+struct vidtv_psi_desc_short_event
+*vidtv_psi_short_event_desc_init(struct vidtv_psi_desc *head,
+ char *iso_language_code,
+ char *event_name,
+ char *text)
+{
+ u32 iso_len = iso_language_code ? strlen(iso_language_code) : 0;
+ u32 event_name_len = event_name ? strlen(event_name) : 0;
+ struct vidtv_psi_desc_short_event *desc;
+ u32 text_len = text ? strlen(text) : 0;
+
+ desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return NULL;
+
+ desc->type = SHORT_EVENT_DESCRIPTOR;
+
+ desc->length = ISO_LANGUAGE_CODE_LEN +
+ sizeof_field(struct vidtv_psi_desc_short_event, event_name_len) +
+ event_name_len +
+ sizeof_field(struct vidtv_psi_desc_short_event, text_len) +
+ text_len;
+
+ desc->event_name_len = event_name_len;
+ desc->text_len = text_len;
+
+ if (iso_len != ISO_LANGUAGE_CODE_LEN)
+ iso_language_code = "eng";
+
+ desc->iso_language_code = kstrdup(iso_language_code, GFP_KERNEL);
+
+ if (event_name && event_name_len)
+ desc->event_name = kstrdup(event_name, GFP_KERNEL);
+
+ if (text && text_len)
+ desc->text = kstrdup(text, GFP_KERNEL);
+
+ vidtv_psi_desc_chain(head, (struct vidtv_psi_desc *)desc);
return desc;
}
struct vidtv_psi_desc *vidtv_psi_desc_clone(struct vidtv_psi_desc *desc)
{
+ struct vidtv_psi_desc_network_name *desc_network_name;
+ struct vidtv_psi_desc_service_list *desc_service_list;
+ struct vidtv_psi_desc_short_event *desc_short_event;
+ struct vidtv_psi_desc_service *service;
struct vidtv_psi_desc *head = NULL;
struct vidtv_psi_desc *prev = NULL;
struct vidtv_psi_desc *curr = NULL;
- struct vidtv_psi_desc_service *service;
-
while (desc) {
switch (desc->type) {
case SERVICE_DESCRIPTOR:
service = (struct vidtv_psi_desc_service *)desc;
curr = (struct vidtv_psi_desc *)
- vidtv_psi_service_desc_init(head,
- service->service_type,
- service->service_name,
- service->provider_name);
+ vidtv_psi_service_desc_init(head,
+ service->service_type,
+ service->service_name,
+ service->provider_name);
+ break;
+
+ case NETWORK_NAME_DESCRIPTOR:
+ desc_network_name = (struct vidtv_psi_desc_network_name *)desc;
+ curr = (struct vidtv_psi_desc *)
+ vidtv_psi_network_name_desc_init(head,
+ desc_network_name->network_name);
+ break;
+
+ case SERVICE_LIST_DESCRIPTOR:
+ desc_service_list = (struct vidtv_psi_desc_service_list *)desc;
+ curr = (struct vidtv_psi_desc *)
+ vidtv_psi_service_list_desc_init(head,
+ desc_service_list->service_list);
+ break;
+
+ case SHORT_EVENT_DESCRIPTOR:
+ desc_short_event = (struct vidtv_psi_desc_short_event *)desc;
+ curr = (struct vidtv_psi_desc *)
+ vidtv_psi_short_event_desc_init(head,
+ desc_short_event->iso_language_code,
+ desc_short_event->event_name,
+ desc_short_event->text);
break;
case REGISTRATION_DESCRIPTOR:
default:
curr = kzalloc(sizeof(*desc) + desc->length, GFP_KERNEL);
+ if (!curr)
+ return NULL;
memcpy(curr, desc, sizeof(*desc) + desc->length);
- break;
- }
+ }
- if (curr)
- curr->next = NULL;
+ if (!curr)
+ return NULL;
+
+ curr->next = NULL;
if (!head)
head = curr;
if (prev)
void vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc)
{
+ struct vidtv_psi_desc_service_list_entry *sl_entry_tmp = NULL;
+ struct vidtv_psi_desc_service_list_entry *sl_entry = NULL;
struct vidtv_psi_desc *curr = desc;
struct vidtv_psi_desc *tmp = NULL;
/* nothing to do */
break;
+ case NETWORK_NAME_DESCRIPTOR:
+ kfree(((struct vidtv_psi_desc_network_name *)tmp)->network_name);
+ break;
+
+ case SERVICE_LIST_DESCRIPTOR:
+ sl_entry = ((struct vidtv_psi_desc_service_list *)tmp)->service_list;
+ while (sl_entry) {
+ sl_entry_tmp = sl_entry;
+ sl_entry = sl_entry->next;
+ kfree(sl_entry_tmp);
+ }
+ break;
+
+ case SHORT_EVENT_DESCRIPTOR:
+ kfree(((struct vidtv_psi_desc_short_event *)tmp)->iso_language_code);
+ kfree(((struct vidtv_psi_desc_short_event *)tmp)->event_name);
+ kfree(((struct vidtv_psi_desc_short_event *)tmp)->text);
+ break;
+
default:
pr_warn_ratelimited("Possible leak: not handling descriptor type %d\n",
tmp->type);
vidtv_psi_update_version_num(&sdt->header);
}
-static u32 vidtv_psi_desc_write_into(struct desc_write_args args)
+static u32 vidtv_psi_desc_write_into(struct desc_write_args *args)
{
- /* the number of bytes written by this function */
+ struct psi_write_args psi_args = {
+ .dest_buf = args->dest_buf,
+ .from = &args->desc->type,
+ .pid = args->pid,
+ .new_psi_section = false,
+ .continuity_counter = args->continuity_counter,
+ .is_crc = false,
+ .dest_buf_sz = args->dest_buf_sz,
+ .crc = args->crc,
+ .len = sizeof_field(struct vidtv_psi_desc, type) +
+ sizeof_field(struct vidtv_psi_desc, length),
+ };
+ struct vidtv_psi_desc_service_list_entry *serv_list_entry = NULL;
u32 nbytes = 0;
- struct psi_write_args psi_args = {};
-
- psi_args.dest_buf = args.dest_buf;
- psi_args.from = &args.desc->type;
- psi_args.len = sizeof_field(struct vidtv_psi_desc, type) +
- sizeof_field(struct vidtv_psi_desc, length);
+ psi_args.dest_offset = args->dest_offset + nbytes;
- psi_args.dest_offset = args.dest_offset + nbytes;
- psi_args.pid = args.pid;
- psi_args.new_psi_section = false;
- psi_args.continuity_counter = args.continuity_counter;
- psi_args.is_crc = false;
- psi_args.dest_buf_sz = args.dest_buf_sz;
- psi_args.crc = args.crc;
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
-
- switch (args.desc->type) {
+ switch (args->desc->type) {
case SERVICE_DESCRIPTOR:
- psi_args.dest_offset = args.dest_offset + nbytes;
+ psi_args.dest_offset = args->dest_offset + nbytes;
psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_type) +
sizeof_field(struct vidtv_psi_desc_service, provider_name_len);
- psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_type;
+ psi_args.from = &((struct vidtv_psi_desc_service *)args->desc)->service_type;
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- psi_args.dest_offset = args.dest_offset + nbytes;
- psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->provider_name_len;
- psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->provider_name;
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = ((struct vidtv_psi_desc_service *)args->desc)->provider_name_len;
+ psi_args.from = ((struct vidtv_psi_desc_service *)args->desc)->provider_name;
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- psi_args.dest_offset = args.dest_offset + nbytes;
+ psi_args.dest_offset = args->dest_offset + nbytes;
psi_args.len = sizeof_field(struct vidtv_psi_desc_service, service_name_len);
- psi_args.from = &((struct vidtv_psi_desc_service *)args.desc)->service_name_len;
+ psi_args.from = &((struct vidtv_psi_desc_service *)args->desc)->service_name_len;
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- psi_args.dest_offset = args.dest_offset + nbytes;
- psi_args.len = ((struct vidtv_psi_desc_service *)args.desc)->service_name_len;
- psi_args.from = ((struct vidtv_psi_desc_service *)args.desc)->service_name;
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = ((struct vidtv_psi_desc_service *)args->desc)->service_name_len;
+ psi_args.from = ((struct vidtv_psi_desc_service *)args->desc)->service_name;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+ break;
+
+ case NETWORK_NAME_DESCRIPTOR:
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = args->desc->length;
+ psi_args.from = ((struct vidtv_psi_desc_network_name *)args->desc)->network_name;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+ break;
+
+ case SERVICE_LIST_DESCRIPTOR:
+ serv_list_entry = ((struct vidtv_psi_desc_service_list *)args->desc)->service_list;
+ while (serv_list_entry) {
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = sizeof(struct vidtv_psi_desc_service_list_entry) -
+ sizeof(struct vidtv_psi_desc_service_list_entry *);
+ psi_args.from = serv_list_entry;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ serv_list_entry = serv_list_entry->next;
+ }
+ break;
+
+ case SHORT_EVENT_DESCRIPTOR:
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = ISO_LANGUAGE_CODE_LEN;
+ psi_args.from = ((struct vidtv_psi_desc_short_event *)
+ args->desc)->iso_language_code;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, event_name_len);
+ psi_args.from = &((struct vidtv_psi_desc_short_event *)
+ args->desc)->event_name_len;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = ((struct vidtv_psi_desc_short_event *)args->desc)->event_name_len;
+ psi_args.from = ((struct vidtv_psi_desc_short_event *)args->desc)->event_name;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = sizeof_field(struct vidtv_psi_desc_short_event, text_len);
+ psi_args.from = &((struct vidtv_psi_desc_short_event *)args->desc)->text_len;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = ((struct vidtv_psi_desc_short_event *)args->desc)->text_len;
+ psi_args.from = ((struct vidtv_psi_desc_short_event *)args->desc)->text;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
break;
case REGISTRATION_DESCRIPTOR:
default:
- psi_args.dest_offset = args.dest_offset + nbytes;
- psi_args.len = args.desc->length;
- psi_args.from = &args.desc->data;
+ psi_args.dest_offset = args->dest_offset + nbytes;
+ psi_args.len = args->desc->length;
+ psi_args.from = &args->desc->data;
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
break;
}
}
static u32
-vidtv_psi_table_header_write_into(struct header_write_args args)
+vidtv_psi_table_header_write_into(struct header_write_args *args)
{
- /* the number of bytes written by this function */
- u32 nbytes = 0;
- struct psi_write_args psi_args = {};
-
- psi_args.dest_buf = args.dest_buf;
- psi_args.from = args.h;
- psi_args.len = sizeof(struct vidtv_psi_table_header);
- psi_args.dest_offset = args.dest_offset;
- psi_args.pid = args.pid;
- psi_args.new_psi_section = true;
- psi_args.continuity_counter = args.continuity_counter;
- psi_args.is_crc = false;
- psi_args.dest_buf_sz = args.dest_buf_sz;
- psi_args.crc = args.crc;
-
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
-
- return nbytes;
+ struct psi_write_args psi_args = {
+ .dest_buf = args->dest_buf,
+ .from = args->h,
+ .len = sizeof(struct vidtv_psi_table_header),
+ .dest_offset = args->dest_offset,
+ .pid = args->pid,
+ .new_psi_section = true,
+ .continuity_counter = args->continuity_counter,
+ .is_crc = false,
+ .dest_buf_sz = args->dest_buf_sz,
+ .crc = args->crc,
+ };
+
+ return vidtv_psi_ts_psi_write_into(&psi_args);
}
void
vidtv_psi_pat_table_update_sec_len(struct vidtv_psi_table_pat *pat)
{
- /* see ISO/IEC 13818-1 : 2000 p.43 */
u16 length = 0;
u32 i;
+ /* see ISO/IEC 13818-1 : 2000 p.43 */
+
/* from immediately after 'section_length' until 'last_section_number'*/
length += PAT_LEN_UNTIL_LAST_SECTION_NUMBER;
/* do not count the pointer */
- for (i = 0; i < pat->programs; ++i)
+ for (i = 0; i < pat->num_pat; ++i)
length += sizeof(struct vidtv_psi_table_pat_program) -
sizeof(struct vidtv_psi_table_pat_program *);
void vidtv_psi_pmt_table_update_sec_len(struct vidtv_psi_table_pmt *pmt)
{
- /* see ISO/IEC 13818-1 : 2000 p.46 */
- u16 length = 0;
struct vidtv_psi_table_pmt_stream *s = pmt->stream;
u16 desc_loop_len;
+ u16 length = 0;
+
+ /* see ISO/IEC 13818-1 : 2000 p.46 */
/* from immediately after 'section_length' until 'program_info_length'*/
length += PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH;
void vidtv_psi_sdt_table_update_sec_len(struct vidtv_psi_table_sdt *sdt)
{
- /* see ETSI EN 300 468 V 1.10.1 p.24 */
- u16 length = 0;
struct vidtv_psi_table_sdt_service *s = sdt->service;
u16 desc_loop_len;
+ u16 length = 0;
+
+ /* see ETSI EN 300 468 V 1.10.1 p.24 */
/*
* from immediately after 'section_length' until
}
length += CRC_SIZE_IN_BYTES;
-
vidtv_psi_set_sec_len(&sdt->header, length);
}
const u16 RESERVED = 0x07;
program = kzalloc(sizeof(*program), GFP_KERNEL);
+ if (!program)
+ return NULL;
program->service_id = cpu_to_be16(service_id);
void
vidtv_psi_pat_program_destroy(struct vidtv_psi_table_pat_program *p)
{
- struct vidtv_psi_table_pat_program *curr = p;
struct vidtv_psi_table_pat_program *tmp = NULL;
+ struct vidtv_psi_table_pat_program *curr = p;
while (curr) {
tmp = curr;
}
}
+/* This function transfers ownership of p to the table */
void
vidtv_psi_pat_program_assign(struct vidtv_psi_table_pat *pat,
struct vidtv_psi_table_pat_program *p)
{
- /* This function transfers ownership of p to the table */
+ struct vidtv_psi_table_pat_program *program;
+ u16 program_count;
- u16 program_count = 0;
- struct vidtv_psi_table_pat_program *program = p;
+ do {
+ program_count = 0;
+ program = p;
- if (p == pat->program)
- return;
+ if (p == pat->program)
+ return;
- while (program) {
- ++program_count;
- program = program->next;
- }
+ while (program) {
+ ++program_count;
+ program = program->next;
+ }
- pat->programs = program_count;
- pat->program = p;
+ pat->num_pat = program_count;
+ pat->program = p;
- /* Recompute section length */
- vidtv_psi_pat_table_update_sec_len(pat);
+ /* Recompute section length */
+ vidtv_psi_pat_table_update_sec_len(pat);
- if (vidtv_psi_get_sec_len(&pat->header) > MAX_SECTION_LEN)
- vidtv_psi_pat_program_assign(pat, NULL);
+ p = NULL;
+ } while (vidtv_psi_get_sec_len(&pat->header) > MAX_SECTION_LEN);
vidtv_psi_update_version_num(&pat->header);
}
struct vidtv_psi_table_pat *vidtv_psi_pat_table_init(u16 transport_stream_id)
{
- struct vidtv_psi_table_pat *pat = kzalloc(sizeof(*pat), GFP_KERNEL);
+ struct vidtv_psi_table_pat *pat;
const u16 SYNTAX = 0x1;
const u16 ZERO = 0x0;
const u16 ONES = 0x03;
+ pat = kzalloc(sizeof(*pat), GFP_KERNEL);
+ if (!pat)
+ return NULL;
+
pat->header.table_id = 0x0;
pat->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ZERO << 14) | (ONES << 12));
pat->header.section_id = 0x0;
pat->header.last_section = 0x0;
- pat->programs = 0;
-
vidtv_psi_pat_table_update_sec_len(pat);
return pat;
}
-u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args)
+u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args *args)
{
- /* the number of bytes written by this function */
+ struct vidtv_psi_table_pat_program *p = args->pat->program;
+ struct header_write_args h_args = {
+ .dest_buf = args->buf,
+ .dest_offset = args->offset,
+ .pid = VIDTV_PAT_PID,
+ .h = &args->pat->header,
+ .continuity_counter = args->continuity_counter,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct psi_write_args psi_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_PAT_PID,
+ .new_psi_section = false,
+ .continuity_counter = args->continuity_counter,
+ .is_crc = false,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct crc32_write_args c_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_PAT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ u32 crc = INITIAL_CRC;
u32 nbytes = 0;
- const u16 pat_pid = VIDTV_PAT_PID;
- u32 crc = 0xffffffff;
-
- struct vidtv_psi_table_pat_program *p = args.pat->program;
- struct header_write_args h_args = {};
- struct psi_write_args psi_args = {};
- struct crc32_write_args c_args = {};
+ vidtv_psi_pat_table_update_sec_len(args->pat);
- vidtv_psi_pat_table_update_sec_len(args.pat);
-
- h_args.dest_buf = args.buf;
- h_args.dest_offset = args.offset;
- h_args.h = &args.pat->header;
- h_args.pid = pat_pid;
- h_args.continuity_counter = args.continuity_counter;
- h_args.dest_buf_sz = args.buf_sz;
h_args.crc = &crc;
- nbytes += vidtv_psi_table_header_write_into(h_args);
+ nbytes += vidtv_psi_table_header_write_into(&h_args);
/* note that the field 'u16 programs' is not really part of the PAT */
- psi_args.dest_buf = args.buf;
- psi_args.pid = pat_pid;
- psi_args.new_psi_section = false;
- psi_args.continuity_counter = args.continuity_counter;
- psi_args.is_crc = false;
- psi_args.dest_buf_sz = args.buf_sz;
- psi_args.crc = &crc;
+ psi_args.crc = &crc;
while (p) {
/* copy the PAT programs */
psi_args.from = p;
/* skip the pointer */
psi_args.len = sizeof(*p) -
- sizeof(struct vidtv_psi_table_pat_program *);
- psi_args.dest_offset = args.offset + nbytes;
+ sizeof(struct vidtv_psi_table_pat_program *);
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
p = p->next;
}
- c_args.dest_buf = args.buf;
- c_args.dest_offset = args.offset + nbytes;
+ c_args.dest_offset = args->offset + nbytes;
+ c_args.continuity_counter = args->continuity_counter;
c_args.crc = cpu_to_be32(crc);
- c_args.pid = pat_pid;
- c_args.continuity_counter = args.continuity_counter;
- c_args.dest_buf_sz = args.buf_sz;
/* Write the CRC32 at the end */
- nbytes += table_section_crc32_write_into(c_args);
+ nbytes += table_section_crc32_write_into(&c_args);
return nbytes;
}
u16 desc_loop_len;
stream = kzalloc(sizeof(*stream), GFP_KERNEL);
+ if (!stream)
+ return NULL;
stream->type = stream_type;
void vidtv_psi_pmt_stream_destroy(struct vidtv_psi_table_pmt_stream *s)
{
- struct vidtv_psi_table_pmt_stream *curr_stream = s;
struct vidtv_psi_table_pmt_stream *tmp_stream = NULL;
+ struct vidtv_psi_table_pmt_stream *curr_stream = s;
while (curr_stream) {
tmp_stream = curr_stream;
void vidtv_psi_pmt_stream_assign(struct vidtv_psi_table_pmt *pmt,
struct vidtv_psi_table_pmt_stream *s)
{
- /* This function transfers ownership of s to the table */
- if (s == pmt->stream)
- return;
+ do {
+ /* This function transfers ownership of s to the table */
+ if (s == pmt->stream)
+ return;
- pmt->stream = s;
- vidtv_psi_pmt_table_update_sec_len(pmt);
+ pmt->stream = s;
+ vidtv_psi_pmt_table_update_sec_len(pmt);
- if (vidtv_psi_get_sec_len(&pmt->header) > MAX_SECTION_LEN)
- vidtv_psi_pmt_stream_assign(pmt, NULL);
+ s = NULL;
+ } while (vidtv_psi_get_sec_len(&pmt->header) > MAX_SECTION_LEN);
vidtv_psi_update_version_num(&pmt->header);
}
struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number,
u16 pcr_pid)
{
- struct vidtv_psi_table_pmt *pmt = kzalloc(sizeof(*pmt), GFP_KERNEL);
- const u16 SYNTAX = 0x1;
- const u16 ZERO = 0x0;
- const u16 ONES = 0x03;
+ struct vidtv_psi_table_pmt *pmt;
const u16 RESERVED1 = 0x07;
const u16 RESERVED2 = 0x0f;
+ const u16 SYNTAX = 0x1;
+ const u16 ONES = 0x03;
+ const u16 ZERO = 0x0;
u16 desc_loop_len;
+ pmt = kzalloc(sizeof(*pmt), GFP_KERNEL);
+ if (!pmt)
+ return NULL;
+
if (!pcr_pid)
pcr_pid = 0x1fff;
return pmt;
}
-u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args)
+u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args *args)
{
- /* the number of bytes written by this function */
+ struct vidtv_psi_desc *table_descriptor = args->pmt->descriptor;
+ struct vidtv_psi_table_pmt_stream *stream = args->pmt->stream;
+ struct vidtv_psi_desc *stream_descriptor;
+ struct header_write_args h_args = {
+ .dest_buf = args->buf,
+ .dest_offset = args->offset,
+ .h = &args->pmt->header,
+ .pid = args->pid,
+ .continuity_counter = args->continuity_counter,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct psi_write_args psi_args = {
+ .dest_buf = args->buf,
+ .from = &args->pmt->bitfield,
+ .len = sizeof_field(struct vidtv_psi_table_pmt, bitfield) +
+ sizeof_field(struct vidtv_psi_table_pmt, bitfield2),
+ .pid = args->pid,
+ .new_psi_section = false,
+ .is_crc = false,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct desc_write_args d_args = {
+ .dest_buf = args->buf,
+ .desc = table_descriptor,
+ .pid = args->pid,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct crc32_write_args c_args = {
+ .dest_buf = args->buf,
+ .pid = args->pid,
+ .dest_buf_sz = args->buf_sz,
+ };
+ u32 crc = INITIAL_CRC;
u32 nbytes = 0;
- u32 crc = 0xffffffff;
-
- struct vidtv_psi_desc *table_descriptor = args.pmt->descriptor;
- struct vidtv_psi_table_pmt_stream *stream = args.pmt->stream;
- struct vidtv_psi_desc *stream_descriptor = (stream) ?
- args.pmt->stream->descriptor :
- NULL;
-
- struct header_write_args h_args = {};
- struct psi_write_args psi_args = {};
- struct desc_write_args d_args = {};
- struct crc32_write_args c_args = {};
-
- vidtv_psi_pmt_table_update_sec_len(args.pmt);
-
- h_args.dest_buf = args.buf;
- h_args.dest_offset = args.offset;
- h_args.h = &args.pmt->header;
- h_args.pid = args.pid;
- h_args.continuity_counter = args.continuity_counter;
- h_args.dest_buf_sz = args.buf_sz;
+
+ vidtv_psi_pmt_table_update_sec_len(args->pmt);
+
h_args.crc = &crc;
- nbytes += vidtv_psi_table_header_write_into(h_args);
+ nbytes += vidtv_psi_table_header_write_into(&h_args);
/* write the two bitfields */
- psi_args.dest_buf = args.buf;
- psi_args.from = &args.pmt->bitfield;
- psi_args.len = sizeof_field(struct vidtv_psi_table_pmt, bitfield) +
- sizeof_field(struct vidtv_psi_table_pmt, bitfield2);
-
- psi_args.dest_offset = args.offset + nbytes;
- psi_args.pid = args.pid;
- psi_args.new_psi_section = false;
- psi_args.continuity_counter = args.continuity_counter;
- psi_args.is_crc = false;
- psi_args.dest_buf_sz = args.buf_sz;
- psi_args.crc = &crc;
-
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
while (table_descriptor) {
/* write the descriptors, if any */
- d_args.dest_buf = args.buf;
- d_args.dest_offset = args.offset + nbytes;
- d_args.desc = table_descriptor;
- d_args.pid = args.pid;
- d_args.continuity_counter = args.continuity_counter;
- d_args.dest_buf_sz = args.buf_sz;
+ d_args.dest_offset = args->offset + nbytes;
+ d_args.continuity_counter = args->continuity_counter;
d_args.crc = &crc;
- nbytes += vidtv_psi_desc_write_into(d_args);
+ nbytes += vidtv_psi_desc_write_into(&d_args);
table_descriptor = table_descriptor->next;
}
+ psi_args.len += sizeof_field(struct vidtv_psi_table_pmt_stream, type);
while (stream) {
/* write the streams, if any */
psi_args.from = stream;
- psi_args.len = sizeof_field(struct vidtv_psi_table_pmt_stream, type) +
- sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield) +
- sizeof_field(struct vidtv_psi_table_pmt_stream, bitfield2);
- psi_args.dest_offset = args.offset + nbytes;
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ stream_descriptor = stream->descriptor;
while (stream_descriptor) {
/* write the stream descriptors, if any */
- d_args.dest_buf = args.buf;
- d_args.dest_offset = args.offset + nbytes;
+ d_args.dest_offset = args->offset + nbytes;
d_args.desc = stream_descriptor;
- d_args.pid = args.pid;
- d_args.continuity_counter = args.continuity_counter;
- d_args.dest_buf_sz = args.buf_sz;
+ d_args.continuity_counter = args->continuity_counter;
d_args.crc = &crc;
- nbytes += vidtv_psi_desc_write_into(d_args);
+ nbytes += vidtv_psi_desc_write_into(&d_args);
stream_descriptor = stream_descriptor->next;
}
stream = stream->next;
}
- c_args.dest_buf = args.buf;
- c_args.dest_offset = args.offset + nbytes;
+ c_args.dest_offset = args->offset + nbytes;
c_args.crc = cpu_to_be32(crc);
- c_args.pid = args.pid;
- c_args.continuity_counter = args.continuity_counter;
- c_args.dest_buf_sz = args.buf_sz;
+ c_args.continuity_counter = args->continuity_counter;
/* Write the CRC32 at the end */
- nbytes += table_section_crc32_write_into(c_args);
+ nbytes += table_section_crc32_write_into(&c_args);
return nbytes;
}
kfree(pmt);
}
-struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id)
+struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id,
+ u16 transport_stream_id)
{
- struct vidtv_psi_table_sdt *sdt = kzalloc(sizeof(*sdt), GFP_KERNEL);
+ struct vidtv_psi_table_sdt *sdt;
+ const u16 RESERVED = 0xff;
const u16 SYNTAX = 0x1;
- const u16 ONE = 0x1;
const u16 ONES = 0x03;
- const u16 RESERVED = 0xff;
+ const u16 ONE = 0x1;
- sdt->header.table_id = 0x42;
+ sdt = kzalloc(sizeof(*sdt), GFP_KERNEL);
+ if (!sdt)
+ return NULL;
+ sdt->header.table_id = 0x42;
sdt->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12));
/*
* This can be changed to something more useful, when support for
* NIT gets added
*/
- sdt->network_id = cpu_to_be16(0xff01);
+ sdt->network_id = cpu_to_be16(network_id);
sdt->reserved = RESERVED;
vidtv_psi_sdt_table_update_sec_len(sdt);
return sdt;
}
-u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args)
+u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args)
{
+ struct header_write_args h_args = {
+ .dest_buf = args->buf,
+ .dest_offset = args->offset,
+ .h = &args->sdt->header,
+ .pid = VIDTV_SDT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct psi_write_args psi_args = {
+ .dest_buf = args->buf,
+ .len = sizeof_field(struct vidtv_psi_table_sdt, network_id) +
+ sizeof_field(struct vidtv_psi_table_sdt, reserved),
+ .pid = VIDTV_SDT_PID,
+ .new_psi_section = false,
+ .is_crc = false,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct desc_write_args d_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_SDT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct crc32_write_args c_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_SDT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct vidtv_psi_table_sdt_service *service = args->sdt->service;
+ struct vidtv_psi_desc *service_desc;
u32 nbytes = 0;
- u16 sdt_pid = VIDTV_SDT_PID; /* see ETSI EN 300 468 v1.15.1 p. 11 */
+ u32 crc = INITIAL_CRC;
- u32 crc = 0xffffffff;
+ /* see ETSI EN 300 468 v1.15.1 p. 11 */
- struct vidtv_psi_table_sdt_service *service = args.sdt->service;
- struct vidtv_psi_desc *service_desc = (args.sdt->service) ?
- args.sdt->service->descriptor :
- NULL;
+ vidtv_psi_sdt_table_update_sec_len(args->sdt);
- struct header_write_args h_args = {};
- struct psi_write_args psi_args = {};
- struct desc_write_args d_args = {};
- struct crc32_write_args c_args = {};
-
- vidtv_psi_sdt_table_update_sec_len(args.sdt);
-
- h_args.dest_buf = args.buf;
- h_args.dest_offset = args.offset;
- h_args.h = &args.sdt->header;
- h_args.pid = sdt_pid;
- h_args.continuity_counter = args.continuity_counter;
- h_args.dest_buf_sz = args.buf_sz;
+ h_args.continuity_counter = args->continuity_counter;
h_args.crc = &crc;
- nbytes += vidtv_psi_table_header_write_into(h_args);
-
- psi_args.dest_buf = args.buf;
- psi_args.from = &args.sdt->network_id;
+ nbytes += vidtv_psi_table_header_write_into(&h_args);
- psi_args.len = sizeof_field(struct vidtv_psi_table_sdt, network_id) +
- sizeof_field(struct vidtv_psi_table_sdt, reserved);
-
- psi_args.dest_offset = args.offset + nbytes;
- psi_args.pid = sdt_pid;
- psi_args.new_psi_section = false;
- psi_args.continuity_counter = args.continuity_counter;
- psi_args.is_crc = false;
- psi_args.dest_buf_sz = args.buf_sz;
+ psi_args.from = &args->sdt->network_id;
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
psi_args.crc = &crc;
/* copy u16 network_id + u8 reserved)*/
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ /* skip both pointers at the end */
+ psi_args.len = sizeof(struct vidtv_psi_table_sdt_service) -
+ sizeof(struct vidtv_psi_desc *) -
+ sizeof(struct vidtv_psi_table_sdt_service *);
while (service) {
/* copy the services, if any */
psi_args.from = service;
- /* skip both pointers at the end */
- psi_args.len = sizeof(struct vidtv_psi_table_sdt_service) -
- sizeof(struct vidtv_psi_desc *) -
- sizeof(struct vidtv_psi_table_sdt_service *);
- psi_args.dest_offset = args.offset + nbytes;
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
- nbytes += vidtv_psi_ts_psi_write_into(psi_args);
+ service_desc = service->descriptor;
while (service_desc) {
/* copy the service descriptors, if any */
- d_args.dest_buf = args.buf;
- d_args.dest_offset = args.offset + nbytes;
+ d_args.dest_offset = args->offset + nbytes;
d_args.desc = service_desc;
- d_args.pid = sdt_pid;
- d_args.continuity_counter = args.continuity_counter;
- d_args.dest_buf_sz = args.buf_sz;
+ d_args.continuity_counter = args->continuity_counter;
d_args.crc = &crc;
- nbytes += vidtv_psi_desc_write_into(d_args);
+ nbytes += vidtv_psi_desc_write_into(&d_args);
service_desc = service_desc->next;
}
service = service->next;
}
- c_args.dest_buf = args.buf;
- c_args.dest_offset = args.offset + nbytes;
+ c_args.dest_offset = args->offset + nbytes;
c_args.crc = cpu_to_be32(crc);
- c_args.pid = sdt_pid;
- c_args.continuity_counter = args.continuity_counter;
- c_args.dest_buf_sz = args.buf_sz;
+ c_args.continuity_counter = args->continuity_counter;
/* Write the CRC at the end */
- nbytes += table_section_crc32_write_into(c_args);
+ nbytes += table_section_crc32_write_into(&c_args);
return nbytes;
}
struct vidtv_psi_table_sdt_service
*vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head,
- u16 service_id)
+ u16 service_id,
+ bool eit_schedule,
+ bool eit_present_following)
{
struct vidtv_psi_table_sdt_service *service;
service = kzalloc(sizeof(*service), GFP_KERNEL);
+ if (!service)
+ return NULL;
/*
* ETSI 300 468: this is a 16bit field which serves as a label to
* corresponding program_map_section
*/
service->service_id = cpu_to_be16(service_id);
- service->EIT_schedule = 0x0;
- service->EIT_present_following = 0x0;
+ service->EIT_schedule = eit_schedule;
+ service->EIT_present_following = eit_present_following;
service->reserved = 0x3f;
service->bitfield = cpu_to_be16(RUNNING << 13);
vidtv_psi_sdt_service_assign(struct vidtv_psi_table_sdt *sdt,
struct vidtv_psi_table_sdt_service *service)
{
- if (service == sdt->service)
- return;
+ do {
+ if (service == sdt->service)
+ return;
- sdt->service = service;
+ sdt->service = service;
- /* recompute section length */
- vidtv_psi_sdt_table_update_sec_len(sdt);
+ /* recompute section length */
+ vidtv_psi_sdt_table_update_sec_len(sdt);
- if (vidtv_psi_get_sec_len(&sdt->header) > MAX_SECTION_LEN)
- vidtv_psi_sdt_service_assign(sdt, NULL);
+ service = NULL;
+ } while (vidtv_psi_get_sec_len(&sdt->header) > MAX_SECTION_LEN);
vidtv_psi_update_version_num(&sdt->header);
}
+/*
+ * PMTs contain information about programs. For each program,
+ * there is one PMT section. This function will create a section
+ * for each program found in the PAT
+ */
struct vidtv_psi_table_pmt**
-vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat, u16 pcr_pid)
+vidtv_psi_pmt_create_sec_for_each_pat_entry(struct vidtv_psi_table_pat *pat,
+ u16 pcr_pid)
{
+ struct vidtv_psi_table_pat_program *program;
+ struct vidtv_psi_table_pmt **pmt_secs;
+ u32 i = 0, num_pmt = 0;
+
/*
- * PMTs contain information about programs. For each program,
- * there is one PMT section. This function will create a section
- * for each program found in the PAT
+ * The number of PMT entries is the number of PAT entries
+ * that contain service_id. That exclude special tables, like NIT
*/
- struct vidtv_psi_table_pat_program *program = pat->program;
- struct vidtv_psi_table_pmt **pmt_secs;
- u32 i = 0;
+ program = pat->program;
+ while (program) {
+ if (program->service_id)
+ num_pmt++;
+ program = program->next;
+ }
- /* a section for each program_id */
- pmt_secs = kcalloc(pat->programs,
+ pmt_secs = kcalloc(num_pmt,
sizeof(struct vidtv_psi_table_pmt *),
GFP_KERNEL);
-
- while (program) {
- pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id), pcr_pid);
- ++i;
- program = program->next;
+ if (!pmt_secs)
+ return NULL;
+
+ for (program = pat->program; program; program = program->next) {
+ if (!program->service_id)
+ continue;
+ pmt_secs[i] = vidtv_psi_pmt_table_init(be16_to_cpu(program->service_id),
+ pcr_pid);
+
+ if (!pmt_secs[i]) {
+ while (i > 0) {
+ i--;
+ vidtv_psi_pmt_table_destroy(pmt_secs[i]);
+ }
+ return NULL;
+ }
+ i++;
}
+ pat->num_pmt = num_pmt;
return pmt_secs;
}
+/* find the PMT section associated with 'program_num' */
struct vidtv_psi_table_pmt
*vidtv_psi_find_pmt_sec(struct vidtv_psi_table_pmt **pmt_sections,
u16 nsections,
u16 program_num)
{
- /* find the PMT section associated with 'program_num' */
struct vidtv_psi_table_pmt *sec = NULL;
u32 i;
return NULL; /* not found */
}
+
+static void vidtv_psi_nit_table_update_sec_len(struct vidtv_psi_table_nit *nit)
+{
+ u16 length = 0;
+ struct vidtv_psi_table_transport *t = nit->transport;
+ u16 desc_loop_len;
+ u16 transport_loop_len = 0;
+
+ /*
+ * from immediately after 'section_length' until
+ * 'network_descriptor_length'
+ */
+ length += NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN;
+
+ desc_loop_len = vidtv_psi_desc_comp_loop_len(nit->descriptor);
+ vidtv_psi_set_desc_loop_len(&nit->bitfield, desc_loop_len, 12);
+
+ length += desc_loop_len;
+
+ length += sizeof_field(struct vidtv_psi_table_nit, bitfield2);
+
+ while (t) {
+ /* skip both pointers at the end */
+ transport_loop_len += sizeof(struct vidtv_psi_table_transport) -
+ sizeof(struct vidtv_psi_desc *) -
+ sizeof(struct vidtv_psi_table_transport *);
+
+ length += transport_loop_len;
+
+ desc_loop_len = vidtv_psi_desc_comp_loop_len(t->descriptor);
+ vidtv_psi_set_desc_loop_len(&t->bitfield, desc_loop_len, 12);
+
+ length += desc_loop_len;
+
+ t = t->next;
+ }
+
+ // Actually sets the transport stream loop len, maybe rename this function later
+ vidtv_psi_set_desc_loop_len(&nit->bitfield2, transport_loop_len, 12);
+ length += CRC_SIZE_IN_BYTES;
+
+ vidtv_psi_set_sec_len(&nit->header, length);
+}
+
+struct vidtv_psi_table_nit
+*vidtv_psi_nit_table_init(u16 network_id,
+ u16 transport_stream_id,
+ char *network_name,
+ struct vidtv_psi_desc_service_list_entry *service_list)
+{
+ struct vidtv_psi_table_transport *transport;
+ struct vidtv_psi_table_nit *nit;
+ const u16 SYNTAX = 0x1;
+ const u16 ONES = 0x03;
+ const u16 ONE = 0x1;
+
+ nit = kzalloc(sizeof(*nit), GFP_KERNEL);
+ if (!nit)
+ return NULL;
+
+ transport = kzalloc(sizeof(*transport), GFP_KERNEL);
+ if (!transport)
+ goto free_nit;
+
+ nit->header.table_id = 0x40; // ACTUAL_NETWORK
+
+ nit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12));
+
+ nit->header.id = cpu_to_be16(network_id);
+ nit->header.current_next = ONE;
+
+ nit->header.version = 0x1f;
+
+ nit->header.one2 = ONES;
+ nit->header.section_id = 0;
+ nit->header.last_section = 0;
+
+ nit->bitfield = cpu_to_be16(0xf);
+ nit->bitfield2 = cpu_to_be16(0xf);
+
+ nit->descriptor = (struct vidtv_psi_desc *)
+ vidtv_psi_network_name_desc_init(NULL, network_name);
+ if (!nit->descriptor)
+ goto free_transport;
+
+ transport->transport_id = cpu_to_be16(transport_stream_id);
+ transport->network_id = cpu_to_be16(network_id);
+ transport->bitfield = cpu_to_be16(0xf);
+ transport->descriptor = (struct vidtv_psi_desc *)
+ vidtv_psi_service_list_desc_init(NULL, service_list);
+ if (!transport->descriptor)
+ goto free_nit_desc;
+
+ nit->transport = transport;
+
+ vidtv_psi_nit_table_update_sec_len(nit);
+
+ return nit;
+
+free_nit_desc:
+ vidtv_psi_desc_destroy((struct vidtv_psi_desc *)nit->descriptor);
+
+free_transport:
+ kfree(transport);
+free_nit:
+ kfree(nit);
+ return NULL;
+}
+
+u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args)
+{
+ struct header_write_args h_args = {
+ .dest_buf = args->buf,
+ .dest_offset = args->offset,
+ .h = &args->nit->header,
+ .pid = VIDTV_NIT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct psi_write_args psi_args = {
+ .dest_buf = args->buf,
+ .from = &args->nit->bitfield,
+ .len = sizeof_field(struct vidtv_psi_table_nit, bitfield),
+ .pid = VIDTV_NIT_PID,
+ .new_psi_section = false,
+ .is_crc = false,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct desc_write_args d_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_NIT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct crc32_write_args c_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_NIT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct vidtv_psi_desc *table_descriptor = args->nit->descriptor;
+ struct vidtv_psi_table_transport *transport = args->nit->transport;
+ struct vidtv_psi_desc *transport_descriptor;
+ u32 crc = INITIAL_CRC;
+ u32 nbytes = 0;
+
+ vidtv_psi_nit_table_update_sec_len(args->nit);
+
+ h_args.continuity_counter = args->continuity_counter;
+ h_args.crc = &crc;
+
+ nbytes += vidtv_psi_table_header_write_into(&h_args);
+
+ /* write the bitfield */
+
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
+ psi_args.crc = &crc;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ while (table_descriptor) {
+ /* write the descriptors, if any */
+ d_args.dest_offset = args->offset + nbytes;
+ d_args.desc = table_descriptor;
+ d_args.continuity_counter = args->continuity_counter;
+ d_args.crc = &crc;
+
+ nbytes += vidtv_psi_desc_write_into(&d_args);
+
+ table_descriptor = table_descriptor->next;
+ }
+
+ /* write the second bitfield */
+ psi_args.from = &args->nit->bitfield2;
+ psi_args.len = sizeof_field(struct vidtv_psi_table_nit, bitfield2);
+ psi_args.dest_offset = args->offset + nbytes;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ psi_args.len = sizeof_field(struct vidtv_psi_table_transport, transport_id) +
+ sizeof_field(struct vidtv_psi_table_transport, network_id) +
+ sizeof_field(struct vidtv_psi_table_transport, bitfield);
+ while (transport) {
+ /* write the transport sections, if any */
+ psi_args.from = transport;
+ psi_args.dest_offset = args->offset + nbytes;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ transport_descriptor = transport->descriptor;
+
+ while (transport_descriptor) {
+ /* write the transport descriptors, if any */
+ d_args.dest_offset = args->offset + nbytes;
+ d_args.desc = transport_descriptor;
+ d_args.continuity_counter = args->continuity_counter;
+ d_args.crc = &crc;
+
+ nbytes += vidtv_psi_desc_write_into(&d_args);
+
+ transport_descriptor = transport_descriptor->next;
+ }
+
+ transport = transport->next;
+ }
+
+ c_args.dest_offset = args->offset + nbytes;
+ c_args.crc = cpu_to_be32(crc);
+ c_args.continuity_counter = args->continuity_counter;
+
+ /* Write the CRC32 at the end */
+ nbytes += table_section_crc32_write_into(&c_args);
+
+ return nbytes;
+}
+
+static void vidtv_psi_transport_destroy(struct vidtv_psi_table_transport *t)
+{
+ struct vidtv_psi_table_transport *tmp_t = NULL;
+ struct vidtv_psi_table_transport *curr_t = t;
+
+ while (curr_t) {
+ tmp_t = curr_t;
+ curr_t = curr_t->next;
+ vidtv_psi_desc_destroy(tmp_t->descriptor);
+ kfree(tmp_t);
+ }
+}
+
+void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit)
+{
+ vidtv_psi_desc_destroy(nit->descriptor);
+ vidtv_psi_transport_destroy(nit->transport);
+ kfree(nit);
+}
+
+void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit)
+{
+ struct vidtv_psi_table_eit_event *e = eit->event;
+ u16 desc_loop_len;
+ u16 length = 0;
+
+ /*
+ * from immediately after 'section_length' until
+ * 'last_table_id'
+ */
+ length += EIT_LEN_UNTIL_LAST_TABLE_ID;
+
+ while (e) {
+ /* skip both pointers at the end */
+ length += sizeof(struct vidtv_psi_table_eit_event) -
+ sizeof(struct vidtv_psi_desc *) -
+ sizeof(struct vidtv_psi_table_eit_event *);
+
+ desc_loop_len = vidtv_psi_desc_comp_loop_len(e->descriptor);
+ vidtv_psi_set_desc_loop_len(&e->bitfield, desc_loop_len, 12);
+
+ length += desc_loop_len;
+
+ e = e->next;
+ }
+
+ length += CRC_SIZE_IN_BYTES;
+
+ vidtv_psi_set_sec_len(&eit->header, length);
+}
+
+void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit,
+ struct vidtv_psi_table_eit_event *e)
+{
+ do {
+ if (e == eit->event)
+ return;
+
+ eit->event = e;
+ vidtv_psi_eit_table_update_sec_len(eit);
+
+ e = NULL;
+ } while (vidtv_psi_get_sec_len(&eit->header) > EIT_MAX_SECTION_LEN);
+
+ vidtv_psi_update_version_num(&eit->header);
+}
+
+struct vidtv_psi_table_eit
+*vidtv_psi_eit_table_init(u16 network_id,
+ u16 transport_stream_id,
+ __be16 service_id)
+{
+ struct vidtv_psi_table_eit *eit;
+ const u16 SYNTAX = 0x1;
+ const u16 ONE = 0x1;
+ const u16 ONES = 0x03;
+
+ eit = kzalloc(sizeof(*eit), GFP_KERNEL);
+ if (!eit)
+ return NULL;
+
+ eit->header.table_id = 0x4e; //actual_transport_stream: present/following
+
+ eit->header.bitfield = cpu_to_be16((SYNTAX << 15) | (ONE << 14) | (ONES << 12));
+
+ eit->header.id = service_id;
+ eit->header.current_next = ONE;
+
+ eit->header.version = 0x1f;
+
+ eit->header.one2 = ONES;
+ eit->header.section_id = 0;
+ eit->header.last_section = 0;
+
+ eit->transport_id = cpu_to_be16(transport_stream_id);
+ eit->network_id = cpu_to_be16(network_id);
+
+ eit->last_segment = eit->header.last_section; /* not implemented */
+ eit->last_table_id = eit->header.table_id; /* not implemented */
+
+ vidtv_psi_eit_table_update_sec_len(eit);
+
+ return eit;
+}
+
+u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args *args)
+{
+ struct header_write_args h_args = {
+ .dest_buf = args->buf,
+ .dest_offset = args->offset,
+ .h = &args->eit->header,
+ .pid = VIDTV_EIT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct psi_write_args psi_args = {
+ .dest_buf = args->buf,
+ .len = sizeof_field(struct vidtv_psi_table_eit, transport_id) +
+ sizeof_field(struct vidtv_psi_table_eit, network_id) +
+ sizeof_field(struct vidtv_psi_table_eit, last_segment) +
+ sizeof_field(struct vidtv_psi_table_eit, last_table_id),
+ .pid = VIDTV_EIT_PID,
+ .new_psi_section = false,
+ .is_crc = false,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct desc_write_args d_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_EIT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct crc32_write_args c_args = {
+ .dest_buf = args->buf,
+ .pid = VIDTV_EIT_PID,
+ .dest_buf_sz = args->buf_sz,
+ };
+ struct vidtv_psi_table_eit_event *event = args->eit->event;
+ struct vidtv_psi_desc *event_descriptor;
+ u32 crc = INITIAL_CRC;
+ u32 nbytes = 0;
+
+ vidtv_psi_eit_table_update_sec_len(args->eit);
+
+ h_args.continuity_counter = args->continuity_counter;
+ h_args.crc = &crc;
+
+ nbytes += vidtv_psi_table_header_write_into(&h_args);
+
+ psi_args.from = &args->eit->transport_id;
+ psi_args.dest_offset = args->offset + nbytes;
+ psi_args.continuity_counter = args->continuity_counter;
+ psi_args.crc = &crc;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ /* skip both pointers at the end */
+ psi_args.len = sizeof(struct vidtv_psi_table_eit_event) -
+ sizeof(struct vidtv_psi_desc *) -
+ sizeof(struct vidtv_psi_table_eit_event *);
+ while (event) {
+ /* copy the events, if any */
+ psi_args.from = event;
+ psi_args.dest_offset = args->offset + nbytes;
+
+ nbytes += vidtv_psi_ts_psi_write_into(&psi_args);
+
+ event_descriptor = event->descriptor;
+
+ while (event_descriptor) {
+ /* copy the event descriptors, if any */
+ d_args.dest_offset = args->offset + nbytes;
+ d_args.desc = event_descriptor;
+ d_args.continuity_counter = args->continuity_counter;
+ d_args.crc = &crc;
+
+ nbytes += vidtv_psi_desc_write_into(&d_args);
+
+ event_descriptor = event_descriptor->next;
+ }
+
+ event = event->next;
+ }
+
+ c_args.dest_offset = args->offset + nbytes;
+ c_args.crc = cpu_to_be32(crc);
+ c_args.continuity_counter = args->continuity_counter;
+
+ /* Write the CRC at the end */
+ nbytes += table_section_crc32_write_into(&c_args);
+
+ return nbytes;
+}
+
+struct vidtv_psi_table_eit_event
+*vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id)
+{
+ const u8 DURATION[] = {0x23, 0x59, 0x59}; /* BCD encoded */
+ struct vidtv_psi_table_eit_event *e;
+ struct timespec64 ts;
+ struct tm time;
+ int mjd, l;
+ __be16 mjd_be;
+
+ e = kzalloc(sizeof(*e), GFP_KERNEL);
+ if (!e)
+ return NULL;
+
+ e->event_id = cpu_to_be16(event_id);
+
+ ts = ktime_to_timespec64(ktime_get_real());
+ time64_to_tm(ts.tv_sec, 0, &time);
+
+ /* Convert date to Modified Julian Date - per EN 300 468 Annex C */
+ if (time.tm_mon < 2)
+ l = 1;
+ else
+ l = 0;
+
+ mjd = 14956 + time.tm_mday;
+ mjd += (time.tm_year - l) * 36525 / 100;
+ mjd += (time.tm_mon + 2 + l * 12) * 306001 / 10000;
+ mjd_be = cpu_to_be16(mjd);
+
+ /*
+ * Store MJD and hour/min/sec to the event.
+ *
+ * Let's make the event to start on a full hour
+ */
+ memcpy(e->start_time, &mjd_be, sizeof(mjd_be));
+ e->start_time[2] = bin2bcd(time.tm_hour);
+ e->start_time[3] = 0;
+ e->start_time[4] = 0;
+
+ /*
+ * TODO: for now, the event will last for a day. Should be
+ * enough for testing purposes, but if one runs the driver
+ * for more than that, the current event will become invalid.
+ * So, we need a better code here in order to change the start
+ * time once the event expires.
+ */
+ memcpy(e->duration, DURATION, sizeof(e->duration));
+
+ e->bitfield = cpu_to_be16(RUNNING << 13);
+
+ if (head) {
+ while (head->next)
+ head = head->next;
+
+ head->next = e;
+ }
+
+ return e;
+}
+
+void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e)
+{
+ struct vidtv_psi_table_eit_event *tmp_e = NULL;
+ struct vidtv_psi_table_eit_event *curr_e = e;
+
+ while (curr_e) {
+ tmp_e = curr_e;
+ curr_e = curr_e->next;
+ vidtv_psi_desc_destroy(tmp_e->descriptor);
+ kfree(tmp_e);
+ }
+}
+
+void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit)
+{
+ vidtv_psi_eit_event_destroy(eit->event);
+ kfree(eit);
+}
* technically be broken into one or more sections, we do not do this here,
* hence 'table' and 'section' are interchangeable for vidtv.
*
- * This code currently supports three tables: PAT, PMT and SDT. These are the
- * bare minimum to get userspace to recognize our MPEG transport stream. It can
- * be extended to support more PSI tables in the future.
- *
* Copyright (C) 2020 Daniel W. S. Almeida
*/
#define VIDTV_PSI_H
#include <linux/types.h>
-#include <asm/byteorder.h>
/*
* all section lengths start immediately after the 'section_length' field
#define PAT_LEN_UNTIL_LAST_SECTION_NUMBER 5
#define PMT_LEN_UNTIL_PROGRAM_INFO_LENGTH 9
#define SDT_LEN_UNTIL_RESERVED_FOR_FUTURE_USE 8
+#define NIT_LEN_UNTIL_NETWORK_DESCRIPTOR_LEN 7
+#define EIT_LEN_UNTIL_LAST_TABLE_ID 11
#define MAX_SECTION_LEN 1021
+#define EIT_MAX_SECTION_LEN 4093 /* see ETSI 300 468 v.1.10.1 p. 26 */
#define VIDTV_PAT_PID 0 /* mandated by the specs */
#define VIDTV_SDT_PID 0x0011 /* mandated by the specs */
+#define VIDTV_NIT_PID 0x0010 /* mandated by the specs */
+#define VIDTV_EIT_PID 0x0012 /*mandated by the specs */
enum vidtv_psi_descriptors {
REGISTRATION_DESCRIPTOR = 0x05, /* See ISO/IEC 13818-1 section 2.6.8 */
+ NETWORK_NAME_DESCRIPTOR = 0x40, /* See ETSI EN 300 468 section 6.2.27 */
+ SERVICE_LIST_DESCRIPTOR = 0x41, /* See ETSI EN 300 468 section 6.2.35 */
SERVICE_DESCRIPTOR = 0x48, /* See ETSI EN 300 468 section 6.2.33 */
+ SHORT_EVENT_DESCRIPTOR = 0x4d, /* See ETSI EN 300 468 section 6.2.37 */
};
enum vidtv_psi_stream_types {
STREAM_PRIVATE_DATA = 0x06, /* see ISO/IEC 13818-1 2000 p. 48 */
};
-/**
+/*
* struct vidtv_psi_desc - A generic PSI descriptor type.
* The descriptor length is an 8-bit field specifying the total number of bytes of the data portion
* of the descriptor following the byte defining the value of this field.
u8 data[];
} __packed;
-/**
+/*
* struct vidtv_psi_desc_service - Service descriptor.
* See ETSI EN 300 468 section 6.2.33.
*/
char *service_name;
} __packed;
-/**
+/*
* struct vidtv_psi_desc_registration - A registration descriptor.
* See ISO/IEC 13818-1 section 2.6.8
*/
u8 additional_identification_info[];
} __packed;
-/**
+/*
+ * struct vidtv_psi_desc_network_name - A network name descriptor
+ * see ETSI EN 300 468 v1.15.1 section 6.2.27
+ */
+struct vidtv_psi_desc_network_name {
+ struct vidtv_psi_desc *next;
+ u8 type;
+ u8 length;
+ char *network_name;
+} __packed;
+
+struct vidtv_psi_desc_service_list_entry {
+ __be16 service_id;
+ u8 service_type;
+ struct vidtv_psi_desc_service_list_entry *next;
+} __packed;
+
+/*
+ * struct vidtv_psi_desc_service_list - A service list descriptor
+ * see ETSI EN 300 468 v1.15.1 section 6.2.35
+ */
+struct vidtv_psi_desc_service_list {
+ struct vidtv_psi_desc *next;
+ u8 type;
+ u8 length;
+ struct vidtv_psi_desc_service_list_entry *service_list;
+} __packed;
+
+/*
+ * struct vidtv_psi_desc_short_event - A short event descriptor
+ * see ETSI EN 300 468 v1.15.1 section 6.2.37
+ */
+struct vidtv_psi_desc_short_event {
+ struct vidtv_psi_desc *next;
+ u8 type;
+ u8 length;
+ char *iso_language_code;
+ u8 event_name_len;
+ char *event_name;
+ u8 text_len;
+ char *text;
+} __packed;
+
+struct vidtv_psi_desc_short_event
+*vidtv_psi_short_event_desc_init(struct vidtv_psi_desc *head,
+ char *iso_language_code,
+ char *event_name,
+ char *text);
+
+/*
* struct vidtv_psi_table_header - A header that is present for all PSI tables.
*/
struct vidtv_psi_table_header {
u8 last_section; /* last_section_number */
} __packed;
-/**
+/*
* struct vidtv_psi_table_pat_program - A single program in the PAT
* See ISO/IEC 13818-1 : 2000 p.43
*/
struct vidtv_psi_table_pat_program *next;
} __packed;
-/**
+/*
* struct vidtv_psi_table_pat - The Program Allocation Table (PAT)
* See ISO/IEC 13818-1 : 2000 p.43
*/
struct vidtv_psi_table_pat {
struct vidtv_psi_table_header header;
- u16 programs; /* Included by libdvbv5, not part of the table and not actually serialized */
+ u16 num_pat;
+ u16 num_pmt;
struct vidtv_psi_table_pat_program *program;
} __packed;
-/**
+/*
* struct vidtv_psi_table_sdt_service - Represents a service in the SDT.
* see ETSI EN 300 468 v1.15.1 section 5.2.3.
*/
struct vidtv_psi_table_sdt_service *next;
} __packed;
-/**
+/*
* struct vidtv_psi_table_sdt - Represents the Service Description Table
* see ETSI EN 300 468 v1.15.1 section 5.2.3.
*/
struct vidtv_psi_table_sdt_service *service;
} __packed;
-/**
+/*
* enum service_running_status - Status of a SDT service.
* see ETSI EN 300 468 v1.15.1 section 5.2.3 table 6.
*/
RUNNING = 0x4,
};
-/**
+/*
* enum service_type - The type of a SDT service.
* see ETSI EN 300 468 v1.15.1 section 6.2.33, table 81.
*/
enum service_type {
/* see ETSI EN 300 468 v1.15.1 p. 77 */
DIGITAL_TELEVISION_SERVICE = 0x1,
+ DIGITAL_RADIO_SOUND_SERVICE = 0X2,
};
-/**
+/*
* struct vidtv_psi_table_pmt_stream - A single stream in the PMT.
* See ISO/IEC 13818-1 : 2000 p.46.
*/
struct vidtv_psi_table_pmt_stream *next;
} __packed;
-/**
+/*
* struct vidtv_psi_table_pmt - The Program Map Table (PMT).
* See ISO/IEC 13818-1 : 2000 p.46.
*/
u8 *additional_ident_info,
u32 additional_info_len);
+struct vidtv_psi_desc_network_name
+*vidtv_psi_network_name_desc_init(struct vidtv_psi_desc *head, char *network_name);
+
+struct vidtv_psi_desc_service_list
+*vidtv_psi_service_list_desc_init(struct vidtv_psi_desc *head,
+ struct vidtv_psi_desc_service_list_entry *entry);
+
struct vidtv_psi_table_pat_program
*vidtv_psi_pat_program_init(struct vidtv_psi_table_pat_program *head,
u16 service_id,
struct vidtv_psi_table_pmt *vidtv_psi_pmt_table_init(u16 program_number,
u16 pcr_pid);
-struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 transport_stream_id);
+struct vidtv_psi_table_sdt *vidtv_psi_sdt_table_init(u16 network_id,
+ u16 transport_stream_id);
struct vidtv_psi_table_sdt_service*
vidtv_psi_sdt_service_init(struct vidtv_psi_table_sdt_service *head,
- u16 service_id);
+ u16 service_id,
+ bool eit_schedule,
+ bool eit_present_following);
void
vidtv_psi_desc_destroy(struct vidtv_psi_desc *desc);
* vidtv_psi_create_sec_for_each_pat_entry - Create a PMT section for each
* program found in the PAT
* @pat: The PAT to look for programs.
- * @s: The stream loop (one or more streams)
* @pcr_pid: packet ID for the PCR to be used for the program described in this
* PMT section
*/
* equal to the size of the PAT, since more space is needed for TS headers during TS
* encapsulation.
*/
-u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args args);
+u32 vidtv_psi_pat_write_into(struct vidtv_psi_pat_write_args *args);
/**
* struct vidtv_psi_sdt_write_args - Arguments for writing a SDT table
* equal to the size of the SDT, since more space is needed for TS headers during TS
* encapsulation.
*/
-u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args args);
+u32 vidtv_psi_sdt_write_into(struct vidtv_psi_sdt_write_args *args);
/**
* struct vidtv_psi_pmt_write_args - Arguments for writing a PMT section
* @buf: The destination buffer.
* @offset: The offset into the destination buffer.
* @pmt: A pointer to the PMT.
+ * @pid: Program ID
* @buf_sz: The size of the destination buffer.
* @continuity_counter: A pointer to the CC. Incremented on every new packet.
- *
+ * @pcr_pid: The TS PID used for the PSI packets. All channels will share the
+ * same PCR.
*/
struct vidtv_psi_pmt_write_args {
char *buf;
* equal to the size of the PMT section, since more space is needed for TS headers
* during TS encapsulation.
*/
-u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args args);
+u32 vidtv_psi_pmt_write_into(struct vidtv_psi_pmt_write_args *args);
/**
* vidtv_psi_find_pmt_sec - Finds the PMT section for 'program_num'
u16 vidtv_psi_get_pat_program_pid(struct vidtv_psi_table_pat_program *p);
u16 vidtv_psi_pmt_stream_get_elem_pid(struct vidtv_psi_table_pmt_stream *s);
+/**
+ * struct vidtv_psi_table_transport - A entry in the TS loop for the NIT and/or other tables.
+ * See ETSI 300 468 section 5.2.1
+ * @transport_id: The TS ID being described
+ * @network_id: The network_id that contains the TS ID
+ * @bitfield: Contains the descriptor loop length
+ * @descriptor: A descriptor loop
+ * @next: Pointer to the next entry
+ *
+ */
+struct vidtv_psi_table_transport {
+ __be16 transport_id;
+ __be16 network_id;
+ __be16 bitfield; /* desc_len: 12, reserved: 4 */
+ struct vidtv_psi_desc *descriptor;
+ struct vidtv_psi_table_transport *next;
+} __packed;
+
+/**
+ * struct vidtv_psi_table_nit - A Network Information Table (NIT). See ETSI 300
+ * 468 section 5.2.1
+ * @header: A PSI table header
+ * @bitfield: Contains the network descriptor length
+ * @descriptor: A descriptor loop describing the network
+ * @bitfield2: Contains the transport stream loop length
+ * @transport: The transport stream loop
+ *
+ */
+struct vidtv_psi_table_nit {
+ struct vidtv_psi_table_header header;
+ __be16 bitfield; /* network_desc_len: 12, reserved:4 */
+ struct vidtv_psi_desc *descriptor;
+ __be16 bitfield2; /* ts_loop_len: 12, reserved: 4 */
+ struct vidtv_psi_table_transport *transport;
+} __packed;
+
+struct vidtv_psi_table_nit
+*vidtv_psi_nit_table_init(u16 network_id,
+ u16 transport_stream_id,
+ char *network_name,
+ struct vidtv_psi_desc_service_list_entry *service_list);
+
+/**
+ * struct vidtv_psi_nit_write_args - Arguments for writing a NIT section
+ * @buf: The destination buffer.
+ * @offset: The offset into the destination buffer.
+ * @nit: A pointer to the NIT
+ * @buf_sz: The size of the destination buffer.
+ * @continuity_counter: A pointer to the CC. Incremented on every new packet.
+ *
+ */
+struct vidtv_psi_nit_write_args {
+ char *buf;
+ u32 offset;
+ struct vidtv_psi_table_nit *nit;
+ u32 buf_sz;
+ u8 *continuity_counter;
+};
+
+/**
+ * vidtv_psi_nit_write_into - Write NIT as MPEG-TS packets into a buffer.
+ * @args: an instance of struct vidtv_psi_nit_write_args
+ *
+ * This function writes the MPEG TS packets for a NIT table into a buffer.
+ * Calling code will usually generate the NIT via a call to its init function
+ * and thus is responsible for freeing it.
+ *
+ * Return: The number of bytes written into the buffer. This is NOT
+ * equal to the size of the NIT, since more space is needed for TS headers during TS
+ * encapsulation.
+ */
+u32 vidtv_psi_nit_write_into(struct vidtv_psi_nit_write_args *args);
+
+void vidtv_psi_nit_table_destroy(struct vidtv_psi_table_nit *nit);
+
+/*
+ * struct vidtv_psi_desc_short_event - A short event descriptor
+ * see ETSI EN 300 468 v1.15.1 section 6.2.37
+ */
+struct vidtv_psi_table_eit_event {
+ __be16 event_id;
+ u8 start_time[5];
+ u8 duration[3];
+ __be16 bitfield; /* desc_length: 12, free_CA_mode: 1, running_status: 1 */
+ struct vidtv_psi_desc *descriptor;
+ struct vidtv_psi_table_eit_event *next;
+} __packed;
+
+/*
+ * struct vidtv_psi_table_eit - A Event Information Table (EIT)
+ * See ETSI 300 468 section 5.2.4
+ */
+struct vidtv_psi_table_eit {
+ struct vidtv_psi_table_header header;
+ __be16 transport_id;
+ __be16 network_id;
+ u8 last_segment;
+ u8 last_table_id;
+ struct vidtv_psi_table_eit_event *event;
+} __packed;
+
+struct vidtv_psi_table_eit
+*vidtv_psi_eit_table_init(u16 network_id,
+ u16 transport_stream_id,
+ u16 service_id);
+
+/**
+ * struct vidtv_psi_eit_write_args - Arguments for writing an EIT section
+ * @buf: The destination buffer.
+ * @offset: The offset into the destination buffer.
+ * @eit: A pointer to the EIT
+ * @buf_sz: The size of the destination buffer.
+ * @continuity_counter: A pointer to the CC. Incremented on every new packet.
+ *
+ */
+struct vidtv_psi_eit_write_args {
+ char *buf;
+ u32 offset;
+ struct vidtv_psi_table_eit *eit;
+ u32 buf_sz;
+ u8 *continuity_counter;
+};
+
+/**
+ * vidtv_psi_eit_write_into - Write EIT as MPEG-TS packets into a buffer.
+ * @args: an instance of struct vidtv_psi_nit_write_args
+ *
+ * This function writes the MPEG TS packets for a EIT table into a buffer.
+ * Calling code will usually generate the EIT via a call to its init function
+ * and thus is responsible for freeing it.
+ *
+ * Return: The number of bytes written into the buffer. This is NOT
+ * equal to the size of the EIT, since more space is needed for TS headers during TS
+ * encapsulation.
+ */
+u32 vidtv_psi_eit_write_into(struct vidtv_psi_eit_write_args *args);
+
+void vidtv_psi_eit_table_destroy(struct vidtv_psi_table_eit *eit);
+
+/**
+ * vidtv_psi_eit_table_update_sec_len - Recompute and update the EIT section length.
+ * @eit: The EIT whose length is to be updated.
+ *
+ * This will traverse the table and accumulate the length of its components,
+ * which is then used to replace the 'section_length' field.
+ *
+ * If section_length > EIT_MAX_SECTION_LEN, the operation fails.
+ */
+void vidtv_psi_eit_table_update_sec_len(struct vidtv_psi_table_eit *eit);
+
+/**
+ * vidtv_psi_eit_event_assign - Assigns the event loop to the EIT.
+ * @eit: The EIT to assign to.
+ * @e: The event loop
+ *
+ * This will free the previous event loop in the table.
+ * This will assign ownership of the stream loop to the table, i.e. the table
+ * will free this stream loop when a call to its destroy function is made.
+ */
+void vidtv_psi_eit_event_assign(struct vidtv_psi_table_eit *eit,
+ struct vidtv_psi_table_eit_event *e);
+
+struct vidtv_psi_table_eit_event
+*vidtv_psi_eit_event_init(struct vidtv_psi_table_eit_event *head, u16 event_id);
+
+void vidtv_psi_eit_event_destroy(struct vidtv_psi_table_eit_event *e);
+
#endif // VIDTV_PSI_H
#define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__
-#include <linux/types.h>
-#include <linux/slab.h>
+#include <linux/bug.h>
#include <linux/crc32.h>
-#include <linux/vmalloc.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
+#include <linux/fixp-arith.h>
#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
#include <linux/printk.h>
#include <linux/ratelimit.h>
-#include <linux/fixp-arith.h>
-
-#include <linux/math64.h>
-#include <asm/byteorder.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/vmalloc.h>
-#include "vidtv_s302m.h"
-#include "vidtv_encoder.h"
#include "vidtv_common.h"
+#include "vidtv_encoder.h"
+#include "vidtv_s302m.h"
#define S302M_SAMPLING_RATE_HZ 48000
#define PES_PRIVATE_STREAM_1 0xbd /* PES: private_stream_1 */
int duration;
};
-#define COMPASS 120 /* beats per minute (Allegro) */
-static const struct tone_duration beethoven_5th_symphony[] = {
+#define COMPASS 100 /* beats per minute */
+static const struct tone_duration beethoven_fur_elise[] = {
+ { NOTE_SILENT, 512},
{ NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128},
{ NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128},
{ NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128},
{ NOTE_E_5, 128}, { NOTE_D_5, 128}, { NOTE_A_3, 128},
{ NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_E_4, 128},
{ NOTE_D_5, 128}, { NOTE_C_5, 128}, { NOTE_E_3, 128},
- { NOTE_E_4, 128}, { NOTE_E_5, 255}, { NOTE_E_6, 128},
- { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_E_5, 255},
+ { NOTE_E_4, 128}, { NOTE_E_5, 128}, { NOTE_E_5, 128},
+ { NOTE_E_6, 128}, { NOTE_E_5, 128}, { NOTE_E_6, 128},
+ { NOTE_E_5, 128}, { NOTE_E_5, 128}, { NOTE_DS_5, 128},
+ { NOTE_E_5, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128},
{ NOTE_DS_5, 128}, { NOTE_E_5, 128}, { NOTE_DS_6, 128},
- { NOTE_E_6, 128}, { NOTE_DS_5, 128}, { NOTE_E_5, 128},
- { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128},
{ NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128},
- { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128},
- { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128},
- { NOTE_C_5, 128}, { NOTE_E_5, 128}, { NOTE_A_5, 128},
- { NOTE_E_3, 128}, { NOTE_E_4, 128}, { NOTE_GS_4, 128},
- { NOTE_E_5, 128}, { NOTE_GS_5, 128}, { NOTE_B_5, 128},
- { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128},
- { NOTE_E_5, 128}, { NOTE_E_6, 128}, { NOTE_DS_6, 128},
+ { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128},
+ { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128},
+ { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_C_5, 128},
+ { NOTE_E_5, 128}, { NOTE_A_5, 128}, { NOTE_E_3, 128},
+ { NOTE_E_4, 128}, { NOTE_GS_4, 128}, { NOTE_E_5, 128},
+ { NOTE_GS_5, 128}, { NOTE_B_5, 128}, { NOTE_A_3, 128},
+ { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_E_5, 128},
{ NOTE_E_6, 128}, { NOTE_DS_6, 128}, { NOTE_E_6, 128},
- { NOTE_B_5, 128}, { NOTE_D_6, 128}, { NOTE_C_6, 128},
- { NOTE_A_3, 128}, { NOTE_E_4, 128}, { NOTE_A_4, 128},
- { NOTE_C_5, 128}, { NOTE_E_5, 128}, { NOTE_A_5, 128},
- { NOTE_E_3, 128}, { NOTE_E_4, 128}, { NOTE_GS_4, 128},
- { NOTE_E_5, 128}, { NOTE_C_6, 128}, { NOTE_B_5, 128},
- { NOTE_C_5, 255}, { NOTE_C_5, 255}, { NOTE_SILENT, 512},
+ { NOTE_DS_6, 128}, { NOTE_E_6, 128}, { NOTE_B_5, 128},
+ { NOTE_D_6, 128}, { NOTE_C_6, 128}, { NOTE_A_3, 128},
+ { NOTE_E_4, 128}, { NOTE_A_4, 128}, { NOTE_C_5, 128},
+ { NOTE_E_5, 128}, { NOTE_A_5, 128}, { NOTE_E_3, 128},
+ { NOTE_E_4, 128}, { NOTE_GS_4, 128}, { NOTE_E_5, 128},
+ { NOTE_C_6, 128}, { NOTE_B_5, 128}, { NOTE_A_5, 512},
+ { NOTE_SILENT, 256},
};
static struct vidtv_access_unit *vidtv_s302m_access_unit_init(struct vidtv_access_unit *head)
{
- struct vidtv_access_unit *au = kzalloc(sizeof(*au), GFP_KERNEL);
+ struct vidtv_access_unit *au;
+
+ au = kzalloc(sizeof(*au), GFP_KERNEL);
+ if (!au)
+ return NULL;
if (head) {
while (head->next)
static void
vidtv_s302m_compute_sample_count_from_video(struct vidtv_encoder *e)
{
- struct vidtv_access_unit *au = e->access_units;
struct vidtv_access_unit *sync_au = e->sync->access_units;
- u32 vau_duration_usecs;
+ struct vidtv_access_unit *au = e->access_units;
u32 sample_duration_usecs;
+ u32 vau_duration_usecs;
u32 s;
vau_duration_usecs = USEC_PER_SEC / e->sync->sampling_rate_hz;
{
u16 sample;
int pos;
+ struct vidtv_s302m_ctx *ctx = e->ctx;
if (!e->src_buf) {
/*
* Simple tone generator: play the tones at the
- * beethoven_5th_symphony array.
+ * beethoven_fur_elise array.
*/
- if (e->last_duration <= 0) {
- if (e->src_buf_offset >= ARRAY_SIZE(beethoven_5th_symphony))
+ if (ctx->last_duration <= 0) {
+ if (e->src_buf_offset >= ARRAY_SIZE(beethoven_fur_elise))
e->src_buf_offset = 0;
- e->last_tone = beethoven_5th_symphony[e->src_buf_offset].note;
- e->last_duration = beethoven_5th_symphony[e->src_buf_offset].duration * S302M_SAMPLING_RATE_HZ / COMPASS / 5;
+ ctx->last_tone = beethoven_fur_elise[e->src_buf_offset].note;
+ ctx->last_duration = beethoven_fur_elise[e->src_buf_offset].duration *
+ S302M_SAMPLING_RATE_HZ / COMPASS / 5;
e->src_buf_offset++;
- e->note_offset = 0;
+ ctx->note_offset = 0;
} else {
- e->last_duration--;
+ ctx->last_duration--;
}
- /* Handle silent */
- if (!e->last_tone) {
- e->src_buf_offset = 0;
+ /* Handle pause notes */
+ if (!ctx->last_tone)
return 0x8000;
- }
- pos = (2 * PI * e->note_offset * e->last_tone / S302M_SAMPLING_RATE_HZ);
-
- if (pos == 360)
- e->note_offset = 0;
- else
- e->note_offset++;
+ pos = (2 * PI * ctx->note_offset * ctx->last_tone) / S302M_SAMPLING_RATE_HZ;
+ ctx->note_offset++;
return (fixp_sin32(pos % (2 * PI)) >> 16) + 0x8000;
}
static u32 vidtv_s302m_write_frame(struct vidtv_encoder *e,
u16 sample)
{
- u32 nbytes = 0;
- struct vidtv_s302m_frame_16 f = {};
struct vidtv_s302m_ctx *ctx = e->ctx;
+ struct vidtv_s302m_frame_16 f = {};
+ u32 nbytes = 0;
/* from ffmpeg: see s302enc.c */
static void *vidtv_s302m_encode(struct vidtv_encoder *e)
{
+ struct vidtv_s302m_ctx *ctx = e->ctx;
+
/*
* According to SMPTE 302M, an audio access unit is specified as those
* AES3 words that are associated with a corresponding video frame.
* ffmpeg
*/
- struct vidtv_s302m_ctx *ctx = e->ctx;
-
vidtv_s302m_access_unit_destroy(e);
vidtv_s302m_alloc_au(e);
struct vidtv_encoder
*vidtv_s302m_encoder_init(struct vidtv_s302m_encoder_init_args args)
{
- struct vidtv_encoder *e = kzalloc(sizeof(*e), GFP_KERNEL);
u32 priv_sz = sizeof(struct vidtv_s302m_ctx);
+ struct vidtv_s302m_ctx *ctx;
+ struct vidtv_encoder *e;
+
+ e = kzalloc(sizeof(*e), GFP_KERNEL);
+ if (!e)
+ return NULL;
e->id = S302M;
e->encoder_buf_offset = 0;
e->sample_count = 0;
- e->last_duration = 0;
e->src_buf = (args.src_buf) ? args.src_buf : NULL;
e->src_buf_sz = (args.src_buf) ? args.src_buf_sz : 0;
e->src_buf_offset = 0;
e->is_video_encoder = false;
- e->ctx = kzalloc(priv_sz, GFP_KERNEL);
+
+ ctx = kzalloc(priv_sz, GFP_KERNEL);
+ if (!ctx)
+ return NULL;
+
+ e->ctx = ctx;
+ ctx->last_duration = 0;
e->encode = vidtv_s302m_encode;
e->clear = vidtv_s302m_clear;
#define VIDTV_S302M_H
#include <linux/types.h>
-#include <asm/byteorder.h>
#include "vidtv_encoder.h"
* @enc: A pointer to the containing encoder structure.
* @frame_index: The current frame in a block
* @au_count: The total number of access units encoded up to now
+ * @last_duration: Duration of the tone currently being played
+ * @note_offset: Position at the music tone array
+ * @last_tone: Tone currently being played
*/
struct vidtv_s302m_ctx {
struct vidtv_encoder *enc;
u32 frame_index;
u32 au_count;
+ int last_duration;
+ unsigned int note_offset;
+ enum musical_notes last_tone;
};
-/**
+/*
* struct vidtv_smpte_s302m_es - s302m MPEG Elementary Stream header.
*
* See SMPTE 302M 2007 table 1.
#define pr_fmt(fmt) KBUILD_MODNAME ":%s, %d: " fmt, __func__, __LINE__
+#include <linux/math64.h>
#include <linux/printk.h>
#include <linux/ratelimit.h>
#include <linux/types.h>
-#include <linux/math64.h>
-#include <asm/byteorder.h>
-#include "vidtv_ts.h"
#include "vidtv_common.h"
+#include "vidtv_ts.h"
static u32 vidtv_ts_write_pcr_bits(u8 *to, u32 to_offset, u64 pcr)
{
#define VIDTV_TS_H
#include <linux/types.h>
-#include <asm/byteorder.h>
#define TS_SYNC_BYTE 0x47
#define TS_PACKET_LEN 188
* @dest_offset: The byte offset into the buffer.
* @pid: The TS PID for the PCR packets.
* @buf_sz: The size of the buffer in bytes.
- * @countinuity_counter: The TS continuity_counter.
+ * @continuity_counter: The TS continuity_counter.
* @pcr: A sample from the system clock.
*/
struct pcr_write_args {
* @dest_buf: The buffer to write into.
* @dest_offset: The byte offset into the buffer.
* @buf_sz: The size of the buffer in bytes.
- * @countinuity_counter: The TS continuity_counter.
+ * @continuity_counter: The TS continuity_counter.
*/
struct null_packet_write_args {
void *dest_buf;
#include <linux/errno.h>
#include <linux/i2c.h>
#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/ratelimit.h>
#include <linux/slab.h>
#include <linux/types.h>
+
#include <media/dvb_frontend.h>
-#include <linux/printk.h>
-#include <linux/ratelimit.h>
#include "vidtv_tuner.h"
#define VIDTV_TUNER_H
#include <linux/types.h>
+
#include <media/dvb_frontend.h>
#define NUM_VALID_TUNER_FREQS 8
MPT_SCSI_HOST *hd;
int sz1;
- if((hd = shost_priv(host)) == NULL)
- return;
+ if (host == NULL)
+ hd = NULL;
+ else
+ hd = shost_priv(host);
mptscsih_shutdown(pdev);
"Free'd ScsiLookup (%d) memory\n",
ioc->name, sz1));
- kfree(hd->info_kbuf);
+ if (hd)
+ kfree(hd->info_kbuf);
/* NULL the Scsi_Host pointer
*/
ioc->sh = NULL;
- scsi_host_put(host);
-
+ if (host)
+ scsi_host_put(host);
mpt_detach(pdev);
}
source "drivers/misc/altera-stapl/Kconfig"
source "drivers/misc/mei/Kconfig"
source "drivers/misc/vmw_vmci/Kconfig"
-source "drivers/misc/mic/Kconfig"
source "drivers/misc/genwqe/Kconfig"
source "drivers/misc/echo/Kconfig"
source "drivers/misc/cxl/Kconfig"
obj-$(CONFIG_LATTICE_ECP3_CONFIG) += lattice-ecp3-config.o
obj-$(CONFIG_SRAM) += sram.o
obj-$(CONFIG_SRAM_EXEC) += sram-exec.o
-obj-y += mic/
obj-$(CONFIG_GENWQE) += genwqe/
obj-$(CONFIG_ECHO) += echo/
obj-$(CONFIG_CXL_BASE) += cxl/
{
if (cb->is_internal)
gen_pool_free(hdev->internal_cb_pool,
- cb->kernel_address, cb->size);
+ (uintptr_t)cb->kernel_address, cb->size);
else
hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size,
- (void *) (uintptr_t) cb->kernel_address,
- cb->bus_address);
+ cb->kernel_address, cb->bus_address);
kfree(cb);
}
return NULL;
}
- cb->kernel_address = (u64) (uintptr_t) p;
+ cb->kernel_address = p;
cb->size = cb_size;
return cb;
vma->vm_private_data = cb;
- rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address,
+ rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
cb->bus_address, cb->size);
if (rc) {
spin_lock(&cb->lock);
static void device_cdev_sysfs_del(struct hl_device *hdev)
{
- /* device_release() won't be called so must free devices explicitly */
- if (!hdev->cdev_sysfs_created) {
- kfree(hdev->dev_ctrl);
- kfree(hdev->dev);
- return;
- }
+ if (!hdev->cdev_sysfs_created)
+ goto put_devices;
hl_sysfs_fini(hdev);
cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl);
cdev_device_del(&hdev->cdev, hdev->dev);
+
+put_devices:
+ put_device(hdev->dev);
+ put_device(hdev->dev_ctrl);
}
/*
early_fini:
device_early_fini(hdev);
free_dev_ctrl:
- kfree(hdev->dev_ctrl);
+ put_device(hdev->dev_ctrl);
free_dev:
- kfree(hdev->dev);
+ put_device(hdev->dev);
out_disabled:
hdev->disabled = true;
if (add_cdev_sysfs_on_err)
struct list_head pool_list;
struct list_head va_block_list;
u64 id;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 mmap_size;
u32 size;
struct hl_hw_sob hw_sob[HL_RSVD_SOBS];
struct hl_cs_job **shadow_queue;
enum hl_queue_type queue_type;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 pi;
atomic_t ci;
*/
struct hl_cq {
struct hl_device *hdev;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 cq_idx;
u32 hw_queue_id;
*/
struct hl_eq {
struct hl_device *hdev;
- u64 kernel_address;
+ void *kernel_address;
dma_addr_t bus_address;
u32 ci;
};
u32 (*get_dma_desc_list_size)(struct hl_device *hdev,
struct sg_table *sgt);
void (*add_end_of_cb_packets)(struct hl_device *hdev,
- u64 kernel_address, u32 len,
+ void *kernel_address, u32 len,
u64 cq_addr, u32 cq_val, u32 msix_num,
bool eb);
void (*update_eq_ci)(struct hl_device *hdev, u32 val);
for (;;) { \
/* Verify we read updates done by other cores or by device */ \
mb(); \
- (val) = *((u32 *) (uintptr_t) (addr)); \
+ (val) = *((u32 *)(addr)); \
if (mem_written_by_device) \
(val) = le32_to_cpu(*(__le32 *) &(val)); \
if (cond) \
break; \
if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
- (val) = *((u32 *) (uintptr_t) (addr)); \
+ (val) = *((u32 *)(addr)); \
if (mem_written_by_device) \
(val) = le32_to_cpu(*(__le32 *) &(val)); \
break; \
{
struct hl_bd *bd;
- bd = (struct hl_bd *) (uintptr_t) q->kernel_address;
+ bd = q->kernel_address;
bd += hl_pi_2_offset(q->pi);
bd->ctl = cpu_to_le32(ctl);
bd->len = cpu_to_le32(len);
bd.len = cpu_to_le32(job->job_cb_size);
bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb);
- pi = (__le64 *) (uintptr_t) (q->kernel_address +
- ((q->pi & (q->int_queue_len - 1)) * sizeof(bd)));
+ pi = q->kernel_address + (q->pi & (q->int_queue_len - 1)) * sizeof(bd);
q->pi++;
q->pi &= ((q->int_queue_len << 1) - 1);
if (!p)
return -ENOMEM;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH,
sizeof(*q->shadow_queue),
if (is_cpu_queue)
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address);
+ q->kernel_address);
else
hdev->asic_funcs->asic_dma_free_coherent(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address,
+ q->kernel_address,
q->bus_address);
return rc;
return -EFAULT;
}
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->pi = 0;
atomic_set(&q->ci, 0);
if (!p)
return -ENOMEM;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
/* Make sure read/write pointers are initialized to start of queue */
atomic_set(&q->ci, 0);
if (q->queue_type == QUEUE_TYPE_CPU)
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address);
+ q->kernel_address);
else
hdev->asic_funcs->asic_dma_free_coherent(hdev,
HL_QUEUE_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address,
+ q->kernel_address,
q->bus_address);
}
return IRQ_HANDLED;
}
- cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address;
+ cq_base = cq->kernel_address;
while (1) {
bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) &
struct hl_eq_entry *eq_base;
struct hl_eqe_work *handle_eqe_work;
- eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address;
+ eq_base = eq->kernel_address;
while (1) {
bool entry_ready =
return -ENOMEM;
q->hdev = hdev;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->hw_queue_id = hw_queue_id;
q->ci = 0;
q->pi = 0;
void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q)
{
hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address, q->bus_address);
+ q->kernel_address,
+ q->bus_address);
}
void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q)
* when the device is operational again
*/
- memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
+ memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES);
}
/**
return -ENOMEM;
q->hdev = hdev;
- q->kernel_address = (u64) (uintptr_t) p;
+ q->kernel_address = p;
q->ci = 0;
return 0;
hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
HL_EQ_SIZE_IN_BYTES,
- (void *) (uintptr_t) q->kernel_address);
+ q->kernel_address);
}
void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q)
* when the device is operational again
*/
- memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
+ memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES);
}
goto host_hpage_range_err;
}
} else {
+ kfree(ctx->host_huge_va_range);
ctx->host_huge_va_range = ctx->host_va_range;
}
if (!cb)
return -EFAULT;
- init_tpc_mem_pkt = (struct packet_lin_dma *) (uintptr_t)
- cb->kernel_address;
+ init_tpc_mem_pkt = cb->kernel_address;
cb_size = sizeof(*init_tpc_mem_pkt);
memset(init_tpc_mem_pkt, 0, cb_size);
u16 pkt_size;
struct gaudi_packet *user_pkt;
- user_pkt = (struct gaudi_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
u32 new_pkt_size = 0;
struct gaudi_packet *user_pkt, *kernel_pkt;
- user_pkt = (struct gaudi_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
- kernel_pkt = (struct gaudi_packet *) (uintptr_t)
- (parser->patched_cb->kernel_address +
- cb_patched_cur_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
+ kernel_pkt = parser->patched_cb->kernel_address +
+ cb_patched_cur_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
* The check that parser->user_cb_size <= parser->user_cb->size was done
* in validate_queue_index().
*/
- memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address,
- (void *) (uintptr_t) parser->user_cb->kernel_address,
+ memcpy(parser->patched_cb->kernel_address,
+ parser->user_cb->kernel_address,
parser->user_cb_size);
patched_cb_size = parser->patched_cb_size;
}
static void gaudi_add_end_of_cb_packets(struct hl_device *hdev,
- u64 kernel_address, u32 len,
+ void *kernel_address, u32 len,
u64 cq_addr, u32 cq_val, u32 msi_vec,
bool eb)
{
struct packet_msg_prot *cq_pkt;
u32 tmp;
- cq_pkt = (struct packet_msg_prot *) (uintptr_t)
- (kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
+ cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2);
tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
if (!cb)
return -EFAULT;
- lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
+ lin_dma_pkt = cb->kernel_address;
memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
cb_size = sizeof(*lin_dma_pkt);
(addr - gaudi->hbm_bar_cur_addr));
}
-static void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid)
+void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid)
{
/* mask to zero the MMBP and ASID bits */
WREG32_AND(reg, ~0x7FF);
gaudi_mmu_prepare_reg(hdev, mmMME2_ACC_WBC, asid);
gaudi_mmu_prepare_reg(hdev, mmMME3_ACC_WBC, asid);
- gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
- gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
-
hdev->asic_funcs->set_clock_gating(hdev);
mutex_unlock(&gaudi->clk_gate_mutex);
cb = job->patched_cb;
- fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
- job->job_cb_size - sizeof(struct packet_msg_prot));
+ fence_pkt = cb->kernel_address +
+ job->job_cb_size - sizeof(struct packet_msg_prot);
tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT);
tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
params.num_memories = 33;
params.derr = true;
params.disable_clock_gating = true;
+ extract_info_from_fw = false;
+ break;
default:
return;
}
struct packet_msg_short *pkt;
u32 value, ctl;
- pkt = (struct packet_msg_short *) (uintptr_t) cb->kernel_address;
+ pkt = cb->kernel_address;
memset(pkt, 0, sizeof(*pkt));
/* Inc by 1, Mode ADD */
u16 sob_val, u16 mon_id, u32 q_idx)
{
struct hl_cb *cb = (struct hl_cb *) data;
- void *buf = (void *) (uintptr_t) cb->kernel_address;
+ void *buf = cb->kernel_address;
u64 monitor_base, fence_addr = 0;
u32 size = 0;
u16 msg_addr_offset;
int gaudi_debug_coresight(struct hl_device *hdev, void *data);
void gaudi_halt_coresight(struct hl_device *hdev);
int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
+void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid);
#endif /* GAUDIP_H_ */
return -EINVAL;
}
+ gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER,
+ hdev->compute_ctx->asid);
+ gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER,
+ hdev->compute_ctx->asid);
+
msb = upper_32_bits(input->buffer_address) >> 8;
msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK;
WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb);
cb = job->patched_cb;
- fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address +
- job->job_cb_size - sizeof(struct packet_msg_prot));
+ fence_pkt = cb->kernel_address +
+ job->job_cb_size - sizeof(struct packet_msg_prot);
tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) |
(1 << GOYA_PKT_CTL_EB_SHIFT) |
u16 pkt_size;
struct goya_packet *user_pkt;
- user_pkt = (struct goya_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
u32 new_pkt_size = 0;
struct goya_packet *user_pkt, *kernel_pkt;
- user_pkt = (struct goya_packet *) (uintptr_t)
- (parser->user_cb->kernel_address + cb_parsed_length);
- kernel_pkt = (struct goya_packet *) (uintptr_t)
- (parser->patched_cb->kernel_address +
- cb_patched_cur_length);
+ user_pkt = parser->user_cb->kernel_address + cb_parsed_length;
+ kernel_pkt = parser->patched_cb->kernel_address +
+ cb_patched_cur_length;
pkt_id = (enum packet_id) (
(le64_to_cpu(user_pkt->header) &
* The check that parser->user_cb_size <= parser->user_cb->size was done
* in validate_queue_index().
*/
- memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address,
- (void *) (uintptr_t) parser->user_cb->kernel_address,
+ memcpy(parser->patched_cb->kernel_address,
+ parser->user_cb->kernel_address,
parser->user_cb_size);
patched_cb_size = parser->patched_cb_size;
return goya_parse_cb_no_mmu(hdev, parser);
}
-void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address,
u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec,
bool eb)
{
struct packet_msg_prot *cq_pkt;
u32 tmp;
- cq_pkt = (struct packet_msg_prot *) (uintptr_t)
- (kernel_address + len - (sizeof(struct packet_msg_prot) * 2));
+ cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2);
tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) |
(1 << GOYA_PKT_CTL_EB_SHIFT) |
if (!cb)
return -ENOMEM;
- lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address;
+ lin_dma_pkt = cb->kernel_address;
do {
memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt));
void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry);
void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size);
-void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address,
+void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address,
u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec,
bool eb);
int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser);
#define QM_ARB_ERR_MSG_EN_MASK (\
QM_ARB_ERR_MSG_EN_CHOISE_OVF_MASK |\
- QM_ARB_ERR_MSG_EN_CHOISE_WDT_MASK |\
QM_ARB_ERR_MSG_EN_AXI_LBW_ERR_MASK)
#define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK 0x1
Supported SoCs:
Intel Bay Trail
-config INTEL_MEI_VIRTIO
- tristate "Intel MEI interface emulation with virtio framework"
- select INTEL_MEI
- depends on X86 && PCI && VIRTIO_PCI
- help
- This module implements mei hw emulation over virtio transport.
- The module will be called mei_virtio.
- Enable this if your virtual machine supports virtual mei
- device over virtio.
-
source "drivers/misc/mei/hdcp/Kconfig"
mei-txe-objs := pci-txe.o
mei-txe-objs += hw-txe.o
-obj-$(CONFIG_INTEL_MEI_VIRTIO) += mei-virtio.o
-mei-virtio-objs := hw-virtio.o
-
mei-$(CONFIG_EVENT_TRACING) += mei-trace.o
CFLAGS_mei-trace.o = -I$(src)
*
* @cl: host client
*
- * Return: mtu
+ * Return: mtu or 0 if client is not connected
*/
static inline size_t mei_cl_mtu(const struct mei_cl *cl)
{
- return cl->me_cl->props.max_msg_length;
+ return cl->me_cl ? cl->me_cl->props.max_msg_length : 0;
}
/**
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Intel Management Engine Interface (Intel MEI) Linux driver
- * Copyright (c) 2018-2020, Intel Corporation.
- */
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/pm_runtime.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock.h>
-#include <linux/slab.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ids.h>
-#include <linux/atomic.h>
-
-#include "mei_dev.h"
-#include "hbm.h"
-#include "client.h"
-
-#define MEI_VIRTIO_RPM_TIMEOUT 500
-/* ACRN virtio device types */
-#ifndef VIRTIO_ID_MEI
-#define VIRTIO_ID_MEI 0xFFFE /* virtio mei */
-#endif
-
-/**
- * struct mei_virtio_cfg - settings passed from the virtio backend
- * @buf_depth: read buffer depth in slots (4bytes)
- * @hw_ready: hw is ready for operation
- * @host_reset: synchronize reset with virtio backend
- * @reserved: reserved for alignment
- * @fw_status: FW status
- */
-struct mei_virtio_cfg {
- u32 buf_depth;
- u8 hw_ready;
- u8 host_reset;
- u8 reserved[2];
- u32 fw_status[MEI_FW_STATUS_MAX];
-} __packed;
-
-struct mei_virtio_hw {
- struct mei_device mdev;
- char name[32];
-
- struct virtqueue *in;
- struct virtqueue *out;
-
- bool host_ready;
- struct work_struct intr_handler;
-
- u32 *recv_buf;
- u8 recv_rdy;
- size_t recv_sz;
- u32 recv_idx;
- u32 recv_len;
-
- /* send buffer */
- atomic_t hbuf_ready;
- const void *send_hdr;
- const void *send_buf;
-
- struct mei_virtio_cfg cfg;
-};
-
-#define to_virtio_hw(_dev) container_of(_dev, struct mei_virtio_hw, mdev)
-
-/**
- * mei_virtio_fw_status() - read status register of mei
- * @dev: mei device
- * @fw_status: fw status register values
- *
- * Return: always 0
- */
-static int mei_virtio_fw_status(struct mei_device *dev,
- struct mei_fw_status *fw_status)
-{
- struct virtio_device *vdev = dev_to_virtio(dev->dev);
-
- fw_status->count = MEI_FW_STATUS_MAX;
- virtio_cread_bytes(vdev, offsetof(struct mei_virtio_cfg, fw_status),
- fw_status->status, sizeof(fw_status->status));
- return 0;
-}
-
-/**
- * mei_virtio_pg_state() - translate internal pg state
- * to the mei power gating state
- * There is no power management in ACRN mode always return OFF
- * @dev: mei device
- *
- * Return:
- * * MEI_PG_OFF - if aliveness is on (always)
- * * MEI_PG_ON - (never)
- */
-static inline enum mei_pg_state mei_virtio_pg_state(struct mei_device *dev)
-{
- return MEI_PG_OFF;
-}
-
-/**
- * mei_virtio_hw_config() - configure hw dependent settings
- *
- * @dev: mei device
- *
- * Return: always 0
- */
-static int mei_virtio_hw_config(struct mei_device *dev)
-{
- return 0;
-}
-
-/**
- * mei_virtio_hbuf_empty_slots() - counts write empty slots.
- * @dev: the device structure
- *
- * Return: always return frontend buf size if buffer is ready, 0 otherwise
- */
-static int mei_virtio_hbuf_empty_slots(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- return (atomic_read(&hw->hbuf_ready) == 1) ? hw->cfg.buf_depth : 0;
-}
-
-/**
- * mei_virtio_hbuf_is_ready() - checks if write buffer is ready
- * @dev: the device structure
- *
- * Return: true if hbuf is ready
- */
-static bool mei_virtio_hbuf_is_ready(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- return atomic_read(&hw->hbuf_ready) == 1;
-}
-
-/**
- * mei_virtio_hbuf_max_depth() - returns depth of FE write buffer.
- * @dev: the device structure
- *
- * Return: size of frontend write buffer in bytes
- */
-static u32 mei_virtio_hbuf_depth(const struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- return hw->cfg.buf_depth;
-}
-
-/**
- * mei_virtio_intr_clear() - clear and stop interrupts
- * @dev: the device structure
- */
-static void mei_virtio_intr_clear(struct mei_device *dev)
-{
- /*
- * In our virtio solution, there are two types of interrupts,
- * vq interrupt and config change interrupt.
- * 1) start/reset rely on virtio config changed interrupt;
- * 2) send/recv rely on virtio virtqueue interrupts.
- * They are all virtual interrupts. So, we don't have corresponding
- * operation to do here.
- */
-}
-
-/**
- * mei_virtio_intr_enable() - enables mei BE virtqueues callbacks
- * @dev: the device structure
- */
-static void mei_virtio_intr_enable(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- struct virtio_device *vdev = dev_to_virtio(dev->dev);
-
- virtio_config_enable(vdev);
-
- virtqueue_enable_cb(hw->in);
- virtqueue_enable_cb(hw->out);
-}
-
-/**
- * mei_virtio_intr_disable() - disables mei BE virtqueues callbacks
- *
- * @dev: the device structure
- */
-static void mei_virtio_intr_disable(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- struct virtio_device *vdev = dev_to_virtio(dev->dev);
-
- virtio_config_disable(vdev);
-
- virtqueue_disable_cb(hw->in);
- virtqueue_disable_cb(hw->out);
-}
-
-/**
- * mei_virtio_synchronize_irq() - wait for pending IRQ handlers for all
- * virtqueue
- * @dev: the device structure
- */
-static void mei_virtio_synchronize_irq(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- /*
- * Now, all IRQ handlers are converted to workqueue.
- * Change synchronize irq to flush this work.
- */
- flush_work(&hw->intr_handler);
-}
-
-static void mei_virtio_free_outbufs(struct mei_virtio_hw *hw)
-{
- kfree(hw->send_hdr);
- kfree(hw->send_buf);
- hw->send_hdr = NULL;
- hw->send_buf = NULL;
-}
-
-/**
- * mei_virtio_write_message() - writes a message to mei virtio back-end service.
- * @dev: the device structure
- * @hdr: mei header of message
- * @hdr_len: header length
- * @data: message payload will be written
- * @data_len: message payload length
- *
- * Return:
- * * 0: on success
- * * -EIO: if write has failed
- * * -ENOMEM: on memory allocation failure
- */
-static int mei_virtio_write_message(struct mei_device *dev,
- const void *hdr, size_t hdr_len,
- const void *data, size_t data_len)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- struct scatterlist sg[2];
- const void *hbuf, *dbuf;
- int ret;
-
- if (WARN_ON(!atomic_add_unless(&hw->hbuf_ready, -1, 0)))
- return -EIO;
-
- hbuf = kmemdup(hdr, hdr_len, GFP_KERNEL);
- hw->send_hdr = hbuf;
-
- dbuf = kmemdup(data, data_len, GFP_KERNEL);
- hw->send_buf = dbuf;
-
- if (!hbuf || !dbuf) {
- ret = -ENOMEM;
- goto fail;
- }
-
- sg_init_table(sg, 2);
- sg_set_buf(&sg[0], hbuf, hdr_len);
- sg_set_buf(&sg[1], dbuf, data_len);
-
- ret = virtqueue_add_outbuf(hw->out, sg, 2, hw, GFP_KERNEL);
- if (ret) {
- dev_err(dev->dev, "failed to add outbuf\n");
- goto fail;
- }
-
- virtqueue_kick(hw->out);
- return 0;
-fail:
-
- mei_virtio_free_outbufs(hw);
-
- return ret;
-}
-
-/**
- * mei_virtio_count_full_read_slots() - counts read full slots.
- * @dev: the device structure
- *
- * Return: -EOVERFLOW if overflow, otherwise filled slots count
- */
-static int mei_virtio_count_full_read_slots(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- if (hw->recv_idx > hw->recv_len)
- return -EOVERFLOW;
-
- return hw->recv_len - hw->recv_idx;
-}
-
-/**
- * mei_virtio_read_hdr() - Reads 32bit dword from mei virtio receive buffer
- *
- * @dev: the device structure
- *
- * Return: 32bit dword of receive buffer (u32)
- */
-static inline u32 mei_virtio_read_hdr(const struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- WARN_ON(hw->cfg.buf_depth < hw->recv_idx + 1);
-
- return hw->recv_buf[hw->recv_idx++];
-}
-
-static int mei_virtio_read(struct mei_device *dev, unsigned char *buffer,
- unsigned long len)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- u32 slots = mei_data2slots(len);
-
- if (WARN_ON(hw->cfg.buf_depth < hw->recv_idx + slots))
- return -EOVERFLOW;
-
- /*
- * Assumption: There is only one MEI message in recv_buf each time.
- * Backend service need follow this rule too.
- */
- memcpy(buffer, hw->recv_buf + hw->recv_idx, len);
- hw->recv_idx += slots;
-
- return 0;
-}
-
-static bool mei_virtio_pg_is_enabled(struct mei_device *dev)
-{
- return false;
-}
-
-static bool mei_virtio_pg_in_transition(struct mei_device *dev)
-{
- return false;
-}
-
-static void mei_virtio_add_recv_buf(struct mei_virtio_hw *hw)
-{
- struct scatterlist sg;
-
- if (hw->recv_rdy) /* not needed */
- return;
-
- /* refill the recv_buf to IN virtqueue to get next message */
- sg_init_one(&sg, hw->recv_buf, mei_slots2data(hw->cfg.buf_depth));
- hw->recv_len = 0;
- hw->recv_idx = 0;
- hw->recv_rdy = 1;
- virtqueue_add_inbuf(hw->in, &sg, 1, hw->recv_buf, GFP_KERNEL);
- virtqueue_kick(hw->in);
-}
-
-/**
- * mei_virtio_hw_is_ready() - check whether the BE(hw) has turned ready
- * @dev: mei device
- * Return: bool
- */
-static bool mei_virtio_hw_is_ready(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- struct virtio_device *vdev = dev_to_virtio(dev->dev);
-
- virtio_cread(vdev, struct mei_virtio_cfg,
- hw_ready, &hw->cfg.hw_ready);
-
- dev_dbg(dev->dev, "hw ready %d\n", hw->cfg.hw_ready);
-
- return hw->cfg.hw_ready;
-}
-
-/**
- * mei_virtio_hw_reset - resets virtio hw.
- *
- * @dev: the device structure
- * @intr_enable: virtio use data/config callbacks
- *
- * Return: 0 on success an error code otherwise
- */
-static int mei_virtio_hw_reset(struct mei_device *dev, bool intr_enable)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- struct virtio_device *vdev = dev_to_virtio(dev->dev);
-
- dev_dbg(dev->dev, "hw reset\n");
-
- dev->recvd_hw_ready = false;
- hw->host_ready = false;
- atomic_set(&hw->hbuf_ready, 0);
- hw->recv_len = 0;
- hw->recv_idx = 0;
-
- hw->cfg.host_reset = 1;
- virtio_cwrite(vdev, struct mei_virtio_cfg,
- host_reset, &hw->cfg.host_reset);
-
- mei_virtio_hw_is_ready(dev);
-
- if (intr_enable)
- mei_virtio_intr_enable(dev);
-
- return 0;
-}
-
-/**
- * mei_virtio_hw_reset_release() - release device from the reset
- * @dev: the device structure
- */
-static void mei_virtio_hw_reset_release(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- struct virtio_device *vdev = dev_to_virtio(dev->dev);
-
- dev_dbg(dev->dev, "hw reset release\n");
- hw->cfg.host_reset = 0;
- virtio_cwrite(vdev, struct mei_virtio_cfg,
- host_reset, &hw->cfg.host_reset);
-}
-
-/**
- * mei_virtio_hw_ready_wait() - wait until the virtio(hw) has turned ready
- * or timeout is reached
- * @dev: mei device
- *
- * Return: 0 on success, error otherwise
- */
-static int mei_virtio_hw_ready_wait(struct mei_device *dev)
-{
- mutex_unlock(&dev->device_lock);
- wait_event_timeout(dev->wait_hw_ready,
- dev->recvd_hw_ready,
- mei_secs_to_jiffies(MEI_HW_READY_TIMEOUT));
- mutex_lock(&dev->device_lock);
- if (!dev->recvd_hw_ready) {
- dev_err(dev->dev, "wait hw ready failed\n");
- return -ETIMEDOUT;
- }
-
- dev->recvd_hw_ready = false;
- return 0;
-}
-
-/**
- * mei_virtio_hw_start() - hw start routine
- * @dev: mei device
- *
- * Return: 0 on success, error otherwise
- */
-static int mei_virtio_hw_start(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
- int ret;
-
- dev_dbg(dev->dev, "hw start\n");
- mei_virtio_hw_reset_release(dev);
-
- ret = mei_virtio_hw_ready_wait(dev);
- if (ret)
- return ret;
-
- mei_virtio_add_recv_buf(hw);
- atomic_set(&hw->hbuf_ready, 1);
- dev_dbg(dev->dev, "hw is ready\n");
- hw->host_ready = true;
-
- return 0;
-}
-
-/**
- * mei_virtio_host_is_ready() - check whether the FE has turned ready
- * @dev: mei device
- *
- * Return: bool
- */
-static bool mei_virtio_host_is_ready(struct mei_device *dev)
-{
- struct mei_virtio_hw *hw = to_virtio_hw(dev);
-
- dev_dbg(dev->dev, "host ready %d\n", hw->host_ready);
-
- return hw->host_ready;
-}
-
-/**
- * mei_virtio_data_in() - The callback of recv virtqueue of virtio mei
- * @vq: receiving virtqueue
- */
-static void mei_virtio_data_in(struct virtqueue *vq)
-{
- struct mei_virtio_hw *hw = vq->vdev->priv;
-
- /* disable interrupts (enabled again from in the interrupt worker) */
- virtqueue_disable_cb(hw->in);
-
- schedule_work(&hw->intr_handler);
-}
-
-/**
- * mei_virtio_data_out() - The callback of send virtqueue of virtio mei
- * @vq: transmitting virtqueue
- */
-static void mei_virtio_data_out(struct virtqueue *vq)
-{
- struct mei_virtio_hw *hw = vq->vdev->priv;
-
- schedule_work(&hw->intr_handler);
-}
-
-static void mei_virtio_intr_handler(struct work_struct *work)
-{
- struct mei_virtio_hw *hw =
- container_of(work, struct mei_virtio_hw, intr_handler);
- struct mei_device *dev = &hw->mdev;
- LIST_HEAD(complete_list);
- s32 slots;
- int rets = 0;
- void *data;
- unsigned int len;
-
- mutex_lock(&dev->device_lock);
-
- if (dev->dev_state == MEI_DEV_DISABLED) {
- dev_warn(dev->dev, "Interrupt in disabled state.\n");
- mei_virtio_intr_disable(dev);
- goto end;
- }
-
- /* check if ME wants a reset */
- if (!mei_hw_is_ready(dev) && dev->dev_state != MEI_DEV_RESETTING) {
- dev_warn(dev->dev, "BE service not ready: resetting.\n");
- schedule_work(&dev->reset_work);
- goto end;
- }
-
- /* check if we need to start the dev */
- if (!mei_host_is_ready(dev)) {
- if (mei_hw_is_ready(dev)) {
- dev_dbg(dev->dev, "we need to start the dev.\n");
- dev->recvd_hw_ready = true;
- wake_up(&dev->wait_hw_ready);
- } else {
- dev_warn(dev->dev, "Spurious Interrupt\n");
- }
- goto end;
- }
-
- /* read */
- if (hw->recv_rdy) {
- data = virtqueue_get_buf(hw->in, &len);
- if (!data || !len) {
- dev_dbg(dev->dev, "No data %d", len);
- } else {
- dev_dbg(dev->dev, "data_in %d\n", len);
- WARN_ON(data != hw->recv_buf);
- hw->recv_len = mei_data2slots(len);
- hw->recv_rdy = 0;
- }
- }
-
- /* write */
- if (!atomic_read(&hw->hbuf_ready)) {
- if (!virtqueue_get_buf(hw->out, &len)) {
- dev_warn(dev->dev, "Failed to getbuf\n");
- } else {
- mei_virtio_free_outbufs(hw);
- atomic_inc(&hw->hbuf_ready);
- }
- }
-
- /* check slots available for reading */
- slots = mei_count_full_read_slots(dev);
- while (slots > 0) {
- dev_dbg(dev->dev, "slots to read = %08x\n", slots);
- rets = mei_irq_read_handler(dev, &complete_list, &slots);
-
- if (rets &&
- (dev->dev_state != MEI_DEV_RESETTING &&
- dev->dev_state != MEI_DEV_POWER_DOWN)) {
- dev_err(dev->dev, "mei_irq_read_handler ret = %d.\n",
- rets);
- schedule_work(&dev->reset_work);
- goto end;
- }
- }
-
- dev->hbuf_is_ready = mei_hbuf_is_ready(dev);
-
- mei_irq_write_handler(dev, &complete_list);
-
- dev->hbuf_is_ready = mei_hbuf_is_ready(dev);
-
- mei_irq_compl_handler(dev, &complete_list);
-
- mei_virtio_add_recv_buf(hw);
-
-end:
- if (dev->dev_state != MEI_DEV_DISABLED) {
- if (!virtqueue_enable_cb(hw->in))
- schedule_work(&hw->intr_handler);
- }
-
- mutex_unlock(&dev->device_lock);
-}
-
-static void mei_virtio_config_changed(struct virtio_device *vdev)
-{
- struct mei_virtio_hw *hw = vdev->priv;
- struct mei_device *dev = &hw->mdev;
-
- virtio_cread(vdev, struct mei_virtio_cfg,
- hw_ready, &hw->cfg.hw_ready);
-
- if (dev->dev_state == MEI_DEV_DISABLED) {
- dev_dbg(dev->dev, "disabled state don't start\n");
- return;
- }
-
- /* Run intr handler once to handle reset notify */
- schedule_work(&hw->intr_handler);
-}
-
-static void mei_virtio_remove_vqs(struct virtio_device *vdev)
-{
- struct mei_virtio_hw *hw = vdev->priv;
-
- virtqueue_detach_unused_buf(hw->in);
- hw->recv_len = 0;
- hw->recv_idx = 0;
- hw->recv_rdy = 0;
-
- virtqueue_detach_unused_buf(hw->out);
-
- mei_virtio_free_outbufs(hw);
-
- vdev->config->del_vqs(vdev);
-}
-
-/*
- * There are two virtqueues, one is for send and another is for recv.
- */
-static int mei_virtio_init_vqs(struct mei_virtio_hw *hw,
- struct virtio_device *vdev)
-{
- struct virtqueue *vqs[2];
-
- vq_callback_t *cbs[] = {
- mei_virtio_data_in,
- mei_virtio_data_out,
- };
- static const char * const names[] = {
- "in",
- "out",
- };
- int ret;
-
- ret = virtio_find_vqs(vdev, 2, vqs, cbs, names, NULL);
- if (ret)
- return ret;
-
- hw->in = vqs[0];
- hw->out = vqs[1];
-
- return 0;
-}
-
-static const struct mei_hw_ops mei_virtio_ops = {
- .fw_status = mei_virtio_fw_status,
- .pg_state = mei_virtio_pg_state,
-
- .host_is_ready = mei_virtio_host_is_ready,
-
- .hw_is_ready = mei_virtio_hw_is_ready,
- .hw_reset = mei_virtio_hw_reset,
- .hw_config = mei_virtio_hw_config,
- .hw_start = mei_virtio_hw_start,
-
- .pg_in_transition = mei_virtio_pg_in_transition,
- .pg_is_enabled = mei_virtio_pg_is_enabled,
-
- .intr_clear = mei_virtio_intr_clear,
- .intr_enable = mei_virtio_intr_enable,
- .intr_disable = mei_virtio_intr_disable,
- .synchronize_irq = mei_virtio_synchronize_irq,
-
- .hbuf_free_slots = mei_virtio_hbuf_empty_slots,
- .hbuf_is_ready = mei_virtio_hbuf_is_ready,
- .hbuf_depth = mei_virtio_hbuf_depth,
-
- .write = mei_virtio_write_message,
-
- .rdbuf_full_slots = mei_virtio_count_full_read_slots,
- .read_hdr = mei_virtio_read_hdr,
- .read = mei_virtio_read,
-};
-
-static int mei_virtio_probe(struct virtio_device *vdev)
-{
- struct mei_virtio_hw *hw;
- int ret;
-
- hw = devm_kzalloc(&vdev->dev, sizeof(*hw), GFP_KERNEL);
- if (!hw)
- return -ENOMEM;
-
- vdev->priv = hw;
-
- INIT_WORK(&hw->intr_handler, mei_virtio_intr_handler);
-
- ret = mei_virtio_init_vqs(hw, vdev);
- if (ret)
- goto vqs_failed;
-
- virtio_cread(vdev, struct mei_virtio_cfg,
- buf_depth, &hw->cfg.buf_depth);
-
- hw->recv_buf = kzalloc(mei_slots2data(hw->cfg.buf_depth), GFP_KERNEL);
- if (!hw->recv_buf) {
- ret = -ENOMEM;
- goto hbuf_failed;
- }
- atomic_set(&hw->hbuf_ready, 0);
-
- virtio_device_ready(vdev);
-
- mei_device_init(&hw->mdev, &vdev->dev, &mei_virtio_ops);
-
- pm_runtime_get_noresume(&vdev->dev);
- pm_runtime_set_active(&vdev->dev);
- pm_runtime_enable(&vdev->dev);
-
- ret = mei_start(&hw->mdev);
- if (ret)
- goto mei_start_failed;
-
- pm_runtime_set_autosuspend_delay(&vdev->dev, MEI_VIRTIO_RPM_TIMEOUT);
- pm_runtime_use_autosuspend(&vdev->dev);
-
- ret = mei_register(&hw->mdev, &vdev->dev);
- if (ret)
- goto mei_failed;
-
- pm_runtime_put(&vdev->dev);
-
- return 0;
-
-mei_failed:
- mei_stop(&hw->mdev);
-mei_start_failed:
- mei_cancel_work(&hw->mdev);
- mei_disable_interrupts(&hw->mdev);
- kfree(hw->recv_buf);
-hbuf_failed:
- vdev->config->del_vqs(vdev);
-vqs_failed:
- return ret;
-}
-
-static int __maybe_unused mei_virtio_pm_runtime_idle(struct device *device)
-{
- struct virtio_device *vdev = dev_to_virtio(device);
- struct mei_virtio_hw *hw = vdev->priv;
-
- dev_dbg(&vdev->dev, "rpm: mei_virtio : runtime_idle\n");
-
- if (!hw)
- return -ENODEV;
-
- if (mei_write_is_idle(&hw->mdev))
- pm_runtime_autosuspend(device);
-
- return -EBUSY;
-}
-
-static int __maybe_unused mei_virtio_pm_runtime_suspend(struct device *device)
-{
- return 0;
-}
-
-static int __maybe_unused mei_virtio_pm_runtime_resume(struct device *device)
-{
- return 0;
-}
-
-static int __maybe_unused mei_virtio_freeze(struct virtio_device *vdev)
-{
- struct mei_virtio_hw *hw = vdev->priv;
-
- dev_dbg(&vdev->dev, "freeze\n");
-
- if (!hw)
- return -ENODEV;
-
- mei_stop(&hw->mdev);
- mei_disable_interrupts(&hw->mdev);
- cancel_work_sync(&hw->intr_handler);
- vdev->config->reset(vdev);
- mei_virtio_remove_vqs(vdev);
-
- return 0;
-}
-
-static int __maybe_unused mei_virtio_restore(struct virtio_device *vdev)
-{
- struct mei_virtio_hw *hw = vdev->priv;
- int ret;
-
- dev_dbg(&vdev->dev, "restore\n");
-
- if (!hw)
- return -ENODEV;
-
- ret = mei_virtio_init_vqs(hw, vdev);
- if (ret)
- return ret;
-
- virtio_device_ready(vdev);
-
- ret = mei_restart(&hw->mdev);
- if (ret)
- return ret;
-
- /* Start timer if stopped in suspend */
- schedule_delayed_work(&hw->mdev.timer_work, HZ);
-
- return 0;
-}
-
-static const struct dev_pm_ops mei_virtio_pm_ops = {
- SET_RUNTIME_PM_OPS(mei_virtio_pm_runtime_suspend,
- mei_virtio_pm_runtime_resume,
- mei_virtio_pm_runtime_idle)
-};
-
-static void mei_virtio_remove(struct virtio_device *vdev)
-{
- struct mei_virtio_hw *hw = vdev->priv;
-
- mei_stop(&hw->mdev);
- mei_disable_interrupts(&hw->mdev);
- cancel_work_sync(&hw->intr_handler);
- mei_deregister(&hw->mdev);
- vdev->config->reset(vdev);
- mei_virtio_remove_vqs(vdev);
- kfree(hw->recv_buf);
- pm_runtime_disable(&vdev->dev);
-}
-
-static struct virtio_device_id id_table[] = {
- { VIRTIO_ID_MEI, VIRTIO_DEV_ANY_ID },
- { }
-};
-
-static struct virtio_driver mei_virtio_driver = {
- .id_table = id_table,
- .probe = mei_virtio_probe,
- .remove = mei_virtio_remove,
- .config_changed = mei_virtio_config_changed,
- .driver = {
- .name = KBUILD_MODNAME,
- .owner = THIS_MODULE,
- .pm = &mei_virtio_pm_ops,
- },
-#ifdef CONFIG_PM_SLEEP
- .freeze = mei_virtio_freeze,
- .restore = mei_virtio_restore,
-#endif
-};
-
-module_virtio_driver(mei_virtio_driver);
-MODULE_DEVICE_TABLE(virtio, id_table);
-MODULE_DESCRIPTION("Virtio MEI frontend driver");
-MODULE_LICENSE("GPL v2");
u8 type;
u8 length;
u8 ext_payload[2];
- u8 hdr[0];
+ u8 hdr[];
};
/**
u8 count;
u8 size;
u8 reserved[2];
- struct mei_ext_hdr hdrs[0];
+ struct mei_ext_hdr hdrs[];
};
/*
u32 dma_ring:1;
u32 internal:1;
u32 msg_complete:1;
- u32 extension[0];
+ u32 extension[];
} __packed;
/* The length is up to 9 bits */
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-menu "Intel MIC & related support"
-
-config INTEL_MIC_BUS
- tristate "Intel MIC Bus Driver"
- depends on 64BIT && PCI && X86
- select DMA_OPS
- help
- This option is selected by any driver which registers a
- device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
- CONFIG_INTEL_MIC_CARD, CONFIG_INTEL_MIC_X100_DMA etc.
-
- If you are building a host/card kernel with an Intel MIC device
- then say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config SCIF_BUS
- tristate "SCIF Bus Driver"
- depends on 64BIT && PCI && X86
- select DMA_OPS
- help
- This option is selected by any driver which registers a
- device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
- and CONFIG_INTEL_MIC_CARD.
-
- If you are building a host/card kernel with an Intel MIC device
- then say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config VOP_BUS
- tristate "VOP Bus Driver"
- depends on HAS_DMA
- select DMA_OPS
- help
- This option is selected by any driver which registers a
- device or driver on the VOP Bus, such as CONFIG_INTEL_MIC_HOST
- and CONFIG_INTEL_MIC_CARD.
-
- If you are building a host/card kernel with an Intel MIC device
- then say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config INTEL_MIC_HOST
- tristate "Intel MIC Host Driver"
- depends on 64BIT && PCI && X86
- depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
- select DMA_OPS
- help
- This enables Host Driver support for the Intel Many Integrated
- Core (MIC) family of PCIe form factor coprocessor devices that
- run a 64 bit Linux OS. The driver manages card OS state and
- enables communication between host and card. Intel MIC X100
- devices are currently supported.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config INTEL_MIC_CARD
- tristate "Intel MIC Card Driver"
- depends on 64BIT && X86
- depends on INTEL_MIC_BUS && SCIF_BUS && MIC_COSM && VOP_BUS
- select VIRTIO
- help
- This enables card driver support for the Intel Many Integrated
- Core (MIC) device family. The card driver communicates shutdown/
- crash events to the host and allows registration/configuration of
- virtio devices. Intel MIC X100 devices are currently supported.
-
- If you are building a card kernel for an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- For more information see
- <http://software.intel.com/en-us/mic-developer>.
-
-config SCIF
- tristate "SCIF Driver"
- depends on 64BIT && PCI && X86 && SCIF_BUS && IOMMU_SUPPORT
- select IOMMU_IOVA
- help
- This enables SCIF Driver support for the Intel Many Integrated
- Core (MIC) family of PCIe form factor coprocessor devices that
- run a 64 bit Linux OS. The Symmetric Communication Interface
- (SCIF (pronounced as skiff)) is a low level communications API
- across PCIe currently implemented for MIC.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config MIC_COSM
- tristate "Intel MIC Coprocessor State Management (COSM) Drivers"
- depends on 64BIT && PCI && X86 && SCIF
- help
- This enables COSM driver support for the Intel Many
- Integrated Core (MIC) family of PCIe form factor coprocessor
- devices. COSM drivers implement functions such as boot,
- shutdown, reset and reboot of MIC devices.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-config VOP
- tristate "VOP Driver"
- depends on VOP_BUS
- select VHOST_RING
- select VIRTIO
- help
- This enables VOP (Virtio over PCIe) Driver support for the Intel
- Many Integrated Core (MIC) family of PCIe form factor coprocessor
- devices. The VOP driver allows virtio drivers, e.g. net, console
- and block drivers, on the card connect to user space virtio
- devices on the host.
-
- If you are building a host kernel with an Intel MIC device then
- say M (recommended) or Y, else say N. If unsure say N.
-
- More information about the Intel MIC family as well as the Linux
- OS and tools for MIC to use with this driver are available from
- <http://software.intel.com/en-us/mic-developer>.
-
-endmenu
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_HOST) += host/
-obj-$(CONFIG_INTEL_MIC_CARD) += card/
-obj-y += bus/
-obj-$(CONFIG_SCIF) += scif/
-obj-$(CONFIG_MIC_COSM) += cosm/
-obj-$(CONFIG_MIC_COSM) += cosm_client/
-obj-$(CONFIG_VOP) += vop/
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2014, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_BUS) += mic_bus.o
-obj-$(CONFIG_SCIF_BUS) += scif_bus.o
-obj-$(CONFIG_MIC_COSM) += cosm_bus.o
-obj-$(CONFIG_VOP_BUS) += vop_bus.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Bus Driver
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include "cosm_bus.h"
-
-/* Unique numbering for cosm devices. */
-static DEFINE_IDA(cosm_index_ida);
-
-static int cosm_dev_probe(struct device *d)
-{
- struct cosm_device *dev = dev_to_cosm(d);
- struct cosm_driver *drv = drv_to_cosm(dev->dev.driver);
-
- return drv->probe(dev);
-}
-
-static int cosm_dev_remove(struct device *d)
-{
- struct cosm_device *dev = dev_to_cosm(d);
- struct cosm_driver *drv = drv_to_cosm(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type cosm_bus = {
- .name = "cosm_bus",
- .probe = cosm_dev_probe,
- .remove = cosm_dev_remove,
-};
-
-int cosm_register_driver(struct cosm_driver *driver)
-{
- driver->driver.bus = &cosm_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(cosm_register_driver);
-
-void cosm_unregister_driver(struct cosm_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(cosm_unregister_driver);
-
-static inline void cosm_release_dev(struct device *d)
-{
- struct cosm_device *cdev = dev_to_cosm(d);
-
- kfree(cdev);
-}
-
-struct cosm_device *
-cosm_register_device(struct device *pdev, struct cosm_hw_ops *hw_ops)
-{
- struct cosm_device *cdev;
- int ret;
-
- cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
- if (!cdev)
- return ERR_PTR(-ENOMEM);
-
- cdev->dev.parent = pdev;
- cdev->dev.release = cosm_release_dev;
- cdev->hw_ops = hw_ops;
- dev_set_drvdata(&cdev->dev, cdev);
- cdev->dev.bus = &cosm_bus;
-
- /* Assign a unique device index and hence name */
- ret = ida_simple_get(&cosm_index_ida, 0, 0, GFP_KERNEL);
- if (ret < 0)
- goto free_cdev;
-
- cdev->index = ret;
- cdev->dev.id = ret;
- dev_set_name(&cdev->dev, "cosm-dev%u", cdev->index);
-
- ret = device_register(&cdev->dev);
- if (ret)
- goto ida_remove;
- return cdev;
-ida_remove:
- ida_simple_remove(&cosm_index_ida, cdev->index);
-free_cdev:
- put_device(&cdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(cosm_register_device);
-
-void cosm_unregister_device(struct cosm_device *dev)
-{
- int index = dev->index; /* save for after device release */
-
- device_unregister(&dev->dev);
- ida_simple_remove(&cosm_index_ida, index);
-}
-EXPORT_SYMBOL_GPL(cosm_unregister_device);
-
-struct cosm_device *cosm_find_cdev_by_id(int id)
-{
- struct device *dev = subsys_find_device_by_id(&cosm_bus, id, NULL);
-
- return dev ? container_of(dev, struct cosm_device, dev) : NULL;
-}
-EXPORT_SYMBOL_GPL(cosm_find_cdev_by_id);
-
-static int __init cosm_init(void)
-{
- return bus_register(&cosm_bus);
-}
-
-static void __exit cosm_exit(void)
-{
- bus_unregister(&cosm_bus);
- ida_destroy(&cosm_index_ida);
-}
-
-core_initcall(cosm_init);
-module_exit(cosm_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC card OS state management bus driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Bus Driver
- */
-#ifndef _COSM_BUS_H_
-#define _COSM_BUS_H_
-
-#include <linux/scif.h>
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-/**
- * cosm_device - representation of a cosm device
- *
- * @attr_group: Pointer to list of sysfs attribute groups.
- * @sdev: Device for sysfs entries.
- * @state: MIC state.
- * @prev_state: MIC state previous to MIC_RESETTING
- * @shutdown_status: MIC status reported by card for shutdown/crashes.
- * @shutdown_status_int: Internal shutdown status maintained by the driver
- * @cosm_mutex: Mutex for synchronizing access to data structures.
- * @reset_trigger_work: Work for triggering reset requests.
- * @scif_work: Work for handling per device SCIF connections
- * @cmdline: Kernel command line.
- * @firmware: Firmware file name.
- * @ramdisk: Ramdisk file name.
- * @bootmode: Boot mode i.e. "linux" or "elf" for flash updates.
- * @log_buf_addr: Log buffer address for MIC.
- * @log_buf_len: Log buffer length address for MIC.
- * @state_sysfs: Sysfs dirent for notifying ring 3 about MIC state changes.
- * @hw_ops: the hardware bus ops for this device.
- * @dev: underlying device.
- * @index: unique position on the cosm bus
- * @dbg_dir: debug fs directory
- * @newepd: new endpoint from scif accept to be assigned to this cdev
- * @epd: SCIF endpoint for this cdev
- * @heartbeat_watchdog_enable: if heartbeat watchdog is enabled for this cdev
- * @sysfs_heartbeat_enable: sysfs setting for disabling heartbeat notification
- */
-struct cosm_device {
- const struct attribute_group **attr_group;
- struct device *sdev;
- u8 state;
- u8 prev_state;
- u8 shutdown_status;
- u8 shutdown_status_int;
- struct mutex cosm_mutex;
- struct work_struct reset_trigger_work;
- struct work_struct scif_work;
- char *cmdline;
- char *firmware;
- char *ramdisk;
- char *bootmode;
- void *log_buf_addr;
- int *log_buf_len;
- struct kernfs_node *state_sysfs;
- struct cosm_hw_ops *hw_ops;
- struct device dev;
- int index;
- struct dentry *dbg_dir;
- scif_epd_t newepd;
- scif_epd_t epd;
- bool heartbeat_watchdog_enable;
- bool sysfs_heartbeat_enable;
-};
-
-/**
- * cosm_driver - operations for a cosm driver
- *
- * @driver: underlying device driver (populate name and owner).
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct cosm_driver {
- struct device_driver driver;
- int (*probe)(struct cosm_device *dev);
- void (*remove)(struct cosm_device *dev);
-};
-
-/**
- * cosm_hw_ops - cosm bus ops
- *
- * @reset: trigger MIC reset
- * @force_reset: force MIC reset
- * @post_reset: inform MIC reset is complete
- * @ready: is MIC ready for OS download
- * @start: boot MIC
- * @stop: prepare MIC for reset
- * @family: return MIC HW family string
- * @stepping: return MIC HW stepping string
- * @aper: return MIC PCIe aperture
- */
-struct cosm_hw_ops {
- void (*reset)(struct cosm_device *cdev);
- void (*force_reset)(struct cosm_device *cdev);
- void (*post_reset)(struct cosm_device *cdev, enum mic_states state);
- bool (*ready)(struct cosm_device *cdev);
- int (*start)(struct cosm_device *cdev, int id);
- void (*stop)(struct cosm_device *cdev, bool force);
- ssize_t (*family)(struct cosm_device *cdev, char *buf);
- ssize_t (*stepping)(struct cosm_device *cdev, char *buf);
- struct mic_mw *(*aper)(struct cosm_device *cdev);
-};
-
-struct cosm_device *
-cosm_register_device(struct device *pdev, struct cosm_hw_ops *hw_ops);
-void cosm_unregister_device(struct cosm_device *dev);
-int cosm_register_driver(struct cosm_driver *drv);
-void cosm_unregister_driver(struct cosm_driver *drv);
-struct cosm_device *cosm_find_cdev_by_id(int id);
-
-static inline struct cosm_device *dev_to_cosm(struct device *dev)
-{
- return container_of(dev, struct cosm_device, dev);
-}
-
-static inline struct cosm_driver *drv_to_cosm(struct device_driver *drv)
-{
- return container_of(drv, struct cosm_driver, driver);
-}
-#endif /* _COSM_BUS_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC Bus driver.
- *
- * This implementation is very similar to the the virtio bus driver
- * implementation @ drivers/virtio/virtio.c
- */
-#include <linux/dma-map-ops.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/mic_bus.h>
-
-static ssize_t device_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- return sprintf(buf, "mbus:d%08Xv%08X\n",
- dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *mbus_dev_attrs[] = {
- &dev_attr_device.attr,
- &dev_attr_vendor.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(mbus_dev);
-
-static inline int mbus_id_match(const struct mbus_device *dev,
- const struct mbus_device_id *id)
-{
- if (id->device != dev->id.device && id->device != MBUS_DEV_ANY_ID)
- return 0;
-
- return id->vendor == MBUS_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support. If any of them
- * match, we return 1 and the kernel will call mbus_dev_probe().
- */
-static int mbus_dev_match(struct device *dv, struct device_driver *dr)
-{
- unsigned int i;
- struct mbus_device *dev = dev_to_mbus(dv);
- const struct mbus_device_id *ids;
-
- ids = drv_to_mbus(dr)->id_table;
- for (i = 0; ids[i].device; i++)
- if (mbus_id_match(dev, &ids[i]))
- return 1;
- return 0;
-}
-
-static int mbus_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
- struct mbus_device *dev = dev_to_mbus(dv);
-
- return add_uevent_var(env, "MODALIAS=mbus:d%08Xv%08X",
- dev->id.device, dev->id.vendor);
-}
-
-static int mbus_dev_probe(struct device *d)
-{
- int err;
- struct mbus_device *dev = dev_to_mbus(d);
- struct mbus_driver *drv = drv_to_mbus(dev->dev.driver);
-
- err = drv->probe(dev);
- if (!err)
- if (drv->scan)
- drv->scan(dev);
- return err;
-}
-
-static int mbus_dev_remove(struct device *d)
-{
- struct mbus_device *dev = dev_to_mbus(d);
- struct mbus_driver *drv = drv_to_mbus(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type mic_bus = {
- .name = "mic_bus",
- .match = mbus_dev_match,
- .dev_groups = mbus_dev_groups,
- .uevent = mbus_uevent,
- .probe = mbus_dev_probe,
- .remove = mbus_dev_remove,
-};
-
-int mbus_register_driver(struct mbus_driver *driver)
-{
- driver->driver.bus = &mic_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(mbus_register_driver);
-
-void mbus_unregister_driver(struct mbus_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(mbus_unregister_driver);
-
-static void mbus_release_dev(struct device *d)
-{
- struct mbus_device *mbdev = dev_to_mbus(d);
- kfree(mbdev);
-}
-
-struct mbus_device *
-mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
- struct mbus_hw_ops *hw_ops, int index,
- void __iomem *mmio_va)
-{
- int ret;
- struct mbus_device *mbdev;
-
- mbdev = kzalloc(sizeof(*mbdev), GFP_KERNEL);
- if (!mbdev)
- return ERR_PTR(-ENOMEM);
-
- mbdev->mmio_va = mmio_va;
- mbdev->dev.parent = pdev;
- mbdev->id.device = id;
- mbdev->id.vendor = MBUS_DEV_ANY_ID;
- mbdev->dev.dma_ops = dma_ops;
- mbdev->dev.dma_mask = &mbdev->dev.coherent_dma_mask;
- dma_set_mask(&mbdev->dev, DMA_BIT_MASK(64));
- mbdev->dev.release = mbus_release_dev;
- mbdev->hw_ops = hw_ops;
- mbdev->dev.bus = &mic_bus;
- mbdev->index = index;
- dev_set_name(&mbdev->dev, "mbus-dev%u", mbdev->index);
- /*
- * device_register() causes the bus infrastructure to look for a
- * matching driver.
- */
- ret = device_register(&mbdev->dev);
- if (ret)
- goto free_mbdev;
- return mbdev;
-free_mbdev:
- put_device(&mbdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(mbus_register_device);
-
-void mbus_unregister_device(struct mbus_device *mbdev)
-{
- device_unregister(&mbdev->dev);
-}
-EXPORT_SYMBOL_GPL(mbus_unregister_device);
-
-static int __init mbus_init(void)
-{
- return bus_register(&mic_bus);
-}
-
-static void __exit mbus_exit(void)
-{
- bus_unregister(&mic_bus);
-}
-
-core_initcall(mbus_init);
-module_exit(mbus_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC Bus driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel Symmetric Communications Interface Bus driver.
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/dma-map-ops.h>
-
-#include "scif_bus.h"
-
-static ssize_t device_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
-
- return sprintf(buf, "scif:d%08Xv%08X\n",
- dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *scif_dev_attrs[] = {
- &dev_attr_device.attr,
- &dev_attr_vendor.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(scif_dev);
-
-static inline int scif_id_match(const struct scif_hw_dev *dev,
- const struct scif_hw_dev_id *id)
-{
- if (id->device != dev->id.device && id->device != SCIF_DEV_ANY_ID)
- return 0;
-
- return id->vendor == SCIF_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support. If any of them
- * match, we return 1 and the kernel will call scif_dev_probe().
- */
-static int scif_dev_match(struct device *dv, struct device_driver *dr)
-{
- unsigned int i;
- struct scif_hw_dev *dev = dev_to_scif(dv);
- const struct scif_hw_dev_id *ids;
-
- ids = drv_to_scif(dr)->id_table;
- for (i = 0; ids[i].device; i++)
- if (scif_id_match(dev, &ids[i]))
- return 1;
- return 0;
-}
-
-static int scif_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
- struct scif_hw_dev *dev = dev_to_scif(dv);
-
- return add_uevent_var(env, "MODALIAS=scif:d%08Xv%08X",
- dev->id.device, dev->id.vendor);
-}
-
-static int scif_dev_probe(struct device *d)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
- struct scif_driver *drv = drv_to_scif(dev->dev.driver);
-
- return drv->probe(dev);
-}
-
-static int scif_dev_remove(struct device *d)
-{
- struct scif_hw_dev *dev = dev_to_scif(d);
- struct scif_driver *drv = drv_to_scif(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type scif_bus = {
- .name = "scif_bus",
- .match = scif_dev_match,
- .dev_groups = scif_dev_groups,
- .uevent = scif_uevent,
- .probe = scif_dev_probe,
- .remove = scif_dev_remove,
-};
-
-int scif_register_driver(struct scif_driver *driver)
-{
- driver->driver.bus = &scif_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(scif_register_driver);
-
-void scif_unregister_driver(struct scif_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(scif_unregister_driver);
-
-static void scif_release_dev(struct device *d)
-{
- struct scif_hw_dev *sdev = dev_to_scif(d);
-
- kfree(sdev);
-}
-
-struct scif_hw_dev *
-scif_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
- struct scif_hw_ops *hw_ops, u8 dnode, u8 snode,
- struct mic_mw *mmio, struct mic_mw *aper, void *dp,
- void __iomem *rdp, struct dma_chan **chan, int num_chan,
- bool card_rel_da)
-{
- int ret;
- struct scif_hw_dev *sdev;
-
- sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
- if (!sdev)
- return ERR_PTR(-ENOMEM);
-
- sdev->dev.parent = pdev;
- sdev->id.device = id;
- sdev->id.vendor = SCIF_DEV_ANY_ID;
- sdev->dev.dma_ops = dma_ops;
- sdev->dev.release = scif_release_dev;
- sdev->hw_ops = hw_ops;
- sdev->dnode = dnode;
- sdev->snode = snode;
- dev_set_drvdata(&sdev->dev, sdev);
- sdev->dev.bus = &scif_bus;
- sdev->mmio = mmio;
- sdev->aper = aper;
- sdev->dp = dp;
- sdev->rdp = rdp;
- sdev->dev.dma_mask = &sdev->dev.coherent_dma_mask;
- dma_set_mask(&sdev->dev, DMA_BIT_MASK(64));
- sdev->dma_ch = chan;
- sdev->num_dma_ch = num_chan;
- sdev->card_rel_da = card_rel_da;
- dev_set_name(&sdev->dev, "scif-dev%u", sdev->dnode);
- /*
- * device_register() causes the bus infrastructure to look for a
- * matching driver.
- */
- ret = device_register(&sdev->dev);
- if (ret)
- goto free_sdev;
- return sdev;
-free_sdev:
- put_device(&sdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(scif_register_device);
-
-void scif_unregister_device(struct scif_hw_dev *sdev)
-{
- device_unregister(&sdev->dev);
-}
-EXPORT_SYMBOL_GPL(scif_unregister_device);
-
-static int __init scif_init(void)
-{
- return bus_register(&scif_bus);
-}
-
-static void __exit scif_exit(void)
-{
- bus_unregister(&scif_bus);
-}
-
-core_initcall(scif_init);
-module_exit(scif_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) SCIF Bus driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel Symmetric Communications Interface Bus driver.
- */
-#ifndef _SCIF_BUS_H_
-#define _SCIF_BUS_H_
-/*
- * Everything a scif driver needs to work with any particular scif
- * hardware abstraction layer.
- */
-#include <linux/dma-map-ops.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-struct scif_hw_dev_id {
- u32 device;
- u32 vendor;
-};
-
-#define MIC_SCIF_DEV 1
-#define SCIF_DEV_ANY_ID 0xffffffff
-
-/**
- * scif_hw_dev - representation of a hardware device abstracted for scif
- * @hw_ops: the hardware ops supported by this device
- * @id: the device type identification (used to match it with a driver)
- * @mmio: MMIO memory window
- * @aper: Aperture memory window
- * @dev: underlying device
- * @dnode - The destination node which this device will communicate with.
- * @snode - The source node for this device.
- * @dp - Self device page
- * @rdp - Remote device page
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @card_rel_da - Set to true if DMA addresses programmed in the DMA engine
- * are relative to the card point of view
- */
-struct scif_hw_dev {
- struct scif_hw_ops *hw_ops;
- struct scif_hw_dev_id id;
- struct mic_mw *mmio;
- struct mic_mw *aper;
- struct device dev;
- u8 dnode;
- u8 snode;
- void *dp;
- void __iomem *rdp;
- struct dma_chan **dma_ch;
- int num_dma_ch;
- bool card_rel_da;
-};
-
-/**
- * scif_driver - operations for a scif I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct scif_driver {
- struct device_driver driver;
- const struct scif_hw_dev_id *id_table;
- int (*probe)(struct scif_hw_dev *dev);
- void (*remove)(struct scif_hw_dev *dev);
-};
-
-/**
- * scif_hw_ops - Hardware operations for accessing a SCIF device on the SCIF bus.
- *
- * @next_db: Obtain the next available doorbell.
- * @request_irq: Request an interrupt on a particular doorbell.
- * @free_irq: Free an interrupt requested previously.
- * @ack_interrupt: acknowledge an interrupt in the ISR.
- * @send_intr: Send an interrupt to the remote node on a specified doorbell.
- * @send_p2p_intr: Send an interrupt to the peer node on a specified doorbell
- * which is specifically targeted for a peer to peer node.
- * @remap: Map a buffer with the specified physical address and length.
- * @unmap: Unmap a buffer previously mapped.
- */
-struct scif_hw_ops {
- int (*next_db)(struct scif_hw_dev *sdev);
- struct mic_irq * (*request_irq)(struct scif_hw_dev *sdev,
- irqreturn_t (*func)(int irq,
- void *data),
- const char *name, void *data,
- int db);
- void (*free_irq)(struct scif_hw_dev *sdev,
- struct mic_irq *cookie, void *data);
- void (*ack_interrupt)(struct scif_hw_dev *sdev, int num);
- void (*send_intr)(struct scif_hw_dev *sdev, int db);
- void (*send_p2p_intr)(struct scif_hw_dev *sdev, int db,
- struct mic_mw *mw);
- void __iomem * (*remap)(struct scif_hw_dev *sdev,
- phys_addr_t pa, size_t len);
- void (*unmap)(struct scif_hw_dev *sdev, void __iomem *va);
-};
-
-int scif_register_driver(struct scif_driver *driver);
-void scif_unregister_driver(struct scif_driver *driver);
-struct scif_hw_dev *
-scif_register_device(struct device *pdev, int id,
- const struct dma_map_ops *dma_ops,
- struct scif_hw_ops *hw_ops, u8 dnode, u8 snode,
- struct mic_mw *mmio, struct mic_mw *aper,
- void *dp, void __iomem *rdp,
- struct dma_chan **chan, int num_chan,
- bool card_rel_da);
-void scif_unregister_device(struct scif_hw_dev *sdev);
-
-static inline struct scif_hw_dev *dev_to_scif(struct device *dev)
-{
- return container_of(dev, struct scif_hw_dev, dev);
-}
-
-static inline struct scif_driver *drv_to_scif(struct device_driver *drv)
-{
- return container_of(drv, struct scif_driver, driver);
-}
-#endif /* _SCIF_BUS_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) Bus driver.
- */
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/idr.h>
-#include <linux/dma-map-ops.h>
-
-#include "vop_bus.h"
-
-static ssize_t device_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.device);
-}
-static DEVICE_ATTR_RO(device);
-
-static ssize_t vendor_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
-}
-static DEVICE_ATTR_RO(vendor);
-
-static ssize_t modalias_show(struct device *d,
- struct device_attribute *attr, char *buf)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- return sprintf(buf, "vop:d%08Xv%08X\n",
- dev->id.device, dev->id.vendor);
-}
-static DEVICE_ATTR_RO(modalias);
-
-static struct attribute *vop_dev_attrs[] = {
- &dev_attr_device.attr,
- &dev_attr_vendor.attr,
- &dev_attr_modalias.attr,
- NULL,
-};
-ATTRIBUTE_GROUPS(vop_dev);
-
-static inline int vop_id_match(const struct vop_device *dev,
- const struct vop_device_id *id)
-{
- if (id->device != dev->id.device && id->device != VOP_DEV_ANY_ID)
- return 0;
-
- return id->vendor == VOP_DEV_ANY_ID || id->vendor == dev->id.vendor;
-}
-
-/*
- * This looks through all the IDs a driver claims to support. If any of them
- * match, we return 1 and the kernel will call vop_dev_probe().
- */
-static int vop_dev_match(struct device *dv, struct device_driver *dr)
-{
- unsigned int i;
- struct vop_device *dev = dev_to_vop(dv);
- const struct vop_device_id *ids;
-
- ids = drv_to_vop(dr)->id_table;
- for (i = 0; ids[i].device; i++)
- if (vop_id_match(dev, &ids[i]))
- return 1;
- return 0;
-}
-
-static int vop_uevent(struct device *dv, struct kobj_uevent_env *env)
-{
- struct vop_device *dev = dev_to_vop(dv);
-
- return add_uevent_var(env, "MODALIAS=vop:d%08Xv%08X",
- dev->id.device, dev->id.vendor);
-}
-
-static int vop_dev_probe(struct device *d)
-{
- struct vop_device *dev = dev_to_vop(d);
- struct vop_driver *drv = drv_to_vop(dev->dev.driver);
-
- return drv->probe(dev);
-}
-
-static int vop_dev_remove(struct device *d)
-{
- struct vop_device *dev = dev_to_vop(d);
- struct vop_driver *drv = drv_to_vop(dev->dev.driver);
-
- drv->remove(dev);
- return 0;
-}
-
-static struct bus_type vop_bus = {
- .name = "vop_bus",
- .match = vop_dev_match,
- .dev_groups = vop_dev_groups,
- .uevent = vop_uevent,
- .probe = vop_dev_probe,
- .remove = vop_dev_remove,
-};
-
-int vop_register_driver(struct vop_driver *driver)
-{
- driver->driver.bus = &vop_bus;
- return driver_register(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(vop_register_driver);
-
-void vop_unregister_driver(struct vop_driver *driver)
-{
- driver_unregister(&driver->driver);
-}
-EXPORT_SYMBOL_GPL(vop_unregister_driver);
-
-static void vop_release_dev(struct device *d)
-{
- struct vop_device *dev = dev_to_vop(d);
-
- kfree(dev);
-}
-
-struct vop_device *
-vop_register_device(struct device *pdev, int id,
- const struct dma_map_ops *dma_ops,
- struct vop_hw_ops *hw_ops, u8 dnode, struct mic_mw *aper,
- struct dma_chan *chan)
-{
- int ret;
- struct vop_device *vdev;
-
- vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
- if (!vdev)
- return ERR_PTR(-ENOMEM);
-
- vdev->dev.parent = pdev;
- vdev->id.device = id;
- vdev->id.vendor = VOP_DEV_ANY_ID;
- vdev->dev.dma_ops = dma_ops;
- vdev->dev.dma_mask = &vdev->dev.coherent_dma_mask;
- dma_set_mask(&vdev->dev, DMA_BIT_MASK(64));
- vdev->dev.release = vop_release_dev;
- vdev->hw_ops = hw_ops;
- vdev->dev.bus = &vop_bus;
- vdev->dnode = dnode;
- vdev->aper = aper;
- vdev->dma_ch = chan;
- vdev->index = dnode - 1;
- dev_set_name(&vdev->dev, "vop-dev%u", vdev->index);
- /*
- * device_register() causes the bus infrastructure to look for a
- * matching driver.
- */
- ret = device_register(&vdev->dev);
- if (ret)
- goto free_vdev;
- return vdev;
-free_vdev:
- put_device(&vdev->dev);
- return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(vop_register_device);
-
-void vop_unregister_device(struct vop_device *dev)
-{
- device_unregister(&dev->dev);
-}
-EXPORT_SYMBOL_GPL(vop_unregister_device);
-
-static int __init vop_init(void)
-{
- return bus_register(&vop_bus);
-}
-
-static void __exit vop_exit(void)
-{
- bus_unregister(&vop_bus);
-}
-
-core_initcall(vop_init);
-module_exit(vop_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) VOP Bus driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio over PCIe Bus driver.
- */
-#ifndef _VOP_BUS_H_
-#define _VOP_BUS_H_
-/*
- * Everything a vop driver needs to work with any particular vop
- * implementation.
- */
-#include <linux/dmaengine.h>
-#include <linux/interrupt.h>
-
-#include "../common/mic_dev.h"
-
-struct vop_device_id {
- u32 device;
- u32 vendor;
-};
-
-#define VOP_DEV_TRNSP 1
-#define VOP_DEV_ANY_ID 0xffffffff
-/*
- * Size of the internal buffer used during DMA's as an intermediate buffer
- * for copy to/from user. Must be an integral number of pages.
- */
-#define VOP_INT_DMA_BUF_SIZE PAGE_ALIGN(64 * 1024ULL)
-
-/**
- * vop_device - representation of a device using vop
- * @hw_ops: the hardware ops supported by this device.
- * @id: the device type identification (used to match it with a driver).
- * @dev: underlying device.
- * @dnode - The destination node which this device will communicate with.
- * @aper: Aperture memory window
- * @dma_ch - DMA channel
- * @index: unique position on the vop bus
- */
-struct vop_device {
- struct vop_hw_ops *hw_ops;
- struct vop_device_id id;
- struct device dev;
- u8 dnode;
- struct mic_mw *aper;
- struct dma_chan *dma_ch;
- int index;
-};
-
-/**
- * vop_driver - operations for a vop I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct vop_driver {
- struct device_driver driver;
- const struct vop_device_id *id_table;
- int (*probe)(struct vop_device *dev);
- void (*remove)(struct vop_device *dev);
-};
-
-/**
- * vop_hw_ops - Hardware operations for accessing a VOP device on the VOP bus.
- *
- * @next_db: Obtain the next available doorbell.
- * @request_irq: Request an interrupt on a particular doorbell.
- * @free_irq: Free an interrupt requested previously.
- * @ack_interrupt: acknowledge an interrupt in the ISR.
- * @get_remote_dp: Get access to the virtio device page used by the remote
- * node to add/remove/configure virtio devices.
- * @get_dp: Get access to the virtio device page used by the self
- * node to add/remove/configure virtio devices.
- * @send_intr: Send an interrupt to the peer node on a specified doorbell.
- * @remap: Map a buffer with the specified DMA address and length.
- * @unmap: Unmap a buffer previously mapped.
- * @dma_filter: The DMA filter function to use for obtaining access to
- * a DMA channel on the peer node.
- */
-struct vop_hw_ops {
- int (*next_db)(struct vop_device *vpdev);
- struct mic_irq *(*request_irq)(struct vop_device *vpdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data,
- int intr_src);
- void (*free_irq)(struct vop_device *vpdev,
- struct mic_irq *cookie, void *data);
- void (*ack_interrupt)(struct vop_device *vpdev, int num);
- void __iomem * (*get_remote_dp)(struct vop_device *vpdev);
- void * (*get_dp)(struct vop_device *vpdev);
- void (*send_intr)(struct vop_device *vpdev, int db);
- void __iomem * (*remap)(struct vop_device *vpdev,
- dma_addr_t pa, size_t len);
- void (*unmap)(struct vop_device *vpdev, void __iomem *va);
-};
-
-struct vop_device *
-vop_register_device(struct device *pdev, int id,
- const struct dma_map_ops *dma_ops,
- struct vop_hw_ops *hw_ops, u8 dnode, struct mic_mw *aper,
- struct dma_chan *chan);
-void vop_unregister_device(struct vop_device *dev);
-int vop_register_driver(struct vop_driver *drv);
-void vop_unregister_driver(struct vop_driver *drv);
-
-/*
- * module_vop_driver() - Helper macro for drivers that don't do
- * anything special in module init/exit. This eliminates a lot of
- * boilerplate. Each module may only use this macro once, and
- * calling it replaces module_init() and module_exit()
- */
-#define module_vop_driver(__vop_driver) \
- module_driver(__vop_driver, vop_register_driver, \
- vop_unregister_driver)
-
-static inline struct vop_device *dev_to_vop(struct device *dev)
-{
- return container_of(dev, struct vop_device, dev);
-}
-
-static inline struct vop_driver *drv_to_vop(struct device_driver *drv)
-{
- return container_of(drv, struct vop_driver, driver);
-}
-#endif /* _VOP_BUS_H */
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-ccflags-y += -DINTEL_MIC_CARD
-
-obj-$(CONFIG_INTEL_MIC_CARD) += mic_card.o
-mic_card-y += mic_x100.o
-mic_card-y += mic_device.o
-mic_card-y += mic_debugfs.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/interrupt.h>
-#include <linux/device.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-/* Debugfs parent dir */
-static struct dentry *mic_dbg;
-
-/*
- * mic_intr_show - Send interrupts to host.
- */
-static int mic_intr_show(struct seq_file *s, void *unused)
-{
- struct mic_driver *mdrv = s->private;
- struct mic_device *mdev = &mdrv->mdev;
-
- mic_send_intr(mdev, 0);
- msleep(1000);
- mic_send_intr(mdev, 1);
- msleep(1000);
- mic_send_intr(mdev, 2);
- msleep(1000);
- mic_send_intr(mdev, 3);
- msleep(1000);
-
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_intr);
-
-/*
- * mic_create_card_debug_dir - Initialize MIC debugfs entries.
- */
-void __init mic_create_card_debug_dir(struct mic_driver *mdrv)
-{
- if (!mic_dbg)
- return;
-
- mdrv->dbg_dir = debugfs_create_dir(mdrv->name, mic_dbg);
-
- debugfs_create_file("intr_test", 0444, mdrv->dbg_dir, mdrv,
- &mic_intr_fops);
-}
-
-/*
- * mic_delete_card_debug_dir - Uninitialize MIC debugfs entries.
- */
-void mic_delete_card_debug_dir(struct mic_driver *mdrv)
-{
- debugfs_remove_recursive(mdrv->dbg_dir);
-}
-
-/*
- * mic_init_card_debugfs - Initialize global debugfs entry.
- */
-void __init mic_init_card_debugfs(void)
-{
- mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-/*
- * mic_exit_card_debugfs - Uninitialize global debugfs entry
- */
-void mic_exit_card_debugfs(void)
-{
- debugfs_remove(mic_dbg);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-#include <linux/reboot.h>
-#include <linux/dmaengine.h>
-#include <linux/kmod.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-static struct mic_driver *g_drv;
-
-static int __init mic_dp_init(void)
-{
- struct mic_driver *mdrv = g_drv;
- struct mic_device *mdev = &mdrv->mdev;
- struct mic_bootparam __iomem *bootparam;
- u64 lo, hi, dp_dma_addr;
- u32 magic;
-
- lo = mic_read_spad(&mdrv->mdev, MIC_DPLO_SPAD);
- hi = mic_read_spad(&mdrv->mdev, MIC_DPHI_SPAD);
-
- dp_dma_addr = lo | (hi << 32);
- mdrv->dp = mic_card_map(mdev, dp_dma_addr, MIC_DP_SIZE);
- if (!mdrv->dp) {
- dev_err(mdrv->dev, "Cannot remap Aperture BAR\n");
- return -ENOMEM;
- }
- bootparam = mdrv->dp;
- magic = ioread32(&bootparam->magic);
- if (MIC_MAGIC != magic) {
- dev_err(mdrv->dev, "bootparam magic mismatch 0x%x\n", magic);
- return -EIO;
- }
- return 0;
-}
-
-/* Uninitialize the device page */
-static void mic_dp_uninit(void)
-{
- mic_card_unmap(&g_drv->mdev, g_drv->dp);
-}
-
-/**
- * mic_request_card_irq - request an irq.
- *
- * @handler: interrupt handler passed to request_threaded_irq.
- * @thread_fn: thread fn. passed to request_threaded_irq.
- * @name: The ASCII name of the callee requesting the irq.
- * @data: private data that is returned back when calling the
- * function handler.
- * @index: The doorbell index of the requester.
- *
- * returns: The cookie that is transparent to the caller. Passed
- * back when calling mic_free_irq. An appropriate error code
- * is returned on failure. Caller needs to use IS_ERR(return_val)
- * to check for failure and PTR_ERR(return_val) to obtained the
- * error code.
- *
- */
-struct mic_irq *
-mic_request_card_irq(irq_handler_t handler,
- irq_handler_t thread_fn, const char *name,
- void *data, int index)
-{
- int rc = 0;
- unsigned long cookie;
- struct mic_driver *mdrv = g_drv;
-
- rc = request_threaded_irq(mic_db_to_irq(mdrv, index), handler,
- thread_fn, 0, name, data);
- if (rc) {
- dev_err(mdrv->dev, "request_threaded_irq failed rc = %d\n", rc);
- goto err;
- }
- mdrv->irq_info.irq_usage_count[index]++;
- cookie = index;
- return (struct mic_irq *)cookie;
-err:
- return ERR_PTR(rc);
-}
-
-/**
- * mic_free_card_irq - free irq.
- *
- * @cookie: cookie obtained during a successful call to mic_request_threaded_irq
- * @data: private data specified by the calling function during the
- * mic_request_threaded_irq
- *
- * returns: none.
- */
-void mic_free_card_irq(struct mic_irq *cookie, void *data)
-{
- int index;
- struct mic_driver *mdrv = g_drv;
-
- index = (unsigned long)cookie & 0xFFFFU;
- free_irq(mic_db_to_irq(mdrv, index), data);
- mdrv->irq_info.irq_usage_count[index]--;
-}
-
-/**
- * mic_next_card_db - Get the doorbell with minimum usage count.
- *
- * Returns the irq index.
- */
-int mic_next_card_db(void)
-{
- int i;
- int index = 0;
- struct mic_driver *mdrv = g_drv;
-
- for (i = 0; i < mdrv->intr_info.num_intr; i++) {
- if (mdrv->irq_info.irq_usage_count[i] <
- mdrv->irq_info.irq_usage_count[index])
- index = i;
- }
-
- return index;
-}
-
-/**
- * mic_init_irq - Initialize irq information.
- *
- * Returns 0 in success. Appropriate error code on failure.
- */
-static int mic_init_irq(void)
-{
- struct mic_driver *mdrv = g_drv;
-
- mdrv->irq_info.irq_usage_count = kzalloc((sizeof(u32) *
- mdrv->intr_info.num_intr),
- GFP_KERNEL);
- if (!mdrv->irq_info.irq_usage_count)
- return -ENOMEM;
- return 0;
-}
-
-/**
- * mic_uninit_irq - Uninitialize irq information.
- *
- * None.
- */
-static void mic_uninit_irq(void)
-{
- struct mic_driver *mdrv = g_drv;
-
- kfree(mdrv->irq_info.irq_usage_count);
-}
-
-static inline struct mic_driver *scdev_to_mdrv(struct scif_hw_dev *scdev)
-{
- return dev_get_drvdata(scdev->dev.parent);
-}
-
-static struct mic_irq *
-___mic_request_irq(struct scif_hw_dev *scdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data,
- int db)
-{
- return mic_request_card_irq(func, NULL, name, data, db);
-}
-
-static void
-___mic_free_irq(struct scif_hw_dev *scdev,
- struct mic_irq *cookie, void *data)
-{
- return mic_free_card_irq(cookie, data);
-}
-
-static void ___mic_ack_interrupt(struct scif_hw_dev *scdev, int num)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- mic_ack_interrupt(&mdrv->mdev);
-}
-
-static int ___mic_next_db(struct scif_hw_dev *scdev)
-{
- return mic_next_card_db();
-}
-
-static void ___mic_send_intr(struct scif_hw_dev *scdev, int db)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- mic_send_intr(&mdrv->mdev, db);
-}
-
-static void ___mic_send_p2p_intr(struct scif_hw_dev *scdev, int db,
- struct mic_mw *mw)
-{
- mic_send_p2p_intr(db, mw);
-}
-
-static void __iomem *
-___mic_ioremap(struct scif_hw_dev *scdev,
- phys_addr_t pa, size_t len)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- return mic_card_map(&mdrv->mdev, pa, len);
-}
-
-static void ___mic_iounmap(struct scif_hw_dev *scdev, void __iomem *va)
-{
- struct mic_driver *mdrv = scdev_to_mdrv(scdev);
-
- mic_card_unmap(&mdrv->mdev, va);
-}
-
-static struct scif_hw_ops scif_hw_ops = {
- .request_irq = ___mic_request_irq,
- .free_irq = ___mic_free_irq,
- .ack_interrupt = ___mic_ack_interrupt,
- .next_db = ___mic_next_db,
- .send_intr = ___mic_send_intr,
- .send_p2p_intr = ___mic_send_p2p_intr,
- .remap = ___mic_ioremap,
- .unmap = ___mic_iounmap,
-};
-
-static inline struct mic_driver *vpdev_to_mdrv(struct vop_device *vpdev)
-{
- return dev_get_drvdata(vpdev->dev.parent);
-}
-
-static struct mic_irq *
-__mic_request_irq(struct vop_device *vpdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data, int intr_src)
-{
- return mic_request_card_irq(func, NULL, name, data, intr_src);
-}
-
-static void __mic_free_irq(struct vop_device *vpdev,
- struct mic_irq *cookie, void *data)
-{
- return mic_free_card_irq(cookie, data);
-}
-
-static void __mic_ack_interrupt(struct vop_device *vpdev, int num)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- mic_ack_interrupt(&mdrv->mdev);
-}
-
-static int __mic_next_db(struct vop_device *vpdev)
-{
- return mic_next_card_db();
-}
-
-static void __iomem *__mic_get_remote_dp(struct vop_device *vpdev)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- return mdrv->dp;
-}
-
-static void __mic_send_intr(struct vop_device *vpdev, int db)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- mic_send_intr(&mdrv->mdev, db);
-}
-
-static void __iomem *__mic_ioremap(struct vop_device *vpdev,
- dma_addr_t pa, size_t len)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- return mic_card_map(&mdrv->mdev, pa, len);
-}
-
-static void __mic_iounmap(struct vop_device *vpdev, void __iomem *va)
-{
- struct mic_driver *mdrv = vpdev_to_mdrv(vpdev);
-
- mic_card_unmap(&mdrv->mdev, va);
-}
-
-static struct vop_hw_ops vop_hw_ops = {
- .request_irq = __mic_request_irq,
- .free_irq = __mic_free_irq,
- .ack_interrupt = __mic_ack_interrupt,
- .next_db = __mic_next_db,
- .get_remote_dp = __mic_get_remote_dp,
- .send_intr = __mic_send_intr,
- .remap = __mic_ioremap,
- .unmap = __mic_iounmap,
-};
-
-static int mic_request_dma_chans(struct mic_driver *mdrv)
-{
- dma_cap_mask_t mask;
- struct dma_chan *chan;
-
- dma_cap_zero(mask);
- dma_cap_set(DMA_MEMCPY, mask);
-
- do {
- chan = dma_request_channel(mask, NULL, NULL);
- if (chan) {
- mdrv->dma_ch[mdrv->num_dma_ch++] = chan;
- if (mdrv->num_dma_ch >= MIC_MAX_DMA_CHAN)
- break;
- }
- } while (chan);
- dev_info(mdrv->dev, "DMA channels # %d\n", mdrv->num_dma_ch);
- return mdrv->num_dma_ch;
-}
-
-static void mic_free_dma_chans(struct mic_driver *mdrv)
-{
- int i = 0;
-
- for (i = 0; i < mdrv->num_dma_ch; i++) {
- dma_release_channel(mdrv->dma_ch[i]);
- mdrv->dma_ch[i] = NULL;
- }
- mdrv->num_dma_ch = 0;
-}
-
-/*
- * mic_driver_init - MIC driver initialization tasks.
- *
- * Returns 0 in success. Appropriate error code on failure.
- */
-int __init mic_driver_init(struct mic_driver *mdrv)
-{
- int rc;
- struct mic_bootparam __iomem *bootparam;
- u8 node_id;
-
- g_drv = mdrv;
- /* Unloading the card module is not supported. */
- if (!try_module_get(mdrv->dev->driver->owner)) {
- rc = -ENODEV;
- goto done;
- }
- rc = mic_dp_init();
- if (rc)
- goto put;
- rc = mic_init_irq();
- if (rc)
- goto dp_uninit;
- if (!mic_request_dma_chans(mdrv)) {
- rc = -ENODEV;
- goto irq_uninit;
- }
- mdrv->vpdev = vop_register_device(mdrv->dev, VOP_DEV_TRNSP,
- NULL, &vop_hw_ops, 0,
- NULL, mdrv->dma_ch[0]);
- if (IS_ERR(mdrv->vpdev)) {
- rc = PTR_ERR(mdrv->vpdev);
- goto dma_free;
- }
- bootparam = mdrv->dp;
- node_id = ioread8(&bootparam->node_id);
- mdrv->scdev = scif_register_device(mdrv->dev, MIC_SCIF_DEV,
- NULL, &scif_hw_ops,
- 0, node_id, &mdrv->mdev.mmio, NULL,
- NULL, mdrv->dp, mdrv->dma_ch,
- mdrv->num_dma_ch, true);
- if (IS_ERR(mdrv->scdev)) {
- rc = PTR_ERR(mdrv->scdev);
- goto vop_remove;
- }
- mic_create_card_debug_dir(mdrv);
-done:
- return rc;
-vop_remove:
- vop_unregister_device(mdrv->vpdev);
-dma_free:
- mic_free_dma_chans(mdrv);
-irq_uninit:
- mic_uninit_irq();
-dp_uninit:
- mic_dp_uninit();
-put:
- module_put(mdrv->dev->driver->owner);
- return rc;
-}
-
-/*
- * mic_driver_uninit - MIC driver uninitialization tasks.
- *
- * Returns None
- */
-void mic_driver_uninit(struct mic_driver *mdrv)
-{
- mic_delete_card_debug_dir(mdrv);
- scif_unregister_device(mdrv->scdev);
- vop_unregister_device(mdrv->vpdev);
- mic_free_dma_chans(mdrv);
- mic_uninit_irq();
- mic_dp_uninit();
- module_put(mdrv->dev->driver->owner);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#ifndef _MIC_CARD_DEVICE_H_
-#define _MIC_CARD_DEVICE_H_
-
-#include <linux/workqueue.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-
-/**
- * struct mic_intr_info - Contains h/w specific interrupt sources info
- *
- * @num_intr: The number of irqs available
- */
-struct mic_intr_info {
- u32 num_intr;
-};
-
-/**
- * struct mic_irq_info - OS specific irq information
- *
- * @irq_usage_count: usage count array tracking the number of sources
- * assigned for each irq.
- */
-struct mic_irq_info {
- int *irq_usage_count;
-};
-
-/**
- * struct mic_device - MIC device information.
- *
- * @mmio: MMIO bar information.
- */
-struct mic_device {
- struct mic_mw mmio;
-};
-
-/**
- * struct mic_driver - MIC card driver information.
- *
- * @name: Name for MIC driver.
- * @dbg_dir: debugfs directory of this MIC device.
- * @dev: The device backing this MIC.
- * @dp: The pointer to the virtio device page.
- * @mdev: MIC device information for the host.
- * @hotplug_work: Hot plug work for adding/removing virtio devices.
- * @irq_info: The OS specific irq information
- * @intr_info: H/W specific interrupt information.
- * @dma_mbdev: dma device on the MIC virtual bus.
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @scdev: SCIF device on the SCIF virtual bus.
- * @vpdev: Virtio over PCIe device on the VOP virtual bus.
- */
-struct mic_driver {
- char name[20];
- struct dentry *dbg_dir;
- struct device *dev;
- void __iomem *dp;
- struct mic_device mdev;
- struct work_struct hotplug_work;
- struct mic_irq_info irq_info;
- struct mic_intr_info intr_info;
- struct mbus_device *dma_mbdev;
- struct dma_chan *dma_ch[MIC_MAX_DMA_CHAN];
- int num_dma_ch;
- struct scif_hw_dev *scdev;
- struct vop_device *vpdev;
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/**
- * mic_mmio_read - read from an MMIO register.
- * @mw: MMIO register base virtual address.
- * @offset: register offset.
- *
- * RETURNS: register value.
- */
-static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset)
-{
- return ioread32(mw->va + offset);
-}
-
-/**
- * mic_mmio_write - write to an MMIO register.
- * @mw: MMIO register base virtual address.
- * @val: the data value to put into the register
- * @offset: register offset.
- *
- * RETURNS: none.
- */
-static inline void
-mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
-{
- iowrite32(val, mw->va + offset);
-}
-
-int mic_driver_init(struct mic_driver *mdrv);
-void mic_driver_uninit(struct mic_driver *mdrv);
-int mic_next_card_db(void);
-struct mic_irq *
-mic_request_card_irq(irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int db);
-void mic_free_card_irq(struct mic_irq *cookie, void *data);
-u32 mic_read_spad(struct mic_device *mdev, unsigned int idx);
-void mic_send_intr(struct mic_device *mdev, int doorbell);
-void mic_send_p2p_intr(int doorbell, struct mic_mw *mw);
-int mic_db_to_irq(struct mic_driver *mdrv, int db);
-u32 mic_ack_interrupt(struct mic_device *mdev);
-void mic_hw_intr_init(struct mic_driver *mdrv);
-void __iomem *
-mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size);
-void mic_card_unmap(struct mic_device *mdev, void __iomem *addr);
-void __init mic_create_card_debug_dir(struct mic_driver *mdrv);
-void mic_delete_card_debug_dir(struct mic_driver *mdrv);
-void __init mic_init_card_debugfs(void);
-void mic_exit_card_debugfs(void);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-
-static const char mic_driver_name[] = "mic";
-
-static struct mic_driver g_drv;
-
-/**
- * mic_read_spad - read from the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to scratchpad register, 0 based
- *
- * This function allows reading of the 32bit scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-u32 mic_read_spad(struct mic_device *mdev, unsigned int idx)
-{
- return mic_mmio_read(&mdev->mmio,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SPAD0 + idx * 4);
-}
-
-/**
- * __mic_send_intr - Send interrupt to Host.
- * @mdev: pointer to mic_device instance
- * @doorbell: Doorbell number.
- */
-void mic_send_intr(struct mic_device *mdev, int doorbell)
-{
- struct mic_mw *mw = &mdev->mmio;
-
- if (doorbell > MIC_X100_MAX_DOORBELL_IDX)
- return;
- /* Ensure that the interrupt is ordered w.r.t previous stores. */
- wmb();
- mic_mmio_write(mw, MIC_X100_SBOX_SDBIC0_DBREQ_BIT,
- MIC_X100_SBOX_BASE_ADDRESS +
- (MIC_X100_SBOX_SDBIC0 + (4 * doorbell)));
-}
-
-/*
- * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC.
- */
-static void mic_x100_send_sbox_intr(struct mic_mw *mw, int doorbell)
-{
- u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8;
- u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS +
- apic_icr_offset);
-
- /* for MIC we need to make sure we "hit" the send_icr bit (13) */
- apicicr_low = (apicicr_low | (1 << 13));
- /*
- * Ensure that the interrupt is ordered w.r.t. previous stores
- * to main memory. Fence instructions are not implemented in X100
- * since execution is in order but a compiler barrier is still
- * required.
- */
- wmb();
- mic_mmio_write(mw, apicicr_low,
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-static void mic_x100_send_rdmasr_intr(struct mic_mw *mw, int doorbell)
-{
- int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2);
- /*
- * Ensure that the interrupt is ordered w.r.t. previous stores
- * to main memory. Fence instructions are not implemented in X100
- * since execution is in order but a compiler barrier is still
- * required.
- */
- wmb();
- mic_mmio_write(mw, 0, MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset);
-}
-
-/**
- * mic_ack_interrupt - Device specific interrupt handling.
- * @mdev: pointer to mic_device instance
- *
- * Returns: bitmask of doorbell events triggered.
- */
-u32 mic_ack_interrupt(struct mic_device *mdev)
-{
- return 0;
-}
-
-static inline int mic_get_sbox_irq(int db)
-{
- return MIC_X100_IRQ_BASE + db;
-}
-
-static inline int mic_get_rdmasr_irq(int index)
-{
- return MIC_X100_RDMASR_IRQ_BASE + index;
-}
-
-void mic_send_p2p_intr(int db, struct mic_mw *mw)
-{
- int rdmasr_index;
-
- if (db < MIC_X100_NUM_SBOX_IRQ) {
- mic_x100_send_sbox_intr(mw, db);
- } else {
- rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ;
- mic_x100_send_rdmasr_intr(mw, rdmasr_index);
- }
-}
-
-/**
- * mic_hw_intr_init - Initialize h/w specific interrupt
- * information.
- * @mdrv: pointer to mic_driver
- */
-void mic_hw_intr_init(struct mic_driver *mdrv)
-{
- mdrv->intr_info.num_intr = MIC_X100_NUM_SBOX_IRQ +
- MIC_X100_NUM_RDMASR_IRQ;
-}
-
-/**
- * mic_db_to_irq - Retrieve irq number corresponding to a doorbell.
- * @mdrv: pointer to mic_driver
- * @db: The doorbell obtained for which the irq is needed. Doorbell
- * may correspond to an sbox doorbell or an rdmasr index.
- *
- * Returns the irq corresponding to the doorbell.
- */
-int mic_db_to_irq(struct mic_driver *mdrv, int db)
-{
- int rdmasr_index;
-
- /*
- * The total number of doorbell interrupts on the card are 16. Indices
- * 0-8 falls in the SBOX category and 8-15 fall in the RDMASR category.
- */
- if (db < MIC_X100_NUM_SBOX_IRQ) {
- return mic_get_sbox_irq(db);
- } else {
- rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ;
- return mic_get_rdmasr_irq(rdmasr_index);
- }
-}
-
-/*
- * mic_card_map - Allocate virtual address for a remote memory region.
- * @mdev: pointer to mic_device instance.
- * @addr: Remote DMA address.
- * @size: Size of the region.
- *
- * Returns: Virtual address backing the remote memory region.
- */
-void __iomem *
-mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size)
-{
- return ioremap(addr, size);
-}
-
-/*
- * mic_card_unmap - Unmap the virtual address for a remote memory region.
- * @mdev: pointer to mic_device instance.
- * @addr: Virtual address for remote memory region.
- *
- * Returns: None.
- */
-void mic_card_unmap(struct mic_device *mdev, void __iomem *addr)
-{
- iounmap(addr);
-}
-
-static inline struct mic_driver *mbdev_to_mdrv(struct mbus_device *mbdev)
-{
- return dev_get_drvdata(mbdev->dev.parent);
-}
-
-static struct mic_irq *
-_mic_request_threaded_irq(struct mbus_device *mbdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src)
-{
- int rc = 0;
- unsigned int irq = intr_src;
- unsigned long cookie = irq;
-
- rc = request_threaded_irq(irq, handler, thread_fn, 0, name, data);
- if (rc) {
- dev_err(mbdev_to_mdrv(mbdev)->dev,
- "request_threaded_irq failed rc = %d\n", rc);
- return ERR_PTR(rc);
- }
- return (struct mic_irq *)cookie;
-}
-
-static void _mic_free_irq(struct mbus_device *mbdev,
- struct mic_irq *cookie, void *data)
-{
- unsigned long irq = (unsigned long)cookie;
- free_irq(irq, data);
-}
-
-static void _mic_ack_interrupt(struct mbus_device *mbdev, int num)
-{
- mic_ack_interrupt(&mbdev_to_mdrv(mbdev)->mdev);
-}
-
-static struct mbus_hw_ops mbus_hw_ops = {
- .request_threaded_irq = _mic_request_threaded_irq,
- .free_irq = _mic_free_irq,
- .ack_interrupt = _mic_ack_interrupt,
-};
-
-static int __init mic_probe(struct platform_device *pdev)
-{
- struct mic_driver *mdrv = &g_drv;
- struct mic_device *mdev = &mdrv->mdev;
- int rc = 0;
-
- mdrv->dev = &pdev->dev;
- snprintf(mdrv->name, sizeof(mic_driver_name), mic_driver_name);
-
- /* FIXME: use dma_set_mask_and_coherent() and check result */
- dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-
- mdev->mmio.pa = MIC_X100_MMIO_BASE;
- mdev->mmio.len = MIC_X100_MMIO_LEN;
- mdev->mmio.va = devm_ioremap(&pdev->dev, MIC_X100_MMIO_BASE,
- MIC_X100_MMIO_LEN);
- if (!mdev->mmio.va) {
- dev_err(&pdev->dev, "Cannot remap MMIO BAR\n");
- rc = -EIO;
- goto done;
- }
- mic_hw_intr_init(mdrv);
- platform_set_drvdata(pdev, mdrv);
- mdrv->dma_mbdev = mbus_register_device(mdrv->dev, MBUS_DEV_DMA_MIC,
- NULL, &mbus_hw_ops, 0,
- mdrv->mdev.mmio.va);
- if (IS_ERR(mdrv->dma_mbdev)) {
- rc = PTR_ERR(mdrv->dma_mbdev);
- dev_err(&pdev->dev, "mbus_add_device failed rc %d\n", rc);
- goto done;
- }
- rc = mic_driver_init(mdrv);
- if (rc) {
- dev_err(&pdev->dev, "mic_driver_init failed rc %d\n", rc);
- goto remove_dma;
- }
-done:
- return rc;
-remove_dma:
- mbus_unregister_device(mdrv->dma_mbdev);
- return rc;
-}
-
-static int mic_remove(struct platform_device *pdev)
-{
- struct mic_driver *mdrv = &g_drv;
-
- mic_driver_uninit(mdrv);
- mbus_unregister_device(mdrv->dma_mbdev);
- return 0;
-}
-
-static void mic_platform_shutdown(struct platform_device *pdev)
-{
- mic_remove(pdev);
-}
-
-static struct platform_driver __refdata mic_platform_driver = {
- .probe = mic_probe,
- .remove = mic_remove,
- .shutdown = mic_platform_shutdown,
- .driver = {
- .name = mic_driver_name,
- },
-};
-
-static struct platform_device *mic_platform_dev;
-
-static int __init mic_init(void)
-{
- int ret;
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- if (!(c->x86 == 11 && c->x86_model == 1)) {
- ret = -ENODEV;
- pr_err("%s not running on X100 ret %d\n", __func__, ret);
- goto done;
- }
-
- request_module("mic_x100_dma");
- mic_init_card_debugfs();
-
- mic_platform_dev = platform_device_register_simple(mic_driver_name,
- 0, NULL, 0);
- ret = PTR_ERR_OR_ZERO(mic_platform_dev);
- if (ret) {
- pr_err("platform_device_register_full ret %d\n", ret);
- goto cleanup_debugfs;
- }
- ret = platform_driver_register(&mic_platform_driver);
- if (ret) {
- pr_err("platform_driver_register ret %d\n", ret);
- goto device_unregister;
- }
- return ret;
-
-device_unregister:
- platform_device_unregister(mic_platform_dev);
-cleanup_debugfs:
- mic_exit_card_debugfs();
-done:
- return ret;
-}
-
-static void __exit mic_exit(void)
-{
- platform_driver_unregister(&mic_platform_driver);
- platform_device_unregister(mic_platform_dev);
- mic_exit_card_debugfs();
-}
-
-module_init(mic_init);
-module_exit(mic_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 Card driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Disclaimer: The codes contained in these modules may be specific to
- * the Intel Software Development Platform codenamed: Knights Ferry, and
- * the Intel product codenamed: Knights Corner, and are not backward
- * compatible with other Intel products. Additionally, Intel will NOT
- * support the codes or instruction set in future products.
- *
- * Intel MIC Card driver.
- */
-#ifndef _MIC_X100_CARD_H_
-#define _MIC_X100_CARD_H_
-
-#define MIC_X100_MMIO_BASE 0x08007C0000ULL
-#define MIC_X100_MMIO_LEN 0x00020000ULL
-#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000ULL
-
-#define MIC_X100_SBOX_SPAD0 0x0000AB20
-#define MIC_X100_SBOX_SDBIC0 0x0000CC90
-#define MIC_X100_SBOX_SDBIC0_DBREQ_BIT 0x80000000
-#define MIC_X100_SBOX_RDMASR0 0x0000B180
-#define MIC_X100_SBOX_APICICR0 0x0000A9D0
-
-#define MIC_X100_MAX_DOORBELL_IDX 8
-
-#define MIC_X100_NUM_SBOX_IRQ 8
-#define MIC_X100_NUM_RDMASR_IRQ 8
-#define MIC_X100_SBOX_IRQ_BASE 0
-#define MIC_X100_RDMASR_IRQ_BASE 17
-
-#define MIC_X100_IRQ_BASE 26
-
-#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC driver.
- */
-#ifndef __MIC_DEV_H__
-#define __MIC_DEV_H__
-
-/* The maximum number of MIC devices supported in a single host system. */
-#define MIC_MAX_NUM_DEVS 128
-
-/**
- * enum mic_hw_family - The hardware family to which a device belongs.
- */
-enum mic_hw_family {
- MIC_FAMILY_X100 = 0,
- MIC_FAMILY_X200,
- MIC_FAMILY_UNKNOWN,
- MIC_FAMILY_LAST
-};
-
-/**
- * struct mic_mw - MIC memory window
- *
- * @pa: Base physical address.
- * @va: Base ioremap'd virtual address.
- * @len: Size of the memory window.
- */
-struct mic_mw {
- phys_addr_t pa;
- void __iomem *va;
- resource_size_t len;
-};
-
-/*
- * Scratch pad register offsets used by the host to communicate
- * device page DMA address to the card.
- */
-#define MIC_DPLO_SPAD 14
-#define MIC_DPHI_SPAD 15
-
-/*
- * These values are supposed to be in the config_change field of the
- * device page when the host sends a config change interrupt to the card.
- */
-#define MIC_VIRTIO_PARAM_DEV_REMOVE 0x1
-#define MIC_VIRTIO_PARAM_CONFIG_CHANGED 0x2
-
-/* Maximum number of DMA channels */
-#define MIC_MAX_DMA_CHAN 4
-
-#endif
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Coprocessor State Management (COSM) Driver
-# Copyright(c) 2015, Intel Corporation.
-#
-obj-$(CONFIG_MIC_COSM) += mic_cosm.o
-
-mic_cosm-objs := cosm_main.o
-mic_cosm-objs += cosm_debugfs.o
-mic_cosm-objs += cosm_sysfs.o
-mic_cosm-objs += cosm_scif_server.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-
-#include <linux/debugfs.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include "cosm_main.h"
-
-/* Debugfs parent dir */
-static struct dentry *cosm_dbg;
-
-/*
- * log_buf_show - Display MIC kernel log buffer
- *
- * log_buf addr/len is read from System.map by user space
- * and populated in sysfs entries.
- */
-static int log_buf_show(struct seq_file *s, void *unused)
-{
- void __iomem *log_buf_va;
- int __iomem *log_buf_len_va;
- struct cosm_device *cdev = s->private;
- void *kva;
- int size;
- u64 aper_offset;
-
- if (!cdev || !cdev->log_buf_addr || !cdev->log_buf_len)
- goto done;
-
- mutex_lock(&cdev->cosm_mutex);
- switch (cdev->state) {
- case MIC_BOOTING:
- case MIC_ONLINE:
- case MIC_SHUTTING_DOWN:
- break;
- default:
- goto unlock;
- }
-
- /*
- * Card kernel will never be relocated and any kernel text/data mapping
- * can be translated to phys address by subtracting __START_KERNEL_map.
- */
- aper_offset = (u64)cdev->log_buf_len - __START_KERNEL_map;
- log_buf_len_va = cdev->hw_ops->aper(cdev)->va + aper_offset;
- aper_offset = (u64)cdev->log_buf_addr - __START_KERNEL_map;
- log_buf_va = cdev->hw_ops->aper(cdev)->va + aper_offset;
-
- size = ioread32(log_buf_len_va);
- kva = kmalloc(size, GFP_KERNEL);
- if (!kva)
- goto unlock;
-
- memcpy_fromio(kva, log_buf_va, size);
- seq_write(s, kva, size);
- kfree(kva);
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
-done:
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(log_buf);
-
-/*
- * force_reset_show - Force MIC reset
- *
- * Invokes the force_reset COSM bus op instead of the standard reset
- * op in case a force reset of the MIC device is required
- */
-static int force_reset_show(struct seq_file *s, void *pos)
-{
- struct cosm_device *cdev = s->private;
-
- cosm_stop(cdev, true);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(force_reset);
-
-void cosm_create_debug_dir(struct cosm_device *cdev)
-{
- char name[16];
-
- if (!cosm_dbg)
- return;
-
- scnprintf(name, sizeof(name), "mic%d", cdev->index);
- cdev->dbg_dir = debugfs_create_dir(name, cosm_dbg);
-
- debugfs_create_file("log_buf", 0444, cdev->dbg_dir, cdev,
- &log_buf_fops);
- debugfs_create_file("force_reset", 0444, cdev->dbg_dir, cdev,
- &force_reset_fops);
-}
-
-void cosm_delete_debug_dir(struct cosm_device *cdev)
-{
- debugfs_remove_recursive(cdev->dbg_dir);
-}
-
-void cosm_init_debugfs(void)
-{
- cosm_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-void cosm_exit_debugfs(void)
-{
- debugfs_remove(cosm_dbg);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/idr.h>
-#include <linux/slab.h>
-#include <linux/cred.h>
-#include "cosm_main.h"
-
-static const char cosm_driver_name[] = "mic";
-
-/* COSM ID allocator */
-static struct ida g_cosm_ida;
-/* Class of MIC devices for sysfs accessibility. */
-static struct class *g_cosm_class;
-/* Number of MIC devices */
-static atomic_t g_num_dev;
-
-/**
- * cosm_hw_reset - Issue a HW reset for the MIC device
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already reset and ready
- */
-static void cosm_hw_reset(struct cosm_device *cdev, bool force)
-{
- int i;
-
-#define MIC_RESET_TO (45)
- if (force && cdev->hw_ops->force_reset)
- cdev->hw_ops->force_reset(cdev);
- else
- cdev->hw_ops->reset(cdev);
-
- for (i = 0; i < MIC_RESET_TO; i++) {
- if (cdev->hw_ops->ready(cdev)) {
- cosm_set_state(cdev, MIC_READY);
- return;
- }
- /*
- * Resets typically take 10s of seconds to complete.
- * Since an MMIO read is required to check if the
- * firmware is ready or not, a 1 second delay works nicely.
- */
- msleep(1000);
- }
- cosm_set_state(cdev, MIC_RESET_FAILED);
-}
-
-/**
- * cosm_start - Start the MIC
- * @cdev: pointer to cosm_device instance
- *
- * This function prepares an MIC for boot and initiates boot.
- * RETURNS: An appropriate -ERRNO error value on error, or 0 for success.
- */
-int cosm_start(struct cosm_device *cdev)
-{
- const struct cred *orig_cred;
- struct cred *override_cred;
- int rc;
-
- mutex_lock(&cdev->cosm_mutex);
- if (!cdev->bootmode) {
- dev_err(&cdev->dev, "%s %d bootmode not set\n",
- __func__, __LINE__);
- rc = -EINVAL;
- goto unlock_ret;
- }
-retry:
- if (cdev->state != MIC_READY) {
- dev_err(&cdev->dev, "%s %d MIC state not READY\n",
- __func__, __LINE__);
- rc = -EINVAL;
- goto unlock_ret;
- }
- if (!cdev->hw_ops->ready(cdev)) {
- cosm_hw_reset(cdev, false);
- /*
- * The state will either be MIC_READY if the reset succeeded
- * or MIC_RESET_FAILED if the firmware reset failed.
- */
- goto retry;
- }
-
- /*
- * Set credentials to root to allow non-root user to download initramsfs
- * with 600 permissions
- */
- override_cred = prepare_creds();
- if (!override_cred) {
- dev_err(&cdev->dev, "%s %d prepare_creds failed\n",
- __func__, __LINE__);
- rc = -ENOMEM;
- goto unlock_ret;
- }
- override_cred->fsuid = GLOBAL_ROOT_UID;
- orig_cred = override_creds(override_cred);
-
- rc = cdev->hw_ops->start(cdev, cdev->index);
-
- revert_creds(orig_cred);
- put_cred(override_cred);
- if (rc)
- goto unlock_ret;
-
- /*
- * If linux is being booted, card is treated 'online' only
- * when the scif interface in the card is up. If anything else
- * is booted, we set card to 'online' immediately.
- */
- if (!strcmp(cdev->bootmode, "linux"))
- cosm_set_state(cdev, MIC_BOOTING);
- else
- cosm_set_state(cdev, MIC_ONLINE);
-unlock_ret:
- mutex_unlock(&cdev->cosm_mutex);
- if (rc)
- dev_err(&cdev->dev, "cosm_start failed rc %d\n", rc);
- return rc;
-}
-
-/**
- * cosm_stop - Prepare the MIC for reset and trigger reset
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already reset and ready.
- *
- * RETURNS: None
- */
-void cosm_stop(struct cosm_device *cdev, bool force)
-{
- mutex_lock(&cdev->cosm_mutex);
- if (cdev->state != MIC_READY || force) {
- /*
- * Don't call hw_ops if they have been called previously.
- * stop(..) calls device_unregister and will crash the system if
- * called multiple times.
- */
- u8 state = cdev->state == MIC_RESETTING ?
- cdev->prev_state : cdev->state;
- bool call_hw_ops = state != MIC_RESET_FAILED &&
- state != MIC_READY;
-
- if (cdev->state != MIC_RESETTING)
- cosm_set_state(cdev, MIC_RESETTING);
- cdev->heartbeat_watchdog_enable = false;
- if (call_hw_ops)
- cdev->hw_ops->stop(cdev, force);
- cosm_hw_reset(cdev, force);
- cosm_set_shutdown_status(cdev, MIC_NOP);
- if (call_hw_ops && cdev->hw_ops->post_reset)
- cdev->hw_ops->post_reset(cdev, cdev->state);
- }
- mutex_unlock(&cdev->cosm_mutex);
- flush_work(&cdev->scif_work);
-}
-
-/**
- * cosm_reset_trigger_work - Trigger MIC reset
- * @work: The work structure
- *
- * This work is scheduled whenever the host wants to reset the MIC.
- */
-static void cosm_reset_trigger_work(struct work_struct *work)
-{
- struct cosm_device *cdev = container_of(work, struct cosm_device,
- reset_trigger_work);
- cosm_stop(cdev, false);
-}
-
-/**
- * cosm_reset - Schedule MIC reset
- * @cdev: pointer to cosm_device instance
- *
- * RETURNS: An -EINVAL if the card is already READY or 0 for success.
- */
-int cosm_reset(struct cosm_device *cdev)
-{
- int rc = 0;
-
- mutex_lock(&cdev->cosm_mutex);
- if (cdev->state != MIC_READY) {
- if (cdev->state != MIC_RESETTING) {
- cdev->prev_state = cdev->state;
- cosm_set_state(cdev, MIC_RESETTING);
- schedule_work(&cdev->reset_trigger_work);
- }
- } else {
- dev_err(&cdev->dev, "%s %d MIC is READY\n", __func__, __LINE__);
- rc = -EINVAL;
- }
- mutex_unlock(&cdev->cosm_mutex);
- return rc;
-}
-
-/**
- * cosm_shutdown - Initiate MIC shutdown.
- * @cdev: pointer to cosm_device instance
- *
- * RETURNS: None
- */
-int cosm_shutdown(struct cosm_device *cdev)
-{
- struct cosm_msg msg = { .id = COSM_MSG_SHUTDOWN };
- int rc = 0;
-
- mutex_lock(&cdev->cosm_mutex);
- if (cdev->state != MIC_ONLINE) {
- rc = -EINVAL;
- dev_err(&cdev->dev, "%s %d skipping shutdown in state: %s\n",
- __func__, __LINE__, cosm_state_string[cdev->state]);
- goto err;
- }
-
- if (!cdev->epd) {
- rc = -ENOTCONN;
- dev_err(&cdev->dev, "%s %d scif endpoint not connected rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
-
- rc = scif_send(cdev->epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0) {
- dev_err(&cdev->dev, "%s %d scif_send failed rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
- cdev->heartbeat_watchdog_enable = false;
- cosm_set_state(cdev, MIC_SHUTTING_DOWN);
- rc = 0;
-err:
- mutex_unlock(&cdev->cosm_mutex);
- return rc;
-}
-
-static int cosm_driver_probe(struct cosm_device *cdev)
-{
- int rc;
-
- /* Initialize SCIF server at first probe */
- if (atomic_add_return(1, &g_num_dev) == 1) {
- rc = cosm_scif_init();
- if (rc)
- goto scif_exit;
- }
- mutex_init(&cdev->cosm_mutex);
- INIT_WORK(&cdev->reset_trigger_work, cosm_reset_trigger_work);
- INIT_WORK(&cdev->scif_work, cosm_scif_work);
- cdev->sysfs_heartbeat_enable = true;
- cosm_sysfs_init(cdev);
- cdev->sdev = device_create_with_groups(g_cosm_class, cdev->dev.parent,
- MKDEV(0, cdev->index), cdev, cdev->attr_group,
- "mic%d", cdev->index);
- if (IS_ERR(cdev->sdev)) {
- rc = PTR_ERR(cdev->sdev);
- dev_err(&cdev->dev, "device_create_with_groups failed rc %d\n",
- rc);
- goto scif_exit;
- }
-
- cdev->state_sysfs = sysfs_get_dirent(cdev->sdev->kobj.sd,
- "state");
- if (!cdev->state_sysfs) {
- rc = -ENODEV;
- dev_err(&cdev->dev, "sysfs_get_dirent failed rc %d\n", rc);
- goto destroy_device;
- }
- cosm_create_debug_dir(cdev);
- return 0;
-destroy_device:
- device_destroy(g_cosm_class, MKDEV(0, cdev->index));
-scif_exit:
- if (atomic_dec_and_test(&g_num_dev))
- cosm_scif_exit();
- return rc;
-}
-
-static void cosm_driver_remove(struct cosm_device *cdev)
-{
- cosm_delete_debug_dir(cdev);
- sysfs_put(cdev->state_sysfs);
- device_destroy(g_cosm_class, MKDEV(0, cdev->index));
- flush_work(&cdev->reset_trigger_work);
- cosm_stop(cdev, false);
- if (atomic_dec_and_test(&g_num_dev))
- cosm_scif_exit();
-
- /* These sysfs entries might have allocated */
- kfree(cdev->cmdline);
- kfree(cdev->firmware);
- kfree(cdev->ramdisk);
- kfree(cdev->bootmode);
-}
-
-static int cosm_suspend(struct device *dev)
-{
- struct cosm_device *cdev = dev_to_cosm(dev);
-
- mutex_lock(&cdev->cosm_mutex);
- switch (cdev->state) {
- /**
- * Suspend/freeze hooks in userspace have already shutdown the card.
- * Card should be 'ready' in most cases. It is however possible that
- * some userspace application initiated a boot. In those cases, we
- * simply reset the card.
- */
- case MIC_ONLINE:
- case MIC_BOOTING:
- case MIC_SHUTTING_DOWN:
- mutex_unlock(&cdev->cosm_mutex);
- cosm_stop(cdev, false);
- break;
- default:
- mutex_unlock(&cdev->cosm_mutex);
- break;
- }
- return 0;
-}
-
-static const struct dev_pm_ops cosm_pm_ops = {
- .suspend = cosm_suspend,
- .freeze = cosm_suspend
-};
-
-static struct cosm_driver cosm_driver = {
- .driver = {
- .name = KBUILD_MODNAME,
- .owner = THIS_MODULE,
- .pm = &cosm_pm_ops,
- },
- .probe = cosm_driver_probe,
- .remove = cosm_driver_remove
-};
-
-static int __init cosm_init(void)
-{
- int ret;
-
- cosm_init_debugfs();
-
- g_cosm_class = class_create(THIS_MODULE, cosm_driver_name);
- if (IS_ERR(g_cosm_class)) {
- ret = PTR_ERR(g_cosm_class);
- pr_err("class_create failed ret %d\n", ret);
- goto cleanup_debugfs;
- }
-
- ida_init(&g_cosm_ida);
- ret = cosm_register_driver(&cosm_driver);
- if (ret) {
- pr_err("cosm_register_driver failed ret %d\n", ret);
- goto ida_destroy;
- }
- return 0;
-ida_destroy:
- ida_destroy(&g_cosm_ida);
- class_destroy(g_cosm_class);
-cleanup_debugfs:
- cosm_exit_debugfs();
- return ret;
-}
-
-static void __exit cosm_exit(void)
-{
- cosm_unregister_driver(&cosm_driver);
- ida_destroy(&g_cosm_ida);
- class_destroy(g_cosm_class);
- cosm_exit_debugfs();
-}
-
-module_init(cosm_init);
-module_exit(cosm_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC Coprocessor State Management (COSM) Driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#ifndef _COSM_COSM_H_
-#define _COSM_COSM_H_
-
-#include <linux/scif.h>
-#include "../bus/cosm_bus.h"
-
-#define COSM_HEARTBEAT_SEND_SEC 30
-#define SCIF_COSM_LISTEN_PORT 201
-
-/**
- * enum COSM msg id's
- * @COSM_MSG_SHUTDOWN: host->card trigger shutdown
- * @COSM_MSG_SYNC_TIME: host->card send host time to card to sync time
- * @COSM_MSG_HEARTBEAT: card->host heartbeat
- * @COSM_MSG_SHUTDOWN_STATUS: card->host with shutdown status as payload
- */
-enum cosm_msg_id {
- COSM_MSG_SHUTDOWN,
- COSM_MSG_SYNC_TIME,
- COSM_MSG_HEARTBEAT,
- COSM_MSG_SHUTDOWN_STATUS,
-};
-
-struct cosm_msg {
- u64 id;
- union {
- u64 shutdown_status;
- struct {
- u64 tv_sec;
- u64 tv_nsec;
- } timespec;
- };
-};
-
-extern const char * const cosm_state_string[];
-extern const char * const cosm_shutdown_status_string[];
-
-void cosm_sysfs_init(struct cosm_device *cdev);
-int cosm_start(struct cosm_device *cdev);
-void cosm_stop(struct cosm_device *cdev, bool force);
-int cosm_reset(struct cosm_device *cdev);
-int cosm_shutdown(struct cosm_device *cdev);
-void cosm_set_state(struct cosm_device *cdev, u8 state);
-void cosm_set_shutdown_status(struct cosm_device *cdev, u8 status);
-void cosm_init_debugfs(void);
-void cosm_exit_debugfs(void);
-void cosm_create_debug_dir(struct cosm_device *cdev);
-void cosm_delete_debug_dir(struct cosm_device *cdev);
-int cosm_scif_init(void);
-void cosm_scif_exit(void);
-void cosm_scif_work(struct work_struct *work);
-
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#include <linux/kthread.h>
-#include <linux/sched/signal.h>
-
-#include "cosm_main.h"
-
-/*
- * The COSM driver uses SCIF to communicate between the management node and the
- * MIC cards. SCIF is used to (a) Send a shutdown command to the card (b)
- * receive a shutdown status back from the card upon completion of shutdown and
- * (c) receive periodic heartbeat messages from the card used to deduce if the
- * card has crashed.
- *
- * A COSM server consisting of a SCIF listening endpoint waits for incoming
- * connections from the card. Upon acceptance of the connection, a separate
- * work-item is scheduled to handle SCIF message processing for that card. The
- * life-time of this work-item is therefore the time from which the connection
- * from a card is accepted to the time at which the connection is closed. A new
- * work-item starts each time the card boots and is alive till the card (a)
- * shuts down (b) is reset (c) crashes (d) cosm_client driver on the card is
- * unloaded.
- *
- * From the point of view of COSM interactions with SCIF during card
- * shutdown, reset and crash are as follows:
- *
- * Card shutdown
- * -------------
- * 1. COSM client on the card invokes orderly_poweroff() in response to SHUTDOWN
- * message from the host.
- * 2. Card driver shutdown callback invokes scif_unregister_device(..) resulting
- * in scif_remove(..) getting called on the card
- * 3. scif_remove -> scif_stop -> scif_handle_remove_node ->
- * scif_peer_unregister_device -> device_unregister for the host peer device
- * 4. During device_unregister remove(..) method of cosm_client is invoked which
- * closes the COSM SCIF endpoint on the card. This results in a SCIF_DISCNCT
- * message being sent to host SCIF. SCIF_DISCNCT message processing on the
- * host SCIF sets the host COSM SCIF endpoint state to DISCONNECTED and wakes
- * up the host COSM thread blocked in scif_poll(..) resulting in
- * scif_poll(..) returning EPOLLHUP.
- * 5. On the card, scif_peer_release_dev is next called which results in an
- * SCIF_EXIT message being sent to the host and after receiving the
- * SCIF_EXIT_ACK from the host the peer device teardown on the card is
- * complete.
- * 6. As part of the SCIF_EXIT message processing on the host, host sends a
- * SCIF_REMOVE_NODE to itself corresponding to the card being removed. This
- * starts a similar SCIF peer device teardown sequence on the host
- * corresponding to the card being shut down.
- *
- * Card reset
- * ----------
- * The case of interest here is when the card has not been previously shut down
- * since most of the steps below are skipped in that case:
-
- * 1. cosm_stop(..) invokes hw_ops->stop(..) method of the base PCIe driver
- * which unregisters the SCIF HW device resulting in scif_remove(..) being
- * called on the host.
- * 2. scif_remove(..) calls scif_disconnect_node(..) which results in a
- * SCIF_EXIT message being sent to the card.
- * 3. The card executes scif_stop() as part of SCIF_EXIT message
- * processing. This results in the COSM endpoint on the card being closed and
- * the SCIF host peer device on the card getting unregistered similar to
- * steps 3, 4 and 5 for the card shutdown case above. scif_poll(..) on the
- * host returns EPOLLHUP as a result.
- * 4. On the host, card peer device unregister and SCIF HW remove(..) also
- * subsequently complete.
- *
- * Card crash
- * ----------
- * If a reset is issued after the card has crashed, there is no SCIF_DISCNT
- * message from the card which would result in scif_poll(..) returning
- * EPOLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE
- * message to itself resulting in the card SCIF peer device being unregistered,
- * this results in a scif_peer_release_dev -> scif_cleanup_scifdev->
- * scif_invalidate_ep call sequence which sets the endpoint state to
- * DISCONNECTED and results in scif_poll(..) returning EPOLLHUP.
- */
-
-#define COSM_SCIF_BACKLOG 16
-#define COSM_HEARTBEAT_CHECK_DELTA_SEC 10
-#define COSM_HEARTBEAT_TIMEOUT_SEC \
- (COSM_HEARTBEAT_SEND_SEC + COSM_HEARTBEAT_CHECK_DELTA_SEC)
-#define COSM_HEARTBEAT_TIMEOUT_MSEC (COSM_HEARTBEAT_TIMEOUT_SEC * MSEC_PER_SEC)
-
-static struct task_struct *server_thread;
-static scif_epd_t listen_epd;
-
-/* Publish MIC card's shutdown status to user space MIC daemon */
-static void cosm_update_mic_status(struct cosm_device *cdev)
-{
- if (cdev->shutdown_status_int != MIC_NOP) {
- cosm_set_shutdown_status(cdev, cdev->shutdown_status_int);
- cdev->shutdown_status_int = MIC_NOP;
- }
-}
-
-/* Store MIC card's shutdown status internally when it is received */
-static void cosm_shutdown_status_int(struct cosm_device *cdev,
- enum mic_status shutdown_status)
-{
- switch (shutdown_status) {
- case MIC_HALTED:
- case MIC_POWER_OFF:
- case MIC_RESTART:
- case MIC_CRASHED:
- break;
- default:
- dev_err(&cdev->dev, "%s %d Unexpected shutdown_status %d\n",
- __func__, __LINE__, shutdown_status);
- return;
- };
- cdev->shutdown_status_int = shutdown_status;
- cdev->heartbeat_watchdog_enable = false;
-
- if (cdev->state != MIC_SHUTTING_DOWN)
- cosm_set_state(cdev, MIC_SHUTTING_DOWN);
-}
-
-/* Non-blocking recv. Read and process all available messages */
-static void cosm_scif_recv(struct cosm_device *cdev)
-{
- struct cosm_msg msg;
- int rc;
-
- while (1) {
- rc = scif_recv(cdev->epd, &msg, sizeof(msg), 0);
- if (!rc) {
- break;
- } else if (rc < 0) {
- dev_dbg(&cdev->dev, "%s: %d rc %d\n",
- __func__, __LINE__, rc);
- break;
- }
- dev_dbg(&cdev->dev, "%s: %d rc %d id 0x%llx\n",
- __func__, __LINE__, rc, msg.id);
-
- switch (msg.id) {
- case COSM_MSG_SHUTDOWN_STATUS:
- cosm_shutdown_status_int(cdev, msg.shutdown_status);
- break;
- case COSM_MSG_HEARTBEAT:
- /* Nothing to do, heartbeat only unblocks scif_poll */
- break;
- default:
- dev_err(&cdev->dev, "%s: %d unknown msg.id %lld\n",
- __func__, __LINE__, msg.id);
- break;
- }
- }
-}
-
-/* Publish crashed status for this MIC card */
-static void cosm_set_crashed(struct cosm_device *cdev)
-{
- dev_err(&cdev->dev, "node alive timeout\n");
- cosm_shutdown_status_int(cdev, MIC_CRASHED);
- cosm_update_mic_status(cdev);
-}
-
-/* Send host time to the MIC card to sync system time between host and MIC */
-static void cosm_send_time(struct cosm_device *cdev)
-{
- struct cosm_msg msg = { .id = COSM_MSG_SYNC_TIME };
- struct timespec64 ts;
- int rc;
-
- ktime_get_real_ts64(&ts);
- msg.timespec.tv_sec = ts.tv_sec;
- msg.timespec.tv_nsec = ts.tv_nsec;
-
- rc = scif_send(cdev->epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0)
- dev_err(&cdev->dev, "%s %d scif_send failed rc %d\n",
- __func__, __LINE__, rc);
-}
-
-/*
- * Close this cosm_device's endpoint after its peer endpoint on the card has
- * been closed. In all cases except MIC card crash EPOLLHUP on the host is
- * triggered by the client's endpoint being closed.
- */
-static void cosm_scif_close(struct cosm_device *cdev)
-{
- /*
- * Because SHUTDOWN_STATUS message is sent by the MIC cards in the
- * reboot notifier when shutdown is still not complete, we notify mpssd
- * to reset the card when SCIF endpoint is closed.
- */
- cosm_update_mic_status(cdev);
- scif_close(cdev->epd);
- cdev->epd = NULL;
- dev_dbg(&cdev->dev, "%s %d\n", __func__, __LINE__);
-}
-
-/*
- * Set card state to ONLINE when a new SCIF connection from a MIC card is
- * received. Normally the state is BOOTING when the connection comes in, but can
- * be ONLINE if cosm_client driver on the card was unloaded and then reloaded.
- */
-static int cosm_set_online(struct cosm_device *cdev)
-{
- int rc = 0;
-
- if (MIC_BOOTING == cdev->state || MIC_ONLINE == cdev->state) {
- cdev->heartbeat_watchdog_enable = cdev->sysfs_heartbeat_enable;
- cdev->epd = cdev->newepd;
- if (cdev->state == MIC_BOOTING)
- cosm_set_state(cdev, MIC_ONLINE);
- cosm_send_time(cdev);
- dev_dbg(&cdev->dev, "%s %d\n", __func__, __LINE__);
- } else {
- dev_warn(&cdev->dev, "%s %d not going online in state: %s\n",
- __func__, __LINE__, cosm_state_string[cdev->state]);
- rc = -EINVAL;
- }
- /* Drop reference acquired by bus_find_device in the server thread */
- put_device(&cdev->dev);
- return rc;
-}
-
-/*
- * Work function for handling work for a SCIF connection from a particular MIC
- * card. It first sets the card state to ONLINE and then calls scif_poll to
- * block on activity such as incoming messages on the SCIF endpoint. When the
- * endpoint is closed, the work function exits, completing its life cycle, from
- * MIC card boot to card shutdown/reset/crash.
- */
-void cosm_scif_work(struct work_struct *work)
-{
- struct cosm_device *cdev = container_of(work, struct cosm_device,
- scif_work);
- struct scif_pollepd pollepd;
- int rc;
-
- mutex_lock(&cdev->cosm_mutex);
- if (cosm_set_online(cdev))
- goto exit;
-
- while (1) {
- pollepd.epd = cdev->epd;
- pollepd.events = EPOLLIN;
-
- /* Drop the mutex before blocking in scif_poll(..) */
- mutex_unlock(&cdev->cosm_mutex);
- /* poll(..) with timeout on our endpoint */
- rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_TIMEOUT_MSEC);
- mutex_lock(&cdev->cosm_mutex);
- if (rc < 0) {
- dev_err(&cdev->dev, "%s %d scif_poll rc %d\n",
- __func__, __LINE__, rc);
- continue;
- }
-
- /* There is a message from the card */
- if (pollepd.revents & EPOLLIN)
- cosm_scif_recv(cdev);
-
- /* The peer endpoint is closed or this endpoint disconnected */
- if (pollepd.revents & EPOLLHUP) {
- cosm_scif_close(cdev);
- break;
- }
-
- /* Did we timeout from poll? */
- if (!rc && cdev->heartbeat_watchdog_enable)
- cosm_set_crashed(cdev);
- }
-exit:
- dev_dbg(&cdev->dev, "%s %d exiting\n", __func__, __LINE__);
- mutex_unlock(&cdev->cosm_mutex);
-}
-
-/*
- * COSM SCIF server thread function. Accepts incoming SCIF connections from MIC
- * cards, finds the correct cosm_device to associate that connection with and
- * schedules individual work items for each MIC card.
- */
-static int cosm_scif_server(void *unused)
-{
- struct cosm_device *cdev;
- scif_epd_t newepd;
- struct scif_port_id port_id;
- int rc;
-
- allow_signal(SIGKILL);
-
- while (!kthread_should_stop()) {
- rc = scif_accept(listen_epd, &port_id, &newepd,
- SCIF_ACCEPT_SYNC);
- if (rc < 0) {
- if (-ERESTARTSYS != rc)
- pr_err("%s %d rc %d\n", __func__, __LINE__, rc);
- continue;
- }
-
- /*
- * Associate the incoming connection with a particular
- * cosm_device, COSM device ID == SCIF node ID - 1
- */
- cdev = cosm_find_cdev_by_id(port_id.node - 1);
- if (!cdev)
- continue;
- cdev->newepd = newepd;
- schedule_work(&cdev->scif_work);
- }
-
- pr_debug("%s %d Server thread stopped\n", __func__, __LINE__);
- return 0;
-}
-
-static int cosm_scif_listen(void)
-{
- int rc;
-
- listen_epd = scif_open();
- if (!listen_epd) {
- pr_err("%s %d scif_open failed\n", __func__, __LINE__);
- return -ENOMEM;
- }
-
- rc = scif_bind(listen_epd, SCIF_COSM_LISTEN_PORT);
- if (rc < 0) {
- pr_err("%s %d scif_bind failed rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
-
- rc = scif_listen(listen_epd, COSM_SCIF_BACKLOG);
- if (rc < 0) {
- pr_err("%s %d scif_listen rc %d\n", __func__, __LINE__, rc);
- goto err;
- }
- pr_debug("%s %d listen_epd set up\n", __func__, __LINE__);
- return 0;
-err:
- scif_close(listen_epd);
- listen_epd = NULL;
- return rc;
-}
-
-static void cosm_scif_listen_exit(void)
-{
- pr_debug("%s %d closing listen_epd\n", __func__, __LINE__);
- if (listen_epd) {
- scif_close(listen_epd);
- listen_epd = NULL;
- }
-}
-
-/*
- * Create a listening SCIF endpoint and a server kthread which accepts incoming
- * SCIF connections from MIC cards
- */
-int cosm_scif_init(void)
-{
- int rc = cosm_scif_listen();
-
- if (rc) {
- pr_err("%s %d cosm_scif_listen rc %d\n",
- __func__, __LINE__, rc);
- goto err;
- }
-
- server_thread = kthread_run(cosm_scif_server, NULL, "cosm_server");
- if (IS_ERR(server_thread)) {
- rc = PTR_ERR(server_thread);
- pr_err("%s %d kthread_run rc %d\n", __func__, __LINE__, rc);
- goto listen_exit;
- }
- return 0;
-listen_exit:
- cosm_scif_listen_exit();
-err:
- return rc;
-}
-
-/* Stop the running server thread and close the listening SCIF endpoint */
-void cosm_scif_exit(void)
-{
- int rc;
-
- if (!IS_ERR_OR_NULL(server_thread)) {
- rc = send_sig(SIGKILL, server_thread, 0);
- if (rc) {
- pr_err("%s %d send_sig rc %d\n",
- __func__, __LINE__, rc);
- return;
- }
- kthread_stop(server_thread);
- }
-
- cosm_scif_listen_exit();
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC Coprocessor State Management (COSM) Driver
- */
-#include <linux/slab.h>
-#include "cosm_main.h"
-
-/*
- * A state-to-string lookup table, for exposing a human readable state
- * via sysfs. Always keep in sync with enum cosm_states
- */
-const char * const cosm_state_string[] = {
- [MIC_READY] = "ready",
- [MIC_BOOTING] = "booting",
- [MIC_ONLINE] = "online",
- [MIC_SHUTTING_DOWN] = "shutting_down",
- [MIC_RESETTING] = "resetting",
- [MIC_RESET_FAILED] = "reset_failed",
-};
-
-/*
- * A shutdown-status-to-string lookup table, for exposing a human
- * readable state via sysfs. Always keep in sync with enum cosm_shutdown_status
- */
-const char * const cosm_shutdown_status_string[] = {
- [MIC_NOP] = "nop",
- [MIC_CRASHED] = "crashed",
- [MIC_HALTED] = "halted",
- [MIC_POWER_OFF] = "poweroff",
- [MIC_RESTART] = "restart",
-};
-
-void cosm_set_shutdown_status(struct cosm_device *cdev, u8 shutdown_status)
-{
- dev_dbg(&cdev->dev, "Shutdown Status %s -> %s\n",
- cosm_shutdown_status_string[cdev->shutdown_status],
- cosm_shutdown_status_string[shutdown_status]);
- cdev->shutdown_status = shutdown_status;
-}
-
-void cosm_set_state(struct cosm_device *cdev, u8 state)
-{
- dev_dbg(&cdev->dev, "State %s -> %s\n",
- cosm_state_string[cdev->state],
- cosm_state_string[state]);
- cdev->state = state;
- sysfs_notify_dirent(cdev->state_sysfs);
-}
-
-static ssize_t
-family_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return cdev->hw_ops->family(cdev, buf);
-}
-static DEVICE_ATTR_RO(family);
-
-static ssize_t
-stepping_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return cdev->hw_ops->stepping(cdev, buf);
-}
-static DEVICE_ATTR_RO(stepping);
-
-static ssize_t
-state_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev || cdev->state >= MIC_LAST)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%s\n",
- cosm_state_string[cdev->state]);
-}
-
-static ssize_t
-state_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int rc;
-
- if (!cdev)
- return -EINVAL;
-
- if (sysfs_streq(buf, "boot")) {
- rc = cosm_start(cdev);
- goto done;
- }
- if (sysfs_streq(buf, "reset")) {
- rc = cosm_reset(cdev);
- goto done;
- }
-
- if (sysfs_streq(buf, "shutdown")) {
- rc = cosm_shutdown(cdev);
- goto done;
- }
- rc = -EINVAL;
-done:
- if (rc)
- count = rc;
- return count;
-}
-static DEVICE_ATTR_RW(state);
-
-static ssize_t shutdown_status_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev || cdev->shutdown_status >= MIC_STATUS_LAST)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%s\n",
- cosm_shutdown_status_string[cdev->shutdown_status]);
-}
-static DEVICE_ATTR_RO(shutdown_status);
-
-static ssize_t
-heartbeat_enable_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%d\n", cdev->sysfs_heartbeat_enable);
-}
-
-static ssize_t
-heartbeat_enable_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int enable;
- int ret;
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- ret = kstrtoint(buf, 10, &enable);
- if (ret)
- goto unlock;
-
- cdev->sysfs_heartbeat_enable = enable;
- /* if state is not online, cdev->heartbeat_watchdog_enable is 0 */
- if (cdev->state == MIC_ONLINE)
- cdev->heartbeat_watchdog_enable = enable;
- ret = count;
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return ret;
-}
-static DEVICE_ATTR_RW(heartbeat_enable);
-
-static ssize_t
-cmdline_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *cmdline;
-
- if (!cdev)
- return -EINVAL;
-
- cmdline = cdev->cmdline;
-
- if (cmdline)
- return scnprintf(buf, PAGE_SIZE, "%s\n", cmdline);
- return 0;
-}
-
-static ssize_t
-cmdline_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->cmdline);
-
- cdev->cmdline = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->cmdline) {
- count = -ENOMEM;
- goto unlock;
- }
-
- strncpy(cdev->cmdline, buf, count);
-
- if (cdev->cmdline[count - 1] == '\n')
- cdev->cmdline[count - 1] = '\0';
- else
- cdev->cmdline[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(cmdline);
-
-static ssize_t
-firmware_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *firmware;
-
- if (!cdev)
- return -EINVAL;
-
- firmware = cdev->firmware;
-
- if (firmware)
- return scnprintf(buf, PAGE_SIZE, "%s\n", firmware);
- return 0;
-}
-
-static ssize_t
-firmware_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->firmware);
-
- cdev->firmware = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->firmware) {
- count = -ENOMEM;
- goto unlock;
- }
- strncpy(cdev->firmware, buf, count);
-
- if (cdev->firmware[count - 1] == '\n')
- cdev->firmware[count - 1] = '\0';
- else
- cdev->firmware[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(firmware);
-
-static ssize_t
-ramdisk_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *ramdisk;
-
- if (!cdev)
- return -EINVAL;
-
- ramdisk = cdev->ramdisk;
-
- if (ramdisk)
- return scnprintf(buf, PAGE_SIZE, "%s\n", ramdisk);
- return 0;
-}
-
-static ssize_t
-ramdisk_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->ramdisk);
-
- cdev->ramdisk = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->ramdisk) {
- count = -ENOMEM;
- goto unlock;
- }
-
- strncpy(cdev->ramdisk, buf, count);
-
- if (cdev->ramdisk[count - 1] == '\n')
- cdev->ramdisk[count - 1] = '\0';
- else
- cdev->ramdisk[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(ramdisk);
-
-static ssize_t
-bootmode_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- char *bootmode;
-
- if (!cdev)
- return -EINVAL;
-
- bootmode = cdev->bootmode;
-
- if (bootmode)
- return scnprintf(buf, PAGE_SIZE, "%s\n", bootmode);
- return 0;
-}
-
-static ssize_t
-bootmode_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- if (!sysfs_streq(buf, "linux") && !sysfs_streq(buf, "flash"))
- return -EINVAL;
-
- mutex_lock(&cdev->cosm_mutex);
- kfree(cdev->bootmode);
-
- cdev->bootmode = kmalloc(count + 1, GFP_KERNEL);
- if (!cdev->bootmode) {
- count = -ENOMEM;
- goto unlock;
- }
-
- strncpy(cdev->bootmode, buf, count);
-
- if (cdev->bootmode[count - 1] == '\n')
- cdev->bootmode[count - 1] = '\0';
- else
- cdev->bootmode[count] = '\0';
-unlock:
- mutex_unlock(&cdev->cosm_mutex);
- return count;
-}
-static DEVICE_ATTR_RW(bootmode);
-
-static ssize_t
-log_buf_addr_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%p\n", cdev->log_buf_addr);
-}
-
-static ssize_t
-log_buf_addr_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int ret;
- unsigned long addr;
-
- if (!cdev)
- return -EINVAL;
-
- ret = kstrtoul(buf, 16, &addr);
- if (ret)
- goto exit;
-
- cdev->log_buf_addr = (void *)addr;
- ret = count;
-exit:
- return ret;
-}
-static DEVICE_ATTR_RW(log_buf_addr);
-
-static ssize_t
-log_buf_len_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
-
- if (!cdev)
- return -EINVAL;
-
- return scnprintf(buf, PAGE_SIZE, "%p\n", cdev->log_buf_len);
-}
-
-static ssize_t
-log_buf_len_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cosm_device *cdev = dev_get_drvdata(dev);
- int ret;
- unsigned long addr;
-
- if (!cdev)
- return -EINVAL;
-
- ret = kstrtoul(buf, 16, &addr);
- if (ret)
- goto exit;
-
- cdev->log_buf_len = (int *)addr;
- ret = count;
-exit:
- return ret;
-}
-static DEVICE_ATTR_RW(log_buf_len);
-
-static struct attribute *cosm_default_attrs[] = {
- &dev_attr_family.attr,
- &dev_attr_stepping.attr,
- &dev_attr_state.attr,
- &dev_attr_shutdown_status.attr,
- &dev_attr_heartbeat_enable.attr,
- &dev_attr_cmdline.attr,
- &dev_attr_firmware.attr,
- &dev_attr_ramdisk.attr,
- &dev_attr_bootmode.attr,
- &dev_attr_log_buf_addr.attr,
- &dev_attr_log_buf_len.attr,
-
- NULL
-};
-
-ATTRIBUTE_GROUPS(cosm_default);
-
-void cosm_sysfs_init(struct cosm_device *cdev)
-{
- cdev->attr_group = cosm_default_groups;
-}
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC COSM Client Driver
-# Copyright(c) 2015, Intel Corporation.
-#
-obj-$(CONFIG_MIC_COSM) += cosm_client.o
-
-cosm_client-objs += cosm_scif_client.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel MIC COSM Client Driver
- */
-#include <linux/module.h>
-#include <linux/delay.h>
-#include <linux/reboot.h>
-#include <linux/kthread.h>
-#include <linux/sched/signal.h>
-
-#include "../cosm/cosm_main.h"
-
-#define COSM_SCIF_MAX_RETRIES 10
-#define COSM_HEARTBEAT_SEND_MSEC (COSM_HEARTBEAT_SEND_SEC * MSEC_PER_SEC)
-
-static struct task_struct *client_thread;
-static scif_epd_t client_epd;
-static struct scif_peer_dev *client_spdev;
-
-/*
- * Reboot notifier: receives shutdown status from the OS and communicates it
- * back to the COSM process on the host
- */
-static int cosm_reboot_event(struct notifier_block *this, unsigned long event,
- void *ptr)
-{
- struct cosm_msg msg = { .id = COSM_MSG_SHUTDOWN_STATUS };
- int rc;
-
- event = (event == SYS_RESTART) ? SYSTEM_RESTART : event;
- dev_info(&client_spdev->dev, "%s %d received event %ld\n",
- __func__, __LINE__, event);
-
- msg.shutdown_status = event;
- rc = scif_send(client_epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0)
- dev_err(&client_spdev->dev, "%s %d scif_send rc %d\n",
- __func__, __LINE__, rc);
-
- return NOTIFY_DONE;
-}
-
-static struct notifier_block cosm_reboot = {
- .notifier_call = cosm_reboot_event,
-};
-
-/* Set system time from timespec value received from the host */
-static void cosm_set_time(struct cosm_msg *msg)
-{
- struct timespec64 ts = {
- .tv_sec = msg->timespec.tv_sec,
- .tv_nsec = msg->timespec.tv_nsec,
- };
- int rc = do_settimeofday64(&ts);
-
- if (rc)
- dev_err(&client_spdev->dev, "%s: %d settimeofday rc %d\n",
- __func__, __LINE__, rc);
-}
-
-/* COSM client receive message processing */
-static void cosm_client_recv(void)
-{
- struct cosm_msg msg;
- int rc;
-
- while (1) {
- rc = scif_recv(client_epd, &msg, sizeof(msg), 0);
- if (!rc) {
- return;
- } else if (rc < 0) {
- dev_err(&client_spdev->dev, "%s: %d rc %d\n",
- __func__, __LINE__, rc);
- return;
- }
-
- dev_dbg(&client_spdev->dev, "%s: %d rc %d id 0x%llx\n",
- __func__, __LINE__, rc, msg.id);
-
- switch (msg.id) {
- case COSM_MSG_SYNC_TIME:
- cosm_set_time(&msg);
- break;
- case COSM_MSG_SHUTDOWN:
- orderly_poweroff(true);
- break;
- default:
- dev_err(&client_spdev->dev, "%s: %d unknown id %lld\n",
- __func__, __LINE__, msg.id);
- break;
- }
- }
-}
-
-/* Initiate connection to the COSM server on the host */
-static int cosm_scif_connect(void)
-{
- struct scif_port_id port_id;
- int i, rc;
-
- client_epd = scif_open();
- if (!client_epd) {
- dev_err(&client_spdev->dev, "%s %d scif_open failed\n",
- __func__, __LINE__);
- return -ENOMEM;
- }
-
- port_id.node = 0;
- port_id.port = SCIF_COSM_LISTEN_PORT;
-
- for (i = 0; i < COSM_SCIF_MAX_RETRIES; i++) {
- rc = scif_connect(client_epd, &port_id);
- if (rc < 0)
- msleep(1000);
- else
- break;
- }
-
- if (rc < 0) {
- dev_err(&client_spdev->dev, "%s %d scif_connect rc %d\n",
- __func__, __LINE__, rc);
- scif_close(client_epd);
- client_epd = NULL;
- }
- return rc < 0 ? rc : 0;
-}
-
-/* Close host SCIF connection */
-static void cosm_scif_connect_exit(void)
-{
- if (client_epd) {
- scif_close(client_epd);
- client_epd = NULL;
- }
-}
-
-/*
- * COSM SCIF client thread function: waits for messages from the host and sends
- * a heartbeat to the host
- */
-static int cosm_scif_client(void *unused)
-{
- struct cosm_msg msg = { .id = COSM_MSG_HEARTBEAT };
- struct scif_pollepd pollepd;
- int rc;
-
- allow_signal(SIGKILL);
-
- while (!kthread_should_stop()) {
- pollepd.epd = client_epd;
- pollepd.events = EPOLLIN;
-
- rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_SEND_MSEC);
- if (rc < 0) {
- if (-EINTR != rc)
- dev_err(&client_spdev->dev,
- "%s %d scif_poll rc %d\n",
- __func__, __LINE__, rc);
- continue;
- }
-
- if (pollepd.revents & EPOLLIN)
- cosm_client_recv();
-
- msg.id = COSM_MSG_HEARTBEAT;
- rc = scif_send(client_epd, &msg, sizeof(msg), SCIF_SEND_BLOCK);
- if (rc < 0)
- dev_err(&client_spdev->dev, "%s %d scif_send rc %d\n",
- __func__, __LINE__, rc);
- }
-
- dev_dbg(&client_spdev->dev, "%s %d Client thread stopped\n",
- __func__, __LINE__);
- return 0;
-}
-
-static void cosm_scif_probe(struct scif_peer_dev *spdev)
-{
- int rc;
-
- dev_dbg(&spdev->dev, "%s %d: dnode %d\n",
- __func__, __LINE__, spdev->dnode);
-
- /* We are only interested in the host with spdev->dnode == 0 */
- if (spdev->dnode)
- return;
-
- client_spdev = spdev;
- rc = cosm_scif_connect();
- if (rc)
- goto exit;
-
- rc = register_reboot_notifier(&cosm_reboot);
- if (rc) {
- dev_err(&spdev->dev,
- "reboot notifier registration failed rc %d\n", rc);
- goto connect_exit;
- }
-
- client_thread = kthread_run(cosm_scif_client, NULL, "cosm_client");
- if (IS_ERR(client_thread)) {
- rc = PTR_ERR(client_thread);
- dev_err(&spdev->dev, "%s %d kthread_run rc %d\n",
- __func__, __LINE__, rc);
- goto unreg_reboot;
- }
- return;
-unreg_reboot:
- unregister_reboot_notifier(&cosm_reboot);
-connect_exit:
- cosm_scif_connect_exit();
-exit:
- client_spdev = NULL;
-}
-
-static void cosm_scif_remove(struct scif_peer_dev *spdev)
-{
- int rc;
-
- dev_dbg(&spdev->dev, "%s %d: dnode %d\n",
- __func__, __LINE__, spdev->dnode);
-
- if (spdev->dnode)
- return;
-
- if (!IS_ERR_OR_NULL(client_thread)) {
- rc = send_sig(SIGKILL, client_thread, 0);
- if (rc) {
- pr_err("%s %d send_sig rc %d\n",
- __func__, __LINE__, rc);
- return;
- }
- kthread_stop(client_thread);
- }
- unregister_reboot_notifier(&cosm_reboot);
- cosm_scif_connect_exit();
- client_spdev = NULL;
-}
-
-static struct scif_client scif_client_cosm = {
- .name = KBUILD_MODNAME,
- .probe = cosm_scif_probe,
- .remove = cosm_scif_remove,
-};
-
-static int __init cosm_client_init(void)
-{
- int rc = scif_client_register(&scif_client_cosm);
-
- if (rc)
- pr_err("scif_client_register failed rc %d\n", rc);
- return rc;
-}
-
-static void __exit cosm_client_exit(void)
-{
- scif_client_unregister(&scif_client_cosm);
-}
-
-module_init(cosm_client_init);
-module_exit(cosm_client_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC card OS state management client driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2013, Intel Corporation.
-#
-obj-$(CONFIG_INTEL_MIC_HOST) += mic_host.o
-mic_host-objs := mic_main.o
-mic_host-objs += mic_x100.o
-mic_host-objs += mic_smpt.o
-mic_host-objs += mic_intr.o
-mic_host-objs += mic_boot.o
-mic_host-objs += mic_debugfs.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/delay.h>
-#include <linux/firmware.h>
-#include <linux/pci.h>
-#include <linux/kmod.h>
-#include <linux/dma-map-ops.h>
-#include <linux/mic_common.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-static inline struct mic_device *vpdev_to_mdev(struct device *dev)
-{
- return dev_get_drvdata(dev->parent);
-}
-
-static dma_addr_t
-_mic_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir, unsigned long attrs)
-{
- void *va = phys_to_virt(page_to_phys(page)) + offset;
- struct mic_device *mdev = vpdev_to_mdev(dev);
-
- return mic_map_single(mdev, va, size);
-}
-
-static void _mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct mic_device *mdev = vpdev_to_mdev(dev);
-
- mic_unmap_single(mdev, dma_addr, size);
-}
-
-static const struct dma_map_ops _mic_dma_ops = {
- .map_page = _mic_dma_map_page,
- .unmap_page = _mic_dma_unmap_page,
-};
-
-static struct mic_irq *
-__mic_request_irq(struct vop_device *vpdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name, void *data, int intr_src)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mic_request_threaded_irq(mdev, func, NULL, name, data,
- intr_src, MIC_INTR_DB);
-}
-
-static void __mic_free_irq(struct vop_device *vpdev,
- struct mic_irq *cookie, void *data)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- mic_free_irq(mdev, cookie, data);
-}
-
-static void __mic_ack_interrupt(struct vop_device *vpdev, int num)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- mdev->ops->intr_workarounds(mdev);
-}
-
-static int __mic_next_db(struct vop_device *vpdev)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mic_next_db(mdev);
-}
-
-static void *__mic_get_dp(struct vop_device *vpdev)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mdev->dp;
-}
-
-static void __iomem *__mic_get_remote_dp(struct vop_device *vpdev)
-{
- return NULL;
-}
-
-static void __mic_send_intr(struct vop_device *vpdev, int db)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- mdev->ops->send_intr(mdev, db);
-}
-
-static void __iomem *__mic_ioremap(struct vop_device *vpdev,
- dma_addr_t pa, size_t len)
-{
- struct mic_device *mdev = vpdev_to_mdev(&vpdev->dev);
-
- return mdev->aper.va + pa;
-}
-
-static void __mic_iounmap(struct vop_device *vpdev, void __iomem *va)
-{
- /* nothing to do */
-}
-
-static struct vop_hw_ops vop_hw_ops = {
- .request_irq = __mic_request_irq,
- .free_irq = __mic_free_irq,
- .ack_interrupt = __mic_ack_interrupt,
- .next_db = __mic_next_db,
- .get_dp = __mic_get_dp,
- .get_remote_dp = __mic_get_remote_dp,
- .send_intr = __mic_send_intr,
- .remap = __mic_ioremap,
- .unmap = __mic_iounmap,
-};
-
-static inline struct mic_device *scdev_to_mdev(struct scif_hw_dev *scdev)
-{
- return dev_get_drvdata(scdev->dev.parent);
-}
-
-static void *__mic_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t gfp,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
- dma_addr_t tmp;
- void *va = kzalloc(size, gfp);
-
- if (va) {
- tmp = mic_map_single(mdev, va, size);
- if (dma_mapping_error(dev, tmp)) {
- kfree(va);
- va = NULL;
- } else {
- *dma_handle = tmp;
- }
- }
- return va;
-}
-
-static void __mic_dma_free(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_handle, unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mic_unmap_single(mdev, dma_handle, size);
- kfree(vaddr);
-}
-
-static dma_addr_t
-__mic_dma_map_page(struct device *dev, struct page *page, unsigned long offset,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- void *va = phys_to_virt(page_to_phys(page)) + offset;
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mic_map_single(mdev, va, size);
-}
-
-static void
-__mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mic_unmap_single(mdev, dma_addr, size);
-}
-
-static int __mic_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
- struct scatterlist *s;
- int i, j, ret;
- dma_addr_t da;
-
- ret = dma_map_sg(&mdev->pdev->dev, sg, nents, dir);
- if (ret <= 0)
- return 0;
-
- for_each_sg(sg, s, nents, i) {
- da = mic_map(mdev, sg_dma_address(s) + s->offset, s->length);
- if (!da)
- goto err;
- sg_dma_address(s) = da;
- }
- return nents;
-err:
- for_each_sg(sg, s, i, j) {
- mic_unmap(mdev, sg_dma_address(s), s->length);
- sg_dma_address(s) = mic_to_dma_addr(mdev, sg_dma_address(s));
- }
- dma_unmap_sg(&mdev->pdev->dev, sg, nents, dir);
- return 0;
-}
-
-static void __mic_dma_unmap_sg(struct device *dev,
- struct scatterlist *sg, int nents,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scif_hw_dev *scdev = dev_get_drvdata(dev);
- struct mic_device *mdev = scdev_to_mdev(scdev);
- struct scatterlist *s;
- dma_addr_t da;
- int i;
-
- for_each_sg(sg, s, nents, i) {
- da = mic_to_dma_addr(mdev, sg_dma_address(s));
- mic_unmap(mdev, sg_dma_address(s), s->length);
- sg_dma_address(s) = da;
- }
- dma_unmap_sg(&mdev->pdev->dev, sg, nents, dir);
-}
-
-static const struct dma_map_ops __mic_dma_ops = {
- .alloc = __mic_dma_alloc,
- .free = __mic_dma_free,
- .map_page = __mic_dma_map_page,
- .unmap_page = __mic_dma_unmap_page,
- .map_sg = __mic_dma_map_sg,
- .unmap_sg = __mic_dma_unmap_sg,
-};
-
-static struct mic_irq *
-___mic_request_irq(struct scif_hw_dev *scdev,
- irqreturn_t (*func)(int irq, void *data),
- const char *name,
- void *data, int db)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mic_request_threaded_irq(mdev, func, NULL, name, data,
- db, MIC_INTR_DB);
-}
-
-static void
-___mic_free_irq(struct scif_hw_dev *scdev,
- struct mic_irq *cookie, void *data)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mic_free_irq(mdev, cookie, data);
-}
-
-static void ___mic_ack_interrupt(struct scif_hw_dev *scdev, int num)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mdev->ops->intr_workarounds(mdev);
-}
-
-static int ___mic_next_db(struct scif_hw_dev *scdev)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mic_next_db(mdev);
-}
-
-static void ___mic_send_intr(struct scif_hw_dev *scdev, int db)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- mdev->ops->send_intr(mdev, db);
-}
-
-static void __iomem *___mic_ioremap(struct scif_hw_dev *scdev,
- phys_addr_t pa, size_t len)
-{
- struct mic_device *mdev = scdev_to_mdev(scdev);
-
- return mdev->aper.va + pa;
-}
-
-static void ___mic_iounmap(struct scif_hw_dev *scdev, void __iomem *va)
-{
- /* nothing to do */
-}
-
-static struct scif_hw_ops scif_hw_ops = {
- .request_irq = ___mic_request_irq,
- .free_irq = ___mic_free_irq,
- .ack_interrupt = ___mic_ack_interrupt,
- .next_db = ___mic_next_db,
- .send_intr = ___mic_send_intr,
- .remap = ___mic_ioremap,
- .unmap = ___mic_iounmap,
-};
-
-static inline struct mic_device *mbdev_to_mdev(struct mbus_device *mbdev)
-{
- return dev_get_drvdata(mbdev->dev.parent);
-}
-
-static dma_addr_t
-mic_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- void *va = phys_to_virt(page_to_phys(page)) + offset;
- struct mic_device *mdev = dev_get_drvdata(dev->parent);
-
- return mic_map_single(mdev, va, size);
-}
-
-static void
-mic_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct mic_device *mdev = dev_get_drvdata(dev->parent);
- mic_unmap_single(mdev, dma_addr, size);
-}
-
-static const struct dma_map_ops mic_dma_ops = {
- .map_page = mic_dma_map_page,
- .unmap_page = mic_dma_unmap_page,
-};
-
-static struct mic_irq *
-_mic_request_threaded_irq(struct mbus_device *mbdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src)
-{
- return mic_request_threaded_irq(mbdev_to_mdev(mbdev), handler,
- thread_fn, name, data,
- intr_src, MIC_INTR_DMA);
-}
-
-static void _mic_free_irq(struct mbus_device *mbdev,
- struct mic_irq *cookie, void *data)
-{
- mic_free_irq(mbdev_to_mdev(mbdev), cookie, data);
-}
-
-static void _mic_ack_interrupt(struct mbus_device *mbdev, int num)
-{
- struct mic_device *mdev = mbdev_to_mdev(mbdev);
- mdev->ops->intr_workarounds(mdev);
-}
-
-static struct mbus_hw_ops mbus_hw_ops = {
- .request_threaded_irq = _mic_request_threaded_irq,
- .free_irq = _mic_free_irq,
- .ack_interrupt = _mic_ack_interrupt,
-};
-
-/* Initialize the MIC bootparams */
-void mic_bootparam_init(struct mic_device *mdev)
-{
- struct mic_bootparam *bootparam = mdev->dp;
-
- bootparam->magic = cpu_to_le32(MIC_MAGIC);
- bootparam->h2c_config_db = -1;
- bootparam->node_id = mdev->id + 1;
- bootparam->scif_host_dma_addr = 0x0;
- bootparam->scif_card_dma_addr = 0x0;
- bootparam->c2h_scif_db = -1;
- bootparam->h2c_scif_db = -1;
-}
-
-static inline struct mic_device *cosmdev_to_mdev(struct cosm_device *cdev)
-{
- return dev_get_drvdata(cdev->dev.parent);
-}
-
-static void _mic_reset(struct cosm_device *cdev)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- mdev->ops->reset_fw_ready(mdev);
- mdev->ops->reset(mdev);
-}
-
-static bool _mic_ready(struct cosm_device *cdev)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- return mdev->ops->is_fw_ready(mdev);
-}
-
-/**
- * mic_request_dma_chans - Request DMA channels
- * @mdev: pointer to mic_device instance
- *
- * returns number of DMA channels acquired
- */
-static int mic_request_dma_chans(struct mic_device *mdev)
-{
- dma_cap_mask_t mask;
- struct dma_chan *chan;
-
- dma_cap_zero(mask);
- dma_cap_set(DMA_MEMCPY, mask);
-
- do {
- chan = dma_request_channel(mask, mdev->ops->dma_filter,
- &mdev->pdev->dev);
- if (chan) {
- mdev->dma_ch[mdev->num_dma_ch++] = chan;
- if (mdev->num_dma_ch >= MIC_MAX_DMA_CHAN)
- break;
- }
- } while (chan);
- dev_info(&mdev->pdev->dev, "DMA channels # %d\n", mdev->num_dma_ch);
- return mdev->num_dma_ch;
-}
-
-/**
- * mic_free_dma_chans - release DMA channels
- * @mdev: pointer to mic_device instance
- *
- * returns none
- */
-static void mic_free_dma_chans(struct mic_device *mdev)
-{
- int i = 0;
-
- for (i = 0; i < mdev->num_dma_ch; i++) {
- dma_release_channel(mdev->dma_ch[i]);
- mdev->dma_ch[i] = NULL;
- }
- mdev->num_dma_ch = 0;
-}
-
-/**
- * _mic_start - Start the MIC.
- * @cdev: pointer to cosm_device instance
- * @id: MIC device id/index provided by COSM used in other drivers like SCIF
- *
- * This function prepares an MIC for boot and initiates boot.
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- *
- * For all cosm_hw_ops the caller holds a mutex to ensure serialization.
- */
-static int _mic_start(struct cosm_device *cdev, int id)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
- int rc;
-
- mic_bootparam_init(mdev);
- mdev->dma_mbdev = mbus_register_device(&mdev->pdev->dev,
- MBUS_DEV_DMA_HOST, &mic_dma_ops,
- &mbus_hw_ops, id, mdev->mmio.va);
- if (IS_ERR(mdev->dma_mbdev)) {
- rc = PTR_ERR(mdev->dma_mbdev);
- goto unlock_ret;
- }
- if (!mic_request_dma_chans(mdev)) {
- rc = -ENODEV;
- goto dma_remove;
- }
- mdev->scdev = scif_register_device(&mdev->pdev->dev, MIC_SCIF_DEV,
- &__mic_dma_ops, &scif_hw_ops,
- id + 1, 0, &mdev->mmio,
- &mdev->aper, mdev->dp, NULL,
- mdev->dma_ch, mdev->num_dma_ch,
- true);
- if (IS_ERR(mdev->scdev)) {
- rc = PTR_ERR(mdev->scdev);
- goto dma_free;
- }
-
- mdev->vpdev = vop_register_device(&mdev->pdev->dev,
- VOP_DEV_TRNSP, &_mic_dma_ops,
- &vop_hw_ops, id + 1, &mdev->aper,
- mdev->dma_ch[0]);
- if (IS_ERR(mdev->vpdev)) {
- rc = PTR_ERR(mdev->vpdev);
- goto scif_remove;
- }
-
- rc = mdev->ops->load_mic_fw(mdev, NULL);
- if (rc)
- goto vop_remove;
- mic_smpt_restore(mdev);
- mic_intr_restore(mdev);
- mdev->intr_ops->enable_interrupts(mdev);
- mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
- mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
- mdev->ops->send_firmware_intr(mdev);
- goto unlock_ret;
-vop_remove:
- vop_unregister_device(mdev->vpdev);
-scif_remove:
- scif_unregister_device(mdev->scdev);
-dma_free:
- mic_free_dma_chans(mdev);
-dma_remove:
- mbus_unregister_device(mdev->dma_mbdev);
-unlock_ret:
- return rc;
-}
-
-/**
- * _mic_stop - Prepare the MIC for reset and trigger reset.
- * @cdev: pointer to cosm_device instance
- * @force: force a MIC to reset even if it is already offline.
- *
- * RETURNS: None.
- */
-static void _mic_stop(struct cosm_device *cdev, bool force)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- /*
- * Since SCIF handles card shutdown and reset (using COSM), it will
- * will be the first to be registered and the last to be
- * unregistered.
- */
- vop_unregister_device(mdev->vpdev);
- scif_unregister_device(mdev->scdev);
- mic_free_dma_chans(mdev);
- mbus_unregister_device(mdev->dma_mbdev);
- mic_bootparam_init(mdev);
-}
-
-static ssize_t _mic_family(struct cosm_device *cdev, char *buf)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
- static const char *family[MIC_FAMILY_LAST] = { "x100", "Unknown" };
-
- return scnprintf(buf, PAGE_SIZE, "%s\n", family[mdev->family]);
-}
-
-static ssize_t _mic_stepping(struct cosm_device *cdev, char *buf)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
- const char *string = "??";
-
- switch (mdev->stepping) {
- case MIC_A0_STEP:
- string = "A0";
- break;
- case MIC_B0_STEP:
- string = "B0";
- break;
- case MIC_B1_STEP:
- string = "B1";
- break;
- case MIC_C0_STEP:
- string = "C0";
- break;
- default:
- break;
- }
- return scnprintf(buf, PAGE_SIZE, "%s\n", string);
-}
-
-static struct mic_mw *_mic_aper(struct cosm_device *cdev)
-{
- struct mic_device *mdev = cosmdev_to_mdev(cdev);
-
- return &mdev->aper;
-}
-
-struct cosm_hw_ops cosm_hw_ops = {
- .reset = _mic_reset,
- .force_reset = _mic_reset,
- .post_reset = NULL,
- .ready = _mic_ready,
- .start = _mic_start,
- .stop = _mic_stop,
- .family = _mic_family,
- .stepping = _mic_stepping,
- .aper = _mic_aper,
-};
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/debugfs.h>
-#include <linux/pci.h>
-#include <linux/seq_file.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-/* Debugfs parent dir */
-static struct dentry *mic_dbg;
-
-static int mic_smpt_show(struct seq_file *s, void *pos)
-{
- int i;
- struct mic_device *mdev = s->private;
- unsigned long flags;
-
- seq_printf(s, "MIC %-2d |%-10s| %-14s %-10s\n",
- mdev->id, "SMPT entry", "SW DMA addr", "RefCount");
- seq_puts(s, "====================================================\n");
-
- if (mdev->smpt) {
- struct mic_smpt_info *smpt_info = mdev->smpt;
- spin_lock_irqsave(&smpt_info->smpt_lock, flags);
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- seq_printf(s, "%9s|%-10d| %-#14llx %-10lld\n",
- " ", i, smpt_info->entry[i].dma_addr,
- smpt_info->entry[i].ref_count);
- }
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- }
- seq_puts(s, "====================================================\n");
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_smpt);
-
-static int mic_post_code_show(struct seq_file *s, void *pos)
-{
- struct mic_device *mdev = s->private;
- u32 reg = mdev->ops->get_postcode(mdev);
-
- seq_printf(s, "%c%c", reg & 0xff, (reg >> 8) & 0xff);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_post_code);
-
-static int mic_msi_irq_info_show(struct seq_file *s, void *pos)
-{
- struct mic_device *mdev = s->private;
- int reg;
- int i, j;
- u16 entry;
- u16 vector;
- struct pci_dev *pdev = mdev->pdev;
-
- if (pci_dev_msi_enabled(pdev)) {
- for (i = 0; i < mdev->irq_info.num_vectors; i++) {
- if (pdev->msix_enabled) {
- entry = mdev->irq_info.msix_entries[i].entry;
- vector = mdev->irq_info.msix_entries[i].vector;
- } else {
- entry = 0;
- vector = pdev->irq;
- }
-
- reg = mdev->intr_ops->read_msi_to_src_map(mdev, entry);
-
- seq_printf(s, "%s %-10d %s %-10d MXAR[%d]: %08X\n",
- "IRQ:", vector, "Entry:", entry, i, reg);
-
- seq_printf(s, "%-10s", "offset:");
- for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
- seq_printf(s, "%4d ", j);
- seq_puts(s, "\n");
-
-
- seq_printf(s, "%-10s", "count:");
- for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--)
- seq_printf(s, "%4d ",
- (mdev->irq_info.mic_msi_map[i] &
- BIT(j)) ? 1 : 0);
- seq_puts(s, "\n\n");
- }
- } else {
- seq_puts(s, "MSI/MSIx interrupts not enabled\n");
- }
-
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(mic_msi_irq_info);
-
-/*
- * mic_create_debug_dir - Initialize MIC debugfs entries.
- */
-void mic_create_debug_dir(struct mic_device *mdev)
-{
- char name[16];
-
- if (!mic_dbg)
- return;
-
- scnprintf(name, sizeof(name), "mic%d", mdev->id);
- mdev->dbg_dir = debugfs_create_dir(name, mic_dbg);
-
- debugfs_create_file("smpt", 0444, mdev->dbg_dir, mdev,
- &mic_smpt_fops);
-
- debugfs_create_file("post_code", 0444, mdev->dbg_dir, mdev,
- &mic_post_code_fops);
-
- debugfs_create_file("msi_irq_info", 0444, mdev->dbg_dir, mdev,
- &mic_msi_irq_info_fops);
-}
-
-/*
- * mic_delete_debug_dir - Uninitialize MIC debugfs entries.
- */
-void mic_delete_debug_dir(struct mic_device *mdev)
-{
- debugfs_remove_recursive(mdev->dbg_dir);
-}
-
-/*
- * mic_init_debugfs - Initialize global debugfs entry.
- */
-void __init mic_init_debugfs(void)
-{
- mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-}
-
-/*
- * mic_exit_debugfs - Uninitialize global debugfs entry
- */
-void mic_exit_debugfs(void)
-{
- debugfs_remove(mic_dbg);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_DEVICE_H_
-#define _MIC_DEVICE_H_
-
-#include <linux/cdev.h>
-#include <linux/idr.h>
-#include <linux/notifier.h>
-#include <linux/irqreturn.h>
-#include <linux/dmaengine.h>
-#include <linux/miscdevice.h>
-#include <linux/mic_bus.h>
-#include "../bus/scif_bus.h"
-#include "../bus/vop_bus.h"
-#include "../bus/cosm_bus.h"
-#include "mic_intr.h"
-
-/**
- * enum mic_stepping - MIC stepping ids.
- */
-enum mic_stepping {
- MIC_A0_STEP = 0x0,
- MIC_B0_STEP = 0x10,
- MIC_B1_STEP = 0x11,
- MIC_C0_STEP = 0x20,
-};
-
-extern struct cosm_hw_ops cosm_hw_ops;
-
-/**
- * struct mic_device - MIC device information for each card.
- *
- * @mmio: MMIO bar information.
- * @aper: Aperture bar information.
- * @family: The MIC family to which this device belongs.
- * @ops: MIC HW specific operations.
- * @id: The unique device id for this MIC device.
- * @stepping: Stepping ID.
- * @pdev: Underlying PCI device.
- * @mic_mutex: Mutex for synchronizing access to mic_device.
- * @intr_ops: HW specific interrupt operations.
- * @smpt_ops: Hardware specific SMPT operations.
- * @smpt: MIC SMPT information.
- * @intr_info: H/W specific interrupt information.
- * @irq_info: The OS specific irq information
- * @dbg_dir: debugfs directory of this MIC device.
- * @bootaddr: MIC boot address.
- * @dp: virtio device page
- * @dp_dma_addr: virtio device page DMA address.
- * @dma_mbdev: MIC BUS DMA device.
- * @dma_ch - Array of DMA channels
- * @num_dma_ch - Number of DMA channels available
- * @scdev: SCIF device on the SCIF virtual bus.
- * @vpdev: Virtio over PCIe device on the VOP virtual bus.
- * @cosm_dev: COSM device
- */
-struct mic_device {
- struct mic_mw mmio;
- struct mic_mw aper;
- enum mic_hw_family family;
- struct mic_hw_ops *ops;
- int id;
- enum mic_stepping stepping;
- struct pci_dev *pdev;
- struct mutex mic_mutex;
- struct mic_hw_intr_ops *intr_ops;
- struct mic_smpt_ops *smpt_ops;
- struct mic_smpt_info *smpt;
- struct mic_intr_info *intr_info;
- struct mic_irq_info irq_info;
- struct dentry *dbg_dir;
- u32 bootaddr;
- void *dp;
- dma_addr_t dp_dma_addr;
- struct mbus_device *dma_mbdev;
- struct dma_chan *dma_ch[MIC_MAX_DMA_CHAN];
- int num_dma_ch;
- struct scif_hw_dev *scdev;
- struct vop_device *vpdev;
- struct cosm_device *cosm_dev;
-};
-
-/**
- * struct mic_hw_ops - MIC HW specific operations.
- * @aper_bar: Aperture bar resource number.
- * @mmio_bar: MMIO bar resource number.
- * @read_spad: Read from scratch pad register.
- * @write_spad: Write to scratch pad register.
- * @send_intr: Send an interrupt for a particular doorbell on the card.
- * @ack_interrupt: Hardware specific operations to ack the h/w on
- * receipt of an interrupt.
- * @intr_workarounds: Hardware specific workarounds needed after
- * handling an interrupt.
- * @reset: Reset the remote processor.
- * @reset_fw_ready: Reset firmware ready field.
- * @is_fw_ready: Check if firmware is ready for OS download.
- * @send_firmware_intr: Send an interrupt to the card firmware.
- * @load_mic_fw: Load firmware segments required to boot the card
- * into card memory. This includes the kernel, command line, ramdisk etc.
- * @get_postcode: Get post code status from firmware.
- * @dma_filter: DMA filter function to be used.
- */
-struct mic_hw_ops {
- u8 aper_bar;
- u8 mmio_bar;
- u32 (*read_spad)(struct mic_device *mdev, unsigned int idx);
- void (*write_spad)(struct mic_device *mdev, unsigned int idx, u32 val);
- void (*send_intr)(struct mic_device *mdev, int doorbell);
- u32 (*ack_interrupt)(struct mic_device *mdev);
- void (*intr_workarounds)(struct mic_device *mdev);
- void (*reset)(struct mic_device *mdev);
- void (*reset_fw_ready)(struct mic_device *mdev);
- bool (*is_fw_ready)(struct mic_device *mdev);
- void (*send_firmware_intr)(struct mic_device *mdev);
- int (*load_mic_fw)(struct mic_device *mdev, const char *buf);
- u32 (*get_postcode)(struct mic_device *mdev);
- bool (*dma_filter)(struct dma_chan *chan, void *param);
-};
-
-/**
- * mic_mmio_read - read from an MMIO register.
- * @mw: MMIO register base virtual address.
- * @offset: register offset.
- *
- * RETURNS: register value.
- */
-static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset)
-{
- return ioread32(mw->va + offset);
-}
-
-/**
- * mic_mmio_write - write to an MMIO register.
- * @mw: MMIO register base virtual address.
- * @val: the data value to put into the register
- * @offset: register offset.
- *
- * RETURNS: none.
- */
-static inline void
-mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset)
-{
- iowrite32(val, mw->va + offset);
-}
-
-void mic_bootparam_init(struct mic_device *mdev);
-void mic_create_debug_dir(struct mic_device *dev);
-void mic_delete_debug_dir(struct mic_device *dev);
-void __init mic_init_debugfs(void);
-void mic_exit_debugfs(void);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/pci.h>
-#include <linux/interrupt.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-
-static irqreturn_t mic_thread_fn(int irq, void *dev)
-{
- struct mic_device *mdev = dev;
- struct mic_intr_info *intr_info = mdev->intr_info;
- struct mic_irq_info *irq_info = &mdev->irq_info;
- struct mic_intr_cb *intr_cb;
- struct pci_dev *pdev = mdev->pdev;
- int i;
-
- spin_lock(&irq_info->mic_thread_lock);
- for (i = intr_info->intr_start_idx[MIC_INTR_DB];
- i < intr_info->intr_len[MIC_INTR_DB]; i++)
- if (test_and_clear_bit(i, &irq_info->mask)) {
- list_for_each_entry(intr_cb, &irq_info->cb_list[i],
- list)
- if (intr_cb->thread_fn)
- intr_cb->thread_fn(pdev->irq,
- intr_cb->data);
- }
- spin_unlock(&irq_info->mic_thread_lock);
- return IRQ_HANDLED;
-}
-/**
- * mic_interrupt - Generic interrupt handler for
- * MSI and INTx based interrupts.
- * @irq: interrupt to handle (unused)
- * @dev: pointer to the mic_device instance
- */
-static irqreturn_t mic_interrupt(int irq, void *dev)
-{
- struct mic_device *mdev = dev;
- struct mic_intr_info *intr_info = mdev->intr_info;
- struct mic_irq_info *irq_info = &mdev->irq_info;
- struct mic_intr_cb *intr_cb;
- struct pci_dev *pdev = mdev->pdev;
- u32 mask;
- int i;
-
- mask = mdev->ops->ack_interrupt(mdev);
- if (!mask)
- return IRQ_NONE;
-
- spin_lock(&irq_info->mic_intr_lock);
- for (i = intr_info->intr_start_idx[MIC_INTR_DB];
- i < intr_info->intr_len[MIC_INTR_DB]; i++)
- if (mask & BIT(i)) {
- list_for_each_entry(intr_cb, &irq_info->cb_list[i],
- list)
- if (intr_cb->handler)
- intr_cb->handler(pdev->irq,
- intr_cb->data);
- set_bit(i, &irq_info->mask);
- }
- spin_unlock(&irq_info->mic_intr_lock);
- return IRQ_WAKE_THREAD;
-}
-
-/* Return the interrupt offset from the index. Index is 0 based. */
-static u16 mic_map_src_to_offset(struct mic_device *mdev,
- int intr_src, enum mic_intr_type type)
-{
- if (type >= MIC_NUM_INTR_TYPES)
- return MIC_NUM_OFFSETS;
- if (intr_src >= mdev->intr_info->intr_len[type])
- return MIC_NUM_OFFSETS;
-
- return mdev->intr_info->intr_start_idx[type] + intr_src;
-}
-
-/* Return next available msix_entry. */
-static struct msix_entry *mic_get_available_vector(struct mic_device *mdev)
-{
- int i;
- struct mic_irq_info *info = &mdev->irq_info;
-
- for (i = 0; i < info->num_vectors; i++)
- if (!info->mic_msi_map[i])
- return &info->msix_entries[i];
- return NULL;
-}
-
-/**
- * mic_register_intr_callback - Register a callback handler for the
- * given source id.
- *
- * @mdev: pointer to the mic_device instance
- * @idx: The source id to be registered.
- * @handler: The function to be called when the source id receives
- * the interrupt.
- * @thread_fn: thread fn. corresponding to the handler
- * @data: Private data of the requester.
- * Return the callback structure that was registered or an
- * appropriate error on failure.
- */
-static struct mic_intr_cb *mic_register_intr_callback(struct mic_device *mdev,
- u8 idx, irq_handler_t handler, irq_handler_t thread_fn,
- void *data)
-{
- struct mic_intr_cb *intr_cb;
- unsigned long flags;
- int rc;
- intr_cb = kmalloc(sizeof(*intr_cb), GFP_KERNEL);
-
- if (!intr_cb)
- return ERR_PTR(-ENOMEM);
-
- intr_cb->handler = handler;
- intr_cb->thread_fn = thread_fn;
- intr_cb->data = data;
- intr_cb->cb_id = ida_simple_get(&mdev->irq_info.cb_ida,
- 0, 0, GFP_KERNEL);
- if (intr_cb->cb_id < 0) {
- rc = intr_cb->cb_id;
- goto ida_fail;
- }
-
- spin_lock(&mdev->irq_info.mic_thread_lock);
- spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
- list_add_tail(&intr_cb->list, &mdev->irq_info.cb_list[idx]);
- spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
-
- return intr_cb;
-ida_fail:
- kfree(intr_cb);
- return ERR_PTR(rc);
-}
-
-/**
- * mic_unregister_intr_callback - Unregister the callback handler
- * identified by its callback id.
- *
- * @mdev: pointer to the mic_device instance
- * @idx: The callback structure id to be unregistered.
- * Return the source id that was unregistered or MIC_NUM_OFFSETS if no
- * such callback handler was found.
