Ben Gardner <bgardner@wabtec.com>
Ben M Cahill <ben.m.cahill@intel.com>
Björn Steinbrink <B.Steinbrink@gmx.de>
+Björn Töpel <bjorn@kernel.org> <bjorn.topel@gmail.com>
+Björn Töpel <bjorn@kernel.org> <bjorn.topel@intel.com>
Boris Brezillon <bbrezillon@kernel.org> <b.brezillon.dev@gmail.com>
Boris Brezillon <bbrezillon@kernel.org> <b.brezillon@overkiz.com>
Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
S: Las Heras, Mendoza CP 5539
S: Argentina
+N: Jay Cliburn
+E: jcliburn@gmail.com
+D: ATLX Ethernet drivers
+
N: Steven P. Cole
E: scole@lanl.gov
E: elenstev@mesatop.com
D: ISDN Maintainer
S: USA
+N: Gerrit Renker
+E: gerrit@erg.abdn.ac.uk
+D: DCCP protocol support.
+
N: Philip Gladstone
E: philip@gladstonefamily.net
D: Kernel / timekeeping stuff
E: seasons@makosteszta.sote.hu
D: Original author of software suspend
+N: Alexey Kuznetsov
+E: kuznet@ms2.inr.ac.ru
+D: Author and maintainer of large parts of the networking stack
+
N: Jaroslav Kysela
E: perex@perex.cz
W: https://www.perex.cz
E: wolfgang@iksw-muees.de
D: Auerswald USB driver
+N: Shrijeet Mukherjee
+E: shrijeet@gmail.com
+D: Network routing domains (VRF).
+
N: Paul Mundt
E: paul.mundt@gmail.com
D: SuperH maintainer
S: 16 Baliqiao Nanjie, Beijing 101100
S: People's Repulic of China
+N: Aviad Yehezkel
+E: aviadye@nvidia.com
+D: Kernel TLS implementation and offload support.
+
N: Victor Yodaiken
E: yodaiken@fsmlabs.com
D: RTLinux (RealTime Linux)
S: Bellevue, Washington 98007
S: USA
+N: Wensong Zhang
+E: wensong@linux-vs.org
+D: IP virtual server (IPVS).
+
N: Haojian Zhuang
E: haojian.zhuang@gmail.com
D: MMP support
the bottom of the diagram above).
Plumbing this into the full grace-period execution is described
-`below <#Forcing%20Quiescent%20States>`__.
+`below <Forcing Quiescent States_>`__.
CPU-Hotplug Interface
^^^^^^^^^^^^^^^^^^^^^
grace period.
Plumbing this into the full grace-period execution is described
-`below <#Forcing%20Quiescent%20States>`__.
+`below <Forcing Quiescent States_>`__.
Forcing Quiescent States
^^^^^^^^^^^^^^^^^^^^^^^^
| RCU. But this diagram is complex enough as it is, so simplicity |
| overrode accuracy. You can think of it as poetic license, or you can |
| think of it as misdirection that is resolved in the |
-| `stitched-together diagram <#Putting%20It%20All%20Together>`__. |
+| `stitched-together diagram <Putting It All Together_>`__. |
+-----------------------------------------------------------------------+
Grace-Period Cleanup
that runs on some other CPU, proper ordering must in place in both the
callback function and the task being awakened. To see why this is
important, consider the top half of the `grace-period
-cleanup <#Grace-Period%20Cleanup>`__ diagram. The callback might be
+cleanup`_ diagram. The callback might be
running on a CPU corresponding to the leftmost leaf ``rcu_node``
structure, and awaken a task that is to run on a CPU corresponding to
the rightmost leaf ``rcu_node`` structure, and the grace-period kernel
#. `Other RCU Flavors`_
#. `Possible Future Changes`_
-This is followed by a `summary <#Summary>`__, however, the answers to
+This is followed by a summary_, however, the answers to
each quick quiz immediately follows the quiz. Select the big white space
with your mouse to see the answer.
| case, voluntary context switch) within an RCU read-side critical |
| section. However, sleeping locks may be used within userspace RCU |
| read-side critical sections, and also within Linux-kernel sleepable |
-| RCU `(SRCU) <#Sleepable%20RCU>`__ read-side critical sections. In |
+| RCU `(SRCU) <Sleepable RCU_>`__ read-side critical sections. In |
| addition, the -rt patchset turns spinlocks into a sleeping locks so |
| that the corresponding critical sections can be preempted, which also |
| means that these sleeplockified spinlocks (but not other sleeping |
RCU <https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com>`__
was born. Josh Triplett has since taken over the small-memory banner
with his `Linux kernel tinification <https://tiny.wiki.kernel.org/>`__
-project, which resulted in `SRCU <#Sleepable%20RCU>`__ becoming optional
+project, which resulted in `SRCU <Sleepable RCU_>`__ becoming optional
for those kernels not needing it.
The remaining performance requirements are, for the most part,
the relevant Kconfig options and kernel boot parameters. RCU currently
does not do much sanity checking of these parameters, so please use
caution when changing them. Note that these forward-progress measures
-are provided only for RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
-RCU <#Tasks%20RCU>`__.
+are provided only for RCU, not for `SRCU <Sleepable RCU_>`__ or `Tasks
+RCU`_.
RCU takes the following steps in ``call_rcu()`` to encourage timely
invocation of callbacks when any given non-\ ``rcu_nocbs`` CPU has
Again, these are default values when running at ``HZ=1000``, and can be
overridden. Again, these forward-progress measures are provided only for
-RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks
-RCU <#Tasks%20RCU>`__. Even for RCU, callback-invocation forward
+RCU, not for `SRCU <Sleepable RCU_>`__ or `Tasks
+RCU`_. Even for RCU, callback-invocation forward
progress for ``rcu_nocbs`` CPUs is much less well-developed, in part
because workloads benefiting from ``rcu_nocbs`` CPUs tend to invoke
``call_rcu()`` relatively infrequently. If workloads emerge that need
The Linux kernel supports CPU hotplug, which means that CPUs can come
and go. It is of course illegal to use any RCU API member from an
-offline CPU, with the exception of `SRCU <#Sleepable%20RCU>`__ read-side
+offline CPU, with the exception of `SRCU <Sleepable RCU_>`__ read-side
critical sections. This requirement was present from day one in
DYNIX/ptx, but on the other hand, the Linux kernel's CPU-hotplug
implementation is “interesting.”
However, RCU must be reliably informed as to whether any given CPU is
currently in the idle loop, and, for ``NO_HZ_FULL``, also whether that
CPU is executing in usermode, as discussed
-`earlier <#Energy%20Efficiency>`__. It also requires that the
+`earlier <Energy Efficiency_>`__. It also requires that the
scheduling-clock interrupt be enabled when RCU needs it to be:
#. If a CPU is either idle or executing in usermode, and RCU believes it
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Expanding on the `earlier
-discussion <#Performance%20and%20Scalability>`__, RCU is used heavily by
+discussion <Performance and Scalability_>`__, RCU is used heavily by
hot code paths in performance-critical portions of the Linux kernel's
networking, security, virtualization, and scheduling code paths. RCU
must therefore use efficient implementations, especially in its
- ``name``
is an identifier string. A new /proc file will be created with this
- ``name below /proc/sys/fs/binfmt_misc``; cannot contain slashes ``/`` for
+ name below ``/proc/sys/fs/binfmt_misc``; cannot contain slashes ``/`` for
obvious reasons.
- ``type``
is the type of recognition. Give ``M`` for magic and ``E`` for extension.
``F`` - fix binary
The usual behaviour of binfmt_misc is to spawn the
binary lazily when the misc format file is invoked. However,
- this doesn``t work very well in the face of mount namespaces and
+ this doesn't work very well in the face of mount namespaces and
changeroots, so the ``F`` mode opens the binary as soon as the
emulation is installed and uses the opened image to spawn the
emulator, meaning it is always available once installed,
Because of this "piggyback" method, there is no need to change or
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.
+loader passes a longer size, the kernel fails 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
The kernel's command-line parameters
====================================
-The following is a consolidated list of the kernel parameters as
-implemented by the __setup(), core_param() and module_param() macros
+The following is a consolidated list of the kernel parameters as implemented
+by the __setup(), early_param(), core_param() and module_param() macros
and sorted into English Dictionary order (defined as ignoring all
punctuation and sorting digits before letters in a case insensitive
manner), and with descriptions where known.
ftrace_filter=[function-list]
[FTRACE] Limit the functions traced by the function
- tracer at boot up. function-list is a comma separated
+ tracer at boot up. function-list is a comma-separated
list of functions. This list can be changed at run
time by the set_ftrace_filter file in the debugfs
tracing directory.
ftrace_graph_filter=[function-list]
[FTRACE] Limit the top level callers functions traced
by the function graph tracer at boot up.