- */
-static u8 mic_unregister_intr_callback(struct mic_device *mdev, u32 idx)
-{
- struct list_head *pos, *tmp;
- struct mic_intr_cb *intr_cb;
- unsigned long flags;
- int i;
-
- spin_lock(&mdev->irq_info.mic_thread_lock);
- spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
- for (i = 0; i < MIC_NUM_OFFSETS; i++) {
- list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) {
- intr_cb = list_entry(pos, struct mic_intr_cb, list);
- if (intr_cb->cb_id == idx) {
- list_del(pos);
- ida_simple_remove(&mdev->irq_info.cb_ida,
- intr_cb->cb_id);
- kfree(intr_cb);
- spin_unlock_irqrestore(
- &mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
- return i;
- }
- }
- }
- spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
- return MIC_NUM_OFFSETS;
-}
-
-/**
- * mic_setup_msix - Initializes MSIx interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_msix(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc, i;
- int entry_size = sizeof(*mdev->irq_info.msix_entries);
-
- mdev->irq_info.msix_entries = kmalloc_array(MIC_MIN_MSIX,
- entry_size, GFP_KERNEL);
- if (!mdev->irq_info.msix_entries) {
- rc = -ENOMEM;
- goto err_nomem1;
- }
-
- for (i = 0; i < MIC_MIN_MSIX; i++)
- mdev->irq_info.msix_entries[i].entry = i;
-
- rc = pci_enable_msix_exact(pdev, mdev->irq_info.msix_entries,
- MIC_MIN_MSIX);
- if (rc) {
- dev_dbg(&pdev->dev, "Error enabling MSIx. rc = %d\n", rc);
- goto err_enable_msix;
- }
-
- mdev->irq_info.num_vectors = MIC_MIN_MSIX;
- mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) *
- mdev->irq_info.num_vectors), GFP_KERNEL);
-
- if (!mdev->irq_info.mic_msi_map) {
- rc = -ENOMEM;
- goto err_nomem2;
- }
-
- dev_dbg(&mdev->pdev->dev,
- "%d MSIx irqs setup\n", mdev->irq_info.num_vectors);
- return 0;
-err_nomem2:
- pci_disable_msix(pdev);
-err_enable_msix:
- kfree(mdev->irq_info.msix_entries);
-err_nomem1:
- mdev->irq_info.num_vectors = 0;
- return rc;
-}
-
-/**
- * mic_setup_callbacks - Initialize data structures needed
- * to handle callbacks.
- *
- * @mdev: pointer to mic_device instance
- */
-static int mic_setup_callbacks(struct mic_device *mdev)
-{
- int i;
-
- mdev->irq_info.cb_list = kmalloc_array(MIC_NUM_OFFSETS,
- sizeof(*mdev->irq_info.cb_list),
- GFP_KERNEL);
- if (!mdev->irq_info.cb_list)
- return -ENOMEM;
-
- for (i = 0; i < MIC_NUM_OFFSETS; i++)
- INIT_LIST_HEAD(&mdev->irq_info.cb_list[i]);
- ida_init(&mdev->irq_info.cb_ida);
- spin_lock_init(&mdev->irq_info.mic_intr_lock);
- spin_lock_init(&mdev->irq_info.mic_thread_lock);
- return 0;
-}
-
-/**
- * mic_release_callbacks - Uninitialize data structures needed
- * to handle callbacks.
- *
- * @mdev: pointer to mic_device instance
- */
-static void mic_release_callbacks(struct mic_device *mdev)
-{
- unsigned long flags;
- struct list_head *pos, *tmp;
- struct mic_intr_cb *intr_cb;
- int i;
-
- spin_lock(&mdev->irq_info.mic_thread_lock);
- spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags);
- for (i = 0; i < MIC_NUM_OFFSETS; i++) {
- if (list_empty(&mdev->irq_info.cb_list[i]))
- break;
-
- list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) {
- intr_cb = list_entry(pos, struct mic_intr_cb, list);
- list_del(pos);
- ida_simple_remove(&mdev->irq_info.cb_ida,
- intr_cb->cb_id);
- kfree(intr_cb);
- }
- }
- spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags);
- spin_unlock(&mdev->irq_info.mic_thread_lock);
- ida_destroy(&mdev->irq_info.cb_ida);
- kfree(mdev->irq_info.cb_list);
-}
-
-/**
- * mic_setup_msi - Initializes MSI interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_msi(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc;
-
- rc = pci_enable_msi(pdev);
- if (rc) {
- dev_dbg(&pdev->dev, "Error enabling MSI. rc = %d\n", rc);
- return rc;
- }
-
- mdev->irq_info.num_vectors = 1;
- mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) *
- mdev->irq_info.num_vectors), GFP_KERNEL);
-
- if (!mdev->irq_info.mic_msi_map) {
- rc = -ENOMEM;
- goto err_nomem1;
- }
-
- rc = mic_setup_callbacks(mdev);
- if (rc) {
- dev_err(&pdev->dev, "Error setting up callbacks\n");
- goto err_nomem2;
- }
-
- rc = request_threaded_irq(pdev->irq, mic_interrupt, mic_thread_fn,
- 0, "mic-msi", mdev);
- if (rc) {
- dev_err(&pdev->dev, "Error allocating MSI interrupt\n");
- goto err_irq_req_fail;
- }
-
- dev_dbg(&pdev->dev, "%d MSI irqs setup\n", mdev->irq_info.num_vectors);
- return 0;
-err_irq_req_fail:
- mic_release_callbacks(mdev);
-err_nomem2:
- kfree(mdev->irq_info.mic_msi_map);
-err_nomem1:
- pci_disable_msi(pdev);
- mdev->irq_info.num_vectors = 0;
- return rc;
-}
-
-/**
- * mic_setup_intx - Initializes legacy interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int mic_setup_intx(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc;
-
- /* Enable intx */
- pci_intx(pdev, 1);
- rc = mic_setup_callbacks(mdev);
- if (rc) {
- dev_err(&pdev->dev, "Error setting up callbacks\n");
- goto err_nomem;
- }
-
- rc = request_threaded_irq(pdev->irq, mic_interrupt, mic_thread_fn,
- IRQF_SHARED, "mic-intx", mdev);
- if (rc)
- goto err;
-
- dev_dbg(&pdev->dev, "intx irq setup\n");
- return 0;
-err:
- mic_release_callbacks(mdev);
-err_nomem:
- return rc;
-}
-
-/**
- * mic_next_db - Retrieve the next doorbell interrupt source id.
- * The id is picked sequentially from the available pool of
- * doorlbell ids.
- *
- * @mdev: pointer to the mic_device instance.
- *
- * Returns the next doorbell interrupt source.
- */
-int mic_next_db(struct mic_device *mdev)
-{
- int next_db;
-
- next_db = mdev->irq_info.next_avail_src %
- mdev->intr_info->intr_len[MIC_INTR_DB];
- mdev->irq_info.next_avail_src++;
- return next_db;
-}
-
-#define COOKIE_ID_SHIFT 16
-#define GET_ENTRY(cookie) ((cookie) & 0xFFFF)
-#define GET_OFFSET(cookie) ((cookie) >> COOKIE_ID_SHIFT)
-#define MK_COOKIE(x, y) ((x) | (y) << COOKIE_ID_SHIFT)
-
-/**
- * mic_request_threaded_irq - request an irq. mic_mutex needs
- * to be held before calling this function.
- *
- * @mdev: pointer to mic_device instance
- * @handler: The callback function that handles the interrupt.
- * The function needs to call ack_interrupts
- * (mdev->ops->ack_interrupt(mdev)) when handling the interrupts.
- * @thread_fn: thread fn required by request_threaded_irq.
- * @name: The ASCII name of the callee requesting the irq.
- * @data: private data that is returned back when calling the
- * function handler.
- * @intr_src: The source id of the requester. Its the doorbell id
- * for Doorbell interrupts and DMA channel id for DMA interrupts.
- * @type: The type of interrupt. Values defined in mic_intr_type
- *
- * returns: The cookie that is transparent to the caller. Passed
- * back when calling mic_free_irq. An appropriate error code
- * is returned on failure. Caller needs to use IS_ERR(return_val)
- * to check for failure and PTR_ERR(return_val) to obtained the
- * error code.
- *
- */
-struct mic_irq *
-mic_request_threaded_irq(struct mic_device *mdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src,
- enum mic_intr_type type)
-{
- u16 offset;
- int rc = 0;
- struct msix_entry *msix = NULL;
- unsigned long cookie = 0;
- u16 entry;
- struct mic_intr_cb *intr_cb;
- struct pci_dev *pdev = mdev->pdev;
-
- offset = mic_map_src_to_offset(mdev, intr_src, type);
- if (offset >= MIC_NUM_OFFSETS) {
- dev_err(&mdev->pdev->dev,
- "Error mapping index %d to a valid source id.\n",
- intr_src);
- rc = -EINVAL;
- goto err;
- }
-
- if (mdev->irq_info.num_vectors > 1) {
- msix = mic_get_available_vector(mdev);
- if (!msix) {
- dev_err(&mdev->pdev->dev,
- "No MSIx vectors available for use.\n");
- rc = -ENOSPC;
- goto err;
- }
-
- rc = request_threaded_irq(msix->vector, handler, thread_fn,
- 0, name, data);
- if (rc) {
- dev_dbg(&mdev->pdev->dev,
- "request irq failed rc = %d\n", rc);
- goto err;
- }
- entry = msix->entry;
- mdev->irq_info.mic_msi_map[entry] |= BIT(offset);
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, true);
- cookie = MK_COOKIE(entry, offset);
- dev_dbg(&mdev->pdev->dev, "irq: %d assigned for src: %d\n",
- msix->vector, intr_src);
- } else {
- intr_cb = mic_register_intr_callback(mdev, offset, handler,
- thread_fn, data);
- if (IS_ERR(intr_cb)) {
- dev_err(&mdev->pdev->dev,
- "No available callback entries for use\n");
- rc = PTR_ERR(intr_cb);
- goto err;
- }
-
- entry = 0;
- if (pci_dev_msi_enabled(pdev)) {
- mdev->irq_info.mic_msi_map[entry] |= (1 << offset);
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, true);
- }
- cookie = MK_COOKIE(entry, intr_cb->cb_id);
- dev_dbg(&mdev->pdev->dev, "callback %d registered for src: %d\n",
- intr_cb->cb_id, intr_src);
- }
- return (struct mic_irq *)cookie;
-err:
- return ERR_PTR(rc);
-}
-
-/**
- * mic_free_irq - free irq. mic_mutex
- * needs to be held before calling this function.
- *
- * @mdev: pointer to mic_device instance
- * @cookie: cookie obtained during a successful call to mic_request_threaded_irq
- * @data: private data specified by the calling function during the
- * mic_request_threaded_irq
- *
- * returns: none.
- */
-void mic_free_irq(struct mic_device *mdev,
- struct mic_irq *cookie, void *data)
-{
- u32 offset;
- u32 entry;
- u8 src_id;
- unsigned int irq;
- struct pci_dev *pdev = mdev->pdev;
-
- entry = GET_ENTRY((unsigned long)cookie);
- offset = GET_OFFSET((unsigned long)cookie);
- if (mdev->irq_info.num_vectors > 1) {
- if (entry >= mdev->irq_info.num_vectors) {
- dev_warn(&mdev->pdev->dev,
- "entry %d should be < num_irq %d\n",
- entry, mdev->irq_info.num_vectors);
- return;
- }
- irq = mdev->irq_info.msix_entries[entry].vector;
- free_irq(irq, data);
- mdev->irq_info.mic_msi_map[entry] &= ~(BIT(offset));
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, false);
-
- dev_dbg(&mdev->pdev->dev, "irq: %d freed\n", irq);
- } else {
- irq = pdev->irq;
- src_id = mic_unregister_intr_callback(mdev, offset);
- if (src_id >= MIC_NUM_OFFSETS) {
- dev_warn(&mdev->pdev->dev, "Error unregistering callback\n");
- return;
- }
- if (pci_dev_msi_enabled(pdev)) {
- mdev->irq_info.mic_msi_map[entry] &= ~(BIT(src_id));
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, src_id, false);
- }
- dev_dbg(&mdev->pdev->dev, "callback %d unregistered for src: %d\n",
- offset, src_id);
- }
-}
-
-/**
- * mic_setup_interrupts - Initializes interrupts.
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int rc;
-
- rc = mic_setup_msix(mdev, pdev);
- if (!rc)
- goto done;
-
- rc = mic_setup_msi(mdev, pdev);
- if (!rc)
- goto done;
-
- rc = mic_setup_intx(mdev, pdev);
- if (rc) {
- dev_err(&mdev->pdev->dev, "no usable interrupts\n");
- return rc;
- }
-done:
- mdev->intr_ops->enable_interrupts(mdev);
- return 0;
-}
-
-/**
- * mic_free_interrupts - Frees interrupts setup by mic_setup_interrupts
- *
- * @mdev: pointer to mic_device instance
- * @pdev: PCI device structure
- *
- * returns none.
- */
-void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev)
-{
- int i;
-
- mdev->intr_ops->disable_interrupts(mdev);
- if (mdev->irq_info.num_vectors > 1) {
- for (i = 0; i < mdev->irq_info.num_vectors; i++) {
- if (mdev->irq_info.mic_msi_map[i])
- dev_warn(&pdev->dev, "irq %d may still be in use.\n",
- mdev->irq_info.msix_entries[i].vector);
- }
- kfree(mdev->irq_info.mic_msi_map);
- kfree(mdev->irq_info.msix_entries);
- pci_disable_msix(pdev);
- } else {
- if (pci_dev_msi_enabled(pdev)) {
- free_irq(pdev->irq, mdev);
- kfree(mdev->irq_info.mic_msi_map);
- pci_disable_msi(pdev);
- } else {
- free_irq(pdev->irq, mdev);
- }
- mic_release_callbacks(mdev);
- }
-}
-
-/**
- * mic_intr_restore - Restore MIC interrupt registers.
- *
- * @mdev: pointer to mic_device instance.
- *
- * Restore the interrupt registers to values previously
- * stored in the SW data structures. mic_mutex needs to
- * be held before calling this function.
- *
- * returns None.
- */
-void mic_intr_restore(struct mic_device *mdev)
-{
- int entry, offset;
- struct pci_dev *pdev = mdev->pdev;
-
- if (!pci_dev_msi_enabled(pdev))
- return;
-
- for (entry = 0; entry < mdev->irq_info.num_vectors; entry++) {
- for (offset = 0; offset < MIC_NUM_OFFSETS; offset++) {
- if (mdev->irq_info.mic_msi_map[entry] & BIT(offset))
- mdev->intr_ops->program_msi_to_src_map(mdev,
- entry, offset, true);
- }
- }
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_INTR_H_
-#define _MIC_INTR_H_
-
-#include <linux/bitops.h>
-#include <linux/interrupt.h>
-/*
- * The minimum number of msix vectors required for normal operation.
- * 3 for virtio network, console and block devices.
- * 1 for card shutdown notifications.
- * 4 for host owned DMA channels.
- * 1 for SCIF
- */
-#define MIC_MIN_MSIX 9
-#define MIC_NUM_OFFSETS 32
-
-/**
- * mic_intr_source - The type of source that will generate
- * the interrupt.The number of types needs to be in sync with
- * MIC_NUM_INTR_TYPES
- *
- * MIC_INTR_DB: The source is a doorbell
- * MIC_INTR_DMA: The source is a DMA channel
- * MIC_INTR_ERR: The source is an error interrupt e.g. SBOX ERR
- * MIC_NUM_INTR_TYPES: Total number of interrupt sources.
- */
-enum mic_intr_type {
- MIC_INTR_DB = 0,
- MIC_INTR_DMA,
- MIC_INTR_ERR,
- MIC_NUM_INTR_TYPES
-};
-
-/**
- * struct mic_intr_info - Contains h/w specific interrupt sources
- * information.
- *
- * @intr_start_idx: Contains the starting indexes of the
- * interrupt types.
- * @intr_len: Contains the length of the interrupt types.
- */
-struct mic_intr_info {
- u16 intr_start_idx[MIC_NUM_INTR_TYPES];
- u16 intr_len[MIC_NUM_INTR_TYPES];
-};
-
-/**
- * struct mic_irq_info - OS specific irq information
- *
- * @next_avail_src: next available doorbell that can be assigned.
- * @msix_entries: msix entries allocated while setting up MSI-x
- * @mic_msi_map: The MSI/MSI-x mapping information.
- * @num_vectors: The number of MSI/MSI-x vectors that have been allocated.
- * @cb_ida: callback ID allocator to track the callbacks registered.
- * @mic_intr_lock: spinlock to protect the interrupt callback list.
- * @mic_thread_lock: spinlock to protect the thread callback list.
- * This lock is used to protect against thread_fn while
- * mic_intr_lock is used to protect against interrupt handler.
- * @cb_list: Array of callback lists one for each source.
- * @mask: Mask used by the main thread fn to call the underlying thread fns.
- */
-struct mic_irq_info {
- int next_avail_src;
- struct msix_entry *msix_entries;
- u32 *mic_msi_map;
- u16 num_vectors;
- struct ida cb_ida;
- spinlock_t mic_intr_lock;
- spinlock_t mic_thread_lock;
- struct list_head *cb_list;
- unsigned long mask;
-};
-
-/**
- * struct mic_intr_cb - Interrupt callback structure.
- *
- * @handler: The callback function
- * @thread_fn: The thread_fn.
- * @data: Private data of the requester.
- * @cb_id: The callback id. Identifies this callback.
- * @list: list head pointing to the next callback structure.
- */
-struct mic_intr_cb {
- irq_handler_t handler;
- irq_handler_t thread_fn;
- void *data;
- int cb_id;
- struct list_head list;
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/* Forward declaration */
-struct mic_device;
-
-/**
- * struct mic_hw_intr_ops: MIC HW specific interrupt operations
- * @intr_init: Initialize H/W specific interrupt information.
- * @enable_interrupts: Enable interrupts from the hardware.
- * @disable_interrupts: Disable interrupts from the hardware.
- * @program_msi_to_src_map: Update MSI mapping registers with
- * irq information.
- * @read_msi_to_src_map: Read MSI mapping registers containing
- * irq information.
- */
-struct mic_hw_intr_ops {
- void (*intr_init)(struct mic_device *mdev);
- void (*enable_interrupts)(struct mic_device *mdev);
- void (*disable_interrupts)(struct mic_device *mdev);
- void (*program_msi_to_src_map) (struct mic_device *mdev,
- int idx, int intr_src, bool set);
- u32 (*read_msi_to_src_map) (struct mic_device *mdev,
- int idx);
-};
-
-int mic_next_db(struct mic_device *mdev);
-struct mic_irq *
-mic_request_threaded_irq(struct mic_device *mdev,
- irq_handler_t handler, irq_handler_t thread_fn,
- const char *name, void *data, int intr_src,
- enum mic_intr_type type);
-void mic_free_irq(struct mic_device *mdev,
- struct mic_irq *cookie, void *data);
-int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev);
-void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev);
-void mic_intr_restore(struct mic_device *mdev);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/poll.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-#include "mic_smpt.h"
-
-static const char mic_driver_name[] = "mic";
-
-static const struct pci_device_id mic_pci_tbl[] = {
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2250)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2251)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2252)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2253)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2254)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2255)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2256)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2257)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2258)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2259)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225a)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225b)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225c)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225d)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225e)},
-
- /* required last entry */
- { 0, }
-};
-
-MODULE_DEVICE_TABLE(pci, mic_pci_tbl);
-
-/* ID allocator for MIC devices */
-static struct ida g_mic_ida;
-
-/* Initialize the device page */
-static int mic_dp_init(struct mic_device *mdev)
-{
- mdev->dp = kzalloc(MIC_DP_SIZE, GFP_KERNEL);
- if (!mdev->dp)
- return -ENOMEM;
-
- mdev->dp_dma_addr = mic_map_single(mdev,
- mdev->dp, MIC_DP_SIZE);
- if (mic_map_error(mdev->dp_dma_addr)) {
- kfree(mdev->dp);
- dev_err(&mdev->pdev->dev, "%s %d err %d\n",
- __func__, __LINE__, -ENOMEM);
- return -ENOMEM;
- }
- mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr);
- mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32);
- return 0;
-}
-
-/* Uninitialize the device page */
-static void mic_dp_uninit(struct mic_device *mdev)
-{
- mic_unmap_single(mdev, mdev->dp_dma_addr, MIC_DP_SIZE);
- kfree(mdev->dp);
-}
-
-/**
- * mic_ops_init: Initialize HW specific operation tables.
- *
- * @mdev: pointer to mic_device instance
- *
- * returns none.
- */
-static void mic_ops_init(struct mic_device *mdev)
-{
- switch (mdev->family) {
- case MIC_FAMILY_X100:
- mdev->ops = &mic_x100_ops;
- mdev->intr_ops = &mic_x100_intr_ops;
- mdev->smpt_ops = &mic_x100_smpt_ops;
- break;
- default:
- break;
- }
-}
-
-/**
- * mic_get_family - Determine hardware family to which this MIC belongs.
- *
- * @pdev: The pci device structure
- *
- * returns family.
- */
-static enum mic_hw_family mic_get_family(struct pci_dev *pdev)
-{
- enum mic_hw_family family;
-
- switch (pdev->device) {
- case MIC_X100_PCI_DEVICE_2250:
- case MIC_X100_PCI_DEVICE_2251:
- case MIC_X100_PCI_DEVICE_2252:
- case MIC_X100_PCI_DEVICE_2253:
- case MIC_X100_PCI_DEVICE_2254:
- case MIC_X100_PCI_DEVICE_2255:
- case MIC_X100_PCI_DEVICE_2256:
- case MIC_X100_PCI_DEVICE_2257:
- case MIC_X100_PCI_DEVICE_2258:
- case MIC_X100_PCI_DEVICE_2259:
- case MIC_X100_PCI_DEVICE_225a:
- case MIC_X100_PCI_DEVICE_225b:
- case MIC_X100_PCI_DEVICE_225c:
- case MIC_X100_PCI_DEVICE_225d:
- case MIC_X100_PCI_DEVICE_225e:
- family = MIC_FAMILY_X100;
- break;
- default:
- family = MIC_FAMILY_UNKNOWN;
- break;
- }
- return family;
-}
-
-/**
- * mic_device_init - Allocates and initializes the MIC device structure
- *
- * @mdev: pointer to mic_device instance
- * @pdev: The pci device structure
- *
- * returns none.
- */
-static void
-mic_device_init(struct mic_device *mdev, struct pci_dev *pdev)
-{
- mdev->pdev = pdev;
- mdev->family = mic_get_family(pdev);
- mdev->stepping = pdev->revision;
- mic_ops_init(mdev);
- mutex_init(&mdev->mic_mutex);
- mdev->irq_info.next_avail_src = 0;
-}
-
-/**
- * mic_probe - Device Initialization Routine
- *
- * @pdev: PCI device structure
- * @ent: entry in mic_pci_tbl
- *
- * returns 0 on success, < 0 on failure.
- */
-static int mic_probe(struct pci_dev *pdev,
- const struct pci_device_id *ent)
-{
- int rc;
- struct mic_device *mdev;
-
- mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
- if (!mdev) {
- rc = -ENOMEM;
- goto mdev_alloc_fail;
- }
- mdev->id = ida_simple_get(&g_mic_ida, 0, MIC_MAX_NUM_DEVS, GFP_KERNEL);
- if (mdev->id < 0) {
- rc = mdev->id;
- dev_err(&pdev->dev, "ida_simple_get failed rc %d\n", rc);
- goto ida_fail;
- }
-
- mic_device_init(mdev, pdev);
-
- rc = pci_enable_device(pdev);
- if (rc) {
- dev_err(&pdev->dev, "failed to enable pci device.\n");
- goto ida_remove;
- }
-
- pci_set_master(pdev);
-
- rc = pci_request_regions(pdev, mic_driver_name);
- if (rc) {
- dev_err(&pdev->dev, "failed to get pci regions.\n");
- goto disable_device;
- }
-
- rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
- if (rc) {
- dev_err(&pdev->dev, "Cannot set DMA mask\n");
- goto release_regions;
- }
-
- mdev->mmio.pa = pci_resource_start(pdev, mdev->ops->mmio_bar);
- mdev->mmio.len = pci_resource_len(pdev, mdev->ops->mmio_bar);
- mdev->mmio.va = pci_ioremap_bar(pdev, mdev->ops->mmio_bar);
- if (!mdev->mmio.va) {
- dev_err(&pdev->dev, "Cannot remap MMIO BAR\n");
- rc = -EIO;
- goto release_regions;
- }
-
- mdev->aper.pa = pci_resource_start(pdev, mdev->ops->aper_bar);
- mdev->aper.len = pci_resource_len(pdev, mdev->ops->aper_bar);
- mdev->aper.va = ioremap_wc(mdev->aper.pa, mdev->aper.len);
- if (!mdev->aper.va) {
- dev_err(&pdev->dev, "Cannot remap Aperture BAR\n");
- rc = -EIO;
- goto unmap_mmio;
- }
-
- mdev->intr_ops->intr_init(mdev);
- rc = mic_setup_interrupts(mdev, pdev);
- if (rc) {
- dev_err(&pdev->dev, "mic_setup_interrupts failed %d\n", rc);
- goto unmap_aper;
- }
- rc = mic_smpt_init(mdev);
- if (rc) {
- dev_err(&pdev->dev, "smpt_init failed %d\n", rc);
- goto free_interrupts;
- }
-
- pci_set_drvdata(pdev, mdev);
-
- rc = mic_dp_init(mdev);
- if (rc) {
- dev_err(&pdev->dev, "mic_dp_init failed rc %d\n", rc);
- goto smpt_uninit;
- }
- mic_bootparam_init(mdev);
- mic_create_debug_dir(mdev);
-
- mdev->cosm_dev = cosm_register_device(&mdev->pdev->dev, &cosm_hw_ops);
- if (IS_ERR(mdev->cosm_dev)) {
- rc = PTR_ERR(mdev->cosm_dev);
- dev_err(&pdev->dev, "cosm_add_device failed rc %d\n", rc);
- goto cleanup_debug_dir;
- }
- return 0;
-cleanup_debug_dir:
- mic_delete_debug_dir(mdev);
- mic_dp_uninit(mdev);
-smpt_uninit:
- mic_smpt_uninit(mdev);
-free_interrupts:
- mic_free_interrupts(mdev, pdev);
-unmap_aper:
- iounmap(mdev->aper.va);
-unmap_mmio:
- iounmap(mdev->mmio.va);
-release_regions:
- pci_release_regions(pdev);
-disable_device:
- pci_disable_device(pdev);
-ida_remove:
- ida_simple_remove(&g_mic_ida, mdev->id);
-ida_fail:
- kfree(mdev);
-mdev_alloc_fail:
- dev_err(&pdev->dev, "Probe failed rc %d\n", rc);
- return rc;
-}
-
-/**
- * mic_remove - Device Removal Routine
- * mic_remove is called by the PCI subsystem to alert the driver
- * that it should release a PCI device.
- *
- * @pdev: PCI device structure
- */
-static void mic_remove(struct pci_dev *pdev)
-{
- struct mic_device *mdev;
-
- mdev = pci_get_drvdata(pdev);
- if (!mdev)
- return;
-
- cosm_unregister_device(mdev->cosm_dev);
- mic_delete_debug_dir(mdev);
- mic_dp_uninit(mdev);
- mic_smpt_uninit(mdev);
- mic_free_interrupts(mdev, pdev);
- iounmap(mdev->aper.va);
- iounmap(mdev->mmio.va);
- pci_release_regions(pdev);
- pci_disable_device(pdev);
- ida_simple_remove(&g_mic_ida, mdev->id);
- kfree(mdev);
-}
-
-static struct pci_driver mic_driver = {
- .name = mic_driver_name,
- .id_table = mic_pci_tbl,
- .probe = mic_probe,
- .remove = mic_remove
-};
-
-static int __init mic_init(void)
-{
- int ret;
-
- request_module("mic_x100_dma");
- mic_init_debugfs();
- ida_init(&g_mic_ida);
- ret = pci_register_driver(&mic_driver);
- if (ret) {
- pr_err("pci_register_driver failed ret %d\n", ret);
- goto cleanup_debugfs;
- }
- return 0;
-cleanup_debugfs:
- ida_destroy(&g_mic_ida);
- mic_exit_debugfs();
- return ret;
-}
-
-static void __exit mic_exit(void)
-{
- pci_unregister_driver(&mic_driver);
- ida_destroy(&g_mic_ida);
- mic_exit_debugfs();
-}
-
-module_init(mic_init);
-module_exit(mic_exit);
-
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) MIC X100 Host driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/pci.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_smpt.h"
-
-static inline u64 mic_system_page_mask(struct mic_device *mdev)
-{
- return (1ULL << mdev->smpt->info.page_shift) - 1ULL;
-}
-
-static inline u8 mic_sys_addr_to_smpt(struct mic_device *mdev, dma_addr_t pa)
-{
- return (pa - mdev->smpt->info.base) >> mdev->smpt->info.page_shift;
-}
-
-static inline u64 mic_smpt_to_pa(struct mic_device *mdev, u8 index)
-{
- return mdev->smpt->info.base + (index * mdev->smpt->info.page_size);
-}
-
-static inline u64 mic_smpt_offset(struct mic_device *mdev, dma_addr_t pa)
-{
- return pa & mic_system_page_mask(mdev);
-}
-
-static inline u64 mic_smpt_align_low(struct mic_device *mdev, dma_addr_t pa)
-{
- return ALIGN(pa - mic_system_page_mask(mdev),
- mdev->smpt->info.page_size);
-}
-
-static inline u64 mic_smpt_align_high(struct mic_device *mdev, dma_addr_t pa)
-{
- return ALIGN(pa, mdev->smpt->info.page_size);
-}
-
-/* Total Cumulative system memory accessible by MIC across all SMPT entries */
-static inline u64 mic_max_system_memory(struct mic_device *mdev)
-{
- return mdev->smpt->info.num_reg * mdev->smpt->info.page_size;
-}
-
-/* Maximum system memory address accessible by MIC */
-static inline u64 mic_max_system_addr(struct mic_device *mdev)
-{
- return mdev->smpt->info.base + mic_max_system_memory(mdev) - 1ULL;
-}
-
-/* Check if the DMA address is a MIC system memory address */
-static inline bool
-mic_is_system_addr(struct mic_device *mdev, dma_addr_t pa)
-{
- return pa >= mdev->smpt->info.base && pa <= mic_max_system_addr(mdev);
-}
-
-/* Populate an SMPT entry and update the reference counts. */
-static void mic_add_smpt_entry(int spt, s64 *ref, u64 addr,
- int entries, struct mic_device *mdev)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- int i;
-
- for (i = spt; i < spt + entries; i++,
- addr += smpt_info->info.page_size) {
- if (!smpt_info->entry[i].ref_count &&
- (smpt_info->entry[i].dma_addr != addr)) {
- mdev->smpt_ops->set(mdev, addr, i);
- smpt_info->entry[i].dma_addr = addr;
- }
- smpt_info->entry[i].ref_count += ref[i - spt];
- }
-}
-
-/*
- * Find an available MIC address in MIC SMPT address space
- * for a given DMA address and size.
- */
-static dma_addr_t mic_smpt_op(struct mic_device *mdev, u64 dma_addr,
- int entries, s64 *ref, size_t size)
-{
- int spt;
- int ae = 0;
- int i;
- unsigned long flags;
- dma_addr_t mic_addr = 0;
- dma_addr_t addr = dma_addr;
- struct mic_smpt_info *smpt_info = mdev->smpt;
-
- spin_lock_irqsave(&smpt_info->smpt_lock, flags);
-
- /* find existing entries */
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- if (smpt_info->entry[i].dma_addr == addr) {
- ae++;
- addr += smpt_info->info.page_size;
- } else if (ae) /* cannot find contiguous entries */
- goto not_found;
-
- if (ae == entries)
- goto found;
- }
-
- /* find free entry */
- for (ae = 0, i = 0; i < smpt_info->info.num_reg; i++) {
- ae = (smpt_info->entry[i].ref_count == 0) ? ae + 1 : 0;
- if (ae == entries)
- goto found;
- }
-
-not_found:
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- return mic_addr;
-
-found:
- spt = i - entries + 1;
- mic_addr = mic_smpt_to_pa(mdev, spt);
- mic_add_smpt_entry(spt, ref, dma_addr, entries, mdev);
- smpt_info->map_count++;
- smpt_info->ref_count += (s64)size;
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- return mic_addr;
-}
-
-/*
- * Returns number of smpt entries needed for dma_addr to dma_addr + size
- * also returns the reference count array for each of those entries
- * and the starting smpt address
- */
-static int mic_get_smpt_ref_count(struct mic_device *mdev, dma_addr_t dma_addr,
- size_t size, s64 *ref, u64 *smpt_start)
-{
- u64 start = dma_addr;
- u64 end = dma_addr + size;
- int i = 0;
-
- while (start < end) {
- ref[i++] = min(mic_smpt_align_high(mdev, start + 1),
- end) - start;
- start = mic_smpt_align_high(mdev, start + 1);
- }
-
- if (smpt_start)
- *smpt_start = mic_smpt_align_low(mdev, dma_addr);
-
- return i;
-}
-
-/*
- * mic_to_dma_addr - Converts a MIC address to a DMA address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC address.
- *
- * returns a DMA address.
- */
-dma_addr_t mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- int spt;
- dma_addr_t dma_addr;
-
- if (!mic_is_system_addr(mdev, mic_addr)) {
- dev_err(&mdev->pdev->dev,
- "mic_addr is invalid. mic_addr = 0x%llx\n", mic_addr);
- return -EINVAL;
- }
- spt = mic_sys_addr_to_smpt(mdev, mic_addr);
- dma_addr = smpt_info->entry[spt].dma_addr +
- mic_smpt_offset(mdev, mic_addr);
- return dma_addr;
-}
-
-/**
- * mic_map - Maps a DMA address to a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @dma_addr: DMA address.
- * @size: Size of the region to be mapped.
- *
- * This API converts the DMA address provided to a DMA address understood
- * by MIC. Caller should check for errors by calling mic_map_error(..).
- *
- * returns DMA address as required by MIC.
- */
-dma_addr_t mic_map(struct mic_device *mdev, dma_addr_t dma_addr, size_t size)
-{
- dma_addr_t mic_addr = 0;
- int num_entries;
- s64 *ref;
- u64 smpt_start;
-
- if (!size || size > mic_max_system_memory(mdev))
- return mic_addr;
-
- ref = kmalloc_array(mdev->smpt->info.num_reg, sizeof(s64), GFP_ATOMIC);
- if (!ref)
- return mic_addr;
-
- num_entries = mic_get_smpt_ref_count(mdev, dma_addr, size,
- ref, &smpt_start);
-
- /* Set the smpt table appropriately and get 16G aligned mic address */
- mic_addr = mic_smpt_op(mdev, smpt_start, num_entries, ref, size);
-
- kfree(ref);
-
- /*
- * If mic_addr is zero then its an error case
- * since mic_addr can never be zero.
- * else generate mic_addr by adding the 16G offset in dma_addr
- */
- if (!mic_addr && MIC_FAMILY_X100 == mdev->family) {
- dev_err(&mdev->pdev->dev,
- "mic_map failed dma_addr 0x%llx size 0x%lx\n",
- dma_addr, size);
- return mic_addr;
- } else {
- return mic_addr + mic_smpt_offset(mdev, dma_addr);
- }
-}
-
-/**
- * mic_unmap - Unmaps a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC physical address.
- * @size: Size of the region to be unmapped.
- *
- * This API unmaps the mappings created by mic_map(..).
- *
- * returns None.
- */
-void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- s64 *ref;
- int num_smpt;
- int spt;
- int i;
- unsigned long flags;
-
- if (!size)
- return;
-
- if (!mic_is_system_addr(mdev, mic_addr)) {
- dev_err(&mdev->pdev->dev,
- "invalid address: 0x%llx\n", mic_addr);
- return;
- }
-
- spt = mic_sys_addr_to_smpt(mdev, mic_addr);
- ref = kmalloc_array(mdev->smpt->info.num_reg, sizeof(s64), GFP_ATOMIC);
- if (!ref)
- return;
-
- /* Get number of smpt entries to be mapped, ref count array */
- num_smpt = mic_get_smpt_ref_count(mdev, mic_addr, size, ref, NULL);
-
- spin_lock_irqsave(&smpt_info->smpt_lock, flags);
- smpt_info->unmap_count++;
- smpt_info->ref_count -= (s64)size;
-
- for (i = spt; i < spt + num_smpt; i++) {
- smpt_info->entry[i].ref_count -= ref[i - spt];
- if (smpt_info->entry[i].ref_count < 0)
- dev_warn(&mdev->pdev->dev,
- "ref count for entry %d is negative\n", i);
- }
- spin_unlock_irqrestore(&smpt_info->smpt_lock, flags);
- kfree(ref);
-}
-
-/**
- * mic_map_single - Maps a virtual address to a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @va: Kernel direct mapped virtual address.
- * @size: Size of the region to be mapped.
- *
- * This API calls pci_map_single(..) for the direct mapped virtual address
- * and then converts the DMA address provided to a DMA address understood
- * by MIC. Caller should check for errors by calling mic_map_error(..).
- *
- * returns DMA address as required by MIC.
- */
-dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size)
-{
- dma_addr_t mic_addr = 0;
- struct pci_dev *pdev = mdev->pdev;
- dma_addr_t dma_addr =
- pci_map_single(pdev, va, size, PCI_DMA_BIDIRECTIONAL);
-
- if (!pci_dma_mapping_error(pdev, dma_addr)) {
- mic_addr = mic_map(mdev, dma_addr, size);
- if (!mic_addr) {
- dev_err(&mdev->pdev->dev,
- "mic_map failed dma_addr 0x%llx size 0x%lx\n",
- dma_addr, size);
- pci_unmap_single(pdev, dma_addr,
- size, PCI_DMA_BIDIRECTIONAL);
- }
- }
- return mic_addr;
-}
-
-/**
- * mic_unmap_single - Unmaps a MIC physical address.
- *
- * @mdev: pointer to mic_device instance.
- * @mic_addr: MIC physical address.
- * @size: Size of the region to be unmapped.
- *
- * This API unmaps the mappings created by mic_map_single(..).
- *
- * returns None.
- */
-void
-mic_unmap_single(struct mic_device *mdev, dma_addr_t mic_addr, size_t size)
-{
- struct pci_dev *pdev = mdev->pdev;
- dma_addr_t dma_addr = mic_to_dma_addr(mdev, mic_addr);
- mic_unmap(mdev, mic_addr, size);
- pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
-}
-
-/**
- * mic_smpt_init - Initialize MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns 0 for success and -errno for error.
- */
-int mic_smpt_init(struct mic_device *mdev)
-{
- int i, err = 0;
- dma_addr_t dma_addr;
- struct mic_smpt_info *smpt_info;
-
- mdev->smpt = kmalloc(sizeof(*mdev->smpt), GFP_KERNEL);
- if (!mdev->smpt)
- return -ENOMEM;
-
- smpt_info = mdev->smpt;
- mdev->smpt_ops->init(mdev);
- smpt_info->entry = kmalloc_array(smpt_info->info.num_reg,
- sizeof(*smpt_info->entry), GFP_KERNEL);
- if (!smpt_info->entry) {
- err = -ENOMEM;
- goto free_smpt;
- }
- spin_lock_init(&smpt_info->smpt_lock);
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- dma_addr = i * smpt_info->info.page_size;
- smpt_info->entry[i].dma_addr = dma_addr;
- smpt_info->entry[i].ref_count = 0;
- mdev->smpt_ops->set(mdev, dma_addr, i);
- }
- smpt_info->ref_count = 0;
- smpt_info->map_count = 0;
- smpt_info->unmap_count = 0;
- return 0;
-free_smpt:
- kfree(smpt_info);
- return err;
-}
-
-/**
- * mic_smpt_uninit - UnInitialize MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns None.
- */
-void mic_smpt_uninit(struct mic_device *mdev)
-{
- struct mic_smpt_info *smpt_info = mdev->smpt;
- int i;
-
- dev_dbg(&mdev->pdev->dev,
- "nodeid %d SMPT ref count %lld map %lld unmap %lld\n",
- mdev->id, smpt_info->ref_count,
- smpt_info->map_count, smpt_info->unmap_count);
-
- for (i = 0; i < smpt_info->info.num_reg; i++) {
- dev_dbg(&mdev->pdev->dev,
- "SMPT entry[%d] dma_addr = 0x%llx ref_count = %lld\n",
- i, smpt_info->entry[i].dma_addr,
- smpt_info->entry[i].ref_count);
- if (smpt_info->entry[i].ref_count)
- dev_warn(&mdev->pdev->dev,
- "ref count for entry %d is not zero\n", i);
- }
- kfree(smpt_info->entry);
- kfree(smpt_info);
-}
-
-/**
- * mic_smpt_restore - Restore MIC System Memory Page Tables.
- *
- * @mdev: pointer to mic_device instance.
- *
- * Restore the SMPT registers to values previously stored in the
- * SW data structures. Some MIC steppings lose register state
- * across resets and this API should be called for performing
- * a restore operation if required.
- *
- * returns None.
- */
-void mic_smpt_restore(struct mic_device *mdev)
-{
- int i;
- dma_addr_t dma_addr;
-
- for (i = 0; i < mdev->smpt->info.num_reg; i++) {
- dma_addr = mdev->smpt->entry[i].dma_addr;
- mdev->smpt_ops->set(mdev, dma_addr, i);
- }
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef MIC_SMPT_H
-#define MIC_SMPT_H
-/**
- * struct mic_smpt_ops - MIC HW specific SMPT operations.
- * @init: Initialize hardware specific SMPT information in mic_smpt_hw_info.
- * @set: Set the value for a particular SMPT entry.
- */
-struct mic_smpt_ops {
- void (*init)(struct mic_device *mdev);
- void (*set)(struct mic_device *mdev, dma_addr_t dma_addr, u8 index);
-};
-
-/**
- * struct mic_smpt - MIC SMPT entry information.
- * @dma_addr: Base DMA address for this SMPT entry.
- * @ref_count: Number of active mappings for this SMPT entry in bytes.
- */
-struct mic_smpt {
- dma_addr_t dma_addr;
- s64 ref_count;
-};
-
-/**
- * struct mic_smpt_hw_info - MIC SMPT hardware specific information.
- * @num_reg: Number of SMPT registers.
- * @page_shift: System memory page shift.
- * @page_size: System memory page size.
- * @base: System address base.
- */
-struct mic_smpt_hw_info {
- u8 num_reg;
- u8 page_shift;
- u64 page_size;
- u64 base;
-};
-
-/**
- * struct mic_smpt_info - MIC SMPT information.
- * @entry: Array of SMPT entries.
- * @smpt_lock: Spin lock protecting access to SMPT data structures.
- * @info: Hardware specific SMPT information.
- * @ref_count: Number of active SMPT mappings (for debug).
- * @map_count: Number of SMPT mappings created (for debug).
- * @unmap_count: Number of SMPT mappings destroyed (for debug).
- */
-struct mic_smpt_info {
- struct mic_smpt *entry;
- spinlock_t smpt_lock;
- struct mic_smpt_hw_info info;
- s64 ref_count;
- s64 map_count;
- s64 unmap_count;
-};
-
-dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size);
-void mic_unmap_single(struct mic_device *mdev,
- dma_addr_t mic_addr, size_t size);
-dma_addr_t mic_map(struct mic_device *mdev,
- dma_addr_t dma_addr, size_t size);
-void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size);
-dma_addr_t mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr);
-
-/**
- * mic_map_error - Check a MIC address for errors.
- *
- * @mdev: pointer to mic_device instance.
- *
- * returns Whether there was an error during mic_map..(..) APIs.
- */
-static inline bool mic_map_error(dma_addr_t mic_addr)
-{
- return !mic_addr;
-}
-
-int mic_smpt_init(struct mic_device *mdev);
-void mic_smpt_uninit(struct mic_device *mdev);
-void mic_smpt_restore(struct mic_device *mdev);
-
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#include <linux/fs.h>
-#include <linux/pci.h>
-#include <linux/sched.h>
-#include <linux/firmware.h>
-#include <linux/delay.h>
-
-#include "../common/mic_dev.h"
-#include "mic_device.h"
-#include "mic_x100.h"
-#include "mic_smpt.h"
-
-static const u16 mic_x100_intr_init[] = {
- MIC_X100_DOORBELL_IDX_START,
- MIC_X100_DMA_IDX_START,
- MIC_X100_ERR_IDX_START,
- MIC_X100_NUM_DOORBELL,
- MIC_X100_NUM_DMA,
- MIC_X100_NUM_ERR,
-};
-
-/**
- * mic_x100_write_spad - write to the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to the scratchpad register, 0 based
- * @val: the data value to put into the register
- *
- * This function allows writing of a 32bit value to the indexed scratchpad
- * register.
- *
- * RETURNS: none.
- */
-static void
-mic_x100_write_spad(struct mic_device *mdev, unsigned int idx, u32 val)
-{
- dev_dbg(&mdev->pdev->dev, "Writing 0x%x to scratch pad index %d\n",
- val, idx);
- mic_mmio_write(&mdev->mmio, val,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SPAD0 + idx * 4);
-}
-
-/**
- * mic_x100_read_spad - read from the scratchpad register
- * @mdev: pointer to mic_device instance
- * @idx: index to scratchpad register, 0 based
- *
- * This function allows reading of the 32bit scratchpad register.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static u32
-mic_x100_read_spad(struct mic_device *mdev, unsigned int idx)
-{
- u32 val = mic_mmio_read(&mdev->mmio,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SPAD0 + idx * 4);
-
- dev_dbg(&mdev->pdev->dev,
- "Reading 0x%x from scratch pad index %d\n", val, idx);
- return val;
-}
-
-/**
- * mic_x100_enable_interrupts - Enable interrupts.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_enable_interrupts(struct mic_device *mdev)
-{
- u32 reg;
- struct mic_mw *mw = &mdev->mmio;
- u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0;
- u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0;
-
- reg = mic_mmio_read(mw, sice0);
- reg |= MIC_X100_SBOX_DBR_BITS(0xf) | MIC_X100_SBOX_DMA_BITS(0xff);
- mic_mmio_write(mw, reg, sice0);
-
- /*
- * Enable auto-clear when enabling interrupts. Applicable only for
- * MSI-x. Legacy and MSI mode cannot have auto-clear enabled.
- */
- if (mdev->irq_info.num_vectors > 1) {
- reg = mic_mmio_read(mw, siac0);
- reg |= MIC_X100_SBOX_DBR_BITS(0xf) |
- MIC_X100_SBOX_DMA_BITS(0xff);
- mic_mmio_write(mw, reg, siac0);
- }
-}
-
-/**
- * mic_x100_disable_interrupts - Disable interrupts.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_disable_interrupts(struct mic_device *mdev)
-{
- u32 reg;
- struct mic_mw *mw = &mdev->mmio;
- u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0;
- u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0;
- u32 sicc0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICC0;
-
- reg = mic_mmio_read(mw, sice0);
- mic_mmio_write(mw, reg, sicc0);
-
- if (mdev->irq_info.num_vectors > 1) {
- reg = mic_mmio_read(mw, siac0);
- reg &= ~(MIC_X100_SBOX_DBR_BITS(0xf) |
- MIC_X100_SBOX_DMA_BITS(0xff));
- mic_mmio_write(mw, reg, siac0);
- }
-}
-
-/**
- * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number
- */
-static void mic_x100_send_sbox_intr(struct mic_device *mdev,
- int doorbell)
-{
- struct mic_mw *mw = &mdev->mmio;
- u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8;
- u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS +
- apic_icr_offset);
-
- /* for MIC we need to make sure we "hit" the send_icr bit (13) */
- apicicr_low = (apicicr_low | (1 << 13));
-
- /* Ensure that the interrupt is ordered w.r.t. previous stores. */
- wmb();
- mic_mmio_write(mw, apicicr_low,
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-/**
- * mic_x100_send_rdmasr_intr - Send an RDMASR interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number
- */
-static void mic_x100_send_rdmasr_intr(struct mic_device *mdev,
- int doorbell)
-{
- int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2);
- /* Ensure that the interrupt is ordered w.r.t. previous stores. */
- wmb();
- mic_mmio_write(&mdev->mmio, 0,
- MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset);
-}
-
-/**
- * __mic_x100_send_intr - Send interrupt to MIC.
- * @mdev: pointer to mic_device instance
- * @doorbell: doorbell number.
- */
-static void mic_x100_send_intr(struct mic_device *mdev, int doorbell)
-{
- int rdmasr_db;
- if (doorbell < MIC_X100_NUM_SBOX_IRQ) {
- mic_x100_send_sbox_intr(mdev, doorbell);
- } else {
- rdmasr_db = doorbell - MIC_X100_NUM_SBOX_IRQ;
- mic_x100_send_rdmasr_intr(mdev, rdmasr_db);
- }
-}
-
-/**
- * mic_x100_ack_interrupt - Read the interrupt sources register and
- * clear it. This function will be called in the MSI/INTx case.
- * @mdev: Pointer to mic_device instance.
- *
- * Returns: bitmask of interrupt sources triggered.
- */
-static u32 mic_x100_ack_interrupt(struct mic_device *mdev)
-{
- u32 sicr0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICR0;
- u32 reg = mic_mmio_read(&mdev->mmio, sicr0);
- mic_mmio_write(&mdev->mmio, reg, sicr0);
- return reg;
-}
-
-/**
- * mic_x100_intr_workarounds - These hardware specific workarounds are
- * to be invoked everytime an interrupt is handled.
- * @mdev: Pointer to mic_device instance.
- *
- * Returns: none
- */
-static void mic_x100_intr_workarounds(struct mic_device *mdev)
-{
- struct mic_mw *mw = &mdev->mmio;
-
- /* Clear pending bit array. */
- if (MIC_A0_STEP == mdev->stepping)
- mic_mmio_write(mw, 1, MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_MSIXPBACR);
-
- if (mdev->stepping >= MIC_B0_STEP)
- mdev->intr_ops->enable_interrupts(mdev);
-}
-
-/**
- * mic_x100_hw_intr_init - Initialize h/w specific interrupt
- * information.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_hw_intr_init(struct mic_device *mdev)
-{
- mdev->intr_info = (struct mic_intr_info *)mic_x100_intr_init;
-}
-
-/**
- * mic_x100_read_msi_to_src_map - read from the MSI mapping registers
- * @mdev: pointer to mic_device instance
- * @idx: index to the mapping register, 0 based
- *
- * This function allows reading of the 32bit MSI mapping register.
- *
- * RETURNS: The value in the register.
- */
-static u32
-mic_x100_read_msi_to_src_map(struct mic_device *mdev, int idx)
-{
- return mic_mmio_read(&mdev->mmio,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_MXAR0 + idx * 4);
-}
-
-/**
- * mic_x100_program_msi_to_src_map - program the MSI mapping registers
- * @mdev: pointer to mic_device instance
- * @idx: index to the mapping register, 0 based
- * @offset: The bit offset in the register that needs to be updated.
- * @set: boolean specifying if the bit in the specified offset needs
- * to be set or cleared.
- *
- * RETURNS: None.
- */
-static void
-mic_x100_program_msi_to_src_map(struct mic_device *mdev,
- int idx, int offset, bool set)
-{
- unsigned long reg;
- struct mic_mw *mw = &mdev->mmio;
- u32 mxar = MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_MXAR0 + idx * 4;
-
- reg = mic_mmio_read(mw, mxar);
- if (set)
- __set_bit(offset, ®);
- else
- __clear_bit(offset, ®);
- mic_mmio_write(mw, reg, mxar);
-}
-
-/*
- * mic_x100_reset_fw_ready - Reset Firmware ready status field.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_reset_fw_ready(struct mic_device *mdev)
-{
- mdev->ops->write_spad(mdev, MIC_X100_DOWNLOAD_INFO, 0);
-}
-
-/*
- * mic_x100_is_fw_ready - Check if firmware is ready.
- * @mdev: pointer to mic_device instance
- */
-static bool mic_x100_is_fw_ready(struct mic_device *mdev)
-{
- u32 scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
- return MIC_X100_SPAD2_DOWNLOAD_STATUS(scratch2) ? true : false;
-}
-
-/**
- * mic_x100_get_apic_id - Get bootstrap APIC ID.
- * @mdev: pointer to mic_device instance
- */
-static u32 mic_x100_get_apic_id(struct mic_device *mdev)
-{
- u32 scratch2 = 0;
-
- scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
- return MIC_X100_SPAD2_APIC_ID(scratch2);
-}
-
-/**
- * mic_x100_send_firmware_intr - Send an interrupt to the firmware on MIC.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_send_firmware_intr(struct mic_device *mdev)
-{
- u32 apicicr_low;
- u64 apic_icr_offset = MIC_X100_SBOX_APICICR7;
- int vector = MIC_X100_BSP_INTERRUPT_VECTOR;
- struct mic_mw *mw = &mdev->mmio;
-
- /*
- * For MIC we need to make sure we "hit"
- * the send_icr bit (13).
- */
- apicicr_low = (vector | (1 << 13));
-
- mic_mmio_write(mw, mic_x100_get_apic_id(mdev),
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset + 4);
-
- /* Ensure that the interrupt is ordered w.r.t. previous stores. */
- wmb();
- mic_mmio_write(mw, apicicr_low,
- MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset);
-}
-
-/**
- * mic_x100_hw_reset - Reset the MIC device.
- * @mdev: pointer to mic_device instance
- */
-static void mic_x100_hw_reset(struct mic_device *mdev)
-{
- u32 reset_reg;
- u32 rgcr = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_RGCR;
- struct mic_mw *mw = &mdev->mmio;
-
- /* Ensure that the reset is ordered w.r.t. previous loads and stores */
- mb();
- /* Trigger reset */
- reset_reg = mic_mmio_read(mw, rgcr);
- reset_reg |= 0x1;
- mic_mmio_write(mw, reset_reg, rgcr);
- /*
- * It seems we really want to delay at least 1 second
- * after touching reset to prevent a lot of problems.
- */
- msleep(1000);
-}
-
-/**
- * mic_x100_load_command_line - Load command line to MIC.
- * @mdev: pointer to mic_device instance
- * @fw: the firmware image
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_command_line(struct mic_device *mdev, const struct firmware *fw)
-{
- u32 len = 0;
- u32 boot_mem;
- char *buf;
- void __iomem *cmd_line_va = mdev->aper.va + mdev->bootaddr + fw->size;
-#define CMDLINE_SIZE 2048
-
- boot_mem = mdev->aper.len >> 20;
- buf = kzalloc(CMDLINE_SIZE, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- len += scnprintf(buf, CMDLINE_SIZE - len,
- " mem=%dM", boot_mem);
- if (mdev->cosm_dev->cmdline)
- scnprintf(buf + len, CMDLINE_SIZE - len, " %s",
- mdev->cosm_dev->cmdline);
- memcpy_toio(cmd_line_va, buf, strlen(buf) + 1);
- kfree(buf);
- return 0;
-}
-
-/**
- * mic_x100_load_ramdisk - Load ramdisk to MIC.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_ramdisk(struct mic_device *mdev)
-{
- const struct firmware *fw;
- int rc;
- struct boot_params __iomem *bp = mdev->aper.va + mdev->bootaddr;
-
- rc = request_firmware(&fw, mdev->cosm_dev->ramdisk, &mdev->pdev->dev);
- if (rc < 0) {
- dev_err(&mdev->pdev->dev,
- "ramdisk request_firmware failed: %d %s\n",
- rc, mdev->cosm_dev->ramdisk);
- goto error;
- }
- /*
- * Typically the bootaddr for card OS is 64M
- * so copy over the ramdisk @ 128M.
- */
- memcpy_toio(mdev->aper.va + (mdev->bootaddr << 1), fw->data, fw->size);
- iowrite32(mdev->bootaddr << 1, &bp->hdr.ramdisk_image);
- iowrite32(fw->size, &bp->hdr.ramdisk_size);
- release_firmware(fw);
-error:
- return rc;
-}
-
-/**
- * mic_x100_get_boot_addr - Get MIC boot address.
- * @mdev: pointer to mic_device instance
- *
- * This function is called during firmware load to determine
- * the address at which the OS should be downloaded in card
- * memory i.e. GDDR.
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_get_boot_addr(struct mic_device *mdev)
-{
- u32 scratch2, boot_addr;
- int rc = 0;
-
- scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO);
- boot_addr = MIC_X100_SPAD2_DOWNLOAD_ADDR(scratch2);
- dev_dbg(&mdev->pdev->dev, "%s %d boot_addr 0x%x\n",
- __func__, __LINE__, boot_addr);
- if (boot_addr > (1 << 31)) {
- dev_err(&mdev->pdev->dev,
- "incorrect bootaddr 0x%x\n",
- boot_addr);
- rc = -EINVAL;
- goto error;
- }
- mdev->bootaddr = boot_addr;
-error:
- return rc;
-}
-
-/**
- * mic_x100_load_firmware - Load firmware to MIC.
- * @mdev: pointer to mic_device instance
- * @buf: buffer containing boot string including firmware/ramdisk path.
- *
- * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
- */
-static int
-mic_x100_load_firmware(struct mic_device *mdev, const char *buf)
-{
- int rc;
- const struct firmware *fw;
-
- rc = mic_x100_get_boot_addr(mdev);
- if (rc)
- return rc;
- /* load OS */
- rc = request_firmware(&fw, mdev->cosm_dev->firmware, &mdev->pdev->dev);
- if (rc < 0) {
- dev_err(&mdev->pdev->dev,
- "ramdisk request_firmware failed: %d %s\n",
- rc, mdev->cosm_dev->firmware);
- return rc;
- }
- if (mdev->bootaddr > mdev->aper.len - fw->size) {
- rc = -EINVAL;
- dev_err(&mdev->pdev->dev, "%s %d rc %d bootaddr 0x%x\n",
- __func__, __LINE__, rc, mdev->bootaddr);
- goto error;
- }
- memcpy_toio(mdev->aper.va + mdev->bootaddr, fw->data, fw->size);
- mdev->ops->write_spad(mdev, MIC_X100_FW_SIZE, fw->size);
- if (!strcmp(mdev->cosm_dev->bootmode, "flash")) {
- rc = -EINVAL;
- dev_err(&mdev->pdev->dev, "%s %d rc %d\n",
- __func__, __LINE__, rc);
- goto error;
- }
- /* load command line */
- rc = mic_x100_load_command_line(mdev, fw);
- if (rc) {
- dev_err(&mdev->pdev->dev, "%s %d rc %d\n",
- __func__, __LINE__, rc);
- goto error;
- }
- release_firmware(fw);
- /* load ramdisk */
- if (mdev->cosm_dev->ramdisk)
- rc = mic_x100_load_ramdisk(mdev);
-
- return rc;
-
-error:
- release_firmware(fw);
- return rc;
-}
-
-/**
- * mic_x100_get_postcode - Get postcode status from firmware.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: postcode.
- */
-static u32 mic_x100_get_postcode(struct mic_device *mdev)
-{
- return mic_mmio_read(&mdev->mmio, MIC_X100_POSTCODE);
-}
-
-/**
- * mic_x100_smpt_set - Update an SMPT entry with a DMA address.
- * @mdev: pointer to mic_device instance
- * @dma_addr: DMA address to use
- * @index: entry to write to
- *
- * RETURNS: none.
- */
-static void
-mic_x100_smpt_set(struct mic_device *mdev, dma_addr_t dma_addr, u8 index)
-{
-#define SNOOP_ON (0 << 0)
-#define SNOOP_OFF (1 << 0)
-/*
- * Sbox Smpt Reg Bits:
- * Bits 31:2 Host address
- * Bits 1 RSVD
- * Bits 0 No snoop
- */
-#define BUILD_SMPT(NO_SNOOP, HOST_ADDR) \
- (u32)(((HOST_ADDR) << 2) | ((NO_SNOOP) & 0x01))
-
- uint32_t smpt_reg_val = BUILD_SMPT(SNOOP_ON,
- dma_addr >> mdev->smpt->info.page_shift);
- mic_mmio_write(&mdev->mmio, smpt_reg_val,
- MIC_X100_SBOX_BASE_ADDRESS +
- MIC_X100_SBOX_SMPT00 + (4 * index));
-}
-
-/**
- * mic_x100_smpt_hw_init - Initialize SMPT X100 specific fields.
- * @mdev: pointer to mic_device instance
- *
- * RETURNS: none.
- */
-static void mic_x100_smpt_hw_init(struct mic_device *mdev)
-{
- struct mic_smpt_hw_info *info = &mdev->smpt->info;
-
- info->num_reg = 32;
- info->page_shift = 34;
- info->page_size = (1ULL << info->page_shift);
- info->base = 0x8000000000ULL;
-}
-
-struct mic_smpt_ops mic_x100_smpt_ops = {
- .init = mic_x100_smpt_hw_init,
- .set = mic_x100_smpt_set,
-};
-
-static bool mic_x100_dma_filter(struct dma_chan *chan, void *param)
-{
- if (chan->device->dev->parent == (struct device *)param)
- return true;
- return false;
-}
-
-struct mic_hw_ops mic_x100_ops = {
- .aper_bar = MIC_X100_APER_BAR,
- .mmio_bar = MIC_X100_MMIO_BAR,
- .read_spad = mic_x100_read_spad,
- .write_spad = mic_x100_write_spad,
- .send_intr = mic_x100_send_intr,
- .ack_interrupt = mic_x100_ack_interrupt,
- .intr_workarounds = mic_x100_intr_workarounds,
- .reset = mic_x100_hw_reset,
- .reset_fw_ready = mic_x100_reset_fw_ready,
- .is_fw_ready = mic_x100_is_fw_ready,
- .send_firmware_intr = mic_x100_send_firmware_intr,
- .load_mic_fw = mic_x100_load_firmware,
- .get_postcode = mic_x100_get_postcode,
- .dma_filter = mic_x100_dma_filter,
-};
-
-struct mic_hw_intr_ops mic_x100_intr_ops = {
- .intr_init = mic_x100_hw_intr_init,
- .enable_interrupts = mic_x100_enable_interrupts,
- .disable_interrupts = mic_x100_disable_interrupts,
- .program_msi_to_src_map = mic_x100_program_msi_to_src_map,
- .read_msi_to_src_map = mic_x100_read_msi_to_src_map,
-};
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC Host driver.
- */
-#ifndef _MIC_X100_HW_H_
-#define _MIC_X100_HW_H_
-
-#define MIC_X100_PCI_DEVICE_2250 0x2250
-#define MIC_X100_PCI_DEVICE_2251 0x2251
-#define MIC_X100_PCI_DEVICE_2252 0x2252
-#define MIC_X100_PCI_DEVICE_2253 0x2253
-#define MIC_X100_PCI_DEVICE_2254 0x2254
-#define MIC_X100_PCI_DEVICE_2255 0x2255
-#define MIC_X100_PCI_DEVICE_2256 0x2256
-#define MIC_X100_PCI_DEVICE_2257 0x2257
-#define MIC_X100_PCI_DEVICE_2258 0x2258
-#define MIC_X100_PCI_DEVICE_2259 0x2259
-#define MIC_X100_PCI_DEVICE_225a 0x225a
-#define MIC_X100_PCI_DEVICE_225b 0x225b
-#define MIC_X100_PCI_DEVICE_225c 0x225c
-#define MIC_X100_PCI_DEVICE_225d 0x225d
-#define MIC_X100_PCI_DEVICE_225e 0x225e
-
-#define MIC_X100_APER_BAR 0
-#define MIC_X100_MMIO_BAR 4
-
-#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000
-#define MIC_X100_SBOX_SPAD0 0x0000AB20
-#define MIC_X100_SBOX_SICR0_DBR(x) ((x) & 0xf)
-#define MIC_X100_SBOX_SICR0_DMA(x) (((x) >> 8) & 0xff)
-#define MIC_X100_SBOX_SICE0_DBR(x) ((x) & 0xf)
-#define MIC_X100_SBOX_DBR_BITS(x) ((x) & 0xf)
-#define MIC_X100_SBOX_SICE0_DMA(x) (((x) >> 8) & 0xff)
-#define MIC_X100_SBOX_DMA_BITS(x) (((x) & 0xff) << 8)
-
-#define MIC_X100_SBOX_APICICR0 0x0000A9D0
-#define MIC_X100_SBOX_SICR0 0x00009004
-#define MIC_X100_SBOX_SICE0 0x0000900C
-#define MIC_X100_SBOX_SICC0 0x00009010
-#define MIC_X100_SBOX_SIAC0 0x00009014
-#define MIC_X100_SBOX_MSIXPBACR 0x00009084
-#define MIC_X100_SBOX_MXAR0 0x00009044
-#define MIC_X100_SBOX_SMPT00 0x00003100
-#define MIC_X100_SBOX_RDMASR0 0x0000B180
-
-#define MIC_X100_DOORBELL_IDX_START 0
-#define MIC_X100_NUM_DOORBELL 4
-#define MIC_X100_DMA_IDX_START 8
-#define MIC_X100_NUM_DMA 8
-#define MIC_X100_ERR_IDX_START 30
-#define MIC_X100_NUM_ERR 1
-
-#define MIC_X100_NUM_SBOX_IRQ 8
-#define MIC_X100_NUM_RDMASR_IRQ 8
-#define MIC_X100_RDMASR_IRQ_BASE 17
-#define MIC_X100_SPAD2_DOWNLOAD_STATUS(x) ((x) & 0x1)
-#define MIC_X100_SPAD2_APIC_ID(x) (((x) >> 1) & 0x1ff)
-#define MIC_X100_SPAD2_DOWNLOAD_ADDR(x) ((x) & 0xfffff000)
-#define MIC_X100_SBOX_APICICR7 0x0000AA08
-#define MIC_X100_SBOX_RGCR 0x00004010
-#define MIC_X100_SBOX_SDBIC0 0x0000CC90
-#define MIC_X100_DOWNLOAD_INFO 2
-#define MIC_X100_FW_SIZE 5
-#define MIC_X100_POSTCODE 0x242c
-
-/* Host->Card(bootstrap) Interrupt Vector */
-#define MIC_X100_BSP_INTERRUPT_VECTOR 229
-
-extern struct mic_hw_ops mic_x100_ops;
-extern struct mic_smpt_ops mic_x100_smpt_ops;
-extern struct mic_hw_intr_ops mic_x100_intr_ops;
-
-#endif
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile - SCIF driver.
-# Copyright(c) 2014, Intel Corporation.
-#
-obj-$(CONFIG_SCIF) += scif.o
-scif-objs := scif_main.o
-scif-objs += scif_peer_bus.o
-scif-objs += scif_ports.o
-scif-objs += scif_debugfs.o
-scif-objs += scif_fd.o
-scif-objs += scif_api.o
-scif-objs += scif_epd.o
-scif-objs += scif_rb.o
-scif-objs += scif_nodeqp.o
-scif-objs += scif_nm.o
-scif-objs += scif_dma.o
-scif-objs += scif_fence.o
-scif-objs += scif_mmap.o
-scif-objs += scif_rma.o
-scif-objs += scif_rma_list.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/scif.h>
-#include "scif_main.h"
-#include "scif_map.h"
-
-static const char * const scif_ep_states[] = {
- "Unbound",
- "Bound",
- "Listening",
- "Connected",
- "Connecting",
- "Mapping",
- "Closing",
- "Close Listening",
- "Disconnected",
- "Zombie"};
-
-enum conn_async_state {
- ASYNC_CONN_IDLE = 1, /* ep setup for async connect */
- ASYNC_CONN_INPROGRESS, /* async connect in progress */
- ASYNC_CONN_FLUSH_WORK /* async work flush in progress */
-};
-
-/*
- * File operations for anonymous inode file associated with a SCIF endpoint,
- * used in kernel mode SCIF poll. Kernel mode SCIF poll calls portions of the
- * poll API in the kernel and these take in a struct file *. Since a struct
- * file is not available to kernel mode SCIF, it uses an anonymous file for
- * this purpose.
- */
-const struct file_operations scif_anon_fops = {
- .owner = THIS_MODULE,
-};
-
-scif_epd_t scif_open(void)
-{
- struct scif_endpt *ep;
- int err;
-
- might_sleep();
- ep = kzalloc(sizeof(*ep), GFP_KERNEL);
- if (!ep)
- goto err_ep_alloc;
-
- ep->qp_info.qp = kzalloc(sizeof(*ep->qp_info.qp), GFP_KERNEL);
- if (!ep->qp_info.qp)
- goto err_qp_alloc;
-
- err = scif_anon_inode_getfile(ep);
- if (err)
- goto err_anon_inode;
-
- spin_lock_init(&ep->lock);
- mutex_init(&ep->sendlock);
- mutex_init(&ep->recvlock);
-
- scif_rma_ep_init(ep);
- ep->state = SCIFEP_UNBOUND;
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI open: ep %p success\n", ep);
- return ep;
-
-err_anon_inode:
- kfree(ep->qp_info.qp);
-err_qp_alloc:
- kfree(ep);
-err_ep_alloc:
- return NULL;
-}
-EXPORT_SYMBOL_GPL(scif_open);
-
-/*
- * scif_disconnect_ep - Disconnects the endpoint if found
- * @epd: The end point returned from scif_open()
- */
-static struct scif_endpt *scif_disconnect_ep(struct scif_endpt *ep)
-{
- struct scifmsg msg;
- struct scif_endpt *fep = NULL;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
- int err;
-
- /*
- * Wake up any threads blocked in send()/recv() before closing
- * out the connection. Grabbing and releasing the send/recv lock
- * will ensure that any blocked senders/receivers have exited for
- * Ring 0 endpoints. It is a Ring 0 bug to call send/recv after
- * close. Ring 3 endpoints are not affected since close will not
- * be called while there are IOCTLs executing.
- */
- wake_up_interruptible(&ep->sendwq);
- wake_up_interruptible(&ep->recvwq);
- mutex_lock(&ep->sendlock);
- mutex_unlock(&ep->sendlock);
- mutex_lock(&ep->recvlock);
- mutex_unlock(&ep->recvlock);
-
- /* Remove from the connected list */
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep) {
- list_del(pos);
- fep = tmpep;
- spin_lock(&ep->lock);
- break;
- }
- }
-
- if (!fep) {
- /*
- * The other side has completed the disconnect before
- * the end point can be removed from the list. Therefore
- * the ep lock is not locked, traverse the disconnected
- * list to find the endpoint and release the conn lock.
- */
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.connlock);
- return NULL;
- }
-
- init_completion(&ep->discon);
- msg.uop = SCIF_DISCNCT;
- msg.src = ep->port;
- msg.dst = ep->peer;
- msg.payload[0] = (u64)ep;
- msg.payload[1] = ep->remote_ep;
-
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- spin_unlock(&ep->lock);
- mutex_unlock(&scif_info.connlock);
-
- if (!err)
- /* Wait for the remote node to respond with SCIF_DISCNT_ACK */
- wait_for_completion_timeout(&ep->discon,
- SCIF_NODE_ALIVE_TIMEOUT);
- return ep;
-}
-
-int scif_close(scif_epd_t epd)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
- enum scif_epd_state oldstate;
- bool flush_conn;
-
- dev_dbg(scif_info.mdev.this_device, "SCIFAPI close: ep %p %s\n",
- ep, scif_ep_states[ep->state]);
- might_sleep();
- spin_lock(&ep->lock);
- flush_conn = (ep->conn_async_state == ASYNC_CONN_INPROGRESS);
- spin_unlock(&ep->lock);
-
- if (flush_conn)
- flush_work(&scif_info.conn_work);
-
- spin_lock(&ep->lock);
- oldstate = ep->state;
-
- ep->state = SCIFEP_CLOSING;
-
- switch (oldstate) {
- case SCIFEP_ZOMBIE:
- dev_err(scif_info.mdev.this_device,
- "SCIFAPI close: zombie state unexpected\n");
- fallthrough;
- case SCIFEP_DISCONNECTED:
- spin_unlock(&ep->lock);
- scif_unregister_all_windows(epd);
- /* Remove from the disconnected list */
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.connlock);
- break;
- case SCIFEP_UNBOUND:
- case SCIFEP_BOUND:
- case SCIFEP_CONNECTING:
- spin_unlock(&ep->lock);
- break;
- case SCIFEP_MAPPING:
- case SCIFEP_CONNECTED:
- case SCIFEP_CLOSING:
- {
- spin_unlock(&ep->lock);
- scif_unregister_all_windows(epd);
- scif_disconnect_ep(ep);
- break;
- }
- case SCIFEP_LISTENING:
- case SCIFEP_CLLISTEN:
- {
- struct scif_conreq *conreq;
- struct scifmsg msg;
- struct scif_endpt *aep;
-
- spin_unlock(&ep->lock);
- mutex_lock(&scif_info.eplock);
-
- /* remove from listen list */
- list_for_each_safe(pos, tmpq, &scif_info.listen) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- if (tmpep == ep)
- list_del(pos);
- }
- /* Remove any dangling accepts */
- while (ep->acceptcnt) {
- aep = list_first_entry(&ep->li_accept,
- struct scif_endpt, liacceptlist);
- list_del(&aep->liacceptlist);
- scif_put_port(aep->port.port);
- list_for_each_safe(pos, tmpq, &scif_info.uaccept) {
- tmpep = list_entry(pos, struct scif_endpt,
- miacceptlist);
- if (tmpep == aep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.eplock);
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- tmpep = list_entry(pos,
- struct scif_endpt, list);
- if (tmpep == aep) {
- list_del(pos);
- break;
- }
- }
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- tmpep = list_entry(pos,
- struct scif_endpt, list);
- if (tmpep == aep) {
- list_del(pos);
- break;
- }
- }
- mutex_unlock(&scif_info.connlock);
- scif_teardown_ep(aep);
- mutex_lock(&scif_info.eplock);
- scif_add_epd_to_zombie_list(aep, SCIF_EPLOCK_HELD);
- ep->acceptcnt--;
- }
-
- spin_lock(&ep->lock);
- mutex_unlock(&scif_info.eplock);
-
- /* Remove and reject any pending connection requests. */
- while (ep->conreqcnt) {
- conreq = list_first_entry(&ep->conlist,
- struct scif_conreq, list);
- list_del(&conreq->list);
-
- msg.uop = SCIF_CNCT_REJ;
- msg.dst.node = conreq->msg.src.node;
- msg.dst.port = conreq->msg.src.port;
- msg.payload[0] = conreq->msg.payload[0];
- msg.payload[1] = conreq->msg.payload[1];
- /*
- * No Error Handling on purpose for scif_nodeqp_send().
- * If the remote node is lost we still want free the
- * connection requests on the self node.
- */
- scif_nodeqp_send(&scif_dev[conreq->msg.src.node],
- &msg);
- ep->conreqcnt--;
- kfree(conreq);
- }
-
- spin_unlock(&ep->lock);
- /* If a kSCIF accept is waiting wake it up */
- wake_up_interruptible(&ep->conwq);
- break;
- }
- }
- scif_put_port(ep->port.port);
- scif_anon_inode_fput(ep);
- scif_teardown_ep(ep);
- scif_add_epd_to_zombie_list(ep, !SCIF_EPLOCK_HELD);
- return 0;
-}
-EXPORT_SYMBOL_GPL(scif_close);
-
-/**
- * scif_flush() - Wakes up any blocking accepts. The endpoint will no longer
- * accept new connections.
- * @epd: The end point returned from scif_open()
- */
-int __scif_flush(scif_epd_t epd)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- switch (ep->state) {
- case SCIFEP_LISTENING:
- {
- ep->state = SCIFEP_CLLISTEN;
-
- /* If an accept is waiting wake it up */
- wake_up_interruptible(&ep->conwq);
- break;
- }
- default:
- break;
- }
- return 0;
-}
-
-int scif_bind(scif_epd_t epd, u16 pn)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int ret = 0;
- int tmp;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI bind: ep %p %s requested port number %d\n",
- ep, scif_ep_states[ep->state], pn);
- if (pn) {
- /*
- * Similar to IETF RFC 1700, SCIF ports below
- * SCIF_ADMIN_PORT_END can only be bound by system (or root)
- * processes or by processes executed by privileged users.
- */
- if (pn < SCIF_ADMIN_PORT_END && !capable(CAP_SYS_ADMIN)) {
- ret = -EACCES;
- goto scif_bind_admin_exit;
- }
- }
-
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_BOUND) {
- ret = -EINVAL;
- goto scif_bind_exit;
- } else if (ep->state != SCIFEP_UNBOUND) {
- ret = -EISCONN;
- goto scif_bind_exit;
- }
-
- if (pn) {
- tmp = scif_rsrv_port(pn);
- if (tmp != pn) {
- ret = -EINVAL;
- goto scif_bind_exit;
- }
- } else {
- ret = scif_get_new_port();
- if (ret < 0)
- goto scif_bind_exit;
- pn = ret;
- }
-
- ep->state = SCIFEP_BOUND;
- ep->port.node = scif_info.nodeid;
- ep->port.port = pn;
- ep->conn_async_state = ASYNC_CONN_IDLE;
- ret = pn;
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI bind: bound to port number %d\n", pn);
-scif_bind_exit:
- spin_unlock(&ep->lock);
-scif_bind_admin_exit:
- return ret;
-}
-EXPORT_SYMBOL_GPL(scif_bind);
-
-int scif_listen(scif_epd_t epd, int backlog)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI listen: ep %p %s\n", ep, scif_ep_states[ep->state]);
- spin_lock(&ep->lock);
- switch (ep->state) {
- case SCIFEP_ZOMBIE:
- case SCIFEP_CLOSING:
- case SCIFEP_CLLISTEN:
- case SCIFEP_UNBOUND:
- case SCIFEP_DISCONNECTED:
- spin_unlock(&ep->lock);
- return -EINVAL;
- case SCIFEP_LISTENING:
- case SCIFEP_CONNECTED:
- case SCIFEP_CONNECTING:
- case SCIFEP_MAPPING:
- spin_unlock(&ep->lock);
- return -EISCONN;
- case SCIFEP_BOUND:
- break;
- }
-
- ep->state = SCIFEP_LISTENING;
- ep->backlog = backlog;
-
- ep->conreqcnt = 0;
- ep->acceptcnt = 0;
- INIT_LIST_HEAD(&ep->conlist);
- init_waitqueue_head(&ep->conwq);
- INIT_LIST_HEAD(&ep->li_accept);
- spin_unlock(&ep->lock);
-
- /*
- * Listen status is complete so delete the qp information not needed
- * on a listen before placing on the list of listening ep's
- */
- scif_teardown_ep(ep);
- ep->qp_info.qp = NULL;
-
- mutex_lock(&scif_info.eplock);
- list_add_tail(&ep->list, &scif_info.listen);
- mutex_unlock(&scif_info.eplock);
- return 0;
-}
-EXPORT_SYMBOL_GPL(scif_listen);
-
-/*
- ************************************************************************
- * SCIF connection flow:
- *
- * 1) A SCIF listening endpoint can call scif_accept(..) to wait for SCIF
- * connections via a SCIF_CNCT_REQ message
- * 2) A SCIF endpoint can initiate a SCIF connection by calling
- * scif_connect(..) which calls scif_setup_qp_connect(..) which
- * allocates the local qp for the endpoint ring buffer and then sends
- * a SCIF_CNCT_REQ to the remote node and waits for a SCIF_CNCT_GNT or
- * a SCIF_CNCT_REJ message
- * 3) The peer node handles a SCIF_CNCT_REQ via scif_cnctreq_resp(..) which
- * wakes up any threads blocked in step 1 or sends a SCIF_CNCT_REJ
- * message otherwise
- * 4) A thread blocked waiting for incoming connections allocates its local
- * endpoint QP and ring buffer following which it sends a SCIF_CNCT_GNT
- * and waits for a SCIF_CNCT_GNT(N)ACK. If the allocation fails then
- * the node sends a SCIF_CNCT_REJ message
- * 5) Upon receipt of a SCIF_CNCT_GNT or a SCIF_CNCT_REJ message the
- * connecting endpoint is woken up as part of handling
- * scif_cnctgnt_resp(..) following which it maps the remote endpoints'
- * QP, updates its outbound QP and sends a SCIF_CNCT_GNTACK message on
- * success or a SCIF_CNCT_GNTNACK message on failure and completes
- * the scif_connect(..) API
- * 6) Upon receipt of a SCIF_CNCT_GNT(N)ACK the accepting endpoint blocked
- * in step 4 is woken up and completes the scif_accept(..) API
- * 7) The SCIF connection is now established between the two SCIF endpoints.
- */
-static int scif_conn_func(struct scif_endpt *ep)
-{
- int err = 0;
- struct scifmsg msg;
- struct device *spdev;
-
- err = scif_reserve_dma_chan(ep);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- ep->state = SCIFEP_BOUND;
- goto connect_error_simple;
- }
- /* Initiate the first part of the endpoint QP setup */
- err = scif_setup_qp_connect(ep->qp_info.qp, &ep->qp_info.qp_offset,
- SCIF_ENDPT_QP_SIZE, ep->remote_dev);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s err %d qp_offset 0x%llx\n",
- __func__, err, ep->qp_info.qp_offset);
- ep->state = SCIFEP_BOUND;
- goto connect_error_simple;
- }
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- goto cleanup_qp;
- }
- /* Format connect message and send it */
- msg.src = ep->port;
- msg.dst = ep->conn_port;
- msg.uop = SCIF_CNCT_REQ;
- msg.payload[0] = (u64)ep;
- msg.payload[1] = ep->qp_info.qp_offset;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- if (err)
- goto connect_error_dec;
- scif_put_peer_dev(spdev);
- /*
- * Wait for the remote node to respond with SCIF_CNCT_GNT or
- * SCIF_CNCT_REJ message.
- */
- err = wait_event_timeout(ep->conwq, ep->state != SCIFEP_CONNECTING,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d timeout\n", __func__, __LINE__);
- ep->state = SCIFEP_BOUND;
- }
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- goto cleanup_qp;
- }
- if (ep->state == SCIFEP_MAPPING) {
- err = scif_setup_qp_connect_response(ep->remote_dev,
- ep->qp_info.qp,
- ep->qp_info.gnt_pld);
- /*
- * If the resource to map the queue are not available then
- * we need to tell the other side to terminate the accept
- */
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- msg.uop = SCIF_CNCT_GNTNACK;
- msg.payload[0] = ep->remote_ep;
- _scif_nodeqp_send(ep->remote_dev, &msg);
- ep->state = SCIFEP_BOUND;
- goto connect_error_dec;
- }
-
- msg.uop = SCIF_CNCT_GNTACK;
- msg.payload[0] = ep->remote_ep;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- if (err) {
- ep->state = SCIFEP_BOUND;
- goto connect_error_dec;
- }
- ep->state = SCIFEP_CONNECTED;
- mutex_lock(&scif_info.connlock);
- list_add_tail(&ep->list, &scif_info.connected);
- mutex_unlock(&scif_info.connlock);
- dev_dbg(&ep->remote_dev->sdev->dev,
- "SCIFAPI connect: ep %p connected\n", ep);
- } else if (ep->state == SCIFEP_BOUND) {
- dev_dbg(&ep->remote_dev->sdev->dev,
- "SCIFAPI connect: ep %p connection refused\n", ep);
- err = -ECONNREFUSED;
- goto connect_error_dec;
- }
- scif_put_peer_dev(spdev);
- return err;
-connect_error_dec:
- scif_put_peer_dev(spdev);
-cleanup_qp:
- scif_cleanup_ep_qp(ep);
-connect_error_simple:
- return err;
-}
-
-/*
- * scif_conn_handler:
- *
- * Workqueue handler for servicing non-blocking SCIF connect
- *
- */
-void scif_conn_handler(struct work_struct *work)
-{
- struct scif_endpt *ep;
-
- do {
- ep = NULL;
- spin_lock(&scif_info.nb_connect_lock);
- if (!list_empty(&scif_info.nb_connect_list)) {
- ep = list_first_entry(&scif_info.nb_connect_list,
- struct scif_endpt, conn_list);
- list_del(&ep->conn_list);
- }
- spin_unlock(&scif_info.nb_connect_lock);
- if (ep) {
- ep->conn_err = scif_conn_func(ep);
- wake_up_interruptible(&ep->conn_pend_wq);
- }
- } while (ep);
-}
-
-int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
- struct scif_dev *remote_dev;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device, "SCIFAPI connect: ep %p %s\n", ep,
- scif_ep_states[ep->state]);
-
- if (!scif_dev || dst->node > scif_info.maxid)
- return -ENODEV;
-
- might_sleep();
-
- remote_dev = &scif_dev[dst->node];
- spdev = scif_get_peer_dev(remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
-
- spin_lock(&ep->lock);
- switch (ep->state) {
- case SCIFEP_ZOMBIE:
- case SCIFEP_CLOSING:
- err = -EINVAL;
- break;
- case SCIFEP_DISCONNECTED:
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
- ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
- else
- err = -EINVAL;
- break;
- case SCIFEP_LISTENING:
- case SCIFEP_CLLISTEN:
- err = -EOPNOTSUPP;
- break;
- case SCIFEP_CONNECTING:
- case SCIFEP_MAPPING:
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
- err = -EINPROGRESS;
- else
- err = -EISCONN;
- break;
- case SCIFEP_CONNECTED:
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS)
- ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
- else
- err = -EISCONN;
- break;
- case SCIFEP_UNBOUND:
- err = scif_get_new_port();
- if (err < 0)
- break;
- ep->port.port = err;
- ep->port.node = scif_info.nodeid;
- ep->conn_async_state = ASYNC_CONN_IDLE;
- fallthrough;
- case SCIFEP_BOUND:
- /*
- * If a non-blocking connect has been already initiated
- * (conn_async_state is either ASYNC_CONN_INPROGRESS or
- * ASYNC_CONN_FLUSH_WORK), the end point could end up in
- * SCIF_BOUND due an error in the connection process
- * (e.g., connection refused) If conn_async_state is
- * ASYNC_CONN_INPROGRESS - transition to ASYNC_CONN_FLUSH_WORK
- * so that the error status can be collected. If the state is
- * already ASYNC_CONN_FLUSH_WORK - then set the error to
- * EINPROGRESS since some other thread is waiting to collect
- * error status.
- */
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- ep->conn_async_state = ASYNC_CONN_FLUSH_WORK;
- } else if (ep->conn_async_state == ASYNC_CONN_FLUSH_WORK) {
- err = -EINPROGRESS;
- } else {
- ep->conn_port = *dst;
- init_waitqueue_head(&ep->sendwq);
- init_waitqueue_head(&ep->recvwq);
- init_waitqueue_head(&ep->conwq);
- ep->conn_async_state = 0;
-
- if (unlikely(non_block))
- ep->conn_async_state = ASYNC_CONN_INPROGRESS;
- }
- break;
- }
-
- if (err || ep->conn_async_state == ASYNC_CONN_FLUSH_WORK)
- goto connect_simple_unlock1;
-
- ep->state = SCIFEP_CONNECTING;
- ep->remote_dev = &scif_dev[dst->node];
- ep->qp_info.qp->magic = SCIFEP_MAGIC;
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- init_waitqueue_head(&ep->conn_pend_wq);
- spin_lock(&scif_info.nb_connect_lock);
- list_add_tail(&ep->conn_list, &scif_info.nb_connect_list);
- spin_unlock(&scif_info.nb_connect_lock);
- err = -EINPROGRESS;
- schedule_work(&scif_info.conn_work);
- }
-connect_simple_unlock1:
- spin_unlock(&ep->lock);
- scif_put_peer_dev(spdev);
- if (err) {
- return err;
- } else if (ep->conn_async_state == ASYNC_CONN_FLUSH_WORK) {
- flush_work(&scif_info.conn_work);
- err = ep->conn_err;
- spin_lock(&ep->lock);
- ep->conn_async_state = ASYNC_CONN_IDLE;
- spin_unlock(&ep->lock);
- } else {
- err = scif_conn_func(ep);
- }
- return err;
-}
-
-int scif_connect(scif_epd_t epd, struct scif_port_id *dst)
-{
- return __scif_connect(epd, dst, false);
-}
-EXPORT_SYMBOL_GPL(scif_connect);
-
-/*
- * scif_accept() - Accept a connection request from the remote node
- *
- * The function accepts a connection request from the remote node. Successful
- * complete is indicate by a new end point being created and passed back
- * to the caller for future reference.
- *
- * Upon successful complete a zero will be returned and the peer information
- * will be filled in.
- *
- * If the end point is not in the listening state -EINVAL will be returned.
- *
- * If during the connection sequence resource allocation fails the -ENOMEM
- * will be returned.
- *
- * If the function is called with the ASYNC flag set and no connection requests
- * are pending it will return -EAGAIN.
- *
- * If the remote side is not sending any connection requests the caller may
- * terminate this function with a signal. If so a -EINTR will be returned.
- */
-int scif_accept(scif_epd_t epd, struct scif_port_id *peer,
- scif_epd_t *newepd, int flags)
-{
- struct scif_endpt *lep = (struct scif_endpt *)epd;
- struct scif_endpt *cep;
- struct scif_conreq *conreq;
- struct scifmsg msg;
- int err;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI accept: ep %p %s\n", lep, scif_ep_states[lep->state]);
-
- if (flags & ~SCIF_ACCEPT_SYNC)
- return -EINVAL;
-
- if (!peer || !newepd)
- return -EINVAL;
-
- might_sleep();
- spin_lock(&lep->lock);
- if (lep->state != SCIFEP_LISTENING) {
- spin_unlock(&lep->lock);
- return -EINVAL;
- }
-
- if (!lep->conreqcnt && !(flags & SCIF_ACCEPT_SYNC)) {
- /* No connection request present and we do not want to wait */
- spin_unlock(&lep->lock);
- return -EAGAIN;
- }
-
- lep->files = current->files;
-retry_connection:
- spin_unlock(&lep->lock);
- /* Wait for the remote node to send us a SCIF_CNCT_REQ */
- err = wait_event_interruptible(lep->conwq,
- (lep->conreqcnt ||
- (lep->state != SCIFEP_LISTENING)));
- if (err)
- return err;
-
- if (lep->state != SCIFEP_LISTENING)
- return -EINTR;
-
- spin_lock(&lep->lock);
-
- if (!lep->conreqcnt)
- goto retry_connection;
-
- /* Get the first connect request off the list */
- conreq = list_first_entry(&lep->conlist, struct scif_conreq, list);
- list_del(&conreq->list);
- lep->conreqcnt--;
- spin_unlock(&lep->lock);
-
- /* Fill in the peer information */
- peer->node = conreq->msg.src.node;
- peer->port = conreq->msg.src.port;
-
- cep = kzalloc(sizeof(*cep), GFP_KERNEL);
- if (!cep) {
- err = -ENOMEM;
- goto scif_accept_error_epalloc;
- }
- spin_lock_init(&cep->lock);
- mutex_init(&cep->sendlock);
- mutex_init(&cep->recvlock);
- cep->state = SCIFEP_CONNECTING;
- cep->remote_dev = &scif_dev[peer->node];
- cep->remote_ep = conreq->msg.payload[0];
-
- scif_rma_ep_init(cep);
-
- err = scif_reserve_dma_chan(cep);
- if (err) {
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto scif_accept_error_qpalloc;
- }
-
- cep->qp_info.qp = kzalloc(sizeof(*cep->qp_info.qp), GFP_KERNEL);
- if (!cep->qp_info.qp) {
- err = -ENOMEM;
- goto scif_accept_error_qpalloc;
- }
-
- err = scif_anon_inode_getfile(cep);
- if (err)
- goto scif_accept_error_anon_inode;
-
- cep->qp_info.qp->magic = SCIFEP_MAGIC;
- spdev = scif_get_peer_dev(cep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- goto scif_accept_error_map;
- }
- err = scif_setup_qp_accept(cep->qp_info.qp, &cep->qp_info.qp_offset,
- conreq->msg.payload[1], SCIF_ENDPT_QP_SIZE,
- cep->remote_dev);
- if (err) {
- dev_dbg(&cep->remote_dev->sdev->dev,
- "SCIFAPI accept: ep %p new %p scif_setup_qp_accept %d qp_offset 0x%llx\n",
- lep, cep, err, cep->qp_info.qp_offset);
- scif_put_peer_dev(spdev);
- goto scif_accept_error_map;
- }
-
- cep->port.node = lep->port.node;
- cep->port.port = lep->port.port;
- cep->peer.node = peer->node;
- cep->peer.port = peer->port;
- init_waitqueue_head(&cep->sendwq);
- init_waitqueue_head(&cep->recvwq);
- init_waitqueue_head(&cep->conwq);
-
- msg.uop = SCIF_CNCT_GNT;
- msg.src = cep->port;
- msg.payload[0] = cep->remote_ep;
- msg.payload[1] = cep->qp_info.qp_offset;
- msg.payload[2] = (u64)cep;
-
- err = _scif_nodeqp_send(cep->remote_dev, &msg);
- scif_put_peer_dev(spdev);
- if (err)
- goto scif_accept_error_map;
-retry:
- /* Wait for the remote node to respond with SCIF_CNCT_GNT(N)ACK */
- err = wait_event_timeout(cep->conwq, cep->state != SCIFEP_CONNECTING,
- SCIF_NODE_ACCEPT_TIMEOUT);
- if (!err && scifdev_alive(cep))
- goto retry;
- err = !err ? -ENODEV : 0;
- if (err)
- goto scif_accept_error_map;
- kfree(conreq);
-
- spin_lock(&cep->lock);
-
- if (cep->state == SCIFEP_CLOSING) {
- /*
- * Remote failed to allocate resources and NAKed the grant.
- * There is at this point nothing referencing the new end point.
- */
- spin_unlock(&cep->lock);
- scif_teardown_ep(cep);
- kfree(cep);
-
- /* If call with sync flag then go back and wait. */
- if (flags & SCIF_ACCEPT_SYNC) {
- spin_lock(&lep->lock);
- goto retry_connection;
- }
- return -EAGAIN;
- }
-
- scif_get_port(cep->port.port);
- *newepd = (scif_epd_t)cep;
- spin_unlock(&cep->lock);
- return 0;
-scif_accept_error_map:
- scif_anon_inode_fput(cep);
-scif_accept_error_anon_inode:
- scif_teardown_ep(cep);
-scif_accept_error_qpalloc:
- kfree(cep);
-scif_accept_error_epalloc:
- msg.uop = SCIF_CNCT_REJ;
- msg.dst.node = conreq->msg.src.node;
- msg.dst.port = conreq->msg.src.port;
- msg.payload[0] = conreq->msg.payload[0];
- msg.payload[1] = conreq->msg.payload[1];
- scif_nodeqp_send(&scif_dev[conreq->msg.src.node], &msg);
- kfree(conreq);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_accept);
-
-/*
- * scif_msg_param_check:
- * @epd: The end point returned from scif_open()
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * Validate parameters for messaging APIs scif_send(..)/scif_recv(..).
- */
-static inline int scif_msg_param_check(scif_epd_t epd, int len, int flags)
-{
- int ret = -EINVAL;
-
- if (len < 0)
- goto err_ret;
- if (flags && (!(flags & SCIF_RECV_BLOCK)))
- goto err_ret;
- ret = 0;
-err_ret:
- return ret;
-}
-
-static int _scif_send(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scifmsg notif_msg;
- int curr_xfer_len = 0, sent_len = 0, write_count;
- int ret = 0;
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (flags & SCIF_SEND_BLOCK)
- might_sleep();
-
- spin_lock(&ep->lock);
- while (sent_len != len && SCIFEP_CONNECTED == ep->state) {
- write_count = scif_rb_space(&qp->outbound_q);
- if (write_count) {
- /* Best effort to send as much data as possible */
- curr_xfer_len = min(len - sent_len, write_count);
- ret = scif_rb_write(&qp->outbound_q, msg,
- curr_xfer_len);
- if (ret < 0)
- break;
- /* Success. Update write pointer */
- scif_rb_commit(&qp->outbound_q);
- /*
- * Send a notification to the peer about the
- * produced data message.
- */
- notif_msg.src = ep->port;
- notif_msg.uop = SCIF_CLIENT_SENT;
- notif_msg.payload[0] = ep->remote_ep;
- ret = _scif_nodeqp_send(ep->remote_dev, ¬if_msg);
- if (ret)
- break;
- sent_len += curr_xfer_len;
- msg = msg + curr_xfer_len;
- continue;
- }
- curr_xfer_len = min(len - sent_len, SCIF_ENDPT_QP_SIZE - 1);
- /* Not enough RB space. return for the Non Blocking case */
- if (!(flags & SCIF_SEND_BLOCK))
- break;
-
- spin_unlock(&ep->lock);
- /* Wait for a SCIF_CLIENT_RCVD message in the Blocking case */
- ret =
- wait_event_interruptible(ep->sendwq,
- (SCIFEP_CONNECTED != ep->state) ||
- (scif_rb_space(&qp->outbound_q) >=
- curr_xfer_len));
- spin_lock(&ep->lock);
- if (ret)
- break;
- }
- if (sent_len)
- ret = sent_len;
- else if (!ret && SCIFEP_CONNECTED != ep->state)
- ret = SCIFEP_DISCONNECTED == ep->state ?
- -ECONNRESET : -ENOTCONN;
- spin_unlock(&ep->lock);
- return ret;
-}
-
-static int _scif_recv(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scifmsg notif_msg;
- int curr_recv_len = 0, remaining_len = len, read_count;
- int ret = 0;
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (flags & SCIF_RECV_BLOCK)
- might_sleep();
- spin_lock(&ep->lock);
- while (remaining_len && (SCIFEP_CONNECTED == ep->state ||
- SCIFEP_DISCONNECTED == ep->state)) {
- read_count = scif_rb_count(&qp->inbound_q, remaining_len);
- if (read_count) {
- /*
- * Best effort to recv as much data as there
- * are bytes to read in the RB particularly
- * important for the Non Blocking case.
- */
- curr_recv_len = min(remaining_len, read_count);
- scif_rb_get_next(&qp->inbound_q, msg, curr_recv_len);
- if (ep->state == SCIFEP_CONNECTED) {
- /*
- * Update the read pointer only if the endpoint
- * is still connected else the read pointer
- * might no longer exist since the peer has
- * freed resources!
- */
- scif_rb_update_read_ptr(&qp->inbound_q);
- /*
- * Send a notification to the peer about the
- * consumed data message only if the EP is in
- * SCIFEP_CONNECTED state.
- */
- notif_msg.src = ep->port;
- notif_msg.uop = SCIF_CLIENT_RCVD;
- notif_msg.payload[0] = ep->remote_ep;
- ret = _scif_nodeqp_send(ep->remote_dev,
- ¬if_msg);
- if (ret)
- break;
- }
- remaining_len -= curr_recv_len;
- msg = msg + curr_recv_len;
- continue;
- }
- /*
- * Bail out now if the EP is in SCIFEP_DISCONNECTED state else
- * we will keep looping forever.
- */
- if (ep->state == SCIFEP_DISCONNECTED)
- break;
- /*
- * Return in the Non Blocking case if there is no data
- * to read in this iteration.
- */
- if (!(flags & SCIF_RECV_BLOCK))
- break;
- curr_recv_len = min(remaining_len, SCIF_ENDPT_QP_SIZE - 1);
- spin_unlock(&ep->lock);
- /*
- * Wait for a SCIF_CLIENT_SEND message in the blocking case
- * or until other side disconnects.
- */
- ret =
- wait_event_interruptible(ep->recvwq,
- SCIFEP_CONNECTED != ep->state ||
- scif_rb_count(&qp->inbound_q,
- curr_recv_len)
- >= curr_recv_len);
- spin_lock(&ep->lock);
- if (ret)
- break;
- }
- if (len - remaining_len)
- ret = len - remaining_len;
- else if (!ret && ep->state != SCIFEP_CONNECTED)
- ret = ep->state == SCIFEP_DISCONNECTED ?
- -ECONNRESET : -ENOTCONN;
- spin_unlock(&ep->lock);
- return ret;
-}
-
-/**
- * scif_user_send() - Send data to connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the driver IOCTL entry point
- * only and is a wrapper for _scif_send().
- */
-int scif_user_send(scif_epd_t epd, void __user *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
- int sent_len = 0;
- char *tmp;
- int loop_len;
- int chunk_len = min(len, (1 << (MAX_ORDER + PAGE_SHIFT - 1)));
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI send (U): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- err = scif_msg_param_check(epd, len, flags);
- if (err)
- goto send_err;
-
- tmp = kmalloc(chunk_len, GFP_KERNEL);
- if (!tmp) {
- err = -ENOMEM;
- goto send_err;
- }
- /*
- * Grabbing the lock before breaking up the transfer in
- * multiple chunks is required to ensure that messages do
- * not get fragmented and reordered.
- */
- mutex_lock(&ep->sendlock);
- while (sent_len != len) {
- loop_len = len - sent_len;
- loop_len = min(chunk_len, loop_len);
- if (copy_from_user(tmp, msg, loop_len)) {
- err = -EFAULT;
- goto send_free_err;
- }
- err = _scif_send(epd, tmp, loop_len, flags);
- if (err < 0)
- goto send_free_err;
- sent_len += err;
- msg += err;
- if (err != loop_len)
- goto send_free_err;
- }
-send_free_err:
- mutex_unlock(&ep->sendlock);
- kfree(tmp);
-send_err:
- return err < 0 ? err : sent_len;
-}
-
-/**
- * scif_user_recv() - Receive data from connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the driver IOCTL entry point
- * only and is a wrapper for _scif_recv().
- */
-int scif_user_recv(scif_epd_t epd, void __user *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
- int recv_len = 0;
- char *tmp;
- int loop_len;
- int chunk_len = min(len, (1 << (MAX_ORDER + PAGE_SHIFT - 1)));
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI recv (U): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- err = scif_msg_param_check(epd, len, flags);
- if (err)
- goto recv_err;
-
- tmp = kmalloc(chunk_len, GFP_KERNEL);
- if (!tmp) {
- err = -ENOMEM;
- goto recv_err;
- }
- /*
- * Grabbing the lock before breaking up the transfer in
- * multiple chunks is required to ensure that messages do
- * not get fragmented and reordered.
- */
- mutex_lock(&ep->recvlock);
- while (recv_len != len) {
- loop_len = len - recv_len;
- loop_len = min(chunk_len, loop_len);
- err = _scif_recv(epd, tmp, loop_len, flags);
- if (err < 0)
- goto recv_free_err;
- if (copy_to_user(msg, tmp, err)) {
- err = -EFAULT;
- goto recv_free_err;
- }
- recv_len += err;
- msg += err;
- if (err != loop_len)
- goto recv_free_err;
- }
-recv_free_err:
- mutex_unlock(&ep->recvlock);
- kfree(tmp);
-recv_err:
- return err < 0 ? err : recv_len;
-}
-
-/**
- * scif_send() - Send data to connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the kernel mode only and is
- * a wrapper for _scif_send().
- */
-int scif_send(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int ret;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI send (K): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- ret = scif_msg_param_check(epd, len, flags);
- if (ret)
- return ret;
- if (!ep->remote_dev)
- return -ENOTCONN;
- /*
- * Grab the mutex lock in the blocking case only
- * to ensure messages do not get fragmented/reordered.
- * The non blocking mode is protected using spin locks
- * in _scif_send().
- */
- if (flags & SCIF_SEND_BLOCK)
- mutex_lock(&ep->sendlock);
-
- ret = _scif_send(epd, msg, len, flags);
-
- if (flags & SCIF_SEND_BLOCK)
- mutex_unlock(&ep->sendlock);
- return ret;
-}
-EXPORT_SYMBOL_GPL(scif_send);
-
-/**
- * scif_recv() - Receive data from connection queue
- * @epd: The end point returned from scif_open()
- * @msg: Address to place data
- * @len: Length to receive
- * @flags: blocking or non blocking
- *
- * This function is called from the kernel mode only and is
- * a wrapper for _scif_recv().
- */
-int scif_recv(scif_epd_t epd, void *msg, int len, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int ret;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI recv (K): ep %p %s\n", ep, scif_ep_states[ep->state]);
- if (!len)
- return 0;
-
- ret = scif_msg_param_check(epd, len, flags);
- if (ret)
- return ret;
- /*
- * Grab the mutex lock in the blocking case only
- * to ensure messages do not get fragmented/reordered.
- * The non blocking mode is protected using spin locks
- * in _scif_send().
- */
- if (flags & SCIF_RECV_BLOCK)
- mutex_lock(&ep->recvlock);
-
- ret = _scif_recv(epd, msg, len, flags);
-
- if (flags & SCIF_RECV_BLOCK)
- mutex_unlock(&ep->recvlock);
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(scif_recv);
-
-static inline void _scif_poll_wait(struct file *f, wait_queue_head_t *wq,
- poll_table *p, struct scif_endpt *ep)
-{
- /*
- * Because poll_wait makes a GFP_KERNEL allocation, give up the lock
- * and regrab it afterwards. Because the endpoint state might have
- * changed while the lock was given up, the state must be checked
- * again after re-acquiring the lock. The code in __scif_pollfd(..)
- * does this.
- */
- spin_unlock(&ep->lock);
- poll_wait(f, wq, p);
- spin_lock(&ep->lock);
-}
-
-__poll_t
-__scif_pollfd(struct file *f, poll_table *wait, struct scif_endpt *ep)
-{
- __poll_t mask = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI pollfd: ep %p %s\n", ep, scif_ep_states[ep->state]);
-
- spin_lock(&ep->lock);
-
- /* Endpoint is waiting for a non-blocking connect to complete */
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- _scif_poll_wait(f, &ep->conn_pend_wq, wait, ep);
- if (ep->conn_async_state == ASYNC_CONN_INPROGRESS) {
- if (ep->state == SCIFEP_CONNECTED ||
- ep->state == SCIFEP_DISCONNECTED ||
- ep->conn_err)
- mask |= EPOLLOUT;
- goto exit;
- }
- }
-
- /* Endpoint is listening for incoming connection requests */
- if (ep->state == SCIFEP_LISTENING) {
- _scif_poll_wait(f, &ep->conwq, wait, ep);
- if (ep->state == SCIFEP_LISTENING) {
- if (ep->conreqcnt)
- mask |= EPOLLIN;
- goto exit;
- }
- }
-
- /* Endpoint is connected or disconnected */
- if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED) {
- if (poll_requested_events(wait) & EPOLLIN)
- _scif_poll_wait(f, &ep->recvwq, wait, ep);
- if (poll_requested_events(wait) & EPOLLOUT)
- _scif_poll_wait(f, &ep->sendwq, wait, ep);
- if (ep->state == SCIFEP_CONNECTED ||
- ep->state == SCIFEP_DISCONNECTED) {
- /* Data can be read without blocking */
- if (scif_rb_count(&ep->qp_info.qp->inbound_q, 1))
- mask |= EPOLLIN;
- /* Data can be written without blocking */
- if (scif_rb_space(&ep->qp_info.qp->outbound_q))
- mask |= EPOLLOUT;
- /* Return EPOLLHUP if endpoint is disconnected */
- if (ep->state == SCIFEP_DISCONNECTED)
- mask |= EPOLLHUP;
- goto exit;
- }
- }
-
- /* Return EPOLLERR if the endpoint is in none of the above states */
- mask |= EPOLLERR;
-exit:
- spin_unlock(&ep->lock);
- return mask;
-}
-
-/**
- * scif_poll() - Kernel mode SCIF poll
- * @ufds: Array of scif_pollepd structures containing the end points
- * and events to poll on
- * @nfds: Size of the ufds array
- * @timeout_msecs: Timeout in msecs, -ve implies infinite timeout
- *
- * The code flow in this function is based on do_poll(..) in select.c
- *
- * Returns the number of endpoints which have pending events or 0 in
- * the event of a timeout. If a signal is used for wake up, -EINTR is
- * returned.
- */
-int
-scif_poll(struct scif_pollepd *ufds, unsigned int nfds, long timeout_msecs)
-{
- struct poll_wqueues table;
- poll_table *pt;
- int i, count = 0, timed_out = timeout_msecs == 0;
- __poll_t mask;
- u64 timeout = timeout_msecs < 0 ? MAX_SCHEDULE_TIMEOUT
- : msecs_to_jiffies(timeout_msecs);
-
- poll_initwait(&table);
- pt = &table.pt;
- while (1) {
- for (i = 0; i < nfds; i++) {
- pt->_key = ufds[i].events | EPOLLERR | EPOLLHUP;
- mask = __scif_pollfd(ufds[i].epd->anon,
- pt, ufds[i].epd);
- mask &= ufds[i].events | EPOLLERR | EPOLLHUP;
- if (mask) {
- count++;
- pt->_qproc = NULL;
- }
- ufds[i].revents = mask;
- }
- pt->_qproc = NULL;
- if (!count) {
- count = table.error;
- if (signal_pending(current))
- count = -EINTR;
- }
- if (count || timed_out)
- break;
-
- if (!schedule_timeout_interruptible(timeout))
- timed_out = 1;
- }
- poll_freewait(&table);
- return count;
-}
-EXPORT_SYMBOL_GPL(scif_poll);
-
-int scif_get_node_ids(u16 *nodes, int len, u16 *self)
-{
- int online = 0;
- int offset = 0;
- int node;
-
- if (!scif_is_mgmt_node())
- scif_get_node_info();
-
- *self = scif_info.nodeid;
- mutex_lock(&scif_info.conflock);
- len = min_t(int, len, scif_info.total);
- for (node = 0; node <= scif_info.maxid; node++) {
- if (_scifdev_alive(&scif_dev[node])) {
- online++;
- if (offset < len)
- nodes[offset++] = node;
- }
- }
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI get_node_ids total %d online %d filled in %d nodes\n",
- scif_info.total, online, offset);
- mutex_unlock(&scif_info.conflock);
-
- return online;
-}
-EXPORT_SYMBOL_GPL(scif_get_node_ids);
-
-static int scif_add_client_dev(struct device *dev, struct subsys_interface *si)
-{
- struct scif_client *client =
- container_of(si, struct scif_client, si);
- struct scif_peer_dev *spdev =
- container_of(dev, struct scif_peer_dev, dev);
-
- if (client->probe)
- client->probe(spdev);
- return 0;
-}
-
-static void scif_remove_client_dev(struct device *dev,
- struct subsys_interface *si)
-{
- struct scif_client *client =
- container_of(si, struct scif_client, si);
- struct scif_peer_dev *spdev =
- container_of(dev, struct scif_peer_dev, dev);
-
- if (client->remove)
- client->remove(spdev);
-}
-
-void scif_client_unregister(struct scif_client *client)
-{
- subsys_interface_unregister(&client->si);
-}
-EXPORT_SYMBOL_GPL(scif_client_unregister);
-
-int scif_client_register(struct scif_client *client)
-{
- struct subsys_interface *si = &client->si;
-
- si->name = client->name;
- si->subsys = &scif_peer_bus;
- si->add_dev = scif_add_client_dev;
- si->remove_dev = scif_remove_client_dev;
-
- return subsys_interface_register(&client->si);
-}
-EXPORT_SYMBOL_GPL(scif_client_register);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-#include "../common/mic_dev.h"
-#include "scif_main.h"
-
-/* Debugfs parent dir */
-static struct dentry *scif_dbg;
-
-static int scif_dev_show(struct seq_file *s, void *unused)
-{
- int node;
-
- seq_printf(s, "Total Nodes %d Self Node Id %d Maxid %d\n",
- scif_info.total, scif_info.nodeid,
- scif_info.maxid);
-
- if (!scif_dev)
- return 0;
-
- seq_printf(s, "%-16s\t%-16s\n", "node_id", "state");
-
- for (node = 0; node <= scif_info.maxid; node++)
- seq_printf(s, "%-16d\t%-16s\n", scif_dev[node].node,
- _scifdev_alive(&scif_dev[node]) ?
- "Running" : "Offline");
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(scif_dev);
-
-static void scif_display_window(struct scif_window *window, struct seq_file *s)
-{
- int j;
- struct scatterlist *sg;
- scif_pinned_pages_t pin = window->pinned_pages;
-
- seq_printf(s, "window %p type %d temp %d offset 0x%llx ",
- window, window->type, window->temp, window->offset);
- seq_printf(s, "nr_pages 0x%llx nr_contig_chunks 0x%x prot %d ",
- window->nr_pages, window->nr_contig_chunks, window->prot);
- seq_printf(s, "ref_count %d magic 0x%llx peer_window 0x%llx ",
- window->ref_count, window->magic, window->peer_window);
- seq_printf(s, "unreg_state 0x%x va_for_temp 0x%lx\n",
- window->unreg_state, window->va_for_temp);
-
- for (j = 0; j < window->nr_contig_chunks; j++)
- seq_printf(s, "page[%d] dma_addr 0x%llx num_pages 0x%llx\n", j,
- window->dma_addr[j], window->num_pages[j]);
-
- if (window->type == SCIF_WINDOW_SELF && pin)
- for (j = 0; j < window->nr_pages; j++)
- seq_printf(s, "page[%d] = pinned_pages %p address %p\n",
- j, pin->pages[j],
- page_address(pin->pages[j]));
-
- if (window->st)
- for_each_sg(window->st->sgl, sg, window->st->nents, j)
- seq_printf(s, "sg[%d] dma addr 0x%llx length 0x%x\n",
- j, sg_dma_address(sg), sg_dma_len(sg));
-}
-
-static void scif_display_all_windows(struct list_head *head, struct seq_file *s)
-{
- struct list_head *item;
- struct scif_window *window;
-
- list_for_each(item, head) {
- window = list_entry(item, struct scif_window, list);
- scif_display_window(window, s);
- }
-}
-
-static int scif_rma_show(struct seq_file *s, void *unused)
-{
- struct scif_endpt *ep;
- struct list_head *pos;
-
- mutex_lock(&scif_info.connlock);
- list_for_each(pos, &scif_info.connected) {
- ep = list_entry(pos, struct scif_endpt, list);
- seq_printf(s, "ep %p self windows\n", ep);
- mutex_lock(&ep->rma_info.rma_lock);
- scif_display_all_windows(&ep->rma_info.reg_list, s);
- seq_printf(s, "ep %p remote windows\n", ep);
- scif_display_all_windows(&ep->rma_info.remote_reg_list, s);
- mutex_unlock(&ep->rma_info.rma_lock);
- }
- mutex_unlock(&scif_info.connlock);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(scif_rma);
-
-void __init scif_init_debugfs(void)
-{
- scif_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL);
-
- debugfs_create_file("scif_dev", 0444, scif_dbg, NULL, &scif_dev_fops);
- debugfs_create_file("scif_rma", 0444, scif_dbg, NULL, &scif_rma_fops);
- debugfs_create_u8("en_msg_log", 0666, scif_dbg, &scif_info.en_msg_log);
- debugfs_create_u8("p2p_enable", 0666, scif_dbg, &scif_info.p2p_enable);
-}
-
-void scif_exit_debugfs(void)
-{
- debugfs_remove_recursive(scif_dbg);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "scif_map.h"
-
-/*
- * struct scif_dma_comp_cb - SCIF DMA completion callback
- *
- * @dma_completion_func: DMA completion callback
- * @cb_cookie: DMA completion callback cookie
- * @temp_buf: Temporary buffer
- * @temp_buf_to_free: Temporary buffer to be freed
- * @is_cache: Is a kmem_cache allocated buffer
- * @dst_offset: Destination registration offset
- * @dst_window: Destination registration window
- * @len: Length of the temp buffer
- * @temp_phys: DMA address of the temp buffer
- * @sdev: The SCIF device
- * @header_padding: padding for cache line alignment
- */
-struct scif_dma_comp_cb {
- void (*dma_completion_func)(void *cookie);
- void *cb_cookie;
- u8 *temp_buf;
- u8 *temp_buf_to_free;
- bool is_cache;
- s64 dst_offset;
- struct scif_window *dst_window;
- size_t len;
- dma_addr_t temp_phys;
- struct scif_dev *sdev;
- int header_padding;
-};
-
-/**
- * struct scif_copy_work - Work for DMA copy
- *
- * @src_offset: Starting source offset
- * @dst_offset: Starting destination offset
- * @src_window: Starting src registered window
- * @dst_window: Starting dst registered window
- * @loopback: true if this is a loopback DMA transfer
- * @len: Length of the transfer
- * @comp_cb: DMA copy completion callback
- * @remote_dev: The remote SCIF peer device
- * @fence_type: polling or interrupt based
- * @ordered: is this a tail byte ordered DMA transfer
- */
-struct scif_copy_work {
- s64 src_offset;
- s64 dst_offset;
- struct scif_window *src_window;
- struct scif_window *dst_window;
- int loopback;
- size_t len;
- struct scif_dma_comp_cb *comp_cb;
- struct scif_dev *remote_dev;
- int fence_type;
- bool ordered;
-};
-
-/**
- * scif_reserve_dma_chan:
- * @ep: Endpoint Descriptor.
- *
- * This routine reserves a DMA channel for a particular
- * endpoint. All DMA transfers for an endpoint are always
- * programmed on the same DMA channel.
- */
-int scif_reserve_dma_chan(struct scif_endpt *ep)
-{
- int err = 0;
- struct scif_dev *scifdev;
- struct scif_hw_dev *sdev;
- struct dma_chan *chan;
-
- /* Loopback DMAs are not supported on the management node */
- if (!scif_info.nodeid && scifdev_self(ep->remote_dev))
- return 0;
- if (scif_info.nodeid)
- scifdev = &scif_dev[0];
- else
- scifdev = ep->remote_dev;
- sdev = scifdev->sdev;
- if (!sdev->num_dma_ch)
- return -ENODEV;
- chan = sdev->dma_ch[scifdev->dma_ch_idx];
- scifdev->dma_ch_idx = (scifdev->dma_ch_idx + 1) % sdev->num_dma_ch;
- mutex_lock(&ep->rma_info.rma_lock);
- ep->rma_info.dma_chan = chan;
- mutex_unlock(&ep->rma_info.rma_lock);
- return err;
-}
-
-#ifdef CONFIG_MMU_NOTIFIER
-/*
- * scif_rma_destroy_tcw:
- *
- * This routine destroys temporary cached windows
- */
-static
-void __scif_rma_destroy_tcw(struct scif_mmu_notif *mmn,
- u64 start, u64 len)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- u64 start_va, end_va;
- u64 end = start + len;
-
- if (end <= start)
- return;
-
- list_for_each_safe(item, tmp, &mmn->tc_reg_list) {
- window = list_entry(item, struct scif_window, list);
- if (!len)
- break;
- start_va = window->va_for_temp;
- end_va = start_va + (window->nr_pages << PAGE_SHIFT);
- if (start < start_va && end <= start_va)
- break;
- if (start >= end_va)
- continue;
- __scif_rma_destroy_tcw_helper(window);
- }
-}
-
-static void scif_rma_destroy_tcw(struct scif_mmu_notif *mmn, u64 start, u64 len)
-{
- struct scif_endpt *ep = mmn->ep;
-
- spin_lock(&ep->rma_info.tc_lock);
- __scif_rma_destroy_tcw(mmn, start, len);
- spin_unlock(&ep->rma_info.tc_lock);
-}
-
-static void scif_rma_destroy_tcw_ep(struct scif_endpt *ep)
-{
- struct list_head *item, *tmp;
- struct scif_mmu_notif *mmn;
-
- list_for_each_safe(item, tmp, &ep->rma_info.mmn_list) {
- mmn = list_entry(item, struct scif_mmu_notif, list);
- scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
- }
-}
-
-static void __scif_rma_destroy_tcw_ep(struct scif_endpt *ep)
-{
- struct list_head *item, *tmp;
- struct scif_mmu_notif *mmn;
-
- spin_lock(&ep->rma_info.tc_lock);
- list_for_each_safe(item, tmp, &ep->rma_info.mmn_list) {
- mmn = list_entry(item, struct scif_mmu_notif, list);
- __scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
- }
- spin_unlock(&ep->rma_info.tc_lock);
-}
-
-static bool scif_rma_tc_can_cache(struct scif_endpt *ep, size_t cur_bytes)
-{
- if ((cur_bytes >> PAGE_SHIFT) > scif_info.rma_tc_limit)
- return false;
- if ((atomic_read(&ep->rma_info.tcw_total_pages)
- + (cur_bytes >> PAGE_SHIFT)) >
- scif_info.rma_tc_limit) {
- dev_info(scif_info.mdev.this_device,
- "%s %d total=%d, current=%zu reached max\n",
- __func__, __LINE__,
- atomic_read(&ep->rma_info.tcw_total_pages),
- (1 + (cur_bytes >> PAGE_SHIFT)));
- scif_rma_destroy_tcw_invalid();
- __scif_rma_destroy_tcw_ep(ep);
- }
- return true;
-}
-
-static void scif_mmu_notifier_release(struct mmu_notifier *mn,
- struct mm_struct *mm)
-{
- struct scif_mmu_notif *mmn;
-
- mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
- scif_rma_destroy_tcw(mmn, 0, ULONG_MAX);
- schedule_work(&scif_info.misc_work);
-}
-
-static int scif_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
-{
- struct scif_mmu_notif *mmn;
-
- mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
- scif_rma_destroy_tcw(mmn, range->start, range->end - range->start);
-
- return 0;
-}
-
-static void scif_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
-{
- /*
- * Nothing to do here, everything needed was done in
- * invalidate_range_start.
- */
-}
-
-static const struct mmu_notifier_ops scif_mmu_notifier_ops = {
- .release = scif_mmu_notifier_release,
- .clear_flush_young = NULL,
- .invalidate_range_start = scif_mmu_notifier_invalidate_range_start,
- .invalidate_range_end = scif_mmu_notifier_invalidate_range_end};
-
-static void scif_ep_unregister_mmu_notifier(struct scif_endpt *ep)
-{
- struct scif_endpt_rma_info *rma = &ep->rma_info;
- struct scif_mmu_notif *mmn = NULL;
- struct list_head *item, *tmp;
-
- mutex_lock(&ep->rma_info.mmn_lock);
- list_for_each_safe(item, tmp, &rma->mmn_list) {
- mmn = list_entry(item, struct scif_mmu_notif, list);
- mmu_notifier_unregister(&mmn->ep_mmu_notifier, mmn->mm);
- list_del(item);
- kfree(mmn);
- }
- mutex_unlock(&ep->rma_info.mmn_lock);
-}
-
-static void scif_init_mmu_notifier(struct scif_mmu_notif *mmn,
- struct mm_struct *mm, struct scif_endpt *ep)
-{
- mmn->ep = ep;
- mmn->mm = mm;
- mmn->ep_mmu_notifier.ops = &scif_mmu_notifier_ops;
- INIT_LIST_HEAD(&mmn->list);
- INIT_LIST_HEAD(&mmn->tc_reg_list);
-}
-
-static struct scif_mmu_notif *
-scif_find_mmu_notifier(struct mm_struct *mm, struct scif_endpt_rma_info *rma)
-{
- struct scif_mmu_notif *mmn;
-
- list_for_each_entry(mmn, &rma->mmn_list, list)
- if (mmn->mm == mm)
- return mmn;
- return NULL;
-}
-
-static struct scif_mmu_notif *
-scif_add_mmu_notifier(struct mm_struct *mm, struct scif_endpt *ep)
-{
- struct scif_mmu_notif *mmn
- = kzalloc(sizeof(*mmn), GFP_KERNEL);
-
- if (!mmn)
- return ERR_PTR(-ENOMEM);
-
- scif_init_mmu_notifier(mmn, current->mm, ep);
- if (mmu_notifier_register(&mmn->ep_mmu_notifier, current->mm)) {
- kfree(mmn);
- return ERR_PTR(-EBUSY);
- }
- list_add(&mmn->list, &ep->rma_info.mmn_list);
- return mmn;
-}
-
-/*
- * Called from the misc thread to destroy temporary cached windows and
- * unregister the MMU notifier for the SCIF endpoint.
- */
-void scif_mmu_notif_handler(struct work_struct *work)
-{
- struct list_head *pos, *tmpq;
- struct scif_endpt *ep;
-restart:
- scif_rma_destroy_tcw_invalid();
- spin_lock(&scif_info.rmalock);
- list_for_each_safe(pos, tmpq, &scif_info.mmu_notif_cleanup) {
- ep = list_entry(pos, struct scif_endpt, mmu_list);
- list_del(&ep->mmu_list);
- spin_unlock(&scif_info.rmalock);
- scif_rma_destroy_tcw_ep(ep);
- scif_ep_unregister_mmu_notifier(ep);
- goto restart;
- }
- spin_unlock(&scif_info.rmalock);
-}
-
-static bool scif_is_set_reg_cache(int flags)
-{
- return !!(flags & SCIF_RMA_USECACHE);
-}
-#else
-static struct scif_mmu_notif *
-scif_find_mmu_notifier(struct mm_struct *mm,
- struct scif_endpt_rma_info *rma)
-{
- return NULL;
-}
-
-static struct scif_mmu_notif *
-scif_add_mmu_notifier(struct mm_struct *mm, struct scif_endpt *ep)
-{
- return NULL;
-}
-
-void scif_mmu_notif_handler(struct work_struct *work)
-{
-}
-
-static bool scif_is_set_reg_cache(int flags)
-{
- return false;
-}
-
-static bool scif_rma_tc_can_cache(struct scif_endpt *ep, size_t cur_bytes)
-{
- return false;
-}
-#endif
-
-/**
- * scif_register_temp:
- * @epd: End Point Descriptor.
- * @addr: virtual address to/from which to copy
- * @len: length of range to copy
- * @prot: read/write protection
- * @out_offset: computed offset returned by reference.
- * @out_window: allocated registered window returned by reference.
- *
- * Create a temporary registered window. The peer will not know about this
- * window. This API is used for scif_vreadfrom()/scif_vwriteto() API's.
- */
-static int
-scif_register_temp(scif_epd_t epd, unsigned long addr, size_t len, int prot,
- off_t *out_offset, struct scif_window **out_window)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err;
- scif_pinned_pages_t pinned_pages;
- size_t aligned_len;
-
- aligned_len = ALIGN(len, PAGE_SIZE);
-
- err = __scif_pin_pages((void *)(addr & PAGE_MASK),
- aligned_len, &prot, 0, &pinned_pages);
- if (err)
- return err;
-
- pinned_pages->prot = prot;
-
- /* Compute the offset for this registration */
- err = scif_get_window_offset(ep, 0, 0,
- aligned_len >> PAGE_SHIFT,
- (s64 *)out_offset);
- if (err)
- goto error_unpin;
-
- /* Allocate and prepare self registration window */
- *out_window = scif_create_window(ep, aligned_len >> PAGE_SHIFT,
- *out_offset, true);
- if (!*out_window) {
- scif_free_window_offset(ep, NULL, *out_offset);
- err = -ENOMEM;
- goto error_unpin;
- }
-
- (*out_window)->pinned_pages = pinned_pages;
- (*out_window)->nr_pages = pinned_pages->nr_pages;
- (*out_window)->prot = pinned_pages->prot;
-
- (*out_window)->va_for_temp = addr & PAGE_MASK;
- err = scif_map_window(ep->remote_dev, *out_window);
- if (err) {
- /* Something went wrong! Rollback */
- scif_destroy_window(ep, *out_window);
- *out_window = NULL;
- } else {
- *out_offset |= (addr - (*out_window)->va_for_temp);
- }
- return err;
-error_unpin:
- if (err)
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- scif_unpin_pages(pinned_pages);
- return err;
-}
-
-#define SCIF_DMA_TO (3 * HZ)
-
-/*
- * scif_sync_dma - Program a DMA without an interrupt descriptor
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @chan - DMA channel to be used.
- * @sync_wait: Wait for DMA to complete?
- *
- * Return 0 on success and -errno on error.
- */
-static int scif_sync_dma(struct scif_hw_dev *sdev, struct dma_chan *chan,
- bool sync_wait)
-{
- int err = 0;
- struct dma_async_tx_descriptor *tx = NULL;
- enum dma_ctrl_flags flags = DMA_PREP_FENCE;
- dma_cookie_t cookie;
- struct dma_device *ddev;
-
- if (!chan) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- ddev = chan->device;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, flags);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- cookie = tx->tx_submit(tx);
-
- if (dma_submit_error(cookie)) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- if (!sync_wait) {
- dma_async_issue_pending(chan);
- } else {
- if (dma_sync_wait(chan, cookie) == DMA_COMPLETE) {
- err = 0;
- } else {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- }
- }
-release:
- return err;
-}
-
-static void scif_dma_callback(void *arg)
-{
- struct completion *done = (struct completion *)arg;
-
- complete(done);
-}
-
-#define SCIF_DMA_SYNC_WAIT true
-#define SCIF_DMA_POLL BIT(0)
-#define SCIF_DMA_INTR BIT(1)
-
-/*
- * scif_async_dma - Program a DMA with an interrupt descriptor
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @chan - DMA channel to be used.
- * Return 0 on success and -errno on error.
- */
-static int scif_async_dma(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
- int err = 0;
- struct dma_device *ddev;
- struct dma_async_tx_descriptor *tx = NULL;
- enum dma_ctrl_flags flags = DMA_PREP_INTERRUPT | DMA_PREP_FENCE;
- DECLARE_COMPLETION_ONSTACK(done_wait);
- dma_cookie_t cookie;
- enum dma_status status;
-
- if (!chan) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- ddev = chan->device;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, flags);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- reinit_completion(&done_wait);
- tx->callback = scif_dma_callback;
- tx->callback_param = &done_wait;
- cookie = tx->tx_submit(tx);
-
- if (dma_submit_error(cookie)) {
- err = -ENOMEM;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- dma_async_issue_pending(chan);
-
- err = wait_for_completion_timeout(&done_wait, SCIF_DMA_TO);
- if (!err) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
- err = 0;
- status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
- if (status != DMA_COMPLETE) {
- err = -EIO;
- dev_err(&sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto release;
- }
-release:
- return err;
-}
-
-/*
- * scif_drain_dma_poll - Drain all outstanding DMA operations for a particular
- * DMA channel via polling.
- *
- * @sdev - The SCIF device
- * @chan - DMA channel
- * Return 0 on success and -errno on error.
- */
-static int scif_drain_dma_poll(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
- if (!chan)
- return -EINVAL;
- return scif_sync_dma(sdev, chan, SCIF_DMA_SYNC_WAIT);
-}
-
-/*
- * scif_drain_dma_intr - Drain all outstanding DMA operations for a particular
- * DMA channel via interrupt based blocking wait.
- *
- * @sdev - The SCIF device
- * @chan - DMA channel
- * Return 0 on success and -errno on error.
- */
-int scif_drain_dma_intr(struct scif_hw_dev *sdev, struct dma_chan *chan)
-{
- if (!chan)
- return -EINVAL;
- return scif_async_dma(sdev, chan);
-}
-
-/**
- * scif_rma_destroy_windows:
- *
- * This routine destroys all windows queued for cleanup
- */
-void scif_rma_destroy_windows(void)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep;
- struct dma_chan *chan;
-
- might_sleep();
-restart:
- spin_lock(&scif_info.rmalock);
- list_for_each_safe(item, tmp, &scif_info.rma) {
- window = list_entry(item, struct scif_window,
- list);
- ep = (struct scif_endpt *)window->ep;
- chan = ep->rma_info.dma_chan;
-
- list_del_init(&window->list);
- spin_unlock(&scif_info.rmalock);
- if (!chan || !scifdev_alive(ep) ||
- !scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan))
- /* Remove window from global list */
- window->unreg_state = OP_COMPLETED;
- else
- dev_warn(&ep->remote_dev->sdev->dev,
- "DMA engine hung?\n");
- if (window->unreg_state == OP_COMPLETED) {
- if (window->type == SCIF_WINDOW_SELF)
- scif_destroy_window(ep, window);
- else
- scif_destroy_remote_window(window);
- atomic_dec(&ep->rma_info.tw_refcount);
- }
- goto restart;
- }
- spin_unlock(&scif_info.rmalock);
-}
-
-/**
- * scif_rma_destroy_tcw:
- *
- * This routine destroys temporary cached registered windows
- * which have been queued for cleanup.
- */
-void scif_rma_destroy_tcw_invalid(void)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep;
- struct dma_chan *chan;
-
- might_sleep();
-restart:
- spin_lock(&scif_info.rmalock);
- list_for_each_safe(item, tmp, &scif_info.rma_tc) {
- window = list_entry(item, struct scif_window, list);
- ep = (struct scif_endpt *)window->ep;
- chan = ep->rma_info.dma_chan;
- list_del_init(&window->list);
- spin_unlock(&scif_info.rmalock);
- mutex_lock(&ep->rma_info.rma_lock);
- if (!chan || !scifdev_alive(ep) ||
- !scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan)) {
- atomic_sub(window->nr_pages,
- &ep->rma_info.tcw_total_pages);
- scif_destroy_window(ep, window);
- atomic_dec(&ep->rma_info.tcw_refcount);
- } else {
- dev_warn(&ep->remote_dev->sdev->dev,
- "DMA engine hung?\n");
- }
- mutex_unlock(&ep->rma_info.rma_lock);
- goto restart;
- }
- spin_unlock(&scif_info.rmalock);
-}
-
-static inline
-void *_get_local_va(off_t off, struct scif_window *window, size_t len)
-{
- int page_nr = (off - window->offset) >> PAGE_SHIFT;
- off_t page_off = off & ~PAGE_MASK;
- void *va = NULL;
-
- if (window->type == SCIF_WINDOW_SELF) {
- struct page **pages = window->pinned_pages->pages;
-
- va = page_address(pages[page_nr]) + page_off;
- }
- return va;
-}
-
-static inline
-void *ioremap_remote(off_t off, struct scif_window *window,
- size_t len, struct scif_dev *dev,
- struct scif_window_iter *iter)
-{
- dma_addr_t phys = scif_off_to_dma_addr(window, off, NULL, iter);
-
- /*
- * If the DMA address is not card relative then we need the DMA
- * addresses to be an offset into the bar. The aperture base was already
- * added so subtract it here since scif_ioremap is going to add it again
- */
- if (!scifdev_self(dev) && window->type == SCIF_WINDOW_PEER &&
- dev->sdev->aper && !dev->sdev->card_rel_da)
- phys = phys - dev->sdev->aper->pa;
- return scif_ioremap(phys, len, dev);
-}
-
-static inline void
-iounmap_remote(void *virt, size_t size, struct scif_copy_work *work)
-{
- scif_iounmap(virt, size, work->remote_dev);
-}
-
-/*
- * Takes care of ordering issue caused by
- * 1. Hardware: Only in the case of cpu copy from mgmt node to card
- * because of WC memory.
- * 2. Software: If memcpy reorders copy instructions for optimization.
- * This could happen at both mgmt node and card.
- */
-static inline void
-scif_ordered_memcpy_toio(char *dst, const char *src, size_t count)
-{
- if (!count)
- return;
-
- memcpy_toio((void __iomem __force *)dst, src, --count);
- /* Order the last byte with the previous stores */
- wmb();
- *(dst + count) = *(src + count);
-}
-
-static inline void scif_unaligned_cpy_toio(char *dst, const char *src,
- size_t count, bool ordered)
-{
- if (ordered)
- scif_ordered_memcpy_toio(dst, src, count);
- else
- memcpy_toio((void __iomem __force *)dst, src, count);
-}
-
-static inline
-void scif_ordered_memcpy_fromio(char *dst, const char *src, size_t count)
-{
- if (!count)
- return;
-
- memcpy_fromio(dst, (void __iomem __force *)src, --count);
- /* Order the last byte with the previous loads */
- rmb();
- *(dst + count) = *(src + count);
-}
-
-static inline void scif_unaligned_cpy_fromio(char *dst, const char *src,
- size_t count, bool ordered)
-{
- if (ordered)
- scif_ordered_memcpy_fromio(dst, src, count);
- else
- memcpy_fromio(dst, (void __iomem __force *)src, count);
-}
-
-#define SCIF_RMA_ERROR_CODE (~(dma_addr_t)0x0)
-
-/*
- * scif_off_to_dma_addr:
- * Obtain the dma_addr given the window and the offset.
- * @window: Registered window.
- * @off: Window offset.
- * @nr_bytes: Return the number of contiguous bytes till next DMA addr index.
- * @index: Return the index of the dma_addr array found.
- * @start_off: start offset of index of the dma addr array found.
- * The nr_bytes provides the callee an estimate of the maximum possible
- * DMA xfer possible while the index/start_off provide faster lookups
- * for the next iteration.
- */
-dma_addr_t scif_off_to_dma_addr(struct scif_window *window, s64 off,
- size_t *nr_bytes, struct scif_window_iter *iter)
-{
- int i, page_nr;
- s64 start, end;
- off_t page_off;
-
- if (window->nr_pages == window->nr_contig_chunks) {
- page_nr = (off - window->offset) >> PAGE_SHIFT;
- page_off = off & ~PAGE_MASK;
-
- if (nr_bytes)
- *nr_bytes = PAGE_SIZE - page_off;
- return window->dma_addr[page_nr] | page_off;
- }
- if (iter) {
- i = iter->index;
- start = iter->offset;
- } else {
- i = 0;
- start = window->offset;
- }
- for (; i < window->nr_contig_chunks; i++) {
- end = start + (window->num_pages[i] << PAGE_SHIFT);
- if (off >= start && off < end) {
- if (iter) {
- iter->index = i;
- iter->offset = start;
- }
- if (nr_bytes)
- *nr_bytes = end - off;
- return (window->dma_addr[i] + (off - start));
- }
- start += (window->num_pages[i] << PAGE_SHIFT);
- }
- dev_err(scif_info.mdev.this_device,
- "%s %d BUG. Addr not found? window %p off 0x%llx\n",
- __func__, __LINE__, window, off);
- return SCIF_RMA_ERROR_CODE;
-}
-
-/*
- * Copy between rma window and temporary buffer
- */
-static void scif_rma_local_cpu_copy(s64 offset, struct scif_window *window,
- u8 *temp, size_t rem_len, bool to_temp)
-{
- void *window_virt;
- size_t loop_len;
- int offset_in_page;
- s64 end_offset;
-
- offset_in_page = offset & ~PAGE_MASK;
- loop_len = PAGE_SIZE - offset_in_page;
-
- if (rem_len < loop_len)
- loop_len = rem_len;
-
- window_virt = _get_local_va(offset, window, loop_len);
- if (!window_virt)
- return;
- if (to_temp)
- memcpy(temp, window_virt, loop_len);
- else
- memcpy(window_virt, temp, loop_len);
-
- offset += loop_len;
- temp += loop_len;
- rem_len -= loop_len;
-
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- while (rem_len) {
- if (offset == end_offset) {
- window = list_next_entry(window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- }
- loop_len = min(PAGE_SIZE, rem_len);
- window_virt = _get_local_va(offset, window, loop_len);
- if (!window_virt)
- return;
- if (to_temp)
- memcpy(temp, window_virt, loop_len);
- else
- memcpy(window_virt, temp, loop_len);
- offset += loop_len;
- temp += loop_len;
- rem_len -= loop_len;
- }
-}
-
-/**
- * scif_rma_completion_cb:
- * @data: RMA cookie
- *
- * RMA interrupt completion callback.
- */
-static void scif_rma_completion_cb(void *data)
-{
- struct scif_dma_comp_cb *comp_cb = data;
-
- /* Free DMA Completion CB. */
- if (comp_cb->dst_window)
- scif_rma_local_cpu_copy(comp_cb->dst_offset,
- comp_cb->dst_window,
- comp_cb->temp_buf +
- comp_cb->header_padding,
- comp_cb->len, false);
- scif_unmap_single(comp_cb->temp_phys, comp_cb->sdev,
- SCIF_KMEM_UNALIGNED_BUF_SIZE);
- if (comp_cb->is_cache)
- kmem_cache_free(unaligned_cache,
- comp_cb->temp_buf_to_free);
- else
- kfree(comp_cb->temp_buf_to_free);
-}
-
-/* Copies between temporary buffer and offsets provided in work */
-static int
-scif_rma_list_dma_copy_unaligned(struct scif_copy_work *work,
- u8 *temp, struct dma_chan *chan,
- bool src_local)
-{
- struct scif_dma_comp_cb *comp_cb = work->comp_cb;
- dma_addr_t window_dma_addr, temp_dma_addr;
- dma_addr_t temp_phys = comp_cb->temp_phys;
- size_t loop_len, nr_contig_bytes = 0, remaining_len = work->len;
- int offset_in_ca, ret = 0;
- s64 end_offset, offset;
- struct scif_window *window;
- void *window_virt_addr;
- size_t tail_len;
- struct dma_async_tx_descriptor *tx;
- struct dma_device *dev = chan->device;
- dma_cookie_t cookie;
-
- if (src_local) {
- offset = work->dst_offset;
- window = work->dst_window;
- } else {
- offset = work->src_offset;
- window = work->src_window;
- }
-
- offset_in_ca = offset & (L1_CACHE_BYTES - 1);
- if (offset_in_ca) {
- loop_len = L1_CACHE_BYTES - offset_in_ca;
- loop_len = min(loop_len, remaining_len);
- window_virt_addr = ioremap_remote(offset, window,
- loop_len,
- work->remote_dev,
- NULL);
- if (!window_virt_addr)
- return -ENOMEM;
- if (src_local)
- scif_unaligned_cpy_toio(window_virt_addr, temp,
- loop_len,
- work->ordered &&
- !(remaining_len - loop_len));
- else
- scif_unaligned_cpy_fromio(temp, window_virt_addr,
- loop_len, work->ordered &&
- !(remaining_len - loop_len));
- iounmap_remote(window_virt_addr, loop_len, work);
-
- offset += loop_len;
- temp += loop_len;
- temp_phys += loop_len;
- remaining_len -= loop_len;
- }
-
- offset_in_ca = offset & ~PAGE_MASK;
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
-
- tail_len = remaining_len & (L1_CACHE_BYTES - 1);
- remaining_len -= tail_len;
- while (remaining_len) {
- if (offset == end_offset) {
- window = list_next_entry(window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- }
- if (scif_is_mgmt_node())
- temp_dma_addr = temp_phys;
- else
- /* Fix if we ever enable IOMMU on the card */
- temp_dma_addr = (dma_addr_t)virt_to_phys(temp);
- window_dma_addr = scif_off_to_dma_addr(window, offset,
- &nr_contig_bytes,
- NULL);
- loop_len = min(nr_contig_bytes, remaining_len);
- if (src_local) {
- if (work->ordered && !tail_len &&
- !(remaining_len - loop_len) &&
- loop_len != L1_CACHE_BYTES) {
- /*
- * Break up the last chunk of the transfer into
- * two steps. if there is no tail to guarantee
- * DMA ordering. SCIF_DMA_POLLING inserts
- * a status update descriptor in step 1 which
- * acts as a double sided synchronization fence
- * for the DMA engine to ensure that the last
- * cache line in step 2 is updated last.
- */
- /* Step 1) DMA: Body Length - L1_CACHE_BYTES. */
- tx =
- dev->device_prep_dma_memcpy(chan,
- window_dma_addr,
- temp_dma_addr,
- loop_len -
- L1_CACHE_BYTES,
- DMA_PREP_FENCE);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- offset += (loop_len - L1_CACHE_BYTES);
- temp_dma_addr += (loop_len - L1_CACHE_BYTES);
- window_dma_addr += (loop_len - L1_CACHE_BYTES);
- remaining_len -= (loop_len - L1_CACHE_BYTES);
- loop_len = remaining_len;
-
- /* Step 2) DMA: L1_CACHE_BYTES */
- tx =
- dev->device_prep_dma_memcpy(chan,
- window_dma_addr,
- temp_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- } else {
- tx =
- dev->device_prep_dma_memcpy(chan,
- window_dma_addr,
- temp_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- }
- } else {
- tx = dev->device_prep_dma_memcpy(chan, temp_dma_addr,
- window_dma_addr, loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- }
- offset += loop_len;
- temp += loop_len;
- temp_phys += loop_len;
- remaining_len -= loop_len;
- offset_in_ca = 0;
- }
- if (tail_len) {
- if (offset == end_offset) {
- window = list_next_entry(window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- }
- window_virt_addr = ioremap_remote(offset, window, tail_len,
- work->remote_dev,
- NULL);
- if (!window_virt_addr)
- return -ENOMEM;
- /*
- * The CPU copy for the tail bytes must be initiated only once
- * previous DMA transfers for this endpoint have completed
- * to guarantee ordering.
- */
- if (work->ordered) {
- struct scif_dev *rdev = work->remote_dev;
-
- ret = scif_drain_dma_intr(rdev->sdev, chan);
- if (ret)
- return ret;
- }
- if (src_local)
- scif_unaligned_cpy_toio(window_virt_addr, temp,
- tail_len, work->ordered);
- else
- scif_unaligned_cpy_fromio(temp, window_virt_addr,
- tail_len, work->ordered);
- iounmap_remote(window_virt_addr, tail_len, work);
- }
- tx = dev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_INTERRUPT);
- if (!tx) {
- ret = -ENOMEM;
- return ret;
- }
- tx->callback = &scif_rma_completion_cb;
- tx->callback_param = comp_cb;
- cookie = tx->tx_submit(tx);
-
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- return ret;
- }
- dma_async_issue_pending(chan);
- return 0;
-err:
- dev_err(scif_info.mdev.this_device,
- "%s %d Desc Prog Failed ret %d\n",
- __func__, __LINE__, ret);
- return ret;
-}
-
-/*
- * _scif_rma_list_dma_copy_aligned:
- *
- * Traverse all the windows and perform DMA copy.
- */
-static int _scif_rma_list_dma_copy_aligned(struct scif_copy_work *work,
- struct dma_chan *chan)
-{
- dma_addr_t src_dma_addr, dst_dma_addr;
- size_t loop_len, remaining_len, src_contig_bytes = 0;
- size_t dst_contig_bytes = 0;
- struct scif_window_iter src_win_iter;
- struct scif_window_iter dst_win_iter;
- s64 end_src_offset, end_dst_offset;
- struct scif_window *src_window = work->src_window;
- struct scif_window *dst_window = work->dst_window;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- int ret = 0;
- struct dma_async_tx_descriptor *tx;
- struct dma_device *dev = chan->device;
- dma_cookie_t cookie;
-
- remaining_len = work->len;
-
- scif_init_window_iter(src_window, &src_win_iter);
- scif_init_window_iter(dst_window, &dst_win_iter);
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- while (remaining_len) {
- if (src_offset == end_src_offset) {
- src_window = list_next_entry(src_window, list);
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(src_window, &src_win_iter);
- }
- if (dst_offset == end_dst_offset) {
- dst_window = list_next_entry(dst_window, list);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(dst_window, &dst_win_iter);
- }
-
- /* compute dma addresses for transfer */
- src_dma_addr = scif_off_to_dma_addr(src_window, src_offset,
- &src_contig_bytes,
- &src_win_iter);
- dst_dma_addr = scif_off_to_dma_addr(dst_window, dst_offset,
- &dst_contig_bytes,
- &dst_win_iter);
- loop_len = min(src_contig_bytes, dst_contig_bytes);
- loop_len = min(loop_len, remaining_len);
- if (work->ordered && !(remaining_len - loop_len)) {
- /*
- * Break up the last chunk of the transfer into two
- * steps to ensure that the last byte in step 2 is
- * updated last.
- */
- /* Step 1) DMA: Body Length - 1 */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len - 1,
- DMA_PREP_FENCE);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- src_offset += (loop_len - 1);
- dst_offset += (loop_len - 1);
- src_dma_addr += (loop_len - 1);
- dst_dma_addr += (loop_len - 1);
- remaining_len -= (loop_len - 1);
- loop_len = remaining_len;
-
- /* Step 2) DMA: 1 BYTES */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr, loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- } else {
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr, loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- }
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- }
- return ret;
-err:
- dev_err(scif_info.mdev.this_device,
- "%s %d Desc Prog Failed ret %d\n",
- __func__, __LINE__, ret);
- return ret;
-}
-
-/*
- * scif_rma_list_dma_copy_aligned:
- *
- * Traverse all the windows and perform DMA copy.
- */
-static int scif_rma_list_dma_copy_aligned(struct scif_copy_work *work,
- struct dma_chan *chan)
-{
- dma_addr_t src_dma_addr, dst_dma_addr;
- size_t loop_len, remaining_len, tail_len, src_contig_bytes = 0;
- size_t dst_contig_bytes = 0;
- int src_cache_off;
- s64 end_src_offset, end_dst_offset;
- struct scif_window_iter src_win_iter;
- struct scif_window_iter dst_win_iter;
- void *src_virt, *dst_virt;
- struct scif_window *src_window = work->src_window;
- struct scif_window *dst_window = work->dst_window;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- int ret = 0;
- struct dma_async_tx_descriptor *tx;
- struct dma_device *dev = chan->device;
- dma_cookie_t cookie;
-
- remaining_len = work->len;
- scif_init_window_iter(src_window, &src_win_iter);
- scif_init_window_iter(dst_window, &dst_win_iter);
-
- src_cache_off = src_offset & (L1_CACHE_BYTES - 1);
- if (src_cache_off != 0) {
- /* Head */
- loop_len = L1_CACHE_BYTES - src_cache_off;
- loop_len = min(loop_len, remaining_len);
- src_dma_addr = __scif_off_to_dma_addr(src_window, src_offset);
- dst_dma_addr = __scif_off_to_dma_addr(dst_window, dst_offset);
- if (src_window->type == SCIF_WINDOW_SELF)
- src_virt = _get_local_va(src_offset, src_window,
- loop_len);
- else
- src_virt = ioremap_remote(src_offset, src_window,
- loop_len,
- work->remote_dev, NULL);
- if (!src_virt)
- return -ENOMEM;
- if (dst_window->type == SCIF_WINDOW_SELF)
- dst_virt = _get_local_va(dst_offset, dst_window,
- loop_len);
- else
- dst_virt = ioremap_remote(dst_offset, dst_window,
- loop_len,
- work->remote_dev, NULL);
- if (!dst_virt) {
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
- return -ENOMEM;
- }
- if (src_window->type == SCIF_WINDOW_SELF)
- scif_unaligned_cpy_toio(dst_virt, src_virt, loop_len,
- remaining_len == loop_len ?
- work->ordered : false);
- else
- scif_unaligned_cpy_fromio(dst_virt, src_virt, loop_len,
- remaining_len == loop_len ?
- work->ordered : false);
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
- if (dst_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(dst_virt, loop_len, work);
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- }
-
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- tail_len = remaining_len & (L1_CACHE_BYTES - 1);
- remaining_len -= tail_len;
- while (remaining_len) {
- if (src_offset == end_src_offset) {
- src_window = list_next_entry(src_window, list);
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(src_window, &src_win_iter);
- }
- if (dst_offset == end_dst_offset) {
- dst_window = list_next_entry(dst_window, list);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- scif_init_window_iter(dst_window, &dst_win_iter);
- }
-
- /* compute dma addresses for transfer */
- src_dma_addr = scif_off_to_dma_addr(src_window, src_offset,
- &src_contig_bytes,
- &src_win_iter);
- dst_dma_addr = scif_off_to_dma_addr(dst_window, dst_offset,
- &dst_contig_bytes,
- &dst_win_iter);
- loop_len = min(src_contig_bytes, dst_contig_bytes);
- loop_len = min(loop_len, remaining_len);
- if (work->ordered && !tail_len &&
- !(remaining_len - loop_len)) {
- /*
- * Break up the last chunk of the transfer into two
- * steps. if there is no tail to gurantee DMA ordering.
- * Passing SCIF_DMA_POLLING inserts a status update
- * descriptor in step 1 which acts as a double sided
- * synchronization fence for the DMA engine to ensure
- * that the last cache line in step 2 is updated last.
- */
- /* Step 1) DMA: Body Length - L1_CACHE_BYTES. */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len -
- L1_CACHE_BYTES,
- DMA_PREP_FENCE);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- src_offset += (loop_len - L1_CACHE_BYTES);
- dst_offset += (loop_len - L1_CACHE_BYTES);
- src_dma_addr += (loop_len - L1_CACHE_BYTES);
- dst_dma_addr += (loop_len - L1_CACHE_BYTES);
- remaining_len -= (loop_len - L1_CACHE_BYTES);
- loop_len = remaining_len;
-
- /* Step 2) DMA: L1_CACHE_BYTES */
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- } else {
- tx = dev->device_prep_dma_memcpy(chan, dst_dma_addr,
- src_dma_addr,
- loop_len, 0);
- if (!tx) {
- ret = -ENOMEM;
- goto err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- ret = -ENOMEM;
- goto err;
- }
- dma_async_issue_pending(chan);
- }
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- }
- remaining_len = tail_len;
- if (remaining_len) {
- loop_len = remaining_len;
- if (src_offset == end_src_offset)
- src_window = list_next_entry(src_window, list);
- if (dst_offset == end_dst_offset)
- dst_window = list_next_entry(dst_window, list);
-
- src_dma_addr = __scif_off_to_dma_addr(src_window, src_offset);
- dst_dma_addr = __scif_off_to_dma_addr(dst_window, dst_offset);
- /*
- * The CPU copy for the tail bytes must be initiated only once
- * previous DMA transfers for this endpoint have completed to
- * guarantee ordering.
- */
- if (work->ordered) {
- struct scif_dev *rdev = work->remote_dev;
-
- ret = scif_drain_dma_poll(rdev->sdev, chan);
- if (ret)
- return ret;
- }
- if (src_window->type == SCIF_WINDOW_SELF)
- src_virt = _get_local_va(src_offset, src_window,
- loop_len);
- else
- src_virt = ioremap_remote(src_offset, src_window,
- loop_len,
- work->remote_dev, NULL);
- if (!src_virt)
- return -ENOMEM;
-
- if (dst_window->type == SCIF_WINDOW_SELF)
- dst_virt = _get_local_va(dst_offset, dst_window,
- loop_len);
- else
- dst_virt = ioremap_remote(dst_offset, dst_window,
- loop_len,
- work->remote_dev, NULL);
- if (!dst_virt) {
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
- return -ENOMEM;
- }
-
- if (src_window->type == SCIF_WINDOW_SELF)
- scif_unaligned_cpy_toio(dst_virt, src_virt, loop_len,
- work->ordered);
- else
- scif_unaligned_cpy_fromio(dst_virt, src_virt,
- loop_len, work->ordered);
- if (src_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(src_virt, loop_len, work);
-
- if (dst_window->type != SCIF_WINDOW_SELF)
- iounmap_remote(dst_virt, loop_len, work);
- remaining_len -= loop_len;
- }
- return ret;
-err:
- dev_err(scif_info.mdev.this_device,
- "%s %d Desc Prog Failed ret %d\n",
- __func__, __LINE__, ret);
- return ret;
-}
-
-/*
- * scif_rma_list_cpu_copy:
- *
- * Traverse all the windows and perform CPU copy.
- */
-static int scif_rma_list_cpu_copy(struct scif_copy_work *work)
-{
- void *src_virt, *dst_virt;
- size_t loop_len, remaining_len;
- int src_page_off, dst_page_off;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- struct scif_window *src_window = work->src_window;
- struct scif_window *dst_window = work->dst_window;
- s64 end_src_offset, end_dst_offset;
- int ret = 0;
- struct scif_window_iter src_win_iter;
- struct scif_window_iter dst_win_iter;
-
- remaining_len = work->len;
-
- scif_init_window_iter(src_window, &src_win_iter);
- scif_init_window_iter(dst_window, &dst_win_iter);
- while (remaining_len) {
- src_page_off = src_offset & ~PAGE_MASK;
- dst_page_off = dst_offset & ~PAGE_MASK;
- loop_len = min(PAGE_SIZE -
- max(src_page_off, dst_page_off),
- remaining_len);
-
- if (src_window->type == SCIF_WINDOW_SELF)
- src_virt = _get_local_va(src_offset, src_window,
- loop_len);
- else
- src_virt = ioremap_remote(src_offset, src_window,
- loop_len,
- work->remote_dev,
- &src_win_iter);
- if (!src_virt) {
- ret = -ENOMEM;
- goto error;
- }
-
- if (dst_window->type == SCIF_WINDOW_SELF)
- dst_virt = _get_local_va(dst_offset, dst_window,
- loop_len);
- else
- dst_virt = ioremap_remote(dst_offset, dst_window,
- loop_len,
- work->remote_dev,
- &dst_win_iter);
- if (!dst_virt) {
- if (src_window->type == SCIF_WINDOW_PEER)
- iounmap_remote(src_virt, loop_len, work);
- ret = -ENOMEM;
- goto error;
- }
-
- if (work->loopback) {
- memcpy(dst_virt, src_virt, loop_len);
- } else {
- if (src_window->type == SCIF_WINDOW_SELF)
- memcpy_toio((void __iomem __force *)dst_virt,
- src_virt, loop_len);
- else
- memcpy_fromio(dst_virt,
- (void __iomem __force *)src_virt,
- loop_len);
- }
- if (src_window->type == SCIF_WINDOW_PEER)
- iounmap_remote(src_virt, loop_len, work);
-
- if (dst_window->type == SCIF_WINDOW_PEER)
- iounmap_remote(dst_virt, loop_len, work);
-
- src_offset += loop_len;
- dst_offset += loop_len;
- remaining_len -= loop_len;
- if (remaining_len) {
- end_src_offset = src_window->offset +
- (src_window->nr_pages << PAGE_SHIFT);
- end_dst_offset = dst_window->offset +
- (dst_window->nr_pages << PAGE_SHIFT);
- if (src_offset == end_src_offset) {
- src_window = list_next_entry(src_window, list);
- scif_init_window_iter(src_window,
- &src_win_iter);
- }
- if (dst_offset == end_dst_offset) {
- dst_window = list_next_entry(dst_window, list);
- scif_init_window_iter(dst_window,
- &dst_win_iter);
- }
- }
- }
-error:
- return ret;
-}
-
-static int scif_rma_list_dma_copy_wrapper(struct scif_endpt *epd,
- struct scif_copy_work *work,
- struct dma_chan *chan, off_t loffset)
-{
- int src_cache_off, dst_cache_off;
- s64 src_offset = work->src_offset, dst_offset = work->dst_offset;
- u8 *temp = NULL;
- bool src_local = true;
- struct scif_dma_comp_cb *comp_cb;
- int err;
-
- if (is_dma_copy_aligned(chan->device, 1, 1, 1))
- return _scif_rma_list_dma_copy_aligned(work, chan);
-
- src_cache_off = src_offset & (L1_CACHE_BYTES - 1);
- dst_cache_off = dst_offset & (L1_CACHE_BYTES - 1);
-
- if (dst_cache_off == src_cache_off)
- return scif_rma_list_dma_copy_aligned(work, chan);
-
- if (work->loopback)
- return scif_rma_list_cpu_copy(work);
- src_local = work->src_window->type == SCIF_WINDOW_SELF;
-
- /* Allocate dma_completion cb */
- comp_cb = kzalloc(sizeof(*comp_cb), GFP_KERNEL);
- if (!comp_cb)
- goto error;
-
- work->comp_cb = comp_cb;
- comp_cb->cb_cookie = comp_cb;
- comp_cb->dma_completion_func = &scif_rma_completion_cb;
-
- if (work->len + (L1_CACHE_BYTES << 1) < SCIF_KMEM_UNALIGNED_BUF_SIZE) {
- comp_cb->is_cache = false;
- /* Allocate padding bytes to align to a cache line */
- temp = kmalloc(work->len + (L1_CACHE_BYTES << 1),
- GFP_KERNEL);
- if (!temp)
- goto free_comp_cb;
- comp_cb->temp_buf_to_free = temp;
- /* kmalloc(..) does not guarantee cache line alignment */
- if (!IS_ALIGNED((u64)temp, L1_CACHE_BYTES))
- temp = PTR_ALIGN(temp, L1_CACHE_BYTES);
- } else {
- comp_cb->is_cache = true;
- temp = kmem_cache_alloc(unaligned_cache, GFP_KERNEL);
- if (!temp)
- goto free_comp_cb;
- comp_cb->temp_buf_to_free = temp;
- }
-
- if (src_local) {
- temp += dst_cache_off;
- scif_rma_local_cpu_copy(work->src_offset, work->src_window,
- temp, work->len, true);
- } else {
- comp_cb->dst_window = work->dst_window;
- comp_cb->dst_offset = work->dst_offset;
- work->src_offset = work->src_offset - src_cache_off;
- comp_cb->len = work->len;
- work->len = ALIGN(work->len + src_cache_off, L1_CACHE_BYTES);
- comp_cb->header_padding = src_cache_off;
- }
- comp_cb->temp_buf = temp;
-
- err = scif_map_single(&comp_cb->temp_phys, temp,
- work->remote_dev, SCIF_KMEM_UNALIGNED_BUF_SIZE);
- if (err)
- goto free_temp_buf;
- comp_cb->sdev = work->remote_dev;
- if (scif_rma_list_dma_copy_unaligned(work, temp, chan, src_local) < 0)
- goto free_temp_buf;
- if (!src_local)
- work->fence_type = SCIF_DMA_INTR;
- return 0;
-free_temp_buf:
- if (comp_cb->is_cache)
- kmem_cache_free(unaligned_cache, comp_cb->temp_buf_to_free);
- else
- kfree(comp_cb->temp_buf_to_free);
-free_comp_cb:
- kfree(comp_cb);
-error:
- return -ENOMEM;
-}
-
-/**
- * scif_rma_copy:
- * @epd: end point descriptor.
- * @loffset: offset in local registered address space to/from which to copy
- * @addr: user virtual address to/from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to/from which to copy
- * @flags: flags
- * @dir: LOCAL->REMOTE or vice versa.
- * @last_chunk: true if this is the last chunk of a larger transfer
- *
- * Validate parameters, check if src/dst registered ranges requested for copy
- * are valid and initiate either CPU or DMA copy.
- */
-static int scif_rma_copy(scif_epd_t epd, off_t loffset, unsigned long addr,
- size_t len, off_t roffset, int flags,
- enum scif_rma_dir dir, bool last_chunk)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_rma_req remote_req;
- struct scif_rma_req req;
- struct scif_window *local_window = NULL;
- struct scif_window *remote_window = NULL;
- struct scif_copy_work copy_work;
- bool loopback;
- int err = 0;
- struct dma_chan *chan;
- struct scif_mmu_notif *mmn = NULL;
- bool cache = false;
- struct device *spdev;
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- if (flags && !(flags & (SCIF_RMA_USECPU | SCIF_RMA_USECACHE |
- SCIF_RMA_SYNC | SCIF_RMA_ORDERED)))
- return -EINVAL;
-
- loopback = scifdev_self(ep->remote_dev) ? true : false;
- copy_work.fence_type = ((flags & SCIF_RMA_SYNC) && last_chunk) ?
- SCIF_DMA_POLL : 0;
- copy_work.ordered = !!((flags & SCIF_RMA_ORDERED) && last_chunk);
-
- /* Use CPU for Mgmt node <-> Mgmt node copies */
- if (loopback && scif_is_mgmt_node()) {
- flags |= SCIF_RMA_USECPU;
- copy_work.fence_type = 0x0;
- }
-
- cache = scif_is_set_reg_cache(flags);
-
- remote_req.out_window = &remote_window;
- remote_req.offset = roffset;
- remote_req.nr_bytes = len;
- /*
- * If transfer is from local to remote then the remote window
- * must be writeable and vice versa.
- */
- remote_req.prot = dir == SCIF_LOCAL_TO_REMOTE ? VM_WRITE : VM_READ;
- remote_req.type = SCIF_WINDOW_PARTIAL;
- remote_req.head = &ep->rma_info.remote_reg_list;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
-
- if (addr && cache) {
- mutex_lock(&ep->rma_info.mmn_lock);
- mmn = scif_find_mmu_notifier(current->mm, &ep->rma_info);
- if (!mmn)
- mmn = scif_add_mmu_notifier(current->mm, ep);
- mutex_unlock(&ep->rma_info.mmn_lock);
- if (IS_ERR(mmn)) {
- scif_put_peer_dev(spdev);
- return PTR_ERR(mmn);
- }
- cache = cache && !scif_rma_tc_can_cache(ep, len);
- }
- mutex_lock(&ep->rma_info.rma_lock);
- if (addr) {
- req.out_window = &local_window;
- req.nr_bytes = ALIGN(len + (addr & ~PAGE_MASK),
- PAGE_SIZE);
- req.va_for_temp = addr & PAGE_MASK;
- req.prot = (dir == SCIF_LOCAL_TO_REMOTE ?
- VM_READ : VM_WRITE | VM_READ);
- /* Does a valid local window exist? */
- if (mmn) {
- spin_lock(&ep->rma_info.tc_lock);
- req.head = &mmn->tc_reg_list;
- err = scif_query_tcw(ep, &req);
- spin_unlock(&ep->rma_info.tc_lock);
- }
- if (!mmn || err) {
- err = scif_register_temp(epd, req.va_for_temp,
- req.nr_bytes, req.prot,
- &loffset, &local_window);
- if (err) {
- mutex_unlock(&ep->rma_info.rma_lock);
- goto error;
- }
- if (!cache)
- goto skip_cache;
- atomic_inc(&ep->rma_info.tcw_refcount);
- atomic_add_return(local_window->nr_pages,
- &ep->rma_info.tcw_total_pages);
- if (mmn) {
- spin_lock(&ep->rma_info.tc_lock);
- scif_insert_tcw(local_window,
- &mmn->tc_reg_list);
- spin_unlock(&ep->rma_info.tc_lock);
- }
- }
-skip_cache:
- loffset = local_window->offset +
- (addr - local_window->va_for_temp);
- } else {
- req.out_window = &local_window;
- req.offset = loffset;
- /*
- * If transfer is from local to remote then the self window
- * must be readable and vice versa.
- */
- req.prot = dir == SCIF_LOCAL_TO_REMOTE ? VM_READ : VM_WRITE;
- req.nr_bytes = len;
- req.type = SCIF_WINDOW_PARTIAL;
- req.head = &ep->rma_info.reg_list;
- /* Does a valid local window exist? */
- err = scif_query_window(&req);
- if (err) {
- mutex_unlock(&ep->rma_info.rma_lock);
- goto error;
- }
- }
-
- /* Does a valid remote window exist? */
- err = scif_query_window(&remote_req);
- if (err) {
- mutex_unlock(&ep->rma_info.rma_lock);
- goto error;
- }
-
- /*
- * Prepare copy_work for submitting work to the DMA kernel thread
- * or CPU copy routine.
- */
- copy_work.len = len;
- copy_work.loopback = loopback;
- copy_work.remote_dev = ep->remote_dev;
- if (dir == SCIF_LOCAL_TO_REMOTE) {
- copy_work.src_offset = loffset;
- copy_work.src_window = local_window;
- copy_work.dst_offset = roffset;
- copy_work.dst_window = remote_window;
- } else {
- copy_work.src_offset = roffset;
- copy_work.src_window = remote_window;
- copy_work.dst_offset = loffset;
- copy_work.dst_window = local_window;
- }
-
- if (flags & SCIF_RMA_USECPU) {
- scif_rma_list_cpu_copy(©_work);
- } else {
- chan = ep->rma_info.dma_chan;
- err = scif_rma_list_dma_copy_wrapper(epd, ©_work,
- chan, loffset);
- }
- if (addr && !cache)
- atomic_inc(&ep->rma_info.tw_refcount);
-
- mutex_unlock(&ep->rma_info.rma_lock);
-
- if (last_chunk) {
- struct scif_dev *rdev = ep->remote_dev;
-
- if (copy_work.fence_type == SCIF_DMA_POLL)
- err = scif_drain_dma_poll(rdev->sdev,
- ep->rma_info.dma_chan);
- else if (copy_work.fence_type == SCIF_DMA_INTR)
- err = scif_drain_dma_intr(rdev->sdev,
- ep->rma_info.dma_chan);
- }
-
- if (addr && !cache)
- scif_queue_for_cleanup(local_window, &scif_info.rma);
- scif_put_peer_dev(spdev);
- return err;
-error:
- if (err) {
- if (addr && local_window && !cache)
- scif_destroy_window(ep, local_window);
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d len 0x%lx\n",
- __func__, __LINE__, err, len);
- }
- scif_put_peer_dev(spdev);
- return err;
-}
-
-int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI readfrom: ep %p loffset 0x%lx len 0x%lx offset 0x%lx flags 0x%x\n",
- epd, loffset, len, roffset, flags);
- if (scif_unaligned(loffset, roffset)) {
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, loffset, 0x0,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_REMOTE_TO_LOCAL, false);
- if (err)
- goto readfrom_err;
- loffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, loffset, 0x0, len,
- roffset, flags, SCIF_REMOTE_TO_LOCAL, true);
-readfrom_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_readfrom);
-
-int scif_writeto(scif_epd_t epd, off_t loffset, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI writeto: ep %p loffset 0x%lx len 0x%lx roffset 0x%lx flags 0x%x\n",
- epd, loffset, len, roffset, flags);
- if (scif_unaligned(loffset, roffset)) {
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, loffset, 0x0,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_LOCAL_TO_REMOTE, false);
- if (err)
- goto writeto_err;
- loffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, loffset, 0x0, len,
- roffset, flags, SCIF_LOCAL_TO_REMOTE, true);
-writeto_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_writeto);
-
-int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI vreadfrom: ep %p addr %p len 0x%lx roffset 0x%lx flags 0x%x\n",
- epd, addr, len, roffset, flags);
- if (scif_unaligned((off_t __force)addr, roffset)) {
- if (len > SCIF_MAX_UNALIGNED_BUF_SIZE)
- flags &= ~SCIF_RMA_USECACHE;
-
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, 0, (u64)addr,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_REMOTE_TO_LOCAL, false);
- if (err)
- goto vreadfrom_err;
- addr += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, 0, (u64)addr, len,
- roffset, flags, SCIF_REMOTE_TO_LOCAL, true);
-vreadfrom_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_vreadfrom);
-
-int scif_vwriteto(scif_epd_t epd, void *addr, size_t len,
- off_t roffset, int flags)
-{
- int err;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI vwriteto: ep %p addr %p len 0x%lx roffset 0x%lx flags 0x%x\n",
- epd, addr, len, roffset, flags);
- if (scif_unaligned((off_t __force)addr, roffset)) {
- if (len > SCIF_MAX_UNALIGNED_BUF_SIZE)
- flags &= ~SCIF_RMA_USECACHE;
-
- while (len > SCIF_MAX_UNALIGNED_BUF_SIZE) {
- err = scif_rma_copy(epd, 0, (u64)addr,
- SCIF_MAX_UNALIGNED_BUF_SIZE,
- roffset, flags,
- SCIF_LOCAL_TO_REMOTE, false);
- if (err)
- goto vwriteto_err;
- addr += SCIF_MAX_UNALIGNED_BUF_SIZE;
- roffset += SCIF_MAX_UNALIGNED_BUF_SIZE;
- len -= SCIF_MAX_UNALIGNED_BUF_SIZE;
- }
- }
- err = scif_rma_copy(epd, 0, (u64)addr, len,
- roffset, flags, SCIF_LOCAL_TO_REMOTE, true);
-vwriteto_err:
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_vwriteto);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "scif_map.h"
-
-void scif_cleanup_ep_qp(struct scif_endpt *ep)
-{
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (qp->outbound_q.rb_base) {
- scif_iounmap((void *)qp->outbound_q.rb_base,
- qp->outbound_q.size, ep->remote_dev);
- qp->outbound_q.rb_base = NULL;
- }
- if (qp->remote_qp) {
- scif_iounmap((void *)qp->remote_qp,
- sizeof(struct scif_qp), ep->remote_dev);
- qp->remote_qp = NULL;
- }
- if (qp->local_qp) {
- scif_unmap_single(qp->local_qp, ep->remote_dev,
- sizeof(struct scif_qp));
- qp->local_qp = 0x0;
- }
- if (qp->local_buf) {
- scif_unmap_single(qp->local_buf, ep->remote_dev,
- SCIF_ENDPT_QP_SIZE);
- qp->local_buf = 0;
- }
-}
-
-void scif_teardown_ep(void *endpt)
-{
- struct scif_endpt *ep = endpt;
- struct scif_qp *qp = ep->qp_info.qp;
-
- if (qp) {
- spin_lock(&ep->lock);
- scif_cleanup_ep_qp(ep);
- spin_unlock(&ep->lock);
- kfree(qp->inbound_q.rb_base);
- kfree(qp);
- }
-}
-
-/*
- * Enqueue the endpoint to the zombie list for cleanup.
- * The endpoint should not be accessed once this API returns.
- */
-void scif_add_epd_to_zombie_list(struct scif_endpt *ep, bool eplock_held)
-{
- if (!eplock_held)
- mutex_lock(&scif_info.eplock);
- spin_lock(&ep->lock);
- ep->state = SCIFEP_ZOMBIE;
- spin_unlock(&ep->lock);
- list_add_tail(&ep->list, &scif_info.zombie);
- scif_info.nr_zombies++;
- if (!eplock_held)
- mutex_unlock(&scif_info.eplock);
- schedule_work(&scif_info.misc_work);
-}
-
-static struct scif_endpt *scif_find_listen_ep(u16 port)
-{
- struct scif_endpt *ep = NULL;
- struct list_head *pos, *tmpq;
-
- mutex_lock(&scif_info.eplock);
- list_for_each_safe(pos, tmpq, &scif_info.listen) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (ep->port.port == port) {
- mutex_unlock(&scif_info.eplock);
- return ep;
- }
- }
- mutex_unlock(&scif_info.eplock);
- return NULL;
-}
-
-void scif_cleanup_zombie_epd(void)
-{
- struct list_head *pos, *tmpq;
- struct scif_endpt *ep;
-
- mutex_lock(&scif_info.eplock);
- list_for_each_safe(pos, tmpq, &scif_info.zombie) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (scif_rma_ep_can_uninit(ep)) {
- list_del(pos);
- scif_info.nr_zombies--;
- put_iova_domain(&ep->rma_info.iovad);
- kfree(ep);
- }
- }
- mutex_unlock(&scif_info.eplock);
-}
-
-/**
- * scif_cnctreq() - Respond to SCIF_CNCT_REQ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * This message is initiated by the remote node to request a connection
- * to the local node. This function looks for an end point in the
- * listen state on the requested port id.
- *
- * If it finds a listening port it places the connect request on the
- * listening end points queue and wakes up any pending accept calls.
- *
- * If it does not find a listening end point it sends a connection
- * reject message to the remote node.
- */
-void scif_cnctreq(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = NULL;
- struct scif_conreq *conreq;
-
- conreq = kmalloc(sizeof(*conreq), GFP_KERNEL);
- if (!conreq)
- /* Lack of resources so reject the request. */
- goto conreq_sendrej;
-
- ep = scif_find_listen_ep(msg->dst.port);
- if (!ep)
- /* Send reject due to no listening ports */
- goto conreq_sendrej_free;
- else
- spin_lock(&ep->lock);
-
- if (ep->backlog <= ep->conreqcnt) {
- /* Send reject due to too many pending requests */
- spin_unlock(&ep->lock);
- goto conreq_sendrej_free;
- }
-
- conreq->msg = *msg;
- list_add_tail(&conreq->list, &ep->conlist);
- ep->conreqcnt++;
- wake_up_interruptible(&ep->conwq);
- spin_unlock(&ep->lock);
- return;
-
-conreq_sendrej_free:
- kfree(conreq);
-conreq_sendrej:
- msg->uop = SCIF_CNCT_REJ;
- scif_nodeqp_send(&scif_dev[msg->src.node], msg);
-}
-
-/**
- * scif_cnctgnt() - Respond to SCIF_CNCT_GNT interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * An accept() on the remote node has occurred and sent this message
- * to indicate success. Place the end point in the MAPPING state and
- * save the remote nodes memory information. Then wake up the connect
- * request so it can finish.
- */
-void scif_cnctgnt(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTING == ep->state) {
- ep->peer.node = msg->src.node;
- ep->peer.port = msg->src.port;
- ep->qp_info.gnt_pld = msg->payload[1];
- ep->remote_ep = msg->payload[2];
- ep->state = SCIFEP_MAPPING;
-
- wake_up(&ep->conwq);
- }
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_cnctgnt_ack() - Respond to SCIF_CNCT_GNTACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote connection request has finished mapping the local memory.
- * Place the connection in the connected state and wake up the pending
- * accept() call.
- */
-void scif_cnctgnt_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- mutex_lock(&scif_info.connlock);
- spin_lock(&ep->lock);
- /* New ep is now connected with all resources set. */
- ep->state = SCIFEP_CONNECTED;
- list_add_tail(&ep->list, &scif_info.connected);
- wake_up(&ep->conwq);
- spin_unlock(&ep->lock);
- mutex_unlock(&scif_info.connlock);
-}
-
-/**
- * scif_cnctgnt_nack() - Respond to SCIF_CNCT_GNTNACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote connection request failed to map the local memory it was sent.
- * Place the end point in the CLOSING state to indicate it and wake up
- * the pending accept();
- */
-void scif_cnctgnt_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- ep->state = SCIFEP_CLOSING;
- wake_up(&ep->conwq);
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_cnctrej() - Respond to SCIF_CNCT_REJ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote end has rejected the connection request. Set the end
- * point back to the bound state and wake up the pending connect().
- */
-void scif_cnctrej(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTING == ep->state) {
- ep->state = SCIFEP_BOUND;
- wake_up(&ep->conwq);
- }
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_discnct() - Respond to SCIF_DISCNCT interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The remote node has indicated close() has been called on its end
- * point. Remove the local end point from the connected list, set its
- * state to disconnected and ensure accesses to the remote node are
- * shutdown.
- *
- * When all accesses to the remote end have completed then send a
- * DISCNT_ACK to indicate it can remove its resources and complete
- * the close routine.
- */
-void scif_discnct(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = NULL;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
-
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- tmpep = list_entry(pos, struct scif_endpt, list);
- /*
- * The local ep may have sent a disconnect and and been closed
- * due to a message response time out. It may have been
- * allocated again and formed a new connection so we want to
- * check if the remote ep matches
- */
- if (((u64)tmpep == msg->payload[1]) &&
- ((u64)tmpep->remote_ep == msg->payload[0])) {
- list_del(pos);
- ep = tmpep;
- spin_lock(&ep->lock);
- break;
- }
- }
-
- /*
- * If the terminated end is not found then this side started closing
- * before the other side sent the disconnect. If so the ep will no
- * longer be on the connected list. Regardless the other side
- * needs to be acked to let it know close is complete.
- */
- if (!ep) {
- mutex_unlock(&scif_info.connlock);
- goto discnct_ack;
- }
-
- ep->state = SCIFEP_DISCONNECTED;
- list_add_tail(&ep->list, &scif_info.disconnected);
-
- wake_up_interruptible(&ep->sendwq);
- wake_up_interruptible(&ep->recvwq);
- spin_unlock(&ep->lock);
- mutex_unlock(&scif_info.connlock);
-
-discnct_ack:
- msg->uop = SCIF_DISCNT_ACK;
- scif_nodeqp_send(&scif_dev[msg->src.node], msg);
-}
-
-/**
- * scif_discnct_ack() - Respond to SCIF_DISCNT_ACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side has indicated it has not more references to local resources
- */
-void scif_discnt_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- ep->state = SCIFEP_DISCONNECTED;
- spin_unlock(&ep->lock);
- complete(&ep->discon);
-}
-
-/**
- * scif_clientsend() - Respond to SCIF_CLIENT_SEND interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side is confirming send or receive interrupt handling is complete.
- */
-void scif_clientsend(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTED == ep->state)
- wake_up_interruptible(&ep->recvwq);
- spin_unlock(&ep->lock);
-}
-
-/**
- * scif_clientrcvd() - Respond to SCIF_CLIENT_RCVD interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side is confirming send or receive interrupt handling is complete.
- */
-void scif_clientrcvd(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
-
- spin_lock(&ep->lock);
- if (SCIFEP_CONNECTED == ep->state)
- wake_up_interruptible(&ep->sendwq);
- spin_unlock(&ep->lock);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_EPD_H
-#define SCIF_EPD_H
-
-#include <linux/delay.h>
-#include <linux/scif.h>
-#include <linux/scif_ioctl.h>
-
-#define SCIF_EPLOCK_HELD true
-
-enum scif_epd_state {
- SCIFEP_UNBOUND,
- SCIFEP_BOUND,
- SCIFEP_LISTENING,
- SCIFEP_CONNECTED,
- SCIFEP_CONNECTING,
- SCIFEP_MAPPING,
- SCIFEP_CLOSING,
- SCIFEP_CLLISTEN,
- SCIFEP_DISCONNECTED,
- SCIFEP_ZOMBIE
-};
-
-/*
- * struct scif_conreq - Data structure added to the connection list.
- *
- * @msg: connection request message received
- * @list: link to list of connection requests
- */
-struct scif_conreq {
- struct scifmsg msg;
- struct list_head list;
-};
-
-/* Size of the RB for the Endpoint QP */
-#define SCIF_ENDPT_QP_SIZE 0x1000
-
-/*
- * scif_endpt_qp_info - SCIF endpoint queue pair
- *
- * @qp - Qpair for this endpoint
- * @qp_offset - DMA address of the QP
- * @gnt_pld - Payload in a SCIF_CNCT_GNT message containing the
- * physical address of the remote_qp.
- */
-struct scif_endpt_qp_info {
- struct scif_qp *qp;
- dma_addr_t qp_offset;
- dma_addr_t gnt_pld;
-};
-
-/*
- * struct scif_endpt - The SCIF endpoint data structure
- *
- * @state: end point state
- * @lock: lock synchronizing access to endpoint fields like state etc
- * @port: self port information
- * @peer: peer port information
- * @backlog: maximum pending connection requests
- * @qp_info: Endpoint QP information for SCIF messaging
- * @remote_dev: scifdev used by this endpt to communicate with remote node.
- * @remote_ep: remote endpoint
- * @conreqcnt: Keep track of number of connection requests.
- * @files: Open file information used to match the id passed in with
- * the flush routine.
- * @conlist: list of connection requests
- * @conwq: waitqueue for connection processing
- * @discon: completion used during disconnection
- * @sendwq: waitqueue used during sending messages
- * @recvwq: waitqueue used during message receipt
- * @sendlock: Synchronize ordering of messages sent
- * @recvlock: Synchronize ordering of messages received
- * @list: link to list of various endpoints like connected, listening etc
- * @li_accept: pending ACCEPTREG
- * @acceptcnt: pending ACCEPTREG cnt
- * @liacceptlist: link to listen accept
- * @miacceptlist: link to uaccept
- * @listenep: associated listen ep
- * @conn_work: Non blocking connect work
- * @conn_port: Connection port
- * @conn_err: Errors during connection
- * @conn_async_state: Async connection
- * @conn_pend_wq: Used by poll while waiting for incoming connections
- * @conn_list: List of async connection requests
- * @rma_info: Information for triggering SCIF RMA and DMA operations
- * @mmu_list: link to list of MMU notifier cleanup work
- * @anon: anonymous file for use in kernel mode scif poll
- */
-struct scif_endpt {
- enum scif_epd_state state;
- spinlock_t lock;
- struct scif_port_id port;
- struct scif_port_id peer;
- int backlog;
- struct scif_endpt_qp_info qp_info;
- struct scif_dev *remote_dev;
- u64 remote_ep;
- int conreqcnt;
- struct files_struct *files;
- struct list_head conlist;
- wait_queue_head_t conwq;
- struct completion discon;
- wait_queue_head_t sendwq;
- wait_queue_head_t recvwq;
- struct mutex sendlock;
- struct mutex recvlock;
- struct list_head list;
- struct list_head li_accept;
- int acceptcnt;
- struct list_head liacceptlist;
- struct list_head miacceptlist;
- struct scif_endpt *listenep;
- struct scif_port_id conn_port;
- int conn_err;
- int conn_async_state;
- wait_queue_head_t conn_pend_wq;
- struct list_head conn_list;
- struct scif_endpt_rma_info rma_info;
- struct list_head mmu_list;
- struct file *anon;
-};
-
-static inline int scifdev_alive(struct scif_endpt *ep)
-{
- return _scifdev_alive(ep->remote_dev);
-}
-
-/*
- * scif_verify_epd:
- * ep: SCIF endpoint
- *
- * Checks several generic error conditions and returns the
- * appropriate error.
- */
-static inline int scif_verify_epd(struct scif_endpt *ep)
-{
- if (ep->state == SCIFEP_DISCONNECTED)
- return -ECONNRESET;
-
- if (ep->state != SCIFEP_CONNECTED)
- return -ENOTCONN;
-
- if (!scifdev_alive(ep))
- return -ENODEV;
-
- return 0;
-}
-
-static inline int scif_anon_inode_getfile(scif_epd_t epd)
-{
- epd->anon = anon_inode_getfile("scif", &scif_anon_fops, NULL, 0);
-
- return PTR_ERR_OR_ZERO(epd->anon);
-}
-
-static inline void scif_anon_inode_fput(scif_epd_t epd)
-{
- if (epd->anon) {
- fput(epd->anon);
- epd->anon = NULL;
- }
-}
-
-void scif_cleanup_zombie_epd(void);
-void scif_teardown_ep(void *endpt);
-void scif_cleanup_ep_qp(struct scif_endpt *ep);
-void scif_add_epd_to_zombie_list(struct scif_endpt *ep, bool eplock_held);
-void scif_get_node_info(void);
-void scif_send_acks(struct scif_dev *dev);
-void scif_conn_handler(struct work_struct *work);
-int scif_rsrv_port(u16 port);
-void scif_get_port(u16 port);
-int scif_get_new_port(void);
-void scif_put_port(u16 port);
-int scif_user_send(scif_epd_t epd, void __user *msg, int len, int flags);
-int scif_user_recv(scif_epd_t epd, void __user *msg, int len, int flags);
-void scif_cnctreq(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctgnt_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_cnctrej(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_discnct(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_discnt_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_clientsend(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_clientrcvd(struct scif_dev *scifdev, struct scifmsg *msg);
-int __scif_connect(scif_epd_t epd, struct scif_port_id *dst, bool non_block);
-int __scif_flush(scif_epd_t epd);
-int scif_mmap(struct vm_area_struct *vma, scif_epd_t epd);
-__poll_t __scif_pollfd(struct file *f, poll_table *wait,
- struct scif_endpt *ep);
-int __scif_pin_pages(void *addr, size_t len, int *out_prot,
- int map_flags, scif_pinned_pages_t *pages);
-#endif /* SCIF_EPD_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-
-static int scif_fdopen(struct inode *inode, struct file *f)
-{
- struct scif_endpt *priv = scif_open();
-
- if (!priv)
- return -ENOMEM;
- f->private_data = priv;
- return 0;
-}
-
-static int scif_fdclose(struct inode *inode, struct file *f)
-{
- struct scif_endpt *priv = f->private_data;
-
- return scif_close(priv);
-}
-
-static int scif_fdmmap(struct file *f, struct vm_area_struct *vma)
-{
- struct scif_endpt *priv = f->private_data;
-
- return scif_mmap(vma, priv);
-}
-
-static __poll_t scif_fdpoll(struct file *f, poll_table *wait)
-{
- struct scif_endpt *priv = f->private_data;
-
- return __scif_pollfd(f, wait, priv);
-}
-
-static int scif_fdflush(struct file *f, fl_owner_t id)
-{
- struct scif_endpt *ep = f->private_data;
-
- spin_lock(&ep->lock);
- /*
- * The listening endpoint stashes the open file information before
- * waiting for incoming connections. The release callback would never be
- * called if the application closed the endpoint, while waiting for
- * incoming connections from a separate thread since the file descriptor
- * reference count is bumped up in the accept IOCTL. Call the flush
- * routine if the id matches the endpoint open file information so that
- * the listening endpoint can be woken up and the fd released.
- */
- if (ep->files == id)
- __scif_flush(ep);
- spin_unlock(&ep->lock);
- return 0;
-}
-
-static __always_inline void scif_err_debug(int err, const char *str)
-{
- /*
- * ENOTCONN is a common uninteresting error which is
- * flooding debug messages to the console unnecessarily.
- */
- if (err < 0 && err != -ENOTCONN)
- dev_dbg(scif_info.mdev.this_device, "%s err %d\n", str, err);
-}
-
-static long scif_fdioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
- struct scif_endpt *priv = f->private_data;
- void __user *argp = (void __user *)arg;
- int err = 0;
- struct scifioctl_msg request;
- bool non_block = false;
-
- non_block = !!(f->f_flags & O_NONBLOCK);
-
- switch (cmd) {
- case SCIF_BIND:
- {
- int pn;
-
- if (copy_from_user(&pn, argp, sizeof(pn)))
- return -EFAULT;
-
- pn = scif_bind(priv, pn);
- if (pn < 0)
- return pn;
-
- if (copy_to_user(argp, &pn, sizeof(pn)))
- return -EFAULT;
-
- return 0;
- }
- case SCIF_LISTEN:
- return scif_listen(priv, arg);
- case SCIF_CONNECT:
- {
- struct scifioctl_connect req;
- struct scif_endpt *ep = (struct scif_endpt *)priv;
-
- if (copy_from_user(&req, argp, sizeof(req)))
- return -EFAULT;
-
- err = __scif_connect(priv, &req.peer, non_block);
- if (err < 0)
- return err;
-
- req.self.node = ep->port.node;
- req.self.port = ep->port.port;
-
- if (copy_to_user(argp, &req, sizeof(req)))
- return -EFAULT;
-
- return 0;
- }
- /*
- * Accept is done in two halves. The request ioctl does the basic
- * functionality of accepting the request and returning the information
- * about it including the internal ID of the end point. The register
- * is done with the internal ID on a new file descriptor opened by the
- * requesting process.
- */
- case SCIF_ACCEPTREQ:
- {
- struct scifioctl_accept request;
- scif_epd_t *ep = (scif_epd_t *)&request.endpt;
-
- if (copy_from_user(&request, argp, sizeof(request)))
- return -EFAULT;
-
- err = scif_accept(priv, &request.peer, ep, request.flags);
- if (err < 0)
- return err;
-
- if (copy_to_user(argp, &request, sizeof(request))) {
- scif_close(*ep);
- return -EFAULT;
- }
- /*
- * Add to the list of user mode eps where the second half
- * of the accept is not yet completed.
- */
- mutex_lock(&scif_info.eplock);
- list_add_tail(&((*ep)->miacceptlist), &scif_info.uaccept);
- list_add_tail(&((*ep)->liacceptlist), &priv->li_accept);
- (*ep)->listenep = priv;
- priv->acceptcnt++;
- mutex_unlock(&scif_info.eplock);
-
- return 0;
- }
- case SCIF_ACCEPTREG:
- {
- struct scif_endpt *priv = f->private_data;
- struct scif_endpt *newep;
- struct scif_endpt *lisep;
- struct scif_endpt *fep = NULL;
- struct scif_endpt *tmpep;
- struct list_head *pos, *tmpq;
-
- /* Finally replace the pointer to the accepted endpoint */
- if (copy_from_user(&newep, argp, sizeof(void *)))
- return -EFAULT;
-
- /* Remove form the user accept queue */
- mutex_lock(&scif_info.eplock);
- list_for_each_safe(pos, tmpq, &scif_info.uaccept) {
- tmpep = list_entry(pos,
- struct scif_endpt, miacceptlist);
- if (tmpep == newep) {
- list_del(pos);
- fep = tmpep;
- break;
- }
- }
-
- if (!fep) {
- mutex_unlock(&scif_info.eplock);
- return -ENOENT;
- }
-
- lisep = newep->listenep;
- list_for_each_safe(pos, tmpq, &lisep->li_accept) {
- tmpep = list_entry(pos,
- struct scif_endpt, liacceptlist);
- if (tmpep == newep) {
- list_del(pos);
- lisep->acceptcnt--;
- break;
- }
- }
-
- mutex_unlock(&scif_info.eplock);
-
- /* Free the resources automatically created from the open. */
- scif_anon_inode_fput(priv);
- scif_teardown_ep(priv);
- scif_add_epd_to_zombie_list(priv, !SCIF_EPLOCK_HELD);
- f->private_data = newep;
- return 0;
- }
- case SCIF_SEND:
- {
- struct scif_endpt *priv = f->private_data;
-
- if (copy_from_user(&request, argp,
- sizeof(struct scifioctl_msg))) {
- err = -EFAULT;
- goto send_err;
- }
- err = scif_user_send(priv, (void __user *)request.msg,
- request.len, request.flags);
- if (err < 0)
- goto send_err;
- if (copy_to_user(&
- ((struct scifioctl_msg __user *)argp)->out_len,
- &err, sizeof(err))) {
- err = -EFAULT;
- goto send_err;
- }
- err = 0;
-send_err:
- scif_err_debug(err, "scif_send");
- return err;
- }
- case SCIF_RECV:
- {
- struct scif_endpt *priv = f->private_data;
-
- if (copy_from_user(&request, argp,
- sizeof(struct scifioctl_msg))) {
- err = -EFAULT;
- goto recv_err;
- }
-
- err = scif_user_recv(priv, (void __user *)request.msg,
- request.len, request.flags);
- if (err < 0)
- goto recv_err;
-
- if (copy_to_user(&
- ((struct scifioctl_msg __user *)argp)->out_len,
- &err, sizeof(err))) {
- err = -EFAULT;
- goto recv_err;
- }
- err = 0;
-recv_err:
- scif_err_debug(err, "scif_recv");
- return err;
- }
- case SCIF_GET_NODEIDS:
- {
- struct scifioctl_node_ids node_ids;
- int entries;
- u16 *nodes;
- void __user *unodes, *uself;
- u16 self;
-
- if (copy_from_user(&node_ids, argp, sizeof(node_ids))) {
- err = -EFAULT;
- goto getnodes_err2;
- }
-
- entries = min_t(int, scif_info.maxid, node_ids.len);
- nodes = kmalloc_array(entries, sizeof(u16), GFP_KERNEL);
- if (entries && !nodes) {
- err = -ENOMEM;
- goto getnodes_err2;
- }
- node_ids.len = scif_get_node_ids(nodes, entries, &self);
-
- unodes = (void __user *)node_ids.nodes;
- if (copy_to_user(unodes, nodes, sizeof(u16) * entries)) {
- err = -EFAULT;
- goto getnodes_err1;
- }
-
- uself = (void __user *)node_ids.self;
- if (copy_to_user(uself, &self, sizeof(u16))) {
- err = -EFAULT;
- goto getnodes_err1;
- }
-
- if (copy_to_user(argp, &node_ids, sizeof(node_ids))) {
- err = -EFAULT;
- goto getnodes_err1;
- }
-getnodes_err1:
- kfree(nodes);
-getnodes_err2:
- return err;
- }
- case SCIF_REG:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_reg reg;
- off_t ret;
-
- if (copy_from_user(®, argp, sizeof(reg))) {
- err = -EFAULT;
- goto reg_err;
- }
- if (reg.flags & SCIF_MAP_KERNEL) {
- err = -EINVAL;
- goto reg_err;
- }
- ret = scif_register(priv, (void *)reg.addr, reg.len,
- reg.offset, reg.prot, reg.flags);
- if (ret < 0) {
- err = (int)ret;
- goto reg_err;
- }
-
- if (copy_to_user(&((struct scifioctl_reg __user *)argp)
- ->out_offset, &ret, sizeof(reg.out_offset))) {
- err = -EFAULT;
- goto reg_err;
- }
- err = 0;
-reg_err:
- scif_err_debug(err, "scif_register");
- return err;
- }
- case SCIF_UNREG:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_unreg unreg;
-
- if (copy_from_user(&unreg, argp, sizeof(unreg))) {
- err = -EFAULT;
- goto unreg_err;
- }
- err = scif_unregister(priv, unreg.offset, unreg.len);
-unreg_err:
- scif_err_debug(err, "scif_unregister");
- return err;
- }
- case SCIF_READFROM:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto readfrom_err;
- }
- err = scif_readfrom(priv, copy.loffset, copy.len, copy.roffset,
- copy.flags);
-readfrom_err:
- scif_err_debug(err, "scif_readfrom");
- return err;
- }
- case SCIF_WRITETO:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto writeto_err;
- }
- err = scif_writeto(priv, copy.loffset, copy.len, copy.roffset,
- copy.flags);
-writeto_err:
- scif_err_debug(err, "scif_writeto");
- return err;
- }
- case SCIF_VREADFROM:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto vreadfrom_err;
- }
- err = scif_vreadfrom(priv, (void __force *)copy.addr, copy.len,
- copy.roffset, copy.flags);
-vreadfrom_err:
- scif_err_debug(err, "scif_vreadfrom");
- return err;
- }
- case SCIF_VWRITETO:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_copy copy;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- err = -EFAULT;
- goto vwriteto_err;
- }
- err = scif_vwriteto(priv, (void __force *)copy.addr, copy.len,
- copy.roffset, copy.flags);
-vwriteto_err:
- scif_err_debug(err, "scif_vwriteto");
- return err;
- }
- case SCIF_FENCE_MARK:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_fence_mark mark;
- int tmp_mark = 0;
-
- if (copy_from_user(&mark, argp, sizeof(mark))) {
- err = -EFAULT;
- goto fence_mark_err;
- }
- err = scif_fence_mark(priv, mark.flags, &tmp_mark);
- if (err)
- goto fence_mark_err;
- if (copy_to_user((void __user *)mark.mark, &tmp_mark,
- sizeof(tmp_mark))) {
- err = -EFAULT;
- goto fence_mark_err;
- }
-fence_mark_err:
- scif_err_debug(err, "scif_fence_mark");
- return err;
- }
- case SCIF_FENCE_WAIT:
- {
- struct scif_endpt *priv = f->private_data;
-
- err = scif_fence_wait(priv, arg);
- scif_err_debug(err, "scif_fence_wait");
- return err;
- }
- case SCIF_FENCE_SIGNAL:
- {
- struct scif_endpt *priv = f->private_data;
- struct scifioctl_fence_signal signal;
-
- if (copy_from_user(&signal, argp, sizeof(signal))) {
- err = -EFAULT;
- goto fence_signal_err;
- }
-
- err = scif_fence_signal(priv, signal.loff, signal.lval,
- signal.roff, signal.rval, signal.flags);
-fence_signal_err:
- scif_err_debug(err, "scif_fence_signal");
- return err;
- }
- }
- return -EINVAL;
-}
-
-const struct file_operations scif_fops = {
- .open = scif_fdopen,
- .release = scif_fdclose,
- .unlocked_ioctl = scif_fdioctl,
- .mmap = scif_fdmmap,
- .poll = scif_fdpoll,
- .flush = scif_fdflush,
- .owner = THIS_MODULE,
-};
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-
-#include "scif_main.h"
-
-/**
- * scif_recv_mark: Handle SCIF_MARK request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested a mark.
- */
-void scif_recv_mark(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- int mark = 0;
- int err;
-
- err = _scif_fence_mark(ep, &mark);
- if (err)
- msg->uop = SCIF_MARK_NACK;
- else
- msg->uop = SCIF_MARK_ACK;
- msg->payload[0] = ep->remote_ep;
- msg->payload[2] = mark;
- scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_mark_resp: Handle SCIF_MARK_(N)ACK messages.
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has responded to a SCIF_MARK message.
- */
-void scif_recv_mark_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_fence_info *fence_req =
- (struct scif_fence_info *)msg->payload[1];
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (msg->uop == SCIF_MARK_ACK) {
- fence_req->state = OP_COMPLETED;
- fence_req->dma_mark = (int)msg->payload[2];
- } else {
- fence_req->state = OP_FAILED;
- }
- mutex_unlock(&ep->rma_info.rma_lock);
- complete(&fence_req->comp);
-}
-
-/**
- * scif_recv_wait: Handle SCIF_WAIT request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested waiting on a fence.
- */
-void scif_recv_wait(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_remote_fence_info *fence;
-
- /*
- * Allocate structure for remote fence information and
- * send a NACK if the allocation failed. The peer will
- * return ENOMEM upon receiving a NACK.
- */
- fence = kmalloc(sizeof(*fence), GFP_KERNEL);
- if (!fence) {
- msg->payload[0] = ep->remote_ep;
- msg->uop = SCIF_WAIT_NACK;
- scif_nodeqp_send(ep->remote_dev, msg);
- return;
- }
-
- /* Prepare the fence request */
- memcpy(&fence->msg, msg, sizeof(struct scifmsg));
- INIT_LIST_HEAD(&fence->list);
-
- /* Insert to the global remote fence request list */
- mutex_lock(&scif_info.fencelock);
- atomic_inc(&ep->rma_info.fence_refcount);
- list_add_tail(&fence->list, &scif_info.fence);
- mutex_unlock(&scif_info.fencelock);
-
- schedule_work(&scif_info.misc_work);
-}
-
-/**
- * scif_recv_wait_resp: Handle SCIF_WAIT_(N)ACK messages.
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has responded to a SCIF_WAIT message.
- */
-void scif_recv_wait_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_fence_info *fence_req =
- (struct scif_fence_info *)msg->payload[1];
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (msg->uop == SCIF_WAIT_ACK)
- fence_req->state = OP_COMPLETED;
- else
- fence_req->state = OP_FAILED;
- mutex_unlock(&ep->rma_info.rma_lock);
- complete(&fence_req->comp);
-}
-
-/**
- * scif_recv_sig_local: Handle SCIF_SIG_LOCAL request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested a signal on a local offset.
- */
-void scif_recv_sig_local(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- int err;
-
- err = scif_prog_signal(ep, msg->payload[1], msg->payload[2],
- SCIF_WINDOW_SELF);
- if (err)
- msg->uop = SCIF_SIG_NACK;
- else
- msg->uop = SCIF_SIG_ACK;
- msg->payload[0] = ep->remote_ep;
- scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_sig_remote: Handle SCIF_SIGNAL_REMOTE request
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has requested a signal on a remote offset.
- */
-void scif_recv_sig_remote(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- int err;
-
- err = scif_prog_signal(ep, msg->payload[1], msg->payload[2],
- SCIF_WINDOW_PEER);
- if (err)
- msg->uop = SCIF_SIG_NACK;
- else
- msg->uop = SCIF_SIG_ACK;
- msg->payload[0] = ep->remote_ep;
- scif_nodeqp_send(ep->remote_dev, msg);
-}
-
-/**
- * scif_recv_sig_resp: Handle SCIF_SIG_(N)ACK messages.
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * The peer has responded to a signal request.
- */
-void scif_recv_sig_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_fence_info *fence_req =
- (struct scif_fence_info *)msg->payload[3];
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (msg->uop == SCIF_SIG_ACK)
- fence_req->state = OP_COMPLETED;
- else
- fence_req->state = OP_FAILED;
- mutex_unlock(&ep->rma_info.rma_lock);
- complete(&fence_req->comp);
-}
-
-static inline void *scif_get_local_va(off_t off, struct scif_window *window)
-{
- struct page **pages = window->pinned_pages->pages;
- int page_nr = (off - window->offset) >> PAGE_SHIFT;
- off_t page_off = off & ~PAGE_MASK;
-
- return page_address(pages[page_nr]) + page_off;
-}
-
-static void scif_prog_signal_cb(void *arg)
-{
- struct scif_cb_arg *cb_arg = arg;
-
- dma_pool_free(cb_arg->ep->remote_dev->signal_pool, cb_arg->status,
- cb_arg->src_dma_addr);
- kfree(cb_arg);
-}
-
-static int _scif_prog_signal(scif_epd_t epd, dma_addr_t dst, u64 val)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct dma_chan *chan = ep->rma_info.dma_chan;
- struct dma_device *ddev = chan->device;
- bool x100 = !is_dma_copy_aligned(chan->device, 1, 1, 1);
- struct dma_async_tx_descriptor *tx;
- struct scif_status *status = NULL;
- struct scif_cb_arg *cb_arg = NULL;
- dma_addr_t src;
- dma_cookie_t cookie;
- int err;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto alloc_fail;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = (int)cookie;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto alloc_fail;
- }
- dma_async_issue_pending(chan);
- if (x100) {
- /*
- * For X100 use the status descriptor to write the value to
- * the destination.
- */
- tx = ddev->device_prep_dma_imm_data(chan, dst, val, 0);
- } else {
- status = dma_pool_alloc(ep->remote_dev->signal_pool, GFP_KERNEL,
- &src);
- if (!status) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto alloc_fail;
- }
- status->val = val;
- status->src_dma_addr = src;
- status->ep = ep;
- src += offsetof(struct scif_status, val);
- tx = ddev->device_prep_dma_memcpy(chan, dst, src, sizeof(val),
- DMA_PREP_INTERRUPT);
- }
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto dma_fail;
- }
- if (!x100) {
- cb_arg = kmalloc(sizeof(*cb_arg), GFP_KERNEL);
- if (!cb_arg) {
- err = -ENOMEM;
- goto dma_fail;
- }
- cb_arg->src_dma_addr = src;
- cb_arg->status = status;
- cb_arg->ep = ep;
- tx->callback = scif_prog_signal_cb;
- tx->callback_param = cb_arg;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = -EIO;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- goto dma_fail;
- }
- dma_async_issue_pending(chan);
- return 0;
-dma_fail:
- if (!x100) {
- dma_pool_free(ep->remote_dev->signal_pool, status,
- src - offsetof(struct scif_status, val));
- kfree(cb_arg);
- }
-alloc_fail:
- return err;
-}
-
-/**
- * scif_prog_signal:
- * @epd: Endpoint Descriptor
- * @offset: registered address to write @val to
- * @val: Value to be written at @offset
- * @type: Type of the window.
- *
- * Arrange to write a value to the registered offset after ensuring that the
- * offset provided is indeed valid.
- */
-int scif_prog_signal(scif_epd_t epd, off_t offset, u64 val,
- enum scif_window_type type)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_window *window = NULL;
- struct scif_rma_req req;
- dma_addr_t dst_dma_addr;
- int err;
-
- mutex_lock(&ep->rma_info.rma_lock);
- req.out_window = &window;
- req.offset = offset;
- req.nr_bytes = sizeof(u64);
- req.prot = SCIF_PROT_WRITE;
- req.type = SCIF_WINDOW_SINGLE;
- if (type == SCIF_WINDOW_SELF)
- req.head = &ep->rma_info.reg_list;
- else
- req.head = &ep->rma_info.remote_reg_list;
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto unlock_ret;
- }
-
- if (scif_is_mgmt_node() && scifdev_self(ep->remote_dev)) {
- u64 *dst_virt;
-
- if (type == SCIF_WINDOW_SELF)
- dst_virt = scif_get_local_va(offset, window);
- else
- dst_virt =
- scif_get_local_va(offset, (struct scif_window *)
- window->peer_window);
- *dst_virt = val;
- } else {
- dst_dma_addr = __scif_off_to_dma_addr(window, offset);
- err = _scif_prog_signal(epd, dst_dma_addr, val);
- }
-unlock_ret:
- mutex_unlock(&ep->rma_info.rma_lock);
- return err;
-}
-
-static int _scif_fence_wait(scif_epd_t epd, int mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- dma_cookie_t cookie = mark & ~SCIF_REMOTE_FENCE;
- int err;
-
- /* Wait for DMA callback in scif_fence_mark_cb(..) */
- err = wait_event_interruptible_timeout(ep->rma_info.markwq,
- dma_async_is_tx_complete(
- ep->rma_info.dma_chan,
- cookie, NULL, NULL) ==
- DMA_COMPLETE,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err)
- err = -ETIMEDOUT;
- else if (err > 0)
- err = 0;
- return err;
-}
-
-/**
- * scif_rma_handle_remote_fences:
- *
- * This routine services remote fence requests.
- */
-void scif_rma_handle_remote_fences(void)
-{
- struct list_head *item, *tmp;
- struct scif_remote_fence_info *fence;
- struct scif_endpt *ep;
- int mark, err;
-
- might_sleep();
- mutex_lock(&scif_info.fencelock);
- list_for_each_safe(item, tmp, &scif_info.fence) {
- fence = list_entry(item, struct scif_remote_fence_info,
- list);
- /* Remove fence from global list */
- list_del(&fence->list);
-
- /* Initiate the fence operation */
- ep = (struct scif_endpt *)fence->msg.payload[0];
- mark = fence->msg.payload[2];
- err = _scif_fence_wait(ep, mark);
- if (err)
- fence->msg.uop = SCIF_WAIT_NACK;
- else
- fence->msg.uop = SCIF_WAIT_ACK;
- fence->msg.payload[0] = ep->remote_ep;
- scif_nodeqp_send(ep->remote_dev, &fence->msg);
- kfree(fence);
- if (!atomic_sub_return(1, &ep->rma_info.fence_refcount))
- schedule_work(&scif_info.misc_work);
- }
- mutex_unlock(&scif_info.fencelock);
-}
-
-static int _scif_send_fence(scif_epd_t epd, int uop, int mark, int *out_mark)
-{
- int err;
- struct scifmsg msg;
- struct scif_fence_info *fence_req;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- fence_req = kmalloc(sizeof(*fence_req), GFP_KERNEL);
- if (!fence_req) {
- err = -ENOMEM;
- goto error;
- }
-
- fence_req->state = OP_IN_PROGRESS;
- init_completion(&fence_req->comp);
-
- msg.src = ep->port;
- msg.uop = uop;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = (u64)fence_req;
- if (uop == SCIF_WAIT)
- msg.payload[2] = mark;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- if (err)
- goto error_free;
-retry:
- /* Wait for a SCIF_WAIT_(N)ACK message */
- err = wait_for_completion_timeout(&fence_req->comp,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- if (!err)
- err = -ENODEV;
- if (err > 0)
- err = 0;
- mutex_lock(&ep->rma_info.rma_lock);
- if (err < 0) {
- if (fence_req->state == OP_IN_PROGRESS)
- fence_req->state = OP_FAILED;
- }
- if (fence_req->state == OP_FAILED && !err)
- err = -ENOMEM;
- if (uop == SCIF_MARK && fence_req->state == OP_COMPLETED)
- *out_mark = SCIF_REMOTE_FENCE | fence_req->dma_mark;
- mutex_unlock(&ep->rma_info.rma_lock);
-error_free:
- kfree(fence_req);
-error:
- return err;
-}
-
-/**
- * scif_send_fence_mark:
- * @epd: end point descriptor.
- * @out_mark: Output DMA mark reported by peer.
- *
- * Send a remote fence mark request.
- */
-static int scif_send_fence_mark(scif_epd_t epd, int *out_mark)
-{
- return _scif_send_fence(epd, SCIF_MARK, 0, out_mark);
-}
-
-/**
- * scif_send_fence_wait:
- * @epd: end point descriptor.
- * @mark: DMA mark to wait for.
- *
- * Send a remote fence wait request.
- */
-static int scif_send_fence_wait(scif_epd_t epd, int mark)
-{
- return _scif_send_fence(epd, SCIF_WAIT, mark, NULL);
-}
-
-static int _scif_send_fence_signal_wait(struct scif_endpt *ep,
- struct scif_fence_info *fence_req)
-{
- int err;
-
-retry:
- /* Wait for a SCIF_SIG_(N)ACK message */
- err = wait_for_completion_timeout(&fence_req->comp,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- if (!err)
- err = -ENODEV;
- if (err > 0)
- err = 0;
- if (err < 0) {
- mutex_lock(&ep->rma_info.rma_lock);
- if (fence_req->state == OP_IN_PROGRESS)
- fence_req->state = OP_FAILED;
- mutex_unlock(&ep->rma_info.rma_lock);
- }
- if (fence_req->state == OP_FAILED && !err)
- err = -ENXIO;
- return err;
-}
-
-/**
- * scif_send_fence_signal:
- * @epd: endpoint descriptor
- * @loff: local offset
- * @lval: local value to write to loffset
- * @roff: remote offset
- * @rval: remote value to write to roffset
- * @flags: flags
- *
- * Sends a remote fence signal request
- */
-static int scif_send_fence_signal(scif_epd_t epd, off_t roff, u64 rval,
- off_t loff, u64 lval, int flags)
-{
- int err = 0;
- struct scifmsg msg;
- struct scif_fence_info *fence_req;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
-
- fence_req = kmalloc(sizeof(*fence_req), GFP_KERNEL);
- if (!fence_req) {
- err = -ENOMEM;
- goto error;
- }
-
- fence_req->state = OP_IN_PROGRESS;
- init_completion(&fence_req->comp);
- msg.src = ep->port;
- if (flags & SCIF_SIGNAL_LOCAL) {
- msg.uop = SCIF_SIG_LOCAL;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = roff;
- msg.payload[2] = rval;
- msg.payload[3] = (u64)fence_req;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- if (err)
- goto error_free;
- err = _scif_send_fence_signal_wait(ep, fence_req);
- if (err)
- goto error_free;
- }
- fence_req->state = OP_IN_PROGRESS;
-
- if (flags & SCIF_SIGNAL_REMOTE) {
- msg.uop = SCIF_SIG_REMOTE;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = loff;
- msg.payload[2] = lval;
- msg.payload[3] = (u64)fence_req;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- if (err)
- goto error_free;
- err = _scif_send_fence_signal_wait(ep, fence_req);
- }
-error_free:
- kfree(fence_req);
-error:
- return err;
-}
-
-static void scif_fence_mark_cb(void *arg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)arg;
-
- wake_up_interruptible(&ep->rma_info.markwq);
- atomic_dec(&ep->rma_info.fence_refcount);
-}
-
-/**
- * _scif_fence_mark:
- * @epd: endpoint descriptor
- * @mark: DMA mark to set-up
- *
- * Set up a mark for this endpoint and return the value of the mark.
- */
-int _scif_fence_mark(scif_epd_t epd, int *mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct dma_chan *chan = ep->rma_info.dma_chan;
- struct dma_device *ddev = chan->device;
- struct dma_async_tx_descriptor *tx;
- dma_cookie_t cookie;
- int err;
-
- tx = ddev->device_prep_dma_memcpy(chan, 0, 0, 0, DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = (int)cookie;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- dma_async_issue_pending(chan);
- tx = ddev->device_prep_dma_interrupt(chan, DMA_PREP_INTERRUPT);
- if (!tx) {
- err = -ENOMEM;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- tx->callback = scif_fence_mark_cb;
- tx->callback_param = ep;
- *mark = cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = (int)cookie;
- dev_err(&ep->remote_dev->sdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
- }
- atomic_inc(&ep->rma_info.fence_refcount);
- dma_async_issue_pending(chan);
- return 0;
-}
-
-#define SCIF_LOOPB_MAGIC_MARK 0xdead
-
-int scif_fence_mark(scif_epd_t epd, int flags, int *mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_mark: ep %p flags 0x%x mark 0x%x\n",
- ep, flags, *mark);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- /* Invalid flags? */
- if (flags & ~(SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER))
- return -EINVAL;
-
- /* At least one of init self or peer RMA should be set */
- if (!(flags & (SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER)))
- return -EINVAL;
-
- /* Exactly one of init self or peer RMA should be set but not both */
- if ((flags & SCIF_FENCE_INIT_SELF) && (flags & SCIF_FENCE_INIT_PEER))
- return -EINVAL;
-
- /*
- * Management node loopback does not need to use DMA.
- * Return a valid mark to be symmetric.
- */
- if (scifdev_self(ep->remote_dev) && scif_is_mgmt_node()) {
- *mark = SCIF_LOOPB_MAGIC_MARK;
- return 0;
- }
-
- if (flags & SCIF_FENCE_INIT_SELF)
- err = _scif_fence_mark(epd, mark);
- else
- err = scif_send_fence_mark(ep, mark);
-
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_mark: ep %p flags 0x%x mark 0x%x err %d\n",
- ep, flags, *mark, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_mark);
-
-int scif_fence_wait(scif_epd_t epd, int mark)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_wait: ep %p mark 0x%x\n",
- ep, mark);
- err = scif_verify_epd(ep);
- if (err)
- return err;
- /*
- * Management node loopback does not need to use DMA.
- * The only valid mark provided is 0 so simply
- * return success if the mark is valid.
- */
- if (scifdev_self(ep->remote_dev) && scif_is_mgmt_node()) {
- if (mark == SCIF_LOOPB_MAGIC_MARK)
- return 0;
- else
- return -EINVAL;
- }
- if (mark & SCIF_REMOTE_FENCE)
- err = scif_send_fence_wait(epd, mark);
- else
- err = _scif_fence_wait(epd, mark);
- if (err < 0)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_wait);
-
-int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval,
- off_t roff, u64 rval, int flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- int err = 0;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI fence_signal: ep %p loff 0x%lx lval 0x%llx roff 0x%lx rval 0x%llx flags 0x%x\n",
- ep, loff, lval, roff, rval, flags);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- /* Invalid flags? */
- if (flags & ~(SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER |
- SCIF_SIGNAL_LOCAL | SCIF_SIGNAL_REMOTE))
- return -EINVAL;
-
- /* At least one of init self or peer RMA should be set */
- if (!(flags & (SCIF_FENCE_INIT_SELF | SCIF_FENCE_INIT_PEER)))
- return -EINVAL;
-
- /* Exactly one of init self or peer RMA should be set but not both */
- if ((flags & SCIF_FENCE_INIT_SELF) && (flags & SCIF_FENCE_INIT_PEER))
- return -EINVAL;
-
- /* At least one of SCIF_SIGNAL_LOCAL or SCIF_SIGNAL_REMOTE required */
- if (!(flags & (SCIF_SIGNAL_LOCAL | SCIF_SIGNAL_REMOTE)))
- return -EINVAL;
-
- /* Only Dword offsets allowed */
- if ((flags & SCIF_SIGNAL_LOCAL) && (loff & (sizeof(u32) - 1)))
- return -EINVAL;
-
- /* Only Dword aligned offsets allowed */
- if ((flags & SCIF_SIGNAL_REMOTE) && (roff & (sizeof(u32) - 1)))
- return -EINVAL;
-
- if (flags & SCIF_FENCE_INIT_PEER) {
- err = scif_send_fence_signal(epd, roff, rval, loff,
- lval, flags);
- } else {
- /* Local Signal in Local RAS */
- if (flags & SCIF_SIGNAL_LOCAL) {
- err = scif_prog_signal(epd, loff, lval,
- SCIF_WINDOW_SELF);
- if (err)
- goto error_ret;
- }
-
- /* Signal in Remote RAS */
- if (flags & SCIF_SIGNAL_REMOTE)
- err = scif_prog_signal(epd, roff,
- rval, SCIF_WINDOW_PEER);
- }
-error_ret:
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_fence_signal);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/module.h>
-#include <linux/idr.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-#include "scif_main.h"
-#include "scif_map.h"
-
-struct scif_info scif_info = {
- .mdev = {
- .minor = MISC_DYNAMIC_MINOR,
- .name = "scif",
- .fops = &scif_fops,
- }
-};
-
-struct scif_dev *scif_dev;
-struct kmem_cache *unaligned_cache;
-static atomic_t g_loopb_cnt;
-
-/* Runs in the context of intr_wq */
-static void scif_intr_bh_handler(struct work_struct *work)
-{
- struct scif_dev *scifdev =
- container_of(work, struct scif_dev, intr_bh);
-
- if (scifdev_self(scifdev))
- scif_loopb_msg_handler(scifdev, scifdev->qpairs);
- else
- scif_nodeqp_intrhandler(scifdev, scifdev->qpairs);
-}
-
-int scif_setup_intr_wq(struct scif_dev *scifdev)
-{
- if (!scifdev->intr_wq) {
- snprintf(scifdev->intr_wqname, sizeof(scifdev->intr_wqname),
- "SCIF INTR %d", scifdev->node);
- scifdev->intr_wq =
- alloc_ordered_workqueue(scifdev->intr_wqname, 0);
- if (!scifdev->intr_wq)
- return -ENOMEM;
- INIT_WORK(&scifdev->intr_bh, scif_intr_bh_handler);
- }
- return 0;
-}
-
-void scif_destroy_intr_wq(struct scif_dev *scifdev)
-{
- if (scifdev->intr_wq) {
- destroy_workqueue(scifdev->intr_wq);
- scifdev->intr_wq = NULL;
- }
-}
-
-irqreturn_t scif_intr_handler(int irq, void *data)
-{
- struct scif_dev *scifdev = data;
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- sdev->hw_ops->ack_interrupt(sdev, scifdev->db);
- queue_work(scifdev->intr_wq, &scifdev->intr_bh);
- return IRQ_HANDLED;
-}
-
-static void scif_qp_setup_handler(struct work_struct *work)
-{
- struct scif_dev *scifdev = container_of(work, struct scif_dev,
- qp_dwork.work);
- struct scif_hw_dev *sdev = scifdev->sdev;
- dma_addr_t da = 0;
- int err;
-
- if (scif_is_mgmt_node()) {
- struct mic_bootparam *bp = sdev->dp;
-
- da = bp->scif_card_dma_addr;
- scifdev->rdb = bp->h2c_scif_db;
- } else {
- struct mic_bootparam __iomem *bp = sdev->rdp;
-
- da = readq(&bp->scif_host_dma_addr);
- scifdev->rdb = ioread8(&bp->c2h_scif_db);
- }
- if (da) {
- err = scif_qp_response(da, scifdev);
- if (err)
- dev_err(&scifdev->sdev->dev,
- "scif_qp_response err %d\n", err);
- } else {
- schedule_delayed_work(&scifdev->qp_dwork,
- msecs_to_jiffies(1000));
- }
-}
-
-static int scif_setup_scifdev(void)
-{
- /* We support a maximum of 129 SCIF nodes including the mgmt node */
-#define MAX_SCIF_NODES 129
- int i;
- u8 num_nodes = MAX_SCIF_NODES;
-
- scif_dev = kcalloc(num_nodes, sizeof(*scif_dev), GFP_KERNEL);
- if (!scif_dev)
- return -ENOMEM;
- for (i = 0; i < num_nodes; i++) {
- struct scif_dev *scifdev = &scif_dev[i];
-
- scifdev->node = i;
- scifdev->exit = OP_IDLE;
- init_waitqueue_head(&scifdev->disconn_wq);
- mutex_init(&scifdev->lock);
- INIT_WORK(&scifdev->peer_add_work, scif_add_peer_device);
- INIT_DELAYED_WORK(&scifdev->p2p_dwork,
- scif_poll_qp_state);
- INIT_DELAYED_WORK(&scifdev->qp_dwork,
- scif_qp_setup_handler);
- INIT_LIST_HEAD(&scifdev->p2p);
- RCU_INIT_POINTER(scifdev->spdev, NULL);
- }
- return 0;
-}
-
-static void scif_destroy_scifdev(void)
-{
- kfree(scif_dev);
- scif_dev = NULL;
-}
-
-static int scif_probe(struct scif_hw_dev *sdev)
-{
- struct scif_dev *scifdev = &scif_dev[sdev->dnode];
- int rc;
-
- dev_set_drvdata(&sdev->dev, sdev);
- scifdev->sdev = sdev;
-
- if (1 == atomic_add_return(1, &g_loopb_cnt)) {
- struct scif_dev *loopb_dev = &scif_dev[sdev->snode];
-
- loopb_dev->sdev = sdev;
- rc = scif_setup_loopback_qp(loopb_dev);
- if (rc)
- goto exit;
- }
-
- rc = scif_setup_intr_wq(scifdev);
- if (rc)
- goto destroy_loopb;
- rc = scif_setup_qp(scifdev);
- if (rc)
- goto destroy_intr;
- scifdev->db = sdev->hw_ops->next_db(sdev);
- scifdev->cookie = sdev->hw_ops->request_irq(sdev, scif_intr_handler,
- "SCIF_INTR", scifdev,
- scifdev->db);
- if (IS_ERR(scifdev->cookie)) {
- rc = PTR_ERR(scifdev->cookie);
- goto free_qp;
- }
- if (scif_is_mgmt_node()) {
- struct mic_bootparam *bp = sdev->dp;
-
- bp->c2h_scif_db = scifdev->db;
- bp->scif_host_dma_addr = scifdev->qp_dma_addr;
- } else {
- struct mic_bootparam __iomem *bp = sdev->rdp;
-
- iowrite8(scifdev->db, &bp->h2c_scif_db);
- writeq(scifdev->qp_dma_addr, &bp->scif_card_dma_addr);
- }
- schedule_delayed_work(&scifdev->qp_dwork,
- msecs_to_jiffies(1000));
- return rc;
-free_qp:
- scif_free_qp(scifdev);
-destroy_intr:
- scif_destroy_intr_wq(scifdev);
-destroy_loopb:
- if (atomic_dec_and_test(&g_loopb_cnt))
- scif_destroy_loopback_qp(&scif_dev[sdev->snode]);
-exit:
- return rc;
-}
-
-void scif_stop(struct scif_dev *scifdev)
-{
- struct scif_dev *dev;
- int i;
-
- for (i = scif_info.maxid; i >= 0; i--) {
- dev = &scif_dev[i];
- if (scifdev_self(dev))
- continue;
- scif_handle_remove_node(i);
- }
-}
-
-static void scif_remove(struct scif_hw_dev *sdev)
-{
- struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-
- if (scif_is_mgmt_node()) {
- struct mic_bootparam *bp = sdev->dp;
-
- bp->c2h_scif_db = -1;
- bp->scif_host_dma_addr = 0x0;
- } else {
- struct mic_bootparam __iomem *bp = sdev->rdp;
-
- iowrite8(-1, &bp->h2c_scif_db);
- writeq(0x0, &bp->scif_card_dma_addr);
- }
- if (scif_is_mgmt_node()) {
- scif_disconnect_node(scifdev->node, true);
- } else {
- scif_info.card_initiated_exit = true;
- scif_stop(scifdev);
- }
- if (atomic_dec_and_test(&g_loopb_cnt))
- scif_destroy_loopback_qp(&scif_dev[sdev->snode]);
- if (scifdev->cookie) {
- sdev->hw_ops->free_irq(sdev, scifdev->cookie, scifdev);
- scifdev->cookie = NULL;
- }
- scif_destroy_intr_wq(scifdev);
- cancel_delayed_work(&scifdev->qp_dwork);
- scif_free_qp(scifdev);
- scifdev->rdb = -1;
- scifdev->sdev = NULL;
-}
-
-static struct scif_hw_dev_id id_table[] = {
- { MIC_SCIF_DEV, SCIF_DEV_ANY_ID },
- { 0 },
-};
-
-static struct scif_driver scif_driver = {
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = scif_probe,
- .remove = scif_remove,
-};
-
-static int _scif_init(void)
-{
- int rc;
-
- mutex_init(&scif_info.eplock);
- spin_lock_init(&scif_info.rmalock);
- spin_lock_init(&scif_info.nb_connect_lock);
- spin_lock_init(&scif_info.port_lock);
- mutex_init(&scif_info.conflock);
- mutex_init(&scif_info.connlock);
- mutex_init(&scif_info.fencelock);
- INIT_LIST_HEAD(&scif_info.uaccept);
- INIT_LIST_HEAD(&scif_info.listen);
- INIT_LIST_HEAD(&scif_info.zombie);
- INIT_LIST_HEAD(&scif_info.connected);
- INIT_LIST_HEAD(&scif_info.disconnected);
- INIT_LIST_HEAD(&scif_info.rma);
- INIT_LIST_HEAD(&scif_info.rma_tc);
- INIT_LIST_HEAD(&scif_info.mmu_notif_cleanup);
- INIT_LIST_HEAD(&scif_info.fence);
- INIT_LIST_HEAD(&scif_info.nb_connect_list);
- init_waitqueue_head(&scif_info.exitwq);
- scif_info.rma_tc_limit = SCIF_RMA_TEMP_CACHE_LIMIT;
- scif_info.en_msg_log = 0;
- scif_info.p2p_enable = 1;
- rc = scif_setup_scifdev();
- if (rc)
- goto error;
- unaligned_cache = kmem_cache_create("Unaligned_DMA",
- SCIF_KMEM_UNALIGNED_BUF_SIZE,
- 0, SLAB_HWCACHE_ALIGN, NULL);
- if (!unaligned_cache) {
- rc = -ENOMEM;
- goto free_sdev;
- }
- INIT_WORK(&scif_info.misc_work, scif_misc_handler);
- INIT_WORK(&scif_info.mmu_notif_work, scif_mmu_notif_handler);
- INIT_WORK(&scif_info.conn_work, scif_conn_handler);
- idr_init(&scif_ports);
- return 0;
-free_sdev:
- scif_destroy_scifdev();
-error:
- return rc;
-}
-
-static void _scif_exit(void)
-{
- idr_destroy(&scif_ports);
- kmem_cache_destroy(unaligned_cache);
- scif_destroy_scifdev();
-}
-
-static int __init scif_init(void)
-{
- struct miscdevice *mdev = &scif_info.mdev;
- int rc;
-
- _scif_init();
- iova_cache_get();
- rc = scif_peer_bus_init();
- if (rc)
- goto exit;
- rc = scif_register_driver(&scif_driver);
- if (rc)
- goto peer_bus_exit;
- rc = misc_register(mdev);
- if (rc)
- goto unreg_scif;
- scif_init_debugfs();
- return 0;
-unreg_scif:
- scif_unregister_driver(&scif_driver);
-peer_bus_exit:
- scif_peer_bus_exit();
-exit:
- _scif_exit();
- return rc;
-}
-
-static void __exit scif_exit(void)
-{
- scif_exit_debugfs();
- misc_deregister(&scif_info.mdev);
- scif_unregister_driver(&scif_driver);
- scif_peer_bus_exit();
- iova_cache_put();
- _scif_exit();
-}
-
-module_init(scif_init);
-module_exit(scif_exit);
-
-MODULE_DEVICE_TABLE(scif, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) SCIF driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_MAIN_H
-#define SCIF_MAIN_H
-
-#include <linux/sched/signal.h>
-#include <linux/pci.h>
-#include <linux/miscdevice.h>
-#include <linux/dmaengine.h>
-#include <linux/iova.h>
-#include <linux/anon_inodes.h>
-#include <linux/file.h>
-#include <linux/vmalloc.h>
-#include <linux/scif.h>
-#include "../common/mic_dev.h"
-
-#define SCIF_MGMT_NODE 0
-#define SCIF_DEFAULT_WATCHDOG_TO 30
-#define SCIF_NODE_ACCEPT_TIMEOUT (3 * HZ)
-#define SCIF_NODE_ALIVE_TIMEOUT (SCIF_DEFAULT_WATCHDOG_TO * HZ)
-#define SCIF_RMA_TEMP_CACHE_LIMIT 0x20000
-
-/*
- * Generic state used for certain node QP message exchanges
- * like Unregister, Alloc etc.
- */
-enum scif_msg_state {
- OP_IDLE = 1,
- OP_IN_PROGRESS,
- OP_COMPLETED,
- OP_FAILED
-};
-
-/*
- * struct scif_info - Global SCIF information
- *
- * @nodeid: Node ID this node is to others
- * @maxid: Max known node ID
- * @total: Total number of SCIF nodes
- * @nr_zombies: number of zombie endpoints
- * @eplock: Lock to synchronize listening, zombie endpoint lists
- * @connlock: Lock to synchronize connected and disconnected lists
- * @nb_connect_lock: Synchronize non blocking connect operations
- * @port_lock: Synchronize access to SCIF ports
- * @uaccept: List of user acceptreq waiting for acceptreg
- * @listen: List of listening end points
- * @zombie: List of zombie end points with pending RMA's
- * @connected: List of end points in connected state
- * @disconnected: List of end points in disconnected state
- * @nb_connect_list: List for non blocking connections
- * @misc_work: miscellaneous SCIF tasks
- * @conflock: Lock to synchronize SCIF node configuration changes
- * @en_msg_log: Enable debug message logging
- * @p2p_enable: Enable P2P SCIF network
- * @mdev: The MISC device
- * @conn_work: Work for workqueue handling all connections
- * @exitwq: Wait queue for waiting for an EXIT node QP message response
- * @loopb_dev: Dummy SCIF device used for loopback
- * @loopb_wq: Workqueue used for handling loopback messages
- * @loopb_wqname[16]: Name of loopback workqueue
- * @loopb_work: Used for submitting work to loopb_wq
- * @loopb_recv_q: List of messages received on the loopb_wq
- * @card_initiated_exit: set when the card has initiated the exit
- * @rmalock: Synchronize access to RMA operations
- * @fencelock: Synchronize access to list of remote fences requested.
- * @rma: List of temporary registered windows to be destroyed.
- * @rma_tc: List of temporary registered & cached Windows to be destroyed
- * @fence: List of remote fence requests
- * @mmu_notif_work: Work for registration caching MMU notifier workqueue
- * @mmu_notif_cleanup: List of temporary cached windows for reg cache
- * @rma_tc_limit: RMA temporary cache limit
- */
-struct scif_info {
- u8 nodeid;
- u8 maxid;
- u8 total;
- u32 nr_zombies;
- struct mutex eplock;
- struct mutex connlock;
- spinlock_t nb_connect_lock;
- spinlock_t port_lock;
- struct list_head uaccept;
- struct list_head listen;
- struct list_head zombie;
- struct list_head connected;
- struct list_head disconnected;
- struct list_head nb_connect_list;
- struct work_struct misc_work;
- struct mutex conflock;
- u8 en_msg_log;
- u8 p2p_enable;
- struct miscdevice mdev;
- struct work_struct conn_work;
- wait_queue_head_t exitwq;
- struct scif_dev *loopb_dev;
- struct workqueue_struct *loopb_wq;
- char loopb_wqname[16];
- struct work_struct loopb_work;
- struct list_head loopb_recv_q;
- bool card_initiated_exit;
- spinlock_t rmalock;
- struct mutex fencelock;
- struct list_head rma;
- struct list_head rma_tc;
- struct list_head fence;
- struct work_struct mmu_notif_work;
- struct list_head mmu_notif_cleanup;
- unsigned long rma_tc_limit;
-};
-
-/*
- * struct scif_p2p_info - SCIF mapping information used for P2P
- *
- * @ppi_peer_id - SCIF peer node id
- * @ppi_sg - Scatter list for bar information (One for mmio and one for aper)
- * @sg_nentries - Number of entries in the scatterlist
- * @ppi_da: DMA address for MMIO and APER bars
- * @ppi_len: Length of MMIO and APER bars
- * @ppi_list: Link in list of mapping information
- */
-struct scif_p2p_info {
- u8 ppi_peer_id;
- struct scatterlist *ppi_sg[2];
- u64 sg_nentries[2];
- dma_addr_t ppi_da[2];
- u64 ppi_len[2];
-#define SCIF_PPI_MMIO 0
-#define SCIF_PPI_APER 1
- struct list_head ppi_list;
-};
-
-/*
- * struct scif_dev - SCIF remote device specific fields
- *
- * @node: Node id
- * @p2p: List of P2P mapping information
- * @qpairs: The node queue pair for exchanging control messages
- * @intr_wq: Workqueue for handling Node QP messages
- * @intr_wqname: Name of node QP workqueue for handling interrupts
- * @intr_bh: Used for submitting work to intr_wq
- * @lock: Lock used for synchronizing access to the scif device
- * @sdev: SCIF hardware device on the SCIF hardware bus
- * @db: doorbell the peer will trigger to generate an interrupt on self
- * @rdb: Doorbell to trigger on the peer to generate an interrupt on the peer
- * @cookie: Cookie received while registering the interrupt handler
- * @peer_add_work: Work for handling device_add for peer devices
- * @p2p_dwork: Delayed work to enable polling for P2P state
- * @qp_dwork: Delayed work for enabling polling for remote QP information
- * @p2p_retry: Number of times to retry polling of P2P state
- * @base_addr: P2P aperture bar base address
- * @mic_mw mmio: The peer MMIO information used for P2P
- * @spdev: SCIF peer device on the SCIF peer bus
- * @node_remove_ack_pending: True if a node_remove_ack is pending
- * @exit_ack_pending: true if an exit_ack is pending
- * @disconn_wq: Used while waiting for a node remove response
- * @disconn_rescnt: Keeps track of number of node remove requests sent
- * @exit: Status of exit message
- * @qp_dma_addr: Queue pair DMA address passed to the peer
- * @dma_ch_idx: Round robin index for DMA channels
- * @signal_pool: DMA pool used for scheduling scif_fence_signal DMA's
-*/
-struct scif_dev {
- u8 node;
- struct list_head p2p;
- struct scif_qp *qpairs;
- struct workqueue_struct *intr_wq;
- char intr_wqname[16];
- struct work_struct intr_bh;
- struct mutex lock;
- struct scif_hw_dev *sdev;
- int db;
- int rdb;
- struct mic_irq *cookie;
- struct work_struct peer_add_work;
- struct delayed_work p2p_dwork;
- struct delayed_work qp_dwork;
- int p2p_retry;
- dma_addr_t base_addr;
- struct mic_mw mmio;
- struct scif_peer_dev __rcu *spdev;
- bool node_remove_ack_pending;
- bool exit_ack_pending;
- wait_queue_head_t disconn_wq;
- atomic_t disconn_rescnt;
- enum scif_msg_state exit;
- dma_addr_t qp_dma_addr;
- int dma_ch_idx;
- struct dma_pool *signal_pool;
-};
-
-extern bool scif_reg_cache_enable;
-extern bool scif_ulimit_check;
-extern struct scif_info scif_info;
-extern struct idr scif_ports;
-extern struct bus_type scif_peer_bus;
-extern struct scif_dev *scif_dev;
-extern const struct file_operations scif_fops;
-extern const struct file_operations scif_anon_fops;
-
-/* Size of the RB for the Node QP */
-#define SCIF_NODE_QP_SIZE 0x10000
-
-#include "scif_nodeqp.h"
-#include "scif_rma.h"
-#include "scif_rma_list.h"
-
-/*
- * scifdev_self:
- * @dev: The remote SCIF Device
- *
- * Returns true if the SCIF Device passed is the self aka Loopback SCIF device.
- */
-static inline int scifdev_self(struct scif_dev *dev)
-{
- return dev->node == scif_info.nodeid;
-}
-
-static inline bool scif_is_mgmt_node(void)
-{
- return !scif_info.nodeid;
-}
-
-/*
- * scifdev_is_p2p:
- * @dev: The remote SCIF Device
- *
- * Returns true if the SCIF Device is a MIC Peer to Peer SCIF device.
- */
-static inline bool scifdev_is_p2p(struct scif_dev *dev)
-{
- if (scif_is_mgmt_node())
- return false;
- else
- return dev != &scif_dev[SCIF_MGMT_NODE] &&
- !scifdev_self(dev);
-}
-
-/*
- * scifdev_alive:
- * @scifdev: The remote SCIF Device
- *
- * Returns true if the remote SCIF Device is running or sleeping for
- * this endpoint.
- */
-static inline int _scifdev_alive(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
-
- rcu_read_lock();
- spdev = rcu_dereference(scifdev->spdev);
- rcu_read_unlock();
- return !!spdev;
-}
-
-#include "scif_epd.h"
-
-void __init scif_init_debugfs(void);
-void scif_exit_debugfs(void);
-int scif_setup_intr_wq(struct scif_dev *scifdev);
-void scif_destroy_intr_wq(struct scif_dev *scifdev);
-void scif_cleanup_scifdev(struct scif_dev *dev);
-void scif_handle_remove_node(int node);
-void scif_disconnect_node(u32 node_id, bool mgmt_initiated);
-void scif_free_qp(struct scif_dev *dev);
-void scif_misc_handler(struct work_struct *work);
-void scif_stop(struct scif_dev *scifdev);
-irqreturn_t scif_intr_handler(int irq, void *data);
-#endif /* SCIF_MAIN_H */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_MAP_H
-#define SCIF_MAP_H
-
-#include "../bus/scif_bus.h"
-
-static __always_inline void *
-scif_alloc_coherent(dma_addr_t *dma_handle,
- struct scif_dev *scifdev, size_t size,
- gfp_t gfp)
-{
- void *va;
-
- if (scifdev_self(scifdev)) {
- va = kmalloc(size, gfp);
- if (va)
- *dma_handle = virt_to_phys(va);
- } else {
- va = dma_alloc_coherent(&scifdev->sdev->dev,
- size, dma_handle, gfp);
- if (va && scifdev_is_p2p(scifdev))
- *dma_handle = *dma_handle + scifdev->base_addr;
- }
- return va;
-}
-
-static __always_inline void
-scif_free_coherent(void *va, dma_addr_t local,
- struct scif_dev *scifdev, size_t size)
-{
- if (scifdev_self(scifdev)) {
- kfree(va);
- } else {
- if (scifdev_is_p2p(scifdev) && local > scifdev->base_addr)
- local = local - scifdev->base_addr;
- dma_free_coherent(&scifdev->sdev->dev,
- size, va, local);
- }
-}
-
-static __always_inline int
-scif_map_single(dma_addr_t *dma_handle,
- void *local, struct scif_dev *scifdev, size_t size)
-{
- int err = 0;
-
- if (scifdev_self(scifdev)) {
- *dma_handle = virt_to_phys((local));
- } else {
- *dma_handle = dma_map_single(&scifdev->sdev->dev,
- local, size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&scifdev->sdev->dev, *dma_handle))
- err = -ENOMEM;
- else if (scifdev_is_p2p(scifdev))
- *dma_handle = *dma_handle + scifdev->base_addr;
- }
- if (err)
- *dma_handle = 0;
- return err;
-}
-
-static __always_inline void
-scif_unmap_single(dma_addr_t local, struct scif_dev *scifdev,
- size_t size)
-{
- if (!scifdev_self(scifdev)) {
- if (scifdev_is_p2p(scifdev))
- local = local - scifdev->base_addr;
- dma_unmap_single(&scifdev->sdev->dev, local,
- size, DMA_BIDIRECTIONAL);
- }
-}
-
-static __always_inline void *
-scif_ioremap(dma_addr_t phys, size_t size, struct scif_dev *scifdev)
-{
- void *out_virt;
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- if (scifdev_self(scifdev))
- out_virt = phys_to_virt(phys);
- else
- out_virt = (void __force *)
- sdev->hw_ops->remap(sdev, phys, size);
- return out_virt;
-}
-
-static __always_inline void
-scif_iounmap(void *virt, size_t len, struct scif_dev *scifdev)
-{
- if (!scifdev_self(scifdev)) {
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- sdev->hw_ops->unmap(sdev, (void __force __iomem *)virt);
- }
-}
-
-static __always_inline int
-scif_map_page(dma_addr_t *dma_handle, struct page *page,
- struct scif_dev *scifdev)
-{
- int err = 0;
-
- if (scifdev_self(scifdev)) {
- *dma_handle = page_to_phys(page);
- } else {
- struct scif_hw_dev *sdev = scifdev->sdev;
- *dma_handle = dma_map_page(&sdev->dev,
- page, 0x0, PAGE_SIZE,
- DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&sdev->dev, *dma_handle))
- err = -ENOMEM;
- else if (scifdev_is_p2p(scifdev))
- *dma_handle = *dma_handle + scifdev->base_addr;
- }
- if (err)
- *dma_handle = 0;
- return err;
-}
-#endif /* SCIF_MAP_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-
-/*
- * struct scif_vma_info - Information about a remote memory mapping
- * created via scif_mmap(..)
- * @vma: VM area struct
- * @list: link to list of active vmas
- */
-struct scif_vma_info {
- struct vm_area_struct *vma;
- struct list_head list;
-};
-
-void scif_recv_munmap(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- struct scif_window *recv_window =
- (struct scif_window *)msg->payload[0];
- struct scif_endpt *ep;
-
- ep = (struct scif_endpt *)recv_window->ep;
- req.out_window = &window;
- req.offset = recv_window->offset;
- req.prot = recv_window->prot;
- req.nr_bytes = recv_window->nr_pages << PAGE_SHIFT;
- req.type = SCIF_WINDOW_FULL;
- req.head = &ep->rma_info.reg_list;
- msg->payload[0] = ep->remote_ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- if (scif_query_window(&req)) {
- dev_err(&scifdev->sdev->dev,
- "%s %d -ENXIO\n", __func__, __LINE__);
- msg->uop = SCIF_UNREGISTER_ACK;
- goto error;
- }
-
- scif_put_window(window, window->nr_pages);
-
- if (!window->ref_count) {
- atomic_inc(&ep->rma_info.tw_refcount);
- ep->rma_info.async_list_del = 1;
- list_del_init(&window->list);
- scif_free_window_offset(ep, window, window->offset);
- }
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (window && !window->ref_count)
- scif_queue_for_cleanup(window, &scif_info.rma);
-}
-
-/*
- * Remove valid remote memory mappings created via scif_mmap(..) from the
- * process address space since the remote node is lost
- */
-static void __scif_zap_mmaps(struct scif_endpt *ep)
-{
- struct list_head *item;
- struct scif_vma_info *info;
- struct vm_area_struct *vma;
- unsigned long size;
-
- spin_lock(&ep->lock);
- list_for_each(item, &ep->rma_info.vma_list) {
- info = list_entry(item, struct scif_vma_info, list);
- vma = info->vma;
- size = vma->vm_end - vma->vm_start;
- zap_vma_ptes(vma, vma->vm_start, size);
- dev_dbg(scif_info.mdev.this_device,
- "%s ep %p zap vma %p size 0x%lx\n",
- __func__, ep, info->vma, size);
- }
- spin_unlock(&ep->lock);
-}
-
-/*
- * Traverse the list of endpoints for a particular remote node and
- * zap valid remote memory mappings since the remote node is lost
- */
-static void _scif_zap_mmaps(int node, struct list_head *head)
-{
- struct scif_endpt *ep;
- struct list_head *item;
-
- mutex_lock(&scif_info.connlock);
- list_for_each(item, head) {
- ep = list_entry(item, struct scif_endpt, list);
- if (ep->remote_dev->node == node)
- __scif_zap_mmaps(ep);
- }
- mutex_unlock(&scif_info.connlock);
-}
-
-/*
- * Wrapper for removing remote memory mappings for a particular node. This API
- * is called by peer nodes as part of handling a lost node.
- */
-void scif_zap_mmaps(int node)
-{
- _scif_zap_mmaps(node, &scif_info.connected);
- _scif_zap_mmaps(node, &scif_info.disconnected);
-}
-
-/*
- * This API is only called while handling a lost node:
- * a) Remote node is dead.
- * b) Remote memory mappings have been zapped
- * So we can traverse the remote_reg_list without any locks. Since
- * the window has not yet been unregistered we can drop the ref count
- * and queue it to the cleanup thread.
- */
-static void __scif_cleanup_rma_for_zombies(struct scif_endpt *ep)
-{
- struct list_head *pos, *tmp;
- struct scif_window *window;
-
- list_for_each_safe(pos, tmp, &ep->rma_info.remote_reg_list) {
- window = list_entry(pos, struct scif_window, list);
- if (window->ref_count)
- scif_put_window(window, window->nr_pages);
- else
- dev_err(scif_info.mdev.this_device,
- "%s %d unexpected\n",
- __func__, __LINE__);
- if (!window->ref_count) {
- atomic_inc(&ep->rma_info.tw_refcount);
- list_del_init(&window->list);
- scif_queue_for_cleanup(window, &scif_info.rma);
- }
- }
-}
-
-/* Cleanup remote registration lists for zombie endpoints */
-void scif_cleanup_rma_for_zombies(int node)
-{
- struct scif_endpt *ep;
- struct list_head *item;
-
- mutex_lock(&scif_info.eplock);
- list_for_each(item, &scif_info.zombie) {
- ep = list_entry(item, struct scif_endpt, list);
- if (ep->remote_dev && ep->remote_dev->node == node)
- __scif_cleanup_rma_for_zombies(ep);
- }
- mutex_unlock(&scif_info.eplock);
- flush_work(&scif_info.misc_work);
-}
-
-/* Insert the VMA into the per endpoint VMA list */
-static int scif_insert_vma(struct scif_endpt *ep, struct vm_area_struct *vma)
-{
- struct scif_vma_info *info;
- int err = 0;
-
- info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info) {
- err = -ENOMEM;
- goto done;
- }
- info->vma = vma;
- spin_lock(&ep->lock);
- list_add_tail(&info->list, &ep->rma_info.vma_list);
- spin_unlock(&ep->lock);
-done:
- return err;
-}
-
-/* Delete the VMA from the per endpoint VMA list */
-static void scif_delete_vma(struct scif_endpt *ep, struct vm_area_struct *vma)
-{
- struct list_head *item;
- struct scif_vma_info *info;
-
- spin_lock(&ep->lock);
- list_for_each(item, &ep->rma_info.vma_list) {
- info = list_entry(item, struct scif_vma_info, list);
- if (info->vma == vma) {
- list_del(&info->list);
- kfree(info);
- break;
- }
- }
- spin_unlock(&ep->lock);
-}
-
-static phys_addr_t scif_get_phys(phys_addr_t phys, struct scif_endpt *ep)
-{
- struct scif_dev *scifdev = (struct scif_dev *)ep->remote_dev;
- struct scif_hw_dev *sdev = scifdev->sdev;
- phys_addr_t out_phys, apt_base = 0;
-
- /*
- * If the DMA address is card relative then we need to add the
- * aperture base for mmap to work correctly
- */
- if (!scifdev_self(scifdev) && sdev->aper && sdev->card_rel_da)
- apt_base = sdev->aper->pa;
- out_phys = apt_base + phys;
- return out_phys;
-}
-
-int scif_get_pages(scif_epd_t epd, off_t offset, size_t len,
- struct scif_range **pages)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- int nr_pages, err, i;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI get_pinned_pages: ep %p offset 0x%lx len 0x%lx\n",
- ep, offset, len);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- if (!len || (offset < 0) ||
- (offset + len < offset) ||
- (ALIGN(offset, PAGE_SIZE) != offset) ||
- (ALIGN(len, PAGE_SIZE) != len))
- return -EINVAL;
-
- nr_pages = len >> PAGE_SHIFT;
-
- req.out_window = &window;
- req.offset = offset;
- req.prot = 0;
- req.nr_bytes = len;
- req.type = SCIF_WINDOW_SINGLE;
- req.head = &ep->rma_info.remote_reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error;
- }
-
- /* Allocate scif_range */
- *pages = kzalloc(sizeof(**pages), GFP_KERNEL);
- if (!*pages) {
- err = -ENOMEM;
- goto error;
- }
-
- /* Allocate phys addr array */
- (*pages)->phys_addr = scif_zalloc(nr_pages * sizeof(dma_addr_t));
- if (!((*pages)->phys_addr)) {
- err = -ENOMEM;
- goto error;
- }
-
- if (scif_is_mgmt_node() && !scifdev_self(ep->remote_dev)) {
- /* Allocate virtual address array */
- ((*pages)->va = scif_zalloc(nr_pages * sizeof(void *)));
- if (!(*pages)->va) {
- err = -ENOMEM;
- goto error;
- }
- }
- /* Populate the values */
- (*pages)->cookie = window;
- (*pages)->nr_pages = nr_pages;
- (*pages)->prot_flags = window->prot;
-
- for (i = 0; i < nr_pages; i++) {
- (*pages)->phys_addr[i] =
- __scif_off_to_dma_addr(window, offset +
- (i * PAGE_SIZE));
- (*pages)->phys_addr[i] = scif_get_phys((*pages)->phys_addr[i],
- ep);
- if (scif_is_mgmt_node() && !scifdev_self(ep->remote_dev))
- (*pages)->va[i] =
- ep->remote_dev->sdev->aper->va +
- (*pages)->phys_addr[i] -
- ep->remote_dev->sdev->aper->pa;
- }
-
- scif_get_window(window, nr_pages);
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (err) {
- if (*pages) {
- scif_free((*pages)->phys_addr,
- nr_pages * sizeof(dma_addr_t));
- scif_free((*pages)->va,
- nr_pages * sizeof(void *));
- kfree(*pages);
- *pages = NULL;
- }
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- }
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_get_pages);
-
-int scif_put_pages(struct scif_range *pages)
-{
- struct scif_endpt *ep;
- struct scif_window *window;
- struct scifmsg msg;
-
- if (!pages || !pages->cookie)
- return -EINVAL;
-
- window = pages->cookie;
-
- if (!window || window->magic != SCIFEP_MAGIC)
- return -EINVAL;
-
- ep = (struct scif_endpt *)window->ep;
- /*
- * If the state is SCIFEP_CONNECTED or SCIFEP_DISCONNECTED then the
- * callee should be allowed to release references to the pages,
- * else the endpoint was not connected in the first place,
- * hence the ENOTCONN.
- */
- if (ep->state != SCIFEP_CONNECTED && ep->state != SCIFEP_DISCONNECTED)
- return -ENOTCONN;
-
- mutex_lock(&ep->rma_info.rma_lock);
-
- scif_put_window(window, pages->nr_pages);
-
- /* Initiate window destruction if ref count is zero */
- if (!window->ref_count) {
- list_del(&window->list);
- mutex_unlock(&ep->rma_info.rma_lock);
- scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan);
- /* Inform the peer about this window being destroyed. */
- msg.uop = SCIF_MUNMAP;
- msg.src = ep->port;
- msg.payload[0] = window->peer_window;
- /* No error handling for notification messages */
- scif_nodeqp_send(ep->remote_dev, &msg);
- /* Destroy this window from the peer's registered AS */
- scif_destroy_remote_window(window);
- } else {
- mutex_unlock(&ep->rma_info.rma_lock);
- }
-
- scif_free(pages->phys_addr, pages->nr_pages * sizeof(dma_addr_t));
- scif_free(pages->va, pages->nr_pages * sizeof(void *));
- kfree(pages);
- return 0;
-}
-EXPORT_SYMBOL_GPL(scif_put_pages);
-
-/*
- * scif_rma_list_mmap:
- *
- * Traverse the remote registration list starting from start_window:
- * 1) Create VtoP mappings via remap_pfn_range(..)
- * 2) Once step 1) and 2) complete successfully then traverse the range of
- * windows again and bump the reference count.
- * RMA lock must be held.
- */
-static int scif_rma_list_mmap(struct scif_window *start_window, s64 offset,
- int nr_pages, struct vm_area_struct *vma)
-{
- s64 end_offset, loop_offset = offset;
- struct scif_window *window = start_window;
- int loop_nr_pages, nr_pages_left = nr_pages;
- struct scif_endpt *ep = (struct scif_endpt *)start_window->ep;
- struct list_head *head = &ep->rma_info.remote_reg_list;
- int i, err = 0;
- dma_addr_t phys_addr;
- struct scif_window_iter src_win_iter;
- size_t contig_bytes = 0;
-
- might_sleep();
- list_for_each_entry_from(window, head, list) {
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min_t(int,
- (end_offset - loop_offset) >> PAGE_SHIFT,
- nr_pages_left);
- scif_init_window_iter(window, &src_win_iter);
- for (i = 0; i < loop_nr_pages; i++) {
- phys_addr = scif_off_to_dma_addr(window, loop_offset,
- &contig_bytes,
- &src_win_iter);
- phys_addr = scif_get_phys(phys_addr, ep);
- err = remap_pfn_range(vma,
- vma->vm_start +
- loop_offset - offset,
- phys_addr >> PAGE_SHIFT,
- PAGE_SIZE,
- vma->vm_page_prot);
- if (err)
- goto error;
- loop_offset += PAGE_SIZE;
- }
- nr_pages_left -= loop_nr_pages;
- if (!nr_pages_left)
- break;
- }
- /*
- * No more failures expected. Bump up the ref count for all
- * the windows. Another traversal from start_window required
- * for handling errors encountered across windows during
- * remap_pfn_range(..).
- */
- loop_offset = offset;
- nr_pages_left = nr_pages;
- window = start_window;
- head = &ep->rma_info.remote_reg_list;
- list_for_each_entry_from(window, head, list) {
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min_t(int,
- (end_offset - loop_offset) >> PAGE_SHIFT,
- nr_pages_left);
- scif_get_window(window, loop_nr_pages);
- nr_pages_left -= loop_nr_pages;
- loop_offset += (loop_nr_pages << PAGE_SHIFT);
- if (!nr_pages_left)
- break;
- }
-error:
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-
-/*
- * scif_rma_list_munmap:
- *
- * Traverse the remote registration list starting from window:
- * 1) Decrement ref count.
- * 2) If the ref count drops to zero then send a SCIF_MUNMAP message to peer.
- * RMA lock must be held.
- */
-static void scif_rma_list_munmap(struct scif_window *start_window,
- s64 offset, int nr_pages)
-{
- struct scifmsg msg;
- s64 loop_offset = offset, end_offset;
- int loop_nr_pages, nr_pages_left = nr_pages;
- struct scif_endpt *ep = (struct scif_endpt *)start_window->ep;
- struct list_head *head = &ep->rma_info.remote_reg_list;
- struct scif_window *window = start_window, *_window;
-
- msg.uop = SCIF_MUNMAP;
- msg.src = ep->port;
- loop_offset = offset;
- nr_pages_left = nr_pages;
- list_for_each_entry_safe_from(window, _window, head, list) {
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min_t(int,
- (end_offset - loop_offset) >> PAGE_SHIFT,
- nr_pages_left);
- scif_put_window(window, loop_nr_pages);
- if (!window->ref_count) {
- struct scif_dev *rdev = ep->remote_dev;
-
- scif_drain_dma_intr(rdev->sdev,
- ep->rma_info.dma_chan);
- /* Inform the peer about this munmap */
- msg.payload[0] = window->peer_window;
- /* No error handling for Notification messages. */
- scif_nodeqp_send(ep->remote_dev, &msg);
- list_del(&window->list);
- /* Destroy this window from the peer's registered AS */
- scif_destroy_remote_window(window);
- }
- nr_pages_left -= loop_nr_pages;
- loop_offset += (loop_nr_pages << PAGE_SHIFT);
- if (!nr_pages_left)
- break;
- }
-}
-
-/*
- * The private data field of each VMA used to mmap a remote window
- * points to an instance of struct vma_pvt
- */
-struct vma_pvt {
- struct scif_endpt *ep; /* End point for remote window */
- s64 offset; /* offset within remote window */
- bool valid_offset; /* offset is valid only if the original
- * mmap request was for a single page
- * else the offset within the vma is
- * the correct offset
- */
- struct kref ref;
-};
-
-static void vma_pvt_release(struct kref *ref)
-{
- struct vma_pvt *vmapvt = container_of(ref, struct vma_pvt, ref);
-
- kfree(vmapvt);
-}
-
-/**
- * scif_vma_open - VMA open driver callback
- * @vma: VMM memory area.
- * The open method is called by the kernel to allow the subsystem implementing
- * the VMA to initialize the area. This method is invoked any time a new
- * reference to the VMA is made (when a process forks, for example).
- * The one exception happens when the VMA is first created by mmap;
- * in this case, the driver's mmap method is called instead.
- * This function is also invoked when an existing VMA is split by the kernel
- * due to a call to munmap on a subset of the VMA resulting in two VMAs.
- * The kernel invokes this function only on one of the two VMAs.
- */
-static void scif_vma_open(struct vm_area_struct *vma)
-{
- struct vma_pvt *vmapvt = vma->vm_private_data;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI vma open: vma_start 0x%lx vma_end 0x%lx\n",
- vma->vm_start, vma->vm_end);
- scif_insert_vma(vmapvt->ep, vma);
- kref_get(&vmapvt->ref);
-}
-
-/**
- * scif_munmap - VMA close driver callback.
- * @vma: VMM memory area.
- * When an area is destroyed, the kernel calls its close operation.
- * Note that there's no usage count associated with VMA's; the area
- * is opened and closed exactly once by each process that uses it.
- */
-static void scif_munmap(struct vm_area_struct *vma)
-{
- struct scif_endpt *ep;
- struct vma_pvt *vmapvt = vma->vm_private_data;
- int nr_pages = vma_pages(vma);
- s64 offset;
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- int err;
-
- might_sleep();
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI munmap: vma_start 0x%lx vma_end 0x%lx\n",
- vma->vm_start, vma->vm_end);
- ep = vmapvt->ep;
- offset = vmapvt->valid_offset ? vmapvt->offset :
- (vma->vm_pgoff) << PAGE_SHIFT;
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI munmap: ep %p nr_pages 0x%x offset 0x%llx\n",
- ep, nr_pages, offset);
- req.out_window = &window;
- req.offset = offset;
- req.nr_bytes = vma->vm_end - vma->vm_start;
- req.prot = vma->vm_flags & (VM_READ | VM_WRITE);
- req.type = SCIF_WINDOW_PARTIAL;
- req.head = &ep->rma_info.remote_reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
-
- err = scif_query_window(&req);
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- else
- scif_rma_list_munmap(window, offset, nr_pages);
-
- mutex_unlock(&ep->rma_info.rma_lock);
- /*
- * The kernel probably zeroes these out but we still want
- * to clean up our own mess just in case.