- function-list is a comma separated list of functions
+ function-list is a comma-separated list of functions
that can be changed at run time by the
set_graph_function file in the debugfs tracing directory.
ftrace_graph_notrace=[function-list]
[FTRACE] Do not trace from the functions specified in
- function-list. This list is a comma separated list of
+ function-list. This list is a comma-separated list of
functions that can be changed at run time by the
set_graph_notrace file in the debugfs tracing directory.
when set.
Format: <int>
- libata.force= [LIBATA] Force configurations. The format is comma
+ libata.force= [LIBATA] Force configurations. The format is comma-
separated list of "[ID:]VAL" where ID is
PORT[.DEVICE]. PORT and DEVICE are decimal numbers
matching port, link or device. Basically, it matches
stacktrace_filter=[function-list]
[FTRACE] Limit the functions that the stack tracer
- will trace at boot up. function-list is a comma separated
+ will trace at boot up. function-list is a comma-separated
list of functions. This list can be changed at run
time by the stack_trace_filter file in the debugfs
tracing directory. Note, this enables stack tracing
trace_event=[event-list]
[FTRACE] Set and start specified trace events in order
to facilitate early boot debugging. The event-list is a
- comma separated list of trace events to enable. See
+ comma-separated list of trace events to enable. See
also Documentation/trace/events.rst
trace_options=[option-list]
This option is obsoleted by the "nopv" option, which
has equivalent effect for XEN platform.
+ xen_no_vector_callback
+ [KNL,X86,XEN] Disable the vector callback for Xen
+ event channel interrupts.
+
xen_scrub_pages= [XEN]
Boolean option to control scrubbing pages before giving them back
to Xen, for use by other domains. Can be also changed at runtime
of the system. When the system is not loaded, most of the memory is free
and allocation requests will be satisfied immediately from the free
pages supply. As the load increases, the amount of the free pages goes
-down and when it reaches a certain threshold (high watermark), an
+down and when it reaches a certain threshold (low watermark), an
allocation request will awaken the ``kswapd`` daemon. It will
asynchronously scan memory pages and either just free them if the data
they contain is available elsewhere, or evict to the backing storage
.. toctree::
:maxdepth: 1
- atomic_ops
refcount-vs-atomic
irq/index
local_ops
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
%YAML 1.2
---
$id: http://devicetree.org/schemas/dma/ti/k3-bcdma.yaml#
title: Texas Instruments K3 DMSS BCDMA Device Tree Bindings
maintainers:
- - Peter Ujfalusi <peter.ujfalusi@ti.com>
+ - Peter Ujfalusi <peter.ujfalusi@gmail.com>
description: |
The Block Copy DMA (BCDMA) is intended to perform similar functions as the TR
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
%YAML 1.2
---
$id: http://devicetree.org/schemas/dma/ti/k3-pktdma.yaml#
title: Texas Instruments K3 DMSS PKTDMA Device Tree Bindings
maintainers:
- - Peter Ujfalusi <peter.ujfalusi@ti.com>
+ - Peter Ujfalusi <peter.ujfalusi@gmail.com>
description: |
The Packet DMA (PKTDMA) is intended to perform similar functions as the packet
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2019 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
%YAML 1.2
---
$id: http://devicetree.org/schemas/dma/ti/k3-udma.yaml#
title: Texas Instruments K3 NAVSS Unified DMA Device Tree Bindings
maintainers:
- - Peter Ujfalusi <peter.ujfalusi@ti.com>
+ - Peter Ujfalusi <peter.ujfalusi@gmail.com>
description: |
The UDMA-P is intended to perform similar (but significantly upgraded)
enum:
- renesas,etheravb-r8a774a1
- renesas,etheravb-r8a774b1
+ - renesas,etheravb-r8a774e1
- renesas,etheravb-r8a7795
- renesas,etheravb-r8a7796
- renesas,etheravb-r8a77961
* snps,route-dcbcp, DCB Control Packets
* snps,route-up, Untagged Packets
* snps,route-multi-broad, Multicast & Broadcast Packets
- * snps,priority, RX queue priority (Range 0x0 to 0xF)
+ * snps,priority, bitmask of the tagged frames priorities assigned to
+ the queue
snps,mtl-tx-config:
$ref: /schemas/types.yaml#/definitions/phandle
* snps,idle_slope, unlock on WoL
* snps,high_credit, max write outstanding req. limit
* snps,low_credit, max read outstanding req. limit
- * snps,priority, TX queue priority (Range 0x0 to 0xF)
+ * snps,priority, bitmask of the priorities assigned to the queue.
+ When a PFC frame is received with priorities matching the bitmask,
+ the queue is blocked from transmitting for the pause time specified
+ in the PFC frame.
snps,reset-gpio:
deprecated: true
properties:
compatible:
enum:
- - nxp,pf8x00
+ - nxp,pf8100
+ - nxp,pf8121a
+ - nxp,pf8200
reg:
maxItems: 1
#size-cells = <0>;
pmic@8 {
- compatible = "nxp,pf8x00";
+ compatible = "nxp,pf8100";
reg = <0x08>;
regulators {
Definition: Must be one of below:
"qcom,pm8005-rpmh-regulators"
"qcom,pm8009-rpmh-regulators"
+ "qcom,pm8009-1-rpmh-regulators"
"qcom,pm8150-rpmh-regulators"
"qcom,pm8150l-rpmh-regulators"
"qcom,pm8350-rpmh-regulators"
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
%YAML 1.2
---
$id: http://devicetree.org/schemas/sound/ti,j721e-cpb-audio.yaml#
title: Texas Instruments J721e Common Processor Board Audio Support
maintainers:
- - Peter Ujfalusi <peter.ujfalusi@ti.com>
+ - Peter Ujfalusi <peter.ujfalusi@gmail.com>
description: |
The audio support on the board is using pcm3168a codec connected to McASP10
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2020 Texas Instruments Incorporated
+# Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
%YAML 1.2
---
$id: http://devicetree.org/schemas/sound/ti,j721e-cpb-ivi-audio.yaml#
title: Texas Instruments J721e Common Processor Board Audio Support
maintainers:
- - Peter Ujfalusi <peter.ujfalusi@ti.com>
+ - Peter Ujfalusi <peter.ujfalusi@gmail.com>
description: |
The Infotainment board plugs into the Common Processor Board, the support of the
properties:
compatible:
- items:
+ oneOf:
- const: ti,j721e-usb
+ - const: ti,am64-usb
+ - items:
+ - const: ti,j721e-usb
+ - const: ti,am64-usb
reg:
description: module registers
those versions, you should run ``pip install 'docutils==0.12'``.
#) It is recommended to use the RTD theme for html output. Depending
- on the Sphinx version, it should be installed in separate,
+ on the Sphinx version, it should be installed separately,
with ``pip install sphinx_rtd_theme``.
- #) Some ReST pages contain math expressions. Due to the way Sphinx work,
+ #) Some ReST pages contain math expressions. Due to the way Sphinx works,
those expressions are written using LaTeX notation. It needs texlive
- installed with amdfonts and amsmath in order to evaluate them.
+ installed with amsfonts and amsmath in order to evaluate them.
In summary, if you want to install Sphinx version 1.7.9, you should do::
============
The usual way to generate the documentation is to run ``make htmldocs`` or
-``make pdfdocs``. There are also other formats available, see the documentation
+``make pdfdocs``. There are also other formats available: see the documentation
section of ``make help``. The generated documentation is placed in
format-specific subdirectories under ``Documentation/output``.
- head col 3
- head col 4
- * - column 1
+ * - row 1
- field 1.1
- field 1.2 with autospan
- * - column 2
+ * - row 2
- field 2.1
- :rspan:`1` :cspan:`1` field 2.2 - 3.3
* .. _`last row`:
- - column 3
+ - row 3
Rendered as:
- head col 3
- head col 4
- * - column 1
+ * - row 1
- field 1.1
- field 1.2 with autospan
- * - column 2
+ * - row 2
- field 2.1
- :rspan:`1` :cspan:`1` field 2.2 - 3.3
* .. _`last row`:
- - column 3
+ - row 3
Cross-referencing
-----------------
If you want to add an image, you should use the ``kernel-figure`` and
``kernel-image`` directives. E.g. to insert a figure with a scalable
-image format use SVG (:ref:`svg_image_example`)::
+image format, use SVG (:ref:`svg_image_example`)::
.. kernel-figure:: svg_image.svg
:alt: simple SVG image
SVG image example
-The kernel figure (and image) directive support **DOT** formatted files, see
+The kernel figure (and image) directive supports **DOT** formatted files, see
* DOT: http://graphviz.org/pdf/dotguide.pdf
* Graphviz: http://www.graphviz.org/content/dot-language
DOT's hello world example
-Embed *render* markups (or languages) like Graphviz's **DOT** is provided by the
+Embedded *render* markups (or languages) like Graphviz's **DOT** are provided by the
``kernel-render`` directives.::
.. kernel-render:: DOT
}
How this will be rendered depends on the installed tools. If Graphviz is
-installed, you will see an vector image. If not the raw markup is inserted as
+installed, you will see a vector image. If not, the raw markup is inserted as
*literal-block* (:ref:`hello_dot_render`).
.. _hello_dot_render:
The *render* directive has all the options known from the *figure* directive,
plus option ``caption``. If ``caption`` has a value, a *figure* node is
-inserted. If not, a *image* node is inserted. A ``caption`` is also needed, if
-you want to refer it (:ref:`hello_svg_render`).
+inserted. If not, an *image* node is inserted. A ``caption`` is also needed, if
+you want to refer to it (:ref:`hello_svg_render`).
Embedded **SVG**::
0x00000010 Memory Uncorrectable non-fatal
0x00000020 Memory Uncorrectable fatal
0x00000040 PCI Express Correctable
- 0x00000080 PCI Express Uncorrectable fatal
- 0x00000100 PCI Express Uncorrectable non-fatal
+ 0x00000080 PCI Express Uncorrectable non-fatal
+ 0x00000100 PCI Express Uncorrectable fatal
0x00000200 Platform Correctable
0x00000400 Platform Uncorrectable non-fatal
0x00000800 Platform Uncorrectable fatal
.. SPDX-License-Identifier: GPL-2.0-or-later
Kernel driver sbtsi_temp
-==================
+========================
Supported hardware:
explicitly added to $(targets).
Assignments to $(targets) are without $(obj)/ prefix. if_changed may be
- used in conjunction with custom rules as defined in "3.9 Custom Rules".
+ used in conjunction with custom rules as defined in "3.11 Custom Rules".
Note: It is a typical mistake to forget the FORCE prerequisite.
Another common pitfall is that whitespace is sometimes significant; for
your task will suspend itself, and be woken up when the mutex is
released. This means the CPU can do something else while you are
waiting. There are many cases when you simply can't sleep (see
-`What Functions Are Safe To Call From Interrupts? <#sleeping-things>`__),
+`What Functions Are Safe To Call From Interrupts?`_),
and so have to use a spinlock instead.
Neither type of lock is recursive: see
-`Deadlock: Simple and Advanced <#deadlock>`__.
+`Deadlock: Simple and Advanced`_.
Locks and Uniprocessor Kernels
------------------------------
Note that you can also use spin_lock_irq() or
spin_lock_irqsave() here, which stop hardware interrupts
-as well: see `Hard IRQ Context <#hard-irq-context>`__.
+as well: see `Hard IRQ Context`_.
This works perfectly for UP as well: the spin lock vanishes, and this
macro simply becomes local_bh_disable()
~~~~~~~~~~~~~~~~
The same softirq can run on the other CPUs: you can use a per-CPU array
-(see `Per-CPU Data <#per-cpu-data>`__) for better performance. If you're
+(see `Per-CPU Data`_) for better performance. If you're
going so far as to use a softirq, you probably care about scalable
performance enough to justify the extra complexity.
NPA Reporters
-------------
-The NPA reporters are responsible for reporting and recovering the following group of errors
+The NPA reporters are responsible for reporting and recovering the following group of errors:
+
1. GENERAL events
+
- Error due to operation of unmapped PF.
- Error due to disabled alloc/free for other HW blocks (NIX, SSO, TIM, DPI and AURA).
+
2. ERROR events
+
- Fault due to NPA_AQ_INST_S read or NPA_AQ_RES_S write.
- AQ Doorbell Error.
+
3. RAS events
+
- RAS Error Reporting for NPA_AQ_INST_S/NPA_AQ_RES_S.
+
4. RVU events
+
- Error due to unmapped slot.
-Sample Output
--------------
-~# devlink health
-pci/0002:01:00.0:
- reporter hw_npa_intr
- state healthy error 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
- reporter hw_npa_gen
- state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
- reporter hw_npa_err
- state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
- reporter hw_npa_ras
- state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
+Sample Output::
+
+ ~# devlink health
+ pci/0002:01:00.0:
+ reporter hw_npa_intr
+ state healthy error 2872 recover 2872 last_dump_date 2020-12-10 last_dump_time 09:39:09 grace_period 0 auto_recover true auto_dump true
+ reporter hw_npa_gen
+ state healthy error 2872 recover 2872 last_dump_date 2020-12-11 last_dump_time 04:43:04 grace_period 0 auto_recover true auto_dump true
+ reporter hw_npa_err
+ state healthy error 2871 recover 2871 last_dump_date 2020-12-10 last_dump_time 09:39:17 grace_period 0 auto_recover true auto_dump true
+ reporter hw_npa_ras
+ state healthy error 0 recover 0 last_dump_date 2020-12-10 last_dump_time 09:32:40 grace_period 0 auto_recover true auto_dump true
Each reporter dumps the
+
- Error Type
- Error Register value
- Reason in words
-For eg:
-~# devlink health dump show pci/0002:01:00.0 reporter hw_npa_gen
- NPA_AF_GENERAL:
- NPA General Interrupt Reg : 1
- NIX0: free disabled RX
-~# devlink health dump show pci/0002:01:00.0 reporter hw_npa_intr
- NPA_AF_RVU:
- NPA RVU Interrupt Reg : 1
- Unmap Slot Error
-~# devlink health dump show pci/0002:01:00.0 reporter hw_npa_err
- NPA_AF_ERR:
- NPA Error Interrupt Reg : 4096
- AQ Doorbell Error
+For example::
+
+ ~# devlink health dump show pci/0002:01:00.0 reporter hw_npa_gen
+ NPA_AF_GENERAL:
+ NPA General Interrupt Reg : 1
+ NIX0: free disabled RX
+ ~# devlink health dump show pci/0002:01:00.0 reporter hw_npa_intr
+ NPA_AF_RVU:
+ NPA RVU Interrupt Reg : 1
+ Unmap Slot Error
+ ~# devlink health dump show pci/0002:01:00.0 reporter hw_npa_err
+ NPA_AF_ERR:
+ NPA Error Interrupt Reg : 4096
+ AQ Doorbell Error
netdev FAQ
==========
-Q: What is netdev?
-------------------
-A: It is a mailing list for all network-related Linux stuff. This
+What is netdev?
+---------------
+It is a mailing list for all network-related Linux stuff. This
includes anything found under net/ (i.e. core code like IPv6) and
drivers/net (i.e. hardware specific drivers) in the Linux source tree.
Linux development (i.e. RFC, review, comments, etc.) takes place on
netdev.
-Q: How do the changes posted to netdev make their way into Linux?
------------------------------------------------------------------
-A: There are always two trees (git repositories) in play. Both are
+How do the changes posted to netdev make their way into Linux?
+--------------------------------------------------------------
+There are always two trees (git repositories) in play. Both are
driven by David Miller, the main network maintainer. There is the
``net`` tree, and the ``net-next`` tree. As you can probably guess from
the names, the ``net`` tree is for fixes to existing code already in the
- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
-Q: How often do changes from these trees make it to the mainline Linus tree?
-----------------------------------------------------------------------------
-A: To understand this, you need to know a bit of background information on
+How often do changes from these trees make it to the mainline Linus tree?
+-------------------------------------------------------------------------
+To understand this, you need to know a bit of background information on
the cadence of Linux development. Each new release starts off with a
two week "merge window" where the main maintainers feed their new stuff
to Linus for merging into the mainline tree. After the two weeks, the
Finally, the vX.Y gets released, and the whole cycle starts over.