- */
- vma->vm_ops = NULL;
- vma->vm_private_data = NULL;
- kref_put(&vmapvt->ref, vma_pvt_release);
- scif_delete_vma(ep, vma);
-}
-
-static const struct vm_operations_struct scif_vm_ops = {
- .open = scif_vma_open,
- .close = scif_munmap,
-};
-
-/**
- * scif_mmap - Map pages in virtual address space to a remote window.
- * @vma: VMM memory area.
- * @epd: endpoint descriptor
- *
- * Return: Upon successful completion, scif_mmap() returns zero
- * else an apt error is returned as documented in scif.h
- */
-int scif_mmap(struct vm_area_struct *vma, scif_epd_t epd)
-{
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- s64 start_offset = vma->vm_pgoff << PAGE_SHIFT;
- int nr_pages = vma_pages(vma);
- int err;
- struct vma_pvt *vmapvt;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI mmap: ep %p start_offset 0x%llx nr_pages 0x%x\n",
- ep, start_offset, nr_pages);
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- might_sleep();
-
- err = scif_insert_vma(ep, vma);
- if (err)
- return err;
-
- vmapvt = kzalloc(sizeof(*vmapvt), GFP_KERNEL);
- if (!vmapvt) {
- scif_delete_vma(ep, vma);
- return -ENOMEM;
- }
-
- vmapvt->ep = ep;
- kref_init(&vmapvt->ref);
-
- req.out_window = &window;
- req.offset = start_offset;
- req.nr_bytes = vma->vm_end - vma->vm_start;
- req.prot = vma->vm_flags & (VM_READ | VM_WRITE);
- req.type = SCIF_WINDOW_PARTIAL;
- req.head = &ep->rma_info.remote_reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unlock;
- }
-
- /* Default prot for loopback */
- if (!scifdev_self(ep->remote_dev))
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
- /*
- * VM_DONTCOPY - Do not copy this vma on fork
- * VM_DONTEXPAND - Cannot expand with mremap()
- * VM_RESERVED - Count as reserved_vm like IO
- * VM_PFNMAP - Page-ranges managed without "struct page"
- * VM_IO - Memory mapped I/O or similar
- *
- * We do not want to copy this VMA automatically on a fork(),
- * expand this VMA due to mremap() or swap out these pages since
- * the VMA is actually backed by physical pages in the remote
- * node's physical memory and not via a struct page.
- */
- vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
-
- if (!scifdev_self(ep->remote_dev))
- vma->vm_flags |= VM_IO | VM_PFNMAP;
-
- /* Map this range of windows */
- err = scif_rma_list_mmap(window, start_offset, nr_pages, vma);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unlock;
- }
- /* Set up the driver call back */
- vma->vm_ops = &scif_vm_ops;
- vma->vm_private_data = vmapvt;
-error_unlock:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (err) {
- kfree(vmapvt);
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- scif_delete_vma(ep, vma);
- }
- return err;
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_peer_bus.h"
-
-#include "scif_main.h"
-#include "scif_map.h"
-
-/**
- * scif_invalidate_ep() - Set state for all connected endpoints
- * to disconnected and wake up all send/recv waitqueues
- *
- * @node: Node to invalidate
- */
-static void scif_invalidate_ep(int node)
-{
- struct scif_endpt *ep;
- struct list_head *pos, *tmpq;
-
- flush_work(&scif_info.conn_work);
- mutex_lock(&scif_info.connlock);
- list_for_each_safe(pos, tmpq, &scif_info.disconnected) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (ep->remote_dev->node == node) {
- scif_unmap_all_windows(ep);
- spin_lock(&ep->lock);
- scif_cleanup_ep_qp(ep);
- spin_unlock(&ep->lock);
- }
- }
- list_for_each_safe(pos, tmpq, &scif_info.connected) {
- ep = list_entry(pos, struct scif_endpt, list);
- if (ep->remote_dev->node == node) {
- list_del(pos);
- spin_lock(&ep->lock);
- ep->state = SCIFEP_DISCONNECTED;
- list_add_tail(&ep->list, &scif_info.disconnected);
- scif_cleanup_ep_qp(ep);
- wake_up_interruptible(&ep->sendwq);
- wake_up_interruptible(&ep->recvwq);
- spin_unlock(&ep->lock);
- scif_unmap_all_windows(ep);
- }
- }
- mutex_unlock(&scif_info.connlock);
-}
-
-void scif_free_qp(struct scif_dev *scifdev)
-{
- struct scif_qp *qp = scifdev->qpairs;
-
- if (!qp)
- return;
- scif_unmap_single(qp->local_buf, scifdev, qp->inbound_q.size);
- kfree(qp->inbound_q.rb_base);
- scif_unmap_single(qp->local_qp, scifdev, sizeof(struct scif_qp));
- kfree(scifdev->qpairs);
- scifdev->qpairs = NULL;
-}
-
-static void scif_cleanup_qp(struct scif_dev *dev)
-{
- struct scif_qp *qp = &dev->qpairs[0];
-
- if (!qp)
- return;
- scif_iounmap((void *)qp->remote_qp, sizeof(struct scif_qp), dev);
- scif_iounmap((void *)qp->outbound_q.rb_base,
- sizeof(struct scif_qp), dev);
- qp->remote_qp = NULL;
- qp->local_write = 0;
- qp->inbound_q.current_write_offset = 0;
- qp->inbound_q.current_read_offset = 0;
- if (scifdev_is_p2p(dev))
- scif_free_qp(dev);
-}
-
-void scif_send_acks(struct scif_dev *dev)
-{
- struct scifmsg msg;
-
- if (dev->node_remove_ack_pending) {
- msg.uop = SCIF_NODE_REMOVE_ACK;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = SCIF_MGMT_NODE;
- msg.payload[0] = dev->node;
- scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], &msg);
- dev->node_remove_ack_pending = false;
- }
- if (dev->exit_ack_pending) {
- msg.uop = SCIF_EXIT_ACK;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = dev->node;
- scif_nodeqp_send(dev, &msg);
- dev->exit_ack_pending = false;
- }
-}
-
-/**
- * scif_cleanup_scifdev - Uninitialize SCIF data structures for remote
- * SCIF device.
- * @dev: Remote SCIF device.
- */
-void scif_cleanup_scifdev(struct scif_dev *dev)
-{
- struct scif_hw_dev *sdev = dev->sdev;
-
- if (!dev->sdev)
- return;
- if (scifdev_is_p2p(dev)) {
- if (dev->cookie) {
- sdev->hw_ops->free_irq(sdev, dev->cookie, dev);
- dev->cookie = NULL;
- }
- scif_destroy_intr_wq(dev);
- }
- flush_work(&scif_info.misc_work);
- scif_destroy_p2p(dev);
- scif_invalidate_ep(dev->node);
- scif_zap_mmaps(dev->node);
- scif_cleanup_rma_for_zombies(dev->node);
- flush_work(&scif_info.misc_work);
- scif_send_acks(dev);
- if (!dev->node && scif_info.card_initiated_exit) {
- /*
- * Send an SCIF_EXIT message which is the last message from MIC
- * to the Host and wait for a SCIF_EXIT_ACK
- */
- scif_send_exit(dev);
- scif_info.card_initiated_exit = false;
- }
- scif_cleanup_qp(dev);
-}
-
-/**
- * scif_remove_node
- *
- * @node: Node to remove
- */
-void scif_handle_remove_node(int node)
-{
- struct scif_dev *scifdev = &scif_dev[node];
-
- if (scif_peer_unregister_device(scifdev))
- scif_send_acks(scifdev);
-}
-
-static int scif_send_rmnode_msg(int node, int remove_node)
-{
- struct scifmsg notif_msg;
- struct scif_dev *dev = &scif_dev[node];
-
- notif_msg.uop = SCIF_NODE_REMOVE;
- notif_msg.src.node = scif_info.nodeid;
- notif_msg.dst.node = node;
- notif_msg.payload[0] = remove_node;
- return scif_nodeqp_send(dev, ¬if_msg);
-}
-
-/**
- * scif_node_disconnect
- *
- * @node_id: source node id [in]
- * @mgmt_initiated: Disconnection initiated from the mgmt node
- *
- * Disconnect a node from the scif network.
- */
-void scif_disconnect_node(u32 node_id, bool mgmt_initiated)
-{
- int ret;
- int msg_cnt = 0;
- u32 i = 0;
- struct scif_dev *scifdev = &scif_dev[node_id];
-
- if (!node_id)
- return;
-
- atomic_set(&scifdev->disconn_rescnt, 0);
-
- /* Destroy p2p network */
- for (i = 1; i <= scif_info.maxid; i++) {
- if (i == node_id)
- continue;
- ret = scif_send_rmnode_msg(i, node_id);
- if (!ret)
- msg_cnt++;
- }
- /* Wait for the remote nodes to respond with SCIF_NODE_REMOVE_ACK */
- ret = wait_event_timeout(scifdev->disconn_wq,
- (atomic_read(&scifdev->disconn_rescnt)
- == msg_cnt), SCIF_NODE_ALIVE_TIMEOUT);
- /* Tell the card to clean up */
- if (mgmt_initiated && _scifdev_alive(scifdev))
- /*
- * Send an SCIF_EXIT message which is the last message from Host
- * to the MIC and wait for a SCIF_EXIT_ACK
- */
- scif_send_exit(scifdev);
- atomic_set(&scifdev->disconn_rescnt, 0);
- /* Tell the mgmt node to clean up */
- ret = scif_send_rmnode_msg(SCIF_MGMT_NODE, node_id);
- if (!ret)
- /* Wait for mgmt node to respond with SCIF_NODE_REMOVE_ACK */
- wait_event_timeout(scifdev->disconn_wq,
- (atomic_read(&scifdev->disconn_rescnt) == 1),
- SCIF_NODE_ALIVE_TIMEOUT);
-}
-
-void scif_get_node_info(void)
-{
- struct scifmsg msg;
- DECLARE_COMPLETION_ONSTACK(node_info);
-
- msg.uop = SCIF_GET_NODE_INFO;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = SCIF_MGMT_NODE;
- msg.payload[3] = (u64)&node_info;
-
- if ((scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], &msg)))
- return;
-
- /* Wait for a response with SCIF_GET_NODE_INFO */
- wait_for_completion(&node_info);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-#include "scif_main.h"
-#include "scif_nodeqp.h"
-#include "scif_map.h"
-
-/*
- ************************************************************************
- * SCIF node Queue Pair (QP) setup flow:
- *
- * 1) SCIF driver gets probed with a scif_hw_dev via the scif_hw_bus
- * 2) scif_setup_qp(..) allocates the local qp and calls
- * scif_setup_qp_connect(..) which allocates and maps the local
- * buffer for the inbound QP
- * 3) The local node updates the device page with the DMA address of the QP
- * 4) A delayed work is scheduled (qp_dwork) which periodically reads if
- * the peer node has updated its QP DMA address
- * 5) Once a valid non zero address is found in the QP DMA address field
- * in the device page, the local node maps the remote node's QP,
- * updates its outbound QP and sends a SCIF_INIT message to the peer
- * 6) The SCIF_INIT message is received by the peer node QP interrupt bottom
- * half handler by calling scif_init(..)
- * 7) scif_init(..) registers a new SCIF peer node by calling
- * scif_peer_register_device(..) which signifies the addition of a new
- * SCIF node
- * 8) On the mgmt node, P2P network setup/teardown is initiated if all the
- * remote nodes are online via scif_p2p_setup(..)
- * 9) For P2P setup, the host maps the remote nodes' aperture and memory
- * bars and sends a SCIF_NODE_ADD message to both nodes
- * 10) As part of scif_nodeadd, both nodes set up their local inbound
- * QPs and send a SCIF_NODE_ADD_ACK to the mgmt node
- * 11) As part of scif_node_add_ack(..) the mgmt node forwards the
- * SCIF_NODE_ADD_ACK to the remote nodes
- * 12) As part of scif_node_add_ack(..) the remote nodes update their
- * outbound QPs, make sure they can access memory on the remote node
- * and then add a new SCIF peer node by calling
- * scif_peer_register_device(..) which signifies the addition of a new
- * SCIF node.
- * 13) The SCIF network is now established across all nodes.
- *
- ************************************************************************
- * SCIF node QP teardown flow (initiated by non mgmt node):
- *
- * 1) SCIF driver gets a remove callback with a scif_hw_dev via the scif_hw_bus
- * 2) The device page QP DMA address field is updated with 0x0
- * 3) A non mgmt node now cleans up all local data structures and sends a
- * SCIF_EXIT message to the peer and waits for a SCIF_EXIT_ACK
- * 4) As part of scif_exit(..) handling scif_disconnect_node(..) is called
- * 5) scif_disconnect_node(..) sends a SCIF_NODE_REMOVE message to all the
- * peers and waits for a SCIF_NODE_REMOVE_ACK
- * 6) As part of scif_node_remove(..) a remote node unregisters the peer
- * node from the SCIF network and sends a SCIF_NODE_REMOVE_ACK
- * 7) When the mgmt node has received all the SCIF_NODE_REMOVE_ACKs
- * it sends itself a node remove message whose handling cleans up local
- * data structures and unregisters the peer node from the SCIF network
- * 8) The mgmt node sends a SCIF_EXIT_ACK
- * 9) Upon receipt of the SCIF_EXIT_ACK the node initiating the teardown
- * completes the SCIF remove routine
- * 10) The SCIF network is now torn down for the node initiating the
- * teardown sequence
- *
- ************************************************************************
- * SCIF node QP teardown flow (initiated by mgmt node):
- *
- * 1) SCIF driver gets a remove callback with a scif_hw_dev via the scif_hw_bus
- * 2) The device page QP DMA address field is updated with 0x0
- * 3) The mgmt node calls scif_disconnect_node(..)
- * 4) scif_disconnect_node(..) sends a SCIF_NODE_REMOVE message to all the peers
- * and waits for a SCIF_NODE_REMOVE_ACK
- * 5) As part of scif_node_remove(..) a remote node unregisters the peer
- * node from the SCIF network and sends a SCIF_NODE_REMOVE_ACK
- * 6) When the mgmt node has received all the SCIF_NODE_REMOVE_ACKs
- * it unregisters the peer node from the SCIF network
- * 7) The mgmt node sends a SCIF_EXIT message and waits for a SCIF_EXIT_ACK.
- * 8) A non mgmt node upon receipt of a SCIF_EXIT message calls scif_stop(..)
- * which would clean up local data structures for all SCIF nodes and
- * then send a SCIF_EXIT_ACK back to the mgmt node
- * 9) Upon receipt of the SCIF_EXIT_ACK the the mgmt node sends itself a node
- * remove message whose handling cleans up local data structures and
- * destroys any P2P mappings.
- * 10) The SCIF hardware device for which a remove callback was received is now
- * disconnected from the SCIF network.
- */
-/*
- * Initializes "local" data structures for the QP. Allocates the QP
- * ring buffer (rb) and initializes the "in bound" queue.
- */
-int scif_setup_qp_connect(struct scif_qp *qp, dma_addr_t *qp_offset,
- int local_size, struct scif_dev *scifdev)
-{
- void *local_q = qp->inbound_q.rb_base;
- int err = 0;
- u32 tmp_rd = 0;
-
- spin_lock_init(&qp->send_lock);
- spin_lock_init(&qp->recv_lock);
-
- /* Allocate rb only if not already allocated */
- if (!local_q) {
- local_q = kzalloc(local_size, GFP_KERNEL);
- if (!local_q) {
- err = -ENOMEM;
- return err;
- }
- }
-
- err = scif_map_single(&qp->local_buf, local_q, scifdev, local_size);
- if (err)
- goto kfree;
- /*
- * To setup the inbound_q, the buffer lives locally, the read pointer
- * is remote and the write pointer is local.
- */
- scif_rb_init(&qp->inbound_q,
- &tmp_rd,
- &qp->local_write,
- local_q, get_count_order(local_size));
- /*
- * The read pointer is NULL initially and it is unsafe to use the ring
- * buffer til this changes!
- */
- qp->inbound_q.read_ptr = NULL;
- err = scif_map_single(qp_offset, qp,
- scifdev, sizeof(struct scif_qp));
- if (err)
- goto unmap;
- qp->local_qp = *qp_offset;
- return err;
-unmap:
- scif_unmap_single(qp->local_buf, scifdev, local_size);
- qp->local_buf = 0;
-kfree:
- kfree(local_q);
- return err;
-}
-
-/* When the other side has already done it's allocation, this is called */
-int scif_setup_qp_accept(struct scif_qp *qp, dma_addr_t *qp_offset,
- dma_addr_t phys, int local_size,
- struct scif_dev *scifdev)
-{
- void *local_q;
- void *remote_q;
- struct scif_qp *remote_qp;
- int remote_size;
- int err = 0;
-
- spin_lock_init(&qp->send_lock);
- spin_lock_init(&qp->recv_lock);
- /* Start by figuring out where we need to point */
- remote_qp = scif_ioremap(phys, sizeof(struct scif_qp), scifdev);
- if (!remote_qp)
- return -EIO;
- qp->remote_qp = remote_qp;
- if (qp->remote_qp->magic != SCIFEP_MAGIC) {
- err = -EIO;
- goto iounmap;
- }
- qp->remote_buf = remote_qp->local_buf;
- remote_size = qp->remote_qp->inbound_q.size;
- remote_q = scif_ioremap(qp->remote_buf, remote_size, scifdev);
- if (!remote_q) {
- err = -EIO;
- goto iounmap;
- }
- qp->remote_qp->local_write = 0;
- /*
- * To setup the outbound_q, the buffer lives in remote memory,
- * the read pointer is local, the write pointer is remote
- */
- scif_rb_init(&qp->outbound_q,
- &qp->local_read,
- &qp->remote_qp->local_write,
- remote_q,
- get_count_order(remote_size));
- local_q = kzalloc(local_size, GFP_KERNEL);
- if (!local_q) {
- err = -ENOMEM;
- goto iounmap_1;
- }
- err = scif_map_single(&qp->local_buf, local_q, scifdev, local_size);
- if (err)
- goto kfree;
- qp->remote_qp->local_read = 0;
- /*
- * To setup the inbound_q, the buffer lives locally, the read pointer
- * is remote and the write pointer is local
- */
- scif_rb_init(&qp->inbound_q,
- &qp->remote_qp->local_read,
- &qp->local_write,
- local_q, get_count_order(local_size));
- err = scif_map_single(qp_offset, qp, scifdev,
- sizeof(struct scif_qp));
- if (err)
- goto unmap;
- qp->local_qp = *qp_offset;
- return err;
-unmap:
- scif_unmap_single(qp->local_buf, scifdev, local_size);
- qp->local_buf = 0;
-kfree:
- kfree(local_q);
-iounmap_1:
- scif_iounmap(remote_q, remote_size, scifdev);
- qp->outbound_q.rb_base = NULL;
-iounmap:
- scif_iounmap(qp->remote_qp, sizeof(struct scif_qp), scifdev);
- qp->remote_qp = NULL;
- return err;
-}
-
-int scif_setup_qp_connect_response(struct scif_dev *scifdev,
- struct scif_qp *qp, u64 payload)
-{
- int err = 0;
- void *r_buf;
- int remote_size;
- phys_addr_t tmp_phys;
-
- qp->remote_qp = scif_ioremap(payload, sizeof(struct scif_qp), scifdev);
-
- if (!qp->remote_qp) {
- err = -ENOMEM;
- goto error;
- }
-
- if (qp->remote_qp->magic != SCIFEP_MAGIC) {
- dev_err(&scifdev->sdev->dev,
- "SCIFEP_MAGIC mismatch between self %d remote %d\n",
- scif_dev[scif_info.nodeid].node, scifdev->node);
- err = -ENODEV;
- goto error;
- }
-
- tmp_phys = qp->remote_qp->local_buf;
- remote_size = qp->remote_qp->inbound_q.size;
- r_buf = scif_ioremap(tmp_phys, remote_size, scifdev);
-
- if (!r_buf)
- return -EIO;
-
- qp->local_read = 0;
- scif_rb_init(&qp->outbound_q,
- &qp->local_read,
- &qp->remote_qp->local_write,
- r_buf,
- get_count_order(remote_size));
- /*
- * Because the node QP may already be processing an INIT message, set
- * the read pointer so the cached read offset isn't lost
- */
- qp->remote_qp->local_read = qp->inbound_q.current_read_offset;
- /*
- * resetup the inbound_q now that we know where the
- * inbound_read really is.
- */
- scif_rb_init(&qp->inbound_q,
- &qp->remote_qp->local_read,
- &qp->local_write,
- qp->inbound_q.rb_base,
- get_count_order(qp->inbound_q.size));
-error:
- return err;
-}
-
-static __always_inline void
-scif_send_msg_intr(struct scif_dev *scifdev)
-{
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- if (scifdev_is_p2p(scifdev))
- sdev->hw_ops->send_p2p_intr(sdev, scifdev->rdb, &scifdev->mmio);
- else
- sdev->hw_ops->send_intr(sdev, scifdev->rdb);
-}
-
-int scif_qp_response(phys_addr_t phys, struct scif_dev *scifdev)
-{
- int err = 0;
- struct scifmsg msg;
-
- err = scif_setup_qp_connect_response(scifdev, scifdev->qpairs, phys);
- if (!err) {
- /*
- * Now that everything is setup and mapped, we're ready
- * to tell the peer about our queue's location
- */
- msg.uop = SCIF_INIT;
- msg.dst.node = scifdev->node;
- err = scif_nodeqp_send(scifdev, &msg);
- }
- return err;
-}
-
-void scif_send_exit(struct scif_dev *scifdev)
-{
- struct scifmsg msg;
- int ret;
-
- scifdev->exit = OP_IN_PROGRESS;
- msg.uop = SCIF_EXIT;
- msg.src.node = scif_info.nodeid;
- msg.dst.node = scifdev->node;
- ret = scif_nodeqp_send(scifdev, &msg);
- if (ret)
- goto done;
- /* Wait for a SCIF_EXIT_ACK message */
- wait_event_timeout(scif_info.exitwq, scifdev->exit == OP_COMPLETED,
- SCIF_NODE_ALIVE_TIMEOUT);
-done:
- scifdev->exit = OP_IDLE;
-}
-
-int scif_setup_qp(struct scif_dev *scifdev)
-{
- int err = 0;
- int local_size;
- struct scif_qp *qp;
-
- local_size = SCIF_NODE_QP_SIZE;
-
- qp = kzalloc(sizeof(*qp), GFP_KERNEL);
- if (!qp) {
- err = -ENOMEM;
- return err;
- }
- qp->magic = SCIFEP_MAGIC;
- scifdev->qpairs = qp;
- err = scif_setup_qp_connect(qp, &scifdev->qp_dma_addr,
- local_size, scifdev);
- if (err)
- goto free_qp;
- /*
- * We're as setup as we can be. The inbound_q is setup, w/o a usable
- * outbound q. When we get a message, the read_ptr will be updated,
- * and we will pull the message.
- */
- return err;
-free_qp:
- kfree(scifdev->qpairs);
- scifdev->qpairs = NULL;
- return err;
-}
-
-static void scif_p2p_freesg(struct scatterlist *sg)
-{
- kfree(sg);
-}
-
-static struct scatterlist *
-scif_p2p_setsg(phys_addr_t pa, int page_size, int page_cnt)
-{
- struct scatterlist *sg;
- struct page *page;
- int i;
-
- sg = kmalloc_array(page_cnt, sizeof(struct scatterlist), GFP_KERNEL);
- if (!sg)
- return NULL;
- sg_init_table(sg, page_cnt);
- for (i = 0; i < page_cnt; i++) {
- page = pfn_to_page(pa >> PAGE_SHIFT);
- sg_set_page(&sg[i], page, page_size, 0);
- pa += page_size;
- }
- return sg;
-}
-
-/* Init p2p mappings required to access peerdev from scifdev */
-static struct scif_p2p_info *
-scif_init_p2p_info(struct scif_dev *scifdev, struct scif_dev *peerdev)
-{
- struct scif_p2p_info *p2p;
- int num_mmio_pages, num_aper_pages, sg_page_shift, err, num_aper_chunks;
- struct scif_hw_dev *psdev = peerdev->sdev;
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- num_mmio_pages = psdev->mmio->len >> PAGE_SHIFT;
- num_aper_pages = psdev->aper->len >> PAGE_SHIFT;
-
- p2p = kzalloc(sizeof(*p2p), GFP_KERNEL);
- if (!p2p)
- return NULL;
- p2p->ppi_sg[SCIF_PPI_MMIO] = scif_p2p_setsg(psdev->mmio->pa,
- PAGE_SIZE, num_mmio_pages);
- if (!p2p->ppi_sg[SCIF_PPI_MMIO])
- goto free_p2p;
- p2p->sg_nentries[SCIF_PPI_MMIO] = num_mmio_pages;
- sg_page_shift = get_order(min(psdev->aper->len, (u64)(1 << 30)));
- num_aper_chunks = num_aper_pages >> (sg_page_shift - PAGE_SHIFT);
- p2p->ppi_sg[SCIF_PPI_APER] = scif_p2p_setsg(psdev->aper->pa,
- 1 << sg_page_shift,
- num_aper_chunks);
- p2p->sg_nentries[SCIF_PPI_APER] = num_aper_chunks;
- err = dma_map_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- num_mmio_pages, PCI_DMA_BIDIRECTIONAL);
- if (err != num_mmio_pages)
- goto scif_p2p_free;
- err = dma_map_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
- num_aper_chunks, PCI_DMA_BIDIRECTIONAL);
- if (err != num_aper_chunks)
- goto dma_unmap;
- p2p->ppi_da[SCIF_PPI_MMIO] = sg_dma_address(p2p->ppi_sg[SCIF_PPI_MMIO]);
- p2p->ppi_da[SCIF_PPI_APER] = sg_dma_address(p2p->ppi_sg[SCIF_PPI_APER]);
- p2p->ppi_len[SCIF_PPI_MMIO] = num_mmio_pages;
- p2p->ppi_len[SCIF_PPI_APER] = num_aper_pages;
- p2p->ppi_peer_id = peerdev->node;
- return p2p;
-dma_unmap:
- dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO], DMA_BIDIRECTIONAL);
-scif_p2p_free:
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
-free_p2p:
- kfree(p2p);
- return NULL;
-}
-
-/* Uninitialize and release resources from a p2p mapping */
-static void scif_deinit_p2p_info(struct scif_dev *scifdev,
- struct scif_p2p_info *p2p)
-{
- struct scif_hw_dev *sdev = scifdev->sdev;
-
- dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO], DMA_BIDIRECTIONAL);
- dma_unmap_sg(&sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
- p2p->sg_nentries[SCIF_PPI_APER], DMA_BIDIRECTIONAL);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
- kfree(p2p);
-}
-
-/**
- * scif_node_connect: Respond to SCIF_NODE_CONNECT interrupt message
- * @scifdev: SCIF device
- * @dst: Destination node
- *
- * Connect the src and dst node by setting up the p2p connection
- * between them. Management node here acts like a proxy.
- */
-static void scif_node_connect(struct scif_dev *scifdev, int dst)
-{
- struct scif_dev *dev_j = scifdev;
- struct scif_dev *dev_i = NULL;
- struct scif_p2p_info *p2p_ij = NULL; /* bus addr for j from i */
- struct scif_p2p_info *p2p_ji = NULL; /* bus addr for i from j */
- struct scif_p2p_info *p2p;
- struct list_head *pos, *tmp;
- struct scifmsg msg;
- int err;
- u64 tmppayload;
-
- if (dst < 1 || dst > scif_info.maxid)
- return;
-
- dev_i = &scif_dev[dst];
-
- if (!_scifdev_alive(dev_i))
- return;
- /*
- * If the p2p connection is already setup or in the process of setting
- * up then just ignore this request. The requested node will get
- * informed by SCIF_NODE_ADD_ACK or SCIF_NODE_ADD_NACK
- */
- if (!list_empty(&dev_i->p2p)) {
- list_for_each_safe(pos, tmp, &dev_i->p2p) {
- p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
- if (p2p->ppi_peer_id == dev_j->node)
- return;
- }
- }
- p2p_ij = scif_init_p2p_info(dev_i, dev_j);
- if (!p2p_ij)
- return;
- p2p_ji = scif_init_p2p_info(dev_j, dev_i);
- if (!p2p_ji) {
- scif_deinit_p2p_info(dev_i, p2p_ij);
- return;
- }
- list_add_tail(&p2p_ij->ppi_list, &dev_i->p2p);
- list_add_tail(&p2p_ji->ppi_list, &dev_j->p2p);
-
- /*
- * Send a SCIF_NODE_ADD to dev_i, pass it its bus address
- * as seen from dev_j
- */
- msg.uop = SCIF_NODE_ADD;
- msg.src.node = dev_j->node;
- msg.dst.node = dev_i->node;
-
- msg.payload[0] = p2p_ji->ppi_da[SCIF_PPI_APER];
- msg.payload[1] = p2p_ij->ppi_da[SCIF_PPI_MMIO];
- msg.payload[2] = p2p_ij->ppi_da[SCIF_PPI_APER];
- msg.payload[3] = p2p_ij->ppi_len[SCIF_PPI_APER] << PAGE_SHIFT;
-
- err = scif_nodeqp_send(dev_i, &msg);
- if (err) {
- dev_err(&scifdev->sdev->dev,
- "%s %d error %d\n", __func__, __LINE__, err);
- return;
- }
-
- /* Same as above but to dev_j */
- msg.uop = SCIF_NODE_ADD;
- msg.src.node = dev_i->node;
- msg.dst.node = dev_j->node;
-
- tmppayload = msg.payload[0];
- msg.payload[0] = msg.payload[2];
- msg.payload[2] = tmppayload;
- msg.payload[1] = p2p_ji->ppi_da[SCIF_PPI_MMIO];
- msg.payload[3] = p2p_ji->ppi_len[SCIF_PPI_APER] << PAGE_SHIFT;
-
- scif_nodeqp_send(dev_j, &msg);
-}
-
-static void scif_p2p_setup(void)
-{
- int i, j;
-
- if (!scif_info.p2p_enable)
- return;
-
- for (i = 1; i <= scif_info.maxid; i++)
- if (!_scifdev_alive(&scif_dev[i]))
- return;
-
- for (i = 1; i <= scif_info.maxid; i++) {
- for (j = 1; j <= scif_info.maxid; j++) {
- struct scif_dev *scifdev = &scif_dev[i];
-
- if (i == j)
- continue;
- scif_node_connect(scifdev, j);
- }
- }
-}
-
-static char *message_types[] = {"BAD",
- "INIT",
- "EXIT",
- "SCIF_EXIT_ACK",
- "SCIF_NODE_ADD",
- "SCIF_NODE_ADD_ACK",
- "SCIF_NODE_ADD_NACK",
- "REMOVE_NODE",
- "REMOVE_NODE_ACK",
- "CNCT_REQ",
- "CNCT_GNT",
- "CNCT_GNTACK",
- "CNCT_GNTNACK",
- "CNCT_REJ",
- "DISCNCT",
- "DISCNT_ACK",
- "CLIENT_SENT",
- "CLIENT_RCVD",
- "SCIF_GET_NODE_INFO",
- "REGISTER",
- "REGISTER_ACK",
- "REGISTER_NACK",
- "UNREGISTER",
- "UNREGISTER_ACK",
- "UNREGISTER_NACK",
- "ALLOC_REQ",
- "ALLOC_GNT",
- "ALLOC_REJ",
- "FREE_PHYS",
- "FREE_VIRT",
- "MUNMAP",
- "MARK",
- "MARK_ACK",
- "MARK_NACK",
- "WAIT",
- "WAIT_ACK",
- "WAIT_NACK",
- "SIGNAL_LOCAL",
- "SIGNAL_REMOTE",
- "SIG_ACK",
- "SIG_NACK"};
-
-static void
-scif_display_message(struct scif_dev *scifdev, struct scifmsg *msg,
- const char *label)
-{
- if (!scif_info.en_msg_log)
- return;
- if (msg->uop > SCIF_MAX_MSG) {
- dev_err(&scifdev->sdev->dev,
- "%s: unknown msg type %d\n", label, msg->uop);
- return;
- }
- dev_info(&scifdev->sdev->dev,
- "%s: msg type %s, src %d:%d, dest %d:%d payload 0x%llx:0x%llx:0x%llx:0x%llx\n",
- label, message_types[msg->uop], msg->src.node, msg->src.port,
- msg->dst.node, msg->dst.port, msg->payload[0], msg->payload[1],
- msg->payload[2], msg->payload[3]);
-}
-
-int _scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_qp *qp = scifdev->qpairs;
- int err = -ENOMEM, loop_cnt = 0;
-
- scif_display_message(scifdev, msg, "Sent");
- if (!qp) {
- err = -EINVAL;
- goto error;
- }
- spin_lock(&qp->send_lock);
-
- while ((err = scif_rb_write(&qp->outbound_q,
- msg, sizeof(struct scifmsg)))) {
- mdelay(1);
-#define SCIF_NODEQP_SEND_TO_MSEC (3 * 1000)
- if (loop_cnt++ > (SCIF_NODEQP_SEND_TO_MSEC)) {
- err = -ENODEV;
- break;
- }
- }
- if (!err)
- scif_rb_commit(&qp->outbound_q);
- spin_unlock(&qp->send_lock);
- if (!err) {
- if (scifdev_self(scifdev))
- /*
- * For loopback we need to emulate an interrupt by
- * queuing work for the queue handling real node
- * Qp interrupts.
- */
- queue_work(scifdev->intr_wq, &scifdev->intr_bh);
- else
- scif_send_msg_intr(scifdev);
- }
-error:
- if (err)
- dev_dbg(&scifdev->sdev->dev,
- "%s %d error %d uop %d\n",
- __func__, __LINE__, err, msg->uop);
- return err;
-}
-
-/**
- * scif_nodeqp_send - Send a message on the node queue pair
- * @scifdev: Scif Device.
- * @msg: The message to be sent.
- */
-int scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- int err;
- struct device *spdev = NULL;
-
- if (msg->uop > SCIF_EXIT_ACK) {
- /* Don't send messages once the exit flow has begun */
- if (OP_IDLE != scifdev->exit)
- return -ENODEV;
- spdev = scif_get_peer_dev(scifdev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
- }
- err = _scif_nodeqp_send(scifdev, msg);
- if (msg->uop > SCIF_EXIT_ACK)
- scif_put_peer_dev(spdev);
- return err;
-}
-
-/*
- * scif_misc_handler:
- *
- * Work queue handler for servicing miscellaneous SCIF tasks.
- * Examples include:
- * 1) Remote fence requests.
- * 2) Destruction of temporary registered windows
- * created during scif_vreadfrom()/scif_vwriteto().
- * 3) Cleanup of zombie endpoints.
- */
-void scif_misc_handler(struct work_struct *work)
-{
- scif_rma_handle_remote_fences();
- scif_rma_destroy_windows();
- scif_rma_destroy_tcw_invalid();
- scif_cleanup_zombie_epd();
-}
-
-/**
- * scif_init() - Respond to SCIF_INIT interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- */
-static __always_inline void
-scif_init(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- /*
- * Allow the thread waiting for device page updates for the peer QP DMA
- * address to complete initializing the inbound_q.
- */
- flush_delayed_work(&scifdev->qp_dwork);
-
- scif_peer_register_device(scifdev);
-
- if (scif_is_mgmt_node()) {
- mutex_lock(&scif_info.conflock);
- scif_p2p_setup();
- mutex_unlock(&scif_info.conflock);
- }
-}
-
-/**
- * scif_exit() - Respond to SCIF_EXIT interrupt message
- * @scifdev: Remote SCIF device node
- * @unused: Interrupt message (unused)
- *
- * This function stops the SCIF interface for the node which sent
- * the SCIF_EXIT message and starts waiting for that node to
- * resetup the queue pair again.
- */
-static __always_inline void
-scif_exit(struct scif_dev *scifdev, struct scifmsg *unused)
-{
- scifdev->exit_ack_pending = true;
- if (scif_is_mgmt_node())
- scif_disconnect_node(scifdev->node, false);
- else
- scif_stop(scifdev);
- schedule_delayed_work(&scifdev->qp_dwork,
- msecs_to_jiffies(1000));
-}
-
-/**
- * scif_exitack() - Respond to SCIF_EXIT_ACK interrupt message
- * @scifdev: Remote SCIF device node
- * @unused: Interrupt message (unused)
- *
- */
-static __always_inline void
-scif_exit_ack(struct scif_dev *scifdev, struct scifmsg *unused)
-{
- scifdev->exit = OP_COMPLETED;
- wake_up(&scif_info.exitwq);
-}
-
-/**
- * scif_node_add() - Respond to SCIF_NODE_ADD interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * When the mgmt node driver has finished initializing a MIC node queue pair it
- * marks the node as online. It then looks for all currently online MIC cards
- * and send a SCIF_NODE_ADD message to identify the ID of the new card for
- * peer to peer initialization
- *
- * The local node allocates its incoming queue and sends its address in the
- * SCIF_NODE_ADD_ACK message back to the mgmt node, the mgmt node "reflects"
- * this message to the new node
- */
-static __always_inline void
-scif_node_add(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_dev *newdev;
- dma_addr_t qp_offset;
- int qp_connect;
- struct scif_hw_dev *sdev;
-
- dev_dbg(&scifdev->sdev->dev,
- "Scifdev %d:%d received NODE_ADD msg for node %d\n",
- scifdev->node, msg->dst.node, msg->src.node);
- dev_dbg(&scifdev->sdev->dev,
- "Remote address for this node's aperture %llx\n",
- msg->payload[0]);
- newdev = &scif_dev[msg->src.node];
- newdev->node = msg->src.node;
- newdev->sdev = scif_dev[SCIF_MGMT_NODE].sdev;
- sdev = newdev->sdev;
-
- if (scif_setup_intr_wq(newdev)) {
- dev_err(&scifdev->sdev->dev,
- "failed to setup interrupts for %d\n", msg->src.node);
- goto interrupt_setup_error;
- }
- newdev->mmio.va = ioremap(msg->payload[1], sdev->mmio->len);
- if (!newdev->mmio.va) {
- dev_err(&scifdev->sdev->dev,
- "failed to map mmio for %d\n", msg->src.node);
- goto mmio_map_error;
- }
- newdev->qpairs = kzalloc(sizeof(*newdev->qpairs), GFP_KERNEL);
- if (!newdev->qpairs)
- goto qp_alloc_error;
- /*
- * Set the base address of the remote node's memory since it gets
- * added to qp_offset
- */
- newdev->base_addr = msg->payload[0];
-
- qp_connect = scif_setup_qp_connect(newdev->qpairs, &qp_offset,
- SCIF_NODE_QP_SIZE, newdev);
- if (qp_connect) {
- dev_err(&scifdev->sdev->dev,
- "failed to setup qp_connect %d\n", qp_connect);
- goto qp_connect_error;
- }
-
- newdev->db = sdev->hw_ops->next_db(sdev);
- newdev->cookie = sdev->hw_ops->request_irq(sdev, scif_intr_handler,
- "SCIF_INTR", newdev,
- newdev->db);
- if (IS_ERR(newdev->cookie))
- goto qp_connect_error;
- newdev->qpairs->magic = SCIFEP_MAGIC;
- newdev->qpairs->qp_state = SCIF_QP_OFFLINE;
-
- msg->uop = SCIF_NODE_ADD_ACK;
- msg->dst.node = msg->src.node;
- msg->src.node = scif_info.nodeid;
- msg->payload[0] = qp_offset;
- msg->payload[2] = newdev->db;
- scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], msg);
- return;
-qp_connect_error:
- kfree(newdev->qpairs);
- newdev->qpairs = NULL;
-qp_alloc_error:
- iounmap(newdev->mmio.va);
- newdev->mmio.va = NULL;
-mmio_map_error:
-interrupt_setup_error:
- dev_err(&scifdev->sdev->dev,
- "node add failed for node %d\n", msg->src.node);
- msg->uop = SCIF_NODE_ADD_NACK;
- msg->dst.node = msg->src.node;
- msg->src.node = scif_info.nodeid;
- scif_nodeqp_send(&scif_dev[SCIF_MGMT_NODE], msg);
-}
-
-void scif_poll_qp_state(struct work_struct *work)
-{
-#define SCIF_NODE_QP_RETRY 100
-#define SCIF_NODE_QP_TIMEOUT 100
- struct scif_dev *peerdev = container_of(work, struct scif_dev,
- p2p_dwork.work);
- struct scif_qp *qp = &peerdev->qpairs[0];
-
- if (qp->qp_state != SCIF_QP_ONLINE ||
- qp->remote_qp->qp_state != SCIF_QP_ONLINE) {
- if (peerdev->p2p_retry++ == SCIF_NODE_QP_RETRY) {
- dev_err(&peerdev->sdev->dev,
- "Warning: QP check timeout with state %d\n",
- qp->qp_state);
- goto timeout;
- }
- schedule_delayed_work(&peerdev->p2p_dwork,
- msecs_to_jiffies(SCIF_NODE_QP_TIMEOUT));
- return;
- }
- return;
-timeout:
- dev_err(&peerdev->sdev->dev,
- "%s %d remote node %d offline, state = 0x%x\n",
- __func__, __LINE__, peerdev->node, qp->qp_state);
- qp->remote_qp->qp_state = SCIF_QP_OFFLINE;
- scif_peer_unregister_device(peerdev);
- scif_cleanup_scifdev(peerdev);
-}
-
-/**
- * scif_node_add_ack() - Respond to SCIF_NODE_ADD_ACK interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * After a MIC node receives the SCIF_NODE_ADD_ACK message it send this
- * message to the mgmt node to confirm the sequence is finished.
- *
- */
-static __always_inline void
-scif_node_add_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_dev *peerdev;
- struct scif_qp *qp;
- struct scif_dev *dst_dev = &scif_dev[msg->dst.node];
-
- dev_dbg(&scifdev->sdev->dev,
- "Scifdev %d received SCIF_NODE_ADD_ACK msg src %d dst %d\n",
- scifdev->node, msg->src.node, msg->dst.node);
- dev_dbg(&scifdev->sdev->dev,
- "payload %llx %llx %llx %llx\n", msg->payload[0],
- msg->payload[1], msg->payload[2], msg->payload[3]);
- if (scif_is_mgmt_node()) {
- /*
- * the lock serializes with scif_qp_response_ack. The mgmt node
- * is forwarding the NODE_ADD_ACK message from src to dst we
- * need to make sure that the dst has already received a
- * NODE_ADD for src and setup its end of the qp to dst
- */
- mutex_lock(&scif_info.conflock);
- msg->payload[1] = scif_info.maxid;
- scif_nodeqp_send(dst_dev, msg);
- mutex_unlock(&scif_info.conflock);
- return;
- }
- peerdev = &scif_dev[msg->src.node];
- peerdev->sdev = scif_dev[SCIF_MGMT_NODE].sdev;
- peerdev->node = msg->src.node;
-
- qp = &peerdev->qpairs[0];
-
- if ((scif_setup_qp_connect_response(peerdev, &peerdev->qpairs[0],
- msg->payload[0])))
- goto local_error;
- peerdev->rdb = msg->payload[2];
- qp->remote_qp->qp_state = SCIF_QP_ONLINE;
-
- scif_peer_register_device(peerdev);
-
- schedule_delayed_work(&peerdev->p2p_dwork, 0);
- return;
-local_error:
- scif_cleanup_scifdev(peerdev);
-}
-
-/**
- * scif_node_add_nack: Respond to SCIF_NODE_ADD_NACK interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * SCIF_NODE_ADD failed, so inform the waiting wq.
- */
-static __always_inline void
-scif_node_add_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- if (scif_is_mgmt_node()) {
- struct scif_dev *dst_dev = &scif_dev[msg->dst.node];
-
- dev_dbg(&scifdev->sdev->dev,
- "SCIF_NODE_ADD_NACK received from %d\n", scifdev->node);
- scif_nodeqp_send(dst_dev, msg);
- }
-}
-
-/**
- * scif_node_remove: Handle SCIF_NODE_REMOVE message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * Handle node removal.
- */
-static __always_inline void
-scif_node_remove(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- int node = msg->payload[0];
- struct scif_dev *scdev = &scif_dev[node];
-
- scdev->node_remove_ack_pending = true;
- scif_handle_remove_node(node);
-}
-
-/**
- * scif_node_remove_ack: Handle SCIF_NODE_REMOVE_ACK message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * The peer has acked a SCIF_NODE_REMOVE message.
- */
-static __always_inline void
-scif_node_remove_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_dev *sdev = &scif_dev[msg->payload[0]];
-
- atomic_inc(&sdev->disconn_rescnt);
- wake_up(&sdev->disconn_wq);
-}
-
-/**
- * scif_get_node_info: Respond to SCIF_GET_NODE_INFO interrupt message
- * @scifdev: Remote SCIF device node
- * @msg: Interrupt message
- *
- * Retrieve node info i.e maxid and total from the mgmt node.
- */
-static __always_inline void
-scif_get_node_info_resp(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- if (scif_is_mgmt_node()) {
- swap(msg->dst.node, msg->src.node);
- mutex_lock(&scif_info.conflock);
- msg->payload[1] = scif_info.maxid;
- msg->payload[2] = scif_info.total;
- mutex_unlock(&scif_info.conflock);
- scif_nodeqp_send(scifdev, msg);
- } else {
- struct completion *node_info =
- (struct completion *)msg->payload[3];
-
- mutex_lock(&scif_info.conflock);
- scif_info.maxid = msg->payload[1];
- scif_info.total = msg->payload[2];
- complete_all(node_info);
- mutex_unlock(&scif_info.conflock);
- }
-}
-
-static void
-scif_msg_unknown(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- /* Bogus Node Qp Message? */
- dev_err(&scifdev->sdev->dev,
- "Unknown message 0x%xn scifdev->node 0x%x\n",
- msg->uop, scifdev->node);
-}
-
-static void (*scif_intr_func[SCIF_MAX_MSG + 1])
- (struct scif_dev *, struct scifmsg *msg) = {
- scif_msg_unknown, /* Error */
- scif_init, /* SCIF_INIT */
- scif_exit, /* SCIF_EXIT */
- scif_exit_ack, /* SCIF_EXIT_ACK */
- scif_node_add, /* SCIF_NODE_ADD */
- scif_node_add_ack, /* SCIF_NODE_ADD_ACK */
- scif_node_add_nack, /* SCIF_NODE_ADD_NACK */
- scif_node_remove, /* SCIF_NODE_REMOVE */
- scif_node_remove_ack, /* SCIF_NODE_REMOVE_ACK */
- scif_cnctreq, /* SCIF_CNCT_REQ */
- scif_cnctgnt, /* SCIF_CNCT_GNT */
- scif_cnctgnt_ack, /* SCIF_CNCT_GNTACK */
- scif_cnctgnt_nack, /* SCIF_CNCT_GNTNACK */
- scif_cnctrej, /* SCIF_CNCT_REJ */
- scif_discnct, /* SCIF_DISCNCT */
- scif_discnt_ack, /* SCIF_DISCNT_ACK */
- scif_clientsend, /* SCIF_CLIENT_SENT */
- scif_clientrcvd, /* SCIF_CLIENT_RCVD */
- scif_get_node_info_resp,/* SCIF_GET_NODE_INFO */
- scif_recv_reg, /* SCIF_REGISTER */
- scif_recv_reg_ack, /* SCIF_REGISTER_ACK */
- scif_recv_reg_nack, /* SCIF_REGISTER_NACK */
- scif_recv_unreg, /* SCIF_UNREGISTER */
- scif_recv_unreg_ack, /* SCIF_UNREGISTER_ACK */
- scif_recv_unreg_nack, /* SCIF_UNREGISTER_NACK */
- scif_alloc_req, /* SCIF_ALLOC_REQ */
- scif_alloc_gnt_rej, /* SCIF_ALLOC_GNT */
- scif_alloc_gnt_rej, /* SCIF_ALLOC_REJ */
- scif_free_virt, /* SCIF_FREE_VIRT */
- scif_recv_munmap, /* SCIF_MUNMAP */
- scif_recv_mark, /* SCIF_MARK */
- scif_recv_mark_resp, /* SCIF_MARK_ACK */
- scif_recv_mark_resp, /* SCIF_MARK_NACK */
- scif_recv_wait, /* SCIF_WAIT */
- scif_recv_wait_resp, /* SCIF_WAIT_ACK */
- scif_recv_wait_resp, /* SCIF_WAIT_NACK */
- scif_recv_sig_local, /* SCIF_SIG_LOCAL */
- scif_recv_sig_remote, /* SCIF_SIG_REMOTE */
- scif_recv_sig_resp, /* SCIF_SIG_ACK */
- scif_recv_sig_resp, /* SCIF_SIG_NACK */
-};
-
-static int scif_max_msg_id = SCIF_MAX_MSG;
-/**
- * scif_nodeqp_msg_handler() - Common handler for node messages
- * @scifdev: Remote device to respond to
- * @qp: Remote memory pointer
- * @msg: The message to be handled.
- *
- * This routine calls the appropriate routine to handle a Node Qp
- * message receipt
- */
-static void
-scif_nodeqp_msg_handler(struct scif_dev *scifdev,
- struct scif_qp *qp, struct scifmsg *msg)
-{
- scif_display_message(scifdev, msg, "Rcvd");
-
- if (msg->uop > (u32)scif_max_msg_id) {
- /* Bogus Node Qp Message? */
- dev_err(&scifdev->sdev->dev,
- "Unknown message 0x%xn scifdev->node 0x%x\n",
- msg->uop, scifdev->node);
- return;
- }
-
- scif_intr_func[msg->uop](scifdev, msg);
-}
-
-/**
- * scif_nodeqp_intrhandler() - Interrupt handler for node messages
- * @scifdev: Remote device to respond to
- * @qp: Remote memory pointer
- *
- * This routine is triggered by the interrupt mechanism. It reads
- * messages from the node queue RB and calls the Node QP Message handling
- * routine.
- */
-void scif_nodeqp_intrhandler(struct scif_dev *scifdev, struct scif_qp *qp)
-{
- struct scifmsg msg;
- int read_size;
-
- do {
- read_size = scif_rb_get_next(&qp->inbound_q, &msg, sizeof(msg));
- if (!read_size)
- break;
- scif_nodeqp_msg_handler(scifdev, qp, &msg);
- /*
- * The node queue pair is unmapped so skip the read pointer
- * update after receipt of a SCIF_EXIT_ACK
- */
- if (SCIF_EXIT_ACK == msg.uop)
- break;
- scif_rb_update_read_ptr(&qp->inbound_q);
- } while (1);
-}
-
-/**
- * scif_loopb_wq_handler - Loopback Workqueue Handler.
- * @unused: loop back work (unused)
- *
- * This work queue routine is invoked by the loopback work queue handler.
- * It grabs the recv lock, dequeues any available messages from the head
- * of the loopback message list, calls the node QP message handler,
- * waits for it to return, then frees up this message and dequeues more
- * elements of the list if available.
- */
-static void scif_loopb_wq_handler(struct work_struct *unused)
-{
- struct scif_dev *scifdev = scif_info.loopb_dev;
- struct scif_qp *qp = scifdev->qpairs;
- struct scif_loopb_msg *msg;
-
- do {
- msg = NULL;
- spin_lock(&qp->recv_lock);
- if (!list_empty(&scif_info.loopb_recv_q)) {
- msg = list_first_entry(&scif_info.loopb_recv_q,
- struct scif_loopb_msg,
- list);
- list_del(&msg->list);
- }
- spin_unlock(&qp->recv_lock);
-
- if (msg) {
- scif_nodeqp_msg_handler(scifdev, qp, &msg->msg);
- kfree(msg);
- }
- } while (msg);
-}
-
-/**
- * scif_loopb_msg_handler() - Workqueue handler for loopback messages.
- * @scifdev: SCIF device
- * @qp: Queue pair.
- *
- * This work queue routine is triggered when a loopback message is received.
- *
- * We need special handling for receiving Node Qp messages on a loopback SCIF
- * device via two workqueues for receiving messages.
- *
- * The reason we need the extra workqueue which is not required with *normal*
- * non-loopback SCIF devices is the potential classic deadlock described below:
- *
- * Thread A tries to send a message on a loopback SCIF device and blocks since
- * there is no space in the RB while it has the send_lock held or another
- * lock called lock X for example.
- *
- * Thread B: The Loopback Node QP message receive workqueue receives the message
- * and tries to send a message (eg an ACK) to the loopback SCIF device. It tries
- * to grab the send lock again or lock X and deadlocks with Thread A. The RB
- * cannot be drained any further due to this classic deadlock.
- *
- * In order to avoid deadlocks as mentioned above we have an extra level of
- * indirection achieved by having two workqueues.
- * 1) The first workqueue whose handler is scif_loopb_msg_handler reads
- * messages from the Node QP RB, adds them to a list and queues work for the
- * second workqueue.
- *
- * 2) The second workqueue whose handler is scif_loopb_wq_handler dequeues
- * messages from the list, handles them, frees up the memory and dequeues
- * more elements from the list if possible.
- */
-int
-scif_loopb_msg_handler(struct scif_dev *scifdev, struct scif_qp *qp)
-{
- int read_size;
- struct scif_loopb_msg *msg;
-
- do {
- msg = kmalloc(sizeof(*msg), GFP_KERNEL);
- if (!msg)
- return -ENOMEM;
- read_size = scif_rb_get_next(&qp->inbound_q, &msg->msg,
- sizeof(struct scifmsg));
- if (read_size != sizeof(struct scifmsg)) {
- kfree(msg);
- scif_rb_update_read_ptr(&qp->inbound_q);
- break;
- }
- spin_lock(&qp->recv_lock);
- list_add_tail(&msg->list, &scif_info.loopb_recv_q);
- spin_unlock(&qp->recv_lock);
- queue_work(scif_info.loopb_wq, &scif_info.loopb_work);
- scif_rb_update_read_ptr(&qp->inbound_q);
- } while (read_size == sizeof(struct scifmsg));
- return read_size;
-}
-
-/**
- * scif_setup_loopback_qp - One time setup work for Loopback Node Qp.
- * @scifdev: SCIF device
- *
- * Sets up the required loopback workqueues, queue pairs and ring buffers
- */
-int scif_setup_loopback_qp(struct scif_dev *scifdev)
-{
- int err = 0;
- void *local_q;
- struct scif_qp *qp;
-
- err = scif_setup_intr_wq(scifdev);
- if (err)
- goto exit;
- INIT_LIST_HEAD(&scif_info.loopb_recv_q);
- snprintf(scif_info.loopb_wqname, sizeof(scif_info.loopb_wqname),
- "SCIF LOOPB %d", scifdev->node);
- scif_info.loopb_wq =
- alloc_ordered_workqueue(scif_info.loopb_wqname, 0);
- if (!scif_info.loopb_wq) {
- err = -ENOMEM;
- goto destroy_intr;
- }
- INIT_WORK(&scif_info.loopb_work, scif_loopb_wq_handler);
- /* Allocate Self Qpair */
- scifdev->qpairs = kzalloc(sizeof(*scifdev->qpairs), GFP_KERNEL);
- if (!scifdev->qpairs) {
- err = -ENOMEM;
- goto destroy_loopb_wq;
- }
-
- qp = scifdev->qpairs;
- qp->magic = SCIFEP_MAGIC;
- spin_lock_init(&qp->send_lock);
- spin_lock_init(&qp->recv_lock);
-
- local_q = kzalloc(SCIF_NODE_QP_SIZE, GFP_KERNEL);
- if (!local_q) {
- err = -ENOMEM;
- goto free_qpairs;
- }
- /*
- * For loopback the inbound_q and outbound_q are essentially the same
- * since the Node sends a message on the loopback interface to the
- * outbound_q which is then received on the inbound_q.
- */
- scif_rb_init(&qp->outbound_q,
- &qp->local_read,
- &qp->local_write,
- local_q, get_count_order(SCIF_NODE_QP_SIZE));
-
- scif_rb_init(&qp->inbound_q,
- &qp->local_read,
- &qp->local_write,
- local_q, get_count_order(SCIF_NODE_QP_SIZE));
- scif_info.nodeid = scifdev->node;
-
- scif_peer_register_device(scifdev);
-
- scif_info.loopb_dev = scifdev;
- return err;
-free_qpairs:
- kfree(scifdev->qpairs);
-destroy_loopb_wq:
- destroy_workqueue(scif_info.loopb_wq);
-destroy_intr:
- scif_destroy_intr_wq(scifdev);
-exit:
- return err;
-}
-
-/**
- * scif_destroy_loopback_qp - One time uninit work for Loopback Node Qp
- * @scifdev: SCIF device
- *
- * Destroys the workqueues and frees up the Ring Buffer and Queue Pair memory.
- */
-int scif_destroy_loopback_qp(struct scif_dev *scifdev)
-{
- scif_peer_unregister_device(scifdev);
- destroy_workqueue(scif_info.loopb_wq);
- scif_destroy_intr_wq(scifdev);
- kfree(scifdev->qpairs->outbound_q.rb_base);
- kfree(scifdev->qpairs);
- scifdev->sdev = NULL;
- scif_info.loopb_dev = NULL;
- return 0;
-}
-
-void scif_destroy_p2p(struct scif_dev *scifdev)
-{
- struct scif_dev *peer_dev;
- struct scif_p2p_info *p2p;
- struct list_head *pos, *tmp;
- int bd;
-
- mutex_lock(&scif_info.conflock);
- /* Free P2P mappings in the given node for all its peer nodes */
- list_for_each_safe(pos, tmp, &scifdev->p2p) {
- p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
- dma_unmap_sg(&scifdev->sdev->dev, p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO],
- DMA_BIDIRECTIONAL);
- dma_unmap_sg(&scifdev->sdev->dev, p2p->ppi_sg[SCIF_PPI_APER],
- p2p->sg_nentries[SCIF_PPI_APER],
- DMA_BIDIRECTIONAL);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
- list_del(pos);
- kfree(p2p);
- }
-
- /* Free P2P mapping created in the peer nodes for the given node */
- for (bd = SCIF_MGMT_NODE + 1; bd <= scif_info.maxid; bd++) {
- peer_dev = &scif_dev[bd];
- list_for_each_safe(pos, tmp, &peer_dev->p2p) {
- p2p = list_entry(pos, struct scif_p2p_info, ppi_list);
- if (p2p->ppi_peer_id == scifdev->node) {
- dma_unmap_sg(&peer_dev->sdev->dev,
- p2p->ppi_sg[SCIF_PPI_MMIO],
- p2p->sg_nentries[SCIF_PPI_MMIO],
- DMA_BIDIRECTIONAL);
- dma_unmap_sg(&peer_dev->sdev->dev,
- p2p->ppi_sg[SCIF_PPI_APER],
- p2p->sg_nentries[SCIF_PPI_APER],
- DMA_BIDIRECTIONAL);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_MMIO]);
- scif_p2p_freesg(p2p->ppi_sg[SCIF_PPI_APER]);
- list_del(pos);
- kfree(p2p);
- }
- }
- }
- mutex_unlock(&scif_info.conflock);
-}
+++ /dev/null
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef SCIF_NODEQP
-#define SCIF_NODEQP
-
-#include "scif_rb.h"
-#include "scif_peer_bus.h"
-
-#define SCIF_INIT 1 /* First message sent to the peer node for discovery */
-#define SCIF_EXIT 2 /* Last message from the peer informing intent to exit */
-#define SCIF_EXIT_ACK 3 /* Response to SCIF_EXIT message */
-#define SCIF_NODE_ADD 4 /* Tell Online nodes a new node exits */
-#define SCIF_NODE_ADD_ACK 5 /* Confirm to mgmt node sequence is finished */
-#define SCIF_NODE_ADD_NACK 6 /* SCIF_NODE_ADD failed */
-#define SCIF_NODE_REMOVE 7 /* Request to deactivate a SCIF node */
-#define SCIF_NODE_REMOVE_ACK 8 /* Response to a SCIF_NODE_REMOVE message */
-#define SCIF_CNCT_REQ 9 /* Phys addr of Request connection to a port */
-#define SCIF_CNCT_GNT 10 /* Phys addr of new Grant connection request */
-#define SCIF_CNCT_GNTACK 11 /* Error type Reject a connection request */
-#define SCIF_CNCT_GNTNACK 12 /* Error type Reject a connection request */
-#define SCIF_CNCT_REJ 13 /* Error type Reject a connection request */
-#define SCIF_DISCNCT 14 /* Notify peer that connection is being terminated */
-#define SCIF_DISCNT_ACK 15 /* Notify peer that connection is being terminated */
-#define SCIF_CLIENT_SENT 16 /* Notify the peer that data has been written */
-#define SCIF_CLIENT_RCVD 17 /* Notify the peer that data has been read */
-#define SCIF_GET_NODE_INFO 18 /* Get current node mask from the mgmt node*/
-#define SCIF_REGISTER 19 /* Tell peer about a new registered window */
-#define SCIF_REGISTER_ACK 20 /* Notify peer about unregistration success */
-#define SCIF_REGISTER_NACK 21 /* Notify peer about registration success */
-#define SCIF_UNREGISTER 22 /* Tell peer about unregistering a window */
-#define SCIF_UNREGISTER_ACK 23 /* Notify peer about registration failure */
-#define SCIF_UNREGISTER_NACK 24 /* Notify peer about unregistration failure */
-#define SCIF_ALLOC_REQ 25 /* Request a mapped buffer */
-#define SCIF_ALLOC_GNT 26 /* Notify peer about allocation success */
-#define SCIF_ALLOC_REJ 27 /* Notify peer about allocation failure */
-#define SCIF_FREE_VIRT 28 /* Free previously allocated virtual memory */
-#define SCIF_MUNMAP 29 /* Acknowledgment for a SCIF_MMAP request */
-#define SCIF_MARK 30 /* SCIF Remote Fence Mark Request */
-#define SCIF_MARK_ACK 31 /* SCIF Remote Fence Mark Success */
-#define SCIF_MARK_NACK 32 /* SCIF Remote Fence Mark Failure */
-#define SCIF_WAIT 33 /* SCIF Remote Fence Wait Request */
-#define SCIF_WAIT_ACK 34 /* SCIF Remote Fence Wait Success */
-#define SCIF_WAIT_NACK 35 /* SCIF Remote Fence Wait Failure */
-#define SCIF_SIG_LOCAL 36 /* SCIF Remote Fence Local Signal Request */
-#define SCIF_SIG_REMOTE 37 /* SCIF Remote Fence Remote Signal Request */
-#define SCIF_SIG_ACK 38 /* SCIF Remote Fence Remote Signal Success */
-#define SCIF_SIG_NACK 39 /* SCIF Remote Fence Remote Signal Failure */
-#define SCIF_MAX_MSG SCIF_SIG_NACK
-
-/*
- * struct scifmsg - Node QP message format
- *
- * @src: Source information
- * @dst: Destination information
- * @uop: The message opcode
- * @payload: Unique payload format for each message
- */
-struct scifmsg {
- struct scif_port_id src;
- struct scif_port_id dst;
- u32 uop;
- u64 payload[4];
-} __packed;
-
-/*
- * struct scif_allocmsg - Used with SCIF_ALLOC_REQ to request
- * the remote note to allocate memory
- *
- * phys_addr: Physical address of the buffer
- * vaddr: Virtual address of the buffer
- * size: Size of the buffer
- * state: Current state
- * allocwq: wait queue for status
- */
-struct scif_allocmsg {
- dma_addr_t phys_addr;
- unsigned long vaddr;
- size_t size;
- enum scif_msg_state state;
- wait_queue_head_t allocwq;
-};
-
-/*
- * struct scif_qp - Node Queue Pair
- *
- * Interesting structure -- a little difficult because we can only
- * write across the PCIe, so any r/w pointer we need to read is
- * local. We only need to read the read pointer on the inbound_q
- * and read the write pointer in the outbound_q
- *
- * @magic: Magic value to ensure the peer sees the QP correctly
- * @outbound_q: The outbound ring buffer for sending messages
- * @inbound_q: The inbound ring buffer for receiving messages
- * @local_write: Local write index
- * @local_read: Local read index
- * @remote_qp: The remote queue pair
- * @local_buf: DMA address of local ring buffer
- * @local_qp: DMA address of the local queue pair data structure
- * @remote_buf: DMA address of remote ring buffer
- * @qp_state: QP state i.e. online or offline used for P2P
- * @send_lock: synchronize access to outbound queue
- * @recv_lock: Synchronize access to inbound queue
- */
-struct scif_qp {
- u64 magic;
-#define SCIFEP_MAGIC 0x5c1f000000005c1fULL
- struct scif_rb outbound_q;
- struct scif_rb inbound_q;
-
- u32 local_write __aligned(64);
- u32 local_read __aligned(64);
- struct scif_qp *remote_qp;
- dma_addr_t local_buf;
- dma_addr_t local_qp;
- dma_addr_t remote_buf;
- u32 qp_state;
-#define SCIF_QP_OFFLINE 0xdead
-#define SCIF_QP_ONLINE 0xc0de
- spinlock_t send_lock;
- spinlock_t recv_lock;
-};
-
-/*
- * struct scif_loopb_msg - An element in the loopback Node QP message list.
- *
- * @msg - The SCIF node QP message
- * @list - link in the list of messages
- */
-struct scif_loopb_msg {
- struct scifmsg msg;
- struct list_head list;
-};
-
-int scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg);
-int _scif_nodeqp_send(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_nodeqp_intrhandler(struct scif_dev *scifdev, struct scif_qp *qp);
-int scif_loopb_msg_handler(struct scif_dev *scifdev, struct scif_qp *qp);
-int scif_setup_qp(struct scif_dev *scifdev);
-int scif_qp_response(phys_addr_t phys, struct scif_dev *dev);
-int scif_setup_qp_connect(struct scif_qp *qp, dma_addr_t *qp_offset,
- int local_size, struct scif_dev *scifdev);
-int scif_setup_qp_accept(struct scif_qp *qp, dma_addr_t *qp_offset,
- dma_addr_t phys, int local_size,
- struct scif_dev *scifdev);
-int scif_setup_qp_connect_response(struct scif_dev *scifdev,
- struct scif_qp *qp, u64 payload);
-int scif_setup_loopback_qp(struct scif_dev *scifdev);
-int scif_destroy_loopback_qp(struct scif_dev *scifdev);
-void scif_poll_qp_state(struct work_struct *work);
-void scif_destroy_p2p(struct scif_dev *scifdev);
-void scif_send_exit(struct scif_dev *scifdev);
-static inline struct device *scif_get_peer_dev(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
- struct device *spdev_ret;
-
- rcu_read_lock();
- spdev = rcu_dereference(scifdev->spdev);
- if (spdev)
- spdev_ret = get_device(&spdev->dev);
- else
- spdev_ret = ERR_PTR(-ENODEV);
- rcu_read_unlock();
- return spdev_ret;
-}
-
-static inline void scif_put_peer_dev(struct device *dev)
-{
- put_device(dev);
-}
-#endif /* SCIF_NODEQP */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include "../bus/scif_bus.h"
-#include "scif_peer_bus.h"
-
-static inline struct scif_peer_dev *
-dev_to_scif_peer(struct device *dev)
-{
- return container_of(dev, struct scif_peer_dev, dev);
-}
-
-struct bus_type scif_peer_bus = {
- .name = "scif_peer_bus",
-};
-
-static void scif_peer_release_dev(struct device *d)
-{
- struct scif_peer_dev *sdev = dev_to_scif_peer(d);
- struct scif_dev *scifdev = &scif_dev[sdev->dnode];
-
- scif_cleanup_scifdev(scifdev);
- kfree(sdev);
-}
-
-static int scif_peer_initialize_device(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
- int ret;
-
- spdev = kzalloc(sizeof(*spdev), GFP_KERNEL);
- if (!spdev) {
- ret = -ENOMEM;
- goto err;
- }
-
- spdev->dev.parent = scifdev->sdev->dev.parent;
- spdev->dev.release = scif_peer_release_dev;
- spdev->dnode = scifdev->node;
- spdev->dev.bus = &scif_peer_bus;
- dev_set_name(&spdev->dev, "scif_peer-dev%u", spdev->dnode);
-
- device_initialize(&spdev->dev);
- get_device(&spdev->dev);
- rcu_assign_pointer(scifdev->spdev, spdev);
-
- mutex_lock(&scif_info.conflock);
- scif_info.total++;
- scif_info.maxid = max_t(u32, spdev->dnode, scif_info.maxid);
- mutex_unlock(&scif_info.conflock);
- return 0;
-err:
- dev_err(&scifdev->sdev->dev,
- "dnode %d: initialize_device rc %d\n", scifdev->node, ret);
- return ret;
-}
-
-static int scif_peer_add_device(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev = rcu_dereference(scifdev->spdev);
- char pool_name[16];
- int ret;
-
- ret = device_add(&spdev->dev);
- put_device(&spdev->dev);
- if (ret) {
- dev_err(&scifdev->sdev->dev,
- "dnode %d: peer device_add failed\n", scifdev->node);
- goto put_spdev;
- }
-
- scnprintf(pool_name, sizeof(pool_name), "scif-%d", spdev->dnode);
- scifdev->signal_pool = dmam_pool_create(pool_name, &scifdev->sdev->dev,
- sizeof(struct scif_status), 1,
- 0);
- if (!scifdev->signal_pool) {
- dev_err(&scifdev->sdev->dev,
- "dnode %d: dmam_pool_create failed\n", scifdev->node);
- ret = -ENOMEM;
- goto del_spdev;
- }
- dev_dbg(&spdev->dev, "Added peer dnode %d\n", spdev->dnode);
- return 0;
-del_spdev:
- device_del(&spdev->dev);
-put_spdev:
- RCU_INIT_POINTER(scifdev->spdev, NULL);
- synchronize_rcu();
- put_device(&spdev->dev);
-
- mutex_lock(&scif_info.conflock);
- scif_info.total--;
- mutex_unlock(&scif_info.conflock);
- return ret;
-}
-
-void scif_add_peer_device(struct work_struct *work)
-{
- struct scif_dev *scifdev = container_of(work, struct scif_dev,
- peer_add_work);
-
- scif_peer_add_device(scifdev);
-}
-
-/*
- * Peer device registration is split into a device_initialize and a device_add.
- * The reason for doing this is as follows: First, peer device registration
- * itself cannot be done in the message processing thread and must be delegated
- * to another workqueue, otherwise if SCIF client probe, called during peer
- * device registration, calls scif_connect(..), it will block the message
- * processing thread causing a deadlock. Next, device_initialize is done in the
- * "top-half" message processing thread and device_add in the "bottom-half"
- * workqueue. If this is not done, SCIF_CNCT_REQ message processing executing
- * concurrently with SCIF_INIT message processing is unable to get a reference
- * on the peer device, thereby failing the connect request.
- */
-void scif_peer_register_device(struct scif_dev *scifdev)
-{
- int ret;
-
- mutex_lock(&scifdev->lock);
- ret = scif_peer_initialize_device(scifdev);
- if (ret)
- goto exit;
- schedule_work(&scifdev->peer_add_work);
-exit:
- mutex_unlock(&scifdev->lock);
-}
-
-int scif_peer_unregister_device(struct scif_dev *scifdev)
-{
- struct scif_peer_dev *spdev;
-
- mutex_lock(&scifdev->lock);
- /* Flush work to ensure device register is complete */
- flush_work(&scifdev->peer_add_work);
-
- /*
- * Continue holding scifdev->lock since theoretically unregister_device
- * can be called simultaneously from multiple threads
- */
- spdev = rcu_dereference(scifdev->spdev);
- if (!spdev) {
- mutex_unlock(&scifdev->lock);
- return -ENODEV;
- }
-
- RCU_INIT_POINTER(scifdev->spdev, NULL);
- synchronize_rcu();
- mutex_unlock(&scifdev->lock);
-
- dev_dbg(&spdev->dev, "Removing peer dnode %d\n", spdev->dnode);
- device_unregister(&spdev->dev);
-
- mutex_lock(&scif_info.conflock);
- scif_info.total--;
- mutex_unlock(&scif_info.conflock);
- return 0;
-}
-
-int scif_peer_bus_init(void)
-{
- return bus_register(&scif_peer_bus);
-}
-
-void scif_peer_bus_exit(void)
-{
- bus_unregister(&scif_peer_bus);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef _SCIF_PEER_BUS_H_
-#define _SCIF_PEER_BUS_H_
-
-#include <linux/device.h>
-#include <linux/mic_common.h>
-#include <linux/scif.h>
-
-struct scif_dev;
-
-void scif_add_peer_device(struct work_struct *work);
-void scif_peer_register_device(struct scif_dev *sdev);
-int scif_peer_unregister_device(struct scif_dev *scifdev);
-int scif_peer_bus_init(void);
-void scif_peer_bus_exit(void);
-#endif /* _SCIF_PEER_BUS_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/idr.h>
-
-#include "scif_main.h"
-
-#define SCIF_PORT_COUNT 0x10000 /* Ports available */
-
-struct idr scif_ports;
-
-/**
- * struct scif_port - SCIF port information
- *
- * @ref_cnt: Reference count since there can be multiple endpoints
- * created via scif_accept(..) simultaneously using a port.
- */
-struct scif_port {
- int ref_cnt;
-};
-
-/**
- * __scif_get_port - Reserve a specified port # for SCIF and add it
- * to the global list.
- * @start: lowest port # to be reserved (inclusive).
- * @end: highest port # to be reserved (exclusive).
- *
- * @return : Allocated SCIF port #, or -ENOSPC if port unavailable.
- * On memory allocation failure, returns -ENOMEM.
- */
-static int __scif_get_port(int start, int end)
-{
- int id;
- struct scif_port *port = kzalloc(sizeof(*port), GFP_ATOMIC);
-
- if (!port)
- return -ENOMEM;
- spin_lock(&scif_info.port_lock);
- id = idr_alloc(&scif_ports, port, start, end, GFP_ATOMIC);
- if (id >= 0)
- port->ref_cnt++;
- spin_unlock(&scif_info.port_lock);
- return id;
-}
-
-/**
- * scif_rsrv_port - Reserve a specified port # for SCIF.
- * @port : port # to be reserved.
- *
- * @return : Allocated SCIF port #, or -ENOSPC if port unavailable.
- * On memory allocation failure, returns -ENOMEM.
- */
-int scif_rsrv_port(u16 port)
-{
- return __scif_get_port(port, port + 1);
-}
-
-/**
- * scif_get_new_port - Get and reserve any port # for SCIF in the range
- * SCIF_PORT_RSVD + 1 to SCIF_PORT_COUNT - 1.
- *
- * @return : Allocated SCIF port #, or -ENOSPC if no ports available.
- * On memory allocation failure, returns -ENOMEM.
- */
-int scif_get_new_port(void)
-{
- return __scif_get_port(SCIF_PORT_RSVD + 1, SCIF_PORT_COUNT);
-}
-
-/**
- * scif_get_port - Increment the reference count for a SCIF port
- * @id : SCIF port
- *
- * @return : None
- */
-void scif_get_port(u16 id)
-{
- struct scif_port *port;
-
- if (!id)
- return;
- spin_lock(&scif_info.port_lock);
- port = idr_find(&scif_ports, id);
- if (port)
- port->ref_cnt++;
- spin_unlock(&scif_info.port_lock);
-}
-
-/**
- * scif_put_port - Release a reserved SCIF port
- * @id : SCIF port to be released.
- *
- * @return : None
- */
-void scif_put_port(u16 id)
-{
- struct scif_port *port;
-
- if (!id)
- return;
- spin_lock(&scif_info.port_lock);
- port = idr_find(&scif_ports, id);
- if (port) {
- port->ref_cnt--;
- if (!port->ref_cnt) {
- idr_remove(&scif_ports, id);
- kfree(port);
- }
- }
- spin_unlock(&scif_info.port_lock);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/circ_buf.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/errno.h>
-
-#include "scif_rb.h"
-
-#define scif_rb_ring_cnt(head, tail, size) CIRC_CNT(head, tail, size)
-#define scif_rb_ring_space(head, tail, size) CIRC_SPACE(head, tail, size)
-
-/**
- * scif_rb_init - Initializes the ring buffer
- * @rb: ring buffer
- * @read_ptr: A pointer to the read offset
- * @write_ptr: A pointer to the write offset
- * @rb_base: A pointer to the base of the ring buffer
- * @size: The size of the ring buffer in powers of two
- */
-void scif_rb_init(struct scif_rb *rb, u32 *read_ptr, u32 *write_ptr,
- void *rb_base, u8 size)
-{
- rb->rb_base = rb_base;
- rb->size = (1 << size);
- rb->read_ptr = read_ptr;
- rb->write_ptr = write_ptr;
- rb->current_read_offset = *read_ptr;
- rb->current_write_offset = *write_ptr;
-}
-
-/* Copies a message to the ring buffer -- handles the wrap around case */
-static void memcpy_torb(struct scif_rb *rb, void *header,
- void *msg, u32 size)
-{
- u32 size1, size2;
-
- if (header + size >= rb->rb_base + rb->size) {
- /* Need to call two copies if it wraps around */
- size1 = (u32)(rb->rb_base + rb->size - header);
- size2 = size - size1;
- memcpy_toio((void __iomem __force *)header, msg, size1);
- memcpy_toio((void __iomem __force *)rb->rb_base,
- msg + size1, size2);
- } else {
- memcpy_toio((void __iomem __force *)header, msg, size);
- }
-}
-
-/* Copies a message from the ring buffer -- handles the wrap around case */
-static void memcpy_fromrb(struct scif_rb *rb, void *header,
- void *msg, u32 size)
-{
- u32 size1, size2;
-
- if (header + size >= rb->rb_base + rb->size) {
- /* Need to call two copies if it wraps around */
- size1 = (u32)(rb->rb_base + rb->size - header);
- size2 = size - size1;
- memcpy_fromio(msg, (void __iomem __force *)header, size1);
- memcpy_fromio(msg + size1,
- (void __iomem __force *)rb->rb_base, size2);
- } else {
- memcpy_fromio(msg, (void __iomem __force *)header, size);
- }
-}
-
-/**
- * scif_rb_space - Query space available for writing to the RB
- * @rb: ring buffer
- *
- * Return: size available for writing to RB in bytes.
- */
-u32 scif_rb_space(struct scif_rb *rb)
-{
- rb->current_read_offset = *rb->read_ptr;
- /*
- * Update from the HW read pointer only once the peer has exposed the
- * new empty slot. This barrier is paired with the memory barrier
- * scif_rb_update_read_ptr()
- */
- mb();
- return scif_rb_ring_space(rb->current_write_offset,
- rb->current_read_offset, rb->size);
-}
-
-/**
- * scif_rb_write - Write a message to the RB
- * @rb: ring buffer
- * @msg: buffer to send the message. Must be at least size bytes long
- * @size: the size (in bytes) to be copied to the RB
- *
- * This API does not block if there isn't enough space in the RB.
- * Returns: 0 on success or -ENOMEM on failure
- */
-int scif_rb_write(struct scif_rb *rb, void *msg, u32 size)
-{
- void *header;
-
- if (scif_rb_space(rb) < size)
- return -ENOMEM;
- header = rb->rb_base + rb->current_write_offset;
- memcpy_torb(rb, header, msg, size);
- /*
- * Wait until scif_rb_commit(). Update the local ring
- * buffer data, not the shared data until commit.
- */
- rb->current_write_offset =
- (rb->current_write_offset + size) & (rb->size - 1);
- return 0;
-}
-
-/**
- * scif_rb_commit - To submit the message to let the peer fetch it
- * @rb: ring buffer
- */
-void scif_rb_commit(struct scif_rb *rb)
-{
- /*
- * We must ensure ordering between the all the data committed
- * previously before we expose the new message to the peer by
- * updating the write_ptr. This write barrier is paired with
- * the read barrier in scif_rb_count(..)
- */
- wmb();
- WRITE_ONCE(*rb->write_ptr, rb->current_write_offset);
-#ifdef CONFIG_INTEL_MIC_CARD
- /*
- * X100 Si bug: For the case where a Core is performing an EXT_WR
- * followed by a Doorbell Write, the Core must perform two EXT_WR to the
- * same address with the same data before it does the Doorbell Write.
- * This way, if ordering is violated for the Interrupt Message, it will
- * fall just behind the first Posted associated with the first EXT_WR.
- */
- WRITE_ONCE(*rb->write_ptr, rb->current_write_offset);
-#endif
-}
-
-/**
- * scif_rb_get - To get next message from the ring buffer
- * @rb: ring buffer
- * @size: Number of bytes to be read
- *
- * Return: NULL if no bytes to be read from the ring buffer, otherwise the
- * pointer to the next byte
- */
-static void *scif_rb_get(struct scif_rb *rb, u32 size)
-{
- void *header = NULL;
-
- if (scif_rb_count(rb, size) >= size)
- header = rb->rb_base + rb->current_read_offset;
- return header;
-}
-
-/*
- * scif_rb_get_next - Read from ring buffer.
- * @rb: ring buffer
- * @msg: buffer to hold the message. Must be at least size bytes long
- * @size: Number of bytes to be read
- *
- * Return: number of bytes read if available bytes are >= size, otherwise
- * returns zero.
- */
-u32 scif_rb_get_next(struct scif_rb *rb, void *msg, u32 size)
-{
- void *header = NULL;
- int read_size = 0;
-
- header = scif_rb_get(rb, size);
- if (header) {
- u32 next_cmd_offset =
- (rb->current_read_offset + size) & (rb->size - 1);
-
- read_size = size;
- rb->current_read_offset = next_cmd_offset;
- memcpy_fromrb(rb, header, msg, size);
- }
- return read_size;
-}
-
-/**
- * scif_rb_update_read_ptr
- * @rb: ring buffer
- */
-void scif_rb_update_read_ptr(struct scif_rb *rb)
-{
- u32 new_offset;
-
- new_offset = rb->current_read_offset;
- /*
- * We must ensure ordering between the all the data committed or read
- * previously before we expose the empty slot to the peer by updating
- * the read_ptr. This barrier is paired with the memory barrier in
- * scif_rb_space(..)
- */
- mb();
- WRITE_ONCE(*rb->read_ptr, new_offset);
-#ifdef CONFIG_INTEL_MIC_CARD
- /*
- * X100 Si Bug: For the case where a Core is performing an EXT_WR
- * followed by a Doorbell Write, the Core must perform two EXT_WR to the
- * same address with the same data before it does the Doorbell Write.
- * This way, if ordering is violated for the Interrupt Message, it will
- * fall just behind the first Posted associated with the first EXT_WR.
- */
- WRITE_ONCE(*rb->read_ptr, new_offset);
-#endif
-}
-
-/**
- * scif_rb_count
- * @rb: ring buffer
- * @size: Number of bytes expected to be read
- *
- * Return: number of bytes that can be read from the RB
- */
-u32 scif_rb_count(struct scif_rb *rb, u32 size)
-{
- if (scif_rb_ring_cnt(rb->current_write_offset,
- rb->current_read_offset,
- rb->size) < size) {
- rb->current_write_offset = *rb->write_ptr;
- /*
- * Update from the HW write pointer if empty only once the peer
- * has exposed the new message. This read barrier is paired
- * with the write barrier in scif_rb_commit(..)
- */
- smp_rmb();
- }
- return scif_rb_ring_cnt(rb->current_write_offset,
- rb->current_read_offset,
- rb->size);
-}
+++ /dev/null
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_RB_H
-#define SCIF_RB_H
-/*
- * This file describes a general purpose, byte based ring buffer. Writers to the
- * ring buffer need to synchronize using a lock. The same is true for readers,
- * although in practice, the ring buffer has a single reader. It is lockless
- * between producer and consumer so it can handle being used across the PCIe
- * bus. The ring buffer ensures that there are no reads across the PCIe bus for
- * performance reasons. Two of these are used to form a single bidirectional
- * queue-pair across PCIe.
- */
-/*
- * struct scif_rb - SCIF Ring Buffer
- *
- * @rb_base: The base of the memory used for storing RB messages
- * @read_ptr: Pointer to the read offset
- * @write_ptr: Pointer to the write offset
- * @size: Size of the memory in rb_base
- * @current_read_offset: Cached read offset for performance
- * @current_write_offset: Cached write offset for performance
- */
-struct scif_rb {
- void *rb_base;
- u32 *read_ptr;
- u32 *write_ptr;
- u32 size;
- u32 current_read_offset;
- u32 current_write_offset;
-};
-
-/* methods used by both */
-void scif_rb_init(struct scif_rb *rb, u32 *read_ptr, u32 *write_ptr,
- void *rb_base, u8 size);
-/* writer only methods */
-/* write a new command, then scif_rb_commit() */
-int scif_rb_write(struct scif_rb *rb, void *msg, u32 size);
-/* after write(), then scif_rb_commit() */
-void scif_rb_commit(struct scif_rb *rb);
-/* query space available for writing to a RB. */
-u32 scif_rb_space(struct scif_rb *rb);
-
-/* reader only methods */
-/* read a new message from the ring buffer of size bytes */
-u32 scif_rb_get_next(struct scif_rb *rb, void *msg, u32 size);
-/* update the read pointer so that the space can be reused */
-void scif_rb_update_read_ptr(struct scif_rb *rb);
-/* count the number of bytes that can be read */
-u32 scif_rb_count(struct scif_rb *rb, u32 size);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include <linux/intel-iommu.h>
-#include <linux/pagemap.h>
-#include <linux/sched/mm.h>
-#include <linux/sched/signal.h>
-
-#include "scif_main.h"
-#include "scif_map.h"
-
-/* Used to skip ulimit checks for registrations with SCIF_MAP_KERNEL flag */
-#define SCIF_MAP_ULIMIT 0x40
-
-bool scif_ulimit_check = 1;
-
-/**
- * scif_rma_ep_init:
- * @ep: end point
- *
- * Initialize RMA per EP data structures.
- */
-void scif_rma_ep_init(struct scif_endpt *ep)
-{
- struct scif_endpt_rma_info *rma = &ep->rma_info;
-
- mutex_init(&rma->rma_lock);
- init_iova_domain(&rma->iovad, PAGE_SIZE, SCIF_IOVA_START_PFN);
- spin_lock_init(&rma->tc_lock);
- mutex_init(&rma->mmn_lock);
- INIT_LIST_HEAD(&rma->reg_list);
- INIT_LIST_HEAD(&rma->remote_reg_list);
- atomic_set(&rma->tw_refcount, 0);
- atomic_set(&rma->tcw_refcount, 0);
- atomic_set(&rma->tcw_total_pages, 0);
- atomic_set(&rma->fence_refcount, 0);
-
- rma->async_list_del = 0;
- rma->dma_chan = NULL;
- INIT_LIST_HEAD(&rma->mmn_list);
- INIT_LIST_HEAD(&rma->vma_list);
- init_waitqueue_head(&rma->markwq);
-}
-
-/**
- * scif_rma_ep_can_uninit:
- * @ep: end point
- *
- * Returns 1 if an endpoint can be uninitialized and 0 otherwise.
- */
-int scif_rma_ep_can_uninit(struct scif_endpt *ep)
-{
- int ret = 0;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Destroy RMA Info only if both lists are empty */
- if (list_empty(&ep->rma_info.reg_list) &&
- list_empty(&ep->rma_info.remote_reg_list) &&
- list_empty(&ep->rma_info.mmn_list) &&
- !atomic_read(&ep->rma_info.tw_refcount) &&
- !atomic_read(&ep->rma_info.tcw_refcount) &&
- !atomic_read(&ep->rma_info.fence_refcount))
- ret = 1;
- mutex_unlock(&ep->rma_info.rma_lock);
- return ret;
-}
-
-/**
- * scif_create_pinned_pages:
- * @nr_pages: number of pages in window
- * @prot: read/write protection
- *
- * Allocate and prepare a set of pinned pages.
- */
-static struct scif_pinned_pages *
-scif_create_pinned_pages(int nr_pages, int prot)
-{
- struct scif_pinned_pages *pin;
-
- might_sleep();
- pin = scif_zalloc(sizeof(*pin));
- if (!pin)
- goto error;
-
- pin->pages = scif_zalloc(nr_pages * sizeof(*pin->pages));
- if (!pin->pages)
- goto error_free_pinned_pages;
-
- pin->prot = prot;
- pin->magic = SCIFEP_MAGIC;
- return pin;
-
-error_free_pinned_pages:
- scif_free(pin, sizeof(*pin));
-error:
- return NULL;
-}
-
-/**
- * scif_destroy_pinned_pages:
- * @pin: A set of pinned pages.
- *
- * Deallocate resources for pinned pages.
- */
-static int scif_destroy_pinned_pages(struct scif_pinned_pages *pin)
-{
- int j;
- int writeable = pin->prot & SCIF_PROT_WRITE;
- int kernel = SCIF_MAP_KERNEL & pin->map_flags;
-
- if (kernel) {
- for (j = 0; j < pin->nr_pages; j++) {
- if (pin->pages[j] && !kernel) {
- if (writeable)
- set_page_dirty_lock(pin->pages[j]);
- put_page(pin->pages[j]);
- }
- }
- } else
- unpin_user_pages_dirty_lock(pin->pages, pin->nr_pages,
- writeable);
- scif_free(pin->pages,
- pin->nr_pages * sizeof(*pin->pages));
- scif_free(pin, sizeof(*pin));
- return 0;
-}
-
-/*
- * scif_create_window:
- * @ep: end point
- * @nr_pages: number of pages
- * @offset: registration offset
- * @temp: true if a temporary window is being created
- *
- * Allocate and prepare a self registration window.
- */
-struct scif_window *scif_create_window(struct scif_endpt *ep, int nr_pages,
- s64 offset, bool temp)
-{
- struct scif_window *window;
-
- might_sleep();
- window = scif_zalloc(sizeof(*window));
- if (!window)
- goto error;
-
- window->dma_addr = scif_zalloc(nr_pages * sizeof(*window->dma_addr));
- if (!window->dma_addr)
- goto error_free_window;
-
- window->num_pages = scif_zalloc(nr_pages * sizeof(*window->num_pages));
- if (!window->num_pages)
- goto error_free_window;
-
- window->offset = offset;
- window->ep = (u64)ep;
- window->magic = SCIFEP_MAGIC;
- window->reg_state = OP_IDLE;
- init_waitqueue_head(&window->regwq);
- window->unreg_state = OP_IDLE;
- init_waitqueue_head(&window->unregwq);
- INIT_LIST_HEAD(&window->list);
- window->type = SCIF_WINDOW_SELF;
- window->temp = temp;
- return window;
-
-error_free_window:
- scif_free(window->dma_addr,
- nr_pages * sizeof(*window->dma_addr));
- scif_free(window, sizeof(*window));
-error:
- return NULL;
-}
-
-/**
- * scif_destroy_incomplete_window:
- * @ep: end point
- * @window: registration window
- *
- * Deallocate resources for self window.
- */
-static void scif_destroy_incomplete_window(struct scif_endpt *ep,
- struct scif_window *window)
-{
- int err;
- int nr_pages = window->nr_pages;
- struct scif_allocmsg *alloc = &window->alloc_handle;
- struct scifmsg msg;
-
-retry:
- /* Wait for a SCIF_ALLOC_GNT/REJ message */
- err = wait_event_timeout(alloc->allocwq,
- alloc->state != OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
-
- mutex_lock(&ep->rma_info.rma_lock);
- if (alloc->state == OP_COMPLETED) {
- msg.uop = SCIF_FREE_VIRT;
- msg.src = ep->port;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = window->alloc_handle.vaddr;
- msg.payload[2] = (u64)window;
- msg.payload[3] = SCIF_REGISTER;
- _scif_nodeqp_send(ep->remote_dev, &msg);
- }
- mutex_unlock(&ep->rma_info.rma_lock);
-
- scif_free_window_offset(ep, window, window->offset);
- scif_free(window->dma_addr, nr_pages * sizeof(*window->dma_addr));
- scif_free(window->num_pages, nr_pages * sizeof(*window->num_pages));
- scif_free(window, sizeof(*window));
-}
-
-/**
- * scif_unmap_window:
- * @remote_dev: SCIF remote device
- * @window: registration window
- *
- * Delete any DMA mappings created for a registered self window
- */
-void scif_unmap_window(struct scif_dev *remote_dev, struct scif_window *window)
-{
- int j;
-
- if (scif_is_iommu_enabled() && !scifdev_self(remote_dev)) {
- if (window->st) {
- dma_unmap_sg(&remote_dev->sdev->dev,
- window->st->sgl, window->st->nents,
- DMA_BIDIRECTIONAL);
- sg_free_table(window->st);
- kfree(window->st);
- window->st = NULL;
- }
- } else {
- for (j = 0; j < window->nr_contig_chunks; j++) {
- if (window->dma_addr[j]) {
- scif_unmap_single(window->dma_addr[j],
- remote_dev,
- window->num_pages[j] <<
- PAGE_SHIFT);
- window->dma_addr[j] = 0x0;
- }
- }
- }
-}
-
-static inline struct mm_struct *__scif_acquire_mm(void)
-{
- if (scif_ulimit_check)
- return get_task_mm(current);
- return NULL;
-}
-
-static inline void __scif_release_mm(struct mm_struct *mm)
-{
- if (mm)
- mmput(mm);
-}
-
-static inline int
-__scif_dec_pinned_vm_lock(struct mm_struct *mm,
- int nr_pages)
-{
- if (!mm || !nr_pages || !scif_ulimit_check)
- return 0;
-
- atomic64_sub(nr_pages, &mm->pinned_vm);
- return 0;
-}
-
-static inline int __scif_check_inc_pinned_vm(struct mm_struct *mm,
- int nr_pages)
-{
- unsigned long locked, lock_limit;
-
- if (!mm || !nr_pages || !scif_ulimit_check)
- return 0;
-
- lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
- locked = atomic64_add_return(nr_pages, &mm->pinned_vm);
-
- if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
- atomic64_sub(nr_pages, &mm->pinned_vm);
- dev_err(scif_info.mdev.this_device,
- "locked(%lu) > lock_limit(%lu)\n",
- locked, lock_limit);
- return -ENOMEM;
- }
- return 0;
-}
-
-/**
- * scif_destroy_window:
- * @ep: end point
- * @window: registration window
- *
- * Deallocate resources for self window.
- */
-int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window)
-{
- int j;
- struct scif_pinned_pages *pinned_pages = window->pinned_pages;
- int nr_pages = window->nr_pages;
-
- might_sleep();
- if (!window->temp && window->mm) {
- __scif_dec_pinned_vm_lock(window->mm, window->nr_pages);
- __scif_release_mm(window->mm);
- window->mm = NULL;
- }
-
- scif_free_window_offset(ep, window, window->offset);
- scif_unmap_window(ep->remote_dev, window);
- /*
- * Decrement references for this set of pinned pages from
- * this window.
- */
- j = atomic_sub_return(1, &pinned_pages->ref_count);
- if (j < 0)
- dev_err(scif_info.mdev.this_device,
- "%s %d incorrect ref count %d\n",
- __func__, __LINE__, j);
- /*
- * If the ref count for pinned_pages is zero then someone
- * has already called scif_unpin_pages() for it and we should
- * destroy the page cache.
- */
- if (!j)
- scif_destroy_pinned_pages(window->pinned_pages);
- scif_free(window->dma_addr, nr_pages * sizeof(*window->dma_addr));
- scif_free(window->num_pages, nr_pages * sizeof(*window->num_pages));
- window->magic = 0;
- scif_free(window, sizeof(*window));
- return 0;
-}
-
-/**
- * scif_create_remote_lookup:
- * @remote_dev: SCIF remote device
- * @window: remote window
- *
- * Allocate and prepare lookup entries for the remote
- * end to copy over the physical addresses.
- * Returns 0 on success and appropriate errno on failure.
- */
-static int scif_create_remote_lookup(struct scif_dev *remote_dev,
- struct scif_window *window)
-{
- int i, j, err = 0;
- int nr_pages = window->nr_pages;
- bool vmalloc_dma_phys, vmalloc_num_pages;
-
- might_sleep();
- /* Map window */
- err = scif_map_single(&window->mapped_offset,
- window, remote_dev, sizeof(*window));
- if (err)
- goto error_window;
-
- /* Compute the number of lookup entries. 21 == 2MB Shift */
- window->nr_lookup = ALIGN(nr_pages * PAGE_SIZE,
- ((2) * 1024 * 1024)) >> 21;
-
- window->dma_addr_lookup.lookup =
- scif_alloc_coherent(&window->dma_addr_lookup.offset,
- remote_dev, window->nr_lookup *
- sizeof(*window->dma_addr_lookup.lookup),
- GFP_KERNEL | __GFP_ZERO);
- if (!window->dma_addr_lookup.lookup) {
- err = -ENOMEM;
- goto error_window;
- }
-
- window->num_pages_lookup.lookup =
- scif_alloc_coherent(&window->num_pages_lookup.offset,
- remote_dev, window->nr_lookup *
- sizeof(*window->num_pages_lookup.lookup),
- GFP_KERNEL | __GFP_ZERO);
- if (!window->num_pages_lookup.lookup) {
- err = -ENOMEM;
- goto error_window;
- }
-
- vmalloc_dma_phys = is_vmalloc_addr(&window->dma_addr[0]);
- vmalloc_num_pages = is_vmalloc_addr(&window->num_pages[0]);
-
- /* Now map each of the pages containing physical addresses */
- for (i = 0, j = 0; i < nr_pages; i += SCIF_NR_ADDR_IN_PAGE, j++) {
- err = scif_map_page(&window->dma_addr_lookup.lookup[j],
- vmalloc_dma_phys ?
- vmalloc_to_page(&window->dma_addr[i]) :
- virt_to_page(&window->dma_addr[i]),
- remote_dev);
- if (err)
- goto error_window;
- err = scif_map_page(&window->num_pages_lookup.lookup[j],
- vmalloc_num_pages ?
- vmalloc_to_page(&window->num_pages[i]) :
- virt_to_page(&window->num_pages[i]),
- remote_dev);
- if (err)
- goto error_window;
- }
- return 0;
-error_window:
- return err;
-}
-
-/**
- * scif_destroy_remote_lookup:
- * @remote_dev: SCIF remote device
- * @window: remote window
- *
- * Destroy lookup entries used for the remote
- * end to copy over the physical addresses.
- */
-static void scif_destroy_remote_lookup(struct scif_dev *remote_dev,
- struct scif_window *window)
-{
- int i, j;
-
- if (window->nr_lookup) {
- struct scif_rma_lookup *lup = &window->dma_addr_lookup;
- struct scif_rma_lookup *npup = &window->num_pages_lookup;
-
- for (i = 0, j = 0; i < window->nr_pages;
- i += SCIF_NR_ADDR_IN_PAGE, j++) {
- if (lup->lookup && lup->lookup[j])
- scif_unmap_single(lup->lookup[j],
- remote_dev,
- PAGE_SIZE);
- if (npup->lookup && npup->lookup[j])
- scif_unmap_single(npup->lookup[j],
- remote_dev,
- PAGE_SIZE);
- }
- if (lup->lookup)
- scif_free_coherent(lup->lookup, lup->offset,
- remote_dev, window->nr_lookup *
- sizeof(*lup->lookup));
- if (npup->lookup)
- scif_free_coherent(npup->lookup, npup->offset,
- remote_dev, window->nr_lookup *
- sizeof(*npup->lookup));
- if (window->mapped_offset)
- scif_unmap_single(window->mapped_offset,
- remote_dev, sizeof(*window));
- window->nr_lookup = 0;
- }
-}
-
-/**
- * scif_create_remote_window:
- * @scifdev: SCIF device
- * @nr_pages: number of pages in window
- *
- * Allocate and prepare a remote registration window.
- */
-static struct scif_window *
-scif_create_remote_window(struct scif_dev *scifdev, int nr_pages)
-{
- struct scif_window *window;
-
- might_sleep();
- window = scif_zalloc(sizeof(*window));
- if (!window)
- goto error_ret;
-
- window->magic = SCIFEP_MAGIC;
- window->nr_pages = nr_pages;
-
- window->dma_addr = scif_zalloc(nr_pages * sizeof(*window->dma_addr));
- if (!window->dma_addr)
- goto error_window;
-
- window->num_pages = scif_zalloc(nr_pages *
- sizeof(*window->num_pages));
- if (!window->num_pages)
- goto error_window;
-
- if (scif_create_remote_lookup(scifdev, window))
- goto error_window;
-
- window->type = SCIF_WINDOW_PEER;
- window->unreg_state = OP_IDLE;
- INIT_LIST_HEAD(&window->list);
- return window;
-error_window:
- scif_destroy_remote_window(window);
-error_ret:
- return NULL;
-}
-
-/**
- * scif_destroy_remote_window:
- * @window: remote registration window
- *
- * Deallocate resources for remote window.
- */
-void
-scif_destroy_remote_window(struct scif_window *window)
-{
- scif_free(window->dma_addr, window->nr_pages *
- sizeof(*window->dma_addr));
- scif_free(window->num_pages, window->nr_pages *
- sizeof(*window->num_pages));
- window->magic = 0;
- scif_free(window, sizeof(*window));
-}
-
-/**
- * scif_iommu_map: create DMA mappings if the IOMMU is enabled
- * @remote_dev: SCIF remote device
- * @window: remote registration window
- *
- * Map the physical pages using dma_map_sg(..) and then detect the number
- * of contiguous DMA mappings allocated
- */
-static int scif_iommu_map(struct scif_dev *remote_dev,
- struct scif_window *window)
-{
- struct scatterlist *sg;
- int i, err;
- scif_pinned_pages_t pin = window->pinned_pages;
-
- window->st = kzalloc(sizeof(*window->st), GFP_KERNEL);
- if (!window->st)
- return -ENOMEM;
-
- err = sg_alloc_table(window->st, window->nr_pages, GFP_KERNEL);
- if (err)
- return err;
-
- for_each_sg(window->st->sgl, sg, window->st->nents, i)
- sg_set_page(sg, pin->pages[i], PAGE_SIZE, 0x0);
-
- err = dma_map_sg(&remote_dev->sdev->dev, window->st->sgl,
- window->st->nents, DMA_BIDIRECTIONAL);
- if (!err)
- return -ENOMEM;
- /* Detect contiguous ranges of DMA mappings */
- sg = window->st->sgl;
- for (i = 0; sg; i++) {
- dma_addr_t last_da;
-
- window->dma_addr[i] = sg_dma_address(sg);
- window->num_pages[i] = sg_dma_len(sg) >> PAGE_SHIFT;
- last_da = sg_dma_address(sg) + sg_dma_len(sg);
- while ((sg = sg_next(sg)) && sg_dma_address(sg) == last_da) {
- window->num_pages[i] +=
- (sg_dma_len(sg) >> PAGE_SHIFT);
- last_da = window->dma_addr[i] +
- sg_dma_len(sg);
- }
- window->nr_contig_chunks++;
- }
- return 0;
-}
-
-/**
- * scif_map_window:
- * @remote_dev: SCIF remote device
- * @window: self registration window
- *
- * Map pages of a window into the aperture/PCI.
- * Also determine addresses required for DMA.
- */
-int
-scif_map_window(struct scif_dev *remote_dev, struct scif_window *window)
-{
- int i, j, k, err = 0, nr_contig_pages;
- scif_pinned_pages_t pin;
- phys_addr_t phys_prev, phys_curr;
-
- might_sleep();
-
- pin = window->pinned_pages;
-
- if (intel_iommu_enabled && !scifdev_self(remote_dev))
- return scif_iommu_map(remote_dev, window);
-
- for (i = 0, j = 0; i < window->nr_pages; i += nr_contig_pages, j++) {
- phys_prev = page_to_phys(pin->pages[i]);
- nr_contig_pages = 1;
-
- /* Detect physically contiguous chunks */
- for (k = i + 1; k < window->nr_pages; k++) {
- phys_curr = page_to_phys(pin->pages[k]);
- if (phys_curr != (phys_prev + PAGE_SIZE))
- break;
- phys_prev = phys_curr;
- nr_contig_pages++;
- }
- window->num_pages[j] = nr_contig_pages;
- window->nr_contig_chunks++;
- if (scif_is_mgmt_node()) {
- /*
- * Management node has to deal with SMPT on X100 and
- * hence the DMA mapping is required
- */
- err = scif_map_single(&window->dma_addr[j],
- phys_to_virt(page_to_phys(
- pin->pages[i])),
- remote_dev,
- nr_contig_pages << PAGE_SHIFT);
- if (err)
- return err;
- } else {
- window->dma_addr[j] = page_to_phys(pin->pages[i]);
- }
- }
- return err;
-}
-
-/**
- * scif_send_scif_unregister:
- * @ep: end point
- * @window: self registration window
- *
- * Send a SCIF_UNREGISTER message.
- */
-static int scif_send_scif_unregister(struct scif_endpt *ep,
- struct scif_window *window)
-{
- struct scifmsg msg;
-
- msg.uop = SCIF_UNREGISTER;
- msg.src = ep->port;
- msg.payload[0] = window->alloc_handle.vaddr;
- msg.payload[1] = (u64)window;
- return scif_nodeqp_send(ep->remote_dev, &msg);
-}
-
-/**
- * scif_unregister_window:
- * @window: self registration window
- *
- * Send an unregistration request and wait for a response.
- */
-int scif_unregister_window(struct scif_window *window)
-{
- int err = 0;
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
- bool send_msg = false;
-
- might_sleep();
- switch (window->unreg_state) {
- case OP_IDLE:
- {
- window->unreg_state = OP_IN_PROGRESS;
- send_msg = true;
- }
- fallthrough;
- case OP_IN_PROGRESS:
- {
- scif_get_window(window, 1);
- mutex_unlock(&ep->rma_info.rma_lock);
- if (send_msg) {
- err = scif_send_scif_unregister(ep, window);
- if (err) {
- window->unreg_state = OP_COMPLETED;
- goto done;
- }
- } else {
- /* Return ENXIO since unregistration is in progress */
- mutex_lock(&ep->rma_info.rma_lock);
- return -ENXIO;
- }
-retry:
- /* Wait for a SCIF_UNREGISTER_(N)ACK message */
- err = wait_event_timeout(window->unregwq,
- window->unreg_state != OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- if (!err) {
- err = -ENODEV;
- window->unreg_state = OP_COMPLETED;
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n", __func__, __LINE__, err);
- }
- if (err > 0)
- err = 0;
-done:
- mutex_lock(&ep->rma_info.rma_lock);
- scif_put_window(window, 1);
- break;
- }
- case OP_FAILED:
- {
- if (!scifdev_alive(ep)) {
- err = -ENODEV;
- window->unreg_state = OP_COMPLETED;
- }
- break;
- }
- case OP_COMPLETED:
- break;
- default:
- err = -ENODEV;
- }
-
- if (window->unreg_state == OP_COMPLETED && window->ref_count)
- scif_put_window(window, window->nr_pages);
-
- if (!window->ref_count) {
- atomic_inc(&ep->rma_info.tw_refcount);
- list_del_init(&window->list);
- scif_free_window_offset(ep, window, window->offset);
- mutex_unlock(&ep->rma_info.rma_lock);
- if ((!!(window->pinned_pages->map_flags & SCIF_MAP_KERNEL)) &&
- scifdev_alive(ep)) {
- scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan);
- } else {
- if (!__scif_dec_pinned_vm_lock(window->mm,
- window->nr_pages)) {
- __scif_release_mm(window->mm);
- window->mm = NULL;
- }
- }
- scif_queue_for_cleanup(window, &scif_info.rma);
- mutex_lock(&ep->rma_info.rma_lock);
- }
- return err;
-}
-
-/**
- * scif_send_alloc_request:
- * @ep: end point
- * @window: self registration window
- *
- * Send a remote window allocation request
- */
-static int scif_send_alloc_request(struct scif_endpt *ep,
- struct scif_window *window)
-{
- struct scifmsg msg;
- struct scif_allocmsg *alloc = &window->alloc_handle;
-
- /* Set up the Alloc Handle */
- alloc->state = OP_IN_PROGRESS;
- init_waitqueue_head(&alloc->allocwq);
-
- /* Send out an allocation request */
- msg.uop = SCIF_ALLOC_REQ;
- msg.payload[1] = window->nr_pages;
- msg.payload[2] = (u64)&window->alloc_handle;
- return _scif_nodeqp_send(ep->remote_dev, &msg);
-}
-
-/**
- * scif_prep_remote_window:
- * @ep: end point
- * @window: self registration window
- *
- * Send a remote window allocation request, wait for an allocation response,
- * and prepares the remote window by copying over the page lists
- */
-static int scif_prep_remote_window(struct scif_endpt *ep,
- struct scif_window *window)
-{
- struct scifmsg msg;
- struct scif_window *remote_window;
- struct scif_allocmsg *alloc = &window->alloc_handle;
- dma_addr_t *dma_phys_lookup, *tmp, *num_pages_lookup, *tmp1;
- int i = 0, j = 0;
- int nr_contig_chunks, loop_nr_contig_chunks;
- int remaining_nr_contig_chunks, nr_lookup;
- int err, map_err;
-
- map_err = scif_map_window(ep->remote_dev, window);
- if (map_err)
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d map_err %d\n", __func__, __LINE__, map_err);
- remaining_nr_contig_chunks = window->nr_contig_chunks;
- nr_contig_chunks = window->nr_contig_chunks;
-retry:
- /* Wait for a SCIF_ALLOC_GNT/REJ message */
- err = wait_event_timeout(alloc->allocwq,
- alloc->state != OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- mutex_lock(&ep->rma_info.rma_lock);
- /* Synchronize with the thread waking up allocwq */
- mutex_unlock(&ep->rma_info.rma_lock);
- if (!err && scifdev_alive(ep))
- goto retry;
-
- if (!err)
- err = -ENODEV;
-
- if (err > 0)
- err = 0;
- else
- return err;
-
- /* Bail out. The remote end rejected this request */
- if (alloc->state == OP_FAILED)
- return -ENOMEM;
-
- if (map_err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, map_err);
- msg.uop = SCIF_FREE_VIRT;
- msg.src = ep->port;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = window->alloc_handle.vaddr;
- msg.payload[2] = (u64)window;
- msg.payload[3] = SCIF_REGISTER;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED)
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- else
- err = -ENOTCONN;
- spin_unlock(&ep->lock);
- return err;
- }
-
- remote_window = scif_ioremap(alloc->phys_addr, sizeof(*window),
- ep->remote_dev);
-
- /* Compute the number of lookup entries. 21 == 2MB Shift */
- nr_lookup = ALIGN(nr_contig_chunks, SCIF_NR_ADDR_IN_PAGE)
- >> ilog2(SCIF_NR_ADDR_IN_PAGE);
-
- dma_phys_lookup =
- scif_ioremap(remote_window->dma_addr_lookup.offset,
- nr_lookup *
- sizeof(*remote_window->dma_addr_lookup.lookup),
- ep->remote_dev);
- num_pages_lookup =
- scif_ioremap(remote_window->num_pages_lookup.offset,
- nr_lookup *
- sizeof(*remote_window->num_pages_lookup.lookup),
- ep->remote_dev);
-
- while (remaining_nr_contig_chunks) {
- loop_nr_contig_chunks = min_t(int, remaining_nr_contig_chunks,
- (int)SCIF_NR_ADDR_IN_PAGE);
- /* #1/2 - Copy physical addresses over to the remote side */
-
- /* #2/2 - Copy DMA addresses (addresses that are fed into the
- * DMA engine) We transfer bus addresses which are then
- * converted into a MIC physical address on the remote
- * side if it is a MIC, if the remote node is a mgmt node we
- * transfer the MIC physical address
- */
- tmp = scif_ioremap(dma_phys_lookup[j],
- loop_nr_contig_chunks *
- sizeof(*window->dma_addr),
- ep->remote_dev);
- tmp1 = scif_ioremap(num_pages_lookup[j],
- loop_nr_contig_chunks *
- sizeof(*window->num_pages),
- ep->remote_dev);
- if (scif_is_mgmt_node()) {
- memcpy_toio((void __force __iomem *)tmp,
- &window->dma_addr[i], loop_nr_contig_chunks
- * sizeof(*window->dma_addr));
- memcpy_toio((void __force __iomem *)tmp1,
- &window->num_pages[i], loop_nr_contig_chunks
- * sizeof(*window->num_pages));
- } else {
- if (scifdev_is_p2p(ep->remote_dev)) {
- /*
- * add remote node's base address for this node
- * to convert it into a MIC address
- */
- int m;
- dma_addr_t dma_addr;
-
- for (m = 0; m < loop_nr_contig_chunks; m++) {
- dma_addr = window->dma_addr[i + m] +
- ep->remote_dev->base_addr;
- writeq(dma_addr,
- (void __force __iomem *)&tmp[m]);
- }
- memcpy_toio((void __force __iomem *)tmp1,
- &window->num_pages[i],
- loop_nr_contig_chunks
- * sizeof(*window->num_pages));
- } else {
- /* Mgmt node or loopback - transfer DMA
- * addresses as is, this is the same as a
- * MIC physical address (we use the dma_addr
- * and not the phys_addr array since the
- * phys_addr is only setup if there is a mmap()
- * request from the mgmt node)
- */
- memcpy_toio((void __force __iomem *)tmp,
- &window->dma_addr[i],
- loop_nr_contig_chunks *
- sizeof(*window->dma_addr));
- memcpy_toio((void __force __iomem *)tmp1,
- &window->num_pages[i],
- loop_nr_contig_chunks *
- sizeof(*window->num_pages));
- }
- }
- remaining_nr_contig_chunks -= loop_nr_contig_chunks;
- i += loop_nr_contig_chunks;
- j++;
- scif_iounmap(tmp, loop_nr_contig_chunks *
- sizeof(*window->dma_addr), ep->remote_dev);
- scif_iounmap(tmp1, loop_nr_contig_chunks *
- sizeof(*window->num_pages), ep->remote_dev);
- }
-
- /* Prepare the remote window for the peer */
- remote_window->peer_window = (u64)window;
- remote_window->offset = window->offset;
- remote_window->prot = window->prot;
- remote_window->nr_contig_chunks = nr_contig_chunks;
- remote_window->ep = ep->remote_ep;
- scif_iounmap(num_pages_lookup,
- nr_lookup *
- sizeof(*remote_window->num_pages_lookup.lookup),
- ep->remote_dev);
- scif_iounmap(dma_phys_lookup,
- nr_lookup *
- sizeof(*remote_window->dma_addr_lookup.lookup),
- ep->remote_dev);
- scif_iounmap(remote_window, sizeof(*remote_window), ep->remote_dev);
- window->peer_window = alloc->vaddr;
- return err;
-}
-
-/**
- * scif_send_scif_register:
- * @ep: end point
- * @window: self registration window
- *
- * Send a SCIF_REGISTER message if EP is connected and wait for a
- * SCIF_REGISTER_(N)ACK message else send a SCIF_FREE_VIRT
- * message so that the peer can free its remote window allocated earlier.
- */
-static int scif_send_scif_register(struct scif_endpt *ep,
- struct scif_window *window)
-{
- int err = 0;
- struct scifmsg msg;
-
- msg.src = ep->port;
- msg.payload[0] = ep->remote_ep;
- msg.payload[1] = window->alloc_handle.vaddr;
- msg.payload[2] = (u64)window;
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED) {
- msg.uop = SCIF_REGISTER;
- window->reg_state = OP_IN_PROGRESS;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- spin_unlock(&ep->lock);
- if (!err) {
-retry:
- /* Wait for a SCIF_REGISTER_(N)ACK message */
- err = wait_event_timeout(window->regwq,
- window->reg_state !=
- OP_IN_PROGRESS,
- SCIF_NODE_ALIVE_TIMEOUT);
- if (!err && scifdev_alive(ep))
- goto retry;
- err = !err ? -ENODEV : 0;
- if (window->reg_state == OP_FAILED)
- err = -ENOTCONN;
- }
- } else {
- msg.uop = SCIF_FREE_VIRT;
- msg.payload[3] = SCIF_REGISTER;
- err = _scif_nodeqp_send(ep->remote_dev, &msg);
- spin_unlock(&ep->lock);
- if (!err)
- err = -ENOTCONN;
- }
- return err;
-}
-
-/**
- * scif_get_window_offset:
- * @ep: end point descriptor
- * @flags: flags
- * @offset: offset hint
- * @num_pages: number of pages
- * @out_offset: computed offset returned by reference.
- *
- * Compute/Claim a new offset for this EP.
- */
-int scif_get_window_offset(struct scif_endpt *ep, int flags, s64 offset,
- int num_pages, s64 *out_offset)
-{
- s64 page_index;
- struct iova *iova_ptr;
- int err = 0;
-
- if (flags & SCIF_MAP_FIXED) {
- page_index = SCIF_IOVA_PFN(offset);
- iova_ptr = reserve_iova(&ep->rma_info.iovad, page_index,
- page_index + num_pages - 1);
- if (!iova_ptr)
- err = -EADDRINUSE;
- } else {
- iova_ptr = alloc_iova(&ep->rma_info.iovad, num_pages,
- SCIF_DMA_63BIT_PFN - 1, 0);
- if (!iova_ptr)
- err = -ENOMEM;
- }
- if (!err)
- *out_offset = (iova_ptr->pfn_lo) << PAGE_SHIFT;
- return err;
-}
-
-/**
- * scif_free_window_offset:
- * @ep: end point descriptor
- * @window: registration window
- * @offset: Offset to be freed
- *
- * Free offset for this EP. The callee is supposed to grab
- * the RMA mutex before calling this API.
- */
-void scif_free_window_offset(struct scif_endpt *ep,
- struct scif_window *window, s64 offset)
-{
- if ((window && !window->offset_freed) || !window) {
- free_iova(&ep->rma_info.iovad, offset >> PAGE_SHIFT);
- if (window)
- window->offset_freed = true;
- }
-}
-
-/**
- * scif_alloc_req: Respond to SCIF_ALLOC_REQ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side is requesting a memory allocation.
- */
-void scif_alloc_req(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- int err;
- struct scif_window *window = NULL;
- int nr_pages = msg->payload[1];
-
- window = scif_create_remote_window(scifdev, nr_pages);
- if (!window) {
- err = -ENOMEM;
- goto error;
- }
-
- /* The peer's allocation request is granted */
- msg->uop = SCIF_ALLOC_GNT;
- msg->payload[0] = (u64)window;
- msg->payload[1] = window->mapped_offset;
- err = scif_nodeqp_send(scifdev, msg);
- if (err)
- scif_destroy_remote_window(window);
- return;
-error:
- /* The peer's allocation request is rejected */
- dev_err(&scifdev->sdev->dev,
- "%s %d error %d alloc_ptr %p nr_pages 0x%x\n",
- __func__, __LINE__, err, window, nr_pages);
- msg->uop = SCIF_ALLOC_REJ;
- scif_nodeqp_send(scifdev, msg);
-}
-
-/**
- * scif_alloc_gnt_rej: Respond to SCIF_ALLOC_GNT/REJ interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remote side responded to a memory allocation.
- */
-void scif_alloc_gnt_rej(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_allocmsg *handle = (struct scif_allocmsg *)msg->payload[2];
- struct scif_window *window = container_of(handle, struct scif_window,
- alloc_handle);
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- handle->vaddr = msg->payload[0];
- handle->phys_addr = msg->payload[1];
- if (msg->uop == SCIF_ALLOC_GNT)
- handle->state = OP_COMPLETED;
- else
- handle->state = OP_FAILED;
- wake_up(&handle->allocwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_free_virt: Respond to SCIF_FREE_VIRT interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Free up memory kmalloc'd earlier.
- */
-void scif_free_virt(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window = (struct scif_window *)msg->payload[1];
-
- scif_destroy_remote_window(window);
-}
-
-static void
-scif_fixup_aper_base(struct scif_dev *dev, struct scif_window *window)
-{
- int j;
- struct scif_hw_dev *sdev = dev->sdev;
- phys_addr_t apt_base = 0;
-
- /*
- * Add the aperture base if the DMA address is not card relative
- * since the DMA addresses need to be an offset into the bar
- */
- if (!scifdev_self(dev) && window->type == SCIF_WINDOW_PEER &&
- sdev->aper && !sdev->card_rel_da)
- apt_base = sdev->aper->pa;
- else
- return;
-
- for (j = 0; j < window->nr_contig_chunks; j++) {
- if (window->num_pages[j])
- window->dma_addr[j] += apt_base;
- else
- break;
- }
-}
-
-/**
- * scif_recv_reg: Respond to SCIF_REGISTER interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Update remote window list with a new registered window.
- */
-void scif_recv_reg(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_endpt *ep = (struct scif_endpt *)msg->payload[0];
- struct scif_window *window =
- (struct scif_window *)msg->payload[1];
-
- mutex_lock(&ep->rma_info.rma_lock);
- spin_lock(&ep->lock);
- if (ep->state == SCIFEP_CONNECTED) {
- msg->uop = SCIF_REGISTER_ACK;
- scif_nodeqp_send(ep->remote_dev, msg);
- scif_fixup_aper_base(ep->remote_dev, window);
- /* No further failures expected. Insert new window */
- scif_insert_window(window, &ep->rma_info.remote_reg_list);
- } else {
- msg->uop = SCIF_REGISTER_NACK;
- scif_nodeqp_send(ep->remote_dev, msg);
- }
- spin_unlock(&ep->lock);
- mutex_unlock(&ep->rma_info.rma_lock);
- /* free up any lookup resources now that page lists are transferred */
- scif_destroy_remote_lookup(ep->remote_dev, window);
- /*
- * We could not insert the window but we need to
- * destroy the window.
- */
- if (msg->uop == SCIF_REGISTER_NACK)
- scif_destroy_remote_window(window);
-}
-
-/**
- * scif_recv_unreg: Respond to SCIF_UNREGISTER interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Remove window from remote registration list;
- */
-void scif_recv_unreg(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_rma_req req;
- struct scif_window *window = NULL;
- struct scif_window *recv_window =
- (struct scif_window *)msg->payload[0];
- struct scif_endpt *ep;
- int del_window = 0;
-
- ep = (struct scif_endpt *)recv_window->ep;
- req.out_window = &window;
- req.offset = recv_window->offset;
- req.prot = 0;
- req.nr_bytes = recv_window->nr_pages << PAGE_SHIFT;
- req.type = SCIF_WINDOW_FULL;
- req.head = &ep->rma_info.remote_reg_list;
- msg->payload[0] = ep->remote_ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- if (scif_query_window(&req)) {
- dev_err(&scifdev->sdev->dev,
- "%s %d -ENXIO\n", __func__, __LINE__);
- msg->uop = SCIF_UNREGISTER_ACK;
- goto error;
- }
- if (window) {
- if (window->ref_count)
- scif_put_window(window, window->nr_pages);
- else
- dev_err(&scifdev->sdev->dev,
- "%s %d ref count should be +ve\n",
- __func__, __LINE__);
- window->unreg_state = OP_COMPLETED;
- if (!window->ref_count) {
- msg->uop = SCIF_UNREGISTER_ACK;
- atomic_inc(&ep->rma_info.tw_refcount);
- ep->rma_info.async_list_del = 1;
- list_del_init(&window->list);
- del_window = 1;
- } else {
- /* NACK! There are valid references to this window */
- msg->uop = SCIF_UNREGISTER_NACK;
- }
- } else {
- /* The window did not make its way to the list at all. ACK */
- msg->uop = SCIF_UNREGISTER_ACK;
- scif_destroy_remote_window(recv_window);
- }
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- if (del_window)
- scif_drain_dma_intr(ep->remote_dev->sdev,
- ep->rma_info.dma_chan);
- scif_nodeqp_send(ep->remote_dev, msg);
- if (del_window)
- scif_queue_for_cleanup(window, &scif_info.rma);
-}
-
-/**
- * scif_recv_reg_ack: Respond to SCIF_REGISTER_ACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to complete registration.
- */
-void scif_recv_reg_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[2];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->reg_state = OP_COMPLETED;
- wake_up(&window->regwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_reg_nack: Respond to SCIF_REGISTER_NACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to inform it that registration
- * cannot be completed.
- */
-void scif_recv_reg_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[2];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->reg_state = OP_FAILED;
- wake_up(&window->regwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_unreg_ack: Respond to SCIF_UNREGISTER_ACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to complete unregistration.
- */
-void scif_recv_unreg_ack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[1];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->unreg_state = OP_COMPLETED;
- wake_up(&window->unregwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/**
- * scif_recv_unreg_nack: Respond to SCIF_UNREGISTER_NACK interrupt message
- * @scifdev: SCIF device
- * @msg: Interrupt message
- *
- * Wake up the window waiting to inform it that unregistration
- * cannot be completed immediately.
- */
-void scif_recv_unreg_nack(struct scif_dev *scifdev, struct scifmsg *msg)
-{
- struct scif_window *window =
- (struct scif_window *)msg->payload[1];
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
-
- mutex_lock(&ep->rma_info.rma_lock);
- window->unreg_state = OP_FAILED;
- wake_up(&window->unregwq);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-int __scif_pin_pages(void *addr, size_t len, int *out_prot,
- int map_flags, scif_pinned_pages_t *pages)
-{
- struct scif_pinned_pages *pinned_pages;
- int nr_pages, err = 0, i;
- bool vmalloc_addr = false;
- bool try_upgrade = false;
- int prot = *out_prot;
- int ulimit = 0;
- struct mm_struct *mm = NULL;
-
- /* Unsupported flags */
- if (map_flags & ~(SCIF_MAP_KERNEL | SCIF_MAP_ULIMIT))
- return -EINVAL;
- ulimit = !!(map_flags & SCIF_MAP_ULIMIT);
-
- /* Unsupported protection requested */
- if (prot & ~(SCIF_PROT_READ | SCIF_PROT_WRITE))
- return -EINVAL;
-
- /* addr/len must be page aligned. len should be non zero */
- if (!len ||
- (ALIGN((u64)addr, PAGE_SIZE) != (u64)addr) ||
- (ALIGN((u64)len, PAGE_SIZE) != (u64)len))
- return -EINVAL;
-
- might_sleep();
-
- nr_pages = len >> PAGE_SHIFT;
-
- /* Allocate a set of pinned pages */
- pinned_pages = scif_create_pinned_pages(nr_pages, prot);
- if (!pinned_pages)
- return -ENOMEM;
-
- if (map_flags & SCIF_MAP_KERNEL) {
- if (is_vmalloc_addr(addr))
- vmalloc_addr = true;
-
- for (i = 0; i < nr_pages; i++) {
- if (vmalloc_addr)
- pinned_pages->pages[i] =
- vmalloc_to_page(addr + (i * PAGE_SIZE));
- else
- pinned_pages->pages[i] =
- virt_to_page(addr + (i * PAGE_SIZE));
- }
- pinned_pages->nr_pages = nr_pages;
- pinned_pages->map_flags = SCIF_MAP_KERNEL;
- } else {
- /*
- * SCIF supports registration caching. If a registration has
- * been requested with read only permissions, then we try
- * to pin the pages with RW permissions so that a subsequent
- * transfer with RW permission can hit the cache instead of
- * invalidating it. If the upgrade fails with RW then we
- * revert back to R permission and retry
- */
- if (prot == SCIF_PROT_READ)
- try_upgrade = true;
- prot |= SCIF_PROT_WRITE;
-retry:
- mm = current->mm;
- if (ulimit) {
- err = __scif_check_inc_pinned_vm(mm, nr_pages);
- if (err) {
- pinned_pages->nr_pages = 0;
- goto error_unmap;
- }
- }
-
- pinned_pages->nr_pages = pin_user_pages_fast(
- (u64)addr,
- nr_pages,
- (prot & SCIF_PROT_WRITE) ? FOLL_WRITE : 0,
- pinned_pages->pages);
- if (nr_pages != pinned_pages->nr_pages) {
- if (pinned_pages->nr_pages < 0)
- pinned_pages->nr_pages = 0;
- if (try_upgrade) {
- if (ulimit)
- __scif_dec_pinned_vm_lock(mm, nr_pages);
- /* Roll back any pinned pages */
- unpin_user_pages(pinned_pages->pages,
- pinned_pages->nr_pages);
- prot &= ~SCIF_PROT_WRITE;
- try_upgrade = false;
- goto retry;
- }
- }
- pinned_pages->map_flags = 0;
- }
-
- if (pinned_pages->nr_pages < nr_pages) {
- err = -EFAULT;
- goto dec_pinned;
- }
-
- *out_prot = prot;
- atomic_set(&pinned_pages->ref_count, 1);
- *pages = pinned_pages;
- return err;
-dec_pinned:
- if (ulimit)
- __scif_dec_pinned_vm_lock(mm, nr_pages);
- /* Something went wrong! Rollback */
-error_unmap:
- scif_destroy_pinned_pages(pinned_pages);
- *pages = NULL;
- dev_dbg(scif_info.mdev.this_device,
- "%s %d err %d len 0x%lx\n", __func__, __LINE__, err, len);
- return err;
-}
-
-int scif_pin_pages(void *addr, size_t len, int prot,
- int map_flags, scif_pinned_pages_t *pages)
-{
- return __scif_pin_pages(addr, len, &prot, map_flags, pages);
-}
-EXPORT_SYMBOL_GPL(scif_pin_pages);
-
-int scif_unpin_pages(scif_pinned_pages_t pinned_pages)
-{
- int err = 0, ret;
-
- if (!pinned_pages || SCIFEP_MAGIC != pinned_pages->magic)
- return -EINVAL;
-
- ret = atomic_sub_return(1, &pinned_pages->ref_count);
- if (ret < 0) {
- dev_err(scif_info.mdev.this_device,
- "%s %d scif_unpin_pages called without pinning? rc %d\n",
- __func__, __LINE__, ret);
- return -EINVAL;
- }
- /*
- * Destroy the window if the ref count for this set of pinned
- * pages has dropped to zero. If it is positive then there is
- * a valid registered window which is backed by these pages and
- * it will be destroyed once all such windows are unregistered.
- */
- if (!ret)
- err = scif_destroy_pinned_pages(pinned_pages);
-
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_unpin_pages);
-
-static inline void
-scif_insert_local_window(struct scif_window *window, struct scif_endpt *ep)
-{
- mutex_lock(&ep->rma_info.rma_lock);
- scif_insert_window(window, &ep->rma_info.reg_list);
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-off_t scif_register_pinned_pages(scif_epd_t epd,
- scif_pinned_pages_t pinned_pages,
- off_t offset, int map_flags)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- s64 computed_offset;
- struct scif_window *window;
- int err;
- size_t len;
- struct device *spdev;
-
- /* Unsupported flags */
- if (map_flags & ~SCIF_MAP_FIXED)
- return -EINVAL;
-
- len = pinned_pages->nr_pages << PAGE_SHIFT;
-
- /*
- * Offset is not page aligned/negative or offset+len
- * wraps around with SCIF_MAP_FIXED.
- */
- if ((map_flags & SCIF_MAP_FIXED) &&
- ((ALIGN(offset, PAGE_SIZE) != offset) ||
- (offset < 0) ||
- (len > LONG_MAX - offset)))
- return -EINVAL;
-
- might_sleep();
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
- /*
- * It is an error to pass pinned_pages to scif_register_pinned_pages()
- * after calling scif_unpin_pages().
- */
- if (!atomic_add_unless(&pinned_pages->ref_count, 1, 0))
- return -EINVAL;
-
- /* Compute the offset for this registration */
- err = scif_get_window_offset(ep, map_flags, offset,
- len, &computed_offset);
- if (err) {
- atomic_sub(1, &pinned_pages->ref_count);
- return err;
- }
-
- /* Allocate and prepare self registration window */
- window = scif_create_window(ep, pinned_pages->nr_pages,
- computed_offset, false);
- if (!window) {
- atomic_sub(1, &pinned_pages->ref_count);
- scif_free_window_offset(ep, NULL, computed_offset);
- return -ENOMEM;
- }
-
- window->pinned_pages = pinned_pages;
- window->nr_pages = pinned_pages->nr_pages;
- window->prot = pinned_pages->prot;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- scif_destroy_window(ep, window);
- return err;
- }
- err = scif_send_alloc_request(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- /* Prepare the remote registration window */
- err = scif_prep_remote_window(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- /* Tell the peer about the new window */
- err = scif_send_scif_register(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- scif_put_peer_dev(spdev);
- /* No further failures expected. Insert new window */
- scif_insert_local_window(window, ep);
- return computed_offset;
-error_unmap:
- scif_destroy_window(ep, window);
- scif_put_peer_dev(spdev);
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_register_pinned_pages);
-
-off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
- int prot, int map_flags)
-{
- scif_pinned_pages_t pinned_pages;
- off_t err;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- s64 computed_offset;
- struct scif_window *window;
- struct mm_struct *mm = NULL;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI register: ep %p addr %p len 0x%lx offset 0x%lx prot 0x%x map_flags 0x%x\n",
- epd, addr, len, offset, prot, map_flags);
- /* Unsupported flags */
- if (map_flags & ~(SCIF_MAP_FIXED | SCIF_MAP_KERNEL))
- return -EINVAL;
-
- /*
- * Offset is not page aligned/negative or offset+len
- * wraps around with SCIF_MAP_FIXED.
- */
- if ((map_flags & SCIF_MAP_FIXED) &&
- ((ALIGN(offset, PAGE_SIZE) != offset) ||
- (offset < 0) ||
- (len > LONG_MAX - offset)))
- return -EINVAL;
-
- /* Unsupported protection requested */
- if (prot & ~(SCIF_PROT_READ | SCIF_PROT_WRITE))
- return -EINVAL;
-
- /* addr/len must be page aligned. len should be non zero */
- if (!len || (ALIGN((u64)addr, PAGE_SIZE) != (u64)addr) ||
- (ALIGN(len, PAGE_SIZE) != len))
- return -EINVAL;
-
- might_sleep();
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- /* Compute the offset for this registration */
- err = scif_get_window_offset(ep, map_flags, offset,
- len >> PAGE_SHIFT, &computed_offset);
- if (err)
- return err;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- scif_free_window_offset(ep, NULL, computed_offset);
- return err;
- }
- /* Allocate and prepare self registration window */
- window = scif_create_window(ep, len >> PAGE_SHIFT,
- computed_offset, false);
- if (!window) {
- scif_free_window_offset(ep, NULL, computed_offset);
- scif_put_peer_dev(spdev);
- return -ENOMEM;
- }
-
- window->nr_pages = len >> PAGE_SHIFT;
-
- err = scif_send_alloc_request(ep, window);
- if (err) {
- scif_destroy_incomplete_window(ep, window);
- scif_put_peer_dev(spdev);
- return err;
- }
-
- if (!(map_flags & SCIF_MAP_KERNEL)) {
- mm = __scif_acquire_mm();
- map_flags |= SCIF_MAP_ULIMIT;
- }
- /* Pin down the pages */
- err = __scif_pin_pages(addr, len, &prot,
- map_flags & (SCIF_MAP_KERNEL | SCIF_MAP_ULIMIT),
- &pinned_pages);
- if (err) {
- scif_destroy_incomplete_window(ep, window);
- __scif_release_mm(mm);
- goto error;
- }
-
- window->pinned_pages = pinned_pages;
- window->prot = pinned_pages->prot;
- window->mm = mm;
-
- /* Prepare the remote registration window */
- err = scif_prep_remote_window(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %ld\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- /* Tell the peer about the new window */
- err = scif_send_scif_register(ep, window);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %ld\n", __func__, __LINE__, err);
- goto error_unmap;
- }
-
- scif_put_peer_dev(spdev);
- /* No further failures expected. Insert new window */
- scif_insert_local_window(window, ep);
- dev_dbg(&ep->remote_dev->sdev->dev,
- "SCIFAPI register: ep %p addr %p len 0x%lx computed_offset 0x%llx\n",
- epd, addr, len, computed_offset);
- return computed_offset;
-error_unmap:
- scif_destroy_window(ep, window);
-error:
- scif_put_peer_dev(spdev);
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %ld\n", __func__, __LINE__, err);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_register);
-
-int
-scif_unregister(scif_epd_t epd, off_t offset, size_t len)
-{
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct scif_window *window = NULL;
- struct scif_rma_req req;
- int nr_pages, err;
- struct device *spdev;
-
- dev_dbg(scif_info.mdev.this_device,
- "SCIFAPI unregister: ep %p offset 0x%lx len 0x%lx\n",
- ep, offset, len);
- /* len must be page aligned. len should be non zero */
- if (!len ||
- (ALIGN((u64)len, PAGE_SIZE) != (u64)len))
- return -EINVAL;
-
- /* Offset is not page aligned or offset+len wraps around */
- if ((ALIGN(offset, PAGE_SIZE) != offset) ||
- (offset < 0) ||
- (len > LONG_MAX - offset))
- return -EINVAL;
-
- err = scif_verify_epd(ep);
- if (err)
- return err;
-
- might_sleep();
- nr_pages = len >> PAGE_SHIFT;
-
- req.out_window = &window;
- req.offset = offset;
- req.prot = 0;
- req.nr_bytes = len;
- req.type = SCIF_WINDOW_FULL;
- req.head = &ep->rma_info.reg_list;
-
- spdev = scif_get_peer_dev(ep->remote_dev);
- if (IS_ERR(spdev)) {
- err = PTR_ERR(spdev);
- return err;
- }
- mutex_lock(&ep->rma_info.rma_lock);
- /* Does a valid window exist? */
- err = scif_query_window(&req);
- if (err) {
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
- goto error;
- }
- /* Unregister all the windows in this range */
- err = scif_rma_list_unregister(window, offset, nr_pages);
- if (err)
- dev_err(&ep->remote_dev->sdev->dev,
- "%s %d err %d\n", __func__, __LINE__, err);
-error:
- mutex_unlock(&ep->rma_info.rma_lock);
- scif_put_peer_dev(spdev);
- return err;
-}
-EXPORT_SYMBOL_GPL(scif_unregister);
+++ /dev/null
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef SCIF_RMA_H
-#define SCIF_RMA_H
-
-#include <linux/intel-iommu.h>
-#include <linux/mmu_notifier.h>
-
-#include "../bus/scif_bus.h"
-
-/* If this bit is set then the mark is a remote fence mark */
-#define SCIF_REMOTE_FENCE_BIT 31
-/* Magic value used to indicate a remote fence request */
-#define SCIF_REMOTE_FENCE BIT_ULL(SCIF_REMOTE_FENCE_BIT)
-
-#define SCIF_MAX_UNALIGNED_BUF_SIZE (1024 * 1024ULL)
-#define SCIF_KMEM_UNALIGNED_BUF_SIZE (SCIF_MAX_UNALIGNED_BUF_SIZE + \
- (L1_CACHE_BYTES << 1))
-
-#define SCIF_IOVA_START_PFN (1)
-#define SCIF_IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
-#define SCIF_DMA_64BIT_PFN SCIF_IOVA_PFN(DMA_BIT_MASK(64))
-#define SCIF_DMA_63BIT_PFN SCIF_IOVA_PFN(DMA_BIT_MASK(63))
-
-/*
- * struct scif_endpt_rma_info - Per Endpoint Remote Memory Access Information
- *
- * @reg_list: List of registration windows for self
- * @remote_reg_list: List of registration windows for peer
- * @iovad: Offset generator
- * @rma_lock: Synchronizes access to self/remote list and also protects the
- * window from being destroyed while RMAs are in progress.
- * @tc_lock: Synchronizes access to temporary cached windows list
- * for SCIF Registration Caching.
- * @mmn_lock: Synchronizes access to the list of MMU notifiers registered
- * @tw_refcount: Keeps track of number of outstanding temporary registered
- * windows created by scif_vreadfrom/scif_vwriteto which have
- * not been destroyed.
- * @tcw_refcount: Same as tw_refcount but for temporary cached windows
- * @tcw_total_pages: Same as tcw_refcount but in terms of pages pinned
- * @mmn_list: MMU notifier so that we can destroy the windows when required
- * @fence_refcount: Keeps track of number of outstanding remote fence
- * requests which have been received by the peer.
- * @dma_chan: DMA channel used for all DMA transfers for this endpoint.
- * @async_list_del: Detect asynchronous list entry deletion
- * @vma_list: List of vmas with remote memory mappings
- * @markwq: Wait queue used for scif_fence_mark/scif_fence_wait
-*/
-struct scif_endpt_rma_info {
- struct list_head reg_list;
- struct list_head remote_reg_list;
- struct iova_domain iovad;
- struct mutex rma_lock;
- spinlock_t tc_lock;
- struct mutex mmn_lock;
- atomic_t tw_refcount;
- atomic_t tcw_refcount;
- atomic_t tcw_total_pages;
- struct list_head mmn_list;
- atomic_t fence_refcount;
- struct dma_chan *dma_chan;
- int async_list_del;
- struct list_head vma_list;
- wait_queue_head_t markwq;
-};
-
-/*
- * struct scif_fence_info - used for tracking fence requests
- *
- * @state: State of this transfer
- * @wq: Fences wait on this queue
- * @dma_mark: Used for storing the DMA mark
- */
-struct scif_fence_info {
- enum scif_msg_state state;
- struct completion comp;
- int dma_mark;
-};
-
-/*
- * struct scif_remote_fence_info - used for tracking remote fence requests
- *
- * @msg: List of SCIF node QP fence messages
- * @list: Link to list of remote fence requests
- */
-struct scif_remote_fence_info {
- struct scifmsg msg;
- struct list_head list;
-};
-
-/*
- * Specifies whether an RMA operation can span across partial windows, a single
- * window or multiple contiguous windows. Mmaps can span across partial windows.
- * Unregistration can span across complete windows. scif_get_pages() can span a
- * single window. A window can also be of type self or peer.
- */
-enum scif_window_type {
- SCIF_WINDOW_PARTIAL,
- SCIF_WINDOW_SINGLE,
- SCIF_WINDOW_FULL,
- SCIF_WINDOW_SELF,
- SCIF_WINDOW_PEER
-};
-
-/* The number of physical addresses that can be stored in a PAGE. */
-#define SCIF_NR_ADDR_IN_PAGE (0x1000 >> 3)
-
-/*
- * struct scif_rma_lookup - RMA lookup data structure for page list transfers
- *
- * Store an array of lookup offsets. Each offset in this array maps
- * one 4K page containing 512 physical addresses i.e. 2MB. 512 such
- * offsets in a 4K page will correspond to 1GB of registered address space.
-
- * @lookup: Array of offsets
- * @offset: DMA offset of lookup array
- */
-struct scif_rma_lookup {
- dma_addr_t *lookup;
- dma_addr_t offset;
-};
-
-/*
- * struct scif_pinned_pages - A set of pinned pages obtained with
- * scif_pin_pages() which could be part of multiple registered
- * windows across different end points.
- *
- * @nr_pages: Number of pages which is defined as a s64 instead of an int
- * to avoid sign extension with buffers >= 2GB
- * @prot: read/write protections
- * @map_flags: Flags specified during the pin operation
- * @ref_count: Reference count bumped in terms of number of pages
- * @magic: A magic value
- * @pages: Array of pointers to struct pages populated with get_user_pages(..)
- */
-struct scif_pinned_pages {
- s64 nr_pages;
- int prot;
- int map_flags;
- atomic_t ref_count;
- u64 magic;
- struct page **pages;
-};
-
-/*
- * struct scif_status - Stores DMA status update information
- *
- * @src_dma_addr: Source buffer DMA address
- * @val: src location for value to be written to the destination
- * @ep: SCIF endpoint
- */
-struct scif_status {
- dma_addr_t src_dma_addr;
- u64 val;
- struct scif_endpt *ep;
-};
-
-/*
- * struct scif_cb_arg - Stores the argument of the callback func
- *
- * @src_dma_addr: Source buffer DMA address
- * @status: DMA status
- * @ep: SCIF endpoint
- */
-struct scif_cb_arg {
- dma_addr_t src_dma_addr;
- struct scif_status *status;
- struct scif_endpt *ep;
-};
-
-/*
- * struct scif_window - Registration Window for Self and Remote
- *
- * @nr_pages: Number of pages which is defined as a s64 instead of an int
- * to avoid sign extension with buffers >= 2GB
- * @nr_contig_chunks: Number of contiguous physical chunks
- * @prot: read/write protections
- * @ref_count: reference count in terms of number of pages
- * @magic: Cookie to detect corruption
- * @offset: registered offset
- * @va_for_temp: va address that this window represents
- * @dma_mark: Used to determine if all DMAs against the window are done
- * @ep: Pointer to EP. Useful for passing EP around with messages to
- avoid expensive list traversals.
- * @list: link to list of windows for the endpoint
- * @type: self or peer window
- * @peer_window: Pointer to peer window. Useful for sending messages to peer
- * without requiring an extra list traversal
- * @unreg_state: unregistration state
- * @offset_freed: True if the offset has been freed
- * @temp: True for temporary windows created via scif_vreadfrom/scif_vwriteto
- * @mm: memory descriptor for the task_struct which initiated the RMA
- * @st: scatter gather table for DMA mappings with IOMMU enabled
- * @pinned_pages: The set of pinned_pages backing this window
- * @alloc_handle: Handle for sending ALLOC_REQ
- * @regwq: Wait Queue for an registration (N)ACK
- * @reg_state: Registration state
- * @unregwq: Wait Queue for an unregistration (N)ACK
- * @dma_addr_lookup: Lookup for physical addresses used for DMA
- * @nr_lookup: Number of entries in lookup
- * @mapped_offset: Offset used to map the window by the peer
- * @dma_addr: Array of physical addresses used for Mgmt node & MIC initiated DMA
- * @num_pages: Array specifying number of pages for each physical address
- */
-struct scif_window {
- s64 nr_pages;
- int nr_contig_chunks;
- int prot;
- int ref_count;
- u64 magic;
- s64 offset;
- unsigned long va_for_temp;
- int dma_mark;
- u64 ep;
- struct list_head list;
- enum scif_window_type type;
- u64 peer_window;
- enum scif_msg_state unreg_state;
- bool offset_freed;
- bool temp;
- struct mm_struct *mm;
- struct sg_table *st;
- union {
- struct {
- struct scif_pinned_pages *pinned_pages;
- struct scif_allocmsg alloc_handle;
- wait_queue_head_t regwq;
- enum scif_msg_state reg_state;
- wait_queue_head_t unregwq;
- };
- struct {
- struct scif_rma_lookup dma_addr_lookup;
- struct scif_rma_lookup num_pages_lookup;
- int nr_lookup;
- dma_addr_t mapped_offset;
- };
- };
- dma_addr_t *dma_addr;
- u64 *num_pages;
-} __packed;
-
-/*
- * scif_mmu_notif - SCIF mmu notifier information
- *
- * @mmu_notifier ep_mmu_notifier: MMU notifier operations
- * @tc_reg_list: List of temp registration windows for self
- * @mm: memory descriptor for the task_struct which initiated the RMA
- * @ep: SCIF endpoint
- * @list: link to list of MMU notifier information
- */
-struct scif_mmu_notif {
-#ifdef CONFIG_MMU_NOTIFIER
- struct mmu_notifier ep_mmu_notifier;
-#endif
- struct list_head tc_reg_list;
- struct mm_struct *mm;
- struct scif_endpt *ep;
- struct list_head list;
-};
-
-enum scif_rma_dir {
- SCIF_LOCAL_TO_REMOTE,
- SCIF_REMOTE_TO_LOCAL
-};
-
-extern struct kmem_cache *unaligned_cache;
-/* Initialize RMA for this EP */
-void scif_rma_ep_init(struct scif_endpt *ep);
-/* Check if epd can be uninitialized */
-int scif_rma_ep_can_uninit(struct scif_endpt *ep);
-/* Obtain a new offset. Callee must grab RMA lock */
-int scif_get_window_offset(struct scif_endpt *ep, int flags,
- s64 offset, int nr_pages, s64 *out_offset);
-/* Free offset. Callee must grab RMA lock */
-void scif_free_window_offset(struct scif_endpt *ep,
- struct scif_window *window, s64 offset);
-/* Create self registration window */
-struct scif_window *scif_create_window(struct scif_endpt *ep, int nr_pages,
- s64 offset, bool temp);
-/* Destroy self registration window.*/
-int scif_destroy_window(struct scif_endpt *ep, struct scif_window *window);
-void scif_unmap_window(struct scif_dev *remote_dev, struct scif_window *window);
-/* Map pages of self window to Aperture/PCI */
-int scif_map_window(struct scif_dev *remote_dev,
- struct scif_window *window);
-/* Unregister a self window */
-int scif_unregister_window(struct scif_window *window);
-/* Destroy remote registration window */
-void
-scif_destroy_remote_window(struct scif_window *window);
-/* remove valid remote memory mappings from process address space */
-void scif_zap_mmaps(int node);
-/* Query if any applications have remote memory mappings */
-bool scif_rma_do_apps_have_mmaps(int node);
-/* Cleanup remote registration lists for zombie endpoints */
-void scif_cleanup_rma_for_zombies(int node);
-/* Reserve a DMA channel for a particular endpoint */
-int scif_reserve_dma_chan(struct scif_endpt *ep);
-/* Setup a DMA mark for an endpoint */
-int _scif_fence_mark(scif_epd_t epd, int *mark);
-int scif_prog_signal(scif_epd_t epd, off_t offset, u64 val,
- enum scif_window_type type);
-void scif_alloc_req(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_alloc_gnt_rej(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_free_virt(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_reg_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg_ack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_unreg_nack(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_munmap(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_mark(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_mark_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_wait(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_wait_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_local(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_remote(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_recv_sig_resp(struct scif_dev *scifdev, struct scifmsg *msg);
-void scif_mmu_notif_handler(struct work_struct *work);
-void scif_rma_handle_remote_fences(void);
-void scif_rma_destroy_windows(void);
-void scif_rma_destroy_tcw_invalid(void);
-int scif_drain_dma_intr(struct scif_hw_dev *sdev, struct dma_chan *chan);
-
-struct scif_window_iter {
- s64 offset;
- int index;
-};
-
-static inline void
-scif_init_window_iter(struct scif_window *window, struct scif_window_iter *iter)
-{
- iter->offset = window->offset;
- iter->index = 0;
-}
-
-dma_addr_t scif_off_to_dma_addr(struct scif_window *window, s64 off,
- size_t *nr_bytes,
- struct scif_window_iter *iter);
-static inline
-dma_addr_t __scif_off_to_dma_addr(struct scif_window *window, s64 off)
-{
- return scif_off_to_dma_addr(window, off, NULL, NULL);
-}
-
-static inline bool scif_unaligned(off_t src_offset, off_t dst_offset)
-{
- src_offset = src_offset & (L1_CACHE_BYTES - 1);
- dst_offset = dst_offset & (L1_CACHE_BYTES - 1);
- return !(src_offset == dst_offset);
-}
-
-/*
- * scif_zalloc:
- * @size: Size of the allocation request.
- *
- * Helper API which attempts to allocate zeroed pages via
- * __get_free_pages(..) first and then falls back on
- * vzalloc(..) if that fails.
- */
-static inline void *scif_zalloc(size_t size)
-{
- void *ret = NULL;
- size_t align = ALIGN(size, PAGE_SIZE);
-
- if (align && get_order(align) < MAX_ORDER)
- ret = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(align));
- return ret ? ret : vzalloc(align);
-}
-
-/*
- * scif_free:
- * @addr: Address to be freed.
- * @size: Size of the allocation.
- * Helper API which frees memory allocated via scif_zalloc().
- */
-static inline void scif_free(void *addr, size_t size)
-{
- size_t align = ALIGN(size, PAGE_SIZE);
-
- if (is_vmalloc_addr(addr))
- vfree(addr);
- else
- free_pages((unsigned long)addr, get_order(align));
-}
-
-static inline void scif_get_window(struct scif_window *window, int nr_pages)
-{
- window->ref_count += nr_pages;
-}
-
-static inline void scif_put_window(struct scif_window *window, int nr_pages)
-{
- window->ref_count -= nr_pages;
-}
-
-static inline void scif_set_window_ref(struct scif_window *window, int nr_pages)
-{
- window->ref_count = nr_pages;
-}
-
-static inline void
-scif_queue_for_cleanup(struct scif_window *window, struct list_head *list)
-{
- spin_lock(&scif_info.rmalock);
- list_add_tail(&window->list, list);
- spin_unlock(&scif_info.rmalock);
- schedule_work(&scif_info.misc_work);
-}
-
-static inline void __scif_rma_destroy_tcw_helper(struct scif_window *window)
-{
- list_del_init(&window->list);
- scif_queue_for_cleanup(window, &scif_info.rma_tc);
-}
-
-static inline bool scif_is_iommu_enabled(void)
-{
-#ifdef CONFIG_INTEL_IOMMU
- return intel_iommu_enabled;
-#else
- return false;
-#endif
-}
-#endif /* SCIF_RMA_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#include "scif_main.h"
-#include <linux/mmu_notifier.h>
-#include <linux/highmem.h>
-
-/*
- * scif_insert_tcw:
- *
- * Insert a temp window to the temp registration list sorted by va_for_temp.
- * RMA lock must be held.
- */
-void scif_insert_tcw(struct scif_window *window, struct list_head *head)
-{
- struct scif_window *curr = NULL;
- struct scif_window *prev = list_entry(head, struct scif_window, list);
- struct list_head *item;
-
- INIT_LIST_HEAD(&window->list);
- /* Compare with tail and if the entry is new tail add it to the end */
- if (!list_empty(head)) {
- curr = list_entry(head->prev, struct scif_window, list);
- if (curr->va_for_temp < window->va_for_temp) {
- list_add_tail(&window->list, head);
- return;
- }
- }
- list_for_each(item, head) {
- curr = list_entry(item, struct scif_window, list);
- if (curr->va_for_temp > window->va_for_temp)
- break;
- prev = curr;
- }
- list_add(&window->list, &prev->list);
-}
-
-/*
- * scif_insert_window:
- *
- * Insert a window to the self registration list sorted by offset.
- * RMA lock must be held.
- */
-void scif_insert_window(struct scif_window *window, struct list_head *head)
-{
- struct scif_window *curr = NULL, *prev = NULL;
- struct list_head *item;
-
- INIT_LIST_HEAD(&window->list);
- list_for_each(item, head) {
- curr = list_entry(item, struct scif_window, list);
- if (curr->offset > window->offset)
- break;
- prev = curr;
- }
- if (!prev)
- list_add(&window->list, head);
- else
- list_add(&window->list, &prev->list);
- scif_set_window_ref(window, window->nr_pages);
-}
-
-/*
- * scif_query_tcw:
- *
- * Query the temp cached registration list of ep for an overlapping window
- * in case of permission mismatch, destroy the previous window. if permissions
- * match and overlap is partial, destroy the window but return the new range
- * RMA lock must be held.
- */
-int scif_query_tcw(struct scif_endpt *ep, struct scif_rma_req *req)
-{
- struct list_head *item, *temp, *head = req->head;
- struct scif_window *window;
- u64 start_va_window, start_va_req = req->va_for_temp;
- u64 end_va_window, end_va_req = start_va_req + req->nr_bytes;
-
- if (!req->nr_bytes)
- return -EINVAL;
- /*
- * Avoid traversing the entire list to find out that there
- * is no entry that matches
- */
- if (!list_empty(head)) {
- window = list_last_entry(head, struct scif_window, list);
- end_va_window = window->va_for_temp +
- (window->nr_pages << PAGE_SHIFT);
- if (start_va_req > end_va_window)
- return -ENXIO;
- }
- list_for_each_safe(item, temp, head) {
- window = list_entry(item, struct scif_window, list);
- start_va_window = window->va_for_temp;
- end_va_window = window->va_for_temp +
- (window->nr_pages << PAGE_SHIFT);
- if (start_va_req < start_va_window &&
- end_va_req < start_va_window)
- break;
- if (start_va_req >= end_va_window)
- continue;
- if ((window->prot & req->prot) == req->prot) {
- if (start_va_req >= start_va_window &&
- end_va_req <= end_va_window) {
- *req->out_window = window;
- return 0;
- }
- /* expand window */
- if (start_va_req < start_va_window) {
- req->nr_bytes +=
- start_va_window - start_va_req;
- req->va_for_temp = start_va_window;
- }
- if (end_va_req >= end_va_window)
- req->nr_bytes += end_va_window - end_va_req;
- }
- /* Destroy the old window to create a new one */
- __scif_rma_destroy_tcw_helper(window);
- break;
- }
- return -ENXIO;
-}
-
-/*
- * scif_query_window:
- *
- * Query the registration list and check if a valid contiguous
- * range of windows exist.
- * RMA lock must be held.
- */
-int scif_query_window(struct scif_rma_req *req)
-{
- struct list_head *item;
- struct scif_window *window;
- s64 end_offset, offset = req->offset;
- u64 tmp_min, nr_bytes_left = req->nr_bytes;
-
- if (!req->nr_bytes)
- return -EINVAL;
-
- list_for_each(item, req->head) {
- window = list_entry(item, struct scif_window, list);
- end_offset = window->offset +
- (window->nr_pages << PAGE_SHIFT);
- if (offset < window->offset)
- /* Offset not found! */
- return -ENXIO;
- if (offset >= end_offset)
- continue;
- /* Check read/write protections. */
- if ((window->prot & req->prot) != req->prot)
- return -EPERM;
- if (nr_bytes_left == req->nr_bytes)
- /* Store the first window */
- *req->out_window = window;
- tmp_min = min((u64)end_offset - offset, nr_bytes_left);
- nr_bytes_left -= tmp_min;
- offset += tmp_min;
- /*
- * Range requested encompasses
- * multiple windows contiguously.
- */
- if (!nr_bytes_left) {
- /* Done for partial window */
- if (req->type == SCIF_WINDOW_PARTIAL ||
- req->type == SCIF_WINDOW_SINGLE)
- return 0;
- /* Extra logic for full windows */
- if (offset == end_offset)
- /* Spanning multiple whole windows */
- return 0;
- /* Not spanning multiple whole windows */
- return -ENXIO;
- }
- if (req->type == SCIF_WINDOW_SINGLE)
- break;
- }
- dev_err(scif_info.mdev.this_device,
- "%s %d ENXIO\n", __func__, __LINE__);
- return -ENXIO;
-}
-
-/*
- * scif_rma_list_unregister:
- *
- * Traverse the self registration list starting from window:
- * 1) Call scif_unregister_window(..)
- * RMA lock must be held.
- */
-int scif_rma_list_unregister(struct scif_window *window,
- s64 offset, int nr_pages)
-{
- struct scif_endpt *ep = (struct scif_endpt *)window->ep;
- struct list_head *head = &ep->rma_info.reg_list;
- s64 end_offset;
- int err = 0;
- int loop_nr_pages;
- struct scif_window *_window;
-
- list_for_each_entry_safe_from(window, _window, head, list) {
- end_offset = window->offset + (window->nr_pages << PAGE_SHIFT);
- loop_nr_pages = min((int)((end_offset - offset) >> PAGE_SHIFT),
- nr_pages);
- err = scif_unregister_window(window);
- if (err)
- return err;
- nr_pages -= loop_nr_pages;
- offset += (loop_nr_pages << PAGE_SHIFT);
- if (!nr_pages)
- break;
- }
- return 0;
-}
-
-/*
- * scif_unmap_all_window:
- *
- * Traverse all the windows in the self registration list and:
- * 1) Delete any DMA mappings created
- */
-void scif_unmap_all_windows(scif_epd_t epd)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct list_head *head = &ep->rma_info.reg_list;
-
- mutex_lock(&ep->rma_info.rma_lock);
- list_for_each_safe(item, tmp, head) {
- window = list_entry(item, struct scif_window, list);
- scif_unmap_window(ep->remote_dev, window);
- }
- mutex_unlock(&ep->rma_info.rma_lock);
-}
-
-/*
- * scif_unregister_all_window:
- *
- * Traverse all the windows in the self registration list and:
- * 1) Call scif_unregister_window(..)
- * RMA lock must be held.
- */
-int scif_unregister_all_windows(scif_epd_t epd)
-{
- struct list_head *item, *tmp;
- struct scif_window *window;
- struct scif_endpt *ep = (struct scif_endpt *)epd;
- struct list_head *head = &ep->rma_info.reg_list;
- int err = 0;
-
- mutex_lock(&ep->rma_info.rma_lock);
-retry:
- item = NULL;
- tmp = NULL;
- list_for_each_safe(item, tmp, head) {
- window = list_entry(item, struct scif_window, list);
- ep->rma_info.async_list_del = 0;
- err = scif_unregister_window(window);
- if (err)
- dev_err(scif_info.mdev.this_device,
- "%s %d err %d\n",
- __func__, __LINE__, err);
- /*
- * Need to restart list traversal if there has been
- * an asynchronous list entry deletion.
- */
- if (READ_ONCE(ep->rma_info.async_list_del))
- goto retry;
- }
- mutex_unlock(&ep->rma_info.rma_lock);
- if (!list_empty(&ep->rma_info.mmn_list)) {
- spin_lock(&scif_info.rmalock);
- list_add_tail(&ep->mmu_list, &scif_info.mmu_notif_cleanup);
- spin_unlock(&scif_info.rmalock);
- schedule_work(&scif_info.mmu_notif_work);
- }
- return err;
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Intel SCIF driver.
- */
-#ifndef SCIF_RMA_LIST_H
-#define SCIF_RMA_LIST_H
-
-/*
- * struct scif_rma_req - Self Registration list RMA Request query
- *
- * @out_window - Returns the window if found
- * @offset: Starting offset
- * @nr_bytes: number of bytes
- * @prot: protection requested i.e. read or write or both
- * @type: Specify single, partial or multiple windows
- * @head: Head of list on which to search
- * @va_for_temp: VA for searching temporary cached windows
- */
-struct scif_rma_req {
- struct scif_window **out_window;
- union {
- s64 offset;
- unsigned long va_for_temp;
- };
- size_t nr_bytes;
- int prot;
- enum scif_window_type type;
- struct list_head *head;
-};
-
-/* Insert */
-void scif_insert_window(struct scif_window *window, struct list_head *head);
-void scif_insert_tcw(struct scif_window *window,
- struct list_head *head);
-/* Query */
-int scif_query_window(struct scif_rma_req *request);
-int scif_query_tcw(struct scif_endpt *ep, struct scif_rma_req *request);
-/* Called from close to unregister all self windows */
-int scif_unregister_all_windows(scif_epd_t epd);
-void scif_unmap_all_windows(scif_epd_t epd);
-/* Traverse list and unregister */
-int scif_rma_list_unregister(struct scif_window *window, s64 offset,
- int nr_pages);
-#endif /* SCIF_RMA_LIST_H */
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile - Intel MIC Linux driver.
-# Copyright(c) 2016, Intel Corporation.
-#
-obj-$(CONFIG_VOP) := vop.o
-
-vop-objs += vop_main.o
-vop-objs += vop_debugfs.o
-vop-objs += vop_vringh.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-#include "vop_main.h"
-
-static int vop_dp_show(struct seq_file *s, void *pos)
-{
- struct mic_device_desc *d;
- struct mic_device_ctrl *dc;
- struct mic_vqconfig *vqconfig;
- __u32 *features;
- __u8 *config;
- struct vop_info *vi = s->private;
- struct vop_device *vpdev = vi->vpdev;
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
- int j, k;
-
- seq_printf(s, "Bootparam: magic 0x%x\n",
- bootparam->magic);
- seq_printf(s, "Bootparam: h2c_config_db %d\n",
- bootparam->h2c_config_db);
- seq_printf(s, "Bootparam: node_id %d\n",
- bootparam->node_id);
- seq_printf(s, "Bootparam: c2h_scif_db %d\n",
- bootparam->c2h_scif_db);
- seq_printf(s, "Bootparam: h2c_scif_db %d\n",
- bootparam->h2c_scif_db);
- seq_printf(s, "Bootparam: scif_host_dma_addr 0x%llx\n",
- bootparam->scif_host_dma_addr);
- seq_printf(s, "Bootparam: scif_card_dma_addr 0x%llx\n",
- bootparam->scif_card_dma_addr);
-
- for (j = sizeof(*bootparam);
- j < MIC_DP_SIZE; j += mic_total_desc_size(d)) {
- d = (void *)bootparam + j;
- dc = (void *)d + mic_aligned_desc_size(d);
-
- /* end of list */
- if (d->type == 0)
- break;
-
- if (d->type == -1)
- continue;
-
- seq_printf(s, "Type %d ", d->type);
- seq_printf(s, "Num VQ %d ", d->num_vq);
- seq_printf(s, "Feature Len %d\n", d->feature_len);
- seq_printf(s, "Config Len %d ", d->config_len);
- seq_printf(s, "Shutdown Status %d\n", d->status);
-
- for (k = 0; k < d->num_vq; k++) {
- vqconfig = mic_vq_config(d) + k;
- seq_printf(s, "vqconfig[%d]: ", k);
- seq_printf(s, "address 0x%llx ",
- vqconfig->address);
- seq_printf(s, "num %d ", vqconfig->num);
- seq_printf(s, "used address 0x%llx\n",
- vqconfig->used_address);
- }
-
- features = (__u32 *)mic_vq_features(d);
- seq_printf(s, "Features: Host 0x%x ", features[0]);
- seq_printf(s, "Guest 0x%x\n", features[1]);
-
- config = mic_vq_configspace(d);
- for (k = 0; k < d->config_len; k++)
- seq_printf(s, "config[%d]=%d\n", k, config[k]);
-
- seq_puts(s, "Device control:\n");
- seq_printf(s, "Config Change %d ", dc->config_change);
- seq_printf(s, "Vdev reset %d\n", dc->vdev_reset);
- seq_printf(s, "Guest Ack %d ", dc->guest_ack);
- seq_printf(s, "Host ack %d\n", dc->host_ack);
- seq_printf(s, "Used address updated %d ",
- dc->used_address_updated);
- seq_printf(s, "Vdev 0x%llx\n", dc->vdev);
- seq_printf(s, "c2h doorbell %d ", dc->c2h_vdev_db);
- seq_printf(s, "h2c doorbell %d\n", dc->h2c_vdev_db);
- }
- schedule_work(&vi->hotplug_work);
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(vop_dp);
-
-static int vop_vdev_info_show(struct seq_file *s, void *unused)
-{
- struct vop_info *vi = s->private;
- struct list_head *pos, *tmp;
- struct vop_vdev *vdev;
- int i, j;
-
- mutex_lock(&vi->vop_mutex);
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev = list_entry(pos, struct vop_vdev, list);
- seq_printf(s, "VDEV type %d state %s in %ld out %ld in_dma %ld out_dma %ld\n",
- vdev->virtio_id,
- vop_vdevup(vdev) ? "UP" : "DOWN",
- vdev->in_bytes,
- vdev->out_bytes,
- vdev->in_bytes_dma,
- vdev->out_bytes_dma);
- for (i = 0; i < MIC_MAX_VRINGS; i++) {
- struct vring_desc *desc;
- struct vring_avail *avail;
- struct vring_used *used;
- struct vop_vringh *vvr = &vdev->vvr[i];
- struct vringh *vrh = &vvr->vrh;
- int num = vrh->vring.num;
-
- if (!num)
- continue;
- desc = vrh->vring.desc;
- seq_printf(s, "vring i %d avail_idx %d",
- i, vvr->vring.info->avail_idx & (num - 1));
- seq_printf(s, " vring i %d avail_idx %d\n",
- i, vvr->vring.info->avail_idx);
- seq_printf(s, "vrh i %d weak_barriers %d",
- i, vrh->weak_barriers);
- seq_printf(s, " last_avail_idx %d last_used_idx %d",
- vrh->last_avail_idx, vrh->last_used_idx);
- seq_printf(s, " completed %d\n", vrh->completed);
- for (j = 0; j < num; j++) {
- seq_printf(s, "desc[%d] addr 0x%llx len %d",
- j, desc->addr, desc->len);
- seq_printf(s, " flags 0x%x next %d\n",
- desc->flags, desc->next);
- desc++;
- }
- avail = vrh->vring.avail;
- seq_printf(s, "avail flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, avail->flags),
- vringh16_to_cpu(vrh,
- avail->idx) & (num - 1));
- seq_printf(s, "avail flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, avail->flags),
- vringh16_to_cpu(vrh, avail->idx));
- for (j = 0; j < num; j++)
- seq_printf(s, "avail ring[%d] %d\n",
- j, avail->ring[j]);
- used = vrh->vring.used;
- seq_printf(s, "used flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, used->flags),
- vringh16_to_cpu(vrh, used->idx) & (num - 1));
- seq_printf(s, "used flags 0x%x idx %d\n",
- vringh16_to_cpu(vrh, used->flags),
- vringh16_to_cpu(vrh, used->idx));
- for (j = 0; j < num; j++)
- seq_printf(s, "used ring[%d] id %d len %d\n",
- j, vringh32_to_cpu(vrh,
- used->ring[j].id),
- vringh32_to_cpu(vrh,
- used->ring[j].len));
- }
- }
- mutex_unlock(&vi->vop_mutex);
-
- return 0;
-}
-
-DEFINE_SHOW_ATTRIBUTE(vop_vdev_info);
-
-void vop_init_debugfs(struct vop_info *vi)
-{
- char name[16];
-
- snprintf(name, sizeof(name), "%s%d", KBUILD_MODNAME, vi->vpdev->dnode);
- vi->dbg = debugfs_create_dir(name, NULL);
- debugfs_create_file("dp", 0444, vi->dbg, vi, &vop_dp_fops);
- debugfs_create_file("vdev_info", 0444, vi->dbg, vi, &vop_vdev_info_fops);
-}
-
-void vop_exit_debugfs(struct vop_info *vi)
-{
- debugfs_remove_recursive(vi->dbg);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Adapted from:
- *
- * virtio for kvm on s390
- *
- * Copyright IBM Corp. 2008
- *
- * Author(s): Christian Borntraeger <borntraeger@de.ibm.com>
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/dma-mapping.h>
-#include <linux/io-64-nonatomic-lo-hi.h>
-
-#include "vop_main.h"
-
-#define VOP_MAX_VRINGS 4
-
-/*
- * _vop_vdev - Allocated per virtio device instance injected by the peer.
- *
- * @vdev: Virtio device
- * @desc: Virtio device page descriptor
- * @dc: Virtio device control
- * @vpdev: VOP device which is the parent for this virtio device
- * @vr: Buffer for accessing the VRING
- * @used_virt: Virtual address of used ring
- * @used: DMA address of used ring
- * @used_size: Size of the used buffer
- * @reset_done: Track whether VOP reset is complete
- * @virtio_cookie: Cookie returned upon requesting a interrupt
- * @c2h_vdev_db: The doorbell used by the guest to interrupt the host
- * @h2c_vdev_db: The doorbell used by the host to interrupt the guest
- * @dnode: The destination node
- */
-struct _vop_vdev {
- struct virtio_device vdev;
- struct mic_device_desc __iomem *desc;
- struct mic_device_ctrl __iomem *dc;
- struct vop_device *vpdev;
- void __iomem *vr[VOP_MAX_VRINGS];
- void *used_virt[VOP_MAX_VRINGS];
- dma_addr_t used[VOP_MAX_VRINGS];
- int used_size[VOP_MAX_VRINGS];
- struct completion reset_done;
- struct mic_irq *virtio_cookie;
- int c2h_vdev_db;
- int h2c_vdev_db;
- int dnode;
-};
-
-#define to_vopvdev(vd) container_of(vd, struct _vop_vdev, vdev)
-
-#define _vop_aligned_desc_size(d) __mic_align(_vop_desc_size(d), 8)
-
-/* Helper API to obtain the parent of the virtio device */
-static inline struct device *_vop_dev(struct _vop_vdev *vdev)
-{
- return vdev->vdev.dev.parent;
-}
-
-static inline unsigned _vop_desc_size(struct mic_device_desc __iomem *desc)
-{
- return sizeof(*desc)
- + ioread8(&desc->num_vq) * sizeof(struct mic_vqconfig)
- + ioread8(&desc->feature_len) * 2
- + ioread8(&desc->config_len);
-}
-
-static inline struct mic_vqconfig __iomem *
-_vop_vq_config(struct mic_device_desc __iomem *desc)
-{
- return (struct mic_vqconfig __iomem *)(desc + 1);
-}
-
-static inline u8 __iomem *
-_vop_vq_features(struct mic_device_desc __iomem *desc)
-{
- return (u8 __iomem *)(_vop_vq_config(desc) + ioread8(&desc->num_vq));
-}
-
-static inline u8 __iomem *
-_vop_vq_configspace(struct mic_device_desc __iomem *desc)
-{
- return _vop_vq_features(desc) + ioread8(&desc->feature_len) * 2;
-}
-
-static inline unsigned
-_vop_total_desc_size(struct mic_device_desc __iomem *desc)
-{
- return _vop_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl);
-}
-
-/* This gets the device's feature bits. */
-static u64 vop_get_features(struct virtio_device *vdev)
-{
- unsigned int i, bits;
- u64 features = 0;
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
- u8 __iomem *in_features = _vop_vq_features(desc);
- int feature_len = ioread8(&desc->feature_len);
-
- bits = min_t(unsigned, feature_len, sizeof(vdev->features)) * 8;
- for (i = 0; i < bits; i++)
- if (ioread8(&in_features[i / 8]) & (BIT(i % 8)))
- features |= BIT_ULL(i);
-
- return features;
-}
-
-static void vop_transport_features(struct virtio_device *vdev)
-{
- /*
- * Packed ring isn't enabled on virtio_vop for now,
- * because virtio_vop uses vring_new_virtqueue() which
- * creates virtio rings on preallocated memory.
- */
- __virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
- __virtio_set_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
-}
-
-static int vop_finalize_features(struct virtio_device *vdev)
-{
- unsigned int i, bits;
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
- u8 feature_len = ioread8(&desc->feature_len);
- /* Second half of bitmap is features we accept. */
- u8 __iomem *out_features =
- _vop_vq_features(desc) + feature_len;
-
- /* Give virtio_ring a chance to accept features. */
- vring_transport_features(vdev);
-
- /* Give virtio_vop a chance to accept features. */
- vop_transport_features(vdev);
-
- memset_io(out_features, 0, feature_len);
- bits = min_t(unsigned, feature_len,
- sizeof(vdev->features)) * 8;
- for (i = 0; i < bits; i++) {
- if (__virtio_test_bit(vdev, i))
- iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)),
- &out_features[i / 8]);
- }
- return 0;
-}
-
-/*
- * Reading and writing elements in config space
- */
-static void vop_get(struct virtio_device *vdev, unsigned int offset,
- void *buf, unsigned len)
-{
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-
- if (offset + len > ioread8(&desc->config_len))
- return;
- memcpy_fromio(buf, _vop_vq_configspace(desc) + offset, len);
-}
-
-static void vop_set(struct virtio_device *vdev, unsigned int offset,
- const void *buf, unsigned len)
-{
- struct mic_device_desc __iomem *desc = to_vopvdev(vdev)->desc;
-
- if (offset + len > ioread8(&desc->config_len))
- return;
- memcpy_toio(_vop_vq_configspace(desc) + offset, buf, len);
-}
-
-/*
- * The operations to get and set the status word just access the status
- * field of the device descriptor. set_status also interrupts the host
- * to tell about status changes.
- */
-static u8 vop_get_status(struct virtio_device *vdev)
-{
- return ioread8(&to_vopvdev(vdev)->desc->status);
-}
-
-static void vop_set_status(struct virtio_device *dev, u8 status)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct vop_device *vpdev = vdev->vpdev;
-
- if (!status)
- return;
- iowrite8(status, &vdev->desc->status);
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-}
-
-/* Inform host on a virtio device reset and wait for ack from host */
-static void vop_reset_inform_host(struct virtio_device *dev)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct mic_device_ctrl __iomem *dc = vdev->dc;
- struct vop_device *vpdev = vdev->vpdev;
- int retry;
-
- iowrite8(0, &dc->host_ack);
- iowrite8(1, &dc->vdev_reset);
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
-
- /* Wait till host completes all card accesses and acks the reset */
- for (retry = 100; retry--;) {
- if (ioread8(&dc->host_ack))
- break;
- msleep(100);
- }
-
- dev_dbg(_vop_dev(vdev), "%s: retry: %d\n", __func__, retry);
-
- /* Reset status to 0 in case we timed out */
- iowrite8(0, &vdev->desc->status);
-}
-
-static void vop_reset(struct virtio_device *dev)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
-
- dev_dbg(_vop_dev(vdev), "%s: virtio id %d\n",
- __func__, dev->id.device);
-
- vop_reset_inform_host(dev);
- complete_all(&vdev->reset_done);
-}
-
-/*
- * The virtio_ring code calls this API when it wants to notify the Host.
- */
-static bool vop_notify(struct virtqueue *vq)
-{
- struct _vop_vdev *vdev = vq->priv;
- struct vop_device *vpdev = vdev->vpdev;
-
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
- return true;
-}
-
-static void vop_del_vq(struct virtqueue *vq, int n)
-{
- struct _vop_vdev *vdev = to_vopvdev(vq->vdev);
- struct vop_device *vpdev = vdev->vpdev;
-
- dma_unmap_single(&vpdev->dev, vdev->used[n],
- vdev->used_size[n], DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vdev->used_virt[n],
- get_order(vdev->used_size[n]));
- vring_del_virtqueue(vq);
- vpdev->hw_ops->unmap(vpdev, vdev->vr[n]);
- vdev->vr[n] = NULL;
-}
-
-static void vop_del_vqs(struct virtio_device *dev)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct virtqueue *vq, *n;
- int idx = 0;
-
- dev_dbg(_vop_dev(vdev), "%s\n", __func__);
-
- list_for_each_entry_safe(vq, n, &dev->vqs, list)
- vop_del_vq(vq, idx++);
-}
-
-static struct virtqueue *vop_new_virtqueue(unsigned int index,
- unsigned int num,
- struct virtio_device *vdev,
- bool context,
- void *pages,
- bool (*notify)(struct virtqueue *vq),
- void (*callback)(struct virtqueue *vq),
- const char *name,
- void *used)
-{
- bool weak_barriers = false;
- struct vring vring;
-
- vring_init(&vring, num, pages, MIC_VIRTIO_RING_ALIGN);
- vring.used = used;
-
- return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
- notify, callback, name);
-}
-
-/*
- * This routine will assign vring's allocated in host/io memory. Code in
- * virtio_ring.c however continues to access this io memory as if it were local
- * memory without io accessors.
- */
-static struct virtqueue *vop_find_vq(struct virtio_device *dev,
- unsigned index,
- void (*callback)(struct virtqueue *vq),
- const char *name, bool ctx)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct vop_device *vpdev = vdev->vpdev;
- struct mic_vqconfig __iomem *vqconfig;
- struct mic_vqconfig config;
- struct virtqueue *vq;
- void __iomem *va;
- struct _mic_vring_info __iomem *info;
- void *used;
- int vr_size, _vr_size, err, magic;
- u8 type = ioread8(&vdev->desc->type);
-
- if (index >= ioread8(&vdev->desc->num_vq))
- return ERR_PTR(-ENOENT);
-
- if (!name)
- return ERR_PTR(-ENOENT);
-
- /* First assign the vring's allocated in host memory */
- vqconfig = _vop_vq_config(vdev->desc) + index;
- memcpy_fromio(&config, vqconfig, sizeof(config));
- _vr_size = round_up(vring_size(le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN), 4);
- vr_size = PAGE_ALIGN(_vr_size + sizeof(struct _mic_vring_info));
- va = vpdev->hw_ops->remap(vpdev, le64_to_cpu(config.address), vr_size);
- if (!va)
- return ERR_PTR(-ENOMEM);
- vdev->vr[index] = va;
- memset_io(va, 0x0, _vr_size);
-
- info = va + _vr_size;
- magic = ioread32(&info->magic);
-
- if (WARN(magic != MIC_MAGIC + type + index, "magic mismatch")) {
- err = -EIO;
- goto unmap;
- }
-
- vdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 +
- sizeof(struct vring_used_elem) *
- le16_to_cpu(config.num));
- used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(vdev->used_size[index]));
- vdev->used_virt[index] = used;
- if (!used) {
- err = -ENOMEM;
- dev_err(_vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto unmap;
- }
-
- vq = vop_new_virtqueue(index, le16_to_cpu(config.num), dev, ctx,
- (void __force *)va, vop_notify, callback,
- name, used);
- if (!vq) {
- err = -ENOMEM;
- goto free_used;
- }
-
- vdev->used[index] = dma_map_single(&vpdev->dev, used,
- vdev->used_size[index],
- DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&vpdev->dev, vdev->used[index])) {
- err = -ENOMEM;
- dev_err(_vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto del_vq;
- }
- writeq(vdev->used[index], &vqconfig->used_address);
-
- vq->priv = vdev;
- return vq;
-del_vq:
- vring_del_virtqueue(vq);
-free_used:
- free_pages((unsigned long)used,
- get_order(vdev->used_size[index]));
-unmap:
- vpdev->hw_ops->unmap(vpdev, vdev->vr[index]);
- return ERR_PTR(err);
-}
-
-static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
- struct virtqueue *vqs[],
- vq_callback_t *callbacks[],
- const char * const names[], const bool *ctx,
- struct irq_affinity *desc)
-{
- struct _vop_vdev *vdev = to_vopvdev(dev);
- struct vop_device *vpdev = vdev->vpdev;
- struct mic_device_ctrl __iomem *dc = vdev->dc;
- int i, err, retry, queue_idx = 0;
-
- /* We must have this many virtqueues. */
- if (nvqs > ioread8(&vdev->desc->num_vq))
- return -ENOENT;
-
- for (i = 0; i < nvqs; ++i) {
- if (!names[i]) {
- vqs[i] = NULL;
- continue;
- }
-
- dev_dbg(_vop_dev(vdev), "%s: %d: %s\n",
- __func__, i, names[i]);
- vqs[i] = vop_find_vq(dev, queue_idx++, callbacks[i], names[i],
- ctx ? ctx[i] : false);
- if (IS_ERR(vqs[i])) {
- err = PTR_ERR(vqs[i]);
- goto error;
- }
- }
-
- iowrite8(1, &dc->used_address_updated);
- /*
- * Send an interrupt to the host to inform it that used
- * rings have been re-assigned.
- */
- vpdev->hw_ops->send_intr(vpdev, vdev->c2h_vdev_db);
- for (retry = 100; --retry;) {
- if (!ioread8(&dc->used_address_updated))
- break;
- msleep(100);
- }
-
- dev_dbg(_vop_dev(vdev), "%s: retry: %d\n", __func__, retry);
- if (!retry) {
- err = -ENODEV;
- goto error;
- }
-
- return 0;
-error:
- vop_del_vqs(dev);
- return err;
-}
-
-/*
- * The config ops structure as defined by virtio config
- */
-static const struct virtio_config_ops vop_vq_config_ops = {
- .get_features = vop_get_features,
- .finalize_features = vop_finalize_features,
- .get = vop_get,
- .set = vop_set,
- .get_status = vop_get_status,
- .set_status = vop_set_status,
- .reset = vop_reset,
- .find_vqs = vop_find_vqs,
- .del_vqs = vop_del_vqs,
-};
-
-static irqreturn_t vop_virtio_intr_handler(int irq, void *data)
-{
- struct _vop_vdev *vdev = data;
- struct vop_device *vpdev = vdev->vpdev;
- struct virtqueue *vq;
-
- vpdev->hw_ops->ack_interrupt(vpdev, vdev->h2c_vdev_db);
- list_for_each_entry(vq, &vdev->vdev.vqs, list)
- vring_interrupt(0, vq);
-
- return IRQ_HANDLED;
-}
-
-static void vop_virtio_release_dev(struct device *_d)
-{
- struct virtio_device *vdev =
- container_of(_d, struct virtio_device, dev);
- struct _vop_vdev *vop_vdev =
- container_of(vdev, struct _vop_vdev, vdev);
-
- kfree(vop_vdev);
-}
-
-/*
- * adds a new device and register it with virtio
- * appropriate drivers are loaded by the device model
- */
-static int _vop_add_device(struct mic_device_desc __iomem *d,
- unsigned int offset, struct vop_device *vpdev,
- int dnode)
-{
- struct _vop_vdev *vdev, *reg_dev = NULL;
- int ret;
- u8 type = ioread8(&d->type);
-
- vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
- if (!vdev)
- return -ENOMEM;
-
- vdev->vpdev = vpdev;
- vdev->vdev.dev.parent = &vpdev->dev;
- vdev->vdev.dev.release = vop_virtio_release_dev;
- vdev->vdev.id.device = type;
- vdev->vdev.config = &vop_vq_config_ops;
- vdev->desc = d;
- vdev->dc = (void __iomem *)d + _vop_aligned_desc_size(d);
- vdev->dnode = dnode;
- vdev->vdev.priv = (void *)(unsigned long)dnode;
- init_completion(&vdev->reset_done);
-
- vdev->h2c_vdev_db = vpdev->hw_ops->next_db(vpdev);
- vdev->virtio_cookie = vpdev->hw_ops->request_irq(vpdev,
- vop_virtio_intr_handler, "virtio intr",
- vdev, vdev->h2c_vdev_db);
- if (IS_ERR(vdev->virtio_cookie)) {
- ret = PTR_ERR(vdev->virtio_cookie);
- goto kfree;
- }
- iowrite8((u8)vdev->h2c_vdev_db, &vdev->dc->h2c_vdev_db);
- vdev->c2h_vdev_db = ioread8(&vdev->dc->c2h_vdev_db);
-
- ret = register_virtio_device(&vdev->vdev);
- reg_dev = vdev;
- if (ret) {
- dev_err(_vop_dev(vdev),
- "Failed to register vop device %u type %u\n",
- offset, type);
- goto free_irq;
- }
- writeq((unsigned long)vdev, &vdev->dc->vdev);
- dev_dbg(_vop_dev(vdev), "%s: registered vop device %u type %u vdev %p\n",
- __func__, offset, type, vdev);
-
- return 0;
-
-free_irq:
- vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
-kfree:
- if (reg_dev)
- put_device(&vdev->vdev.dev);
- else
- kfree(vdev);
- return ret;
-}
-
-/*
- * match for a vop device with a specific desc pointer
- */
-static int vop_match_desc(struct device *dev, void *data)
-{
- struct virtio_device *_dev = dev_to_virtio(dev);
- struct _vop_vdev *vdev = to_vopvdev(_dev);
-
- return vdev->desc == (void __iomem *)data;
-}
-
-static struct _vop_vdev *vop_dc_to_vdev(struct mic_device_ctrl __iomem *dc)
-{
- return (struct _vop_vdev *)(unsigned long)readq(&dc->vdev);
-}
-
-static void _vop_handle_config_change(struct mic_device_desc __iomem *d,
- unsigned int offset,
- struct vop_device *vpdev)
-{
- struct mic_device_ctrl __iomem *dc
- = (void __iomem *)d + _vop_aligned_desc_size(d);
- struct _vop_vdev *vdev = vop_dc_to_vdev(dc);
-
- if (ioread8(&dc->config_change) != MIC_VIRTIO_PARAM_CONFIG_CHANGED)
- return;
-
- dev_dbg(&vpdev->dev, "%s %d\n", __func__, __LINE__);
- virtio_config_changed(&vdev->vdev);
- iowrite8(1, &dc->guest_ack);
-}
-
-/*
- * removes a virtio device if a hot remove event has been
- * requested by the host.
- */
-static int _vop_remove_device(struct mic_device_desc __iomem *d,
- unsigned int offset, struct vop_device *vpdev)
-{
- struct mic_device_ctrl __iomem *dc
- = (void __iomem *)d + _vop_aligned_desc_size(d);
- struct _vop_vdev *vdev = vop_dc_to_vdev(dc);
- u8 status;
- int ret = -1;
-
- if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) {
- struct device *dev = get_device(&vdev->vdev.dev);
-
- dev_dbg(&vpdev->dev,
- "%s %d config_change %d type %d vdev %p\n",
- __func__, __LINE__,
- ioread8(&dc->config_change), ioread8(&d->type), vdev);
- status = ioread8(&d->status);
- reinit_completion(&vdev->reset_done);
- unregister_virtio_device(&vdev->vdev);
- vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
- iowrite8(-1, &dc->h2c_vdev_db);
- if (status & VIRTIO_CONFIG_S_DRIVER_OK)
- wait_for_completion(&vdev->reset_done);
- put_device(dev);
- iowrite8(1, &dc->guest_ack);
- dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n",
- __func__, __LINE__, ioread8(&dc->guest_ack));
- iowrite8(-1, &d->type);
- ret = 0;
- }
- return ret;
-}
-
-#define REMOVE_DEVICES true
-
-static void _vop_scan_devices(void __iomem *dp, struct vop_device *vpdev,
- bool remove, int dnode)
-{
- s8 type;
- unsigned int i;
- struct mic_device_desc __iomem *d;
- struct mic_device_ctrl __iomem *dc;
- struct device *dev;
-
- for (i = sizeof(struct mic_bootparam);
- i < MIC_DP_SIZE; i += _vop_total_desc_size(d)) {
- d = dp + i;
- dc = (void __iomem *)d + _vop_aligned_desc_size(d);
- /*
- * This read barrier is paired with the corresponding write
- * barrier on the host which is inserted before adding or
- * removing a virtio device descriptor, by updating the type.
- */
- rmb();
- type = ioread8(&d->type);
-
- /* end of list */
- if (type == 0)
- break;
-
- if (type == -1)
- continue;
-
- /* device already exists */
- dev = device_find_child(&vpdev->dev, (void __force *)d,
- vop_match_desc);
- if (dev) {
- if (remove)
- iowrite8(MIC_VIRTIO_PARAM_DEV_REMOVE,
- &dc->config_change);
- put_device(dev);
- _vop_handle_config_change(d, i, vpdev);
- _vop_remove_device(d, i, vpdev);
- if (remove) {
- iowrite8(0, &dc->config_change);
- iowrite8(0, &dc->guest_ack);
- }
- continue;
- }
-
- /* new device */
- dev_dbg(&vpdev->dev, "%s %d Adding new virtio device %p\n",
- __func__, __LINE__, d);
- if (!remove)
- _vop_add_device(d, i, vpdev, dnode);
- }
-}
-
-static void vop_scan_devices(struct vop_info *vi,
- struct vop_device *vpdev, bool remove)
-{
- void __iomem *dp = vpdev->hw_ops->get_remote_dp(vpdev);
-
- if (!dp)
- return;
- mutex_lock(&vi->vop_mutex);
- _vop_scan_devices(dp, vpdev, remove, vpdev->dnode);
- mutex_unlock(&vi->vop_mutex);
-}
-
-/*
- * vop_hotplug_device tries to find changes in the device page.
- */
-static void vop_hotplug_devices(struct work_struct *work)
-{
- struct vop_info *vi = container_of(work, struct vop_info,
- hotplug_work);
-
- vop_scan_devices(vi, vi->vpdev, !REMOVE_DEVICES);
-}
-
-/*
- * Interrupt handler for hot plug/config changes etc.
- */
-static irqreturn_t vop_extint_handler(int irq, void *data)
-{
- struct vop_info *vi = data;
- struct mic_bootparam __iomem *bp;
- struct vop_device *vpdev = vi->vpdev;
-
- bp = vpdev->hw_ops->get_remote_dp(vpdev);
- dev_dbg(&vpdev->dev, "%s %d hotplug work\n",
- __func__, __LINE__);
- vpdev->hw_ops->ack_interrupt(vpdev, ioread8(&bp->h2c_config_db));
- schedule_work(&vi->hotplug_work);
- return IRQ_HANDLED;
-}
-
-static int vop_driver_probe(struct vop_device *vpdev)
-{
- struct vop_info *vi;
- int rc;
-
- vi = kzalloc(sizeof(*vi), GFP_KERNEL);
- if (!vi) {
- rc = -ENOMEM;
- goto exit;
- }
- dev_set_drvdata(&vpdev->dev, vi);
- vi->vpdev = vpdev;
-
- mutex_init(&vi->vop_mutex);
- INIT_WORK(&vi->hotplug_work, vop_hotplug_devices);
- if (vpdev->dnode) {
- rc = vop_host_init(vi);
- if (rc < 0)
- goto free;
- } else {
- struct mic_bootparam __iomem *bootparam;
-
- vop_scan_devices(vi, vpdev, !REMOVE_DEVICES);
-
- vi->h2c_config_db = vpdev->hw_ops->next_db(vpdev);
- vi->cookie = vpdev->hw_ops->request_irq(vpdev,
- vop_extint_handler,
- "virtio_config_intr",
- vi, vi->h2c_config_db);
- if (IS_ERR(vi->cookie)) {
- rc = PTR_ERR(vi->cookie);
- goto free;
- }
- bootparam = vpdev->hw_ops->get_remote_dp(vpdev);
- iowrite8(vi->h2c_config_db, &bootparam->h2c_config_db);
- }
- vop_init_debugfs(vi);
- return 0;
-free:
- kfree(vi);
-exit:
- return rc;
-}
-
-static void vop_driver_remove(struct vop_device *vpdev)
-{
- struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
-
- if (vpdev->dnode) {
- vop_host_uninit(vi);
- } else {
- struct mic_bootparam __iomem *bootparam =
- vpdev->hw_ops->get_remote_dp(vpdev);
- if (bootparam)
- iowrite8(-1, &bootparam->h2c_config_db);
- vpdev->hw_ops->free_irq(vpdev, vi->cookie, vi);
- flush_work(&vi->hotplug_work);
- vop_scan_devices(vi, vpdev, REMOVE_DEVICES);
- }
- vop_exit_debugfs(vi);
- kfree(vi);
-}
-
-static const struct vop_device_id id_table[] = {
- { VOP_DEV_TRNSP, VOP_DEV_ANY_ID },
- { 0 },
-};
-
-static struct vop_driver vop_driver = {
- .driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
- .id_table = id_table,
- .probe = vop_driver_probe,
- .remove = vop_driver_remove,
-};
-
-module_vop_driver(vop_driver);
-
-MODULE_DEVICE_TABLE(mbus, id_table);
-MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Intel(R) Virtio Over PCIe (VOP) driver");
-MODULE_LICENSE("GPL v2");
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#ifndef _VOP_MAIN_H_
-#define _VOP_MAIN_H_
-
-#include <linux/vringh.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio.h>
-#include <linux/miscdevice.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-#include "../bus/vop_bus.h"
-
-/*
- * Note on endianness.
- * 1. Host can be both BE or LE
- * 2. Guest/card is LE. Host uses le_to_cpu to access desc/avail
- * rings and ioreadXX/iowriteXX to access used ring.
- * 3. Device page exposed by host to guest contains LE values. Guest
- * accesses these using ioreadXX/iowriteXX etc. This way in general we
- * obey the virtio spec according to which guest works with native
- * endianness and host is aware of guest endianness and does all
- * required endianness conversion.
- * 4. Data provided from user space to guest (in ADD_DEVICE and
- * CONFIG_CHANGE ioctl's) is not interpreted by the driver and should be
- * in guest endianness.
- */
-
-/*
- * vop_info - Allocated per invocation of VOP probe
- *
- * @vpdev: VOP device
- * @hotplug_work: Handle virtio device creation, deletion and configuration
- * @cookie: Cookie received upon requesting a virtio configuration interrupt
- * @h2c_config_db: The doorbell used by the peer to indicate a config change
- * @vdev_list: List of "active" virtio devices injected in the peer node
- * @vop_mutex: Synchronize access to the device page as well as serialize
- * creation/deletion of virtio devices on the peer node
- * @dp: Peer device page information
- * @dbg: Debugfs entry
- * @dma_ch: The DMA channel used by this transport for data transfers.
- * @name: Name for this transport used in misc device creation.
- * @miscdev: The misc device registered.
- */
-struct vop_info {
- struct vop_device *vpdev;
- struct work_struct hotplug_work;
- struct mic_irq *cookie;
- int h2c_config_db;
- struct list_head vdev_list;
- struct mutex vop_mutex;
- void __iomem *dp;
- struct dentry *dbg;
- struct dma_chan *dma_ch;
- char name[16];
- struct miscdevice miscdev;
-};
-
-/**
- * struct vop_vringh - Virtio ring host information.
- *
- * @vring: The VOP vring used for setting up user space mappings.
- * @vrh: The host VRINGH used for accessing the card vrings.
- * @riov: The VRINGH read kernel IOV.
- * @wiov: The VRINGH write kernel IOV.
- * @head: The VRINGH head index address passed to vringh_getdesc_kern(..).
- * @vr_mutex: Mutex for synchronizing access to the VRING.
- * @buf: Temporary kernel buffer used to copy in/out data
- * from/to the card via DMA.
- * @buf_da: dma address of buf.
- * @vdev: Back pointer to VOP virtio device for vringh_notify(..).
- */
-struct vop_vringh {
- struct mic_vring vring;
- struct vringh vrh;
- struct vringh_kiov riov;
- struct vringh_kiov wiov;
- u16 head;
- struct mutex vr_mutex;
- void *buf;
- dma_addr_t buf_da;
- struct vop_vdev *vdev;
-};
-
-/**
- * struct vop_vdev - Host information for a card Virtio device.
- *
- * @virtio_id - Virtio device id.
- * @waitq - Waitqueue to allow ring3 apps to poll.
- * @vpdev - pointer to VOP bus device.
- * @poll_wake - Used for waking up threads blocked in poll.
- * @out_bytes - Debug stats for number of bytes copied from host to card.
- * @in_bytes - Debug stats for number of bytes copied from card to host.
- * @out_bytes_dma - Debug stats for number of bytes copied from host to card
- * using DMA.
- * @in_bytes_dma - Debug stats for number of bytes copied from card to host
- * using DMA.
- * @tx_len_unaligned - Debug stats for number of bytes copied to the card where
- * the transfer length did not have the required DMA alignment.
- * @tx_dst_unaligned - Debug stats for number of bytes copied where the
- * destination address on the card did not have the required DMA alignment.
- * @vvr - Store per VRING data structures.
- * @virtio_bh_work - Work struct used to schedule virtio bottom half handling.
- * @dd - Virtio device descriptor.
- * @dc - Virtio device control fields.
- * @list - List of Virtio devices.
- * @virtio_db - The doorbell used by the card to interrupt the host.
- * @virtio_cookie - The cookie returned while requesting interrupts.
- * @vi: Transport information.
- * @vdev_mutex: Mutex synchronizing virtio device injection,
- * removal and data transfers.
- * @destroy: Track if a virtio device is being destroyed.
- * @deleted: The virtio device has been deleted.
- */
-struct vop_vdev {
- int virtio_id;
- wait_queue_head_t waitq;
- struct vop_device *vpdev;
- int poll_wake;
- unsigned long out_bytes;
- unsigned long in_bytes;
- unsigned long out_bytes_dma;
- unsigned long in_bytes_dma;
- unsigned long tx_len_unaligned;
- unsigned long tx_dst_unaligned;
- unsigned long rx_dst_unaligned;
- struct vop_vringh vvr[MIC_MAX_VRINGS];
- struct work_struct virtio_bh_work;
- struct mic_device_desc *dd;
- struct mic_device_ctrl *dc;
- struct list_head list;
- int virtio_db;
- struct mic_irq *virtio_cookie;
- struct vop_info *vi;
- struct mutex vdev_mutex;
- struct completion destroy;
- bool deleted;
-};
-
-/* Helper API to check if a virtio device is running */
-static inline bool vop_vdevup(struct vop_vdev *vdev)
-{
- return !!vdev->dd->status;
-}
-
-void vop_init_debugfs(struct vop_info *vi);
-void vop_exit_debugfs(struct vop_info *vi);
-int vop_host_init(struct vop_info *vi);
-void vop_host_uninit(struct vop_info *vi);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2016 Intel Corporation.
- *
- * Intel Virtio Over PCIe (VOP) driver.
- */
-#include <linux/sched.h>
-#include <linux/poll.h>
-#include <linux/dma-mapping.h>
-
-#include <linux/mic_common.h>
-#include "../common/mic_dev.h"
-
-#include <linux/mic_ioctl.h>
-#include "vop_main.h"
-
-/* Helper API to obtain the VOP PCIe device */
-static inline struct device *vop_dev(struct vop_vdev *vdev)
-{
- return vdev->vpdev->dev.parent;
-}
-
-/* Helper API to check if a virtio device is initialized */
-static inline int vop_vdev_inited(struct vop_vdev *vdev)
-{
- if (!vdev)
- return -EINVAL;
- /* Device has not been created yet */
- if (!vdev->dd || !vdev->dd->type) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, -EINVAL);
- return -EINVAL;
- }
- /* Device has been removed/deleted */
- if (vdev->dd->type == -1) {
- dev_dbg(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, -ENODEV);
- return -ENODEV;
- }
- return 0;
-}
-
-static void _vop_notify(struct vringh *vrh)
-{
- struct vop_vringh *vvrh = container_of(vrh, struct vop_vringh, vrh);
- struct vop_vdev *vdev = vvrh->vdev;
- struct vop_device *vpdev = vdev->vpdev;
- s8 db = vdev->dc->h2c_vdev_db;
-
- if (db != -1)
- vpdev->hw_ops->send_intr(vpdev, db);
-}
-
-static void vop_virtio_init_post(struct vop_vdev *vdev)
-{
- struct mic_vqconfig *vqconfig = mic_vq_config(vdev->dd);
- struct vop_device *vpdev = vdev->vpdev;
- int i, used_size;
-
- for (i = 0; i < vdev->dd->num_vq; i++) {
- used_size = PAGE_ALIGN(sizeof(u16) * 3 +
- sizeof(struct vring_used_elem) *
- le16_to_cpu(vqconfig->num));
- if (!le64_to_cpu(vqconfig[i].used_address)) {
- dev_warn(vop_dev(vdev), "used_address zero??\n");
- continue;
- }
- vdev->vvr[i].vrh.vring.used =
- (void __force *)vpdev->hw_ops->remap(
- vpdev,
- le64_to_cpu(vqconfig[i].used_address),
- used_size);
- }
-
- vdev->dc->used_address_updated = 0;
-
- dev_info(vop_dev(vdev), "%s: device type %d LINKUP\n",
- __func__, vdev->virtio_id);
-}
-
-static inline void vop_virtio_device_reset(struct vop_vdev *vdev)
-{
- int i;
-
- dev_dbg(vop_dev(vdev), "%s: status %d device type %d RESET\n",
- __func__, vdev->dd->status, vdev->virtio_id);
-
- for (i = 0; i < vdev->dd->num_vq; i++)
- /*
- * Avoid lockdep false positive. The + 1 is for the vop
- * mutex which is held in the reset devices code path.
- */
- mutex_lock_nested(&vdev->vvr[i].vr_mutex, i + 1);
-
- /* 0 status means "reset" */
- vdev->dd->status = 0;
- vdev->dc->vdev_reset = 0;
- vdev->dc->host_ack = 1;
-
- for (i = 0; i < vdev->dd->num_vq; i++) {
- struct vringh *vrh = &vdev->vvr[i].vrh;
-
- vdev->vvr[i].vring.info->avail_idx = 0;
- vrh->completed = 0;
- vrh->last_avail_idx = 0;
- vrh->last_used_idx = 0;
- }
-
- for (i = 0; i < vdev->dd->num_vq; i++)
- mutex_unlock(&vdev->vvr[i].vr_mutex);
-}
-
-static void vop_virtio_reset_devices(struct vop_info *vi)
-{
- struct list_head *pos, *tmp;
- struct vop_vdev *vdev;
-
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev = list_entry(pos, struct vop_vdev, list);
- vop_virtio_device_reset(vdev);
- vdev->poll_wake = 1;
- wake_up(&vdev->waitq);
- }
-}
-
-static void vop_bh_handler(struct work_struct *work)
-{
- struct vop_vdev *vdev = container_of(work, struct vop_vdev,
- virtio_bh_work);
-
- if (vdev->dc->used_address_updated)
- vop_virtio_init_post(vdev);
-
- if (vdev->dc->vdev_reset)
- vop_virtio_device_reset(vdev);
-
- vdev->poll_wake = 1;
- wake_up(&vdev->waitq);
-}
-
-static irqreturn_t _vop_virtio_intr_handler(int irq, void *data)
-{
- struct vop_vdev *vdev = data;
- struct vop_device *vpdev = vdev->vpdev;
-
- vpdev->hw_ops->ack_interrupt(vpdev, vdev->virtio_db);
- schedule_work(&vdev->virtio_bh_work);
- return IRQ_HANDLED;
-}
-
-static int vop_virtio_config_change(struct vop_vdev *vdev, void *argp)
-{
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
- int ret = 0, retry, i;
- struct vop_device *vpdev = vdev->vpdev;
- struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
- s8 db = bootparam->h2c_config_db;
-
- mutex_lock(&vi->vop_mutex);
- for (i = 0; i < vdev->dd->num_vq; i++)
- mutex_lock_nested(&vdev->vvr[i].vr_mutex, i + 1);
-
- if (db == -1 || vdev->dd->type == -1) {
- ret = -EIO;
- goto exit;
- }
-
- memcpy(mic_vq_configspace(vdev->dd), argp, vdev->dd->config_len);
- vdev->dc->config_change = MIC_VIRTIO_PARAM_CONFIG_CHANGED;
- vpdev->hw_ops->send_intr(vpdev, db);
-
- for (retry = 100; retry--;) {
- ret = wait_event_timeout(wake, vdev->dc->guest_ack,
- msecs_to_jiffies(100));
- if (ret)
- break;
- }
-
- dev_dbg(vop_dev(vdev),
- "%s %d retry: %d\n", __func__, __LINE__, retry);
- vdev->dc->config_change = 0;
- vdev->dc->guest_ack = 0;
-exit:
- for (i = 0; i < vdev->dd->num_vq; i++)
- mutex_unlock(&vdev->vvr[i].vr_mutex);
- mutex_unlock(&vi->vop_mutex);
- return ret;
-}
-
-static int vop_copy_dp_entry(struct vop_vdev *vdev,
- struct mic_device_desc *argp, __u8 *type,
- struct mic_device_desc **devpage)
-{
- struct vop_device *vpdev = vdev->vpdev;
- struct mic_device_desc *devp;
- struct mic_vqconfig *vqconfig;
- int ret = 0, i;
- bool slot_found = false;
-
- vqconfig = mic_vq_config(argp);
- for (i = 0; i < argp->num_vq; i++) {
- if (le16_to_cpu(vqconfig[i].num) > MIC_MAX_VRING_ENTRIES) {
- ret = -EINVAL;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto exit;
- }
- }
-
- /* Find the first free device page entry */
- for (i = sizeof(struct mic_bootparam);
- i < MIC_DP_SIZE - mic_total_desc_size(argp);
- i += mic_total_desc_size(devp)) {
- devp = vpdev->hw_ops->get_dp(vpdev) + i;
- if (devp->type == 0 || devp->type == -1) {
- slot_found = true;
- break;
- }
- }
- if (!slot_found) {
- ret = -EINVAL;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto exit;
- }
- /*
- * Save off the type before doing the memcpy. Type will be set in the
- * end after completing all initialization for the new device.
- */
- *type = argp->type;
- argp->type = 0;
- memcpy(devp, argp, mic_desc_size(argp));
-
- *devpage = devp;
-exit:
- return ret;
-}
-
-static void vop_init_device_ctrl(struct vop_vdev *vdev,
- struct mic_device_desc *devpage)
-{
- struct mic_device_ctrl *dc;
-
- dc = (void *)devpage + mic_aligned_desc_size(devpage);
-
- dc->config_change = 0;
- dc->guest_ack = 0;
- dc->vdev_reset = 0;
- dc->host_ack = 0;
- dc->used_address_updated = 0;
- dc->c2h_vdev_db = -1;
- dc->h2c_vdev_db = -1;
- vdev->dc = dc;
-}
-
-static int vop_virtio_add_device(struct vop_vdev *vdev,
- struct mic_device_desc *argp)
-{
- struct vop_info *vi = vdev->vi;
- struct vop_device *vpdev = vi->vpdev;
- struct mic_device_desc *dd = NULL;
- struct mic_vqconfig *vqconfig;
- int vr_size, i, j, ret;
- u8 type = 0;
- s8 db = -1;
- char irqname[16];
- struct mic_bootparam *bootparam;
- u16 num;
- dma_addr_t vr_addr;
-
- bootparam = vpdev->hw_ops->get_dp(vpdev);
- init_waitqueue_head(&vdev->waitq);
- INIT_LIST_HEAD(&vdev->list);
- vdev->vpdev = vpdev;
-
- ret = vop_copy_dp_entry(vdev, argp, &type, &dd);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- return ret;
- }
-
- vop_init_device_ctrl(vdev, dd);
-
- vdev->dd = dd;
- vdev->virtio_id = type;
- vqconfig = mic_vq_config(dd);
- INIT_WORK(&vdev->virtio_bh_work, vop_bh_handler);
-
- for (i = 0; i < dd->num_vq; i++) {
- struct vop_vringh *vvr = &vdev->vvr[i];
- struct mic_vring *vr = &vdev->vvr[i].vring;
-
- num = le16_to_cpu(vqconfig[i].num);
- mutex_init(&vvr->vr_mutex);
- vr_size = PAGE_ALIGN(round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4) +
- sizeof(struct _mic_vring_info));
- vr->va = (void *)
- __get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(vr_size));
- if (!vr->va) {
- ret = -ENOMEM;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto err;
- }
- vr->len = vr_size;
- vr->info = vr->va + round_up(vring_size(num, MIC_VIRTIO_RING_ALIGN), 4);
- vr->info->magic = cpu_to_le32(MIC_MAGIC + vdev->virtio_id + i);
- vr_addr = dma_map_single(&vpdev->dev, vr->va, vr_size,
- DMA_BIDIRECTIONAL);
- if (dma_mapping_error(&vpdev->dev, vr_addr)) {
- free_pages((unsigned long)vr->va, get_order(vr_size));
- ret = -ENOMEM;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto err;
- }
- vqconfig[i].address = cpu_to_le64(vr_addr);
-
- vring_init(&vr->vr, num, vr->va, MIC_VIRTIO_RING_ALIGN);
- ret = vringh_init_kern(&vvr->vrh,
- *(u32 *)mic_vq_features(vdev->dd),
- num, false, vr->vr.desc, vr->vr.avail,
- vr->vr.used);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- goto err;
- }
- vringh_kiov_init(&vvr->riov, NULL, 0);
- vringh_kiov_init(&vvr->wiov, NULL, 0);
- vvr->head = USHRT_MAX;
- vvr->vdev = vdev;
- vvr->vrh.notify = _vop_notify;
- dev_dbg(&vpdev->dev,
- "%s %d index %d va %p info %p vr_size 0x%x\n",
- __func__, __LINE__, i, vr->va, vr->info, vr_size);
- vvr->buf = (void *)__get_free_pages(GFP_KERNEL,
- get_order(VOP_INT_DMA_BUF_SIZE));
- vvr->buf_da = dma_map_single(&vpdev->dev,
- vvr->buf, VOP_INT_DMA_BUF_SIZE,
- DMA_BIDIRECTIONAL);
- }
-
- snprintf(irqname, sizeof(irqname), "vop%dvirtio%d", vpdev->index,
- vdev->virtio_id);
- vdev->virtio_db = vpdev->hw_ops->next_db(vpdev);
- vdev->virtio_cookie = vpdev->hw_ops->request_irq(vpdev,
- _vop_virtio_intr_handler, irqname, vdev,
- vdev->virtio_db);
- if (IS_ERR(vdev->virtio_cookie)) {
- ret = PTR_ERR(vdev->virtio_cookie);
- dev_dbg(&vpdev->dev, "request irq failed\n");
- goto err;
- }
-
- vdev->dc->c2h_vdev_db = vdev->virtio_db;
-
- /*
- * Order the type update with previous stores. This write barrier
- * is paired with the corresponding read barrier before the uncached
- * system memory read of the type, on the card while scanning the
- * device page.
- */
- smp_wmb();
- dd->type = type;
- argp->type = type;
-
- if (bootparam) {
- db = bootparam->h2c_config_db;
- if (db != -1)
- vpdev->hw_ops->send_intr(vpdev, db);
- }
- dev_dbg(&vpdev->dev, "Added virtio id %d db %d\n", dd->type, db);
- return 0;
-err:
- vqconfig = mic_vq_config(dd);
- for (j = 0; j < i; j++) {
- struct vop_vringh *vvr = &vdev->vvr[j];
-
- dma_unmap_single(&vpdev->dev, le64_to_cpu(vqconfig[j].address),
- vvr->vring.len, DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vvr->vring.va,
- get_order(vvr->vring.len));
- }
- return ret;
-}
-
-static void vop_dev_remove(struct vop_info *pvi, struct mic_device_ctrl *devp,
- struct vop_device *vpdev)
-{
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
- s8 db;
- int ret, retry;
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake);
-
- devp->config_change = MIC_VIRTIO_PARAM_DEV_REMOVE;
- db = bootparam->h2c_config_db;
- if (db != -1)
- vpdev->hw_ops->send_intr(vpdev, db);
- else
- goto done;
- for (retry = 15; retry--;) {
- ret = wait_event_timeout(wake, devp->guest_ack,
- msecs_to_jiffies(1000));
- if (ret)
- break;
- }
-done:
- devp->config_change = 0;
- devp->guest_ack = 0;
-}
-
-static void vop_virtio_del_device(struct vop_vdev *vdev)
-{
- struct vop_info *vi = vdev->vi;
- struct vop_device *vpdev = vdev->vpdev;
- int i;
- struct mic_vqconfig *vqconfig;
- struct mic_bootparam *bootparam = vpdev->hw_ops->get_dp(vpdev);
-
- if (!bootparam)
- goto skip_hot_remove;
- vop_dev_remove(vi, vdev->dc, vpdev);
-skip_hot_remove:
- vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
- flush_work(&vdev->virtio_bh_work);
- vqconfig = mic_vq_config(vdev->dd);
- for (i = 0; i < vdev->dd->num_vq; i++) {
- struct vop_vringh *vvr = &vdev->vvr[i];
-
- dma_unmap_single(&vpdev->dev,
- vvr->buf_da, VOP_INT_DMA_BUF_SIZE,
- DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vvr->buf,
- get_order(VOP_INT_DMA_BUF_SIZE));
- vringh_kiov_cleanup(&vvr->riov);
- vringh_kiov_cleanup(&vvr->wiov);
- dma_unmap_single(&vpdev->dev, le64_to_cpu(vqconfig[i].address),
- vvr->vring.len, DMA_BIDIRECTIONAL);
- free_pages((unsigned long)vvr->vring.va,
- get_order(vvr->vring.len));
- }
- /*
- * Order the type update with previous stores. This write barrier
- * is paired with the corresponding read barrier before the uncached
- * system memory read of the type, on the card while scanning the
- * device page.
- */
- smp_wmb();
- vdev->dd->type = -1;
-}
-
-/*
- * vop_sync_dma - Wrapper for synchronous DMAs.
- *
- * @dev - The address of the pointer to the device instance used
- * for DMA registration.
- * @dst - destination DMA address.
- * @src - source DMA address.
- * @len - size of the transfer.
- *
- * Return DMA_SUCCESS on success
- */
-static int vop_sync_dma(struct vop_vdev *vdev, dma_addr_t dst, dma_addr_t src,
- size_t len)
-{
- int err = 0;
- struct dma_device *ddev;
- struct dma_async_tx_descriptor *tx;
- struct vop_info *vi = dev_get_drvdata(&vdev->vpdev->dev);
- struct dma_chan *vop_ch = vi->dma_ch;
-
- if (!vop_ch) {
- err = -EBUSY;
- goto error;
- }
- ddev = vop_ch->device;
- tx = ddev->device_prep_dma_memcpy(vop_ch, dst, src, len,
- DMA_PREP_FENCE);
- if (!tx) {
- err = -ENOMEM;
- goto error;
- } else {
- dma_cookie_t cookie;
-
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- err = -ENOMEM;
- goto error;
- }
- dma_async_issue_pending(vop_ch);
- err = dma_sync_wait(vop_ch, cookie);
- }
-error:
- if (err)
- dev_err(&vi->vpdev->dev, "%s %d err %d\n",
- __func__, __LINE__, err);
- return err;
-}
-
-#define VOP_USE_DMA true
-
-/*
- * Initiates the copies across the PCIe bus from card memory to a user
- * space buffer. When transfers are done using DMA, source/destination
- * addresses and transfer length must follow the alignment requirements of
- * the MIC DMA engine.
- */
-static int vop_virtio_copy_to_user(struct vop_vdev *vdev, void __user *ubuf,
- size_t len, u64 daddr, size_t dlen,
- int vr_idx)
-{
- struct vop_device *vpdev = vdev->vpdev;
- void __iomem *dbuf = vpdev->hw_ops->remap(vpdev, daddr, len);
- struct vop_vringh *vvr = &vdev->vvr[vr_idx];
- struct vop_info *vi = dev_get_drvdata(&vpdev->dev);
- size_t dma_alignment;
- bool x200;
- size_t dma_offset, partlen;
- int err;
-
- if (!VOP_USE_DMA || !vi->dma_ch) {
- if (copy_to_user(ubuf, (void __force *)dbuf, len)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- vdev->in_bytes += len;
- err = 0;
- goto err;
- }
-
- dma_alignment = 1 << vi->dma_ch->device->copy_align;
- x200 = is_dma_copy_aligned(vi->dma_ch->device, 1, 1, 1);
-
- dma_offset = daddr - round_down(daddr, dma_alignment);
- daddr -= dma_offset;
- len += dma_offset;
- /*
- * X100 uses DMA addresses as seen by the card so adding
- * the aperture base is not required for DMA. However x200
- * requires DMA addresses to be an offset into the bar so
- * add the aperture base for x200.
- */
- if (x200)
- daddr += vpdev->aper->pa;
- while (len) {
- partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
- err = vop_sync_dma(vdev, vvr->buf_da, daddr,
- ALIGN(partlen, dma_alignment));
- if (err) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- if (copy_to_user(ubuf, vvr->buf + dma_offset,
- partlen - dma_offset)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- daddr += partlen;
- ubuf += partlen;
- dbuf += partlen;
- vdev->in_bytes_dma += partlen;
- vdev->in_bytes += partlen;
- len -= partlen;
- dma_offset = 0;
- }
- err = 0;
-err:
- vpdev->hw_ops->unmap(vpdev, dbuf);
- dev_dbg(vop_dev(vdev),
- "%s: ubuf %p dbuf %p len 0x%zx vr_idx 0x%x\n",
- __func__, ubuf, dbuf, len, vr_idx);
- return err;
-}
-
-/*
- * Initiates copies across the PCIe bus from a user space buffer to card
- * memory. When transfers are done using DMA, source/destination addresses
- * and transfer length must follow the alignment requirements of the MIC
- * DMA engine.
- */
-static int vop_virtio_copy_from_user(struct vop_vdev *vdev, void __user *ubuf,
- size_t len, u64 daddr, size_t dlen,
- int vr_idx)
-{
- struct vop_device *vpdev = vdev->vpdev;
- void __iomem *dbuf = vpdev->hw_ops->remap(vpdev, daddr, len);
- struct vop_vringh *vvr = &vdev->vvr[vr_idx];
- struct vop_info *vi = dev_get_drvdata(&vdev->vpdev->dev);
- size_t dma_alignment;
- bool x200;
- size_t partlen;
- bool dma = VOP_USE_DMA && vi->dma_ch;
- int err = 0;
- size_t offset = 0;
-
- if (dma) {
- dma_alignment = 1 << vi->dma_ch->device->copy_align;
- x200 = is_dma_copy_aligned(vi->dma_ch->device, 1, 1, 1);
-
- if (daddr & (dma_alignment - 1)) {
- vdev->tx_dst_unaligned += len;
- dma = false;
- } else if (ALIGN(len, dma_alignment) > dlen) {
- vdev->tx_len_unaligned += len;
- dma = false;
- }
- }
-
- if (!dma)
- goto memcpy;
-
- /*
- * X100 uses DMA addresses as seen by the card so adding
- * the aperture base is not required for DMA. However x200
- * requires DMA addresses to be an offset into the bar so
- * add the aperture base for x200.
- */
- if (x200)
- daddr += vpdev->aper->pa;
- while (len) {
- partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-
- if (copy_from_user(vvr->buf, ubuf, partlen)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- err = vop_sync_dma(vdev, daddr, vvr->buf_da,
- ALIGN(partlen, dma_alignment));
- if (err) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- daddr += partlen;
- ubuf += partlen;
- dbuf += partlen;
- vdev->out_bytes_dma += partlen;
- vdev->out_bytes += partlen;
- len -= partlen;
- }
-memcpy:
- /*
- * We are copying to IO below and should ideally use something
- * like copy_from_user_toio(..) if it existed.
- */
- while (len) {
- partlen = min_t(size_t, len, VOP_INT_DMA_BUF_SIZE);
-
- if (copy_from_user(vvr->buf, ubuf + offset, partlen)) {
- err = -EFAULT;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- memcpy_toio(dbuf + offset, vvr->buf, partlen);
- offset += partlen;
- vdev->out_bytes += partlen;
- len -= partlen;
- }
- err = 0;
-err:
- vpdev->hw_ops->unmap(vpdev, dbuf);
- dev_dbg(vop_dev(vdev),
- "%s: ubuf %p dbuf %p len 0x%zx vr_idx 0x%x\n",
- __func__, ubuf, dbuf, len, vr_idx);
- return err;
-}
-
-#define MIC_VRINGH_READ true
-
-/* Determine the total number of bytes consumed in a VRINGH KIOV */
-static inline u32 vop_vringh_iov_consumed(struct vringh_kiov *iov)
-{
- int i;
- u32 total = iov->consumed;
-
- for (i = 0; i < iov->i; i++)
- total += iov->iov[i].iov_len;
- return total;
-}
-
-/*
- * Traverse the VRINGH KIOV and issue the APIs to trigger the copies.
- * This API is heavily based on the vringh_iov_xfer(..) implementation
- * in vringh.c. The reason we cannot reuse vringh_iov_pull_kern(..)
- * and vringh_iov_push_kern(..) directly is because there is no
- * way to override the VRINGH xfer(..) routines as of v3.10.
- */
-static int vop_vringh_copy(struct vop_vdev *vdev, struct vringh_kiov *iov,
- void __user *ubuf, size_t len, bool read, int vr_idx,
- size_t *out_len)
-{
- int ret = 0;
- size_t partlen, tot_len = 0;
-
- while (len && iov->i < iov->used) {
- struct kvec *kiov = &iov->iov[iov->i];
- unsigned long daddr = (unsigned long)kiov->iov_base;
-
- partlen = min(kiov->iov_len, len);
- if (read)
- ret = vop_virtio_copy_to_user(vdev, ubuf, partlen,
- daddr,
- kiov->iov_len,
- vr_idx);
- else
- ret = vop_virtio_copy_from_user(vdev, ubuf, partlen,
- daddr,
- kiov->iov_len,
- vr_idx);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len -= partlen;
- ubuf += partlen;
- tot_len += partlen;
- iov->consumed += partlen;
- kiov->iov_len -= partlen;
- kiov->iov_base += partlen;
- if (!kiov->iov_len) {
- /* Fix up old iov element then increment. */
- kiov->iov_len = iov->consumed;
- kiov->iov_base -= iov->consumed;
-
- iov->consumed = 0;
- iov->i++;
- }
- }
- *out_len = tot_len;
- return ret;
-}
-
-/*
- * Use the standard VRINGH infrastructure in the kernel to fetch new
- * descriptors, initiate the copies and update the used ring.
- */
-static int _vop_virtio_copy(struct vop_vdev *vdev, struct mic_copy_desc *copy)
-{
- int ret = 0;
- u32 iovcnt = copy->iovcnt;
- struct iovec iov;
- struct iovec __user *u_iov = copy->iov;
- void __user *ubuf = NULL;
- struct vop_vringh *vvr = &vdev->vvr[copy->vr_idx];
- struct vringh_kiov *riov = &vvr->riov;
- struct vringh_kiov *wiov = &vvr->wiov;
- struct vringh *vrh = &vvr->vrh;
- u16 *head = &vvr->head;
- struct mic_vring *vr = &vvr->vring;
- size_t len = 0, out_len;
-
- copy->out_len = 0;
- /* Fetch a new IOVEC if all previous elements have been processed */
- if (riov->i == riov->used && wiov->i == wiov->used) {
- ret = vringh_getdesc_kern(vrh, riov, wiov,
- head, GFP_KERNEL);
- /* Check if there are available descriptors */
- if (ret <= 0)
- return ret;
- }
- while (iovcnt) {
- if (!len) {
- /* Copy over a new iovec from user space. */
- ret = copy_from_user(&iov, u_iov, sizeof(*u_iov));
- if (ret) {
- ret = -EINVAL;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len = iov.iov_len;
- ubuf = iov.iov_base;
- }
- /* Issue all the read descriptors first */
- ret = vop_vringh_copy(vdev, riov, ubuf, len,
- MIC_VRINGH_READ, copy->vr_idx, &out_len);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len -= out_len;
- ubuf += out_len;
- copy->out_len += out_len;
- /* Issue the write descriptors next */
- ret = vop_vringh_copy(vdev, wiov, ubuf, len,
- !MIC_VRINGH_READ, copy->vr_idx, &out_len);
- if (ret) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, ret);
- break;
- }
- len -= out_len;
- ubuf += out_len;
- copy->out_len += out_len;
- if (!len) {
- /* One user space iovec is now completed */
- iovcnt--;
- u_iov++;
- }
- /* Exit loop if all elements in KIOVs have been processed. */
- if (riov->i == riov->used && wiov->i == wiov->used)
- break;
- }
- /*
- * Update the used ring if a descriptor was available and some data was
- * copied in/out and the user asked for a used ring update.
- */
- if (*head != USHRT_MAX && copy->out_len && copy->update_used) {
- u32 total = 0;
-
- /* Determine the total data consumed */
- total += vop_vringh_iov_consumed(riov);
- total += vop_vringh_iov_consumed(wiov);
- vringh_complete_kern(vrh, *head, total);
- *head = USHRT_MAX;
- if (vringh_need_notify_kern(vrh) > 0)
- vringh_notify(vrh);
- vringh_kiov_cleanup(riov);
- vringh_kiov_cleanup(wiov);
- /* Update avail idx for user space */
- vr->info->avail_idx = vrh->last_avail_idx;
- }
- return ret;
-}
-
-static inline int vop_verify_copy_args(struct vop_vdev *vdev,
- struct mic_copy_desc *copy)
-{
- if (!vdev || copy->vr_idx >= vdev->dd->num_vq)
- return -EINVAL;
- return 0;
-}
-
-/* Copy a specified number of virtio descriptors in a chain */
-static int vop_virtio_copy_desc(struct vop_vdev *vdev,
- struct mic_copy_desc *copy)
-{
- int err;
- struct vop_vringh *vvr;
-
- err = vop_verify_copy_args(vdev, copy);
- if (err)
- return err;
-
- vvr = &vdev->vvr[copy->vr_idx];
- mutex_lock(&vvr->vr_mutex);
- if (!vop_vdevup(vdev)) {
- err = -ENODEV;
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- goto err;
- }
- err = _vop_virtio_copy(vdev, copy);
- if (err) {
- dev_err(vop_dev(vdev), "%s %d err %d\n",
- __func__, __LINE__, err);
- }
-err:
- mutex_unlock(&vvr->vr_mutex);
- return err;
-}
-
-static int vop_open(struct inode *inode, struct file *f)
-{
- struct vop_vdev *vdev;
- struct vop_info *vi = container_of(f->private_data,
- struct vop_info, miscdev);
-
- vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
- if (!vdev)
- return -ENOMEM;
- vdev->vi = vi;
- mutex_init(&vdev->vdev_mutex);
- f->private_data = vdev;
- init_completion(&vdev->destroy);
- complete(&vdev->destroy);
- return 0;
-}
-
-static int vop_release(struct inode *inode, struct file *f)
-{
- struct vop_vdev *vdev = f->private_data, *vdev_tmp;
- struct vop_info *vi = vdev->vi;
- struct list_head *pos, *tmp;
- bool found = false;
-
- mutex_lock(&vdev->vdev_mutex);
- if (vdev->deleted)
- goto unlock;
- mutex_lock(&vi->vop_mutex);
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev_tmp = list_entry(pos, struct vop_vdev, list);
- if (vdev == vdev_tmp) {
- vop_virtio_del_device(vdev);
- list_del(pos);
- found = true;
- break;
- }
- }
- mutex_unlock(&vi->vop_mutex);
-unlock:
- mutex_unlock(&vdev->vdev_mutex);
- if (!found)
- wait_for_completion(&vdev->destroy);
- f->private_data = NULL;
- kfree(vdev);
- return 0;
-}
-
-static long vop_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
- struct vop_vdev *vdev = f->private_data;
- struct vop_info *vi = vdev->vi;
- void __user *argp = (void __user *)arg;
- int ret;
-
- switch (cmd) {
- case MIC_VIRTIO_ADD_DEVICE:
- {
- struct mic_device_desc dd, *dd_config;
-
- if (copy_from_user(&dd, argp, sizeof(dd)))
- return -EFAULT;
-
- if (mic_aligned_desc_size(&dd) > MIC_MAX_DESC_BLK_SIZE ||
- dd.num_vq > MIC_MAX_VRINGS)
- return -EINVAL;
-
- dd_config = memdup_user(argp, mic_desc_size(&dd));
- if (IS_ERR(dd_config))
- return PTR_ERR(dd_config);
-
- /* Ensure desc has not changed between the two reads */
- if (memcmp(&dd, dd_config, sizeof(dd))) {
- ret = -EINVAL;
- goto free_ret;
- }
- mutex_lock(&vdev->vdev_mutex);
- mutex_lock(&vi->vop_mutex);
- ret = vop_virtio_add_device(vdev, dd_config);
- if (ret)
- goto unlock_ret;
- list_add_tail(&vdev->list, &vi->vdev_list);
-unlock_ret:
- mutex_unlock(&vi->vop_mutex);
- mutex_unlock(&vdev->vdev_mutex);
-free_ret:
- kfree(dd_config);
- return ret;
- }
- case MIC_VIRTIO_COPY_DESC:
- {
- struct mic_copy_desc copy;
-
- mutex_lock(&vdev->vdev_mutex);
- ret = vop_vdev_inited(vdev);
- if (ret)
- goto _unlock_ret;
-
- if (copy_from_user(©, argp, sizeof(copy))) {
- ret = -EFAULT;
- goto _unlock_ret;
- }
-
- ret = vop_virtio_copy_desc(vdev, ©);
- if (ret < 0)
- goto _unlock_ret;
- if (copy_to_user(
- &((struct mic_copy_desc __user *)argp)->out_len,
- ©.out_len, sizeof(copy.out_len)))
- ret = -EFAULT;
-_unlock_ret:
- mutex_unlock(&vdev->vdev_mutex);
- return ret;
- }
- case MIC_VIRTIO_CONFIG_CHANGE:
- {
- void *buf;
-
- mutex_lock(&vdev->vdev_mutex);
- ret = vop_vdev_inited(vdev);
- if (ret)
- goto __unlock_ret;
- buf = memdup_user(argp, vdev->dd->config_len);
- if (IS_ERR(buf)) {
- ret = PTR_ERR(buf);
- goto __unlock_ret;
- }
- ret = vop_virtio_config_change(vdev, buf);
- kfree(buf);
-__unlock_ret:
- mutex_unlock(&vdev->vdev_mutex);
- return ret;
- }
- default:
- return -ENOIOCTLCMD;
- };
- return 0;
-}
-
-/*
- * We return EPOLLIN | EPOLLOUT from poll when new buffers are enqueued, and
- * not when previously enqueued buffers may be available. This means that
- * in the card->host (TX) path, when userspace is unblocked by poll it
- * must drain all available descriptors or it can stall.
- */
-static __poll_t vop_poll(struct file *f, poll_table *wait)
-{
- struct vop_vdev *vdev = f->private_data;
- __poll_t mask = 0;
-
- mutex_lock(&vdev->vdev_mutex);
- if (vop_vdev_inited(vdev)) {
- mask = EPOLLERR;
- goto done;
- }
- poll_wait(f, &vdev->waitq, wait);
- if (vop_vdev_inited(vdev)) {
- mask = EPOLLERR;
- } else if (vdev->poll_wake) {
- vdev->poll_wake = 0;
- mask = EPOLLIN | EPOLLOUT;
- }
-done:
- mutex_unlock(&vdev->vdev_mutex);
- return mask;
-}
-
-static inline int
-vop_query_offset(struct vop_vdev *vdev, unsigned long offset,
- unsigned long *size, unsigned long *pa)
-{
- struct vop_device *vpdev = vdev->vpdev;
- unsigned long start = MIC_DP_SIZE;
- int i;
-
- /*
- * MMAP interface is as follows:
- * offset region
- * 0x0 virtio device_page
- * 0x1000 first vring
- * 0x1000 + size of 1st vring second vring
- * ....
- */
- if (!offset) {
- *pa = virt_to_phys(vpdev->hw_ops->get_dp(vpdev));
- *size = MIC_DP_SIZE;
- return 0;
- }
-
- for (i = 0; i < vdev->dd->num_vq; i++) {
- struct vop_vringh *vvr = &vdev->vvr[i];
-
- if (offset == start) {
- *pa = virt_to_phys(vvr->vring.va);
- *size = vvr->vring.len;
- return 0;
- }
- start += vvr->vring.len;
- }
- return -1;
-}
-
-/*
- * Maps the device page and virtio rings to user space for readonly access.
- */
-static int vop_mmap(struct file *f, struct vm_area_struct *vma)
-{
- struct vop_vdev *vdev = f->private_data;
- unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
- unsigned long pa, size = vma->vm_end - vma->vm_start, size_rem = size;
- int i, err;
-
- err = vop_vdev_inited(vdev);
- if (err)
- goto ret;
- if (vma->vm_flags & VM_WRITE) {
- err = -EACCES;
- goto ret;
- }
- while (size_rem) {
- i = vop_query_offset(vdev, offset, &size, &pa);
- if (i < 0) {
- err = -EINVAL;
- goto ret;
- }
- err = remap_pfn_range(vma, vma->vm_start + offset,
- pa >> PAGE_SHIFT, size,
- vma->vm_page_prot);
- if (err)
- goto ret;
- size_rem -= size;
- offset += size;
- }
-ret:
- return err;
-}
-
-static const struct file_operations vop_fops = {
- .open = vop_open,
- .release = vop_release,
- .unlocked_ioctl = vop_ioctl,
- .poll = vop_poll,
- .mmap = vop_mmap,
- .owner = THIS_MODULE,
-};
-
-int vop_host_init(struct vop_info *vi)
-{
- int rc;
- struct miscdevice *mdev;
- struct vop_device *vpdev = vi->vpdev;
-
- INIT_LIST_HEAD(&vi->vdev_list);
- vi->dma_ch = vpdev->dma_ch;
- mdev = &vi->miscdev;
- mdev->minor = MISC_DYNAMIC_MINOR;
- snprintf(vi->name, sizeof(vi->name), "vop_virtio%d", vpdev->index);
- mdev->name = vi->name;
- mdev->fops = &vop_fops;
- mdev->parent = &vpdev->dev;
-
- rc = misc_register(mdev);
- if (rc)
- dev_err(&vpdev->dev, "%s failed rc %d\n", __func__, rc);
- return rc;
-}
-
-void vop_host_uninit(struct vop_info *vi)
-{
- struct list_head *pos, *tmp;
- struct vop_vdev *vdev;
-
- mutex_lock(&vi->vop_mutex);
- vop_virtio_reset_devices(vi);
- list_for_each_safe(pos, tmp, &vi->vdev_list) {
- vdev = list_entry(pos, struct vop_vdev, list);
- list_del(pos);
- reinit_completion(&vdev->destroy);
- mutex_unlock(&vi->vop_mutex);
- mutex_lock(&vdev->vdev_mutex);
- vop_virtio_del_device(vdev);
- vdev->deleted = true;
- mutex_unlock(&vdev->vdev_mutex);
- complete(&vdev->destroy);
- mutex_lock(&vi->vop_mutex);
- }
- mutex_unlock(&vi->vop_mutex);
- misc_deregister(&vi->miscdev);
-}
TMIO_MASK_INIT_RCAR2);
}
-/*
- * This is a temporary workaround! This driver used 'hw_reset' wrongly and the
- * fix for that showed a regression. So, we mimic the old behaviour until the
- * proper solution is found.
- */
-static void renesas_sdhi_hw_reset(struct mmc_host *mmc)
-{
- struct tmio_mmc_host *host = mmc_priv(mmc);
- renesas_sdhi_reset(host);
-}
-
#define SH_MOBILE_SDHI_MIN_TAP_ROW 3
static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host)
if (of_data && of_data->scc_offset) {
priv->scc_ctl = host->ctl + of_data->scc_offset;
host->reset = renesas_sdhi_reset;
- host->ops.hw_reset = renesas_sdhi_hw_reset;
- host->mmc->caps |= MMC_CAP_HW_RESET;
}
}
tmio_mmc_host_remove(host);
renesas_sdhi_clk_disable(host);
+ tmio_mmc_host_free(host);
return 0;
}
* Copyright (c) 2007 Freescale Semiconductor, Inc.
* Copyright (c) 2009 MontaVista Software, Inc.
* Copyright (c) 2010 Pengutronix e.K.
+ * Copyright 2020 NXP
* Author: Wolfram Sang <kernel@pengutronix.de>
*/
/* DLL Config 0 Register */
#define ESDHC_DLLCFG0 0x160
#define ESDHC_DLL_ENABLE 0x80000000
+#define ESDHC_DLL_RESET 0x40000000
#define ESDHC_DLL_FREQ_SEL 0x08000000
/* DLL Config 1 Register */
#define SDHCI_ARASAN_VENDOR_REGISTER 0x78
#define SDHCI_ARASAN_ITAPDLY_REGISTER 0xF0F8
+#define SDHCI_ARASAN_ITAPDLY_SEL_MASK 0xFF
+
#define SDHCI_ARASAN_OTAPDLY_REGISTER 0xF0FC
+#define SDHCI_ARASAN_OTAPDLY_SEL_MASK 0x3F
#define SDHCI_ARASAN_CQE_BASE_ADDR 0x200
#define VENDOR_ENHANCED_STROBE BIT(0)
u8 tap_delay, tap_max = 0;
int ret;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * ZynqMP does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
switch (host->timing) {
if (ret)
pr_err("Error setting Output Tap Delay\n");
+ /* Release DLL Reset */
+ zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_RELEASE);
+
return ret;
}
u8 tap_delay, tap_max = 0;
int ret;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * ZynqMP does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
+ /* Assert DLL Reset */
+ zynqmp_pm_sd_dll_reset(node_id, PM_DLL_RESET_ASSERT);
+
switch (host->timing) {
case MMC_TIMING_MMC_HS:
case MMC_TIMING_SD_HS:
struct sdhci_host *host = sdhci_arasan->host;
u8 tap_delay, tap_max = 0;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * Versal does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
switch (host->timing) {
regval = sdhci_readl(host, SDHCI_ARASAN_OTAPDLY_REGISTER);
regval |= SDHCI_OTAPDLY_ENABLE;
sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER);
+ regval &= ~SDHCI_ARASAN_OTAPDLY_SEL_MASK;
regval |= tap_delay;
sdhci_writel(host, regval, SDHCI_ARASAN_OTAPDLY_REGISTER);
}
struct sdhci_host *host = sdhci_arasan->host;
u8 tap_delay, tap_max = 0;
- /*
- * This is applicable for SDHCI_SPEC_300 and above
- * Versal does not set phase for <=25MHz clock.
- * If degrees is zero, no need to do anything.
- */
- if (host->version < SDHCI_SPEC_300 ||
- host->timing == MMC_TIMING_LEGACY ||
- host->timing == MMC_TIMING_UHS_SDR12 || !degrees)
+ /* This is applicable for SDHCI_SPEC_300 and above */
+ if (host->version < SDHCI_SPEC_300)
return 0;
switch (host->timing) {
sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER);
regval |= SDHCI_ITAPDLY_ENABLE;
sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER);
+ regval &= ~SDHCI_ARASAN_ITAPDLY_SEL_MASK;
regval |= tap_delay;
sdhci_writel(host, regval, SDHCI_ARASAN_ITAPDLY_REGISTER);
regval &= ~SDHCI_ITAPDLY_CHGWIN;
*
* Copyright (c) 2007, 2010, 2012 Freescale Semiconductor, Inc.
* Copyright (c) 2009 MontaVista Software, Inc.
+ * Copyright 2020 NXP
*
* Authors: Xiaobo Xie <X.Xie@freescale.com>
* Anton Vorontsov <avorontsov@ru.mvista.com>
#include <linux/clk.h>
#include <linux/ktime.h>
#include <linux/dma-mapping.h>
+#include <linux/iopoll.h>
#include <linux/mmc/host.h>
#include <linux/mmc/mmc.h>
#include "sdhci-pltfm.h"
if (host->mmc->actual_clock == MMC_HS200_MAX_DTR)
temp |= ESDHC_DLL_FREQ_SEL;
sdhci_writel(host, temp, ESDHC_DLLCFG0);
+
+ temp |= ESDHC_DLL_RESET;
+ sdhci_writel(host, temp, ESDHC_DLLCFG0);
+ udelay(1);
+ temp &= ~ESDHC_DLL_RESET;
+ sdhci_writel(host, temp, ESDHC_DLLCFG0);
+
+ /* Wait max 20 ms */
+ if (read_poll_timeout(sdhci_readl, temp,
+ temp & ESDHC_DLL_STS_SLV_LOCK,
+ 10, 20000, false,
+ host, ESDHC_DLLSTAT0))
+ pr_err("%s: timeout for delay chain lock.\n",
+ mmc_hostname(host->mmc));
+
temp = sdhci_readl(host, ESDHC_TBCTL);
sdhci_writel(host, temp | ESDHC_HS400_WNDW_ADJUST, ESDHC_TBCTL);
esdhc_tuning_block_enable(host, true);
+ /*
+ * The eSDHC controller takes the data timeout value into account
+ * during tuning. If the SD card is too slow sending the response, the
+ * timer will expire and a "Buffer Read Ready" interrupt without data
+ * is triggered. This leads to tuning errors.
+ *
+ * Just set the timeout to the maximum value because the core will
+ * already take care of it in sdhci_send_tuning().
+ */
+ sdhci_writeb(host, 0xe, SDHCI_TIMEOUT_CONTROL);
+
hs400_tuning = host->flags & SDHCI_HS400_TUNING;
do {
static struct soc_device_attribute soc_unreliable_pulse_detection[] = {
{ .family = "QorIQ LX2160A", .revision = "1.0", },
+ { .family = "QorIQ LX2160A", .revision = "2.0", },
+ { .family = "QorIQ LS1028A", .revision = "1.0", },
{ },
};
}
}
+static void sdhci_intel_set_uhs_signaling(struct sdhci_host *host,
+ unsigned int timing)
+{
+ /* Set UHS timing to SDR25 for High Speed mode */
+ if (timing == MMC_TIMING_MMC_HS || timing == MMC_TIMING_SD_HS)
+ timing = MMC_TIMING_UHS_SDR25;
+ sdhci_set_uhs_signaling(host, timing);
+}
+
#define INTEL_HS400_ES_REG 0x78
#define INTEL_HS400_ES_BIT BIT(0)
.enable_dma = sdhci_pci_enable_dma,
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_reset,
- .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_uhs_signaling = sdhci_intel_set_uhs_signaling,
.hw_reset = sdhci_pci_hw_reset,
};
.enable_dma = sdhci_pci_enable_dma,
.set_bus_width = sdhci_set_bus_width,
.reset = sdhci_cqhci_reset,
- .set_uhs_signaling = sdhci_set_uhs_signaling,
+ .set_uhs_signaling = sdhci_intel_set_uhs_signaling,
.hw_reset = sdhci_pci_hw_reset,
.irq = sdhci_cqhci_irq,
};
/*
* In case of Version 4.10 or later, use of 'Auto CMD Auto
* Select' is recommended rather than use of 'Auto CMD12
- * Enable' or 'Auto CMD23 Enable'.
+ * Enable' or 'Auto CMD23 Enable'. We require Version 4 Mode
+ * here because some controllers (e.g sdhci-of-dwmshc) expect it.
*/
- if (host->version >= SDHCI_SPEC_410 && (use_cmd12 || use_cmd23)) {
+ if (host->version >= SDHCI_SPEC_410 && host->v4_mode &&
+ (use_cmd12 || use_cmd23)) {
*mode |= SDHCI_TRNS_AUTO_SEL;
ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
if (host->reset)
host->reset(host);
+ tmio_mmc_abort_dma(host);
+
if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) {
sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
/* Ready for new calls */
host->mrq = NULL;
-
- tmio_mmc_abort_dma(host);
mmc_request_done(host->mmc, mrq);
}
switch (ios->power_mode) {
case MMC_POWER_OFF:
tmio_mmc_power_off(host);
+ /* Downgrade ensures a sane state for tuning HW (e.g. SCC) */
+ if (host->mmc->ops->hs400_downgrade)
+ host->mmc->ops->hs400_downgrade(host->mmc);
host->set_clock(host, 0);
break;
case MMC_POWER_UP:
return 0;
}
+static int gpio_nand_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
static const struct nand_controller_ops gpio_nand_ops = {
.exec_op = gpio_nand_exec_op,
+ .attach_chip = gpio_nand_attach_chip,
.setup_interface = gpio_nand_setup_interface,
};
return err;
}
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- this->ecc.algo = NAND_ECC_ALGO_HAMMING;
-
platform_set_drvdata(pdev, priv);
/* Set chip enabled but write protected */
return ret;
}
+static int au1550nd_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
static const struct nand_controller_ops au1550nd_ops = {
.exec_op = au1550nd_exec_op,
+ .attach_chip = au1550nd_attach_chip,
};
static int au1550nd_probe(struct platform_device *pdev)
nand_controller_init(&ctx->controller);
ctx->controller.ops = &au1550nd_ops;
this->controller = &ctx->controller;
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- this->ecc.algo = NAND_ECC_ALGO_HAMMING;
if (pd->devwidth)
this->options |= NAND_BUSWIDTH_16;
static struct cs553x_nand_controller *controllers[4];
+static int cs553x_attach_chip(struct nand_chip *chip)
+{
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
+ chip->ecc.size = 256;
+ chip->ecc.bytes = 3;
+ chip->ecc.hwctl = cs_enable_hwecc;
+ chip->ecc.calculate = cs_calculate_ecc;
+ chip->ecc.correct = nand_correct_data;
+ chip->ecc.strength = 1;
+
+ return 0;
+}
+
static const struct nand_controller_ops cs553x_nand_controller_ops = {
.exec_op = cs553x_exec_op,
+ .attach_chip = cs553x_attach_chip,
};
static int __init cs553x_init_one(int cs, int mmio, unsigned long adr)
goto out_mtd;
}
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- this->ecc.size = 256;
- this->ecc.bytes = 3;
- this->ecc.hwctl = cs_enable_hwecc;
- this->ecc.calculate = cs_calculate_ecc;
- this->ecc.correct = nand_correct_data;
- this->ecc.strength = 1;
-
/* Enable the following for a flash based bad block table */
this->bbt_options = NAND_BBT_USE_FLASH;
if (IS_ERR(pdata))
return PTR_ERR(pdata);
+ /* Use board-specific ECC config */
+ info->chip.ecc.engine_type = pdata->engine_type;
+ info->chip.ecc.placement = pdata->ecc_placement;
+
switch (info->chip.ecc.engine_type) {
case NAND_ECC_ENGINE_TYPE_NONE:
pdata->ecc_bits = 0;
info->mask_ale = pdata->mask_ale ? : MASK_ALE;
info->mask_cle = pdata->mask_cle ? : MASK_CLE;
- /* Use board-specific ECC config */
- info->chip.ecc.engine_type = pdata->engine_type;
- info->chip.ecc.placement = pdata->ecc_placement;
-
spin_lock_irq(&davinci_nand_lock);
/* put CSxNAND into NAND mode */
return 1;
}
+static int doc200x_attach_chip(struct nand_chip *chip)
+{
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
+ chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
+ chip->ecc.size = 512;
+ chip->ecc.bytes = 6;
+ chip->ecc.strength = 2;
+ chip->ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
+ chip->ecc.hwctl = doc200x_enable_hwecc;
+ chip->ecc.calculate = doc200x_calculate_ecc;
+ chip->ecc.correct = doc200x_correct_data;
+
+ return 0;
+}
+
static const struct nand_controller_ops doc200x_ops = {
.exec_op = doc200x_exec_op,
+ .attach_chip = doc200x_attach_chip,
};
static const struct nand_controller_ops doc2001plus_ops = {
.exec_op = doc2001plus_exec_op,
+ .attach_chip = doc200x_attach_chip,
};
static int __init doc_probe(unsigned long physadr)
nand->controller = &doc->base;
nand_set_controller_data(nand, doc);
- nand->ecc.hwctl = doc200x_enable_hwecc;
- nand->ecc.calculate = doc200x_calculate_ecc;
- nand->ecc.correct = doc200x_correct_data;
-
- nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- nand->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
- nand->ecc.size = 512;
- nand->ecc.bytes = 6;
- nand->ecc.strength = 2;
- nand->ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
nand->bbt_options = NAND_BBT_USE_FLASH;
/* Skip the automatic BBT scan so we can run it manually */
nand->options |= NAND_SKIP_BBTSCAN | NAND_NO_BBM_QUIRK;
{
struct mtd_info *mtd = nand_to_mtd(chip);
struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
+ struct fsl_ifc_ctrl *ctrl = priv->ctrl;
+ struct fsl_ifc_global __iomem *ifc_global = ctrl->gregs;
+ u32 csor;
+
+ csor = ifc_in32(&ifc_global->csor_cs[priv->bank].csor);
+
+ /* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
+ if (csor & CSOR_NAND_ECC_DEC_EN) {
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
+ mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
+
+ /* Hardware generates ECC per 512 Bytes */
+ chip->ecc.size = 512;
+ if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
+ chip->ecc.bytes = 8;
+ chip->ecc.strength = 4;
+ } else {
+ chip->ecc.bytes = 16;
+ chip->ecc.strength = 8;
+ }
+ } else {
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+ }
dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
nanddev_ntargets(&chip->base));
return -ENODEV;
}
- /* Must also set CSOR_NAND_ECC_ENC_EN if DEC_EN set */
- if (csor & CSOR_NAND_ECC_DEC_EN) {
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- mtd_set_ooblayout(mtd, &fsl_ifc_ooblayout_ops);
-
- /* Hardware generates ECC per 512 Bytes */
- chip->ecc.size = 512;
- if ((csor & CSOR_NAND_ECC_MODE_MASK) == CSOR_NAND_ECC_MODE_4) {
- chip->ecc.bytes = 8;
- chip->ecc.strength = 4;
- } else {
- chip->ecc.bytes = 16;
- chip->ecc.strength = 8;
- }
- } else {
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
- }
-
ret = fsl_ifc_sram_init(priv);
if (ret)
return ret;
struct mtd_info *mtd = nand_to_mtd(nand);
struct fsmc_nand_data *host = nand_to_fsmc(nand);
+ if (nand->ecc.engine_type == NAND_ECC_ENGINE_TYPE_INVALID)
+ nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
+
+ if (!nand->ecc.size)
+ nand->ecc.size = 512;
+
+ if (AMBA_REV_BITS(host->pid) >= 8) {
+ nand->ecc.read_page = fsmc_read_page_hwecc;
+ nand->ecc.calculate = fsmc_read_hwecc_ecc4;
+ nand->ecc.correct = fsmc_bch8_correct_data;
+ nand->ecc.bytes = 13;
+ nand->ecc.strength = 8;
+ }
+
if (AMBA_REV_BITS(host->pid) >= 8) {
switch (mtd->oobsize) {
case 16:
dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
nand->ecc.calculate = fsmc_read_hwecc_ecc1;
nand->ecc.correct = nand_correct_data;
+ nand->ecc.hwctl = fsmc_enable_hwecc;
nand->ecc.bytes = 3;
nand->ecc.strength = 1;
nand->ecc.options |= NAND_ECC_SOFT_HAMMING_SM_ORDER;
mtd->dev.parent = &pdev->dev;
- /*
- * Setup default ECC mode. nand_dt_init() called from nand_scan_ident()
- * can overwrite this value if the DT provides a different value.
- */
- nand->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- nand->ecc.hwctl = fsmc_enable_hwecc;
- nand->ecc.size = 512;
nand->badblockbits = 7;
if (host->mode == USE_DMA_ACCESS) {
nand->options |= NAND_KEEP_TIMINGS;
}
- if (AMBA_REV_BITS(host->pid) >= 8) {
- nand->ecc.read_page = fsmc_read_page_hwecc;
- nand->ecc.calculate = fsmc_read_hwecc_ecc4;
- nand->ecc.correct = fsmc_bch8_correct_data;
- nand->ecc.bytes = 13;
- nand->ecc.strength = 8;
- }
-
nand_controller_init(&host->base);
host->base.ops = &fsmc_nand_controller_ops;
nand->controller = &host->base;
return ret;
}
+static int gpio_nand_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
static const struct nand_controller_ops gpio_nand_ops = {
.exec_op = gpio_nand_exec_op,
+ .attach_chip = gpio_nand_attach_chip,
};
#ifdef CONFIG_OF
gpiomtd->base.ops = &gpio_nand_ops;
nand_set_flash_node(chip, pdev->dev.of_node);
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
chip->options = gpiomtd->plat.options;
chip->controller = &gpiomtd->base;
struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
struct device *dev = &host->pdev->dev;
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
if (!host->dma_buf)
return -ENOMEM;
if (!host->dummy_buf)
return -ENOMEM;
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
chip->ecc.size = 512;
+ chip->ecc.hwctl = lpc32xx_ecc_enable;
+ chip->ecc.read_page_raw = lpc32xx_read_page;
+ chip->ecc.read_page = lpc32xx_read_page;
+ chip->ecc.write_page_raw = lpc32xx_write_page_lowlevel;
+ chip->ecc.write_page = lpc32xx_write_page_lowlevel;
+ chip->ecc.write_oob = lpc32xx_write_oob;
+ chip->ecc.read_oob = lpc32xx_read_oob;
+ chip->ecc.strength = 4;
+ chip->ecc.bytes = 10;
+
mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
host->mlcsubpages = mtd->writesize / 512;
platform_set_drvdata(pdev, host);
/* Initialize function pointers */
- nand_chip->ecc.hwctl = lpc32xx_ecc_enable;
- nand_chip->ecc.read_page_raw = lpc32xx_read_page;
- nand_chip->ecc.read_page = lpc32xx_read_page;
- nand_chip->ecc.write_page_raw = lpc32xx_write_page_lowlevel;
- nand_chip->ecc.write_page = lpc32xx_write_page_lowlevel;
- nand_chip->ecc.write_oob = lpc32xx_write_oob;
- nand_chip->ecc.read_oob = lpc32xx_read_oob;
- nand_chip->ecc.strength = 4;
- nand_chip->ecc.bytes = 10;
nand_chip->legacy.waitfunc = lpc32xx_waitfunc;
nand_chip->options = NAND_NO_SUBPAGE_WRITE;
struct mtd_info *mtd = nand_to_mtd(chip);
struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
/* OOB and ECC CPU and DMA work areas */
host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
if (mtd->writesize <= 512)
mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+ chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
/* These sizes remain the same regardless of page size */
chip->ecc.size = 256;
+ chip->ecc.strength = 1;
chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
chip->ecc.prepad = 0;
chip->ecc.postpad = 0;
+ chip->ecc.read_page_raw = lpc32xx_nand_read_page_raw_syndrome;
+ chip->ecc.read_page = lpc32xx_nand_read_page_syndrome;
+ chip->ecc.write_page_raw = lpc32xx_nand_write_page_raw_syndrome;
+ chip->ecc.write_page = lpc32xx_nand_write_page_syndrome;
+ chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome;
+ chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome;
+ chip->ecc.calculate = lpc32xx_nand_ecc_calculate;
+ chip->ecc.correct = nand_correct_data;
+ chip->ecc.hwctl = lpc32xx_nand_ecc_enable;
/*
* Use a custom BBT marker setup for small page FLASH that
platform_set_drvdata(pdev, host);
/* NAND callbacks for LPC32xx SLC hardware */
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
chip->legacy.read_byte = lpc32xx_nand_read_byte;
chip->legacy.read_buf = lpc32xx_nand_read_buf;
chip->legacy.write_buf = lpc32xx_nand_write_buf;
- chip->ecc.read_page_raw = lpc32xx_nand_read_page_raw_syndrome;
- chip->ecc.read_page = lpc32xx_nand_read_page_syndrome;
- chip->ecc.write_page_raw = lpc32xx_nand_write_page_raw_syndrome;
- chip->ecc.write_page = lpc32xx_nand_write_page_syndrome;
- chip->ecc.write_oob = lpc32xx_nand_write_oob_syndrome;
- chip->ecc.read_oob = lpc32xx_nand_read_oob_syndrome;
- chip->ecc.calculate = lpc32xx_nand_ecc_calculate;
- chip->ecc.correct = nand_correct_data;
- chip->ecc.strength = 1;
- chip->ecc.hwctl = lpc32xx_nand_ecc_enable;
/*
* Allocate a large enough buffer for a single huge page plus
#define NFC_TIMEOUT (HZ / 10) /* 1/10 s */
struct mpc5121_nfc_prv {
+ struct nand_controller controller;
struct nand_chip chip;
int irq;
void __iomem *regs;
iounmap(prv->csreg);
}
+static int mpc5121_nfc_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
+static const struct nand_controller_ops mpc5121_nfc_ops = {
+ .attach_chip = mpc5121_nfc_attach_chip,
+};
+
static int mpc5121_nfc_probe(struct platform_device *op)
{
struct device_node *dn = op->dev.of_node;
chip = &prv->chip;
mtd = nand_to_mtd(chip);
+ nand_controller_init(&prv->controller);
+ prv->controller.ops = &mpc5121_nfc_ops;
+ chip->controller = &prv->controller;
+
mtd->dev.parent = dev;
nand_set_controller_data(chip, prv);
nand_set_flash_node(chip, dn);
chip->legacy.set_features = nand_get_set_features_notsupp;
chip->legacy.get_features = nand_get_set_features_notsupp;
chip->bbt_options = NAND_BBT_USE_FLASH;
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
/* Support external chip-select logic on ADS5121 board */
if (of_machine_is_compatible("fsl,mpc5121ads")) {
struct mxc_nand_host *host = nand_get_controller_data(chip);
struct device *dev = mtd->dev.parent;
+ chip->ecc.bytes = host->devtype_data->eccbytes;
+ host->eccsize = host->devtype_data->eccsize;
+ chip->ecc.size = 512;
+ mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
+
switch (chip->ecc.engine_type) {
case NAND_ECC_ENGINE_TYPE_ON_HOST:
chip->ecc.read_page = mxc_nand_read_page;
if (host->devtype_data->axi_offset)
host->regs_axi = host->base + host->devtype_data->axi_offset;
- this->ecc.bytes = host->devtype_data->eccbytes;
- host->eccsize = host->devtype_data->eccsize;
-
this->legacy.select_chip = host->devtype_data->select_chip;
- this->ecc.size = 512;
- mtd_set_ooblayout(mtd, host->devtype_data->ooblayout);
-
- if (host->pdata.hw_ecc) {
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- } else {
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- this->ecc.algo = NAND_ECC_ALGO_HAMMING;
- }
/* NAND bus width determines access functions used by upper layer */
if (host->pdata.width == 2)
#include <linux/platform_data/mtd-orion_nand.h>
struct orion_nand_info {
+ struct nand_controller controller;
struct nand_chip chip;
struct clk *clk;
};
buf[i++] = readb(io_base);
}
+static int orion_nand_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
+static const struct nand_controller_ops orion_nand_ops = {
+ .attach_chip = orion_nand_attach_chip,
+};
+
static int __init orion_nand_probe(struct platform_device *pdev)
{
struct orion_nand_info *info;
nc = &info->chip;
mtd = nand_to_mtd(nc);
+ nand_controller_init(&info->controller);
+ info->controller.ops = &orion_nand_ops;
+ nc->controller = &info->controller;
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
io_base = devm_ioremap_resource(&pdev->dev, res);
nc->legacy.IO_ADDR_R = nc->legacy.IO_ADDR_W = io_base;
nc->legacy.cmd_ctrl = orion_nand_cmd_ctrl;
nc->legacy.read_buf = orion_nand_read_buf;
- nc->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- nc->ecc.algo = NAND_ECC_ALGO_HAMMING;
if (board->chip_delay)
nc->legacy.chip_delay = board->chip_delay;
static unsigned int lpcctl;
static struct mtd_info *pasemi_nand_mtd;
+static struct nand_controller controller;
static const char driver_name[] = "pasemi-nand";
static void pasemi_read_buf(struct nand_chip *chip, u_char *buf, int len)
return !!(inl(lpcctl) & LBICTRL_LPCCTL_NR);
}
+static int pasemi_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
+static const struct nand_controller_ops pasemi_ops = {
+ .attach_chip = pasemi_attach_chip,
+};
+
static int pasemi_nand_probe(struct platform_device *ofdev)
{
struct device *dev = &ofdev->dev;
goto out;
}
+ controller.ops = &pasemi_ops;
+ nand_controller_init(&controller);
+ chip->controller = &controller;
+
pasemi_nand_mtd = nand_to_mtd(chip);
/* Link the private data with the MTD structure */
chip->legacy.read_buf = pasemi_read_buf;
chip->legacy.write_buf = pasemi_write_buf;
chip->legacy.chip_delay = 0;
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
/* Enable the following for a flash based bad block table */
chip->bbt_options = NAND_BBT_USE_FLASH;
#include <linux/mtd/platnand.h>
struct plat_nand_data {
+ struct nand_controller controller;
struct nand_chip chip;
void __iomem *io_base;
};
+static int plat_nand_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
+static const struct nand_controller_ops plat_nand_ops = {
+ .attach_chip = plat_nand_attach_chip,
+};
+
/*
* Probe for the NAND device.