-Q: So where are we now in this cycle?
+So where are we now in this cycle?
+----------------------------------
Load the mainline (Linus) page here:
the dev cycle. If it was tagged rc7 a week ago, then a release is
probably imminent.
-Q: How do I indicate which tree (net vs. net-next) my patch should be in?
--------------------------------------------------------------------------
-A: Firstly, think whether you have a bug fix or new "next-like" content.
+How do I indicate which tree (net vs. net-next) my patch should be in?
+----------------------------------------------------------------------
+Firstly, think whether you have a bug fix or new "next-like" content.
Then once decided, assuming that you use git, use the prefix flag, i.e.
::
can manually change it yourself with whatever MUA you are comfortable
with.
-Q: I sent a patch and I'm wondering what happened to it?
---------------------------------------------------------
-Q: How can I tell whether it got merged?
-A: Start by looking at the main patchworks queue for netdev:
+I sent a patch and I'm wondering what happened to it - how can I tell whether it got merged?
+--------------------------------------------------------------------------------------------
+Start by looking at the main patchworks queue for netdev:
https://patchwork.kernel.org/project/netdevbpf/list/
The "State" field will tell you exactly where things are at with your
patch.
-Q: The above only says "Under Review". How can I find out more?
-----------------------------------------------------------------
-A: Generally speaking, the patches get triaged quickly (in less than
+The above only says "Under Review". How can I find out more?
+-------------------------------------------------------------
+Generally speaking, the patches get triaged quickly (in less than
48h). So be patient. Asking the maintainer for status updates on your
patch is a good way to ensure your patch is ignored or pushed to the
bottom of the priority list.
-Q: I submitted multiple versions of the patch series
-----------------------------------------------------
-Q: should I directly update patchwork for the previous versions of these
-patch series?
-A: No, please don't interfere with the patch status on patchwork, leave
+I submitted multiple versions of the patch series. Should I directly update patchwork for the previous versions of these patch series?
+--------------------------------------------------------------------------------------------------------------------------------------
+No, please don't interfere with the patch status on patchwork, leave
it to the maintainer to figure out what is the most recent and current
version that should be applied. If there is any doubt, the maintainer
will reply and ask what should be done.
-Q: I made changes to only a few patches in a patch series should I resend only those changed?
----------------------------------------------------------------------------------------------
-A: No, please resend the entire patch series and make sure you do number your
+I made changes to only a few patches in a patch series should I resend only those changed?
+------------------------------------------------------------------------------------------
+No, please resend the entire patch series and make sure you do number your
patches such that it is clear this is the latest and greatest set of patches
that can be applied.
-Q: I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
--------------------------------------------------------------------------------------------------------------------------------------------
-A: There is no revert possible, once it is pushed out, it stays like that.
+I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
+----------------------------------------------------------------------------------------------------------------------------------------
+There is no revert possible, once it is pushed out, it stays like that.
Please send incremental versions on top of what has been merged in order to fix
the patches the way they would look like if your latest patch series was to be
merged.
-Q: How can I tell what patches are queued up for backporting to the various stable releases?
---------------------------------------------------------------------------------------------
-A: Normally Greg Kroah-Hartman collects stable commits himself, but for
+How can I tell what patches are queued up for backporting to the various stable releases?
+-----------------------------------------------------------------------------------------
+Normally Greg Kroah-Hartman collects stable commits himself, but for
networking, Dave collects up patches he deems critical for the
networking subsystem, and then hands them off to Greg.
releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
stable/stable-queue$
-Q: I see a network patch and I think it should be backported to stable.
------------------------------------------------------------------------
-Q: Should I request it via stable@vger.kernel.org like the references in
-the kernel's Documentation/process/stable-kernel-rules.rst file say?
-A: No, not for networking. Check the stable queues as per above first
+I see a network patch and I think it should be backported to stable. Should I request it via stable@vger.kernel.org like the references in the kernel's Documentation/process/stable-kernel-rules.rst file say?
+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+No, not for networking. Check the stable queues as per above first
to see if it is already queued. If not, then send a mail to netdev,
listing the upstream commit ID and why you think it should be a stable
candidate.
scrambling to request a commit be added the day after it appears should
be avoided.
-Q: I have created a network patch and I think it should be backported to stable.
---------------------------------------------------------------------------------
-Q: Should I add a Cc: stable@vger.kernel.org like the references in the
-kernel's Documentation/ directory say?
-A: No. See above answer. In short, if you think it really belongs in
+I have created a network patch and I think it should be backported to stable. Should I add a Cc: stable@vger.kernel.org like the references in the kernel's Documentation/ directory say?
+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+No. See above answer. In short, if you think it really belongs in
stable, then ensure you write a decent commit log that describes who
gets impacted by the bug fix and how it manifests itself, and when the
bug was introduced. If you do that properly, then the commit will get
:ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>`
to temporarily embed that information into the patch that you send.
-Q: Are all networking bug fixes backported to all stable releases?
-------------------------------------------------------------------
-A: Due to capacity, Dave could only take care of the backports for the
+Are all networking bug fixes backported to all stable releases?
+---------------------------------------------------------------
+Due to capacity, Dave could only take care of the backports for the
last two stable releases. For earlier stable releases, each stable
branch maintainer is supposed to take care of them. If you find any
patch is missing from an earlier stable branch, please notify
stable@vger.kernel.org with either a commit ID or a formal patch
backported, and CC Dave and other relevant networking developers.
-Q: Is the comment style convention different for the networking content?
-------------------------------------------------------------------------
-A: Yes, in a largely trivial way. Instead of this::
+Is the comment style convention different for the networking content?
+---------------------------------------------------------------------
+Yes, in a largely trivial way. Instead of this::
/*
* foobar blah blah blah
* another line of text
*/
-Q: I am working in existing code that has the former comment style and not the latter.
---------------------------------------------------------------------------------------
-Q: Should I submit new code in the former style or the latter?
-A: Make it the latter style, so that eventually all code in the domain
+I am working in existing code that has the former comment style and not the latter. Should I submit new code in the former style or the latter?
+-----------------------------------------------------------------------------------------------------------------------------------------------
+Make it the latter style, so that eventually all code in the domain
of netdev is of this format.
-Q: I found a bug that might have possible security implications or similar.
----------------------------------------------------------------------------
-Q: Should I mail the main netdev maintainer off-list?**
-A: No. The current netdev maintainer has consistently requested that
+I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
+---------------------------------------------------------------------------------------------------------------------------
+No. The current netdev maintainer has consistently requested that
people use the mailing lists and not reach out directly. If you aren't
OK with that, then perhaps consider mailing security@kernel.org or
reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
as possible alternative mechanisms.
-Q: What level of testing is expected before I submit my change?
----------------------------------------------------------------
-A: If your changes are against ``net-next``, the expectation is that you
+What level of testing is expected before I submit my change?
+------------------------------------------------------------
+If your changes are against ``net-next``, the expectation is that you
have tested by layering your changes on top of ``net-next``. Ideally
you will have done run-time testing specific to your change, but at a
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
+How do I post corresponding changes to user space components?
+-------------------------------------------------------------
+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.
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
+Any other tips to help ensure my net/net-next patch gets OK'd?
+--------------------------------------------------------------
+Attention to detail. Re-read your own work as if you were the
reviewer. You can start with using ``checkpatch.pl``, perhaps even with
the ``--strict`` flag. But do not be mindlessly robotic in doing so.
If your change is a bug fix, make sure your commit log indicates the
The following is a random collection of documentation regarding
network devices.
-struct net_device allocation rules
-==================================
+struct net_device lifetime rules
+================================
Network device structures need to persist even after module is unloaded and
must be allocated with alloc_netdev_mqs() and friends.
If device has registered successfully, it will be freed on last use
-by free_netdev(). This is required to handle the pathologic case cleanly
-(example: rmmod mydriver </sys/class/net/myeth/mtu )
+by free_netdev(). This is required to handle the pathological case cleanly
+(example: ``rmmod mydriver </sys/class/net/myeth/mtu``)
-alloc_netdev_mqs()/alloc_netdev() reserve extra space for driver
+alloc_netdev_mqs() / alloc_netdev() reserve extra space for driver
private data which gets freed when the network device is freed. If
separately allocated data is attached to the network device
-(netdev_priv(dev)) then it is up to the module exit handler to free that.
+(netdev_priv()) then it is up to the module exit handler to free that.