*/
if (!data)
return -ENOMEM;
+ data->controller.ops = &plat_nand_ops;
+ nand_controller_init(&data->controller);
+ data->chip.controller = &data->controller;
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
data->io_base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(data->io_base))
data->chip.options |= pdata->chip.options;
data->chip.bbt_options |= pdata->chip.bbt_options;
- data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
-
platform_set_drvdata(pdev, data);
/* Handle any platform specific setup */
return ret;
}
+static int r852_attach_chip(struct nand_chip *chip)
+{
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
+ chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
+ chip->ecc.size = R852_DMA_LEN;
+ chip->ecc.bytes = SM_OOB_SIZE;
+ chip->ecc.strength = 2;
+ chip->ecc.hwctl = r852_ecc_hwctl;
+ chip->ecc.calculate = r852_ecc_calculate;
+ chip->ecc.correct = r852_ecc_correct;
+
+ /* TODO: hack */
+ chip->ecc.read_oob = r852_read_oob;
+
+ return 0;
+}
+
+static const struct nand_controller_ops r852_ops = {
+ .attach_chip = r852_attach_chip,
+};
+
static int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
{
int error;
chip->legacy.read_buf = r852_read_buf;
chip->legacy.write_buf = r852_write_buf;
- /* ecc */
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- chip->ecc.placement = NAND_ECC_PLACEMENT_INTERLEAVED;
- chip->ecc.size = R852_DMA_LEN;
- chip->ecc.bytes = SM_OOB_SIZE;
- chip->ecc.strength = 2;
- chip->ecc.hwctl = r852_ecc_hwctl;
- chip->ecc.calculate = r852_ecc_calculate;
- chip->ecc.correct = r852_ecc_correct;
-
- /* TODO: hack */
- chip->ecc.read_oob = r852_read_oob;
-
/* init our device structure */
dev = kzalloc(sizeof(struct r852_device), GFP_KERNEL);
dev->pci_dev = pci_dev;
pci_set_drvdata(pci_dev, dev);
+ nand_controller_init(&dev->controller);
+ dev->controller.ops = &r852_ops;
+ chip->controller = &dev->controller;
+
dev->bounce_buffer = dma_alloc_coherent(&pci_dev->dev, R852_DMA_LEN,
&dev->phys_bounce_buffer, GFP_KERNEL);
#define DMA_MEMORY 1
struct r852_device {
+ struct nand_controller controller;
void __iomem *mmio; /* mmio */
struct nand_chip *chip; /* nand chip backpointer */
struct pci_dev *pci_dev; /* pci backpointer */
#include <linux/io.h>
struct sharpsl_nand {
+ struct nand_controller controller;
struct nand_chip chip;
void __iomem *io;
return readb(sharpsl->io + ECCCNTR) != 0;
}
+static int sharpsl_attach_chip(struct nand_chip *chip)
+{
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
+ chip->ecc.size = 256;
+ chip->ecc.bytes = 3;
+ chip->ecc.strength = 1;
+ chip->ecc.hwctl = sharpsl_nand_enable_hwecc;
+ chip->ecc.calculate = sharpsl_nand_calculate_ecc;
+ chip->ecc.correct = nand_correct_data;
+
+ return 0;
+}
+
+static const struct nand_controller_ops sharpsl_ops = {
+ .attach_chip = sharpsl_attach_chip,
+};
+
/*
* Main initialization routine
*/
/* Get pointer to private data */
this = (struct nand_chip *)(&sharpsl->chip);
+ nand_controller_init(&sharpsl->controller);
+ sharpsl->controller.ops = &sharpsl_ops;
+ this->controller = &sharpsl->controller;
+
/* Link the private data with the MTD structure */
mtd = nand_to_mtd(this);
mtd->dev.parent = &pdev->dev;
this->legacy.dev_ready = sharpsl_nand_dev_ready;
/* 15 us command delay time */
this->legacy.chip_delay = 15;
- /* set eccmode using hardware ECC */
- this->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- this->ecc.size = 256;
- this->ecc.bytes = 3;
- this->ecc.strength = 1;
this->badblock_pattern = data->badblock_pattern;
- this->ecc.hwctl = sharpsl_nand_enable_hwecc;
- this->ecc.calculate = sharpsl_nand_calculate_ecc;
- this->ecc.correct = nand_correct_data;
/* Scan to find existence of the device */
err = nand_scan(this, 1);
#define FPGA_NAND_DATA_SHIFT 16
struct socrates_nand_host {
+ struct nand_controller controller;
struct nand_chip nand_chip;
void __iomem *io_base;
struct device *dev;
return 1;
}
+static int socrates_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
+static const struct nand_controller_ops socrates_ops = {
+ .attach_chip = socrates_attach_chip,
+};
+
/*
* Probe for the NAND device.
*/
mtd = nand_to_mtd(nand_chip);
host->dev = &ofdev->dev;
+ nand_controller_init(&host->controller);
+ host->controller.ops = &socrates_ops;
+ nand_chip->controller = &host->controller;
+
/* link the private data structures */
nand_set_controller_data(nand_chip, host);
nand_set_flash_node(nand_chip, ofdev->dev.of_node);
nand_chip->legacy.read_buf = socrates_nand_read_buf;
nand_chip->legacy.dev_ready = socrates_nand_device_ready;
- /* enable ECC */
- nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- nand_chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
-
/* TODO: I have no idea what real delay is. */
nand_chip->legacy.chip_delay = 20; /* 20us command delay time */
return -EINVAL;
}
+ /* Default ECC settings in case they are not set in the device tree */
+ if (!chip->ecc.size)
+ chip->ecc.size = FMC2_ECC_STEP_SIZE;
+
+ if (!chip->ecc.strength)
+ chip->ecc.strength = FMC2_ECC_BCH8;
+
ret = nand_ecc_choose_conf(chip, &stm32_fmc2_nfc_ecc_caps,
mtd->oobsize - FMC2_BBM_LEN);
if (ret) {
mtd_set_ooblayout(mtd, &stm32_fmc2_nfc_ooblayout_ops);
- if (chip->options & NAND_BUSWIDTH_16)
- stm32_fmc2_nfc_set_buswidth_16(nfc, true);
+ stm32_fmc2_nfc_setup(chip);
return 0;
}
chip->options |= NAND_BUSWIDTH_AUTO | NAND_NO_SUBPAGE_WRITE |
NAND_USES_DMA;
- /* Default ECC settings */
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- chip->ecc.size = FMC2_ECC_STEP_SIZE;
- chip->ecc.strength = FMC2_ECC_BCH8;
-
/* Scan to find existence of the device */
ret = nand_scan(chip, nand->ncs);
if (ret)
/*--------------------------------------------------------------------------*/
struct tmio_nand {
+ struct nand_controller controller;
struct nand_chip chip;
struct completion comp;
cell->disable(dev);
}
+static int tmio_attach_chip(struct nand_chip *chip)
+{
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
+ chip->ecc.size = 512;
+ chip->ecc.bytes = 6;
+ chip->ecc.strength = 2;
+ chip->ecc.hwctl = tmio_nand_enable_hwecc;
+ chip->ecc.calculate = tmio_nand_calculate_ecc;
+ chip->ecc.correct = tmio_nand_correct_data;
+
+ return 0;
+}
+
+static const struct nand_controller_ops tmio_ops = {
+ .attach_chip = tmio_attach_chip,
+};
+
static int tmio_probe(struct platform_device *dev)
{
struct tmio_nand_data *data = dev_get_platdata(&dev->dev);
mtd->name = "tmio-nand";
mtd->dev.parent = &dev->dev;
+ nand_controller_init(&tmio->controller);
+ tmio->controller.ops = &tmio_ops;
+ nand_chip->controller = &tmio->controller;
+
tmio->ccr = devm_ioremap(&dev->dev, ccr->start, resource_size(ccr));
if (!tmio->ccr)
return -EIO;
nand_chip->legacy.write_buf = tmio_nand_write_buf;
nand_chip->legacy.read_buf = tmio_nand_read_buf;
- /* set eccmode using hardware ECC */
- nand_chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- nand_chip->ecc.size = 512;
- nand_chip->ecc.bytes = 6;
- nand_chip->ecc.strength = 2;
- nand_chip->ecc.hwctl = tmio_nand_enable_hwecc;
- nand_chip->ecc.calculate = tmio_nand_calculate_ecc;
- nand_chip->ecc.correct = tmio_nand_correct_data;
-
if (data)
nand_chip->badblock_pattern = data->badblock_pattern;
{
struct mtd_info *mtd = nand_to_mtd(chip);
+ if (chip->ecc.engine_type != NAND_ECC_ENGINE_TYPE_ON_HOST)
+ return 0;
+
+ chip->ecc.strength = 1;
+
if (mtd->writesize >= 512) {
chip->ecc.size = 512;
chip->ecc.bytes = 6;
chip->ecc.bytes = 3;
}
+ chip->ecc.calculate = txx9ndfmc_calculate_ecc;
+ chip->ecc.correct = txx9ndfmc_correct_data;
+ chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
+
return 0;
}
chip->legacy.write_buf = txx9ndfmc_write_buf;
chip->legacy.cmd_ctrl = txx9ndfmc_cmd_ctrl;
chip->legacy.dev_ready = txx9ndfmc_dev_ready;
- chip->ecc.calculate = txx9ndfmc_calculate_ecc;
- chip->ecc.correct = txx9ndfmc_correct_data;
- chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
- chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_ON_HOST;
- chip->ecc.strength = 1;
chip->legacy.chip_delay = 100;
chip->controller = &drvdata->controller;
#define NAND_CON_NANDM 1
struct xway_nand_data {
+ struct nand_controller controller;
struct nand_chip chip;
unsigned long csflags;
void __iomem *nandaddr;
xway_writeb(nand_to_mtd(chip), NAND_WRITE_DATA, buf[i]);
}
+static int xway_attach_chip(struct nand_chip *chip)
+{
+ chip->ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
+ chip->ecc.algo = NAND_ECC_ALGO_HAMMING;
+
+ return 0;
+}
+
+static const struct nand_controller_ops xway_nand_ops = {
+ .attach_chip = xway_attach_chip,
+};
+
/*
* Probe for the NAND device.
*/
data->chip.legacy.read_byte = xway_read_byte;
data->chip.legacy.chip_delay = 30;
- data->chip.ecc.engine_type = NAND_ECC_ENGINE_TYPE_SOFT;
- data->chip.ecc.algo = NAND_ECC_ALGO_HAMMING;
+ nand_controller_init(&data->controller);
+ data->controller.ops = &xway_nand_ops;
+ data->chip.controller = &data->controller;
platform_set_drvdata(pdev, data);
nand_set_controller_data(&data->chip, data);
memcpy(&sfdp_params, nor->params, sizeof(sfdp_params));
- if (spi_nor_parse_sfdp(nor, &sfdp_params)) {
+ if (spi_nor_parse_sfdp(nor, nor->params)) {
+ memcpy(nor->params, &sfdp_params, sizeof(*nor->params));
nor->addr_width = 0;
nor->flags &= ~SNOR_F_4B_OPCODES;
- } else {
- memcpy(nor->params, &sfdp_params, sizeof(*nor->params));
}
}
/* already configured from SFDP */
} else if (nor->info->addr_width) {
nor->addr_width = nor->info->addr_width;
- } else if (nor->mtd.size > 0x1000000) {
- /* enable 4-byte addressing if the device exceeds 16MiB */
- nor->addr_width = 4;
} else {
nor->addr_width = 3;
}
+ if (nor->addr_width == 3 && nor->mtd.size > 0x1000000) {
+ /* enable 4-byte addressing if the device exceeds 16MiB */
+ nor->addr_width = 4;
+ }
+
if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) {
dev_dbg(nor->dev, "address width is too large: %u\n",
nor->addr_width);
slave->dev->flags &= ~IFF_SLAVE;
}
-static struct slave *bond_alloc_slave(struct bonding *bond)
+static void slave_kobj_release(struct kobject *kobj)
+{
+ struct slave *slave = to_slave(kobj);
+ struct bonding *bond = bond_get_bond_by_slave(slave);
+
+ cancel_delayed_work_sync(&slave->notify_work);
+ if (BOND_MODE(bond) == BOND_MODE_8023AD)
+ kfree(SLAVE_AD_INFO(slave));
+
+ kfree(slave);
+}
+
+static struct kobj_type slave_ktype = {
+ .release = slave_kobj_release,
+#ifdef CONFIG_SYSFS
+ .sysfs_ops = &slave_sysfs_ops,
+#endif
+};
+
+static int bond_kobj_init(struct slave *slave)
+{
+ int err;
+
+ err = kobject_init_and_add(&slave->kobj, &slave_ktype,
+ &(slave->dev->dev.kobj), "bonding_slave");
+ if (err)
+ kobject_put(&slave->kobj);
+
+ return err;
+}
+
+static struct slave *bond_alloc_slave(struct bonding *bond,
+ struct net_device *slave_dev)
{
struct slave *slave = NULL;
if (!slave)
return NULL;
+ slave->bond = bond;
+ slave->dev = slave_dev;
+
+ if (bond_kobj_init(slave))
+ return NULL;
+
if (BOND_MODE(bond) == BOND_MODE_8023AD) {
SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info),
GFP_KERNEL);
if (!SLAVE_AD_INFO(slave)) {
- kfree(slave);
+ kobject_put(&slave->kobj);
return NULL;
}
}
return slave;
}
-static void bond_free_slave(struct slave *slave)
-{
- struct bonding *bond = bond_get_bond_by_slave(slave);
-
- cancel_delayed_work_sync(&slave->notify_work);
- if (BOND_MODE(bond) == BOND_MODE_8023AD)
- kfree(SLAVE_AD_INFO(slave));
-
- kfree(slave);
-}
-
static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info)
{
info->bond_mode = BOND_MODE(bond);
goto err_undo_flags;
}
- new_slave = bond_alloc_slave(bond);
+ new_slave = bond_alloc_slave(bond, slave_dev);
if (!new_slave) {
res = -ENOMEM;
goto err_undo_flags;
}
- new_slave->bond = bond;
- new_slave->dev = slave_dev;
/* Set the new_slave's queue_id to be zero. Queue ID mapping
* is set via sysfs or module option if desired.
*/
dev_set_mtu(slave_dev, new_slave->original_mtu);
err_free:
- bond_free_slave(new_slave);
+ kobject_put(&new_slave->kobj);
err_undo_flags:
/* Enslave of first slave has failed and we need to fix master's mac */
if (!netif_is_bond_master(slave_dev))
slave_dev->priv_flags &= ~IFF_BONDING;
- bond_free_slave(slave);
+ kobject_put(&slave->kobj);
return 0;
}
};
#define to_slave_attr(_at) container_of(_at, struct slave_attribute, attr)
-#define to_slave(obj) container_of(obj, struct slave, kobj)
static ssize_t slave_show(struct kobject *kobj,
struct attribute *attr, char *buf)
return slave_attr->show(slave, buf);
}
-static const struct sysfs_ops slave_sysfs_ops = {
+const struct sysfs_ops slave_sysfs_ops = {
.show = slave_show,
};
-static struct kobj_type slave_ktype = {
-#ifdef CONFIG_SYSFS
- .sysfs_ops = &slave_sysfs_ops,
-#endif
-};
-
int bond_sysfs_slave_add(struct slave *slave)
{
const struct slave_attribute **a;
int err;
- err = kobject_init_and_add(&slave->kobj, &slave_ktype,
- &(slave->dev->dev.kobj), "bonding_slave");
- if (err) {
- kobject_put(&slave->kobj);
- return err;
- }
-
for (a = slave_attrs; *a; ++a) {
err = sysfs_create_file(&slave->kobj, &((*a)->attr));
if (err) {
for (a = slave_attrs; *a; ++a)
sysfs_remove_file(&slave->kobj, &((*a)->attr));
-
- kobject_put(&slave->kobj);
}
time_after(time_out, jiffies))
cpu_relax();
- if (time_after(jiffies, time_out))
- return -ETIMEDOUT;
+ if (time_after(jiffies, time_out)) {
+ ret = -ETIMEDOUT;
+ goto err_out;
+ }
ret = c_can_start(dev);
- if (!ret)
- c_can_irq_control(priv, true);
+ if (ret)
+ goto err_out;
+
+ c_can_irq_control(priv, true);
+
+ return 0;
+
+err_out:
+ c_can_reset_ram(priv, false);
+ c_can_pm_runtime_put_sync(priv);
return ret;
}
*/
struct sk_buff *skb = priv->echo_skb[idx];
struct canfd_frame *cf = (struct canfd_frame *)skb->data;
- u8 len = cf->len;
- *len_ptr = len;
+ /* get the real payload length for netdev statistics */
+ if (cf->can_id & CAN_RTR_FLAG)
+ *len_ptr = 0;
+ else
+ *len_ptr = cf->len;
+
priv->echo_skb[idx] = NULL;
return skb;
if (!skb)
return 0;
- netif_rx(skb);
+ skb_get(skb);
+ if (netif_rx(skb) == NET_RX_SUCCESS)
+ dev_consume_skb_any(skb);
+ else
+ dev_kfree_skb_any(skb);
return len;
}
cf->can_id |= CAN_ERR_RESTARTED;
- netif_rx(skb);
+ netif_rx_ni(skb);
stats->rx_packets++;
stats->rx_bytes += cf->can_dlc;
* MX8MP FlexCAN3 03.00.17.01 yes yes no yes yes yes
* VF610 FlexCAN3 ? no yes no yes yes? no
* LS1021A FlexCAN2 03.00.04.00 no yes no no yes no
- * LX2160A FlexCAN3 03.00.23.00 no yes no no yes yes
+ * LX2160A FlexCAN3 03.00.23.00 no yes no yes yes yes
*
* Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
*/
static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP |
- FLEXCAN_QUIRK_BROKEN_PERR_STATE,
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_ECC,
};
static const struct flexcan_devtype_data fsl_ls1021a_r2_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
- FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
- FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
+ FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_USE_OFF_TIMESTAMP,
};
static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
- FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD,
+ FLEXCAN_QUIRK_USE_OFF_TIMESTAMP | FLEXCAN_QUIRK_SUPPORT_FD |
+ FLEXCAN_QUIRK_SUPPORT_ECC,
};
static const struct can_bittiming_const flexcan_bittiming_const = {
int err;
err = pm_runtime_get_sync(priv->dev);
- if (err < 0)
+ if (err < 0) {
+ pm_runtime_put_noidle(priv->dev);
return err;
+ }
err = __flexcan_get_berr_counter(dev, bec);
priv->write(reg_ctrl2, ®s->ctrl2);
}
- err = flexcan_transceiver_enable(priv);
- if (err)
- goto out_chip_disable;
-
/* synchronize with the can bus */
err = flexcan_chip_unfreeze(priv);
if (err)
- goto out_transceiver_disable;
+ goto out_chip_disable;
priv->can.state = CAN_STATE_ERROR_ACTIVE;
return 0;
- out_transceiver_disable:
- flexcan_transceiver_disable(priv);
out_chip_disable:
flexcan_chip_disable(priv);
return err;
priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL,
®s->ctrl);
- flexcan_transceiver_disable(priv);
priv->can.state = CAN_STATE_STOPPED;
return 0;
}
err = pm_runtime_get_sync(priv->dev);
- if (err < 0)
+ if (err < 0) {
+ pm_runtime_put_noidle(priv->dev);
return err;
+ }
err = open_candev(dev);
if (err)
goto out_runtime_put;
- err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
+ err = flexcan_transceiver_enable(priv);
if (err)
goto out_close;
+ err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev);
+ if (err)
+ goto out_transceiver_disable;
+
if (priv->can.ctrlmode & CAN_CTRLMODE_FD)
priv->mb_size = sizeof(struct flexcan_mb) + CANFD_MAX_DLEN;
else
can_rx_offload_del(&priv->offload);
out_free_irq:
free_irq(dev->irq, dev);
+ out_transceiver_disable:
+ flexcan_transceiver_disable(priv);
out_close:
close_candev(dev);
out_runtime_put:
can_rx_offload_del(&priv->offload);
free_irq(dev->irq, dev);
+ flexcan_transceiver_disable(priv);
close_candev(dev);
pm_runtime_put(priv->dev);
return -EINVAL;
/* stop mode property format is:
- * <&gpr req_gpr>.
+ * <&gpr req_gpr req_bit>.
*/
ret = of_property_read_u32_array(np, "fsl,stop-mode", out_val,
ARRAY_SIZE(out_val));
{
struct net_device *dev = platform_get_drvdata(pdev);
+ device_set_wakeup_enable(&pdev->dev, false);
+ device_set_wakeup_capable(&pdev->dev, false);
unregister_flexcandev(dev);
pm_runtime_disable(&pdev->dev);
free_candev(dev);
static const struct can_bittiming_const kvaser_pciefd_bittiming_const = {
.name = KVASER_PCIEFD_DRV_NAME,
.tseg1_min = 1,
- .tseg1_max = 255,
+ .tseg1_max = 512,
.tseg2_min = 1,
.tseg2_max = 32,
.sjw_max = 16,
.brp_min = 1,
- .brp_max = 4096,
+ .brp_max = 8192,
.brp_inc = 1,
};
return err;
err = kvaser_pciefd_bus_on(can);
- if (err)
+ if (err) {
+ close_candev(netdev);
return err;
+ }
return 0;
}
config CAN_M_CAN_TCAN4X5X
depends on CAN_M_CAN
- depends on REGMAP_SPI
+ depends on SPI
+ select REGMAP_SPI
tristate "TCAN4X5X M_CAN device"
help
Say Y here if you want support for Texas Instruments TCAN4x5x
unsigned int ecr;
switch (new_state) {
- case CAN_STATE_ERROR_ACTIVE:
+ case CAN_STATE_ERROR_WARNING:
/* error warning state */
cdev->can.can_stats.error_warning++;
cdev->can.state = CAN_STATE_ERROR_WARNING;
__m_can_get_berr_counter(dev, &bec);
switch (new_state) {
- case CAN_STATE_ERROR_ACTIVE:
+ case CAN_STATE_ERROR_WARNING:
/* error warning state */
cf->can_id |= CAN_ERR_CRTL;
cf->data[1] = (bec.txerr > bec.rxerr) ?
struct net_device_stats *stats = &dev->stats;
u32 ir;
+ if (pm_runtime_suspended(cdev->dev))
+ return IRQ_NONE;
ir = m_can_read(cdev, M_CAN_IR);
if (!ir)
return IRQ_NONE;
.name = KBUILD_MODNAME,
.tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */
.tseg1_max = 256,
- .tseg2_min = 1, /* Time segment 2 = phase_seg2 */
+ .tseg2_min = 2, /* Time segment 2 = phase_seg2 */
.tseg2_max = 128,
.sjw_max = 128,
.brp_min = 1,
&m_can_data_bittiming_const_31X;
break;
case 32:
+ case 33:
+ /* Support both MCAN version v3.2.x and v3.3.0 */
m_can_dev->can.bittiming_const = m_can_dev->bit_timing ?
m_can_dev->bit_timing : &m_can_bittiming_const_31X;
/* disable all interrupts */
m_can_disable_all_interrupts(cdev);
+ /* Set init mode to disengage from the network */
+ m_can_config_endisable(cdev, true);
+
/* set the state as STOPPED */
cdev->can.state = CAN_STATE_STOPPED;
}
INIT_WORK(&cdev->tx_work, m_can_tx_work_queue);
err = request_threaded_irq(dev->irq, NULL, m_can_isr,
- IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
+ IRQF_ONESHOT,
dev->name, dev);
} else {
err = request_irq(dev->irq, m_can_isr, IRQF_SHARED, dev->name,
}
EXPORT_SYMBOL_GPL(m_can_class_allocate_dev);
+void m_can_class_free_dev(struct net_device *net)
+{
+ free_candev(net);
+}
+EXPORT_SYMBOL_GPL(m_can_class_free_dev);
+
int m_can_class_register(struct m_can_classdev *m_can_dev)
{
int ret;
if (ret) {
if (m_can_dev->pm_clock_support)
pm_runtime_disable(m_can_dev->dev);
- free_candev(m_can_dev->net);
}
return ret;
unregister_candev(m_can_dev->net);
m_can_clk_stop(m_can_dev);
-
- free_candev(m_can_dev->net);
}
EXPORT_SYMBOL_GPL(m_can_class_unregister);
};
struct m_can_classdev *m_can_class_allocate_dev(struct device *dev);
+void m_can_class_free_dev(struct net_device *net);
int m_can_class_register(struct m_can_classdev *cdev);
void m_can_class_unregister(struct m_can_classdev *cdev);
int m_can_class_get_clocks(struct m_can_classdev *cdev);
return -ENOMEM;
priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
- if (!priv)
- return -ENOMEM;
+ if (!priv) {
+ ret = -ENOMEM;
+ goto probe_fail;
+ }
mcan_class->device_data = priv;
- m_can_class_get_clocks(mcan_class);
+ ret = m_can_class_get_clocks(mcan_class);
+ if (ret)
+ goto probe_fail;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "m_can");
addr = devm_ioremap_resource(&pdev->dev, res);
irq = platform_get_irq_byname(pdev, "int0");
if (IS_ERR(addr) || irq < 0) {
ret = -EINVAL;
- goto failed_ret;
+ goto probe_fail;
}
/* message ram could be shared */
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "message_ram");
if (!res) {
ret = -ENODEV;
- goto failed_ret;
+ goto probe_fail;
}
mram_addr = devm_ioremap(&pdev->dev, res->start, resource_size(res));
if (!mram_addr) {
ret = -ENOMEM;
- goto failed_ret;
+ goto probe_fail;
}
priv->base = addr;
m_can_init_ram(mcan_class);
- ret = m_can_class_register(mcan_class);
+ return m_can_class_register(mcan_class);
-failed_ret:
+probe_fail:
+ m_can_class_free_dev(mcan_class->net);
return ret;
}
m_can_class_unregister(mcan_class);
+ m_can_class_free_dev(mcan_class->net);
+
platform_set_drvdata(pdev, NULL);
return 0;
return -ENOMEM;
priv = devm_kzalloc(&spi->dev, sizeof(*priv), GFP_KERNEL);
- if (!priv)
- return -ENOMEM;
+ if (!priv) {
+ ret = -ENOMEM;
+ goto out_m_can_class_free_dev;
+ }
priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
- if (PTR_ERR(priv->power) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
- else
+ if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto out_m_can_class_free_dev;
+ } else {
priv->power = NULL;
+ }
mcan_class->device_data = priv;
}
/* Sanity check */
- if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF)
- return -ERANGE;
+ if (freq < 20000000 || freq > TCAN4X5X_EXT_CLK_DEF) {
+ ret = -ERANGE;
+ goto out_m_can_class_free_dev;
+ }
priv->reg_offset = TCAN4X5X_MCAN_OFFSET;
priv->mram_start = TCAN4X5X_MRAM_START;
spi->bits_per_word = 32;
ret = spi_setup(spi);
if (ret)
- goto out_clk;
+ goto out_m_can_class_free_dev;
priv->regmap = devm_regmap_init(&spi->dev, &tcan4x5x_bus,
&spi->dev, &tcan4x5x_regmap);
+ if (IS_ERR(priv->regmap)) {
+ ret = PTR_ERR(priv->regmap);
+ goto out_m_can_class_free_dev;
+ }
ret = tcan4x5x_power_enable(priv->power, 1);
if (ret)
- goto out_clk;
+ goto out_m_can_class_free_dev;
ret = tcan4x5x_parse_config(mcan_class);
if (ret)
out_power:
tcan4x5x_power_enable(priv->power, 0);
-out_clk:
- if (!IS_ERR(mcan_class->cclk)) {
- clk_disable_unprepare(mcan_class->cclk);
- clk_disable_unprepare(mcan_class->hclk);
- }
-
+ out_m_can_class_free_dev:
+ m_can_class_free_dev(mcan_class->net);
dev_err(&spi->dev, "Probe failed, err=%d\n", ret);
+
return ret;
}
{
struct tcan4x5x_priv *priv = spi_get_drvdata(spi);
+ m_can_class_unregister(priv->mcan_dev);
+
tcan4x5x_power_enable(priv->power, 0);
- m_can_class_unregister(priv->mcan_dev);
+ m_can_class_free_dev(priv->mcan_dev->net);
return 0;
}
cf_len = get_can_dlc(pucan_msg_get_dlc(msg));
/* if this frame is an echo, */
- if ((rx_msg_flags & PUCAN_MSG_LOOPED_BACK) &&
- !(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE)) {
+ if (rx_msg_flags & PUCAN_MSG_LOOPED_BACK) {
unsigned long flags;
spin_lock_irqsave(&priv->echo_lock, flags);
netif_wake_queue(priv->ndev);
spin_unlock_irqrestore(&priv->echo_lock, flags);
- return 0;
+
+ /* if this frame is only an echo, stop here. Otherwise,
+ * continue to push this application self-received frame into
+ * its own rx queue.
+ */
+ if (!(rx_msg_flags & PUCAN_MSG_SELF_RECEIVE))
+ return 0;
}
/* otherwise, it should be pushed into rx fifo */
if (skb_queue_len(&offload->skb_queue) >
offload->skb_queue_len_max) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return -ENOBUFS;
}
{
if (skb_queue_len(&offload->skb_queue) >
offload->skb_queue_len_max) {
- kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return -ENOBUFS;
}
netdev_dbg(dev, "arbitration lost interrupt\n");
alc = priv->read_reg(priv, SJA1000_ALC);
priv->can.can_stats.arbitration_lost++;
- stats->tx_errors++;
cf->can_id |= CAN_ERR_LOSTARB;
cf->data[0] = alc & 0x1f;
}
{
switch (model) {
case MCP251XFD_MODEL_MCP2517FD:
- return "MCP2517FD"; break;
+ return "MCP2517FD";
case MCP251XFD_MODEL_MCP2518FD:
- return "MCP2518FD"; break;
+ return "MCP2518FD";
case MCP251XFD_MODEL_MCP251XFD:
- return "MCP251xFD"; break;
+ return "MCP251xFD";
}
return "<unknown>";
{
switch (mode) {
case MCP251XFD_REG_CON_MODE_MIXED:
- return "Mixed (CAN FD/CAN 2.0)"; break;
+ return "Mixed (CAN FD/CAN 2.0)";
case MCP251XFD_REG_CON_MODE_SLEEP:
- return "Sleep"; break;
+ return "Sleep";
case MCP251XFD_REG_CON_MODE_INT_LOOPBACK:
- return "Internal Loopback"; break;
+ return "Internal Loopback";
case MCP251XFD_REG_CON_MODE_LISTENONLY:
- return "Listen Only"; break;
+ return "Listen Only";
case MCP251XFD_REG_CON_MODE_CONFIG:
- return "Configuration"; break;
+ return "Configuration";
case MCP251XFD_REG_CON_MODE_EXT_LOOPBACK:
- return "External Loopback"; break;
+ return "External Loopback";
case MCP251XFD_REG_CON_MODE_CAN2_0:
- return "CAN 2.0"; break;
+ return "CAN 2.0";
case MCP251XFD_REG_CON_MODE_RESTRICTED:
- return "Restricted Operation"; break;
+ return "Restricted Operation";
}
return "<unknown>";
u32 freq;
int err;
+ if (!spi->irq)
+ return dev_err_probe(&spi->dev, -ENXIO,
+ "No IRQ specified (maybe node \"interrupts-extended\" in DT missing)!\n");
+
rx_int = devm_gpiod_get_optional(&spi->dev, "microchip,rx-int",
GPIOD_IN);
if (PTR_ERR(rx_int) == -EPROBE_DEFER)
memcpy(&buf_tx->cmd, reg, sizeof(buf_tx->cmd));
if (MCP251XFD_SANITIZE_SPI)
memset(buf_tx->data, 0x0, val_len);
- };
+ }
err = spi_sync(spi, &msg);
if (err)
goto out;
}
- netdev_dbg(priv->ndev,
- "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n",
- reg, val_len, (int)val_len, buf_rx->data,
- get_unaligned_be16(buf_rx->data + val_len));
- }
-
- if (err) {
netdev_info(priv->ndev,
- "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n",
+ "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x) retrying.\n",
reg, val_len, (int)val_len, buf_rx->data,
get_unaligned_be16(buf_rx->data + val_len));
+ }
+
+ if (err) {
+ netdev_err(priv->ndev,
+ "CRC read error at address 0x%04x (length=%zd, data=%*ph, CRC=0x%04x).\n",
+ reg, val_len, (int)val_len, buf_rx->data,
+ get_unaligned_be16(buf_rx->data + val_len));
return err;
}
netdev_dbg(dev, "arbitration lost interrupt\n");
alc = readl(priv->base + SUN4I_REG_STA_ADDR);
priv->can.can_stats.arbitration_lost++;
- stats->tx_errors++;
if (likely(skb)) {
cf->can_id |= CAN_ERR_LOSTARB;
cf->data[0] = (alc >> 8) & 0x1f;
priv->base = devm_platform_ioremap_resource_byname(pdev, "hecc");
if (IS_ERR(priv->base)) {
dev_err(&pdev->dev, "hecc ioremap failed\n");
- return PTR_ERR(priv->base);
+ err = PTR_ERR(priv->base);
+ goto probe_exit_candev;
}
/* handle hecc-ram memory */
"hecc-ram");
if (IS_ERR(priv->hecc_ram)) {
dev_err(&pdev->dev, "hecc-ram ioremap failed\n");
- return PTR_ERR(priv->hecc_ram);
+ err = PTR_ERR(priv->hecc_ram);
+ goto probe_exit_candev;
}
/* handle mbx memory */
priv->mbx = devm_platform_ioremap_resource_byname(pdev, "mbx");
if (IS_ERR(priv->mbx)) {
dev_err(&pdev->dev, "mbx ioremap failed\n");
- return PTR_ERR(priv->mbx);
+ err = PTR_ERR(priv->mbx);
+ goto probe_exit_candev;
}
irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
if (!irq) {
dev_err(&pdev->dev, "No irq resource\n");
- goto probe_exit;
+ goto probe_exit_candev;
}
priv->ndev = ndev;
err = clk_prepare_enable(priv->clk);
if (err) {
dev_err(&pdev->dev, "clk_prepare_enable() failed\n");
- goto probe_exit_clk;
+ goto probe_exit_release_clk;
}
priv->offload.mailbox_read = ti_hecc_mailbox_read;
err = can_rx_offload_add_timestamp(ndev, &priv->offload);
if (err) {
dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n");
- goto probe_exit_clk;
+ goto probe_exit_disable_clk;
}
err = register_candev(ndev);
probe_exit_offload:
can_rx_offload_del(&priv->offload);
-probe_exit_clk:
+probe_exit_disable_clk:
+ clk_disable_unprepare(priv->clk);
+probe_exit_release_clk:
clk_put(priv->clk);
probe_exit_candev:
free_candev(ndev);
-probe_exit:
+
return err;
}
};
/* data types passed between host and device */
+
+/* The firmware on the original USB2CAN by Geschwister Schneider
+ * Technologie Entwicklungs- und Vertriebs UG exchanges all data
+ * between the host and the device in host byte order. This is done
+ * with the struct gs_host_config::byte_order member, which is sent
+ * first to indicate the desired byte order.
+ *
+ * The widely used open source firmware candleLight doesn't support
+ * this feature and exchanges the data in little endian byte order.
+ */
struct gs_host_config {
- u32 byte_order;
+ __le32 byte_order;
} __packed;
-/* All data exchanged between host and device is exchanged in host byte order,
- * thanks to the struct gs_host_config byte_order member, which is sent first
- * to indicate the desired byte order.
- */
struct gs_device_config {
u8 reserved1;
u8 reserved2;
u8 reserved3;
u8 icount;
- u32 sw_version;
- u32 hw_version;
+ __le32 sw_version;
+ __le32 hw_version;
} __packed;
#define GS_CAN_MODE_NORMAL 0
#define GS_CAN_MODE_ONE_SHOT BIT(3)
struct gs_device_mode {
- u32 mode;
- u32 flags;
+ __le32 mode;
+ __le32 flags;
} __packed;
struct gs_device_state {
- u32 state;
- u32 rxerr;
- u32 txerr;
+ __le32 state;
+ __le32 rxerr;
+ __le32 txerr;
} __packed;
struct gs_device_bittiming {
- u32 prop_seg;
- u32 phase_seg1;
- u32 phase_seg2;
- u32 sjw;
- u32 brp;
+ __le32 prop_seg;
+ __le32 phase_seg1;
+ __le32 phase_seg2;
+ __le32 sjw;
+ __le32 brp;
} __packed;
struct gs_identify_mode {
- u32 mode;
+ __le32 mode;
} __packed;
#define GS_CAN_FEATURE_LISTEN_ONLY BIT(0)
#define GS_CAN_FEATURE_IDENTIFY BIT(5)
struct gs_device_bt_const {
- u32 feature;
- u32 fclk_can;
- u32 tseg1_min;
- u32 tseg1_max;
- u32 tseg2_min;
- u32 tseg2_max;
- u32 sjw_max;
- u32 brp_min;
- u32 brp_max;
- u32 brp_inc;
+ __le32 feature;
+ __le32 fclk_can;
+ __le32 tseg1_min;
+ __le32 tseg1_max;
+ __le32 tseg2_min;
+ __le32 tseg2_max;
+ __le32 sjw_max;
+ __le32 brp_min;
+ __le32 brp_max;
+ __le32 brp_inc;
} __packed;
#define GS_CAN_FLAG_OVERFLOW 1
struct gs_host_frame {
u32 echo_id;
- u32 can_id;
+ __le32 can_id;
u8 can_dlc;
u8 channel;
if (!skb)
return;
- cf->can_id = hf->can_id;
+ cf->can_id = le32_to_cpu(hf->can_id);
cf->can_dlc = get_can_dlc(hf->can_dlc);
memcpy(cf->data, hf->data, 8);
/* ERROR frames tell us information about the controller */
- if (hf->can_id & CAN_ERR_FLAG)
+ if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG)
gs_update_state(dev, cf);
netdev->stats.rx_packets++;
if (!dbt)
return -ENOMEM;
- dbt->prop_seg = bt->prop_seg;
- dbt->phase_seg1 = bt->phase_seg1;
- dbt->phase_seg2 = bt->phase_seg2;
- dbt->sjw = bt->sjw;
- dbt->brp = bt->brp;
+ dbt->prop_seg = cpu_to_le32(bt->prop_seg);
+ dbt->phase_seg1 = cpu_to_le32(bt->phase_seg1);
+ dbt->phase_seg2 = cpu_to_le32(bt->phase_seg2);
+ dbt->sjw = cpu_to_le32(bt->sjw);
+ dbt->brp = cpu_to_le32(bt->brp);
/* request bit timings */
rc = usb_control_msg(interface_to_usbdev(intf),
cf = (struct can_frame *)skb->data;
- hf->can_id = cf->can_id;
+ hf->can_id = cpu_to_le32(cf->can_id);
hf->can_dlc = cf->can_dlc;
memcpy(hf->data, cf->data, cf->can_dlc);
int rc, i;
struct gs_device_mode *dm;
u32 ctrlmode;
+ u32 flags = 0;
rc = open_candev(netdev);
if (rc)
/* flags */
ctrlmode = dev->can.ctrlmode;
- dm->flags = 0;
if (ctrlmode & CAN_CTRLMODE_LOOPBACK)
- dm->flags |= GS_CAN_MODE_LOOP_BACK;
+ flags |= GS_CAN_MODE_LOOP_BACK;
else if (ctrlmode & CAN_CTRLMODE_LISTENONLY)
- dm->flags |= GS_CAN_MODE_LISTEN_ONLY;
+ flags |= GS_CAN_MODE_LISTEN_ONLY;
/* Controller is not allowed to retry TX
* this mode is unavailable on atmels uc3c hardware
*/
if (ctrlmode & CAN_CTRLMODE_ONE_SHOT)
- dm->flags |= GS_CAN_MODE_ONE_SHOT;
+ flags |= GS_CAN_MODE_ONE_SHOT;
if (ctrlmode & CAN_CTRLMODE_3_SAMPLES)
- dm->flags |= GS_CAN_MODE_TRIPLE_SAMPLE;
+ flags |= GS_CAN_MODE_TRIPLE_SAMPLE;
/* finally start device */
- dm->mode = GS_CAN_MODE_START;
+ dm->mode = cpu_to_le32(GS_CAN_MODE_START);
+ dm->flags = cpu_to_le32(flags);
rc = usb_control_msg(interface_to_usbdev(dev->iface),
usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0),
GS_USB_BREQ_MODE,
return -ENOMEM;
if (do_identify)
- imode->mode = GS_CAN_IDENTIFY_ON;
+ imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_ON);
else
- imode->mode = GS_CAN_IDENTIFY_OFF;
+ imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_OFF);
rc = usb_control_msg(interface_to_usbdev(dev->iface),
usb_sndctrlpipe(interface_to_usbdev(dev->iface),
struct net_device *netdev;
int rc;
struct gs_device_bt_const *bt_const;
+ u32 feature;
bt_const = kmalloc(sizeof(*bt_const), GFP_KERNEL);
if (!bt_const)
/* dev setup */
strcpy(dev->bt_const.name, "gs_usb");
- dev->bt_const.tseg1_min = bt_const->tseg1_min;
- dev->bt_const.tseg1_max = bt_const->tseg1_max;
- dev->bt_const.tseg2_min = bt_const->tseg2_min;
- dev->bt_const.tseg2_max = bt_const->tseg2_max;
- dev->bt_const.sjw_max = bt_const->sjw_max;
- dev->bt_const.brp_min = bt_const->brp_min;
- dev->bt_const.brp_max = bt_const->brp_max;
- dev->bt_const.brp_inc = bt_const->brp_inc;
+ dev->bt_const.tseg1_min = le32_to_cpu(bt_const->tseg1_min);
+ dev->bt_const.tseg1_max = le32_to_cpu(bt_const->tseg1_max);
+ dev->bt_const.tseg2_min = le32_to_cpu(bt_const->tseg2_min);
+ dev->bt_const.tseg2_max = le32_to_cpu(bt_const->tseg2_max);
+ dev->bt_const.sjw_max = le32_to_cpu(bt_const->sjw_max);
+ dev->bt_const.brp_min = le32_to_cpu(bt_const->brp_min);
+ dev->bt_const.brp_max = le32_to_cpu(bt_const->brp_max);
+ dev->bt_const.brp_inc = le32_to_cpu(bt_const->brp_inc);
dev->udev = interface_to_usbdev(intf);
dev->iface = intf;
/* can setup */
dev->can.state = CAN_STATE_STOPPED;
- dev->can.clock.freq = bt_const->fclk_can;
+ dev->can.clock.freq = le32_to_cpu(bt_const->fclk_can);
dev->can.bittiming_const = &dev->bt_const;
dev->can.do_set_bittiming = gs_usb_set_bittiming;
dev->can.ctrlmode_supported = 0;
- if (bt_const->feature & GS_CAN_FEATURE_LISTEN_ONLY)
+ feature = le32_to_cpu(bt_const->feature);
+ if (feature & GS_CAN_FEATURE_LISTEN_ONLY)
dev->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
- if (bt_const->feature & GS_CAN_FEATURE_LOOP_BACK)
+ if (feature & GS_CAN_FEATURE_LOOP_BACK)
dev->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK;
- if (bt_const->feature & GS_CAN_FEATURE_TRIPLE_SAMPLE)
+ if (feature & GS_CAN_FEATURE_TRIPLE_SAMPLE)
dev->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
- if (bt_const->feature & GS_CAN_FEATURE_ONE_SHOT)
+ if (feature & GS_CAN_FEATURE_ONE_SHOT)
dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
SET_NETDEV_DEV(netdev, &intf->dev);
- if (dconf->sw_version > 1)
- if (bt_const->feature & GS_CAN_FEATURE_IDENTIFY)
+ if (le32_to_cpu(dconf->sw_version) > 1)
+ if (feature & GS_CAN_FEATURE_IDENTIFY)
netdev->ethtool_ops = &gs_usb_ethtool_ops;
kfree(bt_const);
if (!hconf)
return -ENOMEM;
- hconf->byte_order = 0x0000beef;
+ hconf->byte_order = cpu_to_le32(0x0000beef);
/* send host config */
rc = usb_control_msg(interface_to_usbdev(intf),
.tseg2_max = 32,
.sjw_max = 16,
.brp_min = 1,
- .brp_max = 4096,
+ .brp_max = 8192,
.brp_inc = 1,
};
if (!ctx)
return NETDEV_TX_BUSY;
- can_put_echo_skb(skb, priv->netdev, ctx->ndx);
-
if (cf->can_id & CAN_EFF_FLAG) {
/* SIDH | SIDL | EIDH | EIDL
* 28 - 21 | 20 19 18 x x x 17 16 | 15 - 8 | 7 - 0
if (cf->can_id & CAN_RTR_FLAG)
usb_msg.dlc |= MCBA_DLC_RTR_MASK;
+ can_put_echo_skb(skb, priv->netdev, ctx->ndx);
+
err = mcba_usb_xmit(priv, (struct mcba_usb_msg *)&usb_msg, ctx);
if (err)
goto xmit_failed;
/* protect from getting time before setting now */
if (ktime_to_ns(time_ref->tv_host)) {
u64 delta_us;
+ s64 delta_ts = 0;
+
+ /* General case: dev_ts_1 < dev_ts_2 < ts, with:
+ *
+ * - dev_ts_1 = previous sync timestamp
+ * - dev_ts_2 = last sync timestamp
+ * - ts = event timestamp
+ * - ts_period = known sync period (theoretical)
+ * ~ dev_ts2 - dev_ts1
+ * *but*:
+ *
+ * - time counters wrap (see adapter->ts_used_bits)
+ * - sometimes, dev_ts_1 < ts < dev_ts2
+ *
+ * "normal" case (sync time counters increase):
+ * must take into account case when ts wraps (tsw)
+ *
+ * < ts_period > < >
+ * | | |
+ * ---+--------+----+-------0-+--+-->
+ * ts_dev_1 | ts_dev_2 |
+ * ts tsw
+ */
+ if (time_ref->ts_dev_1 < time_ref->ts_dev_2) {
+ /* case when event time (tsw) wraps */
+ if (ts < time_ref->ts_dev_1)
+ delta_ts = BIT_ULL(time_ref->adapter->ts_used_bits);
+
+ /* Otherwise, sync time counter (ts_dev_2) has wrapped:
+ * handle case when event time (tsn) hasn't.
+ *
+ * < ts_period > < >
+ * | | |
+ * ---+--------+--0-+---------+--+-->
+ * ts_dev_1 | ts_dev_2 |
+ * tsn ts
+ */
+ } else if (time_ref->ts_dev_1 < ts) {
+ delta_ts = -BIT_ULL(time_ref->adapter->ts_used_bits);
+ }
- delta_us = ts - time_ref->ts_dev_2;
- if (ts < time_ref->ts_dev_2)
- delta_us &= (1 << time_ref->adapter->ts_used_bits) - 1;
+ /* add delay between last sync and event timestamps */
+ delta_ts += (signed int)(ts - time_ref->ts_dev_2);
- delta_us += time_ref->ts_total;
+ /* add time from beginning to last sync */
+ delta_ts += time_ref->ts_total;
- delta_us *= time_ref->adapter->us_per_ts_scale;
+ /* convert ticks number into microseconds */
+ delta_us = delta_ts * time_ref->adapter->us_per_ts_scale;
delta_us >>= time_ref->adapter->us_per_ts_shift;
*time = ktime_add_us(time_ref->tv_host_0, delta_us);
struct pucan_msg *rx_msg)
{
struct pucan_rx_msg *rm = (struct pucan_rx_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pucan_msg_get_channel(rm)];
- struct net_device *netdev = dev->netdev;
+ struct peak_usb_device *dev;
+ struct net_device *netdev;
struct canfd_frame *cfd;
struct sk_buff *skb;
const u16 rx_msg_flags = le16_to_cpu(rm->flags);
+ if (pucan_msg_get_channel(rm) >= ARRAY_SIZE(usb_if->dev))
+ return -ENOMEM;
+
+ dev = usb_if->dev[pucan_msg_get_channel(rm)];
+ netdev = dev->netdev;
+
if (rx_msg_flags & PUCAN_MSG_EXT_DATA_LEN) {
/* CANFD frame case */
skb = alloc_canfd_skb(netdev, &cfd);
struct pucan_msg *rx_msg)
{
struct pucan_status_msg *sm = (struct pucan_status_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
- struct pcan_usb_fd_device *pdev =
- container_of(dev, struct pcan_usb_fd_device, dev);
+ struct pcan_usb_fd_device *pdev;
enum can_state new_state = CAN_STATE_ERROR_ACTIVE;
enum can_state rx_state, tx_state;
- struct net_device *netdev = dev->netdev;
+ struct peak_usb_device *dev;
+ struct net_device *netdev;
struct can_frame *cf;
struct sk_buff *skb;
+ if (pucan_stmsg_get_channel(sm) >= ARRAY_SIZE(usb_if->dev))
+ return -ENOMEM;
+
+ dev = usb_if->dev[pucan_stmsg_get_channel(sm)];
+ pdev = container_of(dev, struct pcan_usb_fd_device, dev);
+ netdev = dev->netdev;
+
/* nothing should be sent while in BUS_OFF state */
if (dev->can.state == CAN_STATE_BUS_OFF)
return 0;
struct pucan_msg *rx_msg)
{
struct pucan_error_msg *er = (struct pucan_error_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pucan_ermsg_get_channel(er)];
- struct pcan_usb_fd_device *pdev =
- container_of(dev, struct pcan_usb_fd_device, dev);
+ struct pcan_usb_fd_device *pdev;
+ struct peak_usb_device *dev;
+
+ if (pucan_ermsg_get_channel(er) >= ARRAY_SIZE(usb_if->dev))
+ return -EINVAL;
+
+ dev = usb_if->dev[pucan_ermsg_get_channel(er)];
+ pdev = container_of(dev, struct pcan_usb_fd_device, dev);
/* keep a trace of tx and rx error counters for later use */
pdev->bec.txerr = er->tx_err_cnt;
struct pucan_msg *rx_msg)
{
struct pcan_ufd_ovr_msg *ov = (struct pcan_ufd_ovr_msg *)rx_msg;
- struct peak_usb_device *dev = usb_if->dev[pufd_omsg_get_channel(ov)];
- struct net_device *netdev = dev->netdev;
+ struct peak_usb_device *dev;
+ struct net_device *netdev;
struct can_frame *cf;
struct sk_buff *skb;
+ if (pufd_omsg_get_channel(ov) >= ARRAY_SIZE(usb_if->dev))
+ return -EINVAL;
+
+ dev = usb_if->dev[pufd_omsg_get_channel(ov)];
+ netdev = dev->netdev;
+
/* allocate an skb to store the error frame */
skb = alloc_can_err_skb(netdev, &cf);
if (!skb)
u16 tx_msg_size, tx_msg_flags;
u8 can_dlc;
+ if (cfd->len > CANFD_MAX_DLEN)
+ return -EINVAL;
+
tx_msg_size = ALIGN(sizeof(struct pucan_tx_msg) + cfd->len, 4);
tx_msg->size = cpu_to_le16(tx_msg_size);
tx_msg->type = cpu_to_le16(PUCAN_MSG_CAN_TX);
if (ret < 0) {
netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
__func__, ret);
- return ret;
+ goto err;
}
ret = request_irq(ndev->irq, xcan_interrupt, priv->irq_flags,
if (ret < 0) {
netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
__func__, ret);
+ pm_runtime_put(priv->dev);
return ret;
}
if (ret < 0) {
netdev_err(ndev, "%s: pm_runtime_get failed(%d)\n",
__func__, ret);
- goto err_pmdisable;
+ goto err_disableclks;
}
if (priv->read_reg(priv, XCAN_SR_OFFSET) != XCAN_SR_CONFIG_MASK) {
err_disableclks:
pm_runtime_put(priv->dev);
-err_pmdisable:
pm_runtime_disable(&pdev->dev);
err_free:
free_candev(ndev);
*/
#include <linux/clk.h>
+#include <linux/delay.h>
#include <linux/etherdevice.h>
#include <linux/firmware.h>
#include <linux/if_bridge.h>
i++;
}
+ /* The standalone PHY11G requires 300ms to be fully
+ * initialized and ready for any MDIO communication after being
+ * taken out of reset. For the SoC-internal GPHY variant there
+ * is no (known) documentation for the minimum time after a
+ * reset. Use the same value as for the standalone variant as
+ * some users have reported internal PHYs not being detected
+ * without any delay.
+ */
+ msleep(300);
+
return 0;
remove_gphy:
usleep_range(10000, 20000);
gpiod_set_value_cansleep(gpiod, 0);
usleep_range(10000, 20000);
+
+ mv88e6xxx_g1_wait_eeprom_done(chip);
}
}
mv88e6xxx_reg_lock(chip);
err = mv88e6xxx_fid_map(chip, fid_bitmap);
- if (err)
+ if (err) {
+ kfree(table);
goto out;
+ }
while (1) {
fid = find_next_bit(fid_bitmap, MV88E6XXX_N_FID, fid + 1);
return mv88e6xxx_g1_wait_bit(chip, MV88E6XXX_G1_STS, bit, 1);
}
+void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip)
+{
+ const unsigned long timeout = jiffies + 1 * HZ;
+ u16 val;
+ int err;
+
+ /* Wait up to 1 second for the switch to finish reading the
+ * EEPROM.
+ */
+ while (time_before(jiffies, timeout)) {
+ err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &val);
+ if (err) {
+ dev_err(chip->dev, "Error reading status");
+ return;
+ }
+
+ /* If the switch is still resetting, it may not
+ * respond on the bus, and so MDIO read returns
+ * 0xffff. Differentiate between that, and waiting for
+ * the EEPROM to be done by bit 0 being set.
+ */
+ if (val != 0xffff &&
+ val & BIT(MV88E6XXX_G1_STS_IRQ_EEPROM_DONE))
+ return;
+
+ usleep_range(1000, 2000);
+ }
+
+ dev_err(chip->dev, "Timeout waiting for EEPROM done");
+}
+
/* Offset 0x01: Switch MAC Address Register Bytes 0 & 1
* Offset 0x02: Switch MAC Address Register Bytes 2 & 3
* Offset 0x03: Switch MAC Address Register Bytes 4 & 5
int mv88e6185_g1_reset(struct mv88e6xxx_chip *chip);
int mv88e6352_g1_reset(struct mv88e6xxx_chip *chip);
int mv88e6250_g1_reset(struct mv88e6xxx_chip *chip);
+void mv88e6xxx_g1_wait_eeprom_done(struct mv88e6xxx_chip *chip);
int mv88e6185_g1_ppu_enable(struct mv88e6xxx_chip *chip);
int mv88e6185_g1_ppu_disable(struct mv88e6xxx_chip *chip);
* Offset 0x08: VTU/STU Data Register 2
* Offset 0x09: VTU/STU Data Register 3
*/
-
-static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip,
- struct mv88e6xxx_vtu_entry *entry)
+static int mv88e6185_g1_vtu_stu_data_read(struct mv88e6xxx_chip *chip,
+ u16 *regs)
{
- u16 regs[3];
int i;
/* Read all 3 VTU/STU Data registers */
return err;
}
- /* Extract MemberTag and PortState data */
+ return 0;
+}
+
+static int mv88e6185_g1_vtu_data_read(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_vtu_entry *entry)
+{
+ u16 regs[3];
+ int err;
+ int i;
+
+ err = mv88e6185_g1_vtu_stu_data_read(chip, regs);
+ if (err)
+ return err;
+
+ /* Extract MemberTag data */
for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
unsigned int member_offset = (i % 4) * 4;
- unsigned int state_offset = member_offset + 2;
entry->member[i] = (regs[i / 4] >> member_offset) & 0x3;
+ }
+
+ return 0;
+}
+
+static int mv88e6185_g1_stu_data_read(struct mv88e6xxx_chip *chip,
+ struct mv88e6xxx_vtu_entry *entry)
+{
+ u16 regs[3];
+ int err;
+ int i;
+
+ err = mv88e6185_g1_vtu_stu_data_read(chip, regs);
+ if (err)
+ return err;
+
+ /* Extract PortState data */
+ for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
+ unsigned int state_offset = (i % 4) * 4 + 2;
+
entry->state[i] = (regs[i / 4] >> state_offset) & 0x3;
}
if (err)
return err;
+ err = mv88e6185_g1_stu_data_read(chip, entry);
+ if (err)
+ return err;
+
/* VTU DBNum[3:0] are located in VTU Operation 3:0
* VTU DBNum[7:4] are located in VTU Operation 11:8
*/
return err;
if (entry->valid) {
- /* Fetch (and mask) VLAN PortState data from the STU */
- err = mv88e6xxx_g1_vtu_stu_get(chip, entry);
+ err = mv88e6185_g1_vtu_data_read(chip, entry);
if (err)
return err;
- err = mv88e6185_g1_vtu_data_read(chip, entry);
+ err = mv88e6xxx_g1_vtu_fid_read(chip, entry);
if (err)
return err;
- err = mv88e6xxx_g1_vtu_fid_read(chip, entry);
+ /* Fetch VLAN PortState data from the STU */
+ err = mv88e6xxx_g1_vtu_stu_get(chip, entry);
+ if (err)
+ return err;
+
+ err = mv88e6185_g1_stu_data_read(chip, entry);
if (err)
return err;
}
priv->port_mtu[port] = new_mtu;
for (i = 0; i < QCA8K_NUM_PORTS; i++)
- if (priv->port_mtu[port] > mtu)
- mtu = priv->port_mtu[port];
+ if (priv->port_mtu[i] > mtu)
+ mtu = priv->port_mtu[i];
/* Include L2 header / FCS length */
qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN);
{
struct ena_com_rx_buf_info *ena_buf = &ena_rx_ctx->ena_bufs[0];
struct ena_eth_io_rx_cdesc_base *cdesc = NULL;
+ u16 q_depth = io_cq->q_depth;
u16 cdesc_idx = 0;
u16 nb_hw_desc;
u16 i = 0;
do {
ena_buf[i].len = cdesc->length;
ena_buf[i].req_id = cdesc->req_id;
+ if (unlikely(ena_buf[i].req_id >= q_depth))
+ return -EIO;
if (++i >= nb_hw_desc)
break;
adapter->num_io_queues);
}
-static int validate_rx_req_id(struct ena_ring *rx_ring, u16 req_id)
-{
- if (likely(req_id < rx_ring->ring_size))
- return 0;
-
- netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
- "Invalid rx req_id: %hu\n", req_id);
-
- u64_stats_update_begin(&rx_ring->syncp);
- rx_ring->rx_stats.bad_req_id++;
- u64_stats_update_end(&rx_ring->syncp);
-
- /* Trigger device reset */
- rx_ring->adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID;
- set_bit(ENA_FLAG_TRIGGER_RESET, &rx_ring->adapter->flags);
- return -EFAULT;
-}
-
/* ena_setup_rx_resources - allocate I/O Rx resources (Descriptors)
* @adapter: network interface device structure
* @qid: queue index
static int ena_alloc_rx_page(struct ena_ring *rx_ring,
struct ena_rx_buffer *rx_info, gfp_t gfp)
{
+ int headroom = rx_ring->rx_headroom;
struct ena_com_buf *ena_buf;
struct page *page;
dma_addr_t dma;
+ /* restore page offset value in case it has been changed by device */
+ rx_info->page_offset = headroom;
+
/* if previous allocated page is not used */
if (unlikely(rx_info->page))
return 0;
"Allocate page %p, rx_info %p\n", page, rx_info);
rx_info->page = page;
- rx_info->page_offset = 0;
ena_buf = &rx_info->ena_buf;
- ena_buf->paddr = dma + rx_ring->rx_headroom;
- ena_buf->len = ENA_PAGE_SIZE - rx_ring->rx_headroom;
+ ena_buf->paddr = dma + headroom;
+ ena_buf->len = ENA_PAGE_SIZE - headroom;
return 0;
}
struct ena_rx_buffer *rx_info;
u16 len, req_id, buf = 0;
void *va;
- int rc;
len = ena_bufs[buf].len;
req_id = ena_bufs[buf].req_id;
- rc = validate_rx_req_id(rx_ring, req_id);
- if (unlikely(rc < 0))
- return NULL;
-
rx_info = &rx_ring->rx_buffer_info[req_id];
if (unlikely(!rx_info->page)) {
/* save virt address of first buffer */
va = page_address(rx_info->page) + rx_info->page_offset;
- prefetch(va + NET_IP_ALIGN);
+
+ prefetch(va);
if (len <= rx_ring->rx_copybreak) {
skb = ena_alloc_skb(rx_ring, false);
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page,
rx_info->page_offset, len, ENA_PAGE_SIZE);
- /* The offset is non zero only for the first buffer */
- rx_info->page_offset = 0;
netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
"RX skb updated. len %d. data_len %d\n",
len = ena_bufs[buf].len;
req_id = ena_bufs[buf].req_id;
- rc = validate_rx_req_id(rx_ring, req_id);
- if (unlikely(rc < 0))
- return NULL;
-
rx_info = &rx_ring->rx_buffer_info[req_id];
} while (1);
int ret;
rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
- xdp->data = page_address(rx_info->page) +
- rx_info->page_offset + rx_ring->rx_headroom;
+ xdp->data = page_address(rx_info->page) + rx_info->page_offset;
xdp_set_data_meta_invalid(xdp);
xdp->data_hard_start = page_address(rx_info->page);
xdp->data_end = xdp->data + rx_ring->ena_bufs[0].len;
if (unlikely(ena_rx_ctx.descs == 0))
break;
+ /* First descriptor might have an offset set by the device */
rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id];
- rx_info->page_offset = ena_rx_ctx.pkt_offset;
+ rx_info->page_offset += ena_rx_ctx.pkt_offset;
netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
"rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n",
error:
adapter = netdev_priv(rx_ring->netdev);
- u64_stats_update_begin(&rx_ring->syncp);
- rx_ring->rx_stats.bad_desc_num++;
- u64_stats_update_end(&rx_ring->syncp);
+ if (rc == -ENOSPC) {
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->rx_stats.bad_desc_num++;
+ u64_stats_update_end(&rx_ring->syncp);
+ adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS;
+ } else {
+ u64_stats_update_begin(&rx_ring->syncp);
+ rx_ring->rx_stats.bad_req_id++;
+ u64_stats_update_end(&rx_ring->syncp);
+ adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID;
+ }
- /* Too many desc from the device. Trigger reset */
- adapter->reset_reason = ENA_REGS_RESET_TOO_MANY_RX_DESCS;
set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
return 0;
goto err_mmio_read_less;
}
- rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_width));
+ rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(dma_width));
if (rc) {
- dev_err(dev, "pci_set_dma_mask failed 0x%x\n", rc);
- goto err_mmio_read_less;
- }
-
- rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(dma_width));
- if (rc) {
- dev_err(dev, "err_pci_set_consistent_dma_mask failed 0x%x\n",
- rc);
+ dev_err(dev, "dma_set_mask_and_coherent failed %d\n", rc);
goto err_mmio_read_less;
}
return rc;
}
+ rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(ENA_MAX_PHYS_ADDR_SIZE_BITS));
+ if (rc) {
+ dev_err(&pdev->dev, "dma_set_mask_and_coherent failed %d\n", rc);
+ goto err_disable_device;
+ }
+
pci_set_master(pdev);
ena_dev = vzalloc(sizeof(*ena_dev));
buff->rxdata.pg_off,
buff->len, DMA_FROM_DEVICE);
- /* for single fragment packets use build_skb() */
- if (buff->is_eop &&
- buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) {
- skb = build_skb(aq_buf_vaddr(&buff->rxdata),
+ skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE);
+ if (unlikely(!skb)) {
+ u64_stats_update_begin(&self->stats.rx.syncp);
+ self->stats.rx.skb_alloc_fails++;
+ u64_stats_update_end(&self->stats.rx.syncp);
+ err = -ENOMEM;
+ goto err_exit;
+ }
+ if (is_ptp_ring)
+ buff->len -=
+ aq_ptp_extract_ts(self->aq_nic, skb,
+ aq_buf_vaddr(&buff->rxdata),
+ buff->len);
+
+ hdr_len = buff->len;
+ if (hdr_len > AQ_CFG_RX_HDR_SIZE)
+ hdr_len = eth_get_headlen(skb->dev,
+ aq_buf_vaddr(&buff->rxdata),
+ AQ_CFG_RX_HDR_SIZE);
+
+ memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),
+ ALIGN(hdr_len, sizeof(long)));
+
+ if (buff->len - hdr_len > 0) {
+ skb_add_rx_frag(skb, 0, buff->rxdata.page,
+ buff->rxdata.pg_off + hdr_len,
+ buff->len - hdr_len,
AQ_CFG_RX_FRAME_MAX);
- if (unlikely(!skb)) {
- u64_stats_update_begin(&self->stats.rx.syncp);
- self->stats.rx.skb_alloc_fails++;
- u64_stats_update_end(&self->stats.rx.syncp);
- err = -ENOMEM;
- goto err_exit;
- }
- if (is_ptp_ring)
- buff->len -=
- aq_ptp_extract_ts(self->aq_nic, skb,
- aq_buf_vaddr(&buff->rxdata),
- buff->len);
- skb_put(skb, buff->len);
page_ref_inc(buff->rxdata.page);
- } else {
- skb = napi_alloc_skb(napi, AQ_CFG_RX_HDR_SIZE);
- if (unlikely(!skb)) {
- u64_stats_update_begin(&self->stats.rx.syncp);
- self->stats.rx.skb_alloc_fails++;
- u64_stats_update_end(&self->stats.rx.syncp);
- err = -ENOMEM;
- goto err_exit;
- }
- if (is_ptp_ring)
- buff->len -=
- aq_ptp_extract_ts(self->aq_nic, skb,
- aq_buf_vaddr(&buff->rxdata),
- buff->len);
-
- hdr_len = buff->len;
- if (hdr_len > AQ_CFG_RX_HDR_SIZE)
- hdr_len = eth_get_headlen(skb->dev,
- aq_buf_vaddr(&buff->rxdata),
- AQ_CFG_RX_HDR_SIZE);
-
- memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),
- ALIGN(hdr_len, sizeof(long)));
-
- if (buff->len - hdr_len > 0) {
- skb_add_rx_frag(skb, 0, buff->rxdata.page,
- buff->rxdata.pg_off + hdr_len,
- buff->len - hdr_len,
- AQ_CFG_RX_FRAME_MAX);
- page_ref_inc(buff->rxdata.page);
- }
+ }
- if (!buff->is_eop) {
- buff_ = buff;
- i = 1U;
- do {
- next_ = buff_->next,
- buff_ = &self->buff_ring[next_];
+ if (!buff->is_eop) {
+ buff_ = buff;
+ i = 1U;
+ do {
+ next_ = buff_->next;
+ buff_ = &self->buff_ring[next_];
- dma_sync_single_range_for_cpu(
- aq_nic_get_dev(self->aq_nic),
- buff_->rxdata.daddr,
- buff_->rxdata.pg_off,
- buff_->len,
- DMA_FROM_DEVICE);
- skb_add_rx_frag(skb, i++,
- buff_->rxdata.page,
- buff_->rxdata.pg_off,
- buff_->len,
- AQ_CFG_RX_FRAME_MAX);
- page_ref_inc(buff_->rxdata.page);
- buff_->is_cleaned = 1;
-
- buff->is_ip_cso &= buff_->is_ip_cso;
- buff->is_udp_cso &= buff_->is_udp_cso;
- buff->is_tcp_cso &= buff_->is_tcp_cso;
- buff->is_cso_err |= buff_->is_cso_err;
+ dma_sync_single_range_for_cpu(aq_nic_get_dev(self->aq_nic),
+ buff_->rxdata.daddr,
+ buff_->rxdata.pg_off,
+ buff_->len,
+ DMA_FROM_DEVICE);
+ skb_add_rx_frag(skb, i++,
+ buff_->rxdata.page,
+ buff_->rxdata.pg_off,
+ buff_->len,
+ AQ_CFG_RX_FRAME_MAX);
+ page_ref_inc(buff_->rxdata.page);
+ buff_->is_cleaned = 1;
- } while (!buff_->is_eop);
- }
+ buff->is_ip_cso &= buff_->is_ip_cso;
+ buff->is_udp_cso &= buff_->is_udp_cso;
+ buff->is_tcp_cso &= buff_->is_tcp_cso;
+ buff->is_cso_err |= buff_->is_cso_err;
+
+ } while (!buff_->is_eop);
}
if (buff->is_vlan)
* various kernel subsystems to support the mechanics required by a
* fixed-high-32-bit system.
*/
- if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) ||
- (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
dev_err(&pdev->dev, "No usable DMA configuration,aborting\n");
goto err_dma;
}
* various kernel subsystems to support the mechanics required by a
* fixed-high-32-bit system.
*/
- if ((dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0) ||
- (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) != 0)) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+ if (err) {
dev_err(&pdev->dev, "No usable DMA configuration,aborting\n");
goto err_dma;
}
config CNIC
tristate "QLogic CNIC support"
depends on PCI && (IPV6 || IPV6=n)
+ depends on MMU
select BNX2
select UIO
help
goto err_out_free_dev;
}
- if (dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30))) {
+ err = dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30));
+ if (err) {
dev_err(sdev->dev,
"Required 30BIT DMA mask unsupported by the system\n");
goto err_out_powerdown;
schedule_work(&bp->sp_task);
}
-static void bnxt_cancel_sp_work(struct bnxt *bp)
-{
- if (BNXT_PF(bp)) {
- flush_workqueue(bnxt_pf_wq);
- } else {
- cancel_work_sync(&bp->sp_task);
- cancel_delayed_work_sync(&bp->fw_reset_task);
- }
-}
-
static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
{
if (!rxr->bnapi->in_reset) {
bnxt_free_ntp_fltrs(bp, irq_re_init);
if (irq_re_init) {
bnxt_free_ring_stats(bp);
- if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET))
+ if (!(bp->fw_cap & BNXT_FW_CAP_PORT_STATS_NO_RESET) ||
+ test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
bnxt_free_port_stats(bp);
bnxt_free_ring_grps(bp);
bnxt_free_vnics(bp);
u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
u16 dst = BNXT_HWRM_CHNL_CHIMP;
- if (BNXT_NO_FW_ACCESS(bp))
+ if (BNXT_NO_FW_ACCESS(bp) &&
+ le16_to_cpu(req->req_type) != HWRM_FUNC_RESET)
return -EBUSY;
if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
{
u64 sw_tmp;
+ hw &= mask;
sw_tmp = (*sw & ~mask) | hw;
if (hw < (*sw & mask))
sw_tmp += mask + 1;
{
int rc = 0;
- rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state))
+ rc = -EIO;
+ if (!rc)
+ rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
if (rc) {
netdev_err(bp->dev, "nic open fail (rc: %x)\n", rc);
dev_close(bp->dev);
if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) != 0 &&
dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)) != 0) {
dev_err(&pdev->dev, "System does not support DMA, aborting\n");
- goto init_err_disable;
+ rc = -EIO;
+ goto init_err_release;
}
pci_set_master(pdev);
if (BNXT_PF(bp))
bnxt_sriov_disable(bp);
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- bnxt_cancel_sp_work(bp);
- bp->sp_event = 0;
-
- bnxt_dl_fw_reporters_destroy(bp, true);
if (BNXT_PF(bp))
devlink_port_type_clear(&bp->dl_port);
pci_disable_pcie_error_reporting(pdev);
unregister_netdev(dev);
+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+ /* Flush any pending tasks */
+ cancel_work_sync(&bp->sp_task);
+ cancel_delayed_work_sync(&bp->fw_reset_task);
+ bp->sp_event = 0;
+
+ bnxt_dl_fw_reporters_destroy(bp, true);
bnxt_dl_unregister(bp);
bnxt_shutdown_tc(bp);
create_singlethread_workqueue("bnxt_pf_wq");
if (!bnxt_pf_wq) {
dev_err(&pdev->dev, "Unable to create workqueue.\n");
+ rc = -ENOMEM;
goto init_err_pci_clean;
}
}
return PCI_ERS_RESULT_DISCONNECT;
}
+ if (state == pci_channel_io_frozen)
+ set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state);
+
if (netif_running(netdev))
bnxt_close(netdev);
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct bnxt *bp = netdev_priv(netdev);
- int err = 0;
+ int err = 0, off;
pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
netdev_info(bp->dev, "PCI Slot Reset\n");
"Cannot re-enable PCI device after reset.\n");
} else {
pci_set_master(pdev);
+ /* Upon fatal error, our device internal logic that latches to
+ * BAR value is getting reset and will restore only upon
+ * rewritting the BARs.
+ *
+ * As pci_restore_state() does not re-write the BARs if the
+ * value is same as saved value earlier, driver needs to
+ * write the BARs to 0 to force restore, in case of fatal error.
+ */
+ if (test_and_clear_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN,
+ &bp->state)) {
+ for (off = PCI_BASE_ADDRESS_0;
+ off <= PCI_BASE_ADDRESS_5; off += 4)
+ pci_write_config_dword(bp->pdev, off, 0);
+ }
pci_restore_state(pdev);
pci_save_state(pdev);
#define BNXT_STATE_ABORT_ERR 5
#define BNXT_STATE_FW_FATAL_COND 6
#define BNXT_STATE_DRV_REGISTERED 7
+#define BNXT_STATE_PCI_CHANNEL_IO_FROZEN 8
#define BNXT_NO_FW_ACCESS(bp) \
(test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \
struct hwrm_nvm_get_dev_info_input req = {0};
int rc;
+ if (BNXT_VF(bp))
+ return -EOPNOTSUPP;
+
bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_DEV_INFO, -1, -1);
mutex_lock(&bp->hwrm_cmd_lock);
rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
/* Read A2 portion of the EEPROM */
if (length) {
start -= ETH_MODULE_SFF_8436_LEN;
- rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 1,
+ rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A2, 0,
start, length, data);
}
return rc;
static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
{
- bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb);
+ bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) ||
+ skb_is_nonlinear(*skb);
int padlen = ETH_ZLEN - (*skb)->len;
int headroom = skb_headroom(*skb);
int tailroom = skb_tailroom(*skb);
config CHELSIO_T4
tristate "Chelsio Communications T4/T5/T6 Ethernet support"
- depends on PCI && (IPV6 || IPV6=n)
+ depends on PCI && (IPV6 || IPV6=n) && (TLS || TLS=n)
select FW_LOADER
select MDIO
select ZLIB_DEFLATE
GFP_KERNEL | __GFP_COMP);
if (!avail) {
CH_ALERT(adapter, "free list queue 0 initialization failed\n");
+ ret = -ENOMEM;
goto err;
}
if (avail < q->fl[0].size)
void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q,
struct ulptx_sgl *sgl, u64 *end, unsigned int start,
const dma_addr_t *addr);
+void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q,
+ struct ulptx_sgl *sgl, u64 *end,
+ const dma_addr_t *addr, u32 start, u32 send_len);
void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n);
int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf,
u16 vlan);
atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts));
seq_printf(seq, "TX trim pkts : %20llu\n",
atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts));
+ seq_printf(seq, "TX sw fallback : %20llu\n",
+ atomic64_read(&adap->ch_ktls_stats.ktls_tx_fallback));
while (i < MAX_NPORTS) {
ktls_port = &adap->ch_ktls_stats.ktls_port[i];
seq_printf(seq, "Port %d\n", i);
int err;
/* do a set-tcb for smac-sel and CWR bit.. */
- err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1);
- if (err)
- goto smac_err;
-
err = set_tcb_field(adap, f, f->tid, TCB_SMAC_SEL_W,
TCB_SMAC_SEL_V(TCB_SMAC_SEL_M),
TCB_SMAC_SEL_V(f->smt->idx), 1);
+ if (err)
+ goto smac_err;
+
+ err = set_tcb_tflag(adap, f, f->tid, TF_CCTRL_CWR_S, 1, 1);
if (!err)
return 0;
FW_FILTER_WR_DIRSTEERHASH_V(f->fs.dirsteerhash) |
FW_FILTER_WR_LPBK_V(f->fs.action == FILTER_SWITCH) |
FW_FILTER_WR_DMAC_V(f->fs.newdmac) |
+ FW_FILTER_WR_SMAC_V(f->fs.newsmac) |
FW_FILTER_WR_INSVLAN_V(f->fs.newvlan == VLAN_INSERT ||
f->fs.newvlan == VLAN_REWRITE) |
FW_FILTER_WR_RMVLAN_V(f->fs.newvlan == VLAN_REMOVE ||
FW_FILTER_WR_OVLAN_VLD_V(f->fs.val.ovlan_vld) |
FW_FILTER_WR_IVLAN_VLDM_V(f->fs.mask.ivlan_vld) |
FW_FILTER_WR_OVLAN_VLDM_V(f->fs.mask.ovlan_vld));
- fwr->smac_sel = 0;
+ if (f->fs.newsmac)
+ fwr->smac_sel = f->smt->idx;
fwr->rx_chan_rx_rpl_iq =
htons(FW_FILTER_WR_RX_CHAN_V(0) |
FW_FILTER_WR_RX_RPL_IQ_V(adapter->sge.fw_evtq.abs_id));
TX_QUEUE_V(f->fs.nat_mode) |
T5_OPT_2_VALID_F |
RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) |
- CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
- (f->fs.dirsteer << 1)) |
PACE_V((f->fs.maskhash) |
- ((f->fs.dirsteerhash) << 1)) |
- CCTRL_ECN_V(f->fs.action == FILTER_SWITCH));
+ ((f->fs.dirsteerhash) << 1)));
}
static void mk_act_open_req(struct filter_entry *f, struct sk_buff *skb,
TX_QUEUE_V(f->fs.nat_mode) |
T5_OPT_2_VALID_F |
RX_CHANNEL_V(cxgb4_port_e2cchan(f->dev)) |
- CONG_CNTRL_V((f->fs.action == FILTER_DROP) |
- (f->fs.dirsteer << 1)) |
PACE_V((f->fs.maskhash) |
- ((f->fs.dirsteerhash) << 1)) |
- CCTRL_ECN_V(f->fs.action == FILTER_SWITCH));
+ ((f->fs.dirsteerhash) << 1)));
}
static int cxgb4_set_hash_filter(struct net_device *dev,
}
return;
}
+ switch (f->fs.action) {
+ case FILTER_PASS:
+ if (f->fs.dirsteer)
+ set_tcb_tflag(adap, f, tid,
+ TF_DIRECT_STEER_S, 1, 1);
+ break;
+ case FILTER_DROP:
+ set_tcb_tflag(adap, f, tid, TF_DROP_S, 1, 1);
+ break;
+ case FILTER_SWITCH:
+ set_tcb_tflag(adap, f, tid, TF_LPBK_S, 1, 1);
+ break;
+ }
+
break;
default:
if (ctx)
ctx->result = 0;
} else if (ret == FW_FILTER_WR_FLT_ADDED) {
- int err = 0;
-
- if (f->fs.newsmac)
- err = configure_filter_smac(adap, f);
-
- if (!err) {
- f->pending = 0; /* async setup completed */
- f->valid = 1;
- if (ctx) {
- ctx->result = 0;
- ctx->tid = idx;
- }
- } else {
- clear_filter(adap, f);
- if (ctx)
- ctx->result = err;
+ f->pending = 0; /* async setup completed */
+ f->valid = 1;
+ if (ctx) {
+ ctx->result = 0;
+ ctx->tid = idx;
}
} else {
/* Something went wrong. Issue a warning about the
txq = netdev_pick_tx(dev, skb, sb_dev);
if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) ||
skb->encapsulation ||
+ cxgb4_is_ktls_skb(skb) ||
(proto != IPPROTO_TCP && proto != IPPROTO_UDP))
txq = txq % pi->nqsets;
atomic64_t ktls_tx_retransmit_pkts;
atomic64_t ktls_tx_complete_pkts;
atomic64_t ktls_tx_trimmed_pkts;
+ atomic64_t ktls_tx_fallback;
};
#endif
#endif
};
+static inline bool cxgb4_is_ktls_skb(struct sk_buff *skb)
+{
+ return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk);
+}
+
void cxgb4_uld_enable(struct adapter *adap);
void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p);
int cxgb4_unregister_uld(enum cxgb4_uld type);
}
EXPORT_SYMBOL(cxgb4_write_sgl);
+/* cxgb4_write_partial_sgl - populate SGL for partial packet
+ * @skb: the packet
+ * @q: the Tx queue we are writing into
+ * @sgl: starting location for writing the SGL
+ * @end: points right after the end of the SGL
+ * @addr: the list of bus addresses for the SGL elements
+ * @start: start offset in the SKB where partial data starts
+ * @len: length of data from @start to send out
+ *
+ * This API will handle sending out partial data of a skb if required.
+ * Unlike cxgb4_write_sgl, @start can be any offset into the skb data,
+ * and @len will decide how much data after @start offset to send out.
+ */
+void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q,
+ struct ulptx_sgl *sgl, u64 *end,
+ const dma_addr_t *addr, u32 start, u32 len)
+{
+ struct ulptx_sge_pair buf[MAX_SKB_FRAGS / 2 + 1] = {0}, *to;
+ u32 frag_size, skb_linear_data_len = skb_headlen(skb);
+ struct skb_shared_info *si = skb_shinfo(skb);
+ u8 i = 0, frag_idx = 0, nfrags = 0;
+ skb_frag_t *frag;
+
+ /* Fill the first SGL either from linear data or from partial
+ * frag based on @start.
+ */
+ if (unlikely(start < skb_linear_data_len)) {
+ frag_size = min(len, skb_linear_data_len - start);
+ sgl->len0 = htonl(frag_size);
+ sgl->addr0 = cpu_to_be64(addr[0] + start);
+ len -= frag_size;
+ nfrags++;
+ } else {
+ start -= skb_linear_data_len;
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ /* find the first frag */
+ while (start >= frag_size) {
+ start -= frag_size;
+ frag_idx++;
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ }
+
+ frag_size = min(len, skb_frag_size(frag) - start);
+ sgl->len0 = cpu_to_be32(frag_size);
+ sgl->addr0 = cpu_to_be64(addr[frag_idx + 1] + start);
+ len -= frag_size;
+ nfrags++;
+ frag_idx++;
+ }
+
+ /* If the entire partial data fit in one SGL, then send it out
+ * now.
+ */
+ if (!len)
+ goto done;
+
+ /* Most of the complexity below deals with the possibility we hit the
+ * end of the queue in the middle of writing the SGL. For this case
+ * only we create the SGL in a temporary buffer and then copy it.
+ */
+ to = (u8 *)end > (u8 *)q->stat ? buf : sgl->sge;
+
+ /* If the skb couldn't fit in first SGL completely, fill the
+ * rest of the frags in subsequent SGLs. Note that each SGL
+ * pair can store 2 frags.
+ */
+ while (len) {
+ frag_size = min(len, skb_frag_size(&si->frags[frag_idx]));
+ to->len[i & 1] = cpu_to_be32(frag_size);
+ to->addr[i & 1] = cpu_to_be64(addr[frag_idx + 1]);
+ if (i && (i & 1))
+ to++;
+ nfrags++;
+ frag_idx++;
+ i++;
+ len -= frag_size;
+ }
+
+ /* If we ended in an odd boundary, then set the second SGL's
+ * length in the pair to 0.
+ */
+ if (i & 1)
+ to->len[1] = cpu_to_be32(0);
+
+ /* Copy from temporary buffer to Tx ring, in case we hit the
+ * end of the queue in the middle of writing the SGL.
+ */
+ if (unlikely((u8 *)end > (u8 *)q->stat)) {
+ u32 part0 = (u8 *)q->stat - (u8 *)sgl->sge, part1;
+
+ if (likely(part0))
+ memcpy(sgl->sge, buf, part0);
+ part1 = (u8 *)end - (u8 *)q->stat;
+ memcpy(q->desc, (u8 *)buf + part0, part1);
+ end = (void *)q->desc + part1;
+ }
+
+ /* 0-pad to multiple of 16 */
+ if ((uintptr_t)end & 8)
+ *end = 0;
+done:
+ sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) |
+ ULPTX_NSGE_V(nfrags));
+}
+EXPORT_SYMBOL(cxgb4_write_partial_sgl);
+
/* This function copies 64 byte coalesced work request to
* memory mapped BAR2 space. For coalesced WR SGE fetches
* data from the FIFO instead of from Host.
#endif /* CHELSIO_IPSEC_INLINE */
#if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE)
- if (skb->decrypted)
+ if (cxgb4_is_ktls_skb(skb) &&
+ (skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb))))
return adap->uld[CXGB4_ULD_KTLS].tx_handler(skb, dev);
#endif /* CHELSIO_TLS_DEVICE */
#define TCB_T_FLAGS_M 0xffffffffffffffffULL
#define TCB_T_FLAGS_V(x) ((__u64)(x) << TCB_T_FLAGS_S)
+#define TF_DROP_S 22
+#define TF_DIRECT_STEER_S 23
+#define TF_LPBK_S 59
+
#define TF_CCTRL_ECE_S 60
#define TF_CCTRL_CWR_S 61
#define TF_CCTRL_RFR_S 62
static LIST_HEAD(uld_ctx_list);
static DEFINE_MUTEX(dev_mutex);
+/* chcr_get_nfrags_to_send: get the remaining nfrags after start offset
+ * @skb: skb
+ * @start: start offset.
+ * @len: how much data to send after @start
+ */
+static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len)
+{
+ struct skb_shared_info *si = skb_shinfo(skb);
+ u32 frag_size, skb_linear_data_len = skb_headlen(skb);
+ u8 nfrags = 0, frag_idx = 0;
+ skb_frag_t *frag;
+
+ /* if its a linear skb then return 1 */
+ if (!skb_is_nonlinear(skb))
+ return 1;
+
+ if (unlikely(start < skb_linear_data_len)) {
+ frag_size = min(len, skb_linear_data_len - start);
+ start = 0;
+ } else {
+ start -= skb_linear_data_len;
+
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ while (start >= frag_size) {
+ start -= frag_size;
+ frag_idx++;
+ frag = &si->frags[frag_idx];
+ frag_size = skb_frag_size(frag);
+ }
+ frag_size = min(len, skb_frag_size(frag) - start);
+ }
+ len -= frag_size;
+ nfrags++;
+
+ while (len) {
+ frag_size = min(len, skb_frag_size(&si->frags[frag_idx]));
+ len -= frag_size;
+ nfrags++;
+ frag_idx++;
+ }
+ return nfrags;
+}
+
static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info);
/*
* chcr_ktls_save_keys: calculate and save crypto keys.
/* need to wait for hw response, can't free tx_info yet. */
if (tx_info->open_state == CH_KTLS_OPEN_PENDING)
tx_info->pending_close = true;
- /* free the lock after the cleanup */
+ else
+ spin_unlock_bh(&tx_info->lock);
+ /* if in pending close, free the lock after the cleanup */
goto put_module;
}
spin_unlock_bh(&tx_info->lock);
}
static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info,
- u32 tid, void *pos, u16 word, u64 mask,
+ u32 tid, void *pos, u16 word,
+ struct sge_eth_txq *q, u64 mask,
u64 val, u32 reply)
{
struct cpl_set_tcb_field_core *cpl;
/* ULP_TXPKT */
txpkt = pos;
- txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0));
+ txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) |
+ ULP_TXPKT_CHANNELID_V(tx_info->port_id) |
+ ULP_TXPKT_FID_V(q->q.cntxt_id) |
+ ULP_TXPKT_RO_F);
txpkt->len = htonl(DIV_ROUND_UP(CHCR_SET_TCB_FIELD_LEN, 16));
/* ULPTX_IDATA sub-command */
} else {
u8 buf[48] = {0};
- __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word,
+ __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, q,
mask, val, reply);
return chcr_copy_to_txd(buf, &q->q, pos,
}
}
- pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word,
+ pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, q,
mask, val, reply);
/* check again if we are at the end of the queue */
*/
static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info,
struct sge_eth_txq *q, u64 tcp_seq,
- u64 tcp_ack, u64 tcp_win)
+ u64 tcp_ack, u64 tcp_win, bool offset)
{
bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0));
struct ch_ktls_port_stats_debug *port_stats;
- u32 len, cpl = 0, ndesc, wr_len;
+ u32 len, cpl = 0, ndesc, wr_len, wr_mid = 0;
struct fw_ulptx_wr *wr;
int credits;
void *pos;
return NETDEV_TX_BUSY;
}
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ chcr_eth_txq_stop(q);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
pos = &q->q.desc[q->q.pidx];
/* make space for WR, we'll fill it later when we know all the cpls
* being sent out and have complete length.
cpl++;
}
/* reset snd una if it's a re-transmit pkt */
- if (tcp_seq != tx_info->prev_seq) {
+ if (tcp_seq != tx_info->prev_seq || offset) {
/* reset snd_una */
port_stats =
&tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id];
TCB_SND_UNA_RAW_V
(TCB_SND_UNA_RAW_M),
TCB_SND_UNA_RAW_V(0), 0);
- atomic64_inc(&port_stats->ktls_tx_ooo);
+ if (tcp_seq != tx_info->prev_seq)
+ atomic64_inc(&port_stats->ktls_tx_ooo);
cpl++;
}
/* update ack */
wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR));
wr->cookie = 0;
/* fill len in wr field */
- wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
+ wr->flowid_len16 = htonl(wr_mid |
+ FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
ndesc = DIV_ROUND_UP(len, 64);
chcr_txq_advance(&q->q, ndesc);
return 0;
}
-/*
- * chcr_ktls_skb_copy
- * @nskb - new skb where the frags to be added.
- * @skb - old skb from which frags will be copied.
- */
-static void chcr_ktls_skb_copy(struct sk_buff *skb, struct sk_buff *nskb)
-{
- int i;
-
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- skb_shinfo(nskb)->frags[i] = skb_shinfo(skb)->frags[i];
- __skb_frag_ref(&skb_shinfo(nskb)->frags[i]);
- }
-
- skb_shinfo(nskb)->nr_frags = skb_shinfo(skb)->nr_frags;
- nskb->len += skb->data_len;
- nskb->data_len = skb->data_len;
- nskb->truesize += skb->data_len;
-}
-
/*
* chcr_ktls_get_tx_flits
* returns number of flits to be sent out, it includes key context length, WR
* size and skb fragments.
*/
static unsigned int
-chcr_ktls_get_tx_flits(const struct sk_buff *skb, unsigned int key_ctx_len)
+chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len)
{
- return chcr_sgl_len(skb_shinfo(skb)->nr_frags) +
+ return chcr_sgl_len(nr_frags) +
DIV_ROUND_UP(key_ctx_len + CHCR_KTLS_WR_SIZE, 8);
}
struct tcphdr *tcp;
int len16, pktlen;
struct iphdr *ip;
+ u32 wr_mid = 0;
int credits;
u8 buf[150];
+ u64 cntrl1;
void *pos;
iplen = skb_network_header_len(skb);
/* packet length = eth hdr len + ip hdr len + tcp hdr len
* (including options).
*/
- pktlen = skb->len - skb->data_len;
+ pktlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
ctrl = sizeof(*cpl) + pktlen;
len16 = DIV_ROUND_UP(sizeof(*wr) + ctrl, 16);
return NETDEV_TX_BUSY;
}
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ chcr_eth_txq_stop(q);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
pos = &q->q.desc[q->q.pidx];
wr = pos;
wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
FW_WR_IMMDLEN_V(ctrl));
- wr->equiq_to_len16 = htonl(FW_WR_LEN16_V(len16));
+ wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16));
wr->r3 = 0;
cpl = (void *)(wr + 1);
TXPKT_PF_V(tx_info->adap->pf));
cpl->pack = 0;
cpl->len = htons(pktlen);
- /* checksum offload */
- cpl->ctrl1 = 0;
-
- pos = cpl + 1;
memcpy(buf, skb->data, pktlen);
if (tx_info->ip_family == AF_INET) {
/* we need to correct ip header len */
ip = (struct iphdr *)(buf + maclen);
ip->tot_len = htons(pktlen - maclen);
+ cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP);
#if IS_ENABLED(CONFIG_IPV6)
} else {
ip6 = (struct ipv6hdr *)(buf + maclen);
ip6->payload_len = htons(pktlen - maclen - iplen);
+ cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6);
#endif
}
+
+ cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) |
+ TXPKT_IPHDR_LEN_V(iplen);
+ /* checksum offload */
+ cpl->ctrl1 = cpu_to_be64(cntrl1);
+
+ pos = cpl + 1;
+
/* now take care of the tcp header, if fin is not set then clear push
* bit as well, and if fin is set, it will be sent at the last so we
* need to update the tcp sequence number as per the last packet.
return 0;
}
-/* chcr_ktls_skb_shift - Shifts request length paged data from skb to another.
- * @tgt- buffer into which tail data gets added
- * @skb- buffer from which the paged data comes from
- * @shiftlen- shift up to this many bytes
- */
-static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
- int shiftlen)
-{
- skb_frag_t *fragfrom, *fragto;
- int from, to, todo;
-
- WARN_ON(shiftlen > skb->data_len);
-
- todo = shiftlen;
- from = 0;
- to = 0;
- fragfrom = &skb_shinfo(skb)->frags[from];
-
- while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) {
- fragfrom = &skb_shinfo(skb)->frags[from];
- fragto = &skb_shinfo(tgt)->frags[to];
-
- if (todo >= skb_frag_size(fragfrom)) {
- *fragto = *fragfrom;
- todo -= skb_frag_size(fragfrom);
- from++;
- to++;
-
- } else {
- __skb_frag_ref(fragfrom);
- skb_frag_page_copy(fragto, fragfrom);
- skb_frag_off_copy(fragto, fragfrom);
- skb_frag_size_set(fragto, todo);
-
- skb_frag_off_add(fragfrom, todo);
- skb_frag_size_sub(fragfrom, todo);
- todo = 0;
-
- to++;
- break;
- }
- }
-
- /* Ready to "commit" this state change to tgt */
- skb_shinfo(tgt)->nr_frags = to;
-
- /* Reposition in the original skb */
- to = 0;
- while (from < skb_shinfo(skb)->nr_frags)
- skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++];
-
- skb_shinfo(skb)->nr_frags = to;
-
- WARN_ON(todo > 0 && !skb_shinfo(skb)->nr_frags);
-
- skb->len -= shiftlen;
- skb->data_len -= shiftlen;
- skb->truesize -= shiftlen;
- tgt->len += shiftlen;
- tgt->data_len += shiftlen;
- tgt->truesize += shiftlen;
-
- return shiftlen;
-}
-
/*
* chcr_ktls_xmit_wr_complete: This sends out the complete record. If an skb
* received has partial end part of the record, send out the complete record, so
static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb,
struct chcr_ktls_info *tx_info,
struct sge_eth_txq *q, u32 tcp_seq,
+ bool is_last_wr, u32 data_len,
+ u32 skb_offset, u32 nfrags,
bool tcp_push, u32 mss)
{
u32 len16, wr_mid = 0, flits = 0, ndesc, cipher_start;
u64 *end;
/* get the number of flits required */
- flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len);
+ flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len);
/* number of descriptors */
ndesc = chcr_flits_to_desc(flits);
/* check if enough credits available */
return NETDEV_TX_BUSY;
}
+ if (!is_last_wr)
+ skb_get(skb);
+
pos = &q->q.desc[q->q.pidx];
end = (u64 *)pos + flits;
/* FW_ULPTX_WR */
CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) |
CPL_TX_SEC_PDU_PLACEHOLDER_V(1) |
CPL_TX_SEC_PDU_IVINSRTOFST_V(TLS_HEADER_SIZE + 1));
- cpl->pldlen = htonl(skb->data_len);
+ cpl->pldlen = htonl(data_len);
/* encryption should start after tls header size + iv size */
cipher_start = TLS_HEADER_SIZE + tx_info->iv_size + 1;
/* CPL_TX_DATA */
tx_data = (void *)pos;
OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
- tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(skb->data_len));
+ tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(data_len));
tx_data->rsvd = htonl(tcp_seq);
}
/* send the complete packet except the header */
- cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
- sgl_sdesc->addr);
+ cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+ skb_offset, data_len);
sgl_sdesc->skb = skb;
chcr_txq_advance(&q->q, ndesc);
struct sge_eth_txq *q,
u32 tcp_seq, bool tcp_push, u32 mss,
u32 tls_rec_offset, u8 *prior_data,
- u32 prior_data_len)
+ u32 prior_data_len, u32 data_len,
+ u32 skb_offset)
{
+ u32 len16, wr_mid = 0, cipher_start, nfrags;
struct adapter *adap = tx_info->adap;
- u32 len16, wr_mid = 0, cipher_start;
unsigned int flits = 0, ndesc;
int credits, left, last_desc;
struct tx_sw_desc *sgl_sdesc;
void *pos;
u64 *end;
+ nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len);
/* get the number of flits required, it's a partial record so 2 flits
* (AES_BLOCK_SIZE) will be added.
*/
- flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len) + 2;
+ flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len) + 2;
/* get the correct 8 byte IV of this record */
iv_record = cpu_to_be64(tx_info->iv + tx_info->record_no);
/* If it's a middle record and not 16 byte aligned to run AES CTR, need
htonl(CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) |
CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) |
CPL_TX_SEC_PDU_IVINSRTOFST_V(1));
- cpl->pldlen = htonl(skb->data_len + AES_BLOCK_LEN + prior_data_len);
+ cpl->pldlen = htonl(data_len + AES_BLOCK_LEN + prior_data_len);
cpl->aadstart_cipherstop_hi =
htonl(CPL_TX_SEC_PDU_CIPHERSTART_V(cipher_start));
cpl->cipherstop_lo_authinsert = 0;
tx_data = (void *)pos;
OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
tx_data->len = htonl(TX_DATA_MSS_V(mss) |
- TX_LENGTH_V(skb->data_len + prior_data_len));
+ TX_LENGTH_V(data_len + prior_data_len));
tx_data->rsvd = htonl(tcp_seq);
tx_data->flags = htonl(TX_BYPASS_F);
if (tcp_push)
if (prior_data_len)
pos = chcr_copy_to_txd(prior_data, &q->q, pos, 16);
/* send the complete packet except the header */
- cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
- sgl_sdesc->addr);
+ cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+ skb_offset, data_len);
sgl_sdesc->skb = skb;
chcr_txq_advance(&q->q, ndesc);
struct sk_buff *skb, u32 tcp_seq, u32 mss,
bool tcp_push, struct sge_eth_txq *q,
u32 port_id, u8 *prior_data,
+ u32 data_len, u32 skb_offset,
u32 prior_data_len)
{
int credits, left, len16, last_desc;
struct ulptx_idata *idata;
struct ulp_txpkt *ulptx;
struct fw_ulptx_wr *wr;
- u32 wr_mid = 0;
+ u32 wr_mid = 0, nfrags;
void *pos;
u64 *end;
flits = DIV_ROUND_UP(CHCR_PLAIN_TX_DATA_LEN, 8);
- flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags);
+ nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len);
+ flits += chcr_sgl_len(nfrags);
if (prior_data_len)
flits += 2;
+
/* WR will need len16 */
len16 = DIV_ROUND_UP(flits, 2);
/* check how many descriptors needed */
tx_data = (struct cpl_tx_data *)(idata + 1);
OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid));
tx_data->len = htonl(TX_DATA_MSS_V(mss) |
- TX_LENGTH_V(skb->data_len + prior_data_len));
+ TX_LENGTH_V(data_len + prior_data_len));
/* set tcp seq number */
tx_data->rsvd = htonl(tcp_seq);
tx_data->flags = htonl(TX_BYPASS_F);
end = pos + left;
}
/* send the complete packet including the header */
- cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len,
- sgl_sdesc->addr);
+ cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr,
+ skb_offset, data_len);
sgl_sdesc->skb = skb;
chcr_txq_advance(&q->q, ndesc);
return 0;
}
+static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info,
+ struct sk_buff *skb,
+ struct sge_eth_txq *q)
+{
+ u32 ctrl, iplen, maclen, wr_mid = 0, len16;
+ struct tx_sw_desc *sgl_sdesc;
+ struct fw_eth_tx_pkt_wr *wr;
+ struct cpl_tx_pkt_core *cpl;
+ unsigned int flits, ndesc;
+ int credits, last_desc;
+ u64 cntrl1, *end;
+ void *pos;
+
+ ctrl = sizeof(*cpl);
+ flits = DIV_ROUND_UP(sizeof(*wr) + ctrl, 8);
+
+ flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags + 1);
+ len16 = DIV_ROUND_UP(flits, 2);
+ /* check how many descriptors needed */
+ ndesc = DIV_ROUND_UP(flits, 8);
+
+ credits = chcr_txq_avail(&q->q) - ndesc;
+ if (unlikely(credits < 0)) {
+ chcr_eth_txq_stop(q);
+ return -ENOMEM;
+ }
+
+ if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+ chcr_eth_txq_stop(q);
+ wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+ }
+
+ last_desc = q->q.pidx + ndesc - 1;
+ if (last_desc >= q->q.size)
+ last_desc -= q->q.size;
+ sgl_sdesc = &q->q.sdesc[last_desc];
+
+ if (unlikely(cxgb4_map_skb(tx_info->adap->pdev_dev, skb,
+ sgl_sdesc->addr) < 0)) {
+ memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr));
+ q->mapping_err++;
+ return -ENOMEM;
+ }
+
+ iplen = skb_network_header_len(skb);
+ maclen = skb_mac_header_len(skb);
+
+ pos = &q->q.desc[q->q.pidx];
+ end = (u64 *)pos + flits;
+ wr = pos;
+
+ /* Firmware work request header */
+ wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
+ FW_WR_IMMDLEN_V(ctrl));
+
+ wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16));
+ wr->r3 = 0;
+
+ cpl = (void *)(wr + 1);
+
+ /* CPL header */
+ cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT) |
+ TXPKT_INTF_V(tx_info->tx_chan) |
+ TXPKT_PF_V(tx_info->adap->pf));
+ cpl->pack = 0;
+ cntrl1 = TXPKT_CSUM_TYPE_V(tx_info->ip_family == AF_INET ?
+ TX_CSUM_TCPIP : TX_CSUM_TCPIP6);
+ cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) |
+ TXPKT_IPHDR_LEN_V(iplen);
+ /* checksum offload */
+ cpl->ctrl1 = cpu_to_be64(cntrl1);
+ cpl->len = htons(skb->len);
+
+ pos = cpl + 1;
+
+ cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr);
+ sgl_sdesc->skb = skb;
+ chcr_txq_advance(&q->q, ndesc);
+ cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
+ return 0;
+}
+
/*
* chcr_ktls_copy_record_in_skb
* @nskb - new skb where the frags to be added.
+ * @skb - old skb, to copy socket and destructor details.
* @record - specific record which has complete 16k record in frags.
*/
static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb,
+ struct sk_buff *skb,
struct tls_record_info *record)
{
int i = 0;
nskb->data_len = record->len;
nskb->len += record->len;
nskb->truesize += record->len;
+ nskb->sk = skb->sk;
+ nskb->destructor = skb->destructor;
+ refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc);
}
/*
struct sk_buff *skb,
struct tls_record_info *record,
u32 tcp_seq, int mss, bool tcp_push_no_fin,
- struct sge_eth_txq *q,
+ struct sge_eth_txq *q, u32 skb_offset,
u32 tls_end_offset, bool last_wr)
{
struct sk_buff *nskb = NULL;
nskb = skb;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_complete_pkts);
} else {
- dev_kfree_skb_any(skb);
-
- nskb = alloc_skb(0, GFP_KERNEL);
- if (!nskb)
+ nskb = alloc_skb(0, GFP_ATOMIC);
+ if (!nskb) {
+ dev_kfree_skb_any(skb);
return NETDEV_TX_BUSY;
+ }
+
/* copy complete record in skb */
- chcr_ktls_copy_record_in_skb(nskb, record);
+ chcr_ktls_copy_record_in_skb(nskb, skb, record);
/* packet is being sent from the beginning, update the tcp_seq
* accordingly.
*/
tcp_seq = tls_record_start_seq(record);
- /* reset snd una, so the middle record won't send the already
- * sent part.
- */
- if (chcr_ktls_update_snd_una(tx_info, q))
- goto out;
+ /* reset skb offset */
+ skb_offset = 0;
+
+ if (last_wr)
+ dev_kfree_skb_any(skb);
+
+ last_wr = true;
+
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_end_pkts);
}
if (chcr_ktls_xmit_wr_complete(nskb, tx_info, q, tcp_seq,
+ last_wr, record->len, skb_offset,
+ record->num_frags,
(last_wr && tcp_push_no_fin),
mss)) {
goto out;
}
+ tx_info->prev_seq = record->end_seq;
return 0;
out:
dev_kfree_skb_any(nskb);
struct sk_buff *skb,
struct tls_record_info *record,
u32 tcp_seq, int mss, bool tcp_push_no_fin,
+ u32 data_len, u32 skb_offset,
struct sge_eth_txq *q, u32 tls_end_offset)
{
u32 tls_rec_offset = tcp_seq - tls_record_start_seq(record);
u8 prior_data[16] = {0};
u32 prior_data_len = 0;
- u32 data_len;
/* check if the skb is ending in middle of tag/HASH, its a big
* trouble, send the packet before the HASH.
*/
- int remaining_record = tls_end_offset - skb->data_len;
+ int remaining_record = tls_end_offset - data_len;
if (remaining_record > 0 &&
remaining_record < TLS_CIPHER_AES_GCM_128_TAG_SIZE) {
- int trimmed_len = skb->data_len -
- (TLS_CIPHER_AES_GCM_128_TAG_SIZE - remaining_record);
- struct sk_buff *tmp_skb = NULL;
- /* don't process the pkt if it is only a partial tag */
- if (skb->data_len < TLS_CIPHER_AES_GCM_128_TAG_SIZE)
- goto out;
+ int trimmed_len = 0;
- WARN_ON(trimmed_len > skb->data_len);
+ if (tls_end_offset > TLS_CIPHER_AES_GCM_128_TAG_SIZE)
+ trimmed_len = data_len -
+ (TLS_CIPHER_AES_GCM_128_TAG_SIZE -
+ remaining_record);
+ if (!trimmed_len)
+ return FALLBACK;
- /* shift to those many bytes */
- tmp_skb = alloc_skb(0, GFP_KERNEL);
- if (unlikely(!tmp_skb))
- goto out;
+ WARN_ON(trimmed_len > data_len);
- chcr_ktls_skb_shift(tmp_skb, skb, trimmed_len);
- /* free the last trimmed portion */
- dev_kfree_skb_any(skb);
- skb = tmp_skb;
+ data_len = trimmed_len;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_trimmed_pkts);
}
- data_len = skb->data_len;
+
+ /* check if it is only the header part. */
+ if (tls_rec_offset + data_len <= (TLS_HEADER_SIZE + tx_info->iv_size)) {
+ if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
+ tcp_push_no_fin, q,
+ tx_info->port_id, prior_data,
+ data_len, skb_offset, prior_data_len))
+ goto out;
+
+ tx_info->prev_seq = tcp_seq + data_len;
+ return 0;
+ }
+
/* check if the middle record's start point is 16 byte aligned. CTR
* needs 16 byte aligned start point to start encryption.
*/
}
/* reset tcp_seq as per the prior_data_required len */
tcp_seq -= prior_data_len;
- /* include prio_data_len for further calculation.
- */
- data_len += prior_data_len;
}
/* reset snd una, so the middle record won't send the already
* sent part.
goto out;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts);
} else {
- /* Else means, its a partial first part of the record. Check if
- * its only the header, don't need to send for encryption then.
- */
- if (data_len <= TLS_HEADER_SIZE + tx_info->iv_size) {
- if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
- tcp_push_no_fin, q,
- tx_info->port_id,
- prior_data,
- prior_data_len)) {
- goto out;
- }
- return 0;
- }
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts);
}
if (chcr_ktls_xmit_wr_short(skb, tx_info, q, tcp_seq, tcp_push_no_fin,
mss, tls_rec_offset, prior_data,
- prior_data_len)) {
+ prior_data_len, data_len, skb_offset)) {
goto out;
}
+ tx_info->prev_seq = tcp_seq + data_len + prior_data_len;
return 0;
out:
dev_kfree_skb_any(skb);
return NETDEV_TX_BUSY;
}
+static int chcr_ktls_sw_fallback(struct sk_buff *skb,
+ struct chcr_ktls_info *tx_info,
+ struct sge_eth_txq *q)
+{
+ u32 data_len, skb_offset;
+ struct sk_buff *nskb;
+ struct tcphdr *th;
+
+ nskb = tls_encrypt_skb(skb);
+
+ if (!nskb)
+ return 0;
+
+ th = tcp_hdr(nskb);
+ skb_offset = skb_transport_offset(nskb) + tcp_hdrlen(nskb);
+ data_len = nskb->len - skb_offset;
+ skb_tx_timestamp(nskb);
+
+ if (chcr_ktls_tunnel_pkt(tx_info, nskb, q))
+ goto out;
+
+ tx_info->prev_seq = ntohl(th->seq) + data_len;
+ atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_fallback);
+ return 0;
+out:
+ dev_kfree_skb_any(nskb);
+ return 0;
+}
/* nic tls TX handler */
static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ u32 tls_end_offset, tcp_seq, skb_data_len, skb_offset;
struct ch_ktls_port_stats_debug *port_stats;
struct chcr_ktls_ofld_ctx_tx *tx_ctx;
struct ch_ktls_stats_debug *stats;
int data_len, qidx, ret = 0, mss;
struct tls_record_info *record;
struct chcr_ktls_info *tx_info;
- u32 tls_end_offset, tcp_seq;
struct tls_context *tls_ctx;
- struct sk_buff *local_skb;
struct sge_eth_txq *q;
struct adapter *adap;
unsigned long flags;
tcp_seq = ntohl(th->seq);
+ skb_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
+ skb_data_len = skb->len - skb_offset;
+ data_len = skb_data_len;
- mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : skb->data_len;
-
- /* check if we haven't set it for ktls offload */
- if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk))
- goto out;
+ mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len;
tls_ctx = tls_get_ctx(skb->sk);
if (unlikely(tls_ctx->netdev != dev))
if (unlikely(!tx_info))
goto out;
- /* don't touch the original skb, make a new skb to extract each records
- * and send them separately.
- */
- local_skb = alloc_skb(0, GFP_KERNEL);
-
- if (unlikely(!local_skb))
- return NETDEV_TX_BUSY;
-
adap = tx_info->adap;
stats = &adap->ch_ktls_stats;
port_stats = &stats->ktls_port[tx_info->port_id];
if (ret)
return NETDEV_TX_BUSY;
}
- /* update tcb */
- ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, ntohl(th->seq),
- ntohl(th->ack_seq),
- ntohs(th->window));
- if (ret) {
- dev_kfree_skb_any(local_skb);
- return NETDEV_TX_BUSY;
- }
- /* copy skb contents into local skb */
- chcr_ktls_skb_copy(skb, local_skb);
-
- /* go through the skb and send only one record at a time. */
- data_len = skb->data_len;
/* TCP segments can be in received either complete or partial.
* chcr_end_part_handler will handle cases if complete record or end
* part of the record is received. Incase of partial end part of record,
goto out;
}
+ tls_end_offset = record->end_seq - tcp_seq;
+
+ pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n",
+ tcp_seq, record->end_seq, tx_info->prev_seq, data_len);
+ /* update tcb for the skb */
+ if (skb_data_len == data_len) {
+ u32 tx_max = tcp_seq;
+
+ if (!tls_record_is_start_marker(record) &&
+ tls_end_offset < TLS_CIPHER_AES_GCM_128_TAG_SIZE)
+ tx_max = record->end_seq -
+ TLS_CIPHER_AES_GCM_128_TAG_SIZE;
+
+ ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, tx_max,
+ ntohl(th->ack_seq),
+ ntohs(th->window),
+ tls_end_offset !=
+ record->len);
+ if (ret) {
+ spin_unlock_irqrestore(&tx_ctx->base.lock,
+ flags);
+ goto out;
+ }
+
+ if (th->fin)
+ skb_get(skb);
+ }
+
if (unlikely(tls_record_is_start_marker(record))) {
- spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data);
- goto out;
+ /* If tls_end_offset < data_len, means there is some
+ * data after start marker, which needs encryption, send
+ * plaintext first and take skb refcount. else send out
+ * complete pkt as plaintext.
+ */
+ if (tls_end_offset < data_len)
+ skb_get(skb);
+ else
+ tls_end_offset = data_len;
+
+ ret = chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss,
+ (!th->fin && th->psh), q,
+ tx_info->port_id, NULL,
+ tls_end_offset, skb_offset,
+ 0);
+
+ spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
+ if (ret) {
+ /* free the refcount taken earlier */
+ if (tls_end_offset < data_len)
+ dev_kfree_skb_any(skb);
+ goto out;
+ }
+
+ data_len -= tls_end_offset;
+ tcp_seq = record->end_seq;
+ skb_offset += tls_end_offset;
+ continue;
}
/* increase page reference count of the record, so that there
/* lock cleared */
spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
- tls_end_offset = record->end_seq - tcp_seq;
- pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n",
- tcp_seq, record->end_seq, tx_info->prev_seq, data_len);
/* if a tls record is finishing in this SKB */
if (tls_end_offset <= data_len) {
- struct sk_buff *nskb = NULL;
-
- if (tls_end_offset < data_len) {
- nskb = alloc_skb(0, GFP_KERNEL);
- if (unlikely(!nskb)) {
- ret = -ENOMEM;
- goto clear_ref;
- }
-
- chcr_ktls_skb_shift(nskb, local_skb,
- tls_end_offset);
- } else {
- /* its the only record in this skb, directly
- * point it.
- */
- nskb = local_skb;
- }
- ret = chcr_end_part_handler(tx_info, nskb, record,
+ ret = chcr_end_part_handler(tx_info, skb, record,
tcp_seq, mss,
(!th->fin && th->psh), q,
+ skb_offset,
tls_end_offset,
- (nskb == local_skb));
-
- if (ret && nskb != local_skb)
- dev_kfree_skb_any(local_skb);
+ skb_offset +
+ tls_end_offset == skb->len);
data_len -= tls_end_offset;
/* tcp_seq increment is required to handle next record.
*/
tcp_seq += tls_end_offset;
+ skb_offset += tls_end_offset;
} else {
- ret = chcr_short_record_handler(tx_info, local_skb,
+ ret = chcr_short_record_handler(tx_info, skb,
record, tcp_seq, mss,
(!th->fin && th->psh),
+ data_len, skb_offset,
q, tls_end_offset);
data_len = 0;
}
-clear_ref:
+
/* clear the frag ref count which increased locally before */
for (i = 0; i < record->num_frags; i++) {
/* clear the frag ref count */
__skb_frag_unref(&record->frags[i]);
}
/* if any failure, come out from the loop. */
- if (ret)
- goto out;
+ if (ret) {
+ if (th->fin)
+ dev_kfree_skb_any(skb);
+
+ if (ret == FALLBACK)
+ return chcr_ktls_sw_fallback(skb, tx_info, q);
+
+ return NETDEV_TX_OK;
+ }
+
/* length should never be less than 0 */
WARN_ON(data_len < 0);
} while (data_len > 0);
- tx_info->prev_seq = ntohl(th->seq) + skb->data_len;
atomic64_inc(&port_stats->ktls_tx_encrypted_packets);
- atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes);
+ atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes);
/* tcp finish is set, send a separate tcp msg including all the options
* as well.
*/
- if (th->fin)
+ if (th->fin) {
chcr_ktls_write_tcp_options(tx_info, skb, q, tx_info->tx_chan);
+ dev_kfree_skb_any(skb);
+ }
+ return NETDEV_TX_OK;
out:
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
#define CHCR_KTLS_WR_SIZE (CHCR_PLAIN_TX_DATA_LEN +\
sizeof(struct cpl_tx_sec_pdu))
+#define FALLBACK 35
enum ch_ktls_open_state {
CH_KTLS_OPEN_SUCCESS = 0,
{
if (likely(skb && !skb_shared(skb) && !skb_cloned(skb))) {
__skb_trim(skb, 0);
- refcount_add(2, &skb->users);
+ refcount_inc(&skb->users);
} else {
skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL);
}
if (rpl->status != CPL_ERR_NONE) {
pr_info("Unexpected PASS_OPEN_RPL status %u for STID %u\n",
rpl->status, stid);
- return CPL_RET_BUF_DONE;
+ } else {
+ cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
+ sock_put(listen_ctx->lsk);
+ kfree(listen_ctx);
+ module_put(THIS_MODULE);
}
- cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
- sock_put(listen_ctx->lsk);
- kfree(listen_ctx);
- module_put(THIS_MODULE);
-
- return 0;
+ return CPL_RET_BUF_DONE;
}
static int chtls_close_listsrv_rpl(struct chtls_dev *cdev, struct sk_buff *skb)
if (rpl->status != CPL_ERR_NONE) {
pr_info("Unexpected CLOSE_LISTSRV_RPL status %u for STID %u\n",
rpl->status, stid);
- return CPL_RET_BUF_DONE;
+ } else {
+ cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
+ sock_put(listen_ctx->lsk);
+ kfree(listen_ctx);
+ module_put(THIS_MODULE);
}
-
- cxgb4_free_stid(cdev->tids, stid, listen_ctx->lsk->sk_family);
- sock_put(listen_ctx->lsk);
- kfree(listen_ctx);
- module_put(THIS_MODULE);
-
- return 0;
+ return CPL_RET_BUF_DONE;
}
static void chtls_purge_wr_queue(struct sock *sk)
sk_setup_caps(newsk, dst);
ctx = tls_get_ctx(lsk);
newsk->sk_destruct = ctx->sk_destruct;
+ newsk->sk_prot_creator = lsk->sk_prot_creator;
csk->sk = newsk;
csk->passive_reap_next = oreq;
csk->tx_chan = cxgb4_port_chan(ndev);
struct chtls_sock *csk = sk->sk_user_data;
local_bh_disable();
- bh_lock_sock(sk);
release_tcp_port(sk); /* release the port immediately */
spin_lock(&reap_list_lock);
if (!csk->passive_reap_next)
schedule_work(&reap_task);
spin_unlock(&reap_list_lock);
- bh_unlock_sock(sk);
local_bh_enable();
}
if (ret)
goto out_notcb;
+ if (unlikely(csk_flag(sk, CSK_ABORT_SHUTDOWN)))
+ goto out_notcb;
+
set_wr_txq(skb, CPL_PRIORITY_DATA, csk->tlshws.txqid);
csk->wr_credits -= DIV_ROUND_UP(len, 16);
csk->wr_unacked += DIV_ROUND_UP(len, 16);
enqueue_wr(csk, skb);
cxgb4_ofld_send(csk->egress_dev, skb);
+ skb = NULL;
chtls_set_scmd(csk);
/* Clear quiesce for Rx key */
tp->urg_data = 0;
if ((avail + offset) >= skb->len) {
+ struct sk_buff *next_skb;
if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_TLS_HDR) {
tp->copied_seq += skb->len;
hws->rcvpld = skb->hdr_len;
chtls_free_skb(sk, skb);
buffers_freed++;
hws->copied_seq = 0;
- if (copied >= target &&
- !skb_peek(&sk->sk_receive_queue))
+ next_skb = skb_peek(&sk->sk_receive_queue);
+ if (copied >= target && !next_skb)
+ break;
+ if (ULP_SKB_CB(next_skb)->flags & ULPCB_FLAG_TLS_HDR)
break;
}
} while (len > 0);
clk_disable_unprepare(priv->rclk);
clk_disable_unprepare(priv->clk);
err_ncsi_dev:
+ if (priv->ndev)
+ ncsi_unregister_dev(priv->ndev);
ftgmac100_destroy_mdio(netdev);
err_setup_mdio:
iounmap(priv->base);
netdev = platform_get_drvdata(pdev);
priv = netdev_priv(netdev);
+ if (priv->ndev)
+ ncsi_unregister_dev(priv->ndev);
unregister_netdev(netdev);
clk_disable_unprepare(priv->rclk);
#define DPAA_PARSE_RESULTS_SIZE sizeof(struct fman_prs_result)
#define DPAA_TIME_STAMP_SIZE 8
#define DPAA_HASH_RESULTS_SIZE 8
+#define DPAA_HWA_SIZE (DPAA_PARSE_RESULTS_SIZE + DPAA_TIME_STAMP_SIZE \
+ + DPAA_HASH_RESULTS_SIZE)
+#define DPAA_RX_PRIV_DATA_DEFAULT_SIZE (DPAA_TX_PRIV_DATA_SIZE + \
+ dpaa_rx_extra_headroom)
#ifdef CONFIG_DPAA_ERRATUM_A050385
-#define DPAA_RX_PRIV_DATA_SIZE (DPAA_A050385_ALIGN - (DPAA_PARSE_RESULTS_SIZE\
- + DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE))
+#define DPAA_RX_PRIV_DATA_A050385_SIZE (DPAA_A050385_ALIGN - DPAA_HWA_SIZE)
+#define DPAA_RX_PRIV_DATA_SIZE (fman_has_errata_a050385() ? \
+ DPAA_RX_PRIV_DATA_A050385_SIZE : \
+ DPAA_RX_PRIV_DATA_DEFAULT_SIZE)
#else
-#define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \
- dpaa_rx_extra_headroom)
+#define DPAA_RX_PRIV_DATA_SIZE DPAA_RX_PRIV_DATA_DEFAULT_SIZE
#endif
#define DPAA_ETH_PCD_RXQ_NUM 128
skb_copy_header(new_skb, skb);
new_skb->dev = skb->dev;
+ /* Copy relevant timestamp info from the old skb to the new */
+ if (priv->tx_tstamp) {
+ skb_shinfo(new_skb)->tx_flags = skb_shinfo(skb)->tx_flags;
+ skb_shinfo(new_skb)->hwtstamps = skb_shinfo(skb)->hwtstamps;
+ skb_shinfo(new_skb)->tskey = skb_shinfo(skb)->tskey;
+ if (skb->sk)
+ skb_set_owner_w(new_skb, skb->sk);
+ }
+
/* We move the headroom when we align it so we have to reset the
* network and transport header offsets relative to the new data
* pointer. The checksum offload relies on these offsets.
skb_set_network_header(new_skb, skb_network_offset(skb));
skb_set_transport_header(new_skb, skb_transport_offset(skb));
- /* TODO: does timestamping need the result in the old skb? */
dev_kfree_skb(skb);
*s = new_skb;
return err;
}
-static inline u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl)
+static u16 dpaa_get_headroom(struct dpaa_buffer_layout *bl,
+ enum port_type port)
{
u16 headroom;
*
* Also make sure the headroom is a multiple of data_align bytes
*/
- headroom = (u16)(bl->priv_data_size + DPAA_PARSE_RESULTS_SIZE +
- DPAA_TIME_STAMP_SIZE + DPAA_HASH_RESULTS_SIZE);
+ headroom = (u16)(bl[port].priv_data_size + DPAA_HWA_SIZE);
- return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
+ if (port == RX)
+ return ALIGN(headroom, DPAA_FD_RX_DATA_ALIGNMENT);
+ else
+ return ALIGN(headroom, DPAA_FD_DATA_ALIGNMENT);
}
static int dpaa_eth_probe(struct platform_device *pdev)
goto free_dpaa_fqs;
}
- priv->tx_headroom = dpaa_get_headroom(&priv->buf_layout[TX]);
- priv->rx_headroom = dpaa_get_headroom(&priv->buf_layout[RX]);
+ priv->tx_headroom = dpaa_get_headroom(priv->buf_layout, TX);
+ priv->rx_headroom = dpaa_get_headroom(priv->buf_layout, RX);
/* All real interfaces need their ports initialized */
err = dpaa_eth_init_ports(mac_dev, dpaa_bp, &port_fqs,
depends on FSL_MC_BUS && FSL_MC_DPIO
select PHYLINK
select PCS_LYNX
+ select FSL_XGMAC_MDIO
+ select NET_DEVLINK
help
This is the DPAA2 Ethernet driver supporting Freescale SoCs
with DPAA2 (DataPath Acceleration Architecture v2).
config FSL_ENETC_VF
tristate "ENETC VF driver"
depends on PCI && PCI_MSI
+ select FSL_ENETC_MDIO
select PHYLINK
select DIMLIB
help
return NETDEV_TX_BUSY;
}
+ enetc_lock_mdio();
count = enetc_map_tx_buffs(tx_ring, skb, priv->active_offloads);
+ enetc_unlock_mdio();
+
if (unlikely(!count))
goto drop_packet_err;
skb_tx_timestamp(skb);
/* let H/W know BD ring has been updated */
- enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */
+ enetc_wr_reg_hot(tx_ring->tpir, i); /* includes wmb() */
return count;
struct enetc_int_vector *v = data;
int i;
+ enetc_lock_mdio();
+
/* disable interrupts */
- enetc_wr_reg(v->rbier, 0);
- enetc_wr_reg(v->ricr1, v->rx_ictt);
+ enetc_wr_reg_hot(v->rbier, 0);
+ enetc_wr_reg_hot(v->ricr1, v->rx_ictt);
for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
- enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
+ enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i), 0);
+
+ enetc_unlock_mdio();
napi_schedule(&v->napi);
v->rx_napi_work = false;
+ enetc_lock_mdio();
+
/* enable interrupts */
- enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
+ enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE);
for_each_set_bit(i, &v->tx_rings_map, ENETC_MAX_NUM_TXQS)
- enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
- ENETC_TBIER_TXTIE);
+ enetc_wr_reg_hot(v->tbier_base + ENETC_BDR_OFF(i),
+ ENETC_TBIER_TXTIE);
+
+ enetc_unlock_mdio();
return work_done;
}
static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci)
{
- int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK;
+ int pi = enetc_rd_reg_hot(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK;
return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi;
}
i = tx_ring->next_to_clean;
tx_swbd = &tx_ring->tx_swbd[i];
+
+ enetc_lock_mdio();
bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+ enetc_unlock_mdio();
do_tstamp = false;
tx_swbd = tx_ring->tx_swbd;
}
+ enetc_lock_mdio();
+
/* BD iteration loop end */
if (is_eof) {
tx_frm_cnt++;
/* re-arm interrupt source */
- enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) |
- BIT(16 + tx_ring->index));
+ enetc_wr_reg_hot(tx_ring->idr, BIT(tx_ring->index) |
+ BIT(16 + tx_ring->index));
}
if (unlikely(!bds_to_clean))
bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+
+ enetc_unlock_mdio();
}
tx_ring->next_to_clean = i;
if (likely(j)) {
rx_ring->next_to_alloc = i; /* keep track from page reuse */
rx_ring->next_to_use = i;
- /* update ENETC's consumer index */
- enetc_wr_reg(rx_ring->rcir, i);
}
return j;
u64 tstamp;
if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TSTMP) {
- lo = enetc_rd(hw, ENETC_SICTR0);
- hi = enetc_rd(hw, ENETC_SICTR1);
+ lo = enetc_rd_reg_hot(hw->reg + ENETC_SICTR0);
+ hi = enetc_rd_reg_hot(hw->reg + ENETC_SICTR1);
rxbd = enetc_rxbd_ext(rxbd);
tstamp_lo = le32_to_cpu(rxbd->ext.tstamp);
if (lo <= tstamp_lo)
u32 bd_status;
u16 size;
+ enetc_lock_mdio();
+
if (cleaned_cnt >= ENETC_RXBD_BUNDLE) {
int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt);
+ /* update ENETC's consumer index */
+ enetc_wr_reg_hot(rx_ring->rcir, rx_ring->next_to_use);
cleaned_cnt -= count;
}
rxbd = enetc_rxbd(rx_ring, i);
bd_status = le32_to_cpu(rxbd->r.lstatus);
- if (!bd_status)
+ if (!bd_status) {
+ enetc_unlock_mdio();
break;
+ }
- enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index));
+ enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index));
dma_rmb(); /* for reading other rxbd fields */
size = le16_to_cpu(rxbd->r.buf_len);
skb = enetc_map_rx_buff_to_skb(rx_ring, i, size);
- if (!skb)
+ if (!skb) {
+ enetc_unlock_mdio();
break;
+ }
enetc_get_offloads(rx_ring, rxbd, skb);
if (unlikely(bd_status &
ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) {
+ enetc_unlock_mdio();
dev_kfree_skb(skb);
while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
dma_rmb();
enetc_process_skb(rx_ring, skb);
+ enetc_unlock_mdio();
+
napi_gro_receive(napi, skb);
rx_frm_cnt++;
rx_ring->idr = hw->reg + ENETC_SIRXIDR;
enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
+ enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use);
/* enable ring */
enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);
void __iomem *global;
};
-/* general register accessors */
-#define enetc_rd_reg(reg) ioread32((reg))
-#define enetc_wr_reg(reg, val) iowrite32((val), (reg))
+/* ENETC register accessors */
+
+/* MDIO issue workaround (on LS1028A) -
+ * Due to a hardware issue, an access to MDIO registers
+ * that is concurrent with other ENETC register accesses
+ * may lead to the MDIO access being dropped or corrupted.
+ * To protect the MDIO accesses a readers-writers locking
+ * scheme is used, where the MDIO register accesses are
+ * protected by write locks to insure exclusivity, while
+ * the remaining ENETC registers are accessed under read
+ * locks since they only compete with MDIO accesses.
+ */
+extern rwlock_t enetc_mdio_lock;
+
+/* use this locking primitive only on the fast datapath to
+ * group together multiple non-MDIO register accesses to
+ * minimize the overhead of the lock
+ */
+static inline void enetc_lock_mdio(void)
+{
+ read_lock(&enetc_mdio_lock);
+}
+
+static inline void enetc_unlock_mdio(void)
+{
+ read_unlock(&enetc_mdio_lock);
+}
+
+/* use these accessors only on the fast datapath under
+ * the enetc_lock_mdio() locking primitive to minimize
+ * the overhead of the lock
+ */
+static inline u32 enetc_rd_reg_hot(void __iomem *reg)
+{
+ lockdep_assert_held(&enetc_mdio_lock);
+
+ return ioread32(reg);
+}
+
+static inline void enetc_wr_reg_hot(void __iomem *reg, u32 val)
+{
+ lockdep_assert_held(&enetc_mdio_lock);
+
+ iowrite32(val, reg);
+}
+
+/* internal helpers for the MDIO w/a */
+static inline u32 _enetc_rd_reg_wa(void __iomem *reg)
+{
+ u32 val;
+
+ enetc_lock_mdio();
+ val = ioread32(reg);
+ enetc_unlock_mdio();
+
+ return val;
+}
+
+static inline void _enetc_wr_reg_wa(void __iomem *reg, u32 val)
+{
+ enetc_lock_mdio();
+ iowrite32(val, reg);
+ enetc_unlock_mdio();
+}
+
+static inline u32 _enetc_rd_mdio_reg_wa(void __iomem *reg)
+{
+ unsigned long flags;
+ u32 val;
+
+ write_lock_irqsave(&enetc_mdio_lock, flags);
+ val = ioread32(reg);
+ write_unlock_irqrestore(&enetc_mdio_lock, flags);
+
+ return val;
+}
+
+static inline void _enetc_wr_mdio_reg_wa(void __iomem *reg, u32 val)
+{
+ unsigned long flags;
+
+ write_lock_irqsave(&enetc_mdio_lock, flags);
+ iowrite32(val, reg);
+ write_unlock_irqrestore(&enetc_mdio_lock, flags);
+}
+
#ifdef ioread64
-#define enetc_rd_reg64(reg) ioread64((reg))
+static inline u64 _enetc_rd_reg64(void __iomem *reg)
+{
+ return ioread64(reg);
+}
#else
/* using this to read out stats on 32b systems */
-static inline u64 enetc_rd_reg64(void __iomem *reg)
+static inline u64 _enetc_rd_reg64(void __iomem *reg)
{
u32 low, high, tmp;
}
#endif
+static inline u64 _enetc_rd_reg64_wa(void __iomem *reg)
+{
+ u64 val;
+
+ enetc_lock_mdio();
+ val = _enetc_rd_reg64(reg);
+ enetc_unlock_mdio();
+
+ return val;
+}
+
+/* general register accessors */
+#define enetc_rd_reg(reg) _enetc_rd_reg_wa((reg))
+#define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val))
#define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off))
#define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val)
-#define enetc_rd64(hw, off) enetc_rd_reg64((hw)->reg + (off))
+#define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off))
/* port register accessors - PF only */
#define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off))
#define enetc_port_wr(hw, off, val) enetc_wr_reg((hw)->port + (off), val)
+#define enetc_port_rd_mdio(hw, off) _enetc_rd_mdio_reg_wa((hw)->port + (off))
+#define enetc_port_wr_mdio(hw, off, val) _enetc_wr_mdio_reg_wa(\
+ (hw)->port + (off), val)
/* global register accessors - PF only */
#define enetc_global_rd(hw, off) enetc_rd_reg((hw)->global + (off))
#define enetc_global_wr(hw, off, val) enetc_wr_reg((hw)->global + (off), val)
static inline u32 _enetc_mdio_rd(struct enetc_mdio_priv *mdio_priv, int off)
{
- return enetc_port_rd(mdio_priv->hw, mdio_priv->mdio_base + off);
+ return enetc_port_rd_mdio(mdio_priv->hw, mdio_priv->mdio_base + off);
}
static inline void _enetc_mdio_wr(struct enetc_mdio_priv *mdio_priv, int off,
u32 val)
{
- enetc_port_wr(mdio_priv->hw, mdio_priv->mdio_base + off, val);
+ enetc_port_wr_mdio(mdio_priv->hw, mdio_priv->mdio_base + off, val);
}
#define enetc_mdio_rd(mdio_priv, off) \
return hw;
}
EXPORT_SYMBOL_GPL(enetc_hw_alloc);
+
+/* Lock for MDIO access errata on LS1028A */
+DEFINE_RWLOCK(enetc_mdio_lock);
+EXPORT_SYMBOL_GPL(enetc_mdio_lock);
gcl_config->atc = 0xff;
gcl_config->acl_len = cpu_to_le16(gcl_len);
- if (!admin_conf->base_time) {
- gcl_data->btl =
- cpu_to_le32(enetc_rd(&priv->si->hw, ENETC_SICTR0));
- gcl_data->bth =
- cpu_to_le32(enetc_rd(&priv->si->hw, ENETC_SICTR1));
- } else {
- gcl_data->btl =
- cpu_to_le32(lower_32_bits(admin_conf->base_time));
- gcl_data->bth =
- cpu_to_le32(upper_32_bits(admin_conf->base_time));
- }
-
+ gcl_data->btl = cpu_to_le32(lower_32_bits(admin_conf->base_time));
+ gcl_data->bth = cpu_to_le32(upper_32_bits(admin_conf->base_time));
gcl_data->ct = cpu_to_le32(admin_conf->cycle_time);
gcl_data->cte = cpu_to_le32(admin_conf->cycle_time_extension);
u32 num_entries;
refcount_t refcount;
struct hlist_node node;
- struct action_gate_entry entries[0];
+ struct action_gate_entry entries[];
};
/* Only enable the green color frame now
*/
#define FEC_QUIRK_HAS_FRREG (1 << 16)
+/* Some FEC hardware blocks need the MMFR cleared at setup time to avoid
+ * the generation of an MII event. This must be avoided in the older
+ * FEC blocks where it will stop MII events being generated.
+ */
+#define FEC_QUIRK_CLEAR_SETUP_MII (1 << 17)
+
struct bufdesc_prop {
int qid;
/* Address of Rx and Tx buffers */
static const struct fec_devinfo fec_imx28_info = {
.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC |
- FEC_QUIRK_HAS_FRREG,
+ FEC_QUIRK_HAS_FRREG | FEC_QUIRK_CLEAR_SETUP_MII,
};
static const struct fec_devinfo fec_imx6q_info = {
.quirks = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
- FEC_QUIRK_HAS_RACC,
+ FEC_QUIRK_HAS_RACC | FEC_QUIRK_CLEAR_SETUP_MII,
};
static const struct fec_devinfo fec_mvf600_info = {
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
- FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE,
+ FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE |
+ FEC_QUIRK_CLEAR_SETUP_MII,
};
static const struct fec_devinfo fec_imx6ul_info = {
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR007885 |
FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC |
- FEC_QUIRK_HAS_COALESCE,
+ FEC_QUIRK_HAS_COALESCE | FEC_QUIRK_CLEAR_SETUP_MII,
};
static struct platform_device_id fec_devtype[] = {
int ret = 0, frame_start, frame_addr, frame_op;
bool is_c45 = !!(regnum & MII_ADDR_C45);
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
int ret, frame_start, frame_addr;
bool is_c45 = !!(regnum & MII_ADDR_C45);
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
- else
- ret = 0;
if (is_c45) {
frame_start = FEC_MMFR_ST_C45;
if (suppress_preamble)
fep->phy_speed |= BIT(7);
- /* Clear MMFR to avoid to generate MII event by writing MSCR.
- * MII event generation condition:
- * - writing MSCR:
- * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
- * mscr_reg_data_in[7:0] != 0
- * - writing MMFR:
- * - mscr[7:0]_not_zero
- */
- writel(0, fep->hwp + FEC_MII_DATA);
+ if (fep->quirks & FEC_QUIRK_CLEAR_SETUP_MII) {
+ /* Clear MMFR to avoid to generate MII event by writing MSCR.
+ * MII event generation condition:
+ * - writing MSCR:
+ * - mmfr[31:0]_not_zero & mscr[7:0]_is_zero &
+ * mscr_reg_data_in[7:0] != 0
+ * - writing MMFR:
+ * - mscr[7:0]_not_zero
+ */
+ writel(0, fep->hwp + FEC_MII_DATA);
+ }
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
u32 i, off;
int ret;
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return;
int ret;
bool reset_again;
- ret = pm_runtime_get_sync(&fep->pdev->dev);
+ ret = pm_runtime_resume_and_get(&fep->pdev->dev);
if (ret < 0)
return ret;
struct device_node *np = pdev->dev.of_node;
int ret;
- ret = pm_runtime_get_sync(&pdev->dev);
+ ret = pm_runtime_resume_and_get(&pdev->dev);
if (ret < 0)
return ret;
fcb_len = GMAC_FCB_LEN + GMAC_TXPAL_LEN;
/* make space for additional header when fcb is needed */
- if (fcb_len && unlikely(skb_headroom(skb) < fcb_len)) {
- struct sk_buff *skb_new;
-
- skb_new = skb_realloc_headroom(skb, fcb_len);
- if (!skb_new) {
+ if (fcb_len) {
+ if (unlikely(skb_cow_head(skb, fcb_len))) {
dev->stats.tx_errors++;
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
-
- if (skb->sk)
- skb_set_owner_w(skb_new, skb->sk);
- dev_consume_skb_any(skb);
- skb = skb_new;
}
/* total number of fragments in the SKB */
if (dev->features & NETIF_F_IP_CSUM ||
priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)
- dev->needed_headroom = GMAC_FCB_LEN;
+ dev->needed_headroom = GMAC_FCB_LEN + GMAC_TXPAL_LEN;
/* Initializing some of the rx/tx queue level parameters */
for (i = 0; i < priv->num_tx_queues; i++) {
(ugeth->phy_interface == PHY_INTERFACE_MODE_RTBI)) {
upsmr |= UCC_GETH_UPSMR_TBIM;
}
- if ((ugeth->phy_interface == PHY_INTERFACE_MODE_SGMII))
+ if (ugeth->phy_interface == PHY_INTERFACE_MODE_SGMII)
upsmr |= UCC_GETH_UPSMR_SGMM;
out_be32(&uf_regs->upsmr, upsmr);
struct gve_stats_report {
__be64 written_count;
- struct stats stats[0];
+ struct stats stats[];
};
static_assert(sizeof(struct gve_stats_report) == 8);
priv->tx_cfg.num_queues;
rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) *
priv->rx_cfg.num_queues;
- priv->stats_report_len = sizeof(struct gve_stats_report) +
- (tx_stats_num + rx_stats_num) *
- sizeof(struct stats);
+ priv->stats_report_len = struct_size(priv->stats_report, stats,
+ tx_stats_num + rx_stats_num);
priv->stats_report =
dma_alloc_coherent(&priv->pdev->dev, priv->stats_report_len,
&priv->stats_report_bus, GFP_KERNEL);
return ret;
}
- return ret;
+ return 0;
}
int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init)
hclgevf_uninit_msi(hdev);
}
- hclgevf_pci_uninit(hdev);
hclgevf_cmd_uninit(hdev);
+ hclgevf_pci_uninit(hdev);
hclgevf_uninit_mac_list(hdev);
}
ret = -EOPNOTSUPP;
}
- if (!ether_addr_equal(ether_header->h_source, netdev->dev_addr)) {
- netdev_dbg(netdev, "source packet MAC address does not match veth device's, dropping packet.\n");
- netdev->stats.tx_dropped++;
- ret = -EOPNOTSUPP;
- }
-
return ret;
}
static int ibmvnic_login(struct net_device *netdev)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
- unsigned long timeout = msecs_to_jiffies(30000);
+ unsigned long timeout = msecs_to_jiffies(20000);
int retry_count = 0;
int retries = 10;
bool retry;
adapter->init_done_rc = 0;
reinit_completion(&adapter->init_done);
rc = send_login(adapter);
- if (rc) {
- netdev_warn(netdev, "Unable to login\n");
+ if (rc)
return rc;
- }
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state)
{
struct net_device *netdev = adapter->netdev;
- unsigned long timeout = msecs_to_jiffies(30000);
+ unsigned long timeout = msecs_to_jiffies(20000);
union ibmvnic_crq crq;
bool resend;
int rc;
if (adapter->state != VNIC_CLOSED) {
rc = ibmvnic_login(netdev);
if (rc)
- return rc;
+ goto out;
rc = init_resources(adapter);
if (rc) {
netdev_err(netdev, "failed to initialize resources\n");
release_resources(adapter);
- return rc;
+ goto out;
}
}
rc = __ibmvnic_open(netdev);
+out:
+ /*
+ * If open fails due to a pending failover, set device state and
+ * return. Device operation will be handled by reset routine.
+ */
+ if (rc && adapter->failover_pending) {
+ adapter->state = VNIC_OPEN;
+ rc = 0;
+ }
return rc;
}
int rc;
rc = 0;
- ether_addr_copy(adapter->mac_addr, addr->sa_data);
- if (adapter->state != VNIC_PROBED)
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ if (adapter->state != VNIC_PROBED) {
+ ether_addr_copy(adapter->mac_addr, addr->sa_data);
rc = __ibmvnic_set_mac(netdev, addr->sa_data);
+ }
return rc;
}
if (reset_state == VNIC_OPEN) {
rc = __ibmvnic_close(netdev);
if (rc)
- return rc;
+ goto out;
}
release_resources(adapter);
}
rc = ibmvnic_reset_init(adapter, true);
- if (rc)
- return IBMVNIC_INIT_FAILED;
+ if (rc) {
+ rc = IBMVNIC_INIT_FAILED;
+ goto out;
+ }
/* If the adapter was in PROBE state prior to the reset,
* exit here.
*/
if (reset_state == VNIC_PROBED)
- return 0;
+ goto out;
rc = ibmvnic_login(netdev);
if (rc) {
- adapter->state = reset_state;
- return rc;
+ goto out;
}
rc = init_resources(adapter);
if (rc)
- return rc;
+ goto out;
ibmvnic_disable_irqs(adapter);
return 0;
rc = __ibmvnic_open(netdev);
- if (rc)
- return IBMVNIC_OPEN_FAILED;
+ if (rc) {
+ rc = IBMVNIC_OPEN_FAILED;
+ goto out;
+ }
/* refresh device's multicast list */
ibmvnic_set_multi(netdev);
for (i = 0; i < adapter->req_rx_queues; i++)
napi_schedule(&adapter->napi[i]);
- return 0;
+out:
+ if (rc)
+ adapter->state = reset_state;
+ return rc;
}
/**
rwi->reset_reason);
rtnl_lock();
+ /*
+ * Now that we have the rtnl lock, clear any pending failover.
+ * This will ensure ibmvnic_open() has either completed or will
+ * block until failover is complete.
+ */
+ if (rwi->reset_reason == VNIC_RESET_FAILOVER)
+ adapter->failover_pending = false;
netif_carrier_off(netdev);
adapter->reset_reason = rwi->reset_reason;
rc = ibmvnic_login(netdev);
if (rc) {
- adapter->state = reset_state;
goto out;
}
for (i = 0; i < adapter->req_rx_queues; i++)
napi_schedule(&adapter->napi[i]);
- if (adapter->reset_reason != VNIC_RESET_FAILOVER)
+ if (adapter->reset_reason == VNIC_RESET_FAILOVER ||
+ adapter->reset_reason == VNIC_RESET_MOBILITY) {
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
+ call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev);
+ }
rc = 0;
out:
+ /* restore the adapter state if reset failed */
+ if (rc)
+ adapter->state = reset_state;
rtnl_unlock();
return rc;
if (rc) {
netdev_err(adapter->netdev,
"Couldn't initialize crq. rc=%d\n", rc);
- return rc;
+ goto out;
}
rc = ibmvnic_reset_init(adapter, false);
if (rc)
- return rc;
+ goto out;
/* If the adapter was in PROBE state prior to the reset,
* exit here.
*/
if (reset_state == VNIC_PROBED)
- return 0;
+ goto out;
rc = ibmvnic_login(netdev);
- if (rc) {
- adapter->state = VNIC_PROBED;
- return 0;
- }
+ if (rc)
+ goto out;
rc = init_resources(adapter);
if (rc)
- return rc;
+ goto out;
ibmvnic_disable_irqs(adapter);
adapter->state = VNIC_CLOSED;
if (reset_state == VNIC_CLOSED)
- return 0;
+ goto out;
rc = __ibmvnic_open(netdev);
- if (rc)
- return IBMVNIC_OPEN_FAILED;
+ if (rc) {
+ rc = IBMVNIC_OPEN_FAILED;
+ goto out;
+ }
- return 0;
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
+ call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev);
+out:
+ /* restore adapter state if reset failed */
+ if (rc)
+ adapter->state = reset_state;
+ return rc;
}
static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
return rwi;
}
-static void free_all_rwi(struct ibmvnic_adapter *adapter)
-{
- struct ibmvnic_rwi *rwi;
-
- rwi = get_next_rwi(adapter);
- while (rwi) {
- kfree(rwi);
- rwi = get_next_rwi(adapter);
- }
-}
-
static void __ibmvnic_reset(struct work_struct *work)
{
struct ibmvnic_rwi *rwi;
if (!saved_state) {
reset_state = adapter->state;
- adapter->state = VNIC_RESETTING;
saved_state = true;
}
spin_unlock_irqrestore(&adapter->state_lock, flags);
/* CHANGE_PARAM requestor holds rtnl_lock */
rc = do_change_param_reset(adapter, rwi, reset_state);
} else if (adapter->force_reset_recovery) {
+ /*
+ * Since we are doing a hard reset now, clear the
+ * failover_pending flag so we don't ignore any
+ * future MOBILITY or other resets.
+ */
+ adapter->failover_pending = false;
+
/* Transport event occurred during previous reset */
if (adapter->wait_for_reset) {
/* Previous was CHANGE_PARAM; caller locked */
rc = do_hard_reset(adapter, rwi, reset_state);
rtnl_unlock();
}
+ if (rc) {
+ /* give backing device time to settle down */
+ netdev_dbg(adapter->netdev,
+ "[S:%d] Hard reset failed, waiting 60 secs\n",
+ adapter->state);
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(60 * HZ);
+ }
} else if (!(rwi->reset_reason == VNIC_RESET_FATAL &&
adapter->from_passive_init)) {
rc = do_reset(adapter, rwi, reset_state);
}
kfree(rwi);
- if (rc == IBMVNIC_OPEN_FAILED) {
- if (list_empty(&adapter->rwi_list))
- adapter->state = VNIC_CLOSED;
- else
- adapter->state = reset_state;
- rc = 0;
- } else if (rc && rc != IBMVNIC_INIT_FAILED &&
- !adapter->force_reset_recovery)
- break;
+ adapter->last_reset_time = jiffies;
+
+ if (rc)
+ netdev_dbg(adapter->netdev, "Reset failed, rc=%d\n", rc);
rwi = get_next_rwi(adapter);
complete(&adapter->reset_done);
}
- if (rc) {
- netdev_dbg(adapter->netdev, "Reset failed\n");
- free_all_rwi(adapter);
- }
-
clear_bit_unlock(0, &adapter->resetting);
}
unsigned long flags;
int ret;
+ /*
+ * If failover is pending don't schedule any other reset.
+ * Instead let the failover complete. If there is already a
+ * a failover reset scheduled, we will detect and drop the
+ * duplicate reset when walking the ->rwi_list below.
+ */
if (adapter->state == VNIC_REMOVING ||
adapter->state == VNIC_REMOVED ||
- adapter->failover_pending) {
+ (adapter->failover_pending && reason != VNIC_RESET_FAILOVER)) {
ret = EBUSY;
netdev_dbg(netdev, "Adapter removing or pending failover, skipping reset\n");
goto err;
{
struct ibmvnic_adapter *adapter = netdev_priv(dev);
+ if (test_bit(0, &adapter->resetting)) {
+ netdev_err(adapter->netdev,
+ "Adapter is resetting, skip timeout reset\n");
+ return;
+ }
+ /* No queuing up reset until at least 5 seconds (default watchdog val)
+ * after last reset
+ */
+ if (time_before(jiffies, (adapter->last_reset_time + dev->watchdog_timeo))) {
+ netdev_dbg(dev, "Not yet time to tx timeout.\n");
+ return;
+ }
ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT);
}
if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num]))
break;
+ /* The queue entry at the current index is peeked at above
+ * to determine that there is a valid descriptor awaiting
+ * processing. We want to be sure that the current slot
+ * holds a valid descriptor before reading its contents.
+ */
+ dma_rmb();
next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]);
rx_buff =
(struct ibmvnic_rx_buff *)be64_to_cpu(next->
{
int rc;
+ if (!scrq) {
+ netdev_dbg(adapter->netdev,
+ "Invalid scrq reset. irq (%d) or msgs (%p).\n",
+ scrq->irq, scrq->msgs);
+ return -EINVAL;
+ }
+
if (scrq->irq) {
free_irq(scrq->irq, scrq);
irq_dispose_mapping(scrq->irq);
scrq->irq = 0;
}
-
- memset(scrq->msgs, 0, 4 * PAGE_SIZE);
- atomic_set(&scrq->used, 0);
- scrq->cur = 0;
+ if (scrq->msgs) {
+ memset(scrq->msgs, 0, 4 * PAGE_SIZE);
+ atomic_set(&scrq->used, 0);
+ scrq->cur = 0;
+ } else {
+ netdev_dbg(adapter->netdev, "Invalid scrq reset\n");
+ return -EINVAL;
+ }
rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token,
4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq);
{
int i, rc;
+ if (!adapter->tx_scrq || !adapter->rx_scrq)
+ return -EINVAL;
+
for (i = 0; i < adapter->req_tx_queues; i++) {
netdev_dbg(adapter->netdev, "Re-setting tx_scrq[%d]\n", i);
rc = reset_one_sub_crq_queue(adapter, adapter->tx_scrq[i]);
unsigned int pool = scrq->pool_index;
int num_entries = 0;
+ /* The queue entry at the current index is peeked at above
+ * to determine that there is a valid descriptor awaiting
+ * processing. We want to be sure that the current slot
+ * holds a valid descriptor before reading its contents.
+ */
+ dma_rmb();
+
next = ibmvnic_next_scrq(adapter, scrq);
for (i = 0; i < next->tx_comp.num_comps; i++) {
- if (next->tx_comp.rcs[i]) {
+ if (next->tx_comp.rcs[i])
dev_err(dev, "tx error %x\n",
next->tx_comp.rcs[i]);
- continue;
- }
index = be32_to_cpu(next->tx_comp.correlators[i]);
if (index & IBMVNIC_TSO_POOL_MASK) {
tx_pool = &adapter->tso_pool[pool];
}
spin_unlock_irqrestore(&scrq->lock, flags);
+ /* Ensure that the entire buffer descriptor has been
+ * loaded before reading its contents
+ */
+ dma_rmb();
+
return entry;
}
struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
struct ibmvnic_login_buffer *login_buffer;
struct device *dev = &adapter->vdev->dev;
+ struct vnic_login_client_data *vlcd;
dma_addr_t rsp_buffer_token;
dma_addr_t buffer_token;
size_t rsp_buffer_size;
union ibmvnic_crq crq;
+ int client_data_len;
size_t buffer_size;
__be64 *tx_list_p;
__be64 *rx_list_p;
- int client_data_len;
- struct vnic_login_client_data *vlcd;
+ int rc;
int i;
if (!adapter->tx_scrq || !adapter->rx_scrq) {
crq.login.cmd = LOGIN;
crq.login.ioba = cpu_to_be32(buffer_token);
crq.login.len = cpu_to_be32(buffer_size);
- ibmvnic_send_crq(adapter, &crq);
+
+ adapter->login_pending = true;
+ rc = ibmvnic_send_crq(adapter, &crq);
+ if (rc) {
+ adapter->login_pending = false;
+ netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc);
+ goto buf_rsp_map_failed;
+ }
return 0;
buf_rsp_map_failed:
kfree(login_rsp_buffer);
+ adapter->login_rsp_buf = NULL;
buf_rsp_alloc_failed:
dma_unmap_single(dev, buffer_token, buffer_size, DMA_TO_DEVICE);
buf_map_failed:
kfree(login_buffer);
+ adapter->login_buf = NULL;
buf_alloc_failed:
return -1;
}
u64 *size_array;
int i;
+ /* CHECK: Test/set of login_pending does not need to be atomic
+ * because only ibmvnic_tasklet tests/clears this.
+ */
+ if (!adapter->login_pending) {
+ netdev_warn(netdev, "Ignoring unexpected login response\n");
+ return 0;
+ }
+ adapter->login_pending = false;
+
dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
DMA_TO_DEVICE);
dma_unmap_single(dev, adapter->login_rsp_buf_token,
adapter->req_rx_add_queues !=
be32_to_cpu(login_rsp->num_rxadd_subcrqs))) {
dev_err(dev, "FATAL: Inconsistent login and login rsp\n");
- ibmvnic_remove(adapter->vdev);
+ ibmvnic_reset(adapter, VNIC_RESET_FATAL);
return -EIO;
}
size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
case IBMVNIC_CRQ_INIT:
dev_info(dev, "Partner initialized\n");
adapter->from_passive_init = true;
- adapter->failover_pending = false;
+ /* Discard any stale login responses from prev reset.
+ * CHECK: should we clear even on INIT_COMPLETE?
+ */
+ adapter->login_pending = false;
+
if (!completion_done(&adapter->init_done)) {
complete(&adapter->init_done);
adapter->init_done_rc = -EIO;
} while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
/* Clean out the queue */
+ if (!crq->msgs)
+ return -EINVAL;
+
memset(crq->msgs, 0, PAGE_SIZE);
crq->cur = 0;
crq->active = false;
static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
{
struct device *dev = &adapter->vdev->dev;
- unsigned long timeout = msecs_to_jiffies(30000);
+ unsigned long timeout = msecs_to_jiffies(20000);
u64 old_num_rx_queues, old_num_tx_queues;
int rc;
dev_set_drvdata(&dev->dev, netdev);
adapter->vdev = dev;
adapter->netdev = netdev;
+ adapter->login_pending = false;
ether_addr_copy(adapter->mac_addr, mac_addr_p);
ether_addr_copy(netdev->dev_addr, adapter->mac_addr);
adapter->state = VNIC_PROBED;
adapter->wait_for_reset = false;
-
+ adapter->last_reset_time = jiffies;
return 0;
ibmvnic_register_fail:
unsigned long flags;
spin_lock_irqsave(&adapter->state_lock, flags);
- if (adapter->state == VNIC_RESETTING) {
+ if (test_bit(0, &adapter->resetting)) {
spin_unlock_irqrestore(&adapter->state_lock, flags);
return -EBUSY;
}
VNIC_CLOSING,
VNIC_CLOSED,
VNIC_REMOVING,
- VNIC_REMOVED,
- VNIC_RESETTING};
+ VNIC_REMOVED};
enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1,
VNIC_RESET_MOBILITY,
struct delayed_work ibmvnic_delayed_reset;
unsigned long resetting;
bool napi_enabled, from_passive_init;
+ bool login_pending;
+ /* last device reset time */
+ unsigned long last_reset_time;
bool failover_pending;
bool force_reset_recovery;
__I40E_CLIENT_RESET,
__I40E_VIRTCHNL_OP_PENDING,
__I40E_RECOVERY_MODE,
+ __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */
/* This must be last as it determines the size of the BITMAP */
__I40E_STATE_SIZE__,
};
}
if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) {
- ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK;
- set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+ /* disable any further VFLR event notifications */
+ if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) {
+ u32 reg = rd32(hw, I40E_PFINT_ICR0_ENA);
+
+ reg &= ~I40E_PFINT_ICR0_VFLR_MASK;
+ wr32(hw, I40E_PFINT_ICR0_ENA, reg);
+ } else {
+ ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK;
+ set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+ }
}
if (icr0 & I40E_PFINT_ICR0_GRST_MASK) {
while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
usleep_range(1000, 2000);
+ if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
+ set_bit(__I40E_VF_RESETS_DISABLED, pf->state);
+ i40e_free_vfs(pf);
+ pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
+ }
/* no more scheduling of any task */
set_bit(__I40E_SUSPENDED, pf->state);
set_bit(__I40E_DOWN, pf->state);
*/
i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false);
- if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
- i40e_free_vfs(pf);
- pf->flags &= ~I40E_FLAG_SRIOV_ENABLED;
- }
-
i40e_fdir_teardown(pf);
/* If there is a switch structure or any orphans, remove them.
* @vf: pointer to the VF structure
* @flr: VFLR was issued or not
*
- * Returns true if the VF is reset, false otherwise.
+ * Returns true if the VF is in reset, resets successfully, or resets
+ * are disabled and false otherwise.
**/
bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
{
u32 reg;
int i;
+ if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state))
+ return true;
+
/* If the VFs have been disabled, this means something else is
* resetting the VF, so we shouldn't continue.
*/
if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
- return false;
+ return true;
i40e_trigger_vf_reset(vf, flr);
i40e_notify_client_of_vf_enable(pf, 0);
+ /* Disable IOV before freeing resources. This lets any VF drivers
+ * running in the host get themselves cleaned up before we yank
+ * the carpet out from underneath their feet.
+ */
+ if (!pci_vfs_assigned(pf->pdev))
+ pci_disable_sriov(pf->pdev);
+ else
+ dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
+
/* Amortize wait time by stopping all VFs at the same time */
for (i = 0; i < pf->num_alloc_vfs; i++) {
if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states))
i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[i].lan_vsi_idx]);
}
- /* Disable IOV before freeing resources. This lets any VF drivers
- * running in the host get themselves cleaned up before we yank
- * the carpet out from underneath their feet.
- */
- if (!pci_vfs_assigned(pf->pdev))
- pci_disable_sriov(pf->pdev);
- else
- dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
-
/* free up VF resources */
tmp = pf->num_alloc_vfs;
pf->num_alloc_vfs = 0;
spin_unlock_bh(&vsi->mac_filter_hash_lock);
goto error_param;
}
+ if (is_valid_ether_addr(al->list[i].addr) &&
+ is_zero_ether_addr(vf->default_lan_addr.addr))
+ ether_addr_copy(vf->default_lan_addr.addr,
+ al->list[i].addr);
}
}
spin_unlock_bh(&vsi->mac_filter_hash_lock);
{
struct virtchnl_ether_addr_list *al =
(struct virtchnl_ether_addr_list *)msg;
+ bool was_unimac_deleted = false;
struct i40e_pf *pf = vf->pf;
struct i40e_vsi *vsi = NULL;
i40e_status ret = 0;
ret = I40E_ERR_INVALID_MAC_ADDR;
goto error_param;
}
+ if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr))
+ was_unimac_deleted = true;
}
vsi = pf->vsi[vf->lan_vsi_idx];
dev_err(&pf->pdev->dev, "Unable to program VF %d MAC filters, error %d\n",
vf->vf_id, ret);
+ if (vf->trusted && was_unimac_deleted) {
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
+ u8 *macaddr = NULL;
+ int bkt;
+
+ /* set last unicast mac address as default */
+ spin_lock_bh(&vsi->mac_filter_hash_lock);
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+ if (is_valid_ether_addr(f->macaddr))
+ macaddr = f->macaddr;
+ }
+ if (macaddr)
+ ether_addr_copy(vf->default_lan_addr.addr, macaddr);
+ spin_unlock_bh(&vsi->mac_filter_hash_lock);
+ }
error_param:
/* send the response to the VF */
- return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR,
- ret);
+ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, ret);
}
/**
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
unsigned int xdp_res, xdp_xmit = 0;
+ bool failure = false;
struct sk_buff *skb;
- bool failure;
while (likely(total_rx_packets < (unsigned int)budget)) {
union i40e_rx_desc *rx_desc;
}
/**
- * igc_get_stats - Get System Network Statistics
+ * igc_get_stats64 - Get System Network Statistics
* @netdev: network interface device structure
+ * @stats: rtnl_link_stats64 pointer
*
* Returns the address of the device statistics structure.
* The statistics are updated here and also from the timer callback.
*/
-static struct net_device_stats *igc_get_stats(struct net_device *netdev)
+static void igc_get_stats64(struct net_device *netdev,
+ struct rtnl_link_stats64 *stats)
{
struct igc_adapter *adapter = netdev_priv(netdev);
+ spin_lock(&adapter->stats64_lock);
if (!test_bit(__IGC_RESETTING, &adapter->state))
igc_update_stats(adapter);
-
- /* only return the current stats */
- return &netdev->stats;
+ memcpy(stats, &adapter->stats64, sizeof(*stats));
+ spin_unlock(&adapter->stats64_lock);
}
static netdev_features_t igc_fix_features(struct net_device *netdev,
.ndo_set_rx_mode = igc_set_rx_mode,
.ndo_set_mac_address = igc_set_mac,
.ndo_change_mtu = igc_change_mtu,
- .ndo_get_stats = igc_get_stats,
+ .ndo_get_stats64 = igc_get_stats64,
.ndo_fix_features = igc_fix_features,
.ndo_set_features = igc_set_features,
.ndo_features_check = igc_features_check,
dma_sync_single_for_cpu(dev->dev.parent,
rx_desc->buf_phys_addr,
len, dma_dir);
+ rx_desc->buf_phys_addr = 0;
if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) {
skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags];
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
sinfo->nr_frags++;
-
- rx_desc->buf_phys_addr = 0;
+ } else {
+ page_pool_put_full_page(rxq->page_pool, page, true);
}
*size -= len;
}
if (!valid) {
netdev_err(port->dev,
"invalid configuration: no dt or link IRQ");
+ err = -ENOENT;
goto err_free_irq;
}
config PRESTERA
tristate "Marvell Prestera Switch ASICs support"
depends on NET_SWITCHDEV && VLAN_8021Q
+ depends on BRIDGE || BRIDGE=n
select NET_DEVLINK
help
This driver supports Marvell Prestera Switch ASICs family.
if (err)
return err;
- if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30))) {
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30));
+ if (err) {
dev_err(&pdev->dev, "fail to set DMA mask\n");
goto err_dma_mask;
}
dev_info(fw->dev.dev, "Prestera FW is ready\n");
fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1);
- if (!fw->wq)
+ if (!fw->wq) {
+ err = -ENOMEM;
goto err_wq_alloc;
+ }
INIT_WORK(&fw->evt_work, prestera_fw_evt_work_fn);
mtk_star_adjust_link, 0, priv->phy_intf);
if (!priv->phydev) {
netdev_err(ndev, "failed to connect to PHY\n");
+ ret = -ENODEV;
goto err_free_irq;
}
err_drop_packet:
dev_kfree_skb(skb);
ndev->stats.tx_dropped++;
- return NETDEV_TX_BUSY;
+ return NETDEV_TX_OK;
}
/* Returns the number of bytes sent or a negative number on the first
#define INIT_HCA_LOG_RD_OFFSET (INIT_HCA_QPC_OFFSET + 0x77)
#define INIT_HCA_MCAST_OFFSET 0x0c0
#define INIT_HCA_MC_BASE_OFFSET (INIT_HCA_MCAST_OFFSET + 0x00)
-#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x12)
-#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16)
+#define INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x13)
+#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x17)
#define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18)
#define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b)
#define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6
#define INIT_HCA_DRIVER_VERSION_SZ 0x40
#define INIT_HCA_FS_PARAM_OFFSET 0x1d0
#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00)
-#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12)
+#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x13)
#define INIT_HCA_FS_A0_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x18)
#define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b)
#define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21)
u64 cmpt_base;
u64 mtt_base;
u64 global_caps;
- u16 log_mc_entry_sz;
- u16 log_mc_hash_sz;
+ u8 log_mc_entry_sz;
+ u8 log_mc_hash_sz;
u16 hca_core_clock; /* Internal Clock Frequency (in MHz) */
u8 log_num_qps;
u8 log_num_srqs;
struct mlx5e_priv *priv;
/* A given netdev is not a representor or not a slave of LAG configuration */
- if (!mlx5e_eswitch_rep(netdev) || !bond_slave_get_rtnl(netdev))
+ if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev))
return false;
priv = netdev_priv(netdev);
mlx5e_tc_encap_flows_del(priv, e, &flow_list);
if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
+ struct net_device *route_dev;
+
ether_addr_copy(e->h_dest, ha);
ether_addr_copy(eth->h_dest, ha);
/* Update the encap source mac, in case that we delete
* the flows when encap source mac changed.
*/
- ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
+ route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex);
+ if (route_dev)
+ ether_addr_copy(eth->h_source, route_dev->dev_addr);
mlx5e_tc_encap_flows_add(priv, e, &flow_list);
}
return 0;
}
-static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
- struct net_device *mirred_dev,
- struct net_device **out_dev,
- struct net_device **route_dev,
- struct flowi4 *fl4,
- struct neighbour **out_n,
- u8 *out_ttl)
+static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct net_device **out_dev,
+ struct net_device **route_dev,
+ struct flowi4 *fl4,
+ struct neighbour **out_n,
+ u8 *out_ttl)
{
struct neighbour *n;
struct rtable *rt;
ip_rt_put(rt);
return ret;
}
+ dev_hold(*route_dev);
if (!(*out_ttl))
*out_ttl = ip4_dst_hoplimit(&rt->dst);
n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
ip_rt_put(rt);
- if (!n)
+ if (!n) {
+ dev_put(*route_dev);
return -ENOMEM;
+ }
*out_n = n;
return 0;
}
+static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev,
+ struct neighbour *n)
+{
+ neigh_release(n);
+ dev_put(route_dev);
+}
+
static const char *mlx5e_netdev_kind(struct net_device *dev)
{
if (dev->rtnl_link_ops)
fl4.saddr = tun_key->u.ipv4.src;
ttl = tun_key->ttl;
- err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev,
- &fl4, &n, &ttl);
+ err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev,
+ &fl4, &n, &ttl);
if (err)
return err;
e->m_neigh.family = n->ops->family;
memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
e->out_dev = out_dev;
- e->route_dev = route_dev;
+ e->route_dev_ifindex = route_dev->ifindex;
/* It's important to add the neigh to the hash table before checking
* the neigh validity state. So if we'll get a notification, in case the
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
- neigh_release(n);
+ mlx5e_route_lookup_ipv4_put(route_dev, n);
return err;
destroy_neigh_entry:
free_encap:
kfree(encap_header);
release_neigh:
- neigh_release(n);
+ mlx5e_route_lookup_ipv4_put(route_dev, n);
return err;
}
#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
- struct net_device *mirred_dev,
- struct net_device **out_dev,
- struct net_device **route_dev,
- struct flowi6 *fl6,
- struct neighbour **out_n,
- u8 *out_ttl)
+static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct net_device **out_dev,
+ struct net_device **route_dev,
+ struct flowi6 *fl6,
+ struct neighbour **out_n,
+ u8 *out_ttl)
{
struct dst_entry *dst;
struct neighbour *n;
return ret;
}
+ dev_hold(*route_dev);
n = dst_neigh_lookup(dst, &fl6->daddr);
dst_release(dst);
- if (!n)
+ if (!n) {
+ dev_put(*route_dev);
return -ENOMEM;
+ }
*out_n = n;
return 0;
}
+static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev,
+ struct neighbour *n)
+{
+ neigh_release(n);
+ dev_put(route_dev);
+}
+
int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
struct net_device *mirred_dev,
struct mlx5e_encap_entry *e)
fl6.daddr = tun_key->u.ipv6.dst;
fl6.saddr = tun_key->u.ipv6.src;
- err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev,
- &fl6, &n, &ttl);
+ err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev,
+ &fl6, &n, &ttl);
if (err)
return err;
e->m_neigh.family = n->ops->family;
memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
e->out_dev = out_dev;
- e->route_dev = route_dev;
+ e->route_dev_ifindex = route_dev->ifindex;
/* It's importent to add the neigh to the hash table before checking
* the neigh validity state. So if we'll get a notification, in case the
e->flags |= MLX5_ENCAP_ENTRY_VALID;
mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
- neigh_release(n);
+ mlx5e_route_lookup_ipv6_put(route_dev, n);
return err;
destroy_neigh_entry:
free_encap:
kfree(encap_header);
release_neigh:
- neigh_release(n);
+ mlx5e_route_lookup_ipv6_put(route_dev, n);
return err;
}
#endif
set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
/* TX queue is created active. */
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
mlx5e_trigger_irq(&c->async_icosq);
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
}
void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state))
return 0;
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
mlx5e_trigger_irq(&c->async_icosq);
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
}
return 0;
outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
}
+#if IS_ENABLED(CONFIG_IPV6)
static void accel_fs_tcp_set_ipv6_flow(struct mlx5_flow_spec *spec, struct sock *sk)
{
MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol);
outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
0xff, 16);
}
+#endif
void mlx5e_accel_fs_del_sk(struct mlx5_flow_handle *rule)
{
if (!spec)
return -ENOMEM;
- /* Action to copy 7 bit ipsec_syndrome to regB[0:6] */
+ /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */
MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY);
MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME);
MLX5_SET(copy_action_in, action, src_offset, 0);
MLX5_SET(copy_action_in, action, length, 7);
MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
- MLX5_SET(copy_action_in, action, dst_offset, 0);
+ MLX5_SET(copy_action_in, action, dst_offset, 24);
modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL,
1, action);
setup_fte_common(attrs, ipsec_obj_id, spec, &flow_act);
- /* Set 1 bit ipsec marker */
- /* Set 24 bit ipsec_obj_id */
+ /* Set bit[31] ipsec marker */
+ /* Set bit[23-0] ipsec_obj_id */
MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_B);
- MLX5_SET(set_action_in, action, data, (ipsec_obj_id << 1) | 0x1);
- MLX5_SET(set_action_in, action, offset, 7);
- MLX5_SET(set_action_in, action, length, 25);
+ MLX5_SET(set_action_in, action, data, (ipsec_obj_id | BIT(31)));
+ MLX5_SET(set_action_in, action, offset, 0);
+ MLX5_SET(set_action_in, action, length, 32);
modify_hdr = mlx5_modify_header_alloc(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL,
1, action);
struct mlx5_cqe64 *cqe)
{
u32 ipsec_meta_data = be32_to_cpu(cqe->ft_metadata);
- u8 ipsec_syndrome = ipsec_meta_data & 0xFF;
struct mlx5e_priv *priv;
struct xfrm_offload *xo;
struct xfrm_state *xs;
xo = xfrm_offload(skb);
xo->flags = CRYPTO_DONE;
- switch (ipsec_syndrome & MLX5_IPSEC_METADATA_SYNDROM_MASK) {
+ switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) {
case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED:
xo->status = CRYPTO_SUCCESS;
if (WARN_ON_ONCE(priv->ipsec->no_trailer))
#include "en.h"
#include "en/txrx.h"
-#define MLX5_IPSEC_METADATA_MARKER_MASK (0x80)
-#define MLX5_IPSEC_METADATA_SYNDROM_MASK (0x7F)
-#define MLX5_IPSEC_METADATA_HANDLE(metadata) (((metadata) >> 8) & 0xFF)
+/* Bit31: IPsec marker, Bit30-24: IPsec syndrome, Bit23-0: IPsec obj id */
+#define MLX5_IPSEC_METADATA_MARKER(metadata) (((metadata) >> 31) & 0x1)
+#define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(6, 0))
+#define MLX5_IPSEC_METADATA_HANDLE(metadata) ((metadata) & GENMASK(23, 0))
struct mlx5e_accel_tx_ipsec_state {
struct xfrm_offload *xo;
static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe)
{
- return !!(MLX5_IPSEC_METADATA_MARKER_MASK & be32_to_cpu(cqe->ft_metadata));
+ return MLX5_IPSEC_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata));
}
static inline bool mlx5e_ipsec_is_tx_flow(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
err = 0;
sq = &c->async_icosq;
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
cseg = post_static_params(sq, priv_rx);
if (IS_ERR(cseg))
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
unlock:
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
return err;
BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
- spin_lock(&sq->channel->async_icosq_lock);
+ spin_lock_bh(&sq->channel->async_icosq_lock);
if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
- spin_unlock(&sq->channel->async_icosq_lock);
+ spin_unlock_bh(&sq->channel->async_icosq_lock);
err = -ENOSPC;
goto err_dma_unmap;
}
icosq_fill_wi(sq, pi, &wi);
sq->pc++;
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
- spin_unlock(&sq->channel->async_icosq_lock);
+ spin_unlock_bh(&sq->channel->async_icosq_lock);
return 0;
err = 0;
sq = &c->async_icosq;
- spin_lock(&c->async_icosq_lock);
+ spin_lock_bh(&c->async_icosq_lock);
cseg = post_static_params(sq, priv_rx);
if (IS_ERR(cseg)) {
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
priv_rx->stats->tls_resync_res_ok++;
unlock:
- spin_unlock(&c->async_icosq_lock);
+ spin_unlock_bh(&c->async_icosq_lock);
return err;
}
depth += sizeof(struct tcphdr);
- if (unlikely(!sk || sk->sk_state == TCP_TIME_WAIT))
+ if (unlikely(!sk))
return;
- if (unlikely(!resync_queue_get_psv(sk)))
- return;
+ if (unlikely(sk->sk_state == TCP_TIME_WAIT))
+ goto unref;
- skb->sk = sk;
- skb->destructor = sock_edemux;
+ if (unlikely(!resync_queue_get_psv(sk)))
+ goto unref;
seq = th->seq;
datalen = skb->len - depth;
tls_offload_rx_resync_async_request_start(sk, seq, datalen);
rq->stats->tls_resync_req_start++;
+
+unref:
+ sock_gen_put(sk);
}
void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk,
mlx5e_disable_async_events(priv);
mlx5_lag_remove(mdev);
+ mlx5_vxlan_reset_to_default(mdev->vxlan);
}
int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
unsigned char h_dest[ETH_ALEN]; /* destination eth addr */
struct net_device *out_dev;
- struct net_device *route_dev;
+ int route_dev_ifindex;
struct mlx5e_tc_tunnel *tunnel;
int reformat_type;
u8 flags;
} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
out:
- if (rq->xdp_prog)
+ if (rcu_access_pointer(rq->xdp_prog))
mlx5e_xdp_rx_poll_complete(rq);
mlx5_cqwq_update_db_record(cqwq);
return flow;
err_free:
+ dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
mlx5e_flow_put(priv, flow);
out:
return ERR_PTR(err);
return 0;
err_free:
+ dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts);
mlx5e_flow_put(priv, flow);
out:
return err;
tc->ct = mlx5_tc_ct_init(priv, tc->chains, &priv->fs.tc.mod_hdr,
MLX5_FLOW_NAMESPACE_KERNEL);
- if (IS_ERR(tc->ct))
+ if (IS_ERR(tc->ct)) {
+ err = PTR_ERR(tc->ct);
goto err_ct;
+ }
tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
err = register_netdevice_notifier_dev_net(priv->netdev,
reg_b = be32_to_cpu(cqe->ft_metadata);
+ if (reg_b >> (MLX5E_TC_TABLE_CHAIN_TAG_BITS + ZONE_RESTORE_BITS))
+ return false;
+
chain = reg_b & MLX5E_TC_TABLE_CHAIN_TAG_MASK;
if (chain)
return true;
memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
}
-/* RM 2311217: no L4 inner checksum for IPsec tunnel type packet */
+/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet),
+ * need to set L3 checksum flag for IPsec
+ */
static void
ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5_wqe_eth_seg *eseg)
eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
sq->stats->csum_partial_inner++;
} else {
- eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial++;
}
}
static inline void
-mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+ struct mlx5e_accel_tx_state *accel,
+ struct mlx5_wqe_eth_seg *eseg)
{
- if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) {
- ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
- return;
- }
-
if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
if (skb->encapsulation) {
eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial++;
}
+#ifdef CONFIG_MLX5_EN_TLS
+ } else if (unlikely(accel && accel->tls.tls_tisn)) {
+ eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
+ sq->stats->csum_partial++;
+#endif
+ } else if (unlikely(eseg->flow_table_metadata & cpu_to_be32(MLX5_ETH_WQE_FT_META_IPSEC))) {
+ ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
+
} else
sq->stats->csum_none++;
}
}
static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
- struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+ struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
+ struct mlx5_wqe_eth_seg *eseg)
{
if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg)))
return false;
- mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
+ mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
return true;
}
if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
struct mlx5_wqe_eth_seg eseg = {};
- if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &eseg)))
+ if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg)))
return NETDEV_TX_OK;
mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more());
/* May update the WQE, but may not post other WQEs. */
mlx5e_accel_tx_finish(sq, wqe, &accel,
(struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl));
- if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &wqe->eth)))
+ if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth)))
return NETDEV_TX_OK;
mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());
mlx5e_sq_calc_wqe_attr(skb, &attr, &wqe_attr);
pi = mlx5e_txqsq_get_next_pi(sq, wqe_attr.num_wqebbs);
wqe = MLX5E_TX_FETCH_WQE(sq, pi);
- mlx5e_txwqe_build_eseg_csum(sq, skb, &wqe->eth);
+ mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, &wqe->eth);
mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, xmit_more);
}
mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram);
- mlx5e_txwqe_build_eseg_csum(sq, skb, eseg);
+ mlx5e_txwqe_build_eseg_csum(sq, skb, NULL, eseg);
eseg->mss = attr.mss;
struct mlx5_vport *vport;
vport = mlx5_eswitch_get_vport(esw, vport_num);
+
+ if (!vport->qos.enabled)
+ return -EOPNOTSUPP;
+
MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
return mlx5_modify_scheduling_element_cmd(esw->dev,
int i;
mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+ memset(&vport->qos, 0, sizeof(vport->qos));
memset(&vport->info, 0, sizeof(vport->info));
vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
}
ether_addr_copy(hw_addr, vport->info.mac);
*hw_addr_len = ETH_ALEN;
err = 0;
- } else {
- NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled");
}
mutex_unlock(&esw->state_lock);
return err;
max_guarantee = evport->info.min_rate;
}
- return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+ if (max_guarantee)
+ return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+ return 0;
}
-static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
+static int normalize_vports_min_rate(struct mlx5_eswitch *esw)
{
u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+ u32 divider = calculate_vports_min_rate_divider(esw);
struct mlx5_vport *evport;
u32 vport_max_rate;
u32 vport_min_rate;
continue;
vport_min_rate = evport->info.min_rate;
vport_max_rate = evport->info.max_rate;
- bw_share = MLX5_MIN_BW_SHARE;
+ bw_share = 0;
- if (vport_min_rate)
+ if (divider)
bw_share = MLX5_RATE_TO_BW_SHARE(vport_min_rate,
divider,
fw_max_bw_share);
struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
u32 fw_max_bw_share;
u32 previous_min_rate;
- u32 divider;
bool min_rate_supported;
bool max_rate_supported;
int err = 0;
previous_min_rate = evport->info.min_rate;
evport->info.min_rate = min_rate;
- divider = calculate_vports_min_rate_divider(esw);
- err = normalize_vports_min_rate(esw, divider);
+ err = normalize_vports_min_rate(esw);
if (err) {
evport->info.min_rate = previous_min_rate;
goto unlock;
goto out;
}
+ if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT &&
+ --fte->dests_size) {
+ fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+ fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ goto out;
+ }
+
if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
--fte->dests_size) {
fte->modify_mask |=
down_write_ref_node(&fte->node, false);
for (i = handle->num_rules - 1; i >= 0; i--)
tree_remove_node(&handle->rule[i]->node, true);
- if (fte->modify_mask && fte->dests_size) {
- modify_fte(fte);
+ if (fte->dests_size) {
+ if (fte->modify_mask)
+ modify_fte(fte);
up_write_ref_node(&fte->node, false);
- } else {
+ } else if (list_empty(&fte->node.children)) {
del_hw_fte(&fte->node);
/* Avoid double call to del_hw_fte */
fte->node.del_hw_func = NULL;
u32 key_type, u32 *p_key_id);
void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
- return devlink_net(priv_to_devlink(dev));
-}
-
#endif
}
void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
+{
+ if (!mlx5_vxlan_allowed(vxlan))
+ return;
+
+ mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT);
+ WARN_ON(!hash_empty(vxlan->htable));
+
+ kfree(vxlan);
+}
+
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan)
{
struct mlx5_vxlan_port *vxlanp;
struct hlist_node *tmp;
if (!mlx5_vxlan_allowed(vxlan))
return;
- /* Lockless since we are the only hash table consumers*/
hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
- hash_del(&vxlanp->hlist);
- mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
- kfree(vxlanp);
+ /* Don't delete default UDP port added by the HW.
+ * Remove only user configured ports
+ */
+ if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT)
+ continue;
+ mlx5_vxlan_del_port(vxlan, vxlanp->udp_port);
}
-
- kfree(vxlan);
}
int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan);
#else
static inline struct mlx5_vxlan*
mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; }
+static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; }
#endif
#endif /* __MLX5_VXLAN_H__ */
npages, ec_function, func_id);
}
+static u32 fwp_fill_manage_pages_out(struct fw_page *fwp, u32 *out, u32 index,
+ u32 npages)
+{
+ u32 pages_set = 0;
+ unsigned int n;
+
+ for_each_clear_bit(n, &fwp->bitmask, MLX5_NUM_4K_IN_PAGE) {
+ MLX5_ARRAY_SET64(manage_pages_out, out, pas, index + pages_set,
+ fwp->addr + (n * MLX5_ADAPTER_PAGE_SIZE));
+ pages_set++;
+
+ if (!--npages)
+ break;
+ }
+
+ return pages_set;
+}
+
static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
u32 *in, int in_size, u32 *out, int out_size)
{
fwp = rb_entry(p, struct fw_page, rb_node);
p = rb_next(p);
- MLX5_ARRAY_SET64(manage_pages_out, out, pas, i, fwp->addr);
- i++;
+ i += fwp_fill_manage_pages_out(fwp, out, i, npages - i);
}
MLX5_SET(manage_pages_out, out, output_num_entries, i);
caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager);
caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id);
caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols);
+ caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version);
if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) {
caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0);
if (ret)
return ret;
+ if (dmn->info.caps.sw_format_ver != MLX5_STEERING_FORMAT_CONNECTX_5) {
+ mlx5dr_err(dmn, "SW steering is not supported on this device\n");
+ return -EOPNOTSUPP;
+ }
+
ret = dr_domain_query_fdb_caps(mdev, dmn);
if (ret)
return ret;
u8 max_ft_level;
u16 roce_min_src_udp;
u8 num_esw_ports;
+ u8 sw_format_ver;
bool eswitch_manager;
bool rx_sw_owner;
bool tx_sw_owner;
config MLXSW_CORE
tristate "Mellanox Technologies Switch ASICs support"
select NET_DEVLINK
+ select MLXFW
help
This driver supports Mellanox Technologies Switch ASICs family.
select GENERIC_ALLOCATOR
select PARMAN
select OBJAGG
- select MLXFW
imply PTP_1588_CLOCK
select NET_PTP_CLASSIFY if PTP_1588_CLOCK
default m
if (trans->core->fw_flash_in_progress)
timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS);
- queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout);
+ queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw,
+ timeout << trans->retries);
}
static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core,
err = mlxsw_emad_transmit(trans->core, trans);
if (err == 0)
return;
+
+ if (!atomic_dec_and_test(&trans->active))
+ return;
} else {
err = -EIO;
}
if (!reload)
devlink_resources_unregister(devlink, NULL);
mlxsw_core->bus->fini(mlxsw_core->bus_priv);
+ if (!reload)
+ devlink_free(devlink);
return;
u32 eth_proto_cap, eth_proto_admin, eth_proto_oper;
const struct mlxsw_sp_port_type_speed_ops *ops;
char ptys_pl[MLXSW_REG_PTYS_LEN];
+ u32 eth_proto_cap_masked;
int err;
ops = mlxsw_sp->port_type_speed_ops;
- /* Set advertised speeds to supported speeds. */
+ /* Set advertised speeds to speeds supported by both the driver
+ * and the device.
+ */
ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
0, false);
err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, ð_proto_cap,
ð_proto_admin, ð_proto_oper);
+ eth_proto_cap_masked = ops->ptys_proto_cap_masked_get(eth_proto_cap);
ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
- eth_proto_cap, mlxsw_sp_port->link.autoneg);
+ eth_proto_cap_masked,
+ mlxsw_sp_port->link.autoneg);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
}
u32 *p_eth_proto_cap,
u32 *p_eth_proto_admin,
u32 *p_eth_proto_oper);
+ u32 (*ptys_proto_cap_masked_get)(u32 eth_proto_cap);
};
static inline struct net_device *
p_eth_proto_oper);
}
+static u32 mlxsw_sp1_ptys_proto_cap_masked_get(u32 eth_proto_cap)
+{
+ u32 ptys_proto_cap_masked = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+ if (mlxsw_sp1_port_link_mode[i].mask & eth_proto_cap)
+ ptys_proto_cap_masked |=
+ mlxsw_sp1_port_link_mode[i].mask;
+ }
+
+ return ptys_proto_cap_masked;
+}
+
const struct mlxsw_sp_port_type_speed_ops mlxsw_sp1_port_type_speed_ops = {
.from_ptys_supported_port = mlxsw_sp1_from_ptys_supported_port,
.from_ptys_link = mlxsw_sp1_from_ptys_link,
.to_ptys_speed = mlxsw_sp1_to_ptys_speed,
.reg_ptys_eth_pack = mlxsw_sp1_reg_ptys_eth_pack,
.reg_ptys_eth_unpack = mlxsw_sp1_reg_ptys_eth_unpack,
+ .ptys_proto_cap_masked_get = mlxsw_sp1_ptys_proto_cap_masked_get,
};
static const enum ethtool_link_mode_bit_indices
p_eth_proto_admin, p_eth_proto_oper);
}
+static u32 mlxsw_sp2_ptys_proto_cap_masked_get(u32 eth_proto_cap)
+{
+ u32 ptys_proto_cap_masked = 0;
+ int i;
+
+ for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+ if (mlxsw_sp2_port_link_mode[i].mask & eth_proto_cap)
+ ptys_proto_cap_masked |=
+ mlxsw_sp2_port_link_mode[i].mask;
+ }
+
+ return ptys_proto_cap_masked;
+}
+
const struct mlxsw_sp_port_type_speed_ops mlxsw_sp2_port_type_speed_ops = {
.from_ptys_supported_port = mlxsw_sp2_from_ptys_supported_port,
.from_ptys_link = mlxsw_sp2_from_ptys_link,
.to_ptys_speed = mlxsw_sp2_to_ptys_speed,
.reg_ptys_eth_pack = mlxsw_sp2_reg_ptys_eth_pack,
.reg_ptys_eth_unpack = mlxsw_sp2_reg_ptys_eth_unpack,
+ .ptys_proto_cap_masked_get = mlxsw_sp2_ptys_proto_cap_masked_get,
};
int_sts = lan743x_csr_read(adapter, INT_STS);
if (int_sts & INT_BIT_SW_GP_) {
- lan743x_csr_write(adapter, INT_STS, INT_BIT_SW_GP_);
+ /* disable the interrupt to prevent repeated re-triggering */
+ lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_SW_GP_);
intr->software_isr_flag = 1;
}
}
static int lan743x_dp_write(struct lan743x_adapter *adapter,
u32 select, u32 addr, u32 length, u32 *buf)
{
- int ret = -EIO;
u32 dp_sel;
int i;
- mutex_lock(&adapter->dp_lock);
if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_,
1, 40, 100, 100))
- goto unlock;
+ return -EIO;
dp_sel = lan743x_csr_read(adapter, DP_SEL);
dp_sel &= ~DP_SEL_MASK_;
dp_sel |= select;
lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_);
if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_,
1, 40, 100, 100))
- goto unlock;
+ return -EIO;
}
- ret = 0;
-unlock:
- mutex_unlock(&adapter->dp_lock);
- return ret;
+ return 0;
}
static u32 lan743x_mac_mii_access(u16 id, u16 index, int read)
static int lan743x_phy_open(struct lan743x_adapter *adapter)
{
struct lan743x_phy *phy = &adapter->phy;
+ struct phy_device *phydev = NULL;
struct device_node *phynode;
- struct phy_device *phydev;
struct net_device *netdev;
int ret = -EIO;
netdev = adapter->netdev;
phynode = of_node_get(adapter->pdev->dev.of_node);
- adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
if (phynode) {
+ /* try devicetree phy, or fixed link */
of_get_phy_mode(phynode, &adapter->phy_mode);
if (of_phy_is_fixed_link(phynode)) {
lan743x_phy_link_status_change, 0,
adapter->phy_mode);
of_node_put(phynode);
- if (!phydev)
- goto return_error;
- } else {
+ }
+
+ if (!phydev) {
+ /* try internal phy */
phydev = phy_find_first(adapter->mdiobus);
if (!phydev)
goto return_error;
+ adapter->phy_mode = PHY_INTERFACE_MODE_GMII;
ret = phy_connect_direct(netdev, phydev,
lan743x_phy_link_status_change,
adapter->phy_mode);
goto clear_active;
if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) {
- dev_kfree_skb(buffer_info->skb);
+ dev_kfree_skb_any(buffer_info->skb);
goto clear_skb;
}
if (cleanup) {
lan743x_ptp_unrequest_tx_timestamp(tx->adapter);
- dev_kfree_skb(buffer_info->skb);
+ dev_kfree_skb_any(buffer_info->skb);
} else {
ignore_sync = (buffer_info->flags &
TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0;
if (required_number_of_descriptors >
lan743x_tx_get_avail_desc(tx)) {
if (required_number_of_descriptors > (tx->ring_size - 1)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
} else {
/* save to overflow buffer */
tx->overflow_skb = skb;
start_frame_length,
do_timestamp,
skb->ip_summed == CHECKSUM_PARTIAL)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
goto unlock;
}
* frame assembler clean up was performed inside
* lan743x_tx_frame_add_fragment
*/
- dev_kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
goto unlock;
}
}
adapter->intr.irq = adapter->pdev->irq;
lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF);
- mutex_init(&adapter->dp_lock);
ret = lan743x_gpio_init(adapter);
if (ret)
struct lan743x_csr csr;
struct lan743x_intr intr;
- /* lock, used to prevent concurrent access to data port */
- struct mutex dp_lock;
-
struct lan743x_gpio gpio;
struct lan743x_ptp ptp;
mac->tx = pasemi_mac_setup_tx_resources(dev);
- if (!mac->tx)
+ if (!mac->tx) {
+ ret = -ENOMEM;
goto out_tx_ring;
+ }
/* We might already have allocated rings in case mtu was changed
* before interface was brought up.
*/
if (dev->mtu > 1500 && !mac->num_cs) {
pasemi_mac_setup_csrings(mac);
- if (!mac->num_cs)
+ if (!mac->num_cs) {
+ ret = -ENOMEM;
goto out_tx_ring;
+ }
}
/* Zero out rmon counters */
union ionic_dev_cmd cmd = {
.vf_setattr.opcode = IONIC_CMD_VF_SETATTR,
.vf_setattr.attr = attr,
- .vf_setattr.vf_index = vf,
+ .vf_setattr.vf_index = cpu_to_le16(vf),
};
int err;
{
union ionic_dev_cmd cmd = {
.q_identify.opcode = IONIC_CMD_Q_IDENTIFY,
- .q_identify.lif_type = lif_type,
+ .q_identify.lif_type = cpu_to_le16(lif_type),
.q_identify.type = qtype,
.q_identify.ver = qver,
};
int res_index;
};
+#ifndef __CHECKER__
/* Registers */
static_assert(sizeof(struct ionic_intr) == 32);
static_assert(sizeof(struct ionic_vf_setattr_comp) == 16);
static_assert(sizeof(struct ionic_vf_getattr_cmd) == 64);
static_assert(sizeof(struct ionic_vf_getattr_comp) == 16);
+#endif /* __CHECKER__ */
struct ionic_devinfo {
u8 asic_type;
ethtool_link_ksettings_zero_link_mode(ks, supported);
+ if (!idev->port_info) {
+ netdev_err(netdev, "port_info not initialized\n");
+ return -EOPNOTSUPP;
+ }
+
/* The port_info data is found in a DMA space that the NIC keeps
* up-to-date, so there's no need to request the data from the
* NIC, we already have it in our memory space.
{
union ionic_dev_cmd cmd = {
.fw_download.opcode = IONIC_CMD_FW_DOWNLOAD,
- .fw_download.offset = offset,
- .fw_download.addr = addr,
- .fw_download.length = length
+ .fw_download.offset = cpu_to_le32(offset),
+ .fw_download.addr = cpu_to_le64(addr),
+ .fw_download.length = cpu_to_le32(length),
};
ionic_dev_cmd_go(idev, &cmd);
if (lif->rxqcqs) {
for (i = 0; i < lif->nxqs && lif->rxqcqs[i]; i++) {
ionic_lif_qcq_deinit(lif, lif->rxqcqs[i]);
- ionic_rx_flush(&lif->rxqcqs[i]->cq);
ionic_rx_empty(&lif->rxqcqs[i]->q);
}
}
ret = -EINVAL;
} else {
ivf->vf = vf;
- ivf->vlan = ionic->vfs[vf].vlanid;
+ ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid);
ivf->qos = 0;
ivf->spoofchk = ionic->vfs[vf].spoofchk;
ivf->linkstate = ionic->vfs[vf].linkstate;
- ivf->max_tx_rate = ionic->vfs[vf].maxrate;
+ ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate);
ivf->trusted = ionic->vfs[vf].trusted;
ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr);
}
ret = ionic_set_vf_config(ionic, vf,
IONIC_VF_ATTR_VLAN, (u8 *)&vlan);
if (!ret)
- ionic->vfs[vf].vlanid = vlan;
+ ionic->vfs[vf].vlanid = cpu_to_le16(vlan);
}
up_write(&ionic->vf_op_lock);
ret = ionic_set_vf_config(ionic, vf,
IONIC_VF_ATTR_RATE, (u8 *)&tx_max);
if (!ret)
- lif->ionic->vfs[vf].maxrate = tx_max;
+ lif->ionic->vfs[vf].maxrate = cpu_to_le32(tx_max);
}
up_write(&ionic->vf_op_lock);
static void ionic_lif_queue_identify(struct ionic_lif *lif)
{
+ union ionic_q_identity __iomem *q_ident;
struct ionic *ionic = lif->ionic;
- union ionic_q_identity *q_ident;
struct ionic_dev *idev;
int qtype;
int err;
idev = &lif->ionic->idev;
- q_ident = (union ionic_q_identity *)&idev->dev_cmd_regs->data;
+ q_ident = (union ionic_q_identity __iomem *)&idev->dev_cmd_regs->data;
for (qtype = 0; qtype < ARRAY_SIZE(ionic_qtype_versions); qtype++) {
struct ionic_qtype_info *qti = &lif->qtype_info[qtype];
ionic_qtype_versions[qtype]);
err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
if (!err) {
- qti->version = q_ident->version;
- qti->supported = q_ident->supported;
- qti->features = le64_to_cpu(q_ident->features);
- qti->desc_sz = le16_to_cpu(q_ident->desc_sz);
- qti->comp_sz = le16_to_cpu(q_ident->comp_sz);
- qti->sg_desc_sz = le16_to_cpu(q_ident->sg_desc_sz);
- qti->max_sg_elems = le16_to_cpu(q_ident->max_sg_elems);
- qti->sg_desc_stride = le16_to_cpu(q_ident->sg_desc_stride);
+ qti->version = readb(&q_ident->version);
+ qti->supported = readb(&q_ident->supported);
+ qti->features = readq(&q_ident->features);
+ qti->desc_sz = readw(&q_ident->desc_sz);
+ qti->comp_sz = readw(&q_ident->comp_sz);
+ qti->sg_desc_sz = readw(&q_ident->sg_desc_sz);
+ qti->max_sg_elems = readw(&q_ident->max_sg_elems);
+ qti->sg_desc_stride = readw(&q_ident->sg_desc_stride);
}
mutex_unlock(&ionic->dev_cmd_lock);
static void ionic_dev_cmd_clean(struct ionic *ionic)
{
- union ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs;
+ union __iomem ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs;
iowrite32(0, ®s->doorbell);
memset_io(®s->cmd, 0, sizeof(regs->cmd));
*/
max_wait = jiffies + (max_seconds * HZ);
try_again:
- opcode = idev->dev_cmd_regs->cmd.cmd.opcode;
+ opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode);
start_time = jiffies;
do {
done = ionic_dev_cmd_done(idev);
(*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
#define IONIC_READ_STAT_LE64(base_ptr, desc_ptr) \
- __le64_to_cpu(*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
+ __le64_to_cpu(*((__le64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset)))
struct ionic_stat_desc {
char name[ETH_GSTRING_LEN];
if (likely(netdev->features & NETIF_F_RXCSUM)) {
if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) {
skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum = (__wsum)le16_to_cpu(comp->csum);
+ skb->csum = (__force __wsum)le16_to_cpu(comp->csum);
stats->csum_complete++;
}
} else {
return true;
}
-void ionic_rx_flush(struct ionic_cq *cq)
-{
- struct ionic_dev *idev = &cq->lif->ionic->idev;
- u32 work_done;
-
- work_done = ionic_cq_service(cq, cq->num_descs,
- ionic_rx_service, NULL, NULL);
-
- if (work_done)
- ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index,
- work_done, IONIC_INTR_CRED_RESET_COALESCE);
-}
-
static int ionic_rx_page_alloc(struct ionic_queue *q,
struct ionic_page_info *page_info)
{
void ionic_rx_empty(struct ionic_queue *q)
{
struct ionic_desc_info *desc_info;
- struct ionic_rxq_desc *desc;
- unsigned int i;
- u16 idx;
-
- idx = q->tail_idx;
- while (idx != q->head_idx) {
- desc_info = &q->info[idx];
- desc = desc_info->desc;
- desc->addr = 0;
- desc->len = 0;
+ struct ionic_page_info *page_info;
+ unsigned int i, j;
- for (i = 0; i < desc_info->npages; i++)
- ionic_rx_page_free(q, &desc_info->pages[i]);
+ for (i = 0; i < q->num_descs; i++) {
+ desc_info = &q->info[i];
+ for (j = 0; j < IONIC_RX_MAX_SG_ELEMS + 1; j++) {
+ page_info = &desc_info->pages[j];
+ if (page_info->page)
+ ionic_rx_page_free(q, page_info);
+ }
+ desc_info->npages = 0;
+ desc_info->cb = NULL;
desc_info->cb_arg = NULL;
- idx = (idx + 1) & (q->num_descs - 1);
}
}
skb_frag_t *frag;
bool start, done;
bool outer_csum;
+ dma_addr_t addr;
bool has_vlan;
u16 desc_len;
u8 desc_nsge;
if (frag_left > 0) {
len = min(frag_left, left);
frag_left -= len;
- elem->addr =
- cpu_to_le64(ionic_tx_map_frag(q, frag,
- offset, len));
- if (dma_mapping_error(dev, elem->addr))
+ addr = ionic_tx_map_frag(q, frag, offset, len);
+ if (dma_mapping_error(dev, addr))
goto err_out_abort;
+ elem->addr = cpu_to_le64(addr);
elem->len = cpu_to_le16(len);
elem++;
desc_nsge++;
#ifndef _IONIC_TXRX_H_
#define _IONIC_TXRX_H_
-void ionic_rx_flush(struct ionic_cq *cq);
void ionic_tx_flush(struct ionic_cq *cq);
void ionic_rx_fill(struct ionic_queue *q);
ilog2(rounded_conn_num));
STORE_RT_REG_AGG(p_hwfn, SRC_REG_FIRSTFREE_RT_OFFSET,
- p_hwfn->p_cxt_mngr->first_free);
+ p_hwfn->p_cxt_mngr->src_t2.first_free);
STORE_RT_REG_AGG(p_hwfn, SRC_REG_LASTFREE_RT_OFFSET,
- p_hwfn->p_cxt_mngr->last_free);
+ p_hwfn->p_cxt_mngr->src_t2.last_free);
}
/* Timers PF */
/* SRC T2 */
struct qed_src_t2 src_t2;
- u32 t2_num_pages;
- u64 first_free;
- u64 last_free;
/* total number of SRQ's for this hwfn */
u32 srq_count;
iwarp_info->partial_fpdus = kcalloc((u16)p_hwfn->p_rdma_info->num_qps,
sizeof(*iwarp_info->partial_fpdus),
GFP_KERNEL);
- if (!iwarp_info->partial_fpdus)
+ if (!iwarp_info->partial_fpdus) {
+ rc = -ENOMEM;
goto err;
+ }
iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps;
iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL);
- if (!iwarp_info->mpa_intermediate_buf)
+ if (!iwarp_info->mpa_intermediate_buf) {
+ rc = -ENOMEM;
goto err;
+ }
/* The mpa_bufs array serves for pending RX packets received on the
* mpa ll2 that don't have place on the tx ring and require later
iwarp_info->mpa_bufs = kcalloc(data.input.rx_num_desc,
sizeof(*iwarp_info->mpa_bufs),
GFP_KERNEL);
- if (!iwarp_info->mpa_bufs)
+ if (!iwarp_info->mpa_bufs) {
+ rc = -ENOMEM;
goto err;
+ }
INIT_LIST_HEAD(&iwarp_info->mpa_buf_pending_list);
INIT_LIST_HEAD(&iwarp_info->mpa_buf_list);
/* Boot either flash image or firmware image from host file system */
if (qlcnic_load_fw_file == 1) {
- if (qlcnic_83xx_load_fw_image_from_host(adapter))
+ err = qlcnic_83xx_load_fw_image_from_host(adapter);
+ if (err)
return err;
} else {
QLC_SHARED_REG_WR32(adapter, QLCNIC_FW_IMG_VALID,
dev = skb->dev;
port = rmnet_get_port_rcu(dev);
+ if (unlikely(!port)) {
+ atomic_long_inc(&skb->dev->rx_nohandler);
+ kfree_skb(skb);
+ goto done;
+ }
switch (port->rmnet_mode) {
case RMNET_EPMODE_VND:
return -EIO;
}
-static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb)
+static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp)
{
- return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34;
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_34:
+ case RTL_GIGA_MAC_VER_60:
+ case RTL_GIGA_MAC_VER_61:
+ case RTL_GIGA_MAC_VER_63:
+ return true;
+ default:
+ return false;
+ }
}
static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts)
opts[1] |= transport_offset << TCPHO_SHIFT;
} else {
- if (unlikely(rtl_test_hw_pad_bug(tp, skb)))
- return !eth_skb_pad(skb);
+ if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp)))
+ /* eth_skb_pad would free the skb on error */
+ return !__skb_put_padto(skb, ETH_ZLEN, false);
}
return true;
rtl_chip_supports_csum_v2(tp))
features &= ~NETIF_F_ALL_TSO;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
- if (skb->len < ETH_ZLEN) {
- switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_11:
- case RTL_GIGA_MAC_VER_12:
- case RTL_GIGA_MAC_VER_17:
- case RTL_GIGA_MAC_VER_34:
- features &= ~NETIF_F_CSUM_MASK;
- break;
- default:
- break;
- }
- }
+ /* work around hw bug on some chip versions */
+ if (skb->len < ETH_ZLEN)
+ features &= ~NETIF_F_CSUM_MASK;
if (transport_offset > TCPHO_MAX &&
rtl_chip_supports_csum_v2(tp))
}
rtl_irq_disable(tp);
- napi_schedule_irqoff(&tp->napi);
+ napi_schedule(&tp->napi);
out:
rtl_ack_events(tp, status);
rtl_request_firmware(tp);
retval = request_irq(pci_irq_vector(pdev, 0), rtl8169_interrupt,
- IRQF_NO_THREAD | IRQF_SHARED, dev->name, tp);
+ IRQF_SHARED, dev->name, tp);
if (retval < 0)
goto err_release_fw_2;
config.flags = 0;
config.tx_type = priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON :
HWTSTAMP_TX_OFF;
- if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_V2_L2_EVENT)
+ switch (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE) {
+ case RAVB_RXTSTAMP_TYPE_V2_L2_EVENT:
config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
- else if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_ALL)
+ break;
+ case RAVB_RXTSTAMP_TYPE_ALL:
config.rx_filter = HWTSTAMP_FILTER_ALL;
- else
+ break;
+ default:
config.rx_filter = HWTSTAMP_FILTER_NONE;
+ }
return copy_to_user(req->ifr_data, &config, sizeof(config)) ?
-EFAULT : 0;
/* Enable TX clock */
if (dwmac->data->tx_clk_en) {
dwmac->tx_clk = devm_clk_get(&pdev->dev, "tx_clk");
- if (IS_ERR(dwmac->tx_clk))
+ if (IS_ERR(dwmac->tx_clk)) {
+ ret = PTR_ERR(dwmac->tx_clk);
goto err_remove_config_dt;
+ }
clk_prepare_enable(dwmac->tx_clk);
if (ret)
return ret;
- if (plat->eee_usecs_rate > 0) {
- u32 tx_lpi_usec;
-
- tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
- writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
- }
-
ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (ret < 0)
return ret;
res.wol_irq = pci_irq_vector(pdev, 0);
res.irq = pci_irq_vector(pdev, 0);
+ if (plat->eee_usecs_rate > 0) {
+ u32 tx_lpi_usec;
+
+ tx_lpi_usec = (plat->eee_usecs_rate / 1000000) - 1;
+ writel(tx_lpi_usec, res.addr + GMAC_1US_TIC_COUNTER);
+ }
+
ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
if (ret) {
pci_free_irq_vectors(pdev);
.pcs_get_adv_lp = dwmac4_get_adv_lp,
.debug = dwmac4_debug,
.set_filter = dwmac4_set_filter,
- .flex_pps_config = dwmac5_flex_pps_config,
.set_mac_loopback = dwmac4_set_mac_loopback,
.update_vlan_hash = dwmac4_update_vlan_hash,
.sarc_configure = dwmac4_sarc_configure,
.pcs_get_adv_lp = dwmac4_get_adv_lp,
.debug = dwmac4_debug,
.set_filter = dwmac4_set_filter,
+ .flex_pps_config = dwmac5_flex_pps_config,
.set_mac_loopback = dwmac4_set_mac_loopback,
.update_vlan_hash = dwmac4_update_vlan_hash,
.sarc_configure = dwmac4_sarc_configure,
return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
!(value & DMA_BUS_MODE_SFT_RESET),
- 10000, 100000);
+ 10000, 200000);
}
/* CSR1 enables the transmit DMA to check for new descriptor */
ch->priv_data = priv;
ch->index = queue;
+ spin_lock_init(&ch->lock);
if (queue < priv->plat->rx_queues_to_use) {
netif_napi_add(dev, &ch->rx_napi, stmmac_napi_poll_rx,
return ret;
}
+ rtnl_lock();
mutex_lock(&priv->lock);
stmmac_reset_queues_param(priv);
stmmac_enable_all_queues(priv);
mutex_unlock(&priv->lock);
+ rtnl_unlock();
if (!device_may_wakeup(priv->device) || !priv->plat->pmt) {
rtnl_lock();
if (IS_ERR_OR_NULL(cpts->ptp_clock)) {
dev_err(dev, "Failed to register ptp clk %ld\n",
PTR_ERR(cpts->ptp_clock));
- if (!cpts->ptp_clock)
- ret = -ENODEV;
+ ret = cpts->ptp_clock ? PTR_ERR(cpts->ptp_clock) : -ENODEV;
goto refclk_disable;
}
cpts->phc_index = ptp_clock_index(cpts->ptp_clock);
if (ret < 0)
goto err_cleanup;
- if (cpts_register(cpsw->cpts))
- dev_err(priv->dev, "error registering cpts device\n");
-
+ if (cpsw->cpts) {
+ if (cpts_register(cpsw->cpts))
+ dev_err(priv->dev, "error registering cpts device\n");
+ else
+ writel(0x10, &cpsw->wr_regs->misc_en);
+ }
}
cpsw_restore(priv);
CPSW_MAX_QUEUES, CPSW_MAX_QUEUES);
if (!ndev) {
dev_err(dev, "error allocating net_device\n");
+ ret = -ENOMEM;
goto clean_cpts;
}
/* Enable misc CPTS evnt_pend IRQ */
cpts_set_irqpoll(cpsw->cpts, false);
- writel(0x10, &cpsw->wr_regs->misc_en);
skip_cpts:
cpsw_notice(priv, probe,
(1 << HWTSTAMP_TX_ON);
info->rx_filters =
(1 << HWTSTAMP_FILTER_NONE) |
- (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
return 0;
}
if (ret < 0)
goto err_cleanup;
- if (cpts_register(cpsw->cpts))
- dev_err(priv->dev, "error registering cpts device\n");
+ if (cpsw->cpts) {
+ if (cpts_register(cpsw->cpts))
+ dev_err(priv->dev, "error registering cpts device\n");
+ else
+ writel(0x10, &cpsw->wr_regs->misc_en);
+ }
napi_enable(&cpsw->napi_rx);
napi_enable(&cpsw->napi_tx);
/* Enable misc CPTS evnt_pend IRQ */
cpts_set_irqpoll(cpsw->cpts, false);
- writel(0x10, &cpsw->wr_regs->misc_en);
skip_cpts:
ret = cpsw_register_notifiers(cpsw);
break;
case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_NTP_ALL:
- return -ERANGE;
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
- priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
- cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
- break;
+ return -ERANGE;
case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
if (ip_tunnel_collect_metadata() || gs->collect_md) {
__be16 flags;
- flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
- (gnvh->oam ? TUNNEL_OAM : 0) |
+ flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) |
(gnvh->critical ? TUNNEL_CRIT_OPT : 0);
tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags,
skb_dst_set(skb, &tun_dst->dst);
/* Ignore packet loops (and multicast echo) */
- if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) {
- geneve->dev->stats.rx_errors++;
- goto drop;
- }
+ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
+ goto rx_error;
+ switch (skb_protocol(skb, true)) {
+ case htons(ETH_P_IP):
+ if (pskb_may_pull(skb, sizeof(struct iphdr)))
+ goto rx_error;
+ break;
+ case htons(ETH_P_IPV6):
+ if (pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+ goto rx_error;
+ break;
+ default:
+ goto rx_error;
+ }
oiph = skb_network_header(skb);
skb_reset_network_header(skb);
dev_sw_netstats_rx_add(geneve->dev, len);
return;
+rx_error:
+ geneve->dev->stats.rx_errors++;
drop:
/* Consume bad packet */
kfree_skb(skb);
gtp = netdev_priv(dev);
- err = gtp_encap_enable(gtp, data);
- if (err < 0)
- return err;
-
if (!data[IFLA_GTP_PDP_HASHSIZE]) {
hashsize = 1024;
} else {
err = gtp_hashtable_new(gtp, hashsize);
if (err < 0)
- goto out_encap;
+ return err;
+
+ err = gtp_encap_enable(gtp, data);
+ if (err < 0)
+ goto out_hashtable;
err = register_netdevice(dev);
if (err < 0) {
netdev_dbg(dev, "failed to register new netdev %d\n", err);
- goto out_hashtable;
+ goto out_encap;
}
gn = net_generic(dev_net(dev), gtp_net_id);
return 0;
+out_encap:
+ gtp_encap_disable(gtp);
out_hashtable:
kfree(gtp->addr_hash);
kfree(gtp->tid_hash);
-out_encap:
- gtp_encap_disable(gtp);
return err;
}
return trans;
}
-/* Free a previously-allocated transaction (used only in case of error) */
+/* Free a previously-allocated transaction */
void gsi_trans_free(struct gsi_trans *trans)
{
+ refcount_t *refcount = &trans->refcount;
struct gsi_trans_info *trans_info;
+ bool last;
- if (!refcount_dec_and_test(&trans->refcount))
+ /* We must hold the lock to release the last reference */
+ if (refcount_dec_not_one(refcount))
return;
trans_info = &trans->gsi->channel[trans->channel_id].trans_info;
spin_lock_bh(&trans_info->spinlock);
- list_del(&trans->links);
+ /* Reference might have been added before we got the lock */
+ last = refcount_dec_and_test(refcount);
+ if (last)
+ list_del(&trans->links);
spin_unlock_bh(&trans_info->spinlock);
+ if (!last)
+ return;
+
ipa_gsi_trans_release(trans);
/* Releasing the reserved TREs implicitly frees the sgl[] and
/* assert(which < trans->tre_count); */
- /* Set the page information for the buffer. We also need to fill in
- * the DMA address and length for the buffer (something dma_map_sg()
- * normally does).
+ /* Commands are quite different from data transfer requests.
+ * Their payloads come from a pool whose memory is allocated
+ * using dma_alloc_coherent(). We therefore do *not* map them
+ * for DMA (unlike what we do for pages and skbs).
+ *
+ * When a transaction completes, the SGL is normally unmapped.
+ * A command transaction has direction DMA_NONE, which tells
+ * gsi_trans_complete() to skip the unmapping step.
+ *
+ * The only things we use directly in a command scatter/gather
+ * entry are the DMA address and length. We still need the SG
+ * table flags to be maintained though, so assign a NULL page
+ * pointer for that purpose.
*/
sg = &trans->sgl[which];
-
- sg_set_buf(sg, buf, size);
+ sg_assign_page(sg, NULL);
sg_dma_address(sg) = addr;
- sg_dma_len(sg) = sg->length;
+ sg_dma_len(sg) = size;
info = &trans->info[which];
info->opcode = opcode;
.open = simple_open,
.write = nsim_dev_take_snapshot_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file,
.read = nsim_dev_trap_fa_cookie_read,
.write = nsim_dev_trap_fa_cookie_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
.open = simple_open,
.write = nsim_dev_health_break_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink)
.open = simple_open,
.write = nsim_udp_tunnels_info_reset_write,
.llseek = generic_file_llseek,
+ .owner = THIS_MODULE,
};
int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
switch (phydev->phy_id & phydev->drv->phy_id_mask) {
case PHY_ID_VSC856X:
- case PHY_ID_VSC8575:
case PHY_ID_VSC8582:
case PHY_ID_VSC8584:
INIT_LIST_HEAD(&vsc8531->macsec_flows);
{
PHY_ID_MATCH_EXACT(0x00008201),
.name = "RTL8201CP Ethernet",
+ .read_page = rtl821x_read_page,
+ .write_page = rtl821x_write_page,
}, {
PHY_ID_MATCH_EXACT(0x001cc816),
.name = "RTL8201F Fast Ethernet",
continue;
sfp->gpio_irq[i] = gpiod_to_irq(sfp->gpio[i]);
- if (!sfp->gpio_irq[i]) {
+ if (sfp->gpio_irq[i] < 0) {
+ sfp->gpio_irq[i] = 0;
sfp->need_poll = true;
continue;
}
return ret;
ret = clk_set_rate(priv->refclk, 50 * 1000 * 1000);
- if (ret)
+ if (ret) {
+ clk_disable_unprepare(priv->refclk);
return ret;
+ }
return 0;
}
struct tun_file *tfile = file->private_data;
struct tun_struct *tun = tun_get(tfile);
ssize_t result;
+ int noblock = 0;
if (!tun)
return -EBADFD;
- result = tun_get_user(tun, tfile, NULL, from,
- file->f_flags & O_NONBLOCK, false);
+ if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT))
+ noblock = 1;
+
+ result = tun_get_user(tun, tfile, NULL, from, noblock, false);
tun_put(tun);
return result;
struct tun_file *tfile = file->private_data;
struct tun_struct *tun = tun_get(tfile);
ssize_t len = iov_iter_count(to), ret;
+ int noblock = 0;
if (!tun)
return -EBADFD;
- ret = tun_do_read(tun, tfile, to, file->f_flags & O_NONBLOCK, NULL);
+
+ if ((file->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT))
+ noblock = 1;
+
+ ret = tun_do_read(tun, tfile, to, noblock, NULL);
ret = min_t(ssize_t, ret, len);
if (ret > 0)
iocb->ki_pos = ret;
}
/* enable ethernet mode (?) */
- if (cx82310_enable_ethernet(dev))
+ ret = cx82310_enable_ethernet(dev);
+ if (ret)
goto err;
/* get the MAC address */
#define IPHETH_USBINTF_SUBCLASS 253
#define IPHETH_USBINTF_PROTO 1
-#define IPHETH_BUF_SIZE 1516
+#define IPHETH_BUF_SIZE 1514
#define IPHETH_IP_ALIGN 2 /* padding at front of URB */
#define IPHETH_TX_TIMEOUT (5 * HZ)
{QMI_FIXED_INTF(0x05c6, 0x9011, 4)},
{QMI_FIXED_INTF(0x05c6, 0x9021, 1)},
{QMI_FIXED_INTF(0x05c6, 0x9022, 2)},
- {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */
+ {QMI_QUIRK_SET_DTR(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */
{QMI_FIXED_INTF(0x05c6, 0x9026, 3)},
{QMI_FIXED_INTF(0x05c6, 0x902e, 5)},
{QMI_FIXED_INTF(0x05c6, 0x9031, 5)},
{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1230, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1260, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1261, 2)}, /* Telit LE910Cx */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1900, 1)}, /* Telit LN940 series */
return ret;
}
-static int vrf_finish_direct(struct net *net, struct sock *sk,
- struct sk_buff *skb)
+static void vrf_finish_direct(struct sk_buff *skb)
{
struct net_device *vrf_dev = skb->dev;
skb_pull(skb, ETH_HLEN);
}
- return 1;
+ /* reset skb device */
+ nf_reset_ct(skb);
}
#if IS_ENABLED(CONFIG_IPV6)
return skb;
}
+static int vrf_output6_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ vrf_finish_direct(skb);
+
+ return vrf_ip6_local_out(net, sk, skb);
+}
+
static int vrf_output6_direct(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
+ int err = 1;
+
skb->protocol = htons(ETH_P_IPV6);
- return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, skb->dev,
- vrf_finish_direct,
- !(IPCB(skb)->flags & IPSKB_REROUTED));
+ if (!(IPCB(skb)->flags & IPSKB_REROUTED))
+ err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
+ NULL, skb->dev, vrf_output6_direct_finish);
+
+ if (likely(err == 1))
+ vrf_finish_direct(skb);
+
+ return err;
+}
+
+static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ int err;
+
+ err = vrf_output6_direct(net, sk, skb);
+ if (likely(err == 1))
+ err = vrf_ip6_local_out(net, sk, skb);
+
+ return err;
}
static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
skb->dev = vrf_dev;
err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
- skb, NULL, vrf_dev, vrf_output6_direct);
+ skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);
if (likely(err == 1))
err = vrf_output6_direct(net, sk, skb);
- /* reset skb device */
if (likely(err == 1))
- nf_reset_ct(skb);
- else
- skb = NULL;
+ return skb;
- return skb;
+ return NULL;
}
static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
return skb;
}
+static int vrf_output_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ vrf_finish_direct(skb);
+
+ return vrf_ip_local_out(net, sk, skb);
+}
+
static int vrf_output_direct(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
+ int err = 1;
+
skb->protocol = htons(ETH_P_IP);
- return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
- net, sk, skb, NULL, skb->dev,
- vrf_finish_direct,
- !(IPCB(skb)->flags & IPSKB_REROUTED));
+ if (!(IPCB(skb)->flags & IPSKB_REROUTED))
+ err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
+ NULL, skb->dev, vrf_output_direct_finish);
+
+ if (likely(err == 1))
+ vrf_finish_direct(skb);
+
+ return err;
+}
+
+static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
+{
+ int err;
+
+ err = vrf_output_direct(net, sk, skb);
+ if (likely(err == 1))
+ err = vrf_ip_local_out(net, sk, skb);
+
+ return err;
}
static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
skb->dev = vrf_dev;
err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
- skb, NULL, vrf_dev, vrf_output_direct);
+ skb, NULL, vrf_dev, vrf_ip_out_direct_finish);
if (likely(err == 1))
err = vrf_output_direct(net, sk, skb);
- /* reset skb device */
if (likely(err == 1))
- nf_reset_ct(skb);
- else
- skb = NULL;
+ return skb;
- return skb;
+ return NULL;
}
static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
dev->gso_max_segs = lowerdev->gso_max_segs;
needed_headroom = lowerdev->hard_header_len;
+ needed_headroom += lowerdev->needed_headroom;
+
+ dev->needed_tailroom = lowerdev->needed_tailroom;
max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM :
VXLAN_HEADROOM);
if (dst->remote_ifindex) {
remote_dev = __dev_get_by_index(net, dst->remote_ifindex);
- if (!remote_dev)
+ if (!remote_dev) {
+ err = -ENODEV;
goto errout;
+ }
err = netdev_upper_dev_link(remote_dev, dev, extack);
if (err)
chan->tx_status = 1;
spin_unlock_irqrestore(&cosa->lock, flags);
up(&chan->wsem);
+ kfree(kbuf);
return -ERESTARTSYS;
}
}
*
* GPL LICENSE SUMMARY
*
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012-2014, 2018 - 2020 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
*
* BSD LICENSE
*
- * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2012-2014, 2018 - 2020 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
STA_FLG_MAX_AGG_SIZE_256K = (5 << STA_FLG_MAX_AGG_SIZE_SHIFT),
STA_FLG_MAX_AGG_SIZE_512K = (6 << STA_FLG_MAX_AGG_SIZE_SHIFT),
STA_FLG_MAX_AGG_SIZE_1024K = (7 << STA_FLG_MAX_AGG_SIZE_SHIFT),
- STA_FLG_MAX_AGG_SIZE_MSK = (7 << STA_FLG_MAX_AGG_SIZE_SHIFT),
+ STA_FLG_MAX_AGG_SIZE_2M = (8 << STA_FLG_MAX_AGG_SIZE_SHIFT),
+ STA_FLG_MAX_AGG_SIZE_4M = (9 << STA_FLG_MAX_AGG_SIZE_SHIFT),
+ STA_FLG_MAX_AGG_SIZE_MSK = (0xf << STA_FLG_MAX_AGG_SIZE_SHIFT),
STA_FLG_AGG_MPDU_DENS_SHIFT = 23,
STA_FLG_AGG_MPDU_DENS_2US = (4 << STA_FLG_AGG_MPDU_DENS_SHIFT),
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
* Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 - 2019 Intel Corporation
+ * Copyright(c) 2018 - 2020 Intel Corporation
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* able to run the GO Negotiation. Will not be fragmented and not
* repetitive. Valid only on the P2P Device MAC. Only the duration will
* be taken into account.
+ * @SESSION_PROTECT_CONF_MAX_ID: not used
*/
enum iwl_mvm_session_prot_conf_id {
SESSION_PROTECT_CONF_ASSOC,
SESSION_PROTECT_CONF_GO_CLIENT_ASSOC,
SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV,
SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION,
+ SESSION_PROTECT_CONF_MAX_ID,
}; /* SESSION_PROTECTION_CONF_ID_E_VER_1 */
/**
* @mac_id: the mac id for which the session protection started / ended
* @status: 1 means success, 0 means failure
* @start: 1 means the session protection started, 0 means it ended
- * @conf_id: the configuration id of the session that started / eneded
+ * @conf_id: see &enum iwl_mvm_session_prot_conf_id
*
* Note that any session protection will always get two notifications: start
* and end even the firmware could not schedule it.
#define IWL_CFG_RF_ID_HR 0x7
#define IWL_CFG_RF_ID_HR1 0x4
-#define IWL_CFG_NO_160 0x0
-#define IWL_CFG_160 0x1
+#define IWL_CFG_NO_160 0x1
+#define IWL_CFG_160 0x0
#define IWL_CFG_CORES_BT 0x0
#define IWL_CFG_CORES_BT_GNSS 0x5
#define CSR_MAC_SHADOW_REG_CTL2 (CSR_BASE + 0x0AC)
#define CSR_MAC_SHADOW_REG_CTL2_RX_WAKE 0xFFFF
+/* LTR control (since IWL_DEVICE_FAMILY_22000) */
+#define CSR_LTR_LONG_VAL_AD (CSR_BASE + 0x0D4)
+#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ 0x80000000
+#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE 0x1c000000
+#define CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL 0x03ff0000
+#define CSR_LTR_LONG_VAL_AD_SNOOP_REQ 0x00008000
+#define CSR_LTR_LONG_VAL_AD_SNOOP_SCALE 0x00001c00
+#define CSR_LTR_LONG_VAL_AD_SNOOP_VAL 0x000003ff
+#define CSR_LTR_LONG_VAL_AD_SCALE_USEC 2
+
/* GIO Chicken Bits (PCI Express bus link power management) */
#define CSR_GIO_CHICKEN_BITS (CSR_BASE+0x100)
/* this would be a mac80211 bug ... but don't crash */
if (WARN_ON_ONCE(!mvmvif->phy_ctxt))
- return -EINVAL;
+ return test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) ? 0 : -EINVAL;
/*
* If we are in a STA removal flow and in DQA mode:
goto out_unlock;
}
+ if (vif->type == NL80211_IFTYPE_STATION)
+ vif->bss_conf.he_support = sta->he_cap.has_he;
+
if (sta->tdls &&
(vif->p2p ||
iwl_mvm_tdls_sta_count(mvm, NULL) ==
mpdu_dens = sta->ht_cap.ampdu_density;
}
+
if (sta->vht_cap.vht_supported) {
agg_size = sta->vht_cap.cap &
IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK;
agg_size = sta->ht_cap.ampdu_factor;
}
+ /* D6.0 10.12.2 A-MPDU length limit rules
+ * A STA indicates the maximum length of the A-MPDU preEOF padding
+ * that it can receive in an HE PPDU in the Maximum A-MPDU Length
+ * Exponent field in its HT Capabilities, VHT Capabilities,
+ * and HE 6 GHz Band Capabilities elements (if present) and the
+ * Maximum AMPDU Length Exponent Extension field in its HE
+ * Capabilities element
+ */
+ if (sta->he_cap.has_he)
+ agg_size += u8_get_bits(sta->he_cap.he_cap_elem.mac_cap_info[3],
+ IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK);
+
+ /* Limit to max A-MPDU supported by FW */
+ if (agg_size > (STA_FLG_MAX_AGG_SIZE_4M >> STA_FLG_MAX_AGG_SIZE_SHIFT))
+ agg_size = (STA_FLG_MAX_AGG_SIZE_4M >>
+ STA_FLG_MAX_AGG_SIZE_SHIFT);
+
add_sta_cmd.station_flags |=
cpu_to_le32(agg_size << STA_FLG_MAX_AGG_SIZE_SHIFT);
add_sta_cmd.station_flags |=
}
}
+static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm,
+ struct iwl_mvm_vif *mvmvif)
+{
+ struct iwl_mvm_session_prot_cmd cmd = {
+ .id_and_color =
+ cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id,
+ mvmvif->color)),
+ .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
+ .conf_id = cpu_to_le32(mvmvif->time_event_data.id),
+ };
+ int ret;
+
+ ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD,
+ MAC_CONF_GROUP, 0),
+ 0, sizeof(cmd), &cmd);
+ if (ret)
+ IWL_ERR(mvm,
+ "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret);
+}
+
static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm,
struct iwl_mvm_time_event_data *te_data,
u32 *uid)
{
u32 id;
+ struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif);
/*
* It is possible that by the time we got to this point the time
iwl_mvm_te_clear_data(mvm, te_data);
spin_unlock_bh(&mvm->time_event_lock);
- /*
- * It is possible that by the time we try to remove it, the time event
- * has already ended and removed. In such a case there is no need to
- * send a removal command.
+ /* When session protection is supported, the te_data->id field
+ * is reused to save session protection's configuration.
*/
- if (id == TE_MAX) {
- IWL_DEBUG_TE(mvm, "TE 0x%x has already ended\n", *uid);
+ if (fw_has_capa(&mvm->fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) {
+ if (mvmvif && id < SESSION_PROTECT_CONF_MAX_ID) {
+ /* Session protection is still ongoing. Cancel it */
+ iwl_mvm_cancel_session_protection(mvm, mvmvif);
+ if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) {
+ set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
+ iwl_mvm_roc_finished(mvm);
+ }
+ }
return false;
+ } else {
+ /* It is possible that by the time we try to remove it, the
+ * time event has already ended and removed. In such a case
+ * there is no need to send a removal command.
+ */
+ if (id == TE_MAX) {
+ IWL_DEBUG_TE(mvm, "TE 0x%x has already ended\n", *uid);
+ return false;
+ }
}
return true;
struct iwl_rx_packet *pkt = rxb_addr(rxb);
struct iwl_mvm_session_prot_notif *notif = (void *)pkt->data;
struct ieee80211_vif *vif;
+ struct iwl_mvm_vif *mvmvif;
rcu_read_lock();
vif = iwl_mvm_rcu_dereference_vif_id(mvm, le32_to_cpu(notif->mac_id),
if (!vif)
goto out_unlock;
+ mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
/* The vif is not a P2P_DEVICE, maintain its time_event_data */
if (vif->type != NL80211_IFTYPE_P2P_DEVICE) {
- struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
struct iwl_mvm_time_event_data *te_data =
&mvmvif->time_event_data;
if (!le32_to_cpu(notif->status) || !le32_to_cpu(notif->start)) {
/* End TE, notify mac80211 */
+ mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
ieee80211_remain_on_channel_expired(mvm->hw);
set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
iwl_mvm_roc_finished(mvm);
} else if (le32_to_cpu(notif->start)) {
+ if (WARN_ON(mvmvif->time_event_data.id !=
+ le32_to_cpu(notif->conf_id)))
+ goto out_unlock;
set_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status);
ieee80211_ready_on_channel(mvm->hw); /* Start TE */
}
lockdep_assert_held(&mvm->mutex);
+ /* The time_event_data.id field is reused to save session
+ * protection's configuration.
+ */
switch (type) {
case IEEE80211_ROC_TYPE_NORMAL:
- cmd.conf_id =
- cpu_to_le32(SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV);
+ mvmvif->time_event_data.id =
+ SESSION_PROTECT_CONF_P2P_DEVICE_DISCOV;
break;
case IEEE80211_ROC_TYPE_MGMT_TX:
- cmd.conf_id =
- cpu_to_le32(SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION);
+ mvmvif->time_event_data.id =
+ SESSION_PROTECT_CONF_P2P_GO_NEGOTIATION;
break;
default:
WARN_ONCE(1, "Got an invalid ROC type\n");
return -EINVAL;
}
+ cmd.conf_id = cpu_to_le32(mvmvif->time_event_data.id);
return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD,
MAC_CONF_GROUP, 0),
0, sizeof(cmd), &cmd);
__iwl_mvm_remove_time_event(mvm, te_data, &uid);
}
-static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm,
- struct iwl_mvm_vif *mvmvif)
-{
- struct iwl_mvm_session_prot_cmd cmd = {
- .id_and_color =
- cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id,
- mvmvif->color)),
- .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
- };
- int ret;
-
- ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(SESSION_PROTECTION_CMD,
- MAC_CONF_GROUP, 0),
- 0, sizeof(cmd), &cmd);
- if (ret)
- IWL_ERR(mvm,
- "Couldn't send the SESSION_PROTECTION_CMD: %d\n", ret);
-}
-
void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
{
struct iwl_mvm_vif *mvmvif;
IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) {
mvmvif = iwl_mvm_vif_from_mac80211(vif);
- iwl_mvm_cancel_session_protection(mvm, mvmvif);
-
- if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
+ if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
+ iwl_mvm_cancel_session_protection(mvm, mvmvif);
set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status);
+ } else {
+ iwl_mvm_remove_aux_roc_te(mvm, mvmvif,
+ &mvmvif->time_event_data);
+ }
iwl_mvm_roc_finished(mvm);
cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id,
mvmvif->color)),
.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
- .conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC),
.duration_tu = cpu_to_le32(MSEC_TO_TU(duration)),
};
+ /* The time_event_data.id field is reused to save session
+ * protection's configuration.
+ */
+ mvmvif->time_event_data.id = SESSION_PROTECT_CONF_ASSOC;
+ cmd.conf_id = cpu_to_le32(mvmvif->time_event_data.id);
+
lockdep_assert_held(&mvm->mutex);
spin_lock_bh(&mvm->time_event_lock);
iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL,
CSR_AUTO_FUNC_BOOT_ENA);
+
+ if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210) {
+ /*
+ * The firmware initializes this again later (to a smaller
+ * value), but for the boot process initialize the LTR to
+ * ~250 usec.
+ */
+ u32 val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ |
+ u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
+ CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) |
+ u32_encode_bits(250,
+ CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) |
+ CSR_LTR_LONG_VAL_AD_SNOOP_REQ |
+ u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
+ CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) |
+ u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL);
+
+ iwl_write32(trans, CSR_LTR_LONG_VAL_AD, val);
+ }
+
if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
else
{IWL_PCI_DEVICE(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0)},
{IWL_PCI_DEVICE(0x2725, 0x0020, iwlax210_2ax_cfg_ty_gf_a0)},
+ {IWL_PCI_DEVICE(0x2725, 0x0024, iwlax210_2ax_cfg_ty_gf_a0)},
{IWL_PCI_DEVICE(0x2725, 0x0310, iwlax210_2ax_cfg_ty_gf_a0)},
{IWL_PCI_DEVICE(0x2725, 0x0510, iwlax210_2ax_cfg_ty_gf_a0)},
{IWL_PCI_DEVICE(0x2725, 0x0A10, iwlax210_2ax_cfg_ty_gf_a0)},
+ {IWL_PCI_DEVICE(0x2725, 0xE020, iwlax210_2ax_cfg_ty_gf_a0)},
+ {IWL_PCI_DEVICE(0x2725, 0xE024, iwlax210_2ax_cfg_ty_gf_a0)},
+ {IWL_PCI_DEVICE(0x2725, 0x4020, iwlax210_2ax_cfg_ty_gf_a0)},
+ {IWL_PCI_DEVICE(0x2725, 0x6020, iwlax210_2ax_cfg_ty_gf_a0)},
+ {IWL_PCI_DEVICE(0x2725, 0x6024, iwlax210_2ax_cfg_ty_gf_a0)},
{IWL_PCI_DEVICE(0x2725, 0x00B0, iwlax411_2ax_cfg_sosnj_gf4_a0)},
{IWL_PCI_DEVICE(0x2726, 0x0070, iwlax201_cfg_snj_hr_b0)},
{IWL_PCI_DEVICE(0x2726, 0x0074, iwlax201_cfg_snj_hr_b0)},
void *buf, int dwords)
{
unsigned long flags;
- int offs, ret = 0;
+ int offs = 0;
u32 *vals = buf;
- if (iwl_trans_grab_nic_access(trans, &flags)) {
- iwl_write32(trans, HBUS_TARG_MEM_RADDR, addr);
- for (offs = 0; offs < dwords; offs++)
- vals[offs] = iwl_read32(trans, HBUS_TARG_MEM_RDAT);
- iwl_trans_release_nic_access(trans, &flags);
- } else {
- ret = -EBUSY;
+ while (offs < dwords) {
+ /* limit the time we spin here under lock to 1/2s */
+ ktime_t timeout = ktime_add_us(ktime_get(), 500 * USEC_PER_MSEC);
+
+ if (iwl_trans_grab_nic_access(trans, &flags)) {
+ iwl_write32(trans, HBUS_TARG_MEM_RADDR,
+ addr + 4 * offs);
+
+ while (offs < dwords) {
+ vals[offs] = iwl_read32(trans,
+ HBUS_TARG_MEM_RDAT);
+ offs++;
+
+ /* calling ktime_get is expensive so
+ * do it once in 128 reads
+ */
+ if (offs % 128 == 0 && ktime_after(ktime_get(),
+ timeout))
+ break;
+ }
+ iwl_trans_release_nic_access(trans, &flags);
+ } else {
+ return -EBUSY;
+ }
}
- return ret;
+
+ return 0;
}
static int iwl_trans_pcie_write_mem(struct iwl_trans *trans, u32 addr,
{
int ret;
- mt76_worker_disable(&dev->tx_worker);
-
ret = wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(&dev->phy),
HZ / 5);
if (!ret) {
usb_kill_urb(q->entry[j].urb);
}
+ mt76_worker_disable(&dev->tx_worker);
+
/* On device removal we maight queue skb's, but mt76u_tx_kick()
* will fail to submit urb, cleanup those skb's manually.
*/
if (!q)
continue;
- entry = q->entry[q->tail];
- q->entry[q->tail].done = false;
-
- mt76_queue_tx_complete(dev, q, &entry);
+ while (q->queued > 0) {
+ entry = q->entry[q->tail];
+ q->entry[q->tail].done = false;
+ mt76_queue_tx_complete(dev, q, &entry);
+ }
}
+
+ mt76_worker_enable(&dev->tx_worker);
}
cancel_work_sync(&dev->usb.stat_work);
clear_bit(MT76_READING_STATS, &dev->phy.state);
- mt76_worker_enable(&dev->tx_worker);
-
mt76_tx_status_check(dev, NULL, true);
}
EXPORT_SYMBOL_GPL(mt76u_stop_tx);
{
int tmp_len;
+ memset(tmp, 0, size);
+
if (count < num)
return -EFAULT;
int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size,
u32 *buffer)
{
- if (!rtwdev->chip->fw_fifo_addr) {
+ if (!rtwdev->chip->fw_fifo_addr[0]) {
rtw_dbg(rtwdev, RTW_DBG_FW, "chip not support dump fw fifo\n");
return -ENOTSUPP;
}
struct i2c_client *i2c_dev;
struct nci_dev *ndev;
- unsigned int gpio_en;
- unsigned int gpio_fw_wake;
+ int gpio_en;
+ int gpio_fw_wake;
struct mutex mutex;
if (id->nsattr & NVME_NS_ATTR_RO)
set_disk_ro(disk, true);
- else
- set_disk_ro(disk, false);
}
static inline bool nvme_first_scan(struct gendisk *disk)
if (blk_queue_is_zoned(ns->queue)) {
ret = nvme_revalidate_zones(ns);
- if (ret)
+ if (ret && !nvme_first_scan(ns->disk))
return ret;
}
static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
struct nvme_effects_log **log)
{
- struct nvme_cel *cel = xa_load(&ctrl->cels, csi);
+ struct nvme_effects_log *cel = xa_load(&ctrl->cels, csi);
int ret;
if (cel)
return -ENOMEM;
ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi,
- &cel->log, sizeof(cel->log), 0);
+ cel, sizeof(*cel), 0);
if (ret) {
kfree(cel);
return ret;
}
- cel->csi = csi;
- xa_store(&ctrl->cels, cel->csi, cel, GFP_KERNEL);
+ xa_store(&ctrl->cels, csi, cel, GFP_KERNEL);
out:
- *log = &cel->log;
+ *log = cel;
return 0;
}
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
+static void nvme_free_cels(struct nvme_ctrl *ctrl)
+{
+ struct nvme_effects_log *cel;
+ unsigned long i;
+
+ xa_for_each (&ctrl->cels, i, cel) {
+ xa_erase(&ctrl->cels, i);
+ kfree(cel);
+ }
+
+ xa_destroy(&ctrl->cels);
+}
+
static void nvme_free_ctrl(struct device *dev)
{
struct nvme_ctrl *ctrl =
if (!subsys || ctrl->instance != subsys->instance)
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
- xa_destroy(&ctrl->cels);
-
+ nvme_free_cels(ctrl);
nvme_mpath_uninit(ctrl);
__free_page(ctrl->discard_page);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
-
-void nvme_sync_queues(struct nvme_ctrl *ctrl)
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
list_for_each_entry(ns, &ctrl->namespaces, list)
blk_sync_queue(ns->queue);
up_read(&ctrl->namespaces_rwsem);
+}
+EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
+void nvme_sync_queues(struct nvme_ctrl *ctrl)
+{
+ nvme_sync_io_queues(ctrl);
if (ctrl->admin_q)
blk_sync_queue(ctrl->admin_q);
}
/* fc_ctrl flags values - specified as bit positions */
#define ASSOC_ACTIVE 0
-#define FCCTRL_TERMIO 1
+#define ASSOC_FAILED 1
+#define FCCTRL_TERMIO 2
struct nvme_fc_ctrl {
spinlock_t lock;
u32 cnum;
bool ioq_live;
- atomic_t err_work_active;
u64 association_id;
struct nvmefc_ls_rcv_op *rcv_disconn;
struct blk_mq_tag_set tag_set;
struct delayed_work connect_work;
- struct work_struct err_work;
struct kref ref;
unsigned long flags;
nvme_fc_ctrl_put(ctrl);
}
+/*
+ * This routine is used by the transport when it needs to find active
+ * io on a queue that is to be terminated. The transport uses
+ * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
+ * this routine to kill them on a 1 by 1 basis.
+ *
+ * As FC allocates FC exchange for each io, the transport must contact
+ * the LLDD to terminate the exchange, thus releasing the FC exchange.
+ * After terminating the exchange the LLDD will call the transport's
+ * normal io done path for the request, but it will have an aborted
+ * status. The done path will return the io request back to the block
+ * layer with an error status.
+ */
+static bool
+nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+{
+ struct nvme_ctrl *nctrl = data;
+ struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+ struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
+
+ __nvme_fc_abort_op(ctrl, op);
+ return true;
+}
+
+/*
+ * This routine runs through all outstanding commands on the association
+ * and aborts them. This routine is typically be called by the
+ * delete_association routine. It is also called due to an error during
+ * reconnect. In that scenario, it is most likely a command that initializes
+ * the controller, including fabric Connect commands on io queues, that
+ * may have timed out or failed thus the io must be killed for the connect
+ * thread to see the error.
+ */
static void
-nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
+__nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
{
- int active;
+ /*
+ * If io queues are present, stop them and terminate all outstanding
+ * ios on them. As FC allocates FC exchange for each io, the
+ * transport must contact the LLDD to terminate the exchange,
+ * thus releasing the FC exchange. We use blk_mq_tagset_busy_itr()
+ * to tell us what io's are busy and invoke a transport routine
+ * to kill them with the LLDD. After terminating the exchange
+ * the LLDD will call the transport's normal io done path, but it
+ * will have an aborted status. The done path will return the
+ * io requests back to the block layer as part of normal completions
+ * (but with error status).
+ */
+ if (ctrl->ctrl.queue_count > 1) {
+ nvme_stop_queues(&ctrl->ctrl);
+ blk_mq_tagset_busy_iter(&ctrl->tag_set,
+ nvme_fc_terminate_exchange, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
+ if (start_queues)
+ nvme_start_queues(&ctrl->ctrl);
+ }
+
+ /*
+ * Other transports, which don't have link-level contexts bound
+ * to sqe's, would try to gracefully shutdown the controller by
+ * writing the registers for shutdown and polling (call
+ * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
+ * just aborted and we will wait on those contexts, and given
+ * there was no indication of how live the controlelr is on the
+ * link, don't send more io to create more contexts for the
+ * shutdown. Let the controller fail via keepalive failure if
+ * its still present.
+ */
/*
- * if an error (io timeout, etc) while (re)connecting,
- * it's an error on creating the new association.
- * Start the error recovery thread if it hasn't already
- * been started. It is expected there could be multiple
- * ios hitting this path before things are cleaned up.
+ * clean up the admin queue. Same thing as above.
+ */
+ blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
+ nvme_fc_terminate_exchange, &ctrl->ctrl);
+ blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
+}
+
+static void
+nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
+{
+ /*
+ * if an error (io timeout, etc) while (re)connecting, the remote
+ * port requested terminating of the association (disconnect_ls)
+ * or an error (timeout or abort) occurred on an io while creating
+ * the controller. Abort any ios on the association and let the
+ * create_association error path resolve things.
*/
if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
- active = atomic_xchg(&ctrl->err_work_active, 1);
- if (!active && !queue_work(nvme_fc_wq, &ctrl->err_work)) {
- atomic_set(&ctrl->err_work_active, 0);
- WARN_ON(1);
- }
+ __nvme_fc_abort_outstanding_ios(ctrl, true);
+ set_bit(ASSOC_FAILED, &ctrl->flags);
return;
}
nvme_fc_ctrl_put(ctrl);
}
-/*
- * This routine is used by the transport when it needs to find active
- * io on a queue that is to be terminated. The transport uses
- * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
- * this routine to kill them on a 1 by 1 basis.
- *
- * As FC allocates FC exchange for each io, the transport must contact
- * the LLDD to terminate the exchange, thus releasing the FC exchange.
- * After terminating the exchange the LLDD will call the transport's
- * normal io done path for the request, but it will have an aborted
- * status. The done path will return the io request back to the block
- * layer with an error status.
- */
-static bool
-nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
-{
- struct nvme_ctrl *nctrl = data;
- struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
-
- __nvme_fc_abort_op(ctrl, op);
- return true;
-}
-
static const struct blk_mq_ops nvme_fc_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
ctrl->cnum, ctrl->lport->localport.port_name,
ctrl->rport->remoteport.port_name, ctrl->ctrl.opts->subsysnqn);
+ clear_bit(ASSOC_FAILED, &ctrl->flags);
+
/*
* Create the admin queue
*/
*/
ret = nvme_enable_ctrl(&ctrl->ctrl);
- if (ret)
+ if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
goto out_disconnect_admin_queue;
ctrl->ctrl.max_segments = ctrl->lport->ops->max_sgl_segments;
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
ret = nvme_init_identify(&ctrl->ctrl);
- if (ret)
+ if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
goto out_disconnect_admin_queue;
/* sanity checks */
ret = nvme_fc_create_io_queues(ctrl);
else
ret = nvme_fc_recreate_io_queues(ctrl);
- if (ret)
- goto out_term_aen_ops;
}
+ if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+ goto out_term_aen_ops;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
}
-/*
- * This routine runs through all outstanding commands on the association
- * and aborts them. This routine is typically be called by the
- * delete_association routine. It is also called due to an error during
- * reconnect. In that scenario, it is most likely a command that initializes
- * the controller, including fabric Connect commands on io queues, that
- * may have timed out or failed thus the io must be killed for the connect
- * thread to see the error.
- */
-static void
-__nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
-{
- /*
- * If io queues are present, stop them and terminate all outstanding
- * ios on them. As FC allocates FC exchange for each io, the
- * transport must contact the LLDD to terminate the exchange,
- * thus releasing the FC exchange. We use blk_mq_tagset_busy_itr()
- * to tell us what io's are busy and invoke a transport routine
- * to kill them with the LLDD. After terminating the exchange
- * the LLDD will call the transport's normal io done path, but it
- * will have an aborted status. The done path will return the
- * io requests back to the block layer as part of normal completions
- * (but with error status).
- */
- if (ctrl->ctrl.queue_count > 1) {
- nvme_stop_queues(&ctrl->ctrl);
- blk_mq_tagset_busy_iter(&ctrl->tag_set,
- nvme_fc_terminate_exchange, &ctrl->ctrl);
- blk_mq_tagset_wait_completed_request(&ctrl->tag_set);
- if (start_queues)
- nvme_start_queues(&ctrl->ctrl);
- }
-
- /*
- * Other transports, which don't have link-level contexts bound
- * to sqe's, would try to gracefully shutdown the controller by
- * writing the registers for shutdown and polling (call
- * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
- * just aborted and we will wait on those contexts, and given
- * there was no indication of how live the controlelr is on the
- * link, don't send more io to create more contexts for the
- * shutdown. Let the controller fail via keepalive failure if
- * its still present.
- */
-
- /*
- * clean up the admin queue. Same thing as above.
- */
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
- blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
- nvme_fc_terminate_exchange, &ctrl->ctrl);
- blk_mq_tagset_wait_completed_request(&ctrl->admin_tag_set);
-}
-
/*
* This routine stops operation of the controller on the host side.
* On the host os stack side: Admin and IO queues are stopped,
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- cancel_work_sync(&ctrl->err_work);
cancel_delayed_work_sync(&ctrl->connect_work);
/*
* kill the association on the link side. this will block
}
static void
-__nvme_fc_terminate_io(struct nvme_fc_ctrl *ctrl)
+nvme_fc_reset_ctrl_work(struct work_struct *work)
{
- /*
- * if state is CONNECTING - the error occurred as part of a
- * reconnect attempt. Abort any ios on the association and
- * let the create_association error paths resolve things.
- */
- if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
- __nvme_fc_abort_outstanding_ios(ctrl, true);
- return;
- }
-
- /*
- * For any other state, kill the association. As this routine
- * is a common io abort routine for resetting and such, after
- * the association is terminated, ensure that the state is set
- * to CONNECTING.
- */
+ struct nvme_fc_ctrl *ctrl =
+ container_of(work, struct nvme_fc_ctrl, ctrl.reset_work);
- nvme_stop_keep_alive(&ctrl->ctrl);
+ nvme_stop_ctrl(&ctrl->ctrl);
/* will block will waiting for io to terminate */
nvme_fc_delete_association(ctrl);
- if (ctrl->ctrl.state != NVME_CTRL_CONNECTING &&
- !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
dev_err(ctrl->ctrl.device,
"NVME-FC{%d}: error_recovery: Couldn't change state "
"to CONNECTING\n", ctrl->cnum);
-}
-
-static void
-nvme_fc_reset_ctrl_work(struct work_struct *work)
-{
- struct nvme_fc_ctrl *ctrl =
- container_of(work, struct nvme_fc_ctrl, ctrl.reset_work);
- int ret;
- __nvme_fc_terminate_io(ctrl);
-
- nvme_stop_ctrl(&ctrl->ctrl);
-
- if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE)
- ret = nvme_fc_create_association(ctrl);
- else
- ret = -ENOTCONN;
-
- if (ret)
- nvme_fc_reconnect_or_delete(ctrl, ret);
- else
- dev_info(ctrl->ctrl.device,
- "NVME-FC{%d}: controller reset complete\n",
- ctrl->cnum);
+ if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) {
+ if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: failed to schedule connect "
+ "after reset\n", ctrl->cnum);
+ } else {
+ flush_delayed_work(&ctrl->connect_work);
+ }
+ } else {
+ nvme_fc_reconnect_or_delete(ctrl, -ENOTCONN);
+ }
}
-static void
-nvme_fc_connect_err_work(struct work_struct *work)
-{
- struct nvme_fc_ctrl *ctrl =
- container_of(work, struct nvme_fc_ctrl, err_work);
-
- __nvme_fc_terminate_io(ctrl);
-
- atomic_set(&ctrl->err_work_active, 0);
-
- /*
- * Rescheduling the connection after recovering
- * from the io error is left to the reconnect work
- * item, which is what should have stalled waiting on
- * the io that had the error that scheduled this work.
- */
-}
static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.name = "fc",
ctrl->dev = lport->dev;
ctrl->cnum = idx;
ctrl->ioq_live = false;
- atomic_set(&ctrl->err_work_active, 0);
init_waitqueue_head(&ctrl->ioabort_wait);
get_device(ctrl->dev);
INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work);
INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
- INIT_WORK(&ctrl->err_work, nvme_fc_connect_err_work);
spin_lock_init(&ctrl->lock);
/* io queue count */
fail_ctrl:
nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
cancel_work_sync(&ctrl->ctrl.reset_work);
- cancel_work_sync(&ctrl->err_work);
cancel_delayed_work_sync(&ctrl->connect_work);
ctrl->ctrl.opts = NULL;
#endif
};
-struct nvme_cel {
- struct list_head entry;
- struct nvme_effects_log log;
- u8 csi;
-};
-
struct nvme_ctrl {
bool comp_seen;
enum nvme_ctrl_state state;
void nvme_start_queues(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_sync_queues(struct nvme_ctrl *ctrl);
+void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
void nvme_unfreeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze(struct nvme_ctrl *ctrl);
int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
u32 q_depth;
u16 cq_vector;
u16 sq_tail;
+ u16 last_sq_tail;
u16 cq_head;
u16 qid;
u8 cq_phase;
nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)];
}
+static void nvme_dbbuf_free(struct nvme_queue *nvmeq)
+{
+ if (!nvmeq->qid)
+ return;
+
+ nvmeq->dbbuf_sq_db = NULL;
+ nvmeq->dbbuf_cq_db = NULL;
+ nvmeq->dbbuf_sq_ei = NULL;
+ nvmeq->dbbuf_cq_ei = NULL;
+}
+
static void nvme_dbbuf_set(struct nvme_dev *dev)
{
struct nvme_command c;
+ unsigned int i;
if (!dev->dbbuf_dbs)
return;
dev_warn(dev->ctrl.device, "unable to set dbbuf\n");
/* Free memory and continue on */
nvme_dbbuf_dma_free(dev);
+
+ for (i = 1; i <= dev->online_queues; i++)
+ nvme_dbbuf_free(&dev->queues[i]);
}
}
return 0;
}
-static inline void nvme_write_sq_db(struct nvme_queue *nvmeq)
+/*
+ * Write sq tail if we are asked to, or if the next command would wrap.