+
+There are two groups of APIs for registering struct net_device.
+First group can be used in normal contexts where ``rtnl_lock`` is not already
+held: register_netdev(), unregister_netdev().
+Second group can be used when ``rtnl_lock`` is already held:
+register_netdevice(), unregister_netdevice(), free_netdevice().
+
+Simple drivers
+--------------
+
+Most drivers (especially device drivers) handle lifetime of struct net_device
+in context where ``rtnl_lock`` is not held (e.g. driver probe and remove paths).
+
+In that case the struct net_device registration is done using
+the register_netdev(), and unregister_netdev() functions:
+
+.. code-block:: c
+
+ int probe()
+ {
+ struct my_device_priv *priv;
+ int err;
+
+ dev = alloc_netdev_mqs(...);
+ if (!dev)
+ return -ENOMEM;
+ priv = netdev_priv(dev);
+
+ /* ... do all device setup before calling register_netdev() ...
+ */
+
+ err = register_netdev(dev);
+ if (err)
+ goto err_undo;
+
+ /* net_device is visible to the user! */
+
+ err_undo:
+ /* ... undo the device setup ... */
+ free_netdev(dev);
+ return err;
+ }
+
+ void remove()
+ {
+ unregister_netdev(dev);
+ free_netdev(dev);
+ }
+
+Note that after calling register_netdev() the device is visible in the system.
+Users can open it and start sending / receiving traffic immediately,
+or run any other callback, so all initialization must be done prior to
+registration.
+
+unregister_netdev() closes the device and waits for all users to be done
+with it. The memory of struct net_device itself may still be referenced
+by sysfs but all operations on that device will fail.
+
+free_netdev() can be called after unregister_netdev() returns on when
+register_netdev() failed.
+
+Device management under RTNL
+----------------------------
+
+Registering struct net_device while in context which already holds
+the ``rtnl_lock`` requires extra care. In those scenarios most drivers
+will want to make use of struct net_device's ``needs_free_netdev``
+and ``priv_destructor`` members for freeing of state.
+
+Example flow of netdev handling under ``rtnl_lock``:
+
+.. code-block:: c
+
+ static void my_setup(struct net_device *dev)
+ {
+ dev->needs_free_netdev = true;
+ }
+
+ static void my_destructor(struct net_device *dev)
+ {
+ some_obj_destroy(priv->obj);
+ some_uninit(priv);
+ }
+
+ int create_link()
+ {
+ struct my_device_priv *priv;
+ int err;
+
+ ASSERT_RTNL();
+
+ dev = alloc_netdev(sizeof(*priv), "net%d", NET_NAME_UNKNOWN, my_setup);
+ if (!dev)
+ return -ENOMEM;
+ priv = netdev_priv(dev);
+
+ /* Implicit constructor */
+ err = some_init(priv);
+ if (err)
+ goto err_free_dev;
+
+ priv->obj = some_obj_create();
+ if (!priv->obj) {
+ err = -ENOMEM;
+ goto err_some_uninit;
+ }
+ /* End of constructor, set the destructor: */
+ dev->priv_destructor = my_destructor;
+
+ err = register_netdevice(dev);
+ if (err)
+ /* register_netdevice() calls destructor on failure */
+ goto err_free_dev;
+
+ /* If anything fails now unregister_netdevice() (or unregister_netdev())
+ * will take care of calling my_destructor and free_netdev().
+ */
+
+ return 0;
+
+ err_some_uninit:
+ some_uninit(priv);
+ err_free_dev:
+ free_netdev(dev);
+ return err;
+ }
+
+If struct net_device.priv_destructor is set it will be called by the core
+some time after unregister_netdevice(), it will also be called if
+register_netdevice() fails. The callback may be invoked with or without
+``rtnl_lock`` held.
+
+There is no explicit constructor callback, driver "constructs" the private
+netdev state after allocating it and before registration.
+
+Setting struct net_device.needs_free_netdev makes core call free_netdevice()
+automatically after unregister_netdevice() when all references to the device
+are gone. It only takes effect after a successful call to register_netdevice()
+so if register_netdevice() fails driver is responsible for calling
+free_netdev().
+
+free_netdev() is safe to call on error paths right after unregister_netdevice()
+or when register_netdevice() fails. Parts of netdev (de)registration process
+happen after ``rtnl_lock`` is released, therefore in those cases free_netdev()
+will defer some of the processing until ``rtnl_lock`` is released.
+
+Devices spawned from struct rtnl_link_ops should never free the
+struct net_device directly.
+
+.ndo_init and .ndo_uninit
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+``.ndo_init`` and ``.ndo_uninit`` callbacks are called during net_device
+registration and de-registration, under ``rtnl_lock``. Drivers can use
+those e.g. when parts of their init process need to run under ``rtnl_lock``.
+
+``.ndo_init`` runs before device is visible in the system, ``.ndo_uninit``
+runs during de-registering after device is closed but other subsystems
+may still have outstanding references to the netdevice.
MTU
===
Context: process
ndo_get_stats:
- Synchronization: dev_base_lock rwlock.
- Context: nominally process, but don't sleep inside an rwlock
+ Synchronization: rtnl_lock() semaphore, dev_base_lock rwlock, or RCU.
+ Context: atomic (can't sleep under rwlock or RCU)
ndo_start_xmit:
Synchronization: __netif_tx_lock spinlock.
========
This file documents the mmap() facility available with the PACKET
-socket interface on 2.4/2.6/3.x kernels. This type of sockets is used for
+socket interface. This type of sockets is used for
i) capture network traffic with utilities like tcpdump,
ii) transmit network traffic, or any other that needs raw
Why use PACKET_MMAP
===================
-In Linux 2.4/2.6/3.x if PACKET_MMAP is not enabled, the capture process is very
+Non PACKET_MMAP capture process (plain AF_PACKET) is very
inefficient. It uses very limited buffers and requires one system call to
capture each packet, it requires two if you want to get packet's timestamp
(like libpcap always does).
-In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size
+On the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size
configurable circular buffer mapped in user space that can be used to either
send or receive packets. This way reading packets just needs to wait for them,
most of the time there is no need to issue a single system call. Concerning
In kernel versions prior to 2.4.26 (for the 2.4 branch) and 2.6.5 (2.6 branch),
the PACKET_MMAP buffer could hold only 32768 frames in a 32 bit architecture or
-16384 in a 64 bit architecture. For information on these kernel versions
-see http://pusa.uv.es/~ulisses/packet_mmap/packet_mmap.pre-2.4.26_2.6.5.txt
+16384 in a 64 bit architecture.
Block size limit
----------------
Capture process
^^^^^^^^^^^^^^^
- from include/linux/if_packet.h
+From include/linux/if_packet.h::
#define TP_STATUS_COPY (1 << 1)
#define TP_STATUS_LOSING (1 << 2)
offloads, old connections will remain active after flags are cleared.
TLS encryption cannot be offloaded to devices without checksum calculation
-offload. Hence, TLS TX device feature flag requires NETIF_F_HW_CSUM being set.
+offload. Hence, TLS TX device feature flag requires TX csum offload being set.
Disabling the latter implies clearing the former. Disabling TX checksum offload
should not affect old connections, and drivers should make sure checksum
calculation does not break for them.
+Similarly, device-offloaded TLS decryption implies doing RXCSUM. If the user
+does not want to enable RX csum offload, TLS RX device feature is disabled
+as well.
of these options should be turned on for any kernel used for development or
testing purposes. In particular, you should turn on:
- - ENABLE_MUST_CHECK and FRAME_WARN to get an
- extra set of warnings for problems like the use of deprecated interfaces
- or ignoring an important return value from a function. The output
- generated by these warnings can be verbose, but one need not worry about
+ - FRAME_WARN to get warnings for stack frames larger than a given amount.
+ The output generated can be verbose, but one need not worry about
warnings from other parts of the kernel.
- DEBUG_OBJECTS will add code to track the lifetime of various objects
This module supports multiple cards.
Note: One miXart8 board will be represented as 4 alsa cards.
-See MIXART.txt for details.
+See Documentation/sound/cards/mixart.rst for details.
When the driver is compiled as a module and the hotplug firmware
is supported, the firmware data is loaded via hotplug automatically.
The codes for PCM and mixer OSS emulation modules are stored in this
directory. The rawmidi OSS emulation is included in the ALSA rawmidi
code since it's quite small. The sequencer code is stored in
-``core/seq/oss`` directory (see `below <#core-seq-oss>`__).