+ */
+static inline void nvme_write_sq_db(struct nvme_queue *nvmeq, bool write_sq)
{
+ if (!write_sq) {
+ u16 next_tail = nvmeq->sq_tail + 1;
+
+ if (next_tail == nvmeq->q_depth)
+ next_tail = 0;
+ if (next_tail != nvmeq->last_sq_tail)
+ return;
+ }
+
if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
writel(nvmeq->sq_tail, nvmeq->q_db);
+ nvmeq->last_sq_tail = nvmeq->sq_tail;
}
/**
cmd, sizeof(*cmd));
if (++nvmeq->sq_tail == nvmeq->q_depth)
nvmeq->sq_tail = 0;
- if (write_sq)
- nvme_write_sq_db(nvmeq);
+ nvme_write_sq_db(nvmeq, write_sq);
spin_unlock(&nvmeq->sq_lock);
}
struct nvme_queue *nvmeq = hctx->driver_data;
spin_lock(&nvmeq->sq_lock);
- nvme_write_sq_db(nvmeq);
+ if (nvmeq->sq_tail != nvmeq->last_sq_tail)
+ nvme_write_sq_db(nvmeq, true);
spin_unlock(&nvmeq->sq_lock);
}
struct nvme_dev *dev = nvmeq->dev;
nvmeq->sq_tail = 0;
+ nvmeq->last_sq_tail = 0;
nvmeq->cq_head = 0;
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
struct sockaddr_storage src_addr;
struct nvme_ctrl ctrl;
- struct mutex teardown_lock;
bool use_inline_data;
u32 io_queues[HCTX_MAX_TYPES];
};
static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- mutex_lock(&ctrl->teardown_lock);
blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ blk_sync_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
if (ctrl->ctrl.admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset,
if (remove)
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
nvme_rdma_destroy_admin_queue(ctrl, remove);
- mutex_unlock(&ctrl->teardown_lock);
}
static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- mutex_lock(&ctrl->teardown_lock);
if (ctrl->ctrl.queue_count > 1) {
nvme_start_freeze(&ctrl->ctrl);
nvme_stop_queues(&ctrl->ctrl);
+ nvme_sync_io_queues(&ctrl->ctrl);
nvme_rdma_stop_io_queues(ctrl);
if (ctrl->ctrl.tagset) {
blk_mq_tagset_busy_iter(ctrl->ctrl.tagset,
nvme_start_queues(&ctrl->ctrl);
nvme_rdma_destroy_io_queues(ctrl, remove);
}
- mutex_unlock(&ctrl->teardown_lock);
}
static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
return;
}
+ /* sanity checking for received data length */
+ if (unlikely(wc->byte_len < len)) {
+ dev_err(queue->ctrl->ctrl.device,
+ "Unexpected nvme completion length(%d)\n", wc->byte_len);
+ nvme_rdma_error_recovery(queue->ctrl);
+ return;
+ }
+
ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
/*
* AEN requests are special as they don't time out and can
priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
}
- ret = rdma_connect(queue->cm_id, ¶m);
+ ret = rdma_connect_locked(queue->cm_id, ¶m);
if (ret) {
dev_err(ctrl->ctrl.device,
- "rdma_connect failed (%d).\n", ret);
+ "rdma_connect_locked failed (%d).\n", ret);
goto out_destroy_queue_ib;
}
{
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_rdma_queue *queue = req->queue;
- struct nvme_rdma_ctrl *ctrl = queue->ctrl;
- /* fence other contexts that may complete the command */
- mutex_lock(&ctrl->teardown_lock);
nvme_rdma_stop_queue(queue);
- if (!blk_mq_request_completed(rq)) {
+ if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
blk_mq_complete_request(rq);
}
- mutex_unlock(&ctrl->teardown_lock);
}
static enum blk_eh_timer_return
return ERR_PTR(-ENOMEM);
ctrl->ctrl.opts = opts;
INIT_LIST_HEAD(&ctrl->list);
- mutex_init(&ctrl->teardown_lock);
if (!(opts->mask & NVMF_OPT_TRSVCID)) {
opts->trsvcid =
struct sockaddr_storage src_addr;
struct nvme_ctrl ctrl;
- struct mutex teardown_lock;
struct work_struct err_work;
struct delayed_work connect_work;
struct nvme_tcp_request async_req;
static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
bool remove)
{
- mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
blk_mq_quiesce_queue(ctrl->admin_q);
+ blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
if (ctrl->admin_tagset) {
blk_mq_tagset_busy_iter(ctrl->admin_tagset,
if (remove)
blk_mq_unquiesce_queue(ctrl->admin_q);
nvme_tcp_destroy_admin_queue(ctrl, remove);
- mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
}
static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
bool remove)
{
- mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
if (ctrl->queue_count <= 1)
- goto out;
+ return;
blk_mq_quiesce_queue(ctrl->admin_q);
nvme_start_freeze(ctrl);
nvme_stop_queues(ctrl);
+ nvme_sync_io_queues(ctrl);
nvme_tcp_stop_io_queues(ctrl);
if (ctrl->tagset) {
blk_mq_tagset_busy_iter(ctrl->tagset,
if (remove)
nvme_start_queues(ctrl);
nvme_tcp_destroy_io_queues(ctrl, remove);
-out:
- mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
}
static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
struct nvme_ctrl *ctrl = &req->queue->ctrl->ctrl;
- /* fence other contexts that may complete the command */
- mutex_lock(&to_tcp_ctrl(ctrl)->teardown_lock);
nvme_tcp_stop_queue(ctrl, nvme_tcp_queue_id(req->queue));
- if (!blk_mq_request_completed(rq)) {
+ if (blk_mq_request_started(rq) && !blk_mq_request_completed(rq)) {
nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
blk_mq_complete_request(rq);
}
- mutex_unlock(&to_tcp_ctrl(ctrl)->teardown_lock);
}
static enum blk_eh_timer_return
nvme_tcp_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work);
INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work);
- mutex_init(&ctrl->teardown_lock);
if (!(opts->mask & NVMF_OPT_TRSVCID)) {
opts->trsvcid =
req->error_loc = NVMET_NO_ERROR_LOC;
req->error_slba = 0;
- trace_nvmet_req_init(req, req->cmd);
-
/* no support for fused commands yet */
if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
req->error_loc = offsetof(struct nvme_common_command, flags);
if (status)
goto fail;
+ trace_nvmet_req_init(req, req->cmd);
+
if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
goto fail;
return req->sq->ctrl;
}
-static inline void __assign_disk_name(char *name, struct nvmet_req *req,
- bool init)
+static inline void __assign_req_name(char *name, struct nvmet_req *req)
{
- struct nvmet_ctrl *ctrl = nvmet_req_to_ctrl(req);
- struct nvmet_ns *ns;
-
- if ((init && req->sq->qid) || (!init && req->cq->qid)) {
- ns = nvmet_find_namespace(ctrl, req->cmd->rw.nsid);
- strncpy(name, ns->device_path, DISK_NAME_LEN);
- return;
- }
-
- memset(name, 0, DISK_NAME_LEN);
+ if (req->ns)
+ strncpy(name, req->ns->device_path, DISK_NAME_LEN);
+ else
+ memset(name, 0, DISK_NAME_LEN);
}
#endif
TP_fast_assign(
__entry->cmd = cmd;
__entry->ctrl = nvmet_req_to_ctrl(req);
- __assign_disk_name(__entry->disk, req, true);
+ __assign_req_name(__entry->disk, req);
__entry->qid = req->sq->qid;
__entry->cid = cmd->common.command_id;
__entry->opcode = cmd->common.opcode;
__entry->cid = req->cqe->command_id;
__entry->result = le64_to_cpu(req->cqe->result.u64);
__entry->status = le16_to_cpu(req->cqe->status) >> 1;
- __assign_disk_name(__entry->disk, req, false);
+ __assign_req_name(__entry->disk, req);
),
TP_printk("nvmet%s: %sqid=%d, cmdid=%u, res=%#llx, status=%#x",
__print_ctrl_name(__entry->ctrl),
*/
bool of_dma_is_coherent(struct device_node *np)
{
- struct device_node *node = of_node_get(np);
+ struct device_node *node;
if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
return true;
+ node = of_node_get(np);
+
while (node) {
if (of_property_read_bool(node, "dma-coherent")) {
of_node_put(node);
{
const struct iommu_ops *iommu;
const struct bus_dma_region *map = NULL;
- dma_addr_t dma_start = 0;
+ u64 dma_start = 0;
u64 mask, end, size = 0;
bool coherent;
int ret;
return ret == -ENODEV ? 0 : ret;
} else {
const struct bus_dma_region *r = map;
- dma_addr_t dma_end = 0;
+ u64 dma_end = 0;
/* Determine the overall bounds of all DMA regions */
- for (dma_start = ~(dma_addr_t)0; r->size; r++) {
+ for (dma_start = ~0; r->size; r++) {
/* Take lower and upper limits */
if (r->dma_start < dma_start)
dma_start = r->dma_start;
if (ra->base > rb->base)
return 1;
+ /*
+ * Put the dynamic allocations (address == 0, size == 0) before static
+ * allocations at address 0x0 so that overlap detection works
+ * correctly.
+ */
+ if (ra->size < rb->size)
+ return -1;
+ if (ra->size > rb->size)
+ return 1;
+
return 0;
}
this = &reserved_mem[i];
next = &reserved_mem[i + 1];
- if (!(this->base && next->base))
- continue;
+
if (this->base + this->size > next->base) {
phys_addr_t this_end, next_end;
struct opp_device *opp_dev, *temp;
int i;
+ /* Drop the lock as soon as we can */
+ list_del(&opp_table->node);
+ mutex_unlock(&opp_table_lock);
+
_of_clear_opp_table(opp_table);
/* Release clk */
mutex_destroy(&opp_table->genpd_virt_dev_lock);
mutex_destroy(&opp_table->lock);
- list_del(&opp_table->node);
kfree(opp_table);
-
- mutex_unlock(&opp_table_lock);
}
void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
return ERR_PTR(-EINVAL);
opp_table = dev_pm_opp_get_opp_table(dev);
- if (!IS_ERR(opp_table))
+ if (IS_ERR(opp_table))
return opp_table;
/* This should be called before OPPs are initialized */
nr -= 2;
}
+ return 0;
+
remove_static_opp:
_opp_remove_all_static(opp_table);
* ATU, so we should not program the ATU here.
*/
if (pp->bridge->child_ops == &dw_child_pcie_ops) {
- struct resource_entry *entry =
- resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM);
+ struct resource_entry *tmp, *entry = NULL;
+
+ /* Get last memory resource entry */
+ resource_list_for_each_entry(tmp, &pp->bridge->windows)
+ if (resource_type(tmp->res) == IORESOURCE_MEM)
+ entry = tmp;
dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0,
PCIE_ATU_TYPE_MEM, entry->res->start,
}
/*
- * We can't use devm_of_pci_get_host_bridge_resources() because we
- * need to parse our special DT properties encoding the MEM and IO
- * apertures.
+ * devm_of_pci_get_host_bridge_resources() only sets up translateable resources,
+ * so we need extra resource setup parsing our special DT properties encoding
+ * the MEM and IO apertures.
*/
static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
{
struct device *dev = &pcie->pdev->dev;
- struct device_node *np = dev->of_node;
struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
int ret;
- /* Get the bus range */
- ret = of_pci_parse_bus_range(np, &pcie->busn);
- if (ret) {
- dev_err(dev, "failed to parse bus-range property: %d\n", ret);
- return ret;
- }
- pci_add_resource(&bridge->windows, &pcie->busn);
-
/* Get the PCIe memory aperture */
mvebu_mbus_get_pcie_mem_aperture(&pcie->mem);
if (resource_size(&pcie->mem) == 0) {
pcie->mem.name = "PCI MEM";
pci_add_resource(&bridge->windows, &pcie->mem);
+ ret = devm_request_resource(dev, &iomem_resource, &pcie->mem);
+ if (ret)
+ return ret;
/* Get the PCIe IO aperture */
mvebu_mbus_get_pcie_io_aperture(&pcie->io);
pcie->realio.name = "PCI I/O";
pci_add_resource(&bridge->windows, &pcie->realio);
+ ret = devm_request_resource(dev, &ioport_resource, &pcie->realio);
+ if (ret)
+ return ret;
}
- return devm_request_pci_bus_resources(dev, &bridge->windows);
+ return 0;
}
/*
{
dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
- if (dev->acs_cap)
- pci_enable_acs(dev);
+ /*
+ * Attempt to enable ACS regardless of capability because some Root
+ * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have
+ * the standard ACS capability but still support ACS via those
+ * quirks.
+ */
+ pci_enable_acs(dev);
}
/**
reg |= params->mode << USB_PHY_UTMI_CTL_1_PHY_MODE_SHIFT;
brcm_usb_writel(reg, usb_phy + USB_PHY_UTMI_CTL_1);
- /* Fix the incorrect default */
- reg = brcm_usb_readl(ctrl + USB_CTRL_SETUP);
- reg &= ~USB_CTRL_SETUP_tca_drv_sel_MASK;
- brcm_usb_writel(reg, ctrl + USB_CTRL_SETUP);
-
usb_init_common(params);
/*
#
config PHY_INTEL_KEEMBAY_EMMC
tristate "Intel Keem Bay EMMC PHY driver"
- depends on (OF && ARM64) || COMPILE_TEST
+ depends on ARCH_KEEMBAY || COMPILE_TEST
depends on HAS_IOMEM
select GENERIC_PHY
select REGMAP_MMIO
it supports multiple usb2.0, usb3.0 ports, PCIe and
SATA, and meanwhile supports two version T-PHY which have
different banks layout, the T-PHY with shared banks between
- multi-ports is first version, otherwise is second veriosn,
+ multi-ports is first version, otherwise is second version,
so you can easily distinguish them by banks layout.
config PHY_MTK_UFS
error = devm_request_threaded_irq(ddata->dev, irq, NULL,
cpcap_phy_irq_thread,
- IRQF_SHARED,
+ IRQF_SHARED |
+ IRQF_ONESHOT,
name, ddata);
if (error) {
dev_err(ddata->dev, "could not get irq %s: %i\n",
config PHY_QCOM_USB_HS_28NM
tristate "Qualcomm 28nm High-Speed PHY"
- depends on ARCH_QCOM || COMPILE_TEST
+ depends on OF && (ARCH_QCOM || COMPILE_TEST)
depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in
select GENERIC_PHY
help
config PHY_QCOM_USB_SS
tristate "Qualcomm USB Super-Speed PHY driver"
- depends on ARCH_QCOM || COMPILE_TEST
+ depends on OF && (ARCH_QCOM || COMPILE_TEST)
depends on EXTCON || !EXTCON # if EXTCON=m, this cannot be built-in
select GENERIC_PHY
help
struct phy_provider *phy_provider;
void __iomem *serdes;
void __iomem *usb_serdes;
- void __iomem *dp_serdes;
+ void __iomem *dp_serdes = NULL;
const struct qmp_phy_combo_cfg *combo_cfg = NULL;
const struct qmp_phy_cfg *cfg = NULL;
const struct qmp_phy_cfg *usb_cfg = NULL;
reset:
reset_control_assert(padctl->rst);
remove:
+ platform_set_drvdata(pdev, NULL);
soc->ops->remove(padctl);
return err;
}
static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr)
{
/*
- * The signal type is GPIO if the signal name has "GPIO" as a prefix.
+ * The signal type is GPIO if the signal name has "GPI" as a prefix.
* strncmp (rather than strcmp) is used to implement the prefix
* requirement.
*
- * expr->signal might look like "GPIOT3" in the GPIO case.
+ * expr->signal might look like "GPIOB1" in the GPIO case.
+ * expr->signal might look like "GPIT0" in the GPI case.
*/
- return strncmp(expr->signal, "GPIO", 4) == 0;
+ return strncmp(expr->signal, "GPI", 3) == 0;
}
static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs)
#define PADCFG1_TERM_UP BIT(13)
#define PADCFG1_TERM_SHIFT 10
#define PADCFG1_TERM_MASK GENMASK(12, 10)
-#define PADCFG1_TERM_20K 4
-#define PADCFG1_TERM_2K 3
-#define PADCFG1_TERM_5K 2
-#define PADCFG1_TERM_1K 1
+#define PADCFG1_TERM_20K BIT(2)
+#define PADCFG1_TERM_5K BIT(1)
+#define PADCFG1_TERM_1K BIT(0)
+#define PADCFG1_TERM_833 (BIT(1) | BIT(0))
#define PADCFG2 0x008
#define PADCFG2_DEBEN BIT(0)
return -EINVAL;
switch (term) {
+ case PADCFG1_TERM_833:
+ *arg = 833;
+ break;
case PADCFG1_TERM_1K:
*arg = 1000;
break;
- case PADCFG1_TERM_2K:
- *arg = 2000;
- break;
case PADCFG1_TERM_5K:
*arg = 5000;
break;
return -EINVAL;
switch (term) {
+ case PADCFG1_TERM_833:
+ if (!(community->features & PINCTRL_FEATURE_1K_PD))
+ return -EINVAL;
+ *arg = 833;
+ break;
case PADCFG1_TERM_1K:
if (!(community->features & PINCTRL_FEATURE_1K_PD))
return -EINVAL;
value |= PADCFG1_TERM_UP;
+ /* Set default strength value in case none is given */
+ if (arg == 1)
+ arg = 5000;
+
switch (arg) {
case 20000:
value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT;
case 5000:
value |= PADCFG1_TERM_5K << PADCFG1_TERM_SHIFT;
break;
- case 2000:
- value |= PADCFG1_TERM_2K << PADCFG1_TERM_SHIFT;
- break;
case 1000:
value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT;
break;
+ case 833:
+ value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT;
+ break;
default:
ret = -EINVAL;
}
case PIN_CONFIG_BIAS_PULL_DOWN:
value &= ~(PADCFG1_TERM_UP | PADCFG1_TERM_MASK);
+ /* Set default strength value in case none is given */
+ if (arg == 1)
+ arg = 5000;
+
switch (arg) {
case 20000:
value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT;
}
value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT;
break;
+ case 833:
+ if (!(community->features & PINCTRL_FEATURE_1K_PD)) {
+ ret = -EINVAL;
+ break;
+ }
+ value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT;
+ break;
default:
ret = -EINVAL;
}
pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
} else if (debounce < 250000) {
- time = debounce / 15600;
+ time = debounce / 15625;
pin_reg |= time & DB_TMR_OUT_MASK;
pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg |= BIT(DB_TMR_LARGE_OFF);
pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg |= BIT(DB_TMR_LARGE_OFF);
} else {
- pin_reg &= ~DB_CNTRl_MASK;
+ pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
ret = -EINVAL;
}
} else {
pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF);
pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
pin_reg &= ~DB_TMR_OUT_MASK;
- pin_reg &= ~DB_CNTRl_MASK;
+ pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF);
}
writel(pin_reg, gpio_dev->base + offset * 4);
raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
static int jz4770_uart3_hwflow_pins[] = { 0x88, 0x89, };
static int jz4770_ssi0_dt_a_pins[] = { 0x15, };
static int jz4770_ssi0_dt_b_pins[] = { 0x35, };
-static int jz4770_ssi0_dt_d_pins[] = { 0x55, };
-static int jz4770_ssi0_dt_e_pins[] = { 0x71, };
+static int jz4770_ssi0_dt_d_pins[] = { 0x75, };
+static int jz4770_ssi0_dt_e_pins[] = { 0x91, };
static int jz4770_ssi0_dr_a_pins[] = { 0x14, };
static int jz4770_ssi0_dr_b_pins[] = { 0x34, };
-static int jz4770_ssi0_dr_d_pins[] = { 0x54, };
-static int jz4770_ssi0_dr_e_pins[] = { 0x6e, };
+static int jz4770_ssi0_dr_d_pins[] = { 0x74, };
+static int jz4770_ssi0_dr_e_pins[] = { 0x8e, };
static int jz4770_ssi0_clk_a_pins[] = { 0x12, };
static int jz4770_ssi0_clk_b_pins[] = { 0x3c, };
-static int jz4770_ssi0_clk_d_pins[] = { 0x58, };
-static int jz4770_ssi0_clk_e_pins[] = { 0x6f, };
+static int jz4770_ssi0_clk_d_pins[] = { 0x78, };
+static int jz4770_ssi0_clk_e_pins[] = { 0x8f, };
static int jz4770_ssi0_gpc_b_pins[] = { 0x3e, };
-static int jz4770_ssi0_gpc_d_pins[] = { 0x56, };
-static int jz4770_ssi0_gpc_e_pins[] = { 0x73, };
+static int jz4770_ssi0_gpc_d_pins[] = { 0x76, };
+static int jz4770_ssi0_gpc_e_pins[] = { 0x93, };
static int jz4770_ssi0_ce0_a_pins[] = { 0x13, };
static int jz4770_ssi0_ce0_b_pins[] = { 0x3d, };
-static int jz4770_ssi0_ce0_d_pins[] = { 0x59, };
-static int jz4770_ssi0_ce0_e_pins[] = { 0x70, };
+static int jz4770_ssi0_ce0_d_pins[] = { 0x79, };
+static int jz4770_ssi0_ce0_e_pins[] = { 0x90, };
static int jz4770_ssi0_ce1_b_pins[] = { 0x3f, };
-static int jz4770_ssi0_ce1_d_pins[] = { 0x57, };
-static int jz4770_ssi0_ce1_e_pins[] = { 0x72, };
+static int jz4770_ssi0_ce1_d_pins[] = { 0x77, };
+static int jz4770_ssi0_ce1_e_pins[] = { 0x92, };
static int jz4770_ssi1_dt_b_pins[] = { 0x35, };
-static int jz4770_ssi1_dt_d_pins[] = { 0x55, };
-static int jz4770_ssi1_dt_e_pins[] = { 0x71, };
+static int jz4770_ssi1_dt_d_pins[] = { 0x75, };
+static int jz4770_ssi1_dt_e_pins[] = { 0x91, };
static int jz4770_ssi1_dr_b_pins[] = { 0x34, };
-static int jz4770_ssi1_dr_d_pins[] = { 0x54, };
-static int jz4770_ssi1_dr_e_pins[] = { 0x6e, };
+static int jz4770_ssi1_dr_d_pins[] = { 0x74, };
+static int jz4770_ssi1_dr_e_pins[] = { 0x8e, };
static int jz4770_ssi1_clk_b_pins[] = { 0x3c, };
-static int jz4770_ssi1_clk_d_pins[] = { 0x58, };
-static int jz4770_ssi1_clk_e_pins[] = { 0x6f, };
+static int jz4770_ssi1_clk_d_pins[] = { 0x78, };
+static int jz4770_ssi1_clk_e_pins[] = { 0x8f, };
static int jz4770_ssi1_gpc_b_pins[] = { 0x3e, };
-static int jz4770_ssi1_gpc_d_pins[] = { 0x56, };
-static int jz4770_ssi1_gpc_e_pins[] = { 0x73, };
+static int jz4770_ssi1_gpc_d_pins[] = { 0x76, };
+static int jz4770_ssi1_gpc_e_pins[] = { 0x93, };
static int jz4770_ssi1_ce0_b_pins[] = { 0x3d, };
-static int jz4770_ssi1_ce0_d_pins[] = { 0x59, };
-static int jz4770_ssi1_ce0_e_pins[] = { 0x70, };
+static int jz4770_ssi1_ce0_d_pins[] = { 0x79, };
+static int jz4770_ssi1_ce0_e_pins[] = { 0x90, };
static int jz4770_ssi1_ce1_b_pins[] = { 0x3f, };
-static int jz4770_ssi1_ce1_d_pins[] = { 0x57, };
-static int jz4770_ssi1_ce1_e_pins[] = { 0x72, };
+static int jz4770_ssi1_ce1_d_pins[] = { 0x77, };
+static int jz4770_ssi1_ce1_e_pins[] = { 0x92, };
static int jz4770_mmc0_1bit_a_pins[] = { 0x12, 0x13, 0x14, };
static int jz4770_mmc0_4bit_a_pins[] = { 0x15, 0x16, 0x17, };
static int jz4770_mmc0_1bit_e_pins[] = { 0x9c, 0x9d, 0x94, };
static int jz4780_ssi0_dt_a_21_pins[] = { 0x15, };
static int jz4780_ssi0_dt_a_28_pins[] = { 0x1c, };
static int jz4780_ssi0_dt_b_pins[] = { 0x3d, };
-static int jz4780_ssi0_dt_d_pins[] = { 0x59, };
+static int jz4780_ssi0_dt_d_pins[] = { 0x79, };
static int jz4780_ssi0_dr_a_20_pins[] = { 0x14, };
static int jz4780_ssi0_dr_a_27_pins[] = { 0x1b, };
static int jz4780_ssi0_dr_b_pins[] = { 0x34, };
-static int jz4780_ssi0_dr_d_pins[] = { 0x54, };
+static int jz4780_ssi0_dr_d_pins[] = { 0x74, };
static int jz4780_ssi0_clk_a_pins[] = { 0x12, };
static int jz4780_ssi0_clk_b_5_pins[] = { 0x25, };
static int jz4780_ssi0_clk_b_28_pins[] = { 0x3c, };
-static int jz4780_ssi0_clk_d_pins[] = { 0x58, };
+static int jz4780_ssi0_clk_d_pins[] = { 0x78, };
static int jz4780_ssi0_gpc_b_pins[] = { 0x3e, };
-static int jz4780_ssi0_gpc_d_pins[] = { 0x56, };
+static int jz4780_ssi0_gpc_d_pins[] = { 0x76, };
static int jz4780_ssi0_ce0_a_23_pins[] = { 0x17, };
static int jz4780_ssi0_ce0_a_25_pins[] = { 0x19, };
static int jz4780_ssi0_ce0_b_pins[] = { 0x3f, };
-static int jz4780_ssi0_ce0_d_pins[] = { 0x57, };
+static int jz4780_ssi0_ce0_d_pins[] = { 0x77, };
static int jz4780_ssi0_ce1_b_pins[] = { 0x35, };
-static int jz4780_ssi0_ce1_d_pins[] = { 0x55, };
+static int jz4780_ssi0_ce1_d_pins[] = { 0x75, };
static int jz4780_ssi1_dt_b_pins[] = { 0x3d, };
-static int jz4780_ssi1_dt_d_pins[] = { 0x59, };
+static int jz4780_ssi1_dt_d_pins[] = { 0x79, };
static int jz4780_ssi1_dr_b_pins[] = { 0x34, };
-static int jz4780_ssi1_dr_d_pins[] = { 0x54, };
+static int jz4780_ssi1_dr_d_pins[] = { 0x74, };
static int jz4780_ssi1_clk_b_pins[] = { 0x3c, };
-static int jz4780_ssi1_clk_d_pins[] = { 0x58, };
+static int jz4780_ssi1_clk_d_pins[] = { 0x78, };
static int jz4780_ssi1_gpc_b_pins[] = { 0x3e, };
-static int jz4780_ssi1_gpc_d_pins[] = { 0x56, };
+static int jz4780_ssi1_gpc_d_pins[] = { 0x76, };
static int jz4780_ssi1_ce0_b_pins[] = { 0x3f, };
-static int jz4780_ssi1_ce0_d_pins[] = { 0x57, };
+static int jz4780_ssi1_ce0_d_pins[] = { 0x77, };
static int jz4780_ssi1_ce1_b_pins[] = { 0x35, };
-static int jz4780_ssi1_ce1_d_pins[] = { 0x55, };
+static int jz4780_ssi1_ce1_d_pins[] = { 0x75, };
static int jz4780_mmc0_8bit_a_pins[] = { 0x04, 0x05, 0x06, 0x07, 0x18, };
static int jz4780_i2c3_pins[] = { 0x6a, 0x6b, };
static int jz4780_i2c4_e_pins[] = { 0x8c, 0x8d, };
return -EINVAL;
}
- copy = devm_kmemdup(dev, &config, sizeof(config), GFP_KERNEL);
+ copy = devm_kmemdup(dev, config, sizeof(*config), GFP_KERNEL);
if (!copy)
return -ENOMEM;
copy->name = name;
mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy);
+ if (IS_ERR(mcp->regmap))
+ dev_err(dev, "regmap init failed for %s\n", mcp->chip.label);
return PTR_ERR_OR_ZERO(mcp->regmap);
}
if (!bank->domain)
return -ENXIO;
+ clk_enable(bank->clk);
virq = irq_create_mapping(bank->domain, offset);
+ clk_disable(bank->clk);
return (virq) ? : -ENXIO;
}
irq = __ffs(pend);
pend &= ~BIT(irq);
- virq = irq_linear_revmap(bank->domain, irq);
+ virq = irq_find_mapping(bank->domain, irq);
if (!virq) {
dev_err(bank->drvdata->dev, "unmapped irq %d\n", irq);
unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
struct irq_chip_generic *gc;
int ret;
- int i, j;
+ int i;
for (i = 0; i < ctrl->nr_banks; ++i, ++bank) {
if (!bank->valid) {
ret = irq_alloc_domain_generic_chips(bank->domain, 32, 1,
"rockchip_gpio_irq", handle_level_irq,
- clr, 0, IRQ_GC_INIT_MASK_CACHE);
+ clr, 0, 0);
if (ret) {
dev_err(&pdev->dev, "could not alloc generic chips for bank %s\n",
bank->name);
continue;
}
- /*
- * Linux assumes that all interrupts start out disabled/masked.
- * Our driver only uses the concept of masked and always keeps
- * things enabled, so for us that's all masked and all enabled.
- */
- writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK);
- writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN);
-
gc = irq_get_domain_generic_chip(bank->domain, 0);
gc->reg_base = bank->reg_base;
gc->private = bank;
gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type;
gc->wake_enabled = IRQ_MSK(bank->nr_pins);
+ /*
+ * Linux assumes that all interrupts start out disabled/masked.
+ * Our driver only uses the concept of masked and always keeps
+ * things enabled, so for us that's all masked and all enabled.
+ */
+ writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK);
+ writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN);
+ gc->mask_cache = 0xffffffff;
+
irq_set_chained_handler_and_data(bank->irq,
rockchip_irq_demux, bank);
-
- /* map the gpio irqs here, when the clock is still running */
- for (j = 0 ; j < 32 ; j++)
- irq_create_mapping(bank->domain, j);
-
clk_disable(bank->clk);
}
static void msm_gpio_irq_enable(struct irq_data *d)
{
- /*
- * Clear the interrupt that may be pending before we enable
- * the line.
- * This is especially a problem with the GPIOs routed to the
- * PDC. These GPIOs are direct-connect interrupts to the GIC.
- * Disabling the interrupt line at the PDC does not prevent
- * the interrupt from being latched at the GIC. The state at
- * GIC needs to be cleared before enabling.
- */
- if (d->parent_data) {
- irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+
+ if (d->parent_data)
irq_chip_enable_parent(d);
- }
- msm_gpio_irq_clear_unmask(d, true);
+ if (!test_bit(d->hwirq, pctrl->skip_wake_irqs))
+ msm_gpio_irq_clear_unmask(d, true);
}
static void msm_gpio_irq_disable(struct irq_data *d)
ret = -EINVAL;
goto out;
}
+
+ /*
+ * Clear the interrupt that may be pending before we enable
+ * the line.
+ * This is especially a problem with the GPIOs routed to the
+ * PDC. These GPIOs are direct-connect interrupts to the GIC.
+ * Disabling the interrupt line at the PDC does not prevent
+ * the interrupt from being latched at the GIC. The state at
+ * GIC needs to be cleared before enabling.
+ */
+ if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs))
+ irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0);
+
return 0;
out:
module_put(gc->owner);
[183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0),
};
+static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = {
+ { 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 },
+ { 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 },
+ { 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 },
+ { 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 },
+ { 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 },
+ { 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 },
+ { 84, 98 }, { 86, 99 }, { 87, 100 }, { 88, 101 }, { 89, 102 },
+ { 92, 103 }, { 93, 104 }, { 100, 53 }, { 103, 47 }, { 104, 48 },
+ { 108, 49 }, { 109, 94 }, { 110, 95 }, { 111, 96 }, { 112, 55 },
+ { 113, 56 }, { 118, 50 }, { 121, 51 }, { 122, 57 }, { 123, 58 },
+ { 124, 45 }, { 126, 59 }, { 128, 76 }, { 129, 86 }, { 132, 93 },
+ { 133, 65 }, { 134, 66 }, { 136, 62 }, { 137, 63 }, { 138, 64 },
+ { 142, 60 }, { 143, 61 }
+};
+
static const struct msm_pinctrl_soc_data sm8250_pinctrl = {
.pins = sm8250_pins,
.npins = ARRAY_SIZE(sm8250_pins),
.ngpios = 181,
.tiles = sm8250_tiles,
.ntiles = ARRAY_SIZE(sm8250_tiles),
+ .wakeirq_map = sm8250_pdc_map,
+ .nwakeirq_map = ARRAY_SIZE(sm8250_pdc_map),
};
static int sm8250_pinctrl_probe(struct platform_device *pdev)
{KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} }, /* Display Switch */
{KE_IGNORE, 0x81, {KEY_SLEEP} },
{KE_KEY, 0x82, {KEY_TOUCHPAD_TOGGLE} }, /* Touch Pad Toggle */
+ {KE_IGNORE, 0x84, {KEY_KBDILLUMTOGGLE} }, /* Automatic Keyboard background light toggle */
{KE_KEY, KEY_TOUCHPAD_ON, {KEY_TOUCHPAD_ON} },
{KE_KEY, KEY_TOUCHPAD_OFF, {KEY_TOUCHPAD_OFF} },
{KE_IGNORE, 0x83, {KEY_TOUCHPAD_TOGGLE} },
DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"),
},
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion 13 x360 PC"),
+ },
+ },
{} /* Array terminator */
};
in_tablet_mode = hotkey_gmms_get_tablet_mode(res,
&has_tablet_mode);
- if (has_tablet_mode)
+ /*
+ * The Yoga 11e series has 2 accelerometers described by a
+ * BOSC0200 ACPI node. This setup relies on a Windows service
+ * which calls special ACPI methods on this node to report
+ * the laptop/tent/tablet mode to the EC. The bmc150 iio driver
+ * does not support this, so skip the hotkey on these models.
+ */
+ if (has_tablet_mode && !acpi_dev_present("BOSC0200", "1", -1))
tp_features.hotkey_tablet = TP_HOTKEY_TABLET_USES_GMMS;
type = "GMMS";
} else if (acpi_evalf(hkey_handle, &res, "MHKG", "qd")) {
pr_err("error while attempting to reset the event firmware interface\n");
tpacpi_send_radiosw_update();
+ tpacpi_input_send_tabletsw();
hotkey_tablet_mode_notify_change();
hotkey_wakeup_reason_notify_change();
hotkey_wakeup_hotunplug_complete_notify_change();
TPACPI_Q_LNV3('N', '2', 'C', TPACPI_FAN_2CTL), /* P52 / P72 */
TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */
TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */
+ TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */
+ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */
};
static int __init fan_init(struct ibm_init_struct *iibm)
TPACPI_Q_LNV3('R', '0', 'B', true), /* Thinkpad 11e gen 3 */
TPACPI_Q_LNV3('R', '0', 'C', true), /* Thinkpad 13 */
TPACPI_Q_LNV3('R', '0', 'J', true), /* Thinkpad 13 gen 2 */
+ TPACPI_Q_LNV3('R', '0', 'K', true), /* Thinkpad 11e gen 4 celeron BIOS */
};
static int __init tpacpi_battery_init(struct ibm_init_struct *ibm)
struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file));
char *buffer;
char *cmd;
- int lcd_out, crt_out, tv_out;
+ int lcd_out = -1, crt_out = -1, tv_out = -1;
int remain = count;
int value;
int ret;
kfree(cmd);
- lcd_out = crt_out = tv_out = -1;
ret = get_video_status(dev, &video_out);
if (!ret) {
unsigned int new_video_out = video_out;
.properties = irbis_tw90_props,
};
+static const struct property_entry irbis_tw118_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-min-x", 20),
+ PROPERTY_ENTRY_U32("touchscreen-min-y", 30),
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1960),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 1510),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-irbis-tw118.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ { }
+};
+
+static const struct ts_dmi_data irbis_tw118_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = irbis_tw118_props,
+};
+
static const struct property_entry itworks_tw891_props[] = {
PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
PROPERTY_ENTRY_U32("touchscreen-min-y", 5),
.properties = pov_mobii_wintab_p1006w_v10_props,
};
+static const struct property_entry predia_basic_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-min-x", 3),
+ PROPERTY_ENTRY_U32("touchscreen-min-y", 10),
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1728),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 1144),
+ PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-predia-basic.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ PROPERTY_ENTRY_BOOL("silead,home-button"),
+ { }
+};
+
+static const struct ts_dmi_data predia_basic_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = predia_basic_props,
+};
+
static const struct property_entry schneider_sct101ctm_props[] = {
PROPERTY_ENTRY_U32("touchscreen-size-x", 1715),
PROPERTY_ENTRY_U32("touchscreen-size-y", 1140),
DMI_MATCH(DMI_PRODUCT_NAME, "TW90"),
},
},
+ {
+ /* Irbis TW118 */
+ .driver_data = (void *)&irbis_tw118_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "IRBIS"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "TW118"),
+ },
+ },
{
/* I.T.Works TW891 */
.driver_data = (void *)&itworks_tw891_data,
DMI_MATCH(DMI_BIOS_DATE, "10/24/2014"),
},
},
+ {
+ /* Predia Basic tablet) */
+ .driver_data = (void *)&predia_basic_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"),
+ /* Above matches are too generic, add bios-version match */
+ DMI_MATCH(DMI_BIOS_VERSION, "Mx.WT107.KUBNGEA"),
+ },
+ },
{
/* Point of View mobii wintab p800w (v2.1) */
.driver_data = (void *)&pov_mobii_wintab_p800w_v21_data,
}
/**
- * pnp_protocol_register - adds a pnp protocol to the pnp layer
+ * pnp_register_protocol - adds a pnp protocol to the pnp layer
* @protocol: pointer to the corresponding pnp_protocol structure
*
* Ex protocols: ISAPNP, PNPBIOS, etc
}
/**
- * pnp_protocol_unregister - removes a pnp protocol from the pnp layer
+ * pnp_unregister_protocol - removes a pnp protocol from the pnp layer
* @protocol: pointer to the corresponding pnp_protocol structure
*/
void pnp_unregister_protocol(struct pnp_protocol *protocol)
case ARBITRARY_UNIT:
default:
return value;
- };
+ }
if (to_raw)
return div64_u64(value, units) * scale;
&dev_attr_max_energy_range_uj.attr;
if (power_zone->ops->get_energy_uj) {
if (power_zone->ops->reset_energy_uj)
- dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO;
+ dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUSR;
else
- dev_attr_energy_uj.attr.mode = S_IRUGO;
+ dev_attr_energy_uj.attr.mode = S_IRUSR;
power_zone->zone_dev_attrs[count++] =
&dev_attr_energy_uj.attr;
}
return 0;
}
-static int idtcm_strverscmp(const char *ver1, const char *ver2)
+static int idtcm_strverscmp(const char *version1, const char *version2)
{
- u8 num1;
- u8 num2;
- int result = 0;
-
- /* loop through each level of the version string */
- while (result == 0) {
- /* extract leading version numbers */
- if (kstrtou8(ver1, 10, &num1) < 0)
- return -1;
+ u8 ver1[3], ver2[3];
+ int i;
- if (kstrtou8(ver2, 10, &num2) < 0)
- return -1;
+ if (sscanf(version1, "%hhu.%hhu.%hhu",
+ &ver1[0], &ver1[1], &ver1[2]) != 3)
+ return -1;
+ if (sscanf(version2, "%hhu.%hhu.%hhu",
+ &ver2[0], &ver2[1], &ver2[2]) != 3)
+ return -1;
- /* if numbers differ, then set the result */
- if (num1 < num2)
- result = -1;
- else if (num1 > num2)
- result = 1;
- else {
- /* if numbers are the same, go to next level */
- ver1 = strchr(ver1, '.');
- ver2 = strchr(ver2, '.');
- if (!ver1 && !ver2)
- break;
- else if (!ver1)
- result = -1;
- else if (!ver2)
- result = 1;
- else {
- ver1++;
- ver2++;
- }
- }
+ for (i = 0; i < 3; i++) {
+ if (ver1[i] > ver2[i])
+ return 1;
+ if (ver1[i] < ver2[i])
+ return -1;
}
- return result;
+
+ return 0;
}
static int idtcm_xfer_read(struct idtcm *idtcm,
struct regmap *regmap;
u32 offset;
};
+#define sl28cpld_pwm_from_chip(_chip) \
+ container_of(_chip, struct sl28cpld_pwm, pwm_chip)
static void sl28cpld_pwm_get_state(struct pwm_chip *chip,
struct pwm_device *pwm,
struct pwm_state *state)
{
- struct sl28cpld_pwm *priv = dev_get_drvdata(chip->dev);
+ struct sl28cpld_pwm *priv = sl28cpld_pwm_from_chip(chip);
unsigned int reg;
int prescaler;
static int sl28cpld_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
const struct pwm_state *state)
{
- struct sl28cpld_pwm *priv = dev_get_drvdata(chip->dev);
+ struct sl28cpld_pwm *priv = sl28cpld_pwm_from_chip(chip);
unsigned int cycle, prescaler;
bool write_duty_cycle_first;
int ret;
/**
* set_machine_constraints - sets regulator constraints
* @rdev: regulator source
- * @constraints: constraints to apply
*
* Allows platform initialisation code to define and constrain
* regulator circuits e.g. valid voltage/current ranges, etc. NOTE:
* regulator operations to proceed i.e. set_voltage, set_current_limit,
* set_mode.
*/
-static int set_machine_constraints(struct regulator_dev *rdev,
- const struct regulation_constraints *constraints)
+static int set_machine_constraints(struct regulator_dev *rdev)
{
int ret = 0;
const struct regulator_ops *ops = rdev->desc->ops;
- if (constraints)
- rdev->constraints = kmemdup(constraints, sizeof(*constraints),
- GFP_KERNEL);
- else
- rdev->constraints = kzalloc(sizeof(*constraints),
- GFP_KERNEL);
- if (!rdev->constraints)
- return -ENOMEM;
-
ret = machine_constraints_voltage(rdev, rdev->constraints);
if (ret != 0)
return ret;
}
}
+ if (r == rdev) {
+ dev_err(dev, "Supply for %s (%s) resolved to itself\n",
+ rdev->desc->name, rdev->supply_name);
+ if (!have_full_constraints())
+ return -EINVAL;
+ r = dummy_regulator_rdev;
+ get_device(&r->dev);
+ }
+
/*
* If the supply's parent device is not the same as the
* regulator's parent device, then ensure the parent device
ret = rdev->desc->fixed_uV;
} else if (rdev->supply) {
ret = regulator_get_voltage_rdev(rdev->supply->rdev);
+ } else if (rdev->supply_name) {
+ return -EPROBE_DEFER;
} else {
return -EINVAL;
}
regulator_register(const struct regulator_desc *regulator_desc,
const struct regulator_config *cfg)
{
- const struct regulation_constraints *constraints = NULL;
const struct regulator_init_data *init_data;
struct regulator_config *config = NULL;
static atomic_t regulator_no = ATOMIC_INIT(-1);
/* set regulator constraints */
if (init_data)
- constraints = &init_data->constraints;
+ rdev->constraints = kmemdup(&init_data->constraints,
+ sizeof(*rdev->constraints),
+ GFP_KERNEL);
+ else
+ rdev->constraints = kzalloc(sizeof(*rdev->constraints),
+ GFP_KERNEL);
+ if (!rdev->constraints) {
+ ret = -ENOMEM;
+ goto wash;
+ }
if (init_data && init_data->supply_regulator)
rdev->supply_name = init_data->supply_regulator;
else if (regulator_desc->supply_name)
rdev->supply_name = regulator_desc->supply_name;
- ret = set_machine_constraints(rdev, constraints);
+ ret = set_machine_constraints(rdev);
if (ret == -EPROBE_DEFER) {
/* Regulator might be in bypass mode and so needs its supply
* to set the constraints */
* that is just being created */
ret = regulator_resolve_supply(rdev);
if (!ret)
- ret = set_machine_constraints(rdev, constraints);
+ ret = set_machine_constraints(rdev);
else
rdev_dbg(rdev, "unable to resolve supply early: %pe\n",
ERR_PTR(ret));
if (rdev->use_count)
goto unlock;
- /* If we can't read the status assume it's on. */
+ /* If we can't read the status assume it's always on. */
if (ops->is_enabled)
enabled = ops->is_enabled(rdev);
else
enabled = 1;
- if (!enabled)
+ /* But if reading the status failed, assume that it's off. */
+ if (enabled <= 0)
goto unlock;
if (have_full_constraints()) {
* the switched regulator till yet.
*/
if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) {
- if (pfuze_chip->regulator_descs[i].sw_reg) {
- desc->ops = &pfuze100_sw_disable_regulator_ops;
- desc->enable_val = 0x8;
- desc->disable_val = 0x0;
- desc->enable_time = 500;
+ if (pfuze_chip->chip_id == PFUZE100 ||
+ pfuze_chip->chip_id == PFUZE200) {
+ if (pfuze_chip->regulator_descs[i].sw_reg) {
+ desc->ops = &pfuze100_sw_disable_regulator_ops;
+ desc->enable_val = 0x8;
+ desc->disable_val = 0x0;
+ desc->enable_time = 500;
+ }
}
}
return ret;
}
- /* If data is exactly the same, then just update index, no change */
info = &abb->info[sel];
+ /*
+ * When Linux kernel is starting up, we are'nt sure of the
+ * Bias configuration that bootloader has configured.
+ * So, we get to know the actual setting the first time
+ * we are asked to transition.
+ */
+ if (abb->current_info_idx == -EINVAL)
+ goto just_set_abb;
+
+ /* If data is exactly the same, then just update index, no change */
oinfo = &abb->info[abb->current_info_idx];
if (!memcmp(info, oinfo, sizeof(*info))) {
dev_dbg(dev, "%s: Same data new idx=%d, old idx=%d\n", __func__,
goto out;
}
+just_set_abb:
ret = ti_abb_set_opp(rdev, abb, info);
out:
if (!block)
return -EINVAL;
+ /*
+ * If the request is an ERP request there is nothing to requeue.
+ * This will be done with the remaining original request.
+ */
+ if (cqr->refers)
+ return 0;
spin_lock_irq(&cqr->dq->lock);
req = (struct request *) cqr->callback_data;
blk_mq_requeue_request(req, false);
{
struct ap_device *ap_dev = to_ap_dev(dev);
struct ap_driver *ap_drv = to_ap_drv(dev->driver);
- int card, queue, devres, drvres, rc;
+ int card, queue, devres, drvres, rc = -ENODEV;
+
+ if (!get_device(dev))
+ return rc;
if (is_queue_dev(dev)) {
/*
mutex_unlock(&ap_perms_mutex);
drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT;
if (!!devres != !!drvres)
- return -ENODEV;
+ goto out;
}
/* Add queue/card to list of active queues/cards */
ap_dev->drv = NULL;
}
+out:
+ if (rc)
+ put_device(dev);
return rc;
}
hash_del(&to_ap_queue(dev)->hnode);
spin_unlock_bh(&ap_queues_lock);
+ put_device(dev);
+
return 0;
}
__func__, ac->id, dom);
goto put_dev_and_continue;
}
+ /* get it and thus adjust reference counter */
+ get_device(dev);
if (decfg)
AP_DBF_INFO("%s(%d,%d) new (decfg) queue device created\n",
__func__, ac->id, dom);
#define PROTKEYBLOBBUFSIZE 256 /* protected key buffer size used internal */
#define MAXAPQNSINLIST 64 /* max 64 apqns within a apqn list */
-/* mask of available pckmo subfunctions, fetched once at module init */
-static cpacf_mask_t pckmo_functions;
-
/*
* debug feature data and functions
*/
const struct pkey_clrkey *clrkey,
struct pkey_protkey *protkey)
{
+ /* mask of available pckmo subfunctions */
+ static cpacf_mask_t pckmo_functions;
+
long fc;
int keysize;
u8 paramblock[64];
return -EINVAL;
}
- /*
- * Check if the needed pckmo subfunction is available.
- * These subfunctions can be enabled/disabled by customers
- * in the LPAR profile or may even change on the fly.
- */
+ /* Did we already check for PCKMO ? */
+ if (!pckmo_functions.bytes[0]) {
+ /* no, so check now */
+ if (!cpacf_query(CPACF_PCKMO, &pckmo_functions))
+ return -ENODEV;
+ }
+ /* check for the pckmo subfunction we need now */
if (!cpacf_test_func(&pckmo_functions, fc)) {
DEBUG_ERR("%s pckmo functions not available\n", __func__);
return -ENODEV;
*/
static int __init pkey_init(void)
{
- cpacf_mask_t kmc_functions;
+ cpacf_mask_t func_mask;
/*
* The pckmo instruction should be available - even if we don't
* is also the minimum level for the kmc instructions which
* are able to work with protected keys.
*/
- if (!cpacf_query(CPACF_PCKMO, &pckmo_functions))
+ if (!cpacf_query(CPACF_PCKMO, &func_mask))
return -ENODEV;
/* check for kmc instructions available */
- if (!cpacf_query(CPACF_KMC, &kmc_functions))
+ if (!cpacf_query(CPACF_KMC, &func_mask))
return -ENODEV;
- if (!cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_128) ||
- !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_192) ||
- !cpacf_test_func(&kmc_functions, CPACF_KMC_PAES_256))
+ if (!cpacf_test_func(&func_mask, CPACF_KMC_PAES_128) ||
+ !cpacf_test_func(&func_mask, CPACF_KMC_PAES_192) ||
+ !cpacf_test_func(&func_mask, CPACF_KMC_PAES_256))
return -ENODEV;
pkey_debug_init();
{
int rc;
- rc = sysfs_create_group(&zc->card->ap_dev.device.kobj,
- &zcrypt_card_attr_group);
- if (rc)
- return rc;
-
spin_lock(&zcrypt_list_lock);
list_add_tail(&zc->list, &zcrypt_card_list);
spin_unlock(&zcrypt_list_lock);
ZCRYPT_DBF(DBF_INFO, "card=%02x register online=1\n", zc->card->id);
+ rc = sysfs_create_group(&zc->card->ap_dev.device.kobj,
+ &zcrypt_card_attr_group);
+ if (rc) {
+ spin_lock(&zcrypt_list_lock);
+ list_del_init(&zc->list);
+ spin_unlock(&zcrypt_list_lock);
+ }
+
return rc;
}
EXPORT_SYMBOL(zcrypt_card_register);
&zcrypt_queue_attr_group);
if (rc)
goto out;
- get_device(&zq->queue->ap_dev.device);
if (zq->ops->rng) {
rc = zcrypt_rng_device_add();
out_unregister:
sysfs_remove_group(&zq->queue->ap_dev.device.kobj,
&zcrypt_queue_attr_group);
- put_device(&zq->queue->ap_dev.device);
out:
spin_lock(&zcrypt_list_lock);
list_del_init(&zq->list);
list_del_init(&zq->list);
zcrypt_device_count--;
spin_unlock(&zcrypt_list_lock);
- zcrypt_card_put(zc);
if (zq->ops->rng)
zcrypt_rng_device_remove();
sysfs_remove_group(&zq->queue->ap_dev.device.kobj,
&zcrypt_queue_attr_group);
- put_device(&zq->queue->ap_dev.device);
- zcrypt_queue_put(zq);
+ zcrypt_card_put(zc);
}
EXPORT_SYMBOL(zcrypt_queue_unregister);
}
static struct ism_systemeid SYSTEM_EID = {
- .seid_string = "IBM-SYSZ-IBMSEID00000000",
+ .seid_string = "IBM-SYSZ-ISMSEID00000000",
.serial_number = "0000",
.type = "0000",
};
QETH_QDIO_BUF_EMPTY,
/* Filled by driver; owned by hardware in order to be sent. */
QETH_QDIO_BUF_PRIMED,
- /* Identified to be pending in TPQ. */
+ /* Discovered by the TX completion code: */
QETH_QDIO_BUF_PENDING,
- /* Found in completion queue. */
- QETH_QDIO_BUF_IN_CQ,
+ /* Finished by the TX completion code: */
+ QETH_QDIO_BUF_NEED_QAOB,
+ /* Received QAOB notification on CQ: */
+ QETH_QDIO_BUF_QAOB_OK,
+ QETH_QDIO_BUF_QAOB_ERROR,
/* Handled via transfer pending / completion queue. */
QETH_QDIO_BUF_HANDLED_DELAYED,
};
#include <net/iucv/af_iucv.h>
#include <net/dsfield.h>
+#include <net/sock.h>
#include <asm/ebcdic.h>
#include <asm/chpid.h>
}
}
- if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) ==
- QETH_QDIO_BUF_HANDLED_DELAYED)) {
- /* for recovery situations */
- qeth_init_qdio_out_buf(q, bidx);
- QETH_CARD_TEXT(q->card, 2, "clprecov");
- }
}
static void qeth_qdio_handle_aob(struct qeth_card *card,
unsigned long phys_aob_addr)
{
+ enum qeth_qdio_out_buffer_state new_state = QETH_QDIO_BUF_QAOB_OK;
struct qaob *aob;
struct qeth_qdio_out_buffer *buffer;
enum iucv_tx_notify notification;
buffer = (struct qeth_qdio_out_buffer *) aob->user1;
QETH_CARD_TEXT_(card, 5, "%lx", aob->user1);
- if (atomic_cmpxchg(&buffer->state, QETH_QDIO_BUF_PRIMED,
- QETH_QDIO_BUF_IN_CQ) == QETH_QDIO_BUF_PRIMED) {
- notification = TX_NOTIFY_OK;
- } else {
- WARN_ON_ONCE(atomic_read(&buffer->state) !=
- QETH_QDIO_BUF_PENDING);
- atomic_set(&buffer->state, QETH_QDIO_BUF_IN_CQ);
- notification = TX_NOTIFY_DELAYED_OK;
- }
-
- if (aob->aorc != 0) {
- QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc);
- notification = qeth_compute_cq_notification(aob->aorc, 1);
- }
- qeth_notify_skbs(buffer->q, buffer, notification);
-
/* Free dangling allocations. The attached skbs are handled by
* qeth_cleanup_handled_pending().
*/
if (data && buffer->is_header[i])
kmem_cache_free(qeth_core_header_cache, data);
}
- atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
+
+ if (aob->aorc) {
+ QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc);
+ new_state = QETH_QDIO_BUF_QAOB_ERROR;
+ }
+
+ switch (atomic_xchg(&buffer->state, new_state)) {
+ case QETH_QDIO_BUF_PRIMED:
+ /* Faster than TX completion code. */
+ notification = qeth_compute_cq_notification(aob->aorc, 0);
+ qeth_notify_skbs(buffer->q, buffer, notification);
+ atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
+ break;
+ case QETH_QDIO_BUF_PENDING:
+ /* TX completion code is active and will handle the async
+ * completion for us.
+ */
+ break;
+ case QETH_QDIO_BUF_NEED_QAOB:
+ /* TX completion code is already finished. */
+ notification = qeth_compute_cq_notification(aob->aorc, 1);
+ qeth_notify_skbs(buffer->q, buffer, notification);
+ atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
qdio_release_aob(aob);
}
skb_queue_walk(&buf->skb_list, skb) {
QETH_CARD_TEXT_(q->card, 5, "skbn%d", notification);
QETH_CARD_TEXT_(q->card, 5, "%lx", (long) skb);
- if (skb->protocol == htons(ETH_P_AF_IUCV) && skb->sk)
+ if (skb->sk && skb->sk->sk_family == PF_IUCV)
iucv_sk(skb->sk)->sk_txnotify(skb, notification);
}
}
struct qeth_qdio_out_q *queue = buf->q;
struct sk_buff *skb;
- /* release may never happen from within CQ tasklet scope */
- WARN_ON_ONCE(atomic_read(&buf->state) == QETH_QDIO_BUF_IN_CQ);
-
if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING)
qeth_notify_skbs(queue, buf, TX_NOTIFY_GENERALERROR);
if (atomic_cmpxchg(&buffer->state, QETH_QDIO_BUF_PRIMED,
QETH_QDIO_BUF_PENDING) ==
- QETH_QDIO_BUF_PRIMED)
+ QETH_QDIO_BUF_PRIMED) {
qeth_notify_skbs(queue, buffer, TX_NOTIFY_PENDING);
+ /* Handle race with qeth_qdio_handle_aob(): */
+ switch (atomic_xchg(&buffer->state,
+ QETH_QDIO_BUF_NEED_QAOB)) {
+ case QETH_QDIO_BUF_PENDING:
+ /* No concurrent QAOB notification. */
+ break;
+ case QETH_QDIO_BUF_QAOB_OK:
+ qeth_notify_skbs(queue, buffer,
+ TX_NOTIFY_DELAYED_OK);
+ atomic_set(&buffer->state,
+ QETH_QDIO_BUF_HANDLED_DELAYED);
+ break;
+ case QETH_QDIO_BUF_QAOB_ERROR:
+ qeth_notify_skbs(queue, buffer,
+ TX_NOTIFY_DELAYED_GENERALERROR);
+ atomic_set(&buffer->state,
+ QETH_QDIO_BUF_HANDLED_DELAYED);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+ }
+
QETH_CARD_TEXT_(card, 5, "pel%u", bidx);
/* prepare the queue slot for re-use: */
* change notification' and thus can support the learning_sync bridgeport
* attribute
* @card: qeth_card structure pointer
- *
- * This is a destructive test and must be called before dev2br or
- * bridgeport address notification is enabled!
*/
static void qeth_l2_detect_dev2br_support(struct qeth_card *card)
{
struct qeth_priv *priv = netdev_priv(card->dev);
bool dev2br_supported;
- int rc;
QETH_CARD_TEXT(card, 2, "d2brsup");
if (!IS_IQD(card))
return;
/* dev2br requires valid cssid,iid,chid */
- if (!card->info.ids_valid) {
- dev2br_supported = false;
- } else if (css_general_characteristics.enarf) {
- dev2br_supported = true;
- } else {
- /* Old machines don't have the feature bit:
- * Probe by testing whether a disable succeeds
- */
- rc = qeth_l2_pnso(card, PNSO_OC_NET_ADDR_INFO, 0, NULL, NULL);
- dev2br_supported = !rc;
- }
+ dev2br_supported = card->info.ids_valid &&
+ css_general_characteristics.enarf;
QETH_CARD_TEXT_(card, 2, "D2Bsup%02x", dev2br_supported);
if (dev2br_supported)
struct net_device *dev = card->dev;
int rc = 0;
- /* query before bridgeport_notification may be enabled */
qeth_l2_detect_dev2br_support(card);
mutex_lock(&card->sbp_lock);
rcu_read_lock();
list_for_each_entry_rcu(h,
&tmp_pg->dh_list, node) {
- /* h->sdev should always be valid */
- BUG_ON(!h->sdev);
+ if (!h->sdev)
+ continue;
h->sdev->access_state = desc[0];
}
rcu_read_unlock();
pg->expiry = 0;
rcu_read_lock();
list_for_each_entry_rcu(h, &pg->dh_list, node) {
- BUG_ON(!h->sdev);
+ if (!h->sdev)
+ continue;
h->sdev->access_state =
(pg->state & SCSI_ACCESS_STATE_MASK);
if (pg->pref)
spin_lock(&h->pg_lock);
pg = rcu_dereference_protected(h->pg, lockdep_is_held(&h->pg_lock));
rcu_assign_pointer(h->pg, NULL);
- h->sdev = NULL;
spin_unlock(&h->pg_lock);
if (pg) {
spin_lock_irq(&pg->lock);
kref_put(&pg->kref, release_port_group);
}
sdev->handler_data = NULL;
+ synchronize_rcu();
kfree(h);
}
}
}
- if (scmd) {
+ if (scmd && hisi_hba->shost->nr_hw_queues) {
unsigned int dq_index;
u32 blk_tag;
/* hook into SCSI subsystem */
rc = hpsa_scsi_add_host(h);
if (rc)
- goto clean7; /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
+ goto clean8; /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */
/* Monitor the controller for firmware lockups */
h->heartbeat_sample_interval = HEARTBEAT_SAMPLE_INTERVAL;
HPSA_EVENT_MONITOR_INTERVAL);
return 0;
+clean8: /* lastlogicals, perf, sg, cmd, irq, shost, pci, lu, aer/h */
+ kfree(h->lastlogicals);
clean7: /* perf, sg, cmd, irq, shost, pci, lu, aer/h */
hpsa_free_performant_mode(h);
h->access.set_intr_mask(h, HPSA_INTR_OFF);
spin_unlock_irqrestore(hostdata->host->host_lock, flags);
}
+/**
+ * ibmvscsi_set_request_limit - Set the adapter request_limit in response to
+ * an adapter failure, reset, or SRP Login. Done under host lock to prevent
+ * race with SCSI command submission.
+ * @hostdata: adapter to adjust
+ * @limit: new request limit
+ */
+static void ibmvscsi_set_request_limit(struct ibmvscsi_host_data *hostdata, int limit)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(hostdata->host->host_lock, flags);
+ atomic_set(&hostdata->request_limit, limit);
+ spin_unlock_irqrestore(hostdata->host->host_lock, flags);
+}
+
/**
* ibmvscsi_reset_host - Reset the connection to the server
* @hostdata: struct ibmvscsi_host_data to reset
static void ibmvscsi_reset_host(struct ibmvscsi_host_data *hostdata)
{
scsi_block_requests(hostdata->host);
- atomic_set(&hostdata->request_limit, 0);
+ ibmvscsi_set_request_limit(hostdata, 0);
purge_requests(hostdata, DID_ERROR);
hostdata->action = IBMVSCSI_HOST_ACTION_RESET;
dev_info(hostdata->dev, "SRP_LOGIN_REJ reason %u\n",
evt_struct->xfer_iu->srp.login_rej.reason);
/* Login failed. */
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
return;
default:
dev_err(hostdata->dev, "Invalid login response typecode 0x%02x!\n",
evt_struct->xfer_iu->srp.login_rsp.opcode);
/* Login failed. */
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
return;
}
* This value is set rather than added to request_limit because
* request_limit could have been set to -1 by this client.
*/
- atomic_set(&hostdata->request_limit,
+ ibmvscsi_set_request_limit(hostdata,
be32_to_cpu(evt_struct->xfer_iu->srp.login_rsp.req_lim_delta));
/* If we had any pending I/Os, kick them */
login->req_buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT |
SRP_BUF_FORMAT_INDIRECT);
- spin_lock_irqsave(hostdata->host->host_lock, flags);
/* Start out with a request limit of 0, since this is negotiated in
* the login request we are just sending and login requests always
* get sent by the driver regardless of request_limit.
*/
- atomic_set(&hostdata->request_limit, 0);
+ ibmvscsi_set_request_limit(hostdata, 0);
+ spin_lock_irqsave(hostdata->host->host_lock, flags);
rc = ibmvscsi_send_srp_event(evt_struct, hostdata, login_timeout * 2);
spin_unlock_irqrestore(hostdata->host->host_lock, flags);
dev_info(hostdata->dev, "sent SRP login\n");
return;
case VIOSRP_CRQ_XPORT_EVENT: /* Hypervisor telling us the connection is closed */
scsi_block_requests(hostdata->host);
- atomic_set(&hostdata->request_limit, 0);
+ ibmvscsi_set_request_limit(hostdata, 0);
if (crq->format == 0x06) {
/* We need to re-setup the interpartition connection */
dev_info(hostdata->dev, "Re-enabling adapter!\n");
}
hostdata->action = IBMVSCSI_HOST_ACTION_NONE;
+ spin_unlock_irqrestore(hostdata->host->host_lock, flags);
if (rc) {
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
dev_err(hostdata->dev, "error after %s\n", action);
}
- spin_unlock_irqrestore(hostdata->host->host_lock, flags);
scsi_unblock_requests(hostdata->host);
}
init_waitqueue_head(&hostdata->work_wait_q);
hostdata->host = host;
hostdata->dev = dev;
- atomic_set(&hostdata->request_limit, -1);
+ ibmvscsi_set_request_limit(hostdata, -1);
hostdata->host->max_sectors = IBMVSCSI_MAX_SECTORS_DEFAULT;
if (map_persist_bufs(hostdata)) {
if (conn->task == task)
conn->task = NULL;
- if (conn->ping_task == task)
- conn->ping_task = NULL;
+ if (READ_ONCE(conn->ping_task) == task)
+ WRITE_ONCE(conn->ping_task, NULL);
/* release get from queueing */
__iscsi_put_task(task);
task->conn->session->age);
}
+ if (unlikely(READ_ONCE(conn->ping_task) == INVALID_SCSI_TASK))
+ WRITE_ONCE(conn->ping_task, task);
+
if (!ihost->workq) {
if (iscsi_prep_mgmt_task(conn, task))
goto free_task;
struct iscsi_nopout hdr;
struct iscsi_task *task;
- if (!rhdr && conn->ping_task)
- return -EINVAL;
+ if (!rhdr) {
+ if (READ_ONCE(conn->ping_task))
+ return -EINVAL;
+ WRITE_ONCE(conn->ping_task, INVALID_SCSI_TASK);
+ }
memset(&hdr, 0, sizeof(struct iscsi_nopout));
hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE;
task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0);
if (!task) {
+ if (!rhdr)
+ WRITE_ONCE(conn->ping_task, NULL);
iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n");
return -EIO;
} else if (!rhdr) {
/* only track our nops */
- conn->ping_task = task;
conn->last_ping = jiffies;
}
struct iscsi_conn *conn = task->conn;
int rc = 0;
- if (conn->ping_task != task) {
+ if (READ_ONCE(conn->ping_task) != task) {
/*
* If this is not in response to one of our
* nops then it must be from userspace.
*/
static int iscsi_has_ping_timed_out(struct iscsi_conn *conn)
{
- if (conn->ping_task &&
+ if (READ_ONCE(conn->ping_task) &&
time_before_eq(conn->last_recv + (conn->recv_timeout * HZ) +
(conn->ping_timeout * HZ), jiffies))
return 1;
* Checking the transport already or nop from a cmd timeout still
* running
*/
- if (conn->ping_task) {
+ if (READ_ONCE(conn->ping_task)) {
task->have_checked_conn = true;
rc = BLK_EH_RESET_TIMER;
goto done;
reply_q->irq_poll_scheduled = false;
reply_q->irq_line_enable = true;
enable_irq(reply_q->os_irq);
+ /*
+ * Go for one more round of processing the
+ * reply descriptor post queue incase if HBA
+ * Firmware has posted some reply descriptors
+ * while reenabling the IRQ.
+ */
+ _base_process_reply_queue(reply_q);
}
return num_entries;
r = _base_handshake_req_reply_wait(ioc,
sizeof(Mpi2IOCInitRequest_t), (u32 *)&mpi_request,
- sizeof(Mpi2IOCInitReply_t), (u16 *)&mpi_reply, 10);
+ sizeof(Mpi2IOCInitReply_t), (u16 *)&mpi_reply, 30);
if (r != 0) {
ioc_err(ioc, "%s: handshake failed (r=%d)\n", __func__, r);
Mpi26NVMeEncapsulatedRequest_t *nvme_encap_request = NULL;
struct _pcie_device *pcie_device = NULL;
u16 smid;
- u8 timeout;
+ unsigned long timeout;
u8 issue_reset;
u32 sz, sz_arg;
void *psge;
fcport = qla_rport->fcport;
- if (!qpair || !fcport || (qpair && !qpair->fw_started) ||
- (fcport && fcport->deleted))
+ if (!qpair || !fcport)
return -ENODEV;
+ if (!qpair->fw_started || fcport->deleted)
+ return -EBUSY;
+
vha = fcport->vha;
if (!(fcport->nvme_flag & NVME_FLAG_REGISTERED))
{
ulong flags = 0;
-#ifndef __CHECKER__
if (!hardware_locked)
spin_lock_irqsave(&vha->hw->hardware_lock, flags);
-#endif
if (!vha->hw->mpi_fw_dump) {
ql_log(ql_log_warn, vha, 0x02f3, "-> mpi_fwdump no buffer\n");
} else {
}
bailout:
-#ifndef __CHECKER__
if (!hardware_locked)
spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
-#endif
}
void
*/
static struct async_scan_data *scsi_prep_async_scan(struct Scsi_Host *shost)
{
- struct async_scan_data *data;
+ struct async_scan_data *data = NULL;
unsigned long flags;
if (strncmp(scsi_scan_type, "sync", 4) == 0)
return NULL;
+ mutex_lock(&shost->scan_mutex);
if (shost->async_scan) {
shost_printk(KERN_DEBUG, shost, "%s called twice\n", __func__);
- return NULL;
+ goto err;
}
data = kmalloc(sizeof(*data), GFP_KERNEL);
goto err;
init_completion(&data->prev_finished);
- mutex_lock(&shost->scan_mutex);
spin_lock_irqsave(shost->host_lock, flags);
shost->async_scan = 1;
spin_unlock_irqrestore(shost->host_lock, flags);
return data;
err:
+ mutex_unlock(&shost->scan_mutex);
kfree(data);
return NULL;
}
request = (struct storvsc_cmd_request *)
((unsigned long)desc->trans_id);
+ if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - vmscsi_size_delta) {
+ dev_err(&device->device, "Invalid packet len\n");
+ continue;
+ }
+
if (request == &stor_device->init_request ||
request == &stor_device->reset_request) {
memcpy(&request->vstor_packet, packet,
alloc_ordered_workqueue("storvsc_error_wq_%d",
WQ_MEM_RECLAIM,
host->host_no);
- if (!host_dev->handle_error_wq)
+ if (!host_dev->handle_error_wq) {
+ ret = -ENOMEM;
goto err_out2;
+ }
INIT_WORK(&host_dev->host_scan_work, storvsc_host_scan);
/* Register the HBA and start the scsi bus scan */
ret = scsi_add_host(host, &device->device);
}
spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+ pm_runtime_get_noresume(hba->dev);
+ if (!pm_runtime_active(hba->dev)) {
+ pm_runtime_put_noidle(hba->dev);
+ ret = -EAGAIN;
+ goto out;
+ }
start = ktime_get();
ret = ufshcd_devfreq_scale(hba, scale_up);
+ pm_runtime_put(hba->dev);
trace_ufshcd_profile_clk_scaling(dev_name(hba->dev),
(scale_up ? "up" : "down"),
*/
fallthrough;
case CLKS_OFF:
- ufshcd_scsi_block_requests(hba);
hba->clk_gating.state = REQ_CLKS_ON;
trace_ufshcd_clk_gating(dev_name(hba->dev),
hba->clk_gating.state);
- queue_work(hba->clk_gating.clk_gating_workq,
- &hba->clk_gating.ungate_work);
+ if (queue_work(hba->clk_gating.clk_gating_workq,
+ &hba->clk_gating.ungate_work))
+ ufshcd_scsi_block_requests(hba);
/*
* fall through to check if we should wait for this
* work to be done or not.
unsigned long flags;
if (wait_for_completion_timeout(&uic_cmd->done,
- msecs_to_jiffies(UIC_CMD_TIMEOUT)))
+ msecs_to_jiffies(UIC_CMD_TIMEOUT))) {
ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
- else
+ } else {
ret = -ETIMEDOUT;
+ dev_err(hba->dev,
+ "uic cmd 0x%x with arg3 0x%x completion timeout\n",
+ uic_cmd->command, uic_cmd->argument3);
+
+ if (!uic_cmd->cmd_active) {
+ dev_err(hba->dev, "%s: UIC cmd has been completed, return the result\n",
+ __func__);
+ ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT;
+ }
+ }
spin_lock_irqsave(hba->host->host_lock, flags);
hba->active_uic_cmd = NULL;
if (completion)
init_completion(&uic_cmd->done);
+ uic_cmd->cmd_active = 1;
ufshcd_dispatch_uic_cmd(hba, uic_cmd);
return 0;
/* Get the length of descriptor */
ufshcd_map_desc_id_to_length(hba, desc_id, &buff_len);
if (!buff_len) {
- dev_err(hba->dev, "%s: Failed to get desc length", __func__);
+ dev_err(hba->dev, "%s: Failed to get desc length\n", __func__);
+ return -EINVAL;
+ }
+
+ if (param_offset >= buff_len) {
+ dev_err(hba->dev, "%s: Invalid offset 0x%x in descriptor IDN 0x%x, length 0x%x\n",
+ __func__, param_offset, desc_id, buff_len);
return -EINVAL;
}
/* Check whether we need temp memory */
if (param_offset != 0 || param_size < buff_len) {
- desc_buf = kmalloc(buff_len, GFP_KERNEL);
+ desc_buf = kzalloc(buff_len, GFP_KERNEL);
if (!desc_buf)
return -ENOMEM;
} else {
desc_buf, &buff_len);
if (ret) {
- dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d",
+ dev_err(hba->dev, "%s: Failed reading descriptor. desc_id %d, desc_index %d, param_offset %d, ret %d\n",
__func__, desc_id, desc_index, param_offset, ret);
goto out;
}
/* Sanity check */
if (desc_buf[QUERY_DESC_DESC_TYPE_OFFSET] != desc_id) {
- dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header",
+ dev_err(hba->dev, "%s: invalid desc_id %d in descriptor header\n",
__func__, desc_buf[QUERY_DESC_DESC_TYPE_OFFSET]);
ret = -EINVAL;
goto out;
buff_len = desc_buf[QUERY_DESC_LENGTH_OFFSET];
ufshcd_update_desc_length(hba, desc_id, desc_index, buff_len);
- /* Check wherher we will not copy more data, than available */
- if (is_kmalloc && (param_offset + param_size) > buff_len)
- param_size = buff_len - param_offset;
-
- if (is_kmalloc)
+ if (is_kmalloc) {
+ /* Make sure we don't copy more data than available */
+ if (param_offset + param_size > buff_len)
+ param_size = buff_len - param_offset;
memcpy(param_read_buf, &desc_buf[param_offset], param_size);
+ }
out:
if (is_kmalloc)
kfree(desc_buf);
dev_err(hba->dev,
"pwr ctrl cmd 0x%x with mode 0x%x completion timeout\n",
cmd->command, cmd->argument3);
+
+ if (!cmd->cmd_active) {
+ dev_err(hba->dev, "%s: Power Mode Change operation has been completed, go check UPMCRS\n",
+ __func__);
+ goto check_upmcrs;
+ }
+
ret = -ETIMEDOUT;
goto out;
}
+check_upmcrs:
status = ufshcd_get_upmcrs(hba);
if (status != PWR_LOCAL) {
dev_err(hba->dev,
ufshcd_get_uic_cmd_result(hba);
hba->active_uic_cmd->argument3 =
ufshcd_get_dme_attr_val(hba);
+ if (!hba->uic_async_done)
+ hba->active_uic_cmd->cmd_active = 0;
complete(&hba->active_uic_cmd->done);
retval = IRQ_HANDLED;
}
if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) {
+ hba->active_uic_cmd->cmd_active = 0;
complete(hba->uic_async_done);
retval = IRQ_HANDLED;
}
if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba))
goto out;
- if (pm_runtime_suspended(hba->dev)) {
- ret = ufshcd_runtime_resume(hba);
- if (ret)
- goto out;
- }
+ pm_runtime_get_sync(hba->dev);
ret = ufshcd_suspend(hba, UFS_SHUTDOWN_PM);
out:
blk_mq_free_tag_set(&hba->tmf_tag_set);
blk_cleanup_queue(hba->cmd_queue);
scsi_remove_host(hba->host);
+ destroy_workqueue(hba->eh_wq);
/* disable interrupts */
ufshcd_disable_intr(hba, hba->intr_mask);
ufshcd_hba_stop(hba);
exit_gating:
ufshcd_exit_clk_scaling(hba);
ufshcd_exit_clk_gating(hba);
+ destroy_workqueue(hba->eh_wq);
out_disable:
hba->is_irq_enabled = false;
ufshcd_hba_exit(hba);
* @argument1: UIC command argument 1
* @argument2: UIC command argument 2
* @argument3: UIC command argument 3
+ * @cmd_active: Indicate if UIC command is outstanding
* @done: UIC command completion
*/
struct uic_command {
u32 argument1;
u32 argument2;
u32 argument3;
+ int cmd_active;
struct completion done;
};
{
int error;
struct fsl_mc_device_irq *irq;
- cpumask_t mask;
irq = dpio_dev->irqs[0];
error = devm_request_irq(&dpio_dev->dev,
}
/* set the affinity hint */
- cpumask_clear(&mask);
- cpumask_set_cpu(cpu, &mask);
- if (irq_set_affinity_hint(irq->msi_desc->irq, &mask))
+ if (irq_set_affinity_hint(irq->msi_desc->irq, cpumask_of(cpu)))
dev_err(&dpio_dev->dev,
"irq_set_affinity failed irq %d cpu %d\n",
irq->msi_desc->irq, cpu);
struct genpd_onecell_data *genpd_data = data;
unsigned int idx = genpdspec->args[0];
- if (genpdspec->args_count < 2)
+ if (genpdspec->args_count != 1 && genpdspec->args_count != 2)
return ERR_PTR(-EINVAL);
if (idx >= genpd_data->num_domains) {
data = of_id->data;
- master = spi_alloc_master(dev, sizeof(struct bcm_qspi));
+ master = devm_spi_alloc_master(dev, sizeof(struct bcm_qspi));
if (!master) {
dev_err(dev, "error allocating spi_master\n");
return -ENOMEM;
if (res) {
qspi->base[MSPI] = devm_ioremap_resource(dev, res);
- if (IS_ERR(qspi->base[MSPI])) {
- ret = PTR_ERR(qspi->base[MSPI]);
- goto qspi_resource_err;
- }
+ if (IS_ERR(qspi->base[MSPI]))
+ return PTR_ERR(qspi->base[MSPI]);
} else {
- goto qspi_resource_err;
+ return 0;
}
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "bspi");
if (res) {
qspi->base[BSPI] = devm_ioremap_resource(dev, res);
- if (IS_ERR(qspi->base[BSPI])) {
- ret = PTR_ERR(qspi->base[BSPI]);
- goto qspi_resource_err;
- }
+ if (IS_ERR(qspi->base[BSPI]))
+ return PTR_ERR(qspi->base[BSPI]);
qspi->bspi_mode = true;
} else {
qspi->bspi_mode = false;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs_reg");
if (res) {
qspi->base[CHIP_SELECT] = devm_ioremap_resource(dev, res);
- if (IS_ERR(qspi->base[CHIP_SELECT])) {
- ret = PTR_ERR(qspi->base[CHIP_SELECT]);
- goto qspi_resource_err;
- }
+ if (IS_ERR(qspi->base[CHIP_SELECT]))
+ return PTR_ERR(qspi->base[CHIP_SELECT]);
}
qspi->dev_ids = kcalloc(num_irqs, sizeof(struct bcm_qspi_dev_id),
GFP_KERNEL);
- if (!qspi->dev_ids) {
- ret = -ENOMEM;
- goto qspi_resource_err;
- }
+ if (!qspi->dev_ids)
+ return -ENOMEM;
for (val = 0; val < num_irqs; val++) {
irq = -1;
qspi->xfer_mode.addrlen = -1;
qspi->xfer_mode.hp = -1;
- ret = devm_spi_register_master(&pdev->dev, master);
+ ret = spi_register_master(master);
if (ret < 0) {
dev_err(dev, "can't register master\n");
goto qspi_reg_err;
clk_disable_unprepare(qspi->clk);
qspi_probe_err:
kfree(qspi->dev_ids);
-qspi_resource_err:
- spi_master_put(master);
return ret;
}
/* probe function to be called by SoC specific platform driver probe */
{
struct bcm_qspi *qspi = platform_get_drvdata(pdev);
+ spi_unregister_master(qspi->master);
bcm_qspi_hw_uninit(qspi);
clk_disable_unprepare(qspi->clk);
kfree(qspi->dev_ids);
- spi_unregister_master(qspi->master);
return 0;
}
struct spi_controller *ctlr = spi->controller;
struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
struct gpio_chip *chip;
- enum gpio_lookup_flags lflags;
u32 cs;
/*
if (!chip)
return 0;
- /*
- * Retrieve the corresponding GPIO line used for CS.
- * The inversion semantics will be handled by the GPIO core
- * code, so we pass GPIOD_OUT_LOW for "unasserted" and
- * the correct flag for inversion semantics. The SPI_CS_HIGH
- * on spi->mode cannot be checked for polarity in this case
- * as the flag use_gpio_descriptors enforces SPI_CS_HIGH.
- */
- if (of_property_read_bool(spi->dev.of_node, "spi-cs-high"))
- lflags = GPIO_ACTIVE_HIGH;
- else
- lflags = GPIO_ACTIVE_LOW;
spi->cs_gpiod = gpiochip_request_own_desc(chip, 8 - spi->chip_select,
DRV_NAME,
- lflags,
+ GPIO_LOOKUP_FLAGS_DEFAULT,
GPIOD_OUT_LOW);
if (IS_ERR(spi->cs_gpiod))
return PTR_ERR(spi->cs_gpiod);
struct bcm2835_spi *bs;
int err;
- ctlr = spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
+ ctlr = devm_spi_alloc_master(&pdev->dev, ALIGN(sizeof(*bs),
dma_get_cache_alignment()));
if (!ctlr)
return -ENOMEM;
bs->ctlr = ctlr;
bs->regs = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(bs->regs)) {
- err = PTR_ERR(bs->regs);
- goto out_controller_put;
- }
+ if (IS_ERR(bs->regs))
+ return PTR_ERR(bs->regs);
bs->clk = devm_clk_get(&pdev->dev, NULL);
- if (IS_ERR(bs->clk)) {
- err = dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
- "could not get clk\n");
- goto out_controller_put;
- }
+ if (IS_ERR(bs->clk))
+ return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
+ "could not get clk\n");
bs->irq = platform_get_irq(pdev, 0);
- if (bs->irq <= 0) {
- err = bs->irq ? bs->irq : -ENODEV;
- goto out_controller_put;
- }
+ if (bs->irq <= 0)
+ return bs->irq ? bs->irq : -ENODEV;
clk_prepare_enable(bs->clk);
bcm2835_dma_release(ctlr, bs);
out_clk_disable:
clk_disable_unprepare(bs->clk);
-out_controller_put:
- spi_controller_put(ctlr);
return err;
}
unsigned long clk_hz;
int err;
- master = spi_alloc_master(&pdev->dev, sizeof(*bs));
+ master = devm_spi_alloc_master(&pdev->dev, sizeof(*bs));
if (!master)
return -ENOMEM;
/* the main area */
bs->regs = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(bs->regs)) {
- err = PTR_ERR(bs->regs);
- goto out_master_put;
- }
+ if (IS_ERR(bs->regs))
+ return PTR_ERR(bs->regs);
bs->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(bs->clk)) {
err = PTR_ERR(bs->clk);
dev_err(&pdev->dev, "could not get clk: %d\n", err);
- goto out_master_put;
+ return err;
}
bs->irq = platform_get_irq(pdev, 0);
- if (bs->irq <= 0) {
- err = bs->irq ? bs->irq : -ENODEV;
- goto out_master_put;
- }
+ if (bs->irq <= 0)
+ return bs->irq ? bs->irq : -ENODEV;
/* this also enables the HW block */
err = clk_prepare_enable(bs->clk);
if (err) {
dev_err(&pdev->dev, "could not prepare clock: %d\n", err);
- goto out_master_put;
+ return err;
}
/* just checking if the clock returns a sane value */
out_clk_disable:
clk_disable_unprepare(bs->clk);
-out_master_put:
- spi_master_put(master);
return err;
}
/* Obtain QSPI reset control */
rstc = devm_reset_control_get_optional_exclusive(dev, "qspi");
if (IS_ERR(rstc)) {
+ ret = PTR_ERR(rstc);
dev_err(dev, "Cannot get QSPI reset.\n");
goto probe_reset_failed;
}
rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp");
if (IS_ERR(rstc_ocp)) {
+ ret = PTR_ERR(rstc_ocp);
dev_err(dev, "Cannot get QSPI OCP reset.\n");
goto probe_reset_failed;
}
dw_writel(dws, DW_SPI_TXFTLR, level);
dw_writel(dws, DW_SPI_RXFTLR, level - 1);
+ dws->transfer_handler = dw_spi_transfer_handler;
+
imask = SPI_INT_TXEI | SPI_INT_TXOI | SPI_INT_RXUI | SPI_INT_RXOI |
SPI_INT_RXFI;
spi_umask_intr(dws, imask);
-
- dws->transfer_handler = dw_spi_transfer_handler;
}
/*
master->set_cs = dw_spi_set_cs;
master->transfer_one = dw_spi_transfer_one;
master->handle_err = dw_spi_handle_err;
- master->mem_ops = &dws->mem_ops;
+ if (dws->mem_ops.exec_op)
+ master->mem_ops = &dws->mem_ops;
master->max_speed_hz = dws->max_freq;
master->dev.of_node = dev->of_node;
master->dev.fwnode = dev->fwnode;
rc = fsi_spi_check_mux(ctx->fsi, ctx->dev);
if (rc)
- return rc;
+ goto error;
list_for_each_entry(transfer, &mesg->transfers, transfer_list) {
struct fsi_spi_sequence seq;
#ifdef CONFIG_PM_SLEEP
static int dspi_suspend(struct device *dev)
{
- struct spi_controller *ctlr = dev_get_drvdata(dev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = dev_get_drvdata(dev);
if (dspi->irq)
disable_irq(dspi->irq);
- spi_controller_suspend(ctlr);
+ spi_controller_suspend(dspi->ctlr);
clk_disable_unprepare(dspi->clk);
pinctrl_pm_select_sleep_state(dev);
static int dspi_resume(struct device *dev)
{
- struct spi_controller *ctlr = dev_get_drvdata(dev);
- struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
+ struct fsl_dspi *dspi = dev_get_drvdata(dev);
int ret;
pinctrl_pm_select_default_state(dev);
ret = clk_prepare_enable(dspi->clk);
if (ret)
return ret;
- spi_controller_resume(ctlr);
+ spi_controller_resume(dspi->ctlr);
if (dspi->irq)
enable_irq(dspi->irq);
spi_controller_get_devdata(controller);
pm_runtime_disable(fsl_lpspi->dev);
-
- spi_master_put(controller);
-
return 0;
}
goto out_master_put;
}
- pm_runtime_enable(spi_imx->dev);
+ ret = clk_prepare_enable(spi_imx->clk_per);
+ if (ret)
+ goto out_master_put;
+
+ ret = clk_prepare_enable(spi_imx->clk_ipg);
+ if (ret)
+ goto out_put_per;
+
pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT);
pm_runtime_use_autosuspend(spi_imx->dev);
-
- ret = pm_runtime_get_sync(spi_imx->dev);
- if (ret < 0) {
- dev_err(spi_imx->dev, "failed to enable clock\n");
- goto out_runtime_pm_put;
- }
+ pm_runtime_get_noresume(spi_imx->dev);
+ pm_runtime_set_active(spi_imx->dev);
+ pm_runtime_enable(spi_imx->dev);
spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per);
/*
spi_imx_sdma_exit(spi_imx);
out_runtime_pm_put:
pm_runtime_dont_use_autosuspend(spi_imx->dev);
- pm_runtime_put_sync(spi_imx->dev);
+ pm_runtime_set_suspended(&pdev->dev);
pm_runtime_disable(spi_imx->dev);
+
+ clk_disable_unprepare(spi_imx->clk_ipg);
+out_put_per:
+ clk_disable_unprepare(spi_imx->clk_per);
out_master_put:
spi_master_put(master);
struct resource *res;
int id;
- ctrl = spi_alloc_master(dev, sizeof(*fiu));
+ ctrl = devm_spi_alloc_master(dev, sizeof(*fiu));
if (!ctrl)
return -ENOMEM;
struct resource *res;
struct nxp_fspi *f;
int ret;
+ u32 reg;
ctlr = spi_alloc_master(&pdev->dev, sizeof(*f));
if (!ctlr)
goto err_put_ctrl;
}
+ /* Clear potential interrupts */
+ reg = fspi_readl(f, f->iobase + FSPI_INTR);
+ if (reg)
+ fspi_writel(f, reg, f->iobase + FSPI_INTR);
+
+
/* find the resources - controller memory mapped space */
if (is_acpi_node(f->dev->fwnode))
res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
enable = !enable;
if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) {
- /*
- * Honour the SPI_NO_CS flag and invert the enable line, as
- * active low is default for SPI. Execution paths that handle
- * polarity inversion in gpiolib (such as device tree) will
- * enforce active high using the SPI_CS_HIGH resulting in a
- * double inversion through the code above.
- */
if (!(spi->mode & SPI_NO_CS)) {
if (spi->cs_gpiod)
+ /* polarity handled by gpiolib */
gpiod_set_value_cansleep(spi->cs_gpiod,
- !enable);
+ enable1);
else
+ /*
+ * invert the enable line, as active low is
+ * default for SPI.
+ */
gpio_set_value_cansleep(spi->cs_gpio, !enable);
}
/* Some SPI masters need both GPIO CS & slave_select */
}
spi->chip_select = value;
- /*
- * For descriptors associated with the device, polarity inversion is
- * handled in the gpiolib, so all gpio chip selects are "active high"
- * in the logical sense, the gpiolib will invert the line if need be.
- */
- if ((ctlr->use_gpio_descriptors) && ctlr->cs_gpiods &&
- ctlr->cs_gpiods[spi->chip_select])
- spi->mode |= SPI_CS_HIGH;
-
/* Device speed */
if (!of_property_read_u32(nc, "spi-max-frequency", &value))
spi->max_speed_hz = value;
}
EXPORT_SYMBOL_GPL(__spi_alloc_controller);
+static void devm_spi_release_controller(struct device *dev, void *ctlr)
+{
+ spi_controller_put(*(struct spi_controller **)ctlr);
+}
+
+/**
+ * __devm_spi_alloc_controller - resource-managed __spi_alloc_controller()
+ * @dev: physical device of SPI controller
+ * @size: how much zeroed driver-private data to allocate
+ * @slave: whether to allocate an SPI master (false) or SPI slave (true)
+ * Context: can sleep
+ *
+ * Allocate an SPI controller and automatically release a reference on it
+ * when @dev is unbound from its driver. Drivers are thus relieved from
+ * having to call spi_controller_put().
+ *
+ * The arguments to this function are identical to __spi_alloc_controller().
+ *
+ * Return: the SPI controller structure on success, else NULL.
+ */
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+ unsigned int size,
+ bool slave)
+{
+ struct spi_controller **ptr, *ctlr;
+
+ ptr = devres_alloc(devm_spi_release_controller, sizeof(*ptr),
+ GFP_KERNEL);
+ if (!ptr)
+ return NULL;
+
+ ctlr = __spi_alloc_controller(dev, size, slave);
+ if (ctlr) {
+ *ptr = ctlr;
+ devres_add(dev, ptr);
+ } else {
+ devres_free(ptr);
+ }
+
+ return ctlr;
+}
+EXPORT_SYMBOL_GPL(__devm_spi_alloc_controller);
+
#ifdef CONFIG_OF
static int of_spi_get_gpio_numbers(struct spi_controller *ctlr)
{
}
EXPORT_SYMBOL_GPL(devm_spi_register_controller);
+static int devm_spi_match_controller(struct device *dev, void *res, void *ctlr)
+{
+ return *(struct spi_controller **)res == ctlr;
+}
+
static int __unregister(struct device *dev, void *null)
{
spi_unregister_device(to_spi_device(dev));
list_del(&ctlr->list);
mutex_unlock(&board_lock);
- device_unregister(&ctlr->dev);
+ device_del(&ctlr->dev);
+
+ /* Release the last reference on the controller if its driver
+ * has not yet been converted to devm_spi_alloc_master/slave().
+ */
+ if (!devres_find(ctlr->dev.parent, devm_spi_release_controller,
+ devm_spi_match_controller, ctlr))
+ put_device(&ctlr->dev);
+
/* free bus id */
mutex_lock(&board_lock);
if (found == ctlr)
if (!spi->max_speed_hz)
spi->max_speed_hz = spi->controller->max_speed_hz;
+ mutex_lock(&spi->controller->io_mutex);
+
if (spi->controller->setup)
status = spi->controller->setup(spi);
if (spi->controller->auto_runtime_pm && spi->controller->set_cs) {
status = pm_runtime_get_sync(spi->controller->dev.parent);
if (status < 0) {
+ mutex_unlock(&spi->controller->io_mutex);
pm_runtime_put_noidle(spi->controller->dev.parent);
dev_err(&spi->controller->dev, "Failed to power device: %d\n",
status);
spi_set_cs(spi, false);
}
+ mutex_unlock(&spi->controller->io_mutex);
+
if (spi->rt && !spi->controller->rt) {
spi->controller->rt = true;
spi_set_thread_rt(spi->controller);
if (dev->irq && board->has_ao_fifo) {
dev->write_subdev = s;
s->subdev_flags |= SDF_CMD_WRITE;
+ s->len_chanlist = s->n_chan;
s->do_cmdtest = cb_pcidas_ao_cmdtest;
s->do_cmd = cb_pcidas_ao_cmd;
s->cancel = cb_pcidas_ao_cancel;
regulator = devm_regulator_register(dev, &can_power_desc, &config);
if (IS_ERR(regulator)) {
err = PTR_ERR(regulator);
- goto out_reset;
+ goto out_ida;
}
/* make controller info visible to userspace */
cd->class_dev = kzalloc(sizeof(*cd->class_dev), GFP_KERNEL);
reg |= (pps->second_chroma_qp_index_offset & 0x3f) << 16;
reg |= (pps->chroma_qp_index_offset & 0x3f) << 8;
reg |= (pps->pic_init_qp_minus26 + 26 + slice->slice_qp_delta) & 0x3f;
- if (pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT)
+ if (!(pps->flags & V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT))
reg |= VE_H264_SHS_QP_SCALING_MATRIX_DEFAULT;
cedrus_write(dev, VE_H264_SHS_QP, reg);
return 0;
}
-static int mt7621_pcie_request_resources(struct mt7621_pcie *pcie,
- struct list_head *res)
+static void mt7621_pcie_add_resources(struct mt7621_pcie *pcie,
+ struct list_head *res)
{
- struct device *dev = pcie->dev;
-
pci_add_resource_offset(res, &pcie->io, pcie->offset.io);
pci_add_resource_offset(res, &pcie->mem, pcie->offset.mem);
- pci_add_resource(res, &pcie->busn);
-
- return devm_request_pci_bus_resources(dev, res);
}
static int mt7621_pcie_register_host(struct pci_host_bridge *host,
setup_cm_memory_region(pcie);
- err = mt7621_pcie_request_resources(pcie, &res);
- if (err) {
- dev_err(dev, "Error requesting resources\n");
- return err;
- }
+ mt7621_pcie_add_resources(pcie, &res);
err = mt7621_pcie_register_host(bridge, &res);
if (err) {
phy_node = of_parse_phandle(priv->of_node, "phy-handle", 0);
if (!phy_node && of_phy_is_fixed_link(priv->of_node)) {
- int rc;
-
- rc = of_phy_register_fixed_link(priv->of_node);
- if (rc)
- return rc;
-
phy_node = of_node_get(priv->of_node);
}
if (!phy_node)
else
port = work->word1.cn38xx.ipprt;
- if ((work->word2.snoip.err_code == 10) && (work->word1.len <= 64)) {
+ if ((work->word2.snoip.err_code == 10) && (work->word1.len <= 64))
/*
* Ignore length errors on min size packets. Some
* equipment incorrectly pads packets to 64+4FCS
* instead of 60+4FCS. Note these packets still get
* counted as frame errors.
*/
- } else if (work->word2.snoip.err_code == 5 ||
- work->word2.snoip.err_code == 7) {
+ return 0;
+
+ if (work->word2.snoip.err_code == 5 ||
+ work->word2.snoip.err_code == 7) {
/*
* We received a packet with either an alignment error
* or a FCS error. This may be signalling that we are
/* Port received 0xd5 preamble */
work->packet_ptr.s.addr += i + 1;
work->word1.len -= i + 5;
- } else if ((*ptr & 0xf) == 0xd) {
+ return 0;
+ }
+
+ if ((*ptr & 0xf) == 0xd) {
/* Port received 0xd preamble */
work->packet_ptr.s.addr += i;
work->word1.len -= i + 4;
((*(ptr + 1) & 0xf) << 4);
ptr++;
}
- } else {
- printk_ratelimited("Port %d unknown preamble, packet dropped\n",
- port);
- cvm_oct_free_work(work);
- return 1;
+ return 0;
}
+
+ printk_ratelimited("Port %d unknown preamble, packet dropped\n",
+ port);
+ cvm_oct_free_work(work);
+ return 1;
}
- } else {
- printk_ratelimited("Port %d receive error code %d, packet dropped\n",
- port, work->word2.snoip.err_code);
- cvm_oct_free_work(work);
- return 1;
}
- return 0;
+ printk_ratelimited("Port %d receive error code %d, packet dropped\n",
+ port, work->word2.snoip.err_code);
+ cvm_oct_free_work(work);
+ return 1;
}
static void copy_segments_to_skb(struct cvmx_wqe *work, struct sk_buff *skb)
#include <linux/phy.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
+#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
break;
}
+ if (priv->of_node && of_phy_is_fixed_link(priv->of_node)) {
+ if (of_phy_register_fixed_link(priv->of_node)) {
+ netdev_err(dev, "Failed to register fixed link for interface %d, port %d\n",
+ interface, priv->port);
+ dev->netdev_ops = NULL;
+ }
+ }
+
if (!dev->netdev_ops) {
free_netdev(dev);
} else if (register_netdev(dev) < 0) {
config DMA_RALINK
tristate "RALINK DMA support"
depends on RALINK && !SOC_RT288X
+ depends on DMADEVICES
select DMA_ENGINE
select DMA_VIRTUAL_CHANNELS
{ SDIO_DEVICE(0x024c, 0x0525), },
{ SDIO_DEVICE(0x024c, 0x0623), },
{ SDIO_DEVICE(0x024c, 0x0626), },
+ { SDIO_DEVICE(0x024c, 0x0627), },
{ SDIO_DEVICE(0x024c, 0xb723), },
{ /* end: all zeroes */ },
};
/* ordered workqueue to process all bulk operations */
struct workqueue_struct *bulk_wq;
+
+ /* handle for a vchiq instance */
+ struct vchiq_instance *vchiq_instance;
};
static struct mmal_msg_context *
mutex_unlock(&instance->vchiq_mutex);
+ vchiq_shutdown(instance->vchiq_instance);
flush_workqueue(instance->bulk_wq);
destroy_workqueue(instance->bulk_wq);
int vchiq_mmal_init(struct vchiq_mmal_instance **out_instance)
{
int status;
+ int err = -ENODEV;
struct vchiq_mmal_instance *instance;
static struct vchiq_instance *vchiq_instance;
struct vchiq_service_params_kernel params = {
status = vchiq_connect(vchiq_instance);
if (status) {
pr_err("Failed to connect VCHI instance (status=%d)\n", status);
- return -EIO;
+ err = -EIO;
+ goto err_shutdown_vchiq;
}
instance = kzalloc(sizeof(*instance), GFP_KERNEL);
- if (!instance)
- return -ENOMEM;
+ if (!instance) {
+ err = -ENOMEM;
+ goto err_shutdown_vchiq;
+ }
mutex_init(&instance->vchiq_mutex);
instance->bulk_scratch = vmalloc(PAGE_SIZE);
+ instance->vchiq_instance = vchiq_instance;
mutex_init(&instance->context_map_lock);
idr_init_base(&instance->context_map, 1);
err_free:
vfree(instance->bulk_scratch);
kfree(instance);
- return -ENODEV;
+err_shutdown_vchiq:
+ vchiq_shutdown(vchiq_instance);
+ return err;
}
EXPORT_SYMBOL_GPL(vchiq_mmal_init);
In addition, it is recommended to declare a mmc-pwrseq on SDIO host above
WFx. Without it, you may encounter issues with warm boot. The mmc-pwrseq
should be compatible with mmc-pwrseq-simple. Please consult
- Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt for more
+ Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.yaml for more
information.
For SPI':'
if (!wdev->pdata.gpio_wakeup)
return;
- if (gpiod_get_value_cansleep(wdev->pdata.gpio_wakeup) >= 0)
+ if (gpiod_get_value_cansleep(wdev->pdata.gpio_wakeup) > 0)
return;
if (wfx_api_older_than(wdev, 1, 4)) {
}
return rate->idx + 14;
}
+ // WFx only support 2GHz, else band information should be retrieved
+ // from ieee80211_tx_info
+ band = wdev->hw->wiphy->bands[NL80211_BAND_2GHZ];
if (rate->idx >= band->n_bitrates) {
WARN(1, "wrong rate->idx value: %d", rate->idx);
return -1;
}
- // WFx only support 2GHz, else band information should be retrieved
- // from ieee80211_tx_info
- band = wdev->hw->wiphy->bands[NL80211_BAND_2GHZ];
return band->bitrates[rate->idx].hw_value;
}
void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
spin_lock_bh(&conn->cmd_lock);
- if (!list_empty(&cmd->i_conn_node) &&
- !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP))
+ if (!list_empty(&cmd->i_conn_node))
list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
spin_lock_bh(&conn->cmd_lock);
list_splice_init(&conn->conn_cmd_list, &tmp_list);
- list_for_each_entry(cmd, &tmp_list, i_conn_node) {
+ list_for_each_entry_safe(cmd, cmd_tmp, &tmp_list, i_conn_node) {
struct se_cmd *se_cmd = &cmd->se_cmd;
if (se_cmd->se_tfo != NULL) {
spin_lock_irq(&se_cmd->t_state_lock);
- se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+ if (se_cmd->transport_state & CMD_T_ABORTED) {
+ /*
+ * LIO's abort path owns the cleanup for this,
+ * so put it back on the list and let
+ * aborted_task handle it.
+ */
+ list_move_tail(&cmd->i_conn_node,
+ &conn->conn_cmd_list);
+ } else {
+ se_cmd->transport_state |= CMD_T_FABRIC_STOP;
+ }
spin_unlock_irq(&se_cmd->t_state_lock);
}
}
uint8_t tmr_type;
uint32_t tmr_cmd_cnt;
- int16_t tmr_cmd_ids[0];
+ int16_t tmr_cmd_ids[];
};
/*
/**
* struct amdtee_context_data - AMD-TEE driver context data
* @sess_list: Keeps track of sessions opened in current TEE context
+ * @shm_list: Keeps track of buffers allocated and mapped in current TEE
+ * context
*/
struct amdtee_context_data {
struct list_head sess_list;
+ struct list_head shm_list;
+ struct mutex shm_mutex; /* synchronizes access to @shm_list */
};
struct amdtee_driver_data {
u32 buf_id;
};
-struct amdtee_shm_context {
- struct list_head shmdata_list;
-};
-
#define LOWER_TWO_BYTE_MASK 0x0000FFFF
/**
static struct amdtee_driver_data *drv_data;
static DEFINE_MUTEX(session_list_mutex);
-static struct amdtee_shm_context shmctx;
static void amdtee_get_version(struct tee_device *teedev,
struct tee_ioctl_version_data *vers)
return -ENOMEM;
INIT_LIST_HEAD(&ctxdata->sess_list);
- INIT_LIST_HEAD(&shmctx.shmdata_list);
+ INIT_LIST_HEAD(&ctxdata->shm_list);
+ mutex_init(&ctxdata->shm_mutex);
ctx->data = ctxdata;
return 0;
list_del(&sess->list_node);
release_session(sess);
}
+ mutex_destroy(&ctxdata->shm_mutex);
kfree(ctxdata);
ctx->data = NULL;
u32 get_buffer_id(struct tee_shm *shm)
{
- u32 buf_id = 0;
+ struct amdtee_context_data *ctxdata = shm->ctx->data;
struct amdtee_shm_data *shmdata;
+ u32 buf_id = 0;
- list_for_each_entry(shmdata, &shmctx.shmdata_list, shm_node)
+ mutex_lock(&ctxdata->shm_mutex);
+ list_for_each_entry(shmdata, &ctxdata->shm_list, shm_node)
if (shmdata->kaddr == shm->kaddr) {
buf_id = shmdata->buf_id;
break;
}
+ mutex_unlock(&ctxdata->shm_mutex);
return buf_id;
}
int amdtee_map_shmem(struct tee_shm *shm)
{
- struct shmem_desc shmem;
+ struct amdtee_context_data *ctxdata;
struct amdtee_shm_data *shmnode;
+ struct shmem_desc shmem;
int rc, count;
u32 buf_id;
shmnode->kaddr = shm->kaddr;
shmnode->buf_id = buf_id;
- list_add(&shmnode->shm_node, &shmctx.shmdata_list);
+ ctxdata = shm->ctx->data;
+ mutex_lock(&ctxdata->shm_mutex);
+ list_add(&shmnode->shm_node, &ctxdata->shm_list);
+ mutex_unlock(&ctxdata->shm_mutex);
pr_debug("buf_id :[%x] kaddr[%p]\n", shmnode->buf_id, shmnode->kaddr);
void amdtee_unmap_shmem(struct tee_shm *shm)
{
+ struct amdtee_context_data *ctxdata;
struct amdtee_shm_data *shmnode;
u32 buf_id;
/* Unmap the shared memory from TEE */
handle_unmap_shmem(buf_id);
- list_for_each_entry(shmnode, &shmctx.shmdata_list, shm_node)
+ ctxdata = shm->ctx->data;
+ mutex_lock(&ctxdata->shm_mutex);
+ list_for_each_entry(shmnode, &ctxdata->shm_list, shm_node)
if (buf_id == shmnode->buf_id) {
list_del(&shmnode->shm_node);
kfree(shmnode);
break;
}
+ mutex_unlock(&ctxdata->shm_mutex);
}
int amdtee_invoke_func(struct tee_context *ctx,
static bool is_normal_memory(pgprot_t p)
{
#if defined(CONFIG_ARM)
- return (pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC;
+ return (((pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEALLOC) ||
+ ((pgprot_val(p) & L_PTE_MT_MASK) == L_PTE_MT_WRITEBACK));
#elif defined(CONFIG_ARM64)
return (pgprot_val(p) & PTE_ATTRINDX_MASK) == PTE_ATTRINDX(MT_NORMAL);
#else
int name_len;
int rc;
- if (connection_method == TEE_IOCTL_LOGIN_PUBLIC) {
+ if (connection_method == TEE_IOCTL_LOGIN_PUBLIC ||
+ connection_method == TEE_IOCTL_LOGIN_REE_KERNEL) {
/* Nil UUID to be passed to TEE environment */
uuid_copy(uuid, &uuid_null);
return 0;
#include <linux/err.h>
#include <linux/types.h>
#include <linux/spinlock.h>
+#include <linux/sys_soc.h>
#include <linux/reboot.h>
#include <linux/of_device.h>
#include <linux/of_platform.h>
return bgp;
}
+/*
+ * List of SoCs on which the CPU PM notifier can cause erros on the DTEMP
+ * readout.
+ * Enabled notifier on these machines results in erroneous, random values which
+ * could trigger unexpected thermal shutdown.
+ */
+static const struct soc_device_attribute soc_no_cpu_notifier[] = {
+ { .machine = "OMAP4430" },
+ { /* sentinel */ },
+};
+
/*** Device driver call backs ***/
static
#ifdef CONFIG_PM_SLEEP
bgp->nb.notifier_call = bandgap_omap_cpu_notifier;
- cpu_pm_register_notifier(&bgp->nb);
+ if (!soc_device_match(soc_no_cpu_notifier))
+ cpu_pm_register_notifier(&bgp->nb);
#endif
return 0;
struct ti_bandgap *bgp = platform_get_drvdata(pdev);
int i;
- cpu_pm_unregister_notifier(&bgp->nb);
+ if (!soc_device_match(soc_no_cpu_notifier))
+ cpu_pm_unregister_notifier(&bgp->nb);
/* Remove sensor interfaces */
for (i = 0; i < bgp->conf->sensor_count; i++) {
#include <linux/debugfs.h>
#include <linux/pm_runtime.h>
+#include <linux/uaccess.h>
#include "tb.h"
static void remove_unplugged_switch(struct tb_switch *sw)
{
- pm_runtime_get_sync(sw->dev.parent);
+ struct device *parent = get_device(sw->dev.parent);
+
+ pm_runtime_get_sync(parent);
/*
* Signal this and switches below for rpm_complete because
bus_for_each_dev(&tb_bus_type, &sw->dev, NULL, complete_rpm);
tb_switch_remove(sw);
- pm_runtime_mark_last_busy(sw->dev.parent);
- pm_runtime_put_autosuspend(sw->dev.parent);
+ pm_runtime_mark_last_busy(parent);
+ pm_runtime_put_autosuspend(parent);
+
+ put_device(parent);
}
static void icm_free_unplugged_children(struct tb_switch *sw)
case PCI_DEVICE_ID_INTEL_TGL_NHI0:
case PCI_DEVICE_ID_INTEL_TGL_NHI1:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI0:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI1:
icm->is_supported = icm_tgl_is_supported;
icm->driver_ready = icm_icl_driver_ready;
icm->set_uuid = icm_icl_set_uuid;
ring->vector = ret;
- ring->irq = pci_irq_vector(ring->nhi->pdev, ring->vector);
- if (ring->irq < 0)
- return ring->irq;
+ ret = pci_irq_vector(ring->nhi->pdev, ring->vector);
+ if (ret < 0)
+ goto err_ida_remove;
+
+ ring->irq = ret;
irqflags = no_suspend ? IRQF_NO_SUSPEND : 0;
- return request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
+ ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring);
+ if (ret)
+ goto err_ida_remove;
+
+ return 0;
+
+err_ida_remove:
+ ida_simple_remove(&nhi->msix_ida, ring->vector);
+
+ return ret;
}
static void ring_release_msix(struct tb_ring *ring)
.driver_data = (kernel_ulong_t)&icl_nhi_ops },
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1),
.driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1),
+ .driver_data = (kernel_ulong_t)&icl_nhi_ops },
/* Any USB4 compliant host */
{ PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) },
#define PCI_DEVICE_ID_INTEL_ICL_NHI0 0x8a17
#define PCI_DEVICE_ID_INTEL_TGL_NHI0 0x9a1b
#define PCI_DEVICE_ID_INTEL_TGL_NHI1 0x9a1d
+#define PCI_DEVICE_ID_INTEL_TGL_H_NHI0 0x9a1f
+#define PCI_DEVICE_ID_INTEL_TGL_H_NHI1 0x9a21
#define PCI_CLASS_SERIAL_USB_USB4 0x0c0340
switch (sw->config.device_id) {
case PCI_DEVICE_ID_INTEL_TGL_NHI0:
case PCI_DEVICE_ID_INTEL_TGL_NHI1:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI0:
+ case PCI_DEVICE_ID_INTEL_TGL_H_NHI1:
return true;
}
}
* upstream USB4 port.
*/
tb_switch_for_each_port(sw, port) {
+ if (!tb_port_is_null(port))
+ continue;
if (!route && tb_is_upstream_port(port))
continue;
+ if (!port->cap_usb4)
+ continue;
ret = tb_port_read(port, &val, TB_CFG_PORT,
port->cap_usb4 + PORT_CS_19, 1);
id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL);
if (id < 0) {
+ kfree(svc->key);
kfree(svc);
break;
}
static bool is_enabled(struct uart_port *port, int bit)
{
- unsigned long private_data = (unsigned long)port->private_data;
+ unsigned long *private_data = (unsigned long *)&port->private_data;
- if (test_bit(bit, &private_data))
+ if (test_bit(bit, private_data))
return true;
return false;
}
static void enable(struct uart_port *port, int bit)
{
- unsigned long private_data = (unsigned long)port->private_data;
+ unsigned long *private_data = (unsigned long *)&port->private_data;
- set_bit(bit, &private_data);
+ set_bit(bit, private_data);
}
static void disable(struct uart_port *port, int bit)
{
- unsigned long private_data = (unsigned long)port->private_data;
+ unsigned long *private_data = (unsigned long *)&port->private_data;
- clear_bit(bit, &private_data);
+ clear_bit(bit, private_data);
}
#define is_tx_enabled(port) is_enabled(port, tx_enabled_bit)
*/
baud = tty_termios_baud_rate(termios);
- serial8250_do_set_termios(port, termios, old);
+ serial8250_do_set_termios(port, termios, NULL);
tty_termios_encode_baud_rate(termios, baud, baud);
depends on OF
select SERIAL_EARLYCON
select SERIAL_CORE_CONSOLE
+ default y if SERIAL_IMX_CONSOLE
help
If you have enabled the earlycon on the Freescale IMX
CPU you can make it the earlycon by answering Y to this option.
goto err_disable_clk;
up->gpios = mctrl_gpio_init(port, 0);
- if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS)
- return PTR_ERR(up->gpios);
+ if (IS_ERR(up->gpios) && PTR_ERR(up->gpios) != -ENOSYS) {
+ ret = PTR_ERR(up->gpios);
+ goto err_disable_clk;
+ }
up->rts_gpiod = mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_RTS);
/* Forward declare this for the dma callbacks*/
static void lpuart_dma_tx_complete(void *arg);
-static inline bool is_ls1028a_lpuart(struct lpuart_port *sport)
+static inline bool is_layerscape_lpuart(struct lpuart_port *sport)
{
- return sport->devtype == LS1028A_LPUART;
+ return (sport->devtype == LS1021A_LPUART ||
+ sport->devtype == LS1028A_LPUART);
}
static inline bool is_imx8qxp_lpuart(struct lpuart_port *sport)
UARTFIFO_FIFOSIZE_MASK);
/*
- * The LS1028A has a fixed length of 16 words. Although it supports the
- * RX/TXSIZE fields their encoding is different. Eg the reference manual
- * states 0b101 is 16 words.
+ * The LS1021A and LS1028A have a fixed FIFO depth of 16 words.
+ * Although they support the RX/TXSIZE fields, their encoding is
+ * different. Eg the reference manual states 0b101 is 16 words.
*/
- if (is_ls1028a_lpuart(sport)) {
+ if (is_layerscape_lpuart(sport)) {
sport->rxfifo_size = 16;
sport->txfifo_size = 16;
sport->port.fifosize = sport->txfifo_size;
struct imx_port *sport = dev_id;
unsigned int usr1, usr2, ucr1, ucr2, ucr3, ucr4;
irqreturn_t ret = IRQ_NONE;
+ unsigned long flags = 0;
- spin_lock(&sport->port.lock);
+ /*
+ * IRQs might not be disabled upon entering this interrupt handler,
+ * e.g. when interrupt handlers are forced to be threaded. To support
+ * this scenario as well, disable IRQs when acquiring the spinlock.
+ */
+ spin_lock_irqsave(&sport->port.lock, flags);
usr1 = imx_uart_readl(sport, USR1);
usr2 = imx_uart_readl(sport, USR2);
ret = IRQ_HANDLED;
}
- spin_unlock(&sport->port.lock);
+ spin_unlock_irqrestore(&sport->port.lock, flags);
return ret;
}
unsigned int ucr1;
unsigned long flags = 0;
int locked = 1;
- int retval;
-
- retval = clk_enable(sport->clk_per);
- if (retval)
- return;
- retval = clk_enable(sport->clk_ipg);
- if (retval) {
- clk_disable(sport->clk_per);
- return;
- }
if (sport->port.sysrq)
locked = 0;
if (locked)
spin_unlock_irqrestore(&sport->port.lock, flags);
-
- clk_disable(sport->clk_ipg);
- clk_disable(sport->clk_per);
}
/*
retval = uart_set_options(&sport->port, co, baud, parity, bits, flow);
- clk_disable(sport->clk_ipg);
if (retval) {
- clk_unprepare(sport->clk_ipg);
+ clk_disable_unprepare(sport->clk_ipg);
goto error_console;
}
- retval = clk_prepare(sport->clk_per);
+ retval = clk_prepare_enable(sport->clk_per);
if (retval)
- clk_unprepare(sport->clk_ipg);
+ clk_disable_unprepare(sport->clk_ipg);
error_console:
return retval;
#ifdef ENABLE_SERIAL_TXX9_PCI
ret = pci_register_driver(&serial_txx9_pci_driver);
+ if (ret) {
+ platform_driver_unregister(&serial_txx9_plat_driver);
+ }
#endif
if (ret == 0)
goto out;
tty->ops->shutdown(tty);
tty_save_termios(tty);
tty_driver_remove_tty(tty->driver, tty);
- tty->port->itty = NULL;
+ if (tty->port)
+ tty->port->itty = NULL;
if (tty->link)
tty->link->port->itty = NULL;
- tty_buffer_cancel_work(tty->port);
+ if (tty->port)
+ tty_buffer_cancel_work(tty->port);
if (tty->link)
tty_buffer_cancel_work(tty->link->port);
struct task_struct *g, *p;
struct pid *session;
int i;
+ unsigned long flags;
if (!tty)
return;
- session = tty->session;
+
+ spin_lock_irqsave(&tty->ctrl_lock, flags);
+ session = get_pid(tty->session);
+ spin_unlock_irqrestore(&tty->ctrl_lock, flags);
tty_ldisc_flush(tty);
task_unlock(p);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
+ put_pid(session);
#endif
}
put_pid(tty->session);
put_pid(tty->pgrp);
tty->pgrp = get_pid(task_pgrp(current));
- spin_unlock_irqrestore(&tty->ctrl_lock, flags);
tty->session = get_pid(task_session(current));
+ spin_unlock_irqrestore(&tty->ctrl_lock, flags);
if (current->signal->tty) {
tty_debug(tty, "current tty %s not NULL!!\n",
current->signal->tty->name);
spin_lock_irq(¤t->sighand->siglock);
put_pid(current->signal->tty_old_pgrp);
current->signal->tty_old_pgrp = NULL;
-
tty = tty_kref_get(current->signal->tty);
+ spin_unlock_irq(¤t->sighand->siglock);
+
if (tty) {
unsigned long flags;
+
+ tty_lock(tty);
spin_lock_irqsave(&tty->ctrl_lock, flags);
put_pid(tty->session);
put_pid(tty->pgrp);
tty->session = NULL;
tty->pgrp = NULL;
spin_unlock_irqrestore(&tty->ctrl_lock, flags);
+ tty_unlock(tty);
tty_kref_put(tty);
}
- spin_unlock_irq(¤t->sighand->siglock);
/* Now clear signal->tty under the lock */
read_lock(&tasklist_lock);
session_clear_tty(task_session(current));
return -ENOTTY;
if (retval)
return retval;
- if (!current->signal->tty ||
- (current->signal->tty != real_tty) ||
- (real_tty->session != task_session(current)))
- return -ENOTTY;
+
if (get_user(pgrp_nr, p))
return -EFAULT;
if (pgrp_nr < 0)
return -EINVAL;
+
+ spin_lock_irq(&real_tty->ctrl_lock);
+ if (!current->signal->tty ||
+ (current->signal->tty != real_tty) ||
+ (real_tty->session != task_session(current))) {
+ retval = -ENOTTY;
+ goto out_unlock_ctrl;
+ }
rcu_read_lock();
pgrp = find_vpid(pgrp_nr);
retval = -ESRCH;
if (session_of_pgrp(pgrp) != task_session(current))
goto out_unlock;
retval = 0;
- spin_lock_irq(&tty->ctrl_lock);
put_pid(real_tty->pgrp);
real_tty->pgrp = get_pid(pgrp);
- spin_unlock_irq(&tty->ctrl_lock);
out_unlock:
rcu_read_unlock();
+out_unlock_ctrl:
+ spin_unlock_irq(&real_tty->ctrl_lock);
return retval;
}
*
* Obtain the session id of the tty. If there is no session
* return an error.
- *
- * Locking: none. Reference to current->signal->tty is safe.
*/
static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p)
{
+ unsigned long flags;
+ pid_t sid;
+
/*
* (tty == real_tty) is a cheap way of
* testing if the tty is NOT a master pty.
*/
if (tty == real_tty && current->signal->tty != real_tty)
return -ENOTTY;
+
+ spin_lock_irqsave(&real_tty->ctrl_lock, flags);
if (!real_tty->session)
- return -ENOTTY;
- return put_user(pid_vnr(real_tty->session), p);
+ goto err;
+ sid = pid_vnr(real_tty->session);
+ spin_unlock_irqrestore(&real_tty->ctrl_lock, flags);
+
+ return put_user(sid, p);
+
+err:
+ spin_unlock_irqrestore(&real_tty->ctrl_lock, flags);
+ return -ENOTTY;
}
/*
return;
if ((unsigned)value < ARRAY_SIZE(func_table)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&func_buf_lock, flags);
if (func_table[value])
puts_queue(vc, func_table[value]);
+ spin_unlock_irqrestore(&func_buf_lock, flags);
+
} else
pr_err("k_fn called with value=%d\n", value);
}
#undef s
#undef v
-/* FIXME: This one needs untangling and locking */
+/* FIXME: This one needs untangling */
int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
{
struct kbsentry *kbs;
- char *p;
u_char *q;
- u_char __user *up;
int sz, fnw_sz;
int delta;
char *first_free, *fj, *fnw;
i = array_index_nospec(kbs->kb_func, MAX_NR_FUNC);
switch (cmd) {
- case KDGKBSENT:
- sz = sizeof(kbs->kb_string) - 1; /* sz should have been
- a struct member */
- up = user_kdgkb->kb_string;
- p = func_table[i];
- if(p)
- for ( ; *p && sz; p++, sz--)
- if (put_user(*p, up++)) {
- ret = -EFAULT;
- goto reterr;
- }
- if (put_user('\0', up)) {
- ret = -EFAULT;
- goto reterr;
- }
- kfree(kbs);
- return ((p && *p) ? -EOVERFLOW : 0);
+ case KDGKBSENT: {
+ /* size should have been a struct member */
+ ssize_t len = sizeof(user_kdgkb->kb_string);
+
+ spin_lock_irqsave(&func_buf_lock, flags);
+ len = strlcpy(kbs->kb_string, func_table[i] ? : "", len);
+ spin_unlock_irqrestore(&func_buf_lock, flags);
+
+ ret = copy_to_user(user_kdgkb->kb_string, kbs->kb_string,
+ len + 1) ? -EFAULT : 0;
+
+ goto reterr;
+ }
case KDSKBSENT:
if (!perm) {
ret = -EPERM;
return rc;
}
-static int con_font_copy(struct vc_data *vc, struct console_font_op *op)
-{
- int con = op->height;
- int rc;
-
-
- console_lock();
- if (vc->vc_mode != KD_TEXT)
- rc = -EINVAL;
- else if (!vc->vc_sw->con_font_copy)
- rc = -ENOSYS;
- else if (con < 0 || !vc_cons_allocated(con))
- rc = -ENOTTY;
- else if (con == vc->vc_num) /* nothing to do */
- rc = 0;
- else
- rc = vc->vc_sw->con_font_copy(vc, con);
- console_unlock();
- return rc;
-}
-
int con_font_op(struct vc_data *vc, struct console_font_op *op)
{
switch (op->op) {
case KD_FONT_OP_SET_DEFAULT:
return con_font_default(vc, op);
case KD_FONT_OP_COPY:
- return con_font_copy(vc, op);
+ /* was buggy and never really used */
+ return -EINVAL;
}
return -ENOSYS;
}
return 0;
}
-static inline int do_fontx_ioctl(int cmd,
+static inline int do_fontx_ioctl(struct vc_data *vc, int cmd,
struct consolefontdesc __user *user_cfd,
struct console_font_op *op)
{
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = cfdarg.chardata;
- return con_font_op(vc_cons[fg_console].d, op);
- case GIO_FONTX: {
+ return con_font_op(vc, op);
+
+ case GIO_FONTX:
op->op = KD_FONT_OP_GET;
op->flags = KD_FONT_FLAG_OLD;
op->width = 8;
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = cfdarg.chardata;
- i = con_font_op(vc_cons[fg_console].d, op);
+ i = con_font_op(vc, op);
if (i)
return i;
cfdarg.charheight = op->height;
if (copy_to_user(user_cfd, &cfdarg, sizeof(struct consolefontdesc)))
return -EFAULT;
return 0;
- }
}
return -EINVAL;
}
-static int vt_io_fontreset(struct console_font_op *op)
+static int vt_io_fontreset(struct vc_data *vc, struct console_font_op *op)
{
int ret;
op->op = KD_FONT_OP_SET_DEFAULT;
op->data = NULL;
- ret = con_font_op(vc_cons[fg_console].d, op);
+ ret = con_font_op(vc, op);
if (ret)
return ret;
console_lock();
- con_set_default_unimap(vc_cons[fg_console].d);
+ con_set_default_unimap(vc);
console_unlock();
return 0;
}
static inline int do_unimap_ioctl(int cmd, struct unimapdesc __user *user_ud,
- struct vc_data *vc)
+ bool perm, struct vc_data *vc)
{
struct unimapdesc tmp;
return -EFAULT;
switch (cmd) {
case PIO_UNIMAP:
+ if (!perm)
+ return -EPERM;
return con_set_unimap(vc, tmp.entry_ct, tmp.entries);
case GIO_UNIMAP:
- if (fg_console != vc->vc_num)
+ if (!perm && fg_console != vc->vc_num)
return -EPERM;
return con_get_unimap(vc, tmp.entry_ct, &(user_ud->entry_ct),
tmp.entries);
op.height = 0;
op.charcount = 256;
op.data = up;
- return con_font_op(vc_cons[fg_console].d, &op);
+ return con_font_op(vc, &op);
case GIO_FONT:
op.op = KD_FONT_OP_GET;
op.height = 32;
op.charcount = 256;
op.data = up;
- return con_font_op(vc_cons[fg_console].d, &op);
+ return con_font_op(vc, &op);
case PIO_CMAP:
if (!perm)
fallthrough;
case GIO_FONTX:
- return do_fontx_ioctl(cmd, up, &op);
+ return do_fontx_ioctl(vc, cmd, up, &op);
case PIO_FONTRESET:
if (!perm)
return -EPERM;
- return vt_io_fontreset(&op);
+ return vt_io_fontreset(vc, &op);
case PIO_SCRNMAP:
if (!perm)
case PIO_UNIMAP:
case GIO_UNIMAP:
- if (!perm)
- return -EPERM;
-
- return do_unimap_ioctl(cmd, up, vc);
+ return do_unimap_ioctl(cmd, up, perm, vc);
default:
return -ENOIOCTLCMD;
};
static inline int
-compat_fontx_ioctl(int cmd, struct compat_consolefontdesc __user *user_cfd,
- int perm, struct console_font_op *op)
+compat_fontx_ioctl(struct vc_data *vc, int cmd,
+ struct compat_consolefontdesc __user *user_cfd,
+ int perm, struct console_font_op *op)
{
struct compat_consolefontdesc cfdarg;
int i;
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = compat_ptr(cfdarg.chardata);
- return con_font_op(vc_cons[fg_console].d, op);
+ return con_font_op(vc, op);
+
case GIO_FONTX:
op->op = KD_FONT_OP_GET;
op->flags = KD_FONT_FLAG_OLD;
op->height = cfdarg.charheight;
op->charcount = cfdarg.charcount;
op->data = compat_ptr(cfdarg.chardata);
- i = con_font_op(vc_cons[fg_console].d, op);
+ i = con_font_op(vc, op);
if (i)
return i;
cfdarg.charheight = op->height;
*/
case PIO_FONTX:
case GIO_FONTX:
- return compat_fontx_ioctl(cmd, up, perm, &op);
+ return compat_fontx_ioctl(vc, cmd, up, perm, &op);
case KDFONTOP:
return compat_kdfontop_ioctl(up, perm, &op, vc);
return retval;
}
-static void uio_free_minor(struct uio_device *idev)
+static void uio_free_minor(unsigned long minor)
{
mutex_lock(&minor_lock);
- idr_remove(&uio_idr, idev->minor);
+ idr_remove(&uio_idr, minor);
mutex_unlock(&minor_lock);
}
err_uio_dev_add_attributes:
device_del(&idev->dev);
err_device_create:
- uio_free_minor(idev);
+ uio_free_minor(idev->minor);
put_device(&idev->dev);
return ret;
}
void uio_unregister_device(struct uio_info *info)
{
struct uio_device *idev;
+ unsigned long minor;
if (!info || !info->uio_dev)
return;
idev = info->uio_dev;
+ minor = idev->minor;
mutex_lock(&idev->info_lock);
uio_dev_del_attributes(idev);
device_unregister(&idev->dev);
- uio_free_minor(idev);
+ uio_free_minor(minor);
return;
}
*/
static int cdns3_probe(struct platform_device *pdev)
{
- struct usb_role_switch_desc sw_desc = { };
struct device *dev = &pdev->dev;
struct resource *res;
struct cdns3 *cdns;
if (ret)
goto err2;
- sw_desc.set = cdns3_role_set;
- sw_desc.get = cdns3_role_get;
- sw_desc.allow_userspace_control = true;
- sw_desc.driver_data = cdns;
- if (device_property_read_bool(dev, "usb-role-switch"))
+ if (device_property_read_bool(dev, "usb-role-switch")) {
+ struct usb_role_switch_desc sw_desc = { };
+
+ sw_desc.set = cdns3_role_set;
+ sw_desc.get = cdns3_role_get;
+ sw_desc.allow_userspace_control = true;
+ sw_desc.driver_data = cdns;
sw_desc.fwnode = dev->fwnode;
- cdns->role_sw = usb_role_switch_register(dev, &sw_desc);
- if (IS_ERR(cdns->role_sw)) {
- ret = PTR_ERR(cdns->role_sw);
- dev_warn(dev, "Unable to register Role Switch\n");
- goto err3;
+ cdns->role_sw = usb_role_switch_register(dev, &sw_desc);
+ if (IS_ERR(cdns->role_sw)) {
+ ret = PTR_ERR(cdns->role_sw);
+ dev_warn(dev, "Unable to register Role Switch\n");
+ goto err3;
+ }
}
if (cdns->wakeup_irq) {
if (ret) {
dev_err(cdns->dev, "couldn't register wakeup irq handler\n");
- goto err3;
+ goto err4;
}
}
return 0;
err4:
cdns3_drd_exit(cdns);
- usb_role_switch_unregister(cdns->role_sw);
+ if (cdns->role_sw)
+ usb_role_switch_unregister(cdns->role_sw);
err3:
set_phy_power_off(cdns);
err2:
struct usb_ctrlrequest *ctrl_req)
{
enum usb_device_state device_state = priv_dev->gadget.state;
- struct cdns3_endpoint *priv_ep;
u32 config = le16_to_cpu(ctrl_req->wValue);
int result = 0;
- int i;
switch (device_state) {
case USB_STATE_ADDRESS:
- /* Configure non-control EPs */
- for (i = 0; i < CDNS3_ENDPOINTS_MAX_COUNT; i++) {
- priv_ep = priv_dev->eps[i];
- if (!priv_ep)
- continue;
-
- if (priv_ep->flags & EP_CLAIMED)
- cdns3_ep_config(priv_ep);
- }
-
result = cdns3_ep0_delegate_req(priv_dev, ctrl_req);
- if (result)
- return result;
-
- if (!config) {
- cdns3_hw_reset_eps_config(priv_dev);
- usb_gadget_set_state(&priv_dev->gadget,
- USB_STATE_ADDRESS);
- }
+ if (result || !config)
+ goto reset_config;
break;
case USB_STATE_CONFIGURED:
result = cdns3_ep0_delegate_req(priv_dev, ctrl_req);
+ if (!config && !result)
+ goto reset_config;
- if (!config && !result) {
- cdns3_hw_reset_eps_config(priv_dev);
- usb_gadget_set_state(&priv_dev->gadget,
- USB_STATE_ADDRESS);
- }
break;
default:
- result = -EINVAL;
+ return -EINVAL;
}
+ return 0;
+
+reset_config:
+ if (result != USB_GADGET_DELAYED_STATUS)
+ cdns3_hw_reset_eps_config(priv_dev);
+
+ usb_gadget_set_state(&priv_dev->gadget,
+ USB_STATE_ADDRESS);
+
return result;
}
unsigned long flags;
int ret = 0;
u8 zlp = 0;
+ int i;
spin_lock_irqsave(&priv_dev->lock, flags);
trace_cdns3_ep0_queue(priv_dev, request);
u32 val;
cdns3_select_ep(priv_dev, 0x00);
+
+ /*
+ * Configure all non-control EPs which are not enabled by class driver
+ */
+ for (i = 0; i < CDNS3_ENDPOINTS_MAX_COUNT; i++) {
+ priv_ep = priv_dev->eps[i];
+ if (priv_ep && priv_ep->flags & EP_CLAIMED &&
+ !(priv_ep->flags & EP_ENABLED))
+ cdns3_ep_config(priv_ep, 0);
+ }
+
cdns3_set_hw_configuration(priv_dev);
cdns3_ep0_complete_setup(priv_dev, 0, 1);
/* wait until configuration set */
struct cdns3_usb_regs __iomem *regs;
struct cdns3_endpoint *priv_ep;
u32 max_packet_size = 64;
+ u32 ep_cfg;
regs = priv_dev->regs;
BIT(0) | BIT(16));
}
- writel(EP_CFG_ENABLE | EP_CFG_MAXPKTSIZE(max_packet_size),
- ®s->ep_cfg);
+ ep_cfg = EP_CFG_ENABLE | EP_CFG_MAXPKTSIZE(max_packet_size);
+
+ if (!(priv_ep->flags & EP_CONFIGURED))
+ writel(ep_cfg, ®s->ep_cfg);
writel(EP_STS_EN_SETUPEN | EP_STS_EN_DESCMISEN | EP_STS_EN_TRBERREN,
®s->ep_sts_en);
/* init ep in */
cdns3_select_ep(priv_dev, USB_DIR_IN);
- writel(EP_CFG_ENABLE | EP_CFG_MAXPKTSIZE(max_packet_size),
- ®s->ep_cfg);
+ if (!(priv_ep->flags & EP_CONFIGURED))
+ writel(ep_cfg, ®s->ep_cfg);
+
+ priv_ep->flags |= EP_CONFIGURED;
writel(EP_STS_EN_SETUPEN | EP_STS_EN_TRBERREN, ®s->ep_sts_en);
*/
void cdns3_hw_reset_eps_config(struct cdns3_device *priv_dev)
{
+ int i;
+
writel(USB_CONF_CFGRST, &priv_dev->regs->usb_conf);
cdns3_allow_enable_l1(priv_dev, 0);
priv_dev->out_mem_is_allocated = 0;
priv_dev->wait_for_setup = 0;
priv_dev->using_streams = 0;
+
+ for (i = 0; i < CDNS3_ENDPOINTS_MAX_COUNT; i++)
+ if (priv_dev->eps[i])
+ priv_dev->eps[i]->flags &= ~EP_CONFIGURED;
}
/**
while (!list_empty(&priv_ep->wa2_descmiss_req_list)) {
int chunk_end;
- int length;
descmiss_priv_req =
cdns3_next_priv_request(&priv_ep->wa2_descmiss_req_list);
break;
chunk_end = descmiss_priv_req->flags & REQUEST_INTERNAL_CH;
- length = request->actual + descmiss_req->actual;
request->status = descmiss_req->status;
__cdns3_descmiss_copy_data(request, descmiss_req);
list_del_init(&descmiss_priv_req->list);
struct cdns3_device *priv_dev = priv_ep->cdns3_dev;
struct cdns3_request *priv_req;
struct cdns3_trb *trb;
- struct cdns3_trb *link_trb;
+ struct cdns3_trb *link_trb = NULL;
dma_addr_t trb_dma;
u32 togle_pcs = 1;
int sg_iter = 0;
/* set incorrect Cycle Bit for first trb*/
control = priv_ep->pcs ? 0 : TRB_CYCLE;
+ trb->length = 0;
+ if (priv_dev->dev_ver >= DEV_VER_V2) {
+ u16 td_size;
+
+ td_size = DIV_ROUND_UP(request->length,
+ priv_ep->endpoint.maxpacket);
+ if (priv_dev->gadget.speed == USB_SPEED_SUPER)
+ trb->length = TRB_TDL_SS_SIZE(td_size);
+ else
+ control |= TRB_TDL_HS_SIZE(td_size);
+ }
do {
u32 length;
- u16 td_size = 0;
/* fill TRB */
control |= TRB_TYPE(TRB_NORMAL);
length = request->length;
}
- if (likely(priv_dev->dev_ver >= DEV_VER_V2))
- td_size = DIV_ROUND_UP(length,
- priv_ep->endpoint.maxpacket);
- else if (priv_ep->flags & EP_TDLCHK_EN)
+ if (priv_ep->flags & EP_TDLCHK_EN)
total_tdl += DIV_ROUND_UP(length,
priv_ep->endpoint.maxpacket);
- trb->length = cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) |
+ trb->length |= cpu_to_le32(TRB_BURST_LEN(priv_ep->trb_burst_size) |
TRB_LEN(length));
- if (priv_dev->gadget.speed == USB_SPEED_SUPER)
- trb->length |= cpu_to_le32(TRB_TDL_SS_SIZE(td_size));
- else
- control |= TRB_TDL_HS_SIZE(td_size);
-
pcs = priv_ep->pcs ? TRB_CYCLE : 0;
/*
priv_req->end_trb = priv_ep->enqueue;
cdns3_ep_inc_enq(priv_ep);
trb = priv_ep->trb_pool + priv_ep->enqueue;
+ trb->length = 0;
} while (sg_iter < num_trb);
trb = priv_req->trb;
static void cdns3_disconnect_gadget(struct cdns3_device *priv_dev)
{
- if (priv_dev->gadget_driver && priv_dev->gadget_driver->disconnect) {
- spin_unlock(&priv_dev->lock);
+ if (priv_dev->gadget_driver && priv_dev->gadget_driver->disconnect)
priv_dev->gadget_driver->disconnect(&priv_dev->gadget);
- spin_lock(&priv_dev->lock);
- }
}
/**
*/
static void cdns3_check_usb_interrupt_proceed(struct cdns3_device *priv_dev,
u32 usb_ists)
+__must_hold(&priv_dev->lock)
{
int speed = 0;
/* Disconnection detected */
if (usb_ists & (USB_ISTS_DIS2I | USB_ISTS_DISI)) {
+ spin_unlock(&priv_dev->lock);
cdns3_disconnect_gadget(priv_dev);
+ spin_lock(&priv_dev->lock);
priv_dev->gadget.speed = USB_SPEED_UNKNOWN;
usb_gadget_set_state(&priv_dev->gadget, USB_STATE_NOTATTACHED);
cdns3_hw_reset_eps_config(priv_dev);
return 0;
}
-static void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev,
- struct cdns3_endpoint *priv_ep)
-{
- if (!priv_ep->use_streams || priv_dev->gadget.speed < USB_SPEED_SUPER)
- return;
-
- if (priv_dev->dev_ver >= DEV_VER_V3) {
- u32 mask = BIT(priv_ep->num + (priv_ep->dir ? 16 : 0));
-
- /*
- * Stream capable endpoints are handled by using ep_tdl
- * register. Other endpoints use TDL from TRB feature.
- */
- cdns3_clear_register_bit(&priv_dev->regs->tdl_from_trb, mask);
- }
-
- /* Enable Stream Bit TDL chk and SID chk */
- cdns3_set_register_bit(&priv_dev->regs->ep_cfg, EP_CFG_STREAM_EN |
- EP_CFG_TDL_CHK | EP_CFG_SID_CHK);
-}
-
static void cdns3_configure_dmult(struct cdns3_device *priv_dev,
struct cdns3_endpoint *priv_ep)
{
/**
* cdns3_ep_config Configure hardware endpoint
* @priv_ep: extended endpoint object
+ * @enable: set EP_CFG_ENABLE bit in ep_cfg register.
*/
-void cdns3_ep_config(struct cdns3_endpoint *priv_ep)
+int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable)
{
bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC);
struct cdns3_device *priv_dev = priv_ep->cdns3_dev;
break;
default:
/* all other speed are not supported */
- return;
+ return -EINVAL;
}
if (max_packet_size == 1024)
else
priv_ep->trb_burst_size = 16;
- ret = cdns3_ep_onchip_buffer_reserve(priv_dev, buffering + 1,
- !!priv_ep->dir);
- if (ret) {
- dev_err(priv_dev->dev, "onchip mem is full, ep is invalid\n");
- return;
+ /* onchip buffer is only allocated before configuration */
+ if (!priv_dev->hw_configured_flag) {
+ ret = cdns3_ep_onchip_buffer_reserve(priv_dev, buffering + 1,
+ !!priv_ep->dir);
+ if (ret) {
+ dev_err(priv_dev->dev, "onchip mem is full, ep is invalid\n");
+ return ret;
+ }
+ }
+
+ if (enable)
+ ep_cfg |= EP_CFG_ENABLE;
+
+ if (priv_ep->use_streams && priv_dev->gadget.speed >= USB_SPEED_SUPER) {
+ if (priv_dev->dev_ver >= DEV_VER_V3) {
+ u32 mask = BIT(priv_ep->num + (priv_ep->dir ? 16 : 0));
+
+ /*
+ * Stream capable endpoints are handled by using ep_tdl
+ * register. Other endpoints use TDL from TRB feature.
+ */
+ cdns3_clear_register_bit(&priv_dev->regs->tdl_from_trb,
+ mask);
+ }
+
+ /* Enable Stream Bit TDL chk and SID chk */
+ ep_cfg |= EP_CFG_STREAM_EN | EP_CFG_TDL_CHK | EP_CFG_SID_CHK;
}
ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) |
cdns3_select_ep(priv_dev, bEndpointAddress);
writel(ep_cfg, &priv_dev->regs->ep_cfg);
+ priv_ep->flags |= EP_CONFIGURED;
dev_dbg(priv_dev->dev, "Configure %s: with val %08x\n",
priv_ep->name, ep_cfg);
+
+ return 0;
}
/* Find correct direction for HW endpoint according to description */
u32 bEndpointAddress;
unsigned long flags;
int enable = 1;
- int ret;
+ int ret = 0;
int val;
priv_ep = ep_to_cdns3_ep(ep);
bEndpointAddress = priv_ep->num | priv_ep->dir;
cdns3_select_ep(priv_dev, bEndpointAddress);
+ /*
+ * For some versions of controller at some point during ISO OUT traffic
+ * DMA reads Transfer Ring for the EP which has never got doorbell.
+ * This issue was detected only on simulation, but to avoid this issue
+ * driver add protection against it. To fix it driver enable ISO OUT
+ * endpoint before setting DRBL. This special treatment of ISO OUT
+ * endpoints are recommended by controller specification.
+ */
+ if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && !priv_ep->dir)
+ enable = 0;
+
if (usb_ss_max_streams(comp_desc) && usb_endpoint_xfer_bulk(desc)) {
/*
* Enable stream support (SS mode) related interrupts
EP_STS_EN_SIDERREN | EP_STS_EN_MD_EXITEN |
EP_STS_EN_STREAMREN;
priv_ep->use_streams = true;
- cdns3_stream_ep_reconfig(priv_dev, priv_ep);
+ ret = cdns3_ep_config(priv_ep, enable);
priv_dev->using_streams |= true;
}
+ } else {
+ ret = cdns3_ep_config(priv_ep, enable);
}
- ret = cdns3_allocate_trb_pool(priv_ep);
+ if (ret)
+ goto exit;
+ ret = cdns3_allocate_trb_pool(priv_ep);
if (ret)
goto exit;
writel(reg, &priv_dev->regs->ep_sts_en);
- /*
- * For some versions of controller at some point during ISO OUT traffic
- * DMA reads Transfer Ring for the EP which has never got doorbell.
- * This issue was detected only on simulation, but to avoid this issue
- * driver add protection against it. To fix it driver enable ISO OUT
- * endpoint before setting DRBL. This special treatment of ISO OUT
- * endpoints are recommended by controller specification.
- */
- if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && !priv_ep->dir)
- enable = 0;
-
- if (enable)
- cdns3_set_register_bit(&priv_dev->regs->ep_cfg, EP_CFG_ENABLE);
-
ep->desc = desc;
priv_ep->flags &= ~(EP_PENDING_REQUEST | EP_STALLED | EP_STALL_PENDING |
EP_QUIRK_ISO_OUT_EN | EP_QUIRK_EXTRA_BUF_EN);
}
static int cdns3_gadget_suspend(struct cdns3 *cdns, bool do_wakeup)
+__must_hold(&cdns->lock)
{
struct cdns3_device *priv_dev = cdns->gadget_dev;
+ spin_unlock(&cdns->lock);
cdns3_disconnect_gadget(priv_dev);
+ spin_lock(&cdns->lock);
priv_dev->gadget.speed = USB_SPEED_UNKNOWN;
usb_gadget_set_state(&priv_dev->gadget, USB_STATE_NOTATTACHED);
#define TRB_TDL_SS_SIZE_GET(p) (((p) & GENMASK(23, 17)) >> 17)
/* transfer_len bitmasks - bits 31:24 */
-#define TRB_BURST_LEN(p) (((p) << 24) & GENMASK(31, 24))
+#define TRB_BURST_LEN(p) ((unsigned int)((p) << 24) & GENMASK(31, 24))
#define TRB_BURST_LEN_GET(p) (((p) & GENMASK(31, 24)) >> 24)
/* Data buffer pointer bitmasks*/
#define EP_QUIRK_EXTRA_BUF_DET BIT(12)
#define EP_QUIRK_EXTRA_BUF_EN BIT(13)
#define EP_TDLCHK_EN BIT(15)
+#define EP_CONFIGURED BIT(16)
u32 flags;
struct cdns3_request *descmis_req;
int cdns3_init_ep0(struct cdns3_device *priv_dev,
struct cdns3_endpoint *priv_ep);
void cdns3_ep0_config(struct cdns3_device *priv_dev);
-void cdns3_ep_config(struct cdns3_endpoint *priv_ep);
+int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable);
void cdns3_check_ep0_interrupt_proceed(struct cdns3_device *priv_dev, int dir);
int __cdns3_gadget_wakeup(struct cdns3_device *priv_dev);
"%s - cooling babbling device\n", __func__);
usb_mark_last_busy(acm->dev);
set_bit(rb->index, &acm->urbs_in_error_delay);
+ set_bit(ACM_ERROR_DELAY, &acm->flags);
cooldown = true;
break;
default:
if (stopped || stalled || cooldown) {
if (stalled)
- schedule_work(&acm->work);
+ schedule_delayed_work(&acm->dwork, 0);
else if (cooldown)
schedule_delayed_work(&acm->dwork, HZ / 2);
return;
acm_write_done(acm, wb);
spin_unlock_irqrestore(&acm->write_lock, flags);
set_bit(EVENT_TTY_WAKEUP, &acm->flags);
- schedule_work(&acm->work);
+ schedule_delayed_work(&acm->dwork, 0);
}
static void acm_softint(struct work_struct *work)
{
int i;
- struct acm *acm = container_of(work, struct acm, work);
+ struct acm *acm = container_of(work, struct acm, dwork.work);
if (test_bit(EVENT_RX_STALL, &acm->flags)) {
smp_mb(); /* against acm_suspend() */
if (test_and_clear_bit(ACM_ERROR_DELAY, &acm->flags)) {
for (i = 0; i < acm->rx_buflimit; i++)
if (test_and_clear_bit(i, &acm->urbs_in_error_delay))
- acm_submit_read_urb(acm, i, GFP_NOIO);
+ acm_submit_read_urb(acm, i, GFP_KERNEL);
}
if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))
acm->ctrlsize = ctrlsize;
acm->readsize = readsize;
acm->rx_buflimit = num_rx_buf;
- INIT_WORK(&acm->work, acm_softint);
INIT_DELAYED_WORK(&acm->dwork, acm_softint);
init_waitqueue_head(&acm->wioctl);
spin_lock_init(&acm->write_lock);
}
acm_kill_urbs(acm);
- cancel_work_sync(&acm->work);
cancel_delayed_work_sync(&acm->dwork);
tty_unregister_device(acm_tty_driver, acm->minor);
return 0;
acm_kill_urbs(acm);
- cancel_work_sync(&acm->work);
cancel_delayed_work_sync(&acm->dwork);
acm->urbs_in_error_delay = 0;
{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
+ { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */
+ .driver_info = DISABLE_ECHO, /* Don't echo banner */
+ },
+ { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */
+ .driver_info = DISABLE_ECHO, /* Don't echo banner */
+ },
+ { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */
+ .driver_info = DISABLE_ECHO, /* Don't echo banner */
+ },
{ USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
# define ACM_ERROR_DELAY 3
unsigned long urbs_in_error_delay; /* these need to be restarted after a delay */
struct usb_cdc_line_coding line; /* bits, stop, parity */
- struct work_struct work; /* work queue entry for various purposes*/
- struct delayed_work dwork; /* for cool downs needed in error recovery */
+ struct delayed_work dwork; /* work queue entry for various purposes */
unsigned int ctrlin; /* input control lines (DCD, DSR, RI, break, overruns) */
unsigned int ctrlout; /* output control lines (DTR, RTS) */
struct async_icount iocount; /* counters for control line changes */
if (userurb) { /* Async */
if (when == SUBMIT)
- dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, "
+ dev_info(&udev->dev, "userurb %px, ep%d %s-%s, "
"length %u\n",
userurb, ep, t, d, length);
else
- dev_info(&udev->dev, "userurb %pK, ep%d %s-%s, "
+ dev_info(&udev->dev, "userurb %px, ep%d %s-%s, "
"actual_length %u status %d\n",
userurb, ep, t, d, length,
timeout_or_status);
if (as) {
int retval;
- snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %px\n", as->userurb);
retval = processcompl(as, (void __user * __user *)arg);
free_async(as);
return retval;
as = async_getcompleted(ps);
if (as) {
- snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %px\n", as->userurb);
retval = processcompl(as, (void __user * __user *)arg);
free_async(as);
} else {
if (as) {
int retval;
- snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %px\n", as->userurb);
retval = processcompl_compat(as, (void __user * __user *)arg);
free_async(as);
return retval;
as = async_getcompleted(ps);
if (as) {
- snoop(&ps->dev->dev, "reap %pK\n", as->userurb);
+ snoop(&ps->dev->dev, "reap %px\n", as->userurb);
retval = processcompl_compat(as, (void __user * __user *)arg);
free_async(as);
} else {
#endif
case USBDEVFS_DISCARDURB:
- snoop(&dev->dev, "%s: DISCARDURB %pK\n", __func__, p);
+ snoop(&dev->dev, "%s: DISCARDURB %px\n", __func__, p);
ret = proc_unlinkurb(ps, p);
break;
return NULL;
}
+bool usb_driver_applicable(struct usb_device *udev,
+ struct usb_device_driver *udrv)
+{
+ if (udrv->id_table && udrv->match)
+ return usb_device_match_id(udev, udrv->id_table) != NULL &&
+ udrv->match(udev);
+
+ if (udrv->id_table)
+ return usb_device_match_id(udev, udrv->id_table) != NULL;
+
+ if (udrv->match)
+ return udrv->match(udev);
+
+ return false;
+}
+
static int usb_device_match(struct device *dev, struct device_driver *drv)
{
/* devices and interfaces are handled separately */
udev = to_usb_device(dev);
udrv = to_usb_device_driver(drv);
- if (udrv->id_table)
- return usb_device_match_id(udev, udrv->id_table) != NULL;
-
- if (udrv->match)
- return udrv->match(udev);
-
/* If the device driver under consideration does not have a
* id_table or a match function, then let the driver's probe
* function decide.
*/
- return 1;
+ if (!udrv->id_table && !udrv->match)
+ return 1;
+
+ return usb_driver_applicable(udev, udrv);
} else if (is_usb_interface(dev)) {
struct usb_interface *intf;
return 0;
udev = to_usb_device(dev);
- if (usb_device_match_id(udev, new_udriver->id_table) == NULL &&
- (!new_udriver->match || new_udriver->match(udev) == 0))
+ if (!usb_driver_applicable(udev, new_udriver))
return 0;
ret = device_reprobe(dev);
udrv = to_usb_device_driver(drv);
if (udrv == &usb_generic_driver)
return 0;
- if (usb_device_match_id(udev, udrv->id_table) != NULL)
- return 1;
- return (udrv->match && udrv->match(udev));
+ return usb_driver_applicable(udev, udrv);
}
static bool usb_generic_driver_match(struct usb_device *udev)
/* Guillemot Webcam Hercules Dualpix Exchange*/
{ USB_DEVICE(0x06f8, 0x3005), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Guillemot Hercules DJ Console audio card (BZ 208357) */
+ { USB_DEVICE(0x06f8, 0xb000), .driver_info =
+ USB_QUIRK_ENDPOINT_IGNORE },
+
/* Midiman M-Audio Keystation 88es */
{ USB_DEVICE(0x0763, 0x0192), .driver_info = USB_QUIRK_RESET_RESUME },
{ USB_DEVICE(0x0926, 0x3333), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
+ /* Kingston DataTraveler 3.0 */
+ { USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM },
+
/* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */
{ USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF },
{ USB_DEVICE(0x1532, 0x0116), .driver_info =
USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
+ /* Lenovo ThinkCenter A630Z TI024Gen3 usb-audio */
+ { USB_DEVICE(0x17ef, 0xa012), .driver_info =
+ USB_QUIRK_DISCONNECT_SUSPEND },
+
/* BUILDWIN Photo Frame */
{ USB_DEVICE(0x1908, 0x1315), .driver_info =
USB_QUIRK_HONOR_BNUMINTERFACES },
* Matched for devices with USB_QUIRK_ENDPOINT_IGNORE.
*/
static const struct usb_device_id usb_endpoint_ignore[] = {
+ { USB_DEVICE_INTERFACE_NUMBER(0x06f8, 0xb000, 5), .driver_info = 0x01 },
+ { USB_DEVICE_INTERFACE_NUMBER(0x06f8, 0xb000, 5), .driver_info = 0x81 },
{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0208, 1), .driver_info = 0x85 },
{ }
const struct usb_device_id *id);
extern const struct usb_device_id *usb_device_match_id(struct usb_device *udev,
const struct usb_device_id *id);
+extern bool usb_driver_applicable(struct usb_device *udev,
+ struct usb_device_driver *udrv);
extern void usb_forced_unbind_intf(struct usb_interface *intf);
extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev);
#endif /* CONFIG_USB_DWC2_PERIPHERAL || CONFIG_USB_DWC2_DUAL_ROLE */
return 0;
+#if IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) || \
+ IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)
error_debugfs:
dwc2_debugfs_exit(hsotg);
if (hsotg->hcd_enabled)
dwc2_hcd_remove(hsotg);
+#endif
error_drd:
dwc2_drd_exit(hsotg);
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* core.c - DesignWare USB3 DRD Controller Core file
*
* Copyright (C) 2010-2011 Texas Instruments Incorporated - https://www.ti.com
#define DWC3_DEPEVT_EPCMDCMPLT 0x07
/**
- * struct dwc3_event_depvt - Device Endpoint Events
+ * struct dwc3_event_depevt - Device Endpoint Events
* @one_bit: indicates this is an endpoint event (not used)
* @endpoint_number: number of the endpoint
* @endpoint_event: The event we have:
#define PCI_DEVICE_ID_INTEL_TGPLP 0xa0ee
#define PCI_DEVICE_ID_INTEL_TGPH 0x43ee
#define PCI_DEVICE_ID_INTEL_JSP 0x4dee
+#define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1
#define PCI_INTEL_BXT_DSM_GUID "732b85d5-b7a7-4a1b-9ba0-4bbd00ffd511"
#define PCI_INTEL_BXT_FUNC_PMU_PWR 4
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP),
(kernel_ulong_t) &dwc3_pci_intel_properties, },
+ { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS),
+ (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB),
(kernel_ulong_t) &dwc3_pci_amd_properties, },
{ } /* Terminating Entry */
{
unsigned int direction = !dwc->ep0_expect_in;
+ dwc->delayed_status = false;
+
if (dwc->ep0state != EP0_STATUS_PHASE)
return;
- dwc->delayed_status = false;
__dwc3_ep0_do_control_status(dwc, dwc->eps[direction]);
}
EXPORT_SYMBOL_GPL(usb_string_id);
/**
- * usb_string_ids() - allocate unused string IDs in batch
+ * usb_string_ids_tab() - allocate unused string IDs in batch
* @cdev: the device whose string descriptor IDs are being allocated
* @str: an array of usb_string objects to assign numbers to
* Context: single threaded during gadget setup
case FUNCTIONFS_ENDPOINT_DESC:
{
int desc_idx;
- struct usb_endpoint_descriptor *desc;
+ struct usb_endpoint_descriptor desc1, *desc;
switch (epfile->ffs->gadget->speed) {
case USB_SPEED_SUPER:
default:
desc_idx = 0;
}
+
desc = epfile->ep->descs[desc_idx];
+ memcpy(&desc1, desc, desc->bLength);
spin_unlock_irq(&epfile->ffs->eps_lock);
- ret = copy_to_user((void __user *)value, desc, desc->bLength);
+ ret = copy_to_user((void __user *)value, &desc1, desc1.bLength);
if (ret)
ret = -EFAULT;
return ret;
midi->id = kstrdup(opts->id, GFP_KERNEL);
if (opts->id && !midi->id) {
status = -ENOMEM;
- goto setup_fail;
+ goto midi_free;
}
midi->in_ports = opts->in_ports;
midi->out_ports = opts->out_ports;
status = kfifo_alloc(&midi->in_req_fifo, midi->qlen, GFP_KERNEL);
if (status)
- goto setup_fail;
+ goto midi_free;
spin_lock_init(&midi->transmit_lock);
return &midi->func;
+midi_free:
+ if (midi)
+ kfree(midi->id);
+ kfree(midi);
setup_fail:
mutex_unlock(&opts->lock);
- kfree(midi);
+
return ERR_PTR(status);
}
return 0;
Enomem:
+ kfree(CHIP);
+ CHIP = NULL;
+
return -ENOMEM;
}
return -ENODEV;
}
length = min(arg.length, event->length);
- if (copy_to_user((void __user *)value, event, sizeof(*event) + length))
+ if (copy_to_user((void __user *)value, event, sizeof(*event) + length)) {
+ kfree(event);
return -EFAULT;
+ }
+ kfree(event);
return 0;
}
u32 bitmask;
struct ep_queue_head *qh;
- if (!_ep || _ep->desc || !(_ep->desc->bEndpointAddress&0xF))
+ if (!_ep || !_ep->desc || !(_ep->desc->bEndpointAddress&0xF))
return -ENODEV;
ep = container_of(_ep, struct fsl_ep, ep);
goto err;
}
+ pci_set_drvdata(pdev, dev);
spin_lock_init(&dev->lock);
dev->pdev = pdev;
dev->gadget.ops = &goku_ops;
}
dev->regs = (struct goku_udc_regs __iomem *) base;
- pci_set_drvdata(pdev, dev);
INFO(dev, "%s\n", driver_desc);
INFO(dev, "version: " DRIVER_VERSION " %s\n", dmastr());
INFO(dev, "irq %d, pci mem %p\n", pdev->irq, base);
u_phy->otg->host = hcd_to_bus(hcd);
irq = platform_get_irq(pdev, 0);
- if (!irq) {
- err = -ENODEV;
+ if (irq < 0) {
+ err = irq;
goto cleanup_phy;
}
pdev->dev.coherent_dma_mask = ofdev->dev.coherent_dma_mask;
- if (!pdev->dev.dma_mask)
+ if (!pdev->dev.dma_mask) {
pdev->dev.dma_mask = &ofdev->dev.coherent_dma_mask;
- else
- dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ } else {
+ retval = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
+ if (retval)
+ goto error;
+ }
retval = platform_device_add_data(pdev, pdata, sizeof(*pdata));
if (retval)
| ((1 << 5/*usb1*/) | (1 << 3/*usb2*/)),
INNOVATOR_FPGA_CAM_USB_CONTROL);
else if (priv->power)
- gpiod_set_value(priv->power, 0);
+ gpiod_set_value_cansleep(priv->power, 0);
} else {
if (machine_is_omap_innovator() && cpu_is_omap1510())
__raw_writeb(__raw_readb(INNOVATOR_FPGA_CAM_USB_CONTROL)
& ~((1 << 5/*usb1*/) | (1 << 3/*usb2*/)),
INNOVATOR_FPGA_CAM_USB_CONTROL);
else if (priv->power)
- gpiod_set_value(priv->power, 1);
+ gpiod_set_value_cansleep(priv->power, 1);
}
return 0;
/* Initialize dma_mask and coherent_dma_mask to 32-bits */
ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
if (ret)
- return ret;
+ goto disable_pm;
hcd = usb_create_hcd(driver, dev, dev_name(dev));
if (!hcd) {
if (!rhub->num_ports)
return;
- rhub->ports = kcalloc_node(rhub->num_ports, sizeof(rhub->ports), flags,
- dev_to_node(dev));
+ rhub->ports = kcalloc_node(rhub->num_ports, sizeof(*rhub->ports),
+ flags, dev_to_node(dev));
for (i = 0; i < HCS_MAX_PORTS(xhci->hcs_params1); i++) {
if (xhci->hw_ports[i].rhub != rhub ||
xhci->hw_ports[i].hcd_portnum == DUPLICATE_ENTRY)
#define SSIC_PORT_CFG2_OFFSET 0x30
#define PROG_DONE (1 << 30)
#define SSIC_PORT_UNUSED (1 << 31)
+#define SPARSE_DISABLE_BIT 17
+#define SPARSE_CNTL_ENABLE 0xC12C
/* Device for a quirk */
#define PCI_VENDOR_ID_FRESCO_LOGIC 0x1b73
(pdev->device == 0x15e0 || pdev->device == 0x15e1))
xhci->quirks |= XHCI_SNPS_BROKEN_SUSPEND;
+ if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x15e5)
+ xhci->quirks |= XHCI_DISABLE_SPARSE;
+
if (pdev->vendor == PCI_VENDOR_ID_AMD)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
readl(reg);
}
+static void xhci_sparse_control_quirk(struct usb_hcd *hcd)
+{
+ u32 reg;
+
+ reg = readl(hcd->regs + SPARSE_CNTL_ENABLE);
+ reg &= ~BIT(SPARSE_DISABLE_BIT);
+ writel(reg, hcd->regs + SPARSE_CNTL_ENABLE);
+}
+
static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
if (xhci->quirks & XHCI_SSIC_PORT_UNUSED)
xhci_ssic_port_unused_quirk(hcd, true);
+ if (xhci->quirks & XHCI_DISABLE_SPARSE)
+ xhci_sparse_control_quirk(hcd);
+
ret = xhci_suspend(xhci, do_wakeup);
if (ret && (xhci->quirks & XHCI_SSIC_PORT_UNUSED))
xhci_ssic_port_unused_quirk(hcd, false);
xhci_dbg(xhci, "Slot %u ep ctx %u now has streams.\n",
udev->slot_id, ep_index);
vdev->eps[ep_index].ep_state |= EP_HAS_STREAMS;
- xhci_debugfs_create_stream_files(xhci, vdev, ep_index);
}
xhci_free_command(xhci, config_cmd);
spin_unlock_irqrestore(&xhci->lock, flags);
+ for (i = 0; i < num_eps; i++) {
+ ep_index = xhci_get_endpoint_index(&eps[i]->desc);
+ xhci_debugfs_create_stream_files(xhci, vdev, ep_index);
+ }
/* Subtract 1 for stream 0, which drivers can't use */
return num_streams - 1;
#define XHCI_SNPS_BROKEN_SUSPEND BIT_ULL(35)
#define XHCI_RENESAS_FW_QUIRK BIT_ULL(36)
#define XHCI_SKIP_PHY_INIT BIT_ULL(37)
+#define XHCI_DISABLE_SPARSE BIT_ULL(38)
unsigned int num_active_eps;
unsigned int limit_active_eps;
dev_dbg(&mfi->udev->dev, "prop: %d\n", psp);
ret = pm_runtime_get_sync(&mfi->udev->dev);
- if (ret < 0)
+ if (ret < 0) {
+ pm_runtime_put_noidle(&mfi->udev->dev);
return ret;
+ }
switch (psp) {
case POWER_SUPPLY_PROP_CHARGE_TYPE:
.property_is_writeable = apple_mfi_fc_property_is_writeable
};
+static bool mfi_fc_match(struct usb_device *udev)
+{
+ int idProduct;
+
+ idProduct = le16_to_cpu(udev->descriptor.idProduct);
+ /* See comment above mfi_fc_id_table[] */
+ return (idProduct >= 0x1200 && idProduct <= 0x12ff);
+}
+
static int mfi_fc_probe(struct usb_device *udev)
{
struct power_supply_config battery_cfg = {};
struct mfi_device *mfi = NULL;
- int err, idProduct;
+ int err;
- idProduct = le16_to_cpu(udev->descriptor.idProduct);
- /* See comment above mfi_fc_id_table[] */
- if (idProduct < 0x1200 || idProduct > 0x12ff) {
+ if (!mfi_fc_match(udev))
return -ENODEV;
- }
mfi = kzalloc(sizeof(struct mfi_device), GFP_KERNEL);
if (!mfi) {
.probe = mfi_fc_probe,
.disconnect = mfi_fc_disconnect,
.id_table = mfi_fc_id_table,
+ .match = mfi_fc_match,
.generic_subclass = 1,
};
spin_unlock_irqrestore(&mtu->lock, flags);
+ synchronize_irq(mtu->irq);
return 0;
}
struct platform_device *parent = to_platform_device(dev->parent);
const struct dsps_musb_wrapper *wrp = glue->wrp;
void __iomem *reg_base;
+ struct resource *r;
u32 rev, val;
int ret;
- reg_base = devm_platform_ioremap_resource_byname(parent, "control");
+ r = platform_get_resource_byname(parent, IORESOURCE_MEM, "control");
+ reg_base = devm_ioremap_resource(dev, r);
if (IS_ERR(reg_base))
return PTR_ERR(reg_base);
musb->ctrl_base = reg_base;
#define CH341_QUIRK_SIMULATE_BREAK BIT(1)
static const struct usb_device_id id_table[] = {
- { USB_DEVICE(0x4348, 0x5523) },
+ { USB_DEVICE(0x1a86, 0x5512) },
+ { USB_DEVICE(0x1a86, 0x5523) },
{ USB_DEVICE(0x1a86, 0x7522) },
{ USB_DEVICE(0x1a86, 0x7523) },
- { USB_DEVICE(0x1a86, 0x5523) },
+ { USB_DEVICE(0x4348, 0x5523) },
{ },
};
MODULE_DEVICE_TABLE(usb, id_table);
struct device *dev = &port->dev;
int status = urb->status;
unsigned long flags;
+ bool resubmitted = false;
- set_bit(0, &port->write_urbs_free);
if (status) {
dev_dbg(dev, "%s - nonzero write bulk status received: %d\n",
__func__, status);
+ set_bit(0, &port->write_urbs_free);
return;
}
goto exit;
}
+ resubmitted = true;
+
dev_dbg(dev, "%s - priv->wrsent=%d\n", __func__, priv->wrsent);
dev_dbg(dev, "%s - priv->wrfilled=%d\n", __func__, priv->wrfilled);
exit:
spin_unlock_irqrestore(&priv->lock, flags);
+ if (!resubmitted)
+ set_bit(0, &port->write_urbs_free);
usb_serial_port_softint(port);
}
priv->cfg.unknown2 = cfg->unknown2;
spin_unlock_irqrestore(&priv->lock, flags);
+ kfree(cfg);
+
/* READ_ON and urb submission */
rc = usb_serial_generic_open(tty, port);
- if (rc) {
- retval = rc;
- goto err_free_cfg;
- }
+ if (rc)
+ return rc;
rc = usb_control_msg(port->serial->dev,
usb_sndctrlpipe(port->serial->dev, 0),
KLSI_TIMEOUT);
err_generic_close:
usb_serial_generic_close(port);
-err_free_cfg:
- kfree(cfg);
return retval;
}
#define QUECTEL_PRODUCT_EP06 0x0306
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
+#define QUECTEL_PRODUCT_EC200T 0x6026
#define CMOTECH_VENDOR_ID 0x16d8
#define CMOTECH_PRODUCT_6001 0x6001
#define CINTERION_PRODUCT_PH8 0x0053
#define CINTERION_PRODUCT_AHXX 0x0055
#define CINTERION_PRODUCT_PLXX 0x0060
+#define CINTERION_PRODUCT_EXS82 0x006c
#define CINTERION_PRODUCT_PH8_2RMNET 0x0082
#define CINTERION_PRODUCT_PH8_AUDIO 0x0083
#define CINTERION_PRODUCT_AHXX_2RMNET 0x0084
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff),
.driver_info = NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) },
- { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0xff, 0xff),
- .driver_info = NUMEP2 },
- { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96, 0xff, 0, 0) },
+ { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96),
+ .driver_info = RSVD(4) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10),
.driver_info = ZLP },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
.driver_info = NCTRL(0) | RSVD(1) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1054, 0xff), /* Telit FT980-KS */
.driver_info = NCTRL(2) | RSVD(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1055, 0xff), /* Telit FN980 (PCIe) */
+ .driver_info = NCTRL(0) | RSVD(1) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
.driver_info = NCTRL(0) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1203, 0xff), /* Telit LE910Cx (RNDIS) */
+ .driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1230, 0xff), /* Telit LE910Cx (rmnet) */
+ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */
+ .driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, 0x1260),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
{ USB_DEVICE(TELIT_VENDOR_ID, 0x1261),
{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_AUDIO, 0xff) },
{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_CLS8, 0xff),
.driver_info = RSVD(0) | RSVD(4) },
+ { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EXS82, 0xff) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) },
.driver_info = RSVD(0) | RSVD(1) | RSVD(6) },
{ USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */
.driver_info = RSVD(0) | RSVD(1) | RSVD(6) },
- { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 */
+ { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */
.driver_info = RSVD(4) | RSVD(5) | RSVD(6) },
{ USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */
.driver_info = RSVD(4) | RSVD(5) },
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */
.driver_info = RSVD(6) },
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */
static int slave_configure(struct scsi_device *sdev)
{
struct us_data *us = host_to_us(sdev->host);
- struct device *dev = sdev->host->dma_dev;
+ struct device *dev = us->pusb_dev->bus->sysdev;
/*
* Many devices have trouble transferring more than 32KB at a time,
*/
blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
+ if (devinfo->flags & US_FL_MAX_SECTORS_64)
+ blk_queue_max_hw_sectors(sdev->request_queue, 64);
+ else if (devinfo->flags & US_FL_MAX_SECTORS_240)
+ blk_queue_max_hw_sectors(sdev->request_queue, 240);
+
return 0;
}
static int uas_slave_configure(struct scsi_device *sdev)
{
struct uas_dev_info *devinfo = sdev->hostdata;
- struct device *dev = sdev->host->dma_dev;
-
- if (devinfo->flags & US_FL_MAX_SECTORS_64)
- blk_queue_max_hw_sectors(sdev->request_queue, 64);
- else if (devinfo->flags & US_FL_MAX_SECTORS_240)
- blk_queue_max_hw_sectors(sdev->request_queue, 240);
- else if (devinfo->udev->speed >= USB_SPEED_SUPER)
- blk_queue_max_hw_sectors(sdev->request_queue, 2048);
-
- blk_queue_max_hw_sectors(sdev->request_queue,
- min_t(size_t, queue_max_hw_sectors(sdev->request_queue),
- dma_max_mapping_size(dev) >> SECTOR_SHIFT));
if (devinfo->flags & US_FL_NO_REPORT_OPCODES)
sdev->no_report_opcodes = 1;
shost->can_queue = devinfo->qdepth - 2;
usb_set_intfdata(intf, shost);
- result = scsi_add_host_with_dma(shost, &intf->dev, udev->bus->sysdev);
+ result = scsi_add_host(shost, &intf->dev);
if (result)
goto free_streams;
goto BadDevice;
usb_autopm_get_interface_no_resume(us->pusb_intf);
snprintf(us->scsi_name, sizeof(us->scsi_name), "usb-storage %s",
- dev_name(dev));
- result = scsi_add_host_with_dma(us_to_host(us), dev,
- us->pusb_dev->bus->sysdev);
+ dev_name(&us->pusb_intf->dev));
+ result = scsi_add_host(us_to_host(us), dev);
if (result) {
dev_warn(dev,
"Unable to add the scsi host\n");
config TYPEC_QCOM_PMIC
tristate "Qualcomm PMIC USB Type-C driver"
depends on ARCH_QCOM || COMPILE_TEST
+ depends on USB_ROLE_SWITCH || !USB_ROLE_SWITCH
help
Driver for supporting role switch over the Qualcomm PMIC. This will
handle the USB Type-C role and orientation detection reported by the
EXPORT_SYMBOL_GPL(fwnode_typec_switch_get);
/**
- * typec_put_switch - Release USB Type-C orientation switch
+ * typec_switch_put - Release USB Type-C orientation switch
* @sw: USB Type-C orientation switch
*
* Decrement reference count for @sw.
*/
ret = fwnode_property_read_string(fwnode, "power-role", &cap_str);
if (!ret) {
- chip->port_type = typec_find_port_power_role(cap_str);
- if (chip->port_type < 0) {
- ret = chip->port_type;
+ ret = typec_find_port_power_role(cap_str);
+ if (ret < 0)
return ret;
- }
+ chip->port_type = ret;
}
chip->capability.type = chip->port_type;
* Supported power operation mode can be configured through device tree
* else it is read from chip registers in stusb160x_get_caps.
*/
- ret = fwnode_property_read_string(fwnode, "power-opmode", &cap_str);
+ ret = fwnode_property_read_string(fwnode, "typec-power-opmode", &cap_str);
if (!ret) {
- chip->pwr_opmode = typec_find_pwr_opmode(cap_str);
+ ret = typec_find_pwr_opmode(cap_str);
/* Power delivery not yet supported */
- if (chip->pwr_opmode < 0 ||
- chip->pwr_opmode == TYPEC_PWR_MODE_PD) {
- ret = chip->pwr_opmode < 0 ? chip->pwr_opmode : -EINVAL;
- dev_err(chip->dev, "bad power operation mode: %d\n",
- chip->pwr_opmode);
- return ret;
+ if (ret < 0 || ret == TYPEC_PWR_MODE_PD) {
+ dev_err(chip->dev, "bad power operation mode: %d\n", ret);
+ return -EINVAL;
}
+ chip->pwr_opmode = ret;
}
return 0;
{ .compatible = "st,stusb1600", .data = &stusb1600_regmap_config},
{},
};
+MODULE_DEVICE_TABLE(of, stusb160x_of_match);
static int stusb160x_probe(struct i2c_client *client)
{
}
chip->port = typec_register_port(chip->dev, &chip->capability);
- if (!chip->port) {
- ret = -ENODEV;
+ if (IS_ERR(chip->port)) {
+ ret = PTR_ERR(chip->port);
goto all_reg_disable;
}
static void tcpm_detach(struct tcpm_port *port)
{
+ if (tcpm_port_is_disconnected(port))
+ port->hard_reset_count = 0;
+
if (!port->attached)
return;
port->tcpc->set_bist_data(port->tcpc, false);
}
- if (tcpm_port_is_disconnected(port))
- port->hard_reset_count = 0;
-
tcpm_reset_port(port);
}
return;
power_supply_unregister(con->psy);
+ con->psy = NULL;
+}
+
+void ucsi_port_psy_changed(struct ucsi_connector *con)
+{
+ if (IS_ERR_OR_NULL(con->psy))
+ return;
+
+ power_supply_changed(con->psy);
}
role = !!(con->status.flags & UCSI_CONSTAT_PWR_DIR);
if (con->status.change & UCSI_CONSTAT_POWER_OPMODE_CHANGE ||
- con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE)
+ con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) {
ucsi_pwr_opmode_change(con);
+ ucsi_port_psy_changed(con);
+ }
if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) {
typec_set_pwr_role(con->port, role);
ucsi_register_partner(con);
else
ucsi_unregister_partner(con);
+
+ ucsi_port_psy_changed(con);
}
if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) {
!!(con->status.flags & UCSI_CONSTAT_PWR_DIR));
ucsi_pwr_opmode_change(con);
ucsi_register_partner(con);
+ ucsi_port_psy_changed(con);
}
if (con->partner) {
#if IS_ENABLED(CONFIG_POWER_SUPPLY)
int ucsi_register_port_psy(struct ucsi_connector *con);
void ucsi_unregister_port_psy(struct ucsi_connector *con);
+void ucsi_port_psy_changed(struct ucsi_connector *con);
#else
static inline int ucsi_register_port_psy(struct ucsi_connector *con) { return 0; }
static inline void ucsi_unregister_port_psy(struct ucsi_connector *con) { }
+static inline void ucsi_port_psy_changed(struct ucsi_connector *con) { }
#endif /* CONFIG_POWER_SUPPLY */
#if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE)
depends on RUNTIME_TESTING_MENU && HAS_DMA
select DMA_OPS
select VHOST_RING
+ select GENERIC_NET_UTILS
default n
help
vDPA networking device simulator which loop TX traffic back
config MLX5_VDPA
bool
+ select VHOST_IOTLB
help
Support library for Mellanox VDPA drivers. Provides code that is
common for all types of VDPA drivers. The following drivers are planned:
u64 paend;
struct scatterlist *sg;
struct device *dma = mvdev->mdev->device;
- int ret;
for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) {
done:
mr->log_size = log_entity_size;
mr->nsg = nsg;
- ret = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
- if (!ret)
+ err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
+ if (!err)
goto err_map;
err = create_direct_mr(mvdev, mr);
module_param(batch_mapping, int, 0444);
MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
+static char *macaddr;
+module_param(macaddr, charp, 0);
+MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
+
struct vdpasim_virtqueue {
struct vringh vring;
struct vringh_kiov iov;
static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
(1ULL << VIRTIO_F_VERSION_1) |
- (1ULL << VIRTIO_F_ACCESS_PLATFORM);
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
+ (1ULL << VIRTIO_NET_F_MAC);
/* State of each vdpasim device */
struct vdpasim {
spin_lock_init(&vdpasim->iommu_lock);
dev = &vdpasim->vdpa.dev;
- dev->coherent_dma_mask = DMA_BIT_MASK(64);
+ dev->dma_mask = &dev->coherent_dma_mask;
+ if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)))
+ goto err_iommu;
set_dma_ops(dev, &vdpasim_dma_ops);
vdpasim->iommu = vhost_iotlb_alloc(2048, 0);
if (!vdpasim->buffer)
goto err_iommu;
- eth_random_addr(vdpasim->config.mac);
+ if (macaddr) {
+ mac_pton(macaddr, vdpasim->config.mac);
+ if (!is_valid_ether_addr(vdpasim->config.mac)) {
+ ret = -EADDRNOTAVAIL;
+ goto err_iommu;
+ }
+ } else {
+ eth_random_addr(vdpasim->config.mac);
+ }
vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu);
vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
return vdpasim->generation;
}
+static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)
+{
+ struct vdpa_iova_range range = {
+ .first = 0ULL,
+ .last = ULLONG_MAX,
+ };
+
+ return range;
+}
+
static int vdpasim_set_map(struct vdpa_device *vdpa,
struct vhost_iotlb *iotlb)
{
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
.get_generation = vdpasim_get_generation,
+ .get_iova_range = vdpasim_get_iova_range,
.dma_map = vdpasim_dma_map,
.dma_unmap = vdpasim_dma_unmap,
.free = vdpasim_free,
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
.get_generation = vdpasim_get_generation,
+ .get_iova_range = vdpasim_get_iova_range,
.set_map = vdpasim_set_map,
.free = vdpasim_free,
};
info.size = vdev->regions[info.index].size;
info.flags = vdev->regions[info.index].flags;
- return copy_to_user((void __user *)arg, &info, minsz);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+ return 0;
}
case VFIO_DEVICE_GET_IRQ_INFO:
{
info.flags = VFIO_IRQ_INFO_EVENTFD;
info.count = 1;
- return copy_to_user((void __user *)arg, &info, minsz);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+ return 0;
}
case VFIO_DEVICE_SET_IRQS:
{
{
struct vfio_fsl_mc_device *vdev = device_data;
struct fsl_mc_device *mc_dev = vdev->mc_dev;
- int index;
+ unsigned int index;
index = vma->vm_pgoff >> (VFIO_FSL_MC_OFFSET_SHIFT - PAGE_SHIFT);
#include "linux/fsl/mc.h"
#include "vfio_fsl_mc_private.h"
-int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev)
+static int vfio_fsl_mc_irqs_allocate(struct vfio_fsl_mc_device *vdev)
{
struct fsl_mc_device *mc_dev = vdev->mc_dev;
struct vfio_fsl_mc_irq *mc_irq;
pdev->vendor == PCI_VENDOR_ID_INTEL &&
IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
ret = vfio_pci_igd_init(vdev);
- if (ret) {
+ if (ret && ret != -ENODEV) {
pci_warn(pdev, "Failed to setup Intel IGD regions\n");
goto disable_exit;
}
return done;
}
-static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
+static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
+ bool test_mem)
{
- struct vfio_pci_ioeventfd *ioeventfd = opaque;
-
switch (ioeventfd->count) {
case 1:
- vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite8(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
case 2:
- vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite16(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
case 4:
- vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite32(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
#ifdef iowrite64
case 8:
- vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem,
+ vfio_pci_iowrite64(ioeventfd->vdev, test_mem,
ioeventfd->data, ioeventfd->addr);
break;
#endif
}
+}
+
+static int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
+{
+ struct vfio_pci_ioeventfd *ioeventfd = opaque;
+ struct vfio_pci_device *vdev = ioeventfd->vdev;
+
+ if (ioeventfd->test_mem) {
+ if (!down_read_trylock(&vdev->memory_lock))
+ return 1; /* Lock contended, use thread */
+ if (!__vfio_pci_memory_enabled(vdev)) {
+ up_read(&vdev->memory_lock);
+ return 0;
+ }
+ }
+
+ vfio_pci_ioeventfd_do_write(ioeventfd, false);
+
+ if (ioeventfd->test_mem)
+ up_read(&vdev->memory_lock);
return 0;
}
+static void vfio_pci_ioeventfd_thread(void *opaque, void *unused)
+{
+ struct vfio_pci_ioeventfd *ioeventfd = opaque;
+
+ vfio_pci_ioeventfd_do_write(ioeventfd, ioeventfd->test_mem);
+}
+
long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
uint64_t data, int count, int fd)
{
ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM;
ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler,
- NULL, NULL, &ioeventfd->virqfd, fd);
+ vfio_pci_ioeventfd_thread, NULL,
+ &ioeventfd->virqfd, fd);
if (ret) {
kfree(ioeventfd);
goto out_unlock;
ret = pm_runtime_get_sync(vdev->device);
if (ret < 0)
- goto err_pm;
+ goto err_rst;
ret = vfio_platform_call_reset(vdev, &extra_dbg);
if (ret && vdev->reset_required) {
err_rst:
pm_runtime_put(vdev->device);
-err_pm:
vfio_platform_irq_cleanup(vdev);
err_irq:
vfio_platform_regions_cleanup(vdev);
list_splice_tail(iova_copy, iova);
}
+
static int vfio_iommu_type1_attach_group(void *iommu_data,
struct iommu_group *iommu_group)
{
mutex_lock(&iommu->lock);
- list_for_each_entry(d, &iommu->domain_list, next) {
- if (find_iommu_group(d, iommu_group)) {
- mutex_unlock(&iommu->lock);
- return -EINVAL;
- }
- }
-
- if (iommu->external_domain) {
- if (find_iommu_group(iommu->external_domain, iommu_group)) {
- mutex_unlock(&iommu->lock);
- return -EINVAL;
- }
+ /* Check for duplicates */
+ if (vfio_iommu_find_iommu_group(iommu, iommu_group)) {
+ mutex_unlock(&iommu->lock);
+ return -EINVAL;
}
group = kzalloc(sizeof(*group), GFP_KERNEL);
#define VHOST_SCSI_VERSION "v0.1"
#define VHOST_SCSI_NAMELEN 256
#define VHOST_SCSI_MAX_CDB_SIZE 32
-#define VHOST_SCSI_DEFAULT_TAGS 256
#define VHOST_SCSI_PREALLOC_SGLS 2048
#define VHOST_SCSI_PREALLOC_UPAGES 2048
#define VHOST_SCSI_PREALLOC_PROT_SGLS 2048
struct se_portal_group se_tpg;
/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
struct vhost_scsi *vhost_scsi;
+ struct list_head tmf_queue;
};
struct vhost_scsi_tport {
* Writers must also take dev mutex and flush under it.
*/
int inflight_idx;
+ struct vhost_scsi_cmd *scsi_cmds;
+ struct sbitmap scsi_tags;
+ int max_cmds;
};
struct vhost_scsi {
int vs_events_nr; /* num of pending events, protected by vq->mutex */
};
+struct vhost_scsi_tmf {
+ struct vhost_work vwork;
+ struct vhost_scsi_tpg *tpg;
+ struct vhost_scsi *vhost;
+ struct vhost_scsi_virtqueue *svq;
+ struct list_head queue_entry;
+
+ struct se_cmd se_cmd;
+ u8 scsi_resp;
+ struct vhost_scsi_inflight *inflight;
+ struct iovec resp_iov;
+ int in_iovs;
+ int vq_desc;
+};
+
/*
* Context for processing request and control queue operations.
*/
return 1;
}
-static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd)
{
struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd,
struct vhost_scsi_cmd, tvc_se_cmd);
- struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess;
+ struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_inflight *inflight = tv_cmd->inflight;
int i;
if (tv_cmd->tvc_sgl_count) {
put_page(sg_page(&tv_cmd->tvc_prot_sgl[i]));
}
- vhost_scsi_put_inflight(tv_cmd->inflight);
- target_free_tag(se_sess, se_cmd);
+ sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag);
+ vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf)
+{
+ struct vhost_scsi_tpg *tpg = tmf->tpg;
+ struct vhost_scsi_inflight *inflight = tmf->inflight;
+
+ mutex_lock(&tpg->tv_tpg_mutex);
+ list_add_tail(&tpg->tmf_queue, &tmf->queue_entry);
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ vhost_scsi_put_inflight(inflight);
+}
+
+static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
+{
+ if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) {
+ struct vhost_scsi_tmf *tmf = container_of(se_cmd,
+ struct vhost_scsi_tmf, se_cmd);
+
+ vhost_work_queue(&tmf->vhost->dev, &tmf->vwork);
+ } else {
+ struct vhost_scsi_cmd *cmd = container_of(se_cmd,
+ struct vhost_scsi_cmd, tvc_se_cmd);
+ struct vhost_scsi *vs = cmd->tvc_vhost;
+
+ llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
+ vhost_work_queue(&vs->dev, &vs->vs_completion_work);
+ }
}
static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
return 0;
}
-static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd)
-{
- struct vhost_scsi *vs = cmd->tvc_vhost;
-
- llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list);
-
- vhost_work_queue(&vs->dev, &vs->vs_completion_work);
-}
-
static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd)
{
- struct vhost_scsi_cmd *cmd = container_of(se_cmd,
- struct vhost_scsi_cmd, tvc_se_cmd);
- vhost_scsi_complete_cmd(cmd);
+ transport_generic_free_cmd(se_cmd, 0);
return 0;
}
static int vhost_scsi_queue_status(struct se_cmd *se_cmd)
{
- struct vhost_scsi_cmd *cmd = container_of(se_cmd,
- struct vhost_scsi_cmd, tvc_se_cmd);
- vhost_scsi_complete_cmd(cmd);
+ transport_generic_free_cmd(se_cmd, 0);
return 0;
}
static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd)
{
- return;
+ struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf,
+ se_cmd);
+
+ tmf->scsi_resp = se_cmd->se_tmr_req->response;
+ transport_generic_free_cmd(&tmf->se_cmd, 0);
}
static void vhost_scsi_aborted_task(struct se_cmd *se_cmd)
return evt;
}
-static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd)
-{
- struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
-
- /* TODO locking against target/backend threads? */
- transport_generic_free_cmd(se_cmd, 0);
-
-}
-
static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd)
{
return target_put_sess_cmd(se_cmd);
} else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
- vhost_scsi_free_cmd(cmd);
+ vhost_scsi_release_cmd_res(se_cmd);
}
vq = -1;
}
static struct vhost_scsi_cmd *
-vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
+vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr,
u32 exp_data_len, int data_direction)
{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
struct vhost_scsi_cmd *cmd;
struct vhost_scsi_nexus *tv_nexus;
- struct se_session *se_sess;
struct scatterlist *sg, *prot_sg;
struct page **pages;
- int tag, cpu;
+ int tag;
tv_nexus = tpg->tpg_nexus;
if (!tv_nexus) {
pr_err("Unable to locate active struct vhost_scsi_nexus\n");
return ERR_PTR(-EIO);
}
- se_sess = tv_nexus->tvn_se_sess;
- tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
+ tag = sbitmap_get(&svq->scsi_tags, 0, false);
if (tag < 0) {
pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
return ERR_PTR(-ENOMEM);
}
- cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag];
+ cmd = &svq->scsi_cmds[tag];
sg = cmd->tvc_sgl;
prot_sg = cmd->tvc_prot_sgl;
pages = cmd->tvc_upages;
cmd->tvc_prot_sgl = prot_sg;
cmd->tvc_upages = pages;
cmd->tvc_se_cmd.map_tag = tag;
- cmd->tvc_se_cmd.map_cpu = cpu;
cmd->tvc_tag = scsi_tag;
cmd->tvc_lun = lun;
cmd->tvc_task_attr = task_attr;
return ret;
}
+static u16 vhost_buf_to_lun(u8 *lun_buf)
+{
+ return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF;
+}
+
static void
vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
tag = vhost64_to_cpu(vq, v_req_pi.tag);
task_attr = v_req_pi.task_attr;
cdb = &v_req_pi.cdb[0];
- lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
+ lun = vhost_buf_to_lun(v_req_pi.lun);
} else {
tag = vhost64_to_cpu(vq, v_req.tag);
task_attr = v_req.task_attr;
cdb = &v_req.cdb[0];
- lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
+ lun = vhost_buf_to_lun(v_req.lun);
}
/*
* Check that the received CDB size does not exceeded our
scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE);
goto err;
}
- cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
+ cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr,
exp_data_len + prot_bytes,
data_direction);
if (IS_ERR(cmd)) {
- vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
+ vq_err(vq, "vhost_scsi_get_cmd failed %ld\n",
PTR_ERR(cmd));
goto err;
}
&prot_iter, exp_data_len,
&data_iter))) {
vq_err(vq, "Failed to map iov to sgl\n");
- vhost_scsi_release_cmd(&cmd->tvc_se_cmd);
+ vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd);
goto err;
}
}
}
static void
-vhost_scsi_send_tmf_reject(struct vhost_scsi *vs,
- struct vhost_virtqueue *vq,
- struct vhost_scsi_ctx *vc)
+vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq,
+ int in_iovs, int vq_desc, struct iovec *resp_iov,
+ int tmf_resp_code)
{
struct virtio_scsi_ctrl_tmf_resp rsp;
struct iov_iter iov_iter;
pr_debug("%s\n", __func__);
memset(&rsp, 0, sizeof(rsp));
- rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+ rsp.response = tmf_resp_code;
- iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp));
+ iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp));
ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
if (likely(ret == sizeof(rsp)))
- vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
+ vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0);
else
pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
}
+static void vhost_scsi_tmf_resp_work(struct vhost_work *work)
+{
+ struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf,
+ vwork);
+ int resp_code;
+
+ if (tmf->scsi_resp == TMR_FUNCTION_COMPLETE)
+ resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED;
+ else
+ resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED;
+
+ vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs,
+ tmf->vq_desc, &tmf->resp_iov, resp_code);
+ vhost_scsi_release_tmf_res(tmf);
+}
+
+static void
+vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg,
+ struct vhost_virtqueue *vq,
+ struct virtio_scsi_ctrl_tmf_req *vtmf,
+ struct vhost_scsi_ctx *vc)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_tmf *tmf;
+
+ if (vhost32_to_cpu(vq, vtmf->subtype) !=
+ VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET)
+ goto send_reject;
+
+ if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) {
+ pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n");
+ goto send_reject;
+ }
+
+ mutex_lock(&tpg->tv_tpg_mutex);
+ if (list_empty(&tpg->tmf_queue)) {
+ pr_err("Missing reserve TMF. Could not handle LUN RESET.\n");
+ mutex_unlock(&tpg->tv_tpg_mutex);
+ goto send_reject;
+ }
+
+ tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+ queue_entry);
+ list_del_init(&tmf->queue_entry);
+ mutex_unlock(&tpg->tv_tpg_mutex);
+
+ tmf->tpg = tpg;
+ tmf->vhost = vs;
+ tmf->svq = svq;
+ tmf->resp_iov = vq->iov[vc->out];
+ tmf->vq_desc = vc->head;
+ tmf->in_iovs = vc->in;
+ tmf->inflight = vhost_scsi_get_inflight(vq);
+
+ if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL,
+ vhost_buf_to_lun(vtmf->lun), NULL,
+ TMR_LUN_RESET, GFP_KERNEL, 0,
+ TARGET_SCF_ACK_KREF) < 0) {
+ vhost_scsi_release_tmf_res(tmf);
+ goto send_reject;
+ }
+
+ return;
+
+send_reject:
+ vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out],
+ VIRTIO_SCSI_S_FUNCTION_REJECTED);
+}
+
static void
vhost_scsi_send_an_resp(struct vhost_scsi *vs,
struct vhost_virtqueue *vq,
static void
vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
{
+ struct vhost_scsi_tpg *tpg;
union {
__virtio32 type;
struct virtio_scsi_ctrl_an_req an;
vc.req += typ_size;
vc.req_size -= typ_size;
- ret = vhost_scsi_get_req(vq, &vc, NULL);
+ ret = vhost_scsi_get_req(vq, &vc, &tpg);
if (ret)
goto err;
if (v_req.type == VIRTIO_SCSI_T_TMF)
- vhost_scsi_send_tmf_reject(vs, vq, &vc);
+ vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc);
else
vhost_scsi_send_an_resp(vs, vq, &vc);
err:
wait_for_completion(&old_inflight[i]->comp);
}
+static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_cmd *tv_cmd;
+ unsigned int i;
+
+ if (!svq->scsi_cmds)
+ return;
+
+ for (i = 0; i < svq->max_cmds; i++) {
+ tv_cmd = &svq->scsi_cmds[i];
+
+ kfree(tv_cmd->tvc_sgl);
+ kfree(tv_cmd->tvc_prot_sgl);
+ kfree(tv_cmd->tvc_upages);
+ }
+
+ sbitmap_free(&svq->scsi_tags);
+ kfree(svq->scsi_cmds);
+ svq->scsi_cmds = NULL;
+}
+
+static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds)
+{
+ struct vhost_scsi_virtqueue *svq = container_of(vq,
+ struct vhost_scsi_virtqueue, vq);
+ struct vhost_scsi_cmd *tv_cmd;
+ unsigned int i;
+
+ if (svq->scsi_cmds)
+ return 0;
+
+ if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL,
+ NUMA_NO_NODE))
+ return -ENOMEM;
+ svq->max_cmds = max_cmds;
+
+ svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL);
+ if (!svq->scsi_cmds) {
+ sbitmap_free(&svq->scsi_tags);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < max_cmds; i++) {
+ tv_cmd = &svq->scsi_cmds[i];
+
+ tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_sgl) {
+ pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
+ sizeof(struct page *),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_upages) {
+ pr_err("Unable to allocate tv_cmd->tvc_upages\n");
+ goto out;
+ }
+
+ tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
+ sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_prot_sgl) {
+ pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
+ goto out;
+ }
+ }
+ return 0;
+out:
+ vhost_scsi_destroy_vq_cmds(vq);
+ return -ENOMEM;
+}
+
/*
* Called from vhost_scsi_ioctl() context to walk the list of available
* vhost_scsi_tpg with an active struct vhost_scsi_nexus
if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) {
if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) {
- kfree(vs_tpg);
mutex_unlock(&tpg->tv_tpg_mutex);
ret = -EEXIST;
- goto out;
+ goto undepend;
}
/*
* In order to ensure individual vhost-scsi configfs
ret = target_depend_item(&se_tpg->tpg_group.cg_item);
if (ret) {
pr_warn("target_depend_item() failed: %d\n", ret);
- kfree(vs_tpg);
mutex_unlock(&tpg->tv_tpg_mutex);
- goto out;
+ goto undepend;
}
tpg->tv_tpg_vhost_count++;
tpg->vhost_scsi = vs;
if (match) {
memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
sizeof(vs->vs_vhost_wwpn));
+
+ for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
+ vq = &vs->vqs[i].vq;
+ if (!vhost_vq_is_setup(vq))
+ continue;
+
+ if (vhost_scsi_setup_vq_cmds(vq, vq->num))
+ goto destroy_vq_cmds;
+ }
+
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i].vq;
mutex_lock(&vq->mutex);
vhost_scsi_flush(vs);
kfree(vs->vs_tpg);
vs->vs_tpg = vs_tpg;
+ goto out;
+destroy_vq_cmds:
+ for (i--; i >= VHOST_SCSI_VQ_IO; i--) {
+ if (!vhost_vq_get_backend(&vs->vqs[i].vq))
+ vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq);
+ }
+undepend:
+ for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) {
+ tpg = vs_tpg[i];
+ if (tpg) {
+ tpg->tv_tpg_vhost_count--;
+ target_undepend_item(&tpg->se_tpg.tpg_group.cg_item);
+ }
+ }
+ kfree(vs_tpg);
out:
mutex_unlock(&vs->dev.mutex);
mutex_unlock(&vhost_scsi_mutex);
mutex_lock(&vq->mutex);
vhost_vq_set_backend(vq, NULL);
mutex_unlock(&vq->mutex);
+ /*
+ * Make sure cmds are not running before tearing them
+ * down.
+ */
+ vhost_scsi_flush(vs);
+ vhost_scsi_destroy_vq_cmds(vq);
}
}
/*
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
+ struct vhost_scsi_tmf *tmf;
+
+ tmf = kzalloc(sizeof(*tmf), GFP_KERNEL);
+ if (!tmf)
+ return -ENOMEM;
+ INIT_LIST_HEAD(&tmf->queue_entry);
+ vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work);
mutex_lock(&vhost_scsi_mutex);
mutex_lock(&tpg->tv_tpg_mutex);
tpg->tv_tpg_port_count++;
+ list_add_tail(&tmf->queue_entry, &tpg->tmf_queue);
mutex_unlock(&tpg->tv_tpg_mutex);
vhost_scsi_hotplug(tpg, lun);
{
struct vhost_scsi_tpg *tpg = container_of(se_tpg,
struct vhost_scsi_tpg, se_tpg);
+ struct vhost_scsi_tmf *tmf;
mutex_lock(&vhost_scsi_mutex);
mutex_lock(&tpg->tv_tpg_mutex);
tpg->tv_tpg_port_count--;
+ tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf,
+ queue_entry);
+ list_del(&tmf->queue_entry);
+ kfree(tmf);
mutex_unlock(&tpg->tv_tpg_mutex);
vhost_scsi_hotunplug(tpg, lun);
mutex_unlock(&vhost_scsi_mutex);
}
-static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess)
-{
- struct vhost_scsi_cmd *tv_cmd;
- unsigned int i;
-
- if (!se_sess->sess_cmd_map)
- return;
-
- for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
- tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
- kfree(tv_cmd->tvc_sgl);
- kfree(tv_cmd->tvc_prot_sgl);
- kfree(tv_cmd->tvc_upages);
- }
-}
-
static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store(
struct config_item *item, const char *page, size_t count)
{
NULL,
};
-static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg,
- struct se_session *se_sess, void *p)
-{
- struct vhost_scsi_cmd *tv_cmd;
- unsigned int i;
-
- for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) {
- tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i];
-
- tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS,
- sizeof(struct scatterlist),
- GFP_KERNEL);
- if (!tv_cmd->tvc_sgl) {
- pr_err("Unable to allocate tv_cmd->tvc_sgl\n");
- goto out;
- }
-
- tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES,
- sizeof(struct page *),
- GFP_KERNEL);
- if (!tv_cmd->tvc_upages) {
- pr_err("Unable to allocate tv_cmd->tvc_upages\n");
- goto out;
- }
-
- tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
- sizeof(struct scatterlist),
- GFP_KERNEL);
- if (!tv_cmd->tvc_prot_sgl) {
- pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
- goto out;
- }
- }
- return 0;
-out:
- vhost_scsi_free_cmd_map_res(se_sess);
- return -ENOMEM;
-}
-
static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
const char *name)
{
* struct se_node_acl for the vhost_scsi struct se_portal_group with
* the SCSI Initiator port name of the passed configfs group 'name'.
*/
- tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
- VHOST_SCSI_DEFAULT_TAGS,
- sizeof(struct vhost_scsi_cmd),
+ tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0,
TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
- (unsigned char *)name, tv_nexus,
- vhost_scsi_nexus_cb);
+ (unsigned char *)name, tv_nexus, NULL);
if (IS_ERR(tv_nexus->tvn_se_sess)) {
mutex_unlock(&tpg->tv_tpg_mutex);
kfree(tv_nexus);
" %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport),
tv_nexus->tvn_se_sess->se_node_acl->initiatorname);
- vhost_scsi_free_cmd_map_res(se_sess);
/*
* Release the SCSI I_T Nexus to the emulated vhost Target Port
*/
}
mutex_init(&tpg->tv_tpg_mutex);
INIT_LIST_HEAD(&tpg->tv_tpg_list);
+ INIT_LIST_HEAD(&tpg->tmf_queue);
tpg->tport = tport;
tpg->tport_tpgt = tpgt;
int minor;
struct eventfd_ctx *config_ctx;
int in_batch;
+ struct vdpa_iova_range range;
};
static DEFINE_IDA(vhost_vdpa_ida);
vq->call_ctx.producer.token = vq->call_ctx.ctx;
vq->call_ctx.producer.irq = irq;
ret = irq_bypass_register_producer(&vq->call_ctx.producer);
+ if (unlikely(ret))
+ dev_info(&v->dev, "vq %u, irq bypass producer (token %p) registration fails, ret = %d\n",
+ qid, vq->call_ctx.producer.token, ret);
}
static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid)
return 0;
}
+static long vhost_vdpa_get_iova_range(struct vhost_vdpa *v, u32 __user *argp)
+{
+ struct vhost_vdpa_iova_range range = {
+ .first = v->range.first,
+ .last = v->range.last,
+ };
+
+ if (copy_to_user(argp, &range, sizeof(range)))
+ return -EFAULT;
+ return 0;
+}
+
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
{
void __user *argp = (void __user *)arg;
u64 __user *featurep = argp;
u64 features;
- long r;
+ long r = 0;
if (cmd == VHOST_SET_BACKEND_FEATURES) {
- r = copy_from_user(&features, featurep, sizeof(features));
- if (r)
- return r;
+ if (copy_from_user(&features, featurep, sizeof(features)))
+ return -EFAULT;
if (features & ~VHOST_VDPA_BACKEND_FEATURES)
return -EOPNOTSUPP;
vhost_set_backend_features(&v->vdev, features);
break;
case VHOST_GET_BACKEND_FEATURES:
features = VHOST_VDPA_BACKEND_FEATURES;
- r = copy_to_user(featurep, &features, sizeof(features));
+ if (copy_to_user(featurep, &features, sizeof(features)))
+ r = -EFAULT;
+ break;
+ case VHOST_VDPA_GET_IOVA_RANGE:
+ r = vhost_vdpa_get_iova_range(v, argp);
break;
default:
r = vhost_dev_ioctl(&v->vdev, cmd, argp);
if (r)
vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
+ else
+ atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm);
return r;
}
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb *iotlb = dev->iotlb;
struct page **page_list;
- struct vm_area_struct **vmas;
+ unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
unsigned int gup_flags = FOLL_LONGTERM;
- unsigned long map_pfn, last_pfn = 0;
- unsigned long npages, lock_limit;
- unsigned long i, nmap = 0;
+ unsigned long npages, cur_base, map_pfn, last_pfn = 0;
+ unsigned long lock_limit, sz2pin, nchunks, i;
u64 iova = msg->iova;
long pinned;
int ret = 0;
+ if (msg->iova < v->range.first ||
+ msg->iova + msg->size - 1 > v->range.last)
+ return -EINVAL;
+
if (vhost_iotlb_itree_first(iotlb, msg->iova,
msg->iova + msg->size - 1))
return -EEXIST;
+ /* Limit the use of memory for bookkeeping */
+ page_list = (struct page **) __get_free_page(GFP_KERNEL);
+ if (!page_list)
+ return -ENOMEM;
+
if (msg->perm & VHOST_ACCESS_WO)
gup_flags |= FOLL_WRITE;
npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT;
- if (!npages)
- return -EINVAL;
-
- page_list = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
- vmas = kvmalloc_array(npages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!page_list || !vmas) {
- ret = -ENOMEM;
+ if (!npages) {
+ ret = -EINVAL;
goto free;
}
goto unlock;
}
- pinned = pin_user_pages(msg->uaddr & PAGE_MASK, npages, gup_flags,
- page_list, vmas);
- if (npages != pinned) {
- if (pinned < 0) {
- ret = pinned;
- } else {
- unpin_user_pages(page_list, pinned);
- ret = -ENOMEM;
- }
- goto unlock;
- }
-
+ cur_base = msg->uaddr & PAGE_MASK;
iova &= PAGE_MASK;
- map_pfn = page_to_pfn(page_list[0]);
-
- /* One more iteration to avoid extra vdpa_map() call out of loop. */
- for (i = 0; i <= npages; i++) {
- unsigned long this_pfn;
- u64 csize;
-
- /* The last chunk may have no valid PFN next to it */
- this_pfn = i < npages ? page_to_pfn(page_list[i]) : -1UL;
-
- if (last_pfn && (this_pfn == -1UL ||
- this_pfn != last_pfn + 1)) {
- /* Pin a contiguous chunk of memory */
- csize = last_pfn - map_pfn + 1;
- ret = vhost_vdpa_map(v, iova, csize << PAGE_SHIFT,
- map_pfn << PAGE_SHIFT,
- msg->perm);
- if (ret) {
- /*
- * Unpin the rest chunks of memory on the
- * flight with no corresponding vdpa_map()
- * calls having been made yet. On the other
- * hand, vdpa_unmap() in the failure path
- * is in charge of accounting the number of
- * pinned pages for its own.
- * This asymmetrical pattern of accounting
- * is for efficiency to pin all pages at
- * once, while there is no other callsite
- * of vdpa_map() than here above.
- */
- unpin_user_pages(&page_list[nmap],
- npages - nmap);
- goto out;
+ nchunks = 0;
+
+ while (npages) {
+ sz2pin = min_t(unsigned long, npages, list_size);
+ pinned = pin_user_pages(cur_base, sz2pin,
+ gup_flags, page_list, NULL);
+ if (sz2pin != pinned) {
+ if (pinned < 0) {
+ ret = pinned;
+ } else {
+ unpin_user_pages(page_list, pinned);
+ ret = -ENOMEM;
+ }
+ goto out;
+ }
+ nchunks++;
+
+ if (!last_pfn)
+ map_pfn = page_to_pfn(page_list[0]);
+
+ for (i = 0; i < pinned; i++) {
+ unsigned long this_pfn = page_to_pfn(page_list[i]);
+ u64 csize;
+
+ if (last_pfn && (this_pfn != last_pfn + 1)) {
+ /* Pin a contiguous chunk of memory */
+ csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
+ ret = vhost_vdpa_map(v, iova, csize,
+ map_pfn << PAGE_SHIFT,
+ msg->perm);
+ if (ret) {
+ /*
+ * Unpin the pages that are left unmapped
+ * from this point on in the current
+ * page_list. The remaining outstanding
+ * ones which may stride across several
+ * chunks will be covered in the common
+ * error path subsequently.
+ */
+ unpin_user_pages(&page_list[i],
+ pinned - i);
+ goto out;
+ }
+
+ map_pfn = this_pfn;
+ iova += csize;
+ nchunks = 0;
}
- atomic64_add(csize, &dev->mm->pinned_vm);
- nmap += csize;
- iova += csize << PAGE_SHIFT;
- map_pfn = this_pfn;
+
+ last_pfn = this_pfn;
}
- last_pfn = this_pfn;
+
+ cur_base += pinned << PAGE_SHIFT;
+ npages -= pinned;
}
- WARN_ON(nmap != npages);
+ /* Pin the rest chunk */
+ ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
+ map_pfn << PAGE_SHIFT, msg->perm);
out:
- if (ret)
+ if (ret) {
+ if (nchunks) {
+ unsigned long pfn;
+
+ /*
+ * Unpin the outstanding pages which are yet to be
+ * mapped but haven't due to vdpa_map() or
+ * pin_user_pages() failure.
+ *
+ * Mapped pages are accounted in vdpa_map(), hence
+ * the corresponding unpinning will be handled by
+ * vdpa_unmap().
+ */
+ WARN_ON(!last_pfn);
+ for (pfn = map_pfn; pfn <= last_pfn; pfn++)
+ unpin_user_page(pfn_to_page(pfn));
+ }
vhost_vdpa_unmap(v, msg->iova, msg->size);
+ }
unlock:
mmap_read_unlock(dev->mm);
free:
- kvfree(vmas);
- kvfree(page_list);
+ free_page((unsigned long)page_list);
return ret;
}
v->domain = NULL;
}
+static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v)
+{
+ struct vdpa_iova_range *range = &v->range;
+ struct iommu_domain_geometry geo;
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ if (ops->get_iova_range) {
+ *range = ops->get_iova_range(vdpa);
+ } else if (v->domain &&
+ !iommu_domain_get_attr(v->domain,
+ DOMAIN_ATTR_GEOMETRY, &geo) &&
+ geo.force_aperture) {
+ range->first = geo.aperture_start;
+ range->last = geo.aperture_end;
+ } else {
+ range->first = 0;
+ range->last = ULLONG_MAX;
+ }
+}
+
static int vhost_vdpa_open(struct inode *inode, struct file *filep)
{
struct vhost_vdpa *v;
if (r)
goto err_init_iotlb;
+ vhost_vdpa_set_iova_range(v);
+
filep->private_data = v;
return 0;
memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer));
}
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq)
+{
+ return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq);
+}
+EXPORT_SYMBOL_GPL(vhost_vq_is_setup);
+
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
struct vhost_log *log, unsigned int *log_num);
void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
+bool vhost_vq_is_setup(struct vhost_virtqueue *vq);
int vhost_vq_init_access(struct vhost_virtqueue *);
int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads,
/**
* vringh_iov_push_user - copy bytes into vring_iov.
* @wiov: the wiov as passed to vringh_getdesc_user() (updated as we consume)
- * @dst: the place to copy.
+ * @src: the place to copy from.
* @len: the maximum length to copy.
*
* Returns the bytes copied <= len or a negative errno.
/**
* vringh_iov_push_kern - copy bytes into vring_iov.
* @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume)
- * @dst: the place to copy.
+ * @src: the place to copy from.
* @len: the maximum length to copy.
*
* Returns the bytes copied <= len or a negative errno.
* vringh_iov_push_iotlb - copy bytes into vring_iov.
* @vrh: the vring.
* @wiov: the wiov as passed to vringh_getdesc_iotlb() (updated as we consume)
- * @dst: the place to copy.
+ * @src: the place to copy from.
* @len: the maximum length to copy.
*
* Returns the bytes copied <= len or a negative errno.
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/fb.h>
goto err1;
}
- fb_virt = ioremap(par->mem->start, screen_fb_size);
+ /*
+ * Map the VRAM cacheable for performance. This is also required for
+ * VM Connect to display properly for ARM64 Linux VM, as the host also
+ * maps the VRAM cacheable.
+ */
+ fb_virt = ioremap_cache(par->mem->start, screen_fb_size);
if (!fb_virt)
goto err2;
getmem_done:
remove_conflicting_framebuffers(info->apertures,
KBUILD_MODNAME, false);
- if (!gen2vm)
+
+ if (gen2vm) {
+ /* framebuffer is reallocated, clear screen_info to avoid misuse from kexec */
+ screen_info.lfb_size = 0;
+ screen_info.lfb_base = 0;
+ screen_info.orig_video_isVGA = 0;
+ } else {
pci_dev_put(pdev);
+ }
kfree(info->apertures);
return 0;
poll_wait(file, &ne_enclave->eventq, wait);
- if (!ne_enclave->has_event)
- return mask;
-
- mask = POLLHUP;
+ if (ne_enclave->has_event)
+ mask |= EPOLLHUP;
return mask;
}
*/
trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
- map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start),
- phys, size, size, dir, attrs);
+ map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
if (map == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
.mmap = v9fs_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync,
};
.lock = v9fs_file_lock_dotl,
.flock = v9fs_file_flock_dotl,
.mmap = v9fs_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync_dotl,
};
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
.mmap = generic_file_readonly_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync,
};
.lock = v9fs_file_lock_dotl,
.flock = v9fs_file_flock_dotl,
.mmap = generic_file_readonly_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync_dotl,
};
.release = v9fs_dir_release,
.lock = v9fs_file_lock,
.mmap = v9fs_mmap_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync,
};
.lock = v9fs_file_lock_dotl,
.flock = v9fs_file_flock_dotl,
.mmap = v9fs_mmap_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync_dotl,
};
*/
void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_trace reason)
{
- unsigned int debug_id = cell->debug_id;
+ unsigned int debug_id;
time64_t now, expire_delay;
int u, a;
if (cell->vl_servers->nr_servers)
expire_delay = afs_cell_gc_delay;
+ debug_id = cell->debug_id;
u = atomic_read(&cell->ref);
a = atomic_dec_return(&cell->active);
trace_afs_cell(debug_id, u, a, reason);
if (ret < 0)
goto error;
- set_page_private(req->pages[i], 1);
- SetPagePrivate(req->pages[i]);
+ attach_page_private(req->pages[i], (void *)1);
unlock_page(req->pages[i]);
i++;
} else {
vp->cb_break_before = afs_calc_vnode_cb_break(vnode);
vp->vnode = vnode;
vp->put_vnode = true;
+ vp->speculative = true; /* vnode not locked */
}
}
}
_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index);
- set_page_private(page, 0);
- ClearPagePrivate(page);
+ detach_page_private(page);
/* The directory will need reloading. */
if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
afs_stat_v(dvnode, n_inval);
/* we clean up only if the entire page is being invalidated */
- if (offset == 0 && length == PAGE_SIZE) {
- set_page_private(page, 0);
- ClearPagePrivate(page);
- }
+ if (offset == 0 && length == PAGE_SIZE)
+ detach_page_private(page);
}
index, gfp);
if (!page)
goto error;
- if (!PagePrivate(page)) {
- set_page_private(page, 1);
- SetPagePrivate(page);
- }
+ if (!PagePrivate(page))
+ attach_page_private(page, (void *)1);
dir_page = kmap(page);
}
.write_iter = afs_file_write,
.mmap = afs_file_mmap,
.splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
.fsync = afs_fsync,
.lock = afs_lock,
.flock = afs_flock,
return ret;
}
+/*
+ * Adjust the dirty region of the page on truncation or full invalidation,
+ * getting rid of the markers altogether if the region is entirely invalidated.
+ */
+static void afs_invalidate_dirty(struct page *page, unsigned int offset,
+ unsigned int length)
+{
+ struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+ unsigned long priv;
+ unsigned int f, t, end = offset + length;
+
+ priv = page_private(page);
+
+ /* we clean up only if the entire page is being invalidated */
+ if (offset == 0 && length == thp_size(page))
+ goto full_invalidate;
+
+ /* If the page was dirtied by page_mkwrite(), the PTE stays writable
+ * and we don't get another notification to tell us to expand it
+ * again.
+ */
+ if (afs_is_page_dirty_mmapped(priv))
+ return;
+
+ /* We may need to shorten the dirty region */
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
+
+ if (t <= offset || f >= end)
+ return; /* Doesn't overlap */
+
+ if (f < offset && t > end)
+ return; /* Splits the dirty region - just absorb it */
+
+ if (f >= offset && t <= end)
+ goto undirty;
+
+ if (f < offset)
+ t = offset;
+ else
+ f = end;
+ if (f == t)
+ goto undirty;
+
+ priv = afs_page_dirty(f, t);
+ set_page_private(page, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page->index, priv);
+ return;
+
+undirty:
+ trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page->index, priv);
+ clear_page_dirty_for_io(page);
+full_invalidate:
+ priv = (unsigned long)detach_page_private(page);
+ trace_afs_page_dirty(vnode, tracepoint_string("inval"), page->index, priv);
+}
+
/*
* invalidate part or all of a page
* - release a page and clean up its private data if offset is 0 (indicating
static void afs_invalidatepage(struct page *page, unsigned int offset,
unsigned int length)
{
- struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
- unsigned long priv;
-
_enter("{%lu},%u,%u", page->index, offset, length);
BUG_ON(!PageLocked(page));
+#ifdef CONFIG_AFS_FSCACHE
/* we clean up only if the entire page is being invalidated */
if (offset == 0 && length == PAGE_SIZE) {
-#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
fscache_wait_on_page_write(vnode->cache, page);
fscache_uncache_page(vnode->cache, page);
}
+ }
#endif
- if (PagePrivate(page)) {
- priv = page_private(page);
- trace_afs_page_dirty(vnode, tracepoint_string("inval"),
- page->index, priv);
- set_page_private(page, 0);
- ClearPagePrivate(page);
- }
- }
+ if (PagePrivate(page))
+ afs_invalidate_dirty(page, offset, length);
_leave("");
}
#endif
if (PagePrivate(page)) {
- priv = page_private(page);
+ priv = (unsigned long)detach_page_private(page);
trace_afs_page_dirty(vnode, tracepoint_string("rel"),
page->index, priv);
- set_page_private(page, 0);
- ClearPagePrivate(page);
}
/* indicate that the page can be released */
op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
}
} else if (vp->scb.have_status) {
+ if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version &&
+ vp->speculative)
+ /* Ignore the result of a speculative bulk status fetch
+ * if it splits around a modification op, thereby
+ * appearing to regress the data version.
+ */
+ goto out;
afs_apply_status(op, vp);
if (vp->scb.have_cb)
afs_apply_callback(op, vp);
}
}
+out:
write_sequnlock(&vnode->cb_lock);
if (vp->scb.have_status)
bool update_ctime:1; /* Need to update the ctime */
bool set_size:1; /* Must update i_size */
bool op_unlinked:1; /* True if file was unlinked by op */
+ bool speculative:1; /* T if speculative status fetch (no vnode lock) */
};
/*
pgoff_t last; /* last page in mapping to deal with */
unsigned first_offset; /* offset into mapping[first] */
unsigned last_to; /* amount of mapping[last] */
+ bool laundering; /* Laundering page, PG_writeback not set */
} store;
struct {
struct iattr *attr;
u64 data_version;
} __packed;
+/*
+ * We use page->private to hold the amount of the page that we've written to,
+ * splitting the field into two parts. However, we need to represent a range
+ * 0...PAGE_SIZE, so we reduce the resolution if the size of the page
+ * exceeds what we can encode.
+ */
+#ifdef CONFIG_64BIT
+#define __AFS_PAGE_PRIV_MASK 0x7fffffffUL
+#define __AFS_PAGE_PRIV_SHIFT 32
+#define __AFS_PAGE_PRIV_MMAPPED 0x80000000UL
+#else
+#define __AFS_PAGE_PRIV_MASK 0x7fffUL
+#define __AFS_PAGE_PRIV_SHIFT 16
+#define __AFS_PAGE_PRIV_MMAPPED 0x8000UL
+#endif
+
+static inline unsigned int afs_page_dirty_resolution(void)
+{
+ int shift = PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1);
+ return (shift > 0) ? shift : 0;
+}
+
+static inline size_t afs_page_dirty_from(unsigned long priv)
+{
+ unsigned long x = priv & __AFS_PAGE_PRIV_MASK;
+
+ /* The lower bound is inclusive */
+ return x << afs_page_dirty_resolution();
+}
+
+static inline size_t afs_page_dirty_to(unsigned long priv)
+{
+ unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK;
+
+ /* The upper bound is immediately beyond the region */
+ return (x + 1) << afs_page_dirty_resolution();
+}
+
+static inline unsigned long afs_page_dirty(size_t from, size_t to)
+{
+ unsigned int res = afs_page_dirty_resolution();
+ from >>= res;
+ to = (to - 1) >> res;
+ return (to << __AFS_PAGE_PRIV_SHIFT) | from;
+}
+
+static inline unsigned long afs_page_dirty_mmapped(unsigned long priv)
+{
+ return priv | __AFS_PAGE_PRIV_MMAPPED;
+}
+
+static inline bool afs_is_page_dirty_mmapped(unsigned long priv)
+{
+ return priv & __AFS_PAGE_PRIV_MMAPPED;
+}
+
#include <trace/events/afs.h>
/*****************************************************************************/
*/
int afs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
+ struct page **_page, void **fsdata)
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct page *page;
_enter("{%llx:%llu},{%lx},%u,%u",
vnode->fid.vid, vnode->fid.vnode, index, from, to);
- /* We want to store information about how much of a page is altered in
- * page->private.
- */
- BUILD_BUG_ON(PAGE_SIZE > 32768 && sizeof(page->private) < 8);
-
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
SetPageUptodate(page);
}
- /* page won't leak in error case: it eventually gets cleaned off LRU */
- *pagep = page;
-
try_again:
/* See if this page is already partially written in a way that we can
* merge the new write with.
t = f = 0;
if (PagePrivate(page)) {
priv = page_private(page);
- f = priv & AFS_PRIV_MAX;
- t = priv >> AFS_PRIV_SHIFT;
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
ASSERTCMP(f, <=, t);
}
if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
(to < f || from > t))
goto flush_conflicting_write;
- if (from < f)
- f = from;
- if (to > t)
- t = to;
- } else {
- f = from;
- t = to;
}
- priv = (unsigned long)t << AFS_PRIV_SHIFT;
- priv |= f;
- trace_afs_page_dirty(vnode, tracepoint_string("begin"),
- page->index, priv);
- SetPagePrivate(page);
- set_page_private(page, priv);
+ *_page = page;
_leave(" = 0");
return 0;
flush_conflicting_write:
_debug("flush conflict");
ret = write_one_page(page);
- if (ret < 0) {
- _leave(" = %d", ret);
- return ret;
- }
+ if (ret < 0)
+ goto error;
ret = lock_page_killable(page);
- if (ret < 0) {
- _leave(" = %d", ret);
- return ret;
- }
+ if (ret < 0)
+ goto error;
goto try_again;
+
+error:
+ put_page(page);
+ _leave(" = %d", ret);
+ return ret;
}
/*
{
struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct key *key = afs_file_key(file);
+ unsigned long priv;
+ unsigned int f, from = pos & (PAGE_SIZE - 1);
+ unsigned int t, to = from + copied;
loff_t i_size, maybe_i_size;
- int ret;
+ int ret = 0;
_enter("{%llx:%llu},{%lx}",
vnode->fid.vid, vnode->fid.vnode, page->index);
+ if (copied == 0)
+ goto out;
+
maybe_i_size = pos + copied;
i_size = i_size_read(&vnode->vfs_inode);
SetPageUptodate(page);
}
+ if (PagePrivate(page)) {
+ priv = page_private(page);
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
+ if (from < f)
+ f = from;
+ if (to > t)
+ t = to;
+ priv = afs_page_dirty(f, t);
+ set_page_private(page, priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("dirty+"),
+ page->index, priv);
+ } else {
+ priv = afs_page_dirty(from, to);
+ attach_page_private(page, (void *)priv);
+ trace_afs_page_dirty(vnode, tracepoint_string("dirty"),
+ page->index, priv);
+ }
+
set_page_dirty(page);
if (PageDirty(page))
_debug("dirtied");
ASSERTCMP(pv.nr, ==, count);
for (loop = 0; loop < count; loop++) {
- priv = page_private(pv.pages[loop]);
+ priv = (unsigned long)detach_page_private(pv.pages[loop]);
trace_afs_page_dirty(vnode, tracepoint_string("clear"),
pv.pages[loop]->index, priv);
- set_page_private(pv.pages[loop], 0);
end_page_writeback(pv.pages[loop]);
}
first += count;
op->ctime = op->file[0].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[0]);
if (op->error == 0) {
- afs_pages_written_back(vnode, op->store.first, op->store.last);
+ if (!op->store.laundering)
+ afs_pages_written_back(vnode, op->store.first, op->store.last);
afs_stat_v(vnode, n_stores);
atomic_long_add((op->store.last * PAGE_SIZE + op->store.last_to) -
(op->store.first * PAGE_SIZE + op->store.first_offset),
*/
static int afs_store_data(struct address_space *mapping,
pgoff_t first, pgoff_t last,
- unsigned offset, unsigned to)
+ unsigned offset, unsigned to, bool laundering)
{
struct afs_vnode *vnode = AFS_FS_I(mapping->host);
struct afs_operation *op;
op->store.last = last;
op->store.first_offset = offset;
op->store.last_to = to;
+ op->store.laundering = laundering;
op->mtime = vnode->vfs_inode.i_mtime;
op->flags |= AFS_OPERATION_UNINTR;
op->ops = &afs_store_data_operation;
*/
start = primary_page->index;
priv = page_private(primary_page);
- offset = priv & AFS_PRIV_MAX;
- to = priv >> AFS_PRIV_SHIFT;
+ offset = afs_page_dirty_from(priv);
+ to = afs_page_dirty_to(priv);
trace_afs_page_dirty(vnode, tracepoint_string("store"),
primary_page->index, priv);
}
priv = page_private(page);
- f = priv & AFS_PRIV_MAX;
- t = priv >> AFS_PRIV_SHIFT;
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
if (f != 0 &&
!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)) {
unlock_page(page);
if (end > i_size)
to = i_size & ~PAGE_MASK;
- ret = afs_store_data(mapping, first, last, offset, to);
+ ret = afs_store_data(mapping, first, last, offset, to, false);
switch (ret) {
case 0:
ret = count;
*/
wait_on_page_writeback(vmf->page);
- priv = (unsigned long)PAGE_SIZE << AFS_PRIV_SHIFT; /* To */
- priv |= 0; /* From */
+ priv = afs_page_dirty(0, PAGE_SIZE);
+ priv = afs_page_dirty_mmapped(priv);
trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"),
vmf->page->index, priv);
- SetPagePrivate(vmf->page);
- set_page_private(vmf->page, priv);
+ if (PagePrivate(vmf->page))
+ set_page_private(vmf->page, priv);
+ else
+ attach_page_private(vmf->page, (void *)priv);
file_update_time(file);
sb_end_pagefault(inode->i_sb);
f = 0;
t = PAGE_SIZE;
if (PagePrivate(page)) {
- f = priv & AFS_PRIV_MAX;
- t = priv >> AFS_PRIV_SHIFT;
+ f = afs_page_dirty_from(priv);
+ t = afs_page_dirty_to(priv);
}
trace_afs_page_dirty(vnode, tracepoint_string("launder"),
page->index, priv);
- ret = afs_store_data(mapping, page->index, page->index, t, f);
+ ret = afs_store_data(mapping, page->index, page->index, t, f, true);
}
+ priv = (unsigned long)detach_page_private(page);
trace_afs_page_dirty(vnode, tracepoint_string("laundered"),
page->index, priv);
- set_page_private(page, 0);
- ClearPagePrivate(page);
#ifdef CONFIG_AFS_FSCACHE
if (PageFsCache(page)) {
if (acl->size <= size)
memcpy(buffer, acl->data, acl->size);
else
- op->error = -ERANGE;
+ ret = -ERANGE;
}
}
.set = afs_xattr_set_acl,
};
-static void yfs_acl_put(struct afs_operation *op)
-{
- yfs_free_opaque_acl(op->yacl);
-}
-
static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = {
.issue_yfs_rpc = yfs_fs_fetch_opaque_acl,
.success = afs_acl_success,
static const struct afs_operation_ops yfs_store_opaque_acl2_operation = {
.issue_yfs_rpc = yfs_fs_store_opaque_acl2,
.success = afs_acl_success,
- .put = yfs_acl_put,
+ .put = afs_acl_put,
};
/*
memcpy(bp, acl->data, acl->size);
if (acl->size != size)
memset((void *)bp + acl->size, 0, size - acl->size);
+ bp += size / sizeof(__be32);
yfs_check_req(call, bp);
trace_afs_make_fs_call(call, &vp->fid);
* we return to userspace.
*/
if (S_ISREG(file_inode(file)->i_mode)) {
- __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+ sb_start_write(file_inode(file)->i_sb);
__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}
req->ki_flags |= IOCB_WRITE;
struct elf_thread_core_info *next;
struct task_struct *task;
struct elf_prstatus prstatus;
- struct memelfnote notes[0];
+ struct memelfnote notes[];
};
struct elf_note_info {
int level = ref->level;
struct btrfs_key search_key = ref->key_for_search;
- root = btrfs_get_fs_root(fs_info, ref->root_id, false);
+ /*
+ * If we're search_commit_root we could possibly be holding locks on
+ * other tree nodes. This happens when qgroups does backref walks when
+ * adding new delayed refs. To deal with this we need to look in cache
+ * for the root, and if we don't find it then we need to search the
+ * tree_root's commit root, thus the btrfs_get_fs_root_commit_root usage
+ * here.
+ */
+ if (path->search_commit_root)
+ root = btrfs_get_fs_root_commit_root(fs_info, path, ref->root_id);
+ else
+ root = btrfs_get_fs_root(fs_info, ref->root_id, false);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out_free;
key.offset = 0;
btrfs_release_path(path);
}
+ btrfs_release_path(path);
list_for_each_entry(space_info, &info->space_info, list) {
int i;
/*DEFAULT_RATELIMIT_BURST*/ 1);
if (__ratelimit(&_rs))
WARN(1, KERN_DEBUG
- "BTRFS: block rsv returned %d\n", ret);
+ "BTRFS: block rsv %d returned %d\n",
+ block_rsv->type, ret);
}
try_reserve:
ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize,
*/
struct ulist *qgroup_ulist;
- /* protect user change for quota operations */
+ /*
+ * Protect user change for quota operations. If a transaction is needed,
+ * it must be started before locking this lock.
+ */
struct mutex qgroup_ioctl_lock;
/* list of dirty qgroups to be written at next commit */
int btrfs_reada_wait(void *handle);
void btrfs_reada_detach(void *handle);
int btree_readahead_hook(struct extent_buffer *eb, int err);
+void btrfs_reada_remove_dev(struct btrfs_device *dev);
+void btrfs_reada_undo_remove_dev(struct btrfs_device *dev);
static inline int is_fstree(u64 rootid)
{
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
no_valid_dev_replace_entry_found:
+ /*
+ * We don't have a replace item or it's corrupted. If there is
+ * a replace target, fail the mount.
+ */
+ if (btrfs_find_device(fs_info->fs_devices,
+ BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+ btrfs_err(fs_info,
+ "found replace target device without a valid replace item");
+ ret = -EUCLEAN;
+ goto out;
+ }
ret = 0;
dev_replace->replace_state =
BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
- dev_replace->srcdev = NULL;
- dev_replace->tgtdev = NULL;
+ /*
+ * We don't have an active replace item but if there is a
+ * replace target, fail the mount.
+ */
+ if (btrfs_find_device(fs_info->fs_devices,
+ BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+ btrfs_err(fs_info,
+ "replace devid present without an active replace item");
+ ret = -EUCLEAN;
+ } else {
+ dev_replace->srcdev = NULL;
+ dev_replace->tgtdev = NULL;
+ }
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
}
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+ if (!scrub_ret)
+ btrfs_reada_remove_dev(src_device);
+
/*
* We have to use this loop approach because at this point src_device
* has to be available for transaction commit to complete, yet new
while (1) {
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
+ btrfs_reada_undo_remove_dev(src_device);
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return PTR_ERR(trans);
}
up_write(&dev_replace->rwsem);
mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ btrfs_reada_undo_remove_dev(src_device);
btrfs_rm_dev_replace_blocked(fs_info);
if (tgt_device)
btrfs_destroy_dev_replace_tgtdev(tgt_device);
return 0;
}
-struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
- struct btrfs_key *key)
+static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
+ struct btrfs_path *path,
+ struct btrfs_key *key)
{
struct btrfs_root *root;
struct btrfs_fs_info *fs_info = tree_root->fs_info;
- struct btrfs_path *path;
u64 generation;
int ret;
int level;
- path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
-
root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS);
- if (!root) {
- ret = -ENOMEM;
- goto alloc_fail;
- }
+ if (!root)
+ return ERR_PTR(-ENOMEM);
ret = btrfs_find_root(tree_root, key, path,
&root->root_item, &root->root_key);
if (ret) {
if (ret > 0)
ret = -ENOENT;
- goto find_fail;
+ goto fail;
}
generation = btrfs_root_generation(&root->root_item);
if (IS_ERR(root->node)) {
ret = PTR_ERR(root->node);
root->node = NULL;
- goto find_fail;
+ goto fail;
} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
ret = -EIO;
- goto find_fail;
+ goto fail;
}
root->commit_root = btrfs_root_node(root);
-out:
- btrfs_free_path(path);
return root;
-
-find_fail:
+fail:
btrfs_put_root(root);
-alloc_fail:
- root = ERR_PTR(ret);
- goto out;
+ return ERR_PTR(ret);
+}
+
+struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
+ struct btrfs_key *key)
+{
+ struct btrfs_root *root;
+ struct btrfs_path *path;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return ERR_PTR(-ENOMEM);
+ root = read_tree_root_path(tree_root, path, key);
+ btrfs_free_path(path);
+
+ return root;
}
/*
return root;
}
+static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
+ u64 objectid)
+{
+ if (objectid == BTRFS_ROOT_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->tree_root);
+ if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->extent_root);
+ if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->chunk_root);
+ if (objectid == BTRFS_DEV_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->dev_root);
+ if (objectid == BTRFS_CSUM_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->csum_root);
+ if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->quota_root) ?
+ fs_info->quota_root : ERR_PTR(-ENOENT);
+ if (objectid == BTRFS_UUID_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->uuid_root) ?
+ fs_info->uuid_root : ERR_PTR(-ENOENT);
+ if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
+ return btrfs_grab_root(fs_info->free_space_root) ?
+ fs_info->free_space_root : ERR_PTR(-ENOENT);
+ return NULL;
+}
+
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root)
{
struct btrfs_key key;
int ret;
- if (objectid == BTRFS_ROOT_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->tree_root);
- if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->extent_root);
- if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->chunk_root);
- if (objectid == BTRFS_DEV_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->dev_root);
- if (objectid == BTRFS_CSUM_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->csum_root);
- if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->quota_root) ?
- fs_info->quota_root : ERR_PTR(-ENOENT);
- if (objectid == BTRFS_UUID_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->uuid_root) ?
- fs_info->uuid_root : ERR_PTR(-ENOENT);
- if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
- return btrfs_grab_root(fs_info->free_space_root) ?
- fs_info->free_space_root : ERR_PTR(-ENOENT);
+ root = btrfs_get_global_root(fs_info, objectid);
+ if (root)
+ return root;
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
}
+/*
+ * btrfs_get_fs_root_commit_root - return a root for the given objectid
+ * @fs_info: the fs_info
+ * @objectid: the objectid we need to lookup
+ *
+ * This is exclusively used for backref walking, and exists specifically because
+ * of how qgroups does lookups. Qgroups will do a backref lookup at delayed ref
+ * creation time, which means we may have to read the tree_root in order to look
+ * up a fs root that is not in memory. If the root is not in memory we will
+ * read the tree root commit root and look up the fs root from there. This is a
+ * temporary root, it will not be inserted into the radix tree as it doesn't
+ * have the most uptodate information, it'll simply be discarded once the
+ * backref code is finished using the root.
+ */
+struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ u64 objectid)
+{
+ struct btrfs_root *root;
+ struct btrfs_key key;
+
+ ASSERT(path->search_commit_root && path->skip_locking);
+
+ /*
+ * This can return -ENOENT if we ask for a root that doesn't exist, but
+ * since this is called via the backref walking code we won't be looking
+ * up a root that doesn't exist, unless there's corruption. So if root
+ * != NULL just return it.
+ */
+ root = btrfs_get_global_root(fs_info, objectid);
+ if (root)
+ return root;
+
+ root = btrfs_lookup_fs_root(fs_info, objectid);
+ if (root)
+ return root;
+
+ key.objectid = objectid;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+ root = read_tree_root_path(fs_info->tree_root, path, &key);
+ btrfs_release_path(path);
+
+ return root;
+}
+
/*
* called by the kthread helper functions to finally call the bio end_io
* functions. This is where read checksum verification actually happens
u64 objectid, bool check_ref);
struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, dev_t anon_dev);
+struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_path *path,
+ u64 objectid);
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
struct btrfs_tree_block_info *bi;
if (item_size < sizeof(*ei) + sizeof(*bi)) {
btrfs_crit(info,
-"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %lu",
+"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %zu",
key.objectid, key.type, key.offset,
owner_objectid, item_size,
sizeof(*ei) + sizeof(*bi));
}
}
-static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
- const u64 start,
- const u64 len,
- struct extent_state **cached_state)
-{
- u64 search_start = start;
- const u64 end = start + len - 1;
-
- while (search_start < end) {
- const u64 search_len = end - search_start + 1;
- struct extent_map *em;
- u64 em_len;
- int ret = 0;
-
- em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
- if (IS_ERR(em))
- return PTR_ERR(em);
-
- if (em->block_start != EXTENT_MAP_HOLE)
- goto next;
-
- em_len = em->len;
- if (em->start < search_start)
- em_len -= search_start - em->start;
- if (em_len > search_len)
- em_len = search_len;
-
- ret = set_extent_bit(&inode->io_tree, search_start,
- search_start + em_len - 1,
- EXTENT_DELALLOC_NEW,
- NULL, cached_state, GFP_NOFS);
-next:
- search_start = extent_map_end(em);
- free_extent_map(em);
- if (ret)
- return ret;
- }
- return 0;
-}
-
/*
* after copy_from_user, pages need to be dirtied and we need to make
* sure holes are created between the current EOF and the start of
EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, cached);
- if (!btrfs_is_free_space_inode(inode)) {
- if (start_pos >= isize &&
- !(inode->flags & BTRFS_INODE_PREALLOC)) {
- /*
- * There can't be any extents following eof in this case
- * so just set the delalloc new bit for the range
- * directly.
- */
- extra_bits |= EXTENT_DELALLOC_NEW;
- } else {
- err = btrfs_find_new_delalloc_bytes(inode, start_pos,
- num_bytes, cached);
- if (err)
- return err;
- }
- }
-
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
extra_bits, cached);
if (err)
inode_lock_shared(inode);
ret = btrfs_direct_IO(iocb, to);
inode_unlock_shared(inode);
- if (ret < 0)
+ if (ret < 0 || !iov_iter_count(to) ||
+ iocb->ki_pos >= i_size_read(file_inode(iocb->ki_filp)))
return ret;
}
return 0;
}
+static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
+ const u64 start,
+ const u64 len,
+ struct extent_state **cached_state)
+{
+ u64 search_start = start;
+ const u64 end = start + len - 1;
+
+ while (search_start < end) {
+ const u64 search_len = end - search_start + 1;
+ struct extent_map *em;
+ u64 em_len;
+ int ret = 0;
+
+ em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ if (em->block_start != EXTENT_MAP_HOLE)
+ goto next;
+
+ em_len = em->len;
+ if (em->start < search_start)
+ em_len -= search_start - em->start;
+ if (em_len > search_len)
+ em_len = search_len;
+
+ ret = set_extent_bit(&inode->io_tree, search_start,
+ search_start + em_len - 1,
+ EXTENT_DELALLOC_NEW,
+ NULL, cached_state, GFP_NOFS);
+next:
+ search_start = extent_map_end(em);
+ free_extent_map(em);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
unsigned int extra_bits,
struct extent_state **cached_state)
{
WARN_ON(PAGE_ALIGNED(end));
+
+ if (start >= i_size_read(&inode->vfs_inode) &&
+ !(inode->flags & BTRFS_INODE_PREALLOC)) {
+ /*
+ * There can't be any extents following eof in this case so just
+ * set the delalloc new bit for the range directly.
+ */
+ extra_bits |= EXTENT_DELALLOC_NEW;
+ } else {
+ int ret;
+
+ ret = btrfs_find_new_delalloc_bytes(inode, start,
+ end + 1 - start,
+ cached_state);
+ if (ret)
+ return ret;
+ }
+
return set_extent_delalloc(&inode->io_tree, start, end, extra_bits,
cached_state);
}
* clear_offset by our extent size.
*/
clear_offset += ins.offset;
- btrfs_dec_block_group_reservations(fs_info, ins.objectid);
last_alloc = ins.offset;
trans = insert_prealloc_file_extent(trans, inode, &ins, cur_offset);
+ /*
+ * Now that we inserted the prealloc extent we can finally
+ * decrement the number of reservations in the block group.
+ * If we did it before, we could race with relocation and have
+ * relocation miss the reserved extent, making it fail later.
+ */
+ btrfs_dec_block_group_reservations(fs_info, ins.objectid);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_free_reserved_extent(fs_info, ins.objectid,
u64 page_start;
u64 page_end;
u64 page_cnt;
+ u64 start = (u64)start_index << PAGE_SHIFT;
int ret;
int i;
int i_done;
page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
- start_index << PAGE_SHIFT,
- page_cnt << PAGE_SHIFT);
+ start, page_cnt << PAGE_SHIFT);
if (ret)
return ret;
i_done = 0;
btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
- start_index << PAGE_SHIFT,
- (page_cnt - i_done) << PAGE_SHIFT, true);
+ start, (page_cnt - i_done) << PAGE_SHIFT, true);
}
put_page(pages[i]);
}
btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
- start_index << PAGE_SHIFT,
- page_cnt << PAGE_SHIFT, true);
+ start, page_cnt << PAGE_SHIFT, true);
btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return ret;
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/btrfs.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "transaction.h"
break;
}
out:
+ btrfs_free_path(path);
fs_info->qgroup_flags |= flags;
if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN &&
ret >= 0)
ret = qgroup_rescan_init(fs_info, rescan_progress, 0);
- btrfs_free_path(path);
if (ret < 0) {
ulist_free(fs_info->qgroup_ulist);
struct btrfs_key found_key;
struct btrfs_qgroup *qgroup = NULL;
struct btrfs_trans_handle *trans = NULL;
+ struct ulist *ulist = NULL;
int ret = 0;
int slot;
if (fs_info->quota_root)
goto out;
- fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
- if (!fs_info->qgroup_ulist) {
+ ulist = ulist_alloc(GFP_KERNEL);
+ if (!ulist) {
ret = -ENOMEM;
goto out;
}
ret = btrfs_sysfs_add_qgroups(fs_info);
if (ret < 0)
goto out;
+
+ /*
+ * Unlock qgroup_ioctl_lock before starting the transaction. This is to
+ * avoid lock acquisition inversion problems (reported by lockdep) between
+ * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we
+ * start a transaction.
+ * After we started the transaction lock qgroup_ioctl_lock again and
+ * check if someone else created the quota root in the meanwhile. If so,
+ * just return success and release the transaction handle.
+ *
+ * Also we don't need to worry about someone else calling
+ * btrfs_sysfs_add_qgroups() after we unlock and getting an error because
+ * that function returns 0 (success) when the sysfs entries already exist.
+ */
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
/*
* 1 for quota root item
* 1 for BTRFS_QGROUP_STATUS item
* would be a lot of overkill.
*/
trans = btrfs_start_transaction(tree_root, 2);
+
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
goto out;
}
+ if (fs_info->quota_root)
+ goto out;
+
+ fs_info->qgroup_ulist = ulist;
+ ulist = NULL;
+
/*
* initially create the quota tree
*/
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.type == BTRFS_ROOT_REF_KEY) {
+
+ /* Release locks on tree_root before we access quota_root */
+ btrfs_release_path(path);
+
ret = add_qgroup_item(trans, quota_root,
found_key.offset);
if (ret) {
btrfs_abort_transaction(trans, ret);
goto out_free_path;
}
+ ret = btrfs_search_slot_for_read(tree_root, &found_key,
+ path, 1, 0);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_free_path;
+ }
+ if (ret > 0) {
+ /*
+ * Shouldn't happen, but in case it does we
+ * don't need to do the btrfs_next_item, just
+ * continue.
+ */
+ continue;
+ }
}
ret = btrfs_next_item(tree_root, path);
if (ret < 0) {
if (ret) {
ulist_free(fs_info->qgroup_ulist);
fs_info->qgroup_ulist = NULL;
- if (trans)
- btrfs_end_transaction(trans);
btrfs_sysfs_del_qgroups(fs_info);
}
mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ if (ret && trans)
+ btrfs_end_transaction(trans);
+ else if (trans)
+ ret = btrfs_end_transaction(trans);
+ ulist_free(ulist);
return ret;
}
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
goto out;
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
/*
* 1 For the root item
*
* We should also reserve enough items for the quota tree deletion in
* btrfs_clean_quota_tree but this is not done.
+ *
+ * Also, we must always start a transaction without holding the mutex
+ * qgroup_ioctl_lock, see btrfs_quota_enable().
*/
trans = btrfs_start_transaction(fs_info->tree_root, 1);
+
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
+ trans = NULL;
goto out;
}
+ if (!fs_info->quota_root)
+ goto out;
+
clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
ret = btrfs_clean_quota_tree(trans, quota_root);
if (ret) {
btrfs_abort_transaction(trans, ret);
- goto end_trans;
+ goto out;
}
ret = btrfs_del_root(trans, "a_root->root_key);
if (ret) {
btrfs_abort_transaction(trans, ret);
- goto end_trans;
+ goto out;
}
list_del("a_root->dirty_list);
btrfs_put_root(quota_root);
-end_trans:
- ret = btrfs_end_transaction(trans);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ if (ret && trans)
+ btrfs_end_transaction(trans);
+ else if (trans)
+ ret = btrfs_end_transaction(trans);
+
return ret;
}
struct btrfs_qgroup *member;
struct btrfs_qgroup_list *list;
struct ulist *tmp;
+ unsigned int nofs_flag;
int ret = 0;
/* Check the level of src and dst first */
if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst))
return -EINVAL;
+ /* We hold a transaction handle open, must do a NOFS allocation. */
+ nofs_flag = memalloc_nofs_save();
tmp = ulist_alloc(GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
if (!tmp)
return -ENOMEM;
struct btrfs_qgroup_list *list;
struct ulist *tmp;
bool found = false;
+ unsigned int nofs_flag;
int ret = 0;
int ret2;
+ /* We hold a transaction handle open, must do a NOFS allocation. */
+ nofs_flag = memalloc_nofs_save();
tmp = ulist_alloc(GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
if (!tmp)
return -ENOMEM;
{
struct rb_node *node;
struct rb_node *next;
- struct ulist_node *entry = NULL;
+ struct ulist_node *entry;
int ret = 0;
node = reserved->range_changed.root.rb_node;
+ if (!node)
+ return 0;
while (node) {
entry = rb_entry(node, struct ulist_node, rb_node);
if (entry->val < start)
node = node->rb_right;
- else if (entry)
- node = node->rb_left;
else
- break;
+ node = node->rb_left;
}
- /* Empty changeset */
- if (!entry)
- return 0;
-
if (entry->val > start && rb_prev(&entry->rb_node))
entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node,
rb_node);
{
struct btrfs_trans_handle *trans;
int ret;
+ bool can_commit = true;
/*
* We don't want to run flush again and again, so if there is a running
return 0;
}
+ /*
+ * If current process holds a transaction, we shouldn't flush, as we
+ * assume all space reservation happens before a transaction handle is
+ * held.
+ *
+ * But there are cases like btrfs_delayed_item_reserve_metadata() where
+ * we try to reserve space with one transction handle already held.
+ * In that case we can't commit transaction, but at least try to end it
+ * and hope the started data writes can free some space.
+ */
+ if (current->journal_info &&
+ current->journal_info != BTRFS_SEND_TRANS_STUB)
+ can_commit = false;
+
ret = btrfs_start_delalloc_snapshot(root);
if (ret < 0)
goto out;
goto out;
}
- ret = btrfs_commit_transaction(trans);
+ if (can_commit)
+ ret = btrfs_commit_transaction(trans);
+ else
+ ret = btrfs_end_transaction(trans);
out:
clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state);
wake_up(&root->qgroup_flush_wait);
if (!dev->bdev)
continue;
+ if (test_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state))
+ continue;
+
if (dev_replace_is_ongoing &&
dev == fs_info->dev_replace.tgtdev) {
/*
}
have_zone = 1;
}
+ if (!have_zone)
+ radix_tree_delete(&fs_info->reada_tree, index);
spin_unlock(&fs_info->reada_lock);
up_read(&fs_info->dev_replace.rwsem);
kref_put(&rc->refcnt, reada_control_release);
}
+
+/*
+ * Before removing a device (device replace or device remove ioctls), call this
+ * function to wait for all existing readahead requests on the device and to
+ * make sure no one queues more readahead requests for the device.
+ *
+ * Must be called without holding neither the device list mutex nor the device
+ * replace semaphore, otherwise it will deadlock.
+ */
+void btrfs_reada_remove_dev(struct btrfs_device *dev)
+{
+ struct btrfs_fs_info *fs_info = dev->fs_info;
+
+ /* Serialize with readahead extent creation at reada_find_extent(). */
+ spin_lock(&fs_info->reada_lock);
+ set_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state);
+ spin_unlock(&fs_info->reada_lock);
+
+ /*
+ * There might be readahead requests added to the radix trees which
+ * were not yet added to the readahead work queue. We need to start
+ * them and wait for their completion, otherwise we can end up with
+ * use-after-free problems when dropping the last reference on the
+ * readahead extents and their zones, as they need to access the
+ * device structure.
+ */
+ reada_start_machine(fs_info);
+ btrfs_flush_workqueue(fs_info->readahead_workers);
+}
+
+/*
+ * If when removing a device (device replace or device remove ioctls) an error
+ * happens after calling btrfs_reada_remove_dev(), call this to undo what that
+ * function did. This is safe to call even if btrfs_reada_remove_dev() was not
+ * called before.
+ */
+void btrfs_reada_undo_remove_dev(struct btrfs_device *dev)
+{
+ spin_lock(&dev->fs_info->reada_lock);
+ clear_bit(BTRFS_DEV_STATE_NO_READA, &dev->dev_state);
+ spin_unlock(&dev->fs_info->reada_lock);
+}
"dropping a ref for a root that doesn't have a ref on the block");
dump_block_entry(fs_info, be);
dump_ref_action(fs_info, ra);
+ kfree(ref);
kfree(ra);
goto out_unlock;
}
struct btrfs_root_item *root_item;
struct btrfs_path *path;
struct extent_buffer *leaf;
+ int reserve_level;
int level;
int max_level;
int replaced = 0;
* Thus the needed metadata size is at most root_level * nodesize,
* and * 2 since we have two trees to COW.
*/
- min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2;
+ reserve_level = max_t(int, 1, btrfs_root_level(root_item));
+ min_reserved = fs_info->nodesize * reserve_level * 2;
memset(&next_key, 0, sizeof(next_key));
while (1) {
if (!is_dev_replace && !readonly &&
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
- rcu_str_deref(dev->name));
+ btrfs_err_in_rcu(fs_info,
+ "scrub on devid %llu: filesystem on %s is not writable",
+ devid, rcu_str_deref(dev->name));
ret = -EROFS;
goto out;
}
ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
BTRFS_MAX_EXTENT_SIZE >> 1,
(BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1,
- EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL);
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_UPTODATE, 0, 0, NULL);
if (ret) {
test_err("clear_extent_bit returned %d", ret);
goto out;
ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
BTRFS_MAX_EXTENT_SIZE + sectorsize,
BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1,
- EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL);
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_UPTODATE, 0, 0, NULL);
if (ret) {
test_err("clear_extent_bit returned %d", ret);
goto out;
/* Empty */
ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
- EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL);
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_UPTODATE, 0, 0, NULL);
if (ret) {
test_err("clear_extent_bit returned %d", ret);
goto out;
out:
if (ret)
clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
- EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL);
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_UPTODATE, 0, 0, NULL);
iput(inode);
btrfs_free_dummy_root(root);
btrfs_free_dummy_fs_info(fs_info);
u64 type;
u64 features;
bool mixed = false;
+ int raid_index;
+ int nparity;
+ int ncopies;
length = btrfs_chunk_length(leaf, chunk);
stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
type = btrfs_chunk_type(leaf, chunk);
+ raid_index = btrfs_bg_flags_to_raid_index(type);
+ ncopies = btrfs_raid_array[raid_index].ncopies;
+ nparity = btrfs_raid_array[raid_index].nparity;
if (!num_stripes) {
chunk_err(leaf, chunk, logical,
"invalid chunk num_stripes, have %u", num_stripes);
return -EUCLEAN;
}
+ if (num_stripes < ncopies) {
+ chunk_err(leaf, chunk, logical,
+ "invalid chunk num_stripes < ncopies, have %u < %d",
+ num_stripes, ncopies);
+ return -EUCLEAN;
+ }
+ if (nparity && num_stripes == nparity) {
+ chunk_err(leaf, chunk, logical,
+ "invalid chunk num_stripes == nparity, have %u == %d",
+ num_stripes, nparity);
+ return -EUCLEAN;
+ }
if (!IS_ALIGNED(logical, fs_info->sectorsize)) {
chunk_err(leaf, chunk, logical,
"invalid chunk logical, have %llu should aligned to %u",
"invalid root item size, have %u expect %zu or %u",
btrfs_item_size_nr(leaf, slot), sizeof(ri),
btrfs_legacy_root_item_size());
+ return -EUCLEAN;
}
/*
"invalid item size, have %u expect aligned to %zu for key type %u",
btrfs_item_size_nr(leaf, slot),
sizeof(*dref), key->type);
+ return -EUCLEAN;
}
if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) {
generic_err(leaf, slot,
extent_err(leaf, slot,
"invalid extent data backref offset, have %llu expect aligned to %u",
offset, leaf->fs_info->sectorsize);
+ return -EUCLEAN;
}
}
return 0;
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
- btrfs_device_data_ordered_init(dev);
+ btrfs_device_data_ordered_init(dev, fs_info);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
extent_io_tree_init(fs_info, &dev->alloc_state,
if (device->bdev != path_bdev) {
bdput(path_bdev);
mutex_unlock(&fs_devices->device_list_mutex);
- btrfs_warn_in_rcu(device->fs_info,
+ /*
+ * device->fs_info may not be reliable here, so
+ * pass in a NULL instead. This avoids a
+ * possible use-after-free when the fs_info and
+ * fs_info->sb are already torn down.
+ */
+ btrfs_warn_in_rcu(NULL,
"duplicate device %s devid %llu generation %llu scanned by %s (%d)",
path, devid, found_transid,
current->comm,
continue;
}
- if (device->devid == BTRFS_DEV_REPLACE_DEVID) {
- /*
- * In the first step, keep the device which has
- * the correct fsid and the devid that is used
- * for the dev_replace procedure.
- * In the second step, the dev_replace state is
- * read from the device tree and it is known
- * whether the procedure is really active or
- * not, which means whether this device is
- * used or whether it should be removed.
- */
- if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
- &device->dev_state)) {
- continue;
- }
- }
+ /*
+ * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID,
+ * in btrfs_init_dev_replace() so just continue.
+ */
+ if (device->devid == BTRFS_DEV_REPLACE_DEVID)
+ continue;
+
if (device->bdev) {
blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
list_del_init(&device->dev_alloc_list);
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
- if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT,
- &device->dev_state))
- fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
mutex_unlock(&uuid_mutex);
ret = btrfs_shrink_device(device, 0);
+ if (!ret)
+ btrfs_reada_remove_dev(device);
mutex_lock(&uuid_mutex);
if (ret)
goto error_undo;
return ret;
error_undo:
+ btrfs_reada_undo_remove_dev(device);
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
mutex_lock(&fs_info->chunk_mutex);
list_add(&device->dev_alloc_list,
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __BTRFS_NEED_DEVICE_DATA_ORDERED
-#define btrfs_device_data_ordered_init(device) \
- seqcount_init(&device->data_seqcount)
+#define btrfs_device_data_ordered_init(device, info) \
+ seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex)
#else
-#define btrfs_device_data_ordered_init(device) do { } while (0)
+#define btrfs_device_data_ordered_init(device, info) do { } while (0)
#endif
#define BTRFS_DEV_STATE_WRITEABLE (0)
#define BTRFS_DEV_STATE_MISSING (2)
#define BTRFS_DEV_STATE_REPLACE_TGT (3)
#define BTRFS_DEV_STATE_FLUSH_SENT (4)
+#define BTRFS_DEV_STATE_NO_READA (5)
struct btrfs_device {
struct list_head dev_list; /* device_list_mutex */
blk_status_t last_flush_error;
#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
- seqcount_t data_seqcount;
+ /* A seqcount_t with associated chunk_mutex (for lockdep) */
+ seqcount_mutex_t data_seqcount;
#endif
/* the internal btrfs device id */
static inline void \
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
{ \
- preempt_disable(); \
write_seqcount_begin(&dev->data_seqcount); \
dev->name = size; \
write_seqcount_end(&dev->data_seqcount); \
- preempt_enable(); \
}
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
_debug("reissue read");
ret = bmapping->a_ops->readpage(NULL, backpage);
if (ret < 0)
- goto unlock_discard;
+ goto discard;
}
/* but the page may have been read before the monitor was installed, so
unlock_discard:
unlock_page(backpage);
+discard:
spin_lock_irq(&object->work_lock);
list_del(&monitor->op_link);
spin_unlock_irq(&object->work_lock);
vino.snap, inode);
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
(unsigned)seq);
dname.len, dname.name);
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
if (!inode) {
dout("handle_lease no inode %llx\n", vino.ino);
bool check_session_state(struct ceph_mds_session *s)
{
- if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
- dout("resending session close request for mds%d\n",
- s->s_mds);
- request_close_session(s);
- return false;
- }
- if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
- if (s->s_state == CEPH_MDS_SESSION_OPEN) {
+ switch (s->s_state) {
+ case CEPH_MDS_SESSION_OPEN:
+ if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
s->s_state = CEPH_MDS_SESSION_HUNG;
pr_info("mds%d hung\n", s->s_mds);
}
- }
- if (s->s_state == CEPH_MDS_SESSION_NEW ||
- s->s_state == CEPH_MDS_SESSION_RESTARTING ||
- s->s_state == CEPH_MDS_SESSION_CLOSED ||
- s->s_state == CEPH_MDS_SESSION_REJECTED)
- /* this mds is failed or recovering, just wait */
+ break;
+ case CEPH_MDS_SESSION_CLOSING:
+ /* Should never reach this when we're unmounting */
+ WARN_ON_ONCE(true);
+ fallthrough;
+ case CEPH_MDS_SESSION_NEW:
+ case CEPH_MDS_SESSION_RESTARTING:
+ case CEPH_MDS_SESSION_CLOSED:
+ case CEPH_MDS_SESSION_REJECTED:
return false;
+ }
return true;
}
+/*
+ * If the sequence is incremented while we're waiting on a REQUEST_CLOSE reply,
+ * then we need to retransmit that request.