+``core/seq/oss`` directory (see `below <core/seq/oss_>`__).
core/seq
~~~~~~~~
Each time the ``probe`` callback is called, check the availability of
the device. If not available, simply increment the device index and
returns. dev will be incremented also later (`step 7
-<#set-the-pci-driver-data-and-return-zero>`__).
+<7) Set the PCI driver data and return zero._>`__).
2) Create a card instance
~~~~~~~~~~~~~~~~~~~~~~~~~
5) Create other components, such as mixer, MIDI, etc.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Here you define the basic components such as `PCM <#PCM-Interface>`__,
-mixer (e.g. `AC97 <#API-for-AC97-Codec>`__), MIDI (e.g.
-`MPU-401 <#MIDI-MPU401-UART-Interface>`__), and other interfaces.
-Also, if you want a `proc file <#Proc-Interface>`__, define it here,
+Here you define the basic components such as `PCM <PCM Interface_>`__,
+mixer (e.g. `AC97 <API for AC97 Codec_>`__), MIDI (e.g.
+`MPU-401 <MIDI (MPU401-UART) Interface_>`__), and other interfaces.
+Also, if you want a `proc file <Proc Interface_>`__, define it here,
too.
6) Register the card instance.
chip->irq = pci->irq;
where :c:func:`snd_mychip_interrupt()` is the interrupt handler
-defined `later <#pcm-interface-interrupt-handler>`__. Note that
+defined `later <PCM Interrupt Handler_>`__. Note that
``chip->irq`` should be defined only when :c:func:`request_irq()`
succeeded.
If the MPU-401 interface shares its interrupt with the other logical
devices on the card, set ``MPU401_INFO_IRQ_HOOK`` (see
-`below <#MIDI-Interrupt-Handler>`__).
+`below <MIDI Interrupt Handler_>`__).
Usually, the port address corresponds to the command port and port + 1
corresponds to the data port. If not, you may change the ``cport``
Errors:
- ===== =============================
+ ======= ==============================================================
EINTR an unmasked signal is pending
- ===== =============================
+ ENOEXEC the vcpu hasn't been initialized or the guest tried to execute
+ instructions from device memory (arm64)
+ ENOSYS data abort outside memslots with no syndrome info and
+ KVM_CAP_ARM_NISV_TO_USER not enabled (arm64)
+ EPERM SVE feature set but not finalized (arm64)
+ ======= ==============================================================
This ioctl is used to run a guest virtual cpu. While there are no
explicit parameters, there is an implicit parameter block that can be
F: net/wireless/
8169 10/100/1000 GIGABIT ETHERNET DRIVER
-M: Realtek linux nic maintainers <nic_swsd@realtek.com>
M: Heiner Kallweit <hkallweit1@gmail.com>
+M: nic_swsd@realtek.com
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/realtek/r8169*
M: Arthur Kiyanovski <akiyano@amazon.com>
R: Guy Tzalik <gtzalik@amazon.com>
R: Saeed Bishara <saeedb@amazon.com>
-R: Zorik Machulsky <zorik@amazon.com>
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst
M: Felix Kuehling <Felix.Kuehling@amd.com>
L: amd-gfx@lists.freedesktop.org
S: Supported
-T: git git://people.freedesktop.org/~agd5f/linux
+T: git https://gitlab.freedesktop.org/agd5f/linux.git
F: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd*.[ch]
F: drivers/gpu/drm/amd/amdkfd/
F: drivers/gpu/drm/amd/include/cik_structs.h
ARM/Microchip Sparx5 SoC support
M: Lars Povlsen <lars.povlsen@microchip.com>
M: Steen Hegelund <Steen.Hegelund@microchip.com>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: UNGLinuxDriver@microchip.com
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Supported
T: git git://github.com/microchip-ung/linux-upstream.git
F: drivers/hwmon/asus_atk0110.c
ATLX ETHERNET DRIVERS
-M: Jay Cliburn <jcliburn@gmail.com>
M: Chris Snook <chris.snook@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
X: arch/riscv/net/bpf_jit_comp64.c
BPF JIT for RISC-V (64-bit)
-M: Björn Töpel <bjorn.topel@gmail.com>
+M: Björn Töpel <bjorn@kernel.org>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/broadcom/bnxt/
BROADCOM BRCM80211 IEEE802.11n WIRELESS DRIVER
-M: Arend van Spriel <arend.vanspriel@broadcom.com>
+M: Arend van Spriel <aspriel@gmail.com>
M: Franky Lin <franky.lin@broadcom.com>
M: Hante Meuleman <hante.meuleman@broadcom.com>
M: Chi-hsien Lin <chi-hsien.lin@infineon.com>
CADENCE USB3 DRD IP DRIVER
M: Peter Chen <peter.chen@nxp.com>
M: Pawel Laszczak <pawell@cadence.com>
-M: Roger Quadros <rogerq@ti.com>
+R: Roger Quadros <rogerq@kernel.org>
R: Aswath Govindraju <a-govindraju@ti.com>
L: linux-usb@vger.kernel.org
S: Maintained
CAN-J1939 NETWORK LAYER
M: Robin van der Gracht <robin@protonic.nl>
M: Oleksij Rempel <o.rempel@pengutronix.de>
-R: Pengutronix Kernel Team <kernel@pengutronix.de>
+R: kernel@pengutronix.de
L: linux-can@vger.kernel.org
S: Maintained
F: Documentation/networking/j1939.rst
T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
F: Documentation/admin-guide/pm/cpuidle.rst
F: Documentation/driver-api/pm/cpuidle.rst
-F: drivers/cpuidle/*
+F: drivers/cpuidle/
F: include/linux/cpuidle.h
CPU POWER MONITORING SUBSYSTEM
F: drivers/scsi/dc395x.*
DCCP PROTOCOL
-M: Gerrit Renker <gerrit@erg.abdn.ac.uk>
L: dccp@vger.kernel.org
-S: Maintained
+S: Orphan
W: http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp
F: include/linux/dccp.h
F: include/linux/tfrc.h
S: Maintained
F: Documentation/kbuild/gcc-plugins.rst
F: scripts/Makefile.gcc-plugins
-F: scripts/gcc-plugin.sh
F: scripts/gcc-plugins/
GCOV BASED KERNEL PROFILING
K: \bSGX_
INTERCONNECT API
-M: Georgi Djakov <georgi.djakov@linaro.org>
+M: Georgi Djakov <djakov@kernel.org>
L: linux-pm@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/interconnect/
IOMAP FILESYSTEM LIBRARY
M: Christoph Hellwig <hch@infradead.org>
-M: Darrick J. Wong <darrick.wong@oracle.com>
+M: Darrick J. Wong <djwong@kernel.org>
M: linux-xfs@vger.kernel.org
M: linux-fsdevel@vger.kernel.org
L: linux-xfs@vger.kernel.org
F: drivers/scsi/ips*
IPVS
-M: Wensong Zhang <wensong@linux-vs.org>
M: Simon Horman <horms@verge.net.au>
M: Julian Anastasov <ja@ssi.bg>
L: netdev@vger.kernel.org
KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
M: Paolo Bonzini <pbonzini@redhat.com>
-R: Sean Christopherson <sean.j.christopherson@intel.com>
+R: Sean Christopherson <seanjc@google.com>
R: Vitaly Kuznetsov <vkuznets@redhat.com>
R: Wanpeng Li <wanpengli@tencent.com>