+ */
+void inc_session_sequence(struct ceph_mds_session *s)
+{
+ lockdep_assert_held(&s->s_mutex);
+
+ s->s_seq++;
+
+ if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
+ int ret;
+
+ dout("resending session close request for mds%d\n", s->s_mds);
+ ret = request_close_session(s);
+ if (ret < 0)
+ pr_err("unable to close session to mds%d: %d\n",
+ s->s_mds, ret);
+ }
+}
+
/*
* delayed work -- periodically trim expired leases, renew caps with mds
*/
extern const char *ceph_mds_op_name(int op);
extern bool check_session_state(struct ceph_mds_session *s);
+void inc_session_sequence(struct ceph_mds_session *s);
extern struct ceph_mds_session *
__ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
/* increment msg sequence number */
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
mutex_unlock(&session->s_mutex);
/* lookup inode */
ceph_snap_op_name(op), split, trace_len);
mutex_lock(&session->s_mutex);
- session->s_seq++;
+ inc_session_sequence(session);
mutex_unlock(&session->s_mutex);
down_write(&mdsc->snap_rwsem);
cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
} else if (mode_from_special_sid) {
rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, true);
+ kfree(pntsd);
} else {
/* get approximated mode from ACL */
rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, false);
list_del_init(&server->tcp_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
+ cancel_delayed_work_sync(&server->echo);
+
spin_lock(&GlobalMid_Lock);
server->tcpStatus = CifsExiting;
spin_unlock(&GlobalMid_Lock);
if (ses) {
spin_lock(&cifs_tcp_ses_lock);
ses->ses_count++;
- ses->tcon_ipc->remap = cifs_remap(cifs_sb);
+ if (ses->tcon_ipc)
+ ses->tcon_ipc->remap = cifs_remap(cifs_sb);
spin_unlock(&cifs_tcp_ses_lock);
}
*root_ses = ses;
}
static struct mid_q_entry *
-smb2_find_mid(struct TCP_Server_Info *server, char *buf)
+__smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue)
{
struct mid_q_entry *mid;
struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf;
(mid->mid_state == MID_REQUEST_SUBMITTED) &&
(mid->command == shdr->Command)) {
kref_get(&mid->refcount);
+ if (dequeue) {
+ list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
spin_unlock(&GlobalMid_Lock);
return mid;
}
return NULL;
}
+static struct mid_q_entry *
+smb2_find_mid(struct TCP_Server_Info *server, char *buf)
+{
+ return __smb2_find_mid(server, buf, false);
+}
+
+static struct mid_q_entry *
+smb2_find_dequeue_mid(struct TCP_Server_Info *server, char *buf)
+{
+ return __smb2_find_mid(server, buf, true);
+}
+
static void
smb2_dump_detail(void *buf, struct TCP_Server_Info *server)
{
rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE;
rc = SMB2_ioctl_init(tcon, server,
- &rqst[1], fid.persistent_fid,
- fid.volatile_fid, FSCTL_GET_REPARSE_POINT,
+ &rqst[1], COMPOUND_FID,
+ COMPOUND_FID, FSCTL_GET_REPARSE_POINT,
true /* is_fctl */, NULL, 0,
CIFSMaxBufSize -
MAX_SMB2_CREATE_RESPONSE_SIZE -
static int
handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
char *buf, unsigned int buf_len, struct page **pages,
- unsigned int npages, unsigned int page_data_size)
+ unsigned int npages, unsigned int page_data_size,
+ bool is_offloaded)
{
unsigned int data_offset;
unsigned int data_len;
if (server->ops->is_session_expired &&
server->ops->is_session_expired(buf)) {
- cifs_reconnect(server);
+ if (!is_offloaded)
+ cifs_reconnect(server);
return -1;
}
cifs_dbg(FYI, "%s: server returned error %d\n",
__func__, rdata->result);
/* normal error on read response */
- dequeue_mid(mid, false);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_RECEIVED;
+ else
+ dequeue_mid(mid, false);
return 0;
}
cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n",
__func__, data_offset);
rdata->result = -EIO;
- dequeue_mid(mid, rdata->result);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_MALFORMED;
+ else
+ dequeue_mid(mid, rdata->result);
return 0;
}
cifs_dbg(FYI, "%s: data offset (%u) beyond 1st page of response\n",
__func__, data_offset);
rdata->result = -EIO;
- dequeue_mid(mid, rdata->result);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_MALFORMED;
+ else
+ dequeue_mid(mid, rdata->result);
return 0;
}
if (data_len > page_data_size - pad_len) {
/* data_len is corrupt -- discard frame */
rdata->result = -EIO;
- dequeue_mid(mid, rdata->result);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_MALFORMED;
+ else
+ dequeue_mid(mid, rdata->result);
return 0;
}
rdata->result = init_read_bvec(pages, npages, page_data_size,
cur_off, &bvec);
if (rdata->result != 0) {
- dequeue_mid(mid, rdata->result);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_MALFORMED;
+ else
+ dequeue_mid(mid, rdata->result);
return 0;
}
/* read response payload cannot be in both buf and pages */
WARN_ONCE(1, "buf can not contain only a part of read data");
rdata->result = -EIO;
- dequeue_mid(mid, rdata->result);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_MALFORMED;
+ else
+ dequeue_mid(mid, rdata->result);
return 0;
}
if (length < 0)
return length;
- dequeue_mid(mid, false);
+ if (is_offloaded)
+ mid->mid_state = MID_RESPONSE_RECEIVED;
+ else
+ dequeue_mid(mid, false);
return length;
}
}
dw->server->lstrp = jiffies;
- mid = smb2_find_mid(dw->server, dw->buf);
+ mid = smb2_find_dequeue_mid(dw->server, dw->buf);
if (mid == NULL)
cifs_dbg(FYI, "mid not found\n");
else {
mid->decrypted = true;
rc = handle_read_data(dw->server, mid, dw->buf,
dw->server->vals->read_rsp_size,
- dw->ppages, dw->npages, dw->len);
- mid->callback(mid);
+ dw->ppages, dw->npages, dw->len,
+ true);
+ if (rc >= 0) {
+#ifdef CONFIG_CIFS_STATS2
+ mid->when_received = jiffies;
+#endif
+ mid->callback(mid);
+ } else {
+ spin_lock(&GlobalMid_Lock);
+ if (dw->server->tcpStatus == CifsNeedReconnect) {
+ mid->mid_state = MID_RETRY_NEEDED;
+ spin_unlock(&GlobalMid_Lock);
+ mid->callback(mid);
+ } else {
+ mid->mid_state = MID_REQUEST_SUBMITTED;
+ mid->mid_flags &= ~(MID_DELETED);
+ list_add_tail(&mid->qhead,
+ &dw->server->pending_mid_q);
+ spin_unlock(&GlobalMid_Lock);
+ }
+ }
cifs_mid_q_entry_release(mid);
}
(*mid)->decrypted = true;
rc = handle_read_data(server, *mid, buf,
server->vals->read_rsp_size,
- pages, npages, len);
+ pages, npages, len, false);
}
free_pages:
char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
return handle_read_data(server, mid, buf, server->pdu_size,
- NULL, 0, 0);
+ NULL, 0, 0, false);
}
static int
create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
{
struct crt_sd_ctxt *buf;
- struct cifs_ace *pace;
- unsigned int sdlen, acelen;
+ __u8 *ptr, *aclptr;
+ unsigned int acelen, acl_size, ace_count;
unsigned int owner_offset = 0;
unsigned int group_offset = 0;
+ struct smb3_acl acl;
- *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 2), 8);
+ *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8);
if (set_owner) {
- /* offset fields are from beginning of security descriptor not of create context */
- owner_offset = sizeof(struct smb3_acl) + (sizeof(struct cifs_ace) * 2);
-
/* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */
*len += sizeof(struct owner_group_sids);
}
if (buf == NULL)
return buf;
+ ptr = (__u8 *)&buf[1];
if (set_owner) {
+ /* offset fields are from beginning of security descriptor not of create context */
+ owner_offset = ptr - (__u8 *)&buf->sd;
buf->sd.OffsetOwner = cpu_to_le32(owner_offset);
- group_offset = owner_offset + sizeof(struct owner_sid);
+ group_offset = owner_offset + offsetof(struct owner_group_sids, group);
buf->sd.OffsetGroup = cpu_to_le32(group_offset);
+
+ setup_owner_group_sids(ptr);
+ ptr += sizeof(struct owner_group_sids);
} else {
buf->sd.OffsetOwner = 0;
buf->sd.OffsetGroup = 0;
}
- sdlen = sizeof(struct smb3_sd) + sizeof(struct smb3_acl) +
- 2 * sizeof(struct cifs_ace);
- if (set_owner) {
- sdlen += sizeof(struct owner_group_sids);
- setup_owner_group_sids(owner_offset + sizeof(struct create_context) + 8 /* name */
- + (char *)buf);
- }
-
- buf->ccontext.DataOffset = cpu_to_le16(offsetof
- (struct crt_sd_ctxt, sd));
- buf->ccontext.DataLength = cpu_to_le32(sdlen);
+ buf->ccontext.DataOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, sd));
buf->ccontext.NameOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, Name));
buf->ccontext.NameLength = cpu_to_le16(4);
/* SMB2_CREATE_SD_BUFFER_TOKEN is "SecD" */
buf->Name[2] = 'c';
buf->Name[3] = 'D';
buf->sd.Revision = 1; /* Must be one see MS-DTYP 2.4.6 */
+
/*
* ACL is "self relative" ie ACL is stored in contiguous block of memory
* and "DP" ie the DACL is present
buf->sd.Control = cpu_to_le16(ACL_CONTROL_SR | ACL_CONTROL_DP);
/* offset owner, group and Sbz1 and SACL are all zero */
- buf->sd.OffsetDacl = cpu_to_le32(sizeof(struct smb3_sd));
- buf->acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */
+ buf->sd.OffsetDacl = cpu_to_le32(ptr - (__u8 *)&buf->sd);
+ /* Ship the ACL for now. we will copy it into buf later. */
+ aclptr = ptr;
+ ptr += sizeof(struct cifs_acl);
/* create one ACE to hold the mode embedded in reserved special SID */
- pace = (struct cifs_ace *)(sizeof(struct crt_sd_ctxt) + (char *)buf);
- acelen = setup_special_mode_ACE(pace, (__u64)mode);
+ acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode);
+ ptr += acelen;
+ acl_size = acelen + sizeof(struct smb3_acl);
+ ace_count = 1;
if (set_owner) {
/* we do not need to reallocate buffer to add the two more ACEs. plenty of space */
- pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + (char *)buf));
- acelen += setup_special_user_owner_ACE(pace);
- /* it does not appear necessary to add an ACE for the NFS group SID */
- buf->acl.AceCount = cpu_to_le16(3);
- } else
- buf->acl.AceCount = cpu_to_le16(2);
+ acelen = setup_special_user_owner_ACE((struct cifs_ace *)ptr);
+ ptr += acelen;
+ acl_size += acelen;
+ ace_count += 1;
+ }
/* and one more ACE to allow access for authenticated users */
- pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) +
- (char *)buf));
- acelen += setup_authusers_ACE(pace);
-
- buf->acl.AclSize = cpu_to_le16(sizeof(struct cifs_acl) + acelen);
+ acelen = setup_authusers_ACE((struct cifs_ace *)ptr);
+ ptr += acelen;
+ acl_size += acelen;
+ ace_count += 1;
+
+ acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */
+ acl.AclSize = cpu_to_le16(acl_size);
+ acl.AceCount = cpu_to_le16(ace_count);
+ memcpy(aclptr, &acl, sizeof(struct cifs_acl));
+
+ buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd);
+ *len = ptr - (__u8 *)buf;
return buf;
}
struct create_context ccontext;
__u8 Name[8];
struct smb3_sd sd;
- struct smb3_acl acl;
- /* Followed by at least 4 ACEs */
} __packed;
return -EAGAIN;
if (signal_pending(current)) {
- cifs_dbg(FYI, "signal is pending before sending any data\n");
- return -EINTR;
+ cifs_dbg(FYI, "signal pending before send request\n");
+ return -ERESTARTSYS;
}
/* cork the socket */
*/
if (ispipe) {
if (isspace(*pat_ptr)) {
- was_space = true;
+ if (cn->used != 0)
+ was_space = true;
pat_ptr++;
continue;
} else if (was_space) {
int i;
/* The file must need contents encryption, not filenames encryption */
- if (!fscrypt_needs_contents_encryption(inode))
+ if (!S_ISREG(inode->i_mode))
return 0;
/* The crypto mode must have a blk-crypto counterpart */
* New inodes may not have an inode number assigned yet.
* Hashing their inode number is delayed until later.
*/
- if (ci->ci_inode->i_ino == 0)
- WARN_ON(!(ci->ci_inode->i_state & I_CREATING));
- else
+ if (ci->ci_inode->i_ino)
fscrypt_hash_inode_number(ci, mk);
return 0;
}
* file will be created in the root of the debugfs filesystem.
* @read_fn: function pointer called to print the seq_file content.
*/
-struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
- struct dentry *parent,
- int (*read_fn)(struct seq_file *s,
- void *data))
+void debugfs_create_devm_seqfile(struct device *dev, const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s, void *data))
{
struct debugfs_devm_entry *entry;
if (IS_ERR(parent))
- return ERR_PTR(-ENOENT);
+ return;
entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL);
if (!entry)
- return ERR_PTR(-ENOMEM);
+ return;
entry->read = read_fn;
entry->dev = dev;
- return debugfs_create_file(name, S_IRUGO, parent, entry,
- &debugfs_devm_entry_ops);
+ debugfs_create_file(name, S_IRUGO, parent, entry,
+ &debugfs_devm_entry_ops);
}
EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile);
#include <linux/efi.h>
#include <linux/fs.h>
#include <linux/ctype.h>
+#include <linux/kmemleak.h>
#include <linux/slab.h>
#include <linux/uuid.h>
var->var.VariableName[i] = '\0';
inode->i_private = var;
+ kmemleak_ignore(var);
err = efivar_entry_add(var, &efivarfs_list);
if (err)
i_gid_write(inode, le32_to_cpu(die->i_gid));
set_nlink(inode, le32_to_cpu(die->i_nlink));
- /* ns timestamp */
- inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
- le64_to_cpu(die->i_ctime);
- inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
- le32_to_cpu(die->i_ctime_nsec);
+ /* extended inode has its own timestamp */
+ inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime);
+ inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec);
inode->i_size = le64_to_cpu(die->i_size);
i_gid_write(inode, le16_to_cpu(dic->i_gid));
set_nlink(inode, le16_to_cpu(dic->i_nlink));
- /* use build time to derive all file time */
- inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
- sbi->build_time;
- inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
- sbi->build_time_nsec;
+ /* use build time for compact inodes */
+ inode->i_ctime.tv_sec = sbi->build_time;
+ inode->i_ctime.tv_nsec = sbi->build_time_nsec;
inode->i_size = le32_to_cpu(dic->i_size);
if (erofs_inode_is_data_compressed(vi->datalayout))
goto err_out;
}
+ inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
+ inode->i_atime.tv_sec = inode->i_ctime.tv_sec;
+ inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec;
+ inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;
+
if (!nblks)
/* measure inode.i_blocks as generic filesystems */
inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
cond_resched();
goto repeat;
}
- set_page_private(page, (unsigned long)pcl);
- SetPagePrivate(page);
+
+ if (tocache) {
+ set_page_private(page, (unsigned long)pcl);
+ SetPagePrivate(page);
+ }
out: /* the only exit (for tracing and debugging) */
return page;
}
};
#ifdef CONFIG_UNICODE
-static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
- const char *str, const struct qstr *name)
-{
- struct qstr qstr = {.name = str, .len = len };
- const struct dentry *parent = READ_ONCE(dentry->d_parent);
- const struct inode *inode = d_inode_rcu(parent);
- char strbuf[DNAME_INLINE_LEN];
-
- if (!inode || !IS_CASEFOLDED(inode) ||
- !EXT4_SB(inode->i_sb)->s_encoding) {
- if (len != name->len)
- return -1;
- return memcmp(str, name->name, len);
- }
-
- /*
- * If the dentry name is stored in-line, then it may be concurrently
- * modified by a rename. If this happens, the VFS will eventually retry
- * the lookup, so it doesn't matter what ->d_compare() returns.
- * However, it's unsafe to call utf8_strncasecmp() with an unstable
- * string. Therefore, we have to copy the name into a temporary buffer.
- */
- if (len <= DNAME_INLINE_LEN - 1) {
- memcpy(strbuf, str, len);
- strbuf[len] = 0;
- qstr.name = strbuf;
- /* prevent compiler from optimizing out the temporary buffer */
- barrier();
- }
-
- return ext4_ci_compare(inode, name, &qstr, false);
-}
-
-static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
-{
- const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
- const struct unicode_map *um = sbi->s_encoding;
- const struct inode *inode = d_inode_rcu(dentry);
- unsigned char *norm;
- int len, ret = 0;
-
- if (!inode || !IS_CASEFOLDED(inode) || !um)
- return 0;
-
- norm = kmalloc(PATH_MAX, GFP_ATOMIC);
- if (!norm)
- return -ENOMEM;
-
- len = utf8_casefold(um, str, norm, PATH_MAX);
- if (len < 0) {
- if (ext4_has_strict_mode(sbi))
- ret = -EINVAL;
- goto out;
- }
- str->hash = full_name_hash(dentry, norm, len);
-out:
- kfree(norm);
- return ret;
-}
-
const struct dentry_operations ext4_dentry_ops = {
- .d_hash = ext4_d_hash,
- .d_compare = ext4_d_compare,
+ .d_hash = generic_ci_d_hash,
+ .d_compare = generic_ci_d_compare,
};
#endif
* protected by sbi->s_fc_lock.
*/
- /* Fast commit subtid when this inode was committed */
- unsigned int i_fc_committed_subtid;
-
/* Start of lblk range that needs to be committed in this fast commit */
ext4_lblk_t i_fc_lblk_start;
#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */
#define EXT4_ERROR_FS 0x0002 /* Errors detected */
#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */
-#define EXT4_FC_INELIGIBLE 0x0008 /* Fast commit ineligible */
-#define EXT4_FC_COMMITTING 0x0010 /* File system underoing a fast
- * commit.
- */
#define EXT4_FC_REPLAY 0x0020 /* Fast commit replay ongoing */
/*
blocks */
#define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated
file systems */
-#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */
-#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */
-
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly
specified journal checksum */
#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */
+#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */
+
#define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \
~EXT4_MOUNT_##opt
#ifdef __KERNEL__
-/*
- * run-time mount flags
- */
-#define EXT4_MF_MNTDIR_SAMPLED 0x0001
-#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */
-
#ifdef CONFIG_FS_ENCRYPTION
#define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL)
#else
#define EXT4_ENC_UTF8_12_1 1
-/*
- * Flags for ext4_sb_info.s_encoding_flags.
- */
-#define EXT4_ENC_STRICT_MODE_FL (1 << 0)
-
-#define ext4_has_strict_mode(sbi) \
- (sbi->s_encoding_flags & EXT4_ENC_STRICT_MODE_FL)
-
/*
* fourth extended-fs super-block data in memory
*/
struct buffer_head * __rcu *s_group_desc;
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
- unsigned int s_mount_flags;
+ unsigned long s_mount_flags;
unsigned int s_def_mount_opt;
ext4_fsblk_t s_sb_block;
atomic64_t s_resv_clusters;
struct kobject s_kobj;
struct completion s_kobj_unregister;
struct super_block *s_sb;
-#ifdef CONFIG_UNICODE
- struct unicode_map *s_encoding;
- __u16 s_encoding_flags;
-#endif
/* Journaling */
struct journal_s *s_journal;
_v; \
})
+/*
+ * run-time mount flags
+ */
+enum {
+ EXT4_MF_MNTDIR_SAMPLED,
+ EXT4_MF_FS_ABORTED, /* Fatal error detected */
+ EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */
+ EXT4_MF_FC_COMMITTING /* File system underoing a fast
+ * commit.
+ */
+};
+
+static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
+{
+ set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
+{
+ clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
+{
+ return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+
/*
* Simulate_fail codes
*/
#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200
+/*
+ * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
+ * incompatible only if fast commit blocks are present in the FS. Since we
+ * clear the journal (and thus the fast commit blocks), we don't mark FS as
+ * incompatible. We also have a JBD2 incompat feature, which gets set when
+ * there are fast commit blocks present in the journal.
+ */
#define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400
#define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800
struct ext4_filename *fname);
static inline void ext4_update_dx_flag(struct inode *inode)
{
- if (!ext4_has_feature_dir_index(inode->i_sb)) {
+ if (!ext4_has_feature_dir_index(inode->i_sb) &&
+ ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
/* ext4_iget() should have caught this... */
WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
int ext4_fc_info_show(struct seq_file *seq, void *v);
void ext4_fc_init(struct super_block *sb, journal_t *journal);
void ext4_fc_init_inode(struct inode *inode);
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end);
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry);
-void ext4_fc_track_inode(struct inode *inode);
+void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
+ struct dentry *dentry);
+void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
+ struct dentry *dentry);
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
void ext4_fc_start_ineligible(struct super_block *sb, int reason);
void ext4_fc_stop_ineligible(struct super_block *sb);
extern int ext4_ci_compare(const struct inode *parent,
const struct qstr *fname,
const struct qstr *entry, bool quick);
-extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
struct inode *inode);
extern int __ext4_link(struct inode *dir, struct inode *inode,
struct dentry *dentry);
}
/*
- * search the closest allocated block to the right for *logical
- * and returns it at @logical + it's physical address at @phys
- * if *logical is the largest allocated block, the function
- * returns 0 at @phys
- * return value contains 0 (success) or error code
+ * Search the closest allocated block to the right for *logical
+ * and returns it at @logical + it's physical address at @phys.
+ * If not exists, return 0 and @phys is set to 0. We will return
+ * 1 which means we found an allocated block and ret_ex is valid.
+ * Or return a (< 0) error code.
*/
static int ext4_ext_search_right(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t *logical, ext4_fsblk_t *phys,
- struct ext4_extent **ret_ex)
+ struct ext4_extent *ret_ex)
{
struct buffer_head *bh = NULL;
struct ext4_extent_header *eh;
found_extent:
*logical = le32_to_cpu(ex->ee_block);
*phys = ext4_ext_pblock(ex);
- *ret_ex = ex;
+ if (ret_ex)
+ *ret_ex = *ex;
if (bh)
put_bh(bh);
- return 0;
+ return 1;
}
/*
*/
lblk = ex_end + 1;
err = ext4_ext_search_right(inode, path, &lblk, &pblk,
- &ex);
- if (err)
+ NULL);
+ if (err < 0)
goto out;
if (pblk) {
partial.pclu = EXT4_B2C(sbi, pblk);
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
out:
ext4_ext_show_leaf(inode, path);
- ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
return err;
}
if (*allocated > map->m_len)
*allocated = map->m_len;
map->m_len = *allocated;
- ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1);
return 0;
}
struct ext4_map_blocks *map, int flags)
{
struct ext4_ext_path *path = NULL;
- struct ext4_extent newex, *ex, *ex2;
+ struct ext4_extent newex, *ex, ex2;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0, pblk;
int err = 0, depth, ret;
if (err)
goto out;
ar.lright = map->m_lblk;
- ex2 = NULL;
err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2);
- if (err)
+ if (err < 0)
goto out;
/* Check if the extent after searching to the right implies a
* cluster we can use. */
- if ((sbi->s_cluster_ratio > 1) && ex2 &&
- get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) {
+ if ((sbi->s_cluster_ratio > 1) && err &&
+ get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) {
ar.len = allocated = map->m_len;
newblock = map->m_pblk;
goto got_allocated_blocks;
map->m_len = ar.len;
allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
- ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1);
out:
ext4_ext_drop_refs(path);
kfree(path);
ret = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret))
goto out_handle;
- ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits,
+ ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits,
(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
/* Zero out partial block at the edges of the range */
ret = ext4_zero_partial_blocks(handle, inode, offset, len);
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
return -EOPNOTSUPP;
- ext4_fc_track_range(inode, offset >> blkbits,
- (offset + len - 1) >> blkbits);
ext4_fc_start_update(inode);
*
* Atomicity of commits
* --------------------
- * In order to gaurantee atomicity during the commit operation, fast commit
+ * In order to guarantee atomicity during the commit operation, fast commit
* uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
* tag contains CRC of the contents and TID of the transaction after which
* this fast commit should be applied. Recovery code replays fast commit
INIT_LIST_HEAD(&ei->i_fc_list);
init_waitqueue_head(&ei->i_fc_wait);
atomic_set(&ei->i_fc_updates, 0);
- ei->i_fc_committed_subtid = 0;
+}
+
+/* This function must be called with sbi->s_fc_lock held. */
+static void ext4_fc_wait_committing_inode(struct inode *inode)
+__releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
+{
+ wait_queue_head_t *wq;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+#if (BITS_PER_LONG < 64)
+ DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+ EXT4_STATE_FC_COMMITTING);
+ wq = bit_waitqueue(&ei->i_state_flags,
+ EXT4_STATE_FC_COMMITTING);
+#else
+ DEFINE_WAIT_BIT(wait, &ei->i_flags,
+ EXT4_STATE_FC_COMMITTING);
+ wq = bit_waitqueue(&ei->i_flags,
+ EXT4_STATE_FC_COMMITTING);
+#endif
+ lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock);
+ prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+ schedule();
+ finish_wait(wq, &wait.wq_entry);
}
/*
goto out;
if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
- wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
- DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
-#else
- DEFINE_WAIT_BIT(wait, &ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
-#endif
- prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- schedule();
- finish_wait(wq, &wait.wq_entry);
+ ext4_fc_wait_committing_inode(inode);
goto restart;
}
out:
}
if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
- wait_queue_head_t *wq;
-#if (BITS_PER_LONG < 64)
- DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
-#else
- DEFINE_WAIT_BIT(wait, &ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
-#endif
- prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- schedule();
- finish_wait(wq, &wait.wq_entry);
+ ext4_fc_wait_committing_inode(inode);
goto restart;
}
- if (!list_empty(&ei->i_fc_list))
- list_del_init(&ei->i_fc_list);
+ list_del_init(&ei->i_fc_list);
spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
}
(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return;
- sbi->s_mount_state |= EXT4_FC_INELIGIBLE;
+ ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
WARN_ON(reason >= EXT4_FC_REASON_MAX);
sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
}
}
/*
- * Stop a fast commit ineligible update. We set EXT4_FC_INELIGIBLE flag here
+ * Stop a fast commit ineligible update. We set EXT4_MF_FC_INELIGIBLE flag here
* to ensure that after stopping the ineligible update, at least one full
* commit takes place.
*/
(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return;
- EXT4_SB(sb)->s_mount_state |= EXT4_FC_INELIGIBLE;
+ ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
}
static inline int ext4_fc_is_ineligible(struct super_block *sb)
{
- return (EXT4_SB(sb)->s_mount_state & EXT4_FC_INELIGIBLE) ||
- atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates);
+ return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) ||
+ atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates));
}
/*
* If enqueue is set, this function enqueues the inode in fast commit list.
*/
static int ext4_fc_track_template(
- struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool),
+ handle_t *handle, struct inode *inode,
+ int (*__fc_track_fn)(struct inode *, void *, bool),
void *args, int enqueue)
{
- tid_t running_txn_tid;
bool update = false;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ tid_t tid = 0;
int ret;
if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
if (ext4_fc_is_ineligible(inode->i_sb))
return -EINVAL;
- running_txn_tid = sbi->s_journal ?
- sbi->s_journal->j_commit_sequence + 1 : 0;
-
+ tid = handle->h_transaction->t_tid;
mutex_lock(&ei->i_fc_lock);
- if (running_txn_tid == ei->i_sync_tid) {
+ if (tid == ei->i_sync_tid) {
update = true;
} else {
ext4_fc_reset_inode(inode);
- ei->i_sync_tid = running_txn_tid;
+ ei->i_sync_tid = tid;
}
ret = __fc_track_fn(inode, args, update);
mutex_unlock(&ei->i_fc_lock);
spin_lock(&sbi->s_fc_lock);
if (list_empty(&EXT4_I(inode)->i_fc_list))
list_add_tail(&EXT4_I(inode)->i_fc_list,
- (sbi->s_mount_state & EXT4_FC_COMMITTING) ?
+ (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
&sbi->s_fc_q[FC_Q_STAGING] :
&sbi->s_fc_q[FC_Q_MAIN]);
spin_unlock(&sbi->s_fc_lock);
mutex_unlock(&ei->i_fc_lock);
node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
if (!node) {
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
if (!node->fcd_name.name) {
kmem_cache_free(ext4_fc_dentry_cachep, node);
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_MEM);
+ EXT4_FC_REASON_NOMEM);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
node->fcd_name.len = dentry->d_name.len;
spin_lock(&sbi->s_fc_lock);
- if (sbi->s_mount_state & EXT4_FC_COMMITTING)
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
list_add_tail(&node->fcd_list,
&sbi->s_fc_dentry_q[FC_Q_STAGING]);
else
return 0;
}
-void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry)
+void __ext4_fc_track_unlink(handle_t *handle,
+ struct inode *inode, struct dentry *dentry)
{
struct __track_dentry_update_args args;
int ret;
args.dentry = dentry;
args.op = EXT4_FC_TAG_UNLINK;
- ret = ext4_fc_track_template(inode, __track_dentry_update,
+ ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
trace_ext4_fc_track_unlink(inode, dentry, ret);
}
-void ext4_fc_track_link(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
+{
+ __ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+}
+
+void __ext4_fc_track_link(handle_t *handle,
+ struct inode *inode, struct dentry *dentry)
{
struct __track_dentry_update_args args;
int ret;
args.dentry = dentry;
args.op = EXT4_FC_TAG_LINK;
- ret = ext4_fc_track_template(inode, __track_dentry_update,
+ ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
trace_ext4_fc_track_link(inode, dentry, ret);
}
-void ext4_fc_track_create(struct inode *inode, struct dentry *dentry)
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
+{
+ __ext4_fc_track_link(handle, d_inode(dentry), dentry);
+}
+
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
{
struct __track_dentry_update_args args;
+ struct inode *inode = d_inode(dentry);
int ret;
args.dentry = dentry;
args.op = EXT4_FC_TAG_CREAT;
- ret = ext4_fc_track_template(inode, __track_dentry_update,
+ ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
trace_ext4_fc_track_create(inode, dentry, ret);
}
return 0;
}
-void ext4_fc_track_inode(struct inode *inode)
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
{
int ret;
if (S_ISDIR(inode->i_mode))
return;
- ret = ext4_fc_track_template(inode, __track_inode, NULL, 1);
+ if (ext4_should_journal_data(inode)) {
+ ext4_fc_mark_ineligible(inode->i_sb,
+ EXT4_FC_REASON_INODE_JOURNAL_DATA);
+ return;
+ }
+
+ ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
trace_ext4_fc_track_inode(inode, ret);
}
return 0;
}
-void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start,
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
struct __track_range_args args;
args.start = start;
args.end = end;
- ret = ext4_fc_track_template(inode, __track_range, &args, 1);
+ ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1);
trace_ext4_fc_track_range(inode, start, end, ret);
}
int write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
+ /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
if (test_opt(sb, BARRIER))
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
- clear_buffer_dirty(bh);
+ set_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = ext4_end_buffer_io_sync;
submit_bh(REQ_OP_WRITE, write_flags, bh);
int ret = 0;
spin_lock(&sbi->s_fc_lock);
- sbi->s_mount_state |= EXT4_FC_COMMITTING;
+ ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
/* Commit all the directory entry updates */
static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
+__acquires(&sbi->s_fc_lock)
+__releases(&sbi->s_fc_lock)
{
struct super_block *sb = (struct super_block *)(journal->j_private);
struct ext4_sb_info *sbi = EXT4_SB(sb);
fc_dentry->fcd_parent, fc_dentry->fcd_ino,
fc_dentry->fcd_name.len,
fc_dentry->fcd_name.name, crc)) {
- spin_lock(&sbi->s_fc_lock);
ret = -ENOSPC;
goto lock_and_exit;
}
if (ret)
return ret;
+ /*
+ * If file system device is different from journal device, issue a cache
+ * flush before we start writing fast commit blocks.
+ */
+ if (journal->j_fs_dev != journal->j_dev)
+ blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS);
+
blk_start_plug(&plug);
if (sbi->s_fc_bytes == 0) {
/*
if (ret)
goto out;
spin_lock(&sbi->s_fc_lock);
- EXT4_I(inode)->i_fc_committed_subtid =
- atomic_read(&sbi->s_fc_subtid);
}
spin_unlock(&sbi->s_fc_lock);
"Fast commit ended with blks = %d, reason = %d, subtid - %d",
nblks, reason, subtid);
if (reason == EXT4_FC_REASON_FC_FAILED)
- return jbd2_fc_end_commit_fallback(journal, commit_tid);
+ return jbd2_fc_end_commit_fallback(journal);
if (reason == EXT4_FC_REASON_FC_START_FAILED ||
reason == EXT4_FC_REASON_INELIGIBLE)
return jbd2_complete_transaction(journal, commit_tid);
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
&sbi->s_fc_q[FC_Q_STAGING]);
- sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
- sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
if (full)
sbi->s_fc_bytes = 0;
return 0;
}
- ret = __ext4_unlink(old_parent, &entry, inode);
+ ret = __ext4_unlink(NULL, old_parent, &entry, inode);
/* -ENOENT ok coz it might not exist anymore. */
if (ret == -ENOENT)
ret = 0;
if (ret == 0) {
/* Range is not mapped */
path = ext4_find_extent(inode, cur, NULL, 0);
- if (!path)
- continue;
+ if (IS_ERR(path)) {
+ iput(inode);
+ return 0;
+ }
memset(&newex, 0, sizeof(newex));
newex.ee_block = cpu_to_le32(cur);
ext4_ext_store_pblock(
if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
return;
journal->j_fc_cleanup_callback = ext4_fc_cleanup;
- if (jbd2_fc_init(journal, EXT4_NUM_FC_BLKS)) {
- pr_warn("Error while enabling fast commits, turning off.");
- ext4_clear_feature_fast_commit(sb);
- }
}
-const char *fc_ineligible_reasons[] = {
+static const char *fc_ineligible_reasons[] = {
"Extended attributes changed",
"Cross rename",
"Journal flag changed",
"Resize",
"Dir renamed",
"Falloc range op",
+ "Data journalling",
"FC Commit Failed"
};
#ifndef __FAST_COMMIT_H__
#define __FAST_COMMIT_H__
-/* Number of blocks in journal area to allocate for fast commits */
-#define EXT4_NUM_FC_BLKS 256
-
/* Fast commit tags */
#define EXT4_FC_TAG_ADD_RANGE 0x0001
#define EXT4_FC_TAG_DEL_RANGE 0x0002
EXT4_FC_REASON_XATTR = 0,
EXT4_FC_REASON_CROSS_RENAME,
EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
- EXT4_FC_REASON_MEM,
+ EXT4_FC_REASON_NOMEM,
EXT4_FC_REASON_SWAP_BOOT,
EXT4_FC_REASON_RESIZE,
EXT4_FC_REASON_RENAME_DIR,
EXT4_FC_REASON_FALLOC_RANGE,
+ EXT4_FC_REASON_INODE_JOURNAL_DATA,
EXT4_FC_COMMIT_FAILED,
EXT4_FC_REASON_MAX
};
if (!daxdev_mapping_supported(vma, dax_dev))
return -EOPNOTSUPP;
- ext4_fc_start_update(inode);
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
} else {
vma->vm_ops = &ext4_file_vm_ops;
}
- ext4_fc_stop_update(inode);
return 0;
}
handle_t *handle;
int err;
- if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+ if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED)))
return 0;
if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
return 0;
- sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+ ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED);
/*
* Sample where the filesystem has been mounted and
* store it in the superblock for sysadmin convenience
/* Fabricate an rmap entry for the external log device. */
irec.fmr_physical = journal->j_blk_offset;
- irec.fmr_length = journal->j_maxlen;
+ irec.fmr_length = journal->j_total_len;
irec.fmr_owner = EXT4_FMR_OWN_LOG;
irec.fmr_flags = 0;
if (sb_rdonly(inode->i_sb)) {
/* Make sure that we read updated s_mount_flags value */
smp_rmb();
- if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))
ret = -EROFS;
goto out;
}
struct dx_hash_info *hinfo)
{
#ifdef CONFIG_UNICODE
- const struct unicode_map *um = EXT4_SB(dir->i_sb)->s_encoding;
+ const struct unicode_map *um = dir->i_sb->s_encoding;
int r, dlen;
unsigned char *buff;
struct qstr qstr = {.name = name, .len = len };
ext4_write_lock_xattr(inode, &no_expand);
if (!ext4_has_inline_data(inode)) {
+ ext4_write_unlock_xattr(inode, &no_expand);
*has_inline = 0;
ext4_journal_stop(handle);
return 0;
ext4_xattr_inode_array_free(ea_inode_array);
return;
no_delete:
+ if (!list_empty(&EXT4_I(inode)->i_fc_list))
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
if (ret)
return ret;
}
- ext4_fc_track_range(inode, map->m_lblk,
+ ext4_fc_track_range(handle, inode, map->m_lblk,
map->m_lblk + map->m_len - 1);
}
}
if (ret == 0)
ret = err;
- err = ext4_jbd2_inode_add_write(handle, inode, 0, len);
+ err = ext4_jbd2_inode_add_write(handle, inode, page_offset(page), len);
if (ret == 0)
ret = err;
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
struct super_block *sb = inode->i_sb;
if (ext4_forced_shutdown(EXT4_SB(sb)) ||
- EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
* the stack trace.
*/
if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
- sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
ret = -EROFS;
goto out_writepages;
}
if (journal) {
if (jbd2_transaction_committed(journal,
- EXT4_I(inode)->i_datasync_tid))
- return true;
- return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) >=
- EXT4_I(inode)->i_fc_committed_subtid;
+ EXT4_I(inode)->i_datasync_tid))
+ return false;
+ if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+ return !list_empty(&EXT4_I(inode)->i_fc_list);
+ return true;
}
/* Any metadata buffers to write? */
up_write(&EXT4_I(inode)->i_data_sem);
}
- ext4_fc_track_range(inode, first_block, stop_block);
+ ext4_fc_track_range(handle, inode, first_block, stop_block);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
}
if (shrink)
- ext4_fc_track_range(inode,
+ ext4_fc_track_range(handle, inode,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
inode->i_sb->s_blocksize_bits,
(oldsize > 0 ? oldsize - 1 : 0) >>
inode->i_sb->s_blocksize_bits);
else
ext4_fc_track_range(
- inode,
+ handle, inode,
(oldsize > 0 ? oldsize - 1 : oldsize) >>
inode->i_sb->s_blocksize_bits,
(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
put_bh(iloc->bh);
return -EIO;
}
- ext4_fc_track_inode(inode);
+ ext4_fc_track_inode(handle, inode);
if (IS_I_VERSION(inode))
inode_inc_iversion(inode);
if (ext4_walk_page_buffers(handle, page_buffers(page),
0, len, NULL, write_end_fn))
goto out_error;
- if (ext4_jbd2_inode_add_write(handle, inode, 0, len))
+ if (ext4_jbd2_inode_add_write(handle, inode,
+ page_offset(page), len))
goto out_error;
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
} else {
{
ext4_group_t i, ngroups;
- if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
return;
ngroups = ext4_get_groups_count(sb);
{
struct super_block *sb = ac->ac_sb;
- if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
return;
mb_debug(sb, "Can't allocate:"
struct super_block *sb = ar->inode->i_sb;
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i;
+ int i = sb->s_blocksize;
ext4_fsblk_t goal, block;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
const struct qstr *entry, bool quick)
{
- const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb);
- const struct unicode_map *um = sbi->s_encoding;
+ const struct super_block *sb = parent->i_sb;
+ const struct unicode_map *um = sb->s_encoding;
int ret;
if (quick)
/* Handle invalid character sequence as either an error
* or as an opaque byte sequence.
*/
- if (ext4_has_strict_mode(sbi))
+ if (sb_has_strict_encoding(sb))
return -EINVAL;
if (name->len != entry->len)
{
int len;
- if (!IS_CASEFOLDED(dir) || !EXT4_SB(dir->i_sb)->s_encoding) {
+ if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) {
cf_name->name = NULL;
return;
}
if (!cf_name->name)
return;
- len = utf8_casefold(EXT4_SB(dir->i_sb)->s_encoding,
+ len = utf8_casefold(dir->i_sb->s_encoding,
iname, cf_name->name,
EXT4_NAME_LEN);
if (len <= 0) {
#endif
#ifdef CONFIG_UNICODE
- if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) {
+ if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent)) {
if (fname->cf_name.name) {
struct qstr cf = {.name = fname->cf_name.name,
.len = fname->cf_name.len};
struct buffer_head *bh = NULL;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
-#ifdef CONFIG_UNICODE
- struct ext4_sb_info *sbi;
-#endif
struct ext4_filename fname;
int retval;
int dx_fallback=0;
return -EINVAL;
#ifdef CONFIG_UNICODE
- sbi = EXT4_SB(sb);
- if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) &&
- sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name))
+ if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
+ sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
return -EINVAL;
#endif
bool excl)
{
handle_t *handle;
- struct inode *inode, *inode_save;
+ struct inode *inode;
int err, credits, retries = 0;
err = dquot_initialize(dir);
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
- inode_save = inode;
- ihold(inode_save);
err = ext4_add_nondir(handle, dentry, &inode);
- ext4_fc_track_create(inode_save, dentry);
- iput(inode_save);
+ if (!err)
+ ext4_fc_track_create(handle, dentry);
}
if (handle)
ext4_journal_stop(handle);
umode_t mode, dev_t rdev)
{
handle_t *handle;
- struct inode *inode, *inode_save;
+ struct inode *inode;
int err, credits, retries = 0;
err = dquot_initialize(dir);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &ext4_special_inode_operations;
- inode_save = inode;
- ihold(inode_save);
err = ext4_add_nondir(handle, dentry, &inode);
if (!err)
- ext4_fc_track_create(inode_save, dentry);
- iput(inode_save);
+ ext4_fc_track_create(handle, dentry);
}
if (handle)
ext4_journal_stop(handle);
iput(inode);
goto out_retry;
}
- ext4_fc_track_create(inode, dentry);
ext4_inc_count(dir);
ext4_update_dx_flag(dir);
if (err)
goto out_clear_inode;
d_instantiate_new(dentry, inode);
+ ext4_fc_track_create(handle, dentry);
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
goto end_rmdir;
ext4_dec_count(dir);
ext4_update_dx_flag(dir);
- ext4_fc_track_unlink(inode, dentry);
+ ext4_fc_track_unlink(handle, dentry);
retval = ext4_mark_inode_dirty(handle, dir);
#ifdef CONFIG_UNICODE
return retval;
}
-int __ext4_unlink(struct inode *dir, const struct qstr *d_name,
+int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
struct inode *inode)
{
int retval = -ENOENT;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
- handle_t *handle = NULL;
int skip_remove_dentry = 0;
bh = ext4_find_entry(dir, d_name, &de, NULL);
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
skip_remove_dentry = 1;
else
- goto out_bh;
- }
-
- handle = ext4_journal_start(dir, EXT4_HT_DIR,
- EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
- if (IS_ERR(handle)) {
- retval = PTR_ERR(handle);
- goto out_bh;
+ goto out;
}
if (IS_DIRSYNC(dir))
if (!skip_remove_dentry) {
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
- goto out_handle;
+ goto out;
dir->i_ctime = dir->i_mtime = current_time(dir);
ext4_update_dx_flag(dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (retval)
- goto out_handle;
+ goto out;
} else {
retval = 0;
}
inode->i_ctime = current_time(inode);
retval = ext4_mark_inode_dirty(handle, inode);
-out_handle:
- ext4_journal_stop(handle);
-out_bh:
+out:
brelse(bh);
return retval;
}
static int ext4_unlink(struct inode *dir, struct dentry *dentry)
{
+ handle_t *handle;
int retval;
if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
if (retval)
goto out_trace;
- retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry));
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
+ EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle)) {
+ retval = PTR_ERR(handle);
+ goto out_trace;
+ }
+
+ retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
if (!retval)
- ext4_fc_track_unlink(d_inode(dentry), dentry);
+ ext4_fc_track_unlink(handle, dentry);
#ifdef CONFIG_UNICODE
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
if (IS_CASEFOLDED(dir))
d_invalidate(dentry);
#endif
+ if (handle)
+ ext4_journal_stop(handle);
out_trace:
trace_ext4_unlink_exit(dentry, retval);
err = ext4_add_entry(handle, dentry, inode);
if (!err) {
- ext4_fc_track_link(inode, dentry);
err = ext4_mark_inode_dirty(handle, inode);
/* this can happen only for tmpfile being
* linked the first time
if (inode->i_nlink == 1)
ext4_orphan_del(handle, inode);
d_instantiate(dentry, inode);
+ ext4_fc_track_link(handle, dentry);
} else {
drop_nlink(inode);
iput(inode);
EXT4_FC_REASON_RENAME_DIR);
} else {
if (new.inode)
- ext4_fc_track_unlink(new.inode, new.dentry);
- ext4_fc_track_link(old.inode, new.dentry);
- ext4_fc_track_unlink(old.inode, old.dentry);
+ ext4_fc_track_unlink(handle, new.dentry);
+ __ext4_fc_track_link(handle, old.inode, new.dentry);
+ __ext4_fc_track_unlink(handle, old.inode, old.dentry);
}
if (new.inode) {
if (!ext4_has_metadata_csum(sb))
return;
- /*
- * Locking the superblock prevents the scenario
- * where:
- * 1) a first thread pauses during checksum calculation.
- * 2) a second thread updates the superblock, recalculates
- * the checksum, and updates s_checksum
- * 3) the first thread resumes and finishes its checksum calculation
- * and updates s_checksum with a potentially stale or torn value.
- */
- lock_buffer(EXT4_SB(sb)->s_sbh);
es->s_checksum = ext4_superblock_csum(sb, es);
- unlock_buffer(EXT4_SB(sb)->s_sbh);
}
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
if (!test_opt(sb, ERRORS_CONT)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
- EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
if (journal)
jbd2_journal_abort(journal, -EIO);
}
va_end(args);
if (sb_rdonly(sb) == 0) {
- EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
fs_put_dax(sbi->s_daxdev);
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
#ifdef CONFIG_UNICODE
- utf8_unload(sbi->s_encoding);
+ utf8_unload(sb->s_encoding);
#endif
kfree(sbi);
}
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
- Opt_prefetch_block_bitmaps, Opt_no_fc,
+ Opt_prefetch_block_bitmaps,
#ifdef CONFIG_EXT4_DEBUG
- Opt_fc_debug_max_replay,
+ Opt_fc_debug_max_replay, Opt_fc_debug_force
#endif
- Opt_fc_debug_force
};
static const match_table_t tokens = {
{Opt_init_itable, "init_itable=%u"},
{Opt_init_itable, "init_itable"},
{Opt_noinit_itable, "noinit_itable"},
- {Opt_no_fc, "no_fc"},
- {Opt_fc_debug_force, "fc_debug_force"},
#ifdef CONFIG_EXT4_DEBUG
+ {Opt_fc_debug_force, "fc_debug_force"},
{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
#endif
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
MOPT_CLEAR | MOPT_Q},
- {Opt_usrjquota, 0, MOPT_Q},
- {Opt_grpjquota, 0, MOPT_Q},
+ {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING},
+ {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING},
{Opt_offusrjquota, 0, MOPT_Q},
{Opt_offgrpjquota, 0, MOPT_Q},
{Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT},
{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
MOPT_SET},
- {Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
- MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY},
+#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
-#ifdef CONFIG_EXT4_DEBUG
{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
#endif
{Opt_err, 0, 0}
ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
return 1;
case Opt_abort:
- sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
return 1;
case Opt_i_version:
sb->s_flags |= SB_I_VERSION;
} else if (test_opt2(sb, DAX_INODE)) {
SEQ_OPTS_PUTS("dax=inode");
}
-
- if (test_opt2(sb, JOURNAL_FAST_COMMIT))
- SEQ_OPTS_PUTS("fast_commit");
-
ext4_show_quota_options(seq, sb);
return 0;
}
* loaded or not
*/
if (sbi->s_journal && !sbi->s_journal_bdev)
- overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
+ overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
/* j_inum for internal journal is non-zero */
j_inode = ext4_get_journal_inode(sb, j_inum);
goto failed_mount;
#ifdef CONFIG_UNICODE
- if (ext4_has_feature_casefold(sb) && !sbi->s_encoding) {
+ if (ext4_has_feature_casefold(sb) && !sb->s_encoding) {
const struct ext4_sb_encodings *encoding_info;
struct unicode_map *encoding;
__u16 encoding_flags;
"%s-%s with flags 0x%hx", encoding_info->name,
encoding_info->version?:"\b", encoding_flags);
- sbi->s_encoding = encoding;
- sbi->s_encoding_flags = encoding_flags;
+ sb->s_encoding = encoding;
+ sb->s_encoding_flags = encoding_flags;
}
#endif
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
- printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+ printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n");
/* can't mount with both data=journal and dioread_nolock. */
clear_opt(sb, DIOREAD_NOLOCK);
+ clear_opt2(sb, JOURNAL_FAST_COMMIT);
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and delalloc");
INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
sbi->s_fc_bytes = 0;
- sbi->s_mount_state &= ~EXT4_FC_INELIGIBLE;
- sbi->s_mount_state &= ~EXT4_FC_COMMITTING;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
spin_lock_init(&sbi->s_fc_lock);
memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
sbi->s_fc_replay_state.fc_regions = NULL;
goto failed_mount_wq;
}
+ if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+ !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+ JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) {
+ ext4_msg(sb, KERN_ERR,
+ "Failed to set fast commit journal feature");
+ goto failed_mount_wq;
+ }
+
/* We have now updated the journal if required, so we can
* validate the data journaling mode. */
switch (test_opt(sb, DATA_FLAGS)) {
}
#ifdef CONFIG_UNICODE
- if (sbi->s_encoding)
+ if (sb->s_encoding)
sb->s_d_op = &ext4_dentry_ops;
#endif
crypto_free_shash(sbi->s_chksum_driver);
#ifdef CONFIG_UNICODE
- utf8_unload(sbi->s_encoding);
+ utf8_unload(sb->s_encoding);
#endif
#ifdef CONFIG_QUOTA
goto restore_opts;
}
- if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
}
if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
- if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
+ if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
err = -EROFS;
goto restore_opts;
}
brelse(bh);
out:
if (inode->i_size < off + len) {
- ext4_fc_track_range(inode,
- (inode->i_size > 0 ? inode->i_size - 1 : 0)
- >> inode->i_sb->s_blocksize_bits,
- (off + len) >> inode->i_sb->s_blocksize_bits);
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
err2 = ext4_mark_inode_dirty(handle, inode);
EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
+EXT4_ATTR_FEATURE(fast_commit);
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
ATTR_LIST(verity),
#endif
ATTR_LIST(metadata_csum_seed),
+ ATTR_LIST(fast_commit),
NULL,
};
ATTRIBUTE_GROUPS(ext4_feat);
if (error)
return error;
if (!buffer_mapped(bh_result))
- return -EIO;
+ return -ENODATA;
return 0;
}
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp);
- if (!ret && iomap.type == IOMAP_HOLE) {
- if (create)
- ret = gfs2_iomap_alloc(inode, &iomap, &mp);
- else
- ret = -ENODATA;
- }
+ if (create && !ret && iomap.type == IOMAP_HOLE)
+ ret = gfs2_iomap_alloc(inode, &iomap, &mp);
release_metapath(&mp);
if (ret)
goto out;
gl->gl_node.next = NULL;
gl->gl_flags = 0;
gl->gl_name = name;
+ lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass);
gl->gl_lockref.count = 1;
gl->gl_state = LM_ST_UNLOCKED;
gl->gl_target = LM_ST_UNLOCKED;
out_free:
kfree(gl->gl_lksb.sb_lvbptr);
kmem_cache_free(cachep, gl);
- atomic_dec(&sdp->sd_glock_disposal);
+ if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+ wake_up(&sdp->sd_glock_wait);
out:
return ret;
GFS2_LFC_AIL_FLUSH);
}
+/**
+ * gfs2_rgrp_metasync - sync out the metadata of a resource group
+ * @gl: the glock protecting the resource group
+ *
+ */
+
+static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+ struct address_space *metamapping = &sdp->sd_aspace;
+ struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+ const unsigned bsize = sdp->sd_sb.sb_bsize;
+ loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
+ loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
+ int error;
+
+ filemap_fdatawrite_range(metamapping, start, end);
+ error = filemap_fdatawait_range(metamapping, start, end);
+ WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
+ mapping_set_error(metamapping, error);
+ if (error)
+ gfs2_io_error(sdp);
+ return error;
+}
+
/**
* rgrp_go_sync - sync out the metadata for this glock
* @gl: the glock
static int rgrp_go_sync(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- struct address_space *mapping = &sdp->sd_aspace;
struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
- const unsigned bsize = sdp->sd_sb.sb_bsize;
- loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
- loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1;
int error;
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_RGRP_GO_SYNC);
- filemap_fdatawrite_range(mapping, start, end);
- error = filemap_fdatawait_range(mapping, start, end);
- WARN_ON_ONCE(error && !gfs2_withdrawn(sdp));
- mapping_set_error(mapping, error);
+ error = gfs2_rgrp_metasync(gl);
if (!error)
error = gfs2_ail_empty_gl(gl);
gfs2_free_clones(rgd);
static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl,
const char *fs_id_buf)
{
- struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
+ struct gfs2_rgrpd *rgd = gl->gl_object;
if (rgd)
gfs2_rgrp_dump(seq, rgd, fs_id_buf);
}
/**
- * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
+ * gfs2_inode_metasync - sync out the metadata of an inode
+ * @gl: the glock protecting the inode
+ *
+ */
+int gfs2_inode_metasync(struct gfs2_glock *gl)
+{
+ struct address_space *metamapping = gfs2_glock2aspace(gl);
+ int error;
+
+ filemap_fdatawrite(metamapping);
+ error = filemap_fdatawait(metamapping);
+ if (error)
+ gfs2_io_error(gl->gl_name.ln_sbd);
+ return error;
+}
+
+/**
+ * inode_go_sync - Sync the dirty metadata of an inode
* @gl: the glock protecting the inode
*
*/
error = filemap_fdatawait(mapping);
mapping_set_error(mapping, error);
}
- ret = filemap_fdatawait(metamapping);
- mapping_set_error(metamapping, ret);
+ ret = gfs2_inode_metasync(gl);
if (!error)
error = ret;
gfs2_ail_empty_gl(gl);
int error = 0;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) {
+ /*
+ * We need to check gl_state == LM_ST_SHARED here and not gl_req ==
+ * LM_ST_EXCLUSIVE. That's because when any node does a freeze,
+ * all the nodes should have the freeze glock in SH mode and they all
+ * call do_xmote: One for EX and the others for UN. They ALL must
+ * freeze locally, and they ALL must queue freeze work. The freeze_work
+ * calls freeze_func, which tries to reacquire the freeze glock in SH,
+ * effectively waiting for the thaw on the node who holds it in EX.
+ * Once thawed, the work func acquires the freeze glock in
+ * SH and everybody goes back to thawed.
+ */
+ if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) &&
+ !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) {
atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE);
error = freeze_super(sdp->sd_vfs);
if (error) {
.go_callback = iopen_go_callback,
.go_demote_ok = iopen_go_demote_ok,
.go_flags = GLOF_LRU | GLOF_NONDISK,
+ .go_subclass = 1,
};
const struct gfs2_glock_operations gfs2_flock_glops = {
extern const struct gfs2_glock_operations gfs2_journal_glops;
extern const struct gfs2_glock_operations *gfs2_glops_list[];
+extern int gfs2_inode_metasync(struct gfs2_glock *gl);
extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
#endif /* __GLOPS_DOT_H__ */
const char *fs_id_buf);
void (*go_callback)(struct gfs2_glock *gl, bool remote);
void (*go_free)(struct gfs2_glock *gl);
+ const int go_subclass;
const int go_type;
const unsigned long go_flags;
#define GLOF_ASPACE 1 /* address space attached */
error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (unlikely(error))
goto fail;
+ if (blktype != GFS2_BLKST_UNLINKED)
+ gfs2_cancel_delete_work(io_gl);
if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) {
/*
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail;
- gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_glock_put(io_gl);
io_gl = NULL;
flush_delayed_work(&ip->i_gl->gl_work);
glock_set_object(ip->i_gl, ip);
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
+ error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
goto fail_free_inode;
+ gfs2_cancel_delete_work(io_gl);
+ glock_set_object(io_gl, ip);
+
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
+ if (error)
+ goto fail_gunlock2;
error = gfs2_trans_begin(sdp, blocks, 0);
if (error)
- goto fail_free_inode;
+ goto fail_gunlock2;
if (blocks > 1) {
ip->i_eattr = ip->i_no_addr + 1;
init_dinode(dip, ip, symname);
gfs2_trans_end(sdp);
- error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
- if (error)
- goto fail_free_inode;
-
BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (error)
goto fail_gunlock2;
- gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl);
- glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_set_iop(inode);
insert_inode_hash(inode);
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
fail_gunlock2:
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
+ glock_clear_object(io_gl, ip);
gfs2_glock_put(io_gl);
fail_free_inode:
if (ip->i_gl) {
return vfs_setpos(file, ret, inode->i_sb->s_maxbytes);
}
+static int gfs2_update_time(struct inode *inode, struct timespec64 *time,
+ int flags)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_glock *gl = ip->i_gl;
+ struct gfs2_holder *gh;
+ int error;
+
+ gh = gfs2_glock_is_locked_by_me(gl);
+ if (gh && !gfs2_glock_is_held_excl(gl)) {
+ gfs2_glock_dq(gh);
+ gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, gh);
+ error = gfs2_glock_nq(gh);
+ if (error)
+ return error;
+ }
+ return generic_update_time(inode, time, flags);
+}
+
const struct inode_operations gfs2_file_iops = {
.permission = gfs2_permission,
.setattr = gfs2_setattr,
.fiemap = gfs2_fiemap,
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
+ .update_time = gfs2_update_time,
};
const struct inode_operations gfs2_dir_iops = {
.fiemap = gfs2_fiemap,
.get_acl = gfs2_get_acl,
.set_acl = gfs2_set_acl,
+ .update_time = gfs2_update_time,
.atomic_open = gfs2_atomic_open,
};
spin_unlock(&sdp->sd_ail_lock);
ret = generic_writepages(mapping, wbc);
spin_lock(&sdp->sd_ail_lock);
+ if (ret == -ENODATA) /* if a jdata write into a new hole */
+ ret = 0; /* ignore it */
if (ret || wbc->nr_to_write <= 0)
break;
return -EBUSY;
#include "incore.h"
#include "inode.h"
#include "glock.h"
+#include "glops.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
return error;
}
-/**
- * gfs2_meta_sync - Sync all buffers associated with a glock
- * @gl: The glock
- *
- */
-
-void gfs2_meta_sync(struct gfs2_glock *gl)
-{
- struct address_space *mapping = gfs2_glock2aspace(gl);
- struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
- int error;
-
- if (mapping == NULL)
- mapping = &sdp->sd_aspace;
-
- filemap_fdatawrite(mapping);
- error = filemap_fdatawait(mapping);
-
- if (error)
- gfs2_io_error(gl->gl_name.ln_sbd);
-}
-
static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
return;
}
if (pass != 1)
return;
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
if (error) {
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
return;
}
if (pass != 1)
return;
/* data sync? */
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, bool keep_cache);
-extern void gfs2_meta_sync(struct gfs2_glock *gl);
-
static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
{
unsigned int limit;
if (IS_ERR(sdp->sd_statfs_inode)) {
error = PTR_ERR(sdp->sd_statfs_inode);
fs_err(sdp, "can't read in statfs inode: %d\n", error);
- goto fail;
+ goto out;
}
+ if (sdp->sd_args.ar_spectator)
+ goto out;
pn = gfs2_lookup_simple(master, "per_node");
if (IS_ERR(pn)) {
iput(pn);
put_statfs:
iput(sdp->sd_statfs_inode);
-fail:
+out:
return error;
}
/* Uninitialize and free up memory used by the list of statfs inodes */
static void uninit_statfs(struct gfs2_sbd *sdp)
{
- gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
- free_local_statfs_inodes(sdp);
+ if (!sdp->sd_args.ar_spectator) {
+ gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
+ free_local_statfs_inodes(sdp);
+ }
iput(sdp->sd_statfs_inode);
}
if (undo) {
jindex = 0;
- goto fail_jinode_gh;
+ goto fail_statfs;
}
sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
mark_buffer_dirty(bh);
brelse(bh);
- gfs2_meta_sync(ip->i_gl);
+ gfs2_inode_metasync(ip->i_gl);
out:
return error;
}
gfs2_free_clones(rgd);
+ return_all_reservations(rgd);
kfree(rgd->rd_bits);
rgd->rd_bits = NULL;
- return_all_reservations(rgd);
kmem_cache_free(gfs2_rgrpd_cachep, rgd);
}
}
if (error < 0)
return error;
+ if (RB_EMPTY_ROOT(&sdp->sd_rindex_tree)) {
+ fs_err(sdp, "no resource groups found in the file system.\n");
+ return -ENOENT;
+ }
set_rgrp_preferences(sdp);
sdp->sd_rindex_uptodate = 1;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
+ return -EROFS;
+
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
rbm.rgd = rgd;
error = gfs2_rbm_from_block(&rbm, no_addr);
- if (WARN_ON_ONCE(error))
- goto fail;
-
- if (gfs2_testbit(&rbm, false) != type)
- error = -ESTALE;
+ if (!WARN_ON_ONCE(error)) {
+ if (gfs2_testbit(&rbm, false) != type)
+ error = -ESTALE;
+ }
gfs2_glock_dq_uninit(&rgd_gh);
+
fail:
return error;
}
gfs2_jindex_free(sdp);
/* Take apart glock structures and buffer lists */
gfs2_gl_hash_clear(sdp);
+ truncate_inode_pages_final(&sdp->sd_aspace);
gfs2_delete_debugfs_file(sdp);
/* Unmount the locking protocol */
gfs2_lm_unmount(sdp);
wait_queue_head_t lock_wq;
atomic_t refcnt;
unsigned int page_offset;
- struct page *page[0];
+ struct page *page[];
};
#define HFS_BNODE_ERROR 0
wait_queue_head_t lock_wq;
atomic_t refcnt;
unsigned int page_offset;
- struct page *page[0];
+ struct page *page[];
};
#define HFS_BNODE_LOCK 0
current->files = work->identity->files;
current->nsproxy = work->identity->nsproxy;
task_unlock(current);
+ if (!work->identity->files) {
+ /* failed grabbing files, ensure work gets cancelled */
+ work->flags |= IO_WQ_WORK_CANCEL;
+ }
}
if ((work->flags & IO_WQ_WORK_FS) && current->fs != work->identity->fs)
current->fs = work->identity->fs;
struct list_head file_list;
struct fixed_file_data *file_data;
struct llist_node llist;
+ bool done;
};
struct fixed_file_data {
struct io_open {
struct file *file;
int dfd;
+ bool ignore_nonblock;
struct filename *filename;
struct open_how how;
unsigned long nofile;
if (mm) {
kthread_unuse_mm(mm);
mmput(mm);
+ current->mm = NULL;
}
}
static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
{
- if (!current->mm) {
- if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL) ||
- !ctx->sqo_task->mm ||
- !mmget_not_zero(ctx->sqo_task->mm)))
- return -EFAULT;
- kthread_use_mm(ctx->sqo_task->mm);
+ struct mm_struct *mm;
+
+ if (current->mm)
+ return 0;
+
+ /* Should never happen */
+ if (unlikely(!(ctx->flags & IORING_SETUP_SQPOLL)))
+ return -EFAULT;
+
+ task_lock(ctx->sqo_task);
+ mm = ctx->sqo_task->mm;
+ if (unlikely(!mm || !mmget_not_zero(mm)))
+ mm = NULL;
+ task_unlock(ctx->sqo_task);
+
+ if (mm) {
+ kthread_use_mm(mm);
+ return 0;
}
- return 0;
+ return -EFAULT;
}
static int io_sq_thread_acquire_mm(struct io_ring_ctx *ctx,
/* add one for this request */
refcount_inc(&id->count);
- /* drop old identity, assign new one. one ref for req, one for tctx */
- if (req->work.identity != tctx->identity &&
- refcount_sub_and_test(2, &req->work.identity->count))
+ /* drop tctx and req identity references, if needed */
+ if (tctx->identity != &tctx->__identity &&
+ refcount_dec_and_test(&tctx->identity->count))
+ kfree(tctx->identity);
+ if (req->work.identity != &tctx->__identity &&
+ refcount_dec_and_test(&req->work.identity->count))
kfree(req->work.identity);
req->work.identity = id;
return false;
req->work.flags |= IO_WQ_WORK_FSIZE;
}
-
- if (!(req->work.flags & IO_WQ_WORK_FILES) &&
- (def->work_flags & IO_WQ_WORK_FILES) &&
- !(req->flags & REQ_F_NO_FILE_TABLE)) {
- if (id->files != current->files ||
- id->nsproxy != current->nsproxy)
- return false;
- atomic_inc(&id->files->count);
- get_nsproxy(id->nsproxy);
- req->flags |= REQ_F_INFLIGHT;
-
- spin_lock_irq(&ctx->inflight_lock);
- list_add(&req->inflight_entry, &ctx->inflight_list);
- spin_unlock_irq(&ctx->inflight_lock);
- req->work.flags |= IO_WQ_WORK_FILES;
- }
#ifdef CONFIG_BLK_CGROUP
if (!(req->work.flags & IO_WQ_WORK_BLKCG) &&
(def->work_flags & IO_WQ_WORK_BLKCG)) {
}
spin_unlock(¤t->fs->lock);
}
+ if (!(req->work.flags & IO_WQ_WORK_FILES) &&
+ (def->work_flags & IO_WQ_WORK_FILES) &&
+ !(req->flags & REQ_F_NO_FILE_TABLE)) {
+ if (id->files != current->files ||
+ id->nsproxy != current->nsproxy)
+ return false;
+ atomic_inc(&id->files->count);
+ get_nsproxy(id->nsproxy);
+ req->flags |= REQ_F_INFLIGHT;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_add(&req->inflight_entry, &ctx->inflight_list);
+ spin_unlock_irq(&ctx->inflight_lock);
+ req->work.flags |= IO_WQ_WORK_FILES;
+ }
return true;
}
io_req_init_async(req);
id = req->work.identity;
+ if (req->flags & REQ_F_FORCE_ASYNC)
+ req->work.flags |= IO_WQ_WORK_CONCURRENT;
+
if (req->flags & REQ_F_ISREG) {
if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
}
}
-static inline bool io_match_files(struct io_kiocb *req,
- struct files_struct *files)
+static inline bool __io_match_files(struct io_kiocb *req,
+ struct files_struct *files)
+{
+ return ((req->flags & REQ_F_WORK_INITIALIZED) &&
+ (req->work.flags & IO_WQ_WORK_FILES)) &&
+ req->work.identity->files == files;
+}
+
+static bool io_match_files(struct io_kiocb *req,
+ struct files_struct *files)
{
+ struct io_kiocb *link;
+
if (!files)
return true;
- if ((req->flags & REQ_F_WORK_INITIALIZED) &&
- (req->work.flags & IO_WQ_WORK_FILES))
- return req->work.identity->files == files;
+ if (__io_match_files(req, files))
+ return true;
+ if (req->flags & REQ_F_LINK_HEAD) {
+ list_for_each_entry(link, &req->link_list, link_list) {
+ if (__io_match_files(link, files))
+ return true;
+ }
+ }
return false;
}
WRITE_ONCE(cqe->user_data, req->user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, cflags);
- } else if (ctx->cq_overflow_flushed || req->task->io_uring->in_idle) {
+ } else if (ctx->cq_overflow_flushed ||
+ atomic_read(&req->task->io_uring->in_idle)) {
/*
* If we're in ring overflow flush mode, or in task cancel mode,
* then we cannot store the request for later flushing, we need
io_dismantle_req(req);
percpu_counter_dec(&tctx->inflight);
- if (tctx->in_idle)
+ if (atomic_read(&tctx->in_idle))
wake_up(&tctx->wait);
put_task_struct(req->task);
percpu_ref_put(&ctx->refs);
}
-static bool io_link_cancel_timeout(struct io_kiocb *req)
+static void io_kill_linked_timeout(struct io_kiocb *req)
{
- struct io_timeout_data *io = req->async_data;
struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- ret = hrtimer_try_to_cancel(&io->timer);
- if (ret != -1) {
- io_cqring_fill_event(req, -ECANCELED);
- io_commit_cqring(ctx);
- req->flags &= ~REQ_F_LINK_HEAD;
- io_put_req_deferred(req, 1);
- return true;
- }
-
- return false;
-}
-
-static bool __io_kill_linked_timeout(struct io_kiocb *req)
-{
struct io_kiocb *link;
- bool wake_ev;
+ bool cancelled = false;
+ unsigned long flags;
- if (list_empty(&req->link_list))
- return false;
- link = list_first_entry(&req->link_list, struct io_kiocb, link_list);
- if (link->opcode != IORING_OP_LINK_TIMEOUT)
- return false;
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ link = list_first_entry_or_null(&req->link_list, struct io_kiocb,
+ link_list);
/*
* Can happen if a linked timeout fired and link had been like
* req -> link t-out -> link t-out [-> ...]
*/
- if (!(link->flags & REQ_F_LTIMEOUT_ACTIVE))
- return false;
+ if (link && (link->flags & REQ_F_LTIMEOUT_ACTIVE)) {
+ struct io_timeout_data *io = link->async_data;
+ int ret;
- list_del_init(&link->link_list);
- wake_ev = io_link_cancel_timeout(link);
+ list_del_init(&link->link_list);
+ ret = hrtimer_try_to_cancel(&io->timer);
+ if (ret != -1) {
+ io_cqring_fill_event(link, -ECANCELED);
+ io_commit_cqring(ctx);
+ cancelled = true;
+ }
+ }
req->flags &= ~REQ_F_LINK_TIMEOUT;
- return wake_ev;
-}
-
-static void io_kill_linked_timeout(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- unsigned long flags;
- bool wake_ev;
-
- spin_lock_irqsave(&ctx->completion_lock, flags);
- wake_ev = __io_kill_linked_timeout(req);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
- if (wake_ev)
+ if (cancelled) {
io_cqring_ev_posted(ctx);
+ io_put_req(link);
+ }
}
static struct io_kiocb *io_req_link_next(struct io_kiocb *req)
}
end_req:
req_set_fail_links(req);
- io_req_complete(req, ret);
return false;
}
#endif
rw->free_iovec = iovec;
rw->bytes_done = 0;
/* can only be fixed buffers, no need to do anything */
- if (iter->type == ITER_BVEC)
+ if (iov_iter_is_bvec(iter))
return;
if (!iovec) {
unsigned iov_off = 0;
* we return to userspace.
*/
if (req->flags & REQ_F_ISREG) {
- __sb_start_write(file_inode(req->file)->i_sb,
- SB_FREEZE_WRITE, true);
+ sb_start_write(file_inode(req->file)->i_sb);
__sb_writers_release(file_inode(req->file)->i_sb,
SB_FREEZE_WRITE);
}
return ret;
}
req->open.nofile = rlimit(RLIMIT_NOFILE);
+ req->open.ignore_nonblock = false;
req->flags |= REQ_F_NEED_CLEANUP;
return 0;
}
struct file *file;
int ret;
- if (force_nonblock)
+ if (force_nonblock && !req->open.ignore_nonblock)
return -EAGAIN;
ret = build_open_flags(&req->open.how, &op);
if (IS_ERR(file)) {
put_unused_fd(ret);
ret = PTR_ERR(file);
+ /*
+ * A work-around to ensure that /proc/self works that way
+ * that it should - if we get -EOPNOTSUPP back, then assume
+ * that proc_self_get_link() failed us because we're in async
+ * context. We should be safe to retry this from the task
+ * itself with force_nonblock == false set, as it should not
+ * block on lookup. Would be nice to know this upfront and
+ * avoid the async dance, but doesn't seem feasible.
+ */
+ if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) {
+ req->open.ignore_nonblock = true;
+ refcount_inc(&req->refs);
+ io_req_task_queue(req);
+ return 0;
+ }
} else {
fsnotify_open(file);
fd_install(ret, file);
return -EFAULT;
if (clen < 0)
return -EINVAL;
- sr->len = iomsg->iov[0].iov_len;
+ sr->len = clen;
+ iomsg->iov[0].iov_len = clen;
iomsg->iov = NULL;
} else {
ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
/* make sure double remove sees this as being gone */
wait->private = NULL;
spin_unlock(&poll->head->lock);
- if (!done)
- __io_async_wake(req, poll, mask, io_poll_task_func);
+ if (!done) {
+ /* use wait func handler, so it matches the rq type */
+ poll->wait.func(&poll->wait, mode, sync, key);
+ }
}
refcount_dec(&req->refs);
return 1;
static void __io_queue_sqe(struct io_kiocb *req, struct io_comp_state *cs)
{
struct io_kiocb *linked_timeout;
- struct io_kiocb *nxt;
const struct cred *old_creds = NULL;
int ret;
*/
if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
if (!io_arm_poll_handler(req)) {
-punt:
/*
* Queued up for async execution, worker will release
* submit reference when the iocb is actually submitted.
if (linked_timeout)
io_queue_linked_timeout(linked_timeout);
- goto exit;
- }
+ } else if (likely(!ret)) {
+ /* drop submission reference */
+ req = io_put_req_find_next(req);
+ if (linked_timeout)
+ io_queue_linked_timeout(linked_timeout);
- if (unlikely(ret)) {
+ if (req) {
+ if (!(req->flags & REQ_F_FORCE_ASYNC))
+ goto again;
+ io_queue_async_work(req);
+ }
+ } else {
/* un-prep timeout, so it'll be killed as any other linked */
req->flags &= ~REQ_F_LINK_TIMEOUT;
req_set_fail_links(req);
io_put_req(req);
io_req_complete(req, ret);
- goto exit;
}
- /* drop submission reference */
- nxt = io_put_req_find_next(req);
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
-
- if (nxt) {
- req = nxt;
-
- if (req->flags & REQ_F_FORCE_ASYNC) {
- linked_timeout = NULL;
- goto punt;
- }
- goto again;
- }
-exit:
if (old_creds)
revert_creds(old_creds);
}
if (unlikely(ret))
goto fail_req;
}
-
- /*
- * Never try inline submit of IOSQE_ASYNC is set, go straight
- * to async execution.
- */
- io_req_init_async(req);
- req->work.flags |= IO_WQ_WORK_CONCURRENT;
io_queue_async_work(req);
} else {
if (sqe) {
return -ENXIO;
spin_lock(&data->lock);
- if (!list_empty(&data->ref_list))
- ref_node = list_first_entry(&data->ref_list,
- struct fixed_file_ref_node, node);
+ ref_node = data->node;
spin_unlock(&data->lock);
if (ref_node)
percpu_ref_kill(&ref_node->refs);
kfree(pfile);
}
- spin_lock(&file_data->lock);
- list_del(&ref_node->node);
- spin_unlock(&file_data->lock);
-
percpu_ref_exit(&ref_node->refs);
kfree(ref_node);
percpu_ref_put(&file_data->refs);
static void io_file_data_ref_zero(struct percpu_ref *ref)
{
struct fixed_file_ref_node *ref_node;
+ struct fixed_file_data *data;
struct io_ring_ctx *ctx;
- bool first_add;
+ bool first_add = false;
int delay = HZ;
ref_node = container_of(ref, struct fixed_file_ref_node, refs);
- ctx = ref_node->file_data->ctx;
+ data = ref_node->file_data;
+ ctx = data->ctx;
+
+ spin_lock(&data->lock);
+ ref_node->done = true;
- if (percpu_ref_is_dying(&ctx->file_data->refs))
+ while (!list_empty(&data->ref_list)) {
+ ref_node = list_first_entry(&data->ref_list,
+ struct fixed_file_ref_node, node);
+ /* recycle ref nodes in order */
+ if (!ref_node->done)
+ break;
+ list_del(&ref_node->node);
+ first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist);
+ }
+ spin_unlock(&data->lock);
+
+ if (percpu_ref_is_dying(&data->refs))
delay = 0;
- first_add = llist_add(&ref_node->llist, &ctx->file_put_llist);
if (!delay)
mod_delayed_work(system_wq, &ctx->file_put_work, 0);
else if (first_add)
INIT_LIST_HEAD(&ref_node->node);
INIT_LIST_HEAD(&ref_node->file_list);
ref_node->file_data = ctx->file_data;
+ ref_node->done = false;
return ref_node;
}
file_data->node = ref_node;
spin_lock(&file_data->lock);
- list_add(&ref_node->node, &file_data->ref_list);
+ list_add_tail(&ref_node->node, &file_data->ref_list);
spin_unlock(&file_data->lock);
percpu_ref_get(&file_data->refs);
return ret;
if (needs_switch) {
percpu_ref_kill(&data->node->refs);
spin_lock(&data->lock);
- list_add(&ref_node->node, &data->ref_list);
+ list_add_tail(&ref_node->node, &data->ref_list);
data->node = ref_node;
spin_unlock(&data->lock);
percpu_ref_get(&ctx->file_data->refs);
xa_init(&tctx->xa);
init_waitqueue_head(&tctx->wait);
tctx->last = NULL;
- tctx->in_idle = 0;
+ atomic_set(&tctx->in_idle, 0);
+ tctx->sqpoll = false;
io_init_identity(&tctx->__identity);
tctx->identity = &tctx->__identity;
task->io_uring = tctx;
return false;
}
-static bool io_match_link_files(struct io_kiocb *req,
- struct files_struct *files)
-{
- struct io_kiocb *link;
-
- if (io_match_files(req, files))
- return true;
- if (req->flags & REQ_F_LINK_HEAD) {
- list_for_each_entry(link, &req->link_list, link_list) {
- if (io_match_files(link, files))
- return true;
- }
- }
- return false;
-}
-
/*
* We're looking to cancel 'req' because it's holding on to our files, but
* 'req' could be a link to another request. See if it is, and cancel that
static bool io_cancel_link_cb(struct io_wq_work *work, void *data)
{
- return io_match_link(container_of(work, struct io_kiocb, work), data);
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ bool ret;
+
+ if (req->flags & REQ_F_LINK_TIMEOUT) {
+ unsigned long flags;
+ struct io_ring_ctx *ctx = req->ctx;
+
+ /* protect against races with linked timeouts */
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ ret = io_match_link(req, data);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else {
+ ret = io_match_link(req, data);
+ }
+ return ret;
}
static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
}
static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+ struct task_struct *task,
struct files_struct *files)
{
struct io_defer_entry *de = NULL;
spin_lock_irq(&ctx->completion_lock);
list_for_each_entry_reverse(de, &ctx->defer_list, list) {
- if (io_match_link_files(de->req, files)) {
+ if (io_task_match(de->req, task) &&
+ io_match_files(de->req, files)) {
list_cut_position(&list, &ctx->defer_list, &de->list);
break;
}
if (list_empty_careful(&ctx->inflight_list))
return false;
- io_cancel_defer_files(ctx, files);
/* cancel all at once, should be faster than doing it one by one*/
io_wq_cancel_cb(ctx->io_wq, io_wq_files_match, files, true);
{
struct task_struct *task = current;
- if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data)
+ if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
task = ctx->sq_data->thread;
+ atomic_inc(&task->io_uring->in_idle);
+ io_sq_thread_park(ctx->sq_data);
+ }
+
+ if (files)
+ io_cancel_defer_files(ctx, NULL, files);
+ else
+ io_cancel_defer_files(ctx, task, NULL);
io_cqring_overflow_flush(ctx, true, task, files);
io_run_task_work();
cond_resched();
}
+
+ if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
+ atomic_dec(&task->io_uring->in_idle);
+ /*
+ * If the files that are going away are the ones in the thread
+ * identity, clear them out.
+ */
+ if (task->io_uring->identity->files == files)
+ task->io_uring->identity->files = NULL;
+ io_sq_thread_unpark(ctx->sq_data);
+ }
}
/*
* Note that this task has used io_uring. We use it for cancelation purposes.
*/
-static int io_uring_add_task_file(struct file *file)
+static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
{
struct io_uring_task *tctx = current->io_uring;
tctx->last = file;
}
+ /*
+ * This is race safe in that the task itself is doing this, hence it
+ * cannot be going through the exit/cancel paths at the same time.
+ * This cannot be modified while exit/cancel is running.
+ */
+ if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL))
+ tctx->sqpoll = true;
+
return 0;
}
unsigned long index;
/* make sure overflow events are dropped */
- tctx->in_idle = true;
+ atomic_inc(&tctx->in_idle);
xa_for_each(&tctx->xa, index, file) {
struct io_ring_ctx *ctx = file->private_data;
if (files)
io_uring_del_task_file(file);
}
+
+ atomic_dec(&tctx->in_idle);
+}
+
+static s64 tctx_inflight(struct io_uring_task *tctx)
+{
+ unsigned long index;
+ struct file *file;
+ s64 inflight;
+
+ inflight = percpu_counter_sum(&tctx->inflight);
+ if (!tctx->sqpoll)
+ return inflight;
+
+ /*
+ * If we have SQPOLL rings, then we need to iterate and find them, and
+ * add the pending count for those.
+ */
+ xa_for_each(&tctx->xa, index, file) {
+ struct io_ring_ctx *ctx = file->private_data;
+
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
+ struct io_uring_task *__tctx = ctx->sqo_task->io_uring;
+
+ inflight += percpu_counter_sum(&__tctx->inflight);
+ }
+ }
+
+ return inflight;
}
/*
s64 inflight;
/* make sure overflow events are dropped */
- tctx->in_idle = true;
+ atomic_inc(&tctx->in_idle);
do {
/* read completions before cancelations */
- inflight = percpu_counter_sum(&tctx->inflight);
+ inflight = tctx_inflight(tctx);
if (!inflight)
break;
__io_uring_files_cancel(NULL);
* If we've seen completions, retry. This avoids a race where
* a completion comes in before we did prepare_to_wait().
*/
- if (inflight != percpu_counter_sum(&tctx->inflight))
+ if (inflight != tctx_inflight(tctx))
continue;
schedule();
} while (1);
finish_wait(&tctx->wait, &wait);
- tctx->in_idle = false;
+ atomic_dec(&tctx->in_idle);
}
static int io_uring_flush(struct file *file, void *data)
io_sqpoll_wait_sq(ctx);
submitted = to_submit;
} else if (to_submit) {
- ret = io_uring_add_task_file(f.file);
+ ret = io_uring_add_task_file(ctx, f.file);
if (unlikely(ret))
goto out;
mutex_lock(&ctx->uring_lock);
#ifdef CONFIG_PROC_FS
static int io_uring_show_cred(int id, void *p, void *data)
{
- const struct cred *cred = p;
+ struct io_identity *iod = p;
+ const struct cred *cred = iod->creds;
struct seq_file *m = data;
struct user_namespace *uns = seq_user_ns(m);
struct group_info *gi;
#if defined(CONFIG_UNIX)
ctx->ring_sock->file = file;
#endif
- if (unlikely(io_uring_add_task_file(file))) {
+ if (unlikely(io_uring_add_task_file(ctx, file))) {
file = ERR_PTR(-ENOMEM);
goto err_fd;
}
* to a power-of-two, if it isn't already. We do NOT impose
* any cq vs sq ring sizing.
*/
- if (p->cq_entries < p->sq_entries)
+ if (!p->cq_entries)
return -EINVAL;
if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
if (!(p->flags & IORING_SETUP_CLAMP))
p->cq_entries = IORING_MAX_CQ_ENTRIES;
}
p->cq_entries = roundup_pow_of_two(p->cq_entries);
+ if (p->cq_entries < p->sq_entries)
+ return -EINVAL;
} else {
p->cq_entries = 2 * p->sq_entries;
}
WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
WARN_ON_ONCE(!PageLocked(page));
WARN_ON_ONCE(PageWriteback(page));
+ WARN_ON_ONCE(PageDirty(page));
/*
* We cannot cancel the ioend directly here on error. We may have
* appropriately.
*/
if (unlikely(error)) {
+ /*
+ * Let the filesystem know what portion of the current page
+ * failed to map. If the page wasn't been added to ioend, it
+ * won't be affected by I/O completion and we must unlock it
+ * now.
+ */
+ if (wpc->ops->discard_page)
+ wpc->ops->discard_page(page, file_offset);
if (!count) {
- /*
- * If the current page hasn't been added to ioend, it
- * won't be affected by I/O completions and we must
- * discard and unlock it right here.
- */
- if (wpc->ops->discard_page)
- wpc->ops->discard_page(page);
ClearPageUptodate(page);
unlock_page(page);
goto done;
}
-
- /*
- * If the page was not fully cleaned, we need to ensure that the
- * higher layers come back to it correctly. That means we need
- * to keep the page dirty, and for WB_SYNC_ALL writeback we need
- * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
- * so another attempt to write this page in this writeback sweep
- * will be made.
- */
- set_page_writeback_keepwrite(page);
- } else {
- clear_page_dirty_for_io(page);
- set_page_writeback(page);
}
+ set_page_writeback(page);
unlock_page(page);
/*
__u8 len_des;
__u8 len_src;
__u8 ext_ver;
- __u8 data[0];
+ __u8 data[];
} __attribute__ ((packed));
struct RR_RR_s {
struct SL_component {
__u8 flags;
__u8 len;
- __u8 text[0];
+ __u8 text[];
} __attribute__ ((packed));
struct RR_SL_s {
struct RR_NM_s {
__u8 flags;
- char name[0];
+ char name[];
} __attribute__ ((packed));
struct RR_CL_s {
struct RR_TF_s {
__u8 flags;
- struct stamp times[0]; /* Variable number of these beasts */
+ struct stamp times[]; /* Variable number of these beasts */
} __attribute__ ((packed));
/* Linux-specific extension for transparent decompression */
* for a checkpoint to free up some space in the log.
*/
void __jbd2_log_wait_for_space(journal_t *journal)
+__acquires(&journal->j_state_lock)
+__releases(&journal->j_state_lock)
{
int nblocks, space_left;
/* assert_spin_locked(&journal->j_state_lock); */
schedule();
write_lock(&journal->j_state_lock);
finish_wait(&journal->j_fc_wait, &wait);
+ /*
+ * TODO: by blocking fast commits here, we are increasing
+ * fsync() latency slightly. Strictly speaking, we don't need
+ * to block fast commits until the transaction enters T_FLUSH
+ * state. So an optimization is possible where we block new fast
+ * commits here and wait for existing ones to complete
+ * just before we enter T_FLUSH. That way, the existing fast
+ * commits and this full commit can proceed parallely.
+ */
}
write_unlock(&journal->j_state_lock);
if (first_block < journal->j_tail)
freed += journal->j_last - journal->j_first;
/* Update tail only if we free significant amount of space */
- if (freed < journal->j_maxlen / 4)
+ if (freed < jbd2_journal_get_max_txn_bufs(journal))
update_tail = 0;
}
J_ASSERT(commit_transaction->t_state == T_COMMIT);
}
/**
- * Force and wait upon a commit if the calling process is not within
- * transaction. This is used for forcing out undo-protected data which contains
- * bitmaps, when the fs is running out of space.
+ * jbd2_journal_force_commit_nested - Force and wait upon a commit if the
+ * calling process is not within transaction.
*
* @journal: journal to force
* Returns true if progress was made.
+ *
+ * This is used for forcing out undo-protected data which contains
+ * bitmaps, when the fs is running out of space.
*/
int jbd2_journal_force_commit_nested(journal_t *journal)
{
}
/**
- * int journal_force_commit() - force any uncommitted transactions
+ * jbd2_journal_force_commit() - force any uncommitted transactions
* @journal: journal to force
*
* Caller want unconditional commit. We can only force the running transaction
*/
int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
{
+ if (unlikely(is_journal_aborted(journal)))
+ return -EIO;
/*
* Fast commits only allowed if at least one full commit has
* been processed.
if (!journal->j_stats.ts_tid)
return -EINVAL;
- if (tid <= journal->j_commit_sequence)
+ write_lock(&journal->j_state_lock);
+ if (tid <= journal->j_commit_sequence) {
+ write_unlock(&journal->j_state_lock);
return -EALREADY;
+ }
- write_lock(&journal->j_state_lock);
if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
(journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
DEFINE_WAIT(wait);
int jbd2_fc_end_commit(journal_t *journal)
{
- return __jbd2_fc_end_commit(journal, 0, 0);
+ return __jbd2_fc_end_commit(journal, 0, false);
}
EXPORT_SYMBOL(jbd2_fc_end_commit);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid)
+int jbd2_fc_end_commit_fallback(journal_t *journal)
{
- return __jbd2_fc_end_commit(journal, tid, 1);
+ tid_t tid;
+
+ read_lock(&journal->j_state_lock);
+ tid = journal->j_running_transaction ?
+ journal->j_running_transaction->t_tid : 0;
+ read_unlock(&journal->j_state_lock);
+ return __jbd2_fc_end_commit(journal, tid, true);
}
EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
int fc_off;
*bh_out = NULL;
- write_lock(&journal->j_state_lock);
if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
fc_off = journal->j_fc_off;
} else {
ret = -EINVAL;
}
- write_unlock(&journal->j_state_lock);
if (ret)
return ret;
if (!bh)
return -ENOMEM;
- lock_buffer(bh);
- clear_buffer_uptodate(bh);
- set_buffer_dirty(bh);
- unlock_buffer(bh);
journal->j_fc_wbuf[fc_off] = bh;
*bh_out = bh;
struct buffer_head *bh;
int i, j_fc_off;
- read_lock(&journal->j_state_lock);
j_fc_off = journal->j_fc_off;
- read_unlock(&journal->j_state_lock);
/*
* Wait in reverse order to minimize chances of us being woken up before
struct buffer_head *bh;
int i, j_fc_off;
- read_lock(&journal->j_state_lock);
j_fc_off = journal->j_fc_off;
- read_unlock(&journal->j_state_lock);
/*
* Wait in reverse order to minimize chances of us being woken up before
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
- journal->j_maxlen = len;
+ journal->j_total_len = len;
/* We need enough buffers to write out full descriptor block. */
n = journal->j_blocksize / jbd2_min_tag_size();
journal->j_wbufsize = n;
+ journal->j_fc_wbuf = NULL;
journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
GFP_KERNEL);
if (!journal->j_wbuf)
goto err_cleanup;
- if (journal->j_fc_wbufsize > 0) {
- journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
- sizeof(struct buffer_head *),
- GFP_KERNEL);
- if (!journal->j_fc_wbuf)
- goto err_cleanup;
- }
-
bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
if (!bh) {
pr_err("%s: Cannot get buffer for journal superblock\n",
err_cleanup:
kfree(journal->j_wbuf);
- kfree(journal->j_fc_wbuf);
jbd2_journal_destroy_revoke(journal);
kfree(journal);
return NULL;
}
-int jbd2_fc_init(journal_t *journal, int num_fc_blks)
-{
- journal->j_fc_wbufsize = num_fc_blks;
- journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize,
- sizeof(struct buffer_head *), GFP_KERNEL);
- if (!journal->j_fc_wbuf)
- return -ENOMEM;
- return 0;
-}
-EXPORT_SYMBOL(jbd2_fc_init);
-
/* jbd2_journal_init_dev and jbd2_journal_init_inode:
*
* Create a journal structure assigned some fixed set of disk blocks to
}
journal->j_first = first;
-
- if (jbd2_has_feature_fast_commit(journal) &&
- journal->j_fc_wbufsize > 0) {
- journal->j_fc_last = last;
- journal->j_last = last - journal->j_fc_wbufsize;
- journal->j_fc_first = journal->j_last + 1;
- journal->j_fc_off = 0;
- } else {
- journal->j_last = last;
- }
+ journal->j_last = last;
journal->j_head = journal->j_first;
journal->j_tail = journal->j_first;
journal->j_commit_sequence = journal->j_transaction_sequence - 1;
journal->j_commit_request = journal->j_commit_sequence;
- journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+ journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
+
+ /*
+ * Now that journal recovery is done, turn fast commits off here. This
+ * way, if fast commit was enabled before the crash but if now FS has
+ * disabled it, we don't enable fast commits.
+ */
+ jbd2_clear_feature_fast_commit(journal);
/*
* As a special case, if the on-disk copy is already marked as needing
goto out;
}
- if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
- journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
- else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+ if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
+ journal->j_total_len = be32_to_cpu(sb->s_maxlen);
+ else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
printk(KERN_WARNING "JBD2: journal file too short\n");
goto out;
}
if (be32_to_cpu(sb->s_first) == 0 ||
- be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+ be32_to_cpu(sb->s_first) >= journal->j_total_len) {
printk(KERN_WARNING
"JBD2: Invalid start block of journal: %u\n",
be32_to_cpu(sb->s_first));
{
int err;
journal_superblock_t *sb;
+ int num_fc_blocks;
err = journal_get_superblock(journal);
if (err)
journal->j_tail = be32_to_cpu(sb->s_start);
journal->j_first = be32_to_cpu(sb->s_first);
journal->j_errno = be32_to_cpu(sb->s_errno);
+ journal->j_last = be32_to_cpu(sb->s_maxlen);
- if (jbd2_has_feature_fast_commit(journal) &&
- journal->j_fc_wbufsize > 0) {
+ if (jbd2_has_feature_fast_commit(journal)) {
journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
- journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize;
+ num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks);
+ if (!num_fc_blocks)
+ num_fc_blocks = JBD2_MIN_FC_BLOCKS;
+ if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
+ journal->j_last = journal->j_fc_last - num_fc_blocks;
journal->j_fc_first = journal->j_last + 1;
journal->j_fc_off = 0;
- } else {
- journal->j_last = be32_to_cpu(sb->s_maxlen);
}
return 0;
/**
- * int jbd2_journal_load() - Read journal from disk.
+ * jbd2_journal_load() - Read journal from disk.
* @journal: Journal to act on.
*
* Given a journal_t structure which tells us which disk blocks contain
*/
journal->j_flags &= ~JBD2_ABORT;
- if (journal->j_fc_wbufsize > 0)
- jbd2_journal_set_features(journal, 0, 0,
- JBD2_FEATURE_INCOMPAT_FAST_COMMIT);
/* OK, we've finished with the dynamic journal bits:
* reinitialise the dynamic contents of the superblock in memory
* and reset them on disk. */
}
/**
- * void jbd2_journal_destroy() - Release a journal_t structure.
+ * jbd2_journal_destroy() - Release a journal_t structure.
* @journal: Journal to act on.
*
* Release a journal_t structure once it is no longer in use by the
jbd2_journal_destroy_revoke(journal);
if (journal->j_chksum_driver)
crypto_free_shash(journal->j_chksum_driver);
- if (journal->j_fc_wbufsize > 0)
- kfree(journal->j_fc_wbuf);
+ kfree(journal->j_fc_wbuf);
kfree(journal->j_wbuf);
kfree(journal);
/**
- *int jbd2_journal_check_used_features() - Check if features specified are used.
+ * jbd2_journal_check_used_features() - Check if features specified are used.
* @journal: Journal to check.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
}
/**
- * int jbd2_journal_check_available_features() - Check feature set in journalling layer
+ * jbd2_journal_check_available_features() - Check feature set in journalling layer
* @journal: Journal to check.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
return 0;
}
+static int
+jbd2_journal_initialize_fast_commit(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+ unsigned long long num_fc_blks;
+
+ num_fc_blks = be32_to_cpu(sb->s_num_fc_blks);
+ if (num_fc_blks == 0)
+ num_fc_blks = JBD2_MIN_FC_BLOCKS;
+ if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
+ return -ENOSPC;
+
+ /* Are we called twice? */
+ WARN_ON(journal->j_fc_wbuf != NULL);
+ journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
+ sizeof(struct buffer_head *), GFP_KERNEL);
+ if (!journal->j_fc_wbuf)
+ return -ENOMEM;
+
+ journal->j_fc_wbufsize = num_fc_blks;
+ journal->j_fc_last = journal->j_last;
+ journal->j_last = journal->j_fc_last - num_fc_blks;
+ journal->j_fc_first = journal->j_last + 1;
+ journal->j_fc_off = 0;
+ journal->j_free = journal->j_last - journal->j_first;
+ journal->j_max_transaction_buffers =
+ jbd2_journal_get_max_txn_bufs(journal);
+
+ return 0;
+}
+
/**
- * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
+ * jbd2_journal_set_features() - Mark a given journal feature in the superblock
* @journal: Journal to act on.
* @compat: bitmask of compatible features
* @ro: bitmask of features that force read-only mount
sb = journal->j_superblock;
+ if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
+ if (jbd2_journal_initialize_fast_commit(journal)) {
+ pr_err("JBD2: Cannot enable fast commits.\n");
+ return 0;
+ }
+ }
+
/* Load the checksum driver if necessary */
if ((journal->j_chksum_driver == NULL) &&
INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
}
/*
- * jbd2_journal_clear_features () - Clear a given journal feature in the
+ * jbd2_journal_clear_features() - Clear a given journal feature in the
* superblock
* @journal: Journal to act on.
* @compat: bitmask of compatible features
EXPORT_SYMBOL(jbd2_journal_clear_features);
/**
- * int jbd2_journal_flush () - Flush journal
+ * jbd2_journal_flush() - Flush journal
* @journal: Journal to act on.
*
* Flush all data for a given journal to disk and empty the journal.
}
/**
- * int jbd2_journal_wipe() - Wipe journal contents
+ * jbd2_journal_wipe() - Wipe journal contents
* @journal: Journal to act on.
* @write: flag (see below)
*
}
/**
- * void jbd2_journal_abort () - Shutdown the journal immediately.
+ * jbd2_journal_abort () - Shutdown the journal immediately.
* @journal: the journal to shutdown.
* @errno: an error number to record in the journal indicating
* the reason for the shutdown.
}
/**
- * int jbd2_journal_errno () - returns the journal's error state.
+ * jbd2_journal_errno() - returns the journal's error state.
* @journal: journal to examine.
*
* This is the errno number set with jbd2_journal_abort(), the last
}
/**
- * int jbd2_journal_clear_err () - clears the journal's error state
+ * jbd2_journal_clear_err() - clears the journal's error state
* @journal: journal to act on.
*
* An error must be cleared or acked to take a FS out of readonly
}
/**
- * void jbd2_journal_ack_err() - Ack journal err.
+ * jbd2_journal_ack_err() - Ack journal err.
* @journal: journal to act on.
*
* An error must be cleared or acked to take a FS out of readonly
/* Do up to 128K of readahead */
max = start + (128 * 1024 / journal->j_blocksize);
- if (max > journal->j_maxlen)
- max = journal->j_maxlen;
+ if (max > journal->j_total_len)
+ max = journal->j_total_len;
/* Do the readahead itself. We'll submit MAXBUF buffer_heads at
* a time to the block device IO layer. */
*bhp = NULL;
- if (offset >= journal->j_maxlen) {
+ if (offset >= journal->j_total_len) {
printk(KERN_ERR "JBD2: corrupted journal superblock\n");
return -EFSCORRUPTED;
}
DEFINE_WAIT(wait);
if (WARN_ON(!journal->j_running_transaction ||
- journal->j_running_transaction->t_state != T_SWITCH))
+ journal->j_running_transaction->t_state != T_SWITCH)) {
+ read_unlock(&journal->j_state_lock);
return;
+ }
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
read_unlock(&journal->j_state_lock);
/**
- * handle_t *jbd2_journal_start() - Obtain a new handle.
+ * jbd2_journal_start() - Obtain a new handle.
* @journal: Journal to start transaction on.
* @nblocks: number of block buffer we might modify
*
EXPORT_SYMBOL(jbd2_journal_free_reserved);
/**
- * int jbd2_journal_start_reserved() - start reserved handle
+ * jbd2_journal_start_reserved() - start reserved handle
* @handle: handle to start
* @type: for handle statistics
* @line_no: for handle statistics
EXPORT_SYMBOL(jbd2_journal_start_reserved);
/**
- * int jbd2_journal_extend() - extend buffer credits.
+ * jbd2_journal_extend() - extend buffer credits.
* @handle: handle to 'extend'
* @nblocks: nr blocks to try to extend by.
* @revoke_records: number of revoke records to try to extend by.
}
/**
- * int jbd2_journal_restart() - restart a handle .
+ * jbd2__journal_restart() - restart a handle .
* @handle: handle to restart
* @nblocks: nr credits requested
* @revoke_records: number of revoke record credits requested
EXPORT_SYMBOL(jbd2_journal_restart);
/**
- * void jbd2_journal_lock_updates () - establish a transaction barrier.
+ * jbd2_journal_lock_updates () - establish a transaction barrier.
* @journal: Journal to establish a barrier on.
*
* This locks out any further updates from being started, and blocks
}
/**
- * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier
+ * jbd2_journal_unlock_updates () - release barrier
* @journal: Journal to release the barrier on.
*
* Release a transaction barrier obtained with jbd2_journal_lock_updates().
}
/**
- * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update.
+ * jbd2_journal_get_write_access() - notify intent to modify a buffer
+ * for metadata (not data) update.
* @handle: transaction to add buffer modifications to
* @bh: bh to be used for metadata writes
*
* unlocked buffer beforehand. */
/**
- * int jbd2_journal_get_create_access () - notify intent to use newly created bh
+ * jbd2_journal_get_create_access () - notify intent to use newly created bh
* @handle: transaction to new buffer to
* @bh: new buffer.
*
}
/**
- * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with
+ * jbd2_journal_get_undo_access() - Notify intent to modify metadata with
* non-rewindable consequences
* @handle: transaction
* @bh: buffer to undo
}
/**
- * void jbd2_journal_set_triggers() - Add triggers for commit writeout
+ * jbd2_journal_set_triggers() - Add triggers for commit writeout
* @bh: buffer to trigger on
* @type: struct jbd2_buffer_trigger_type containing the trigger(s).
*
}
/**
- * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata
+ * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata
* @handle: transaction to add buffer to.
* @bh: buffer to mark
*
}
/**
- * void jbd2_journal_forget() - bforget() for potentially-journaled buffers.
+ * jbd2_journal_forget() - bforget() for potentially-journaled buffers.
* @handle: transaction handle
* @bh: bh to 'forget'
*
}
/**
- * int jbd2_journal_stop() - complete a transaction
+ * jbd2_journal_stop() - complete a transaction
* @handle: transaction to complete.
*
* All done for a particular handle.
}
/**
- * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
+ * jbd2_journal_try_to_free_buffers() - try to free page buffers.
* @journal: journal for operation
* @page: to try and free
*
}
/**
- * void jbd2_journal_invalidatepage()
+ * jbd2_journal_invalidatepage()
* @journal: journal to use for flush...
* @page: page to flush
* @offset: start of the range to invalidate
size_t len, loff_t *ppos)
{
struct simple_attr *attr;
- u64 val;
+ unsigned long long val;
size_t size;
ssize_t ret;
goto out;
attr->set_buf[size] = '\0';
- val = simple_strtoll(attr->set_buf, NULL, 0);
+ ret = kstrtoull(attr->set_buf, 0, &val);
+ if (ret)
+ goto out;
ret = attr->set(attr->data, val);
if (ret == 0)
ret = len; /* on success, claim we got the whole input */
static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
- struct inode *inode = file_inode(filp);
struct nfs_open_dir_context *dir_ctx = filp->private_data;
dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
case SEEK_SET:
if (offset < 0)
return -EINVAL;
- inode_lock(inode);
+ spin_lock(&filp->f_lock);
break;
case SEEK_CUR:
if (offset == 0)
return filp->f_pos;
- inode_lock(inode);
+ spin_lock(&filp->f_lock);
offset += filp->f_pos;
if (offset < 0) {
- inode_unlock(inode);
+ spin_unlock(&filp->f_lock);
return -EINVAL;
}
}
dir_ctx->dir_cookie = 0;
dir_ctx->duped = 0;
}
- inode_unlock(inode);
+ spin_unlock(&filp->f_lock);
return offset;
}
static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end,
int datasync)
{
- struct inode *inode = file_inode(filp);
-
dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync);
- inode_lock(inode);
- nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
- inode_unlock(inode);
+ nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC);
return 0;
}
void nfs4_xattr_cache_exit(void)
{
+ unregister_shrinker(&nfs4_xattr_large_entry_shrinker);
unregister_shrinker(&nfs4_xattr_entry_shrinker);
unregister_shrinker(&nfs4_xattr_cache_shrinker);
+ list_lru_destroy(&nfs4_xattr_large_entry_lru);
list_lru_destroy(&nfs4_xattr_entry_lru);
list_lru_destroy(&nfs4_xattr_cache_lru);
kmem_cache_destroy(nfs4_xattr_cache_cachep);
1 + nfs4_xattr_name_maxsz + 1)
#define decode_setxattr_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz)
#define encode_listxattrs_maxsz (op_encode_hdr_maxsz + 2 + 1)
-#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1)
+#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1 + 1)
#define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \
nfs4_xattr_name_maxsz)
#define decode_removexattr_maxsz (op_decode_hdr_maxsz + \
{
__be32 *p;
- encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr);
+ encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz, hdr);
p = reserve_space(xdr, 12);
if (unlikely(!p))
#define NFS_ROOT "/tftpboot/%s"
/* Default NFSROOT mount options. */
+#if defined(CONFIG_NFS_V2)
#define NFS_DEF_OPTIONS "vers=2,tcp,rsize=4096,wsize=4096"
+#elif defined(CONFIG_NFS_V3)
+#define NFS_DEF_OPTIONS "vers=3,tcp,rsize=4096,wsize=4096"
+#else
+#define NFS_DEF_OPTIONS "vers=4,tcp,rsize=4096,wsize=4096"
+#endif
/* Parameters passed from the kernel command line */
static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = "";
fh_copy(&resp->dirfh, &argp->fh);
fh_init(&resp->fh, NFS3_FHSIZE);
- if (argp->ftype == 0 || argp->ftype >= NF3BAD) {
- resp->status = nfserr_inval;
- goto out;
- }
if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) {
rdev = MKDEV(argp->major, argp->minor);
if (MAJOR(rdev) != argp->major ||
goto out;
}
} else if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO) {
- resp->status = nfserr_inval;
+ resp->status = nfserr_badtype;
goto out;
}
{
struct nfsd3_pathconfres *resp = rqstp->rq_resp;
+ *p++ = resp->status;
*p++ = xdr_zero; /* no post_op_attr */
if (resp->status == 0) {
struct nfsd_file *dst)
{
nfs42_ssc_close(src->nf_file);
- nfsd_file_put(src);
+ /* 'src' is freed by nfsd4_do_async_copy */
nfsd_file_put(dst);
mntput(ss_mnt);
}
cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL);
if (!cb_copy)
goto out;
+ refcount_set(&cb_copy->refcount, 1);
memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res));
cb_copy->cp_clp = copy->cp_clp;
cb_copy->nfserr = copy->nfserr;
struct inode *inode = d_inode(dentry);
struct dentry *parent;
bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
+ bool parent_needed, parent_interested;
__u32 p_mask;
struct inode *p_inode = NULL;
struct name_snapshot name;
return 0;
parent = NULL;
- if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask))
+ parent_needed = fsnotify_event_needs_parent(inode, mnt, mask);
+ if (!parent_watched && !parent_needed)
goto notify;
/* Does parent inode care about events on children? */
/*
* Include parent/name in notification either if some notification
- * groups require parent info (!parent_watched case) or the parent is
- * interested in this event.
+ * groups require parent info or the parent is interested in this event.
*/
- if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) {
+ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS;
+ if (parent_needed || parent_interested) {
/* When notifying parent, child should be passed as data */
WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type));
/* Notify both parent and child with child name info */
take_dentry_name_snapshot(&name, dentry);
file_name = &name.name;
- if (parent_watched)
+ if (parent_interested)
mask |= FS_EVENT_ON_CHILD;
}
goto done;
}
- trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
+ trace_ocfs2_journal_init_maxlen(j_journal->j_total_len);
*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
OCFS2_JOURNAL_DIRTY_FL);
oi->ip_blkno = 0ULL;
oi->ip_clusters = 0;
+ oi->ip_next_orphan = NULL;
ocfs2_resv_init_once(&oi->ip_la_data_resv);
oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
OOM_SCORE_ADJ_MAX;
put_task_struct(task);
+ if (oom_adj > OOM_ADJUST_MAX)
+ oom_adj = OOM_ADJUST_MAX;
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
static const struct proc_ops cpuinfo_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = cpuinfo_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = seq_release,
};
static const struct proc_ops proc_seq_ops = {
/* not permanent -- can call into arbitrary seq_operations */
.proc_open = proc_seq_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = proc_seq_release,
};
static const struct proc_ops proc_single_ops = {
/* not permanent -- can call into arbitrary ->single_show */
.proc_open = proc_single_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = single_release,
};
.llseek = proc_reg_llseek,
.read_iter = proc_reg_read_iter,
.write = proc_reg_write,
+ .splice_read = generic_file_splice_read,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
static const struct file_operations proc_iter_file_ops_compat = {
.llseek = proc_reg_llseek,
.read_iter = proc_reg_read_iter,
+ .splice_read = generic_file_splice_read,
.write = proc_reg_write,
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
pid_t tgid = task_tgid_nr_ns(current, ns);
char *name;
+ /*
+ * Not currently supported. Once we can inherit all of struct pid,
+ * we can allow this.
+ */
+ if (current->flags & PF_KTHREAD)
+ return ERR_PTR(-EOPNOTSUPP);
+
if (!tgid)
return ERR_PTR(-ENOENT);
/* max length of unsigned int in decimal + NULL term */
static const struct proc_ops stat_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = stat_open,
- .proc_read = seq_read,
+ .proc_read_iter = seq_read_iter,
.proc_lseek = seq_lseek,
.proc_release = single_release,
};
struct poll_table_page {
struct poll_table_page * next;
struct poll_table_entry * entry;
- struct poll_table_entry entries[0];
+ struct poll_table_entry entries[];
};
#define POLL_TABLE_FULL(table) \
struct poll_list {
struct poll_list *next;
int len;
- struct pollfd entries[0];
+ struct pollfd entries[];
};
#define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd))
#include <linux/mm.h>
#include <linux/printk.h>
#include <linux/string_helpers.h>
+#include <linux/uio.h>
#include <linux/uaccess.h>
#include <asm/page.h>
*/
ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
{
- struct seq_file *m = file->private_data;
+ struct iovec iov = { .iov_base = buf, .iov_len = size};
+ struct kiocb kiocb;
+ struct iov_iter iter;
+ ssize_t ret;
+
+ init_sync_kiocb(&kiocb, file);
+ iov_iter_init(&iter, READ, &iov, 1, size);
+
+ kiocb.ki_pos = *ppos;
+ ret = seq_read_iter(&kiocb, &iter);
+ *ppos = kiocb.ki_pos;
+ return ret;
+}
+EXPORT_SYMBOL(seq_read);
+
+/*
+ * Ready-made ->f_op->read_iter()
+ */
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct seq_file *m = iocb->ki_filp->private_data;
+ size_t size = iov_iter_count(iter);
size_t copied = 0;
size_t n;
void *p;
* if request is to read from zero offset, reset iterator to first
* record as it might have been already advanced by previous requests
*/
- if (*ppos == 0) {
+ if (iocb->ki_pos == 0) {
m->index = 0;
m->count = 0;
}
- /* Don't assume *ppos is where we left it */
- if (unlikely(*ppos != m->read_pos)) {
- while ((err = traverse(m, *ppos)) == -EAGAIN)
+ /* Don't assume ki_pos is where we left it */
+ if (unlikely(iocb->ki_pos != m->read_pos)) {
+ while ((err = traverse(m, iocb->ki_pos)) == -EAGAIN)
;
if (err) {
/* With prejudice... */
m->count = 0;
goto Done;
} else {
- m->read_pos = *ppos;
+ m->read_pos = iocb->ki_pos;
}
}
/* if not empty - flush it first */
if (m->count) {
n = min(m->count, size);
- err = copy_to_user(buf, m->buf + m->from, n);
- if (err)
+ if (copy_to_iter(m->buf + m->from, n, iter) != n)
goto Efault;
m->count -= n;
m->from += n;
size -= n;
- buf += n;
copied += n;
if (!size)
goto Done;
}
m->op->stop(m, p);
n = min(m->count, size);
- err = copy_to_user(buf, m->buf, n);
- if (err)
+ if (copy_to_iter(m->buf, n, iter) != n)
goto Efault;
copied += n;
m->count -= n;
if (!copied)
copied = err;
else {
- *ppos += copied;
+ iocb->ki_pos += copied;
m->read_pos += copied;
}
mutex_unlock(&m->lock);
err = -EFAULT;
goto Done;
}
-EXPORT_SYMBOL(seq_read);
+EXPORT_SYMBOL(seq_read_iter);
/**
* seq_lseek - ->llseek() method for sequential files.
}
EXPORT_SYMBOL(super_setup_bdi);
-/*
- * This is an internal function, please use sb_end_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_end_write(struct super_block *sb, int level)
-{
- percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-EXPORT_SYMBOL(__sb_end_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-int __sb_start_write(struct super_block *sb, int level, bool wait)
-{
- bool force_trylock = false;
- int ret = 1;
-
-#ifdef CONFIG_LOCKDEP
- /*
- * We want lockdep to tell us about possible deadlocks with freezing
- * but it's it bit tricky to properly instrument it. Getting a freeze
- * protection works as getting a read lock but there are subtle
- * problems. XFS for example gets freeze protection on internal level
- * twice in some cases, which is OK only because we already hold a
- * freeze protection also on higher level. Due to these cases we have
- * to use wait == F (trylock mode) which must not fail.
- */
- if (wait) {
- int i;
-
- for (i = 0; i < level - 1; i++)
- if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
- force_trylock = true;
- break;
- }
- }
-#endif
- if (wait && !force_trylock)
- percpu_down_read(sb->s_writers.rw_sem + level-1);
- else
- ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
-
- WARN_ON(force_trylock && !ret);
- return ret;
-}
-EXPORT_SYMBOL(__sb_start_write);
-
/**
* sb_wait_write - wait until all writers to given file system finish
* @sb: the super for which we wait
new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
new->xefi_blockcount = 1;
new->xefi_oinfo = *oinfo;
+ new->xefi_skip_discard = false;
trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
*========================================================================*/
/*
- * Query whether the requested number of additional bytes of extended
+ * Query whether the total requested number of attr fork bytes of extended
* attribute space will be able to fit inline.
*
* Returns zero if not, else the di_forkoff fork offset to be used in the
int maxforkoff;
int offset;
+ /*
+ * Check if the new size could fit at all first:
+ */
+ if (bytes > XFS_LITINO(mp))
+ return 0;
+
/* rounded down */
offset = (XFS_LITINO(mp) - bytes) >> 3;
{
xfs_fsblock_t xefi_startblock;/* starting fs block number */
xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
+ bool xefi_skip_discard;
struct list_head xefi_list;
struct xfs_owner_info xefi_oinfo; /* extent owner */
- bool xefi_skip_discard;
};
#define XFS_BMAP_MAX_NMAP 4
* record for our insertion point. This will also give us the record for
* start block contiguity tests.
*/
- error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags,
+ error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext,
&PREV, &i);
if (error)
goto done;
if (info->whichfork == XFS_ATTR_FORK)
rflags |= XFS_RMAP_ATTR_FORK;
+ if (irec->br_state == XFS_EXT_UNWRITTEN)
+ rflags |= XFS_RMAP_UNWRITTEN;
/*
* CoW staging extents are owned (on disk) by the refcountbt, so
* which doesn't track unwritten state.
*/
if (owner != XFS_RMAP_OWN_COW &&
- irec->br_state == XFS_EXT_UNWRITTEN &&
- !(rmap.rm_flags & XFS_RMAP_UNWRITTEN))
+ !!(irec->br_state == XFS_EXT_UNWRITTEN) !=
+ !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN))
xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
irec->br_startoff);
- if (info->whichfork == XFS_ATTR_FORK &&
- !(rmap.rm_flags & XFS_RMAP_ATTR_FORK))
+ if (!!(info->whichfork == XFS_ATTR_FORK) !=
+ !!(rmap.rm_flags & XFS_RMAP_ATTR_FORK))
xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
irec->br_startoff);
if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK)
int level,
struct xfs_btree_block *block)
{
- unsigned int numrecs;
- int ok_level;
-
- numrecs = be16_to_cpu(block->bb_numrecs);
+ struct xfs_btree_cur *cur = bs->cur;
+ unsigned int root_level = cur->bc_nlevels - 1;
+ unsigned int numrecs = be16_to_cpu(block->bb_numrecs);
/* More records than minrecs means the block is ok. */
- if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level))
+ if (numrecs >= cur->bc_ops->get_minrecs(cur, level))
return;
/*
- * Certain btree blocks /can/ have fewer than minrecs records. Any
- * level greater than or equal to the level of the highest dedicated
- * btree block are allowed to violate this constraint.
- *
- * For a btree rooted in a block, the btree root can have fewer than
- * minrecs records. If the btree is rooted in an inode and does not
- * store records in the root, the direct children of the root and the
- * root itself can have fewer than minrecs records.
+ * For btrees rooted in the inode, it's possible that the root block
+ * contents spilled into a regular ondisk block because there wasn't
+ * enough space in the inode root. The number of records in that
+ * child block might be less than the standard minrecs, but that's ok
+ * provided that there's only one direct child of the root.
*/
- ok_level = bs->cur->bc_nlevels - 1;
- if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
- ok_level--;
- if (level >= ok_level)
+ if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+ level == cur->bc_nlevels - 2) {
+ struct xfs_btree_block *root_block;
+ struct xfs_buf *root_bp;
+ int root_maxrecs;
+
+ root_block = xfs_btree_get_block(cur, root_level, &root_bp);
+ root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level);
+ if (be16_to_cpu(root_block->bb_numrecs) != 1 ||
+ numrecs <= root_maxrecs)
+ xchk_btree_set_corrupt(bs->sc, cur, level);
return;
+ }
- xchk_btree_set_corrupt(bs->sc, bs->cur, level);
+ /*
+ * Otherwise, only the root level is allowed to have fewer than minrecs
+ * records or keyptrs.
+ */
+ if (level < root_level)
+ xchk_btree_set_corrupt(bs->sc, cur, level);
}
/*
/* Check all the bestfree entries. */
for (i = 0; i < bestcount; i++, bestp++) {
best = be16_to_cpu(*bestp);
- if (best == NULLDATAOFF)
- continue;
error = xfs_dir3_data_read(sc->tp, sc->ip,
- i * args->geo->fsbcount, 0, &dbp);
+ xfs_dir2_db_to_da(args->geo, i),
+ XFS_DABUF_MAP_HOLE_OK,
+ &dbp);
if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
&error))
break;
- xchk_directory_check_freesp(sc, lblk, dbp, best);
+
+ if (!dbp) {
+ if (best != NULLDATAOFF) {
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
+ lblk);
+ break;
+ }
+ continue;
+ }
+
+ if (best == NULLDATAOFF)
+ xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+ else
+ xchk_directory_check_freesp(sc, lblk, dbp, best);
xfs_trans_brelse(sc->tp, dbp);
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
break;
goto bad;
/* rt flags require rt device */
- if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) &&
- !mp->m_rtdev_targp)
+ if ((flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
goto bad;
/* new rt bitmap flag only valid for rbmino */
*/
INIT_LIST_HEAD(&worklist);
rbno = NULLAGBLOCK;
- nr = 1;
/* Make sure the fragments actually /are/ in agbno order. */
bno = 0;
* Find all the rmaps that start at or before the refc extent,
* and put them on the worklist.
*/
+ nr = 0;
list_for_each_entry_safe(frag, n, &refchk->fragments, list) {
- if (frag->rm.rm_startblock > refchk->bno)
- goto done;
+ if (frag->rm.rm_startblock > refchk->bno || nr > target_nr)
+ break;
bno = frag->rm.rm_startblock + frag->rm.rm_blockcount;
if (bno < rbno)
rbno = bno;
list_move_tail(&frag->list, &worklist);
- if (nr == target_nr)
- break;
nr++;
}
ssize_t count = i_blocksize(inode);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
- xfs_fileoff_t cow_fsb = NULLFILEOFF;
- int whichfork = XFS_DATA_FORK;
+ xfs_fileoff_t cow_fsb;
+ int whichfork;
struct xfs_bmbt_irec imap;
struct xfs_iext_cursor icur;
int retries = 0;
* landed in a hole and we skip the block.
*/
retry:
+ cow_fsb = NULLFILEOFF;
+ whichfork = XFS_DATA_FORK;
xfs_ilock(ip, XFS_ILOCK_SHARED);
ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
*/
static void
xfs_discard_page(
- struct page *page)
+ struct page *page,
+ loff_t fileoff)
{
struct inode *inode = page->mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- loff_t offset = page_offset(page);
- xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, offset);
+ unsigned int pageoff = offset_in_page(fileoff);
+ xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, fileoff);
+ xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff);
int error;
if (XFS_FORCED_SHUTDOWN(mp))
xfs_alert_ratelimited(mp,
"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
- page, ip->i_ino, offset);
+ page, ip->i_ino, fileoff);
error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
- i_blocks_per_page(inode, page));
+ i_blocks_per_page(inode, page) - pageoff_fsb);
if (error && !XFS_FORCED_SHUTDOWN(mp))
xfs_alert(mp, "page discard unable to remove delalloc mapping.");
out_invalidate:
- iomap_invalidatepage(page, 0, PAGE_SIZE);
+ iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff);
}
static const struct iomap_writeback_ops xfs_writeback_ops = {
return 0;
}
+/*
+ * Check that the imap we are going to return to the caller spans the entire
+ * range that the caller requested for the IO.
+ */
+static bool
+imap_spans_range(
+ struct xfs_bmbt_irec *imap,
+ xfs_fileoff_t offset_fsb,
+ xfs_fileoff_t end_fsb)
+{
+ if (imap->br_startoff > offset_fsb)
+ return false;
+ if (imap->br_startoff + imap->br_blockcount < end_fsb)
+ return false;
+ return true;
+}
+
static int
xfs_direct_write_iomap_begin(
struct inode *inode,
if (imap_needs_alloc(inode, flags, &imap, nimaps))
goto allocate_blocks;
+ /*
+ * NOWAIT IO needs to span the entire requested IO with a single map so
+ * that we avoid partial IO failures due to the rest of the IO range not
+ * covered by this map triggering an EAGAIN condition when it is
+ * subsequently mapped and aborting the IO.
+ */
+ if ((flags & IOMAP_NOWAIT) &&
+ !imap_spans_range(&imap, offset_fsb, end_fsb)) {
+ error = -EAGAIN;
+ goto out_unlock;
+ }
+
xfs_iunlock(ip, lockmode);
trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
error = iomap_zero_range(inode, oldsize, newsize - oldsize,
&did_zeroing, &xfs_buffered_write_iomap_ops);
} else {
+ /*
+ * iomap won't detect a dirty page over an unwritten block (or a
+ * cow block over a hole) and subsequently skips zeroing the
+ * newly post-EOF portion of the page. Flush the new EOF to
+ * convert the block before the pagecache truncate.
+ */
+ error = filemap_write_and_wait_range(inode->i_mapping, newsize,
+ newsize);
+ if (error)
+ return error;
error = iomap_truncate_page(inode, newsize, &did_zeroing,
&xfs_buffered_write_iomap_ops);
}
/* Where do we start the traversal? */
xfs_ino_t startino;
+ /* What was the last inode number we saw when iterating the inobt? */
+ xfs_ino_t lastino;
+
/* Array of inobt records we cache. */
struct xfs_inobt_rec_incore *recs;
if (XFS_IS_CORRUPT(mp, *has_more != 1))
return -EFSCORRUPTED;
+ iwag->lastino = XFS_AGINO_TO_INO(mp, agno,
+ irec->ir_startino + XFS_INODES_PER_CHUNK - 1);
+
/*
* If the LE lookup yielded an inobt record before the cursor position,
* skip it and see if there's another one after it.
struct xfs_mount *mp = iwag->mp;
struct xfs_trans *tp = iwag->tp;
struct xfs_inobt_rec_incore *irec;
- xfs_agino_t restart;
+ xfs_agino_t next_agino;
int error;
+ next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1;
+
ASSERT(iwag->nr_recs > 0);
/* Delete cursor but remember the last record we cached... */
xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0);
irec = &iwag->recs[iwag->nr_recs - 1];
- restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1;
+ ASSERT(next_agino == irec->ir_startino + XFS_INODES_PER_CHUNK);
error = xfs_iwalk_ag_recs(iwag);
if (error)
if (error)
return error;
- return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more);
+ return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more);
}
/* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */
while (!error && has_more) {
struct xfs_inobt_rec_incore *irec;
+ xfs_ino_t rec_fsino;
cond_resched();
if (xfs_pwork_want_abort(&iwag->pwork))
if (error || !has_more)
break;
+ /* Make sure that we always move forward. */
+ rec_fsino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino);
+ if (iwag->lastino != NULLFSINO &&
+ XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+ iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1;
+
/* No allocated inodes in this chunk; skip it. */
if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) {
error = xfs_btree_increment(cur, 0, &has_more);
.trim_start = 1,
.skip_empty = 1,
.pwork = XFS_PWORK_SINGLE_THREADED,
+ .lastino = NULLFSINO,
};
xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino);
int error;
iwag->data = data;
iwag->startino = startino;
iwag->sz_recs = xfs_iwalk_prefetch(inode_records);
+ iwag->lastino = NULLFSINO;
xfs_pwork_queue(&pctl, &iwag->pwork);
startino = XFS_AGINO_TO_INO(mp, agno + 1, 0);
if (flags & XFS_INOBT_WALK_SAME_AG)
.startino = startino,
.sz_recs = xfs_inobt_walk_prefetch(inobt_records),
.pwork = XFS_PWORK_SINGLE_THREADED,
+ .lastino = NULLFSINO,
};
xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino);
int error;
}
pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
- if (!pag)
+ if (!pag) {
+ error = -ENOMEM;
goto out_unwind_new_pags;
+ }
pag->pag_agno = index;
pag->pag_mount = mp;
spin_lock_init(&pag->pag_ici_lock);
INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
- if (xfs_buf_hash_init(pag))
+
+ error = xfs_buf_hash_init(pag);
+ if (error)
goto out_free_pag;
init_waitqueue_head(&pag->pagb_wait);
spin_lock_init(&pag->pagb_lock);
pag->pagb_count = 0;
pag->pagb_tree = RB_ROOT;
- if (radix_tree_preload(GFP_NOFS))
+ error = radix_tree_preload(GFP_NOFS);
+ if (error)
goto out_hash_destroy;
spin_lock(&mp->m_perag_lock);
goto out_unlock;
error = invalidate_inode_pages2(inode->i_mapping);
if (WARN_ON_ONCE(error))
- return error;
+ goto out_unlock;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
&xfs_buffered_write_iomap_ops);
if (error)
goto out;
- error = filemap_write_and_wait(inode->i_mapping);
+
+ error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
if (error)
goto out;
#ifndef __ASSEMBLY__
+#include <linux/compiler.h>
#include <asm/rwonce.h>
#ifndef nop
#define __this_cpu_generic_read_nopreempt(pcp) \
({ \
- typeof(pcp) __ret; \
+ typeof(pcp) ___ret; \
preempt_disable_notrace(); \
- __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \
+ ___ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \
preempt_enable_notrace(); \
- __ret; \
+ ___ret; \
})
#define __this_cpu_generic_read_noirq(pcp) \
({ \
- typeof(pcp) __ret; \
- unsigned long __flags; \
- raw_local_irq_save(__flags); \
- __ret = raw_cpu_generic_read(pcp); \
- raw_local_irq_restore(__flags); \
- __ret; \
+ typeof(pcp) ___ret; \
+ unsigned long ___flags; \
+ raw_local_irq_save(___flags); \
+ ___ret = raw_cpu_generic_read(pcp); \
+ raw_local_irq_restore(___flags); \
+ ___ret; \
})
#define this_cpu_generic_read(pcp) \
#ifdef CONFIG_UACCESS_MEMCPY
#include <asm/unaligned.h>
-static inline int __get_user_fn(size_t size, const void __user *from, void *to)
+static __always_inline int
+__get_user_fn(size_t size, const void __user *from, void *to)
{
BUILD_BUG_ON(!__builtin_constant_p(size));
}
#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k)
-static inline int __put_user_fn(size_t size, void __user *to, void *from)
+static __always_inline int
+__put_user_fn(size_t size, void __user *to, void *from)
{
BUILD_BUG_ON(!__builtin_constant_p(size));
#ifdef CONFIG_CONSTRUCTORS
#define KERNEL_CTORS() . = ALIGN(8); \
__ctors_start = .; \
+ KEEP(*(SORT(.ctors.*))) \
KEEP(*(.ctors)) \
KEEP(*(SORT(.init_array.*))) \
KEEP(*(.init_array)) \
* @link_rate: Requested Link rate from DPCD 0x219
* @num_lanes: Number of lanes requested by sing through DPCD 0x220
* @phy_pattern: DP Phy test pattern from DPCD 0x248
- * @hb2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B
+ * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B
* @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259
* @enhanced_frame_cap: flag for enhanced frame capability.
*/
}
#endif
-/**
- * drm_edid_are_equal - compare two edid blobs.
- * @edid1: pointer to first blob
- * @edid2: pointer to second blob
- * This helper can be used during probing to determine if
- * edid had changed.
- */
bool drm_edid_are_equal(const struct edid *edid1, const struct edid *edid2);
int
const char *format, ...);
/**
- * Error output.
+ * DRM_DEV_ERROR() - Error output.
*
* @dev: device pointer
* @fmt: printf() like format string.
drm_dev_printk(dev, KERN_ERR, "*ERROR* " fmt, ##__VA_ARGS__)
/**
- * Rate limited error output. Like DRM_ERROR() but won't flood the log.
+ * DRM_DEV_ERROR_RATELIMITED() - Rate limited error output.
*
* @dev: device pointer
* @fmt: printf() like format string.
+ *
+ * Like DRM_ERROR() but won't flood the log.
*/
#define DRM_DEV_ERROR_RATELIMITED(dev, fmt, ...) \
({ \
})
/**
- * Debug output.
+ * DRM_DEV_DEBUG() - Debug output for generic drm code
*
* @dev: device pointer
* @fmt: printf() like format string.
*/
#define DRM_DEV_DEBUG(dev, fmt, ...) \
drm_dev_dbg(dev, DRM_UT_CORE, fmt, ##__VA_ARGS__)
+/**
+ * DRM_DEV_DEBUG_DRIVER() - Debug output for vendor specific part of the driver
+ *
+ * @dev: device pointer
+ * @fmt: printf() like format string.
+ */
#define DRM_DEV_DEBUG_DRIVER(dev, fmt, ...) \
drm_dev_dbg(dev, DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
+/**
+ * DRM_DEV_DEBUG_KMS() - Debug output for modesetting code
+ *
+ * @dev: device pointer
+ * @fmt: printf() like format string.
+ */
#define DRM_DEV_DEBUG_KMS(dev, fmt, ...) \
drm_dev_dbg(dev, DRM_UT_KMS, fmt, ##__VA_ARGS__)
}
#endif /* IS_BUILTIN(CONFIG_KUNIT) */
+#ifdef MODULE
/**
- * kunit_test_suites() - used to register one or more &struct kunit_suite
- * with KUnit.
+ * kunit_test_suites_for_module() - used to register one or more
+ * &struct kunit_suite with KUnit.
*
- * @suites_list...: a statically allocated list of &struct kunit_suite.
+ * @__suites: a statically allocated list of &struct kunit_suite.
*
- * Registers @suites_list with the test framework. See &struct kunit_suite for
+ * Registers @__suites with the test framework. See &struct kunit_suite for
* more information.
*
* If a test suite is built-in, module_init() gets translated into
* module_{init|exit} functions for the builtin case when registering
* suites via kunit_test_suites() below.
*/
-#ifdef MODULE
#define kunit_test_suites_for_module(__suites) \
static int __init kunit_test_suites_init(void) \
{ \
* kunit_test_suites() - used to register one or more &struct kunit_suite
* with KUnit.
*
- * @suites: a statically allocated list of &struct kunit_suite.
+ * @__suites: a statically allocated list of &struct kunit_suite.
*
* Registers @suites with the test framework. See &struct kunit_suite for
* more information.
* module.
*
*/
-#define kunit_test_suites(...) \
+#define kunit_test_suites(__suites...) \
__kunit_test_suites(__UNIQUE_ID(array), \
__UNIQUE_ID(suites), \
- __VA_ARGS__)
+ ##__suites)
#define kunit_test_suite(suite) kunit_test_suites(&suite)
KUNIT_ASSERTION(test, \
strcmp(__left, __right) op 0, \
kunit_binary_str_assert, \
- KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \
+ KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \
assert_type, \
#op, \
#left, \
ARM_SMCCC_SMC_32, \
0, 0x7fff)
+#define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1
+
/* Paravirtualised time calls (defined by ARM DEN0057A) */
#define ARM_SMCCC_HV_PV_TIME_FEATURES \
ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
* @flags: Zero or more BLK_MQ_F_* flags.
* @driver_data: Pointer to data owned by the block driver that created this
* tag set.
+ * @active_queues_shared_sbitmap:
+ * number of active request queues per tag set.
* @__bitmap_tags: A shared tags sbitmap, used over all hctx's
* @__breserved_tags:
* A shared reserved tags sbitmap, used over all hctx's
* file system requests.
*/
static inline unsigned int blk_max_size_offset(struct request_queue *q,
- sector_t offset)
-{
- unsigned int chunk_sectors = q->limits.chunk_sectors;
-
- if (!chunk_sectors)
- return q->limits.max_sectors;
+ sector_t offset,
+ unsigned int chunk_sectors)
+{
+ if (!chunk_sectors) {
+ if (q->limits.chunk_sectors)
+ chunk_sectors = q->limits.chunk_sectors;
+ else
+ return q->limits.max_sectors;
+ }
if (likely(is_power_of_2(chunk_sectors)))
chunk_sectors -= offset & (chunk_sectors - 1);
req_op(rq) == REQ_OP_SECURE_ERASE)
return blk_queue_get_max_sectors(q, req_op(rq));
- return min(blk_max_size_offset(q, offset),
+ return min(blk_max_size_offset(q, offset, 0),
blk_queue_get_max_sectors(q, req_op(rq)));
}
#define BOOTCONFIG_MAGIC "#BOOTCONFIG\n"
#define BOOTCONFIG_MAGIC_LEN 12
+#define BOOTCONFIG_ALIGN_SHIFT 2
+#define BOOTCONFIG_ALIGN (1 << BOOTCONFIG_ALIGN_SHIFT)
+#define BOOTCONFIG_ALIGN_MASK (BOOTCONFIG_ALIGN - 1)
/* XBC tree node */
struct xbc_node {
*/
static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
{
- if (skb_shared(skb)) {
- struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+ struct sk_buff *nskb;
- if (likely(nskb)) {
- can_skb_set_owner(nskb, skb->sk);
- consume_skb(skb);
- return nskb;
- } else {
- kfree_skb(skb);
- return NULL;
- }
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (unlikely(!nskb)) {
+ kfree_skb(skb);
+ return NULL;
}
- /* we can assume to have an unshared skb with proper owner */
- return skb;
+ can_skb_set_owner(nskb, skb->sk);
+ consume_skb(skb);
+ return nskb;
}
#endif /* !_CAN_SKB_H */
+ __clang_patchlevel__)
#if CLANG_VERSION < 100001
+#ifndef __BPF_TRACING__
# error Sorry, your version of Clang is too old - please use 10.0.1 or newer.
#endif
+#endif
/* Compiler specific definitions for Clang compiler */
#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
#endif
-/* The following are for compatibility with GCC, from compiler-gcc.h,
- * and may be redefined here because they should not be shared with other
- * compilers, like ICC.
- */
-#define barrier() __asm__ __volatile__("" : : : "memory")
-
#if __has_feature(shadow_call_stack)
# define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
#endif
# error Sorry, your version of GCC is too old - please use 4.9 or newer.
#endif
-/* Optimization barrier */
-
-/* The "volatile" is due to gcc bugs */
-#define barrier() __asm__ __volatile__("": : :"memory")
-/*
- * This version is i.e. to prevent dead stores elimination on @ptr
- * where gcc and llvm may behave differently when otherwise using
- * normal barrier(): while gcc behavior gets along with a normal
- * barrier(), llvm needs an explicit input variable to be assumed
- * clobbered. The issue is as follows: while the inline asm might
- * access any memory it wants, the compiler could have fit all of
- * @ptr into memory registers instead, and since @ptr never escaped
- * from that, it proved that the inline asm wasn't touching any of
- * it. This version works well with both compilers, i.e. we're telling
- * the compiler that the inline asm absolutely may see the contents
- * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
- */
-#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
-
/*
* This macro obfuscates arithmetic on a variable address so that gcc
* shouldn't recognize the original var, and make assumptions about it.
#else
#define __diag_GCC_8(s)
#endif
-
-#define __no_fgcse __attribute__((optimize("-fno-gcse")))
/* Optimization barrier */
#ifndef barrier
-# define barrier() __memory_barrier()
+/* The "volatile" is due to gcc bugs */
+# define barrier() __asm__ __volatile__("": : :"memory")
#endif
#ifndef barrier_data
-# define barrier_data(ptr) barrier()
+/*
+ * This version is i.e. to prevent dead stores elimination on @ptr
+ * where gcc and llvm may behave differently when otherwise using
+ * normal barrier(): while gcc behavior gets along with a normal
+ * barrier(), llvm needs an explicit input variable to be assumed
+ * clobbered. The issue is as follows: while the inline asm might
+ * access any memory it wants, the compiler could have fit all of
+ * @ptr into memory registers instead, and since @ptr never escaped
+ * from that, it proved that the inline asm wasn't touching any of
+ * it. This version works well with both compilers, i.e. we're telling
+ * the compiler that the inline asm absolutely may see the contents
+ * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495
+ */
+# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory")
#endif
/* workaround for GCC PR82365 if needed */
#define asm_inline asm
#endif
-#ifndef __no_fgcse
-# define __no_fgcse
-#endif
-
/* Are two types/vars the same type (ignoring qualifiers)? */
#define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
bool fast_switch_possible;
bool fast_switch_enabled;
+ /*
+ * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current
+ * governor.
+ */
+ bool strict_target;
+
/*
* Preferred average time interval between consecutive invocations of
* the driver to set the frequency for this policy. To be set by the
struct cpufreq_driver {
char name[CPUFREQ_NAME_LEN];
- u8 flags;
+ u16 flags;
void *driver_data;
/* needed by all drivers */
*/
#define CPUFREQ_IS_COOLING_DEV BIT(7)
+/*
+ * Set by drivers that need to update internale upper and lower boundaries along
+ * with the target frequency and so the core and governors should also invoke
+ * the diver if the target frequency does not change, but the policy min or max
+ * may have changed.
+ */
+#define CPUFREQ_NEED_UPDATE_LIMITS BIT(8)
+
int cpufreq_register_driver(struct cpufreq_driver *driver_data);
int cpufreq_unregister_driver(struct cpufreq_driver *driver_data);
+bool cpufreq_driver_test_flags(u16 flags);
const char *cpufreq_get_current_driver(void);
void *cpufreq_get_driver_data(void);
char *buf);
int (*store_setspeed) (struct cpufreq_policy *policy,
unsigned int freq);
- /* For governors which change frequency dynamically by themselves */
- bool dynamic_switching;
struct list_head governor_list;
struct module *owner;
+ u8 flags;
};
+/* Governor flags */
+
+/* For governors which change frequency dynamically by themselves */
+#define CPUFREQ_GOV_DYNAMIC_SWITCHING BIT(0)
+
+/* For governors wanting the target frequency to be set exactly */
+#define CPUFREQ_GOV_STRICT_TARGET BIT(1)
+
+
/* Pass a target to the cpufreq driver */
unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq);
struct dentry *parent,
struct debugfs_u32_array *array);
-struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
- struct dentry *parent,
- int (*read_fn)(struct seq_file *s,
- void *data));
+void debugfs_create_devm_seqfile(struct device *dev, const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s, void *data));
bool debugfs_initialized(void);
{
}
-static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev,
- const char *name,
- struct dentry *parent,
- int (*read_fn)(struct seq_file *s,
- void *data))
+static inline void debugfs_create_devm_seqfile(struct device *dev,
+ const char *name,
+ struct dentry *parent,
+ int (*read_fn)(struct seq_file *s,
+ void *data))
{
- return ERR_PTR(-ENODEV);
}
static inline ssize_t debugfs_read_file_bool(struct file *file,
u32 buf_info1;
u32 org_buf_len;
u64 org_buf_ptr;
- u32 epib[0];
+ u32 epib[];
} __packed;
#define CPPI5_DESC_MIN_ALIGN (16U)
*/
struct cppi5_monolithic_desc_t {
struct cppi5_desc_hdr_t hdr;
- u32 epib[0];
+ u32 epib[];
};
#define CPPI5_INFO2_MDESC_DATA_OFFSET_SHIFT (18U)
* This is a variant of the DDR4 memories.
* @MEM_LRDDR4: Load-Reduced DDR4 memory.
* @MEM_LPDDR4: Low-Power DDR4 memory.
+ * @MEM_DDR5: Unbuffered DDR5 RAM
* @MEM_NVDIMM: Non-volatile RAM
* @MEM_WIO2: Wide I/O 2.
*/
MEM_RDDR4,
MEM_LRDDR4,
MEM_LPDDR4,
+ MEM_DDR5,
MEM_NVDIMM,
MEM_WIO2,
};
#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4)
#define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4)
#define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4)
+#define MEM_FLAG_DDR5 BIT(MEM_DDR5)
#define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM)
#define MEM_FLAG_WIO2 BIT(MEM_WIO2)
/**
- * enum edac-type - Error Detection and Correction capabilities and mode
+ * enum edac_type - Error Detection and Correction capabilities and mode
* @EDAC_UNKNOWN: Unknown if ECC is available
* @EDAC_NONE: Doesn't support ECC
* @EDAC_RESERVED: Reserved ECC type
#define OP_OFFLINE 0x300
/**
- * enum edac_mc_layer - memory controller hierarchy layer
+ * enum edac_mc_layer_type - memory controller hierarchy layer
*
* @EDAC_MC_LAYER_BRANCH: memory layer is named "branch"
* @EDAC_MC_LAYER_CHANNEL: memory layer is named "channel"
DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
#define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \
- u32 ret; \
+ u32 __ret; \
cant_migrate(); \
if (static_branch_unlikely(&bpf_stats_enabled_key)) { \
- struct bpf_prog_stats *stats; \
- u64 start = sched_clock(); \
- ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
- stats = this_cpu_ptr(prog->aux->stats); \
- u64_stats_update_begin(&stats->syncp); \
- stats->cnt++; \
- stats->nsecs += sched_clock() - start; \
- u64_stats_update_end(&stats->syncp); \
+ struct bpf_prog_stats *__stats; \
+ u64 __start = sched_clock(); \
+ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
+ __stats = this_cpu_ptr(prog->aux->stats); \
+ u64_stats_update_begin(&__stats->syncp); \
+ __stats->cnt++; \
+ __stats->nsecs += sched_clock() - __start; \
+ u64_stats_update_end(&__stats->syncp); \
} else { \
- ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
+ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \
} \
- ret; })
+ __ret; })
#define BPF_PROG_RUN(prog, ctx) \
__BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func)
#define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U
#define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U
-/* Feature check status */
-#define PM_FEATURE_INVALID -1
-#define PM_FEATURE_UNCHECKED 0
-
/*
* Firmware FPGA Manager flags
* XILINX_ZYNQMP_PM_FPGA_FULL: FPGA full reconfiguration
* Snapshotting support.
*/
-void __sb_end_write(struct super_block *sb, int level);
-int __sb_start_write(struct super_block *sb, int level, bool wait);
+/*
+ * These are internal functions, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+static inline void __sb_end_write(struct super_block *sb, int level)
+{
+ percpu_up_read(sb->s_writers.rw_sem + level-1);
+}
+
+static inline void __sb_start_write(struct super_block *sb, int level)
+{
+ percpu_down_read(sb->s_writers.rw_sem + level - 1);
+}
+
+static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+ return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
#define __sb_writers_acquired(sb, lev) \
percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
*/
static inline void sb_start_write(struct super_block *sb)
{
- __sb_start_write(sb, SB_FREEZE_WRITE, true);
+ __sb_start_write(sb, SB_FREEZE_WRITE);
}
-static inline int sb_start_write_trylock(struct super_block *sb)
+static inline bool sb_start_write_trylock(struct super_block *sb)
{
- return __sb_start_write(sb, SB_FREEZE_WRITE, false);
+ return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
}
/**
*/
static inline void sb_start_pagefault(struct super_block *sb)
{
- __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
+ __sb_start_write(sb, SB_FREEZE_PAGEFAULT);
}
/*
*/
static inline void sb_start_intwrite(struct super_block *sb)
{
- __sb_start_write(sb, SB_FREEZE_FS, true);
+ __sb_start_write(sb, SB_FREEZE_FS);
}
-static inline int sb_start_intwrite_trylock(struct super_block *sb)
+static inline bool sb_start_intwrite_trylock(struct super_block *sb)
{
- return __sb_start_write(sb, SB_FREEZE_FS, false);
+ return __sb_start_write_trylock(sb, SB_FREEZE_FS);
}
{
if (!S_ISREG(file_inode(file)->i_mode))
return;
- __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
+ sb_start_write(file_inode(file)->i_sb);
}
static inline bool file_start_write_trylock(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
- return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
+ return sb_start_write_trylock(file_inode(file)->i_sb);
}
static inline void file_end_write(struct file *file)
*/
struct simple_transaction_argresp {
ssize_t size;
- char data[0];
+ char data[];
};
#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
extern void disk_block_events(struct gendisk *disk);
extern void disk_unblock_events(struct gendisk *disk);
extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
-void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
bool update_bdev);
/* drivers/char/random.c */
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled;
extern int intel_iommu_enabled;
-extern int intel_iommu_tboot_noforce;
extern int intel_iommu_gfx_mapped;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
struct percpu_counter inflight;
struct io_identity __identity;
struct io_identity *identity;
- bool in_idle;
+ atomic_t in_idle;
+ bool sqpoll;
};
#if defined(CONFIG_IO_URING)
* Optional, allows the file system to discard state on a page where
* we failed to submit any I/O.
*/
- void (*discard_page)(struct page *page);
+ void (*discard_page)(struct page *page, loff_t fileoff);
};
struct iomap_writepage_ctx {
extern void irq_domain_disassociate(struct irq_domain *domain,
unsigned int irq);
-extern unsigned int irq_create_mapping(struct irq_domain *host,
- irq_hw_number_t hwirq);
+extern unsigned int irq_create_mapping_affinity(struct irq_domain *host,
+ irq_hw_number_t hwirq,
+ const struct irq_affinity_desc *affinity);
extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec);
extern void irq_dispose_mapping(unsigned int virq);
+static inline unsigned int irq_create_mapping(struct irq_domain *host,
+ irq_hw_number_t hwirq)
+{
+ return irq_create_mapping_affinity(host, hwirq, NULL);
+}
+
+
/**
* irq_linear_revmap() - Find a linux irq from a hw irq number.
* @domain: domain owning this hardware interrupt
extern void jbd2_free(void *ptr, size_t size);
#define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_MIN_FC_BLOCKS 256
#ifdef __KERNEL__
/* 0x0050 */
__u8 s_checksum_type; /* checksum type */
__u8 s_padding2[3];
- __u32 s_padding[42];
+/* 0x0054 */
+ __be32 s_num_fc_blks; /* Number of fast commit blocks */
+/* 0x0058 */
+ __u32 s_padding[41];
__be32 s_checksum; /* crc32c(superblock) */
/* 0x0100 */
#define JI_WAIT_DATA (1 << __JI_WAIT_DATA)
/**
- * struct jbd_inode - The jbd_inode type is the structure linking inodes in
+ * struct jbd2_inode - The jbd_inode type is the structure linking inodes in
* ordered mode present in a transaction so that we can sync them during commit.
*/
struct jbd2_inode {
/**
* @j_fc_off:
*
- * Number of fast commit blocks currently allocated.
- * [j_state_lock].
+ * Number of fast commit blocks currently allocated. Accessed only
+ * during fast commit. Currently only process can do fast commit, so
+ * this field is not protected by any lock.
*/
unsigned long j_fc_off;
struct block_device *j_fs_dev;
/**
- * @j_maxlen: Total maximum capacity of the journal region on disk.
+ * @j_total_len: Total maximum capacity of the journal region on disk.
*/
- unsigned int j_maxlen;
+ unsigned int j_total_len;
/**
* @j_reserved_credits:
struct buffer_head **j_wbuf;
/**
- * @j_fc_wbuf: Array of fast commit bhs for
- * jbd2_journal_commit_transaction.
+ * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
+ * during a fast commit. Currently only process can do fast commit, so
+ * this field is not protected by any lock.
*/
struct buffer_head **j_fc_wbuf;
*/
void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
- /*
+ /**
* @j_fc_replay_callback:
*
* File-system specific function that performs replay of a fast
extern int jbd2_cleanup_journal_tail(journal_t *);
/* Fast commit related APIs */
-int jbd2_fc_init(journal_t *journal, int num_fc_blks);
int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
int jbd2_fc_end_commit(journal_t *journal);
-int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit_fallback(journal_t *journal);
int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
int jbd2_submit_inode_data(struct jbd2_inode *jinode);
int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
int jbd2_fc_release_bufs(journal_t *journal);
+static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+ return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+}
+
/*
* is_journal_abort
*
case 2: a += (u32)k[1]<<8; fallthrough;
case 1: a += k[0];
__jhash_final(a, b, c);
+ break;
case 0: /* Nothing left to add */
break;
}
case 2: b += k[1]; fallthrough;
case 1: a += k[0];
__jhash_final(a, b, c);
+ break;
case 0: /* Nothing left to add */
break;
}
*/
struct zynqmp_ipi_message {
size_t len;
- u8 data[0];
+ u8 data[];
};
#endif /* _LINUX_ZYNQMP_IPI_MESSAGE_H_ */
MEMCG_PADDING(_pad1_);
- /*
- * set > 0 if pages under this cgroup are moving to other cgroup.
- */
- atomic_t moving_account;
- struct task_struct *move_lock_task;
-
- /* Legacy local VM stats and events */
- struct memcg_vmstats_percpu __percpu *vmstats_local;
-
- /* Subtree VM stats and events (batched updates) */
- struct memcg_vmstats_percpu __percpu *vmstats_percpu;
-
- MEMCG_PADDING(_pad2_);
-
atomic_long_t vmstats[MEMCG_NR_STAT];
atomic_long_t vmevents[NR_VM_EVENT_ITEMS];
struct list_head objcg_list; /* list of inherited objcgs */
#endif
+ MEMCG_PADDING(_pad2_);
+
+ /*
+ * set > 0 if pages under this cgroup are moving to other cgroup.
+ */
+ atomic_t moving_account;
+ struct task_struct *move_lock_task;
+
+ /* Legacy local VM stats and events */
+ struct memcg_vmstats_percpu __percpu *vmstats_local;
+
+ /* Subtree VM stats and events (batched updates) */
+ struct memcg_vmstats_percpu __percpu *vmstats_percpu;
+
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
struct wb_domain cgwb_domain;
static inline void memcg_memory_event(struct mem_cgroup *memcg,
enum memcg_memory_event event)
{
+ bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
+ event == MEMCG_SWAP_FAIL;
+
atomic_long_inc(&memcg->memory_events_local[event]);
- cgroup_file_notify(&memcg->events_local_file);
+ if (!swap_event)
+ cgroup_file_notify(&memcg->events_local_file);
do {
atomic_long_inc(&memcg->memory_events[event]);
- cgroup_file_notify(&memcg->events_file);
+ if (swap_event)
+ cgroup_file_notify(&memcg->swap_events_file);
+ else
+ cgroup_file_notify(&memcg->events_file);
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
break;
}
#endif /* ! CONFIG_MEMORY_HOTPLUG */
-#ifdef CONFIG_NUMA
-extern int memory_add_physaddr_to_nid(u64 start);
-extern int phys_to_target_node(u64 start);
-#else
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
- return 0;
-}
-static inline int phys_to_target_node(u64 start)
-{
- return 0;
-}
-#endif
-
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
* pgdat resizing functions
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Intel MIC Bus driver.
- *
- * This implementation is very similar to the virtio bus driver
- * implementation @ include/linux/virtio.h.
- */
-#ifndef _MIC_BUS_H_
-#define _MIC_BUS_H_
-/*
- * Everything a mbus driver needs to work with any particular mbus
- * implementation.
- */
-#include <linux/interrupt.h>
-#include <linux/dma-mapping.h>
-
-struct mbus_device_id {
- __u32 device;
- __u32 vendor;
-};
-
-#define MBUS_DEV_DMA_HOST 2
-#define MBUS_DEV_DMA_MIC 3
-#define MBUS_DEV_ANY_ID 0xffffffff
-
-/**
- * mbus_device - representation of a device using mbus
- * @mmio_va: virtual address of mmio space
- * @hw_ops: the hardware ops supported by this device.
- * @id: the device type identification (used to match it with a driver).
- * @dev: underlying device.
- * be used to communicate with.
- * @index: unique position on the mbus bus
- */
-struct mbus_device {
- void __iomem *mmio_va;
- struct mbus_hw_ops *hw_ops;
- struct mbus_device_id id;
- struct device dev;
- int index;
-};
-
-/**
- * mbus_driver - operations for a mbus I/O driver
- * @driver: underlying device driver (populate name and owner).
- * @id_table: the ids serviced by this driver.
- * @probe: the function to call when a device is found. Returns 0 or -errno.
- * @remove: the function to call when a device is removed.
- */
-struct mbus_driver {
- struct device_driver driver;
- const struct mbus_device_id *id_table;
- int (*probe)(struct mbus_device *dev);
- void (*scan)(struct mbus_device *dev);
- void (*remove)(struct mbus_device *dev);
-};
-
-/**
- * struct mic_irq - opaque pointer used as cookie
- */
-struct mic_irq;
-
-/**
- * mbus_hw_ops - Hardware operations for accessing a MIC device on the MIC bus.
- */
-struct mbus_hw_ops {
- struct mic_irq* (*request_threaded_irq)(struct mbus_device *mbdev,
- irq_handler_t handler,
- irq_handler_t thread_fn,
- const char *name, void *data,
- int intr_src);
- void (*free_irq)(struct mbus_device *mbdev,
- struct mic_irq *cookie, void *data);
- void (*ack_interrupt)(struct mbus_device *mbdev, int num);
-};
-
-struct mbus_device *
-mbus_register_device(struct device *pdev, int id, const struct dma_map_ops *dma_ops,
- struct mbus_hw_ops *hw_ops, int index,
- void __iomem *mmio_va);
-void mbus_unregister_device(struct mbus_device *mbdev);
-
-int mbus_register_driver(struct mbus_driver *drv);
-void mbus_unregister_driver(struct mbus_driver *drv);
-
-static inline struct mbus_device *dev_to_mbus(struct device *_dev)
-{
- return container_of(_dev, struct mbus_device, dev);
-}
-
-static inline struct mbus_driver *drv_to_mbus(struct device_driver *drv)
-{
- return container_of(drv, struct mbus_driver, driver);
-}
-
-#endif /* _MIC_BUS_H */
return val.vbool;
}
+/**
+ * mlx5_core_net - Provide net namespace of the mlx5_core_dev
+ * @dev: mlx5 core device
+ *
+ * mlx5_core_net() returns the net namespace of mlx5 core device.
+ * This can be called only in below described limited context.
+ * (a) When a devlink instance for mlx5_core is registered and
+ * when devlink reload operation is disabled.
+ * or
+ * (b) during devlink reload reload_down() and reload_up callbacks
+ * where it is ensured that devlink instance's net namespace is
+ * stable.
+ */
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+ return devlink_net(priv_to_devlink(dev));
+}
+
#endif /* MLX5_DRIVER_H */
#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
+enum {
+ MLX5_STEERING_FORMAT_CONNECTX_5 = 0,
+ MLX5_STEERING_FORMAT_CONNECTX_6DX = 1,
+};
+
struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_0[0x30];
u8 vhca_id[0x10];
u8 general_obj_types[0x40];
- u8 reserved_at_440[0x20];
+ u8 reserved_at_440[0x4];
+ u8 steering_format_version[0x4];
+ u8 create_qp_start_hint[0x18];
u8 reserved_at_460[0x3];
u8 log_max_uctx[0x5];
u8 reserved_at_68[0x10];
u8 num_of_actions[0x8];
- union mlx5_ifc_set_add_copy_action_in_auto_bits actions[0];
+ union mlx5_ifc_set_add_copy_action_in_auto_bits actions[];
};
struct mlx5_ifc_dealloc_modify_header_context_out_bits {
u8 reserved_at_60[0x20];
- u8 data[0][0x20];
+ u8 data[][0x20];
};
enum {
return VM_FAULT_NOPAGE;
}
+#ifndef io_remap_pfn_range
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+ unsigned long addr, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
+}
+#endif
+
static inline vm_fault_t vmf_error(int err)
{
if (err == -ENOMEM)
}
/* Get/put a kernel symbol (calls should be symmetric) */
-#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); })
+#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); })
#define symbol_put(x) do { } while (0)
#define symbol_put_addr(x) do { } while (0)
struct net_device *sb_dev);
u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev);
+
int dev_queue_xmit(struct sk_buff *skb);
int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
+
+static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+ int ret;
+
+ ret = __dev_direct_xmit(skb, queue_id);
+ if (!dev_xmit_complete(ret))
+ kfree_skb(skb);
+ return ret;
+}
+
int register_netdevice(struct net_device *dev);
void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
void unregister_netdevice_many(struct list_head *head);
return false;
}
+static inline bool dev_has_header(const struct net_device *dev)
+{
+ return dev->header_ops && dev->header_ops->create;
+}
+
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr,
int len, int size);
int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
const u_int16_t attr_count; /* number of nlattr's */
};
+enum nfnl_abort_action {
+ NFNL_ABORT_NONE = 0,
+ NFNL_ABORT_AUTOLOAD,
+ NFNL_ABORT_VALIDATE,
+};
+
struct nfnetlink_subsystem {
const char *name;
__u8 subsys_id; /* nfnetlink subsystem ID */
const struct nfnl_callback *cb; /* callback for individual types */
struct module *owner;
int (*commit)(struct net *net, struct sk_buff *skb);
- int (*abort)(struct net *net, struct sk_buff *skb, bool autoload);
+ int (*abort)(struct net *net, struct sk_buff *skb,
+ enum nfnl_abort_action action);
void (*cleanup)(struct net *net);
bool (*valid_genid)(struct net *net, u32 genid);
};
u_int32_t mark;
};
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type);
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned addr_type);
struct nf_queue_entry;
#if IS_MODULE(CONFIG_IPV6)
int (*chk_addr)(struct net *net, const struct in6_addr *addr,
const struct net_device *dev, int strict);
- int (*route_me_harder)(struct net *net, struct sk_buff *skb);
+ int (*route_me_harder)(struct net *net, struct sock *sk, struct sk_buff *skb);
int (*dev_get_saddr)(struct net *net, const struct net_device *dev,
const struct in6_addr *daddr, unsigned int srcprefs,
struct in6_addr *saddr);
#endif
}
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+int ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb);
-static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+static inline int nf_ip6_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb)
{
#if IS_MODULE(CONFIG_IPV6)
const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
if (!v6_ops)
return -EHOSTUNREACH;
- return v6_ops->route_me_harder(net, skb);
+ return v6_ops->route_me_harder(net, sk, skb);
#elif IS_BUILTIN(CONFIG_IPV6)
- return ip6_route_me_harder(net, skb);
+ return ip6_route_me_harder(net, sk, skb);
#else
return -EHOSTUNREACH;
#endif
#endif
#ifdef CONFIG_NUMA
+#include <linux/printk.h>
+#include <asm/sparsemem.h>
+
/* Generic implementation available */
int numa_map_to_online_node(int node);
-#else
+
+#ifndef memory_add_physaddr_to_nid
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+ pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
+ start);
+ return 0;
+}
+#endif
+#ifndef phys_to_target_node
+static inline int phys_to_target_node(u64 start)
+{
+ pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
+ start);
+ return 0;
+}
+#endif
+#else /* !CONFIG_NUMA */
static inline int numa_map_to_online_node(int node)
{
return NUMA_NO_NODE;
}
+static inline int memory_add_physaddr_to_nid(u64 start)
+{
+ return 0;
+}
+static inline int phys_to_target_node(u64 start)
+{
+ return 0;
+}
#endif
#endif /* _LINUX_NUMA_H */
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
- * @offset: the page index
+ * @index: the page index
*
- * Looks up the page cache entry at @mapping & @offset. If there is a
+ * Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
/**
* find_lock_head - Locate, pin and lock a pagecache page.
* @mapping: The address_space to search.
- * @offset: The page index.
+ * @index: The page index.
*
- * Looks up the page cache entry at @mapping & @offset. If there is a
+ * Looks up the page cache entry at @mapping & @index. If there is a
* page cache page, its head page is returned locked and with an increased
* refcount.
*
xas_set(&xas, rac->_index);
rcu_read_lock();
xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) {
+ if (xas_retry(&xas, page))
+ continue;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageTail(page), page);
array[i++] = page;
struct perf_callchain_entry *callchain;
u64 aux_size;
- /*
- * regs_user may point to task_pt_regs or to regs_user_copy, depending
- * on arch details.
- */
struct perf_regs regs_user;
- struct pt_regs regs_user_copy;
-
struct perf_regs regs_intr;
u64 stack_user_size;
extern void perf_event_addr_filters_sync(struct perf_event *event);
extern int perf_output_begin(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size);
extern int perf_output_begin_forward(struct perf_output_handle *handle,
- struct perf_event *event,
- unsigned int size);
+ struct perf_sample_data *data,
+ struct perf_event *event,
+ unsigned int size);
extern int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event,
unsigned int size);
int perf_reg_validate(u64 mask);
u64 perf_reg_abi(struct task_struct *task);
void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy);
+ struct pt_regs *regs);
#else
#define PERF_REG_EXTENDED_MASK 0
}
static inline void perf_get_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
regs_user->regs = task_pt_regs(current);
regs_user->abi = perf_reg_abi(current);
#endif /* !__ASSEMBLY__ */
-#ifndef io_remap_pfn_range
-#define io_remap_pfn_range remap_pfn_range
+#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+/*
+ * ZSMALLOC needs to know the highest PFN on 32-bit architectures
+ * with physical address space extension, but falls back to
+ * BITS_PER_LONG otherwise.
+ */
+#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition
+#else
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
+#endif
#endif
#ifndef has_transparent_hugepage
PHY_INTERFACE_MODE_MAX,
} phy_interface_t;
-/**
+/*
* phy_supported_speeds - return all speeds currently supported by a PHY device
- * @phy: The PHY device to return supported speeds of.
- * @speeds: buffer to store supported speeds in.
- * @size: size of speeds buffer.
- *
- * Description: Returns the number of supported speeds, and fills
- * the speeds buffer with the supported speeds. If speeds buffer is
- * too small to contain all currently supported speeds, will return as
- * many speeds as can fit.
*/
unsigned int phy_supported_speeds(struct phy_device *phy,
unsigned int *speeds,
regnum, mask, set);
}
-/**
+/*
* phy_read_mmd - Convenience function for reading a register
* from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for phy_read();
*/
int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
__ret; \
})
-/**
+/*
* __phy_read_mmd - Convenience function for reading a register
* from an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Same rules as for __phy_read();
*/
int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum);
-/**
+/*
* phy_write_mmd - Convenience function for writing a register
* on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for phy_write();
*/
int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
-/**
+/*
* __phy_write_mmd - Convenience function for writing a register
* on an MMD on a given PHY.
- * @phydev: The phy_device struct
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to read
- * @val: value to write to @regnum
- *
- * Same rules as for __phy_write();
*/
int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val);
uint16_t num_banks_total;
/* Number of banks described in banks array. */
uint16_t num_banks_desc;
- struct ec_flash_bank banks[0];
+ struct ec_flash_bank banks[];
} __ec_align4;
/*
/* Total amount of vector lost */
uint16_t total_lost;
/* Lost events since the last fifo_info, per sensors */
- uint16_t lost[0];
+ uint16_t lost[];
} __ec_todo_packed;
struct ec_response_motion_sense_fifo_data {
uint32_t number_data;
- struct ec_response_motion_sensor_data data[0];
+ struct ec_response_motion_sensor_data data[];
} __ec_todo_packed;
/* List supported activity recognition */
uint8_t algorithm;
uint8_t num_params;
uint8_t reserved[2];
- float val[0];
+ float val[];
} __ec_align4;
struct ec_params_tmp006_set_calibration_v1 {
uint8_t algorithm;
uint8_t num_params;
uint8_t reserved;
- float val[0];
+ float val[];
} __ec_align4;
uint8_t type; /* event type : see PD_EVENT_xx below */
uint8_t size_port; /* [7:5] port number [4:0] payload size in bytes */
uint16_t data; /* type-defined data payload */
- uint8_t payload[0]; /* optional additional data payload: 0..16 bytes */
+ uint8_t payload[]; /* optional additional data payload: 0..16 bytes */
} __ec_align4;
/* The timestamp is the microsecond counter shifted to get about a ms. */
struct ec_response_tp_frame_info {
uint32_t n_frames;
- uint32_t frame_sizes[0];
+ uint32_t frame_sizes[];
} __ec_align4;
/* Create a snapshot of current frame readings */
uint32_t outsize;
uint32_t insize;
uint32_t result;
- uint8_t data[0];
+ uint8_t data[];
};
/**
s8 emufree_shift;
};
+#define SYSC_MODULE_QUIRK_ENA_RESETDONE BIT(25)
#define SYSC_MODULE_QUIRK_PRUSS BIT(24)
#define SYSC_MODULE_QUIRK_DSS_RESET BIT(23)
#define SYSC_MODULE_QUIRK_RTC_UNLOCK BIT(22)
extern void pm_runtime_update_max_time_suspended(struct device *dev,
s64 delta_ns);
extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable);
-extern void pm_runtime_clean_up_links(struct device *dev);
extern void pm_runtime_get_suppliers(struct device *dev);
extern void pm_runtime_put_suppliers(struct device *dev);
extern void pm_runtime_new_link(struct device *dev);
-extern void pm_runtime_drop_link(struct device *dev);
+extern void pm_runtime_drop_link(struct device_link *link);
/**
* pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter.
struct device *dev) { return 0; }
static inline void pm_runtime_set_memalloc_noio(struct device *dev,
bool enable){}
-static inline void pm_runtime_clean_up_links(struct device *dev) {}
static inline void pm_runtime_get_suppliers(struct device *dev) {}
static inline void pm_runtime_put_suppliers(struct device *dev) {}
static inline void pm_runtime_new_link(struct device *dev) {}
-static inline void pm_runtime_drop_link(struct device *dev) {}
+static inline void pm_runtime_drop_link(struct device_link *link) {}
#endif /* !CONFIG_PM */
return __pm_runtime_resume(dev, RPM_GET_PUT);
}
+/**
+ * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it.
+ * @dev: Target device.
+ *
+ * Resume @dev synchronously and if that is successful, increment its runtime
+ * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been
+ * incremented or a negative error code otherwise.
+ */
+static inline int pm_runtime_resume_and_get(struct device *dev)
+{
+ int ret;
+
+ ret = __pm_runtime_resume(dev, RPM_GET_PUT);
+ if (ret < 0) {
+ pm_runtime_put_noidle(dev);
+ return ret;
+ }
+
+ return 0;
+}
+
/**
* pm_runtime_put - Drop device usage counter and queue up "idle check" if 0.
* @dev: Target device.
return atomic_read(&r->refs);
}
-/**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
- * @i: the value to add to the refcount
- * @r: the refcount
- *
- * Will saturate at REFCOUNT_SATURATED and WARN.
- *
- * Provides no memory ordering, it is assumed the caller has guaranteed the
- * object memory to be stable (RCU, etc.). It does provide a control dependency
- * and thereby orders future stores. See the comment on top.
- *
- * Use of this function is not recommended for the normal reference counting
- * use case in which references are taken and released one at a time. In these
- * cases, refcount_inc(), or one of its variants, should instead be used to
- * increment a reference count.
- *
- * Return: false if the passed refcount is 0, true otherwise
- */
static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp)
{
int old = refcount_read(r);
return old;
}
-static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
-{
- return __refcount_add_not_zero(i, r, NULL);
-}
-
/**
- * refcount_add - add a value to a refcount
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
* @i: the value to add to the refcount
* @r: the refcount
*
- * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
+ * Will saturate at REFCOUNT_SATURATED and WARN.
*
* Provides no memory ordering, it is assumed the caller has guaranteed the
* object memory to be stable (RCU, etc.). It does provide a control dependency
* use case in which references are taken and released one at a time. In these
* cases, refcount_inc(), or one of its variants, should instead be used to
* increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
*/
+static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
+{
+ return __refcount_add_not_zero(i, r, NULL);
+}
+
static inline void __refcount_add(int i, refcount_t *r, int *oldp)
{
int old = atomic_fetch_add_relaxed(i, &r->refs);
refcount_warn_saturate(r, REFCOUNT_ADD_OVF);
}
+/**
+ * refcount_add - add a value to a refcount
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time. In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ */
static inline void refcount_add(int i, refcount_t *r)
{
__refcount_add(i, r, NULL);
}
+static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+{
+ return __refcount_add_not_zero(1, r, oldp);
+}
+
/**
* refcount_inc_not_zero - increment a refcount unless it is 0
* @r: the refcount to increment
*
* Return: true if the increment was successful, false otherwise
*/
-static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp)
+static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
{
- return __refcount_add_not_zero(1, r, oldp);
+ return __refcount_inc_not_zero(r, NULL);
}
-static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
+static inline void __refcount_inc(refcount_t *r, int *oldp)
{
- return __refcount_inc_not_zero(r, NULL);
+ __refcount_add(1, r, oldp);
}
/**
* Will WARN if the refcount is 0, as this represents a possible use-after-free
* condition.
*/
-static inline void __refcount_inc(refcount_t *r, int *oldp)
+static inline void refcount_inc(refcount_t *r)
{
- __refcount_add(1, r, oldp);
+ __refcount_inc(r, NULL);
}
-static inline void refcount_inc(refcount_t *r)
+static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
{
- __refcount_inc(r, NULL);
+ int old = atomic_fetch_sub_release(i, &r->refs);
+
+ if (oldp)
+ *oldp = old;
+
+ if (old == i) {
+ smp_acquire__after_ctrl_dep();
+ return true;
+ }
+
+ if (unlikely(old < 0 || old - i < 0))
+ refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
+
+ return false;
}
/**
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp)
+static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
{
- int old = atomic_fetch_sub_release(i, &r->refs);
-
- if (oldp)
- *oldp = old;
-
- if (old == i) {
- smp_acquire__after_ctrl_dep();
- return true;
- }
-
- if (unlikely(old < 0 || old - i < 0))
- refcount_warn_saturate(r, REFCOUNT_SUB_UAF);
-
- return false;
+ return __refcount_sub_and_test(i, r, NULL);
}
-static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
+static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
{
- return __refcount_sub_and_test(i, r, NULL);
+ return __refcount_sub_and_test(1, r, oldp);
}
/**
*
* Return: true if the resulting refcount is 0, false otherwise
*/
-static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp)
-{
- return __refcount_sub_and_test(1, r, oldp);
-}
-
static inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
return __refcount_dec_and_test(r, NULL);
}
-/**
- * refcount_dec - decrement a refcount
- * @r: the refcount
- *
- * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
- * when saturated at REFCOUNT_SATURATED.
- *
- * Provides release memory ordering, such that prior loads and stores are done
- * before.
- */
static inline void __refcount_dec(refcount_t *r, int *oldp)
{
int old = atomic_fetch_sub_release(1, &r->refs);
refcount_warn_saturate(r, REFCOUNT_DEC_LEAK);
}
+/**
+ * refcount_dec - decrement a refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
+ * when saturated at REFCOUNT_SATURATED.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before.
+ */
static inline void refcount_dec(refcount_t *r)
{
__refcount_dec(r, NULL);
* overruns.
*/
unsigned int dl_throttled : 1;
- unsigned int dl_boosted : 1;
unsigned int dl_yielded : 1;
unsigned int dl_non_contending : 1;
unsigned int dl_overrun : 1;
* time.
*/
struct hrtimer inactive_timer;
+
+#ifdef CONFIG_RT_MUTEXES
+ /*
+ * Priority Inheritance. When a DEADLINE scheduling entity is boosted
+ * pi_se points to the donor, otherwise points to the dl_se it belongs
+ * to (the original one/itself).
+ */
+ struct sched_dl_entity *pi_se;
+#endif
};
#ifdef CONFIG_UCLAMP_TASK
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
- unsigned sched_remote_wakeup:1;
#ifdef CONFIG_PSI
unsigned sched_psi_wake_requeue:1;
#endif
/* Unserialized, strictly 'current' */
+ /*
+ * This field must not be in the scheduler word above due to wakelist
+ * queueing no longer being serialized by p->on_cpu. However:
+ *
+ * p->XXX = X; ttwu()
+ * schedule() if (p->on_rq && ..) // false
+ * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true
+ * deactivate_task() ttwu_queue_wakelist())
+ * p->on_rq = 0; p->sched_remote_wakeup = Y;
+ *
+ * guarantees all stores of 'current' are visible before
+ * ->sched_remote_wakeup gets used, so it can be in this word.
+ */
+ unsigned sched_remote_wakeup:1;
+
/* Bit to tell LSMs we're in execve(): */
unsigned in_execve:1;
unsigned in_iowait:1;
+++ /dev/null
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * Intel SCIF driver.
- *
- */
-#ifndef __SCIF_H__
-#define __SCIF_H__
-
-#include <linux/types.h>
-#include <linux/poll.h>
-#include <linux/device.h>
-#include <linux/scif_ioctl.h>
-
-#define SCIF_ACCEPT_SYNC 1
-#define SCIF_SEND_BLOCK 1
-#define SCIF_RECV_BLOCK 1
-
-enum {
- SCIF_PROT_READ = (1 << 0),
- SCIF_PROT_WRITE = (1 << 1)
-};
-
-enum {
- SCIF_MAP_FIXED = 0x10,
- SCIF_MAP_KERNEL = 0x20,
-};
-
-enum {
- SCIF_FENCE_INIT_SELF = (1 << 0),
- SCIF_FENCE_INIT_PEER = (1 << 1),
- SCIF_SIGNAL_LOCAL = (1 << 4),
- SCIF_SIGNAL_REMOTE = (1 << 5)
-};
-
-enum {
- SCIF_RMA_USECPU = (1 << 0),
- SCIF_RMA_USECACHE = (1 << 1),
- SCIF_RMA_SYNC = (1 << 2),
- SCIF_RMA_ORDERED = (1 << 3)
-};
-
-/* End of SCIF Admin Reserved Ports */
-#define SCIF_ADMIN_PORT_END 1024
-
-/* End of SCIF Reserved Ports */
-#define SCIF_PORT_RSVD 1088
-
-typedef struct scif_endpt *scif_epd_t;
-typedef struct scif_pinned_pages *scif_pinned_pages_t;
-
-/**
- * struct scif_range - SCIF registered range used in kernel mode
- * @cookie: cookie used internally by SCIF
- * @nr_pages: number of pages of PAGE_SIZE
- * @prot_flags: R/W protection
- * @phys_addr: Array of bus addresses
- * @va: Array of kernel virtual addresses backed by the pages in the phys_addr
- * array. The va is populated only when called on the host for a remote
- * SCIF connection on MIC. This is required to support the use case of DMA
- * between MIC and another device which is not a SCIF node e.g., an IB or
- * ethernet NIC.
- */
-struct scif_range {
- void *cookie;
- int nr_pages;
- int prot_flags;
- dma_addr_t *phys_addr;
- void __iomem **va;
-};
-
-/**
- * struct scif_pollepd - SCIF endpoint to be monitored via scif_poll
- * @epd: SCIF endpoint
- * @events: requested events
- * @revents: returned events
- */
-struct scif_pollepd {
- scif_epd_t epd;
- __poll_t events;
- __poll_t revents;
-};
-
-/**
- * scif_peer_dev - representation of a peer SCIF device
- *
- * Peer devices show up as PCIe devices for the mgmt node but not the cards.
- * The mgmt node discovers all the cards on the PCIe bus and informs the other
- * cards about their peers. Upon notification of a peer a node adds a peer
- * device to the peer bus to maintain symmetry in the way devices are
- * discovered across all nodes in the SCIF network.
- *
- * @dev: underlying device
- * @dnode - The destination node which this device will communicate with.
- */
-struct scif_peer_dev {
- struct device dev;
- u8 dnode;
-};
-
-/**
- * scif_client - representation of a SCIF client
- * @name: client name
- * @probe - client method called when a peer device is registered
- * @remove - client method called when a peer device is unregistered
- * @si - subsys_interface used internally for implementing SCIF clients
- */
-struct scif_client {
- const char *name;
- void (*probe)(struct scif_peer_dev *spdev);
- void (*remove)(struct scif_peer_dev *spdev);
- struct subsys_interface si;
-};
-
-#define SCIF_OPEN_FAILED ((scif_epd_t)-1)
-#define SCIF_REGISTER_FAILED ((off_t)-1)
-#define SCIF_MMAP_FAILED ((void *)-1)
-
-/**
- * scif_open() - Create an endpoint
- *
- * Return:
- * Upon successful completion, scif_open() returns an endpoint descriptor to
- * be used in subsequent SCIF functions calls to refer to that endpoint;
- * otherwise in user mode SCIF_OPEN_FAILED (that is ((scif_epd_t)-1)) is
- * returned and errno is set to indicate the error; in kernel mode a NULL
- * scif_epd_t is returned.
- *
- * Errors:
- * ENOMEM - Insufficient kernel memory was available
- */
-scif_epd_t scif_open(void);
-
-/**
- * scif_bind() - Bind an endpoint to a port
- * @epd: endpoint descriptor
- * @pn: port number
- *
- * scif_bind() binds endpoint epd to port pn, where pn is a port number on the
- * local node. If pn is zero, a port number greater than or equal to
- * SCIF_PORT_RSVD is assigned and returned. Each endpoint may be bound to
- * exactly one local port. Ports less than 1024 when requested can only be bound
- * by system (or root) processes or by processes executed by privileged users.
- *
- * Return:
- * Upon successful completion, scif_bind() returns the port number to which epd
- * is bound; otherwise in user mode -1 is returned and errno is set to
- * indicate the error; in kernel mode the negative of one of the following
- * errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINVAL - the endpoint or the port is already bound
- * EISCONN - The endpoint is already connected
- * ENOSPC - No port number available for assignment
- * EACCES - The port requested is protected and the user is not the superuser
- */
-int scif_bind(scif_epd_t epd, u16 pn);
-
-/**
- * scif_listen() - Listen for connections on an endpoint
- * @epd: endpoint descriptor
- * @backlog: maximum pending connection requests
- *
- * scif_listen() marks the endpoint epd as a listening endpoint - that is, as
- * an endpoint that will be used to accept incoming connection requests. Once
- * so marked, the endpoint is said to be in the listening state and may not be
- * used as the endpoint of a connection.
- *
- * The endpoint, epd, must have been bound to a port.
- *
- * The backlog argument defines the maximum length to which the queue of
- * pending connections for epd may grow. If a connection request arrives when
- * the queue is full, the client may receive an error with an indication that
- * the connection was refused.
- *
- * Return:
- * Upon successful completion, scif_listen() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINVAL - the endpoint is not bound to a port
- * EISCONN - The endpoint is already connected or listening
- */
-int scif_listen(scif_epd_t epd, int backlog);
-
-/**
- * scif_connect() - Initiate a connection on a port
- * @epd: endpoint descriptor
- * @dst: global id of port to which to connect
- *
- * The scif_connect() function requests the connection of endpoint epd to remote
- * port dst. If the connection is successful, a peer endpoint, bound to dst, is
- * created on node dst.node. On successful return, the connection is complete.
- *
- * If the endpoint epd has not already been bound to a port, scif_connect()
- * will bind it to an unused local port.
- *
- * A connection is terminated when an endpoint of the connection is closed,
- * either explicitly by scif_close(), or when a process that owns one of the
- * endpoints of the connection is terminated.
- *
- * In user space, scif_connect() supports an asynchronous connection mode
- * if the application has set the O_NONBLOCK flag on the endpoint via the
- * fcntl() system call. Setting this flag will result in the calling process
- * not to wait during scif_connect().
- *
- * Return:
- * Upon successful completion, scif_connect() returns the port ID to which the
- * endpoint, epd, is bound; otherwise in user mode -1 is returned and errno is
- * set to indicate the error; in kernel mode the negative of one of the
- * following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNREFUSED - The destination was not listening for connections or refused
- * the connection request
- * EINVAL - dst.port is not a valid port ID
- * EISCONN - The endpoint is already connected
- * ENOMEM - No buffer space is available
- * ENODEV - The destination node does not exist, or the node is lost or existed,
- * but is not currently in the network since it may have crashed
- * ENOSPC - No port number available for assignment
- * EOPNOTSUPP - The endpoint is listening and cannot be connected
- */
-int scif_connect(scif_epd_t epd, struct scif_port_id *dst);
-
-/**
- * scif_accept() - Accept a connection on an endpoint
- * @epd: endpoint descriptor
- * @peer: global id of port to which connected
- * @newepd: new connected endpoint descriptor
- * @flags: flags
- *
- * The scif_accept() call extracts the first connection request from the queue
- * of pending connections for the port on which epd is listening. scif_accept()
- * creates a new endpoint, bound to the same port as epd, and allocates a new
- * SCIF endpoint descriptor, returned in newepd, for the endpoint. The new
- * endpoint is connected to the endpoint through which the connection was
- * requested. epd is unaffected by this call, and remains in the listening
- * state.
- *
- * On successful return, peer holds the global port identifier (node id and
- * local port number) of the port which requested the connection.
- *
- * A connection is terminated when an endpoint of the connection is closed,
- * either explicitly by scif_close(), or when a process that owns one of the
- * endpoints of the connection is terminated.
- *
- * The number of connections that can (subsequently) be accepted on epd is only
- * limited by system resources (memory).
- *
- * The flags argument is formed by OR'ing together zero or more of the
- * following values.
- * SCIF_ACCEPT_SYNC - block until a connection request is presented. If
- * SCIF_ACCEPT_SYNC is not in flags, and no pending
- * connections are present on the queue, scif_accept()
- * fails with an EAGAIN error
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when there is a connection request. In kernel mode, the scif_poll()
- * function may be used for this purpose. A readable event will be delivered
- * when a connection is requested.
- *
- * Return:
- * Upon successful completion, scif_accept() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EAGAIN - SCIF_ACCEPT_SYNC is not set and no connections are present to be
- * accepted or SCIF_ACCEPT_SYNC is not set and remote node failed to complete
- * its connection request
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * EINTR - Interrupted function
- * EINVAL - epd is not a listening endpoint, or flags is invalid, or peer is
- * NULL, or newepd is NULL
- * ENODEV - The requesting node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOENT - Secondary part of epd registration failed
- */
-int scif_accept(scif_epd_t epd, struct scif_port_id *peer, scif_epd_t
- *newepd, int flags);
-
-/**
- * scif_close() - Close an endpoint
- * @epd: endpoint descriptor
- *
- * scif_close() closes an endpoint and performs necessary teardown of
- * facilities associated with that endpoint.
- *
- * If epd is a listening endpoint then it will no longer accept connection
- * requests on the port to which it is bound. Any pending connection requests
- * are rejected.
- *
- * If epd is a connected endpoint, then its peer endpoint is also closed. RMAs
- * which are in-process through epd or its peer endpoint will complete before
- * scif_close() returns. Registered windows of the local and peer endpoints are
- * released as if scif_unregister() was called against each window.
- *
- * Closing a SCIF endpoint does not affect local registered memory mapped by
- * a SCIF endpoint on a remote node. The local memory remains mapped by the peer
- * SCIF endpoint explicitly removed by calling munmap(..) by the peer.
- *
- * If the peer endpoint's receive queue is not empty at the time that epd is
- * closed, then the peer endpoint can be passed as the endpoint parameter to
- * scif_recv() until the receive queue is empty.
- *
- * epd is freed and may no longer be accessed.
- *
- * Return:
- * Upon successful completion, scif_close() returns 0; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- */
-int scif_close(scif_epd_t epd);
-
-/**
- * scif_send() - Send a message
- * @epd: endpoint descriptor
- * @msg: message buffer address
- * @len: message length
- * @flags: blocking mode flags
- *
- * scif_send() sends data to the peer of endpoint epd. Up to len bytes of data
- * are copied from memory starting at address msg. On successful execution the
- * return value of scif_send() is the number of bytes that were sent, and is
- * zero if no bytes were sent because len was zero. scif_send() may be called
- * only when the endpoint is in a connected state.
- *
- * If a scif_send() call is non-blocking, then it sends only those bytes which
- * can be sent without waiting, up to a maximum of len bytes.
- *
- * If a scif_send() call is blocking, then it normally returns after sending
- * all len bytes. If a blocking call is interrupted or the connection is
- * reset, the call is considered successful if some bytes were sent or len is
- * zero, otherwise the call is considered unsuccessful.
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when the send queue is not full. In kernel mode, the scif_poll() function
- * may be used for this purpose.
- *
- * It is recommended that scif_send()/scif_recv() only be used for short
- * control-type message communication between SCIF endpoints. The SCIF RMA
- * APIs are expected to provide better performance for transfer sizes of
- * 1024 bytes or longer for the current MIC hardware and software
- * implementation.
- *
- * scif_send() will block until the entire message is sent if SCIF_SEND_BLOCK
- * is passed as the flags argument.
- *
- * Return:
- * Upon successful completion, scif_send() returns the number of bytes sent;
- * otherwise in user mode -1 is returned and errno is set to indicate the
- * error; in kernel mode the negative of one of the following errors is
- * returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or len is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-int scif_send(scif_epd_t epd, void *msg, int len, int flags);
-
-/**
- * scif_recv() - Receive a message
- * @epd: endpoint descriptor
- * @msg: message buffer address
- * @len: message buffer length
- * @flags: blocking mode flags
- *
- * scif_recv() receives data from the peer of endpoint epd. Up to len bytes of
- * data are copied to memory starting at address msg. On successful execution
- * the return value of scif_recv() is the number of bytes that were received,
- * and is zero if no bytes were received because len was zero. scif_recv() may
- * be called only when the endpoint is in a connected state.
- *
- * If a scif_recv() call is non-blocking, then it receives only those bytes
- * which can be received without waiting, up to a maximum of len bytes.
- *
- * If a scif_recv() call is blocking, then it normally returns after receiving
- * all len bytes. If the blocking call was interrupted due to a disconnection,
- * subsequent calls to scif_recv() will copy all bytes received upto the point
- * of disconnection.
- *
- * In user mode, the select() and poll() functions can be used to determine
- * when data is available to be received. In kernel mode, the scif_poll()
- * function may be used for this purpose.
- *
- * It is recommended that scif_send()/scif_recv() only be used for short
- * control-type message communication between SCIF endpoints. The SCIF RMA
- * APIs are expected to provide better performance for transfer sizes of
- * 1024 bytes or longer for the current MIC hardware and software
- * implementation.
- *
- * scif_recv() will block until the entire message is received if
- * SCIF_RECV_BLOCK is passed as the flags argument.
- *
- * Return:
- * Upon successful completion, scif_recv() returns the number of bytes
- * received; otherwise in user mode -1 is returned and errno is set to
- * indicate the error; in kernel mode the negative of one of the following
- * errors is returned.
- *
- * Errors:
- * EAGAIN - The destination node is returning from a low power state
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or len is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-int scif_recv(scif_epd_t epd, void *msg, int len, int flags);
-
-/**
- * scif_register() - Mark a memory region for remote access.
- * @epd: endpoint descriptor
- * @addr: starting virtual address
- * @len: length of range
- * @offset: offset of window
- * @prot_flags: read/write protection flags
- * @map_flags: mapping flags
- *
- * The scif_register() function opens a window, a range of whole pages of the
- * registered address space of the endpoint epd, starting at offset po and
- * continuing for len bytes. The value of po, further described below, is a
- * function of the parameters offset and len, and the value of map_flags. Each
- * page of the window represents the physical memory page which backs the
- * corresponding page of the range of virtual address pages starting at addr
- * and continuing for len bytes. addr and len are constrained to be multiples
- * of the page size. A successful scif_register() call returns po.
- *
- * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset
- * exactly, and offset is constrained to be a multiple of the page size. The
- * mapping established by scif_register() will not replace any existing
- * registration; an error is returned if any page within the range [offset,
- * offset + len - 1] intersects an existing window.
- *
- * When SCIF_MAP_FIXED is not set, the implementation uses offset in an
- * implementation-defined manner to arrive at po. The po value so chosen will
- * be an area of the registered address space that the implementation deems
- * suitable for a mapping of len bytes. An offset value of 0 is interpreted as
- * granting the implementation complete freedom in selecting po, subject to
- * constraints described below. A non-zero value of offset is taken to be a
- * suggestion of an offset near which the mapping should be placed. When the
- * implementation selects a value for po, it does not replace any extant
- * window. In all cases, po will be a multiple of the page size.
- *
- * The physical pages which are so represented by a window are available for
- * access in calls to mmap(), scif_readfrom(), scif_writeto(),
- * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the
- * physical pages represented by the window will not be reused by the memory
- * subsystem for any other purpose. Note that the same physical page may be
- * represented by multiple windows.
- *
- * Subsequent operations which change the memory pages to which virtual
- * addresses are mapped (such as mmap(), munmap()) have no effect on
- * existing window.
- *
- * If the process will fork(), it is recommended that the registered
- * virtual address range be marked with MADV_DONTFORK. Doing so will prevent
- * problems due to copy-on-write semantics.
- *
- * The prot_flags argument is formed by OR'ing together one or more of the
- * following values.
- * SCIF_PROT_READ - allow read operations from the window
- * SCIF_PROT_WRITE - allow write operations to the window
- *
- * Return:
- * Upon successful completion, scif_register() returns the offset at which the
- * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that
- * is (off_t *)-1) is returned and errno is set to indicate the error; in
- * kernel mode the negative of one of the following errors is returned.
- *
- * Errors:
- * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags, and pages in the range
- * [offset, offset + len -1] are already registered
- * EAGAIN - The mapping could not be performed due to lack of resources
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is
- * set in flags, and offset is not a multiple of the page size, or addr is not a
- * multiple of the page size, or len is not a multiple of the page size, or is
- * 0, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN -The endpoint is not connected
- */
-off_t scif_register(scif_epd_t epd, void *addr, size_t len, off_t offset,
- int prot_flags, int map_flags);
-
-/**
- * scif_unregister() - Mark a memory region for remote access.
- * @epd: endpoint descriptor
- * @offset: start of range to unregister
- * @len: length of range to unregister
- *
- * The scif_unregister() function closes those previously registered windows
- * which are entirely within the range [offset, offset + len - 1]. It is an
- * error to specify a range which intersects only a subrange of a window.
- *
- * On a successful return, pages within the window may no longer be specified
- * in calls to mmap(), scif_readfrom(), scif_writeto(), scif_vreadfrom(),
- * scif_vwriteto(), scif_get_pages, and scif_fence_signal(). The window,
- * however, continues to exist until all previous references against it are
- * removed. A window is referenced if there is a mapping to it created by
- * mmap(), or if scif_get_pages() was called against the window
- * (and the pages have not been returned via scif_put_pages()). A window is
- * also referenced while an RMA, in which some range of the window is a source
- * or destination, is in progress. Finally a window is referenced while some
- * offset in that window was specified to scif_fence_signal(), and the RMAs
- * marked by that call to scif_fence_signal() have not completed. While a
- * window is in this state, its registered address space pages are not
- * available for use in a new registered window.
- *
- * When all such references to the window have been removed, its references to
- * all the physical pages which it represents are removed. Similarly, the
- * registered address space pages of the window become available for
- * registration in a new window.
- *
- * Return:
- * Upon successful completion, scif_unregister() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned. In the event of an
- * error, no windows are unregistered.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - the range [offset, offset + len - 1] intersects a subrange of a
- * window, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_unregister(scif_epd_t epd, off_t offset, size_t len);
-
-/**
- * scif_readfrom() - Copy from a remote address space
- * @epd: endpoint descriptor
- * @loffset: offset in local registered address space to
- * which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space
- * from which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_readfrom() copies len bytes from the remote registered address space of
- * the peer of endpoint epd, starting at the offset roffset to the local
- * registered address space of epd, starting at the offset loffset.
- *
- * Each of the specified ranges [loffset, loffset + len - 1] and [roffset,
- * roffset + len - 1] must be within some registered window or windows of the
- * local and remote nodes. A range may intersect multiple registered windows,
- * but only if those windows are contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_readfrom() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * The optimal DMA performance will likely be realized if both
- * loffset and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if loffset and roffset are not
- * cacheline aligned but are separated by some multiple of 64. The lowest level
- * of performance is likely if loffset and roffset are not separated by a
- * multiple of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_readfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered
- * address space of epd, or, The range [roffset, roffset + len - 1] is invalid
- * for the registered address space of the peer of epd, or loffset or roffset
- * is negative
- */
-int scif_readfrom(scif_epd_t epd, off_t loffset, size_t len, off_t
- roffset, int rma_flags);
-
-/**
- * scif_writeto() - Copy to a remote address space
- * @epd: endpoint descriptor
- * @loffset: offset in local registered address space
- * from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to
- * which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_writeto() copies len bytes from the local registered address space of
- * epd, starting at the offset loffset to the remote registered address space
- * of the peer of endpoint epd, starting at the offset roffset.
- *
- * Each of the specified ranges [loffset, loffset + len - 1] and [roffset,
- * roffset + len - 1] must be within some registered window or windows of the
- * local and remote nodes. A range may intersect multiple registered windows,
- * but only if those windows are contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_writeto() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * The optimal DMA performance will likely be realized if both
- * loffset and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if loffset and roffset are not cacheline
- * aligned but are separated by some multiple of 64. The lowest level of
- * performance is likely if loffset and roffset are not separated by a multiple
- * of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_readfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - The range [loffset, loffset + len - 1] is invalid for the registered
- * address space of epd, or, The range [roffset , roffset + len -1] is invalid
- * for the registered address space of the peer of epd, or loffset or roffset
- * is negative
- */
-int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t
- roffset, int rma_flags);
-
-/**
- * scif_vreadfrom() - Copy from a remote address space
- * @epd: endpoint descriptor
- * @addr: address to which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space
- * from which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_vreadfrom() copies len bytes from the remote registered address
- * space of the peer of endpoint epd, starting at the offset roffset, to local
- * memory, starting at addr.
- *
- * The specified range [roffset, roffset + len - 1] must be within some
- * registered window or windows of the remote nodes. The range may
- * intersect multiple registered windows, but only if those windows are
- * contiguous in the registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_vreadfrom() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back
- * the specified local memory range may be remain in a pinned state even after
- * the specified transfer completes. This may reduce overhead if some or all of
- * the same virtual address range is referenced in a subsequent call of
- * scif_vreadfrom() or scif_vwriteto().
- *
- * The optimal DMA performance will likely be realized if both
- * addr and roffset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if addr and roffset are not
- * cacheline aligned but are separated by some multiple of 64. The lowest level
- * of performance is likely if addr and roffset are not separated by a
- * multiple of 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_USECACHE - enable registration caching
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_vreadfrom() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset,
- int rma_flags);
-
-/**
- * scif_vwriteto() - Copy to a remote address space
- * @epd: endpoint descriptor
- * @addr: address from which to copy
- * @len: length of range to copy
- * @roffset: offset in remote registered address space to
- * which to copy
- * @rma_flags: transfer mode flags
- *
- * scif_vwriteto() copies len bytes from the local memory, starting at addr, to
- * the remote registered address space of the peer of endpoint epd, starting at
- * the offset roffset.
- *
- * The specified range [roffset, roffset + len - 1] must be within some
- * registered window or windows of the remote nodes. The range may intersect
- * multiple registered windows, but only if those windows are contiguous in the
- * registered address space.
- *
- * If rma_flags includes SCIF_RMA_USECPU, then the data is copied using
- * programmed read/writes. Otherwise the data is copied using DMA. If rma_-
- * flags includes SCIF_RMA_SYNC, then scif_vwriteto() will return after the
- * transfer is complete. Otherwise, the transfer may be performed asynchron-
- * ously. The order in which any two asynchronous RMA operations complete
- * is non-deterministic. The synchronization functions, scif_fence_mark()/
- * scif_fence_wait() and scif_fence_signal(), can be used to synchronize to
- * the completion of asynchronous RMA operations on the same endpoint.
- *
- * The DMA transfer of individual bytes is not guaranteed to complete in
- * address order. If rma_flags includes SCIF_RMA_ORDERED, then the last
- * cacheline or partial cacheline of the source range will become visible on
- * the destination node after all other transferred data in the source
- * range has become visible on the destination node.
- *
- * If rma_flags includes SCIF_RMA_USECACHE, then the physical pages which back
- * the specified local memory range may be remain in a pinned state even after
- * the specified transfer completes. This may reduce overhead if some or all of
- * the same virtual address range is referenced in a subsequent call of
- * scif_vreadfrom() or scif_vwriteto().
- *
- * The optimal DMA performance will likely be realized if both
- * addr and offset are cacheline aligned (are a multiple of 64). Lower
- * performance will likely be realized if addr and offset are not cacheline
- * aligned but are separated by some multiple of 64. The lowest level of
- * performance is likely if addr and offset are not separated by a multiple of
- * 64.
- *
- * The rma_flags argument is formed by ORing together zero or more of the
- * following values.
- * SCIF_RMA_USECPU - perform the transfer using the CPU, otherwise use the DMA
- * engine.
- * SCIF_RMA_USECACHE - allow registration caching
- * SCIF_RMA_SYNC - perform the transfer synchronously, returning after the
- * transfer has completed. Passing this flag results in the
- * current implementation busy waiting and consuming CPU cycles
- * while the DMA transfer is in progress for best performance by
- * avoiding the interrupt latency.
- * SCIF_RMA_ORDERED - ensure that the last cacheline or partial cacheline of
- * the source range becomes visible on the destination node
- * after all other transferred data in the source range has
- * become visible on the destination
- *
- * Return:
- * Upon successful completion, scif_vwriteto() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EACCES - Attempt to write to a read-only range
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - rma_flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [roffset, roffset + len - 1] are invalid for the
- * registered address space of epd
- */
-int scif_vwriteto(scif_epd_t epd, void *addr, size_t len, off_t roffset,
- int rma_flags);
-
-/**
- * scif_fence_mark() - Mark previously issued RMAs
- * @epd: endpoint descriptor
- * @flags: control flags
- * @mark: marked value returned as output.
- *
- * scif_fence_mark() returns after marking the current set of all uncompleted
- * RMAs initiated through the endpoint epd or the current set of all
- * uncompleted RMAs initiated through the peer of endpoint epd. The RMAs are
- * marked with a value returned at mark. The application may subsequently call
- * scif_fence_wait(), passing the value returned at mark, to await completion
- * of all RMAs so marked.
- *
- * The flags argument has exactly one of the following values.
- * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint
- * epd are marked
- * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer
- * of endpoint epd are marked
- *
- * Return:
- * Upon successful completion, scif_fence_mark() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENOMEM - Insufficient kernel memory was available
- */
-int scif_fence_mark(scif_epd_t epd, int flags, int *mark);
-
-/**
- * scif_fence_wait() - Wait for completion of marked RMAs
- * @epd: endpoint descriptor
- * @mark: mark request
- *
- * scif_fence_wait() returns after all RMAs marked with mark have completed.
- * The value passed in mark must have been obtained in a previous call to
- * scif_fence_mark().
- *
- * Return:
- * Upon successful completion, scif_fence_wait() returns 0; otherwise in user
- * mode -1 is returned and errno is set to indicate the error; in kernel mode
- * the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENOMEM - Insufficient kernel memory was available
- */
-int scif_fence_wait(scif_epd_t epd, int mark);
-
-/**
- * scif_fence_signal() - Request a memory update on completion of RMAs
- * @epd: endpoint descriptor
- * @loff: local offset
- * @lval: local value to write to loffset
- * @roff: remote offset
- * @rval: remote value to write to roffset
- * @flags: flags
- *
- * scif_fence_signal() returns after marking the current set of all uncompleted
- * RMAs initiated through the endpoint epd or marking the current set of all
- * uncompleted RMAs initiated through the peer of endpoint epd.
- *
- * If flags includes SCIF_SIGNAL_LOCAL, then on completion of the RMAs in the
- * marked set, lval is written to memory at the address corresponding to offset
- * loff in the local registered address space of epd. loff must be within a
- * registered window. If flags includes SCIF_SIGNAL_REMOTE, then on completion
- * of the RMAs in the marked set, rval is written to memory at the address
- * corresponding to offset roff in the remote registered address space of epd.
- * roff must be within a remote registered window of the peer of epd. Note
- * that any specified offset must be DWORD (4 byte / 32 bit) aligned.
- *
- * The flags argument is formed by OR'ing together the following.
- * Exactly one of the following values.
- * SCIF_FENCE_INIT_SELF - RMA operations initiated through endpoint
- * epd are marked
- * SCIF_FENCE_INIT_PEER - RMA operations initiated through the peer
- * of endpoint epd are marked
- * One or more of the following values.
- * SCIF_SIGNAL_LOCAL - On completion of the marked set of RMAs, write lval to
- * memory at the address corresponding to offset loff in the local
- * registered address space of epd.
- * SCIF_SIGNAL_REMOTE - On completion of the marked set of RMAs, write rval to
- * memory at the address corresponding to offset roff in the remote
- * registered address space of epd.
- *
- * Return:
- * Upon successful completion, scif_fence_signal() returns 0; otherwise in
- * user mode -1 is returned and errno is set to indicate the error; in kernel
- * mode the negative of one of the following errors is returned.
- *
- * Errors:
- * EBADF, ENOTTY - epd is not a valid endpoint descriptor
- * ECONNRESET - Connection reset by peer
- * EINVAL - flags is invalid, or loff or roff are not DWORD aligned
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - loff is invalid for the registered address of epd, or roff is invalid
- * for the registered address space, of the peer of epd
- */
-int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff,
- u64 rval, int flags);
-
-/**
- * scif_get_node_ids() - Return information about online nodes
- * @nodes: array in which to return online node IDs
- * @len: number of entries in the nodes array
- * @self: address to place the node ID of the local node
- *
- * scif_get_node_ids() fills in the nodes array with up to len node IDs of the
- * nodes in the SCIF network. If there is not enough space in nodes, as
- * indicated by the len parameter, only len node IDs are returned in nodes. The
- * return value of scif_get_node_ids() is the total number of nodes currently in
- * the SCIF network. By checking the return value against the len parameter,
- * the user may determine if enough space for nodes was allocated.
- *
- * The node ID of the local node is returned at self.
- *
- * Return:
- * Upon successful completion, scif_get_node_ids() returns the actual number of
- * online nodes in the SCIF network including 'self'; otherwise in user mode
- * -1 is returned and errno is set to indicate the error; in kernel mode no
- * errors are returned.
- */
-int scif_get_node_ids(u16 *nodes, int len, u16 *self);
-
-/**
- * scif_pin_pages() - Pin a set of pages
- * @addr: Virtual address of range to pin
- * @len: Length of range to pin
- * @prot_flags: Page protection flags
- * @map_flags: Page classification flags
- * @pinned_pages: Handle to pinned pages
- *
- * scif_pin_pages() pins (locks in physical memory) the physical pages which
- * back the range of virtual address pages starting at addr and continuing for
- * len bytes. addr and len are constrained to be multiples of the page size. A
- * successful scif_pin_pages() call returns a handle to pinned_pages which may
- * be used in subsequent calls to scif_register_pinned_pages().
- *
- * The pages will remain pinned as long as there is a reference against the
- * scif_pinned_pages_t value returned by scif_pin_pages() and until
- * scif_unpin_pages() is called, passing the scif_pinned_pages_t value. A
- * reference is added to a scif_pinned_pages_t value each time a window is
- * created by calling scif_register_pinned_pages() and passing the
- * scif_pinned_pages_t value. A reference is removed from a
- * scif_pinned_pages_t value each time such a window is deleted.
- *
- * Subsequent operations which change the memory pages to which virtual
- * addresses are mapped (such as mmap(), munmap()) have no effect on the
- * scif_pinned_pages_t value or windows created against it.
- *
- * If the process will fork(), it is recommended that the registered
- * virtual address range be marked with MADV_DONTFORK. Doing so will prevent
- * problems due to copy-on-write semantics.
- *
- * The prot_flags argument is formed by OR'ing together one or more of the
- * following values.
- * SCIF_PROT_READ - allow read operations against the pages
- * SCIF_PROT_WRITE - allow write operations against the pages
- * The map_flags argument can be set as SCIF_MAP_KERNEL to interpret addr as a
- * kernel space address. By default, addr is interpreted as a user space
- * address.
- *
- * Return:
- * Upon successful completion, scif_pin_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EINVAL - prot_flags is invalid, map_flags is invalid, or offset is negative
- * ENOMEM - Not enough space
- */
-int scif_pin_pages(void *addr, size_t len, int prot_flags, int map_flags,
- scif_pinned_pages_t *pinned_pages);
-
-/**
- * scif_unpin_pages() - Unpin a set of pages
- * @pinned_pages: Handle to pinned pages to be unpinned
- *
- * scif_unpin_pages() prevents scif_register_pinned_pages() from registering new
- * windows against pinned_pages. The physical pages represented by pinned_pages
- * will remain pinned until all windows previously registered against
- * pinned_pages are deleted (the window is scif_unregister()'d and all
- * references to the window are removed (see scif_unregister()).
- *
- * pinned_pages must have been obtain from a previous call to scif_pin_pages().
- * After calling scif_unpin_pages(), it is an error to pass pinned_pages to
- * scif_register_pinned_pages().
- *
- * Return:
- * Upon successful completion, scif_unpin_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- *
- * Errors:
- * EINVAL - pinned_pages is not valid
- */
-int scif_unpin_pages(scif_pinned_pages_t pinned_pages);
-
-/**
- * scif_register_pinned_pages() - Mark a memory region for remote access.
- * @epd: endpoint descriptor
- * @pinned_pages: Handle to pinned pages
- * @offset: Registered address space offset
- * @map_flags: Flags which control where pages are mapped
- *
- * The scif_register_pinned_pages() function opens a window, a range of whole
- * pages of the registered address space of the endpoint epd, starting at
- * offset po. The value of po, further described below, is a function of the
- * parameters offset and pinned_pages, and the value of map_flags. Each page of
- * the window represents a corresponding physical memory page of the range
- * represented by pinned_pages; the length of the window is the same as the
- * length of range represented by pinned_pages. A successful
- * scif_register_pinned_pages() call returns po as the return value.
- *
- * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset
- * exactly, and offset is constrained to be a multiple of the page size. The
- * mapping established by scif_register_pinned_pages() will not replace any
- * existing registration; an error is returned if any page of the new window
- * would intersect an existing window.
- *
- * When SCIF_MAP_FIXED is not set, the implementation uses offset in an
- * implementation-defined manner to arrive at po. The po so chosen will be an
- * area of the registered address space that the implementation deems suitable
- * for a mapping of the required size. An offset value of 0 is interpreted as
- * granting the implementation complete freedom in selecting po, subject to
- * constraints described below. A non-zero value of offset is taken to be a
- * suggestion of an offset near which the mapping should be placed. When the
- * implementation selects a value for po, it does not replace any extant
- * window. In all cases, po will be a multiple of the page size.
- *
- * The physical pages which are so represented by a window are available for
- * access in calls to scif_get_pages(), scif_readfrom(), scif_writeto(),
- * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the
- * physical pages represented by the window will not be reused by the memory
- * subsystem for any other purpose. Note that the same physical page may be
- * represented by multiple windows.
- *
- * Windows created by scif_register_pinned_pages() are unregistered by
- * scif_unregister().
- *
- * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a
- * fixed offset.
- *
- * Return:
- * Upon successful completion, scif_register_pinned_pages() returns the offset
- * at which the mapping was placed (po); otherwise the negative of one of the
- * following errors is returned.
- *
- * Errors:
- * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags and pages in the new window
- * would intersect an existing window
- * EAGAIN - The mapping could not be performed due to lack of resources
- * ECONNRESET - Connection reset by peer
- * EINVAL - map_flags is invalid, or SCIF_MAP_FIXED is set in map_flags, and
- * offset is not a multiple of the page size, or offset is negative
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOMEM - Not enough space
- * ENOTCONN - The endpoint is not connected
- */
-off_t scif_register_pinned_pages(scif_epd_t epd,
- scif_pinned_pages_t pinned_pages,
- off_t offset, int map_flags);
-
-/**
- * scif_get_pages() - Add references to remote registered pages
- * @epd: endpoint descriptor
- * @offset: remote registered offset
- * @len: length of range of pages
- * @pages: returned scif_range structure
- *
- * scif_get_pages() returns the addresses of the physical pages represented by
- * those pages of the registered address space of the peer of epd, starting at
- * offset and continuing for len bytes. offset and len are constrained to be
- * multiples of the page size.
- *
- * All of the pages in the specified range [offset, offset + len - 1] must be
- * within a single window of the registered address space of the peer of epd.
- *
- * The addresses are returned as a virtually contiguous array pointed to by the
- * phys_addr component of the scif_range structure whose address is returned in
- * pages. The nr_pages component of scif_range is the length of the array. The
- * prot_flags component of scif_range holds the protection flag value passed
- * when the pages were registered.
- *
- * Each physical page whose address is returned by scif_get_pages() remains
- * available and will not be released for reuse until the scif_range structure
- * is returned in a call to scif_put_pages(). The scif_range structure returned
- * by scif_get_pages() must be unmodified.
- *
- * It is an error to call scif_close() on an endpoint on which a scif_range
- * structure of that endpoint has not been returned to scif_put_pages().
- *
- * Return:
- * Upon successful completion, scif_get_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- * Errors:
- * ECONNRESET - Connection reset by peer.
- * EINVAL - offset is not a multiple of the page size, or offset is negative, or
- * len is not a multiple of the page size
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid
- * for the registered address space of the peer epd
- */
-int scif_get_pages(scif_epd_t epd, off_t offset, size_t len,
- struct scif_range **pages);
-
-/**
- * scif_put_pages() - Remove references from remote registered pages
- * @pages: pages to be returned
- *
- * scif_put_pages() releases a scif_range structure previously obtained by
- * calling scif_get_pages(). The physical pages represented by pages may
- * be reused when the window which represented those pages is unregistered.
- * Therefore, those pages must not be accessed after calling scif_put_pages().
- *
- * Return:
- * Upon successful completion, scif_put_pages() returns 0; otherwise the
- * negative of one of the following errors is returned.
- * Errors:
- * EINVAL - pages does not point to a valid scif_range structure, or
- * the scif_range structure pointed to by pages was already returned
- * ENODEV - The remote node is lost or existed, but is not currently in the
- * network since it may have crashed
- * ENOTCONN - The endpoint is not connected
- */
-int scif_put_pages(struct scif_range *pages);
-
-/**
- * scif_poll() - Wait for some event on an endpoint
- * @epds: Array of endpoint descriptors
- * @nepds: Length of epds
- * @timeout: Upper limit on time for which scif_poll() will block
- *
- * scif_poll() waits for one of a set of endpoints to become ready to perform
- * an I/O operation.
- *
- * The epds argument specifies the endpoint descriptors to be examined and the
- * events of interest for each endpoint descriptor. epds is a pointer to an
- * array with one member for each open endpoint descriptor of interest.
- *
- * The number of items in the epds array is specified in nepds. The epd field
- * of scif_pollepd is an endpoint descriptor of an open endpoint. The field
- * events is a bitmask specifying the events which the application is
- * interested in. The field revents is an output parameter, filled by the
- * kernel with the events that actually occurred. The bits returned in revents
- * can include any of those specified in events, or one of the values EPOLLERR,
- * EPOLLHUP, or EPOLLNVAL. (These three bits are meaningless in the events
- * field, and will be set in the revents field whenever the corresponding
- * condition is true.)
- *
- * If none of the events requested (and no error) has occurred for any of the
- * endpoint descriptors, then scif_poll() blocks until one of the events occurs.
- *
- * The timeout argument specifies an upper limit on the time for which
- * scif_poll() will block, in milliseconds. Specifying a negative value in
- * timeout means an infinite timeout.
- *
- * The following bits may be set in events and returned in revents.
- * EPOLLIN - Data may be received without blocking. For a connected
- * endpoint, this means that scif_recv() may be called without blocking. For a
- * listening endpoint, this means that scif_accept() may be called without
- * blocking.
- * EPOLLOUT - Data may be sent without blocking. For a connected endpoint, this
- * means that scif_send() may be called without blocking. EPOLLOUT may also be
- * used to block waiting for a non-blocking connect to complete. This bit value
- * has no meaning for a listening endpoint and is ignored if specified.
- *
- * The following bits are only returned in revents, and are ignored if set in
- * events.
- * EPOLLERR - An error occurred on the endpoint
- * EPOLLHUP - The connection to the peer endpoint was disconnected
- * EPOLLNVAL - The specified endpoint descriptor is invalid.
- *
- * Return:
- * Upon successful completion, scif_poll() returns a non-negative value. A
- * positive value indicates the total number of endpoint descriptors that have
- * been selected (that is, endpoint descriptors for which the revents member is
- * non-zero). A value of 0 indicates that the call timed out and no endpoint
- * descriptors have been selected. Otherwise in user mode -1 is returned and
- * errno is set to indicate the error; in kernel mode the negative of one of
- * the following errors is returned.
- *
- * Errors:
- * EINTR - A signal occurred before any requested event
- * EINVAL - The nepds argument is greater than {OPEN_MAX}
- * ENOMEM - There was no space to allocate file descriptor tables
- */
-int scif_poll(struct scif_pollepd *epds, unsigned int nepds, long timeout);
-
-/**
- * scif_client_register() - Register a SCIF client
- * @client: client to be registered
- *
- * scif_client_register() registers a SCIF client. The probe() method
- * of the client is called when SCIF peer devices come online and the
- * remove() method is called when the peer devices disappear.
- *
- * Return:
- * Upon successful completion, scif_client_register() returns a non-negative
- * value. Otherwise the return value is the same as subsys_interface_register()
- * in the kernel.
- */
-int scif_client_register(struct scif_client *client);
-
-/**
- * scif_client_unregister() - Unregister a SCIF client
- * @client: client to be unregistered
- *
- * scif_client_unregister() unregisters a SCIF client.
- *
- * Return:
- * None
- */
-void scif_client_unregister(struct scif_client *client);
-
-#endif /* __SCIF_H__ */
char *mangle_path(char *s, const char *p, const char *esc);
int seq_open(struct file *, const struct seq_operations *);
ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
+ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter);
loff_t seq_lseek(struct file *, loff_t, int);
int seq_release(struct inode *, struct file *);
int seq_write(struct seq_file *seq, const void *data, size_t len);
memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1));
break;
case 2: set->sig[1] = 0;
+ break;
case 1: ;
}
}
memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1));
break;
case 2: set->sig[1] = -1;
+ break;
case 1: ;
}
}
return __spi_alloc_controller(host, size, true);
}
+struct spi_controller *__devm_spi_alloc_controller(struct device *dev,
+ unsigned int size,
+ bool slave);
+
+static inline struct spi_controller *devm_spi_alloc_master(struct device *dev,
+ unsigned int size)
+{
+ return __devm_spi_alloc_controller(dev, size, false);
+}
+
+static inline struct spi_controller *devm_spi_alloc_slave(struct device *dev,
+ unsigned int size)
+{
+ if (!IS_ENABLED(CONFIG_SPI_SLAVE))
+ return NULL;
+
+ return __devm_spi_alloc_controller(dev, size, true);
+}
+
extern int spi_register_controller(struct spi_controller *ctlr);
extern int devm_spi_register_controller(struct device *dev,
struct spi_controller *ctlr);
#include <linux/dma-direction.h>
#include <linux/init.h>
#include <linux/types.h>
+#include <linux/limits.h>
struct device;
struct page;
SYNC_FOR_DEVICE = 1,
};
-extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
- dma_addr_t tbl_dma_addr,
- phys_addr_t phys,
- size_t mapping_size,
- size_t alloc_size,
- enum dma_data_direction dir,
- unsigned long attrs);
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs);
extern void swiotlb_tbl_unmap_single(struct device *hwdev,
phys_addr_t tlb_addr,
*/
static inline s64 timespec64_to_ns(const struct timespec64 *ts)
{
+ /* Prevent multiplication overflow */
+ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX)
+ return KTIME_MAX;
+
return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
}
struct termiox *termiox; /* May be NULL for unsupported */
char name[64];
struct pid *pgrp; /* Protected by ctrl lock */
+ /*
+ * Writes protected by both ctrl lock and legacy mutex, readers must use
+ * at least one of them.
+ */
struct pid *session;
unsigned long flags;
int count;
#define OS_STRING_IDX 0xEE
/**
- * struct usb_composite_device - represents one composite usb gadget
+ * struct usb_composite_dev - represents one composite usb gadget
* @gadget: read-only, abstracts the gadget's usb peripheral controller
* @req: used for control responses; buffer is pre-allocated
* @os_desc_req: used for OS descriptors responses; buffer is pre-allocated
int nvqs;
};
+/**
+ * vDPA IOVA range - the IOVA range support by the device
+ * @first: start of the IOVA range
+ * @last: end of the IOVA range
+ */
+struct vdpa_iova_range {
+ u64 first;
+ u64 last;
+};
+
/**
* vDPA_config_ops - operations for configuring a vDPA device.
* Note: vDPA device drivers are required to implement all of the
* @get_generation: Get device config generation (optional)
* @vdev: vdpa device
* Returns u32: device generation
+ * @get_iova_range: Get supported iova range (optional)
+ * @vdev: vdpa device
+ * Returns the iova range supported by
+ * the device.
* @set_map: Set device memory mapping (optional)
* Needed for device that using device
* specific DMA translation (on-chip IOMMU)
void (*set_config)(struct vdpa_device *vdev, unsigned int offset,
const void *buf, unsigned int len);
u32 (*get_generation)(struct vdpa_device *vdev);
+ struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev);
/* DMA ops */
int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
* zsmalloc mapping modes
*
* NOTE: These only make a difference when a mapped object spans pages.
- * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected.
*/
enum zs_mapmode {
ZS_MM_RW, /* normal read-write mapping */
struct rtnl_link_stats64 slave_stats;
};
+static inline struct slave *to_slave(struct kobject *kobj)
+{
+ return container_of(kobj, struct slave, kobj);
+}
+
struct bond_up_slave {
unsigned int count;
struct rcu_head rcu;
/* exported from bond_netlink.c */
extern struct rtnl_link_ops bond_link_ops;
+/* exported from bond_sysfs_slave.c */
+extern const struct sysfs_ops slave_sysfs_ops;
+
static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb)
{
atomic_long_inc(&dev->tx_dropped);
enum cfg80211_station_type statype);
/**
- * enum station_info_rate_flags - bitrate info flags
+ * enum rate_info_flags - bitrate info flags
*
* Used by the driver to indicate the specific rate transmission
* type for 802.11n transmissions.
};
/**
- * enum station_info_rate_flags - bitrate info flags
+ * enum bss_param_flags - bitrate info flags
*
* Used by the driver to indicate the specific rate transmission
* type for 802.11n transmissions.
struct ieee80211_channel *channel, gfp_t gfp);
/**
- * cfg80211_notify_new_candidate - notify cfg80211 of a new mesh peer candidate
+ * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer
+ * candidate
*
* @dev: network device
* @macaddr: the MAC address of the new candidate
void cfg80211_unregister_wdev(struct wireless_dev *wdev);
/**
- * struct cfg80211_ft_event - FT Information Elements
+ * struct cfg80211_ft_event_params - FT Information Elements
* @ies: FT IEs
* @ies_len: length of the FT IE in bytes
* @target_ap: target AP's MAC address
if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0)
return 0;
- check += (__force u16)htons(0x100);
+ check += (__force u16)htons(0x1);
iph->check = (__force __sum16)(check + (check>=0xFFFF));
iph->tos ^= INET_ECN_MASK;
unsigned long high_limit);
int inet_hashinfo2_init_mod(struct inet_hashinfo *h);
-bool inet_ehash_insert(struct sock *sk, struct sock *osk);
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk);
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk);
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk,
+ bool *found_dup_sk);
int __inet_hash(struct sock *sk, struct sock *osk);
int inet_hash(struct sock *sk);
void inet_unhash(struct sock *sk);
const void *from, int len,
__be16 flags)
{
- memcpy(ip_tunnel_info_opts(info), from, len);
info->options_len = len;
- info->key.tun_flags |= flags;
+ if (len > 0) {
+ memcpy(ip_tunnel_info_opts(info), from, len);
+ info->key.tun_flags |= flags;
+ }
}
static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
__be16 flags)
{
info->options_len = 0;
- info->key.tun_flags |= flags;
}
#endif /* CONFIG_INET */
rcu_read_unlock();
inet_frag_put(&fq->q);
}
+
+/* Check if the upper layer header is truncated in the first fragment. */
+static inline bool
+ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp)
+{
+ u8 nexthdr = *nexthdrp;
+ __be16 frag_off;
+ int offset;
+
+ offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off);
+ if (offset < 0 || (frag_off & htons(IP6_OFFSET)))
+ return false;
+ switch (nexthdr) {
+ case NEXTHDR_TCP:
+ offset += sizeof(struct tcphdr);
+ break;
+ case NEXTHDR_UDP:
+ offset += sizeof(struct udphdr);
+ break;
+ case NEXTHDR_ICMP:
+ offset += sizeof(struct icmp6hdr);
+ break;
+ default:
+ offset += 1;
+ }
+ if (offset > skb->len)
+ return true;
+ return false;
+}
+
#endif
#endif
};
/**
- * enum ieee80211_reconfig_complete_type - reconfig type
+ * enum ieee80211_reconfig_type - reconfig type
*
* This enum is used by the reconfig_complete() callback to indicate what
* reconfiguration type was completed.
int band, struct ieee80211_sta **sta);
/**
- * Sanity-check and parse the radiotap header of injected frames
+ * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header
+ * of injected frames
* @skb: packet injected by userspace
* @dev: the &struct device of this 802.11 device
*/
void ieee80211_update_p2p_noa(struct ieee80211_noa_data *data, u32 tsf);
/**
- * ieee80211_tdls_oper - request userspace to perform a TDLS operation
+ * ieee80211_tdls_oper_request - request userspace to perform a TDLS operation
* @vif: virtual interface
* @peer: the peer's destination address
* @oper: the requested TDLS operation
int (*pconstructor)(struct pneigh_entry *);
void (*pdestructor)(struct pneigh_entry *);
void (*proxy_redo)(struct sk_buff *skb);
+ int (*is_multicast)(const void *pkey);
bool (*allow_add)(const struct net_device *dev,
struct netlink_ext_ack *extack);
char *id;
struct nft_flow_key {
struct flow_dissector_key_basic basic;
+ struct flow_dissector_key_control control;
union {
struct flow_dissector_key_ipv4_addrs ipv4;
struct flow_dissector_key_ipv6_addrs ipv6;
#define NFT_OFFLOAD_F_ACTION (1 << 0)
+void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow,
+ enum flow_dissector_key_id addr_type);
+
struct nft_rule;
struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule);
void nft_flow_rule_destroy(struct nft_flow_rule *flow);
offsetof(struct nft_flow_key, __base.__field); \
(__reg)->len = __len; \
(__reg)->key = __key; \
+
+#define NFT_OFFLOAD_MATCH_EXACT(__key, __base, __field, __len, __reg) \
+ NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \
memset(&(__reg)->mask, 0xff, (__reg)->len);
int nft_chain_offload_priority(struct nft_base_chain *basechain);
* to be atomic.
*/
TLS_TX_SYNC_SCHED = 1,
+ /* tls_dev_del was called for the RX side, device state was released,
+ * but tls_ctx->netdev might still be kept, because TX-side driver
+ * resources might not be released yet. Used to prevent the second
+ * tls_dev_del call in tls_device_down if it happens simultaneously.
+ */
+ TLS_RX_DEV_CLOSED = 2,
};
struct cipher_context {
#define TLS_DEVICE_RESYNC_ASYNC_LOGMAX 13
struct tls_offload_resync_async {
atomic64_t req;
- u32 loglen;
+ u16 loglen;
+ u16 rcd_delta;
u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX];
};
return (i == -1);
}
+static inline void tls_bigint_subtract(unsigned char *seq, int n)
+{
+ u64 rcd_sn;
+ __be64 *p;
+
+ BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8);
+
+ p = (__be64 *)seq;
+ rcd_sn = be64_to_cpu(*p);
+ *p = cpu_to_be64(rcd_sn - n);
+}
+
static inline struct tls_context *tls_get_ctx(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) |
((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC);
rx_ctx->resync_async->loglen = 0;
+ rx_ctx->resync_async->rcd_delta = 0;
}
static inline void
struct page **pgs;
int id;
struct list_head xsk_dma_list;
+ struct work_struct work;
};
struct xsk_map {
void xp_destroy(struct xsk_buff_pool *pool);
void xp_release(struct xdp_buff_xsk *xskb);
void xp_get_pool(struct xsk_buff_pool *pool);
-void xp_put_pool(struct xsk_buff_pool *pool);
+bool xp_put_pool(struct xsk_buff_pool *pool);
void xp_clear_dev(struct xsk_buff_pool *pool);
void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
int *qp_attr_mask);
-/**
- * rdma_connect - Initiate an active connection request.
- * @id: Connection identifier to connect.
- * @conn_param: Connection information used for connected QPs.
- *
- * Users must have resolved a route for the rdma_cm_id to connect with
- * by having called rdma_resolve_route before calling this routine.
- *
- * This call will either connect to a remote QP or obtain remote QP
- * information for unconnected rdma_cm_id's. The actual operation is
- * based on the rdma_cm_id's port space.
- */
int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param);
+int rdma_connect_locked(struct rdma_cm_id *id,
+ struct rdma_conn_param *conn_param);
int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,
struct rdma_ucm_ece *ece);
void *dd_data; /* driver/transport data */
};
+/* invalid scsi_task pointer */
+#define INVALID_SCSI_TASK (struct iscsi_task *)-1l
+
static inline int iscsi_task_has_unsol_data(struct iscsi_task *task)
{
return task->unsol_r2t.data_length > task->unsol_r2t.sent;
snd_ctl_elem_iface_t iface; /* interface identifier */
unsigned int device; /* device/client number */
unsigned int subdevice; /* subdevice (substream) number */
- const unsigned char *name; /* ASCII name of item */
+ const char *name; /* ASCII name of item */
unsigned int index; /* index of item */
unsigned int access; /* access rights */
unsigned int count; /* count of same elements */
#define snd_BUG() WARN(1, "BUG?\n")
/**
- * Suppress high rates of output when CONFIG_SND_DEBUG is enabled.
+ * snd_printd_ratelimit - Suppress high rates of output when
+ * CONFIG_SND_DEBUG is enabled.
*/
#define snd_printd_ratelimit() printk_ratelimit()
}
/**
- * snd_pcm_sgbuf_chunk_size - Compute the max size that fits within the contig.
- * page from the given size
+ * snd_pcm_sgbuf_get_chunk_size - Compute the max size that fits within the
+ * contig. page from the given size
* @substream: PCM substream
* @ofs: byte offset
* @size: byte size to examine
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/sound/rt1015.h -- Platform data for RT1015
+ *
+ * Copyright 2020 Realtek Microelectronics
+ */
+
+#ifndef __LINUX_SND_RT1015_H
+#define __LINUX_SND_RT1015_H
+
+struct rt1015_platform_data {
+ unsigned int power_up_delay_ms;
+};
+
+#endif
__entry->vnode, __entry->off, __entry->i_size)
);
-/*
- * We use page->private to hold the amount of the page that we've written to,
- * splitting the field into two parts. However, we need to represent a range
- * 0...PAGE_SIZE inclusive, so we can't support 64K pages on a 32-bit system.
- */
-#if PAGE_SIZE > 32768
-#define AFS_PRIV_MAX 0xffffffff
-#define AFS_PRIV_SHIFT 32
-#else
-#define AFS_PRIV_MAX 0xffff
-#define AFS_PRIV_SHIFT 16
-#endif
-
TRACE_EVENT(afs_page_dirty,
TP_PROTO(struct afs_vnode *vnode, const char *where,
pgoff_t page, unsigned long priv),
__entry->priv = priv;
),
- TP_printk("vn=%p %lx %s %lu-%lu",
+ TP_printk("vn=%p %lx %s %zx-%zx%s",
__entry->vnode, __entry->page, __entry->where,
- __entry->priv & AFS_PRIV_MAX,
- __entry->priv >> AFS_PRIV_SHIFT)
+ afs_page_dirty_from(__entry->priv),
+ afs_page_dirty_to(__entry->priv),
+ afs_is_page_dirty_mmapped(__entry->priv) ? " M" : "")
);
TRACE_EVENT(afs_call_state,
{ EXT4_FC_REASON_XATTR, "XATTR"}, \
{ EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \
{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
- { EXT4_FC_REASON_MEM, "NO_MEM"}, \
+ { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \
{ EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \
{ EXT4_FC_REASON_RESIZE, "RESIZE"}, \
{ EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \
- { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"})
+ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \
+ { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"})
TRACE_EVENT(ext4_other_inode_update_time,
TP_PROTO(struct inode *inode, ino_t orig_ino),
),
TP_printk("dev %d:%d fc ineligible reasons:\n"
- "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+ "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; "
"num_commits:%ld, ineligible: %ld, numblks: %ld",
MAJOR(__entry->dev), MINOR(__entry->dev),
FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
- FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+ FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM),
FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+ FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA),
__entry->sbi->s_fc_stats.fc_num_commits,
__entry->sbi->s_fc_stats.fc_ineligible_commits,
__entry->sbi->s_fc_stats.fc_numblks)
TP_fast_assign(
__entry->task_id = task->tk_pid;
- __entry->client_id = task->tk_client->cl_clid;
+ __entry->client_id = task->tk_client ?
+ task->tk_client->cl_clid : -1;
__entry->head_base = xdr->head[0].iov_base;
__entry->head_len = xdr->head[0].iov_len;
__entry->tail_base = xdr->tail[0].iov_base;
__field(size_t, tail_len)
__field(unsigned int, page_len)
__field(unsigned int, len)
- __string(progname,
- xdr->rqst->rq_task->tk_client->cl_program->name)
- __string(procedure,
- xdr->rqst->rq_task->tk_msg.rpc_proc->p_name)
+ __string(progname, xdr->rqst ?
+ xdr->rqst->rq_task->tk_client->cl_program->name : "unknown")
+ __string(procedure, xdr->rqst ?
+ xdr->rqst->rq_task->tk_msg.rpc_proc->p_name : "unknown")
),
TP_fast_assign(
),
TP_fast_assign(
- strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32);
__entry->ino = inode->i_ino;
__entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc);
__entry->history = history;
),
TP_fast_assign(
- strncpy(__entry->name, bdi_dev_name(old_wb->bdi), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32);
__entry->ino = inode->i_ino;
__entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb);
__entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb);
struct address_space *mapping = page_mapping(page);
struct inode *inode = mapping ? mapping->host : NULL;
- strncpy(__entry->name, bdi_dev_name(wb->bdi), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->bdi_id = wb->bdi->id;
__entry->ino = inode ? inode->i_ino : 0;
__entry->memcg_id = wb->memcg_css->id;
),
TP_fast_assign(
- strncpy(__entry->name, bdi_dev_name(wb->bdi), 32);
+ strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
__entry->frn_bdi_id = frn_bdi_id;
__entry->frn_memcg_id = frn_memcg_id;
DEVLINK_ATTR_RELOAD_STATS_LIMIT, /* u8 */
DEVLINK_ATTR_RELOAD_STATS_VALUE, /* u32 */
DEVLINK_ATTR_REMOTE_RELOAD_STATS, /* nested */
+ DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */
+ DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */
/* add new attributes above here, update the policy in devlink.c */
* struct gpiochip_info - Information about a certain GPIO chip
* @name: the Linux kernel name of this GPIO chip
* @label: a functional name for this GPIO chip, such as a product
- * number, may be empty
+ * number, may be empty (i.e. label[0] == '\0')
* @lines: number of GPIO lines on this chip
*/
struct gpiochip_info {
* identifying which field of the attribute union is in use.
* @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use
* @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use
- * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use
+ * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us field is in use
*/
enum gpio_v2_line_attr_id {
GPIO_V2_LINE_ATTR_ID_FLAGS = 1,
* struct gpio_v2_line_attribute - a configurable attribute of a line
* @id: attribute identifier with value from &enum gpio_v2_line_attr_id
* @padding: reserved for future use and must be zero filled
- * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
- * line, with values from enum gpio_v2_line_flag, such as
- * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed
+ * @flags: if id is %GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO
+ * line, with values from &enum gpio_v2_line_flag, such as
+ * %GPIO_V2_LINE_FLAG_ACTIVE_LOW, %GPIO_V2_LINE_FLAG_OUTPUT etc, added
* together. This overrides the default flags contained in the &struct
* gpio_v2_line_config for the associated line.
- * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
+ * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap
* containing the values to which the lines will be set, with each bit
* number corresponding to the index into &struct
* gpio_v2_line_request.offsets.
- * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired
- * debounce period, in microseconds
+ * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the
+ * desired debounce period, in microseconds
*/
struct gpio_v2_line_attribute {
__u32 id;
/**
* struct gpio_v2_line_config - Configuration for GPIO lines
- * @flags: flags for the GPIO lines, with values from enum
- * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
- * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together. This is the default for
+ * @flags: flags for the GPIO lines, with values from &enum
+ * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. This is the default for
* all requested lines but may be overridden for particular lines using
- * attrs.
- * @num_attrs: the number of attributes in attrs
+ * @attrs.
+ * @num_attrs: the number of attributes in @attrs
* @padding: reserved for future use and must be zero filled
* @attrs: the configuration attributes associated with the requested
* lines. Any attribute should only be associated with a particular line
* "my-bitbanged-relay"
* @config: requested configuration for the lines.
* @num_lines: number of lines requested in this request, i.e. the number
- * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to
+ * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to
* request a single line
* @event_buffer_size: a suggested minimum number of line events that the
* kernel should buffer. This is only relevant if edge detection is
* enabled in the configuration. Note that this is only a suggested value
* and the kernel may allocate a larger buffer or cap the size of the
* buffer. If this field is zero then the buffer size defaults to a minimum
- * of num_lines*16.
+ * of @num_lines * 16.
* @padding: reserved for future use and must be zero filled
* @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means
+ * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means
* error
*/
struct gpio_v2_line_request {
* struct gpio_v2_line_info - Information about a certain GPIO line
* @name: the name of this GPIO line, such as the output pin of the line on
* the chip, a rail or a pin header name on a board, as specified by the
- * GPIO chip, may be empty
+ * GPIO chip, may be empty (i.e. name[0] == '\0')
* @consumer: a functional name for the consumer of this GPIO line as set
* by whatever is using it, will be empty if there is no current user but
* may also be empty if the consumer doesn't set this up
- * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW,
- * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together
* @offset: the local offset on this GPIO chip, fill this in when
* requesting the line information from the kernel
- * @num_attrs: the number of attributes in attrs
+ * @num_attrs: the number of attributes in @attrs
+ * @flags: flags for the GPIO lines, with values from &enum
+ * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW,
+ * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together.
* @attrs: the configuration attributes associated with the line
* @padding: reserved for future use
*/
* of a GPIO line
* @info: updated line information
* @timestamp_ns: estimate of time of status change occurrence, in nanoseconds
- * @event_type: the type of change with a value from enum
+ * @event_type: the type of change with a value from &enum
* gpio_v2_line_changed_type
* @padding: reserved for future use
*/
/**
* struct gpio_v2_line_event - The actual event being pushed to userspace
* @timestamp_ns: best estimate of time of event occurrence, in nanoseconds.
- * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the
- * accurate measurement of the time between events. It does not provide
+ * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow
+ * the accurate measurement of the time between events. It does not provide
* the wall-clock time.
- * @id: event identifier with value from enum gpio_v2_line_event_id
+ * @id: event identifier with value from &enum gpio_v2_line_event_id
* @offset: the offset of the line that triggered the event
* @seqno: the sequence number for this event in the sequence of events for
* all the lines in this line request
};
/*
- * ABI v1
+ * ABI v1
*
* This version of the ABI is deprecated.
* Use the latest version of the ABI, defined above, instead.
* @flags: various flags for this line
* @name: the name of this GPIO line, such as the output pin of the line on the
* chip, a rail or a pin header name on a board, as specified by the gpio
- * chip, may be empty
+ * chip, may be empty (i.e. name[0] == '\0')
* @consumer: a functional name for the consumer of this GPIO line as set by
* whatever is using it, will be empty if there is no current user but may
* also be empty if the consumer doesn't set this up
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_info instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_info instead.
*/
struct gpioline_info {
__u32 line_offset;
* of a GPIO line
* @info: updated line information
* @timestamp: estimate of time of status change occurrence, in nanoseconds
- * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED
- * and GPIOLINE_CHANGED_CONFIG
+ * @event_type: one of %GPIOLINE_CHANGED_REQUESTED,
+ * %GPIOLINE_CHANGED_RELEASED and %GPIOLINE_CHANGED_CONFIG
+ * @padding: reserved for future use
*
- * Note: struct gpioline_info embedded here has 32-bit alignment on its own,
+ * The &struct gpioline_info embedded here has 32-bit alignment on its own,
* but it works fine with 64-bit alignment too. With its 72 byte size, we can
* guarantee there are no implicit holes between it and subsequent members.
* The 20-byte padding at the end makes sure we don't add any implicit padding
* at the end of the structure on 64-bit architectures.
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_info_changed instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_info_changed instead.
*/
struct gpioline_info_changed {
struct gpioline_info info;
* @lineoffsets: an array of desired lines, specified by offset index for the
* associated GPIO device
* @flags: desired flags for the desired GPIO lines, such as
- * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added
* together. Note that even if multiple lines are requested, the same flags
* must be applicable to all of them, if you want lines with individual
* flags set, request them one by one. It is possible to select
* a batch of input or output lines, but they must all have the same
* characteristics, i.e. all inputs or all outputs, all active low etc
- * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested
+ * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested
* line, this specifies the default output value, should be 0 (low) or
* 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
* @consumer_label: a desired consumer label for the selected GPIO line(s)
* @lines: number of lines requested in this request, i.e. the number of
* valid fields in the above arrays, set to 1 to request a single line
* @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
+ * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value
* means error
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_request instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_request instead.
*/
struct gpiohandle_request {
__u32 lineoffsets[GPIOHANDLES_MAX];
/**
* struct gpiohandle_config - Configuration for a GPIO handle request
* @flags: updated flags for the requested GPIO lines, such as
- * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed
+ * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added
* together
- * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set in flags,
+ * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags,
* this specifies the default output value, should be 0 (low) or
* 1 (high), anything else than 0 or 1 will be interpreted as 1 (high)
* @padding: reserved for future use and should be zero filled
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_config instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_config instead.
*/
struct gpiohandle_config {
__u32 flags;
* state of a line, when setting the state of lines these should contain
* the desired target state
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_values instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_values instead.
*/
struct gpiohandle_data {
__u8 values[GPIOHANDLES_MAX];
* @lineoffset: the desired line to subscribe to events from, specified by
* offset index for the associated GPIO device
* @handleflags: desired handle flags for the desired GPIO line, such as
- * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN
+ * %GPIOHANDLE_REQUEST_ACTIVE_LOW or %GPIOHANDLE_REQUEST_OPEN_DRAIN
* @eventflags: desired flags for the desired GPIO event line, such as
- * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE
+ * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE
* @consumer_label: a desired consumer label for the selected GPIO line(s)
* such as "my-listener"
* @fd: if successful this field will contain a valid anonymous file handle
- * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
+ * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value
* means error
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_request instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_request instead.
*/
struct gpioevent_request {
__u32 lineoffset;
int fd;
};
-/**
+/*
* GPIO event types
*/
#define GPIOEVENT_EVENT_RISING_EDGE 0x01
* @timestamp: best estimate of time of event occurrence, in nanoseconds
* @id: event identifier
*
- * This struct is part of ABI v1 and is deprecated.
- * Use struct gpio_v2_line_event instead.
+ * Note: This struct is part of ABI v1 and is deprecated.
+ * Use &struct gpio_v2_line_event instead.
*/
struct gpioevent_data {
__u64 timestamp;
#define ICMPV6_HDR_FIELD 0
#define ICMPV6_UNK_NEXTHDR 1
#define ICMPV6_UNK_OPTION 2
+#define ICMPV6_HDR_INCOMP 3
/*
* constants for (set|get)sockopt
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Intel MIC driver.
- *
- */
-#ifndef __MIC_COMMON_H_
-#define __MIC_COMMON_H_
-
-#include <linux/virtio_ring.h>
-
-#define __mic_align(a, x) (((a) + (x) - 1) & ~((x) - 1))
-
-/**
- * struct mic_device_desc: Virtio device information shared between the
- * virtio driver and userspace backend
- *
- * @type: Device type: console/network/disk etc. Type 0/-1 terminates.
- * @num_vq: Number of virtqueues.
- * @feature_len: Number of bytes of feature bits. Multiply by 2: one for
- host features and one for guest acknowledgements.
- * @config_len: Number of bytes of the config array after virtqueues.
- * @status: A status byte, written by the Guest.
- * @config: Start of the following variable length config.
- */
-struct mic_device_desc {
- __s8 type;
- __u8 num_vq;
- __u8 feature_len;
- __u8 config_len;
- __u8 status;
- __le64 config[0];
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_device_ctrl: Per virtio device information in the device page
- * used internally by the host and card side drivers.
- *
- * @vdev: Used for storing MIC vdev information by the guest.
- * @config_change: Set to 1 by host when a config change is requested.
- * @vdev_reset: Set to 1 by guest to indicate virtio device has been reset.
- * @guest_ack: Set to 1 by guest to ack a command.
- * @host_ack: Set to 1 by host to ack a command.
- * @used_address_updated: Set to 1 by guest when the used address should be
- * updated.
- * @c2h_vdev_db: The doorbell number to be used by guest. Set by host.
- * @h2c_vdev_db: The doorbell number to be used by host. Set by guest.
- */
-struct mic_device_ctrl {
- __le64 vdev;
- __u8 config_change;
- __u8 vdev_reset;
- __u8 guest_ack;
- __u8 host_ack;
- __u8 used_address_updated;
- __s8 c2h_vdev_db;
- __s8 h2c_vdev_db;
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_bootparam: Virtio device independent information in device page
- *
- * @magic: A magic value used by the card to ensure it can see the host
- * @h2c_config_db: Host to Card Virtio config doorbell set by card
- * @node_id: Unique id of the node
- * @h2c_scif_db - Host to card SCIF doorbell set by card
- * @c2h_scif_db - Card to host SCIF doorbell set by host
- * @scif_host_dma_addr - SCIF host queue pair DMA address
- * @scif_card_dma_addr - SCIF card queue pair DMA address
- */
-struct mic_bootparam {
- __le32 magic;
- __s8 h2c_config_db;
- __u8 node_id;
- __u8 h2c_scif_db;
- __u8 c2h_scif_db;
- __u64 scif_host_dma_addr;
- __u64 scif_card_dma_addr;
-} __attribute__ ((aligned(8)));
-
-/**
- * struct mic_device_page: High level representation of the device page
- *
- * @bootparam: The bootparam structure is used for sharing information and
- * status updates between MIC host and card drivers.
- * @desc: Array of MIC virtio device descriptors.
- */
-struct mic_device_page {
- struct mic_bootparam bootparam;
- struct mic_device_desc desc[0];
-};
-/**
- * struct mic_vqconfig: This is how we expect the device configuration field
- * for a virtqueue to be laid out in config space.
- *
- * @address: Guest/MIC physical address of the virtio ring
- * (avail and desc rings)
- * @used_address: Guest/MIC physical address of the used ring
- * @num: The number of entries in the virtio_ring
- */
-struct mic_vqconfig {
- __le64 address;
- __le64 used_address;
- __le16 num;
-} __attribute__ ((aligned(8)));
-
-/*
- * The alignment to use between consumer and producer parts of vring.
- * This is pagesize for historical reasons.
- */
-#define MIC_VIRTIO_RING_ALIGN 4096
-
-#define MIC_MAX_VRINGS 4
-#define MIC_VRING_ENTRIES 128
-
-/*
- * Max vring entries (power of 2) to ensure desc and avail rings
- * fit in a single page
- */
-#define MIC_MAX_VRING_ENTRIES 128
-
-/**
- * Max size of the desc block in bytes: includes:
- * - struct mic_device_desc
- * - struct mic_vqconfig (num_vq of these)
- * - host and guest features
- * - virtio device config space
- */
-#define MIC_MAX_DESC_BLK_SIZE 256
-
-/**
- * struct _mic_vring_info - Host vring info exposed to userspace backend
- * for the avail index and magic for the card.
- *
- * @avail_idx: host avail idx
- * @magic: A magic debug cookie.
- */
-struct _mic_vring_info {
- __u16 avail_idx;
- __le32 magic;
-};
-
-/**
- * struct mic_vring - Vring information.
- *
- * @vr: The virtio ring.
- * @info: Host vring information exposed to the userspace backend for the
- * avail index and magic for the card.
- * @va: The va for the buffer allocated for vr and info.
- * @len: The length of the buffer required for allocating vr and info.
- */
-struct mic_vring {
- struct vring vr;
- struct _mic_vring_info *info;
- void *va;
- int len;
-};
-
-#define mic_aligned_desc_size(d) __mic_align(mic_desc_size(d), 8)
-
-#ifndef INTEL_MIC_CARD
-static inline unsigned mic_desc_size(const struct mic_device_desc *desc)
-{
- return sizeof(*desc) + desc->num_vq * sizeof(struct mic_vqconfig)
- + desc->feature_len * 2 + desc->config_len;
-}
-
-static inline struct mic_vqconfig *
-mic_vq_config(const struct mic_device_desc *desc)
-{
- return (struct mic_vqconfig *)(desc + 1);
-}
-
-static inline __u8 *mic_vq_features(const struct mic_device_desc *desc)
-{
- return (__u8 *)(mic_vq_config(desc) + desc->num_vq);
-}
-
-static inline __u8 *mic_vq_configspace(const struct mic_device_desc *desc)
-{
- return mic_vq_features(desc) + desc->feature_len * 2;
-}
-static inline unsigned mic_total_desc_size(struct mic_device_desc *desc)
-{
- return mic_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl);
-}
-#endif
-
-/* Device page size */
-#define MIC_DP_SIZE 4096
-
-#define MIC_MAGIC 0xc0ffee00
-
-/**
- * enum mic_states - MIC states.
- */
-enum mic_states {
- MIC_READY = 0,
- MIC_BOOTING,
- MIC_ONLINE,
- MIC_SHUTTING_DOWN,
- MIC_RESETTING,
- MIC_RESET_FAILED,
- MIC_LAST
-};
-
-/**
- * enum mic_status - MIC status reported by card after
- * a host or card initiated shutdown or a card crash.
- */
-enum mic_status {
- MIC_NOP = 0,
- MIC_CRASHED,
- MIC_HALTED,
- MIC_POWER_OFF,
- MIC_RESTART,
- MIC_STATUS_LAST
-};
-
-#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution in
- * the file called "COPYING".
- *
- * Intel MIC Host driver.
- *
- */
-#ifndef _MIC_IOCTL_H_
-#define _MIC_IOCTL_H_
-
-#include <linux/types.h>
-
-/*
- * mic_copy - MIC virtio descriptor copy.
- *
- * @iov: An array of IOVEC structures containing user space buffers.
- * @iovcnt: Number of IOVEC structures in iov.
- * @vr_idx: The vring index.
- * @update_used: A non zero value results in used index being updated.
- * @out_len: The aggregate of the total length written to or read from
- * the virtio device.
- */
-struct mic_copy_desc {
-#ifdef __KERNEL__
- struct iovec __user *iov;
-#else
- struct iovec *iov;
-#endif
- __u32 iovcnt;
- __u8 vr_idx;
- __u8 update_used;
- __u32 out_len;
-};
-
-/*
- * Add a new virtio device
- * The (struct mic_device_desc *) pointer points to a device page entry
- * for the virtio device consisting of:
- * - struct mic_device_desc
- * - struct mic_vqconfig (num_vq of these)
- * - host and guest features
- * - virtio device config space
- * The total size referenced by the pointer should equal the size returned
- * by desc_size() in mic_common.h
- */
-#define MIC_VIRTIO_ADD_DEVICE _IOWR('s', 1, struct mic_device_desc *)
-
-/*
- * Copy the number of entries in the iovec and update the used index
- * if requested by the user.
- */
-#define MIC_VIRTIO_COPY_DESC _IOWR('s', 2, struct mic_copy_desc *)
-
-/*
- * Notify virtio device of a config change
- * The (__u8 *) pointer points to config space values for the device
- * as they should be written into the device page. The total size
- * referenced by the pointer should equal the config_len field of struct
- * mic_device_desc.
- */
-#define MIC_VIRTIO_CONFIG_CHANGE _IOWR('s', 5, __u8 *)
-
-#endif
__OVS_DEC_TTL_ATTR_MAX
};
+#define OVS_DEC_TTL_ATTR_MAX (__OVS_DEC_TTL_ATTR_MAX - 1)
+
#endif /* _LINUX_OPENVSWITCH_H */
* be of use to ordinary userspace programs such as GUIs or ls rather than
* specialised tools.
*
- * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
* semantically. Where possible, the numerical value is picked to correspond
- * also.
+ * also. Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state. It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
*/
#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */
#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */
#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
-#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */
+#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */
#endif /* _UAPI_LINUX_STAT_H */
/* Set event fd for config interrupt*/
#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
+ struct vhost_vdpa_iova_range)
#endif
__u8 buf[0];
};
+/* vhost vdpa IOVA range
+ * @first: First address that can be mapped by vhost-vDPA
+ * @last: Last address that can be mapped by vhost-vDPA
+ */
+struct vhost_vdpa_iova_range {
+ __u64 first;
+ __u64 last;
+};
+
/* Feature bits */
/* Log all write descriptors. Can be changed while device is active. */
#define VHOST_F_LOG_ALL 26
__u32 value[8];
} __attribute__((packed, aligned(4)));
-/**
+/*
* compress path ioctl definitions
* SNDRV_COMPRESS_GET_CAPS: Query capability of DSP
* SNDRV_COMPRESS_GET_CODEC_CAPS: Query capability of a codec
enum ipu_color_space ipu_drm_fourcc_to_colorspace(u32 drm_fourcc);
enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat);
-enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code);
-int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat);
-bool ipu_pixelformat_is_planar(u32 pixelformat);
int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees,
bool hflip, bool vflip);
int ipu_rot_mode_to_degrees(int *degrees, enum ipu_rotate_mode mode,
int
default $(shell,$(srctree)/scripts/clang-version.sh $(CC))
+config LLD_VERSION
+ int
+ default $(shell,$(srctree)/scripts/lld-version.sh $(LD))
+
config CC_CAN_LINK
bool
default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(m64-flag)) if 64BIT
with more CPUs. Therefore this value is used only when the sum of
contributions is greater than the half of the default kernel ring
buffer as defined by LOG_BUF_SHIFT. The default values are set
- so that more than 64 CPUs are needed to trigger the allocation.
+ so that more than 16 CPUs are needed to trigger the allocation.
Also this option is ignored when "log_buf_len" kernel parameter is
used as it forces an exact (power of two) size of the ring buffer.
present. This option is not well tested yet, so use at your
own risk.
+config LD_ORPHAN_WARN
+ def_bool y
+ depends on ARCH_WANT_LD_ORPHAN_WARN
+ depends on !LD_IS_LLD || LLD_VERSION >= 110000
+ depends on $(ld-option,--orphan-handling=warn)
+
config SYSCTL
bool
u32 size, csum;
char *data;
u32 *hdr;
+ int i;
if (!initrd_end)
return NULL;
data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN;
- if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
- return NULL;
+ /*
+ * Since Grub may align the size of initrd to 4, we must
+ * check the preceding 3 bytes as well.
+ */
+ for (i = 0; i < 4; i++) {
+ if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN))
+ goto found;
+ data--;
+ }
+ return NULL;
+found:
hdr = (u32 *)(data - 8);
- size = hdr[0];
- csum = hdr[1];
+ size = le32_to_cpu(hdr[0]);
+ csum = le32_to_cpu(hdr[1]);
data = ((void *)hdr) - size;
if ((unsigned long)data < initrd_start) {
# SPDX-License-Identifier: GPL-2.0
obj-y := core.o
-CFLAGS_core.o += $(call cc-disable-warning, override-init)
+ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
+# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
+cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
+endif
+CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
#include <linux/bpf_verifier.h>
#include <net/bpf_sk_storage.h>
#include <linux/bpf_local_storage.h>
+#include <linux/btf_ids.h>
/* For every LSM hook that allows attachment of BPF programs, declare a nop
* function where a BPF program can be attached.
#include <linux/lsm_hook_defs.h>
#undef LSM_HOOK
-#define BPF_LSM_SYM_PREFX "bpf_lsm_"
+#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME)
+BTF_SET_START(bpf_lsm_hooks)
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+BTF_SET_END(bpf_lsm_hooks)
int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
const struct bpf_prog *prog)
return -EINVAL;
}
- if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name,
- sizeof(BPF_LSM_SYM_PREFX) - 1)) {
+ if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) {
bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n",
prog->aux->attach_btf_id, prog->aux->attach_func_name);
return -EINVAL;
*
* Decode and execute eBPF instructions.
*/
-static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
{
#define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y
#define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
}
}
+static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr,
+ void *value, bool onallcpus)
+{
+ /* When using prealloc and not setting the initial value on all cpus,
+ * zero-fill element values for other cpus (just as what happens when
+ * not using prealloc). Otherwise, bpf program has no way to ensure
+ * known initial values for cpus other than current one
+ * (onallcpus=false always when coming from bpf prog).
+ */
+ if (htab_is_prealloc(htab) && !onallcpus) {
+ u32 size = round_up(htab->map.value_size, 8);
+ int current_cpu = raw_smp_processor_id();
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (cpu == current_cpu)
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value,
+ size);
+ else
+ memset(per_cpu_ptr(pptr, cpu), 0, size);
+ }
+ } else {
+ pcpu_copy_value(htab, pptr, value, onallcpus);
+ }
+}
+
static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab)
{
return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS &&
}
}
- pcpu_copy_value(htab, pptr, value, onallcpus);
+ pcpu_init_value(htab, pptr, value, onallcpus);
if (!prealloc)
htab_elem_set_ptr(l_new, key_size, pptr);
pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size),
value, onallcpus);
} else {
- pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size),
+ pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size),
value, onallcpus);
hlist_nulls_add_head_rcu(&l_new->hash_node, head);
l_new = NULL;
menuconfig BPF_PRELOAD
bool "Preload BPF file system with kernel specific program and map iterators"
depends on BPF
+ depends on BPF_SYSCALL
# The dependency on !COMPILE_TEST prevents it from being enabled
# in allmodconfig or allyesconfig configurations
depends on !COMPILE_TEST
struct tnum range = tnum_range(0, 1);
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
int err;
+ const bool is_subprog = env->cur_state->frame[0]->subprogno;
/* LSM and struct_ops func-ptr's return type could be "void" */
- if ((prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
+ if (!is_subprog &&
+ (prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
prog_type == BPF_PROG_TYPE_LSM) &&
!prog->aux->attach_func_proto->type)
return 0;
return -EACCES;
}
+ reg = cur_regs(env) + BPF_REG_0;
+ if (is_subprog) {
+ if (reg->type != SCALAR_VALUE) {
+ verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
+ reg_type_str[reg->type]);
+ return -EINVAL;
+ }
+ return 0;
+ }
+
switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
return 0;
}
- reg = cur_regs(env) + BPF_REG_0;
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
reg_type_str[reg->type]);
struct bpf_insn *insn,
struct bpf_insn_aux_data *aux)
{
- u32 datasec_id, type, id = insn->imm;
const struct btf_var_secinfo *vsi;
const struct btf_type *datasec;
const struct btf_type *t;
const char *sym_name;
bool percpu = false;
+ u32 type, id = insn->imm;
+ s32 datasec_id;
u64 addr;
int i;
}
#ifdef CONFIG_HOTPLUG_CPU
+#ifndef arch_clear_mm_cpumask_cpu
+#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
+#endif
+
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
t = find_lock_task_mm(p);
if (!t)
continue;
- cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
+ arch_clear_mm_cpumask_cpu(cpu, t->mm);
task_unlock(t);
}
rcu_read_unlock();
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
}
io_tlb_index = 0;
+ no_iotlb_memory = false;
if (verbose)
swiotlb_print_info();
if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
return;
- if (io_tlb_start)
+ if (io_tlb_start) {
memblock_free_early(io_tlb_start,
PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ io_tlb_start = 0;
+ }
pr_warn("Cannot allocate buffer");
no_iotlb_memory = true;
}
io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
}
io_tlb_index = 0;
+ no_iotlb_memory = false;
swiotlb_print_info();
}
}
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
- dma_addr_t tbl_dma_addr,
- phys_addr_t orig_addr,
- size_t mapping_size,
- size_t alloc_size,
- enum dma_data_direction dir,
- unsigned long attrs)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+ size_t mapping_size, size_t alloc_size,
+ enum dma_data_direction dir, unsigned long attrs)
{
+ dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
unsigned long flags;
phys_addr_t tlb_addr;
unsigned int nslots, stride, index, wrap;
trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
swiotlb_force);
- swiotlb_addr = swiotlb_tbl_map_single(dev,
- phys_to_dma_unencrypted(dev, io_tlb_start),
- paddr, size, size, dir, attrs);
+ swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+ attrs);
if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
* already contains a warning when RCU is not watching, so no point
* in having another one here.
*/
+ lockdep_hardirqs_off(CALLER_ADDR0);
instrumentation_begin();
rcu_irq_enter_check_tick();
- /* Use the combo lockdep/tracing function */
- trace_hardirqs_off();
+ trace_hardirqs_off_finish();
instrumentation_end();
return ret;
event_sched_out(event, cpuctx, ctx);
perf_pmu_enable(ctx->pmu);
-
- if (group_event->attr.exclusive)
- cpuctx->exclusive = 0;
}
#define DETACH_GROUP 0x01UL
pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
- if (event_sched_in(group_event, cpuctx, ctx)) {
- pmu->cancel_txn(pmu);
- perf_mux_hrtimer_restart(cpuctx);
- return -EAGAIN;
- }
+ if (event_sched_in(group_event, cpuctx, ctx))
+ goto error;
/*
* Schedule in siblings as one group (if any):
}
event_sched_out(group_event, cpuctx, ctx);
+error:
pmu->cancel_txn(pmu);
-
- perf_mux_hrtimer_restart(cpuctx);
-
return -EAGAIN;
}
* If this group is exclusive and there are already
* events on the CPU, it can't go on.
*/
- if (event->attr.exclusive && cpuctx->active_oncpu)
+ if (event->attr.exclusive && !list_empty(get_event_list(event)))
return 0;
/*
* Otherwise, try to add it if all previous groups were able
*can_add_hw = 0;
ctx->rotate_necessary = 1;
+ perf_mux_hrtimer_restart(cpuctx);
}
return 0;
}
static void perf_sample_regs_user(struct perf_regs *regs_user,
- struct pt_regs *regs,
- struct pt_regs *regs_user_copy)
+ struct pt_regs *regs)
{
if (user_mode(regs)) {
regs_user->abi = perf_reg_abi(current);
regs_user->regs = regs;
} else if (!(current->flags & PF_KTHREAD)) {
- perf_get_regs_user(regs_user, regs, regs_user_copy);
+ perf_get_regs_user(regs_user, regs);
} else {
regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
regs_user->regs = NULL;
}
if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
- perf_sample_regs_user(&data->regs_user, regs,
- &data->regs_user_copy);
+ perf_sample_regs_user(&data->regs_user, regs);
if (sample_type & PERF_SAMPLE_REGS_USER) {
/* regs dump ABI info */
struct perf_sample_data *data,
struct pt_regs *regs,
int (*output_begin)(struct perf_output_handle *,
+ struct perf_sample_data *,
struct perf_event *,
unsigned int))
{
perf_prepare_sample(&header, data, event, regs);
- err = output_begin(&handle, event, header.size);
+ err = output_begin(&handle, data, event, header.size);
if (err)
goto exit;
int ret;
perf_event_header__init_id(&read_event.header, &sample, event);
- ret = perf_output_begin(&handle, event, read_event.header.size);
+ ret = perf_output_begin(&handle, &sample, event, read_event.header.size);
if (ret)
return;
perf_event_header__init_id(&task_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
task_event->event_id.header.size);
if (ret)
goto out;
return;
perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
comm_event->event_id.header.size);
if (ret)
perf_event_header__init_id(&namespaces_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
namespaces_event->event_id.header.size);
if (ret)
goto out;
perf_event_header__init_id(&cgroup_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
cgroup_event->event_id.header.size);
if (ret)
goto out;
}
perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
mmap_event->event_id.header.size);
if (ret)
goto out;
int ret;
perf_event_header__init_id(&rec.header, &sample, event);
- ret = perf_output_begin(&handle, event, rec.header.size);
+ ret = perf_output_begin(&handle, &sample, event, rec.header.size);
if (ret)
return;
perf_event_header__init_id(&lost_samples_event.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
lost_samples_event.header.size);
if (ret)
return;
perf_event_header__init_id(&se->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event, se->event_id.header.size);
+ ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size);
if (ret)
return;
perf_event_header__init_id(&throttle_event.header, &sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
throttle_event.header.size);
if (ret)
return;
perf_event_header__init_id(&ksymbol_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, &sample, event,
ksymbol_event->event_id.header.size);
if (ret)
return;
perf_event_header__init_id(&bpf_event->event_id.header,
&sample, event);
- ret = perf_output_begin(&handle, event,
+ ret = perf_output_begin(&handle, data, event,
bpf_event->event_id.header.size);
if (ret)
return;
perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
- ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+ ret = perf_output_begin(&handle, &sample, event,
+ text_poke_event->event_id.header.size);
if (ret)
return;
rec.tid = perf_event_tid(event, current);
perf_event_header__init_id(&rec.header, &sample, event);
- ret = perf_output_begin(&handle, event, rec.header.size);
+ ret = perf_output_begin(&handle, &sample, event, rec.header.size);
if (ret)
return;
if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
int fpos = token == IF_SRC_FILE ? 2 : 1;
+ kfree(filename);
filename = match_strdup(&args[fpos]);
if (!filename) {
ret = -ENOMEM;
*/
ret = -EOPNOTSUPP;
if (!event->ctx->task)
- goto fail_free_name;
+ goto fail;
/* look up the path and grab its inode */
ret = kern_path(filename, LOOKUP_FOLLOW,
&filter->path);
if (ret)
- goto fail_free_name;
-
- kfree(filename);
- filename = NULL;
+ goto fail;
ret = -EINVAL;
if (!filter->path.dentry ||
if (state != IF_STATE_ACTION)
goto fail;
+ kfree(filename);
kfree(orig);
return 0;
-fail_free_name:
- kfree(filename);
fail:
+ kfree(filename);
free_filters_list(filters);
kfree(orig);
static inline int get_recursion_context(int *recursion)
{
- int rctx;
-
- if (unlikely(in_nmi()))
- rctx = 3;
- else if (in_irq())
- rctx = 2;
- else if (in_softirq())
- rctx = 1;
- else
- rctx = 0;
+ unsigned int pc = preempt_count();
+ unsigned char rctx = 0;
+
+ rctx += !!(pc & (NMI_MASK));
+ rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+ rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
if (recursion[rctx])
return -1;
static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size,
bool backward)
{
handle->size = (1UL << page_shift) - offset;
if (unlikely(have_lost)) {
- struct perf_sample_data sample_data;
-
lost_event.header.size = sizeof(lost_event);
lost_event.header.type = PERF_RECORD_LOST;
lost_event.header.misc = 0;
lost_event.id = event->id;
lost_event.lost = local_xchg(&rb->lost, 0);
- perf_event_header__init_id(&lost_event.header,
- &sample_data, event);
+ /* XXX mostly redundant; @data is already fully initializes */
+ perf_event_header__init_id(&lost_event.header, data, event);
perf_output_put(handle, lost_event);
- perf_event__output_id_sample(event, handle, &sample_data);
+ perf_event__output_id_sample(event, handle, data);
}
return 0;
}
int perf_output_begin_forward(struct perf_output_handle *handle,
- struct perf_event *event, unsigned int size)
+ struct perf_sample_data *data,
+ struct perf_event *event, unsigned int size)
{
- return __perf_output_begin(handle, event, size, false);
+ return __perf_output_begin(handle, data, event, size, false);
}
int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size)
{
- return __perf_output_begin(handle, event, size, true);
+ return __perf_output_begin(handle, data, event, size, true);
}
int perf_output_begin(struct perf_output_handle *handle,
+ struct perf_sample_data *data,
struct perf_event *event, unsigned int size)
{
- return __perf_output_begin(handle, event, size,
+ return __perf_output_begin(handle, data, event, size,
unlikely(is_write_backward(event)));
}
mmap_read_unlock(mm);
self.task = current;
- self.next = xchg(&core_state->dumper.next, &self);
+ if (self.task->flags & PF_SIGNALED)
+ self.next = xchg(&core_state->dumper.next, &self);
+ else
+ self.task = NULL;
/*
* Implies mb(), the result of xchg() must be visible
* to core_state->dumper.
if (copy_from_user(buf, buffer, count)) {
ret = -EFAULT;
- goto out;
+ goto out_free;
}
buf[count] = '\0';
sym = strstrip(buf);
ret = count;
}
out:
- kfree(buf);
mutex_unlock(&fei_lock);
+out_free:
+ kfree(buf);
return ret;
}
/* ok, now we should be set up.. */
p->pid = pid_nr(pid);
if (clone_flags & CLONE_THREAD) {
- p->exit_signal = -1;
p->group_leader = current->group_leader;
p->tgid = current->tgid;
} else {
- if (clone_flags & CLONE_PARENT)
- p->exit_signal = current->group_leader->exit_signal;
- else
- p->exit_signal = args->exit_signal;
p->group_leader = p;
p->tgid = p->pid;
}
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
+ if (clone_flags & CLONE_THREAD)
+ p->exit_signal = -1;
+ else
+ p->exit_signal = current->group_leader->exit_signal;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
+ p->exit_signal = args->exit_signal;
}
klp_copy_process(p);
*/
if (pi_state->owner) {
struct task_struct *owner;
+ unsigned long flags;
- raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
owner = pi_state->owner;
if (owner) {
raw_spin_lock(&owner->pi_lock);
raw_spin_unlock(&owner->pi_lock);
}
rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
- raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+ raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
}
if (current->pi_state_cache) {
*/
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- if (unlikely(should_fail_futex(true)))
+ if (unlikely(should_fail_futex(true))) {
ret = -EFAULT;
+ goto out_unlock;
+ }
ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
if (!ret && (curval != uval)) {
}
/*
- * Since we just failed the trylock; there must be an owner.
+ * The trylock just failed, so either there is an owner or
+ * there is a higher priority waiter than this one.
*/
newowner = rt_mutex_owner(&pi_state->pi_mutex);
- BUG_ON(!newowner);
+ /*
+ * If the higher priority waiter has not yet taken over the
+ * rtmutex then newowner is NULL. We can't return here with
+ * that state because it's inconsistent vs. the user space
+ * state. So drop the locks and try again. It's a valid
+ * situation and not any different from the other retry
+ * conditions.
+ */
+ if (unlikely(!newowner)) {
+ err = -EAGAIN;
+ goto handle_err;
+ }
} else {
WARN_ON_ONCE(argowner != current);
if (oldowner == current) {
* Process updating of timeout sysctl
*/
int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int ret;
# Generic IRQ IPI support
config GENERIC_IRQ_IPI
bool
+ select IRQ_DOMAIN_HIERARCHY
# Generic MSI interrupt support
config GENERIC_MSI_IRQ
EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
/**
- * irq_create_mapping() - Map a hardware interrupt into linux irq space
+ * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space
* @domain: domain owning this hardware interrupt or NULL for default domain
* @hwirq: hardware irq number in that domain space
+ * @affinity: irq affinity
*
* Only one mapping per hardware interrupt is permitted. Returns a linux
* irq number.
* If the sense/trigger is to be specified, set_irq_type() should be called
* on the number returned from that call.
*/
-unsigned int irq_create_mapping(struct irq_domain *domain,
- irq_hw_number_t hwirq)
+unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
+ irq_hw_number_t hwirq,
+ const struct irq_affinity_desc *affinity)
{
struct device_node *of_node;
int virq;
}
/* Allocate a virtual interrupt number */
- virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL);
+ virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node),
+ affinity);
if (virq <= 0) {
pr_debug("-> virq allocation failed\n");
return 0;
return virq;
}
-EXPORT_SYMBOL_GPL(irq_create_mapping);
+EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
/**
* irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs
*head = &kretprobe_inst_table[hash];
hlist_lock = kretprobe_table_lock_ptr(hash);
- raw_spin_lock_irqsave(hlist_lock, *flags);
+ /*
+ * Nested is a workaround that will soon not be needed.
+ * There's other protections that make sure the same lock
+ * is not taken on the same CPU that lockdep is unaware of.
+ * Differentiate when it is taken in NMI context.
+ */
+ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
}
NOKPROBE_SYMBOL(kretprobe_hash_lock);
__acquires(hlist_lock)
{
raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
- raw_spin_lock_irqsave(hlist_lock, *flags);
+ /*
+ * Nested is a workaround that will soon not be needed.
+ * There's other protections that make sure the same lock
+ * is not taken on the same CPU that lockdep is unaware of.
+ * Differentiate when it is taken in NMI context.
+ */
+ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi());
}
NOKPROBE_SYMBOL(kretprobe_table_lock);
/* TODO: consider to only swap the RA after the last pre_handler fired */
hash = hash_ptr(current, KPROBE_HASH_BITS);
- raw_spin_lock_irqsave(&rp->lock, flags);
+ /*
+ * Nested is a workaround that will soon not be needed.
+ * There's other protections that make sure the same lock
+ * is not taken on the same CPU that lockdep is unaware of.
+ */
+ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
if (!hlist_empty(&rp->free_instances)) {
ri = hlist_entry(rp->free_instances.first,
struct kretprobe_instance, hlist);
ri->task = current;
if (rp->entry_handler && rp->entry_handler(ri, regs)) {
- raw_spin_lock_irqsave(&rp->lock, flags);
+ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1);
hlist_add_head(&ri->hlist, &rp->free_instances);
raw_spin_unlock_irqrestore(&rp->lock, flags);
return 0;
/* Move the work from worker->delayed_work_list. */
WARN_ON_ONCE(list_empty(&work->node));
list_del_init(&work->node);
- kthread_insert_work(worker, work, &worker->work_list);
+ if (!work->canceling)
+ kthread_insert_work(worker, work, &worker->work_list);
raw_spin_unlock_irqrestore(&worker->lock, flags);
}
if (!debug_locks)
return false;
- if (raw_cpu_read(lockdep_recursion))
+ if (this_cpu_read(lockdep_recursion))
return false;
if (current->lockdep_recursion)
{
DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+ __this_cpu_inc(lockdep_recursion);
arch_spin_lock(&__lock);
__owner = current;
- __this_cpu_inc(lockdep_recursion);
}
static inline void lockdep_unlock(void)
{
+ DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
if (debug_locks && DEBUG_LOCKS_WARN_ON(__owner != current))
return;
- __this_cpu_dec(lockdep_recursion);
__owner = NULL;
arch_spin_unlock(&__lock);
+ __this_cpu_dec(lockdep_recursion);
}
static inline bool lockdep_assert_locked(void)
* (Note that this has to be done separately, because the graph cannot
* detect such classes of deadlocks.)
*
- * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
+ * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same
+ * lock class is held but nest_lock is also held, i.e. we rely on the
+ * nest_lock to avoid the deadlock.
*/
static int
check_deadlock(struct task_struct *curr, struct held_lock *next)
* lock class (i.e. read_lock(lock)+read_lock(lock)):
*/
if ((next->read == 2) && prev->read)
- return 2;
+ continue;
/*
* We're holding the nest_lock, which serializes this lock's
if (!ret)
return 0;
- /*
- * Mark recursive read, as we jump over it when
- * building dependencies (just like we jump over
- * trylock entries):
- */
- if (ret == 2)
- hlock->read = 2;
/*
* Add dependency only if this lock is not the head
- * of the chain, and if it's not a secondary read-lock:
+ * of the chain, and if the new lock introduces no more
+ * lock dependency (because we already hold a lock with the
+ * same lock class) nor deadlock (because the nest_lock
+ * serializes nesting locks), see the comments for
+ * check_deadlock().
*/
if (!chain_head && ret != 2) {
if (!check_prevs_add(curr, hlock))
if (unlikely(in_nmi()))
return;
- if (unlikely(__this_cpu_read(lockdep_recursion)))
+ if (unlikely(this_cpu_read(lockdep_recursion)))
return;
if (unlikely(lockdep_hardirqs_enabled())) {
goto skip_checks;
}
- if (unlikely(__this_cpu_read(lockdep_recursion)))
+ if (unlikely(this_cpu_read(lockdep_recursion)))
return;
if (lockdep_hardirqs_enabled()) {
if (unlikely(hlock_class(this)->usage_mask & new_mask))
goto unlock;
+ if (!hlock_class(this)->usage_mask)
+ debug_atomic_dec(nr_unused_locks);
+
hlock_class(this)->usage_mask |= new_mask;
if (new_bit < LOCK_TRACE_STATES) {
return 0;
}
- switch (new_bit) {
- case 0 ... LOCK_USED-1:
+ if (new_bit < LOCK_USED) {
ret = mark_lock_irq(curr, this, new_bit);
if (!ret)
return 0;
- break;
-
- case LOCK_USED:
- debug_atomic_dec(nr_unused_locks);
- break;
-
- default:
- break;
}
unlock:
panic("panic_on_warn set ...\n");
}
- dump_stack();
+ if (!regs)
+ dump_stack();
print_irqtrace_events(current);
{
unsigned int num;
struct attribute_group grp;
- struct param_attribute attrs[0];
+ struct param_attribute attrs[];
};
#ifdef CONFIG_SYSFS
BUG_ON(in_atomic());
/*
- * Now that the whole userspace is frozen we need to disbale
+ * Now that the whole userspace is frozen we need to disable
* the OOM killer to disallow any further interference with
* killable tasks. There is no guarantee oom victims will
* ever reach a point they go away we have to wait with a timeout.
if (dev_info)
memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));
- /* insert message */
- if ((flags & LOG_CONT) || !(flags & LOG_NEWLINE))
+ /* A message without a trailing newline can be continued. */
+ if (!(flags & LOG_NEWLINE))
prb_commit(&e);
else
prb_final_commit(&e);
*/
struct prb_data_block {
unsigned long id;
- char data[0];
+ char data[];
};
/*
head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */
do {
- desc = to_desc(desc_ring, head_id);
-
id = DESC_ID(head_id + 1);
id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id);
return ret;
}
-static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns,
- unsigned int mode)
+static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
{
- int ret;
-
if (mode & PTRACE_MODE_NOAUDIT)
- ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT);
- else
- ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE);
-
- return ret == 0;
+ return ns_capable_noaudit(ns, CAP_SYS_PTRACE);
+ return ns_capable(ns, CAP_SYS_PTRACE);
}
/* Returns 0 on success, -errno on denial. */
gid_eq(caller_gid, tcred->sgid) &&
gid_eq(caller_gid, tcred->gid))
goto ok;
- if (ptrace_has_cap(cred, tcred->user_ns, mode))
+ if (ptrace_has_cap(tcred->user_ns, mode))
goto ok;
rcu_read_unlock();
return -EPERM;
mm = task->mm;
if (mm &&
((get_dumpable(mm) != SUID_DUMP_USER) &&
- !ptrace_has_cap(cred, mm->user_ns, mode)))
+ !ptrace_has_cap(mm->user_ns, mode)))
return -EPERM;
return security_ptrace_access_check(task, mode);
*
* The caller must have disabled interrupts and must not be idle.
*/
-void rcu_momentary_dyntick_idle(void)
+notrace void rcu_momentary_dyntick_idle(void)
{
int special;
smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
}
-#ifdef CONFIG_HOTPLUG_CPU
/*
* The outgoing function has no further need of RCU, so remove it from
* the rcu_node tree's ->qsmaskinitnext bit masks.
rdp->cpu_started = false;
}
+#ifdef CONFIG_HOTPLUG_CPU
/*
* The outgoing CPU has just passed through the dying-idle state, and we
* are being invoked from the CPU that was IPIed to continue the offline
/*
* Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
+ * sections, printing out the tid of each of the first few of them.
*/
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
+ __releases(rnp->lock)
{
+ int i = 0;
int ndetected = 0;
struct rcu_stall_chk_rdr rscr;
struct task_struct *t;
+ struct task_struct *ts[8];
if (!rcu_preempt_blocked_readers_cgp(rnp))
return 0;
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+ get_task_struct(t);
+ ts[i++] = t;
+ if (i >= ARRAY_SIZE(ts))
+ break;
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ for (i--; i; i--) {
+ t = ts[i];
if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
pr_cont(" P%d", t->pid);
else
".q"[rscr.rs.b.need_qs],
".e"[rscr.rs.b.exp_hint],
".l"[rscr.on_blkd_list]);
+ put_task_struct(t);
ndetected++;
}
pr_cont("\n");
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
{
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return 0;
}
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- ndetected += rcu_print_task_stall(rnp);
if (rnp->qsmask != 0) {
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
ndetected++;
}
}
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
}
for_each_possible_cpu(cpu)
break;
case 's':
- {
- int rc;
-
- if (isdigit(*(str+1))) {
- rc = kstrtoint(str+1, 0, &reboot_cpu);
- if (rc)
- return rc;
- } else if (str[1] == 'm' && str[2] == 'p' &&
- isdigit(*(str+3))) {
- rc = kstrtoint(str+3, 0, &reboot_cpu);
- if (rc)
- return rc;
- } else
+ if (isdigit(*(str+1)))
+ reboot_cpu = simple_strtoul(str+1, NULL, 0);
+ else if (str[1] == 'm' && str[2] == 'p' &&
+ isdigit(*(str+3)))
+ reboot_cpu = simple_strtoul(str+3, NULL, 0);
+ else
*mode = REBOOT_SOFT;
+ if (reboot_cpu >= num_possible_cpus()) {
+ pr_err("Ignoring the CPU number in reboot= option. "
+ "CPU %d exceeds possible cpu number %d\n",
+ reboot_cpu, num_possible_cpus());
+ reboot_cpu = 0;
+ break;
+ }
break;
- }
+
case 'g':
*mode = REBOOT_GPIO;
break;
#ifdef CONFIG_SMP
if (wake_flags & WF_MIGRATED)
en_flags |= ENQUEUE_MIGRATED;
+ else
#endif
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
activate_task(rq, p, en_flags);
ttwu_do_wakeup(rq, p, wake_flags, rf);
if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
goto unlock;
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&task_rq(p)->nr_iowait);
- }
-
#ifdef CONFIG_SMP
/*
* Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
wake_flags |= WF_MIGRATED;
psi_ttwu_dequeue(p);
set_task_cpu(p, cpu);
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_prio(pi_task->prio) &&
dl_entity_preempt(&pi_task->dl, &p->dl))) {
- p->dl.dl_boosted = 1;
+ p->dl.pi_se = pi_task->dl.pi_se;
queue_flag |= ENQUEUE_REPLENISH;
- } else
- p->dl.dl_boosted = 0;
+ } else {
+ p->dl.pi_se = &p->dl;
+ }
p->sched_class = &dl_sched_class;
} else if (rt_prio(prio)) {
if (dl_prio(oldprio))
- p->dl.dl_boosted = 0;
+ p->dl.pi_se = &p->dl;
if (oldprio < prio)
queue_flag |= ENQUEUE_HEAD;
p->sched_class = &rt_sched_class;
} else {
if (dl_prio(oldprio))
- p->dl.dl_boosted = 0;
+ p->dl.pi_se = &p->dl;
if (rt_prio(oldprio))
p->rt.timeout = 0;
p->sched_class = &fair_sched_class;
static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
unsigned int next_freq)
{
- if (sg_policy->next_freq == next_freq)
- return false;
+ if (!sg_policy->need_freq_update) {
+ if (sg_policy->next_freq == next_freq)
+ return false;
+ } else {
+ sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+ }
sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
return sg_policy->next_freq;
- sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = freq;
return cpufreq_driver_resolve_freq(policy, freq);
}
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
unsigned long util, max;
unsigned int next_f;
- bool busy;
unsigned int cached_freq = sg_policy->cached_raw_freq;
sugov_iowait_boost(sg_cpu, time, flags);
if (!sugov_should_update_freq(sg_policy, time))
return;
- /* Limits may have changed, don't skip frequency update */
- busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
-
util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
util = sugov_iowait_apply(sg_cpu, time, util, max);
* Do not reduce the frequency if the CPU has not been idle
* recently, as the reduction is likely to be premature then.
*/
- if (busy && next_f < sg_policy->next_freq) {
+ if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
next_f = sg_policy->next_freq;
/* Restore cached freq as next_freq has changed */
sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
sg_policy->limits_changed = false;
- sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
+ sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
+
for_each_cpu(cpu, policy->cpus) {
struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
struct cpufreq_governor schedutil_gov = {
.name = "schedutil",
.owner = THIS_MODULE,
- .dynamic_switching = true,
+ .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING,
.init = sugov_init,
.exit = sugov_exit,
.start = sugov_start,
return !RB_EMPTY_NODE(&dl_se->rb_node);
}
+#ifdef CONFIG_RT_MUTEXES
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+ return dl_se->pi_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+ return pi_of(dl_se) != dl_se;
+}
+#else
+static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
+{
+ return dl_se;
+}
+
+static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_SMP
static inline struct dl_bw *dl_bw_of(int i)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
- WARN_ON(dl_se->dl_boosted);
+ WARN_ON(is_dl_boosted(dl_se));
WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
/*
* could happen are, typically, a entity voluntarily trying to overcome its
* runtime, or it just underestimated it during sched_setattr().
*/
-static void replenish_dl_entity(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
- BUG_ON(pi_se->dl_runtime <= 0);
+ BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
/*
* This could be the case for a !-dl task that is boosted.
* Just go with full inherited parameters.
*/
if (dl_se->dl_deadline == 0) {
- dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
- dl_se->runtime = pi_se->dl_runtime;
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
}
if (dl_se->dl_yielded && dl_se->runtime > 0)
* arbitrary large.
*/
while (dl_se->runtime <= 0) {
- dl_se->deadline += pi_se->dl_period;
- dl_se->runtime += pi_se->dl_runtime;
+ dl_se->deadline += pi_of(dl_se)->dl_period;
+ dl_se->runtime += pi_of(dl_se)->dl_runtime;
}
/*
*/
if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
printk_deferred_once("sched: DL replenish lagged too much\n");
- dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
- dl_se->runtime = pi_se->dl_runtime;
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
}
if (dl_se->dl_yielded)
* task with deadline equal to period this is the same of using
* dl_period instead of dl_deadline in the equation above.
*/
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
{
u64 left, right;
* of anything below microseconds resolution is actually fiction
* (but still we want to give the user that illusion >;).
*/
- left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
right = ((dl_se->deadline - t) >> DL_SCALE) *
- (pi_se->dl_runtime >> DL_SCALE);
+ (pi_of(dl_se)->dl_runtime >> DL_SCALE);
return dl_time_before(right, left);
}
* Please refer to the comments update_dl_revised_wakeup() function to find
* more about the Revised CBS rule.
*/
-static void update_dl_entity(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
- dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+ dl_entity_overflow(dl_se, rq_clock(rq))) {
if (unlikely(!dl_is_implicit(dl_se) &&
!dl_time_before(dl_se->deadline, rq_clock(rq)) &&
- !dl_se->dl_boosted)){
+ !is_dl_boosted(dl_se))) {
update_dl_revised_wakeup(dl_se, rq);
return;
}
- dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
- dl_se->runtime = pi_se->dl_runtime;
+ dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
+ dl_se->runtime = pi_of(dl_se)->dl_runtime;
}
}
* The task might have been boosted by someone else and might be in the
* boosting/deboosting path, its not throttled.
*/
- if (dl_se->dl_boosted)
+ if (is_dl_boosted(dl_se))
goto unlock;
/*
* but do not enqueue -- wait for our wakeup to do that.
*/
if (!task_on_rq_queued(p)) {
- replenish_dl_entity(dl_se, dl_se);
+ replenish_dl_entity(dl_se);
goto unlock;
}
if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
- if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+ if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
return;
dl_se->dl_throttled = 1;
if (dl_se->runtime > 0)
dl_se->dl_overrun = 1;
__dequeue_task_dl(rq, curr, 0);
- if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr)))
+ if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
if (!is_leftmost(curr, &rq->dl))
}
static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se,
- struct sched_dl_entity *pi_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
{
BUG_ON(on_dl_rq(dl_se));
*/
if (flags & ENQUEUE_WAKEUP) {
task_contending(dl_se, flags);
- update_dl_entity(dl_se, pi_se);
+ update_dl_entity(dl_se);
} else if (flags & ENQUEUE_REPLENISH) {
- replenish_dl_entity(dl_se, pi_se);
+ replenish_dl_entity(dl_se);
} else if ((flags & ENQUEUE_RESTORE) &&
dl_time_before(dl_se->deadline,
rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
- struct task_struct *pi_task = rt_mutex_get_top_task(p);
- struct sched_dl_entity *pi_se = &p->dl;
-
- /*
- * Use the scheduling parameters of the top pi-waiter task if:
- * - we have a top pi-waiter which is a SCHED_DEADLINE task AND
- * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is
- * smaller than our deadline OR we are a !SCHED_DEADLINE task getting
- * boosted due to a SCHED_DEADLINE pi-waiter).
- * Otherwise we keep our runtime and deadline.
- */
- if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) {
- pi_se = &pi_task->dl;
+ if (is_dl_boosted(&p->dl)) {
/*
* Because of delays in the detection of the overrun of a
* thread's runtime, it might be the case that a thread
* the throttle.
*/
p->dl.dl_throttled = 0;
- BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+ BUG_ON(!is_dl_boosted(&p->dl) || flags != ENQUEUE_REPLENISH);
return;
}
return;
}
- enqueue_dl_entity(&p->dl, pi_se, flags);
+ enqueue_dl_entity(&p->dl, flags);
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_dl_task(rq, p);
dl_se->dl_bw = 0;
dl_se->dl_density = 0;
- dl_se->dl_boosted = 0;
dl_se->dl_throttled = 0;
dl_se->dl_yielded = 0;
dl_se->dl_non_contending = 0;
dl_se->dl_overrun = 0;
+
+#ifdef CONFIG_RT_MUTEXES
+ dl_se->pi_se = dl_se;
+#endif
}
bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
unsigned long flags = *(unsigned long *)table->data;
size_t data_size = 0;
size_t len = 0;
- char *tmp;
+ char *tmp, *buf;
int idx;
if (write)
return 0;
}
- tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL);
- if (!tmp)
+ buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL);
+ if (!buf)
return -ENOMEM;
for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
char *name = sd_flag_debug[idx].name;
- len += snprintf(tmp + len, strlen(name) + 2, "%s ", name);
+ len += snprintf(buf + len, strlen(name) + 2, "%s ", name);
}
- tmp += *ppos;
+ tmp = buf + *ppos;
len -= *ppos;
if (len > *lenp)
*lenp = len;
*ppos += len;
- kfree(tmp);
+ kfree(buf);
return 0;
}
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
int idle_h_nr_running = task_has_idle_policy(p);
+ int task_new = !(flags & ENQUEUE_WAKEUP);
/*
* The code below (indirectly) updates schedutil which looks at
* into account, but that is not straightforward to implement,
* and the following generally works well enough in practice.
*/
- if (flags & ENQUEUE_WAKEUP)
+ if (!task_new)
update_overutilized_status(rq);
enqueue_throttle:
static int
select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
{
- unsigned long best_cap = 0;
+ unsigned long task_util, best_cap = 0;
int cpu, best_cpu = -1;
struct cpumask *cpus;
- sync_entity_load_avg(&p->se);
-
cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
+ task_util = uclamp_task_util(p);
+
for_each_cpu_wrap(cpu, cpus, target) {
unsigned long cpu_cap = capacity_of(cpu);
if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
continue;
- if (task_fits_capacity(p, cpu_cap))
+ if (fits_capacity(task_util, cpu_cap))
return cpu;
if (cpu_cap > best_cap) {
return best_cpu;
}
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+ if (static_branch_unlikely(&sched_asym_cpucapacity))
+ return fits_capacity(task_util, capacity_of(cpu));
+
+ return true;
+}
+
/*
* Try and locate an idle core/thread in the LLC cache domain.
*/
static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
struct sched_domain *sd;
+ unsigned long task_util;
int i, recent_used_cpu;
/*
- * For asymmetric CPU capacity systems, our domain of interest is
- * sd_asym_cpucapacity rather than sd_llc.
+ * On asymmetric system, update task utilization because we will check
+ * that the task fits with cpu's capacity.
*/
if (static_branch_unlikely(&sched_asym_cpucapacity)) {
- sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
- /*
- * On an asymmetric CPU capacity system where an exclusive
- * cpuset defines a symmetric island (i.e. one unique
- * capacity_orig value through the cpuset), the key will be set
- * but the CPUs within that cpuset will not have a domain with
- * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
- * capacity path.
- */
- if (!sd)
- goto symmetric;
-
- i = select_idle_capacity(p, sd, target);
- return ((unsigned)i < nr_cpumask_bits) ? i : target;
+ sync_entity_load_avg(&p->se);
+ task_util = uclamp_task_util(p);
}
-symmetric:
- if (available_idle_cpu(target) || sched_idle_cpu(target))
+ if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+ asym_fits_capacity(task_util, target))
return target;
/*
* If the previous CPU is cache affine and idle, don't be stupid:
*/
if (prev != target && cpus_share_cache(prev, target) &&
- (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+ (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+ asym_fits_capacity(task_util, prev))
return prev;
/*
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
(available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
- cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+ asym_fits_capacity(task_util, recent_used_cpu)) {
/*
* Replace recent_used_cpu with prev as it is a potential
* candidate for the next wake:
return recent_used_cpu;
}
+ /*
+ * For asymmetric CPU capacity systems, our domain of interest is
+ * sd_asym_cpucapacity rather than sd_llc.
+ */
+ if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+ /*
+ * On an asymmetric CPU capacity system where an exclusive
+ * cpuset defines a symmetric island (i.e. one unique
+ * capacity_orig value through the cpuset), the key will be set
+ * but the CPUs within that cpuset will not have a domain with
+ * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+ * capacity path.
+ */
+ if (sd) {
+ i = select_idle_capacity(p, sd, target);
+ return ((unsigned)i < nr_cpumask_bits) ? i : target;
+ }
+ }
+
sd = rcu_dereference(per_cpu(sd_llc, target));
if (!sd)
return target;
* emptying busiest.
*/
if (local->group_type == group_has_spare) {
- if (busiest->group_type > group_fully_busy) {
+ if ((busiest->group_type > group_fully_busy) &&
+ !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
/*
* If busiest is overloaded, try to fill spare
* capacity. This might end up creating spare capacity
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
- local_irq_enable();
+ raw_local_irq_enable();
}
/**
trace_cpu_idle(1, smp_processor_id());
stop_critical_timings();
+
+ /*
+ * arch_cpu_idle() is supposed to enable IRQs, however
+ * we can't do that because of RCU and tracing.
+ *
+ * Trace IRQs enable here, then switch off RCU, and have
+ * arch_cpu_idle() use raw_local_irq_enable(). Note that
+ * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+ * last -- this is very similar to the entry code.
+ */
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(_THIS_IP_);
rcu_idle_enter();
+ lockdep_hardirqs_on(_THIS_IP_);
+
arch_cpu_idle();
+
+ /*
+ * OK, so IRQs are enabled here, but RCU needs them disabled to
+ * turn itself back on.. funny thing is that disabling IRQs
+ * will cause tracing, which needs RCU. Jump through hoops to
+ * make it 'work'.
+ */
+ raw_local_irq_disable();
+ lockdep_hardirqs_off(_THIS_IP_);
rcu_idle_exit();
+ lockdep_hardirqs_on(_THIS_IP_);
+ raw_local_irq_enable();
+
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
#include <linux/filter.h>
#include <linux/pid.h>
#include <linux/ptrace.h>
-#include <linux/security.h>
+#include <linux/capability.h>
#include <linux/tracehook.h>
#include <linux/uaccess.h>
#include <linux/anon_inodes.h>
* behavior of privileged children.
*/
if (!task_no_new_privs(current) &&
- security_capable(current_cred(), current_user_ns(),
- CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) != 0)
+ !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
return ERR_PTR(-EACCES);
/* Allocate a new seccomp_filter */
void task_join_group_stop(struct task_struct *task)
{
+ unsigned long mask = current->jobctl & JOBCTL_STOP_SIGMASK;
+ struct signal_struct *sig = current->signal;
+
+ if (sig->group_stop_count) {
+ sig->group_stop_count++;
+ mask |= JOBCTL_STOP_CONSUME;
+ } else if (!(sig->flags & SIGNAL_STOP_STOPPED))
+ return;
+
/* Have the new thread join an on-going signal group stop */
- unsigned long jobctl = current->jobctl;
- if (jobctl & JOBCTL_STOP_PENDING) {
- struct signal_struct *sig = current->signal;
- unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
- unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
- if (task_set_jobctl_pending(task, signr | gstop)) {
- sig->group_stop_count++;
- }
- }
+ task_set_jobctl_pending(task, mask | JOBCTL_STOP_PENDING);
}
/*
set_state(msdata, msdata->state + 1);
}
-void __weak stop_machine_yield(const struct cpumask *cpumask)
+notrace void __weak stop_machine_yield(const struct cpumask *cpumask)
{
cpu_relax();
}
debug_object_deactivate(timer, &hrtimer_debug_descr);
}
-static inline void debug_hrtimer_free(struct hrtimer *timer)
-{
- debug_object_free(timer, &hrtimer_debug_descr);
-}
-
static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
enum hrtimer_mode mode);
u64 oval, nval, ointerval, ninterval;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
- /*
- * Use the to_ktime conversion because that clamps the maximum
- * value to KTIME_MAX and avoid multiplication overflows.
- */
nval = timespec64_to_ns(&value->it_value);
ninterval = timespec64_to_ns(&value->it_interval);
return (cyc * mult) >> shift;
}
-struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
+notrace struct clock_read_data *sched_clock_read_begin(unsigned int *seq)
{
*seq = raw_read_seqcount_latch(&cd.seq);
return cd.read_data + (*seq & 1);
}
-int sched_clock_read_retry(unsigned int seq)
+notrace int sched_clock_read_retry(unsigned int seq)
{
return read_seqcount_latch_retry(&cd.seq, seq);
}
debug_object_deactivate(timer, &timer_debug_descr);
}
-static inline void debug_timer_free(struct timer_list *timer)
-{
- debug_object_free(timer, &timer_debug_descr);
-}
-
static inline void debug_timer_assert_init(struct timer_list *timer)
{
debug_object_assert_init(timer, &timer_debug_descr);
config DYNAMIC_FTRACE_WITH_DIRECT_CALLS
def_bool y
- depends on DYNAMIC_FTRACE
+ depends on DYNAMIC_FTRACE_WITH_REGS
depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
config FUNCTION_PROFILER
{
int ret;
+ /*
+ * NB: We rely on strncpy_from_user() not copying junk past the NUL
+ * terminator into `dst`.
+ *
+ * strncpy_from_user() does long-sized strides in the fast path. If the
+ * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`,
+ * then there could be junk after the NUL in `dst`. If user takes `dst`
+ * and keys a hash map with it, then semantically identical strings can
+ * occupy multiple entries in the map.
+ */
ret = strncpy_from_user_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
memset(dst, 0, size);
*btf = bpf_get_btf_vmlinux();
if (IS_ERR_OR_NULL(*btf))
- return PTR_ERR(*btf);
+ return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL;
if (ptr->type_id > 0)
*btf_id = ptr->type_id;
static struct ftrace_ops *
ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
static struct ftrace_ops *
+ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude);
+static struct ftrace_ops *
ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
* to it.
*/
if (ftrace_rec_count(rec) == 1 &&
- ftrace_find_tramp_ops_any(rec))
+ ftrace_find_tramp_ops_any_other(rec, ops))
rec->flags |= FTRACE_FL_TRAMP;
else
rec->flags &= ~FTRACE_FL_TRAMP;
return NULL;
}
+static struct ftrace_ops *
+ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude)
+{
+ struct ftrace_ops *op;
+ unsigned long ip = rec->ip;
+
+ do_for_each_ftrace_op(op, ftrace_ops_list) {
+
+ if (op == op_exclude || !op->trampoline)
+ continue;
+
+ if (hash_contains_ip(ip, op->func_hash))
+ return op;
+ } while_for_each_ftrace_op(op);
+
+ return NULL;
+}
+
static struct ftrace_ops *
ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
struct ftrace_ops *op)
};
/*
* Used for which event context the event is in.
- * NMI = 0
- * IRQ = 1
- * SOFTIRQ = 2
- * NORMAL = 3
+ * TRANSITION = 0
+ * NMI = 1
+ * IRQ = 2
+ * SOFTIRQ = 3
+ * NORMAL = 4
*
* See trace_recursive_lock() comment below for more details.
*/
enum {
+ RB_CTX_TRANSITION,
RB_CTX_NMI,
RB_CTX_IRQ,
RB_CTX_SOFTIRQ,
* a bit of overhead in something as critical as function tracing,
* we use a bitmask trick.
*
- * bit 0 = NMI context
- * bit 1 = IRQ context
- * bit 2 = SoftIRQ context
- * bit 3 = normal context.
+ * bit 1 = NMI context
+ * bit 2 = IRQ context
+ * bit 3 = SoftIRQ context
+ * bit 4 = normal context.
*
* This works because this is the order of contexts that can
* preempt other contexts. A SoftIRQ never preempts an IRQ
* The least significant bit can be cleared this way, and it
* just so happens that it is the same bit corresponding to
* the current context.
+ *
+ * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit
+ * is set when a recursion is detected at the current context, and if
+ * the TRANSITION bit is already set, it will fail the recursion.
+ * This is needed because there's a lag between the changing of
+ * interrupt context and updating the preempt count. In this case,
+ * a false positive will be found. To handle this, one extra recursion
+ * is allowed, and this is done by the TRANSITION bit. If the TRANSITION
+ * bit is already set, then it is considered a recursion and the function
+ * ends. Otherwise, the TRANSITION bit is set, and that bit is returned.
+ *
+ * On the trace_recursive_unlock(), the TRANSITION bit will be the first
+ * to be cleared. Even if it wasn't the context that set it. That is,
+ * if an interrupt comes in while NORMAL bit is set and the ring buffer
+ * is called before preempt_count() is updated, since the check will
+ * be on the NORMAL bit, the TRANSITION bit will then be set. If an
+ * NMI then comes in, it will set the NMI bit, but when the NMI code
+ * does the trace_recursive_unlock() it will clear the TRANSTION bit
+ * and leave the NMI bit set. But this is fine, because the interrupt
+ * code that set the TRANSITION bit will then clear the NMI bit when it
+ * calls trace_recursive_unlock(). If another NMI comes in, it will
+ * set the TRANSITION bit and continue.
+ *
+ * Note: The TRANSITION bit only handles a single transition between context.
*/
static __always_inline int
bit = pc & NMI_MASK ? RB_CTX_NMI :
pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;
- if (unlikely(val & (1 << (bit + cpu_buffer->nest))))
- return 1;
+ if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) {
+ /*
+ * It is possible that this was called by transitioning
+ * between interrupt context, and preempt_count() has not
+ * been updated yet. In this case, use the TRANSITION bit.
+ */
+ bit = RB_CTX_TRANSITION;
+ if (val & (1 << (bit + cpu_buffer->nest)))
+ return 1;
+ }
val |= (1 << (bit + cpu_buffer->nest));
cpu_buffer->current_context = val;
cpu_buffer->current_context - (1 << cpu_buffer->nest);
}
-/* The recursive locking above uses 4 bits */
-#define NESTED_BITS 4
+/* The recursive locking above uses 5 bits */
+#define NESTED_BITS 5
/**
* ring_buffer_nest_start - Allow to trace while nested
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE)) {
- if (tail != w) {
- /* before and after may now different, fix it up*/
- b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
- a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
- if (a_ok && b_ok && info->before != info->after)
- (void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
- info->before, info->after);
- }
+ /* before and after may now different, fix it up*/
+ b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
+ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+ if (a_ok && b_ok && info->before != info->after)
+ (void)rb_time_cmpxchg(&cpu_buffer->before_stamp,
+ info->before, info->after);
return rb_move_tail(cpu_buffer, tail, info);
}
ts = rb_time_stamp(cpu_buffer->buffer);
barrier();
/*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
- info->after < ts) {
+ info->after < ts &&
+ rb_time_cmpxchg(&cpu_buffer->write_stamp,
+ info->after, ts)) {
/* Nothing came after this event between C and E */
info->delta = ts - info->after;
- (void)rb_time_cmpxchg(&cpu_buffer->write_stamp,
- info->after, info->ts);
info->ts = ts;
} else {
/*
/*
* If tracing is off, but we have triggers enabled
* we still need to look at the event data. Use the temp_buffer
- * to store the trace event for the tigger to use. It's recusive
+ * to store the trace event for the trigger to use. It's recursive
* safe and will not be recorded anywhere.
*/
if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) {
stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
/* This should never happen. If it does, yell once and skip */
- if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+ if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING))
goto out;
/*
/* Interrupts must see nesting incremented before we use the buffer */
barrier();
- return &buffer->buffer[buffer->nesting][0];
+ return &buffer->buffer[buffer->nesting - 1][0];
}
static void put_trace_buf(void)
}
#define STATIC_TEMP_BUF_SIZE 128
-static char static_temp_buf[STATIC_TEMP_BUF_SIZE];
+static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4);
/* Find the next real entry, without updating the iterator itself */
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
* function is called to clear it.
*/
TRACE_GRAPH_NOTRACE_BIT,
+
+ /*
+ * When transitioning between context, the preempt_count() may
+ * not be correct. Allow for a single recursion to cover this case.
+ */
+ TRACE_TRANSITION_BIT,
};
#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0)
return 0;
bit = trace_get_context_bit() + start;
- if (unlikely(val & (1 << bit)))
- return -1;
+ if (unlikely(val & (1 << bit))) {
+ /*
+ * It could be that preempt_count has not been updated during
+ * a switch between contexts. Allow for a single recursion.
+ */
+ bit = TRACE_TRANSITION_BIT;
+ if (trace_recursion_test(bit))
+ return -1;
+ trace_recursion_set(bit);
+ barrier();
+ return bit + 1;
+ }
+
+ /* Normal check passed, clear the transition to allow it again */
+ trace_recursion_clear(TRACE_TRANSITION_BIT);
val |= 1 << bit;
current->trace_recursion = val;
barrier();
- return bit;
+ return bit + 1;
}
static __always_inline void trace_clear_recursion(int bit)
if (!bit)
return;
+ bit--;
bit = 1 << bit;
val &= ~bit;
{
struct synth_field *field;
const char *prefix = NULL, *field_type = argv[0], *field_name, *array;
- int len, ret = 0;
+ int len, ret = -ENOMEM;
+ struct seq_buf s;
ssize_t size;
if (field_type[0] == ';')
len--;
field->name = kmemdup_nul(field_name, len, GFP_KERNEL);
- if (!field->name) {
- ret = -ENOMEM;
+ if (!field->name)
goto free;
- }
+
if (!is_good_name(field->name)) {
synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name));
ret = -EINVAL;
field_type++;
len = strlen(field_type) + 1;
- if (array) {
- int l = strlen(array);
+ if (array)
+ len += strlen(array);
- if (l && array[l - 1] == ';')
- l--;
- len += l;
- }
if (prefix)
len += strlen(prefix);
field->type = kzalloc(len, GFP_KERNEL);
- if (!field->type) {
- ret = -ENOMEM;
+ if (!field->type)
goto free;
- }
+
+ seq_buf_init(&s, field->type, len);
if (prefix)
- strcat(field->type, prefix);
- strcat(field->type, field_type);
+ seq_buf_puts(&s, prefix);
+ seq_buf_puts(&s, field_type);
if (array) {
- strcat(field->type, array);
- if (field->type[len - 1] == ';')
- field->type[len - 1] = '\0';
+ seq_buf_puts(&s, array);
+ if (s.buffer[s.len - 1] == ';')
+ s.len--;
}
+ if (WARN_ON_ONCE(!seq_buf_buffer_left(&s)))
+ goto free;
+
+ s.buffer[s.len] = '\0';
size = synth_field_size(field->type);
if (size < 0) {
if (synth_field_is_string(field->type)) {
char *type;
- type = kzalloc(sizeof("__data_loc ") + strlen(field->type) + 1, GFP_KERNEL);
- if (!type) {
- ret = -ENOMEM;
+ len = sizeof("__data_loc ") + strlen(field->type) + 1;
+ type = kzalloc(len, GFP_KERNEL);
+ if (!type)
goto free;
- }
- strcat(type, "__data_loc ");
- strcat(type, field->type);
+ seq_buf_init(&s, type, len);
+ seq_buf_puts(&s, "__data_loc ");
+ seq_buf_puts(&s, field->type);
+
+ if (WARN_ON_ONCE(!seq_buf_buffer_left(&s)))
+ goto free;
+ s.buffer[s.len] = '\0';
+
kfree(field->type);
field->type = type;
struct task_struct *kthread;
int next_cpu;
- if (WARN_ON(hwlat_kthread))
+ if (hwlat_kthread)
return 0;
/* Just pick the first CPU on first iteration */
unregister_ftrace_function(&test_rec_probe);
ret = -1;
- if (trace_selftest_recursion_cnt != 1) {
- pr_cont("*callback not called once (%d)* ",
+ /*
+ * Recursion allows for transitions between context,
+ * and may call the callback twice.
+ */
+ if (trace_selftest_recursion_cnt != 1 &&
+ trace_selftest_recursion_cnt != 2) {
+ pr_cont("*callback not called once (or twice) (%d)* ",
trace_selftest_recursion_cnt);
goto out;
}
*/
struct tp_probes {
struct rcu_head rcu;
- struct tracepoint_func probes[0];
+ struct tracepoint_func probes[];
};
static inline void *allocate_probes(int count)
int __read_mostly watchdog_thresh = 10;
static int __read_mostly nmi_watchdog_available;
-static struct cpumask watchdog_allowed_mask __read_mostly;
-
struct cpumask watchdog_cpumask __read_mostly;
unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
int __read_mostly sysctl_softlockup_all_cpu_backtrace;
#endif
+static struct cpumask watchdog_allowed_mask __read_mostly;
+
/* Global variables, exported for sysctl */
unsigned int __read_mostly softlockup_panic =
CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
endmenu # "Kernel Testing and Coverage"
+source "Documentation/Kconfig"
+
endmenu # Kernel hacking
/* reduce OS noise */
local_irq_save(flags);
- local_irq_disable();
nsec = ktime_get_ns();
for (i = 0; i < 100; i++) {
nsec = ktime_get_ns() - nsec;
local_irq_restore(flags);
- local_irq_enable();
pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
/* reduce OS noise */
local_irq_save(flags);
- local_irq_disable();
nsec = ktime_get_ns();
for (i = 0; i < 100; i++) {
nsec = ktime_get_ns() - nsec;
local_irq_restore(flags);
- local_irq_enable();
pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
CRC_LE_BITS, CRC_BE_BITS);
#define FONTDATAMAX 9216
-static struct font_data fontdata_10x18 = {
+static const struct font_data fontdata_10x18 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, 0x00, /* 0000000000 */
#define FONTDATAMAX 2560
-static struct font_data fontdata_6x10 = {
+static const struct font_data fontdata_6x10 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
#define FONTDATAMAX (11*256)
-static struct font_data fontdata_6x11 = {
+static const struct font_data fontdata_6x11 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
#define FONTDATAMAX 2048
-static struct font_data fontdata_6x8 = {
+static const struct font_data fontdata_6x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 000000 */
#define FONTDATAMAX 3584
-static struct font_data fontdata_7x14 = {
+static const struct font_data fontdata_7x14 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 0000000 */
#define FONTDATAMAX 4096
-static struct font_data fontdata_8x16 = {
+static const struct font_data fontdata_8x16 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
#define FONTDATAMAX 2048
-static struct font_data fontdata_8x8 = {
+static const struct font_data fontdata_8x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
#define FONTDATAMAX 2048
-static struct font_data acorndata_8x8 = {
+static const struct font_data acorndata_8x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */
/* 01 */ 0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */
#define FONTDATAMAX 1536
-static struct font_data fontdata_mini_4x6 = {
+static const struct font_data fontdata_mini_4x6 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/*{*/
/* Char 0: ' ' */
#define FONTDATAMAX 2048
-static struct font_data fontdata_pearl8x8 = {
+static const struct font_data fontdata_pearl8x8 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, /* 00000000 */
#define FONTDATAMAX 11264
-static struct font_data fontdata_sun12x22 = {
+static const struct font_data fontdata_sun12x22 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* 0 0x00 '^@' */
0x00, 0x00, /* 000000000000 */
#define FONTDATAMAX 4096
-static struct font_data fontdata_sun8x16 = {
+static const struct font_data fontdata_sun8x16 = {
{ 0, 0, FONTDATAMAX, 0 }, {
/* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,
/* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00,
#define FONTDATAMAX 16384
-static struct font_data fontdata_ter16x32 = {
+static const struct font_data fontdata_ter16x32 = {
{ 0, 0, FONTDATAMAX, 0 }, {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc,
sg_miter_start(&miter, sgl, nents, sg_flags);
if (!sg_miter_skip(&miter, skip))
- return false;
+ return 0;
while ((offset < buflen) && sg_miter_next(&miter)) {
unsigned int len;
goto byte_at_a_time;
while (max >= sizeof(unsigned long)) {
- unsigned long c, data;
+ unsigned long c, data, mask;
/* Fall back to byte-at-a-time if we get a page fault */
unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
- *(unsigned long *)(dst+res) = c;
+ /*
+ * Note that we mask out the bytes following the NUL. This is
+ * important to do because string oblivious code may read past
+ * the NUL. For those routines, we don't want to give them
+ * potentially random bytes after the NUL in `src`.
+ *
+ * One example of such code is BPF map keys. BPF treats map keys
+ * as an opaque set of bytes. Without the post-NUL mask, any BPF
+ * maps keyed by strings returned from strncpy_from_user() may
+ * have multiple entries for semantically identical strings.
+ */
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
data = create_zero_mask(data);
+ mask = zero_bytemask(data);
+ *(unsigned long *)(dst+res) = c & mask;
return res + find_zero(data);
}
+
+ *(unsigned long *)(dst+res) = c;
+
res += sizeof(unsigned long);
max -= sizeof(unsigned long);
}
static int collect_syscall(struct task_struct *target, struct syscall_info *info)
{
+ unsigned long args[6] = { };
struct pt_regs *regs;
if (!try_get_task_stack(target)) {
info->data.nr = syscall_get_nr(target, regs);
if (info->data.nr != -1L)
- syscall_get_arguments(target, regs,
- (unsigned long *)&info->data.args[0]);
+ syscall_get_arguments(target, regs, args);
+
+ info->data.args[0] = args[0];
+ info->data.args[1] = args[1];
+ info->data.args[2] = args[2];
+ info->data.args[3] = args[3];
+ info->data.args[4] = args[4];
+ info->data.args[5] = args[5];
put_task_stack(target);
return 0;
u64 words[2];
} *ptr1, *ptr2;
+ /* This test is specifically crafted for the generic mode. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+ return;
+ }
+
ptr1 = kmalloc(sizeof(*ptr1) - 3, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
kfree(ptr2);
}
+static void kmalloc_uaf_16(struct kunit *test)
+{
+ struct {
+ u64 words[2];
+ } *ptr1, *ptr2;
+
+ ptr1 = kmalloc(sizeof(*ptr1), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr1);
+
+ ptr2 = kmalloc(sizeof(*ptr2), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2);
+ kfree(ptr2);
+
+ KUNIT_EXPECT_KASAN_FAIL(test, *ptr1 = *ptr2);
+ kfree(ptr1);
+}
+
static void kmalloc_oob_memset_2(struct kunit *test)
{
char *ptr;
volatile int i = 3;
char *p = &global_array[ARRAY_SIZE(global_array) + i];
+ /* Only generic mode instruments globals. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
KUNIT_EXPECT_KASAN_FAIL(test, *(volatile char *)p);
}
char alloca_array[i];
char *p = alloca_array - 1;
+ /* Only generic mode instruments dynamic allocas. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
return;
char alloca_array[i];
char *p = alloca_array + i;
+ /* Only generic mode instruments dynamic allocas. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required");
+ return;
+ }
+
if (!IS_ENABLED(CONFIG_KASAN_STACK)) {
kunit_info(test, "CONFIG_KASAN_STACK is not enabled");
return;
return;
}
+ if (OOB_TAG_OFF)
+ size = round_up(size, OOB_TAG_OFF);
+
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
return;
}
+ if (OOB_TAG_OFF)
+ size = round_up(size, OOB_TAG_OFF);
+
ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
memset(arr, 0, sizeof(arr));
KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = strnlen(ptr, 1));
}
-static void kasan_bitops(struct kunit *test)
+static void kasan_bitops_modify(struct kunit *test, int nr, void *addr)
+{
+ KUNIT_EXPECT_KASAN_FAIL(test, set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(nr, addr));
+}
+
+static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr)
+{
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_set_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_set_bit_lock(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_clear_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr));
+ KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr));
+
+#if defined(clear_bit_unlock_is_negative_byte)
+ KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result =
+ clear_bit_unlock_is_negative_byte(nr, addr));
+#endif
+}
+
+static void kasan_bitops_generic(struct kunit *test)
{
+ long *bits;
+
+ /* This test is specifically crafted for the generic mode. */
+ if (!IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_GENERIC required\n");
+ return;
+ }
+
/*
* Allocate 1 more byte, which causes kzalloc to round up to 16-bytes;
* this way we do not actually corrupt other memory.
*/
- long *bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
+ bits = kzalloc(sizeof(*bits) + 1, GFP_KERNEL);
KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
/*
* below accesses are still out-of-bounds, since bitops are defined to
* operate on the whole long the bit is in.
*/
- KUNIT_EXPECT_KASAN_FAIL(test, set_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __set_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, clear_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, clear_bit_unlock(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __clear_bit_unlock(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, change_bit(BITS_PER_LONG, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test, __change_bit(BITS_PER_LONG, bits));
+ kasan_bitops_modify(test, BITS_PER_LONG, bits);
/*
* Below calls try to access bit beyond allocated memory.
*/
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_set_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
-
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_set_bit_lock(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, bits);
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ kfree(bits);
+}
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_clear_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+static void kasan_bitops_tags(struct kunit *test)
+{
+ long *bits;
- KUNIT_EXPECT_KASAN_FAIL(test,
- test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* This test is specifically crafted for the tag-based mode. */
+ if (IS_ENABLED(CONFIG_KASAN_GENERIC)) {
+ kunit_info(test, "CONFIG_KASAN_SW_TAGS required\n");
+ return;
+ }
- KUNIT_EXPECT_KASAN_FAIL(test,
- __test_and_change_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* Allocation size will be rounded to up granule size, which is 16. */
+ bits = kzalloc(sizeof(*bits), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_ERR_OR_NULL(test, bits);
- KUNIT_EXPECT_KASAN_FAIL(test,
- kasan_int_result =
- test_bit(BITS_PER_LONG + BITS_PER_BYTE, bits));
+ /* Do the accesses past the 16 allocated bytes. */
+ kasan_bitops_modify(test, BITS_PER_LONG, &bits[1]);
+ kasan_bitops_test_and_modify(test, BITS_PER_LONG + BITS_PER_BYTE, &bits[1]);
-#if defined(clear_bit_unlock_is_negative_byte)
- KUNIT_EXPECT_KASAN_FAIL(test,
- kasan_int_result = clear_bit_unlock_is_negative_byte(
- BITS_PER_LONG + BITS_PER_BYTE, bits));
-#endif
kfree(bits);
}
KUNIT_CASE(kmalloc_oob_krealloc_more),
KUNIT_CASE(kmalloc_oob_krealloc_less),
KUNIT_CASE(kmalloc_oob_16),
+ KUNIT_CASE(kmalloc_uaf_16),
KUNIT_CASE(kmalloc_oob_in_memset),
KUNIT_CASE(kmalloc_oob_memset_2),
KUNIT_CASE(kmalloc_oob_memset_4),
KUNIT_CASE(kasan_memchr),
KUNIT_CASE(kasan_memcmp),
KUNIT_CASE(kasan_strings),
- KUNIT_CASE(kasan_bitops),
+ KUNIT_CASE(kasan_bitops_generic),
+ KUNIT_CASE(kasan_bitops_tags),
KUNIT_CASE(kmalloc_double_kzfree),
KUNIT_CASE(vmalloc_oob),
{}
#include "dfltcc_util.h"
#include "dfltcc.h"
#include <asm/setup.h>
+#include <linux/export.h>
#include <linux/zutil.h>
/*
return is_bit_set(dfltcc_state->af.fns, DFLTCC_XPND) &&
is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0);
}
+EXPORT_SYMBOL(dfltcc_can_inflate);
static int dfltcc_was_inflate_used(
z_streamp strm
return (cc == DFLTCC_CC_OP1_TOO_SHORT || cc == DFLTCC_CC_OP2_TOO_SHORT) ?
DFLTCC_INFLATE_BREAK : DFLTCC_INFLATE_CONTINUE;
}
+EXPORT_SYMBOL(dfltcc_inflate);
returned by an alloc(). This handle must be mapped in order to
access the allocated space.
-config ZSMALLOC_PGTABLE_MAPPING
- bool "Use page table mapping to access object in zsmalloc"
- depends on ZSMALLOC=y
- help
- By default, zsmalloc uses a copy-based object mapping method to
- access allocations that span two pages. However, if a particular
- architecture (ex, ARM) performs VM mapping faster than copying,
- then you should select this. This causes zsmalloc to use page table
- mapping rather than copying for object mapping.
-
- You can check speed with zsmalloc benchmark:
- https://github.com/spartacus06/zsmapbench
-
config ZSMALLOC_STAT
bool "Export zsmalloc statistics"
depends on ZSMALLOC
* delay for some time until fewer pages are isolated
*/
while (unlikely(too_many_isolated(pgdat))) {
+ /* stop isolation if there are still pages not migrated */
+ if (cc->nr_migratepages)
+ return 0;
+
/* async migration should just abort */
if (cc->mode == MIGRATE_ASYNC)
return 0;
isolate_success:
list_add(&page->lru, &cc->migratepages);
- cc->nr_migratepages++;
- nr_isolated++;
+ cc->nr_migratepages += compound_nr(page);
+ nr_isolated += compound_nr(page);
/*
* Avoid isolating too much unless this block is being
* or a lock is contended. For contention, isolate quickly to
* potentially remove one source of contention.
*/
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX &&
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
!cc->rescan && !cc->contended) {
++low_pfn;
break;
if (!pfn)
break;
- if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+ if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX)
break;
}
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
-noinline int __add_to_page_cache_locked(struct page *page,
+static noinline int __add_to_page_cache_locked(struct page *page,
struct address_space *mapping,
pgoff_t offset, gfp_t gfp,
void **shadowp)
rotate_reclaimable_page(page);
}
+ /*
+ * Writeback does not hold a page reference of its own, relying
+ * on truncation to wait for the clearing of PG_writeback.
+ * But here we must make sure that the page is not freed and
+ * reused before the wake_up_page().
+ */
+ get_page(page);
if (!test_clear_page_writeback(page))
BUG();
smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
+ put_page(page);
}
EXPORT_SYMBOL(end_page_writeback);
page_not_up_to_date:
/* Get exclusive access to the page ... */
- if (iocb->ki_flags & IOCB_WAITQ)
+ if (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
error = lock_page_async(page, iocb->ki_waitq);
- else
+ } else {
error = lock_page_killable(page);
+ }
if (unlikely(error))
goto readpage_error;
}
if (!PageUptodate(page)) {
- if (iocb->ki_flags & IOCB_WAITQ)
+ if (iocb->ki_flags & IOCB_WAITQ) {
+ if (written) {
+ put_page(page);
+ goto out;
+ }
error = lock_page_async(page, iocb->ki_waitq);
- else
+ } else {
error = lock_page_killable(page);
+ }
if (unlikely(error))
goto readpage_error;
/*
* drop the above get_user_pages reference.
*/
- for (i = 0; i < nr_pages; i++)
- put_page(pages[i]);
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, nr_pages);
+ else
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
if (migrate_pages(&cma_page_list, alloc_migration_target, NULL,
(unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) {
goto out;
if (check_dax_vmas(vmas_tmp, rc)) {
- for (i = 0; i < rc; i++)
- put_page(pages[i]);
+ if (gup_flags & FOLL_PIN)
+ unpin_user_pages(pages, rc);
+ else
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
rc = -EOPNOTSUPP;
goto out;
}
transparent_hugepage_use_zero_page()) {
pgtable_t pgtable;
struct page *zero_page;
- bool set;
vm_fault_t ret;
pgtable = pte_alloc_one(vma->vm_mm);
if (unlikely(!pgtable))
}
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
ret = 0;
- set = false;
if (pmd_none(*vmf->pmd)) {
ret = check_stable_address_space(vma->vm_mm);
if (ret) {
spin_unlock(vmf->ptl);
+ pte_free(vma->vm_mm, pgtable);
} else if (userfaultfd_missing(vma)) {
spin_unlock(vmf->ptl);
+ pte_free(vma->vm_mm, pgtable);
ret = handle_userfault(vmf, VM_UFFD_MISSING);
VM_BUG_ON(ret & VM_FAULT_FALLBACK);
} else {
set_huge_zero_page(pgtable, vma->vm_mm, vma,
haddr, vmf->pmd, zero_page);
spin_unlock(vmf->ptl);
- set = true;
}
- } else
+ } else {
spin_unlock(vmf->ptl);
- if (!set)
pte_free(vma->vm_mm, pgtable);
+ }
return ret;
}
gfp = alloc_hugepage_direct_gfpmask(vma);
}
del += t - f;
+ hugetlb_cgroup_uncharge_file_region(
+ resv, rg, t - f);
/* New entry for end of split region */
nrg->from = t;
/* Original entry is trimmed */
rg->to = f;
- hugetlb_cgroup_uncharge_file_region(
- resv, rg, nrg->to - nrg->from);
-
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
}
if (f <= rg->from) { /* Trim beginning of region */
- del += t - rg->from;
- rg->from = t;
-
hugetlb_cgroup_uncharge_file_region(resv, rg,
t - rg->from);
- } else { /* Trim end of region */
- del += rg->to - f;
- rg->to = f;
+ del += t - rg->from;
+ rg->from = t;
+ } else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
rg->to - f);
+
+ del += rg->to - f;
+ rg->to = f;
}
}
return page_head[1].compound_dtor == HUGETLB_PAGE_DTOR;
}
-/*
- * Find address_space associated with hugetlbfs page.
- * Upon entry page is locked and page 'was' mapped although mapped state
- * could change. If necessary, use anon_vma to find vma and associated
- * address space. The returned mapping may be stale, but it can not be
- * invalid as page lock (which is held) is required to destroy mapping.
- */
-static struct address_space *_get_hugetlb_page_mapping(struct page *hpage)
-{
- struct anon_vma *anon_vma;
- pgoff_t pgoff_start, pgoff_end;
- struct anon_vma_chain *avc;
- struct address_space *mapping = page_mapping(hpage);
-
- /* Simple file based mapping */
- if (mapping)
- return mapping;
-
- /*
- * Even anonymous hugetlbfs mappings are associated with an
- * underlying hugetlbfs file (see hugetlb_file_setup in mmap
- * code). Find a vma associated with the anonymous vma, and
- * use the file pointer to get address_space.
- */
- anon_vma = page_lock_anon_vma_read(hpage);
- if (!anon_vma)
- return mapping; /* NULL */
-
- /* Use first found vma */
- pgoff_start = page_to_pgoff(hpage);
- pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1;
- anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root,
- pgoff_start, pgoff_end) {
- struct vm_area_struct *vma = avc->vma;
-
- mapping = vma->vm_file->f_mapping;
- break;
- }
-
- anon_vma_unlock_read(anon_vma);
- return mapping;
-}
-
/*
* Find and lock address space (mapping) in write mode.
*
- * Upon entry, the page is locked which allows us to find the mapping
- * even in the case of an anon page. However, locking order dictates
- * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs
- * specific. So, we first try to lock the sema while still holding the
- * page lock. If this works, great! If not, then we need to drop the
- * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of
- * course, need to revalidate state along the way.
+ * Upon entry, the page is locked which means that page_mapping() is
+ * stable. Due to locking order, we can only trylock_write. If we can
+ * not get the lock, simply return NULL to caller.
*/
struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage)
{
- struct address_space *mapping, *mapping2;
+ struct address_space *mapping = page_mapping(hpage);
- mapping = _get_hugetlb_page_mapping(hpage);
-retry:
if (!mapping)
return mapping;
- /*
- * If no contention, take lock and return
- */
if (i_mmap_trylock_write(mapping))
return mapping;
- /*
- * Must drop page lock and wait on mapping sema.
- * Note: Once page lock is dropped, mapping could become invalid.
- * As a hack, increase map count until we lock page again.
- */
- atomic_inc(&hpage->_mapcount);
- unlock_page(hpage);
- i_mmap_lock_write(mapping);
- lock_page(hpage);
- atomic_add_negative(-1, &hpage->_mapcount);
-
- /* verify page is still mapped */
- if (!page_mapped(hpage)) {
- i_mmap_unlock_write(mapping);
- return NULL;
- }
-
- /*
- * Get address space again and verify it is the same one
- * we locked. If not, drop lock and retry.
- */
- mapping2 = _get_hugetlb_page_mapping(hpage);
- if (mapping2 != mapping) {
- i_mmap_unlock_write(mapping);
- mapping = mapping2;
- goto retry;
- }
-
- return mapping;
+ return NULL;
}
pgoff_t __basepage_index(struct page *page)
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
+ if (deferred_reserve)
+ hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h),
+ pages_per_huge_page(h), page);
}
return page;
for (idx = 0; idx < hugetlb_max_hstate; idx++) {
if (page_counter_read(
- hugetlb_cgroup_counter_from_cgroup(h_cg, idx)) ||
- page_counter_read(hugetlb_cgroup_counter_from_cgroup_rsvd(
- h_cg, idx))) {
+ hugetlb_cgroup_counter_from_cgroup(h_cg, idx)))
return true;
- }
}
return false;
}
struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
struct hstate *h;
struct page *page;
- int idx = 0;
+ int idx;
do {
+ idx = 0;
for_each_hstate(h) {
spin_lock(&hugetlb_lock);
list_for_each_entry(page, &h->hugepage_activelist, lru)
struct list_lru_node *nlru = &lru->node[nid];
int dst_idx = dst_memcg->kmemcg_id;
struct list_lru_one *src, *dst;
- bool set;
/*
* Since list_lru_{add,del} may be called under an IRQ-safe lock,
dst = list_lru_from_memcg_idx(nlru, dst_idx);
list_splice_init(&src->list, &dst->list);
- set = (!dst->nr_items && src->nr_items);
- dst->nr_items += src->nr_items;
- if (set)
+
+ if (src->nr_items) {
+ dst->nr_items += src->nr_items;
memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru));
- src->nr_items = 0;
+ src->nr_items = 0;
+ }
spin_unlock_irq(&nlru->lock);
}
struct address_space *mapping)
{
XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start));
- pgoff_t end_index = end / PAGE_SIZE;
+ pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1);
struct page *page;
rcu_read_lock();
ret = total_len - iov_iter_count(&iter);
mmput(mm);
- return ret;
-
release_task:
put_task_struct(task);
put_pid:
rcu_read_lock();
memcg = mem_cgroup_from_obj(p);
- /* Untracked pages have no memcg, no lruvec. Update only the node */
- if (!memcg || memcg == root_mem_cgroup) {
+ /*
+ * Untracked pages have no memcg, no lruvec. Update only the
+ * node. If we reparent the slab objects to the root memcg,
+ * when we free the slab object, we need to update the per-memcg
+ * vmstats to keep it correct for the root memcg.
+ */
+ if (!memcg) {
__mod_node_page_state(pgdat, idx, val);
} else {
lruvec = mem_cgroup_lruvec(memcg, pgdat);
(u64)memsw * PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
+ unsigned long nr;
+
if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
continue;
+ nr = memcg_page_state(memcg, memcg1_stats[i]);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (memcg1_stats[i] == NR_ANON_THPS)
+ nr *= HPAGE_PMD_NR;
+#endif
seq_printf(m, "total_%s %llu\n", memcg1_stat_names[i],
- (u64)memcg_page_state(memcg, memcg1_stats[i]) *
- PAGE_SIZE);
+ (u64)nr * PAGE_SIZE);
}
for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
memcg->swappiness = mem_cgroup_swappiness(parent);
memcg->oom_kill_disable = parent->oom_kill_disable;
}
- if (parent && parent->use_hierarchy) {
+ if (!parent) {
+ page_counter_init(&memcg->memory, NULL);
+ page_counter_init(&memcg->swap, NULL);
+ page_counter_init(&memcg->kmem, NULL);
+ page_counter_init(&memcg->tcpmem, NULL);
+ } else if (parent->use_hierarchy) {
memcg->use_hierarchy = true;
page_counter_init(&memcg->memory, &parent->memory);
page_counter_init(&memcg->swap, &parent->swap);
page_counter_init(&memcg->kmem, &parent->kmem);
page_counter_init(&memcg->tcpmem, &parent->tcpmem);
} else {
- page_counter_init(&memcg->memory, NULL);
- page_counter_init(&memcg->swap, NULL);
- page_counter_init(&memcg->kmem, NULL);
- page_counter_init(&memcg->tcpmem, NULL);
+ page_counter_init(&memcg->memory, &root_mem_cgroup->memory);
+ page_counter_init(&memcg->swap, &root_mem_cgroup->swap);
+ page_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+ page_counter_init(&memcg->tcpmem, &root_mem_cgroup->tcpmem);
/*
* Deeper hierachy with use_hierarchy == false doesn't make
* much sense so let cgroup subsystem know about this
if (!PageHuge(hpage)) {
unmap_success = try_to_unmap(hpage, ttu);
} else {
- /*
- * For hugetlb pages, try_to_unmap could potentially call
- * huge_pmd_unshare. Because of this, take semaphore in
- * write mode here and set TTU_RMAP_LOCKED to indicate we
- * have taken the lock at this higer level.
- *
- * Note that the call to hugetlb_page_mapping_lock_write
- * is necessary even if mapping is already set. It handles
- * ugliness of potentially having to drop page lock to obtain
- * i_mmap_rwsem.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
-
- if (mapping) {
- unmap_success = try_to_unmap(hpage,
+ if (!PageAnon(hpage)) {
+ /*
+ * For hugetlb pages in shared mappings, try_to_unmap
+ * could potentially call huge_pmd_unshare. Because of
+ * this, take semaphore in write mode here and set
+ * TTU_RMAP_LOCKED to indicate we have taken the lock
+ * at this higer level.
+ */
+ mapping = hugetlb_page_mapping_lock_write(hpage);
+ if (mapping) {
+ unmap_success = try_to_unmap(hpage,
ttu|TTU_RMAP_LOCKED);
- i_mmap_unlock_write(mapping);
+ i_mmap_unlock_write(mapping);
+ } else {
+ pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
+ unmap_success = false;
+ }
} else {
- pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n",
- pfn);
- unmap_success = false;
+ unmap_success = try_to_unmap(hpage, ttu);
}
}
if (!unmap_success)
return err;
}
-#ifdef CONFIG_NUMA
-int __weak memory_add_physaddr_to_nid(u64 start)
-{
- pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
- start);
- return 0;
-}
-EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
-
-int __weak phys_to_target_node(u64 start)
-{
- pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
- start);
- return 0;
-}
-EXPORT_SYMBOL_GPL(phys_to_target_node);
-#endif
-
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
unsigned long start_pfn,
unsigned long flags = qp->flags;
int ret;
bool has_unmovable = false;
- pte_t *pte;
+ pte_t *pte, *mapped_pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
if (pmd_trans_unstable(pmd))
return 0;
- pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
if (!pte_present(*pte))
continue;
} else
break;
}
- pte_unmap_unlock(pte - 1, ptl);
+ pte_unmap_unlock(mapped_pte, ptl);
cond_resched();
if (has_unmovable)
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
EXPORT_SYMBOL(devmap_managed_key);
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
- static_branch_dec(&devmap_managed_key);
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_dec(&devmap_managed_key);
}
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
- (!pgmap->ops || !pgmap->ops->page_free)) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- static_branch_inc(&devmap_managed_key);
- return 0;
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
+ pgmap->type == MEMORY_DEVICE_FS_DAX)
+ static_branch_inc(&devmap_managed_key);
}
#else
-static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
+static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
{
- return -EINVAL;
}
-static void devmap_managed_enable_put(void)
+static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
{
}
#endif /* CONFIG_DEV_PAGEMAP_OPS */
pageunmap_range(pgmap, i);
WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
- devmap_managed_enable_put();
+ devmap_managed_enable_put(pgmap);
}
EXPORT_SYMBOL_GPL(memunmap_pages);
.pgprot = PAGE_KERNEL,
};
const int nr_range = pgmap->nr_range;
- bool need_devmap_managed = true;
int error, i;
if (WARN_ONCE(!nr_range, "nr_range must be specified\n"))
WARN(1, "Missing migrate_to_ram method\n");
return ERR_PTR(-EINVAL);
}
+ if (!pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return ERR_PTR(-EINVAL);
+ }
if (!pgmap->owner) {
WARN(1, "Missing owner\n");
return ERR_PTR(-EINVAL);
}
break;
case MEMORY_DEVICE_GENERIC:
- need_devmap_managed = false;
break;
case MEMORY_DEVICE_PCI_P2PDMA:
params.pgprot = pgprot_noncached(params.pgprot);
- need_devmap_managed = false;
break;
default:
WARN(1, "Invalid pgmap type %d\n", pgmap->type);
}
}
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(pgmap);
- if (error)
- return ERR_PTR(error);
- }
+ devmap_managed_enable_get(pgmap);
/*
* Clear the pgmap nr_range as it will be incremented for each
goto put_anon;
if (page_mapped(hpage)) {
- /*
- * try_to_unmap could potentially call huge_pmd_unshare.
- * Because of this, take semaphore in write mode here and
- * set TTU_RMAP_LOCKED to let lower levels know we have
- * taken the lock.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
- if (unlikely(!mapping))
- goto unlock_put_anon;
+ bool mapping_locked = false;
+ enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK|
+ TTU_IGNORE_ACCESS;
+
+ if (!PageAnon(hpage)) {
+ /*
+ * In shared mappings, try_to_unmap could potentially
+ * call huge_pmd_unshare. Because of this, take
+ * semaphore in write mode here and set TTU_RMAP_LOCKED
+ * to let lower levels know we have taken the lock.
+ */
+ mapping = hugetlb_page_mapping_lock_write(hpage);
+ if (unlikely(!mapping))
+ goto unlock_put_anon;
+
+ mapping_locked = true;
+ ttu |= TTU_RMAP_LOCKED;
+ }
- try_to_unmap(hpage,
- TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
- TTU_RMAP_LOCKED);
+ try_to_unmap(hpage, ttu);
page_was_mapped = 1;
- /*
- * Leave mapping locked until after subsequent call to
- * remove_migration_ptes()
- */
+
+ if (mapping_locked)
+ i_mmap_unlock_write(mapping);
}
if (!page_mapped(hpage))
rc = move_to_new_page(new_hpage, hpage, mode);
- if (page_was_mapped) {
+ if (page_was_mapped)
remove_migration_ptes(hpage,
- rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true);
- i_mmap_unlock_write(mapping);
- }
+ rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);
unlock_put_anon:
unlock_page(new_hpage);
if (error)
goto unmap_and_free_vma;
+ /* Can addr have changed??
+ *
+ * Answer: Yes, several device drivers can do it in their
+ * f_op->mmap method. -DaveM
+ * Bug: If addr is changed, prev, rb_link, rb_parent should
+ * be updated for vma_link()
+ */
+ WARN_ON_ONCE(addr != vma->vm_start);
+
+ addr = vma->vm_start;
+
/* If vm_flags changed after call_mmap(), we should try merge vma again
* as we may succeed this time.
*/
fput(vma->vm_file);
vm_area_free(vma);
vma = merge;
- /* Update vm_flags and possible addr to pick up the change. We don't
- * warn here if addr changed as the vma is not linked by vma_link().
- */
- addr = vma->vm_start;
+ /* Update vm_flags to pick up the change. */
vm_flags = vma->vm_flags;
goto unmap_writable;
}
}
- /* Can addr have changed??
- *
- * Answer: Yes, several device drivers can do it in their
- * f_op->mmap method. -DaveM
- * Bug: If addr is changed, prev, rb_link, rb_parent should
- * be updated for vma_link()
- */
- WARN_ON_ONCE(addr != vma->vm_start);
-
- addr = vma->vm_start;
vm_flags = vma->vm_flags;
} else if (vm_flags & VM_SHARED) {
error = shmem_zero_setup(vma);
} else {
ret = TestClearPageWriteback(page);
}
- /*
- * NOTE: Page might be free now! Writeback doesn't hold a page
- * reference on its own, it relies on truncation to wait for
- * the clearing of PG_writeback. The below can only access
- * page state that is static across allocation cycles.
- */
if (ret) {
dec_lruvec_state(lruvec, NR_WRITEBACK);
dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
+ if (unlikely(nc->pfmemalloc)) {
+ free_the_page(page, compound_order(page));
+ goto refill;
+ }
+
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
/* if size can vary use size else just use PAGE_SIZE */
size = nc->size;
region_size = ALIGN(start_offset + map_size, lcm_align);
/* allocate chunk */
- alloc_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long);
+ alloc_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(region_size >> PAGE_SHIFT));
chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
if (!chunk)
panic("%s: Failed to allocate %zu bytes\n", __func__,
pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_atom_size = ai->atom_size;
- pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
- BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
+ pcpu_chunk_struct_size = struct_size(chunk, populated,
+ BITS_TO_LONGS(pcpu_unit_pages));
pcpu_stats_save_ai(ai);
* Copyright (C) 2010-2011 Christopher Yeoh <cyeoh@au1.ibm.com>, IBM Corp.
*/
+#include <linux/compat.h>
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
return rc;
if (!iov_iter_count(&iter))
goto free_iov_l;
- iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r, false);
+ iov_r = iovec_from_user(rvec, riovcnt, UIO_FASTIOV, iovstack_r,
+ in_compat_syscall());
if (IS_ERR(iov_r)) {
rc = PTR_ERR(iov_r);
goto free_iov_l;
/*
* If sharing is possible, start and end will be adjusted
* accordingly.
- *
- * If called for a huge page, caller must hold i_mmap_rwsem
- * in write mode as it is possible to call huge_pmd_unshare.
*/
adjust_range_if_pmd_sharing_possible(vma, &range.start,
&range.end);
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
- if (PageHuge(page)) {
+ if (PageHuge(page) && !PageAnon(page)) {
/*
* To call huge_pmd_unshare, i_mmap_rwsem must be
* held in write mode. Caller needs to explicitly
return s->size + sizeof(struct obj_cgroup *);
}
-static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
- size_t objects,
- gfp_t flags)
+/*
+ * Returns false if the allocation should fail.
+ */
+static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+ struct obj_cgroup **objcgp,
+ size_t objects, gfp_t flags)
{
struct obj_cgroup *objcg;
+ if (!memcg_kmem_enabled())
+ return true;
+
+ if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
+ return true;
+
objcg = get_obj_cgroup_from_current();
if (!objcg)
- return NULL;
+ return true;
if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
obj_cgroup_put(objcg);
- return NULL;
+ return false;
}
- return objcg;
+ *objcgp = objcg;
+ return true;
}
static inline void mod_objcg_state(struct obj_cgroup *objcg,
unsigned long off;
size_t i;
- if (!objcg)
+ if (!memcg_kmem_enabled() || !objcg)
return;
flags &= ~__GFP_ACCOUNT;
{
}
-static inline struct obj_cgroup *memcg_slab_pre_alloc_hook(struct kmem_cache *s,
- size_t objects,
- gfp_t flags)
+static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
+ struct obj_cgroup **objcgp,
+ size_t objects, gfp_t flags)
{
- return NULL;
+ return true;
}
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
if (should_failslab(s, flags))
return NULL;
- if (memcg_kmem_enabled() &&
- ((flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)))
- *objcgp = memcg_slab_pre_alloc_hook(s, size, flags);
+ if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags))
+ return NULL;
return s;
}
s->flags, flags);
}
- if (memcg_kmem_enabled())
- memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
+ memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
}
#ifndef CONFIG_SLOB
object = c->freelist;
page = c->page;
- if (unlikely(!object || !node_match(page, node))) {
+ if (unlikely(!object || !page || !node_match(page, node))) {
object = __slab_alloc(s, gfpflags, node, addr, c);
} else {
void *next_object = get_freepointer_safe(s, object);
static struct swap_info_struct *alloc_swap_info(void)
{
struct swap_info_struct *p;
+ struct swap_info_struct *defer = NULL;
unsigned int type;
int i;
smp_wmb();
WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1);
} else {
- kvfree(p);
+ defer = p;
p = swap_info[type];
/*
* Do not memset this entry: a racing procfs swap_next()
plist_node_init(&p->avail_lists[i], 0);
p->flags = SWP_USED;
spin_unlock(&swap_lock);
+ kvfree(defer);
spin_lock_init(&p->lock);
spin_lock_init(&p->cont_lock);
}
EXPORT_SYMBOL(truncate_inode_pages_final);
-unsigned long __invalidate_mapping_pages(struct address_space *mapping,
+static unsigned long __invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end, unsigned long *nr_pagevec)
{
pgoff_t indices[PAGEVEC_SIZE];
nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
TTU_IGNORE_ACCESS, &stat, true);
list_splice(&clean_pages, page_list);
- mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+ -(long)nr_reclaimed);
/*
* Since lazyfree pages are isolated from file LRU from the beginning,
* they will rotate back to anonymous LRU in the end if it failed to
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
stat.nr_lazyfree_fail);
mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
- -stat.nr_lazyfree_fail);
+ -(long)stat.nr_lazyfree_fail);
return nr_reclaimed;
}
};
struct mapping_area {
-#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
- struct vm_struct *vm; /* vm area for mapping object that span pages */
-#else
char *vm_buf; /* copy buffer for objects that span pages */
-#endif
char *vm_addr; /* address of kmap_atomic()'ed pages */
enum zs_mapmode vm_mm; /* mapping mode */
};
return zspage;
}
-#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
- /*
- * Make sure we don't leak memory if a cpu UP notification
- * and zs_init() race and both call zs_cpu_up() on the same cpu
- */
- if (area->vm)
- return 0;
- area->vm = get_vm_area(PAGE_SIZE * 2, 0);
- if (!area->vm)
- return -ENOMEM;
-
- /*
- * Populate ptes in advance to avoid pte allocation with GFP_KERNEL
- * in non-preemtible context of zs_map_object.
- */
- return apply_to_page_range(&init_mm, (unsigned long)area->vm->addr,
- PAGE_SIZE * 2, NULL, NULL);
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
- if (area->vm)
- free_vm_area(area->vm);
- area->vm = NULL;
-}
-
-static inline void *__zs_map_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- unsigned long addr = (unsigned long)area->vm->addr;
-
- BUG_ON(map_kernel_range(addr, PAGE_SIZE * 2, PAGE_KERNEL, pages) < 0);
- area->vm_addr = area->vm->addr;
- return area->vm_addr + off;
-}
-
-static inline void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- unsigned long addr = (unsigned long)area->vm_addr;
-
- unmap_kernel_range(addr, PAGE_SIZE * 2);
-}
-
-#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
-
static inline int __zs_cpu_up(struct mapping_area *area)
{
/*
pagefault_enable();
}
-#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
-
static int zs_cpu_prepare(unsigned int cpu)
{
struct mapping_area *area;
{
struct lec_state *state = seq->private;
- v = lec_get_idx(state, 1);
- *pos += !!PTR_ERR(v);
- return v;
+ ++*pos;
+ return lec_get_idx(state, 1);
}
static int lec_seq_show(struct seq_file *seq, void *v)
/**
* batadv_frag_create() - create a fragment from skb
+ * @net_dev: outgoing device for fragment
* @skb: skb to create fragment from
* @frag_head: header to use in new fragment
* @fragment_size: size of new fragment
*
* Return: the new fragment, NULL on error.
*/
-static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
+static struct sk_buff *batadv_frag_create(struct net_device *net_dev,
+ struct sk_buff *skb,
struct batadv_frag_packet *frag_head,
unsigned int fragment_size)
{
+ unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev);
+ unsigned int tailroom = net_dev->needed_tailroom;
struct sk_buff *skb_fragment;
unsigned int header_size = sizeof(*frag_head);
unsigned int mtu = fragment_size + header_size;
- skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN);
+ skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom);
if (!skb_fragment)
goto err;
skb_fragment->priority = skb->priority;
/* Eat the last mtu-bytes of the skb */
- skb_reserve(skb_fragment, header_size + ETH_HLEN);
+ skb_reserve(skb_fragment, ll_reserved + header_size);
skb_split(skb, skb_fragment, skb->len - fragment_size);
/* Add the header */
struct batadv_orig_node *orig_node,
struct batadv_neigh_node *neigh_node)
{
+ struct net_device *net_dev = neigh_node->if_incoming->net_dev;
struct batadv_priv *bat_priv;
struct batadv_hard_iface *primary_if = NULL;
struct batadv_frag_packet frag_header;
struct sk_buff *skb_fragment;
- unsigned int mtu = neigh_node->if_incoming->net_dev->mtu;
+ unsigned int mtu = net_dev->mtu;
unsigned int header_size = sizeof(frag_header);
unsigned int max_fragment_size, num_fragments;
int ret;
goto put_primary_if;
}
- skb_fragment = batadv_frag_create(skb, &frag_header,
+ skb_fragment = batadv_frag_create(net_dev, skb, &frag_header,
max_fragment_size);
if (!skb_fragment) {
ret = -ENOMEM;
frag_header.no++;
}
- /* Make room for the fragment header. */
- if (batadv_skb_head_push(skb, header_size) < 0 ||
- pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) {
- ret = -ENOMEM;
+ /* make sure that there is at least enough head for the fragmentation
+ * and ethernet headers
+ */
+ ret = skb_cow_head(skb, ETH_HLEN + header_size);
+ if (ret < 0)
goto put_primary_if;
- }
+ skb_push(skb, header_size);
memcpy(skb->data, &frag_header, header_size);
/* Send the last fragment */
needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN);
needed_headroom += batadv_max_header_len();
+ /* fragmentation headers don't strip the unicast/... header */
+ needed_headroom += sizeof(struct batadv_frag_packet);
+
soft_iface->needed_headroom = needed_headroom;
soft_iface->needed_tailroom = lower_tailroom;
}
.read = batadv_log_read,
.poll = batadv_log_poll,
.llseek = no_llseek,
+ .owner = THIS_MODULE,
};
/**
struct msft_cp_read_supported_features {
__u8 sub_opcode;
} __packed;
+
struct msft_rp_read_supported_features {
__u8 status;
__u8 sub_opcode;
__le64 features;
__u8 evt_prefix_len;
- __u8 evt_prefix[0];
+ __u8 evt_prefix[];
} __packed;
struct msft_data {
{
struct net_bridge *br = netdev_priv(dev);
+ netdev_stats_to_stats64(stats, &dev->stats);
dev_fetch_sw_netstats(stats, br->stats);
}
mtu_reserved = nf_bridge_mtu_reduction(skb);
mtu = skb->dev->mtu;
+ if (nf_bridge->pkt_otherhost) {
+ skb->pkt_type = PACKET_OTHERHOST;
+ nf_bridge->pkt_otherhost = false;
+ }
+
if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu)
mtu = nf_bridge->frag_max_size;
else
return NF_ACCEPT;
- /* We assume any code from br_dev_queue_push_xmit onwards doesn't care
- * about the value of skb->pkt_type. */
if (skb->pkt_type == PACKET_OTHERHOST) {
skb->pkt_type = PACKET_HOST;
nf_bridge->pkt_otherhost = true;
communication between CAN nodes via two defined CAN Identifiers.
As CAN frames can only transport a small amount of data bytes
(max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this
- segmentation is needed to transport longer PDUs as needed e.g. for
- vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic.
+ segmentation is needed to transport longer Protocol Data Units (PDU)
+ as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN
+ traffic.
This protocol driver implements data transfers according to
ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.
If you want to perform automotive vehicle diagnostic services (UDS),
/* Check for bugs in CAN protocol implementations using af_can.c:
* 'rcv' will be NULL if no matching list item was found for removal.
+ * As this case may potentially happen when closing a socket while
+ * the notifier for removing the CAN netdev is running we just print
+ * a warning here.
*/
if (!rcv) {
- WARN(1, "BUG: receive list entry not found for dev %s, id %03X, mask %03X\n",
- DNAME(dev), can_id, mask);
+ pr_warn("can: receive list entry not found for dev %s, id %03X, mask %03X\n",
+ DNAME(dev), can_id, mask);
goto out;
}
{
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
- if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU ||
- cfd->len > CAN_MAX_DLEN)) {
- pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n",
+ if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n",
+ dev->type, skb->len);
+ goto free_skb;
+ }
+
+ /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */
+ if (unlikely(cfd->len > CAN_MAX_DLEN)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n",
dev->type, skb->len, cfd->len);
- kfree_skb(skb);
- return NET_RX_DROP;
+ goto free_skb;
}
can_receive(skb, dev);
return NET_RX_SUCCESS;
+
+free_skb:
+ kfree_skb(skb);
+ return NET_RX_DROP;
}
static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
{
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
- if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU ||
- cfd->len > CANFD_MAX_DLEN)) {
- pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n",
+ if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n",
+ dev->type, skb->len);
+ goto free_skb;
+ }
+
+ /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */
+ if (unlikely(cfd->len > CANFD_MAX_DLEN)) {
+ pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n",
dev->type, skb->len, cfd->len);
- kfree_skb(skb);
- return NET_RX_DROP;
+ goto free_skb;
}
can_receive(skb, dev);
return NET_RX_SUCCESS;
+
+free_skb:
+ kfree_skb(skb);
+ return NET_RX_DROP;
}
/* af_can protocol functions */
static u8 padlen(u8 datalen)
{
- const u8 plen[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */
- 12, 12, 12, 12, /* 9 - 12 */
- 16, 16, 16, 16, /* 13 - 16 */
- 20, 20, 20, 20, /* 17 - 20 */
- 24, 24, 24, 24, /* 21 - 24 */
- 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */
- 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */
- 48, 48, 48, 48, 48, 48, 48, 48}; /* 41 - 48 */
+ static const u8 plen[] = {
+ 8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */
+ 12, 12, 12, 12, /* 9 - 12 */
+ 16, 16, 16, 16, /* 13 - 16 */
+ 20, 20, 20, 20, /* 17 - 20 */
+ 24, 24, 24, 24, /* 21 - 24 */
+ 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */
+ 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */
+ 48, 48, 48, 48, 48, 48, 48, 48 /* 41 - 48 */
+ };
if (datalen > 48)
return 64;
return 0;
}
- /* no creation of flow control frames */
- if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
- return 0;
-
/* perform blocksize handling, if enabled */
if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) {
/* start rx timeout watchdog */
return 0;
}
+ /* no creation of flow control frames */
+ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+ return 0;
+
/* we reached the specified blocksize so->rxfc.bs */
isotp_send_fc(sk, ae, ISOTP_FC_CTS);
return 0;
goto out_release_sock;
}
+ if (!(ndev->flags & IFF_UP)) {
+ dev_put(ndev);
+ ret = -ENETDOWN;
+ goto out_release_sock;
+ }
+
priv = j1939_netdev_start(ndev);
dev_put(ndev);
if (IS_ERR(priv)) {
*/
void can_remove_proc(struct net *net)
{
+ if (!net->can.proc_dir)
+ return;
+
if (net->can.pde_stats)
remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
if (net->can.pde_rcvlist_sff)
remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
- if (net->can.proc_dir)
- remove_proc_entry("can", net->proc_net);
+ remove_proc_entry("can", net->proc_net);
}
}
EXPORT_SYMBOL(dev_queue_xmit_accel);
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
{
struct net_device *dev = skb->dev;
struct sk_buff *orig_skb = skb;
dev_xmit_recursion_dec();
local_bh_enable();
-
- if (!dev_xmit_complete(ret))
- kfree_skb(skb);
-
return ret;
drop:
atomic_long_inc(&dev->tx_dropped);
kfree_skb_list(skb);
return NET_XMIT_DROP;
}
-EXPORT_SYMBOL(dev_direct_xmit);
+EXPORT_SYMBOL(__dev_direct_xmit);
/*************************************************************************
* Receiver routines
return test_bit(limit, &devlink->ops->reload_limits);
}
-static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action,
+static int devlink_reload_stat_put(struct sk_buff *msg,
enum devlink_reload_limit limit, u32 value)
{
struct nlattr *reload_stats_entry;
if (!reload_stats_entry)
return -EMSGSIZE;
- if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) ||
- nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) ||
+ if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) ||
nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value))
goto nla_put_failure;
nla_nest_end(msg, reload_stats_entry);
static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote)
{
- struct nlattr *reload_stats_attr;
+ struct nlattr *reload_stats_attr, *act_info, *act_stats;
int i, j, stat_idx;
u32 value;
if (!reload_stats_attr)
return -EMSGSIZE;
- for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) {
- /* Remote stats are shown even if not locally supported. Stats
- * of actions with unspecified limit are shown though drivers
- * don't need to register unspecified limit.
- */
- if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
- !devlink_reload_limit_is_supported(devlink, j))
+ for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
+ if ((!is_remote &&
+ !devlink_reload_action_is_supported(devlink, i)) ||
+ i == DEVLINK_RELOAD_ACTION_UNSPEC)
continue;
- for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
- if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) ||
- i == DEVLINK_RELOAD_ACTION_UNSPEC ||
+ act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO);
+ if (!act_info)
+ goto nla_put_failure;
+
+ if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i))
+ goto action_info_nest_cancel;
+ act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS);
+ if (!act_stats)
+ goto action_info_nest_cancel;
+
+ for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) {
+ /* Remote stats are shown even if not locally supported.
+ * Stats of actions with unspecified limit are shown
+ * though drivers don't need to register unspecified
+ * limit.
+ */
+ if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
+ !devlink_reload_limit_is_supported(devlink, j)) ||
devlink_reload_combination_is_invalid(i, j))
continue;
value = devlink->stats.reload_stats[stat_idx];
else
value = devlink->stats.remote_reload_stats[stat_idx];
- if (devlink_reload_stat_put(msg, i, j, value))
- goto nla_put_failure;
+ if (devlink_reload_stat_put(msg, j, value))
+ goto action_stats_nest_cancel;
}
+ nla_nest_end(msg, act_stats);
+ nla_nest_end(msg, act_info);
}
nla_nest_end(msg, reload_stats_attr);
return 0;
+action_stats_nest_cancel:
+ nla_nest_cancel(msg, act_stats);
+action_info_nest_cancel:
+ nla_nest_cancel(msg, act_info);
nla_put_failure:
nla_nest_cancel(msg, reload_stats_attr);
return -EMSGSIZE;
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
goto nla_put_failure;
+ /* Hold rtnl lock while accessing port's netdev attributes. */
+ rtnl_lock();
spin_lock_bh(&devlink_port->type_lock);
if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
goto nla_put_failure_type_locked;
devlink_port->desired_type))
goto nla_put_failure_type_locked;
if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
+ struct net *net = devlink_net(devlink_port->devlink);
struct net_device *netdev = devlink_port->type_dev;
- if (netdev &&
+ if (netdev && net_eq(net, dev_net(netdev)) &&
(nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
netdev->ifindex) ||
nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
goto nla_put_failure_type_locked;
}
spin_unlock_bh(&devlink_port->type_lock);
+ rtnl_unlock();
if (devlink_nl_port_attrs_put(msg, devlink_port))
goto nla_put_failure;
if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack))
nla_put_failure_type_locked:
spin_unlock_bh(&devlink_port->type_lock);
+ rtnl_unlock();
nla_put_failure:
genlmsg_cancel(msg, hdr);
return -EMSGSIZE;
err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
pool_index, &cur, &max);
if (err && err != -EOPNOTSUPP)
- return err;
+ goto sb_occ_get_failure;
if (!err) {
if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
goto nla_put_failure;
return 0;
nla_put_failure:
+ err = -EMSGSIZE;
+sb_occ_get_failure:
genlmsg_cancel(msg, hdr);
- return -EMSGSIZE;
+ return err;
}
static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb,
if (err)
goto nla_put_failure;
- if (region->port)
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
- region->port->index))
+ if (region->port) {
+ err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+ region->port->index);
+ if (err)
goto nla_put_failure;
+ }
err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
if (err)
if (err)
goto out_cancel_msg;
- if (region->port)
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
- region->port->index))
+ if (region->port) {
+ err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+ region->port->index);
+ if (err)
goto out_cancel_msg;
+ }
err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
region->ops->name);
index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
port = devlink_port_get_by_index(devlink, index);
- if (!port)
- return -ENODEV;
+ if (!port) {
+ err = -ENODEV;
+ goto out_unlock;
+ }
}
region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
if (err)
goto nla_put_failure;
- if (region->port)
- if (nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
- region->port->index))
+ if (region->port) {
+ err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
+ region->port->index);
+ if (err)
goto nla_put_failure;
+ }
err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
if (err)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
- if (WARN_ON(devlink_port->registered))
- return -EEXIST;
devlink_port->attrs_set = true;
attrs->flavour = flavour;
if (attrs->switch_id.id_len) {
{
int ret;
+ if (WARN_ON(devlink_port->registered))
+ return;
devlink_port->attrs = *attrs;
ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
if (ret)
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
+ if (WARN_ON(devlink_port->registered))
+ return;
ret = __devlink_port_attrs_set(devlink_port,
DEVLINK_PORT_FLAVOUR_PCI_PF);
if (ret)
struct devlink_port_attrs *attrs = &devlink_port->attrs;
int ret;
+ if (WARN_ON(devlink_port->registered))
+ return;
ret = __devlink_port_attrs_set(devlink_port,
DEVLINK_PORT_FLAVOUR_PCI_VF);
if (ret)
struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
napi_disable(&cell->napi);
- netif_napi_del(&cell->napi);
+ __netif_napi_del(&cell->napi);
__skb_queue_purge(&cell->napi_skbs);
}
+ /* This barrier is needed because netpoll could access dev->napi_list
+ * under rcu protection.
+ */
+ synchronize_net();
+
free_percpu(gcells->cells);
gcells->cells = NULL;
}
write_lock(&n->lock);
if ((n->nud_state == NUD_FAILED) ||
+ (tbl->is_multicast &&
+ tbl->is_multicast(n->primary_key)) ||
time_after(tref, n->updated))
remove = true;
write_unlock(&n->lock);
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/if_vlan.h>
+#include <net/dsa.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/addrconf.h>
int netpoll_setup(struct netpoll *np)
{
- struct net_device *ndev = NULL;
+ struct net_device *ndev = NULL, *dev = NULL;
+ struct net *net = current->nsproxy->net_ns;
struct in_device *in_dev;
int err;
rtnl_lock();
- if (np->dev_name[0]) {
- struct net *net = current->nsproxy->net_ns;
+ if (np->dev_name[0])
ndev = __dev_get_by_name(net, np->dev_name);
- }
+
if (!ndev) {
np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
err = -ENODEV;
}
dev_hold(ndev);
+ /* bring up DSA management network devices up first */
+ for_each_netdev(net, dev) {
+ if (!netdev_uses_dsa(dev))
+ continue;
+
+ err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
+ if (err < 0) {
+ np_err(np, "%s failed to open %s\n",
+ np->dev_name, dev->name);
+ goto put;
+ }
+ }
+
if (netdev_master_upper_dev_get(ndev)) {
np_err(np, "%s is a slave device, aborting\n", np->dev_name);
err = -EBUSY;
if (skb && (skb_next = skb_peek(q))) {
icmp_next = is_icmp_err_skb(skb_next);
if (icmp_next)
- sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin;
+ sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
}
spin_unlock_irqrestore(&q->lock, flags);
if (unlikely(!eth_p_mpls(skb->protocol)))
return -EINVAL;
+ if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+ return -ENOMEM;
+
lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry);
ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
if (!--ttl)
struct scatterlist *sge = sk_msg_elem(msg, i);
u32 len = sge->length;
- if (charge)
- sk_mem_uncharge(sk, len);
- if (!msg->skb)
+ /* When the skb owns the memory we free it from consume_skb path. */
+ if (!msg->skb) {
+ if (charge)
+ sk_mem_uncharge(sk, len);
put_page(sg_page(sge));
+ }
memset(sge, 0, sizeof(*sge));
return len;
}
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
-static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
+ struct sk_buff *skb)
{
- struct sock *sk = psock->sk;
- int copied = 0, num_sge;
struct sk_msg *msg;
+ if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+ return NULL;
+
+ if (!sk_rmem_schedule(sk, skb, skb->truesize))
+ return NULL;
+
msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
if (unlikely(!msg))
- return -EAGAIN;
- if (!sk_rmem_schedule(sk, skb, skb->len)) {
- kfree(msg);
- return -EAGAIN;
- }
+ return NULL;
sk_msg_init(msg);
+ return msg;
+}
+
+static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
+ struct sk_psock *psock,
+ struct sock *sk,
+ struct sk_msg *msg)
+{
+ int num_sge, copied;
+
+ /* skb linearize may fail with ENOMEM, but lets simply try again
+ * later if this happens. Under memory pressure we don't want to
+ * drop the skb. We need to linearize the skb so that the mapping
+ * in skb_to_sgvec can not error.
+ */
+ if (skb_linearize(skb))
+ return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
if (unlikely(num_sge < 0)) {
kfree(msg);
return num_sge;
}
- sk_mem_charge(sk, skb->len);
copied = skb->len;
msg->sg.start = 0;
msg->sg.size = copied;
return copied;
}
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);
+
+static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+{
+ struct sock *sk = psock->sk;
+ struct sk_msg *msg;
+
+ /* If we are receiving on the same sock skb->sk is already assigned,
+ * skip memory accounting and owner transition seeing it already set
+ * correctly.
+ */
+ if (unlikely(skb->sk == sk))
+ return sk_psock_skb_ingress_self(psock, skb);
+ msg = sk_psock_create_ingress_msg(sk, skb);
+ if (!msg)
+ return -EAGAIN;
+
+ /* This will transition ownership of the data from the socket where
+ * the BPF program was run initiating the redirect to the socket
+ * we will eventually receive this data on. The data will be released
+ * from skb_consume found in __tcp_bpf_recvmsg() after its been copied
+ * into user buffers.
+ */
+ skb_set_owner_r(skb, sk);
+ return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
+/* Puts an skb on the ingress queue of the socket already assigned to the
+ * skb. In this case we do not need to check memory limits or skb_set_owner_r
+ * because the skb is already accounted for here.
+ */
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
+{
+ struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
+ struct sock *sk = psock->sk;
+
+ if (unlikely(!msg))
+ return -EAGAIN;
+ sk_msg_init(msg);
+ return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len, bool ingress)
{
* retrying later from workqueue.
*/
if (skb_queue_empty(&psock->ingress_skb)) {
- err = sk_psock_skb_ingress(psock, skb);
+ err = sk_psock_skb_ingress_self(psock, skb);
}
if (err < 0) {
skb_queue_tail(&psock->ingress_skb, skb);
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
if (*own_req)
ireq->ireq_opt = NULL;
else
dccp_done(newsk);
goto out;
}
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
/* Clone pktoptions received with SYN, if we own the req */
if (*own_req && ireq->pktopts) {
newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
active_diff_mask, compact);
}
if (mod)
- ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL);
+ netdev_features_change(dev);
out_rtnl:
rtnl_unlock();
static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
static void parp_redo(struct sk_buff *skb);
+static int arp_is_multicast(const void *pkey);
static const struct neigh_ops arp_generic_ops = {
.family = AF_INET,
.key_eq = arp_key_eq,
.constructor = arp_constructor,
.proxy_redo = parp_redo,
+ .is_multicast = arp_is_multicast,
.id = "arp_cache",
.parms = {
.tbl = &arp_tbl,
arp_process(dev_net(skb->dev), NULL, skb);
}
+static int arp_is_multicast(const void *pkey)
+{
+ return ipv4_is_multicast(*((__be32 *)pkey));
+}
/*
* Receive an arp request from the device layer.
cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
break;
case AF_INET6:
-#ifdef CONFIG_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
if (alen != sizeof(struct in6_addr)) {
NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
return -EINVAL;
timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
mod_timer(&req->rsk_timer, jiffies + timeout);
- inet_ehash_insert(req_to_sk(req), NULL);
+ inet_ehash_insert(req_to_sk(req), NULL, NULL);
/* before letting lookups find us, make sure all req fields
* are committed to memory and refcnt initialized.
*/
r->idiag_inode = 0;
if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
- inet_rsk(reqsk)->ir_mark))
+ inet_rsk(reqsk)->ir_mark)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
nlmsg_end(skb, nlh);
return 0;
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/inet6_hashtables.h>
+#endif
#include <net/secure_seq.h>
#include <net/ip.h>
#include <net/tcp.h>
inet->inet_dport);
}
-/* insert a socket into ehash, and eventually remove another one
- * (The another one can be a SYN_RECV or TIMEWAIT
+/* Searches for an exsiting socket in the ehash bucket list.
+ * Returns true if found, false otherwise.
*/
-bool inet_ehash_insert(struct sock *sk, struct sock *osk)
+static bool inet_ehash_lookup_by_sk(struct sock *sk,
+ struct hlist_nulls_head *list)
+{
+ const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);
+ const int sdif = sk->sk_bound_dev_if;
+ const int dif = sk->sk_bound_dev_if;
+ const struct hlist_nulls_node *node;
+ struct net *net = sock_net(sk);
+ struct sock *esk;
+
+ INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);
+
+ sk_nulls_for_each_rcu(esk, node, list) {
+ if (esk->sk_hash != sk->sk_hash)
+ continue;
+ if (sk->sk_family == AF_INET) {
+ if (unlikely(INET_MATCH(esk, net, acookie,
+ sk->sk_daddr,
+ sk->sk_rcv_saddr,
+ ports, dif, sdif))) {
+ return true;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (sk->sk_family == AF_INET6) {
+ if (unlikely(INET6_MATCH(esk, net,
+ &sk->sk_v6_daddr,
+ &sk->sk_v6_rcv_saddr,
+ ports, dif, sdif))) {
+ return true;
+ }
+ }
+#endif
+ }
+ return false;
+}
+
+/* Insert a socket into ehash, and eventually remove another one
+ * (The another one can be a SYN_RECV or TIMEWAIT)
+ * If an existing socket already exists, socket sk is not inserted,
+ * and sets found_dup_sk parameter to true.
+ */
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
ret = sk_nulls_del_node_init_rcu(osk);
+ } else if (found_dup_sk) {
+ *found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
+ if (*found_dup_sk)
+ ret = false;
}
+
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+
spin_unlock(lock);
+
return ret;
}
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
{
- bool ok = inet_ehash_insert(sk, osk);
+ bool ok = inet_ehash_insert(sk, osk, found_dup_sk);
if (ok) {
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
- inet_ehash_nolisten(sk, osk);
+ inet_ehash_nolisten(sk, osk, NULL);
return 0;
}
WARN_ON(!sk_unhashed(sk));
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- inet_ehash_nolisten(sk, NULL);
+ inet_ehash_nolisten(sk, NULL, NULL);
spin_unlock_bh(&head->lock);
return 0;
}
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
- inet_ehash_nolisten(sk, (struct sock *)tw);
+ inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
ttl = ip4_dst_hoplimit(&rt->dst);
}
- if (!df && skb->protocol == htons(ETH_P_IP))
- df = inner_iph->frag_off & htons(IP_DF);
-
headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
if (headroom > dev->needed_headroom)
dev->needed_headroom = headroom;
const struct icmphdr *icmph = icmp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
- if (mtu <= 576 || iph->frag_off != htons(IP_DF))
+ if (mtu < 576 || iph->frag_off != htons(IP_DF))
return 0;
if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) ||
__be16 frag_off;
int offset;
- if (mtu <= IPV6_MIN_MTU)
+ if (mtu < IPV6_MIN_MTU)
return 0;
if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
#include <net/netfilter/nf_queue.h>
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
__be32 saddr = iph->saddr;
- const struct sock *sk = skb_to_full_sk(skb);
- __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
+ __u8 flags;
struct net_device *dev = skb_dst(skb)->dev;
unsigned int hh_len;
+ sk = sk_to_full_sk(sk);
+ flags = sk ? inet_sk_flowi_flags(sk) : 0;
+
if (addr_type == RTN_UNSPEC)
addr_type = inet_addr_type_dev_table(net, dev, saddr);
if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
iph->daddr != daddr ||
skb->mark != mark ||
iph->tos != tos) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
ip4_dst_hoplimit(skb_dst(nskb)));
nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
- if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+ if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
goto free_nskb;
niph = ip_hdr(nskb);
fl4.daddr = dst;
fl4.saddr = src;
- fl4.flowi4_tos = rtm->rtm_tos;
+ fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
fl4.flowi4_uid = uid;
fl4.flowi4_iif = iif; /* for rt_fill_info */
skb->dev = dev;
skb->mark = mark;
- err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
- dev, &res);
+ err = ip_route_input_rcu(skb, dst, src,
+ rtm->rtm_tos & IPTOS_RT_MASK, dev,
+ &res);
rt = skb_rtable(skb);
if (err == 0 && rt->dst.error)
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
- int mss;
+ int full_space, mss;
struct rtable *rt;
__u8 rcv_wscale;
struct flowi4 fl4;
/* Try to redo what tcp_v4_send_synack did. */
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ full_space = tcp_full_space(sk);
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
- tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+ tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(&rt->dst, RTAX_INITRWND));
return true;
if (tcp_rmem_pressure(sk))
return true;
+ if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss)
+ return true;
}
if (sk->sk_prot->stream_memory_read)
return sk->sk_prot->stream_memory_read(sk);
filter_expired = after(tcp_jiffies32,
bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
if (rs->rtt_us >= 0 &&
- (rs->rtt_us <= bbr->min_rtt_us ||
+ (rs->rtt_us < bbr->min_rtt_us ||
(filter_expired && !rs->is_ack_delayed))) {
bbr->min_rtt_us = rs->rtt_us;
bbr->min_rtt_stamp = tcp_jiffies32;
{
struct iov_iter *iter = &msg->msg_iter;
int peek = flags & MSG_PEEK;
- int i, ret, copied = 0;
struct sk_msg *msg_rx;
+ int i, copied = 0;
msg_rx = list_first_entry_or_null(&psock->ingress_msg,
struct sk_msg, list);
page = sg_page(sge);
if (copied + copy > len)
copy = len - copied;
- ret = copy_page_to_iter(page, sge->offset, copy, iter);
- if (ret != copy) {
- msg_rx->sg.start = i;
- return -EFAULT;
- }
+ copy = copy_page_to_iter(page, sge->offset, copy, iter);
+ if (!copy)
+ return copied ? copied : -EFAULT;
copied += copy;
if (likely(!peek)) {
sge->offset += copy;
sge->length -= copy;
- sk_mem_uncharge(sk, copy);
+ if (!msg_rx->skb)
+ sk_mem_uncharge(sk, copy);
msg_rx->sg.size -= copy;
if (!sge->length) {
put_page(page);
}
} else {
+ /* Lets not optimize peek case if copy_page_to_iter
+ * didn't copy the entire length lets just break.
+ */
+ if (copy != sge->length)
+ return copied;
sk_msg_iter_var_next(i);
}
icsk->icsk_ca_setsockopt = 1;
memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+ if (ca->flags & TCP_CONG_NEEDS_ECN)
+ INET_ECN_xmit(sk);
+ else
+ INET_ECN_dontxmit(sk);
+
if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
tcp_init_congestion_control(sk);
}
int avail = tp->rcv_nxt - tp->copied_seq;
if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
- !sock_flag(sk, SOCK_DONE))
+ !sock_flag(sk, SOCK_DONE) &&
+ tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss)
return;
sk->sk_data_ready(sk);
skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
- tcp_rsk(req)->syn_tos : inet_sk(sk)->tos;
-
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
+ tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :
+ inet_sk(sk)->tos;
+
+ if (!INET_ECN_is_capable(tos) &&
+ tcp_bpf_ca_needs_ecn((struct sock *)req))
+ tos |= INET_ECN_ECT_0;
+
rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
rcu_dereference(ireq->ireq_opt),
- tos & ~INET_ECN_MASK);
+ tos);
rcu_read_unlock();
err = net_xmit_eval(err);
}
bool *own_req)
{
struct inet_request_sock *ireq;
+ bool found_dup_sk = false;
struct inet_sock *newinet;
struct tcp_sock *newtp;
struct sock *newsk;
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+ &found_dup_sk);
if (likely(*own_req)) {
tcp_move_syn(newtp, req);
ireq->ireq_opt = NULL;
} else {
- newinet->inet_opt = NULL;
+ if (!req_unhash && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
+ } else {
+ newinet->inet_opt = NULL;
+ }
}
return newsk;
static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
struct sk_buff *skb)
{
- struct udphdr *uh = udp_hdr(skb);
+ struct udphdr *uh = udp_gro_udphdr(skb);
struct sk_buff *pp = NULL;
struct udphdr *uh2;
struct sk_buff *p;
}
EXPORT_SYMBOL(udp_gro_receive);
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ const struct iphdr *iph = skb_gro_network_header(skb);
+
+ return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb),
+ inet_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 0;
rcu_read_lock();
- sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udp_encap_needed_key))
+ sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
- .priority = 3,
+ .priority = 4,
};
#if IS_ENABLED(CONFIG_IPV6)
static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
#endif
return -EMSGSIZE;
if (args->netnsid >= 0 &&
- nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 ||
return -EMSGSIZE;
if (args->netnsid >= 0 &&
- nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+ nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+ nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
+ }
put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 ||
/* add default label */
static int __net_init ip6addrlbl_net_init(struct net *net)
{
- int err = 0;
+ struct ip6addrlbl_entry *p = NULL;
+ struct hlist_node *n;
+ int err;
int i;
ADDRLABEL(KERN_DEBUG "%s\n", __func__);
INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head);
for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) {
- int ret = ip6addrlbl_add(net,
- ip6addrlbl_init_table[i].prefix,
- ip6addrlbl_init_table[i].prefixlen,
- 0,
- ip6addrlbl_init_table[i].label, 0);
- /* XXX: should we free all rules when we catch an error? */
- if (ret && (!err || err != -ENOMEM))
- err = ret;
+ err = ip6addrlbl_add(net,
+ ip6addrlbl_init_table[i].prefix,
+ ip6addrlbl_init_table[i].prefixlen,
+ 0,
+ ip6addrlbl_init_table[i].label, 0);
+ if (err)
+ goto err_ip6addrlbl_add;
+ }
+ return 0;
+
+err_ip6addrlbl_add:
+ hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
+ hlist_del_rcu(&p->list);
+ kfree_rcu(p, rcu);
}
return err;
}
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
memset(ah->auth_data, 0, ahp->icv_trunc_len);
- if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN))
+ err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN);
+ if (err)
goto out_free;
ip6h->priority = 0;
tp = skb_header_pointer(skb,
ptr+offsetof(struct icmp6hdr, icmp6_type),
sizeof(_type), &_type);
- if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
+
+ /* Based on RFC 8200, Section 4.5 Fragment Header, return
+ * false if this is a fragment packet with no icmp header info.
+ */
+ if (!tp && frag_off != 0)
+ return false;
+ else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
return true;
}
return false;
return;
if (rt->dst.dev) {
- dev->needed_headroom = rt->dst.dev->hard_header_len +
- t_hlen;
+ unsigned short dst_len = rt->dst.dev->hard_header_len +
+ t_hlen;
+
+ if (t->dev->header_ops)
+ dev->hard_header_len = dst_len;
+ else
+ dev->needed_headroom = dst_len;
if (set_mtu) {
dev->mtu = rt->dst.dev->mtu - t_hlen;
tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
- tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
+
+ if (tunnel->dev->header_ops)
+ tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ else
+ tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
+
return t_hlen;
}
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
+ skb_set_inner_ipproto(skb, proto);
+
err = ip6_tnl_encap(skb, t, &proto, fl6);
if (err)
return err;
ipv6_push_frag_opts(skb, &opt.ops, &proto);
}
- skb_set_inner_ipproto(skb, proto);
-
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);
+static int ndisc_is_multicast(const void *pkey);
static const struct neigh_ops ndisc_generic_ops = {
.family = AF_INET6,
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
+ .is_multicast = ndisc_is_multicast,
.allow_add = ndisc_allow_add,
.id = "ndisc_cache",
.parms = {
kfree_skb(skb);
}
+static int ndisc_is_multicast(const void *pkey)
+{
+ return ipv6_addr_is_multicast((struct in6_addr *)pkey);
+}
+
static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
{
struct inet6_dev *idev = __in6_dev_get(skb->dev);
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include "../bridge/br_private.h"
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
- struct sock *sk = sk_to_full_sk(skb->sk);
+ struct sock *sk = sk_to_full_sk(sk_partial);
unsigned int hh_len;
struct dst_entry *dst;
int strict = (ipv6_addr_type(&iph->daddr) &
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
- return ip6_route_me_harder(entry->state.net, skb);
+ return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
}
return 0;
}
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
- err = ip6_route_me_harder(state->net, skb);
+ err = ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
{
u16 savethdr = skb->transport_header;
+ u8 nexthdr = NEXTHDR_FRAGMENT;
int fhoff, nhoff, ret;
struct frag_hdr *fhdr;
struct frag_queue *fq;
if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
return 0;
+ /* Discard the first fragment if it does not include all headers
+ * RFC 8200, Section 4.5
+ */
+ if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) {
+ pr_debug("Drop incomplete fragment\n");
+ return 0;
+ }
+
if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
return -ENOMEM;
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
#include <net/sock.h>
#include <net/snmp.h>
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ u8 nexthdr;
int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
return 1;
}
+ /* RFC 8200, Section 4.5 Fragment Header:
+ * If the first fragment does not include all headers through an
+ * Upper-Layer header, then that fragment should be discarded and
+ * an ICMP Parameter Problem, Code 3, message should be sent to
+ * the source of the fragment, with the Pointer field set to zero.
+ */
+ nexthdr = hdr->nexthdr;
+ if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) {
+ __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+ return -1;
+ }
+
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
if (tdev && !netif_is_l3_master(tdev)) {
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
- dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
dev->mtu = tdev->mtu - t_hlen;
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
dev->priv_destructor = ipip6_dev_free;
dev->type = ARPHRD_SIT;
- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
dev->min_mtu = IPV6_MIN_MTU;
dev->max_mtu = IP6_MAX_MTU - t_hlen;
__u32 cookie = ntohl(th->ack_seq) - 1;
struct sock *ret = sk;
struct request_sock *req;
- int mss;
+ int full_space, mss;
struct dst_entry *dst;
__u8 rcv_wscale;
u32 tsoff = 0;
}
req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
- tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ full_space = tcp_full_space(sk);
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+ req->rsk_window_clamp = full_space;
+
+ tcp_select_initial_window(sk, full_space, req->mss,
&req->rsk_rcv_wnd, &req->rsk_window_clamp,
ireq->wscale_ok, &rcv_wscale,
dst_metric(dst, RTAX_INITRWND));
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
+ tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :
+ np->tclass;
+
+ if (!INET_ECN_is_capable(tclass) &&
+ tcp_bpf_ca_needs_ecn((struct sock *)req))
+ tclass |= INET_ECN_ECT_0;
+
rcu_read_lock();
opt = ireq->ipv6_opt;
- tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
- tcp_rsk(req)->syn_tos : np->tclass;
if (!opt)
opt = rcu_dereference(np->opt);
err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
- tclass & ~INET_ECN_MASK,
- sk->sk_priority);
+ tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
}
const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
+ bool found_dup_sk = false;
struct tcp_sock *newtp;
struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
tcp_done(newsk);
goto out;
}
- *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+ &found_dup_sk);
if (*own_req) {
tcp_move_syn(newtp, req);
skb_set_owner_r(newnp->pktoptions, newsk);
}
}
+ } else {
+ if (!req_unhash && found_dup_sk) {
+ /* This code path should only be executed in the
+ * syncookie case only
+ */
+ bh_unlock_sock(newsk);
+ sock_put(newsk);
+ newsk = NULL;
+ }
}
return newsk;
return segs;
}
+static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+ __be16 dport)
+{
+ const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+ return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+ &iph->daddr, dport, inet6_iif(skb),
+ inet6_sdif(skb), &udp_table, NULL);
+}
+
INDIRECT_CALLABLE_SCOPE
struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ struct sock *sk = NULL;
struct sk_buff *pp;
- struct sock *sk;
if (unlikely(!uh))
goto flush;
skip:
NAPI_GRO_CB(skb)->is_ipv6 = 1;
rcu_read_lock();
- sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+ if (static_branch_unlikely(&udpv6_encap_needed_key))
+ sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest);
+
pp = udp_gro_receive(head, skb, uh, sk);
rcu_read_unlock();
return pp;
static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
static int __net_init xfrm6_tunnel_net_init(struct net *net)
break;
}
- if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) {
+ if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) &&
+ sk->sk_state == IUCV_CONNECTED) {
if (iucv->transport == AF_IUCV_TRANS_IUCV) {
txmsg.class = 0;
txmsg.tag = 0;
}
/* Create the new socket */
- nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0);
+ nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0);
if (!nsk) {
err = pr_iucv->path_sever(path, user_data);
iucv_path_free(path);
goto out;
}
- nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0);
+ nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0);
bh_lock_sock(sk);
if ((sk->sk_state != IUCV_LISTEN) ||
sk_acceptq_is_full(sk) ||
struct cfg80211_assoc_request *req)
{
bool is_6ghz = req->bss->channel->band == NL80211_BAND_6GHZ;
+ bool is_5ghz = req->bss->channel->band == NL80211_BAND_5GHZ;
struct ieee80211_local *local = sdata->local;
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct ieee80211_bss *bss = (void *)req->bss->priv;
if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap))
memcpy(&assoc_data->ap_vht_cap, vht_ie + 2,
sizeof(struct ieee80211_vht_cap));
- else if (!is_6ghz)
+ else if (is_5ghz)
ifmgd->flags |= IEEE80211_STA_DISABLE_VHT |
IEEE80211_STA_DISABLE_HE;
rcu_read_unlock();
success = !!(info->flags & IEEE80211_TX_STAT_ACK);
for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
- if (ar[i].idx < 0)
+ if (ar[i].idx < 0 || !ar[i].count)
break;
ndx = rix_to_ndx(mi, ar[i].idx);
mi->r[ndx].stats.success += success;
}
- if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0))
- mi->sample_packets++;
-
- if (mi->sample_deferred > 0)
- mi->sample_deferred--;
-
if (time_after(jiffies, mi->last_stats_update +
mp->update_interval / (mp->new_avg ? 2 : 1)))
minstrel_update_stats(mp, mi);
return;
delta = (mi->total_packets * sampling_ratio / 100) -
- (mi->sample_packets + mi->sample_deferred / 2);
+ mi->sample_packets;
/* delta < 0: no sampling required */
prev_sample = mi->prev_sample;
return;
if (mi->total_packets >= 10000) {
- mi->sample_deferred = 0;
mi->sample_packets = 0;
mi->total_packets = 0;
} else if (delta > mi->n_rates * 2) {
* rate sampling method should be used.
* Respect such rates that are not sampled for 20 interations.
*/
- if (mrr_capable &&
- msr->perfect_tx_time > mr->perfect_tx_time &&
- msr->stats.sample_skipped < 20) {
- /* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark
- * packets that have the sampling rate deferred to the
- * second MRR stage. Increase the sample counter only
- * if the deferred sample rate was actually used.
- * Use the sample_deferred counter to make sure that
- * the sampling is not done in large bursts */
- info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
- rate++;
- mi->sample_deferred++;
- } else {
+ if (msr->perfect_tx_time < mr->perfect_tx_time ||
+ msr->stats.sample_skipped >= 20) {
if (!msr->sample_limit)
return;
rate->idx = mi->r[ndx].rix;
rate->count = minstrel_get_retry_count(&mi->r[ndx], info);
+ info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
}
u8 max_prob_rate;
unsigned int total_packets;
unsigned int sample_packets;
- int sample_deferred;
unsigned int sample_row;
unsigned int sample_column;
*/
void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
{
+ /*
+ * If we had used sta_info_pre_move_state() then we might not
+ * have gone through the state transitions down again, so do
+ * it here now (and warn if it's inserted).
+ *
+ * This will clear state such as fast TX/RX that may have been
+ * allocated during state transitions.
+ */
+ while (sta->sta_state > IEEE80211_STA_NONE) {
+ int ret;
+
+ WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+ ret = sta_info_move_state(sta, sta->sta_state - 1);
+ if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+ break;
+ }
+
if (sta->rate_ctrl)
rate_control_free_sta(sta);
out_drop_sta:
local->num_sta--;
synchronize_net();
- __cleanup_single_sta(sta);
+ cleanup_single_sta(sta);
out_err:
mutex_unlock(&local->sta_mtx);
kfree(sinfo);
err = sta_info_insert_check(sta);
if (err) {
+ sta_info_free(local, sta);
mutex_unlock(&local->sta_mtx);
rcu_read_lock();
- goto out_free;
+ return err;
}
- err = sta_info_insert_finish(sta);
- if (err)
- goto out_free;
-
- return 0;
- out_free:
- sta_info_free(local, sta);
- return err;
+ return sta_info_insert_finish(sta);
}
int sta_info_insert(struct sta_info *sta)
void sta_info_stop(struct ieee80211_local *local);
/**
- * sta_info_flush - flush matching STA entries from the STA table
+ * __sta_info_flush - flush matching STA entries from the STA table
*
* Returns the number of removed STA entries.
*
*/
int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans);
+/**
+ * sta_info_flush - flush matching STA entries from the STA table
+ *
+ * Returns the number of removed STA entries.
+ *
+ * @sdata: sdata to remove all stations from
+ */
static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata)
{
return __sta_info_flush(sdata, false);
int ac;
if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER |
- IEEE80211_TX_CTL_AMPDU)) {
+ IEEE80211_TX_CTL_AMPDU |
+ IEEE80211_TX_CTL_HW_80211_ENCAP)) {
ieee80211_free_txskb(&local->hw, skb);
return;
}
ieee80211_mpsp_trigger_process(
ieee80211_get_qos_ctl(hdr), sta, true, acked);
- if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) {
- /*
- * The STA is in power save mode, so assume
- * that this TX packet failed because of that.
- */
- ieee80211_handle_filtered_frame(local, sta, skb);
- return;
- }
-
if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) &&
(ieee80211_is_data(hdr->frame_control)) &&
(rates_idx != -1))
-info->status.ack_signal);
}
} else if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+ /*
+ * The STA is in power save mode, so assume
+ * that this TX packet failed because of that.
+ */
+ if (skb)
+ ieee80211_handle_filtered_frame(local, sta, skb);
return;
} else if (noack_success) {
/* nothing to do here, do not account as lost */
/* device xmit handlers */
+enum ieee80211_encrypt {
+ ENCRYPT_NO,
+ ENCRYPT_MGMT,
+ ENCRYPT_DATA,
+};
+
static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb,
- int head_need, bool may_encrypt)
+ int head_need,
+ enum ieee80211_encrypt encrypt)
{
struct ieee80211_local *local = sdata->local;
- struct ieee80211_hdr *hdr;
bool enc_tailroom;
int tail_need = 0;
- hdr = (struct ieee80211_hdr *) skb->data;
- enc_tailroom = may_encrypt &&
- (sdata->crypto_tx_tailroom_needed_cnt ||
- ieee80211_is_mgmt(hdr->frame_control));
+ enc_tailroom = encrypt == ENCRYPT_MGMT ||
+ (encrypt == ENCRYPT_DATA &&
+ sdata->crypto_tx_tailroom_needed_cnt);
if (enc_tailroom) {
tail_need = IEEE80211_ENCRYPT_TAILROOM;
{
struct ieee80211_local *local = sdata->local;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
- struct ieee80211_hdr *hdr;
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
int headroom;
- bool may_encrypt;
+ enum ieee80211_encrypt encrypt;
- may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT);
+ if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)
+ encrypt = ENCRYPT_NO;
+ else if (ieee80211_is_mgmt(hdr->frame_control))
+ encrypt = ENCRYPT_MGMT;
+ else
+ encrypt = ENCRYPT_DATA;
headroom = local->tx_headroom;
- if (may_encrypt)
+ if (encrypt != ENCRYPT_NO)
headroom += sdata->encrypt_headroom;
headroom -= skb_headroom(skb);
headroom = max_t(int, 0, headroom);
- if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) {
+ if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) {
ieee80211_free_txskb(&local->hw, skb);
return;
}
+ /* reload after potential resize */
hdr = (struct ieee80211_hdr *) skb->data;
info->control.vif = &sdata->vif;
head_need += sdata->encrypt_headroom;
head_need += local->tx_headroom;
head_need = max_t(int, 0, head_need);
- if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
+ if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
ieee80211_free_txskb(&local->hw, skb);
skb = NULL;
return ERR_PTR(-ENOMEM);
if (unlikely(ieee80211_skb_resize(sdata, skb,
max_t(int, extra_head + hw_headroom -
skb_headroom(skb), 0),
- false))) {
+ ENCRYPT_NO))) {
kfree_skb(skb);
return true;
}
tx.skb = skb;
tx.sdata = vif_to_sdata(info->control.vif);
- if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) {
+ if (txq->sta) {
tx.sta = container_of(txq->sta, struct sta_info, sta);
/*
* Drop unicast frames to unauthorised stations unless they are
- * EAPOL frames from the local station.
+ * injected frames or EAPOL frames from the local station.
*/
- if (unlikely(ieee80211_is_data(hdr->frame_control) &&
+ if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) &&
+ ieee80211_is_data(hdr->frame_control) &&
!ieee80211_vif_is_mesh(&tx.sdata->vif) &&
tx.sdata->vif.type != NL80211_IFTYPE_OCB &&
!is_multicast_ether_addr(hdr->addr1) &&
skb_ext_reset(skb);
skb_orphan(skb);
+ /* try to fetch required memory from subflow */
+ if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+ if (ssk->sk_forward_alloc < skb->truesize)
+ goto drop;
+ __sk_mem_reclaim(ssk, skb->truesize);
+ if (!sk_rmem_schedule(sk, skb, skb->truesize))
+ goto drop;
+ }
+
/* the skb map_seq accounts for the skb offset:
* mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
* value
* will retransmit as needed, if needed.
*/
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+drop:
mptcp_drop(sk, skb);
return false;
}
.memory_pressure = &tcp_memory_pressure,
.stream_memory_free = mptcp_memory_free,
.sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem),
+ .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem),
.sysctl_mem = sysctl_tcp_mem,
.obj_size = sizeof(struct mptcp_sock),
.slab_flags = SLAB_TYPESAFE_BY_RCU,
fallback = true;
} else if (subflow_req->mp_join) {
mptcp_get_options(skb, &mp_opt);
- if (!mp_opt.mp_join ||
- !mptcp_can_accept_new_subflow(subflow_req->msk) ||
- !subflow_hmac_valid(req, &mp_opt)) {
+ if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) ||
+ !mptcp_can_accept_new_subflow(subflow_req->msk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
fallback = true;
}
{
struct mptcp_sock *ret = NULL;
struct hlist_nulls_node *pos;
- int slot, num;
+ int slot, num = 0;
for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) {
struct token_bucket *bucket = &token_hash[slot];
ndp->ptype.dev = dev;
dev_add_pack(&ndp->ptype);
- /* Set up generic netlink interface */
- ncsi_init_netlink(dev);
-
pdev = to_platform_device(dev->dev.parent);
if (pdev) {
np = pdev->dev.of_node;
list_del_rcu(&ndp->node);
spin_unlock_irqrestore(&ncsi_dev_lock, flags);
- ncsi_unregister_netlink(nd->dev);
-
kfree(ndp);
}
EXPORT_SYMBOL_GPL(ncsi_unregister_dev);
.n_small_ops = ARRAY_SIZE(ncsi_ops),
};
-int ncsi_init_netlink(struct net_device *dev)
+static int __init ncsi_init_netlink(void)
{
- int rc;
-
- rc = genl_register_family(&ncsi_genl_family);
- if (rc)
- netdev_err(dev, "ncsi: failed to register netlink family\n");
-
- return rc;
-}
-
-int ncsi_unregister_netlink(struct net_device *dev)
-{
- int rc;
-
- rc = genl_unregister_family(&ncsi_genl_family);
- if (rc)
- netdev_err(dev, "ncsi: failed to unregister netlink family\n");
-
- return rc;
+ return genl_register_family(&ncsi_genl_family);
}
+subsys_initcall(ncsi_init_netlink);
struct nlmsghdr *nlhdr,
int err);
-int ncsi_init_netlink(struct net_device *dev);
-int ncsi_unregister_netlink(struct net_device *dev);
-
#endif /* __NCSI_NETLINK_H__ */
static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = {
[IPSET_ATTR_IPADDR_IPV4] = { .type = NLA_U32 },
- [IPSET_ATTR_IPADDR_IPV6] = { .type = NLA_BINARY,
- .len = sizeof(struct in6_addr) },
+ [IPSET_ATTR_IPADDR_IPV6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
};
int
if (SET_WITH_COUNTER(set)) {
struct ip_set_counter *counter = ext_counter(data, set);
+ ip_set_update_counter(counter, ext, flags);
+
if (flags & IPSET_FLAG_MATCH_COUNTERS &&
!(ip_set_match_counter(ip_set_get_packets(counter),
mext->packets, mext->packets_op) &&
ip_set_match_counter(ip_set_get_bytes(counter),
mext->bytes, mext->bytes_op)))
return false;
- ip_set_update_counter(counter, ext, flags);
}
if (SET_WITH_SKBINFO(set))
ip_set_get_skbinfo(ext_skbinfo(data, set),
struct dst_entry *dst = skb_dst(skb);
if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
- ip6_route_me_harder(ipvs->net, skb) != 0)
+ ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
return 1;
} else
#endif
if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
- ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
+ ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
return 1;
return 0;
spin_lock_init(&ipvs->tot_stats.lock);
- proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops,
- sizeof(struct ip_vs_iter));
- proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net,
- ip_vs_stats_show, NULL);
- proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
- ip_vs_stats_percpu_show, NULL);
+#ifdef CONFIG_PROC_FS
+ if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net,
+ &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter)))
+ goto err_vs;
+ if (!proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net,
+ ip_vs_stats_show, NULL))
+ goto err_stats;
+ if (!proc_create_net_single("ip_vs_stats_percpu", 0,
+ ipvs->net->proc_net,
+ ip_vs_stats_percpu_show, NULL))
+ goto err_percpu;
+#endif
if (ip_vs_control_net_init_sysctl(ipvs))
goto err;
return 0;
err:
+#ifdef CONFIG_PROC_FS
+ remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net);
+
+err_percpu:
+ remove_proc_entry("ip_vs_stats", ipvs->net->proc_net);
+
+err_stats:
+ remove_proc_entry("ip_vs", ipvs->net->proc_net);
+
+err_vs:
+#endif
free_percpu(ipvs->tot_stats.cpustats);
return -ENOMEM;
}
{
ip_vs_trash_cleanup(ipvs);
ip_vs_control_net_cleanup_sysctl(ipvs);
+#ifdef CONFIG_PROC_FS
remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net);
remove_proc_entry("ip_vs_stats", ipvs->net->proc_net);
remove_proc_entry("ip_vs", ipvs->net->proc_net);
+#endif
free_percpu(ipvs->tot_stats.cpustats);
}
if (ct->tuplehash[dir].tuple.dst.u3.ip !=
ct->tuplehash[!dir].tuple.src.u3.ip) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
&ct->tuplehash[!dir].tuple.src.u3)) {
- err = nf_ip6_route_me_harder(state->net, skb);
+ err = nf_ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
skb_dst_set_noref(nskb, skb_dst(skb));
nskb->protocol = htons(ETH_P_IP);
- if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+ if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
goto free_nskb;
if (nfct) {
static void lockdep_nfnl_nft_mutex_not_held(void)
{
#ifdef CONFIG_PROVE_LOCKING
- WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+ if (debug_locks)
+ WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
#endif
}
GFP_KERNEL);
kfree(buf);
- if (ctx->report &&
+ if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
return;
audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL);
- if (nlmsg_report(nlh) &&
+ if (!nlmsg_report(nlh) &&
!nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
return;
kfree(trans);
}
-static int __nf_tables_abort(struct net *net, bool autoload)
+static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
{
struct nft_trans *trans, *next;
struct nft_trans_elem *te;
struct nft_hook *hook;
+ if (action == NFNL_ABORT_VALIDATE &&
+ nf_tables_validate(net) < 0)
+ return -EAGAIN;
+
list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
list) {
switch (trans->msg_type) {
nf_tables_abort_release(trans);
}
- if (autoload)
+ if (action == NFNL_ABORT_AUTOLOAD)
nf_tables_module_autoload(net);
else
nf_tables_module_autoload_cleanup(net);
nft_validate_state_update(net, NFT_VALIDATE_SKIP);
}
-static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb,
+ enum nfnl_abort_action action)
{
- int ret = __nf_tables_abort(net, autoload);
+ int ret = __nf_tables_abort(net, action);
mutex_unlock(&net->nft.commit_mutex);
{
mutex_lock(&net->nft.commit_mutex);
if (!list_empty(&net->nft.commit_list))
- __nf_tables_abort(net, false);
+ __nf_tables_abort(net, NFNL_ABORT_NONE);
__nft_release_tables(net);
mutex_unlock(&net->nft.commit_mutex);
WARN_ON_ONCE(!list_empty(&net->nft.tables));
return flow;
}
+void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow,
+ enum flow_dissector_key_id addr_type)
+{
+ struct nft_flow_match *match = &flow->match;
+ struct nft_flow_key *mask = &match->mask;
+ struct nft_flow_key *key = &match->key;
+
+ if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL))
+ return;
+
+ key->control.addr_type = addr_type;
+ mask->control.addr_type = 0xffff;
+ match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL);
+ match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] =
+ offsetof(struct nft_flow_key, control);
+}
+
struct nft_flow_rule *nft_flow_rule_create(struct net *net,
const struct nft_rule *rule)
{
return netlink_ack(skb, nlh, -EINVAL, NULL);
replay:
status = 0;
-
+replay_abort:
skb = netlink_skb_clone(oskb, GFP_KERNEL);
if (!skb)
return netlink_ack(oskb, nlh, -ENOMEM, NULL);
}
done:
if (status & NFNL_BATCH_REPLAY) {
- ss->abort(net, oskb, true);
+ ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
nfnl_err_reset(&err_list);
kfree_skb(skb);
module_put(ss->owner);
status |= NFNL_BATCH_REPLAY;
goto done;
} else if (err) {
- ss->abort(net, oskb, false);
+ ss->abort(net, oskb, NFNL_ABORT_NONE);
netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
}
} else {
- ss->abort(net, oskb, false);
+ enum nfnl_abort_action abort_action;
+
+ if (status & NFNL_BATCH_FAILURE)
+ abort_action = NFNL_ABORT_NONE;
+ else
+ abort_action = NFNL_ABORT_VALIDATE;
+
+ err = ss->abort(net, oskb, abort_action);
+ if (err == -EAGAIN) {
+ nfnl_err_reset(&err_list);
+ kfree_skb(skb);
+ module_put(ss->owner);
+ status |= NFNL_BATCH_FAILURE;
+ goto replay_abort;
+ }
}
if (ss->cleanup)
ss->cleanup(net);
iph->daddr != daddr ||
skb->mark != mark ||
iph->tos != tos) {
- err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
if (err < 0)
ret = NF_DROP_ERR(err);
}
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
flowlabel != *((u32 *)ipv6_hdr(skb)))) {
- err = nf_ip6_route_me_harder(state->net, skb);
+ err = nf_ip6_route_me_harder(state->net, state->sk, skb);
if (err < 0)
ret = NF_DROP_ERR(err);
}
u8 *mask = (u8 *)&flow->match.mask;
u8 *key = (u8 *)&flow->match.key;
- if (priv->op != NFT_CMP_EQ || reg->len != priv->len)
+ if (priv->op != NFT_CMP_EQ || priv->len > reg->len)
return -EOPNOTSUPP;
- memcpy(key + reg->offset, &priv->data, priv->len);
- memcpy(mask + reg->offset, ®->mask, priv->len);
+ memcpy(key + reg->offset, &priv->data, reg->len);
+ memcpy(mask + reg->offset, ®->mask, reg->len);
flow->match.dissector.used_keys |= BIT(reg->key);
flow->match.dissector.offset[reg->key] = reg->base_offset;
nft_reg_load16(priv->data.data) != ARPHRD_ETHER)
return -EOPNOTSUPP;
- nft_offload_update_dependency(ctx, &priv->data, priv->len);
+ nft_offload_update_dependency(ctx, &priv->data, reg->len);
return 0;
}
switch (priv->key) {
case NFT_META_PROTOCOL:
- NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto,
- sizeof(__u16), reg);
+ NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto,
+ sizeof(__u16), reg);
nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
break;
case NFT_META_L4PROTO:
- NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
- sizeof(__u8), reg);
+ NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
+ sizeof(__u8), reg);
nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
break;
case NFT_META_IIF:
- NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta,
- ingress_ifindex, sizeof(__u32), reg);
+ NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta,
+ ingress_ifindex, sizeof(__u32), reg);
break;
case NFT_META_IIFTYPE:
- NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta,
- ingress_iftype, sizeof(__u16), reg);
+ NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta,
+ ingress_iftype, sizeof(__u16), reg);
break;
default:
return -EOPNOTSUPP;
return -1;
}
+static bool nft_payload_offload_mask(struct nft_offload_reg *reg,
+ u32 priv_len, u32 field_len)
+{
+ unsigned int remainder, delta, k;
+ struct nft_data mask = {};
+ __be32 remainder_mask;
+
+ if (priv_len == field_len) {
+ memset(®->mask, 0xff, priv_len);
+ return true;
+ } else if (priv_len > field_len) {
+ return false;
+ }
+
+ memset(&mask, 0xff, field_len);
+ remainder = priv_len % sizeof(u32);
+ if (remainder) {
+ k = priv_len / sizeof(u32);
+ delta = field_len - priv_len;
+ remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1));
+ mask.data[k] = (__force u32)remainder_mask;
+ }
+
+ memcpy(®->mask, &mask, field_len);
+
+ return true;
+}
+
static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
struct nft_flow_rule *flow,
const struct nft_payload *priv)
switch (priv->offset) {
case offsetof(struct ethhdr, h_source):
- if (priv->len != ETH_ALEN)
+ if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
src, ETH_ALEN, reg);
break;
case offsetof(struct ethhdr, h_dest):
- if (priv->len != ETH_ALEN)
+ if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
dst, ETH_ALEN, reg);
break;
case offsetof(struct ethhdr, h_proto):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic,
nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
break;
case offsetof(struct vlan_ethhdr, h_vlan_TCI):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan,
vlan_tci, sizeof(__be16), reg);
break;
case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan,
nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
break;
case offsetof(struct vlan_ethhdr, h_vlan_TCI) + sizeof(struct vlan_hdr):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan,
break;
case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto) +
sizeof(struct vlan_hdr):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan,
switch (priv->offset) {
case offsetof(struct iphdr, saddr):
- if (priv->len != sizeof(struct in_addr))
+ if (!nft_payload_offload_mask(reg, priv->len,
+ sizeof(struct in_addr)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src,
sizeof(struct in_addr), reg);
+ nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
break;
case offsetof(struct iphdr, daddr):
- if (priv->len != sizeof(struct in_addr))
+ if (!nft_payload_offload_mask(reg, priv->len,
+ sizeof(struct in_addr)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst,
sizeof(struct in_addr), reg);
+ nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
break;
case offsetof(struct iphdr, protocol):
- if (priv->len != sizeof(__u8))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
switch (priv->offset) {
case offsetof(struct ipv6hdr, saddr):
- if (priv->len != sizeof(struct in6_addr))
+ if (!nft_payload_offload_mask(reg, priv->len,
+ sizeof(struct in6_addr)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src,
sizeof(struct in6_addr), reg);
+ nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
break;
case offsetof(struct ipv6hdr, daddr):
- if (priv->len != sizeof(struct in6_addr))
+ if (!nft_payload_offload_mask(reg, priv->len,
+ sizeof(struct in6_addr)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst,
sizeof(struct in6_addr), reg);
+ nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
break;
case offsetof(struct ipv6hdr, nexthdr):
- if (priv->len != sizeof(__u8))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
switch (priv->offset) {
case offsetof(struct tcphdr, source):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
sizeof(__be16), reg);
break;
case offsetof(struct tcphdr, dest):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
switch (priv->offset) {
case offsetof(struct udphdr, source):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
sizeof(__be16), reg);
break;
case offsetof(struct udphdr, dest):
- if (priv->len != sizeof(__be16))
+ if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
return -EOPNOTSUPP;
NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
skb->mark == rt_info->mark &&
iph->daddr == rt_info->daddr &&
iph->saddr == rt_info->saddr))
- return ip_route_me_harder(entry->state.net, skb,
- RTN_UNSPEC);
+ return ip_route_me_harder(entry->state.net, entry->state.sk,
+ skb, RTN_UNSPEC);
}
#endif
return 0;
struct netlbl_unlhsh_walk_arg cb_arg;
u32 skip_bkt = cb->args[0];
u32 skip_chain = cb->args[1];
- u32 iter_bkt;
- u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
+ u32 skip_addr4 = cb->args[2];
+ u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
struct netlbl_unlhsh_iface *iface;
struct list_head *iter_list;
struct netlbl_af4list *addr4;
#if IS_ENABLED(CONFIG_IPV6)
+ u32 skip_addr6 = cb->args[3];
struct netlbl_af6list *addr6;
#endif
rcu_read_lock();
for (iter_bkt = skip_bkt;
iter_bkt < rcu_dereference(netlbl_unlhsh)->size;
- iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) {
+ iter_bkt++) {
iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt];
list_for_each_entry_rcu(iface, iter_list, list) {
if (!iface->valid ||
continue;
netlbl_af4list_foreach_rcu(addr4,
&iface->addr4_list) {
- if (iter_addr4++ < cb->args[2])
+ if (iter_addr4++ < skip_addr4)
continue;
if (netlbl_unlabel_staticlist_gen(
NLBL_UNLABEL_C_STATICLIST,
goto unlabel_staticlist_return;
}
}
+ iter_addr4 = 0;
+ skip_addr4 = 0;
#if IS_ENABLED(CONFIG_IPV6)
netlbl_af6list_foreach_rcu(addr6,
&iface->addr6_list) {
- if (iter_addr6++ < cb->args[3])
+ if (iter_addr6++ < skip_addr6)
continue;
if (netlbl_unlabel_staticlist_gen(
NLBL_UNLABEL_C_STATICLIST,
goto unlabel_staticlist_return;
}
}
+ iter_addr6 = 0;
+ skip_addr6 = 0;
#endif /* IPv6 */
}
+ iter_chain = 0;
+ skip_chain = 0;
}
unlabel_staticlist_return:
__be32 lse;
int err;
+ if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+ return -ENOMEM;
+
stack = mpls_hdr(skb);
lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
err = skb_mpls_update_lse(skb, lse);
{
/* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */
struct nlattr *dec_ttl_arg = nla_data(attr);
- int rem = nla_len(attr);
if (nla_len(dec_ttl_arg)) {
- struct nlattr *actions = nla_next(dec_ttl_arg, &rem);
+ struct nlattr *actions = nla_data(dec_ttl_arg);
if (actions)
- return clone_execute(dp, skb, key, 0, actions, rem,
- last, false);
+ return clone_execute(dp, skb, key, 0, nla_data(actions),
+ nla_len(actions), last, false);
}
consume_skb(skb);
return 0;
parms.port_no = OVSP_LOCAL;
parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
- err = ovs_dp_change(dp, a);
- if (err)
- goto err_destroy_meters;
-
/* So far only local changes have been made, now need the lock. */
ovs_lock();
+ err = ovs_dp_change(dp, a);
+ if (err)
+ goto err_unlock_and_destroy_meters;
+
vport = new_vport(&parms);
if (IS_ERR(vport)) {
err = PTR_ERR(vport);
ovs_dp_reset_user_features(skb, info);
}
- ovs_unlock();
- goto err_destroy_meters;
+ goto err_unlock_and_destroy_meters;
}
err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
-err_destroy_meters:
+err_unlock_and_destroy_meters:
+ ovs_unlock();
ovs_meters_exit(dp);
err_destroy_ports:
kfree(dp->ports);
__be16 eth_type, __be16 vlan_tci,
u32 mpls_label_count, bool log)
{
- int start, err;
- u32 nested = true;
+ const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1];
+ int start, action_start, err, rem;
+ const struct nlattr *a, *actions;
+
+ memset(attrs, 0, sizeof(attrs));
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
- if (!nla_len(attr))
- return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL,
- NULL, 0, log);
+ /* Ignore unknown attributes to be future proof. */
+ if (type > OVS_DEC_TTL_ATTR_MAX)
+ continue;
+
+ if (!type || attrs[type])
+ return -EINVAL;
+
+ attrs[type] = a;
+ }
+
+ actions = attrs[OVS_DEC_TTL_ATTR_ACTION];
+ if (rem || !actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
+ return -EINVAL;
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log);
if (start < 0)
return start;
- err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested,
- sizeof(nested), log);
-
- if (err)
- return err;
+ action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log);
+ if (action_start < 0)
+ return start;
- err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type,
+ err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
vlan_tci, mpls_label_count, log);
if (err)
return err;
+ add_nested_action_end(*sfa, action_start);
add_nested_action_end(*sfa, start);
return 0;
}
static int dec_ttl_action_to_attr(const struct nlattr *attr,
struct sk_buff *skb)
{
- int err = 0, rem = nla_len(attr);
- struct nlattr *start;
+ struct nlattr *start, *action_start;
+ const struct nlattr *a;
+ int err = 0, rem;
start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL);
-
if (!start)
return -EMSGSIZE;
- err = ovs_nla_put_actions(nla_data(attr), rem, skb);
- if (err)
- nla_nest_cancel(skb, start);
- else
- nla_nest_end(skb, start);
+ nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) {
+ switch (nla_type(a)) {
+ case OVS_DEC_TTL_ATTR_ACTION:
+
+ action_start = nla_nest_start_noflag(skb, OVS_DEC_TTL_ATTR_ACTION);
+ if (!action_start) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
+ if (err)
+ goto out;
+
+ nla_nest_end(skb, action_start);
+ break;
+ default:
+ /* Ignore all other option to be future compatible */
+ break;
+ }
+ }
+
+ nla_nest_end(skb, start);
+ return 0;
+
+out:
+ nla_nest_cancel(skb, start);
return err;
}
}
int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size)
{
- struct mask_cache *mc = rcu_dereference(table->mask_cache);
+ struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache);
struct mask_cache *new;
if (size == mc->cache_size)
/*
Assumptions:
- - If the device has no dev->header_ops, there is no LL header visible
- above the device. In this case, its hard_header_len should be 0.
+ - If the device has no dev->header_ops->create, there is no LL header
+ visible above the device. In this case, its hard_header_len should be 0.
The device may prepend its own header internally. In this case, its
needed_headroom should be set to the space needed for it to add its
internal header.
On receive:
-----------
-Incoming, dev->header_ops != NULL
+Incoming, dev_has_header(dev) == true
mac_header -> ll header
data -> data
-Outgoing, dev->header_ops != NULL
+Outgoing, dev_has_header(dev) == true
mac_header -> ll header
data -> ll header
-Incoming, dev->header_ops == NULL
+Incoming, dev_has_header(dev) == false
mac_header -> data
However drivers often make it point to the ll header.
This is incorrect because the ll header should be invisible to us.
data -> data
-Outgoing, dev->header_ops == NULL
+Outgoing, dev_has_header(dev) == false
mac_header -> data. ll header is invisible to us.
data -> data
Resume
- If dev->header_ops == NULL we are unable to restore the ll header,
+ If dev_has_header(dev) == false we are unable to restore the ll header,
because it is invisible to us.
skb->dev = dev;
- if (dev->header_ops) {
+ if (dev_has_header(dev)) {
/* The device has an explicit notion of ll header,
* exported to higher levels.
*
if (!net_eq(dev_net(dev), sock_net(sk)))
goto drop;
- if (dev->header_ops) {
+ if (dev_has_header(dev)) {
if (sk->sk_type != SOCK_DGRAM)
skb_push(skb, skb->data - skb_mac_header(skb));
else if (skb->pkt_type == PACKET_OUTGOING) {
rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
conn->c_proposed_version,
UINT_MAX, UINT_MAX, isv6);
- ret = rdma_connect(cm_id, &conn_param);
+ ret = rdma_connect_locked(cm_id, &conn_param);
if (ret)
- rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+ rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+ ret);
out:
/* Beware - returning non-zero tells the rdma_cm to destroy
rfkill->suspended = false;
+ if (!rfkill->registered)
+ return 0;
+
if (!rfkill->persistent) {
cur = !!(rfkill->state & RFKILL_BLOCK_SW);
rfkill_set_block(rfkill, cur);
}
if (frametype == ROSE_CALL_REQUEST) {
- if ((dev = rose_dev_get(dest)) != NULL) {
- if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0)
- kfree_skb(skb);
- } else {
+ if (!rose_loopback_neigh->dev) {
+ kfree_skb(skb);
+ continue;
+ }
+
+ dev = rose_dev_get(dest);
+ if (!dev) {
+ kfree_skb(skb);
+ continue;
+ }
+
+ if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) {
+ dev_put(dev);
kfree_skb(skb);
}
} else {
goto drop;
break;
case TCA_MPLS_ACT_MODIFY:
+ if (!pskb_may_pull(skb,
+ skb_network_offset(skb) + MPLS_HLEN))
+ goto drop;
new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false);
if (skb_mpls_update_lse(skb, new_lse))
goto drop;
module_init(mpls_init_module);
module_exit(mpls_cleanup_module);
+MODULE_SOFTDEP("post: mpls_gso");
MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MPLS manipulation actions");
block_cb->indr.binder_type,
&block->flow_block, tcf_block_shared(block),
&extack);
+ rtnl_lock();
down_write(&block->cb_lock);
list_del(&block_cb->driver_list);
list_move(&block_cb->list, &bo.cb_list);
- up_write(&block->cb_lock);
- rtnl_lock();
tcf_block_unbind(block, &bo);
+ up_write(&block->cb_lock);
rtnl_unlock();
}
/* default uniform distribution */
if (dist == NULL)
- return ((rnd % (2 * sigma)) + mu) - sigma;
+ return ((rnd % (2 * (u32)sigma)) + mu) - sigma;
t = dist->table[rnd % dist->size];
x = (sigma % NETEM_DIST_SCALE) * t;
q->slot_config.max_packets = INT_MAX;
if (q->slot_config.max_bytes == 0)
q->slot_config.max_bytes = INT_MAX;
+
+ /* capping dist_jitter to the range acceptable by tabledist() */
+ q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter));
+
q->slot.packets_left = q->slot_config.max_packets;
q->slot.bytes_left = q->slot_config.max_bytes;
if (q->slot_config.min_delay | q->slot_config.max_delay |
if (tb[TCA_NETEM_SLOT])
get_slot(q, tb[TCA_NETEM_SLOT]);
+ /* capping jitter to the range acceptable by tabledist() */
+ q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+
return ret;
get_table_failure:
else {
if (!mod_timer(&t->proto_unreach_timer,
jiffies + (HZ/20)))
- sctp_association_hold(asoc);
+ sctp_transport_hold(t);
}
} else {
struct net *net = sock_net(sk);
"encountered!\n", __func__);
if (del_timer(&t->proto_unreach_timer))
- sctp_association_put(asoc);
+ sctp_transport_put(t);
sctp_do_sm(net, SCTP_EVENT_T_OTHER,
SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
/* Try again later. */
if (!mod_timer(&transport->proto_unreach_timer,
jiffies + (HZ/20)))
- sctp_association_hold(asoc);
+ sctp_transport_hold(transport);
goto out_unlock;
}
out_unlock:
bh_unlock_sock(sk);
- sctp_association_put(asoc);
+ sctp_transport_put(transport);
}
/* Handle the timeout of the RE-CONFIG timer. */
break;
case SCTP_CMD_INIT_FAILED:
- sctp_cmd_init_failed(commands, asoc, cmd->obj.u32);
+ sctp_cmd_init_failed(commands, asoc, cmd->obj.u16);
break;
case SCTP_CMD_ASSOC_FAILED:
sctp_cmd_assoc_failed(commands, asoc, event_type,
- subtype, chunk, cmd->obj.u32);
+ subtype, chunk, cmd->obj.u16);
break;
case SCTP_CMD_INIT_COUNTER_INC:
/* Delete the ICMP proto unreachable timer if it's active. */
if (del_timer(&transport->proto_unreach_timer))
- sctp_association_put(transport->asoc);
+ sctp_transport_put(transport);
sctp_transport_put(transport);
}
/* check if smc modes and versions of CLC proposal and accept match */
rc = smc_connect_check_aclc(ini, aclc);
- version = aclc->hdr.version == SMC_V1 ? SMC_V1 : version;
+ version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2;
+ ini->smcd_version = version;
if (rc)
goto vlan_cleanup;
/* listen worker: decline and fall back if possible */
static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
- struct smc_init_info *ini, u8 version)
+ int local_first, u8 version)
{
/* RDMA setup failed, switch back to TCP */
- if (ini->first_contact_local)
+ if (local_first)
smc_lgr_cleanup_early(&new_smc->conn);
else
smc_conn_free(&new_smc->conn);
out_unlock:
mutex_unlock(&smc_server_lgr_pending);
out_decl:
- smc_listen_decline(new_smc, rc, ini, version);
+ smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0,
+ version);
out_free:
kfree(ini);
kfree(buf);
struct smc_clnt_opts_area_hdr hdr;
u8 roce[16]; /* RoCEv2 GID */
u8 reserved[16];
- u8 user_eids[0][SMC_MAX_EID_LEN];
+ u8 user_eids[][SMC_MAX_EID_LEN];
};
struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/
struct smc_clc_smcd_v2_extension {
u8 system_eid[SMC_MAX_EID_LEN];
u8 reserved[16];
- struct smc_clc_smcd_gid_chid gidchid[0];
+ struct smc_clc_smcd_gid_chid gidchid[];
};
struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */
ini->ism_peer_gid[ini->ism_selected]) :
smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
!lgr->sync_err &&
- lgr->vlan_id == ini->vlan_id &&
+ (ini->smcd_version == SMC_V2 ||
+ lgr->vlan_id == ini->vlan_id) &&
(role == SMC_CLNT || ini->is_smcd ||
lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
/* link group found */
rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
if (rc) {
kfree(buf_desc);
- return (rc == -ENOMEM) ? ERR_PTR(-EAGAIN) :
- ERR_PTR(-EIO);
+ if (rc == -ENOMEM)
+ return ERR_PTR(-EAGAIN);
+ if (rc == -ENOSPC)
+ return ERR_PTR(-ENOSPC);
+ return ERR_PTR(-EIO);
}
buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
/* CDC header stored in buf. So, pretend it was smaller */
rcu_read_lock();
ndev = rdma_read_gid_attr_ndev_rcu(attr);
if (!IS_ERR(ndev) &&
- ((!vlan_id && !is_vlan_dev(attr->ndev)) ||
- (vlan_id && is_vlan_dev(attr->ndev) &&
- vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
+ ((!vlan_id && !is_vlan_dev(ndev)) ||
+ (vlan_id && is_vlan_dev(ndev) &&
+ vlan_dev_vlan_id(ndev) == vlan_id)) &&
attr->gid_type == IB_GID_TYPE_ROCE) {
rcu_read_unlock();
if (gid)
void *buffer, size_t *lenp, loff_t *ppos)
{
char tmpbuf[256];
- size_t len;
+ ssize_t len;
- if ((*ppos && !write) || !*lenp) {
+ if (write || *ppos) {
*lenp = 0;
return 0;
}
len = svc_print_xprts(tmpbuf, sizeof(tmpbuf));
- *lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
+ len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
- if (*lenp < 0) {
+ if (len < 0) {
*lenp = 0;
return -EINVAL;
}
+ *lenp = len;
return 0;
}
if (fragid == FIRST_FRAGMENT) {
if (unlikely(head))
goto err;
- if (skb_cloned(frag))
- frag = skb_copy(frag, GFP_ATOMIC);
+ *buf = NULL;
+ frag = skb_unshare(frag, GFP_ATOMIC);
if (unlikely(!frag))
goto err;
head = *headbuf = frag;
- *buf = NULL;
TIPC_SKB_CB(head)->tail = NULL;
if (skb_is_nonlinear(head)) {
skb_walk_frags(head, tail) {
else if (prop == TIPC_NLA_PROP_MTU)
tipc_link_set_mtu(e->link, b->mtu);
}
+ /* Update MTU for node link entry */
+ e->mtu = tipc_link_mss(e->link);
tipc_node_write_unlock(n);
tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL);
}
ret = tipc_topsrv_work_start(srv);
if (ret < 0)
- return ret;
+ goto err_start;
ret = tipc_topsrv_create_listener(srv);
if (ret < 0)
- tipc_topsrv_work_stop(srv);
+ goto err_create;
+ return 0;
+
+err_create:
+ tipc_topsrv_work_stop(srv);
+err_start:
+ kfree(srv);
return ret;
}
static bool
tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async,
- s64 resync_req, u32 *seq)
+ s64 resync_req, u32 *seq, u16 *rcd_delta)
{
u32 is_async = resync_req & RESYNC_REQ_ASYNC;
u32 req_seq = resync_req >> 32;
u32 req_end = req_seq + ((resync_req >> 16) & 0xffff);
+ u16 i;
+
+ *rcd_delta = 0;
if (is_async) {
+ /* shouldn't get to wraparound:
+ * too long in async stage, something bad happened
+ */
+ if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX))
+ return false;
+
/* asynchronous stage: log all headers seq such that
* req_seq <= seq <= end_seq, and wait for real resync request
*/
- if (between(*seq, req_seq, req_end) &&
+ if (before(*seq, req_seq))
+ return false;
+ if (!after(*seq, req_end) &&
resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX)
resync_async->log[resync_async->loglen++] = *seq;
+ resync_async->rcd_delta++;
+
return false;
}
/* synchronous stage: check against the logged entries and
* proceed to check the next entries if no match was found
*/
- while (resync_async->loglen) {
- if (req_seq == resync_async->log[resync_async->loglen - 1] &&
- atomic64_try_cmpxchg(&resync_async->req,
- &resync_req, 0)) {
- resync_async->loglen = 0;
+ for (i = 0; i < resync_async->loglen; i++)
+ if (req_seq == resync_async->log[i] &&
+ atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) {
+ *rcd_delta = resync_async->rcd_delta - i;
*seq = req_seq;
+ resync_async->loglen = 0;
+ resync_async->rcd_delta = 0;
return true;
}
- resync_async->loglen--;
- }
+
+ resync_async->loglen = 0;
+ resync_async->rcd_delta = 0;
if (req_seq == *seq &&
atomic64_try_cmpxchg(&resync_async->req,
u32 sock_data, is_req_pending;
struct tls_prot_info *prot;
s64 resync_req;
+ u16 rcd_delta;
u32 req_seq;
if (tls_ctx->rx_conf != TLS_HW)
return;
if (!tls_device_rx_resync_async(rx_ctx->resync_async,
- resync_req, &seq))
+ resync_req, &seq, &rcd_delta))
return;
+ tls_bigint_subtract(rcd_sn, rcd_delta);
break;
}
if (tls_ctx->tx_conf != TLS_HW) {
dev_put(netdev);
tls_ctx->netdev = NULL;
+ } else {
+ set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags);
}
out:
up_read(&device_offload_lock);
if (ctx->tx_conf == TLS_HW)
netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
TLS_OFFLOAD_CTX_DIR_TX);
- if (ctx->rx_conf == TLS_HW)
+ if (ctx->rx_conf == TLS_HW &&
+ !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags))
netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
TLS_OFFLOAD_CTX_DIR_RX);
WRITE_ONCE(ctx->netdev, NULL);
return NULL;
}
+ if (!skb_queue_empty(&sk->sk_receive_queue)) {
+ __strp_unpause(&ctx->strp);
+ if (ctx->recv_pkt)
+ return ctx->recv_pkt;
+ }
+
if (sk->sk_shutdown & RCV_SHUTDOWN)
return NULL;
* another message type
*/
msg->msg_flags |= MSG_EOR;
- if (ctx->control != TLS_RECORD_TYPE_DATA)
+ if (control != TLS_RECORD_TYPE_DATA)
goto recv_end;
} else {
break;
case SOCK_STREAM:
if (vsock_use_local_transport(remote_cid))
new_transport = transport_local;
- else if (remote_cid <= VMADDR_CID_HOST)
+ else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g)
new_transport = transport_g2h;
else
new_transport = transport_h2g;
vsk->buffer_min_size = psk->buffer_min_size;
vsk->buffer_max_size = psk->buffer_max_size;
} else {
- vsk->trusted = capable(CAP_NET_ADMIN);
+ vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
vsk->owner = get_current_cred();
vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE;
virtio_transport_free_pkt(pkt);
}
- if (remove_sock)
+ if (remove_sock) {
+ sock_set_flag(sk, SOCK_DONE);
vsock_remove_sock(vsk);
+ }
}
EXPORT_SYMBOL_GPL(virtio_transport_release);
lock_sock(sk);
- /* Check if sk has been released before lock_sock */
- if (sk->sk_shutdown == SHUTDOWN_MASK) {
+ /* Check if sk has been closed before lock_sock */
+ if (sock_flag(sk, SOCK_DONE)) {
(void)virtio_transport_reset_no_sock(t, pkt);
release_sock(sk);
sock_put(sk);
}
EXPORT_SYMBOL(cfg80211_stop_iface);
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
- struct wireless_dev *wdev)
+void cfg80211_init_wdev(struct wireless_dev *wdev)
{
mutex_init(&wdev->mtx);
INIT_LIST_HEAD(&wdev->event_list);
spin_lock_init(&wdev->pmsr_lock);
INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
+#ifdef CONFIG_CFG80211_WEXT
+ wdev->wext.default_key = -1;
+ wdev->wext.default_mgmt_key = -1;
+ wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
+#endif
+
+ if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
+ wdev->ps = true;
+ else
+ wdev->ps = false;
+ /* allow mac80211 to determine the timeout */
+ wdev->ps_timeout = -1;
+
+ if ((wdev->iftype == NL80211_IFTYPE_STATION ||
+ wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
+ wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
+ wdev->netdev->priv_flags |= IFF_DONT_BRIDGE;
+
+ INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
+}
+
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+ struct wireless_dev *wdev)
+{
/*
* We get here also when the interface changes network namespaces,
* as it's registered into the new one, but we don't want it to
switch (state) {
case NETDEV_POST_INIT:
SET_NETDEV_DEVTYPE(dev, &wiphy_type);
+ wdev->netdev = dev;
+ /* can only change netns with wiphy */
+ dev->features |= NETIF_F_NETNS_LOCAL;
+
+ cfg80211_init_wdev(wdev);
break;
case NETDEV_REGISTER:
/*
* called within code protected by it when interfaces
* are added with nl80211.
*/
- /* can only change netns with wiphy */
- dev->features |= NETIF_F_NETNS_LOCAL;
-
if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj,
"phy80211")) {
pr_err("failed to add phy80211 symlink to netdev!\n");
}
- wdev->netdev = dev;
-#ifdef CONFIG_CFG80211_WEXT
- wdev->wext.default_key = -1;
- wdev->wext.default_mgmt_key = -1;
- wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
-#endif
-
- if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
- wdev->ps = true;
- else
- wdev->ps = false;
- /* allow mac80211 to determine the timeout */
- wdev->ps_timeout = -1;
-
- if ((wdev->iftype == NL80211_IFTYPE_STATION ||
- wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
- wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
- dev->priv_flags |= IFF_DONT_BRIDGE;
-
- INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
- cfg80211_init_wdev(rdev, wdev);
+ cfg80211_register_wdev(rdev, wdev);
break;
case NETDEV_GOING_DOWN:
cfg80211_leave(rdev, wdev);
int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
struct net *net);
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
- struct wireless_dev *wdev);
+void cfg80211_init_wdev(struct wireless_dev *wdev);
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+ struct wireless_dev *wdev);
static inline void wdev_lock(struct wireless_dev *wdev)
__acquires(wdev)
* P2P Device and NAN do not have a netdev, so don't go
* through the netdev notifier and must be added here
*/
- cfg80211_init_wdev(rdev, wdev);
+ cfg80211_init_wdev(wdev);
+ cfg80211_register_wdev(rdev, wdev);
break;
default:
break;
power_rule = ®_rule->power_rule;
if (reg_rule->flags & NL80211_RRF_AUTO_BW)
- snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+ snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO",
freq_range->max_bandwidth_khz,
reg_get_max_bandwidth(rd, reg_rule));
else
int len, i, rc = 0;
if (addr_len != sizeof(struct sockaddr_x25) ||
- addr->sx25_family != AF_X25) {
+ addr->sx25_family != AF_X25 ||
+ strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) {
rc = -EINVAL;
goto out;
}
rc = -EINVAL;
if (addr_len != sizeof(struct sockaddr_x25) ||
- addr->sx25_family != AF_X25)
+ addr->sx25_family != AF_X25 ||
+ strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN)
goto out;
rc = -ENETUNREACH;
sock->state = SS_CONNECTED;
rc = 0;
out_put_neigh:
- if (rc) {
+ if (rc && x25->neighbour) {
read_lock_bh(&x25_list_lock);
x25_neigh_put(x25->neighbour);
x25->neighbour = NULL;
makex25->lci = lci;
makex25->dest_addr = dest_addr;
makex25->source_addr = source_addr;
+ x25_neigh_hold(nb);
makex25->neighbour = nb;
makex25->facilities = facilities;
makex25->dte_facilities= dte_facilities;
kfree(umem);
}
+static void xdp_umem_release_deferred(struct work_struct *work)
+{
+ struct xdp_umem *umem = container_of(work, struct xdp_umem, work);
+
+ xdp_umem_release(umem);
+}
+
void xdp_get_umem(struct xdp_umem *umem)
{
refcount_inc(&umem->users);
}
-void xdp_put_umem(struct xdp_umem *umem)
+void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup)
{
if (!umem)
return;
- if (refcount_dec_and_test(&umem->users))
- xdp_umem_release(umem);
+ if (refcount_dec_and_test(&umem->users)) {
+ if (defer_cleanup) {
+ INIT_WORK(&umem->work, xdp_umem_release_deferred);
+ schedule_work(&umem->work);
+ } else {
+ xdp_umem_release(umem);
+ }
+ }
}
static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
#include <net/xdp_sock_drv.h>
void xdp_get_umem(struct xdp_umem *umem);
-void xdp_put_umem(struct xdp_umem *umem);
+void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup);
struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr);
#endif /* XDP_UMEM_H_ */
skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
skb->destructor = xsk_destruct_skb;
- /* Hinder dev_direct_xmit from freeing the packet and
- * therefore completing it in the destructor
- */
- refcount_inc(&skb->users);
- err = dev_direct_xmit(skb, xs->queue_id);
+ err = __dev_direct_xmit(skb, xs->queue_id);
if (err == NETDEV_TX_BUSY) {
/* Tell user-space to retry the send */
skb->destructor = sock_wfree;
/* Ignore NET_XMIT_CN as packet might have been sent */
if (err == NET_XMIT_DROP) {
/* SKB completed but not sent */
- kfree_skb(skb);
err = -EBUSY;
goto out;
}
- consume_skb(skb);
sent_frame = true;
}
if (!sock_flag(sk, SOCK_DEAD))
return;
- xp_put_pool(xs->pool);
+ if (!xp_put_pool(xs->pool))
+ xdp_put_umem(xs->umem, !xs->pool);
sk_refcnt_debug_dec(sk);
}
err_unreg_pool:
if (!force_zc)
err = 0; /* fallback to copy mode */
- if (err)
+ if (err) {
xsk_clear_pool_at_qid(netdev, queue_id);
+ dev_put(netdev);
+ }
return err;
}
pool->cq = NULL;
}
- xdp_put_umem(pool->umem);
+ xdp_put_umem(pool->umem, false);
xp_destroy(pool);
}
refcount_inc(&pool->users);
}
-void xp_put_pool(struct xsk_buff_pool *pool)
+bool xp_put_pool(struct xsk_buff_pool *pool)
{
if (!pool)
- return;
+ return false;
if (refcount_dec_and_test(&pool->users)) {
INIT_WORK(&pool->work, xp_release_deferred);
schedule_work(&pool->work);
+ return true;
}
+
+ return false;
}
static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
.handler = xfrmi6_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi6_err,
- .priority = -1,
+ .priority = 2,
};
static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
.handler = xfrmi6_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi6_err,
- .priority = -1,
+ .priority = 2,
};
#endif
.handler = xfrmi4_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi4_err,
- .priority = -1,
+ .priority = 3,
};
static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = {
.handler = xfrmi4_rcv_tunnel,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi4_err,
- .priority = -1,
+ .priority = 2,
};
#endif
int err = -ENOENT;
__be32 minspi = htonl(low);
__be32 maxspi = htonl(high);
+ __be32 newspi = 0;
u32 mark = x->mark.v & x->mark.m;
spin_lock_bh(&x->lock);
xfrm_state_put(x0);
goto unlock;
}
- x->id.spi = minspi;
+ newspi = minspi;
} else {
u32 spi = 0;
for (h = 0; h < high-low+1; h++) {
spi = low + prandom_u32()%(high-low+1);
x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
if (x0 == NULL) {
- x->id.spi = htonl(spi);
+ newspi = htonl(spi);
break;
}
xfrm_state_put(x0);
}
}
- if (x->id.spi) {
+ if (newspi) {
spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ x->id.spi = newspi;
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
int main(int argc, char **argv)
{
- struct rlimit r = {1024*1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
extern char __executable_start;
char filename[256], buf[256];
__u64 uprobe_file_offset;
int main(int ac, char **argv)
{
- struct rlimit r = {1024*1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
long key, next_key, value;
struct bpf_link *links[2];
struct bpf_program *prog;
int main(int ac, char **argv)
{
- struct rlimit r = {1024*1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_link *links[2];
struct bpf_program *prog;
struct bpf_object *obj;
int main(int argc, char **argv)
{
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs";
char *mprog_filename = "xdp_redirect_kern.o";
char *redir_interface = NULL, *redir_map = NULL;
int main(int argc, char **argv)
{
__u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */
- struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
struct bpf_prog_load_attr prog_load_attr = {
.prog_type = BPF_PROG_TYPE_XDP,
};
asm (
" .pushsection .text, \"ax\", @progbits\n"
" .type my_tramp1, @function\n"
+" .globl my_tramp1\n"
" my_tramp1:"
" pushq %rbp\n"
" movq %rsp, %rbp\n"
" .size my_tramp1, .-my_tramp1\n"
" ret\n"
" .type my_tramp2, @function\n"
+" .globl my_tramp2\n"
" my_tramp2:"
" pushq %rbp\n"
" movq %rsp, %rbp\n"
asm (
" .pushsection .text, \"ax\", @progbits\n"
" .type my_tramp, @function\n"
+" .globl my_tramp\n"
" my_tramp:"
" pushq %rbp\n"
" movq %rsp, %rbp\n"
asm (
" .pushsection .text, \"ax\", @progbits\n"
" .type my_tramp, @function\n"
+" .globl my_tramp\n"
" my_tramp:"
" pushq %rbp\n"
" movq %rsp, %rbp\n"
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-mpssd
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0
-ifndef CROSS_COMPILE
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-
-ifeq ($(ARCH),x86)
-
-PROGS := mpssd
-CC = $(CROSS_COMPILE)gcc
-CFLAGS := -I../../../usr/include -I../../../tools/include
-
-ifdef DEBUG
-CFLAGS += -DDEBUG=$(DEBUG)
-endif
-
-all: $(PROGS)
-mpssd: mpssd.c sysfs.c
- $(CC) $(CFLAGS) mpssd.c sysfs.c -o mpssd -lpthread
-
-install:
- install mpssd /usr/sbin/mpssd
- install micctrl /usr/sbin/micctrl
-
-clean:
- rm -fr $(PROGS)
-
-endif
-endif
+++ /dev/null
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-# Intel MIC Platform Software Stack (MPSS)
-#
-# Copyright(c) 2013 Intel Corporation.
-#
-# Intel MIC User Space Tools.
-#
-# micctrl - Controls MIC boot/start/stop.
-#
-# chkconfig: 2345 95 05
-# description: start MPSS stack processing.
-#
-### BEGIN INIT INFO
-# Provides: micctrl
-### END INIT INFO
-
-# Source function library.
-. /etc/init.d/functions
-
-sysfs="/sys/class/mic"
-
-_status()
-{
- f=$sysfs/$1
- echo -e $1 state: "`cat $f/state`" shutdown_status: "`cat $f/shutdown_status`"
-}
-
-status()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _status $1
- return $?
- fi
- for f in $sysfs/*
- do
- _status `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_reset()
-{
- f=$sysfs/$1
- echo reset > $f/state
-}
-
-reset()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _reset $1
- return $?
- fi
- for f in $sysfs/*
- do
- _reset `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_boot()
-{
- f=$sysfs/$1
- echo "linux" > $f/bootmode
- echo "mic/uos.img" > $f/firmware
- echo "mic/$1.image" > $f/ramdisk
- echo "boot" > $f/state
-}
-
-boot()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _boot $1
- return $?
- fi
- for f in $sysfs/*
- do
- _boot `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_shutdown()
-{
- f=$sysfs/$1
- echo shutdown > $f/state
-}
-
-shutdown()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _shutdown $1
- return $?
- fi
- for f in $sysfs/*
- do
- _shutdown `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-_wait()
-{
- f=$sysfs/$1
- while [ "`cat $f/state`" != "offline" -a "`cat $f/state`" != "online" ]
- do
- sleep 1
- echo -e "Waiting for $1 to go offline"
- done
-}
-
-wait()
-{
- if [ "`echo $1 | head -c3`" == "mic" ]; then
- _wait $1
- return $?
- fi
- # Wait for the cards to go offline
- for f in $sysfs/*
- do
- _wait `basename $f`
- RETVAL=$?
- [ $RETVAL -ne 0 ] && return $RETVAL
- done
- return 0
-}
-
-if [ ! -d "$sysfs" ]; then
- echo -e $"Module unloaded "
- exit 3
-fi
-
-case $1 in
- -s)
- status $2
- ;;
- -r)
- reset $2
- ;;
- -b)
- boot $2
- ;;
- -S)
- shutdown $2
- ;;
- -w)
- wait $2
- ;;
- *)
- echo $"Usage: $0 {-s (status) |-r (reset) |-b (boot) |-S (shutdown) |-w (wait)}"
- exit 2
-esac
-
-exit $?
+++ /dev/null
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-# Intel MIC Platform Software Stack (MPSS)
-#
-# Copyright(c) 2013 Intel Corporation.
-#
-# Intel MIC User Space Tools.
-#
-# mpss Start mpssd.
-#
-# chkconfig: 2345 95 05
-# description: start MPSS stack processing.
-#
-### BEGIN INIT INFO
-# Provides: mpss
-# Required-Start:
-# Required-Stop:
-# Short-Description: MPSS stack control
-# Description: MPSS stack control
-### END INIT INFO
-
-# Source function library.
-. /etc/init.d/functions
-
-exec=/usr/sbin/mpssd
-sysfs="/sys/class/mic"
-mic_modules="mic_host mic_x100_dma scif vop"
-
-start()
-{
- [ -x $exec ] || exit 5
-
- if [ "`ps -e | awk '{print $4}' | grep mpssd | head -1`" = "mpssd" ]; then
- echo -e $"MPSSD already running! "
- success
- echo
- return 0
- fi
-
- echo -e $"Starting MPSS Stack"
- echo -e $"Loading MIC drivers:" $mic_modules
-
- modprobe -a $mic_modules
- RETVAL=$?
- if [ $RETVAL -ne 0 ]; then
- failure
- echo
- return $RETVAL
- fi
-
- # Start the daemon
- echo -n $"Starting MPSSD "
- $exec
- RETVAL=$?
- if [ $RETVAL -ne 0 ]; then
- failure
- echo
- return $RETVAL
- fi
- success
- echo
-
- sleep 5
-
- # Boot the cards
- micctrl -b
-
- # Wait till ping works
- for f in $sysfs/*
- do
- count=100
- ipaddr=`cat $f/cmdline`
- ipaddr=${ipaddr#*address,}
- ipaddr=`echo $ipaddr | cut -d, -f1 | cut -d\; -f1`
- while [ $count -ge 0 ]
- do
- echo -e "Pinging "`basename $f`" "
- ping -c 1 $ipaddr &> /dev/null
- RETVAL=$?
- if [ $RETVAL -eq 0 ]; then
- success
- break
- fi
- sleep 1
- count=`expr $count - 1`
- done
- [ $RETVAL -ne 0 ] && failure || success
- echo
- done
- return $RETVAL
-}
-
-stop()
-{
- echo -e $"Shutting down MPSS Stack: "
-
- # Bail out if module is unloaded
- if [ ! -d "$sysfs" ]; then
- echo -n $"Module unloaded "
- success
- echo
- return 0
- fi
-
- # Shut down the cards.
- micctrl -S
-
- # Wait for the cards to go offline
- for f in $sysfs/*
- do
- while [ "`cat $f/state`" != "ready" ]
- do
- sleep 1
- echo -e "Waiting for "`basename $f`" to become ready"
- done
- done
-
- # Display the status of the cards
- micctrl -s
-
- # Kill MPSSD now
- echo -n $"Killing MPSSD"
- killall -9 mpssd 2>/dev/null
- RETVAL=$?
- [ $RETVAL -ne 0 ] && failure || success
- echo
- return $RETVAL
-}
-
-restart()
-{
- stop
- sleep 5
- start
-}
-
-status()
-{
- micctrl -s
- if [ "`ps -e | awk '{print $4}' | grep mpssd | head -n 1`" = "mpssd" ]; then
- echo "mpssd is running"
- else
- echo "mpssd is stopped"
- fi
- return 0
-}
-
-unload()
-{
- if [ ! -d "$sysfs" ]; then
- echo -n $"No MIC_HOST Module: "
- success
- echo
- return
- fi
-
- stop
-
- sleep 5
- echo -n $"Removing MIC drivers:" $mic_modules
- modprobe -r $mic_modules
- RETVAL=$?
- [ $RETVAL -ne 0 ] && failure || success
- echo
- return $RETVAL
-}
-
-case $1 in
- start)
- start
- ;;
- stop)
- stop
- ;;
- restart)
- restart
- ;;
- status)
- status
- ;;
- unload)
- unload
- ;;
- *)
- echo $"Usage: $0 {start|stop|restart|status|unload}"
- exit 2
-esac
-
-exit $?
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-
-#define _GNU_SOURCE
-
-#include <stdlib.h>
-#include <fcntl.h>
-#include <getopt.h>
-#include <assert.h>
-#include <unistd.h>
-#include <stdbool.h>
-#include <signal.h>
-#include <poll.h>
-#include <features.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <sys/socket.h>
-#include <linux/virtio_ring.h>
-#include <linux/virtio_net.h>
-#include <linux/virtio_console.h>
-#include <linux/virtio_blk.h>
-#include <linux/version.h>
-#include "mpssd.h"
-#include <linux/mic_ioctl.h>
-#include <linux/mic_common.h>
-#include <tools/endian.h>
-
-static void *init_mic(void *arg);
-
-static FILE *logfp;
-static struct mic_info mic_list;
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-
-#define min_t(type, x, y) ({ \
- type __min1 = (x); \
- type __min2 = (y); \
- __min1 < __min2 ? __min1 : __min2; })
-
-/* align addr on a size boundary - adjust address up/down if needed */
-#define _ALIGN_DOWN(addr, size) ((addr)&(~((size)-1)))
-#define _ALIGN_UP(addr, size) _ALIGN_DOWN(addr + size - 1, size)
-
-/* align addr on a size boundary - adjust address up if needed */
-#define _ALIGN(addr, size) _ALIGN_UP(addr, size)
-
-/* to align the pointer to the (next) page boundary */
-#define PAGE_ALIGN(addr) _ALIGN(addr, PAGE_SIZE)
-
-#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
-
-#define GSO_ENABLED 1
-#define MAX_GSO_SIZE (64 * 1024)
-#define ETH_H_LEN 14
-#define MAX_NET_PKT_SIZE (_ALIGN_UP(MAX_GSO_SIZE + ETH_H_LEN, 64))
-#define MIC_DEVICE_PAGE_END 0x1000
-
-#ifndef VIRTIO_NET_HDR_F_DATA_VALID
-#define VIRTIO_NET_HDR_F_DATA_VALID 2 /* Csum is valid */
-#endif
-
-static struct {
- struct mic_device_desc dd;
- struct mic_vqconfig vqconfig[2];
- __u32 host_features, guest_acknowledgements;
- struct virtio_console_config cons_config;
-} virtcons_dev_page = {
- .dd = {
- .type = VIRTIO_ID_CONSOLE,
- .num_vq = ARRAY_SIZE(virtcons_dev_page.vqconfig),
- .feature_len = sizeof(virtcons_dev_page.host_features),
- .config_len = sizeof(virtcons_dev_page.cons_config),
- },
- .vqconfig[0] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
- .vqconfig[1] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
-};
-
-static struct {
- struct mic_device_desc dd;
- struct mic_vqconfig vqconfig[2];
- __u32 host_features, guest_acknowledgements;
- struct virtio_net_config net_config;
-} virtnet_dev_page = {
- .dd = {
- .type = VIRTIO_ID_NET,
- .num_vq = ARRAY_SIZE(virtnet_dev_page.vqconfig),
- .feature_len = sizeof(virtnet_dev_page.host_features),
- .config_len = sizeof(virtnet_dev_page.net_config),
- },
- .vqconfig[0] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
- .vqconfig[1] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
-#if GSO_ENABLED
- .host_features = htole32(
- 1 << VIRTIO_NET_F_CSUM |
- 1 << VIRTIO_NET_F_GSO |
- 1 << VIRTIO_NET_F_GUEST_TSO4 |
- 1 << VIRTIO_NET_F_GUEST_TSO6 |
- 1 << VIRTIO_NET_F_GUEST_ECN),
-#else
- .host_features = 0,
-#endif
-};
-
-static const char *mic_config_dir = "/etc/mpss";
-static const char *virtblk_backend = "VIRTBLK_BACKEND";
-static struct {
- struct mic_device_desc dd;
- struct mic_vqconfig vqconfig[1];
- __u32 host_features, guest_acknowledgements;
- struct virtio_blk_config blk_config;
-} virtblk_dev_page = {
- .dd = {
- .type = VIRTIO_ID_BLOCK,
- .num_vq = ARRAY_SIZE(virtblk_dev_page.vqconfig),
- .feature_len = sizeof(virtblk_dev_page.host_features),
- .config_len = sizeof(virtblk_dev_page.blk_config),
- },
- .vqconfig[0] = {
- .num = htole16(MIC_VRING_ENTRIES),
- },
- .host_features =
- htole32(1<<VIRTIO_BLK_F_SEG_MAX),
- .blk_config = {
- .seg_max = htole32(MIC_VRING_ENTRIES - 2),
- .capacity = htole64(0),
- }
-};
-
-static char *myname;
-
-static int
-tap_configure(struct mic_info *mic, char *dev)
-{
- pid_t pid;
- char *ifargv[7];
- char ipaddr[IFNAMSIZ];
- int ret = 0;
-
- pid = fork();
- if (pid == 0) {
- ifargv[0] = "ip";
- ifargv[1] = "link";
- ifargv[2] = "set";
- ifargv[3] = dev;
- ifargv[4] = "up";
- ifargv[5] = NULL;
- mpsslog("Configuring %s\n", dev);
- ret = execvp("ip", ifargv);
- if (ret < 0) {
- mpsslog("%s execvp failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
- }
- if (pid < 0) {
- mpsslog("%s fork failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
-
- ret = waitpid(pid, NULL, 0);
- if (ret < 0) {
- mpsslog("%s waitpid failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
-
- snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id + 1);
-
- pid = fork();
- if (pid == 0) {
- ifargv[0] = "ip";
- ifargv[1] = "addr";
- ifargv[2] = "add";
- ifargv[3] = ipaddr;
- ifargv[4] = "dev";
- ifargv[5] = dev;
- ifargv[6] = NULL;
- mpsslog("Configuring %s ipaddr %s\n", dev, ipaddr);
- ret = execvp("ip", ifargv);
- if (ret < 0) {
- mpsslog("%s execvp failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
- }
- if (pid < 0) {
- mpsslog("%s fork failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
-
- ret = waitpid(pid, NULL, 0);
- if (ret < 0) {
- mpsslog("%s waitpid failed errno %s\n",
- mic->name, strerror(errno));
- return ret;
- }
- mpsslog("MIC name %s %s %d DONE!\n",
- mic->name, __func__, __LINE__);
- return 0;
-}
-
-static int tun_alloc(struct mic_info *mic, char *dev)
-{
- struct ifreq ifr;
- int fd, err;
-#if GSO_ENABLED
- unsigned offload;
-#endif
- fd = open("/dev/net/tun", O_RDWR);
- if (fd < 0) {
- mpsslog("Could not open /dev/net/tun %s\n", strerror(errno));
- goto done;
- }
-
- memset(&ifr, 0, sizeof(ifr));
-
- ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
- if (*dev)
- strncpy(ifr.ifr_name, dev, IFNAMSIZ);
-
- err = ioctl(fd, TUNSETIFF, (void *)&ifr);
- if (err < 0) {
- mpsslog("%s %s %d TUNSETIFF failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- close(fd);
- return err;
- }
-#if GSO_ENABLED
- offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_TSO_ECN;
-
- err = ioctl(fd, TUNSETOFFLOAD, offload);
- if (err < 0) {
- mpsslog("%s %s %d TUNSETOFFLOAD failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- close(fd);
- return err;
- }
-#endif
- strcpy(dev, ifr.ifr_name);
- mpsslog("Created TAP %s\n", dev);
-done:
- return fd;
-}
-
-#define NET_FD_VIRTIO_NET 0
-#define NET_FD_TUN 1
-#define MAX_NET_FD 2
-
-static void set_dp(struct mic_info *mic, int type, void *dp)
-{
- switch (type) {
- case VIRTIO_ID_CONSOLE:
- mic->mic_console.console_dp = dp;
- return;
- case VIRTIO_ID_NET:
- mic->mic_net.net_dp = dp;
- return;
- case VIRTIO_ID_BLOCK:
- mic->mic_virtblk.block_dp = dp;
- return;
- }
- mpsslog("%s %s %d not found\n", mic->name, __func__, type);
- assert(0);
-}
-
-static void *get_dp(struct mic_info *mic, int type)
-{
- switch (type) {
- case VIRTIO_ID_CONSOLE:
- return mic->mic_console.console_dp;
- case VIRTIO_ID_NET:
- return mic->mic_net.net_dp;
- case VIRTIO_ID_BLOCK:
- return mic->mic_virtblk.block_dp;
- }
- mpsslog("%s %s %d not found\n", mic->name, __func__, type);
- assert(0);
- return NULL;
-}
-
-static struct mic_device_desc *get_device_desc(struct mic_info *mic, int type)
-{
- struct mic_device_desc *d;
- int i;
- void *dp = get_dp(mic, type);
-
- for (i = sizeof(struct mic_bootparam); i < PAGE_SIZE;
- i += mic_total_desc_size(d)) {
- d = dp + i;
-
- /* End of list */
- if (d->type == 0)
- break;
-
- if (d->type == -1)
- continue;
-
- mpsslog("%s %s d-> type %d d %p\n",
- mic->name, __func__, d->type, d);
-
- if (d->type == (__u8)type)
- return d;
- }
- mpsslog("%s %s %d not found\n", mic->name, __func__, type);
- return NULL;
-}
-
-/* See comments in vhost.c for explanation of next_desc() */
-static unsigned next_desc(struct vring_desc *desc)
-{
- unsigned int next;
-
- if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT))
- return -1U;
- next = le16toh(desc->next);
- return next;
-}
-
-/* Sum up all the IOVEC length */
-static ssize_t
-sum_iovec_len(struct mic_copy_desc *copy)
-{
- ssize_t sum = 0;
- unsigned int i;
-
- for (i = 0; i < copy->iovcnt; i++)
- sum += copy->iov[i].iov_len;
- return sum;
-}
-
-static inline void verify_out_len(struct mic_info *mic,
- struct mic_copy_desc *copy)
-{
- if (copy->out_len != sum_iovec_len(copy)) {
- mpsslog("%s %s %d BUG copy->out_len 0x%x len 0x%zx\n",
- mic->name, __func__, __LINE__,
- copy->out_len, sum_iovec_len(copy));
- assert(copy->out_len == sum_iovec_len(copy));
- }
-}
-
-/* Display an iovec */
-static void
-disp_iovec(struct mic_info *mic, struct mic_copy_desc *copy,
- const char *s, int line)
-{
- unsigned int i;
-
- for (i = 0; i < copy->iovcnt; i++)
- mpsslog("%s %s %d copy->iov[%d] addr %p len 0x%zx\n",
- mic->name, s, line, i,
- copy->iov[i].iov_base, copy->iov[i].iov_len);
-}
-
-static inline __u16 read_avail_idx(struct mic_vring *vr)
-{
- return READ_ONCE(vr->info->avail_idx);
-}
-
-static inline void txrx_prepare(int type, bool tx, struct mic_vring *vr,
- struct mic_copy_desc *copy, ssize_t len)
-{
- copy->vr_idx = tx ? 0 : 1;
- copy->update_used = true;
- if (type == VIRTIO_ID_NET)
- copy->iov[1].iov_len = len - sizeof(struct virtio_net_hdr);
- else
- copy->iov[0].iov_len = len;
-}
-
-/* Central API which triggers the copies */
-static int
-mic_virtio_copy(struct mic_info *mic, int fd,
- struct mic_vring *vr, struct mic_copy_desc *copy)
-{
- int ret;
-
- ret = ioctl(fd, MIC_VIRTIO_COPY_DESC, copy);
- if (ret) {
- mpsslog("%s %s %d errno %s ret %d\n",
- mic->name, __func__, __LINE__,
- strerror(errno), ret);
- }
- return ret;
-}
-
-static inline unsigned _vring_size(unsigned int num, unsigned long align)
-{
- return _ALIGN_UP(((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num)
- + align - 1) & ~(align - 1))
- + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num, 4);
-}
-
-/*
- * This initialization routine requires at least one
- * vring i.e. vr0. vr1 is optional.
- */
-static void *
-init_vr(struct mic_info *mic, int fd, int type,
- struct mic_vring *vr0, struct mic_vring *vr1, int num_vq)
-{
- int vr_size;
- char *va;
-
- vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
- MIC_VIRTIO_RING_ALIGN) +
- sizeof(struct _mic_vring_info));
- va = mmap(NULL, MIC_DEVICE_PAGE_END + vr_size * num_vq,
- PROT_READ, MAP_SHARED, fd, 0);
- if (MAP_FAILED == va) {
- mpsslog("%s %s %d mmap failed errno %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- goto done;
- }
- set_dp(mic, type, va);
- vr0->va = (struct mic_vring *)&va[MIC_DEVICE_PAGE_END];
- vr0->info = vr0->va +
- _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN);
- vring_init(&vr0->vr,
- MIC_VRING_ENTRIES, vr0->va, MIC_VIRTIO_RING_ALIGN);
- mpsslog("%s %s vr0 %p vr0->info %p vr_size 0x%x vring 0x%x ",
- __func__, mic->name, vr0->va, vr0->info, vr_size,
- _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
- mpsslog("magic 0x%x expected 0x%x\n",
- le32toh(vr0->info->magic), MIC_MAGIC + type);
- assert(le32toh(vr0->info->magic) == MIC_MAGIC + type);
- if (vr1) {
- vr1->va = (struct mic_vring *)
- &va[MIC_DEVICE_PAGE_END + vr_size];
- vr1->info = vr1->va + _vring_size(MIC_VRING_ENTRIES,
- MIC_VIRTIO_RING_ALIGN);
- vring_init(&vr1->vr,
- MIC_VRING_ENTRIES, vr1->va, MIC_VIRTIO_RING_ALIGN);
- mpsslog("%s %s vr1 %p vr1->info %p vr_size 0x%x vring 0x%x ",
- __func__, mic->name, vr1->va, vr1->info, vr_size,
- _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN));
- mpsslog("magic 0x%x expected 0x%x\n",
- le32toh(vr1->info->magic), MIC_MAGIC + type + 1);
- assert(le32toh(vr1->info->magic) == MIC_MAGIC + type + 1);
- }
-done:
- return va;
-}
-
-static int
-wait_for_card_driver(struct mic_info *mic, int fd, int type)
-{
- struct pollfd pollfd;
- int err;
- struct mic_device_desc *desc = get_device_desc(mic, type);
- __u8 prev_status;
-
- if (!desc)
- return -ENODEV;
- prev_status = desc->status;
- pollfd.fd = fd;
- mpsslog("%s %s Waiting .... desc-> type %d status 0x%x\n",
- mic->name, __func__, type, desc->status);
-
- while (1) {
- pollfd.events = POLLIN;
- pollfd.revents = 0;
- err = poll(&pollfd, 1, -1);
- if (err < 0) {
- mpsslog("%s %s poll failed %s\n",
- mic->name, __func__, strerror(errno));
- continue;
- }
-
- if (pollfd.revents) {
- if (desc->status != prev_status) {
- mpsslog("%s %s Waiting... desc-> type %d "
- "status 0x%x\n",
- mic->name, __func__, type,
- desc->status);
- prev_status = desc->status;
- }
- if (desc->status & VIRTIO_CONFIG_S_DRIVER_OK) {
- mpsslog("%s %s poll.revents %d\n",
- mic->name, __func__, pollfd.revents);
- mpsslog("%s %s desc-> type %d status 0x%x\n",
- mic->name, __func__, type,
- desc->status);
- break;
- }
- }
- }
- return 0;
-}
-
-/* Spin till we have some descriptors */
-static void
-spin_for_descriptors(struct mic_info *mic, struct mic_vring *vr)
-{
- __u16 avail_idx = read_avail_idx(vr);
-
- while (avail_idx == le16toh(READ_ONCE(vr->vr.avail->idx))) {
-#ifdef DEBUG
- mpsslog("%s %s waiting for desc avail %d info_avail %d\n",
- mic->name, __func__,
- le16toh(vr->vr.avail->idx), vr->info->avail_idx);
-#endif
- sched_yield();
- }
-}
-
-static void *
-virtio_net(void *arg)
-{
- static __u8 vnet_hdr[2][sizeof(struct virtio_net_hdr)];
- static __u8 vnet_buf[2][MAX_NET_PKT_SIZE] __attribute__ ((aligned(64)));
- struct iovec vnet_iov[2][2] = {
- { { .iov_base = vnet_hdr[0], .iov_len = sizeof(vnet_hdr[0]) },
- { .iov_base = vnet_buf[0], .iov_len = sizeof(vnet_buf[0]) } },
- { { .iov_base = vnet_hdr[1], .iov_len = sizeof(vnet_hdr[1]) },
- { .iov_base = vnet_buf[1], .iov_len = sizeof(vnet_buf[1]) } },
- };
- struct iovec *iov0 = vnet_iov[0], *iov1 = vnet_iov[1];
- struct mic_info *mic = (struct mic_info *)arg;
- char if_name[IFNAMSIZ];
- struct pollfd net_poll[MAX_NET_FD];
- struct mic_vring tx_vr, rx_vr;
- struct mic_copy_desc copy;
- struct mic_device_desc *desc;
- int err;
-
- snprintf(if_name, IFNAMSIZ, "mic%d", mic->id);
- mic->mic_net.tap_fd = tun_alloc(mic, if_name);
- if (mic->mic_net.tap_fd < 0)
- goto done;
-
- if (tap_configure(mic, if_name))
- goto done;
- mpsslog("MIC name %s id %d\n", mic->name, mic->id);
-
- net_poll[NET_FD_VIRTIO_NET].fd = mic->mic_net.virtio_net_fd;
- net_poll[NET_FD_VIRTIO_NET].events = POLLIN;
- net_poll[NET_FD_TUN].fd = mic->mic_net.tap_fd;
- net_poll[NET_FD_TUN].events = POLLIN;
-
- if (MAP_FAILED == init_vr(mic, mic->mic_net.virtio_net_fd,
- VIRTIO_ID_NET, &tx_vr, &rx_vr,
- virtnet_dev_page.dd.num_vq)) {
- mpsslog("%s init_vr failed %s\n",
- mic->name, strerror(errno));
- goto done;
- }
-
- copy.iovcnt = 2;
- desc = get_device_desc(mic, VIRTIO_ID_NET);
-
- while (1) {
- ssize_t len;
-
- net_poll[NET_FD_VIRTIO_NET].revents = 0;
- net_poll[NET_FD_TUN].revents = 0;
-
- /* Start polling for data from tap and virtio net */
- err = poll(net_poll, 2, -1);
- if (err < 0) {
- mpsslog("%s poll failed %s\n",
- __func__, strerror(errno));
- continue;
- }
- if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
- err = wait_for_card_driver(mic,
- mic->mic_net.virtio_net_fd,
- VIRTIO_ID_NET);
- if (err) {
- mpsslog("%s %s %d Exiting...\n",
- mic->name, __func__, __LINE__);
- break;
- }
- }
- /*
- * Check if there is data to be read from TUN and write to
- * virtio net fd if there is.
- */
- if (net_poll[NET_FD_TUN].revents & POLLIN) {
- copy.iov = iov0;
- len = readv(net_poll[NET_FD_TUN].fd,
- copy.iov, copy.iovcnt);
- if (len > 0) {
- struct virtio_net_hdr *hdr
- = (struct virtio_net_hdr *)vnet_hdr[0];
-
- /* Disable checksums on the card since we are on
- a reliable PCIe link */
- hdr->flags |= VIRTIO_NET_HDR_F_DATA_VALID;
-#ifdef DEBUG
- mpsslog("%s %s %d hdr->flags 0x%x ", mic->name,
- __func__, __LINE__, hdr->flags);
- mpsslog("copy.out_len %d hdr->gso_type 0x%x\n",
- copy.out_len, hdr->gso_type);
-#endif
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read from tap 0x%lx\n",
- mic->name, __func__, __LINE__,
- len);
-#endif
- spin_for_descriptors(mic, &tx_vr);
- txrx_prepare(VIRTIO_ID_NET, 1, &tx_vr, ©,
- len);
-
- err = mic_virtio_copy(mic,
- mic->mic_net.virtio_net_fd, &tx_vr,
- ©);
- if (err < 0) {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- }
- if (!err)
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d wrote to net 0x%lx\n",
- mic->name, __func__, __LINE__,
- sum_iovec_len(©));
-#endif
- /* Reinitialize IOV for next run */
- iov0[1].iov_len = MAX_NET_PKT_SIZE;
- } else if (len < 0) {
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read failed %s ", mic->name,
- __func__, __LINE__, strerror(errno));
- mpsslog("cnt %d sum %zd\n",
- copy.iovcnt, sum_iovec_len(©));
- }
- }
-
- /*
- * Check if there is data to be read from virtio net and
- * write to TUN if there is.
- */
- if (net_poll[NET_FD_VIRTIO_NET].revents & POLLIN) {
- while (rx_vr.info->avail_idx !=
- le16toh(rx_vr.vr.avail->idx)) {
- copy.iov = iov1;
- txrx_prepare(VIRTIO_ID_NET, 0, &rx_vr, ©,
- MAX_NET_PKT_SIZE
- + sizeof(struct virtio_net_hdr));
-
- err = mic_virtio_copy(mic,
- mic->mic_net.virtio_net_fd, &rx_vr,
- ©);
- if (!err) {
-#ifdef DEBUG
- struct virtio_net_hdr *hdr
- = (struct virtio_net_hdr *)
- vnet_hdr[1];
-
- mpsslog("%s %s %d hdr->flags 0x%x, ",
- mic->name, __func__, __LINE__,
- hdr->flags);
- mpsslog("out_len %d gso_type 0x%x\n",
- copy.out_len,
- hdr->gso_type);
-#endif
- /* Set the correct output iov_len */
- iov1[1].iov_len = copy.out_len -
- sizeof(struct virtio_net_hdr);
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__, __LINE__);
- mpsslog("read from net 0x%lx\n",
- sum_iovec_len(©));
-#endif
- len = writev(net_poll[NET_FD_TUN].fd,
- copy.iov, copy.iovcnt);
- if (len != sum_iovec_len(©)) {
- mpsslog("Tun write failed %s ",
- strerror(errno));
- mpsslog("len 0x%zx ", len);
- mpsslog("read_len 0x%zx\n",
- sum_iovec_len(©));
- } else {
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__,
- __LINE__);
- mpsslog("wrote to tap 0x%lx\n",
- len);
-#endif
- }
- } else {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- break;
- }
- }
- }
- if (net_poll[NET_FD_VIRTIO_NET].revents & POLLERR)
- mpsslog("%s: %s: POLLERR\n", __func__, mic->name);
- }
-done:
- pthread_exit(NULL);
-}
-
-/* virtio_console */
-#define VIRTIO_CONSOLE_FD 0
-#define MONITOR_FD (VIRTIO_CONSOLE_FD + 1)
-#define MAX_CONSOLE_FD (MONITOR_FD + 1) /* must be the last one + 1 */
-#define MAX_BUFFER_SIZE PAGE_SIZE
-
-static void *
-virtio_console(void *arg)
-{
- static __u8 vcons_buf[2][PAGE_SIZE];
- struct iovec vcons_iov[2] = {
- { .iov_base = vcons_buf[0], .iov_len = sizeof(vcons_buf[0]) },
- { .iov_base = vcons_buf[1], .iov_len = sizeof(vcons_buf[1]) },
- };
- struct iovec *iov0 = &vcons_iov[0], *iov1 = &vcons_iov[1];
- struct mic_info *mic = (struct mic_info *)arg;
- int err;
- struct pollfd console_poll[MAX_CONSOLE_FD];
- int pty_fd;
- char *pts_name;
- ssize_t len;
- struct mic_vring tx_vr, rx_vr;
- struct mic_copy_desc copy;
- struct mic_device_desc *desc;
-
- pty_fd = posix_openpt(O_RDWR);
- if (pty_fd < 0) {
- mpsslog("can't open a pseudoterminal master device: %s\n",
- strerror(errno));
- goto _return;
- }
- pts_name = ptsname(pty_fd);
- if (pts_name == NULL) {
- mpsslog("can't get pts name\n");
- goto _close_pty;
- }
- printf("%s console message goes to %s\n", mic->name, pts_name);
- mpsslog("%s console message goes to %s\n", mic->name, pts_name);
- err = grantpt(pty_fd);
- if (err < 0) {
- mpsslog("can't grant access: %s %s\n",
- pts_name, strerror(errno));
- goto _close_pty;
- }
- err = unlockpt(pty_fd);
- if (err < 0) {
- mpsslog("can't unlock a pseudoterminal: %s %s\n",
- pts_name, strerror(errno));
- goto _close_pty;
- }
- console_poll[MONITOR_FD].fd = pty_fd;
- console_poll[MONITOR_FD].events = POLLIN;
-
- console_poll[VIRTIO_CONSOLE_FD].fd = mic->mic_console.virtio_console_fd;
- console_poll[VIRTIO_CONSOLE_FD].events = POLLIN;
-
- if (MAP_FAILED == init_vr(mic, mic->mic_console.virtio_console_fd,
- VIRTIO_ID_CONSOLE, &tx_vr, &rx_vr,
- virtcons_dev_page.dd.num_vq)) {
- mpsslog("%s init_vr failed %s\n",
- mic->name, strerror(errno));
- goto _close_pty;
- }
-
- copy.iovcnt = 1;
- desc = get_device_desc(mic, VIRTIO_ID_CONSOLE);
-
- for (;;) {
- console_poll[MONITOR_FD].revents = 0;
- console_poll[VIRTIO_CONSOLE_FD].revents = 0;
- err = poll(console_poll, MAX_CONSOLE_FD, -1);
- if (err < 0) {
- mpsslog("%s %d: poll failed: %s\n", __func__, __LINE__,
- strerror(errno));
- continue;
- }
- if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
- err = wait_for_card_driver(mic,
- mic->mic_console.virtio_console_fd,
- VIRTIO_ID_CONSOLE);
- if (err) {
- mpsslog("%s %s %d Exiting...\n",
- mic->name, __func__, __LINE__);
- break;
- }
- }
-
- if (console_poll[MONITOR_FD].revents & POLLIN) {
- copy.iov = iov0;
- len = readv(pty_fd, copy.iov, copy.iovcnt);
- if (len > 0) {
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read from tap 0x%lx\n",
- mic->name, __func__, __LINE__,
- len);
-#endif
- spin_for_descriptors(mic, &tx_vr);
- txrx_prepare(VIRTIO_ID_CONSOLE, 1, &tx_vr,
- ©, len);
-
- err = mic_virtio_copy(mic,
- mic->mic_console.virtio_console_fd,
- &tx_vr, ©);
- if (err < 0) {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- }
- if (!err)
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d wrote to net 0x%lx\n",
- mic->name, __func__, __LINE__,
- sum_iovec_len(©));
-#endif
- /* Reinitialize IOV for next run */
- iov0->iov_len = PAGE_SIZE;
- } else if (len < 0) {
- disp_iovec(mic, ©, __func__, __LINE__);
- mpsslog("%s %s %d read failed %s ",
- mic->name, __func__, __LINE__,
- strerror(errno));
- mpsslog("cnt %d sum %zd\n",
- copy.iovcnt, sum_iovec_len(©));
- }
- }
-
- if (console_poll[VIRTIO_CONSOLE_FD].revents & POLLIN) {
- while (rx_vr.info->avail_idx !=
- le16toh(rx_vr.vr.avail->idx)) {
- copy.iov = iov1;
- txrx_prepare(VIRTIO_ID_CONSOLE, 0, &rx_vr,
- ©, PAGE_SIZE);
-
- err = mic_virtio_copy(mic,
- mic->mic_console.virtio_console_fd,
- &rx_vr, ©);
- if (!err) {
- /* Set the correct output iov_len */
- iov1->iov_len = copy.out_len;
- verify_out_len(mic, ©);
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__, __LINE__);
- mpsslog("read from net 0x%lx\n",
- sum_iovec_len(©));
-#endif
- len = writev(pty_fd,
- copy.iov, copy.iovcnt);
- if (len != sum_iovec_len(©)) {
- mpsslog("Tun write failed %s ",
- strerror(errno));
- mpsslog("len 0x%zx ", len);
- mpsslog("read_len 0x%zx\n",
- sum_iovec_len(©));
- } else {
-#ifdef DEBUG
- disp_iovec(mic, ©, __func__,
- __LINE__);
- mpsslog("%s %s %d ",
- mic->name, __func__,
- __LINE__);
- mpsslog("wrote to tap 0x%lx\n",
- len);
-#endif
- }
- } else {
- mpsslog("%s %s %d mic_virtio_copy %s\n",
- mic->name, __func__, __LINE__,
- strerror(errno));
- break;
- }
- }
- }
- if (console_poll[NET_FD_VIRTIO_NET].revents & POLLERR)
- mpsslog("%s: %s: POLLERR\n", __func__, mic->name);
- }
-_close_pty:
- close(pty_fd);
-_return:
- pthread_exit(NULL);
-}
-
-static void
-add_virtio_device(struct mic_info *mic, struct mic_device_desc *dd)
-{
- char path[PATH_MAX];
- int fd, err;
-
- snprintf(path, PATH_MAX, "/dev/vop_virtio%d", mic->id);
- fd = open(path, O_RDWR);
- if (fd < 0) {
- mpsslog("Could not open %s %s\n", path, strerror(errno));
- return;
- }
-
- err = ioctl(fd, MIC_VIRTIO_ADD_DEVICE, dd);
- if (err < 0) {
- mpsslog("Could not add %d %s\n", dd->type, strerror(errno));
- close(fd);
- return;
- }
- switch (dd->type) {
- case VIRTIO_ID_NET:
- mic->mic_net.virtio_net_fd = fd;
- mpsslog("Added VIRTIO_ID_NET for %s\n", mic->name);
- break;
- case VIRTIO_ID_CONSOLE:
- mic->mic_console.virtio_console_fd = fd;
- mpsslog("Added VIRTIO_ID_CONSOLE for %s\n", mic->name);
- break;
- case VIRTIO_ID_BLOCK:
- mic->mic_virtblk.virtio_block_fd = fd;
- mpsslog("Added VIRTIO_ID_BLOCK for %s\n", mic->name);
- break;
- }
-}
-
-static bool
-set_backend_file(struct mic_info *mic)
-{
- FILE *config;
- char buff[PATH_MAX], *line, *evv, *p;
-
- snprintf(buff, PATH_MAX, "%s/mpssd%03d.conf", mic_config_dir, mic->id);
- config = fopen(buff, "r");
- if (config == NULL)
- return false;
- do { /* look for "virtblk_backend=XXXX" */
- line = fgets(buff, PATH_MAX, config);
- if (line == NULL)
- break;
- if (*line == '#')
- continue;
- p = strchr(line, '\n');
- if (p)
- *p = '\0';
- } while (strncmp(line, virtblk_backend, strlen(virtblk_backend)) != 0);
- fclose(config);
- if (line == NULL)
- return false;
- evv = strchr(line, '=');
- if (evv == NULL)
- return false;
- mic->mic_virtblk.backend_file = malloc(strlen(evv) + 1);
- if (mic->mic_virtblk.backend_file == NULL) {
- mpsslog("%s %d can't allocate memory\n", mic->name, mic->id);
- return false;
- }
- strcpy(mic->mic_virtblk.backend_file, evv + 1);
- return true;
-}
-
-#define SECTOR_SIZE 512
-static bool
-set_backend_size(struct mic_info *mic)
-{
- mic->mic_virtblk.backend_size = lseek(mic->mic_virtblk.backend, 0,
- SEEK_END);
- if (mic->mic_virtblk.backend_size < 0) {
- mpsslog("%s: can't seek: %s\n",
- mic->name, mic->mic_virtblk.backend_file);
- return false;
- }
- virtblk_dev_page.blk_config.capacity =
- mic->mic_virtblk.backend_size / SECTOR_SIZE;
- if ((mic->mic_virtblk.backend_size % SECTOR_SIZE) != 0)
- virtblk_dev_page.blk_config.capacity++;
-
- virtblk_dev_page.blk_config.capacity =
- htole64(virtblk_dev_page.blk_config.capacity);
-
- return true;
-}
-
-static bool
-open_backend(struct mic_info *mic)
-{
- if (!set_backend_file(mic))
- goto _error_exit;
- mic->mic_virtblk.backend = open(mic->mic_virtblk.backend_file, O_RDWR);
- if (mic->mic_virtblk.backend < 0) {
- mpsslog("%s: can't open: %s\n", mic->name,
- mic->mic_virtblk.backend_file);
- goto _error_free;
- }
- if (!set_backend_size(mic))
- goto _error_close;
- mic->mic_virtblk.backend_addr = mmap(NULL,
- mic->mic_virtblk.backend_size,
- PROT_READ|PROT_WRITE, MAP_SHARED,
- mic->mic_virtblk.backend, 0L);
- if (mic->mic_virtblk.backend_addr == MAP_FAILED) {
- mpsslog("%s: can't map: %s %s\n",
- mic->name, mic->mic_virtblk.backend_file,
- strerror(errno));
- goto _error_close;
- }
- return true;
-
- _error_close:
- close(mic->mic_virtblk.backend);
- _error_free:
- free(mic->mic_virtblk.backend_file);
- _error_exit:
- return false;
-}
-
-static void
-close_backend(struct mic_info *mic)
-{
- munmap(mic->mic_virtblk.backend_addr, mic->mic_virtblk.backend_size);
- close(mic->mic_virtblk.backend);
- free(mic->mic_virtblk.backend_file);
-}
-
-static bool
-start_virtblk(struct mic_info *mic, struct mic_vring *vring)
-{
- if (((unsigned long)&virtblk_dev_page.blk_config % 8) != 0) {
- mpsslog("%s: blk_config is not 8 byte aligned.\n",
- mic->name);
- return false;
- }
- add_virtio_device(mic, &virtblk_dev_page.dd);
- if (MAP_FAILED == init_vr(mic, mic->mic_virtblk.virtio_block_fd,
- VIRTIO_ID_BLOCK, vring, NULL,
- virtblk_dev_page.dd.num_vq)) {
- mpsslog("%s init_vr failed %s\n",
- mic->name, strerror(errno));
- return false;
- }
- return true;
-}
-
-static void
-stop_virtblk(struct mic_info *mic)
-{
- int vr_size, ret;
-
- vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES,
- MIC_VIRTIO_RING_ALIGN) +
- sizeof(struct _mic_vring_info));
- ret = munmap(mic->mic_virtblk.block_dp,
- MIC_DEVICE_PAGE_END + vr_size * virtblk_dev_page.dd.num_vq);
- if (ret < 0)
- mpsslog("%s munmap errno %d\n", mic->name, errno);
- close(mic->mic_virtblk.virtio_block_fd);
-}
-
-static __u8
-header_error_check(struct vring_desc *desc)
-{
- if (le32toh(desc->len) != sizeof(struct virtio_blk_outhdr)) {
- mpsslog("%s() %d: length is not sizeof(virtio_blk_outhd)\n",
- __func__, __LINE__);
- return -EIO;
- }
- if (!(le16toh(desc->flags) & VRING_DESC_F_NEXT)) {
- mpsslog("%s() %d: alone\n",
- __func__, __LINE__);
- return -EIO;
- }
- if (le16toh(desc->flags) & VRING_DESC_F_WRITE) {
- mpsslog("%s() %d: not read\n",
- __func__, __LINE__);
- return -EIO;
- }
- return 0;
-}
-
-static int
-read_header(int fd, struct virtio_blk_outhdr *hdr, __u32 desc_idx)
-{
- struct iovec iovec;
- struct mic_copy_desc copy;
-
- iovec.iov_len = sizeof(*hdr);
- iovec.iov_base = hdr;
- copy.iov = &iovec;
- copy.iovcnt = 1;
- copy.vr_idx = 0; /* only one vring on virtio_block */
- copy.update_used = false; /* do not update used index */
- return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©);
-}
-
-static int
-transfer_blocks(int fd, struct iovec *iovec, __u32 iovcnt)
-{
- struct mic_copy_desc copy;
-
- copy.iov = iovec;
- copy.iovcnt = iovcnt;
- copy.vr_idx = 0; /* only one vring on virtio_block */
- copy.update_used = false; /* do not update used index */
- return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©);
-}
-
-static __u8
-status_error_check(struct vring_desc *desc)
-{
- if (le32toh(desc->len) != sizeof(__u8)) {
- mpsslog("%s() %d: length is not sizeof(status)\n",
- __func__, __LINE__);
- return -EIO;
- }
- return 0;
-}
-
-static int
-write_status(int fd, __u8 *status)
-{
- struct iovec iovec;
- struct mic_copy_desc copy;
-
- iovec.iov_base = status;
- iovec.iov_len = sizeof(*status);
- copy.iov = &iovec;
- copy.iovcnt = 1;
- copy.vr_idx = 0; /* only one vring on virtio_block */
- copy.update_used = true; /* Update used index */
- return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©);
-}
-
-#ifndef VIRTIO_BLK_T_GET_ID
-#define VIRTIO_BLK_T_GET_ID 8
-#endif
-
-static void *
-virtio_block(void *arg)
-{
- struct mic_info *mic = (struct mic_info *)arg;
- int ret;
- struct pollfd block_poll;
- struct mic_vring vring;
- __u16 avail_idx;
- __u32 desc_idx;
- struct vring_desc *desc;
- struct iovec *iovec, *piov;
- __u8 status;
- __u32 buffer_desc_idx;
- struct virtio_blk_outhdr hdr;
- void *fos;
-
- for (;;) { /* forever */
- if (!open_backend(mic)) { /* No virtblk */
- for (mic->mic_virtblk.signaled = 0;
- !mic->mic_virtblk.signaled;)
- sleep(1);
- continue;
- }
-
- /* backend file is specified. */
- if (!start_virtblk(mic, &vring))
- goto _close_backend;
- iovec = malloc(sizeof(*iovec) *
- le32toh(virtblk_dev_page.blk_config.seg_max));
- if (!iovec) {
- mpsslog("%s: can't alloc iovec: %s\n",
- mic->name, strerror(ENOMEM));
- goto _stop_virtblk;
- }
-
- block_poll.fd = mic->mic_virtblk.virtio_block_fd;
- block_poll.events = POLLIN;
- for (mic->mic_virtblk.signaled = 0;
- !mic->mic_virtblk.signaled;) {
- block_poll.revents = 0;
- /* timeout in 1 sec to see signaled */
- ret = poll(&block_poll, 1, 1000);
- if (ret < 0) {
- mpsslog("%s %d: poll failed: %s\n",
- __func__, __LINE__,
- strerror(errno));
- continue;
- }
-
- if (!(block_poll.revents & POLLIN)) {
-#ifdef DEBUG
- mpsslog("%s %d: block_poll.revents=0x%x\n",
- __func__, __LINE__, block_poll.revents);
-#endif
- continue;
- }
-
- /* POLLIN */
- while (vring.info->avail_idx !=
- le16toh(vring.vr.avail->idx)) {
- /* read header element */
- avail_idx =
- vring.info->avail_idx &
- (vring.vr.num - 1);
- desc_idx = le16toh(
- vring.vr.avail->ring[avail_idx]);
- desc = &vring.vr.desc[desc_idx];
-#ifdef DEBUG
- mpsslog("%s() %d: avail_idx=%d ",
- __func__, __LINE__,
- vring.info->avail_idx);
- mpsslog("vring.vr.num=%d desc=%p\n",
- vring.vr.num, desc);
-#endif
- status = header_error_check(desc);
- ret = read_header(
- mic->mic_virtblk.virtio_block_fd,
- &hdr, desc_idx);
- if (ret < 0) {
- mpsslog("%s() %d %s: ret=%d %s\n",
- __func__, __LINE__,
- mic->name, ret,
- strerror(errno));
- break;
- }
- /* buffer element */
- piov = iovec;
- status = 0;
- fos = mic->mic_virtblk.backend_addr +
- (hdr.sector * SECTOR_SIZE);
- buffer_desc_idx = next_desc(desc);
- desc_idx = buffer_desc_idx;
- for (desc = &vring.vr.desc[buffer_desc_idx];
- desc->flags & VRING_DESC_F_NEXT;
- desc_idx = next_desc(desc),
- desc = &vring.vr.desc[desc_idx]) {
- piov->iov_len = desc->len;
- piov->iov_base = fos;
- piov++;
- fos += desc->len;
- }
- /* Returning NULLs for VIRTIO_BLK_T_GET_ID. */
- if (hdr.type & ~(VIRTIO_BLK_T_OUT |
- VIRTIO_BLK_T_GET_ID)) {
- /*
- VIRTIO_BLK_T_IN - does not do
- anything. Probably for documenting.
- VIRTIO_BLK_T_SCSI_CMD - for
- virtio_scsi.
- VIRTIO_BLK_T_FLUSH - turned off in
- config space.
- VIRTIO_BLK_T_BARRIER - defined but not
- used in anywhere.
- */
- mpsslog("%s() %d: type %x ",
- __func__, __LINE__,
- hdr.type);
- mpsslog("is not supported\n");
- status = -ENOTSUP;
-
- } else {
- ret = transfer_blocks(
- mic->mic_virtblk.virtio_block_fd,
- iovec,
- piov - iovec);
- if (ret < 0 &&
- status != 0)
- status = ret;
- }
- /* write status and update used pointer */
- if (status != 0)
- status = status_error_check(desc);
- ret = write_status(
- mic->mic_virtblk.virtio_block_fd,
- &status);
-#ifdef DEBUG
- mpsslog("%s() %d: write status=%d on desc=%p\n",
- __func__, __LINE__,
- status, desc);
-#endif
- }
- }
- free(iovec);
-_stop_virtblk:
- stop_virtblk(mic);
-_close_backend:
- close_backend(mic);
- } /* forever */
-
- pthread_exit(NULL);
-}
-
-static void
-reset(struct mic_info *mic)
-{
-#define RESET_TIMEOUT 120
- int i = RESET_TIMEOUT;
- setsysfs(mic->name, "state", "reset");
- while (i) {
- char *state;
- state = readsysfs(mic->name, "state");
- if (!state)
- goto retry;
- mpsslog("%s: %s %d state %s\n",
- mic->name, __func__, __LINE__, state);
-
- if (!strcmp(state, "ready")) {
- free(state);
- break;
- }
- free(state);
-retry:
- sleep(1);
- i--;
- }
-}
-
-static int
-get_mic_shutdown_status(struct mic_info *mic, char *shutdown_status)
-{
- if (!strcmp(shutdown_status, "nop"))
- return MIC_NOP;
- if (!strcmp(shutdown_status, "crashed"))
- return MIC_CRASHED;
- if (!strcmp(shutdown_status, "halted"))
- return MIC_HALTED;
- if (!strcmp(shutdown_status, "poweroff"))
- return MIC_POWER_OFF;
- if (!strcmp(shutdown_status, "restart"))
- return MIC_RESTART;
- mpsslog("%s: BUG invalid status %s\n", mic->name, shutdown_status);
- /* Invalid state */
- assert(0);
-};
-
-static int get_mic_state(struct mic_info *mic)
-{
- char *state = NULL;
- enum mic_states mic_state;
-
- while (!state) {
- state = readsysfs(mic->name, "state");
- sleep(1);
- }
- mpsslog("%s: %s %d state %s\n",
- mic->name, __func__, __LINE__, state);
-
- if (!strcmp(state, "ready")) {
- mic_state = MIC_READY;
- } else if (!strcmp(state, "booting")) {
- mic_state = MIC_BOOTING;
- } else if (!strcmp(state, "online")) {
- mic_state = MIC_ONLINE;
- } else if (!strcmp(state, "shutting_down")) {
- mic_state = MIC_SHUTTING_DOWN;
- } else if (!strcmp(state, "reset_failed")) {
- mic_state = MIC_RESET_FAILED;
- } else if (!strcmp(state, "resetting")) {
- mic_state = MIC_RESETTING;
- } else {
- mpsslog("%s: BUG invalid state %s\n", mic->name, state);
- assert(0);
- }
-
- free(state);
- return mic_state;
-};
-
-static void mic_handle_shutdown(struct mic_info *mic)
-{
-#define SHUTDOWN_TIMEOUT 60
- int i = SHUTDOWN_TIMEOUT;
- char *shutdown_status;
- while (i) {
- shutdown_status = readsysfs(mic->name, "shutdown_status");
- if (!shutdown_status) {
- sleep(1);
- continue;
- }
- mpsslog("%s: %s %d shutdown_status %s\n",
- mic->name, __func__, __LINE__, shutdown_status);
- switch (get_mic_shutdown_status(mic, shutdown_status)) {
- case MIC_RESTART:
- mic->restart = 1;
- case MIC_HALTED:
- case MIC_POWER_OFF:
- case MIC_CRASHED:
- free(shutdown_status);
- goto reset;
- default:
- break;
- }
- free(shutdown_status);
- sleep(1);
- i--;
- }
-reset:
- if (!i)
- mpsslog("%s: %s %d timing out waiting for shutdown_status %s\n",
- mic->name, __func__, __LINE__, shutdown_status);
- reset(mic);
-}
-
-static int open_state_fd(struct mic_info *mic)
-{
- char pathname[PATH_MAX];
- int fd;
-
- snprintf(pathname, PATH_MAX - 1, "%s/%s/%s",
- MICSYSFSDIR, mic->name, "state");
-
- fd = open(pathname, O_RDONLY);
- if (fd < 0)
- mpsslog("%s: opening file %s failed %s\n",
- mic->name, pathname, strerror(errno));
- return fd;
-}
-
-static int block_till_state_change(int fd, struct mic_info *mic)
-{
- struct pollfd ufds[1];
- char value[PAGE_SIZE];
- int ret;
-
- ufds[0].fd = fd;
- ufds[0].events = POLLERR | POLLPRI;
- ret = poll(ufds, 1, -1);
- if (ret < 0) {
- mpsslog("%s: %s %d poll failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- return ret;
- }
-
- ret = lseek(fd, 0, SEEK_SET);
- if (ret < 0) {
- mpsslog("%s: %s %d Failed to seek to 0: %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- return ret;
- }
-
- ret = read(fd, value, sizeof(value));
- if (ret < 0) {
- mpsslog("%s: %s %d Failed to read sysfs entry: %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- return ret;
- }
-
- return 0;
-}
-
-static void *
-mic_config(void *arg)
-{
- struct mic_info *mic = (struct mic_info *)arg;
- int fd, ret, stat = 0;
-
- fd = open_state_fd(mic);
- if (fd < 0) {
- mpsslog("%s: %s %d open state fd failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- goto exit;
- }
-
- do {
- ret = block_till_state_change(fd, mic);
- if (ret < 0) {
- mpsslog("%s: %s %d block_till_state_change error %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- goto close_exit;
- }
-
- switch (get_mic_state(mic)) {
- case MIC_SHUTTING_DOWN:
- mic_handle_shutdown(mic);
- break;
- case MIC_READY:
- case MIC_RESET_FAILED:
- ret = kill(mic->pid, SIGTERM);
- mpsslog("%s: %s %d kill pid %d ret %d\n",
- mic->name, __func__, __LINE__,
- mic->pid, ret);
- if (!ret) {
- ret = waitpid(mic->pid, &stat,
- WIFSIGNALED(stat));
- mpsslog("%s: %s %d waitpid ret %d pid %d\n",
- mic->name, __func__, __LINE__,
- ret, mic->pid);
- }
- if (mic->boot_on_resume) {
- setsysfs(mic->name, "state", "boot");
- mic->boot_on_resume = 0;
- }
- goto close_exit;
- default:
- break;
- }
- } while (1);
-
-close_exit:
- close(fd);
-exit:
- init_mic(mic);
- pthread_exit(NULL);
-}
-
-static void
-set_cmdline(struct mic_info *mic)
-{
- char buffer[PATH_MAX];
- int len;
-
- len = snprintf(buffer, PATH_MAX,
- "clocksource=tsc highres=off nohz=off ");
- len += snprintf(buffer + len, PATH_MAX - len,
- "cpufreq_on;corec6_off;pc3_off;pc6_off ");
- len += snprintf(buffer + len, PATH_MAX - len,
- "ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0",
- mic->id + 1);
-
- setsysfs(mic->name, "cmdline", buffer);
- mpsslog("%s: Command line: \"%s\"\n", mic->name, buffer);
- snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id + 1);
- mpsslog("%s: IPADDR: \"%s\"\n", mic->name, buffer);
-}
-
-static void
-set_log_buf_info(struct mic_info *mic)
-{
- int fd;
- off_t len;
- char system_map[] = "/lib/firmware/mic/System.map";
- char *map, *temp, log_buf[17] = {'\0'};
-
- fd = open(system_map, O_RDONLY);
- if (fd < 0) {
- mpsslog("%s: Opening System.map failed: %d\n",
- mic->name, errno);
- return;
- }
- len = lseek(fd, 0, SEEK_END);
- if (len < 0) {
- mpsslog("%s: Reading System.map size failed: %d\n",
- mic->name, errno);
- close(fd);
- return;
- }
- map = mmap(NULL, len, PROT_READ, MAP_PRIVATE, fd, 0);
- if (map == MAP_FAILED) {
- mpsslog("%s: mmap of System.map failed: %d\n",
- mic->name, errno);
- close(fd);
- return;
- }
- temp = strstr(map, "__log_buf");
- if (!temp) {
- mpsslog("%s: __log_buf not found: %d\n", mic->name, errno);
- munmap(map, len);
- close(fd);
- return;
- }
- strncpy(log_buf, temp - 19, 16);
- setsysfs(mic->name, "log_buf_addr", log_buf);
- mpsslog("%s: log_buf_addr: %s\n", mic->name, log_buf);
- temp = strstr(map, "log_buf_len");
- if (!temp) {
- mpsslog("%s: log_buf_len not found: %d\n", mic->name, errno);
- munmap(map, len);
- close(fd);
- return;
- }
- strncpy(log_buf, temp - 19, 16);
- setsysfs(mic->name, "log_buf_len", log_buf);
- mpsslog("%s: log_buf_len: %s\n", mic->name, log_buf);
- munmap(map, len);
- close(fd);
-}
-
-static void
-change_virtblk_backend(int x, siginfo_t *siginfo, void *p)
-{
- struct mic_info *mic;
-
- for (mic = mic_list.next; mic != NULL; mic = mic->next)
- mic->mic_virtblk.signaled = 1/* true */;
-}
-
-static void
-set_mic_boot_params(struct mic_info *mic)
-{
- set_log_buf_info(mic);
- set_cmdline(mic);
-}
-
-static void *
-init_mic(void *arg)
-{
- struct mic_info *mic = (struct mic_info *)arg;
- struct sigaction ignore = {
- .sa_flags = 0,
- .sa_handler = SIG_IGN
- };
- struct sigaction act = {
- .sa_flags = SA_SIGINFO,
- .sa_sigaction = change_virtblk_backend,
- };
- char buffer[PATH_MAX];
- int err, fd;
-
- /*
- * Currently, one virtio block device is supported for each MIC card
- * at a time. Any user (or test) can send a SIGUSR1 to the MIC daemon.
- * The signal informs the virtio block backend about a change in the
- * configuration file which specifies the virtio backend file name on
- * the host. Virtio block backend then re-reads the configuration file
- * and switches to the new block device. This signalling mechanism may
- * not be required once multiple virtio block devices are supported by
- * the MIC daemon.
- */
- sigaction(SIGUSR1, &ignore, NULL);
-retry:
- fd = open_state_fd(mic);
- if (fd < 0) {
- mpsslog("%s: %s %d open state fd failed %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- sleep(2);
- goto retry;
- }
-
- if (mic->restart) {
- snprintf(buffer, PATH_MAX, "boot");
- setsysfs(mic->name, "state", buffer);
- mpsslog("%s restarting mic %d\n",
- mic->name, mic->restart);
- mic->restart = 0;
- }
-
- while (1) {
- while (block_till_state_change(fd, mic)) {
- mpsslog("%s: %s %d block_till_state_change error %s\n",
- mic->name, __func__, __LINE__, strerror(errno));
- sleep(2);
- continue;
- }
-
- if (get_mic_state(mic) == MIC_BOOTING)
- break;
- }
-
- mic->pid = fork();
- switch (mic->pid) {
- case 0:
- add_virtio_device(mic, &virtcons_dev_page.dd);
- add_virtio_device(mic, &virtnet_dev_page.dd);
- err = pthread_create(&mic->mic_console.console_thread, NULL,
- virtio_console, mic);
- if (err)
- mpsslog("%s virtcons pthread_create failed %s\n",
- mic->name, strerror(err));
- err = pthread_create(&mic->mic_net.net_thread, NULL,
- virtio_net, mic);
- if (err)
- mpsslog("%s virtnet pthread_create failed %s\n",
- mic->name, strerror(err));
- err = pthread_create(&mic->mic_virtblk.block_thread, NULL,
- virtio_block, mic);
- if (err)
- mpsslog("%s virtblk pthread_create failed %s\n",
- mic->name, strerror(err));
- sigemptyset(&act.sa_mask);
- err = sigaction(SIGUSR1, &act, NULL);
- if (err)
- mpsslog("%s sigaction SIGUSR1 failed %s\n",
- mic->name, strerror(errno));
- while (1)
- sleep(60);
- case -1:
- mpsslog("fork failed MIC name %s id %d errno %d\n",
- mic->name, mic->id, errno);
- break;
- default:
- err = pthread_create(&mic->config_thread, NULL,
- mic_config, mic);
- if (err)
- mpsslog("%s mic_config pthread_create failed %s\n",
- mic->name, strerror(err));
- }
-
- return NULL;
-}
-
-static void
-start_daemon(void)
-{
- struct mic_info *mic;
- int err;
-
- for (mic = mic_list.next; mic; mic = mic->next) {
- set_mic_boot_params(mic);
- err = pthread_create(&mic->init_thread, NULL, init_mic, mic);
- if (err)
- mpsslog("%s init_mic pthread_create failed %s\n",
- mic->name, strerror(err));
- }
-
- while (1)
- sleep(60);
-}
-
-static int
-init_mic_list(void)
-{
- struct mic_info *mic = &mic_list;
- struct dirent *file;
- DIR *dp;
- int cnt = 0;
-
- dp = opendir(MICSYSFSDIR);
- if (!dp)
- return 0;
-
- while ((file = readdir(dp)) != NULL) {
- if (!strncmp(file->d_name, "mic", 3)) {
- mic->next = calloc(1, sizeof(struct mic_info));
- if (mic->next) {
- mic = mic->next;
- mic->id = atoi(&file->d_name[3]);
- mic->name = malloc(strlen(file->d_name) + 16);
- if (mic->name)
- strcpy(mic->name, file->d_name);
- mpsslog("MIC name %s id %d\n", mic->name,
- mic->id);
- cnt++;
- }
- }
- }
-
- closedir(dp);
- return cnt;
-}
-
-void
-mpsslog(char *format, ...)
-{
- va_list args;
- char buffer[4096];
- char ts[52], *ts1;
- time_t t;
-
- if (logfp == NULL)
- return;
-
- va_start(args, format);
- vsprintf(buffer, format, args);
- va_end(args);
-
- time(&t);
- ts1 = ctime_r(&t, ts);
- ts1[strlen(ts1) - 1] = '\0';
- fprintf(logfp, "%s: %s", ts1, buffer);
-
- fflush(logfp);
-}
-
-int
-main(int argc, char *argv[])
-{
- int cnt;
- pid_t pid;
-
- myname = argv[0];
-
- logfp = fopen(LOGFILE_NAME, "a+");
- if (!logfp) {
- fprintf(stderr, "cannot open logfile '%s'\n", LOGFILE_NAME);
- exit(1);
- }
- pid = fork();
- switch (pid) {
- case 0:
- break;
- case -1:
- exit(2);
- default:
- exit(0);
- }
-
- mpsslog("MIC Daemon start\n");
-
- cnt = init_mic_list();
- if (cnt == 0) {
- mpsslog("MIC module not loaded\n");
- exit(3);
- }
- mpsslog("MIC found %d devices\n", cnt);
-
- start_daemon();
-
- exit(0);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-#ifndef _MPSSD_H_
-#define _MPSSD_H_
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <dirent.h>
-#include <libgen.h>
-#include <pthread.h>
-#include <stdarg.h>
-#include <time.h>
-#include <errno.h>
-#include <sys/dir.h>
-#include <sys/ioctl.h>
-#include <sys/poll.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/stat.h>
-#include <sys/mman.h>
-#include <sys/utsname.h>
-#include <sys/wait.h>
-#include <netinet/in.h>
-#include <arpa/inet.h>
-#include <netdb.h>
-#include <signal.h>
-#include <limits.h>
-#include <syslog.h>
-#include <getopt.h>
-#include <net/if.h>
-#include <linux/if_tun.h>
-#include <linux/virtio_ids.h>
-
-#define MICSYSFSDIR "/sys/class/mic"
-#define LOGFILE_NAME "/var/log/mpssd"
-#define PAGE_SIZE 4096
-
-struct mic_console_info {
- pthread_t console_thread;
- int virtio_console_fd;
- void *console_dp;
-};
-
-struct mic_net_info {
- pthread_t net_thread;
- int virtio_net_fd;
- int tap_fd;
- void *net_dp;
-};
-
-struct mic_virtblk_info {
- pthread_t block_thread;
- int virtio_block_fd;
- void *block_dp;
- volatile sig_atomic_t signaled;
- char *backend_file;
- int backend;
- void *backend_addr;
- long backend_size;
-};
-
-struct mic_info {
- int id;
- char *name;
- pthread_t config_thread;
- pthread_t init_thread;
- pid_t pid;
- struct mic_console_info mic_console;
- struct mic_net_info mic_net;
- struct mic_virtblk_info mic_virtblk;
- int restart;
- int boot_on_resume;
- struct mic_info *next;
-};
-
-__attribute__((format(printf, 1, 2)))
-void mpsslog(char *format, ...);
-char *readsysfs(char *dir, char *entry);
-int setsysfs(char *dir, char *entry, char *value);
-#endif
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Intel MIC Platform Software Stack (MPSS)
- *
- * Copyright(c) 2013 Intel Corporation.
- *
- * Intel MIC User Space Tools.
- */
-
-#include "mpssd.h"
-
-#define PAGE_SIZE 4096
-
-char *
-readsysfs(char *dir, char *entry)
-{
- char filename[PATH_MAX];
- char value[PAGE_SIZE];
- char *string = NULL;
- int fd;
- int len;
-
- if (dir == NULL)
- snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
- else
- snprintf(filename, PATH_MAX,
- "%s/%s/%s", MICSYSFSDIR, dir, entry);
-
- fd = open(filename, O_RDONLY);
- if (fd < 0) {
- mpsslog("Failed to open sysfs entry '%s': %s\n",
- filename, strerror(errno));
- return NULL;
- }
-
- len = read(fd, value, sizeof(value));
- if (len < 0) {
- mpsslog("Failed to read sysfs entry '%s': %s\n",
- filename, strerror(errno));
- goto readsys_ret;
- }
- if (len == 0)
- goto readsys_ret;
-
- value[len - 1] = '\0';
-
- string = malloc(strlen(value) + 1);
- if (string)
- strcpy(string, value);
-
-readsys_ret:
- close(fd);
- return string;
-}
-
-int
-setsysfs(char *dir, char *entry, char *value)
-{
- char filename[PATH_MAX];
- char *oldvalue;
- int fd, ret = 0;
-
- if (dir == NULL)
- snprintf(filename, PATH_MAX, "%s/%s", MICSYSFSDIR, entry);
- else
- snprintf(filename, PATH_MAX, "%s/%s/%s",
- MICSYSFSDIR, dir, entry);
-
- oldvalue = readsysfs(dir, entry);
-
- fd = open(filename, O_RDWR);
- if (fd < 0) {
- ret = errno;
- mpsslog("Failed to open sysfs entry '%s': %s\n",
- filename, strerror(errno));
- goto done;
- }
-
- if (!oldvalue || strcmp(value, oldvalue)) {
- if (write(fd, value, strlen(value)) < 0) {
- ret = errno;
- mpsslog("Failed to write new sysfs entry '%s': %s\n",
- filename, strerror(errno));
- }
- }
- close(fd);
-done:
- if (oldvalue)
- free(oldvalue);
- return ret;
-}
ifdef CONFIG_TRIM_UNUSED_KSYMS
cmd_gen_ksymdeps = \
$(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd
+
+# List module undefined symbols
+undefined_syms = $(NM) $< | $(AWK) '$$1 == "U" { printf("%s%s", x++ ? " " : "", $$2) }';
endif
define rule_cc_o_c
$(call cmd,modversions_S)
endef
-# List module undefined symbols (or empty line if not enabled)
-ifdef CONFIG_TRIM_UNUSED_KSYMS
-cmd_undef_syms = $(NM) $< | sed -n 's/^ *U //p' | xargs echo
-else
-cmd_undef_syms = echo
-endif
-
# Built-in and composite module parts
$(obj)/%.o: $(src)/%.c $(recordmcount_source) $(objtool_dep) FORCE
$(call if_changed_rule,cc_o_c)
cmd_mod = { \
echo $(if $($*-objs)$($*-y)$($*-m), $(addprefix $(obj)/, $($*-objs) $($*-y) $($*-m)), $(@:.mod=.o)); \
- $(cmd_undef_syms); \
+ $(undefined_syms) echo; \
} > $@
$(obj)/%.mod: $(obj)/%.o FORCE
#
ifneq ($(findstring 2, $(KBUILD_EXTRA_WARN)),)
-KBUILD_CFLAGS += -Wcast-align
KBUILD_CFLAGS += -Wdisabled-optimization
KBUILD_CFLAGS += -Wnested-externs
KBUILD_CFLAGS += -Wshadow
ifneq ($(findstring 3, $(KBUILD_EXTRA_WARN)),)
KBUILD_CFLAGS += -Wbad-function-cast
+KBUILD_CFLAGS += -Wcast-align
KBUILD_CFLAGS += -Wcast-qual
KBUILD_CFLAGS += -Wconversion
KBUILD_CFLAGS += -Wpacked
'struct bpf_perf_event_data',
'struct bpf_perf_event_value',
'struct bpf_pidns_info',
+ 'struct bpf_redir_neigh',
'struct bpf_sock',
'struct bpf_sock_addr',
'struct bpf_sock_ops',
# SPDX-License-Identifier: GPL-2.0
use strict;
+use warnings;
+use utf8;
use Pod::Usage;
use Getopt::Long;
use File::Find;
use Fcntl ':mode';
-my $help;
-my $man;
-my $debug;
+my $help = 0;
+my $man = 0;
+my $debug = 0;
+my $enable_lineno = 0;
my $prefix="Documentation/ABI";
+#
+# If true, assumes that the description is formatted with ReST
+#
+my $description_is_rst = 1;
+
GetOptions(
"debug|d+" => \$debug,
+ "enable-lineno" => \$enable_lineno,
+ "rst-source!" => \$description_is_rst,
"dir=s" => \$prefix,
'help|?' => \$help,
man => \$man
require Data::Dumper if ($debug);
my %data;
+my %symbols;
#
# Displays an error message, printing file name and line
sub parse_error($$$$) {
my ($file, $ln, $msg, $data) = @_;
- print STDERR "file $file#$ln: $msg at\n\t$data";
+ $data =~ s/\s+$/\n/;
+
+ print STDERR "Warning: file $file#$ln:\n\t$msg";
+
+ if ($data ne "") {
+ print STDERR ". Line\n\t\t$data";
+ } else {
+ print STDERR "\n";
+ }
}
#
my $name = $file;
$name =~ s,.*/,,;
- my $nametag = "File $name";
+ my $fn = $file;
+ $fn =~ s,Documentation/ABI/,,;
+
+ my $nametag = "File $fn";
$data{$nametag}->{what} = "File $name";
$data{$nametag}->{type} = "File";
$data{$nametag}->{file} = $name;
$data{$nametag}->{filepath} = $file;
$data{$nametag}->{is_file} = 1;
+ $data{$nametag}->{line_no} = 1;
my $type = $file;
$type =~ s,.*/(.*)/.*,$1,;
my $what;
my $new_what;
- my $tag;
+ my $tag = "";
my $ln;
my $xrefs;
my $space;
my @labels;
- my $label;
+ my $label = "";
print STDERR "Opening $file\n" if ($debug > 1);
open IN, $file;
# Invalid, but it is a common mistake
if ($new_tag eq "where") {
- parse_error($file, $ln, "tag 'Where' is invalid. Should be 'What:' instead", $_);
+ parse_error($file, $ln, "tag 'Where' is invalid. Should be 'What:' instead", "");
$new_tag = "what";
}
if ($new_tag =~ m/what/) {
$space = "";
+ $content =~ s/[,.;]$//;
+
+ push @{$symbols{$content}->{file}}, " $file:" . ($ln - 1);
+
if ($tag =~ m/what/) {
$what .= ", " . $content;
} else {
- parse_error($file, $ln, "What '$what' doesn't have a description", "") if ($what && !$data{$what}->{description});
+ if ($what) {
+ parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description});
+
+ foreach my $w(split /, /, $what) {
+ $symbols{$w}->{xref} = $what;
+ };
+ }
$what = $content;
$label = $content;
push @labels, [($content, $label)];
$tag = $new_tag;
- push @{$data{$nametag}->{xrefs}}, [($content, $label)] if ($data{$nametag}->{what});
+ push @{$data{$nametag}->{symbols}}, $content if ($data{$nametag}->{what});
next;
}
$tag = $new_tag;
if ($new_what) {
- @{$data{$what}->{label}} = @labels if ($data{$nametag}->{what});
+ @{$data{$what}->{label_list}} = @labels if ($data{$nametag}->{what});
@labels = ();
$label = "";
$new_what = 0;
$data{$what}->{type} = $type;
- $data{$what}->{file} = $name;
- $data{$what}->{filepath} = $file;
+ if (!defined($data{$what}->{file})) {
+ $data{$what}->{file} = $name;
+ $data{$what}->{filepath} = $file;
+ } else {
+ if ($name ne $data{$what}->{file}) {
+ $data{$what}->{file} .= " " . $name;
+ $data{$what}->{filepath} .= " " . $file;
+ }
+ }
print STDERR "\twhat: $what\n" if ($debug > 1);
+ $data{$what}->{line_no} = $ln;
+ } else {
+ $data{$what}->{line_no} = $ln if (!defined($data{$what}->{line_no}));
}
if (!$what) {
parse_error($file, $ln, "'What:' should come first:", $_);
next;
}
- if ($tag eq "description") {
- next if ($content =~ m/^\s*$/);
- if ($content =~ m/^(\s*)(.*)/) {
- my $new_content = $2;
- $space = $new_tag . $sep . $1;
- while ($space =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
- $space =~ s/./ /g;
- $data{$what}->{$tag} .= "$new_content\n";
+ if ($new_tag eq "description") {
+ $sep =~ s,:, ,;
+ $content = ' ' x length($new_tag) . $sep . $content;
+ while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
+ if ($content =~ m/^(\s*)(\S.*)$/) {
+ # Preserve initial spaces for the first line
+ $space = $1;
+ $content = "$2\n";
+ $data{$what}->{$tag} .= $content;
+ } else {
+ undef($space);
}
+
} else {
$data{$what}->{$tag} = $content;
}
}
if ($tag eq "description") {
- if (!$data{$what}->{description}) {
- next if (m/^\s*\n/);
- if (m/^(\s*)(.*)/) {
+ my $content = $_;
+ while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
+ if (m/^\s*\n/) {
+ $data{$what}->{$tag} .= "\n";
+ next;
+ }
+
+ if (!defined($space)) {
+ # Preserve initial spaces for the first line
+ if ($content =~ m/^(\s*)(\S.*)$/) {
$space = $1;
- while ($space =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
- $data{$what}->{$tag} .= "$2\n";
+ $content = "$2\n";
}
} else {
- my $content = $_;
- if (m/^\s*\n/) {
- $data{$what}->{$tag} .= $content;
- next;
- }
-
- while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
$space = "" if (!($content =~ s/^($space)//));
-
- # Compress spaces with tabs
- $content =~ s<^ {8}> <\t>;
- $content =~ s<^ {1,7}\t> <\t>;
- $content =~ s< {1,7}\t> <\t>;
- $data{$what}->{$tag} .= $content;
}
+ $data{$what}->{$tag} .= $content;
+
next;
}
if (m/^\s*(.*)/) {
}
# Everything else is error
- parse_error($file, $ln, "Unexpected line:", $_);
+ parse_error($file, $ln, "Unexpected content", $_);
+ }
+ $data{$nametag}->{description} =~ s/^\n+// if ($data{$nametag}->{description});
+ if ($what) {
+ parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description});
+
+ foreach my $w(split /, /,$what) {
+ $symbols{$w}->{xref} = $what;
+ };
}
- $data{$nametag}->{description} =~ s/^\n+//;
close IN;
}
-#
-# Outputs the book on ReST format
-#
+sub create_labels {
+ my %labels;
-my %labels;
+ foreach my $what (keys %data) {
+ next if ($data{$what}->{file} eq "File");
-sub output_rest {
- foreach my $what (sort {
- ($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") ||
- $a cmp $b
- } keys %data) {
- my $type = $data{$what}->{type};
- my $file = $data{$what}->{file};
- my $filepath = $data{$what}->{filepath};
-
- my $w = $what;
- $w =~ s/([\(\)\_\-\*\=\^\~\\])/\\$1/g;
-
-
- foreach my $p (@{$data{$what}->{label}}) {
+ foreach my $p (@{$data{$what}->{label_list}}) {
my ($content, $label) = @{$p};
$label = "abi_" . $label . " ";
$label =~ tr/A-Z/a-z/;
}
$labels{$label} = 1;
- $data{$what}->{label} .= $label;
-
- printf ".. _%s:\n\n", $label;
+ $data{$what}->{label} = $label;
# only one label is enough
last;
}
+ }
+}
+#
+# Outputs the book on ReST format
+#
- $filepath =~ s,.*/(.*/.*),\1,;;
- $filepath =~ s,[/\-],_,g;;
- my $fileref = "abi_file_".$filepath;
+# \b doesn't work well with paths. So, we need to define something else
+my $bondary = qr { (?<![\w\/\`\{])(?=[\w\/\`\{])|(?<=[\w\/\`\{])(?![\w\/\`\{]) }x;
- if ($type eq "File") {
- my $bar = $w;
- $bar =~ s/./-/g;
+sub output_rest {
+ create_labels();
- print ".. _$fileref:\n\n";
- print "$w\n$bar\n\n";
- } else {
- my @names = split /\s*,\s*/,$w;
+ my $part = "";
+
+ foreach my $what (sort {
+ ($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") ||
+ $a cmp $b
+ } keys %data) {
+ my $type = $data{$what}->{type};
+
+ my @file = split / /, $data{$what}->{file};
+ my @filepath = split / /, $data{$what}->{filepath};
+
+ if ($enable_lineno) {
+ printf "#define LINENO %s%s#%s\n\n",
+ $prefix, $file[0],
+ $data{$what}->{line_no};
+ }
+
+ my $w = $what;
+ $w =~ s/([\(\)\_\-\*\=\^\~\\])/\\$1/g;
+
+ if ($type ne "File") {
+ my $cur_part = $what;
+ if ($what =~ '/') {
+ if ($what =~ m#^(\/?(?:[\w\-]+\/?){1,2})#) {
+ $cur_part = "Symbols under $1";
+ $cur_part =~ s,/$,,;
+ }
+ }
+
+ if ($cur_part ne "" && $part ne $cur_part) {
+ $part = $cur_part;
+ my $bar = $part;
+ $bar =~ s/./-/g;
+ print "$part\n$bar\n\n";
+ }
+
+ printf ".. _%s:\n\n", $data{$what}->{label};
+ my @names = split /, /,$w;
my $len = 0;
foreach my $name (@names) {
+ $name = "**$name**";
$len = length($name) if (length($name) > $len);
}
- print "What:\n\n";
-
print "+-" . "-" x $len . "-+\n";
foreach my $name (@names) {
printf "| %s", $name . " " x ($len - length($name)) . " |\n";
print "+-" . "-" x $len . "-+\n";
}
+
print "\n";
}
- print "Defined on file :ref:`$file <$fileref>`\n\n" if ($type ne "File");
+ for (my $i = 0; $i < scalar(@filepath); $i++) {
+ my $path = $filepath[$i];
+ my $f = $file[$i];
+
+ $path =~ s,.*/(.*/.*),$1,;;
+ $path =~ s,[/\-],_,g;;
+ my $fileref = "abi_file_".$path;
+
+ if ($type eq "File") {
+ print ".. _$fileref:\n\n";
+ } else {
+ print "Defined on file :ref:`$f <$fileref>`\n\n";
+ }
+ }
- my $desc = $data{$what}->{description};
- $desc =~ s/^\s+//;
+ if ($type eq "File") {
+ my $bar = $w;
+ $bar =~ s/./-/g;
+ print "$w\n$bar\n\n";
+ }
- # Remove title markups from the description, as they won't work
- $desc =~ s/\n[\-\*\=\^\~]+\n/\n/g;
+ my $desc = "";
+ $desc = $data{$what}->{description} if (defined($data{$what}->{description}));
+ $desc =~ s/\s+$/\n/;
if (!($desc =~ /^\s*$/)) {
- if ($desc =~ m/\:\n/ || $desc =~ m/\n[\t ]+/ || $desc =~ m/[\x00-\x08\x0b-\x1f\x7b-\xff]/) {
- # put everything inside a code block
- $desc =~ s/\n/\n /g;
+ if ($description_is_rst) {
+ # Remove title markups from the description
+ # Having titles inside ABI files will only work if extra
+ # care would be taken in order to strictly follow the same
+ # level order for each markup.
+ $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;
+
+ # Enrich text by creating cross-references
+
+ $desc =~ s,Documentation/(?!devicetree)(\S+)\.rst,:doc:`/$1`,g;
+
+ my @matches = $desc =~ m,Documentation/ABI/([\w\/\-]+),;
+ foreach my $f (@matches) {
+ my $xref = $f;
+ my $path = $f;
+ $path =~ s,.*/(.*/.*),$1,;;
+ $path =~ s,[/\-],_,g;;
+ $xref .= " <abi_file_" . $path . ">";
+ $desc =~ s,\bDocumentation/ABI/$f\b,:ref:`$xref`,g;
+ }
- print "::\n\n";
- print " $desc\n\n";
- } else {
- # Escape any special chars from description
- $desc =~s/([\x00-\x08\x0b-\x1f\x21-\x2a\x2d\x2f\x3c-\x40\x5c\x5e-\x60\x7b-\xff])/\\$1/g;
+ @matches = $desc =~ m,$bondary(/sys/[^\s\.\,\;\:\*\s\`\'\(\)]+)$bondary,;
+
+ foreach my $s (@matches) {
+ if (defined($data{$s}) && defined($data{$s}->{label})) {
+ my $xref = $s;
+
+ $xref =~ s/([\x00-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])/\\$1/g;
+ $xref = ":ref:`$xref <" . $data{$s}->{label} . ">`";
+
+ $desc =~ s,$bondary$s$bondary,$xref,g;
+ }
+ }
print "$desc\n\n";
+ } else {
+ $desc =~ s/^\s+//;
+
+ # Remove title markups from the description, as they won't work
+ $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;
+
+ if ($desc =~ m/\:\n/ || $desc =~ m/\n[\t ]+/ || $desc =~ m/[\x00-\x08\x0b-\x1f\x7b-\xff]/) {
+ # put everything inside a code block
+ $desc =~ s/\n/\n /g;
+
+ print "::\n\n";
+ print " $desc\n\n";
+ } else {
+ # Escape any special chars from description
+ $desc =~s/([\x00-\x08\x0b-\x1f\x21-\x2a\x2d\x2f\x3c-\x40\x5c\x5e-\x60\x7b-\xff])/\\$1/g;
+ print "$desc\n\n";
+ }
}
} else {
print "DESCRIPTION MISSING for $what\n\n" if (!$data{$what}->{is_file});
}
- if ($data{$what}->{xrefs}) {
+ if ($data{$what}->{symbols}) {
printf "Has the following ABI:\n\n";
- foreach my $p(@{$data{$what}->{xrefs}}) {
- my ($content, $label) = @{$p};
- $label = "abi_" . $label . " ";
- $label =~ tr/A-Z/a-z/;
-
- # Convert special chars to "_"
- $label =~s/([\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\xff])/_/g;
- $label =~ s,_+,_,g;
- $label =~ s,_$,,;
+ foreach my $content(@{$data{$what}->{symbols}}) {
+ my $label = $data{$symbols{$content}->{xref}}->{label};
# Escape special chars from content
$content =~s/([\x00-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])/\\$1/g;
print "- :ref:`$content <$label>`\n\n";
}
}
+
+ if (defined($data{$what}->{users})) {
+ my $users = $data{$what}->{users};
+
+ $users =~ s/\n/\n\t/g;
+ printf "Users:\n\t%s\n\n", $users if ($users ne "");
+ }
+
}
}
print "\n$what\n$bar\n\n";
- my $kernelversion = $data{$what}->{kernelversion};
- my $contact = $data{$what}->{contact};
- my $users = $data{$what}->{users};
- my $date = $data{$what}->{date};
- my $desc = $data{$what}->{description};
- $kernelversion =~ s/^\s+//;
- $contact =~ s/^\s+//;
- $users =~ s/^\s+//;
- $users =~ s/\n//g;
- $date =~ s/^\s+//;
- $desc =~ s/^\s+//;
+ my $kernelversion = $data{$what}->{kernelversion} if (defined($data{$what}->{kernelversion}));
+ my $contact = $data{$what}->{contact} if (defined($data{$what}->{contact}));
+ my $users = $data{$what}->{users} if (defined($data{$what}->{users}));
+ my $date = $data{$what}->{date} if (defined($data{$what}->{date}));
+ my $desc = $data{$what}->{description} if (defined($data{$what}->{description}));
+
+ $kernelversion =~ s/^\s+// if ($kernelversion);
+ $contact =~ s/^\s+// if ($contact);
+ if ($users) {
+ $users =~ s/^\s+//;
+ $users =~ s/\n//g;
+ }
+ $date =~ s/^\s+// if ($date);
+ $desc =~ s/^\s+// if ($desc);
printf "Kernel version:\t\t%s\n", $kernelversion if ($kernelversion);
printf "Date:\t\t\t%s\n", $date if ($date);
printf "Contact:\t\t%s\n", $contact if ($contact);
printf "Users:\t\t\t%s\n", $users if ($users);
- print "Defined on file:\t$file\n\n";
+ print "Defined on file(s):\t$file\n\n";
print "Description:\n\n$desc";
}
}
+# Ensure that the prefix will always end with a slash
+# While this is not needed for find, it makes the patch nicer
+# with --enable-lineno
+$prefix =~ s,/?$,/,;
#
# Parses all ABI files located at $prefix dir
#
# Handles the command
#
-if ($cmd eq "rest") {
- output_rest;
-} elsif ($cmd eq "search") {
+if ($cmd eq "search") {
search_symbols;
-}
+} else {
+ if ($cmd eq "rest") {
+ output_rest;
+ }
+
+ # Warn about duplicated ABI entries
+ foreach my $what(sort keys %symbols) {
+ my @files = @{$symbols{$what}->{file}};
+ next if (scalar(@files) == 1);
+
+ printf STDERR "Warning: $what is defined %d times: @files\n",
+ scalar(@files);
+ }
+}
__END__
=head1 SYNOPSIS
-B<abi_book.pl> [--debug] [--man] [--help] [--dir=<dir>] <COMAND> [<ARGUMENT>]
+B<abi_book.pl> [--debug] [--enable-lineno] [--man] [--help]
+ [--(no-)rst-source] [--dir=<dir>] <COMAND> [<ARGUMENT>]
Where <COMMAND> can be:
Changes the location of the ABI search. By default, it uses
the Documentation/ABI directory.