R: Jim Mattson <jmattson@google.com>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
F: Documentation/atomic_bitops.txt
F: Documentation/atomic_t.txt
-F: Documentation/core-api/atomic_ops.rst
F: Documentation/core-api/refcount-vs-atomic.rst
F: Documentation/litmus-tests/
F: Documentation/memory-barriers.txt
MCAN MMIO DEVICE DRIVER
M: Dan Murphy <dmurphy@ti.com>
-M: Sriram Dash <sriram.dash@samsung.com>
+M: Pankaj Sharma <pankj.sharma@samsung.com>
L: linux-can@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/can/bosch,m_can.yaml
MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
M: Woojung Huh <woojung.huh@microchip.com>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: UNGLinuxDriver@microchip.com
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
MICROCHIP LAN743X ETHERNET DRIVER
M: Bryan Whitehead <bryan.whitehead@microchip.com>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: UNGLinuxDriver@microchip.com
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/microchip/lan743x_*
MICROSEMI MIPS SOCS
M: Alexandre Belloni <alexandre.belloni@bootlin.com>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: UNGLinuxDriver@microchip.com
L: linux-mips@vger.kernel.org
S: Supported
F: Documentation/devicetree/bindings/mips/mscc.txt
NETWORKING [IPv4/IPv6]
M: "David S. Miller" <davem@davemloft.net>
-M: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
L: netdev@vger.kernel.org
S: Maintained
NETWORKING [TLS]
M: Boris Pismenny <borisp@nvidia.com>
-M: Aviad Yehezkel <aviadye@nvidia.com>
M: John Fastabend <john.fastabend@gmail.com>
M: Daniel Borkmann <daniel@iogearbox.net>
M: Jakub Kicinski <kuba@kernel.org>
F: include/linux/objtool.h
OCELOT ETHERNET SWITCH DRIVER
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
M: Vladimir Oltean <vladimir.oltean@nxp.com>
M: Claudiu Manoil <claudiu.manoil@nxp.com>
M: Alexandre Belloni <alexandre.belloni@bootlin.com>
+M: UNGLinuxDriver@microchip.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/dsa/ocelot/*
F: include/uapi/misc/ocxl.h
OMAP AUDIO SUPPORT
-M: Peter Ujfalusi <peter.ujfalusi@ti.com>
+M: Peter Ujfalusi <peter.ujfalusi@gmail.com>
M: Jarkko Nikula <jarkko.nikula@bitmer.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
L: linux-omap@vger.kernel.org
PENSANDO ETHERNET DRIVERS
M: Shannon Nelson <snelson@pensando.io>
-M: Pensando Drivers <drivers@pensando.io>
+M: drivers@pensando.io
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/device_drivers/ethernet/pensando/ionic.rst
F: drivers/net/wireless/ath/ath11k/
QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
-M: QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
+M: ath9k-devel@qca.qualcomm.com
L: linux-wireless@vger.kernel.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/ath9k
M: Christian König <christian.koenig@amd.com>
L: amd-gfx@lists.freedesktop.org
S: Supported
-T: git git://people.freedesktop.org/~agd5f/linux
+T: git https://gitlab.freedesktop.org/agd5f/linux.git
F: drivers/gpu/drm/amd/
F: drivers/gpu/drm/radeon/
F: include/uapi/drm/amdgpu_drm.h
M: David Rientjes <rientjes@google.com>
M: Joonsoo Kim <iamjoonsoo.kim@lge.com>
M: Andrew Morton <akpm@linux-foundation.org>
+M: Vlastimil Babka <vbabka@suse.cz>
L: linux-mm@kvack.org
S: Maintained
F: include/linux/sl?b*.h
L: speakup@linux-speakup.org
S: Odd Fixes
W: http://www.linux-speakup.org/
+W: https://github.com/linux-speakup/speakup
+B: https://github.com/linux-speakup/speakup/issues
F: drivers/accessibility/speakup/
SPEAR CLOCK FRAMEWORK SUPPORT
F: drivers/irqchip/irq-xtensa-*
TEXAS INSTRUMENTS ASoC DRIVERS
-M: Peter Ujfalusi <peter.ujfalusi@ti.com>
+M: Peter Ujfalusi <peter.ujfalusi@gmail.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Maintained
F: sound/soc/ti/
F: Documentation/devicetree/bindings/iio/dac/ti,dac7612.txt
F: drivers/iio/dac/ti-dac7612.c
+TEXAS INSTRUMENTS DMA DRIVERS
+M: Peter Ujfalusi <peter.ujfalusi@gmail.com>
+L: dmaengine@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
+F: Documentation/devicetree/bindings/dma/ti-edma.txt
+F: Documentation/devicetree/bindings/dma/ti/
+F: drivers/dma/ti/
+X: drivers/dma/ti/cppi41.c
+F: include/linux/dma/k3-udma-glue.h
+F: include/linux/dma/ti-cppi5.h
+F: include/linux/dma/k3-psil.h
+
TEXAS INSTRUMENTS' SYSTEM CONTROL INTERFACE (TISCI) PROTOCOL DRIVER
M: Nishanth Menon <nm@ti.com>
M: Tero Kristo <t-kristo@ti.com>
F: drivers/nfc/trf7970a.c
TI TWL4030 SERIES SOC CODEC DRIVER
-M: Peter Ujfalusi <peter.ujfalusi@ti.com>
+M: Peter Ujfalusi <peter.ujfalusi@gmail.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Maintained
F: sound/soc/codecs/twl4030*
USB LAN78XX ETHERNET DRIVER
M: Woojung Huh <woojung.huh@microchip.com>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: UNGLinuxDriver@microchip.com
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/microchip,lan78xx.txt
USB SMSC95XX ETHERNET DRIVER
M: Steve Glendinning <steve.glendinning@shawell.net>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: UNGLinuxDriver@microchip.com
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/usb/smsc95xx.*
VMWARE VMXNET3 ETHERNET DRIVER
M: Ronak Doshi <doshir@vmware.com>
-M: "VMware, Inc." <pv-drivers@vmware.com>
+M: pv-drivers@vmware.com
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/vmxnet3/
VRF
M: David Ahern <dsahern@kernel.org>
-M: Shrijeet Mukherjee <shrijeet@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/networking/vrf.rst
K: (?:\b|_)xdp(?:\b|_)
XDP SOCKETS (AF_XDP)
-M: Björn Töpel <bjorn.topel@intel.com>
+M: Björn Töpel <bjorn@kernel.org>
M: Magnus Karlsson <magnus.karlsson@intel.com>
R: Jonathan Lemon <jonathan.lemon@gmail.com>
L: netdev@vger.kernel.org
F: drivers/xen/*swiotlb*
XFS FILESYSTEM
-M: Darrick J. Wong <darrick.wong@oracle.com>
+M: Darrick J. Wong <djwong@kernel.org>
M: linux-xfs@vger.kernel.org
L: linux-xfs@vger.kernel.org
S: Supported
VERSION = 5
PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc4
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
bool
+config ARCH_SPLIT_ARG64
+ bool
+ help
+ If a 32-bit architecture requires 64-bit arguments to be split into
+ pairs of 32-bit arguments, select this option.
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
+++ /dev/null
-#include <asm-generic/local64.h>
boot := arch/arc/boot
-#default target for make without any arguments.