+=item B<--rst-source> and B<--no-rst-source>
+
+The input file may be using ReST syntax or not. Those two options allow
+selecting between a rst-compliant source ABI (--rst-source), or a
+plain text that may be violating ReST spec, so it requres some escaping
+logic (--no-rst-source).
+
+=item B<--enable-lineno>
+
+Enable output of #define LINENO lines.
+
=item B<--debug>
Put the script in verbose mode, useful for debugging. Can be called multiple
print "\n\n.. c:type:: " . $name . "\n\n";
} else {
my $name = $args{'struct'};
- print "\n\n.. c:struct:: " . $name . "\n\n";
+ if ($args{'type'} eq 'union') {
+ print "\n\n.. c:union:: " . $name . "\n\n";
+ } else {
+ print "\n\n.. c:struct:: " . $name . "\n\n";
+ }
}
print_lineno($declaration_start_line);
$lineprefix = " ";
}
}
+my $typedef_type = qr { ((?:\s+[\w\*]+){1,8})\s* }x;
+my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x;
+my $typedef_args = qr { \s*\((.*)\); }x;
+
+my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x;
+my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x;
+
sub dump_typedef($$) {
my $x = shift;
my $file = shift;
$x =~ s@/\*.*?\*/@@gos; # strip comments.
- # Parse function prototypes
- if ($x =~ /typedef\s+(\w+)\s*\(\*\s*(\w\S+)\s*\)\s*\((.*)\);/ ||
- $x =~ /typedef\s+(\w+)\s*(\w\S+)\s*\s*\((.*)\);/) {
-
- # Function typedefs
+ # Parse function typedef prototypes
+ if ($x =~ $typedef1 || $x =~ $typedef2) {
$return_type = $1;
$declaration_name = $2;
my $args = $3;
+ $return_type =~ s/^\s+//;
create_parameterlist($args, ',', $file, $declaration_name);
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Usage: $ ./scripts/lld-version.sh ld.lld
+#
+# Print the linker version of `ld.lld' in a 5 or 6-digit form
+# such as `100001' for ld.lld 10.0.1 etc.
+
+linker_string="$($* --version)"
+
+if ! ( echo $linker_string | grep -q LLD ); then
+ echo 0
+ exit 1
+fi
+
+VERSION=$(echo $linker_string | cut -d ' ' -f 2)
+MAJOR=$(echo $VERSION | cut -d . -f 1)
+MINOR=$(echo $VERSION | cut -d . -f 2)
+PATCHLEVEL=$(echo $VERSION | cut -d . -f 3)
+printf "%d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL
chmod -R go-w "$pdir"
# in case we are in a restrictive umask environment like 0077
chmod -R a+rX "$pdir"
+ # in case we build in a setuid/setgid directory
+ chmod -R ug-s "$pdir"
# Create the package
dpkg-gencontrol -p$pname -P"$pdir"
struct tpm_digest *digests;
struct ima_template_desc *template_desc; /* template descriptor */
u32 template_data_len;
- struct ima_field_data template_data[0]; /* template related data */
+ struct ima_field_data template_data[]; /* template related data */
};
struct ima_queue_entry {
* is valid, it just won't be added to the cache.
*/
new = kzalloc(sizeof(*new), GFP_ATOMIC);
- if (!new)
+ if (!new) {
+ ret = -ENOMEM;
goto out;
+ }
new->psec.subnet_prefix = subnet_prefix;
new->psec.pkey = pkey_num;
unlock:
up_write(&card->controls_rwsem);
- return 0;
+ return err;
}
static int snd_ctl_elem_add_user(struct snd_ctl_file *file,
#ifdef CONFIG_COMPAT
/**
- * snd_ctl_unregister_ioctl - de-register the device-specific compat 32bit
- * control-ioctls
+ * snd_ctl_unregister_ioctl_compat - de-register the device-specific compat
+ * 32bit control-ioctls
* @fcn: ioctl callback function to unregister
*/
int snd_ctl_unregister_ioctl_compat(snd_kctl_ioctl_func_t fcn)
EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_close);
/**
- * snd_dmaengine_pcm_release_chan_close - Close a dmaengine based PCM substream and release channel
+ * snd_dmaengine_pcm_close_release_chan - Close a dmaengine based PCM
+ * substream and release channel
* @substream: PCM substream
*
* Releases the DMA channel associated with the PCM substream.
EXPORT_SYMBOL(snd_pcm_set_ops);
/**
- * snd_pcm_sync - set the PCM sync id
+ * snd_pcm_set_sync - set the PCM sync id
* @substream: the pcm substream
*
* Sets the PCM sync identifier for the card.
EXPORT_SYMBOL_GPL(snd_pcm_stream_lock);
/**
- * snd_pcm_stream_lock - Unlock the PCM stream
+ * snd_pcm_stream_unlock - Unlock the PCM stream
* @substream: PCM substream
*
* This unlocks the PCM stream that has been locked via snd_pcm_stream_lock().
}
/**
- * snd_pcm_hw_param_choose - choose a configuration defined by @params
+ * snd_pcm_hw_params_choose - choose a configuration defined by @params
* @pcm: PCM instance
* @params: the hw_params instance
*
t = (struct snd_efw_transaction *)data;
length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
- spin_lock_irq(&efw->lock);
+ spin_lock(&efw->lock);
if (efw->push_ptr < efw->pull_ptr)
capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
copy_resp_to_buf(efw, data, length, rcode);
end:
- spin_unlock_irq(&instances_lock);
+ spin_unlock(&instances_lock);
}
static void
return NULL;
if (bus->idx != bus_idx)
return NULL;
+ if (addr < 0 || addr > 31)
+ return NULL;
list_for_each_entry(hlink, &bus->hlink_list, list) {
for (i = 0; i < HDA_MAX_CODECS; i++) {
snd_hdac_leave_pm(&codec->core);
}
-static int hda_codec_runtime_suspend(struct device *dev)
+static int hda_codec_suspend(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
unsigned int state;
return 0;
}
-static int hda_codec_runtime_resume(struct device *dev)
+static int hda_codec_resume(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
pm_runtime_mark_last_busy(dev);
return 0;
}
+
+static int hda_codec_runtime_suspend(struct device *dev)
+{
+ return hda_codec_suspend(dev);
+}
+
+static int hda_codec_runtime_resume(struct device *dev)
+{
+ return hda_codec_resume(dev);
+}
+
#endif /* CONFIG_PM */
#ifdef CONFIG_PM_SLEEP
-static int hda_codec_force_resume(struct device *dev)
+static int hda_codec_pm_prepare(struct device *dev)
+{
+ return pm_runtime_suspended(dev);
+}
+
+static void hda_codec_pm_complete(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
- int ret;
- ret = pm_runtime_force_resume(dev);
- /* schedule jackpoll work for jack detection update */
- if (codec->jackpoll_interval ||
- (pm_runtime_suspended(dev) && hda_codec_need_resume(codec)))
- schedule_delayed_work(&codec->jackpoll_work,
- codec->jackpoll_interval);
- return ret;
+ if (pm_runtime_suspended(dev) && (codec->jackpoll_interval ||
+ hda_codec_need_resume(codec) || codec->forced_resume))
+ pm_request_resume(dev);
}
static int hda_codec_pm_suspend(struct device *dev)
{
dev->power.power_state = PMSG_SUSPEND;
- return pm_runtime_force_suspend(dev);
+ return hda_codec_suspend(dev);
}
static int hda_codec_pm_resume(struct device *dev)
{
dev->power.power_state = PMSG_RESUME;
- return hda_codec_force_resume(dev);
+ return hda_codec_resume(dev);
}
static int hda_codec_pm_freeze(struct device *dev)
{
dev->power.power_state = PMSG_FREEZE;
- return pm_runtime_force_suspend(dev);
+ return hda_codec_suspend(dev);
}
static int hda_codec_pm_thaw(struct device *dev)
{
dev->power.power_state = PMSG_THAW;
- return hda_codec_force_resume(dev);
+ return hda_codec_resume(dev);
}
static int hda_codec_pm_restore(struct device *dev)
{
dev->power.power_state = PMSG_RESTORE;
- return hda_codec_force_resume(dev);
+ return hda_codec_resume(dev);
}
#endif /* CONFIG_PM_SLEEP */
/* referred in hda_bind.c */
const struct dev_pm_ops hda_codec_driver_pm = {
#ifdef CONFIG_PM_SLEEP
+ .prepare = hda_codec_pm_prepare,
+ .complete = hda_codec_pm_complete,
.suspend = hda_codec_pm_suspend,
.resume = hda_codec_pm_resume,
.freeze = hda_codec_pm_freeze,
/* 24 unused */
#define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */
#define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */
-#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */
+/* 27 unused */
#define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */
#define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */
#define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */
unsigned int align_buffer_size:1;
unsigned int region_requested:1;
unsigned int disabled:1; /* disabled by vga_switcheroo */
+ unsigned int pm_prepared:1;
/* GTS present */
unsigned int gts_present:1;
struct nid_path *path;
hda_nid_t pin = pins[i];
- path = snd_hda_get_path_from_idx(codec, path_idx[i]);
- if (path) {
- badness += assign_out_path_ctls(codec, path);
- continue;
+ if (!spec->obey_preferred_dacs) {
+ path = snd_hda_get_path_from_idx(codec, path_idx[i]);
+ if (path) {
+ badness += assign_out_path_ctls(codec, path);
+ continue;
+ }
}
dacs[i] = get_preferred_dac(codec, pin);
if (dacs[i]) {
if (is_dac_already_used(codec, dacs[i]))
badness += bad->shared_primary;
+ } else if (spec->obey_preferred_dacs) {
+ badness += BAD_NO_PRIMARY_DAC;
}
if (!dacs[i])
unsigned int power_down_unused:1; /* power down unused widgets */
unsigned int dac_min_mute:1; /* minimal = mute for DACs */
unsigned int suppress_vmaster:1; /* don't create vmaster kctls */
+ unsigned int obey_preferred_dacs:1; /* obey preferred_dacs assignment */
/* other internal flags */
unsigned int no_analog:1; /* digital I/O only */
/* PCH for HSW/BDW; with runtime PM */
/* no i915 binding for this as HSW/BDW has another controller for HDMI */
#define AZX_DCAPS_INTEL_PCH \
- (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
- AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+ (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME)
/* HSW HDMI */
#define AZX_DCAPS_INTEL_HASWELL \
display_power(chip, false);
}
-static void __azx_runtime_resume(struct azx *chip, bool from_rt)
+static void __azx_runtime_resume(struct azx *chip)
{
struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
struct hdac_bus *bus = azx_bus(chip);
azx_init_pci(chip);
hda_intel_init_chip(chip, true);
- if (from_rt) {
+ /* Avoid codec resume if runtime resume is for system suspend */
+ if (!chip->pm_prepared) {
list_for_each_codec(codec, &chip->bus) {
if (codec->relaxed_resume)
continue;
}
#ifdef CONFIG_PM_SLEEP
+static int azx_prepare(struct device *dev)
+{
+ struct snd_card *card = dev_get_drvdata(dev);
+ struct azx *chip;
+
+ chip = card->private_data;
+ chip->pm_prepared = 1;
+
+ /* HDA controller always requires different WAKEEN for runtime suspend
+ * and system suspend, so don't use direct-complete here.
+ */
+ return 0;
+}
+
+static void azx_complete(struct device *dev)
+{
+ struct snd_card *card = dev_get_drvdata(dev);
+ struct azx *chip;
+
+ chip = card->private_data;
+ chip->pm_prepared = 0;
+}
+
static int azx_suspend(struct device *dev)
{
struct snd_card *card = dev_get_drvdata(dev);
chip = card->private_data;
bus = azx_bus(chip);
- snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
- /* An ugly workaround: direct call of __azx_runtime_suspend() and
- * __azx_runtime_resume() for old Intel platforms that suffer from
- * spurious wakeups after S3 suspend
- */
- if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
- __azx_runtime_suspend(chip);
- else
- pm_runtime_force_suspend(dev);
+ __azx_runtime_suspend(chip);
if (bus->irq >= 0) {
free_irq(bus->irq, chip);
bus->irq = -1;
if (azx_acquire_irq(chip, 1) < 0)
return -EIO;
- if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
- __azx_runtime_resume(chip, false);
- else
- pm_runtime_force_resume(dev);
- snd_power_change_state(card, SNDRV_CTL_POWER_D0);
+ __azx_runtime_resume(chip);
trace_azx_resume(chip);
return 0;
chip = card->private_data;
/* enable controller wake up event */
- if (snd_power_get_state(card) == SNDRV_CTL_POWER_D0) {
- azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) |
- STATESTS_INT_MASK);
- }
+ azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) | STATESTS_INT_MASK);
__azx_runtime_suspend(chip);
trace_azx_runtime_suspend(chip);
{
struct snd_card *card = dev_get_drvdata(dev);
struct azx *chip;
- bool from_rt = snd_power_get_state(card) == SNDRV_CTL_POWER_D0;
if (!azx_is_pm_ready(card))
return 0;
chip = card->private_data;
- __azx_runtime_resume(chip, from_rt);
+ __azx_runtime_resume(chip);
/* disable controller Wake Up event*/
- if (from_rt) {
- azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
- ~STATESTS_INT_MASK);
- }
+ azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK);
trace_azx_runtime_resume(chip);
return 0;
static const struct dev_pm_ops azx_pm = {
SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume)
#ifdef CONFIG_PM_SLEEP
+ .prepare = azx_prepare,
+ .complete = azx_complete,
.freeze_noirq = azx_freeze_noirq,
.thaw_noirq = azx_thaw_noirq,
#endif
if (azx_has_pm_runtime(chip)) {
pm_runtime_use_autosuspend(&pci->dev);
+ pm_runtime_allow(&pci->dev);
pm_runtime_put_autosuspend(&pci->dev);
}
/* DG1 */
{ PCI_DEVICE(0x8086, 0x490d),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+ /* Alderlake-S */
+ { PCI_DEVICE(0x8086, 0x7ad0),
+ .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
/* Elkhart Lake */
{ PCI_DEVICE(0x8086, 0x4b55),
.driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
case QUIRK_AE5:
ca0132_mmio_init_ae5(codec);
break;
+ default:
+ break;
}
}
HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI", patch_i915_icl_hdmi),
HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI", patch_i915_tgl_hdmi),
HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI", patch_i915_tgl_hdmi),
+HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI", patch_i915_tgl_hdmi),
HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI", patch_i915_tgl_hdmi),
HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI", patch_i915_icl_hdmi),
HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI", patch_i915_icl_hdmi),
unsigned int no_shutup_pins:1;
unsigned int ultra_low_power:1;
unsigned int has_hs_key:1;
+ unsigned int no_internal_mic_pin:1;
/* for PLL fix */
hda_nid_t pll_nid;
alc_update_coef_idx(codec, 0x7, 1<<5, 0);
break;
case 0x10ec0892:
+ case 0x10ec0897:
alc_update_coef_idx(codec, 0x7, 1<<5, 0);
break;
case 0x10ec0899:
SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x9506, "Clevo P955HQ", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x950A, "Clevo P955H[PR]", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e3, "Clevo P955[ER]T", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e4, "Clevo P955ER", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e5, "Clevo P955EE6", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x95e6, "Clevo P950R[CDF]", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x96e1, "Clevo P960[ER][CDFN]-K", ALC1220_FIXUP_CLEVO_P950),
SND_PCI_QUIRK(0x1558, 0x97e1, "Clevo P970[ER][CDFN]", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x97e2, "Clevo P970RC-M", ALC1220_FIXUP_CLEVO_P950),
+ SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
- SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20);
}
+static void alc287_fixup_hp_gpio_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc_fixup_hp_gpio_led(codec, action, 0x10, 0);
+}
+
/* turn on/off mic-mute LED per capture hook via VREF change */
static int vref_micmute_led_set(struct led_classdev *led_cdev,
enum led_brightness brightness)
static void alc_headset_mode_unplugged(struct hda_codec *codec)
{
+ struct alc_spec *spec = codec->spec;
static const struct coef_fw coef0255[] = {
WRITE_COEF(0x1b, 0x0c0b), /* LDO and MISC control */
WRITE_COEF(0x45, 0xd089), /* UAJ function set to menual mode */
{}
};
+ if (spec->no_internal_mic_pin) {
+ alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12);
+ return;
+ }
+
switch (codec->core.vendor_id) {
case 0x10ec0255:
alc_process_coef_fw(codec, coef0255);
{}
};
+ if (spec->no_internal_mic_pin) {
+ alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12);
+ return;
+ }
+
switch (codec->core.vendor_id) {
case 0x10ec0255:
alc_process_coef_fw(codec, coef0255);
codec->power_save_node = 0;
}
+/* avoid DAC 0x06 for bass speaker 0x17; it has no volume control */
+static void alc289_fixup_asus_ga401(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static const hda_nid_t preferred_pairs[] = {
+ 0x14, 0x02, 0x17, 0x02, 0x21, 0x03, 0
+ };
+ struct alc_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ spec->gen.preferred_dacs = preferred_pairs;
+ spec->gen.obey_preferred_dacs = 1;
+ }
+}
+
/* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */
static void alc285_fixup_invalidate_dacs(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
snd_hda_override_wcaps(codec, 0x03, 0);
}
+static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec)
+{
+ switch (codec->core.vendor_id) {
+ case 0x10ec0274:
+ case 0x10ec0294:
+ case 0x10ec0225:
+ case 0x10ec0295:
+ case 0x10ec0299:
+ alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
+ alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
+ break;
+ case 0x10ec0235:
+ case 0x10ec0236:
+ case 0x10ec0255:
+ case 0x10ec0256:
+ alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
+ alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
+ break;
+ }
+}
+
static void alc295_fixup_chromebook(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
spec->ultra_low_power = true;
break;
case HDA_FIXUP_ACT_INIT:
- switch (codec->core.vendor_id) {
- case 0x10ec0295:
- alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
- alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
- break;
- case 0x10ec0236:
- alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
- alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
- break;
- }
+ alc_combo_jack_hp_jd_restart(codec);
break;
}
}
alc_write_coef_idx(codec, 0x65, 0x0);
}
+static void alc274_fixup_hp_headset_mic(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ switch (action) {
+ case HDA_FIXUP_ACT_INIT:
+ alc_combo_jack_hp_jd_restart(codec);
+ break;
+ }
+}
+
+static void alc_fixup_no_int_mic(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ /* Mic RING SLEEVE swap for combo jack */
+ alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12);
+ spec->no_internal_mic_pin = true;
+ break;
+ case HDA_FIXUP_ACT_INIT:
+ alc_combo_jack_hp_jd_restart(codec);
+ break;
+ }
+}
+
/* for hda_fixup_thinkpad_acpi() */
#include "thinkpad_helper.c"
ALC256_FIXUP_INTEL_NUC8_RUGGED,
ALC255_FIXUP_XIAOMI_HEADSET_MIC,
ALC274_FIXUP_HP_MIC,
+ ALC274_FIXUP_HP_HEADSET_MIC,
+ ALC256_FIXUP_ASUS_HPE,
+ ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK,
+ ALC287_FIXUP_HP_GPIO_LED,
+ ALC256_FIXUP_HP_HEADSET_MIC,
+ ALC236_FIXUP_DELL_AIO_HEADSET_MIC,
};
static const struct hda_fixup alc269_fixups[] = {
.chain_id = ALC269_FIXUP_HEADSET_MIC
},
[ALC289_FIXUP_ASUS_GA401] = {
- .type = HDA_FIXUP_PINS,
- .v.pins = (const struct hda_pintbl[]) {
- { 0x19, 0x03a11020 }, /* headset mic with jack detect */
- { }
- },
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc289_fixup_asus_ga401,
+ .chained = true,
+ .chain_id = ALC289_FIXUP_ASUS_GA502,
},
[ALC289_FIXUP_ASUS_GA502] = {
.type = HDA_FIXUP_PINS,
{ }
},
.chained = true,
- .chain_id = ALC289_FIXUP_ASUS_GA401
+ .chain_id = ALC289_FIXUP_ASUS_GA502
},
[ALC274_FIXUP_HP_MIC] = {
.type = HDA_FIXUP_VERBS,
{ }
},
},
+ [ALC274_FIXUP_HP_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc274_fixup_hp_headset_mic,
+ .chained = true,
+ .chain_id = ALC274_FIXUP_HP_MIC
+ },
+ [ALC256_FIXUP_ASUS_HPE] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ /* Set EAPD high */
+ { 0x20, AC_VERB_SET_COEF_INDEX, 0x0f },
+ { 0x20, AC_VERB_SET_PROC_COEF, 0x7778 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC
+ },
+ [ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_headset_jack,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_THINKPAD_ACPI
+ },
+ [ALC287_FIXUP_HP_GPIO_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc287_fixup_hp_gpio_led,
+ },
+ [ALC256_FIXUP_HP_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc274_fixup_hp_headset_mic,
+ },
+ [ALC236_FIXUP_DELL_AIO_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc_fixup_no_int_mic,
+ .chained = true,
+ .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x097d, "Dell Precision", ALC289_FIXUP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x098d, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x09bf, "Dell Precision", ALC233_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC),
SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360),
+ SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
- SND_PCI_QUIRK(0x103c, 0x874e, "HP", ALC274_FIXUP_HP_MIC),
SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x877d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+ SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x1401, "Clevo L140[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x1403, "Clevo N140CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x40a1, "Clevo NL40GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x40c1, "Clevo NL40[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x40d1, "Clevo NL41DU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50a3, "Clevo NJ51GU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50b3, "Clevo NK50S[BEZ]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50b6, "Clevo NK50S5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50b8, "Clevo NK50SZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50d5, "Clevo NP50D5", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50f0, "Clevo NH50A[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x50f3, "Clevo NH58DPQ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x5101, "Clevo S510WU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x5157, "Clevo W517GU1", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x51a1, "Clevo NS50MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8535, "Clevo NH50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8536, "Clevo NH79D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8550, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8551, "System76 Gazelle (gaze14)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x8560, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1558, 0x8561, "System76 Gazelle (gaze14)", ALC269_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8a20, "Clevo NH55DCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8a51, "Clevo NH70RCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x8d50, "Clevo NH55RCQ-M", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x951d, "Clevo N950T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x961d, "Clevo N960S[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0x971d, "Clevo N970T[CDF]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0xa500, "Clevo NL53RU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS),
SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x17aa, 0x2292, "Thinkpad X1 Carbon 7th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x22be, "Thinkpad X1 Carbon 8th", ALC285_FIXUP_THINKPAD_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x22c1, "Thinkpad P1 Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
+ SND_PCI_QUIRK(0x17aa, 0x22c2, "Thinkpad X1 Extreme Gen 3", ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
{0x19, 0x02a11020},
{0x1a, 0x02a11030},
{0x21, 0x0221101f}),
+ SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC,
+ {0x21, 0x02211010}),
+ SND_HDA_PIN_QUIRK(0x10ec0236, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11020},
+ {0x21, 0x02211030}),
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
{0x14, 0x90170110},
{0x21, 0x02211020}),
{0x1a, 0x90a70130},
{0x1b, 0x90170110},
{0x21, 0x03211020}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x103c, "HP", ALC256_FIXUP_HP_HEADSET_MIC,
+ {0x14, 0x90170110},
+ {0x19, 0x02a11020},
+ {0x21, 0x0221101f}),
+ SND_HDA_PIN_QUIRK(0x10ec0274, 0x103c, "HP", ALC274_FIXUP_HP_HEADSET_MIC,
+ {0x17, 0x90170110},
+ {0x19, 0x03a11030},
+ {0x21, 0x03211020}),
SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
{0x12, 0x90a60130},
{0x14, 0x90170110},
SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC292_STANDARD_PINS,
{0x13, 0x90a60140}),
+ SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_HPE,
+ {0x17, 0x90170110},
+ {0x21, 0x04211020}),
SND_HDA_PIN_QUIRK(0x10ec0294, 0x1043, "ASUS", ALC294_FIXUP_ASUS_MIC,
{0x14, 0x90170110},
{0x1b, 0x90a70130},
HDA_CODEC_ENTRY(0x10ec0888, "ALC888", patch_alc882),
HDA_CODEC_ENTRY(0x10ec0889, "ALC889", patch_alc882),
HDA_CODEC_ENTRY(0x10ec0892, "ALC892", patch_alc662),
+ HDA_CODEC_ENTRY(0x10ec0897, "ALC897", patch_alc662),
HDA_CODEC_ENTRY(0x10ec0899, "ALC898", patch_alc882),
HDA_CODEC_ENTRY(0x10ec0900, "ALC1150", patch_alc882),
HDA_CODEC_ENTRY(0x10ec0b00, "ALCS1200A", patch_alc882),
unsigned int i;
#endif
- mutex_lock(&mgr->msg_lock);
err = 0;
/* copy message descriptor from miXart to driver */
writel_be(headptr, MIXART_MEM(mgr, MSG_OUTBOUND_FREE_HEAD));
_clean_exit:
- mutex_unlock(&mgr->msg_lock);
-
return err;
}
resp.data = resp_data;
resp.size = max_resp_size;
+ mutex_lock(&mgr->msg_lock);
err = get_msg(mgr, &resp, msg_frame);
+ mutex_unlock(&mgr->msg_lock);
if( request->message_id != resp.message_id )
dev_err(&mgr->pci->dev, "RESPONSE ERROR!\n");
}
mchp_spdiftx_channel_status_write(dev);
spin_unlock_irqrestore(&ctrl->lock, flags);
- mr |= SPDIFTX_MR_VALID1 | SPDIFTX_MR_VALID2;
if (dev->gclk_enabled) {
clk_disable_unprepare(dev->gclk);
&cs42l51_adcr_mux_controls),
};
+static int mclk_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_component *comp = snd_soc_dapm_to_component(w->dapm);
+ struct cs42l51_private *cs42l51 = snd_soc_component_get_drvdata(comp);
+
+ switch (event) {
+ case SND_SOC_DAPM_PRE_PMU:
+ return clk_prepare_enable(cs42l51->mclk_handle);
+ case SND_SOC_DAPM_POST_PMD:
+ /* Delay mclk shutdown to fulfill power-down sequence requirements */
+ msleep(20);
+ clk_disable_unprepare(cs42l51->mclk_handle);
+ break;
+ }
+
+ return 0;
+}
+
static const struct snd_soc_dapm_widget cs42l51_dapm_mclk_widgets[] = {
- SND_SOC_DAPM_CLOCK_SUPPLY("MCLK")
+ SND_SOC_DAPM_SUPPLY("MCLK", SND_SOC_NOPM, 0, 0, mclk_event,
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
};
static const struct snd_soc_dapm_route cs42l51_routes[] = {
#include <sound/soc-dapm.h>
#include <sound/soc.h>
#include <sound/tlv.h>
+#include <sound/rt1015.h>
#include "rl6231.h"
#include "rt1015.h"
+static const struct rt1015_platform_data i2s_default_platform_data = {
+ .power_up_delay_ms = 50,
+};
+
static const struct reg_default rt1015_reg[] = {
{ 0x0000, 0x0000 },
{ 0x0004, 0xa000 },
struct rt1015_priv *rt1015 = container_of(work, struct rt1015_priv,
flush_work.work);
struct snd_soc_component *component = rt1015->component;
- unsigned int val, i = 0, count = 20;
+ unsigned int val, i = 0, count = 200;
while (i < count) {
usleep_range(1000, 1500);
case SND_SOC_DAPM_POST_PMU:
if (rt1015->hw_config == RT1015_HW_28)
schedule_delayed_work(&rt1015->flush_work, msecs_to_jiffies(10));
+ msleep(rt1015->pdata.power_up_delay_ms);
break;
default:
break;
MODULE_DEVICE_TABLE(acpi, rt1015_acpi_match);
#endif
+static void rt1015_parse_dt(struct rt1015_priv *rt1015, struct device *dev)
+{
+ device_property_read_u32(dev, "realtek,power-up-delay-ms",
+ &rt1015->pdata.power_up_delay_ms);
+}
+
static int rt1015_i2c_probe(struct i2c_client *i2c,
const struct i2c_device_id *id)
{
+ struct rt1015_platform_data *pdata = dev_get_platdata(&i2c->dev);
struct rt1015_priv *rt1015;
int ret;
unsigned int val;
i2c_set_clientdata(i2c, rt1015);
+ rt1015->pdata = i2s_default_platform_data;
+
+ if (pdata)
+ rt1015->pdata = *pdata;
+ else
+ rt1015_parse_dt(rt1015, &i2c->dev);
+
rt1015->regmap = devm_regmap_init_i2c(i2c, &rt1015_regmap);
if (IS_ERR(rt1015->regmap)) {
ret = PTR_ERR(rt1015->regmap);
#ifndef __RT1015_H__
#define __RT1015_H__
+#include <sound/rt1015.h>
#define RT1015_DEVICE_ID_VAL 0x1011
#define RT1015_DEVICE_ID_VAL2 0x1015
struct rt1015_priv {
struct snd_soc_component *component;
+ struct rt1015_platform_data pdata;
struct regmap *regmap;
int sysclk;
int sysclk_src;
{RT5682_DAC_ADC_DIG_VOL1, 0xa020},
{RT5682_I2C_CTRL, 0x000f},
{RT5682_PLL2_INTERNAL, 0x8266},
+ {RT5682_SAR_IL_CMD_3, 0x8365},
};
void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev)
"ZERO", "RX_MIX_TX8", "DEC8", "DEC8_192"
};
-static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0);
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1);
static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1);
static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0);
struct soc_bytes_ext bytes_ext;
};
-static const DECLARE_TLV_DB_SCALE(digital_gain, 0, 1, 0);
+static const DECLARE_TLV_DB_SCALE(digital_gain, -8400, 100, -8400);
static const DECLARE_TLV_DB_SCALE(line_gain, 0, 7, 1);
static const DECLARE_TLV_DB_SCALE(analog_gain, 0, 25, 1);
static const DECLARE_TLV_DB_SCALE(ear_pa_gain, 0, 150, 0);
mem = wm_adsp_find_region(dsp, type);
if (!mem) {
adsp_err(dsp, "No region of type: %x\n", type);
+ ret = -EINVAL;
goto out_fw;
}
.id = 0,
.playback = {
.stream_name = "SPKR Playback",
+ .rates = SNDRV_PCM_RATE_48000,
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
.rate_max = 48000,
.rate_min = 48000,
.channels_min = 1,
if SND_SOC_INTEL_SST_TOPLEVEL
-config SND_SST_IPC
- tristate
- # This option controls the IPC core for HiFi2 platforms
-
-config SND_SST_IPC_PCI
- tristate
- select SND_SST_IPC
- # This option controls the PCI-based IPC for HiFi2 platforms
- # (Medfield, Merrifield).
-
-config SND_SST_IPC_ACPI
- tristate
- select SND_SST_IPC
- # This option controls the ACPI-based IPC for HiFi2 platforms
- # (Baytrail, Cherrytrail)
-
config SND_SOC_INTEL_SST
tristate
config SND_SST_ATOM_HIFI2_PLATFORM_PCI
tristate "PCI HiFi2 (Merrifield) Platforms"
depends on X86 && PCI
- select SND_SST_IPC_PCI
select SND_SST_ATOM_HIFI2_PLATFORM
help
If you have a Intel Merrifield/Edison platform, then
tristate "ACPI HiFi2 (Baytrail, Cherrytrail) Platforms"
default ACPI
depends on X86 && ACPI && PCI
- select SND_SST_IPC_ACPI
select SND_SST_ATOM_HIFI2_PLATFORM
select SND_SOC_ACPI_INTEL_MATCH
select IOSF_MBI
obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-soc-sst-atom-hifi2-platform.o
# DSP driver
-obj-$(CONFIG_SND_SST_IPC) += sst/
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += sst/
snd-intel-sst-pci-objs += sst_pci.o
snd-intel-sst-acpi-objs += sst_acpi.o
-obj-$(CONFIG_SND_SST_IPC) += snd-intel-sst-core.o
-obj-$(CONFIG_SND_SST_IPC_PCI) += snd-intel-sst-pci.o
-obj-$(CONFIG_SND_SST_IPC_ACPI) += snd-intel-sst-acpi.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM) += snd-intel-sst-core.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_PCI) += snd-intel-sst-pci.o
+obj-$(CONFIG_SND_SST_ATOM_HIFI2_PLATFORM_ACPI) += snd-intel-sst-acpi.o
.driver_data = (void *)(BYT_RT5640_IN1_MAP |
BYT_RT5640_MCLK_EN),
},
- { /* HP Pavilion x2 10-n000nd */
+ { /* HP Pavilion x2 10-k0XX, 10-n0XX */
.matches = {
- DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion x2 Detachable"),
},
.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
BYT_RT5640_JD_SRC_JD2_IN4N |
BYT_RT5640_SSP0_AIF1 |
BYT_RT5640_MCLK_EN),
},
+ { /* HP Pavilion x2 10-p0XX */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP x2 Detachable 10-p0XX"),
+ },
+ .driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+ BYT_RT5640_JD_SRC_JD1_IN4P |
+ BYT_RT5640_OVCD_TH_1500UA |
+ BYT_RT5640_OVCD_SF_0P75 |
+ BYT_RT5640_MCLK_EN),
+ },
{ /* HP Stream 7 */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
struct snd_interval *chan = hw_param_interval(params,
SNDRV_PCM_HW_PARAM_CHANNELS);
struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
- struct snd_soc_dpcm *dpcm = container_of(
- params, struct snd_soc_dpcm, hw_params);
- struct snd_soc_dai_link *fe_dai_link = dpcm->fe->dai_link;
- struct snd_soc_dai_link *be_dai_link = dpcm->be->dai_link;
+ struct snd_soc_dpcm *dpcm, *rtd_dpcm = NULL;
+
+ /*
+ * The following loop will be called only for playback stream
+ * In this platform, there is only one playback device on every SSP
+ */
+ for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_PLAYBACK, dpcm) {
+ rtd_dpcm = dpcm;
+ break;
+ }
+
+ /*
+ * This following loop will be called only for capture stream
+ * In this platform, there is only one capture device on every SSP
+ */
+ for_each_dpcm_fe(rtd, SNDRV_PCM_STREAM_CAPTURE, dpcm) {
+ rtd_dpcm = dpcm;
+ break;
+ }
+
+ if (!rtd_dpcm)
+ return -EINVAL;
+
+ /*
+ * The above 2 loops are mutually exclusive based on the stream direction,
+ * thus rtd_dpcm variable will never be overwritten
+ */
/*
* The ADSP will convert the FE rate to 48k, stereo, 24 bit
*/
- if (!strcmp(fe_dai_link->name, "Kbl Audio Port") ||
- !strcmp(fe_dai_link->name, "Kbl Audio Headset Playback") ||
- !strcmp(fe_dai_link->name, "Kbl Audio Capture Port")) {
+ if (!strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Port") ||
+ !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Headset Playback") ||
+ !strcmp(rtd_dpcm->fe->dai_link->name, "Kbl Audio Capture Port")) {
rate->min = rate->max = 48000;
chan->min = chan->max = 2;
snd_mask_none(fmt);
* The speaker on the SSP0 supports S16_LE and not S24_LE.
* thus changing the mask here
*/
- if (!strcmp(be_dai_link->name, "SSP0-Codec"))
+ if (!strcmp(rtd_dpcm->be->dai_link->name, "SSP0-Codec"))
snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
return 0;
switch (level) {
case SND_SOC_BIAS_PREPARE:
if (dapm->bias_level == SND_SOC_BIAS_ON) {
+ if (!__clk_is_enabled(priv->mclk))
+ return 0;
dev_dbg(card->dev, "Disable mclk");
clk_disable_unprepare(priv->mclk);
} else {
reg, (reg & CATPT_ISD_DCPWM),
500, 10000);
if (ret) {
- dev_err(cdev->dev, "await WAITI timeout\n");
- mutex_unlock(&cdev->clk_mutex);
- return ret;
+ dev_warn(cdev->dev, "await WAITI timeout\n");
+ /* no signal - only high clock selection allowed */
+ if (lp) {
+ mutex_unlock(&cdev->clk_mutex);
+ return 0;
+ }
}
}
if (ret)
return CATPT_IPC_ERROR(ret);
- ret = catpt_dsp_update_lpclock(cdev);
- if (ret)
- return ret;
-
ret = catpt_dai_apply_usettings(dai, stream);
if (ret)
return ret;
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
resume_stream:
+ catpt_dsp_update_lpclock(cdev);
ret = catpt_ipc_resume_stream(cdev, stream->info.stream_hw_id);
if (ret)
return CATPT_IPC_ERROR(ret);
case SNDRV_PCM_TRIGGER_STOP:
stream->prepared = false;
- catpt_dsp_update_lpclock(cdev);
fallthrough;
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
ret = catpt_ipc_pause_stream(cdev, stream->info.stream_hw_id);
+ catpt_dsp_update_lpclock(cdev);
if (ret)
return CATPT_IPC_ERROR(ret);
break;
dsppos = bytes_to_frames(r, pos->stream_position);
+ if (!stream->prepared)
+ goto exit;
/* only offload is set_write_pos driven */
if (stream->template->type != CATPT_STRM_TYPE_RENDER)
goto exit;
break;
}
+ /* see if this is a new configuration */
+ if (!memcmp(&cdev->devfmt[devfmt.iface], &devfmt, sizeof(devfmt)))
+ return 0;
+
+ pm_runtime_get_sync(cdev->dev);
+
ret = catpt_ipc_set_device_format(cdev, &devfmt);
+
+ pm_runtime_mark_last_busy(cdev->dev);
+ pm_runtime_put_autosuspend(cdev->dev);
+
if (ret)
return CATPT_IPC_ERROR(ret);
kmb_i2s->xfer_resolution = 0x02;
break;
case SNDRV_PCM_FORMAT_S24_LE:
- config->data_width = 24;
- kmb_i2s->ccr = 0x08;
- kmb_i2s->xfer_resolution = 0x04;
+ config->data_width = 32;
+ kmb_i2s->ccr = 0x14;
+ kmb_i2s->xfer_resolution = 0x05;
break;
case SNDRV_PCM_FORMAT_S32_LE:
config->data_width = 32;
},
};
+static const struct snd_kcontrol_new mt8183_da7219_rt1015_snd_controls[] = {
+ SOC_DAPM_PIN_SWITCH("Left Spk"),
+ SOC_DAPM_PIN_SWITCH("Right Spk"),
+};
+
+static const
+struct snd_soc_dapm_widget mt8183_da7219_rt1015_dapm_widgets[] = {
+ SND_SOC_DAPM_SPK("Left Spk", NULL),
+ SND_SOC_DAPM_SPK("Right Spk", NULL),
+ SND_SOC_DAPM_PINCTRL("TDM_OUT_PINCTRL",
+ "aud_tdm_out_on", "aud_tdm_out_off"),
+};
+
+static const struct snd_soc_dapm_route mt8183_da7219_rt1015_dapm_routes[] = {
+ {"Left Spk", NULL, "Left SPO"},
+ {"Right Spk", NULL, "Right SPO"},
+ {"I2S Playback", NULL, "TDM_OUT_PINCTRL"},
+};
+
static struct snd_soc_card mt8183_da7219_rt1015_card = {
.name = "mt8183_da7219_rt1015",
.owner = THIS_MODULE,
- .controls = mt8183_da7219_max98357_snd_controls,
- .num_controls = ARRAY_SIZE(mt8183_da7219_max98357_snd_controls),
- .dapm_widgets = mt8183_da7219_max98357_dapm_widgets,
- .num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_max98357_dapm_widgets),
- .dapm_routes = mt8183_da7219_max98357_dapm_routes,
- .num_dapm_routes = ARRAY_SIZE(mt8183_da7219_max98357_dapm_routes),
+ .controls = mt8183_da7219_rt1015_snd_controls,
+ .num_controls = ARRAY_SIZE(mt8183_da7219_rt1015_snd_controls),
+ .dapm_widgets = mt8183_da7219_rt1015_dapm_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_widgets),
+ .dapm_routes = mt8183_da7219_rt1015_dapm_routes,
+ .num_dapm_routes = ARRAY_SIZE(mt8183_da7219_rt1015_dapm_routes),
.dai_link = mt8183_da7219_dai_links,
.num_links = ARRAY_SIZE(mt8183_da7219_dai_links),
.aux_dev = &mt8183_da7219_max98357_headset_dev,
dev_err(dai->dev, "error in enabling mi2s osr clk: %d\n", ret);
return ret;
}
+ ret = clk_prepare(drvdata->mi2s_bit_clk[dai->driver->id]);
+ if (ret) {
+ dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
+ clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]);
+ return ret;
+ }
return 0;
}
{
struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai);
- clk_disable_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]);
-
clk_disable_unprepare(drvdata->mi2s_osr_clk[dai->driver->id]);
+ clk_unprepare(drvdata->mi2s_bit_clk[dai->driver->id]);
}
static int lpass_cpu_daiops_hw_params(struct snd_pcm_substream *substream,
return 0;
}
-static int lpass_cpu_daiops_prepare(struct snd_pcm_substream *substream,
- struct snd_soc_dai *dai)
-{
- struct lpass_data *drvdata = snd_soc_dai_get_drvdata(dai);
- struct lpaif_i2sctl *i2sctl = drvdata->i2sctl;
- unsigned int id = dai->driver->id;
- int ret;
-
- if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
- ret = regmap_fields_write(i2sctl->spken, id,
- LPAIF_I2SCTL_SPKEN_ENABLE);
- } else {
- ret = regmap_fields_write(i2sctl->micen, id,
- LPAIF_I2SCTL_MICEN_ENABLE);
- }
-
- if (ret)
- dev_err(dai->dev, "error writing to i2sctl enable: %d\n", ret);
-
- return ret;
-}
-
static int lpass_cpu_daiops_trigger(struct snd_pcm_substream *substream,
int cmd, struct snd_soc_dai *dai)
{
struct lpaif_i2sctl *i2sctl = drvdata->i2sctl;
unsigned int id = dai->driver->id;
int ret = -EINVAL;
+ unsigned int val = 0;
+
+ ret = regmap_read(drvdata->lpaif_map,
+ LPAIF_I2SCTL_REG(drvdata->variant, dai->driver->id), &val);
+ if (ret) {
+ dev_err(dai->dev, "error reading from i2sctl reg: %d\n", ret);
+ return ret;
+ }
+ if (val == LPAIF_I2SCTL_RESET_STATE) {
+ dev_err(dai->dev, "error in i2sctl register state\n");
+ return -ENOTRECOVERABLE;
+ }
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
dev_err(dai->dev, "error writing to i2sctl reg: %d\n",
ret);
- ret = clk_prepare_enable(drvdata->mi2s_bit_clk[id]);
- if (ret) {
- dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
- clk_disable_unprepare(drvdata->mi2s_osr_clk[id]);
- return ret;
+ if (drvdata->bit_clk_state[id] == LPAIF_BIT_CLK_DISABLE) {
+ ret = clk_enable(drvdata->mi2s_bit_clk[id]);
+ if (ret) {
+ dev_err(dai->dev, "error in enabling mi2s bit clk: %d\n", ret);
+ clk_disable(drvdata->mi2s_osr_clk[id]);
+ return ret;
+ }
+ drvdata->bit_clk_state[id] = LPAIF_BIT_CLK_ENABLE;
}
break;
if (ret)
dev_err(dai->dev, "error writing to i2sctl reg: %d\n",
ret);
+ if (drvdata->bit_clk_state[id] == LPAIF_BIT_CLK_ENABLE) {
+ clk_disable(drvdata->mi2s_bit_clk[dai->driver->id]);
+ drvdata->bit_clk_state[id] = LPAIF_BIT_CLK_DISABLE;
+ }
break;
}
.startup = lpass_cpu_daiops_startup,
.shutdown = lpass_cpu_daiops_shutdown,
.hw_params = lpass_cpu_daiops_hw_params,
- .prepare = lpass_cpu_daiops_prepare,
.trigger = lpass_cpu_daiops_trigger,
};
EXPORT_SYMBOL_GPL(asoc_qcom_lpass_cpu_dai_ops);
struct lpass_variant *v = drvdata->variant;
int i;
+ for (i = 0; i < v->i2s_ports; ++i)
+ if (reg == LPAIF_I2SCTL_REG(v, i))
+ return true;
for (i = 0; i < v->irq_ports; ++i)
if (reg == LPAIF_IRQSTAT_REG(v, i))
return true;
for (i = 0; i < v->rdma_channels; ++i)
- if (reg == LPAIF_RDMACURR_REG(v, i))
+ if (reg == LPAIF_RDMACURR_REG(v, i) || reg == LPAIF_RDMACTL_REG(v, i))
return true;
for (i = 0; i < v->wrdma_channels; ++i)
- if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start))
+ if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start) ||
+ reg == LPAIF_WRDMACTL_REG(v, i + v->wrdma_channel_start))
return true;
return false;
PTR_ERR(drvdata->mi2s_bit_clk[dai_id]));
return PTR_ERR(drvdata->mi2s_bit_clk[dai_id]);
}
+ drvdata->bit_clk_state[dai_id] = LPAIF_BIT_CLK_DISABLE;
}
/* Allocation for i2sctl regmap fields */
#define LPAIF_I2SCTL_BITWIDTH_24 1
#define LPAIF_I2SCTL_BITWIDTH_32 2
+#define LPAIF_BIT_CLK_DISABLE 0
+#define LPAIF_BIT_CLK_ENABLE 1
+
+#define LPAIF_I2SCTL_RESET_STATE 0x003C0004
+#define LPAIF_DMACTL_RESET_STATE 0x00200000
+
+
/* LPAIF IRQ */
#define LPAIF_IRQ_REG_ADDR(v, addr, port) \
(v->irq_reg_base + (addr) + v->irq_reg_stride * (port))
struct regmap *map;
unsigned int dai_id = cpu_dai->driver->id;
+ component->id = dai_id;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
else
dma_ch = 0;
- if (dma_ch < 0)
+ if (dma_ch < 0) {
+ kfree(data);
return dma_ch;
+ }
if (cpu_dai->driver->id == LPASS_DP_RX) {
map = drvdata->hdmiif_map;
ret = snd_pcm_hw_constraint_integer(runtime,
SNDRV_PCM_HW_PARAM_PERIODS);
if (ret < 0) {
+ kfree(data);
dev_err(soc_runtime->dev, "setting constraints failed: %d\n",
ret);
return -EINVAL;
unsigned int reg_irqclr = 0, val_irqclr = 0;
unsigned int reg_irqen = 0, val_irqen = 0, val_mask = 0;
unsigned int dai_id = cpu_dai->driver->id;
+ unsigned int dma_ctrl_reg = 0;
ch = pcm_data->dma_ch;
if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
id = pcm_data->dma_ch;
- if (dai_id == LPASS_DP_RX)
+ if (dai_id == LPASS_DP_RX) {
dmactl = drvdata->hdmi_rd_dmactl;
- else
+ map = drvdata->hdmiif_map;
+ } else {
dmactl = drvdata->rd_dmactl;
+ map = drvdata->lpaif_map;
+ }
} else {
dmactl = drvdata->wr_dmactl;
id = pcm_data->dma_ch - v->wrdma_channel_start;
+ map = drvdata->lpaif_map;
+ }
+ ret = regmap_read(map, LPAIF_DMACTL_REG(v, ch, dir, dai_id), &dma_ctrl_reg);
+ if (ret) {
+ dev_err(soc_runtime->dev, "error reading from rdmactl reg: %d\n", ret);
+ return ret;
}
+ if (dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE ||
+ dma_ctrl_reg == LPAIF_DMACTL_RESET_STATE + 1) {
+ dev_err(soc_runtime->dev, "error in rdmactl register state\n");
+ return -ENOTRECOVERABLE;
+ }
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
case SNDRV_PCM_TRIGGER_RESUME:
.micmode = REG_FIELD_ID(0x1000, 4, 8, 3, 0x1000),
.micmono = REG_FIELD_ID(0x1000, 3, 3, 3, 0x1000),
.wssrc = REG_FIELD_ID(0x1000, 2, 2, 3, 0x1000),
- .bitwidth = REG_FIELD_ID(0x1000, 0, 0, 3, 0x1000),
+ .bitwidth = REG_FIELD_ID(0x1000, 0, 1, 3, 0x1000),
.rdma_dyncclk = REG_FIELD_ID(0xC000, 21, 21, 5, 0x1000),
.rdma_bursten = REG_FIELD_ID(0xC000, 20, 20, 5, 0x1000),
unsigned int mi2s_playback_sd_mode[LPASS_MAX_MI2S_PORTS];
unsigned int mi2s_capture_sd_mode[LPASS_MAX_MI2S_PORTS];
int hdmi_port_enable;
+ int bit_clk_state[LPASS_MAX_MI2S_PORTS];
/* low-power audio interface (LPAIF) registers */
void __iomem *lpaif;
#include "qdsp6/q6afe.h"
#include "../codecs/rt5663.h"
+#define DRIVER_NAME "sdm845"
#define DEFAULT_SAMPLE_RATE_48K 48000
#define DEFAULT_MCLK_RATE 24576000
#define TDM_BCLK_RATE 6144000
if (!data)
return -ENOMEM;
+ card->driver_name = DRIVER_NAME;
card->dapm_widgets = sdm845_snd_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sdm845_snd_widgets);
card->dev = dev;
}
/**
- * snd_soc_unregister_dai - Unregister DAIs from the ASoC core
+ * snd_soc_unregister_dais - Unregister DAIs from the ASoC core
*
* @component: The component for which the DAIs should be unregistered
*/
}
/**
- * snd_soc_dapm_get_connected_widgets - query audio path and it's widgets.
+ * snd_soc_dapm_dai_get_connected_widgets - query audio path and it's widgets.
* @dai: the soc DAI.
* @stream: stream direction.
* @list: list of active widgets for this stream.
case SOF_IPC_EXT_CC_INFO:
ret = get_cc_info(sdev, ext_hdr);
break;
+ case SOF_IPC_EXT_UNUSED:
+ case SOF_IPC_EXT_PROBE_INFO:
+ case SOF_IPC_EXT_USER_ABI_INFO:
+ /* They are supported but we don't do anything here */
+ break;
default:
dev_warn(sdev->dev, "warning: unknown ext header type %d size 0x%x\n",
ext_hdr->type, ext_hdr->hdr.size);
DEVICE_NAME(0x046d, 0x0990, "Logitech, Inc.", "QuickCam Pro 9000"),
+ /* ASUS ROG Strix */
+ PROFILE_NAME(0x0b05, 0x1917,
+ "Realtek", "ALC1220-VB-DT", "Realtek-ALC1220-VB-Desktop"),
+
/* Dell WD15 Dock */
PROFILE_NAME(0x0bda, 0x4014, "Dell", "WD15 Dock", "Dell-WD15-Dock"),
/* Dell WD19 Dock */
},
{ /* ASUS ROG Strix */
.id = USB_ID(0x0b05, 0x1917),
- .map = asus_rog_map,
+ .map = trx40_mobo_map,
+ .connector_map = trx40_mobo_connector_map,
},
{ /* MSI TRX40 Creator */
.id = USB_ID(0x0db0, 0x0d64),
static int snd_us16x08_meter_info(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_info *uinfo)
{
- uinfo->count = 1;
+ uinfo->count = 34;
uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
uinfo->value.integer.max = 0x7FFF;
uinfo->value.integer.min = 0;
switch (subs->stream->chip->usb_id) {
case USB_ID(0x0763, 0x2030): /* M-Audio Fast Track C400 */
case USB_ID(0x0763, 0x2031): /* M-Audio Fast Track C600 */
+ case USB_ID(0x22f0, 0x0006): /* Allen&Heath Qu-16 */
ep = 0x81;
ifnum = 3;
goto add_sync_ep_from_ifnum;
ifnum = 2;
goto add_sync_ep_from_ifnum;
case USB_ID(0x2466, 0x8003): /* Fractal Audio Axe-Fx II */
+ case USB_ID(0x0499, 0x172a): /* Yamaha MODX */
ep = 0x86;
ifnum = 2;
goto add_sync_ep_from_ifnum;
ep = 0x81;
ifnum = 2;
goto add_sync_ep_from_ifnum;
+ case USB_ID(0x1686, 0xf029): /* Zoom UAC-2 */
+ ep = 0x82;
+ ifnum = 2;
+ goto add_sync_ep_from_ifnum;
case USB_ID(0x1397, 0x0001): /* Behringer UFX1604 */
case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */
ep = 0x81;
&& (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
msleep(20);
- /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX
- * needs a tiny delay here, otherwise requests like get/set
- * frequency return as failed despite actually succeeding.
+ /* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950),
+ * Jabra 550a, Kingston HyperX needs a tiny delay here,
+ * otherwise requests like get/set frequency return
+ * as failed despite actually succeeding.
*/
if ((chip->usb_id == USB_ID(0x1686, 0x00dd) ||
- chip->usb_id == USB_ID(0x046d, 0x0a46) ||
- chip->usb_id == USB_ID(0x046d, 0x0a56) ||
+ USB_ID_VENDOR(chip->usb_id) == 0x046d || /* Logitech */
chip->usb_id == USB_ID(0x0b0e, 0x0349) ||
chip->usb_id == USB_ID(0x0951, 0x16ad)) &&
(requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
case 0x278b: /* Rotel? */
case 0x292b: /* Gustard/Ess based devices */
case 0x2ab6: /* T+A devices */
+ case 0x3353: /* Khadas devices */
case 0x3842: /* EVGA */
case 0xc502: /* HiBy devices */
if (fp->dsd_raw)
struct kvm_arch_memory_slot {
};
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+ __u16 base_event;
+ __u16 nevents;
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+ __u8 action;
+ __u8 pad[3];
+};
+
/* for KVM_GET/SET_VCPU_EVENTS */
struct kvm_vcpu_events {
struct {
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+
+/*
+ * Only two states can be presented by the host kernel:
+ * - NOT_REQUIRED: the guest doesn't need to do anything
+ * - NOT_AVAIL: the guest isn't mitigated (it can still use SSBS if available)
+ *
+ * All the other values are deprecated. The host still accepts all
+ * values (they are ABI), but will narrow them to the above two.
+ */
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
#define KVM_ARM_VCPU_PMU_V3_IRQ 0
#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_PMU_V3_FILTER 2
#define KVM_ARM_VCPU_TIMER_CTRL 1
#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
{ 0x13, "SIGP conditional emergency signal" }, \
{ 0x15, "SIGP sense running" }, \
{ 0x16, "SIGP set multithreading"}, \
- { 0x17, "SIGP store additional status ait address"}
+ { 0x17, "SIGP store additional status at address"}
#define icpt_prog_codes \
{ 0x0001, "Prog Operation" }, \
#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
-/* free ( 3*32+17) */
+#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */
#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */
+#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD 0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+ DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+/**
+ * for_each_insn_prefix() -- Iterate prefixes in the instruction
+ * @insn: Pointer to struct insn.
+ * @idx: Index storage.
+ * @prefix: Prefix byte.
+ *
+ * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
+ * and the index is stored in @idx (note that this @idx is just for a cursor,
+ * do not change it.)
+ * Since prefixes.nbytes can be bigger than 4 if some prefixes
+ * are repeated, it cannot be used for looping over the prefixes.
+ */
+#define for_each_insn_prefix(insn, idx, prefix) \
+ for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+
#define POP_SS_OPCODE 0x1f
#define MOV_SREG_OPCODE 0x8e
#define MSR_IA32_LASTINTFROMIP 0x000001dd
#define MSR_IA32_LASTINTTOIP 0x000001de
+#define MSR_IA32_PASID 0x00000d93
+#define MSR_IA32_PASID_VALID BIT_ULL(31)
+
/* DEBUGCTLMSR bits (others vary by model): */
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
#define DEBUGCTLMSR_BTF_SHIFT 1
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_ICIBSEXTDCTL 0xc001103c
#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
+#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c
#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390
+#define MSR_PERF_METRICS 0x00000329
+
/* PERF_GLOBAL_OVF_CTL bits */
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55
#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT)
#endif
#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT
+#ifdef CONFIG_PARAVIRT_XXL
/* Paravirtualized systems may not have PSE or PGE available */
#define NEED_PSE 0
#define NEED_PGE 0
__u32 indices[0];
};
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+ __u32 flags;
+ __u32 nmsrs; /* number of msrs in bitmap */
+ __u32 base; /* MSR index the bitmap starts at */
+ __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+ __u32 flags;
+ struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
struct kvm_cpuid_entry {
__u32 function;
#define SVM_EXIT_WRITE_DR6 0x036
#define SVM_EXIT_WRITE_DR7 0x037
#define SVM_EXIT_EXCP_BASE 0x040
+#define SVM_EXIT_LAST_EXCP 0x05f
#define SVM_EXIT_INTR 0x060
#define SVM_EXIT_NMI 0x061
#define SVM_EXIT_SMI 0x062
#define SVM_EXIT_MWAIT_COND 0x08c
#define SVM_EXIT_XSETBV 0x08d
#define SVM_EXIT_RDPRU 0x08e
+#define SVM_EXIT_INVPCID 0x0a2
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
#define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402
+/* SEV-ES software-defined VMGEXIT events */
+#define SVM_VMGEXIT_MMIO_READ 0x80000001
+#define SVM_VMGEXIT_MMIO_WRITE 0x80000002
+#define SVM_VMGEXIT_NMI_COMPLETE 0x80000003
+#define SVM_VMGEXIT_AP_HLT_LOOP 0x80000004
+#define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005
+#define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0
+#define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1
+#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
+
#define SVM_EXIT_ERR -1
#define SVM_EXIT_REASONS \
{ SVM_EXIT_MONITOR, "monitor" }, \
{ SVM_EXIT_MWAIT, "mwait" }, \
{ SVM_EXIT_XSETBV, "xsetbv" }, \
+ { SVM_EXIT_INVPCID, "invpcid" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \
* to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
*/
-.weak memcpy
-
/*
* memcpy - Copy a memory block.
*
* rax original destination
*/
SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
* memcpy_erms() - enhanced fast string memcpy. This is faster and
* simpler than memcpy. Use memcpy_erms when possible.
*/
-SYM_FUNC_START(memcpy_erms)
+SYM_FUNC_START_LOCAL(memcpy_erms)
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
ret
SYM_FUNC_END(memcpy_erms)
-SYM_FUNC_START(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
movq %rdi, %rax
cmpq $0x20, %rdx
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
-
-.weak memset
+#include <asm/export.h>
/*
* ISO C memset - set a memory block to a byte value. This function uses fast
*
* rax original destination
*/
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
SYM_FUNC_START(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
ret
SYM_FUNC_END(__memset)
SYM_FUNC_END_ALIAS(memset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
/*
* ISO C memset - set a memory block to a byte value. This function uses
*
* rax original destination
*/
-SYM_FUNC_START(memset_erms)
+SYM_FUNC_START_LOCAL(memset_erms)
movq %rdi,%r9
movb %sil,%al
movq %rdx,%rcx
ret
SYM_FUNC_END(memset_erms)
-SYM_FUNC_START(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
movq %rdi,%r10
/* expand byte value */
#include <unistd.h>
#include <string.h>
#include <errno.h>
+#include <endian.h>
#include <linux/kernel.h>
#include <linux/bootconfig.h>
return ret;
}
+static int pr_errno(const char *msg, int err)
+{
+ pr_err("%s: %d\n", msg, err);
+ return err;
+}
+
static int load_xbc_from_initrd(int fd, char **buf)
{
struct stat stat;
if (stat.st_size < 8 + BOOTCONFIG_MAGIC_LEN)
return 0;
- if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) {
- pr_err("Failed to lseek: %d\n", -errno);
- return -errno;
- }
+ if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0)
+ return pr_errno("Failed to lseek for magic", -errno);
+
if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0)
- return -errno;
+ return pr_errno("Failed to read", -errno);
+
/* Check the bootconfig magic bytes */
if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
return 0;
- if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) {
- pr_err("Failed to lseek: %d\n", -errno);
- return -errno;
- }
+ if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0)
+ return pr_errno("Failed to lseek for size", -errno);
if (read(fd, &size, sizeof(u32)) < 0)
- return -errno;
+ return pr_errno("Failed to read size", -errno);
+ size = le32toh(size);
if (read(fd, &csum, sizeof(u32)) < 0)
- return -errno;
+ return pr_errno("Failed to read checksum", -errno);
+ csum = le32toh(csum);
/* Wrong size error */
if (stat.st_size < size + 8 + BOOTCONFIG_MAGIC_LEN) {
}
if (lseek(fd, stat.st_size - (size + 8 + BOOTCONFIG_MAGIC_LEN),
- SEEK_SET) < 0) {
- pr_err("Failed to lseek: %d\n", -errno);
- return -errno;
- }
+ SEEK_SET) < 0)
+ return pr_errno("Failed to lseek", -errno);
ret = load_xbc_fd(fd, buf, size);
if (ret < 0)
ret = stat(path, &st);
if (ret < 0) {
- pr_err("Failed to stat %s: %d\n", path, -errno);
- return -errno;
+ ret = -errno;
+ pr_err("Failed to stat %s: %d\n", path, ret);
+ return ret;
}
fd = open(path, O_RDONLY);
if (fd < 0) {
- pr_err("Failed to open initrd %s: %d\n", path, fd);
- return -errno;
+ ret = -errno;
+ pr_err("Failed to open initrd %s: %d\n", path, ret);
+ return ret;
}
ret = load_xbc_from_initrd(fd, &buf);
fd = open(path, O_RDWR);
if (fd < 0) {
- pr_err("Failed to open initrd %s: %d\n", path, fd);
- return -errno;
+ ret = -errno;
+ pr_err("Failed to open initrd %s: %d\n", path, ret);
+ return ret;
}
size = load_xbc_from_initrd(fd, &buf);
static int apply_xbc(const char *path, const char *xbc_path)
{
+ char *buf, *data, *p;
+ size_t total_size;
+ struct stat stat;
+ const char *msg;
u32 size, csum;
- char *buf, *data;
+ int pos, pad;
int ret, fd;
- const char *msg;
- int pos;
ret = load_xbc_file(xbc_path, &buf);
if (ret < 0) {
size = strlen(buf) + 1;
csum = checksum((unsigned char *)buf, size);
- /* Prepare xbc_path data */
- data = malloc(size + 8);
+ /* Backup the bootconfig data */
+ data = calloc(size + BOOTCONFIG_ALIGN +
+ sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1);
if (!data)
return -ENOMEM;
- strcpy(data, buf);
- *(u32 *)(data + size) = size;
- *(u32 *)(data + size + 4) = csum;
+ memcpy(data, buf, size);
/* Check the data format */
ret = xbc_init(buf, &msg, &pos);
/* Apply new one */
fd = open(path, O_RDWR | O_APPEND);
if (fd < 0) {
- pr_err("Failed to open %s: %d\n", path, fd);
+ ret = -errno;
+ pr_err("Failed to open %s: %d\n", path, ret);
free(data);
- return fd;
+ return ret;
}
/* TODO: Ensure the @path is initramfs/initrd image */
- ret = write(fd, data, size + 8);
- if (ret < 0) {
- pr_err("Failed to apply a boot config: %d\n", ret);
+ if (fstat(fd, &stat) < 0) {
+ pr_err("Failed to get the size of %s\n", path);
goto out;
}
- /* Write a magic word of the bootconfig */
- ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
- if (ret < 0) {
- pr_err("Failed to apply a boot config magic: %d\n", ret);
- goto out;
- }
- ret = 0;
+
+ /* To align up the total size to BOOTCONFIG_ALIGN, get padding size */
+ total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN;
+ pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size;
+ size += pad;
+
+ /* Add a footer */
+ p = data + size;
+ *(u32 *)p = htole32(size);
+ p += sizeof(u32);
+
+ *(u32 *)p = htole32(csum);
+ p += sizeof(u32);
+
+ memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN);
+ p += BOOTCONFIG_MAGIC_LEN;
+
+ total_size = p - data;
+
+ ret = write(fd, data, total_size);
+ if (ret < total_size) {
+ if (ret < 0)
+ ret = -errno;
+ pr_err("Failed to apply a boot config: %d\n", ret);
+ if (ret >= 0)
+ goto out_rollback;
+ } else
+ ret = 0;
+
out:
close(fd);
free(data);
return ret;
+
+out_rollback:
+ /* Map the partial write to -ENOSPC */
+ if (ret >= 0)
+ ret = -ENOSPC;
+ if (ftruncate(fd, stat.st_size) < 0) {
+ ret = -errno;
+ pr_err("Failed to rollback the write error: %d\n", ret);
+ pr_err("The initrd %s may be corrupted. Recommend to rebuild.\n", path);
+ }
+ goto out;
}
static int usage(void)
TESTDIR=.
fi
BOOTCONF=${TESTDIR}/bootconfig
+ALIGN=4
INITRD=`mktemp ${TESTDIR}/initrd-XXXX`
TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf`
xpass $BOOTCONF $INITRD
echo "File size check"
-xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9 + 12)
+total_size=$(expr $bconf_size + $initrd_size + 9 + 12 + $ALIGN - 1 )
+total_size=$(expr $total_size / $ALIGN)
+total_size=$(expr $total_size \* $ALIGN)
+xpass test $new_size -eq $total_size
echo "Apply command repeat test"
xpass $BOOTCONF -a $TEMPCONF $INITRD
obj_node = calloc(1, sizeof(*obj_node));
if (!obj_node) {
p_err("failed to allocate memory: %s", strerror(errno));
+ err = -ENOMEM;
goto err_free;
}
else
p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'",
capability_msg(bpf_caps, 0),
+#ifdef CAP_BPF
capability_msg(bpf_caps, 1),
capability_msg(bpf_caps, 2),
- capability_msg(bpf_caps, 3));
+ capability_msg(bpf_caps, 3)
+#else
+ "", "", "", "", "", ""
+#endif /* CAP_BPF */
+ );
goto exit_free;
}
ifindex = net_parse_dev(&argc, &argv);
if (ifindex < 1) {
- close(progfd);
- return -EINVAL;
+ err = -EINVAL;
+ goto cleanup;
}
if (argc) {
overwrite = true;
} else {
p_err("expected 'overwrite', got: '%s'?", *argv);
- close(progfd);
- return -EINVAL;
+ err = -EINVAL;
+ goto cleanup;
}
}
if (is_prefix("xdp", attach_type_strings[attach_type]))
err = do_attach_detach_xdp(progfd, attach_type, ifindex,
overwrite);
-
- if (err < 0) {
+ if (err) {
p_err("interface %s attach failed: %s",
attach_type_strings[attach_type], strerror(-err));
- return err;
+ goto cleanup;
}
if (json_output)
jsonw_null(json_wtr);
-
- return 0;
+cleanup:
+ close(progfd);
+ return err;
}
static int do_detach(int argc, char **argv)
}
if (*attach_type == BPF_FLOW_DISSECTOR) {
- *mapfd = -1;
+ *mapfd = 0;
return 0;
}
static inline void
fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
{
- struct bpf_perf_event_value *before, diff, *accum;
+ struct bpf_perf_event_value *before, diff;
before = bpf_map_lookup_elem(&fentry_readings, &id);
/* only account samples with a valid fentry_reading */
{
struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
u32 cpu = bpf_get_smp_processor_id();
- u32 i, one = 1, zero = 0;
+ u32 i, zero = 0;
int err;
u64 *count;
main_test_libperl();
main_test_hello();
main_test_libelf();
- main_test_libelf_mmap();
main_test_get_current_dir_name();
main_test_gettid();
main_test_glibc();
#define __pure __attribute__((pure))
#endif
#define noinline __attribute__((noinline))
-#ifdef __has_attribute
-#if __has_attribute(disable_tail_calls)
-#define __no_tail_call __attribute__((disable_tail_calls))
-#endif
-#endif
-#ifndef __no_tail_call
-#if GCC_VERSION > 40201
-#define __no_tail_call __attribute__((optimize("no-optimize-sibling-calls")))
-#else
-#define __no_tail_call
-#endif
-#endif
#ifndef __packed
#define __packed __attribute__((packed))
#endif
#ifndef noinline
#define noinline
#endif
-#ifndef __no_tail_call
-#define __no_tail_call
-#endif
/* Are two types/vars the same type (ignoring qualifiers)? */
#ifndef __same_type
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_faccessat2 439
__SYSCALL(__NR_faccessat2, sys_faccessat2)
+#define __NR_process_madvise 440
+__SYSCALL(__NR_process_madvise, sys_process_madvise)
#undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
/*
* 32 bit systems traditionally used different
*/
#define I915_PARAM_PERF_REVISION 54
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
/* Must be kept compact -- no holes and well documented */
typedef struct drm_i915_getparam {
__u32 flags;
};
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+ struct i915_user_extension base;
+
+ /**
+ * Number of element in the handles_ptr & value_ptr arrays.
+ */
+ __u64 fence_count;
+
+ /**
+ * Pointer to an array of struct drm_i915_gem_exec_fence of length
+ * fence_count.
+ */
+ __u64 handles_ptr;
+
+ /**
+ * Pointer to an array of u64 values of length fence_count. Values
+ * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+ * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+ */
+ __u64 values_ptr;
+};
+
struct drm_i915_gem_execbuffer2 {
/**
* List of gem_exec_object2 structs
__u32 num_cliprects;
/**
* This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
- * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a
- * struct drm_i915_gem_exec_fence *fences.
+ * & I915_EXEC_USE_EXTENSIONS are not set.
+ *
+ * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+ * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+ * of the array.
+ *
+ * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+ * single struct i915_user_extension and num_cliprects is 0.
*/
__u64 cliprects_ptr;
#define I915_EXEC_RING_MASK (0x3f)
*/
#define I915_EXEC_FENCE_SUBMIT (1 << 20)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS (1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
__u8 flags;
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
-#define fscrypt_policy fscrypt_policy_v1
/*
* Process-subscribed "logon" key description prefix and payload format.
__u32 __out_reserved[13];
};
-#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1)
#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg)
/* old names; don't add anything new here! */
#ifndef __KERNEL__
+#define fscrypt_policy fscrypt_policy_v1
#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE
#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4
#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8
#define KVM_EXIT_IOAPIC_EOI 26
#define KVM_EXIT_HYPERV 27
#define KVM_EXIT_ARM_NISV 28
+#define KVM_EXIT_X86_RDMSR 29
+#define KVM_EXIT_X86_WRMSR 30
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
__u64 esr_iss;
__u64 fault_ipa;
} arm_nisv;
+ /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+ struct {
+ __u8 error; /* user -> kernel */
+ __u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+ __u32 reason; /* kernel -> user */
+ __u32 index; /* kernel -> user */
+ __u64 data; /* kernel <-> user */
+ } msr;
/* Fix the size of the union. */
char padding[256];
};
#define KVM_CAP_SMALLER_MAXPHYADDR 185
#define KVM_CAP_S390_DIAG318 186
#define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
+#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#ifdef KVM_CAP_IRQ_ROUTING
/* Available with KVM_CAP_S390_PROTECTED */
#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB
#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
+#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */
#define MS_NOATIME 1024 /* Do not update access times. */
#define MS_NODIRATIME 2048 /* Do not update directory access times */
#define MS_BIND 4096
#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */
/* 1 free */
-#define PERF_MEM_SNOOPX_SHIFT 38
+#define PERF_MEM_SNOOPX_SHIFT 38
/* locked instruction */
#define PERF_MEM_LOCK_NA 0x01 /* not available */
#define PR_SET_TAGGED_ADDR_CTRL 55
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
+/* MTE tag check fault modes */
+# define PR_MTE_TCF_SHIFT 1
+# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT)
+# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT)
+/* MTE tag inclusion mask */
+# define PR_MTE_TAG_SHIFT 3
+# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
/* Control reclaim behavior when allocating memory */
#define PR_SET_IO_FLUSHER 57
/* Set event fd for config interrupt*/
#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
+
+/* Get the valid iova range */
+#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
+ struct vhost_vdpa_iova_range)
#endif
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
sort -u | wc -l)
VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+ sed 's/\[.*\]//' | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \
sort -u > $(OUTPUT)libbpf_global_syms.tmp; \
readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
+ sed 's/\[.*\]//' | \
awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \
grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \
sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \
static inline size_t hash_bits(size_t h, int bits)
{
/* shuffle bits and return requested number of upper bits */
+ if (bits == 0)
+ return 0;
+
#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
/* LP64 case */
return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
* @key: key to iterate entries for
*/
#define hashmap__for_each_key_entry(map, cur, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur; \
cur = cur->next) \
if (map->equal_fn(cur->key, (_key), map->ctx))
#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- cur = map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur && ({ tmp = cur->next; true; }); \
cur = tmp) \
if (map->equal_fn(cur->key, (_key), map->ctx))
const char *name, size_t sec_idx, const char *sec_name,
size_t sec_off, void *insn_data, size_t insn_data_sz)
{
- int i;
-
if (insn_data_sz == 0 || insn_data_sz % BPF_INSN_SZ || sec_off % BPF_INSN_SZ) {
pr_warn("sec '%s': corrupted program '%s', offset %zu, size %zu\n",
sec_name, name, sec_off, insn_data_sz);
goto errout;
memcpy(prog->insns, insn_data, insn_data_sz);
- for (i = 0; i < prog->insns_cnt; i++) {
- if (insn_is_subprog_call(&prog->insns[i])) {
- obj->has_subcalls = true;
- break;
- }
- }
-
return 0;
errout:
pr_warn("sec '%s': failed to allocate memory for prog '%s'\n", sec_name, name);
static bool prog_is_subprog(const struct bpf_object *obj,
const struct bpf_program *prog)
{
- return prog->sec_idx == obj->efile.text_shndx && obj->has_subcalls;
+ /* For legacy reasons, libbpf supports an entry-point BPF programs
+ * without SEC() attribute, i.e., those in the .text section. But if
+ * there are 2 or more such programs in the .text section, they all
+ * must be subprograms called from entry-point BPF programs in
+ * designated SEC()'tions, otherwise there is no way to distinguish
+ * which of those programs should be loaded vs which are a subprogram.
+ * Similarly, if there is a function/program in .text and at least one
+ * other BPF program with custom SEC() attribute, then we just assume
+ * .text programs are subprograms (even if they are not called from
+ * other programs), because libbpf never explicitly supported mixing
+ * SEC()-designated BPF programs and .text entry-point BPF programs.
+ */
+ return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1;
}
struct bpf_program *
void xsk_socket__delete(struct xsk_socket *xsk)
{
size_t desc_sz = sizeof(struct xdp_desc);
- struct xsk_ctx *ctx = xsk->ctx;
struct xdp_mmap_offsets off;
+ struct xsk_umem *umem;
+ struct xsk_ctx *ctx;
int err;
if (!xsk)
return;
+ ctx = xsk->ctx;
+ umem = ctx->umem;
if (ctx->prog_fd != -1) {
xsk_delete_bpf_maps(xsk);
close(ctx->prog_fd);
xsk_put_ctx(ctx);
- ctx->umem->refcount--;
+ umem->refcount--;
/* Do not close an fd that also has an associated umem connected
* to it.
*/
- if (xsk->fd != ctx->umem->fd)
+ if (xsk->fd != umem->fd)
close(xsk->fd);
free(xsk);
}
PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
+440 common process_madvise sys_process_madvise
#
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64. These syscalls have numbers 512-547.
+# Do not add new syscalls to this range. Numbers 548 and above are available
+# for non-x32 use.
#
512 x32 rt_sigaction compat_sys_rt_sigaction
513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn
545 x32 execveat compat_sys_execveat
546 x32 preadv2 compat_sys_preadv64v2
547 x32 pwritev2 compat_sys_pwritev64v2
+# This is the end of the legacy x32 range. Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
memcpy(buf, (void *) sp, stack_size);
+#ifdef MEMORY_SANITIZER
+ /*
+ * Copying the stack may copy msan poison, avoid false positives in the
+ * unwinder by removing the poison here.
+ */
+ __msan_unpoison(buf, stack_size);
+#endif
stack->data = (char *) buf;
stack->size = stack_size;
return 0;
/* Various wrappers to make the kernel .S file build in user-space: */
+// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
#define memcpy MEMCPY /* don't hide glibc's memcpy() */
#define altinstr_replacement text
#define globl p2align 4; .globl
/* SPDX-License-Identifier: GPL-2.0 */
+// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
#define memset MEMSET /* don't hide glibc's memset() */
#define altinstr_replacement text
#define globl p2align 4; .globl
if (compute == COMPUTE_STREAM) {
d->evlist_streams = evlist__create_streams(
d->session->evlist, 5);
- if (!d->evlist_streams)
+ if (!d->evlist_streams) {
+ ret = -ENOMEM;
goto out_delete;
+ }
}
}
dsos__hit_all(session);
/*
* The AUX areas have been removed and replaced with
- * synthesized hardware events, so clear the feature flag and
- * remove the evsel.
+ * synthesized hardware events, so clear the feature flag.
*/
if (inject->itrace_synth_opts.set) {
- struct evsel *evsel;
-
perf_header__clear_feat(&session->header,
HEADER_AUXTRACE);
if (inject->itrace_synth_opts.last_branch ||
inject->itrace_synth_opts.add_last_branch)
perf_header__set_feat(&session->header,
HEADER_BRANCH_STACK);
- evsel = perf_evlist__id2evsel_strict(session->evlist,
- inject->aux_id);
- if (evsel) {
- pr_debug("Deleting %s\n", evsel__name(evsel));
- evlist__remove(session->evlist, evsel);
- evsel__delete(evsel);
- }
}
session->header.data_offset = output_data_offset;
session->header.data_size = inject->bytes_written;
struct lock_seq_stat *seq;
const char *name = evsel__strval(evsel, sample, "name");
u64 tmp = evsel__intval(evsel, sample, "lockdep_addr");
- int flag = evsel__intval(evsel, sample, "flag");
+ int flag = evsel__intval(evsel, sample, "flags");
memcpy(&addr, &tmp, sizeof(void *));
case SEQ_STATE_READ_ACQUIRED:
seq->read_count--;
BUG_ON(seq->read_count < 0);
- if (!seq->read_count) {
+ if (seq->read_count) {
ls->nr_release++;
goto end;
}
err = 0;
if (lists[0]) {
- struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
- "event selector. use 'perf list' to list available events",
- parse_events_option);
+ struct option o = {
+ .value = &trace->evlist,
+ };
err = parse_events_option(&o, lists[0], 0);
}
out:
{
struct trace *trace = opt->value;
- if (!list_empty(&trace->evlist->core.entries))
- return parse_cgroups(opt, str, unset);
-
+ if (!list_empty(&trace->evlist->core.entries)) {
+ struct option o = {
+ .value = &trace->evlist,
+ };
+ return parse_cgroups(&o, str, unset);
+ }
trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
return 0;
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW;SoC",
"MetricName": "DRAM_BW_Use"
},
},
{
"BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
- "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+ "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
"MetricGroup": "Memory_BW;SoC",
"MetricName": "DRAM_BW_Use"
},
return strcmp((const char *) symbol, funcs[idx]);
}
-__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
{
struct perf_sample sample;
unsigned long cnt = 0;
static int global_unwind_retval = -INT_MAX;
-__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
{
/* Any possible value should be 'thread' */
struct thread *thread = *(struct thread **)p1;
return p1 - p2;
}
-__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
{
struct thread *array[2] = {thread, thread};
void *fp = &bsearch;
return global_unwind_retval;
}
-__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
{
return test_dwarf_unwind__krava_3(thread);
}
-__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
{
return test_dwarf_unwind__krava_2(thread);
}
# touch 6512 1 branches:u: ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so)
# touch 6512 1 branches:u: ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so)
perf script -F,-time -i ${perfdata} | \
- egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +"
+ egrep " +$1 +[0-9]+ .* +branches:(.*:)? +"
}
perf_report_branch_samples() {
# `> device_name = 'tmc_etf0'
device_name=$(basename $path)
- if is_device_sink $path $devce_name; then
+ if is_device_sink $path $device_name; then
record_touch_file $device_name $2 &&
perf_script_branch_samples touch &&
struct popup_action actions[MAX_OPTIONS];
int nr_options = 0;
int key = -1;
- char buf[64];
+ char buf[128];
int delay_secs = hbt ? hbt->refresh : 0;
#define HIST_BROWSER_HELP_COMMON \
const u8 *raw = build_id->data;
size_t i;
+ bf[0] = 0x0;
+
for (i = 0; i < build_id->size; ++i) {
sprintf(bid, "%02x", *raw);
++raw;
bool die_is_func_def(Dwarf_Die *dw_die)
{
Dwarf_Attribute attr;
+ Dwarf_Addr addr = 0;
+
+ if (dwarf_tag(dw_die) != DW_TAG_subprogram)
+ return false;
+
+ if (dwarf_attr(dw_die, DW_AT_declaration, &attr))
+ return false;
- return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
- dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+ /*
+ * DW_AT_declaration can be lost from function declaration
+ * by gcc's bug #97060.
+ * So we need to check this subprogram DIE has DW_AT_inline
+ * or an entry address.
+ */
+ if (!dwarf_attr(dw_die, DW_AT_inline, &attr) &&
+ die_entrypc(dw_die, &addr) < 0)
+ return false;
+
+ return true;
}
/**
int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr)
{
Dwarf_Addr base, end;
+ Dwarf_Attribute attr;
if (!addr)
return -EINVAL;
if (dwarf_entrypc(dw_die, addr) == 0)
return 0;
+ /*
+ * Since the dwarf_ranges() will return 0 if there is no
+ * DW_AT_ranges attribute, we should check it first.
+ */
+ if (!dwarf_attr(dw_die, DW_AT_ranges, &attr))
+ return -ENOENT;
+
return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0;
}
/* make sure libbpf doesn't use kernel-only integer typedefs */
#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
/* start with 4 buckets */
#define HASHMAP_MIN_CAP_BITS 2
static inline size_t hash_bits(size_t h, int bits)
{
/* shuffle bits and return requested number of upper bits */
+ if (bits == 0)
+ return 0;
+
#if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
/* LP64 case */
return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
#endif
}
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+ size_t h = 0;
+
+ while (*s) {
+ h = h * 31 + *s;
+ s++;
+ }
+ return h;
+}
+
typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
* @key: key to iterate entries for
*/
#define hashmap__for_each_key_entry(map, cur, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur; \
cur = cur->next) \
if (map->equal_fn(cur->key, (_key), map->ctx))
#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \
- for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
- map->cap_bits); \
- cur = map->buckets ? map->buckets[bkt] : NULL; }); \
+ for (cur = map->buckets \
+ ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+ : NULL; \
cur && ({ tmp = cur->next; true; }); \
cur = tmp) \
if (map->equal_fn(cur->key, (_key), map->ctx))
/* SYM_L_* -- linkage of symbols */
#define SYM_L_GLOBAL(name) .globl name
+#define SYM_L_WEAK(name) .weak name
#define SYM_L_LOCAL(name) /* nothing */
#define ALIGN __ALIGN
SYM_END(name, SYM_T_FUNC)
#endif
+/* SYM_FUNC_START_WEAK -- use for weak functions */
+#ifndef SYM_FUNC_START_WEAK
+#define SYM_FUNC_START_WEAK(name) \
+ SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)
+#endif
+
/*
* SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
* SYM_FUNC_START_WEAK, ...
union perf_event *event,
struct perf_sample *sample __maybe_unused)
{
+ struct symbol *sym;
struct map *map;
map = maps__find(&machine->kmaps, event->ksymbol.addr);
- if (map)
+ if (!map)
+ return 0;
+
+ if (map != machine->vmlinux_map)
maps__remove(&machine->kmaps, map);
+ else {
+ sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+ if (sym)
+ dso__delete_symbol(map->dso, sym);
+ }
return 0;
}
if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
return DWARF_CB_OK;
- if (die_is_func_def(sp_die) &&
- die_match_name(sp_die, lr->function)) {
+ if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) {
lf->fname = dwarf_decl_file(sp_die);
dwarf_decl_line(sp_die, &lr->offset);
pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
static int python_start_script(const char *script, int argc, const char **argv)
{
struct tables *tables = &tables_global;
- PyMODINIT_FUNC (*initfunc)(void);
#if PY_MAJOR_VERSION < 3
const char **command_line;
#else
FILE *fp;
#if PY_MAJOR_VERSION < 3
- initfunc = initperf_trace_context;
command_line = malloc((argc + 1) * sizeof(const char *));
command_line[0] = script;
for (i = 1; i < argc + 1; i++)
command_line[i] = argv[i - 1];
+ PyImport_AppendInittab(name, initperf_trace_context);
#else
- initfunc = PyInit_perf_trace_context;
command_line = malloc((argc + 1) * sizeof(wchar_t *));
command_line[0] = Py_DecodeLocale(script, NULL);
for (i = 1; i < argc + 1; i++)
command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+ PyImport_AppendInittab(name, PyInit_perf_trace_context);
#endif
-
- PyImport_AppendInittab(name, initfunc);
Py_Initialize();
#if PY_MAJOR_VERSION < 3
event->mmap2.maj = bswap_32(event->mmap2.maj);
event->mmap2.min = bswap_32(event->mmap2.min);
event->mmap2.ino = bswap_64(event->mmap2.ino);
+ event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
if (sample_id_all) {
void *data = &event->mmap2.filename;
swap_sample_id_all(event, &event->namespaces.link_info[i]);
}
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+ event->cgroup.id = bswap_64(event->cgroup.id);
+
+ if (sample_id_all) {
+ void *data = &event->cgroup.path;
+
+ data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
+}
+
static u8 revbyte(u8 b)
{
int rev = (b >> 4) | ((b & 0xf) << 4);
[PERF_RECORD_SWITCH] = perf_event__switch_swap,
[PERF_RECORD_SWITCH_CPU_WIDE] = perf_event__switch_swap,
[PERF_RECORD_NAMESPACES] = perf_event__namespaces_swap,
+ [PERF_RECORD_CGROUP] = perf_event__cgroup_swap,
[PERF_RECORD_TEXT_POKE] = perf_event__text_poke_swap,
[PERF_RECORD_HEADER_ATTR] = perf_event__hdr_attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap,
struct evlist *evlist = evsel->evlist;
int i;
- if (!config->aggr_get_id)
- return 0;
-
if (config->aggr_mode == AGGR_NONE)
return id;
- if (config->aggr_mode == AGGR_GLOBAL)
+ if (!config->aggr_get_id)
return 0;
for (i = 0; i < evsel__nr_cpus(evsel); i++) {
}
}
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+ rb_erase_cached(&sym->rb_node, &dso->symbols);
+ symbol__delete(sym);
+ dso__reset_find_symbol_cache(dso);
+}
+
struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
{
if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
void dso__insert_symbol(struct dso *dso,
struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+ struct symbol *sym);
struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
char cgrp_root[PATH_MAX];
size_t mount_len; /* length of mount point in the path */
+ if (!tool || !tool->cgroup_events)
+ return 0;
+
if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) {
pr_debug("cannot find cgroup mount point\n");
return -1;
override CFLAGS += -O2 -Wall -I../../../include
override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
+override CFLAGS += -D_FILE_OFFSET_BITS=64
override CFLAGS += -D_FORTIFY_SOURCE=2
%: %.c
@mkdir -p $(BUILD_OUTPUT)
- $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap
+ $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt
.PHONY : clean
clean :
.SH REFERENCES
Volume 3B: System Programming Guide"
-http://www.intel.com/products/processor/manuals/
+https://www.intel.com/products/processor/manuals/
.SH FILES
.ta
unsigned long long cpuidle_cur_cpu_lpi_us;
unsigned long long cpuidle_cur_sys_lpi_us;
unsigned int gfx_cur_mhz;
+unsigned int gfx_act_mhz;
unsigned int tcc_activation_temp;
unsigned int tcc_activation_temp_override;
double rapl_power_units, rapl_time_units;
unsigned long long pkg_both_core_gfxe_c0;
long long gfx_rc6_ms;
unsigned int gfx_mhz;
+ unsigned int gfx_act_mhz;
unsigned int package_id;
- unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */
- unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */
- unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */
- unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */
- unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
- unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
+ unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */
+ unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */
+ unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */
+ unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */
+ unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
+ unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
unsigned int pkg_temp_c;
unsigned long long counter[MAX_ADDED_COUNTERS];
} *package_even, *package_odd;
#define SYSFS_PERCPU (1 << 1)
};
+/*
+ * The accumulated sum of MSR is defined as a monotonic
+ * increasing MSR, it will be accumulated periodically,
+ * despite its register's bit width.
+ */
+enum {
+ IDX_PKG_ENERGY,
+ IDX_DRAM_ENERGY,
+ IDX_PP0_ENERGY,
+ IDX_PP1_ENERGY,
+ IDX_PKG_PERF,
+ IDX_DRAM_PERF,
+ IDX_COUNT,
+};
+
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr);
+
+struct msr_sum_array {
+ /* get_msr_sum() = sum + (get_msr() - last) */
+ struct {
+ /*The accumulated MSR value is updated by the timer*/
+ unsigned long long sum;
+ /*The MSR footprint recorded in last timer*/
+ unsigned long long last;
+ } entries[IDX_COUNT];
+};
+
+/* The percpu MSR sum array.*/
+struct msr_sum_array *per_cpu_msr_sum;
+
+int idx_to_offset(int idx)
+{
+ int offset;
+
+ switch (idx) {
+ case IDX_PKG_ENERGY:
+ offset = MSR_PKG_ENERGY_STATUS;
+ break;
+ case IDX_DRAM_ENERGY:
+ offset = MSR_DRAM_ENERGY_STATUS;
+ break;
+ case IDX_PP0_ENERGY:
+ offset = MSR_PP0_ENERGY_STATUS;
+ break;
+ case IDX_PP1_ENERGY:
+ offset = MSR_PP1_ENERGY_STATUS;
+ break;
+ case IDX_PKG_PERF:
+ offset = MSR_PKG_PERF_STATUS;
+ break;
+ case IDX_DRAM_PERF:
+ offset = MSR_DRAM_PERF_STATUS;
+ break;
+ default:
+ offset = -1;
+ }
+ return offset;
+}
+
+int offset_to_idx(int offset)
+{
+ int idx;
+
+ switch (offset) {
+ case MSR_PKG_ENERGY_STATUS:
+ idx = IDX_PKG_ENERGY;
+ break;
+ case MSR_DRAM_ENERGY_STATUS:
+ idx = IDX_DRAM_ENERGY;
+ break;
+ case MSR_PP0_ENERGY_STATUS:
+ idx = IDX_PP0_ENERGY;
+ break;
+ case MSR_PP1_ENERGY_STATUS:
+ idx = IDX_PP1_ENERGY;
+ break;
+ case MSR_PKG_PERF_STATUS:
+ idx = IDX_PKG_PERF;
+ break;
+ case MSR_DRAM_PERF_STATUS:
+ idx = IDX_DRAM_PERF;
+ break;
+ default:
+ idx = -1;
+ }
+ return idx;
+}
+
+int idx_valid(int idx)
+{
+ switch (idx) {
+ case IDX_PKG_ENERGY:
+ return do_rapl & RAPL_PKG;
+ case IDX_DRAM_ENERGY:
+ return do_rapl & RAPL_DRAM;
+ case IDX_PP0_ENERGY:
+ return do_rapl & RAPL_CORES_ENERGY_STATUS;
+ case IDX_PP1_ENERGY:
+ return do_rapl & RAPL_GFX;
+ case IDX_PKG_PERF:
+ return do_rapl & RAPL_PKG_PERF_STATUS;
+ case IDX_DRAM_PERF:
+ return do_rapl & RAPL_DRAM_PERF_STATUS;
+ default:
+ return 0;
+ }
+}
struct sys_counters {
unsigned int added_thread_counters;
unsigned int added_core_counters;
{ 0x0, "APIC" },
{ 0x0, "X2APIC" },
{ 0x0, "Die" },
+ { 0x0, "GFXAMHz" },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
#define BIC_APIC (1ULL << 48)
#define BIC_X2APIC (1ULL << 49)
#define BIC_Die (1ULL << 50)
+#define BIC_GFXACTMHz (1ULL << 51)
#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
if (DO_BIC(BIC_GFXMHz))
outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_GFXACTMHz))
+ outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
if (DO_BIC(BIC_Any_c0))
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
- outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
- outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
- outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
- outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram);
- outp += sprintf(outp, "Throttle PKG: %0X\n",
+ outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
+ outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
+ outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
+ outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
+ outp += sprintf(outp, "Throttle PKG: %0llX\n",
p->rapl_pkg_perf_status);
- outp += sprintf(outp, "Throttle RAM: %0X\n",
+ outp += sprintf(outp, "Throttle RAM: %0llX\n",
p->rapl_dram_perf_status);
outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
}
}
- /*
- * If measurement interval exceeds minimum RAPL Joule Counter range,
- * indicate that results are suspect by printing "**" in fraction place.
- */
- if (interval_float < rapl_joule_counter_range)
- fmt8 = "%s%.2f";
- else
- fmt8 = "%6.0f**";
+ fmt8 = "%s%.2f";
if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
if (DO_BIC(BIC_GFXMHz))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz);
+ /* GFXACTMHz */
+ if (DO_BIC(BIC_GFXACTMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+
/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc);
}
#define DELTA_WRAP32(new, old) \
- if (new > old) { \
- old = new - old; \
- } else { \
- old = 0x100000000 + new - old; \
- }
+ old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32);
int
delta_package(struct pkg_data *new, struct pkg_data *old)
old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
old->gfx_mhz = new->gfx_mhz;
+ old->gfx_act_mhz = new->gfx_act_mhz;
- DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
- DELTA_WRAP32(new->energy_cores, old->energy_cores);
- DELTA_WRAP32(new->energy_gfx, old->energy_gfx);
- DELTA_WRAP32(new->energy_dram, old->energy_dram);
- DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status);
- DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status);
+ old->energy_pkg = new->energy_pkg - old->energy_pkg;
+ old->energy_cores = new->energy_cores - old->energy_cores;
+ old->energy_gfx = new->energy_gfx - old->energy_gfx;
+ old->energy_dram = new->energy_dram - old->energy_dram;
+ old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
+ old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
p->gfx_rc6_ms = 0;
p->gfx_mhz = 0;
+ p->gfx_act_mhz = 0;
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
t->counter[i] = 0;
average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
average.packages.gfx_mhz = p->gfx_mhz;
+ average.packages.gfx_act_mhz = p->gfx_act_mhz;
average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
int i;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu);
return -1;
}
p->sys_lpi = cpuidle_cur_sys_lpi_us;
if (do_rapl & RAPL_PKG) {
- if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
return -13;
- p->energy_pkg = msr & 0xFFFFFFFF;
+ p->energy_pkg = msr;
}
if (do_rapl & RAPL_CORES_ENERGY_STATUS) {
- if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
return -14;
- p->energy_cores = msr & 0xFFFFFFFF;
+ p->energy_cores = msr;
}
if (do_rapl & RAPL_DRAM) {
- if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
return -15;
- p->energy_dram = msr & 0xFFFFFFFF;
+ p->energy_dram = msr;
}
if (do_rapl & RAPL_GFX) {
- if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
return -16;
- p->energy_gfx = msr & 0xFFFFFFFF;
+ p->energy_gfx = msr;
}
if (do_rapl & RAPL_PKG_PERF_STATUS) {
- if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
return -16;
- p->rapl_pkg_perf_status = msr & 0xFFFFFFFF;
+ p->rapl_pkg_perf_status = msr;
}
if (do_rapl & RAPL_DRAM_PERF_STATUS) {
- if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr))
+ if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
return -16;
- p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
+ p->rapl_dram_perf_status = msr;
}
if (do_rapl & RAPL_AMD_F17H) {
- if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+ if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
return -13;
- p->energy_pkg = msr & 0xFFFFFFFF;
+ p->energy_pkg = msr;
}
if (DO_BIC(BIC_PkgTmp)) {
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
if (DO_BIC(BIC_GFXMHz))
p->gfx_mhz = gfx_cur_mhz;
+ if (DO_BIC(BIC_GFXACTMHz))
+ p->gfx_act_mhz = gfx_act_mhz;
+
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &p->counter[i]))
return -10;
case INTEL_FAM6_ATOM_GOLDMONT:
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_ATOM_GOLDMONT_D:
+ case INTEL_FAM6_ATOM_TREMONT_D:
return 1;
}
return 0;
sprintf(path,
"/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
- filep = fopen_or_die(path, "r");
+ filep = fopen(path, "r");
+
+ if (!filep) {
+ warnx("%s: open failed", path);
+ return -1;
+ }
do {
offset -= BITMASK_SIZE;
if (fscanf(filep, "%lx%c", &map, &character) != 2)
{
free_all_buffers();
setup_all_buffers();
- printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
+ fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
}
void set_max_cpu_num(void)
{
FILE *filep;
+ int base_cpu;
unsigned long dummy;
+ char pathname[64];
+
+ base_cpu = sched_getcpu();
+ if (base_cpu < 0)
+ err(1, "cannot find calling cpu ID");
+ sprintf(pathname,
+ "/sys/devices/system/cpu/cpu%d/topology/thread_siblings",
+ base_cpu);
+ filep = fopen_or_die(pathname, "r");
topo.max_cpu_num = 0;
- filep = fopen_or_die(
- "/sys/devices/system/cpu/cpu0/topology/thread_siblings",
- "r");
while (fscanf(filep, "%lx,", &dummy) == 1)
topo.max_cpu_num += BITMASK_SIZE;
fclose(filep);
return 0;
}
+/*
+ * snapshot_gfx_cur_mhz()
+ *
+ * record snapshot of
+ * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_gfx_act_mhz(void)
+{
+ static FILE *fp;
+ int retval;
+
+ if (fp == NULL)
+ fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
+ else {
+ rewind(fp);
+ fflush(fp);
+ }
+
+ retval = fscanf(fp, "%d", &gfx_act_mhz);
+ if (retval != 1)
+ err(1, "GFX ACT MHz");
+
+ return 0;
+}
+
/*
* snapshot_cpu_lpi()
*
if (DO_BIC(BIC_GFXMHz))
snapshot_gfx_mhz();
+ if (DO_BIC(BIC_GFXACTMHz))
+ snapshot_gfx_act_mhz();
+
if (DO_BIC(BIC_CPU_LPI))
snapshot_cpu_lpi_us();
}
}
+int get_msr_sum(int cpu, off_t offset, unsigned long long *msr)
+{
+ int ret, idx;
+ unsigned long long msr_cur, msr_last;
+
+ if (!per_cpu_msr_sum)
+ return 1;
+
+ idx = offset_to_idx(offset);
+ if (idx < 0)
+ return idx;
+ /* get_msr_sum() = sum + (get_msr() - last) */
+ ret = get_msr(cpu, offset, &msr_cur);
+ if (ret)
+ return ret;
+ msr_last = per_cpu_msr_sum[cpu].entries[idx].last;
+ DELTA_WRAP32(msr_cur, msr_last);
+ *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum;
+
+ return 0;
+}
+
+timer_t timerid;
+
+/* Timer callback, update the sum of MSRs periodically. */
+static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
+ int i, ret;
+ int cpu = t->cpu_id;
+
+ for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
+ unsigned long long msr_cur, msr_last;
+ int offset;
+
+ if (!idx_valid(i))
+ continue;
+ offset = idx_to_offset(i);
+ if (offset < 0)
+ continue;
+ ret = get_msr(cpu, offset, &msr_cur);
+ if (ret) {
+ fprintf(outf, "Can not update msr(0x%x)\n", offset);
+ continue;
+ }
+
+ msr_last = per_cpu_msr_sum[cpu].entries[i].last;
+ per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff;
+
+ DELTA_WRAP32(msr_cur, msr_last);
+ per_cpu_msr_sum[cpu].entries[i].sum += msr_last;
+ }
+ return 0;
+}
+
+static void
+msr_record_handler(union sigval v)
+{
+ for_all_cpus(update_msr_sum, EVEN_COUNTERS);
+}
+
+void msr_sum_record(void)
+{
+ struct itimerspec its;
+ struct sigevent sev;
+
+ per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array));
+ if (!per_cpu_msr_sum) {
+ fprintf(outf, "Can not allocate memory for long time MSR.\n");
+ return;
+ }
+ /*
+ * Signal handler might be restricted, so use thread notifier instead.
+ */
+ memset(&sev, 0, sizeof(struct sigevent));
+ sev.sigev_notify = SIGEV_THREAD;
+ sev.sigev_notify_function = msr_record_handler;
+
+ sev.sigev_value.sival_ptr = &timerid;
+ if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) {
+ fprintf(outf, "Can not create timer.\n");
+ goto release_msr;
+ }
+
+ its.it_value.tv_sec = 0;
+ its.it_value.tv_nsec = 1;
+ /*
+ * A wraparound time has been calculated early.
+ * Some sources state that the peak power for a
+ * microprocessor is usually 1.5 times the TDP rating,
+ * use 2 * TDP for safety.
+ */
+ its.it_interval.tv_sec = rapl_joule_counter_range / 2;
+ its.it_interval.tv_nsec = 0;
+
+ if (timer_settime(timerid, 0, &its, NULL) == -1) {
+ fprintf(outf, "Can not set timer.\n");
+ goto release_timer;
+ }
+ return;
+
+ release_timer:
+ timer_delete(timerid);
+ release_msr:
+ free(per_cpu_msr_sum);
+}
void turbostat_loop()
{
if (retval < -1) {
exit(retval);
} else if (retval == -1) {
- if (restarted > 1) {
+ if (restarted > 10) {
exit(retval);
}
re_initialize();
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */
case INTEL_FAM6_ATOM_TREMONT: /* EHL */
+ case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
pkg_cstate_limits = glm_pkg_cstate_limits;
break;
default:
}
return 0;
}
+int is_jvl(unsigned int family, unsigned int model)
+{
+ if (!genuine_intel)
+ return 0;
+
+ switch (model) {
+ case INTEL_FAM6_ATOM_TREMONT_D:
+ return 1;
+ }
+ return 0;
+}
int has_turbo_ratio_limit(unsigned int family, unsigned int model)
{
}
}
+static void
+remove_underbar(char *s)
+{
+ char *to = s;
+
+ while (*s) {
+ if (*s != '_')
+ *to++ = *s;
+ s++;
+ }
+
+ *to = 0;
+}
+
static void
dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
{
int state;
char *sp;
- if (!DO_BIC(BIC_sysfs))
- return;
-
if (access("/sys/devices/system/cpu/cpuidle", R_OK)) {
fprintf(outf, "cpuidle not loaded\n");
return;
*sp = '\0';
fclose(input);
+ remove_underbar(name_buf);
+
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
base_cpu, state);
input = fopen(path, "r");
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu);
return -1;
}
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu);
return -1;
}
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu);
return -1;
}
double get_tdp_amd(unsigned int family)
{
- switch (family) {
- case 0x17:
- case 0x18:
- default:
- /* This is the max stock TDP of HEDT/Server Fam17h chips */
- return 250.0;
- }
+ /* This is the max stock TDP of HEDT/Server Fam17h+ chips */
+ return 280.0;
}
/*
BIC_PRESENT(BIC_GFXWatt);
}
break;
+ case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
+ do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+ BIC_PRESENT(BIC_PKG__);
+ if (rapl_joules)
+ BIC_PRESENT(BIC_Pkg_J);
+ else
+ BIC_PRESENT(BIC_PkgWatt);
+ break;
case INTEL_FAM6_SKYLAKE_L: /* SKL */
case INTEL_FAM6_CANNONLAKE_L: /* CNL */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
if (max_extended_level >= 0x80000007) {
__cpuid(0x80000007, eax, ebx, ecx, edx);
- /* RAPL (Fam 17h) */
+ /* RAPL (Fam 17h+) */
has_rapl = edx & (1 << 14);
}
- if (!has_rapl)
+ if (!has_rapl || family < 0x17)
return;
- switch (family) {
- case 0x17: /* Zen, Zen+ */
- case 0x18: /* Hygon Dhyana */
- do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
- if (rapl_joules) {
- BIC_PRESENT(BIC_Pkg_J);
- BIC_PRESENT(BIC_Cor_J);
- } else {
- BIC_PRESENT(BIC_PkgWatt);
- BIC_PRESENT(BIC_CorWatt);
- }
- break;
- default:
- return;
+ do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+ if (rapl_joules) {
+ BIC_PRESENT(BIC_Pkg_J);
+ BIC_PRESENT(BIC_Cor_J);
+ } else {
+ BIC_PRESENT(BIC_PkgWatt);
+ BIC_PRESENT(BIC_CorWatt);
}
if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
return 0;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu);
return -1;
}
cpu = t->cpu_id;
if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu);
return -1;
}
case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */
case INTEL_FAM6_ATOM_TREMONT: /* EHL */
+ case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */
return 1;
}
return 0;
* below this value, including the Digital Thermal Sensor (DTS),
* Package Thermal Management Sensor (PTM), and thermal event thresholds.
*/
-int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+int read_tcc_activation_temp()
{
unsigned long long msr;
- unsigned int target_c_local;
- int cpu;
+ unsigned int tcc, target_c, offset_c;
+ /* Temperature Target MSR is Nehalem and newer only */
+ if (!do_nhm_platform_info)
+ return 0;
+
+ if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
+ return 0;
+
+ target_c = (msr >> 16) & 0xFF;
+
+ offset_c = (msr >> 24) & 0xF;
+
+ tcc = target_c - offset_c;
+
+ if (!quiet)
+ fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n",
+ base_cpu, msr, tcc, target_c, offset_c);
+
+ return tcc;
+}
+
+int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p)
+{
/* tcc_activation_temp is used only for dts or ptm */
if (!(do_dts || do_ptm))
return 0;
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
return 0;
- cpu = t->cpu_id;
- if (cpu_migrate(cpu)) {
- fprintf(outf, "Could not migrate to CPU %d\n", cpu);
- return -1;
- }
-
if (tcc_activation_temp_override != 0) {
tcc_activation_temp = tcc_activation_temp_override;
- fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n",
- cpu, tcc_activation_temp);
+ fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp);
return 0;
}
- /* Temperature Target MSR is Nehalem and newer only */
- if (!do_nhm_platform_info)
- goto guess;
-
- if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
- goto guess;
-
- target_c_local = (msr >> 16) & 0xFF;
-
- if (!quiet)
- fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n",
- cpu, msr, target_c_local);
-
- if (!target_c_local)
- goto guess;
-
- tcc_activation_temp = target_c_local;
-
- return 0;
+ tcc_activation_temp = read_tcc_activation_temp();
+ if (tcc_activation_temp)
+ return 0;
-guess:
tcc_activation_temp = TJMAX_DEFAULT;
- fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n",
- cpu, tcc_activation_temp);
+ fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp);
return 0;
}
case INTEL_FAM6_ICELAKE_NNPI:
case INTEL_FAM6_TIGERLAKE_L:
case INTEL_FAM6_TIGERLAKE:
+ case INTEL_FAM6_ROCKETLAKE:
+ case INTEL_FAM6_LAKEFIELD:
+ case INTEL_FAM6_ALDERLAKE:
return INTEL_FAM6_CANNONLAKE_L;
- case INTEL_FAM6_ATOM_TREMONT_D:
- return INTEL_FAM6_ATOM_GOLDMONT_D;
-
case INTEL_FAM6_ATOM_TREMONT_L:
return INTEL_FAM6_ATOM_TREMONT;
case INTEL_FAM6_ICELAKE_X:
+ case INTEL_FAM6_SAPPHIRERAPIDS_X:
return INTEL_FAM6_SKYLAKE_X;
}
return model;
}
+
+void print_dev_latency(void)
+{
+ char *path = "/dev/cpu_dma_latency";
+ int fd;
+ int value;
+ int retval;
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ warn("fopen %s\n", path);
+ return;
+ }
+
+ retval = read(fd, (void *)&value, sizeof(int));
+ if (retval != sizeof(int)) {
+ warn("read %s\n", path);
+ close(fd);
+ return;
+ }
+ fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n",
+ value, value == 2000000000 ? "default" : "constrained");
+
+ close(fd);
+}
+
void process_cpuid()
{
unsigned int eax, ebx, ecx, edx;
BIC_PRESENT(BIC_Mod_c6);
use_c1_residency_msr = 1;
}
+ if (is_jvl(family, model)) {
+ BIC_NOT_PRESENT(BIC_CPU_c3);
+ BIC_NOT_PRESENT(BIC_CPU_c7);
+ BIC_NOT_PRESENT(BIC_Pkgpc2);
+ BIC_NOT_PRESENT(BIC_Pkgpc3);
+ BIC_NOT_PRESENT(BIC_Pkgpc6);
+ BIC_NOT_PRESENT(BIC_Pkgpc7);
+ }
if (is_dnv(family, model)) {
BIC_PRESENT(BIC_CPU_c1);
BIC_NOT_PRESENT(BIC_CPU_c3);
BIC_NOT_PRESENT(BIC_Pkgpc7);
}
if (has_c8910_msrs(family, model)) {
- BIC_PRESENT(BIC_Pkgpc8);
- BIC_PRESENT(BIC_Pkgpc9);
- BIC_PRESENT(BIC_Pkgpc10);
+ if (pkg_cstate_limit >= PCL__8)
+ BIC_PRESENT(BIC_Pkgpc8);
+ if (pkg_cstate_limit >= PCL__9)
+ BIC_PRESENT(BIC_Pkgpc9);
+ if (pkg_cstate_limit >= PCL_10)
+ BIC_PRESENT(BIC_Pkgpc10);
}
do_irtl_hsw = has_c8910_msrs(family, model);
if (has_skl_msrs(family, model)) {
if (!quiet)
dump_cstate_pstate_config_info(family, model);
+ if (!quiet)
+ print_dev_latency();
if (!quiet)
dump_sysfs_cstate_config();
if (!quiet)
if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
BIC_PRESENT(BIC_GFXMHz);
+ if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ BIC_PRESENT(BIC_GFXACTMHz);
+
if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
BIC_PRESENT(BIC_CPU_LPI);
else
}
void print_version() {
- fprintf(outf, "turbostat version 20.03.20"
+ fprintf(outf, "turbostat version 20.09.30"
" - Len Brown <lenb@kernel.org>\n");
}
*sp = '%';
*(sp + 1) = '\0';
+ remove_underbar(name_buf);
+
fclose(input);
sprintf(path, "cpuidle/state%d/time", state);
*sp = '\0';
fclose(input);
+ remove_underbar(name_buf);
+
sprintf(path, "cpuidle/state%d/usage", state);
if (is_deferred_skip(name_buf))
return 0;
}
+ msr_sum_record();
/*
* if any params left, it must be a command to fork
*/
}
}
+/*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+ FILE *filep = fopen(path, "r");
+
+ if (!filep)
+ err(1, "%s: open failed", path);
+ return filep;
+}
+
+void err_on_hypervisor(void)
+{
+ FILE *cpuinfo;
+ char *flags, *hypervisor;
+ char *buffer;
+
+ /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */
+ cpuinfo = fopen_or_die("/proc/cpuinfo", "ro");
+
+ buffer = malloc(4096);
+ if (!buffer) {
+ fclose(cpuinfo);
+ err(-ENOMEM, "buffer malloc fail");
+ }
+
+ if (!fread(buffer, 1024, 1, cpuinfo)) {
+ fclose(cpuinfo);
+ free(buffer);
+ err(1, "Reading /proc/cpuinfo failed");
+ }
+
+ flags = strstr(buffer, "flags");
+ rewind(cpuinfo);
+ fseek(cpuinfo, flags - buffer, SEEK_SET);
+ if (!fgets(buffer, 4096, cpuinfo)) {
+ fclose(cpuinfo);
+ free(buffer);
+ err(1, "Reading /proc/cpuinfo failed");
+ }
+ fclose(cpuinfo);
+
+ hypervisor = strstr(buffer, "hypervisor");
+
+ free(buffer);
+
+ if (hypervisor)
+ err(-1,
+ "not supported on this virtual machine");
+}
int get_msr(int cpu, int offset, unsigned long long *msr)
{
err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
retval = pread(fd, msr, sizeof(*msr), offset);
- if (retval != sizeof(*msr))
+ if (retval != sizeof(*msr)) {
+ err_on_hypervisor();
err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset);
+ }
if (debug > 1)
fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr);
return 0;
}
-/*
- * Open a file, and exit on failure
- */
-FILE *fopen_or_die(const char *path, const char *mode)
-{
- FILE *filep = fopen(path, "r");
-
- if (!filep)
- err(1, "%s: open failed", path);
- return filep;
-}
-
unsigned int get_pkg_num(int cpu)
{
FILE *fp;
+++ /dev/null
-test_data/* binary
import sys
import os
import time
-import shutil
from collections import namedtuple
from enum import Enum, auto
BUILD_FAILURE = auto()
TEST_FAILURE = auto()
-def create_default_kunitconfig():
- if not os.path.exists(kunit_kernel.kunitconfig_path):
- shutil.copyfile('arch/um/configs/kunit_defconfig',
- kunit_kernel.kunitconfig_path)
-
def get_kernel_root_path():
parts = sys.argv[0] if not __file__ else __file__
parts = os.path.realpath(parts).split('tools/testing/kunit')
kunit_parser.print_with_timestamp('Configuring KUnit Kernel ...')
config_start = time.time()
- create_default_kunitconfig()
success = linux.build_reconfig(request.build_dir, request.make_options)
config_end = time.time()
if not success:
if not os.path.exists(cli_args.build_dir):
os.mkdir(cli_args.build_dir)
- if not os.path.exists(kunit_kernel.kunitconfig_path):
- create_default_kunitconfig()
-
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
request = KunitRequest(cli_args.raw_output,
cli_args.timeout,
cli_args.jobs,
not os.path.exists(cli_args.build_dir)):
os.mkdir(cli_args.build_dir)
- if not os.path.exists(kunit_kernel.kunitconfig_path):
- create_default_kunitconfig()
-
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
request = KunitConfigRequest(cli_args.build_dir,
cli_args.make_options)
result = config_tests(linux, request)
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
request = KunitBuildRequest(cli_args.jobs,
cli_args.build_dir,
cli_args.alltests,
if not linux:
linux = kunit_kernel.LinuxSourceTree()
+ linux.create_kunitconfig(cli_args.build_dir)
+ linux.read_kunitconfig(cli_args.build_dir)
+
exec_request = KunitExecRequest(cli_args.timeout,
cli_args.build_dir,
cli_args.alltests)
kunit_output = f.read().splitlines()
request = KunitParseRequest(cli_args.raw_output,
kunit_output,
- cli_args.build_dir,
+ None,
cli_args.json)
result = parse_tests(request)
if result.status != KunitStatus.SUCCESS:
# Author: Felix Guo <felixguoxiuping@gmail.com>
# Author: Brendan Higgins <brendanhiggins@google.com>
-
import logging
import subprocess
import os
+import shutil
import signal
from contextlib import ExitStack
import kunit_parser
KCONFIG_PATH = '.config'
-kunitconfig_path = '.kunitconfig'
+KUNITCONFIG_PATH = '.kunitconfig'
+DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig'
BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config'
+OUTFILE_PATH = 'test.log'
class ConfigError(Exception):
"""Represents an error trying to configure the Linux kernel."""
if build_dir:
command += ['O=' + build_dir]
try:
- subprocess.check_output(command, stderr=subprocess.STDOUT)
+ proc = subprocess.Popen(command,
+ stderr=subprocess.PIPE,
+ stdout=subprocess.DEVNULL)
except OSError as e:
- raise BuildError('Could not call execute make: ' + str(e))
- except subprocess.CalledProcessError as e:
- raise BuildError(e.output.decode())
-
- def linux_bin(self, params, timeout, build_dir, outfile):
+ raise BuildError('Could not call make command: ' + str(e))
+ _, stderr = proc.communicate()
+ if proc.returncode != 0:
+ raise BuildError(stderr.decode())
+ if stderr: # likely only due to build warnings
+ print(stderr.decode())
+
+ def linux_bin(self, params, timeout, build_dir):
"""Runs the Linux UML binary. Must be named 'linux'."""
linux_bin = './linux'
if build_dir:
linux_bin = os.path.join(build_dir, 'linux')
+ outfile = get_outfile_path(build_dir)
with open(outfile, 'w') as output:
process = subprocess.Popen([linux_bin] + params,
stdout=output,
stderr=subprocess.STDOUT)
process.wait(timeout)
-
def get_kconfig_path(build_dir):
kconfig_path = KCONFIG_PATH
if build_dir:
kconfig_path = os.path.join(build_dir, KCONFIG_PATH)
return kconfig_path
+def get_kunitconfig_path(build_dir):
+ kunitconfig_path = KUNITCONFIG_PATH
+ if build_dir:
+ kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH)
+ return kunitconfig_path
+
+def get_outfile_path(build_dir):
+ outfile_path = OUTFILE_PATH
+ if build_dir:
+ outfile_path = os.path.join(build_dir, OUTFILE_PATH)
+ return outfile_path
+
class LinuxSourceTree(object):
"""Represents a Linux kernel source tree with KUnit tests."""
def __init__(self):
- self._kconfig = kunit_config.Kconfig()
- self._kconfig.read_from_file(kunitconfig_path)
self._ops = LinuxSourceTreeOperations()
signal.signal(signal.SIGINT, self.signal_handler)
return False
return True
+ def create_kunitconfig(self, build_dir, defconfig=DEFAULT_KUNITCONFIG_PATH):
+ kunitconfig_path = get_kunitconfig_path(build_dir)
+ if not os.path.exists(kunitconfig_path):
+ shutil.copyfile(defconfig, kunitconfig_path)
+
+ def read_kunitconfig(self, build_dir):
+ kunitconfig_path = get_kunitconfig_path(build_dir)
+ self._kconfig = kunit_config.Kconfig()
+ self._kconfig.read_from_file(kunitconfig_path)
+
def validate_config(self, build_dir):
kconfig_path = get_kconfig_path(build_dir)
validated_kconfig = kunit_config.Kconfig()
def run_kernel(self, args=[], build_dir='', timeout=None):
args.extend(['mem=1G'])
- outfile = 'test.log'
- self._ops.linux_bin(args, timeout, build_dir, outfile)
+ self._ops.linux_bin(args, timeout, build_dir)
+ outfile = get_outfile_path(build_dir)
subprocess.call(['stty', 'sane'])
with open(outfile, 'r') as file:
for line in file:
from datetime import datetime
from enum import Enum, auto
from functools import reduce
-from typing import List
+from typing import List, Optional, Tuple
TestResult = namedtuple('TestResult', ['status','suites','log'])
def isolate_kunit_output(kernel_output):
started = False
for line in kernel_output:
+ line = line.rstrip() # line always has a trailing \n
if kunit_start_re.search(line):
prefix_len = len(line.split('TAP version')[0])
started = True
def raw_output(kernel_output):
for line in kernel_output:
- print(line)
- yield line
+ print(line.rstrip())
DIVIDER = '=' * 60
else:
return False
-def parse_test_case(lines: List[str]) -> TestCase:
+def parse_test_case(lines: List[str]) -> Optional[TestCase]:
test_case = TestCase()
save_non_diagnositic(lines, test_case)
while parse_diagnostic(lines, test_case):
SUBTEST_HEADER = re.compile(r'^[\s]+# Subtest: (.*)$')
-def parse_subtest_header(lines: List[str]) -> str:
+def parse_subtest_header(lines: List[str]) -> Optional[str]:
consume_non_diagnositic(lines)
if not lines:
return None
SUBTEST_PLAN = re.compile(r'[\s]+[0-9]+\.\.([0-9]+)')
-def parse_subtest_plan(lines: List[str]) -> int:
+def parse_subtest_plan(lines: List[str]) -> Optional[int]:
consume_non_diagnositic(lines)
match = SUBTEST_PLAN.match(lines[0])
if match:
max_test_case_status = bubble_up_errors(lambda x: x.status, test_suite.cases)
return max_status(max_test_case_status, test_suite.status)
-def parse_test_suite(lines: List[str], expected_suite_index: int) -> TestSuite:
+def parse_test_suite(lines: List[str], expected_suite_index: int) -> Optional[TestSuite]:
if not lines:
return None
consume_non_diagnositic(lines)
return None
test_suite.name = name
expected_test_case_num = parse_subtest_plan(lines)
- if not expected_test_case_num:
+ if expected_test_case_num is None:
return None
while expected_test_case_num > 0:
test_case = parse_test_case(lines)
TEST_PLAN = re.compile(r'[0-9]+\.\.([0-9]+)')
-def parse_test_plan(lines: List[str]) -> int:
+def parse_test_plan(lines: List[str]) -> Optional[int]:
consume_non_diagnositic(lines)
match = TEST_PLAN.match(lines[0])
if match:
else:
return TestResult(TestStatus.NO_TESTS, [], lines)
-def print_and_count_results(test_result: TestResult) -> None:
+def print_and_count_results(test_result: TestResult) -> Tuple[int, int, int]:
total_tests = 0
failed_tests = 0
crashed_tests = 0
'test_data/test_output_isolated_correctly.log')
file = open(log_path)
result = kunit_parser.isolate_kunit_output(file.readlines())
- self.assertContains('TAP version 14\n', result)
+ self.assertContains('TAP version 14', result)
self.assertContains(' # Subtest: example', result)
self.assertContains(' 1..2', result)
self.assertContains(' ok 1 - example_simple_test', result)
'test_data/test_pound_sign.log')
with open(log_path) as file:
result = kunit_parser.isolate_kunit_output(file.readlines())
- self.assertContains('TAP version 14\n', result)
+ self.assertContains('TAP version 14', result)
self.assertContains(' # Subtest: kunit-resource-test', result)
self.assertContains(' 1..5', result)
self.assertContains(' ok 1 - kunit_resource_test_init_resources', result)
print_mock = mock.patch('builtins.print').start()
result = kunit_parser.parse_run_tests(
kunit_parser.isolate_kunit_output(file.readlines()))
- print_mock.assert_any_call(StrContains("no kunit output detected"))
+ print_mock.assert_any_call(StrContains('no tests run!'))
print_mock.stop()
file.close()
'test_data/test_config_printk_time.log')
with open(prefix_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_ignores_multiple_prefixes(self):
prefix_log = get_absolute_path(
'test_data/test_multiple_prefixes.log')
with open(prefix_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_prefix_mixed_kernel_output(self):
mixed_prefix_log = get_absolute_path(
'test_data/test_interrupted_tap_output.log')
with open(mixed_prefix_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_prefix_poundsign(self):
pound_log = get_absolute_path('test_data/test_pound_sign.log')
with open(pound_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_kernel_panic_end(self):
panic_log = get_absolute_path('test_data/test_kernel_panic_interrupt.log')
with open(panic_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.TEST_CRASHED,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
def test_pound_no_prefix(self):
pound_log = get_absolute_path('test_data/test_pound_no_prefix.log')
with open(pound_log) as file:
result = kunit_parser.parse_run_tests(file.readlines())
- self.assertEqual('kunit-resource-test', result.suites[0].name)
+ self.assertEqual(
+ kunit_parser.TestStatus.SUCCESS,
+ result.status)
+ self.assertEqual('kunit-resource-test', result.suites[0].name)
class KUnitJsonTest(unittest.TestCase):
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
[ 0.060000] Stack:
[ 0.060000] 602086f8 601bc260 705c0000 705c0000
[ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
[ 0.060000] Stack:
[ 0.060000] 602086f8 601bc260 705c0000 705c0000
[ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
[ 0.060000] Stack:
[ 0.060000] 602086f8 601bc260 705c0000 705c0000
[ 0.060000] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000] 6005fcec 601bc260 705c0000 3000000010
[ 0.060000][ T1] printk: console [mc-1] enabled
[ 0.060000][ T1] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000][ T1] TAP version 14
+[ 0.060000][ T1] 1..3
[ 0.060000][ T1] # Subtest: kunit-resource-test
[ 0.060000][ T1] 1..5
[ 0.060000][ T1] ok 1 - kunit_resource_test_init_resources
[ 0.060000][ T1] Stack:
[ 0.060000][ T1] 602086f8 601bc260 705c0000 705c0000
[ 0.060000][ T1] 602086f8 6005fcec 705c0000 6002c6ab
-[ 0.060000][ T1] 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+[ 0.060000][ T1] 6005fcec 601bc260 705c0000 3000000010
printk: console [mc-1] enabled
random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
TAP version 14
+ 1..3
# Subtest: kunit-resource-test
1..5
ok 1 - kunit_resource_test_init_resources
Stack:
602086f8 601bc260 705c0000 705c0000
602086f8 6005fcec 705c0000 6002c6ab
- 6005fcec 601bc260 705c0000 3000000010
\ No newline at end of file
+ 6005fcec 601bc260 705c0000 3000000010
[ 0.060000] printk: console [mc-1] enabled
[ 0.060000] random: get_random_bytes called from init_oops_id+0x35/0x40 with crng_init=0
[ 0.060000] TAP version 14
+[ 0.060000] 1..3
[ 0.060000] # Subtest: kunit-resource-test
[ 0.060000] 1..5
[ 0.060000] ok 1 - kunit_resource_test_init_resources
#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask))
#define ALIGN(x, a) __ALIGN_KERNEL((x), (a))
+#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a))
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
{
const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT;
struct test *test, tests[] = {
- { -EINVAL, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
{ -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 },
- { -EINVAL, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
+ { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
+ { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
{ 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 },
{ 0, 1, pfn(0), 1, sgmax, 1 },
{ 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 },
/* Register SIGSEGV handler */
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(20);
+
/* Buffer by byte tests */
evaluate_test(check_buffer_by_byte(USE_MMAP, MTE_SYNC_ERR),
"Check buffer correctness by byte with sync err mode and mmap memory\n");
mte_register_signal(SIGSEGV, mte_default_handler);
mte_register_signal(SIGBUS, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(12);
+
evaluate_test(check_child_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
"Check child anonymous memory with private mapping, precise mode and mmap memory\n");
evaluate_test(check_child_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED),
/* Register signal handlers */
mte_register_signal(SIGBUS, mte_default_handler);
mte_register_signal(SIGSEGV, mte_default_handler);
+
+ /* Set test plan */
+ ksft_set_plan(4);
+
/* Enable KSM */
mte_ksm_setup();
mte_register_signal(SIGBUS, mte_default_handler);
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(22);
+
mte_enable_pstate_tco();
+
evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
"Check anonymous memory with private mapping, sync error mode, mmap memory and tag check off\n");
evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
/* Register SIGSEGV handler */
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(4);
+
evaluate_test(check_single_included_tags(USE_MMAP, MTE_SYNC_ERR),
"Check an included tag value with sync mode\n");
evaluate_test(check_multiple_included_tags(USE_MMAP, MTE_SYNC_ERR),
err = mte_default_setup();
if (err)
return err;
+
/* Register signal handlers */
mte_register_signal(SIGSEGV, mte_default_handler);
+ /* Set test plan */
+ ksft_set_plan(4);
+
evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
"Check memory access from kernel in sync mode, private mapping and mmap memory\n");
evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED),
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */
+
+#include <test_progs.h>
+#include "test_map_init.skel.h"
+
+#define TEST_VALUE 0x1234
+#define FILL_VALUE 0xdeadbeef
+
+static int nr_cpus;
+static int duration;
+
+typedef unsigned long long map_key_t;
+typedef unsigned long long map_value_t;
+typedef struct {
+ map_value_t v; /* padding */
+} __bpf_percpu_val_align pcpu_map_value_t;
+
+
+static int map_populate(int map_fd, int num)
+{
+ pcpu_map_value_t value[nr_cpus];
+ int i, err;
+ map_key_t key;
+
+ for (i = 0; i < nr_cpus; i++)
+ bpf_percpu(value, i) = FILL_VALUE;
+
+ for (key = 1; key <= num; key++) {
+ err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ return -1;
+ }
+
+ return 0;
+}
+
+static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz,
+ int *map_fd, int populate)
+{
+ struct test_map_init *skel;
+ int err;
+
+ skel = test_map_init__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return NULL;
+
+ err = bpf_map__set_type(skel->maps.hashmap1, map_type);
+ if (!ASSERT_OK(err, "bpf_map__set_type"))
+ goto error;
+
+ err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz);
+ if (!ASSERT_OK(err, "bpf_map__set_max_entries"))
+ goto error;
+
+ err = test_map_init__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto error;
+
+ *map_fd = bpf_map__fd(skel->maps.hashmap1);
+ if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n"))
+ goto error;
+
+ err = map_populate(*map_fd, populate);
+ if (!ASSERT_OK(err, "map_populate"))
+ goto error_map;
+
+ return skel;
+
+error_map:
+ close(*map_fd);
+error:
+ test_map_init__destroy(skel);
+ return NULL;
+}
+
+/* executes bpf program that updates map with key, value */
+static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key,
+ map_value_t value)
+{
+ struct test_map_init__bss *bss;
+
+ bss = skel->bss;
+
+ bss->inKey = key;
+ bss->inValue = value;
+ bss->inPid = getpid();
+
+ if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach"))
+ return -1;
+
+ /* Let tracepoint trigger */
+ syscall(__NR_getpgid);
+
+ test_map_init__detach(skel);
+
+ return 0;
+}
+
+static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected)
+{
+ int i, nzCnt = 0;
+ map_value_t val;
+
+ for (i = 0; i < nr_cpus; i++) {
+ val = bpf_percpu(value, i);
+ if (val) {
+ if (CHECK(val != expected, "map value",
+ "unexpected for cpu %d: 0x%llx\n", i, val))
+ return -1;
+ nzCnt++;
+ }
+ }
+
+ if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n",
+ nzCnt))
+ return -1;
+
+ return 0;
+}
+
+/* Add key=1 elem with values set for all CPUs
+ * Delete elem key=1
+ * Run bpf prog that inserts new key=1 elem with value=0x1234
+ * (bpf prog can only set value for current CPU)
+ * Lookup Key=1 and check value is as expected for all CPUs:
+ * value set by bpf prog for one CPU, 0 for all others
+ */
+static void test_pcpu_map_init(void)
+{
+ pcpu_map_value_t value[nr_cpus];
+ struct test_map_init *skel;
+ int map_fd, err;
+ map_key_t key;
+
+ /* max 1 elem in map so insertion is forced to reuse freed entry */
+ skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1);
+ if (!ASSERT_OK_PTR(skel, "prog_setup"))
+ return;
+
+ /* delete element so the entry can be re-used*/
+ key = 1;
+ err = bpf_map_delete_elem(map_fd, &key);
+ if (!ASSERT_OK(err, "bpf_map_delete_elem"))
+ goto cleanup;
+
+ /* run bpf prog that inserts new elem, re-using the slot just freed */
+ err = prog_run_insert_elem(skel, key, TEST_VALUE);
+ if (!ASSERT_OK(err, "prog_run_insert_elem"))
+ goto cleanup;
+
+ /* check that key=1 was re-created by bpf prog */
+ err = bpf_map_lookup_elem(map_fd, &key, value);
+ if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+ goto cleanup;
+
+ /* and has expected values */
+ check_values_one_cpu(value, TEST_VALUE);
+
+cleanup:
+ test_map_init__destroy(skel);
+}
+
+/* Add key=1 and key=2 elems with values set for all CPUs
+ * Run bpf prog that inserts new key=3 elem
+ * (only for current cpu; other cpus should have initial value = 0)
+ * Lookup Key=1 and check value is as expected for all CPUs
+ */
+static void test_pcpu_lru_map_init(void)
+{
+ pcpu_map_value_t value[nr_cpus];
+ struct test_map_init *skel;
+ int map_fd, err;
+ map_key_t key;
+
+ /* Set up LRU map with 2 elements, values filled for all CPUs.
+ * With these 2 elements, the LRU map is full
+ */
+ skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2);
+ if (!ASSERT_OK_PTR(skel, "prog_setup"))
+ return;
+
+ /* run bpf prog that inserts new key=3 element, re-using LRU slot */
+ key = 3;
+ err = prog_run_insert_elem(skel, key, TEST_VALUE);
+ if (!ASSERT_OK(err, "prog_run_insert_elem"))
+ goto cleanup;
+
+ /* check that key=3 replaced one of earlier elements */
+ err = bpf_map_lookup_elem(map_fd, &key, value);
+ if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+ goto cleanup;
+
+ /* and has expected values */
+ check_values_one_cpu(value, TEST_VALUE);
+
+cleanup:
+ test_map_init__destroy(skel);
+}
+
+void test_map_init(void)
+{
+ nr_cpus = bpf_num_possible_cpus();
+ if (nr_cpus <= 1) {
+ printf("%s:SKIP: >1 cpu needed for this test\n", __func__);
+ test__skip();
+ return;
+ }
+
+ if (test__start_subtest("pcpu_map_init"))
+ test_pcpu_map_init();
+ if (test__start_subtest("pcpu_lru_map_init"))
+ test_pcpu_lru_map_init();
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "test_probe_read_user_str.skel.h"
+
+static const char str1[] = "mestring";
+static const char str2[] = "mestringalittlebigger";
+static const char str3[] = "mestringblubblubblubblubblub";
+
+static int test_one_str(struct test_probe_read_user_str *skel, const char *str,
+ size_t len)
+{
+ int err, duration = 0;
+ char buf[256];
+
+ /* Ensure bytes after string are ones */
+ memset(buf, 1, sizeof(buf));
+ memcpy(buf, str, len);
+
+ /* Give prog our userspace pointer */
+ skel->bss->user_ptr = buf;
+
+ /* Trigger tracepoint */
+ usleep(1);
+
+ /* Did helper fail? */
+ if (CHECK(skel->bss->ret < 0, "prog_ret", "prog returned: %ld\n",
+ skel->bss->ret))
+ return 1;
+
+ /* Check that string was copied correctly */
+ err = memcmp(skel->bss->buf, str, len);
+ if (CHECK(err, "memcmp", "prog copied wrong string"))
+ return 1;
+
+ /* Now check that no extra trailing bytes were copied */
+ memset(buf, 0, sizeof(buf));
+ err = memcmp(skel->bss->buf + len, buf, sizeof(buf) - len);
+ if (CHECK(err, "memcmp", "trailing bytes were not stripped"))
+ return 1;
+
+ return 0;
+}
+
+void test_probe_read_user_str(void)
+{
+ struct test_probe_read_user_str *skel;
+ int err, duration = 0;
+
+ skel = test_probe_read_user_str__open_and_load();
+ if (CHECK(!skel, "test_probe_read_user_str__open_and_load",
+ "skeleton open and load failed\n"))
+ return;
+
+ /* Give pid to bpf prog so it doesn't read from anyone else */
+ skel->bss->pid = getpid();
+
+ err = test_probe_read_user_str__attach(skel);
+ if (CHECK(err, "test_probe_read_user_str__attach",
+ "skeleton attach failed: %d\n", err))
+ goto out;
+
+ if (test_one_str(skel, str1, sizeof(str1)))
+ goto out;
+ if (test_one_str(skel, str2, sizeof(str2)))
+ goto out;
+ if (test_one_str(skel, str3, sizeof(str3)))
+ goto out;
+
+out:
+ test_probe_read_user_str__destroy(skel);
+}
*/
buf = 0x40;
- if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) {
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (err < 0) {
log_err("Failed to call setsockopt(IP_TOS)");
goto detach;
}
#include <test_progs.h>
#include <time.h>
#include "test_subprogs.skel.h"
+#include "test_subprogs_unused.skel.h"
static int duration;
void test_subprogs(void)
{
struct test_subprogs *skel;
+ struct test_subprogs_unused *skel2;
int err;
skel = test_subprogs__open_and_load();
CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19);
CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36);
+ skel2 = test_subprogs_unused__open_and_load();
+ ASSERT_OK_PTR(skel2, "unused_progs_skel");
+ test_subprogs_unused__destroy(skel2);
+
cleanup:
test_subprogs__destroy(skel);
}
{ "test_global_func5.o" , "expected pointer to ctx, but got PTR" },
{ "test_global_func6.o" , "modified ctx ptr R2" },
{ "test_global_func7.o" , "foo() doesn't return scalar" },
+ { "test_global_func8.o" },
};
libbpf_print_fn_t old_print_fn = NULL;
int err, i, duration = 0;
}
}
-int pids_cgrp_id = 1;
+extern bool CONFIG_CGROUP_PIDS __kconfig __weak;
+enum cgroup_subsys_id___local {
+ pids_cgrp_id___local = 123, /* value doesn't matter */
+};
static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
struct task_struct* task,
BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn);
struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
- if (ENABLE_CGROUP_V1_RESOLVER) {
+ if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) {
+ int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
+ pids_cgrp_id___local);
#ifdef UNROLL
#pragma unroll
#endif
BPF_CORE_READ(task, cgroups, subsys[i]);
if (subsys != NULL) {
int subsys_id = BPF_CORE_READ(subsys, ss, id);
- if (subsys_id == pids_cgrp_id) {
+ if (subsys_id == cgrp_id) {
proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn);
root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn);
break;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__noinline int foo(struct __sk_buff *skb)
+{
+ return bpf_get_prandom_u32();
+}
+
+SEC("cgroup_skb/ingress")
+int test_cls(struct __sk_buff *skb)
+{
+ if (!foo(skb))
+ return 0;
+
+ return 1;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+__u64 inKey = 0;
+__u64 inValue = 0;
+__u32 inPid = 0;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+ __uint(max_entries, 2);
+ __type(key, __u64);
+ __type(value, __u64);
+} hashmap1 SEC(".maps");
+
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int sysenter_getpgid(const void *ctx)
+{
+ /* Just do it for once, when called from our own test prog. This
+ * ensures the map value is only updated for a single CPU.
+ */
+ int cur_pid = bpf_get_current_pid_tgid() >> 32;
+
+ if (cur_pid == inPid)
+ bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include <sys/types.h>
+
+pid_t pid = 0;
+long ret = 0;
+void *user_ptr = 0;
+char buf[256] = {};
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int on_write(void *ctx)
+{
+ if (pid != (bpf_get_current_pid_tgid() >> 32))
+ return 0;
+
+ ret = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+const char LICENSE[] SEC("license") = "GPL";
+
+__attribute__((unused)) __noinline int unused1(int x)
+{
+ return x + 1;
+}
+
+static __attribute__((unused)) __noinline int unused2(int x)
+{
+ return x + 2;
+}
+
+SEC("raw_tp/sys_enter")
+int main_prog(void *ctx)
+{
+ return 0;
+}
test_clone3_supported();
EXPECT_EQ(getuid(), 0)
- XFAIL(return, "Skipping all tests as non-root\n");
+ SKIP(return, "Skipping all tests as non-root");
memset(&set_tid, 0, sizeof(set_tid));
fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(fd, 0) {
if (errno == ENOENT)
- XFAIL(return, "Skipping test since /dev/null does not exist");
+ SKIP(return, "Skipping test since /dev/null does not exist");
}
open_fds[i] = fd;
EXPECT_EQ(-1, sys_close_range(open_fds[0], open_fds[100], -1)) {
if (errno == ENOSYS)
- XFAIL(return, "close_range() syscall not supported");
+ SKIP(return, "close_range() syscall not supported");
}
EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0));
fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(fd, 0) {
if (errno == ENOENT)
- XFAIL(return, "Skipping test since /dev/null does not exist");
+ SKIP(return, "Skipping test since /dev/null does not exist");
}
open_fds[i] = fd;
fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(fd, 0) {
if (errno == ENOENT)
- XFAIL(return, "Skipping test since /dev/null does not exist");
+ SKIP(return, "Skipping test since /dev/null does not exist");
}
open_fds[i] = fd;
ret = mount(NULL, binderfs_mntpt, "binder", 0, 0);
EXPECT_EQ(ret, 0) {
if (errno == ENODEV)
- XFAIL(goto out, "binderfs missing");
+ SKIP(goto out, "binderfs missing");
TH_LOG("%s - Failed to mount binderfs", strerror(errno));
goto rmdir;
}
TEST(binderfs_test_privileged)
{
if (geteuid() != 0)
- XFAIL(return, "Tests are not run as root. Skipping privileged tests");
+ SKIP(return, "Tests are not run as root. Skipping privileged tests");
if (__do_binderfs_test(_metadata))
- XFAIL(return, "The Android binderfs filesystem is not available");
+ SKIP(return, "The Android binderfs filesystem is not available");
}
TEST(binderfs_test_unprivileged)
ret = wait_for_pid(pid);
if (ret) {
if (ret == 2)
- XFAIL(return, "The Android binderfs filesystem is not available");
+ SKIP(return, "The Android binderfs filesystem is not available");
ASSERT_EQ(ret, 0) {
TH_LOG("wait_for_pid() failed");
}
close(ctx.epfd);
}
+struct epoll61_ctx {
+ int epfd;
+ int evfd;
+};
+
+static void *epoll61_write_eventfd(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ int64_t l = 1;
+
+ usleep(10950);
+ write(ctx->evfd, &l, sizeof(l));
+ return NULL;
+}
+
+static void *epoll61_epoll_with_timeout(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ struct epoll_event events[1];
+ int n;
+
+ n = epoll_wait(ctx->epfd, events, 1, 11);
+ /*
+ * If epoll returned the eventfd, write on the eventfd to wake up the
+ * blocking poller.
+ */
+ if (n == 1) {
+ int64_t l = 1;
+
+ write(ctx->evfd, &l, sizeof(l));
+ }
+ return NULL;
+}
+
+static void *epoll61_blocking_epoll(void *ctx_)
+{
+ struct epoll61_ctx *ctx = ctx_;
+ struct epoll_event events[1];
+
+ epoll_wait(ctx->epfd, events, 1, -1);
+ return NULL;
+}
+
+TEST(epoll61)
+{
+ struct epoll61_ctx ctx;
+ struct epoll_event ev;
+ int i, r;
+
+ ctx.epfd = epoll_create1(0);
+ ASSERT_GE(ctx.epfd, 0);
+ ctx.evfd = eventfd(0, EFD_NONBLOCK);
+ ASSERT_GE(ctx.evfd, 0);
+
+ ev.events = EPOLLIN | EPOLLET | EPOLLERR | EPOLLHUP;
+ ev.data.ptr = NULL;
+ r = epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd, &ev);
+ ASSERT_EQ(r, 0);
+
+ /*
+ * We are testing a race. Repeat the test case 1000 times to make it
+ * more likely to fail in case of a bug.
+ */
+ for (i = 0; i < 1000; i++) {
+ pthread_t threads[3];
+ int n;
+
+ /*
+ * Start 3 threads:
+ * Thread 1 sleeps for 10.9ms and writes to the evenfd.
+ * Thread 2 calls epoll with a timeout of 11ms.
+ * Thread 3 calls epoll with a timeout of -1.
+ *
+ * The eventfd write by Thread 1 should either wakeup Thread 2
+ * or Thread 3. If it wakes up Thread 2, Thread 2 writes on the
+ * eventfd to wake up Thread 3.
+ *
+ * If no events are missed, all three threads should eventually
+ * be joinable.
+ */
+ ASSERT_EQ(pthread_create(&threads[0], NULL,
+ epoll61_write_eventfd, &ctx), 0);
+ ASSERT_EQ(pthread_create(&threads[1], NULL,
+ epoll61_epoll_with_timeout, &ctx), 0);
+ ASSERT_EQ(pthread_create(&threads[2], NULL,
+ epoll61_blocking_epoll, &ctx), 0);
+
+ for (n = 0; n < ARRAY_SIZE(threads); ++n)
+ ASSERT_EQ(pthread_join(threads[n], NULL), 0);
+ }
+
+ close(ctx.epfd);
+ close(ctx.evfd);
+}
+
TEST_HARNESS_MAIN
echo 0 > events/enable
echo > dynamic_events
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
echo "p:myevent1 $PLACE" >> dynamic_events
echo "r:myevent2 $PLACE" >> dynamic_events
echo 0 > events/enable
echo > dynamic_events
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
setup_events() {
echo "p:myevent1 $PLACE" >> dynamic_events
echo 0 > events/enable
echo > dynamic_events
-PLACE=kernel_clone
+PLACE=$FUNCTION_FORK
setup_events() {
echo "p:myevent1 $PLACE" >> dynamic_events
disable_tracing
echo do_execve* > set_ftrace_filter
- echo *do_fork >> set_ftrace_filter
+ echo $FUNCTION_FORK >> set_ftrace_filter
echo $PID > set_ftrace_notrace_pid
echo function > current_tracer
disable_tracing
echo do_execve* > set_ftrace_filter
- echo *do_fork >> set_ftrace_filter
+ echo $FUNCTION_FORK >> set_ftrace_filter
echo $PID > set_ftrace_pid
echo function > current_tracer
# requires: set_ftrace_filter
# flags: instance
-echo kernel_clone:stacktrace >> set_ftrace_filter
+echo $FUNCTION_FORK:stacktrace >> set_ftrace_filter
-grep -q "kernel_clone:stacktrace:unlimited" set_ftrace_filter
+grep -q "$FUNCTION_FORK:stacktrace:unlimited" set_ftrace_filter
(echo "forked"; sleep 1)
ping $LOCALHOST -c 1 || sleep .001 || usleep 1 || sleep 1
}
+# The fork function in the kernel was renamed from "_do_fork" to
+# "kernel_fork". As older tests should still work with older kernels
+# as well as newer kernels, check which version of fork is used on this
+# kernel so that the tests can use the fork function for the running kernel.
+FUNCTION_FORK=`(if grep '\bkernel_clone\b' /proc/kallsyms > /dev/null; then
+ echo kernel_clone; else echo '_do_fork'; fi)`
+
# Since probe event command may include backslash, explicitly use printf "%s"
# to NOT interpret it.
ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file
# description: Kprobe dynamic event - adding and removing
# requires: kprobe_events
-echo p:myevent kernel_clone > kprobe_events
+echo p:myevent $FUNCTION_FORK > kprobe_events
grep myevent kprobe_events
test -d events/kprobes/myevent
echo > kprobe_events
# description: Kprobe dynamic event - busy event check
# requires: kprobe_events
-echo p:myevent kernel_clone > kprobe_events
+echo p:myevent $FUNCTION_FORK > kprobe_events
test -d events/kprobes/myevent
echo 1 > events/kprobes/myevent/enable
echo > kprobe_events && exit_fail # this must fail
# description: Kprobe dynamic event with arguments
# requires: kprobe_events
-echo 'p:testprobe kernel_clone $stack $stack0 +0($stack)' > kprobe_events
+echo "p:testprobe $FUNCTION_FORK \$stack \$stack0 +0(\$stack)" > kprobe_events
grep testprobe kprobe_events | grep -q 'arg1=\$stack arg2=\$stack0 arg3=+0(\$stack)'
test -d events/kprobes/testprobe
echo 1 > events/kprobes/testprobe/enable
( echo "forked")
-grep testprobe trace | grep 'kernel_clone' | \
+grep testprobe trace | grep "$FUNCTION_FORK" | \
grep -q 'arg1=0x[[:xdigit:]]* arg2=0x[[:xdigit:]]* arg3=0x[[:xdigit:]]*$'
echo 0 > events/kprobes/testprobe/enable
grep -A1 "fetcharg:" README | grep -q "\$comm" || exit_unsupported # this is too old
-echo 'p:testprobe kernel_clone comm=$comm ' > kprobe_events
+echo "p:testprobe $FUNCTION_FORK comm=\$comm " > kprobe_events
grep testprobe kprobe_events | grep -q 'comm=$comm'
test -d events/kprobes/testprobe
: "Test get argument (1)"
echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string" > kprobe_events
echo 1 > events/kprobes/testprobe/enable
-echo "p:test kernel_clone" >> kprobe_events
+echo "p:test $FUNCTION_FORK" >> kprobe_events
grep -qe "testprobe.* arg1=\"test\"" trace
echo 0 > events/kprobes/testprobe/enable
: "Test get argument (2)"
echo "p:testprobe tracefs_create_dir arg1=+0(${ARG1}):string arg2=+0(${ARG1}):string" > kprobe_events
echo 1 > events/kprobes/testprobe/enable
-echo "p:test kernel_clone" >> kprobe_events
+echo "p:test $FUNCTION_FORK" >> kprobe_events
grep -qe "testprobe.* arg1=\"test\" arg2=\"test\"" trace
fi
: "Test get basic types symbol argument"
-echo "p:testprobe_u kernel_clone arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
-echo "p:testprobe_s kernel_clone arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
+echo "p:testprobe_u $FUNCTION_FORK arg1=@linux_proc_banner:u64 arg2=@linux_proc_banner:u32 arg3=@linux_proc_banner:u16 arg4=@linux_proc_banner:u8" > kprobe_events
+echo "p:testprobe_s $FUNCTION_FORK arg1=@linux_proc_banner:s64 arg2=@linux_proc_banner:s32 arg3=@linux_proc_banner:s16 arg4=@linux_proc_banner:s8" >> kprobe_events
if grep -q "x8/16/32/64" README; then
- echo "p:testprobe_x kernel_clone arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
+ echo "p:testprobe_x $FUNCTION_FORK arg1=@linux_proc_banner:x64 arg2=@linux_proc_banner:x32 arg3=@linux_proc_banner:x16 arg4=@linux_proc_banner:x8" >> kprobe_events
fi
-echo "p:testprobe_bf kernel_clone arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
+echo "p:testprobe_bf $FUNCTION_FORK arg1=@linux_proc_banner:b8@4/32" >> kprobe_events
echo 1 > events/kprobes/enable
(echo "forked")
echo 0 > events/kprobes/enable
grep "testprobe_bf:.* arg1=.*" trace
: "Test get string symbol argument"
-echo "p:testprobe_str kernel_clone arg1=@linux_proc_banner:string" > kprobe_events
+echo "p:testprobe_str $FUNCTION_FORK arg1=@linux_proc_banner:string" > kprobe_events
echo 1 > events/kprobes/enable
(echo "forked")
echo 0 > events/kprobes/enable
# requires: kprobe_events "x8/16/32/64":README
gen_event() { # Bitsize
- echo "p:testprobe kernel_clone \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
+ echo "p:testprobe $FUNCTION_FORK \$stack0:s$1 \$stack0:u$1 \$stack0:x$1 \$stack0:b4@4/$1"
}
check_types() { # s-type u-type x-type bf-type width
:;: "user-memory access syntax and ustring working on user memory";:
echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \
> kprobe_events
+echo 'p:myevent2 do_sys_openat2 path=+0($arg2):ustring path2=+u0($arg2):string' \
+ >> kprobe_events
grep myevent kprobe_events | \
grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string'
echo 1 > events/kprobes/myevent/enable
+echo 1 > events/kprobes/myevent2/enable
echo > /dev/null
echo 0 > events/kprobes/myevent/enable
+echo 0 > events/kprobes/myevent2/enable
grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"'
# prepare
echo nop > current_tracer
-echo kernel_clone > set_ftrace_filter
-echo 'p:testprobe kernel_clone' > kprobe_events
+echo $FUNCTION_FORK > set_ftrace_filter
+echo "p:testprobe $FUNCTION_FORK" > kprobe_events
# kprobe on / ftrace off
echo 1 > events/kprobes/testprobe/enable
echo > trace
( echo "forked")
grep testprobe trace
-! grep 'kernel_clone <-' trace
+! grep "$FUNCTION_FORK <-" trace
# kprobe on / ftrace on
echo function > current_tracer
echo > trace
( echo "forked")
grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
# kprobe off / ftrace on
echo 0 > events/kprobes/testprobe/enable
echo > trace
( echo "forked")
! grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
# kprobe on / ftrace on
echo 1 > events/kprobes/testprobe/enable
echo > trace
( echo "forked")
grep testprobe trace
-grep 'kernel_clone <-' trace
+grep "$FUNCTION_FORK <-" trace
# kprobe on / ftrace off
echo nop > current_tracer
echo > trace
( echo "forked")
grep testprobe trace
-! grep 'kernel_clone <-' trace
+! grep "$FUNCTION_FORK <-" trace
# requires: kprobe_events "Create/append/":README
# Choose 2 symbols for target
-SYM1=kernel_clone
+SYM1=$FUNCTION_FORK
SYM2=do_exit
EVENT_NAME=kprobes/testevent
# multiprobe errors
if grep -q "Create/append/" README && grep -q "imm-value" README; then
-echo 'p:kprobes/testevent kernel_clone' > kprobe_events
+echo "p:kprobes/testevent $FUNCTION_FORK" > kprobe_events
check_error '^r:kprobes/testevent do_exit' # DIFF_PROBE_TYPE
# Explicitly use printf "%s" to not interpret \1
-printf "%s" 'p:kprobes/testevent kernel_clone abcd=\1' > kprobe_events
-check_error 'p:kprobes/testevent kernel_clone ^bcd=\1' # DIFF_ARG_TYPE
-check_error 'p:kprobes/testevent kernel_clone ^abcd=\1:u8' # DIFF_ARG_TYPE
-check_error 'p:kprobes/testevent kernel_clone ^abcd=\"foo"' # DIFF_ARG_TYPE
-check_error '^p:kprobes/testevent kernel_clone abcd=\1' # SAME_PROBE
+printf "%s" "p:kprobes/testevent $FUNCTION_FORK abcd=\\1" > kprobe_events
+check_error "p:kprobes/testevent $FUNCTION_FORK ^bcd=\\1" # DIFF_ARG_TYPE
+check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\1:u8" # DIFF_ARG_TYPE
+check_error "p:kprobes/testevent $FUNCTION_FORK ^abcd=\\\"foo\"" # DIFF_ARG_TYPE
+check_error "^p:kprobes/testevent $FUNCTION_FORK abcd=\\1" # SAME_PROBE
fi
# %return suffix errors
# requires: kprobe_events
# Add new kretprobe event
-echo 'r:testprobe2 kernel_clone $retval' > kprobe_events
+echo "r:testprobe2 $FUNCTION_FORK \$retval" > kprobe_events
grep testprobe2 kprobe_events | grep -q 'arg1=\$retval'
test -d events/kprobes/testprobe2
echo 1 > events/kprobes/testprobe2/enable
( echo "forked")
-cat trace | grep testprobe2 | grep -q '<- kernel_clone'
+cat trace | grep testprobe2 | grep -q "<- $FUNCTION_FORK"
echo 0 > events/kprobes/testprobe2/enable
echo '-:testprobe2' >> kprobe_events
# requires: kprobe_events
! grep -q 'myevent' kprobe_profile
-echo p:myevent kernel_clone > kprobe_events
+echo "p:myevent $FUNCTION_FORK" > kprobe_events
grep -q 'myevent[[:space:]]*0[[:space:]]*0$' kprobe_profile
echo 1 > events/kprobes/myevent/enable
( echo "forked" )
snprintf(_metadata->results->reason, \
sizeof(_metadata->results->reason), fmt, ##__VA_ARGS__); \
if (TH_LOG_ENABLED) { \
- fprintf(TH_LOG_STREAM, "# SKIP %s\n", \
+ fprintf(TH_LOG_STREAM, "# SKIP %s\n", \
_metadata->results->reason); \
} \
_metadata->passed = 1; \
*/
/**
- * ASSERT_EQ(expected, seen)
+ * ASSERT_EQ()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, ==, 1)
/**
- * ASSERT_NE(expected, seen)
+ * ASSERT_NE()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, !=, 1)
/**
- * ASSERT_LT(expected, seen)
+ * ASSERT_LT()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, <, 1)
/**
- * ASSERT_LE(expected, seen)
+ * ASSERT_LE()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, <=, 1)
/**
- * ASSERT_GT(expected, seen)
+ * ASSERT_GT()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, >, 1)
/**
- * ASSERT_GE(expected, seen)
+ * ASSERT_GE()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, >=, 1)
/**
- * ASSERT_NULL(seen)
+ * ASSERT_NULL()
*
* @seen: measured value
*
__EXPECT(NULL, "NULL", seen, #seen, ==, 1)
/**
- * ASSERT_TRUE(seen)
+ * ASSERT_TRUE()
*
* @seen: measured value
*
__EXPECT(0, "0", seen, #seen, !=, 1)
/**
- * ASSERT_FALSE(seen)
+ * ASSERT_FALSE()
*
* @seen: measured value
*
__EXPECT(0, "0", seen, #seen, ==, 1)
/**
- * ASSERT_STREQ(expected, seen)
+ * ASSERT_STREQ()
*
* @expected: expected value
* @seen: measured value
__EXPECT_STR(expected, seen, ==, 1)
/**
- * ASSERT_STRNE(expected, seen)
+ * ASSERT_STRNE()
*
* @expected: expected value
* @seen: measured value
__EXPECT_STR(expected, seen, !=, 1)
/**
- * EXPECT_EQ(expected, seen)
+ * EXPECT_EQ()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, ==, 0)
/**
- * EXPECT_NE(expected, seen)
+ * EXPECT_NE()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, !=, 0)
/**
- * EXPECT_LT(expected, seen)
+ * EXPECT_LT()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, <, 0)
/**
- * EXPECT_LE(expected, seen)
+ * EXPECT_LE()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, <=, 0)
/**
- * EXPECT_GT(expected, seen)
+ * EXPECT_GT()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, >, 0)
/**
- * EXPECT_GE(expected, seen)
+ * EXPECT_GE()
*
* @expected: expected value
* @seen: measured value
__EXPECT(expected, #expected, seen, #seen, >=, 0)
/**
- * EXPECT_NULL(seen)
+ * EXPECT_NULL()
*
* @seen: measured value
*
__EXPECT(NULL, "NULL", seen, #seen, ==, 0)
/**
- * EXPECT_TRUE(seen)
+ * EXPECT_TRUE()
*
* @seen: measured value
*
__EXPECT(0, "0", seen, #seen, !=, 0)
/**
- * EXPECT_FALSE(seen)
+ * EXPECT_FALSE()
*
* @seen: measured value
*
__EXPECT(0, "0", seen, #seen, ==, 0)
/**
- * EXPECT_STREQ(expected, seen)
+ * EXPECT_STREQ()
*
* @expected: expected value
* @seen: measured value
__EXPECT_STR(expected, seen, ==, 0)
/**
- * EXPECT_STRNE(expected, seen)
+ * EXPECT_STRNE()
*
* @expected: expected value
* @seen: measured value
# SPDX-License-Identifier: GPL-2.0-only
+/aarch64/get-reg-list
+/aarch64/get-reg-list-sve
/s390x/memop
/s390x/resets
/s390x/sync_regs_test
/x86_64/cr4_cpuid_sync_test
/x86_64/debug_regs
/x86_64/evmcs_test
+/x86_64/kvm_pv_test
/x86_64/hyperv_cpuid
/x86_64/mmio_warning_test
/x86_64/platform_info_test
/x86_64/vmx_preemption_timer_test
/x86_64/svm_vmcall_test
/x86_64/sync_regs_test
+/x86_64/vmx_apic_access_test
/x86_64/vmx_close_while_nested_test
/x86_64/vmx_dirty_log_test
/x86_64/vmx_set_nested_state_test
/clear_dirty_log_test
/demand_paging_test
/dirty_log_test
+/dirty_log_perf_test
/kvm_create_max_vcpus
/set_memory_region_test
/steal_time
endif
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
+TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
-TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
TEST_GEN_PROGS_x86_64 += set_memory_region_test
TEST_GEN_PROGS_x86_64 += steal_time
-TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
TEST_GEN_PROGS_aarch64 += demand_paging_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
include ../lib.mk
STATIC_LIBS := $(OUTPUT)/libkvm.a
-LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_C := $(filter %.c,$(LIBKVM))
+LIBKVM_S := $(filter %.S,$(LIBKVM))
+LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
+LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
+EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
+
+x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
+ $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
-$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
$(AR) crs $@ $^
x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define REG_LIST_SVE
+#include "get-reg-list.c"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Check for KVM_GET_REG_LIST regressions.
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ *
+ * When attempting to migrate from a host with an older kernel to a host
+ * with a newer kernel we allow the newer kernel on the destination to
+ * list new registers with get-reg-list. We assume they'll be unused, at
+ * least until the guest reboots, and so they're relatively harmless.
+ * However, if the destination host with the newer kernel is missing
+ * registers which the source host with the older kernel has, then that's
+ * a regression in get-reg-list. This test checks for that regression by
+ * checking the current list against a blessed list. We should never have
+ * missing registers, but if new ones appear then they can probably be
+ * added to the blessed list. A completely new blessed list can be created
+ * by running the test with the --list command line argument.
+ *
+ * Note, the blessed list should be created from the oldest possible
+ * kernel. We can't go older than v4.15, though, because that's the first
+ * release to expose the ID system registers in KVM_GET_REG_LIST, see
+ * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features
+ * from guests"). Also, one must use the --core-reg-fixup command line
+ * option when running on an older kernel that doesn't include df205b5c6328
+ * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST")
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "test_util.h"
+#include "processor.h"
+
+#ifdef REG_LIST_SVE
+#define reg_list_sve() (true)
+#else
+#define reg_list_sve() (false)
+#endif
+
+#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK)
+
+#define for_each_reg(i) \
+ for ((i) = 0; (i) < reg_list->n; ++(i))
+
+#define for_each_missing_reg(i) \
+ for ((i) = 0; (i) < blessed_n; ++(i)) \
+ if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i]))
+
+#define for_each_new_reg(i) \
+ for ((i) = 0; (i) < reg_list->n; ++(i)) \
+ if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i]))
+
+
+static struct kvm_reg_list *reg_list;
+
+static __u64 base_regs[], vregs[], sve_regs[], rejects_set[];
+static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n;
+static __u64 *blessed_reg, blessed_n;
+
+static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg)
+{
+ int i;
+
+ for (i = 0; i < nr_regs; ++i)
+ if (reg == regs[i])
+ return true;
+ return false;
+}
+
+static const char *str_with_index(const char *template, __u64 index)
+{
+ char *str, *p;
+ int n;
+
+ str = strdup(template);
+ p = strstr(str, "##");
+ n = sprintf(p, "%lld", index);
+ strcat(p + n, strstr(template, "##") + 2);
+
+ return (const char *)str;
+}
+
+#define CORE_REGS_XX_NR_WORDS 2
+#define CORE_SPSR_XX_NR_WORDS 2
+#define CORE_FPREGS_XX_NR_WORDS 4
+
+static const char *core_id_to_str(__u64 id)
+{
+ __u64 core_off = id & ~REG_MASK, idx;
+
+ /*
+ * core_off is the offset into struct kvm_regs
+ */
+ switch (core_off) {
+ case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+ KVM_REG_ARM_CORE_REG(regs.regs[30]):
+ idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS;
+ TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx);
+ return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx);
+ case KVM_REG_ARM_CORE_REG(regs.sp):
+ return "KVM_REG_ARM_CORE_REG(regs.sp)";
+ case KVM_REG_ARM_CORE_REG(regs.pc):
+ return "KVM_REG_ARM_CORE_REG(regs.pc)";
+ case KVM_REG_ARM_CORE_REG(regs.pstate):
+ return "KVM_REG_ARM_CORE_REG(regs.pstate)";
+ case KVM_REG_ARM_CORE_REG(sp_el1):
+ return "KVM_REG_ARM_CORE_REG(sp_el1)";
+ case KVM_REG_ARM_CORE_REG(elr_el1):
+ return "KVM_REG_ARM_CORE_REG(elr_el1)";
+ case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+ KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+ idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS;
+ TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx);
+ return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx);
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS;
+ TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx);
+ return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx);
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)";
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)";
+ }
+
+ TEST_FAIL("Unknown core reg id: 0x%llx", id);
+ return NULL;
+}
+
+static const char *sve_id_to_str(__u64 id)
+{
+ __u64 sve_off, n, i;
+
+ if (id == KVM_REG_ARM64_SVE_VLS)
+ return "KVM_REG_ARM64_SVE_VLS";
+
+ sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1));
+ i = id & (KVM_ARM64_SVE_MAX_SLICES - 1);
+
+ TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id);
+
+ switch (sve_off) {
+ case KVM_REG_ARM64_SVE_ZREG_BASE ...
+ KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1:
+ n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1);
+ TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0),
+ "Unexpected bits set in SVE ZREG id: 0x%llx", id);
+ return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n);
+ case KVM_REG_ARM64_SVE_PREG_BASE ...
+ KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1:
+ n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1);
+ TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0),
+ "Unexpected bits set in SVE PREG id: 0x%llx", id);
+ return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n);
+ case KVM_REG_ARM64_SVE_FFR_BASE:
+ TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0),
+ "Unexpected bits set in SVE FFR id: 0x%llx", id);
+ return "KVM_REG_ARM64_SVE_FFR(0)";
+ }
+
+ return NULL;
+}
+
+static void print_reg(__u64 id)
+{
+ unsigned op0, op1, crn, crm, op2;
+ const char *reg_size = NULL;
+
+ TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64,
+ "KVM_REG_ARM64 missing in reg id: 0x%llx", id);
+
+ switch (id & KVM_REG_SIZE_MASK) {
+ case KVM_REG_SIZE_U8:
+ reg_size = "KVM_REG_SIZE_U8";
+ break;
+ case KVM_REG_SIZE_U16:
+ reg_size = "KVM_REG_SIZE_U16";
+ break;
+ case KVM_REG_SIZE_U32:
+ reg_size = "KVM_REG_SIZE_U32";
+ break;
+ case KVM_REG_SIZE_U64:
+ reg_size = "KVM_REG_SIZE_U64";
+ break;
+ case KVM_REG_SIZE_U128:
+ reg_size = "KVM_REG_SIZE_U128";
+ break;
+ case KVM_REG_SIZE_U256:
+ reg_size = "KVM_REG_SIZE_U256";
+ break;
+ case KVM_REG_SIZE_U512:
+ reg_size = "KVM_REG_SIZE_U512";
+ break;
+ case KVM_REG_SIZE_U1024:
+ reg_size = "KVM_REG_SIZE_U1024";
+ break;
+ case KVM_REG_SIZE_U2048:
+ reg_size = "KVM_REG_SIZE_U2048";
+ break;
+ default:
+ TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx",
+ (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id);
+ }
+
+ switch (id & KVM_REG_ARM_COPROC_MASK) {
+ case KVM_REG_ARM_CORE:
+ printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id));
+ break;
+ case KVM_REG_ARM_DEMUX:
+ TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)),
+ "Unexpected bits set in DEMUX reg id: 0x%llx", id);
+ printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n",
+ reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK);
+ break;
+ case KVM_REG_ARM64_SYSREG:
+ op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT;
+ op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT;
+ crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT;
+ crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT;
+ op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT;
+ TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2),
+ "Unexpected bits set in SYSREG reg id: 0x%llx", id);
+ printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2);
+ break;
+ case KVM_REG_ARM_FW:
+ TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff),
+ "Unexpected bits set in FW reg id: 0x%llx", id);
+ printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff);
+ break;
+ case KVM_REG_ARM64_SVE:
+ if (reg_list_sve())
+ printf("\t%s,\n", sve_id_to_str(id));
+ else
+ TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id);
+ break;
+ default:
+ TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx",
+ (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id);
+ }
+}
+
+/*
+ * Older kernels listed each 32-bit word of CORE registers separately.
+ * For 64 and 128-bit registers we need to ignore the extra words. We
+ * also need to fixup the sizes, because the older kernels stated all
+ * registers were 64-bit, even when they weren't.
+ */
+static void core_reg_fixup(void)
+{
+ struct kvm_reg_list *tmp;
+ __u64 id, core_off;
+ int i;
+
+ tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64));
+
+ for (i = 0; i < reg_list->n; ++i) {
+ id = reg_list->reg[i];
+
+ if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) {
+ tmp->reg[tmp->n++] = id;
+ continue;
+ }
+
+ core_off = id & ~REG_MASK;
+
+ switch (core_off) {
+ case 0x52: case 0xd2: case 0xd6:
+ /*
+ * These offsets are pointing at padding.
+ * We need to ignore them too.
+ */
+ continue;
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ if (core_off & 3)
+ continue;
+ id &= ~KVM_REG_SIZE_MASK;
+ id |= KVM_REG_SIZE_U128;
+ tmp->reg[tmp->n++] = id;
+ continue;
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ id &= ~KVM_REG_SIZE_MASK;
+ id |= KVM_REG_SIZE_U32;
+ tmp->reg[tmp->n++] = id;
+ continue;
+ default:
+ if (core_off & 1)
+ continue;
+ tmp->reg[tmp->n++] = id;
+ break;
+ }
+ }
+
+ free(reg_list);
+ reg_list = tmp;
+}
+
+static void prepare_vcpu_init(struct kvm_vcpu_init *init)
+{
+ if (reg_list_sve())
+ init->features[0] |= 1 << KVM_ARM_VCPU_SVE;
+}
+
+static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ int feature;
+
+ if (reg_list_sve()) {
+ feature = KVM_ARM_VCPU_SVE;
+ vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature);
+ }
+}
+
+static void check_supported(void)
+{
+ if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) {
+ fprintf(stderr, "SVE not available, skipping tests\n");
+ exit(KSFT_SKIP);
+ }
+}
+
+int main(int ac, char **av)
+{
+ struct kvm_vcpu_init init = { .target = -1, };
+ int new_regs = 0, missing_regs = 0, i;
+ int failed_get = 0, failed_set = 0, failed_reject = 0;
+ bool print_list = false, fixup_core_regs = false;
+ struct kvm_vm *vm;
+ __u64 *vec_regs;
+
+ check_supported();
+
+ for (i = 1; i < ac; ++i) {
+ if (strcmp(av[i], "--core-reg-fixup") == 0)
+ fixup_core_regs = true;
+ else if (strcmp(av[i], "--list") == 0)
+ print_list = true;
+ else
+ fprintf(stderr, "Ignoring unknown option: %s\n", av[i]);
+ }
+
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+ prepare_vcpu_init(&init);
+ aarch64_vcpu_add_default(vm, 0, &init, NULL);
+ finalize_vcpu(vm, 0);
+
+ reg_list = vcpu_get_reg_list(vm, 0);
+
+ if (fixup_core_regs)
+ core_reg_fixup();
+
+ if (print_list) {
+ putchar('\n');
+ for_each_reg(i)
+ print_reg(reg_list->reg[i]);
+ putchar('\n');
+ return 0;
+ }
+
+ /*
+ * We only test that we can get the register and then write back the
+ * same value. Some registers may allow other values to be written
+ * back, but others only allow some bits to be changed, and at least
+ * for ID registers set will fail if the value does not exactly match
+ * what was returned by get. If registers that allow other values to
+ * be written need to have the other values tested, then we should
+ * create a new set of tests for those in a new independent test
+ * executable.
+ */
+ for_each_reg(i) {
+ uint8_t addr[2048 / 8];
+ struct kvm_one_reg reg = {
+ .id = reg_list->reg[i],
+ .addr = (__u64)&addr,
+ };
+ int ret;
+
+ ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®);
+ if (ret) {
+ puts("Failed to get ");
+ print_reg(reg.id);
+ putchar('\n');
+ ++failed_get;
+ }
+
+ /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */
+ if (find_reg(rejects_set, rejects_set_n, reg.id)) {
+ ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®);
+ if (ret != -1 || errno != EPERM) {
+ printf("Failed to reject (ret=%d, errno=%d) ", ret, errno);
+ print_reg(reg.id);
+ putchar('\n');
+ ++failed_reject;
+ }
+ continue;
+ }
+
+ ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®);
+ if (ret) {
+ puts("Failed to set ");
+ print_reg(reg.id);
+ putchar('\n');
+ ++failed_set;
+ }
+ }
+
+ if (reg_list_sve()) {
+ blessed_n = base_regs_n + sve_regs_n;
+ vec_regs = sve_regs;
+ } else {
+ blessed_n = base_regs_n + vregs_n;
+ vec_regs = vregs;
+ }
+
+ blessed_reg = calloc(blessed_n, sizeof(__u64));
+ for (i = 0; i < base_regs_n; ++i)
+ blessed_reg[i] = base_regs[i];
+ for (i = 0; i < blessed_n - base_regs_n; ++i)
+ blessed_reg[base_regs_n + i] = vec_regs[i];
+
+ for_each_new_reg(i)
+ ++new_regs;
+
+ for_each_missing_reg(i)
+ ++missing_regs;
+
+ if (new_regs || missing_regs) {
+ printf("Number blessed registers: %5lld\n", blessed_n);
+ printf("Number registers: %5lld\n", reg_list->n);
+ }
+
+ if (new_regs) {
+ printf("\nThere are %d new registers.\n"
+ "Consider adding them to the blessed reg "
+ "list with the following lines:\n\n", new_regs);
+ for_each_new_reg(i)
+ print_reg(reg_list->reg[i]);
+ putchar('\n');
+ }
+
+ if (missing_regs) {
+ printf("\nThere are %d missing registers.\n"
+ "The following lines are missing registers:\n\n", missing_regs);
+ for_each_missing_reg(i)
+ print_reg(blessed_reg[i]);
+ putchar('\n');
+ }
+
+ TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject,
+ "There are %d missing registers; "
+ "%d registers failed get; %d registers failed set; %d registers failed reject",
+ missing_regs, failed_get, failed_set, failed_reject);
+
+ return 0;
+}
+
+/*
+ * The current blessed list was primed with the output of kernel version
+ * v4.15 with --core-reg-fixup and then later updated with new registers.
+ */
+static __u64 base_regs[] = {
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
+ KVM_REG_ARM_FW_REG(0),
+ KVM_REG_ARM_FW_REG(1),
+ KVM_REG_ARM_FW_REG(2),
+ ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */
+ ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */
+ ARM64_SYS_REG(3, 3, 14, 0, 2),
+ ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */
+ ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */
+ ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */
+ ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */
+ ARM64_SYS_REG(2, 0, 0, 0, 4),
+ ARM64_SYS_REG(2, 0, 0, 0, 5),
+ ARM64_SYS_REG(2, 0, 0, 0, 6),
+ ARM64_SYS_REG(2, 0, 0, 0, 7),
+ ARM64_SYS_REG(2, 0, 0, 1, 4),
+ ARM64_SYS_REG(2, 0, 0, 1, 5),
+ ARM64_SYS_REG(2, 0, 0, 1, 6),
+ ARM64_SYS_REG(2, 0, 0, 1, 7),
+ ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */
+ ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */
+ ARM64_SYS_REG(2, 0, 0, 2, 4),
+ ARM64_SYS_REG(2, 0, 0, 2, 5),
+ ARM64_SYS_REG(2, 0, 0, 2, 6),
+ ARM64_SYS_REG(2, 0, 0, 2, 7),
+ ARM64_SYS_REG(2, 0, 0, 3, 4),
+ ARM64_SYS_REG(2, 0, 0, 3, 5),
+ ARM64_SYS_REG(2, 0, 0, 3, 6),
+ ARM64_SYS_REG(2, 0, 0, 3, 7),
+ ARM64_SYS_REG(2, 0, 0, 4, 4),
+ ARM64_SYS_REG(2, 0, 0, 4, 5),
+ ARM64_SYS_REG(2, 0, 0, 4, 6),
+ ARM64_SYS_REG(2, 0, 0, 4, 7),
+ ARM64_SYS_REG(2, 0, 0, 5, 4),
+ ARM64_SYS_REG(2, 0, 0, 5, 5),
+ ARM64_SYS_REG(2, 0, 0, 5, 6),
+ ARM64_SYS_REG(2, 0, 0, 5, 7),
+ ARM64_SYS_REG(2, 0, 0, 6, 4),
+ ARM64_SYS_REG(2, 0, 0, 6, 5),
+ ARM64_SYS_REG(2, 0, 0, 6, 6),
+ ARM64_SYS_REG(2, 0, 0, 6, 7),
+ ARM64_SYS_REG(2, 0, 0, 7, 4),
+ ARM64_SYS_REG(2, 0, 0, 7, 5),
+ ARM64_SYS_REG(2, 0, 0, 7, 6),
+ ARM64_SYS_REG(2, 0, 0, 7, 7),
+ ARM64_SYS_REG(2, 0, 0, 8, 4),
+ ARM64_SYS_REG(2, 0, 0, 8, 5),
+ ARM64_SYS_REG(2, 0, 0, 8, 6),
+ ARM64_SYS_REG(2, 0, 0, 8, 7),
+ ARM64_SYS_REG(2, 0, 0, 9, 4),
+ ARM64_SYS_REG(2, 0, 0, 9, 5),
+ ARM64_SYS_REG(2, 0, 0, 9, 6),
+ ARM64_SYS_REG(2, 0, 0, 9, 7),
+ ARM64_SYS_REG(2, 0, 0, 10, 4),
+ ARM64_SYS_REG(2, 0, 0, 10, 5),
+ ARM64_SYS_REG(2, 0, 0, 10, 6),
+ ARM64_SYS_REG(2, 0, 0, 10, 7),
+ ARM64_SYS_REG(2, 0, 0, 11, 4),
+ ARM64_SYS_REG(2, 0, 0, 11, 5),
+ ARM64_SYS_REG(2, 0, 0, 11, 6),
+ ARM64_SYS_REG(2, 0, 0, 11, 7),
+ ARM64_SYS_REG(2, 0, 0, 12, 4),
+ ARM64_SYS_REG(2, 0, 0, 12, 5),
+ ARM64_SYS_REG(2, 0, 0, 12, 6),
+ ARM64_SYS_REG(2, 0, 0, 12, 7),
+ ARM64_SYS_REG(2, 0, 0, 13, 4),
+ ARM64_SYS_REG(2, 0, 0, 13, 5),
+ ARM64_SYS_REG(2, 0, 0, 13, 6),
+ ARM64_SYS_REG(2, 0, 0, 13, 7),
+ ARM64_SYS_REG(2, 0, 0, 14, 4),
+ ARM64_SYS_REG(2, 0, 0, 14, 5),
+ ARM64_SYS_REG(2, 0, 0, 14, 6),
+ ARM64_SYS_REG(2, 0, 0, 14, 7),
+ ARM64_SYS_REG(2, 0, 0, 15, 4),
+ ARM64_SYS_REG(2, 0, 0, 15, 5),
+ ARM64_SYS_REG(2, 0, 0, 15, 6),
+ ARM64_SYS_REG(2, 0, 0, 15, 7),
+ ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */
+ ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 3),
+ ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 3, 7),
+ ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 4, 2),
+ ARM64_SYS_REG(3, 0, 0, 4, 3),
+ ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 4, 5),
+ ARM64_SYS_REG(3, 0, 0, 4, 6),
+ ARM64_SYS_REG(3, 0, 0, 4, 7),
+ ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 2),
+ ARM64_SYS_REG(3, 0, 0, 5, 3),
+ ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 5, 6),
+ ARM64_SYS_REG(3, 0, 0, 5, 7),
+ ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 6, 2),
+ ARM64_SYS_REG(3, 0, 0, 6, 3),
+ ARM64_SYS_REG(3, 0, 0, 6, 4),
+ ARM64_SYS_REG(3, 0, 0, 6, 5),
+ ARM64_SYS_REG(3, 0, 0, 6, 6),
+ ARM64_SYS_REG(3, 0, 0, 6, 7),
+ ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */
+ ARM64_SYS_REG(3, 0, 0, 7, 3),
+ ARM64_SYS_REG(3, 0, 0, 7, 4),
+ ARM64_SYS_REG(3, 0, 0, 7, 5),
+ ARM64_SYS_REG(3, 0, 0, 7, 6),
+ ARM64_SYS_REG(3, 0, 0, 7, 7),
+ ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */
+ ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */
+ ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */
+ ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */
+ ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */
+ ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */
+ ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */
+ ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */
+ ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */
+ ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */
+ ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */
+ ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */
+ ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */
+ ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */
+ ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */
+ ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */
+ ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */
+ ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */
+ ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */
+ ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */
+ ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */
+ ARM64_SYS_REG(3, 3, 14, 8, 0),
+ ARM64_SYS_REG(3, 3, 14, 8, 1),
+ ARM64_SYS_REG(3, 3, 14, 8, 2),
+ ARM64_SYS_REG(3, 3, 14, 8, 3),
+ ARM64_SYS_REG(3, 3, 14, 8, 4),
+ ARM64_SYS_REG(3, 3, 14, 8, 5),
+ ARM64_SYS_REG(3, 3, 14, 8, 6),
+ ARM64_SYS_REG(3, 3, 14, 8, 7),
+ ARM64_SYS_REG(3, 3, 14, 9, 0),
+ ARM64_SYS_REG(3, 3, 14, 9, 1),
+ ARM64_SYS_REG(3, 3, 14, 9, 2),
+ ARM64_SYS_REG(3, 3, 14, 9, 3),
+ ARM64_SYS_REG(3, 3, 14, 9, 4),
+ ARM64_SYS_REG(3, 3, 14, 9, 5),
+ ARM64_SYS_REG(3, 3, 14, 9, 6),
+ ARM64_SYS_REG(3, 3, 14, 9, 7),
+ ARM64_SYS_REG(3, 3, 14, 10, 0),
+ ARM64_SYS_REG(3, 3, 14, 10, 1),
+ ARM64_SYS_REG(3, 3, 14, 10, 2),
+ ARM64_SYS_REG(3, 3, 14, 10, 3),
+ ARM64_SYS_REG(3, 3, 14, 10, 4),
+ ARM64_SYS_REG(3, 3, 14, 10, 5),
+ ARM64_SYS_REG(3, 3, 14, 10, 6),
+ ARM64_SYS_REG(3, 3, 14, 10, 7),
+ ARM64_SYS_REG(3, 3, 14, 11, 0),
+ ARM64_SYS_REG(3, 3, 14, 11, 1),
+ ARM64_SYS_REG(3, 3, 14, 11, 2),
+ ARM64_SYS_REG(3, 3, 14, 11, 3),
+ ARM64_SYS_REG(3, 3, 14, 11, 4),
+ ARM64_SYS_REG(3, 3, 14, 11, 5),
+ ARM64_SYS_REG(3, 3, 14, 11, 6),
+ ARM64_SYS_REG(3, 3, 14, 12, 0),
+ ARM64_SYS_REG(3, 3, 14, 12, 1),
+ ARM64_SYS_REG(3, 3, 14, 12, 2),
+ ARM64_SYS_REG(3, 3, 14, 12, 3),
+ ARM64_SYS_REG(3, 3, 14, 12, 4),
+ ARM64_SYS_REG(3, 3, 14, 12, 5),
+ ARM64_SYS_REG(3, 3, 14, 12, 6),
+ ARM64_SYS_REG(3, 3, 14, 12, 7),
+ ARM64_SYS_REG(3, 3, 14, 13, 0),
+ ARM64_SYS_REG(3, 3, 14, 13, 1),
+ ARM64_SYS_REG(3, 3, 14, 13, 2),
+ ARM64_SYS_REG(3, 3, 14, 13, 3),
+ ARM64_SYS_REG(3, 3, 14, 13, 4),
+ ARM64_SYS_REG(3, 3, 14, 13, 5),
+ ARM64_SYS_REG(3, 3, 14, 13, 6),
+ ARM64_SYS_REG(3, 3, 14, 13, 7),
+ ARM64_SYS_REG(3, 3, 14, 14, 0),
+ ARM64_SYS_REG(3, 3, 14, 14, 1),
+ ARM64_SYS_REG(3, 3, 14, 14, 2),
+ ARM64_SYS_REG(3, 3, 14, 14, 3),
+ ARM64_SYS_REG(3, 3, 14, 14, 4),
+ ARM64_SYS_REG(3, 3, 14, 14, 5),
+ ARM64_SYS_REG(3, 3, 14, 14, 6),
+ ARM64_SYS_REG(3, 3, 14, 14, 7),
+ ARM64_SYS_REG(3, 3, 14, 15, 0),
+ ARM64_SYS_REG(3, 3, 14, 15, 1),
+ ARM64_SYS_REG(3, 3, 14, 15, 2),
+ ARM64_SYS_REG(3, 3, 14, 15, 3),
+ ARM64_SYS_REG(3, 3, 14, 15, 4),
+ ARM64_SYS_REG(3, 3, 14, 15, 5),
+ ARM64_SYS_REG(3, 3, 14, 15, 6),
+ ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */
+ ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */
+ ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */
+ ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0,
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1,
+ KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2,
+};
+static __u64 base_regs_n = ARRAY_SIZE(base_regs);
+
+static __u64 vregs[] = {
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]),
+ KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]),
+};
+static __u64 vregs_n = ARRAY_SIZE(vregs);
+
+static __u64 sve_regs[] = {
+ KVM_REG_ARM64_SVE_VLS,
+ KVM_REG_ARM64_SVE_ZREG(0, 0),
+ KVM_REG_ARM64_SVE_ZREG(1, 0),
+ KVM_REG_ARM64_SVE_ZREG(2, 0),
+ KVM_REG_ARM64_SVE_ZREG(3, 0),
+ KVM_REG_ARM64_SVE_ZREG(4, 0),
+ KVM_REG_ARM64_SVE_ZREG(5, 0),
+ KVM_REG_ARM64_SVE_ZREG(6, 0),
+ KVM_REG_ARM64_SVE_ZREG(7, 0),
+ KVM_REG_ARM64_SVE_ZREG(8, 0),
+ KVM_REG_ARM64_SVE_ZREG(9, 0),
+ KVM_REG_ARM64_SVE_ZREG(10, 0),
+ KVM_REG_ARM64_SVE_ZREG(11, 0),
+ KVM_REG_ARM64_SVE_ZREG(12, 0),
+ KVM_REG_ARM64_SVE_ZREG(13, 0),
+ KVM_REG_ARM64_SVE_ZREG(14, 0),
+ KVM_REG_ARM64_SVE_ZREG(15, 0),
+ KVM_REG_ARM64_SVE_ZREG(16, 0),
+ KVM_REG_ARM64_SVE_ZREG(17, 0),
+ KVM_REG_ARM64_SVE_ZREG(18, 0),
+ KVM_REG_ARM64_SVE_ZREG(19, 0),
+ KVM_REG_ARM64_SVE_ZREG(20, 0),
+ KVM_REG_ARM64_SVE_ZREG(21, 0),
+ KVM_REG_ARM64_SVE_ZREG(22, 0),
+ KVM_REG_ARM64_SVE_ZREG(23, 0),
+ KVM_REG_ARM64_SVE_ZREG(24, 0),
+ KVM_REG_ARM64_SVE_ZREG(25, 0),
+ KVM_REG_ARM64_SVE_ZREG(26, 0),
+ KVM_REG_ARM64_SVE_ZREG(27, 0),
+ KVM_REG_ARM64_SVE_ZREG(28, 0),
+ KVM_REG_ARM64_SVE_ZREG(29, 0),
+ KVM_REG_ARM64_SVE_ZREG(30, 0),
+ KVM_REG_ARM64_SVE_ZREG(31, 0),
+ KVM_REG_ARM64_SVE_PREG(0, 0),
+ KVM_REG_ARM64_SVE_PREG(1, 0),
+ KVM_REG_ARM64_SVE_PREG(2, 0),
+ KVM_REG_ARM64_SVE_PREG(3, 0),
+ KVM_REG_ARM64_SVE_PREG(4, 0),
+ KVM_REG_ARM64_SVE_PREG(5, 0),
+ KVM_REG_ARM64_SVE_PREG(6, 0),
+ KVM_REG_ARM64_SVE_PREG(7, 0),
+ KVM_REG_ARM64_SVE_PREG(8, 0),
+ KVM_REG_ARM64_SVE_PREG(9, 0),
+ KVM_REG_ARM64_SVE_PREG(10, 0),
+ KVM_REG_ARM64_SVE_PREG(11, 0),
+ KVM_REG_ARM64_SVE_PREG(12, 0),
+ KVM_REG_ARM64_SVE_PREG(13, 0),
+ KVM_REG_ARM64_SVE_PREG(14, 0),
+ KVM_REG_ARM64_SVE_PREG(15, 0),
+ KVM_REG_ARM64_SVE_FFR(0),
+ ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */
+};
+static __u64 sve_regs_n = ARRAY_SIZE(sve_regs);
+
+static __u64 rejects_set[] = {
+#ifdef REG_LIST_SVE
+ KVM_REG_ARM64_SVE_VLS,
+#endif
+};
+static __u64 rejects_set_n = ARRAY_SIZE(rejects_set);
+++ /dev/null
-#define USE_CLEAR_DIRTY_LOG
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
-#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
- KVM_DIRTY_LOG_INITIALLY_SET)
-#include "dirty_log_test.c"
#include <linux/bitops.h>
#include <linux/userfaultfd.h>
-#include "test_util.h"
-#include "kvm_util.h"
+#include "perf_test_util.h"
#include "processor.h"
+#include "test_util.h"
#ifdef __NR_userfaultfd
-/* The memory slot index demand page */
-#define TEST_MEM_SLOT_INDEX 1
-
-/* Default guest test virtual memory offset */
-#define DEFAULT_GUEST_TEST_MEM 0xc0000000
-
-#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */
-
#ifdef PRINT_PER_PAGE_UPDATES
#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
#else
#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
#endif
-#define MAX_VCPUS 512
-
-/*
- * Guest/Host shared variables. Ensure addr_gva2hva() and/or
- * sync_global_to/from_guest() are used when accessing from
- * the host. READ/WRITE_ONCE() should also be used with anything
- * that may change.
- */
-static uint64_t host_page_size;
-static uint64_t guest_page_size;
-
static char *guest_data_prototype;
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-static uint64_t guest_test_phys_mem;
-
-/*
- * Guest virtual memory offset of the testing memory slot.
- * Must not conflict with identity mapped test code.
- */
-static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
-
-struct vcpu_args {
- uint64_t gva;
- uint64_t pages;
-
- /* Only used by the host userspace part of the vCPU thread */
- int vcpu_id;
- struct kvm_vm *vm;
-};
-
-static struct vcpu_args vcpu_args[MAX_VCPUS];
-
-/*
- * Continuously write to the first 8 bytes of each page in the demand paging
- * memory region.
- */
-static void guest_code(uint32_t vcpu_id)
-{
- uint64_t gva;
- uint64_t pages;
- int i;
-
- /* Make sure vCPU args data structure is not corrupt. */
- GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id);
-
- gva = vcpu_args[vcpu_id].gva;
- pages = vcpu_args[vcpu_id].pages;
-
- for (i = 0; i < pages; i++) {
- uint64_t addr = gva + (i * guest_page_size);
-
- addr &= ~(host_page_size - 1);
- *(uint64_t *)addr = 0x0123456789ABCDEF;
- }
-
- GUEST_SYNC(1);
-}
-
static void *vcpu_worker(void *data)
{
int ret;
- struct vcpu_args *args = (struct vcpu_args *)data;
- struct kvm_vm *vm = args->vm;
- int vcpu_id = args->vcpu_id;
+ struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ int vcpu_id = vcpu_args->vcpu_id;
+ struct kvm_vm *vm = perf_test_args.vm;
struct kvm_run *run;
- struct timespec start, end, ts_diff;
+ struct timespec start;
+ struct timespec ts_diff;
vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
run = vcpu_state(vm, vcpu_id);
exit_reason_str(run->exit_reason));
}
- clock_gettime(CLOCK_MONOTONIC, &end);
- ts_diff = timespec_sub(end, start);
+ ts_diff = timespec_diff_now(start);
PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
ts_diff.tv_sec, ts_diff.tv_nsec);
return NULL;
}
-#define PAGE_SHIFT_4K 12
-#define PTES_PER_4K_PT 512
-
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
- uint64_t vcpu_memory_bytes)
-{
- struct kvm_vm *vm;
- uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
-
- /* Account for a few pages per-vCPU for stacks */
- pages += DEFAULT_STACK_PGS * vcpus;
-
- /*
- * Reserve twice the ammount of memory needed to map the test region and
- * the page table / stacks region, at 4k, for page tables. Do the
- * calculation with 4K page size: the smallest of all archs. (e.g., 64K
- * page size guest will need even less memory for page tables).
- */
- pages += (2 * pages) / PTES_PER_4K_PT;
- pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
- PTES_PER_4K_PT;
- pages = vm_adjust_num_guest_pages(mode, pages);
-
- pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
-
- vm = _vm_create(mode, pages, O_RDWR);
- kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-#ifdef __x86_64__
- vm_create_irqchip(vm);
-#endif
- return vm;
-}
-
static int handle_uffd_page_request(int uffd, uint64_t addr)
{
pid_t tid;
struct timespec start;
- struct timespec end;
+ struct timespec ts_diff;
struct uffdio_copy copy;
int r;
copy.src = (uint64_t)guest_data_prototype;
copy.dst = addr;
- copy.len = host_page_size;
+ copy.len = perf_test_args.host_page_size;
copy.mode = 0;
clock_gettime(CLOCK_MONOTONIC, &start);
return r;
}
- clock_gettime(CLOCK_MONOTONIC, &end);
+ ts_diff = timespec_diff_now(start);
PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid,
- timespec_to_ns(timespec_sub(end, start)));
+ timespec_to_ns(ts_diff));
PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n",
- host_page_size, addr, tid);
+ perf_test_args.host_page_size, addr, tid);
return 0;
}
int pipefd = uffd_args->pipefd;
useconds_t delay = uffd_args->delay;
int64_t pages = 0;
- struct timespec start, end, ts_diff;
+ struct timespec start;
+ struct timespec ts_diff;
clock_gettime(CLOCK_MONOTONIC, &start);
while (!quit_uffd_thread) {
pages++;
}
- clock_gettime(CLOCK_MONOTONIC, &end);
- ts_diff = timespec_sub(end, start);
+ ts_diff = timespec_diff_now(start);
PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
pages, ts_diff.tv_sec, ts_diff.tv_nsec,
pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
}
static void run_test(enum vm_guest_mode mode, bool use_uffd,
- useconds_t uffd_delay, int vcpus,
- uint64_t vcpu_memory_bytes)
+ useconds_t uffd_delay)
{
pthread_t *vcpu_threads;
pthread_t *uffd_handler_threads = NULL;
struct uffd_handler_args *uffd_args = NULL;
- struct timespec start, end, ts_diff;
+ struct timespec start;
+ struct timespec ts_diff;
int *pipefds = NULL;
struct kvm_vm *vm;
- uint64_t guest_num_pages;
int vcpu_id;
int r;
- vm = create_vm(mode, vcpus, vcpu_memory_bytes);
-
- guest_page_size = vm_get_page_size(vm);
-
- TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0,
- "Guest memory size is not guest page size aligned.");
-
- guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size;
- guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
-
- /*
- * If there should be more memory in the guest test region than there
- * can be pages in the guest, it will definitely cause problems.
- */
- TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
- "Requested more guest memory than address space allows.\n"
- " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
- guest_num_pages, vm_get_max_gfn(vm), vcpus,
- vcpu_memory_bytes);
-
- host_page_size = getpagesize();
- TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0,
- "Guest memory size is not host page size aligned.");
+ vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
- guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
- guest_page_size;
- guest_test_phys_mem &= ~(host_page_size - 1);
+ perf_test_args.wr_fract = 1;
-#ifdef __s390x__
- /* Align to 1M (segment size) */
- guest_test_phys_mem &= ~((1 << 20) - 1);
-#endif
-
- pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
-
- /* Add an extra memory slot for testing demand paging */
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
- guest_test_phys_mem,
- TEST_MEM_SLOT_INDEX,
- guest_num_pages, 0);
-
- /* Do mapping for the demand paging memory slot */
- virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
-
- ucall_init(vm, NULL);
-
- guest_data_prototype = malloc(host_page_size);
+ guest_data_prototype = malloc(perf_test_args.host_page_size);
TEST_ASSERT(guest_data_prototype,
"Failed to allocate buffer for guest data pattern");
- memset(guest_data_prototype, 0xAB, host_page_size);
+ memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size);
- vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads));
+ vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+ add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
if (use_uffd) {
uffd_handler_threads =
- malloc(vcpus * sizeof(*uffd_handler_threads));
+ malloc(nr_vcpus * sizeof(*uffd_handler_threads));
TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
- uffd_args = malloc(vcpus * sizeof(*uffd_args));
+ uffd_args = malloc(nr_vcpus * sizeof(*uffd_args));
TEST_ASSERT(uffd_args, "Memory allocation failed");
- pipefds = malloc(sizeof(int) * vcpus * 2);
+ pipefds = malloc(sizeof(int) * nr_vcpus * 2);
TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
- }
-
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
- vm_paddr_t vcpu_gpa;
- void *vcpu_hva;
- vm_vcpu_add_default(vm, vcpu_id, guest_code);
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ vm_paddr_t vcpu_gpa;
+ void *vcpu_hva;
- vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
- PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
- vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+ vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size);
+ PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size);
- /* Cache the HVA pointer of the region */
- vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
+ /* Cache the HVA pointer of the region */
+ vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
- if (use_uffd) {
/*
* Set up user fault fd to handle demand paging
* requests.
&uffd_handler_threads[vcpu_id],
pipefds[vcpu_id * 2],
uffd_delay, &uffd_args[vcpu_id],
- vcpu_hva, vcpu_memory_bytes);
+ vcpu_hva, guest_percpu_mem_size);
if (r < 0)
exit(-r);
}
-
-#ifdef __x86_64__
- vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
-#endif
-
- vcpu_args[vcpu_id].vm = vm;
- vcpu_args[vcpu_id].vcpu_id = vcpu_id;
- vcpu_args[vcpu_id].gva = guest_test_virt_mem +
- (vcpu_id * vcpu_memory_bytes);
- vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size;
}
/* Export the shared variables to the guest */
- sync_global_to_guest(vm, host_page_size);
- sync_global_to_guest(vm, guest_page_size);
- sync_global_to_guest(vm, vcpu_args);
+ sync_global_to_guest(vm, perf_test_args);
pr_info("Finished creating vCPUs and starting uffd threads\n");
clock_gettime(CLOCK_MONOTONIC, &start);
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
- &vcpu_args[vcpu_id]);
+ &perf_test_args.vcpu_args[vcpu_id]);
}
pr_info("Started all vCPUs\n");
/* Wait for the vcpu threads to quit */
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
pthread_join(vcpu_threads[vcpu_id], NULL);
PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
}
- pr_info("All vCPU threads joined\n");
+ ts_diff = timespec_diff_now(start);
- clock_gettime(CLOCK_MONOTONIC, &end);
+ pr_info("All vCPU threads joined\n");
if (use_uffd) {
char c;
/* Tell the user fault fd handler threads to quit */
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
r = write(pipefds[vcpu_id * 2 + 1], &c, 1);
TEST_ASSERT(r == 1, "Unable to write to pipefd");
}
}
- ts_diff = timespec_sub(end, start);
pr_info("Total guest execution time: %ld.%.9lds\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
pr_info("Overall demand paging rate: %f pgs/sec\n",
- guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+ perf_test_args.vcpu_args[0].pages * nr_vcpus /
+ ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
ucall_uninit(vm);
kvm_vm_free(vm);
int main(int argc, char *argv[])
{
+ int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
bool mode_selected = false;
- uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE;
- int vcpus = 1;
unsigned int mode;
int opt, i;
bool use_uffd = false;
"A negative UFFD delay is not supported.");
break;
case 'b':
- vcpu_memory_bytes = parse_size(optarg);
+ guest_percpu_mem_size = parse_size(optarg);
break;
case 'v':
- vcpus = atoi(optarg);
- TEST_ASSERT(vcpus > 0,
- "Must have a positive number of vCPUs");
- TEST_ASSERT(vcpus <= MAX_VCPUS,
- "This test does not currently support\n"
- "more than %d vCPUs.", MAX_VCPUS);
+ nr_vcpus = atoi(optarg);
+ TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+ "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
break;
case 'h':
default:
TEST_ASSERT(guest_modes[i].supported,
"Guest mode ID %d (%s) not supported.",
i, vm_guest_mode_string(i));
- run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes);
+ run_test(i, use_uffd, uffd_delay);
}
return 0;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging performance test
+ *
+ * Based on dirty_log_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2020, Google, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
+#define TEST_HOST_LOOP_N 2UL
+
+/* Host variables */
+static bool host_quit;
+static uint64_t iteration;
+static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+
+static void *vcpu_worker(void *data)
+{
+ int ret;
+ struct kvm_vm *vm = perf_test_args.vm;
+ uint64_t pages_count = 0;
+ struct kvm_run *run;
+ struct timespec start;
+ struct timespec ts_diff;
+ struct timespec total = (struct timespec){0};
+ struct timespec avg;
+ struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ int vcpu_id = vcpu_args->vcpu_id;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+ run = vcpu_state(vm, vcpu_id);
+
+ while (!READ_ONCE(host_quit)) {
+ uint64_t current_iteration = READ_ONCE(iteration);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ ret = _vcpu_run(vm, vcpu_id);
+ ts_diff = timespec_diff_now(start);
+
+ TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
+ TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC,
+ "Invalid guest sync status: exit_reason=%s\n",
+ exit_reason_str(run->exit_reason));
+
+ pr_debug("Got sync event from vCPU %d\n", vcpu_id);
+ vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+ pr_debug("vCPU %d updated last completed iteration to %lu\n",
+ vcpu_id, vcpu_last_completed_iteration[vcpu_id]);
+
+ if (current_iteration) {
+ pages_count += vcpu_args->pages;
+ total = timespec_add(total, ts_diff);
+ pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n",
+ vcpu_id, current_iteration, ts_diff.tv_sec,
+ ts_diff.tv_nsec);
+ } else {
+ pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n",
+ vcpu_id, current_iteration, ts_diff.tv_sec,
+ ts_diff.tv_nsec);
+ }
+
+ while (current_iteration == READ_ONCE(iteration) &&
+ !READ_ONCE(host_quit)) {}
+ }
+
+ avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]);
+ pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+ vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
+ total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+ return NULL;
+}
+
+#ifdef USE_CLEAR_DIRTY_LOG
+static u64 dirty_log_manual_caps;
+#endif
+
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+ uint64_t phys_offset, int wr_fract)
+{
+ pthread_t *vcpu_threads;
+ struct kvm_vm *vm;
+ unsigned long *bmap;
+ uint64_t guest_num_pages;
+ uint64_t host_num_pages;
+ int vcpu_id;
+ struct timespec start;
+ struct timespec ts_diff;
+ struct timespec get_dirty_log_total = (struct timespec){0};
+ struct timespec vcpu_dirty_total = (struct timespec){0};
+ struct timespec avg;
+#ifdef USE_CLEAR_DIRTY_LOG
+ struct kvm_enable_cap cap = {};
+ struct timespec clear_dirty_log_total = (struct timespec){0};
+#endif
+
+ vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+
+ perf_test_args.wr_fract = wr_fract;
+
+ guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
+ guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+ host_num_pages = vm_num_host_pages(mode, guest_num_pages);
+ bmap = bitmap_alloc(host_num_pages);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+ cap.args[0] = dirty_log_manual_caps;
+ vm_enable_cap(vm, &cap);
+#endif
+
+ vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
+ TEST_ASSERT(vcpu_threads, "Memory allocation failed");
+
+ add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+
+ sync_global_to_guest(vm, perf_test_args);
+
+ /* Start the iterations */
+ iteration = 0;
+ host_quit = false;
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
+ &perf_test_args.vcpu_args[vcpu_id]);
+ }
+
+ /* Allow the vCPU to populate memory */
+ pr_debug("Starting iteration %lu - Populating\n", iteration);
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+ pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n",
+ iteration);
+
+ ts_diff = timespec_diff_now(start);
+ pr_info("Populate memory time: %ld.%.9lds\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ /* Enable dirty logging */
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+ KVM_MEM_LOG_DIRTY_PAGES);
+ ts_diff = timespec_diff_now(start);
+ pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ while (iteration < iterations) {
+ /*
+ * Incrementing the iteration number will start the vCPUs
+ * dirtying memory again.
+ */
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ iteration++;
+
+ pr_debug("Starting iteration %lu\n", iteration);
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration)
+ pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n",
+ vcpu_id, iteration);
+ }
+
+ ts_diff = timespec_diff_now(start);
+ vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff);
+ pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n",
+ iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+
+ ts_diff = timespec_diff_now(start);
+ get_dirty_log_total = timespec_add(get_dirty_log_total,
+ ts_diff);
+ pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n",
+ iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+ host_num_pages);
+
+ ts_diff = timespec_diff_now(start);
+ clear_dirty_log_total = timespec_add(clear_dirty_log_total,
+ ts_diff);
+ pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n",
+ iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
+#endif
+ }
+
+ /* Tell the vcpu thread to quit */
+ host_quit = true;
+ for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
+ pthread_join(vcpu_threads[vcpu_id], NULL);
+
+ /* Disable dirty logging */
+ clock_gettime(CLOCK_MONOTONIC, &start);
+ vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+ ts_diff = timespec_diff_now(start);
+ pr_info("Disabling dirty logging time: %ld.%.9lds\n",
+ ts_diff.tv_sec, ts_diff.tv_nsec);
+
+ avg = timespec_div(get_dirty_log_total, iterations);
+ pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+ iterations, get_dirty_log_total.tv_sec,
+ get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ avg = timespec_div(clear_dirty_log_total, iterations);
+ pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
+ iterations, clear_dirty_log_total.tv_sec,
+ clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
+#endif
+
+ free(bmap);
+ free(vcpu_threads);
+ ucall_uninit(vm);
+ kvm_vm_free(vm);
+}
+
+struct guest_mode {
+ bool supported;
+ bool enabled;
+};
+static struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_init(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+static void help(char *name)
+{
+ int i;
+
+ puts("");
+ printf("usage: %s [-h] [-i iterations] [-p offset] "
+ "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
+ puts("");
+ printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+ TEST_HOST_LOOP_N);
+ printf(" -p: specify guest physical test memory offset\n"
+ " Warning: a low offset can conflict with the loaded test code.\n");
+ printf(" -m: specify the guest mode ID to test "
+ "(default: test all supported modes)\n"
+ " This option may be used multiple times.\n"
+ " Guest mode IDs:\n");
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
+ guest_modes[i].supported ? " (supported)" : "");
+ }
+ printf(" -b: specify the size of the memory region which should be\n"
+ " dirtied by each vCPU. e.g. 10M or 3G.\n"
+ " (default: 1G)\n");
+ printf(" -f: specify the fraction of pages which should be written to\n"
+ " as opposed to simply read, in the form\n"
+ " 1/<fraction of pages to write>.\n"
+ " (default: 1 i.e. all pages are written to.)\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long iterations = TEST_HOST_LOOP_N;
+ bool mode_selected = false;
+ uint64_t phys_offset = 0;
+ unsigned int mode;
+ int opt, i;
+ int wr_fract = 1;
+
+#ifdef USE_CLEAR_DIRTY_LOG
+ dirty_log_manual_caps =
+ kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+ if (!dirty_log_manual_caps) {
+ print_skip("KVM_CLEAR_DIRTY_LOG not available");
+ exit(KSFT_SKIP);
+ }
+ dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+ KVM_DIRTY_LOG_INITIALLY_SET);
+#endif
+
+#ifdef __x86_64__
+ guest_mode_init(VM_MODE_PXXV48_4K, true, true);
+#endif
+#ifdef __aarch64__
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+ guest_mode_init(VM_MODE_P40V48_64K, true, true);
+
+ {
+ unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+
+ if (limit >= 52)
+ guest_mode_init(VM_MODE_P52V48_64K, true, true);
+ if (limit >= 48) {
+ guest_mode_init(VM_MODE_P48V48_4K, true, true);
+ guest_mode_init(VM_MODE_P48V48_64K, true, true);
+ }
+ }
+#endif
+#ifdef __s390x__
+ guest_mode_init(VM_MODE_P40V48_4K, true, true);
+#endif
+
+ while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
+ switch (opt) {
+ case 'i':
+ iterations = strtol(optarg, NULL, 10);
+ break;
+ case 'p':
+ phys_offset = strtoull(optarg, NULL, 0);
+ break;
+ case 'm':
+ if (!mode_selected) {
+ for (i = 0; i < NUM_VM_MODES; ++i)
+ guest_modes[i].enabled = false;
+ mode_selected = true;
+ }
+ mode = strtoul(optarg, NULL, 10);
+ TEST_ASSERT(mode < NUM_VM_MODES,
+ "Guest mode ID %d too big", mode);
+ guest_modes[mode].enabled = true;
+ break;
+ case 'b':
+ guest_percpu_mem_size = parse_size(optarg);
+ break;
+ case 'f':
+ wr_fract = atoi(optarg);
+ TEST_ASSERT(wr_fract >= 1,
+ "Write fraction cannot be less than one");
+ break;
+ case 'v':
+ nr_vcpus = atoi(optarg);
+ TEST_ASSERT(nr_vcpus > 0,
+ "Must have a positive number of vCPUs");
+ TEST_ASSERT(nr_vcpus <= MAX_VCPUS,
+ "This test does not currently support\n"
+ "more than %d vCPUs.", MAX_VCPUS);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ TEST_ASSERT(iterations >= 2, "The test should have at least two iterations");
+
+ pr_info("Test iterations: %"PRIu64"\n", iterations);
+
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ if (!guest_modes[i].enabled)
+ continue;
+ TEST_ASSERT(guest_modes[i].supported,
+ "Guest mode ID %d (%s) not supported.",
+ i, vm_guest_mode_string(i));
+ run_test(i, iterations, phys_offset, wr_fract);
+ }
+
+ return 0;
+}
static uint64_t host_clear_count;
static uint64_t host_track_next_count;
+enum log_mode_t {
+ /* Only use KVM_GET_DIRTY_LOG for logging */
+ LOG_MODE_DIRTY_LOG = 0,
+
+ /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
+ LOG_MODE_CLEAR_LOG = 1,
+
+ LOG_MODE_NUM,
+
+ /* Run all supported modes */
+ LOG_MODE_ALL = LOG_MODE_NUM,
+};
+
+/* Mode of logging to test. Default is to run all supported modes */
+static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
+/* Logging mode for current run */
+static enum log_mode_t host_log_mode;
+
+static bool clear_log_supported(void)
+{
+ return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+}
+
+static void clear_log_create_vm_done(struct kvm_vm *vm)
+{
+ struct kvm_enable_cap cap = {};
+ u64 manual_caps;
+
+ manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+ TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!");
+ manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+ KVM_DIRTY_LOG_INITIALLY_SET);
+ cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+ cap.args[0] = manual_caps;
+ vm_enable_cap(vm, &cap);
+}
+
+static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages)
+{
+ kvm_vm_get_dirty_log(vm, slot, bitmap);
+}
+
+static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages)
+{
+ kvm_vm_get_dirty_log(vm, slot, bitmap);
+ kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
+}
+
+struct log_mode {
+ const char *name;
+ /* Return true if this mode is supported, otherwise false */
+ bool (*supported)(void);
+ /* Hook when the vm creation is done (before vcpu creation) */
+ void (*create_vm_done)(struct kvm_vm *vm);
+ /* Hook to collect the dirty pages into the bitmap provided */
+ void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages);
+} log_modes[LOG_MODE_NUM] = {
+ {
+ .name = "dirty-log",
+ .collect_dirty_pages = dirty_log_collect_dirty_pages,
+ },
+ {
+ .name = "clear-log",
+ .supported = clear_log_supported,
+ .create_vm_done = clear_log_create_vm_done,
+ .collect_dirty_pages = clear_log_collect_dirty_pages,
+ },
+};
+
/*
* We use this bitmap to track some pages that should have its dirty
* bit set in the _next_ iteration. For example, if we detected the
*/
static unsigned long *host_bmap_track;
+static void log_modes_dump(void)
+{
+ int i;
+
+ printf("all");
+ for (i = 0; i < LOG_MODE_NUM; i++)
+ printf(", %s", log_modes[i].name);
+ printf("\n");
+}
+
+static bool log_mode_supported(void)
+{
+ struct log_mode *mode = &log_modes[host_log_mode];
+
+ if (mode->supported)
+ return mode->supported();
+
+ return true;
+}
+
+static void log_mode_create_vm_done(struct kvm_vm *vm)
+{
+ struct log_mode *mode = &log_modes[host_log_mode];
+
+ if (mode->create_vm_done)
+ mode->create_vm_done(vm);
+}
+
+static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
+ void *bitmap, uint32_t num_pages)
+{
+ struct log_mode *mode = &log_modes[host_log_mode];
+
+ TEST_ASSERT(mode->collect_dirty_pages != NULL,
+ "collect_dirty_pages() is required for any log mode!");
+ mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
+}
+
static void generate_random_array(uint64_t *guest_array, uint64_t size)
{
uint64_t i;
page);
}
- if (test_bit_le(page, bmap)) {
+ if (test_and_clear_bit_le(page, bmap)) {
host_dirty_count++;
/*
* If the bit is set, the value written onto
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
- vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+ vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
#ifdef __x86_64__
vm_create_irqchip(vm);
#endif
+ log_mode_create_vm_done(vm);
vm_vcpu_add_default(vm, vcpuid, guest_code);
return vm;
}
#define DIRTY_MEM_BITS 30 /* 1G */
#define PAGE_SHIFT_4K 12
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
-
static void run_test(enum vm_guest_mode mode, unsigned long iterations,
unsigned long interval, uint64_t phys_offset)
{
struct kvm_vm *vm;
unsigned long *bmap;
+ if (!log_mode_supported()) {
+ print_skip("Log mode '%s' not supported",
+ log_modes[host_log_mode].name);
+ return;
+ }
+
/*
* We reserve page table for 2 times of extra dirty mem which
* will definitely cover the original (1G+) test range. Here
bmap = bitmap_alloc(host_num_pages);
host_bmap_track = bitmap_alloc(host_num_pages);
-#ifdef USE_CLEAR_DIRTY_LOG
- struct kvm_enable_cap cap = {};
-
- cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
- cap.args[0] = dirty_log_manual_caps;
- vm_enable_cap(vm, &cap);
-#endif
-
/* Add an extra memory slot for testing dirty logging */
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
guest_test_phys_mem,
while (iteration < iterations) {
/* Give the vcpu thread some time to dirty some pages */
usleep(interval * 1000);
- kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-#ifdef USE_CLEAR_DIRTY_LOG
- kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
- host_num_pages);
-#endif
+ log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
+ bmap, host_num_pages);
vm_dirty_log_verify(mode, bmap);
iteration++;
sync_global_to_guest(vm, iteration);
TEST_HOST_LOOP_INTERVAL);
printf(" -p: specify guest physical test memory offset\n"
" Warning: a low offset can conflict with the loaded test code.\n");
+ printf(" -M: specify the host logging mode "
+ "(default: run all log modes). Supported modes: \n\t");
+ log_modes_dump();
printf(" -m: specify the guest mode ID to test "
"(default: test all supported modes)\n"
" This option may be used multiple times.\n"
bool mode_selected = false;
uint64_t phys_offset = 0;
unsigned int mode;
- int opt, i;
-
-#ifdef USE_CLEAR_DIRTY_LOG
- dirty_log_manual_caps =
- kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
- if (!dirty_log_manual_caps) {
- print_skip("KVM_CLEAR_DIRTY_LOG not available");
- exit(KSFT_SKIP);
- }
- dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
- KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
+ int opt, i, j;
#ifdef __x86_64__
guest_mode_init(VM_MODE_PXXV48_4K, true, true);
guest_mode_init(VM_MODE_P40V48_4K, true, true);
#endif
- while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
+ while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
switch (opt) {
case 'i':
iterations = strtol(optarg, NULL, 10);
"Guest mode ID %d too big", mode);
guest_modes[mode].enabled = true;
break;
+ case 'M':
+ if (!strcmp(optarg, "all")) {
+ host_log_mode_option = LOG_MODE_ALL;
+ break;
+ }
+ for (i = 0; i < LOG_MODE_NUM; i++) {
+ if (!strcmp(optarg, log_modes[i].name)) {
+ pr_info("Setting log mode to: '%s'\n",
+ optarg);
+ host_log_mode_option = i;
+ break;
+ }
+ }
+ if (i == LOG_MODE_NUM) {
+ printf("Log mode '%s' invalid. Please choose "
+ "from: ", optarg);
+ log_modes_dump();
+ exit(1);
+ }
+ break;
case 'h':
default:
help(argv[0]);
TEST_ASSERT(guest_modes[i].supported,
"Guest mode ID %d (%s) not supported.",
i, vm_guest_mode_string(i));
- run_test(i, iterations, interval, phys_offset);
+ if (host_log_mode_option == LOG_MODE_ALL) {
+ /* Run each log mode */
+ for (j = 0; j < LOG_MODE_NUM; j++) {
+ pr_info("Testing Log Mode '%s'\n",
+ log_modes[j].name);
+ host_log_mode = j;
+ run_test(i, iterations, interval, phys_offset);
+ }
+ } else {
+ host_log_mode = host_log_mode_option;
+ run_test(i, iterations, interval, phys_offset);
+ }
}
return 0;
int kvm_check_cap(long cap);
int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+ struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
void kvm_vm_free(struct kvm_vm *vmp);
void kvm_vm_restart(struct kvm_vm *vmp, int perm);
void kvm_vm_release(struct kvm_vm *vmp);
struct kvm_guest_debug *debug);
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
memcpy(&(g), _p, sizeof(g)); \
})
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
/* Common ucalls */
enum {
UCALL_NONE,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/perf_test_util.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
+#define SELFTEST_KVM_PERF_TEST_UTIL_H
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define MAX_VCPUS 512
+
+#define PAGE_SHIFT_4K 12
+#define PTES_PER_4K_PT 512
+
+#define TEST_MEM_SLOT_INDEX 1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM 0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
+/* Number of VCPUs for the test */
+static int nr_vcpus = 1;
+
+struct vcpu_args {
+ uint64_t gva;
+ uint64_t pages;
+
+ /* Only used by the host userspace part of the vCPU thread */
+ int vcpu_id;
+};
+
+struct perf_test_args {
+ struct kvm_vm *vm;
+ uint64_t host_page_size;
+ uint64_t guest_page_size;
+ int wr_fract;
+
+ struct vcpu_args vcpu_args[MAX_VCPUS];
+};
+
+static struct perf_test_args perf_test_args;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+ struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+ uint64_t gva;
+ uint64_t pages;
+ int i;
+
+ /* Make sure vCPU args data structure is not corrupt. */
+ GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+ gva = vcpu_args->gva;
+ pages = vcpu_args->pages;
+
+ while (true) {
+ for (i = 0; i < pages; i++) {
+ uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+ if (i % perf_test_args.wr_fract == 0)
+ *(uint64_t *)addr = 0x0123456789ABCDEF;
+ else
+ READ_ONCE(*(uint64_t *)addr);
+ }
+
+ GUEST_SYNC(1);
+ }
+}
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes)
+{
+ struct kvm_vm *vm;
+ uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+ uint64_t guest_num_pages;
+
+ /* Account for a few pages per-vCPU for stacks */
+ pages += DEFAULT_STACK_PGS * vcpus;
+
+ /*
+ * Reserve twice the ammount of memory needed to map the test region and
+ * the page table / stacks region, at 4k, for page tables. Do the
+ * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+ * page size guest will need even less memory for page tables).
+ */
+ pages += (2 * pages) / PTES_PER_4K_PT;
+ pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+ PTES_PER_4K_PT;
+ pages = vm_adjust_num_guest_pages(mode, pages);
+
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+ vm = vm_create(mode, pages, O_RDWR);
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+ vm_create_irqchip(vm);
+#endif
+
+ perf_test_args.vm = vm;
+ perf_test_args.guest_page_size = vm_get_page_size(vm);
+ perf_test_args.host_page_size = getpagesize();
+
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+ "Guest memory size is not guest page size aligned.");
+
+ guest_num_pages = (vcpus * vcpu_memory_bytes) /
+ perf_test_args.guest_page_size;
+ guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+ /*
+ * If there should be more memory in the guest test region than there
+ * can be pages in the guest, it will definitely cause problems.
+ */
+ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+ "Requested more guest memory than address space allows.\n"
+ " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+ guest_num_pages, vm_get_max_gfn(vm), vcpus,
+ vcpu_memory_bytes);
+
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+ "Guest memory size is not host page size aligned.");
+
+ guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+ perf_test_args.guest_page_size;
+ guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+
+#ifdef __s390x__
+ /* Align to 1M (segment size) */
+ guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+ pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+ /* Add an extra memory slot for testing */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ guest_test_phys_mem,
+ TEST_MEM_SLOT_INDEX,
+ guest_num_pages, 0);
+
+ /* Do mapping for the demand paging memory slot */
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+ ucall_init(vm, NULL);
+
+ return vm;
+}
+
+static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+ vm_paddr_t vcpu_gpa;
+ struct vcpu_args *vcpu_args;
+ int vcpu_id;
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+ vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+#ifdef __x86_64__
+ vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+ vcpu_args->vcpu_id = vcpu_id;
+ vcpu_args->gva = guest_test_virt_mem +
+ (vcpu_id * vcpu_memory_bytes);
+ vcpu_args->pages = vcpu_memory_bytes /
+ perf_test_args.guest_page_size;
+
+ vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+ pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+ }
+}
+
+#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_diff_now(struct timespec start);
+struct timespec timespec_div(struct timespec ts, int divisor);
#endif /* SELFTEST_KVM_TEST_UTIL_H */
#define X86_CR4_SMAP (1ul << 21)
#define X86_CR4_PKE (1ul << 22)
+#define UNEXPECTED_VECTOR_PORT 0xfff0u
+
/* General Registers in 64-Bit Mode */
struct gpr64_regs {
u64 rax;
struct desc64 {
uint16_t limit0;
uint16_t base0;
- unsigned base1:8, s:1, type:4, dpl:2, p:1;
+ unsigned base1:8, type:4, s:1, dpl:2, p:1;
unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
uint32_t base3;
uint32_t zero1;
return idt;
}
+static inline void outl(uint16_t port, uint32_t value)
+{
+ __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
+}
+
#define SET_XMM(__var, __xmm) \
asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
uint32_t kvm_get_cpuid_max_extended(void);
void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
+struct ex_regs {
+ uint64_t rax, rcx, rdx, rbx;
+ uint64_t rbp, rsi, rdi;
+ uint64_t r8, r9, r10, r11;
+ uint64_t r12, r13, r14, r15;
+ uint64_t vector;
+ uint64_t error_code;
+ uint64_t rip;
+ uint64_t cs;
+ uint64_t rflags;
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+ void (*handler)(struct ex_regs *));
+
+/*
+ * set_cpuid() - overwrites a matching cpuid entry with the provided value.
+ * matches based on ent->function && ent->index. returns true
+ * if a match was found and successfully overwritten.
+ * @cpuid: the kvm cpuid list to modify.
+ * @ent: cpuid entry to insert
+ */
+bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent);
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+ uint64_t a3);
+
/*
* Basic CPU control in CR0
*/
void *eptp_hva;
uint64_t eptp_gpa;
void *eptp;
+
+ void *apic_access_hva;
+ uint64_t apic_access_gpa;
+ void *apic_access;
};
union vmx_basic {
uint32_t memslot, uint32_t eptp_memslot);
void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t eptp_memslot);
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot);
#endif /* SELFTEST_KVM_VMX_H */
va_end(ap);
}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
struct kvm_run *run = vcpu_state(vm, vcpu_id);
struct ucall ucall = {};
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
if (run->exit_reason == KVM_EXIT_MMIO &&
run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
vm_vaddr_t gva;
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <unistd.h>
#include <linux/kernel.h>
#define KVM_UTIL_PGS_PER_HUGEPG 512
return ret;
}
+/* VCPU Enable Capability
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpu_id - VCPU
+ * cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VCPU.
+ */
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+ struct kvm_enable_cap *cap)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpu_id);
+ int r;
+
+ TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id);
+
+ r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap);
+ TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n"
+ " rc: %i, errno: %i", r, errno);
+
+ return r;
+}
+
static void vm_open(struct kvm_vm *vm, int perm)
{
vm->kvm_fd = open(KVM_DEV_PATH, perm);
* descriptor to control the created VM is created with the permissions
* given by perm (e.g. O_RDWR).
*/
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
{
struct kvm_vm *vm;
return vm;
}
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
-{
- return _vm_create(mode, phy_pages, perm);
-}
-
/*
* VM Restart
*
/* As needed perform madvise */
if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
- ret = madvise(region->host_mem, npages * vm->page_size,
- src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
- TEST_ASSERT(ret == 0, "madvise failed,\n"
- " addr: %p\n"
- " length: 0x%lx\n"
- " src_type: %x",
- region->host_mem, npages * vm->page_size, src_type);
+ struct stat statbuf;
+
+ ret = stat("/sys/kernel/mm/transparent_hugepage", &statbuf);
+ TEST_ASSERT(ret == 0 || (ret == -1 && errno == ENOENT),
+ "stat /sys/kernel/mm/transparent_hugepage");
+
+ TEST_ASSERT(ret == 0 || src_type != VM_MEM_SRC_ANONYMOUS_THP,
+ "VM_MEM_SRC_ANONYMOUS_THP requires THP to be configured in the host kernel");
+
+ if (ret == 0) {
+ ret = madvise(region->host_mem, npages * vm->page_size,
+ src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
+ TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %x",
+ region->host_mem, npages * vm->page_size, src_type);
+ }
}
region->unused_phy_pages = sparsebit_alloc();
do {
rc = ioctl(vcpu->fd, KVM_RUN, NULL);
} while (rc == -1 && errno == EINTR);
+
+ assert_on_unhandled_exception(vm, vcpuid);
+
return rc;
}
"rc: %i errno: %i", ret, errno);
}
+/*
+ * VM VCPU Get Reg List
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args:
+ * None
+ *
+ * Return:
+ * A pointer to an allocated struct kvm_reg_list
+ *
+ * Get the list of guest registers which are supported for
+ * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls
+ */
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
+ int ret;
+
+ ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n);
+ TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");
+ reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
+ reg_list->n = reg_list_n.n;
+ vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list);
+ return reg_list;
+}
+
/*
* VM VCPU Regs Get
*
vm_paddr_t pgd;
vm_vaddr_t gdt;
vm_vaddr_t tss;
+ vm_vaddr_t idt;
+ vm_vaddr_t handlers;
};
struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
struct kvm_run *run = vcpu_state(vm, vcpu_id);
struct ucall ucall = {};
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
if (run->exit_reason == KVM_EXIT_S390_SIEIC &&
run->s390_sieic.icptcode == 4 &&
(run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */
*
* Copyright (C) 2020, Google LLC.
*/
-#include <stdlib.h>
+
+#include <assert.h>
#include <ctype.h>
#include <limits.h>
-#include <assert.h>
+#include <stdlib.h>
+#include <time.h>
+
#include "test_util.h"
/*
return timespec_add_ns((struct timespec){0}, ns1 - ns2);
}
+struct timespec timespec_diff_now(struct timespec start)
+{
+ struct timespec end;
+
+ clock_gettime(CLOCK_MONOTONIC, &end);
+ return timespec_sub(end, start);
+}
+
+struct timespec timespec_div(struct timespec ts, int divisor)
+{
+ int64_t ns = timespec_to_ns(ts) / divisor;
+
+ return timespec_add_ns((struct timespec){0}, ns);
+}
+
void print_skip(const char *fmt, ...)
{
va_list ap;
--- /dev/null
+handle_exception:
+ push %r15
+ push %r14
+ push %r13
+ push %r12
+ push %r11
+ push %r10
+ push %r9
+ push %r8
+
+ push %rdi
+ push %rsi
+ push %rbp
+ push %rbx
+ push %rdx
+ push %rcx
+ push %rax
+ mov %rsp, %rdi
+
+ call route_exception
+
+ pop %rax
+ pop %rcx
+ pop %rdx
+ pop %rbx
+ pop %rbp
+ pop %rsi
+ pop %rdi
+ pop %r8
+ pop %r9
+ pop %r10
+ pop %r11
+ pop %r12
+ pop %r13
+ pop %r14
+ pop %r15
+
+ /* Discard vector and error code. */
+ add $16, %rsp
+ iretq
+
+/*
+ * Build the handle_exception wrappers which push the vector/error code on the
+ * stack and an array of pointers to those wrappers.
+ */
+.pushsection .rodata
+.globl idt_handlers
+idt_handlers:
+.popsection
+
+.macro HANDLERS has_error from to
+ vector = \from
+ .rept \to - \from + 1
+ .align 8
+
+ /* Fetch current address and append it to idt_handlers. */
+ current_handler = .
+.pushsection .rodata
+.quad current_handler
+.popsection
+
+ .if ! \has_error
+ pushq $0
+ .endif
+ pushq $vector
+ jmp handle_exception
+ vector = vector + 1
+ .endr
+.endm
+
+.global idt_handler_code
+idt_handler_code:
+ HANDLERS has_error=0 from=0 to=7
+ HANDLERS has_error=1 from=8 to=8
+ HANDLERS has_error=0 from=9 to=9
+ HANDLERS has_error=1 from=10 to=14
+ HANDLERS has_error=0 from=15 to=16
+ HANDLERS has_error=1 from=17 to=17
+ HANDLERS has_error=0 from=18 to=255
+
+.section .note.GNU-stack, "", %progbits
#include "../kvm_util_internal.h"
#include "processor.h"
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
+#define DEFAULT_CODE_SELECTOR 0x8
+#define DEFAULT_DATA_SELECTOR 0x10
+
/* Minimum physical address used for virtual translation tables. */
#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+vm_vaddr_t exception_handlers;
+
/* Virtual translation table structure declarations */
struct pageMapL4Entry {
uint64_t present:1;
desc->limit0 = segp->limit & 0xFFFF;
desc->base0 = segp->base & 0xFFFF;
desc->base1 = segp->base >> 16;
- desc->s = segp->s;
desc->type = segp->type;
+ desc->s = segp->s;
desc->dpl = segp->dpl;
desc->p = segp->present;
desc->limit1 = segp->limit >> 16;
+ desc->avl = segp->avl;
desc->l = segp->l;
desc->db = segp->db;
desc->g = segp->g;
sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
kvm_seg_set_unusable(&sregs.ldt);
- kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
- kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
- kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+ kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs);
+ kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds);
+ kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es);
kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
break;
*va_bits = (entry->eax >> 8) & 0xff;
}
}
+
+struct idt_entry {
+ uint16_t offset0;
+ uint16_t selector;
+ uint16_t ist : 3;
+ uint16_t : 5;
+ uint16_t type : 4;
+ uint16_t : 1;
+ uint16_t dpl : 2;
+ uint16_t p : 1;
+ uint16_t offset1;
+ uint32_t offset2; uint32_t reserved;
+};
+
+static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
+ int dpl, unsigned short selector)
+{
+ struct idt_entry *base =
+ (struct idt_entry *)addr_gva2hva(vm, vm->idt);
+ struct idt_entry *e = &base[vector];
+
+ memset(e, 0, sizeof(*e));
+ e->offset0 = addr;
+ e->selector = selector;
+ e->ist = 0;
+ e->type = 14;
+ e->dpl = dpl;
+ e->p = 1;
+ e->offset1 = addr >> 16;
+ e->offset2 = addr >> 32;
+}
+
+void kvm_exit_unexpected_vector(uint32_t value)
+{
+ outl(UNEXPECTED_VECTOR_PORT, value);
+}
+
+void route_exception(struct ex_regs *regs)
+{
+ typedef void(*handler)(struct ex_regs *);
+ handler *handlers = (handler *)exception_handlers;
+
+ if (handlers && handlers[regs->vector]) {
+ handlers[regs->vector](regs);
+ return;
+ }
+
+ kvm_exit_unexpected_vector(regs->vector);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+ extern void *idt_handlers;
+ int i;
+
+ vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0);
+ vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0);
+ /* Handlers have the same address in both address spaces.*/
+ for (i = 0; i < NUM_INTERRUPTS; i++)
+ set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,
+ DEFAULT_CODE_SELECTOR);
+}
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct kvm_sregs sregs;
+
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+ sregs.idt.base = vm->idt;
+ sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+ sregs.gdt.base = vm->gdt;
+ sregs.gdt.limit = getpagesize() - 1;
+ kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs);
+ vcpu_sregs_set(vm, vcpuid, &sregs);
+ *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+ void (*handler)(struct ex_regs *))
+{
+ vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
+
+ handlers[vector] = (vm_vaddr_t)handler;
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
+ && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
+ && vcpu_state(vm, vcpuid)->io.size == 4) {
+ /* Grab pointer to io data */
+ uint32_t *data = (void *)vcpu_state(vm, vcpuid)
+ + vcpu_state(vm, vcpuid)->io.data_offset;
+
+ TEST_ASSERT(false,
+ "Unexpected vectored event in guest (vector:0x%x)",
+ *data);
+ }
+}
+
+bool set_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 *ent)
+{
+ int i;
+
+ for (i = 0; i < cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+ if (cur->function != ent->function || cur->index != ent->index)
+ continue;
+
+ memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2));
+ return true;
+ }
+
+ return false;
+}
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+ uint64_t a3)
+{
+ uint64_t r;
+
+ asm volatile("vmcall"
+ : "=a"(r)
+ : "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+ return r;
+}
struct kvm_run *run = vcpu_state(vm, vcpu_id);
struct ucall ucall = {};
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
struct kvm_regs regs;
vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
}
+
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot)
+{
+ vmx->apic_access = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access);
+ vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <stdint.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+extern unsigned char rdmsr_start;
+extern unsigned char rdmsr_end;
+
+static u64 do_rdmsr(u32 idx)
+{
+ u32 lo, hi;
+
+ asm volatile("rdmsr_start: rdmsr;"
+ "rdmsr_end:"
+ : "=a"(lo), "=c"(hi)
+ : "c"(idx));
+
+ return (((u64) hi) << 32) | lo;
+}
+
+extern unsigned char wrmsr_start;
+extern unsigned char wrmsr_end;
+
+static void do_wrmsr(u32 idx, u64 val)
+{
+ u32 lo, hi;
+
+ lo = val;
+ hi = val >> 32;
+
+ asm volatile("wrmsr_start: wrmsr;"
+ "wrmsr_end:"
+ : : "a"(lo), "c"(idx), "d"(hi));
+}
+
+static int nr_gp;
+
+static void guest_gp_handler(struct ex_regs *regs)
+{
+ unsigned char *rip = (unsigned char *)regs->rip;
+ bool r, w;
+
+ r = rip == &rdmsr_start;
+ w = rip == &wrmsr_start;
+ GUEST_ASSERT(r || w);
+
+ nr_gp++;
+
+ if (r)
+ regs->rip = (uint64_t)&rdmsr_end;
+ else
+ regs->rip = (uint64_t)&wrmsr_end;
+}
+
+struct msr_data {
+ uint32_t idx;
+ const char *name;
+};
+
+#define TEST_MSR(msr) { .idx = msr, .name = #msr }
+#define UCALL_PR_MSR 0xdeadbeef
+#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr)
+
+/*
+ * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or
+ * written, as the KVM_CPUID_FEATURES leaf is cleared.
+ */
+static struct msr_data msrs_to_test[] = {
+ TEST_MSR(MSR_KVM_SYSTEM_TIME),
+ TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW),
+ TEST_MSR(MSR_KVM_WALL_CLOCK),
+ TEST_MSR(MSR_KVM_WALL_CLOCK_NEW),
+ TEST_MSR(MSR_KVM_ASYNC_PF_EN),
+ TEST_MSR(MSR_KVM_STEAL_TIME),
+ TEST_MSR(MSR_KVM_PV_EOI_EN),
+ TEST_MSR(MSR_KVM_POLL_CONTROL),
+ TEST_MSR(MSR_KVM_ASYNC_PF_INT),
+ TEST_MSR(MSR_KVM_ASYNC_PF_ACK),
+};
+
+static void test_msr(struct msr_data *msr)
+{
+ PR_MSR(msr);
+ do_rdmsr(msr->idx);
+ GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+
+ nr_gp = 0;
+ do_wrmsr(msr->idx, 0);
+ GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+ nr_gp = 0;
+}
+
+struct hcall_data {
+ uint64_t nr;
+ const char *name;
+};
+
+#define TEST_HCALL(hc) { .nr = hc, .name = #hc }
+#define UCALL_PR_HCALL 0xdeadc0de
+#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc)
+
+/*
+ * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding
+ * features have been cleared in KVM_CPUID_FEATURES.
+ */
+static struct hcall_data hcalls_to_test[] = {
+ TEST_HCALL(KVM_HC_KICK_CPU),
+ TEST_HCALL(KVM_HC_SEND_IPI),
+ TEST_HCALL(KVM_HC_SCHED_YIELD),
+};
+
+static void test_hcall(struct hcall_data *hc)
+{
+ uint64_t r;
+
+ PR_HCALL(hc);
+ r = kvm_hypercall(hc->nr, 0, 0, 0, 0);
+ GUEST_ASSERT(r == -KVM_ENOSYS);
+}
+
+static void guest_main(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) {
+ test_msr(&msrs_to_test[i]);
+ }
+
+ for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) {
+ test_hcall(&hcalls_to_test[i]);
+ }
+
+ GUEST_DONE();
+}
+
+static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid)
+{
+ struct kvm_cpuid_entry2 ent = {0};
+
+ ent.function = KVM_CPUID_FEATURES;
+ TEST_ASSERT(set_cpuid(cpuid, &ent),
+ "failed to clear KVM_CPUID_FEATURES leaf");
+}
+
+static void pr_msr(struct ucall *uc)
+{
+ struct msr_data *msr = (struct msr_data *)uc->args[0];
+
+ pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx);
+}
+
+static void pr_hcall(struct ucall *uc)
+{
+ struct hcall_data *hc = (struct hcall_data *)uc->args[0];
+
+ pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+ TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+ __FILE__, uc->args[1]);
+}
+
+#define VCPU_ID 0
+
+static void enter_guest(struct kvm_vm *vm)
+{
+ struct kvm_run *run;
+ struct ucall uc;
+ int r;
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ while (true) {
+ r = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(!r, "vcpu_run failed: %d\n", r);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "unexpected exit reason: %u (%s)",
+ run->exit_reason, exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_PR_MSR:
+ pr_msr(&uc);
+ break;
+ case UCALL_PR_HCALL:
+ pr_hcall(&uc);
+ break;
+ case UCALL_ABORT:
+ handle_abort(&uc);
+ return;
+ case UCALL_DONE:
+ return;
+ }
+ }
+}
+
+int main(void)
+{
+ struct kvm_enable_cap cap = {0};
+ struct kvm_cpuid2 *best;
+ struct kvm_vm *vm;
+
+ if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) {
+ pr_info("will skip kvm paravirt restriction tests.\n");
+ return 0;
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, guest_main);
+
+ cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID;
+ cap.args[0] = 1;
+ vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+ best = kvm_get_supported_cpuid();
+ clear_kvm_cpuid_features(best);
+ vcpu_set_cpuid(vm, VCPU_ID, best);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+
+ enter_guest(vm);
+ kvm_vm_free(vm);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vmx_apic_access_test
+ *
+ * Copyright (C) 2020, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * The first subtest simply checks to see that an L2 guest can be
+ * launched with a valid APIC-access address that is backed by a
+ * page of L1 physical memory.
+ *
+ * The second subtest sets the APIC-access address to a (valid) L1
+ * physical address that is not backed by memory. KVM can't handle
+ * this situation, so resuming L2 should result in a KVM exit for
+ * internal error (emulation). This is not an architectural
+ * requirement. It is just a shortcoming of KVM. The internal error
+ * is unfortunate, but it's better than what used to happen!
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID 0
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+static void l2_guest_code(void)
+{
+ /* Exit to L1 */
+ __asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages, unsigned long high_gpa)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ uint32_t control;
+
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+
+ /* Prepare the VMCS for L2 execution. */
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+ control |= CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+ control = vmreadz(SECONDARY_VM_EXEC_CONTROL);
+ control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ vmwrite(SECONDARY_VM_EXEC_CONTROL, control);
+ vmwrite(APIC_ACCESS_ADDR, vmx_pages->apic_access_gpa);
+
+ /* Try to launch L2 with the memory-backed APIC-access address. */
+ GUEST_SYNC(vmreadz(APIC_ACCESS_ADDR));
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ vmwrite(APIC_ACCESS_ADDR, high_gpa);
+
+ /* Try to resume L2 with the unbacked APIC-access address. */
+ GUEST_SYNC(vmreadz(APIC_ACCESS_ADDR));
+ GUEST_ASSERT(!vmresume());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long apic_access_addr = ~0ul;
+ unsigned int paddr_width;
+ unsigned int vaddr_width;
+ vm_vaddr_t vmx_pages_gva;
+ unsigned long high_gpa;
+ struct vmx_pages *vmx;
+ bool done = false;
+
+ nested_vmx_check_supported();
+
+ vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ kvm_get_cpu_address_width(&paddr_width, &vaddr_width);
+ high_gpa = (1ul << paddr_width) - getpagesize();
+ if ((unsigned long)DEFAULT_GUEST_PHY_PAGES * getpagesize() > high_gpa) {
+ print_skip("No unbacked physical page available");
+ exit(KSFT_SKIP);
+ }
+
+ vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ prepare_virtualize_apic_accesses(vmx, vm, 0);
+ vcpu_args_set(vm, VCPU_ID, 2, vmx_pages_gva, high_gpa);
+
+ while (!done) {
+ volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct ucall uc;
+
+ vcpu_run(vm, VCPU_ID);
+ if (apic_access_addr == high_gpa) {
+ TEST_ASSERT(run->exit_reason ==
+ KVM_EXIT_INTERNAL_ERROR,
+ "Got exit reason other than KVM_EXIT_INTERNAL_ERROR: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->internal.suberror ==
+ KVM_INTERNAL_ERROR_EMULATION,
+ "Got internal suberror other than KVM_INTERNAL_ERROR_EMULATION: %u\n",
+ run->internal.suberror);
+ break;
+ }
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ apic_access_addr = uc.args[1];
+ break;
+ case UCALL_DONE:
+ done = true;
+ break;
+ default:
+ TEST_ASSERT(false, "Unknown ucall %lu", uc.cmd);
+ }
+ }
+ kvm_vm_free(vm);
+ return 0;
+}
ifeq ($(OVERRIDE_TARGETS),)
LOCAL_HDRS := $(selfdir)/kselftest_harness.h $(selfdir)/kselftest.h
$(OUTPUT)/%:%.c $(LOCAL_HDRS)
- $(LINK.c) $^ $(LDLIBS) -o $@
+ $(LINK.c) $(filter-out $(LOCAL_HDRS),$^) $(LDLIBS) -o $@
$(OUTPUT)/%.o:%.S
$(COMPILE.S) $^ -o $@
CONFIG_PID_NS=y
CONFIG_NET_NS=y
CONFIG_CGROUPS=y
+CONFIG_CHECKPOINT_RESTORE=y
fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
ASSERT_GE(fd, 0);
- EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd));
+ ret = sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd);
+ if (ret < 0 && errno == ENOSYS)
+ SKIP(return, "kcmp() syscall not supported");
+ EXPECT_EQ(ret, 0);
ret = fcntl(fd, F_GETFD);
ASSERT_GE(ret, 0);
#include <inttypes.h>
#include <limits.h>
#include <linux/types.h>
-#include <linux/wait.h>
#include <sched.h>
#include <signal.h>
#include <stdbool.h>
#define _GNU_SOURCE
#include <errno.h>
#include <linux/types.h>
-#include <linux/wait.h>
#include <poll.h>
#include <signal.h>
#include <stdbool.h>
#include <unistd.h>
#include <sys/socket.h>
#include <sys/stat.h>
-#include <linux/kcmp.h>
#include "pidfd.h"
#include "../clone3/clone3_selftests.h"
ksft_exit_fail_msg("%s test: Failed to recycle pid %d\n",
test_name, PID_RECYCLE);
case PIDFD_SKIP:
- ksft_print_msg("%s test: Skipping test\n", test_name);
+ ksft_test_result_skip("%s test: Skipping test\n", test_name);
ret = 0;
break;
case PIDFD_XFAIL:
int perf_event_disable(int fd);
int perf_event_reset(int fd);
+struct perf_event_read {
+ __u64 nr;
+ __u64 l1d_misses;
+};
+
#if !defined(__GLIBC_PREREQ) || !__GLIBC_PREREQ(2, 30)
#include <unistd.h>
#include <sys/syscall.h>
# SPDX-License-Identifier: GPL-2.0-only
rfi_flush
+entry_flush
# SPDX-License-Identifier: GPL-2.0+
-TEST_GEN_PROGS := rfi_flush spectre_v2
+TEST_GEN_PROGS := rfi_flush entry_flush spectre_v2
top_srcdir = ../../../../..
CFLAGS += -I../../../../../usr/include
$(OUTPUT)/spectre_v2: CFLAGS += -m64
$(OUTPUT)/spectre_v2: ../pmu/event.c branch_loops.S
+$(OUTPUT)/rfi_flush: flush_utils.c
+$(OUTPUT)/entry_flush: flush_utils.c
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#define __SANE_USERSPACE_TYPES__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <malloc.h>
+#include <unistd.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include "utils.h"
+#include "flush_utils.h"
+
+int entry_flush_test(void)
+{
+ char *p;
+ int repetitions = 10;
+ int fd, passes = 0, iter, rc = 0;
+ struct perf_event_read v;
+ __u64 l1d_misses_total = 0;
+ unsigned long iterations = 100000, zero_size = 24 * 1024;
+ unsigned long l1d_misses_expected;
+ int rfi_flush_orig;
+ int entry_flush, entry_flush_orig;
+
+ SKIP_IF(geteuid() != 0);
+
+ // The PMU event we use only works on Power7 or later
+ SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
+
+ if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) {
+ perror("Unable to read powerpc/rfi_flush debugfs file");
+ SKIP_IF(1);
+ }
+
+ if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) {
+ perror("Unable to read powerpc/entry_flush debugfs file");
+ SKIP_IF(1);
+ }
+
+ if (rfi_flush_orig != 0) {
+ if (write_debugfs_file("powerpc/rfi_flush", 0) < 0) {
+ perror("error writing to powerpc/rfi_flush debugfs file");
+ FAIL_IF(1);
+ }
+ }
+
+ entry_flush = entry_flush_orig;
+
+ fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1);
+ FAIL_IF(fd < 0);
+
+ p = (char *)memalign(zero_size, CACHELINE_SIZE);
+
+ FAIL_IF(perf_event_enable(fd));
+
+ // disable L1 prefetching
+ set_dscr(1);
+
+ iter = repetitions;
+
+ /*
+ * We expect to see l1d miss for each cacheline access when entry_flush
+ * is set. Allow a small variation on this.
+ */
+ l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2);
+
+again:
+ FAIL_IF(perf_event_reset(fd));
+
+ syscall_loop(p, iterations, zero_size);
+
+ FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v));
+
+ if (entry_flush && v.l1d_misses >= l1d_misses_expected)
+ passes++;
+ else if (!entry_flush && v.l1d_misses < (l1d_misses_expected / 2))
+ passes++;
+
+ l1d_misses_total += v.l1d_misses;
+
+ while (--iter)
+ goto again;
+
+ if (passes < repetitions) {
+ printf("FAIL (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d failures]\n",
+ entry_flush, l1d_misses_total, entry_flush ? '<' : '>',
+ entry_flush ? repetitions * l1d_misses_expected :
+ repetitions * l1d_misses_expected / 2,
+ repetitions - passes, repetitions);
+ rc = 1;
+ } else {
+ printf("PASS (L1D misses with entry_flush=%d: %llu %c %lu) [%d/%d pass]\n",
+ entry_flush, l1d_misses_total, entry_flush ? '>' : '<',
+ entry_flush ? repetitions * l1d_misses_expected :
+ repetitions * l1d_misses_expected / 2,
+ passes, repetitions);
+ }
+
+ if (entry_flush == entry_flush_orig) {
+ entry_flush = !entry_flush_orig;
+ if (write_debugfs_file("powerpc/entry_flush", entry_flush) < 0) {
+ perror("error writing to powerpc/entry_flush debugfs file");
+ return 1;
+ }
+ iter = repetitions;
+ l1d_misses_total = 0;
+ passes = 0;
+ goto again;
+ }
+
+ perf_event_disable(fd);
+ close(fd);
+
+ set_dscr(0);
+
+ if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) {
+ perror("unable to restore original value of powerpc/rfi_flush debugfs file");
+ return 1;
+ }
+
+ if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) {
+ perror("unable to restore original value of powerpc/entry_flush debugfs file");
+ return 1;
+ }
+
+ return rc;
+}
+
+int main(int argc, char *argv[])
+{
+ return test_harness(entry_flush_test, "entry_flush_test");
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#define __SANE_USERSPACE_TYPES__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include "utils.h"
+#include "flush_utils.h"
+
+static inline __u64 load(void *addr)
+{
+ __u64 tmp;
+
+ asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr));
+
+ return tmp;
+}
+
+void syscall_loop(char *p, unsigned long iterations,
+ unsigned long zero_size)
+{
+ for (unsigned long i = 0; i < iterations; i++) {
+ for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE)
+ load(p + j);
+ getppid();
+ }
+}
+
+static void sigill_handler(int signr, siginfo_t *info, void *unused)
+{
+ static int warned;
+ ucontext_t *ctx = (ucontext_t *)unused;
+ unsigned long *pc = &UCONTEXT_NIA(ctx);
+
+ /* mtspr 3,RS to check for move to DSCR below */
+ if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) {
+ if (!warned++)
+ printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
+ *pc += 4;
+ } else {
+ printf("SIGILL at %p\n", pc);
+ abort();
+ }
+}
+
+void set_dscr(unsigned long val)
+{
+ static int init;
+ struct sigaction sa;
+
+ if (!init) {
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = sigill_handler;
+ sa.sa_flags = SA_SIGINFO;
+ if (sigaction(SIGILL, &sa, NULL))
+ perror("sigill_handler");
+ init = 1;
+ }
+
+ asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+/*
+ * Copyright 2018 IBM Corporation.
+ */
+
+#ifndef _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H
+#define _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H
+
+#define CACHELINE_SIZE 128
+
+void syscall_loop(char *p, unsigned long iterations,
+ unsigned long zero_size);
+
+void set_dscr(unsigned long val);
+
+#endif /* _SELFTESTS_POWERPC_SECURITY_FLUSH_UTILS_H */
#include <stdint.h>
#include <malloc.h>
#include <unistd.h>
-#include <signal.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include "utils.h"
+#include "flush_utils.h"
-#define CACHELINE_SIZE 128
-
-struct perf_event_read {
- __u64 nr;
- __u64 l1d_misses;
-};
-
-static inline __u64 load(void *addr)
-{
- __u64 tmp;
-
- asm volatile("ld %0,0(%1)" : "=r"(tmp) : "b"(addr));
-
- return tmp;
-}
-
-static void syscall_loop(char *p, unsigned long iterations,
- unsigned long zero_size)
-{
- for (unsigned long i = 0; i < iterations; i++) {
- for (unsigned long j = 0; j < zero_size; j += CACHELINE_SIZE)
- load(p + j);
- getppid();
- }
-}
-
-static void sigill_handler(int signr, siginfo_t *info, void *unused)
-{
- static int warned = 0;
- ucontext_t *ctx = (ucontext_t *)unused;
- unsigned long *pc = &UCONTEXT_NIA(ctx);
-
- /* mtspr 3,RS to check for move to DSCR below */
- if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) {
- if (!warned++)
- printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n");
- *pc += 4;
- } else {
- printf("SIGILL at %p\n", pc);
- abort();
- }
-}
-
-static void set_dscr(unsigned long val)
-{
- static int init = 0;
- struct sigaction sa;
-
- if (!init) {
- memset(&sa, 0, sizeof(sa));
- sa.sa_sigaction = sigill_handler;
- sa.sa_flags = SA_SIGINFO;
- if (sigaction(SIGILL, &sa, NULL))
- perror("sigill_handler");
- init = 1;
- }
-
- asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR));
-}
int rfi_flush_test(void)
{
__u64 l1d_misses_total = 0;
unsigned long iterations = 100000, zero_size = 24 * 1024;
unsigned long l1d_misses_expected;
- int rfi_flush_org, rfi_flush;
+ int rfi_flush_orig, rfi_flush;
+ int have_entry_flush, entry_flush_orig;
SKIP_IF(geteuid() != 0);
// The PMU event we use only works on Power7 or later
SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
- if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_org)) {
+ if (read_debugfs_file("powerpc/rfi_flush", &rfi_flush_orig) < 0) {
perror("Unable to read powerpc/rfi_flush debugfs file");
SKIP_IF(1);
}
- rfi_flush = rfi_flush_org;
+ if (read_debugfs_file("powerpc/entry_flush", &entry_flush_orig) < 0) {
+ have_entry_flush = 0;
+ } else {
+ have_entry_flush = 1;
+
+ if (entry_flush_orig != 0) {
+ if (write_debugfs_file("powerpc/entry_flush", 0) < 0) {
+ perror("error writing to powerpc/entry_flush debugfs file");
+ return 1;
+ }
+ }
+ }
+
+ rfi_flush = rfi_flush_orig;
fd = perf_event_open_counter(PERF_TYPE_RAW, /* L1d miss */ 0x400f0, -1);
FAIL_IF(fd < 0);
FAIL_IF(perf_event_enable(fd));
+ // disable L1 prefetching
set_dscr(1);
iter = repetitions;
repetitions * l1d_misses_expected / 2,
passes, repetitions);
- if (rfi_flush == rfi_flush_org) {
- rfi_flush = !rfi_flush_org;
+ if (rfi_flush == rfi_flush_orig) {
+ rfi_flush = !rfi_flush_orig;
if (write_debugfs_file("powerpc/rfi_flush", rfi_flush) < 0) {
perror("error writing to powerpc/rfi_flush debugfs file");
return 1;
set_dscr(0);
- if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_org) < 0) {
+ if (write_debugfs_file("powerpc/rfi_flush", rfi_flush_orig) < 0) {
perror("unable to restore original value of powerpc/rfi_flush debugfs file");
return 1;
}
+ if (have_entry_flush) {
+ if (write_debugfs_file("powerpc/entry_flush", entry_flush_orig) < 0) {
+ perror("unable to restore original value of powerpc/entry_flush "
+ "debugfs file");
+ return 1;
+ }
+ }
+
return rc;
}
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
/* Test that /proc/loadavg correctly reports last pid in pid namespace. */
-#define _GNU_SOURCE
#include <errno.h>
#include <sched.h>
#include <sys/types.h>
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
-#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/types.h>
*/
// Test that values in /proc/uptime increment monotonically
// while shifting across CPUs.
-#define _GNU_SOURCE
#undef NDEBUG
#include <assert.h>
#include <unistd.h>
* and the code is stored as a positive value. \
*/ \
if (_result < 0) { \
- SYSCALL_RET(_regs) = -result; \
+ SYSCALL_RET(_regs) = -_result; \
(_regs).ccr |= 0x10000000; \
} else { \
- SYSCALL_RET(_regs) = result; \
+ SYSCALL_RET(_regs) = _result; \
(_regs).ccr &= ~0x10000000; \
} \
} while (0)
#define SYSCALL_RET(_regs) (_regs).a[(_regs).windowbase * 4 + 2]
#elif defined(__sh__)
# define ARCH_REGS struct pt_regs
-# define SYSCALL_NUM(_regs) (_regs).gpr[3]
-# define SYSCALL_RET(_regs) (_regs).gpr[0]
+# define SYSCALL_NUM(_regs) (_regs).regs[3]
+# define SYSCALL_RET(_regs) (_regs).regs[0]
#else
# error "Do not know how to find your architecture's registers and syscalls"
#endif
CONFIG_NET_IFE_SKBTCINDEX=m
CONFIG_NET_SCH_FIFO=y
CONFIG_NET_SCH_ETS=m
+CONFIG_NET_SCH_RED=m
#
## Network testing
],
"cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
"expExitCode": "0",
- "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+ "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
"matchPattern": "filter protocol ip pref 1 flower.*handle",
"matchCount": "1",
"teardown": [
],
"cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop",
"expExitCode": "0",
- "verifyCmd": "$TC filter show terse dev $DEV2 ingress",
+ "verifyCmd": "$TC -br filter show dev $DEV2 ingress",
"matchPattern": " dst_mac e4:11:22:11:4a:51",
"matchCount": "0",
"teardown": [
TEST_GEN_FILES += $(BINARIES_64)
endif
else
+
+ifneq (,$(findstring $(ARCH),powerpc))
TEST_GEN_FILES += protection_keys
endif
+endif
+
ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
TEST_GEN_FILES += va_128TBswitch
TEST_GEN_FILES += virtual_address_range
return ret;
}
-
static void hugetlb_allocate_area(void **alloc_area)
{
void *area_alias = NULL;
char **alloc_area_alias;
+
*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
(map_shared ? MAP_SHARED : MAP_PRIVATE) |
MAP_HUGETLB,
huge_fd, *alloc_area == area_src ? 0 :
nr_pages * page_size);
if (*alloc_area == MAP_FAILED) {
- fprintf(stderr, "mmap of hugetlbfs file failed\n");
- *alloc_area = NULL;
+ perror("mmap of hugetlbfs file failed");
+ goto fail;
}
if (map_shared) {
huge_fd, *alloc_area == area_src ? 0 :
nr_pages * page_size);
if (area_alias == MAP_FAILED) {
- if (munmap(*alloc_area, nr_pages * page_size) < 0) {
- perror("hugetlb munmap");
- exit(1);
- }
- *alloc_area = NULL;
- return;
+ perror("mmap of hugetlb file alias failed");
+ goto fail_munmap;
}
}
+
if (*alloc_area == area_src) {
huge_fd_off0 = *alloc_area;
alloc_area_alias = &area_src_alias;
}
if (area_alias)
*alloc_area_alias = area_alias;
+
+ return;
+
+fail_munmap:
+ if (munmap(*alloc_area, nr_pages * page_size) < 0) {
+ perror("hugetlb munmap");
+ exit(1);
+ }
+fail:
+ *alloc_area = NULL;
}
static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset)
n2 ping -W 1 -c 1 192.168.241.1
n1 wg set wg0 peer "$pub2" persistent-keepalive 0
+# Test that sk_bound_dev_if works
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2
+# What about when the mark changes and the packet must be rerouted?
+n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1
+n1 ping -c 1 -W 1 192.168.241.2 # First the boring case
+n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case
+n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1
+
# Test that onion routing works, even when it loops
n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5
ip1 addr add 192.168.242.1/24 dev wg0
CONFIG_NETFILTER_XTABLES=y
CONFIG_NETFILTER_XT_NAT=y
CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MARK=y
CONFIG_NF_CONNTRACK_IPV4=y
CONFIG_NF_NAT_IPV4=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_MANGLE=y
CONFIG_IP_NF_NAT=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTIPLE_TABLES=y
git.samba.org / sfrench / cifs-2.6.git / commitdiff