-KBUILD_IMAGE := $(boot)/bootpImage
-
-all: bootpImage
-bootpImage: vmlinux
-
-boot_targets += uImage uImage.bin uImage.gz
+boot_targets := uImage.bin uImage.gz uImage.lzma
+PHONY += $(boot_targets)
$(boot_targets): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+uimage-default-y := uImage.bin
+uimage-default-$(CONFIG_KERNEL_GZIP) := uImage.gz
+uimage-default-$(CONFIG_KERNEL_LZMA) := uImage.lzma
+
+PHONY += uImage
+uImage: $(uimage-default-y)
+ @ln -sf $< $(boot)/uImage
+ @$(kecho) ' Image $(boot)/uImage is ready'
+
+CLEAN_FILES += $(boot)/uImage
+
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
# SPDX-License-Identifier: GPL-2.0
-targets := vmlinux.bin vmlinux.bin.gz uImage
# uImage build relies on mkimage being availble on your host for ARC target
# You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage
OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S
-LINUX_START_TEXT = $$(readelf -h vmlinux | \
+LINUX_START_TEXT = $$($(READELF) -h vmlinux | \
grep "Entry point address" | grep -o 0x.*)
UIMAGE_LOADADDR = $(CONFIG_LINUX_LINK_BASE)
UIMAGE_ENTRYADDR = $(LINUX_START_TEXT)
-suffix-y := bin
-suffix-$(CONFIG_KERNEL_GZIP) := gz
-suffix-$(CONFIG_KERNEL_LZMA) := lzma
-
-targets += uImage
+targets += vmlinux.bin
+targets += vmlinux.bin.gz
+targets += vmlinux.bin.lzma
targets += uImage.bin
targets += uImage.gz
targets += uImage.lzma
-extra-y += vmlinux.bin
-extra-y += vmlinux.bin.gz
-extra-y += vmlinux.bin.lzma
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
$(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE
$(call if_changed,uimage,lzma)
-
-$(obj)/uImage: $(obj)/uImage.$(suffix-y)
- @ln -sf $(notdir $<) $@
- @echo ' Image $@ is ready'
# SPDX-License-Identifier: GPL-2.0
generic-y += extable.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += parport.h
generic-y += user.h
#ifndef __ASSEMBLY__
#define clear_page(paddr) memset((paddr), 0, PAGE_SIZE)
+#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE)
struct vm_area_struct;
mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume()
GET_CURR_THR_INFO_FLAGS r9
- and.f 0, r9, TIF_SIGPENDING|TIF_NOTIFY_SIGNAL
+ and.f 0, r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL
bz .Lchk_notify_resume
; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs
depends on ISA_ARCV2
select ARC_HAS_ACCL_REGS
select ARC_IRQ_NO_AUTOSAVE
+ select ARC_FPU_SAVE_RESTORE
select CLK_HSDK
select RESET_CONTROLLER
select RESET_HSDK
clock-names = "sysclk";
};
};
+
+&aes1_target {
+ status = "disabled";
+};
+
+&aes2_target {
+ status = "disabled";
+};
emac: gem@30000 {
compatible = "cadence,gem";
reg = <0x30000 0x10000>;
+ interrupt-parent = <&vic0>;
interrupts = <31>;
};
dmac1: dmac@40000 {
compatible = "snps,dw-dmac";
reg = <0x40000 0x10000>;
+ interrupt-parent = <&vic0>;
interrupts = <25>;
};
dmac2: dmac@50000 {
compatible = "snps,dw-dmac";
reg = <0x50000 0x10000>;
+ interrupt-parent = <&vic0>;
interrupts = <26>;
};
axi2pico@c0000000 {
compatible = "picochip,axi2pico-pc3x2";
reg = <0xc0000000 0x10000>;
+ interrupt-parent = <&vic0>;
interrupts = <13 14 15 16 17 18 19 20 21>;
};
};
panel@0 {
compatible = "samsung,s6e63m0";
reg = <0>;
+ max-brightness = <15>;
vdd3-supply = <&panel_reg_3v0>;
vci-supply = <&panel_reg_1v8>;
reset-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>;
CONFIG_SERIAL_DEV_BUS=y
CONFIG_I2C_CHARDEV=y
CONFIG_SPI=y
+CONFIG_SPI_GPIO=m
CONFIG_SPI_OMAP24XX=y
CONFIG_SPI_TI_QSPI=m
CONFIG_HSI=m
CONFIG_W1=m
CONFIG_HDQ_MASTER_OMAP=m
CONFIG_W1_SLAVE_DS250X=m
-CONFIG_POWER_AVS=y
CONFIG_POWER_RESET=y
CONFIG_POWER_RESET_GPIO=y
CONFIG_BATTERY_BQ27XXX=m
chacha_block_xor_neon(state, d, s, nrounds);
if (d != dst)
memcpy(dst, buf, bytes);
+ state[12]++;
}
}
generic-y += early_ioremap.h
generic-y += extable.h
generic-y += flat.h
-generic-y += local64.h
generic-y += parport.h
generated-y += mach-types.h
break;
case BUS_NOTIFY_BIND_DRIVER:
od = to_omap_device(pdev);
- if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
- pm_runtime_status_suspended(dev)) {
+ if (od) {
od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
- pm_runtime_set_active(dev);
+ if (od->_state == OMAP_DEVICE_STATE_ENABLED &&
+ pm_runtime_status_suspended(dev)) {
+ pm_runtime_set_active(dev);
+ }
}
break;
case BUS_NOTIFY_ADD_DEVICE:
.vp_vstepmin = OMAP4_VP_VSTEPMIN_VSTEPMIN,
.vp_vstepmax = OMAP4_VP_VSTEPMAX_VSTEPMAX,
.vddmin = 900000,
- .vddmax = 1350000,
+ .vddmax = 1375000,
.vp_timeout_us = OMAP4_VP_VLIMITTO_TIMEOUT_US,
.i2c_slave_addr = 0x44,
.volt_reg_addr = 0x0,
}
gnttab_init();
if (!xen_initial_domain())
- xenbus_probe(NULL);
+ xenbus_probe();
/*
* Making sure board specific code will not set up ops for
select HAVE_NMI
select HAVE_PATA_PLATFORM
select HAVE_PERF_EVENTS
- select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
- select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
#
# Copyright (C) 1995-2001 by Russell King
-LDFLAGS_vmlinux :=--no-undefined -X -z norelro
+LDFLAGS_vmlinux :=--no-undefined -X
ifeq ($(CONFIG_RELOCATABLE), y)
# Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
CHECKFLAGS += -D__AARCH64EB__
# Prefer the baremetal ELF build target, but not all toolchains include
# it so fall back to the standard linux version if needed.
-KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb)
+KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro)
UTS_MACHINE := aarch64_be
else
KBUILD_CPPFLAGS += -mlittle-endian
CHECKFLAGS += -D__AARCH64EL__
# Same as above, prefer ELF but fall back to linux target if needed.
-KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux)
+KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro)
UTS_MACHINE := aarch64
endif
+ifeq ($(CONFIG_LD_IS_LLD), y)
+KBUILD_LDFLAGS += -z norelro
+endif
+
CHECKFLAGS += -D__aarch64__
ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <32>;
+ ngpios = <32>;
reg = <0>;
interrupt-controller;
#interrupt-cells = <2>;
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <32>;
+ ngpios = <32>;
reg = <0>;
interrupt-controller;
#interrupt-cells = <2>;
compatible = "snps,dw-apb-gpio-port";
gpio-controller;
#gpio-cells = <2>;
- snps,nr-gpios = <8>;
+ ngpios = <8>;
reg = <0>;
interrupt-controller;
#interrupt-cells = <2>;
# SPDX-License-Identifier: GPL-2.0
generic-y += early_ioremap.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += qrwlock.h
generic-y += qspinlock.h
#include <asm/lse.h>
#define ATOMIC_OP(op) \
-static inline void arch_##op(int i, atomic_t *v) \
+static __always_inline void arch_##op(int i, atomic_t *v) \
{ \
__lse_ll_sc_body(op, i, v); \
}
#undef ATOMIC_OP
#define ATOMIC_FETCH_OP(name, op) \
-static inline int arch_##op##name(int i, atomic_t *v) \
+static __always_inline int arch_##op##name(int i, atomic_t *v) \
{ \
return __lse_ll_sc_body(op##name, i, v); \
}
#undef ATOMIC_FETCH_OPS
#define ATOMIC64_OP(op) \
-static inline void arch_##op(long i, atomic64_t *v) \
+static __always_inline void arch_##op(long i, atomic64_t *v) \
{ \
__lse_ll_sc_body(op, i, v); \
}
#undef ATOMIC64_OP
#define ATOMIC64_FETCH_OP(name, op) \
-static inline long arch_##op##name(long i, atomic64_t *v) \
+static __always_inline long arch_##op##name(long i, atomic64_t *v) \
{ \
return __lse_ll_sc_body(op##name, i, v); \
}
#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_FETCH_OPS
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
{
return __lse_ll_sc_body(atomic64_dec_if_positive, v);
}
#include <linux/jump_label.h>
#include <linux/kvm_types.h>
#include <linux/percpu.h>
+#include <linux/psci.h>
#include <asm/arch_gicv3.h>
#include <asm/barrier.h>
#include <asm/cpufeature.h>
struct kvm_pmu_events pmu_events;
};
+struct kvm_host_psci_config {
+ /* PSCI version used by host. */
+ u32 version;
+
+ /* Function IDs used by host if version is v0.1. */
+ struct psci_0_1_function_ids function_ids_0_1;
+
+ bool psci_0_1_cpu_suspend_implemented;
+ bool psci_0_1_cpu_on_implemented;
+ bool psci_0_1_cpu_off_implemented;
+ bool psci_0_1_migrate_implemented;
+};
+
+extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config);
+#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config)
+
+extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
+#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset)
+
+extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS];
+#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map)
+
struct vcpu_reset_state {
unsigned long pc;
unsigned long r0;
* The Tag check override (TCO) bit disables temporarily the tag checking
* preventing the issue.
*/
-static inline void uaccess_disable_privileged(void)
+static inline void __uaccess_disable_tco(void)
{
asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0),
ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+static inline void __uaccess_enable_tco(void)
+{
+ asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
+ ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+}
+
+static inline void uaccess_disable_privileged(void)
+{
+ __uaccess_disable_tco();
if (uaccess_ttbr0_disable())
return;
static inline void uaccess_enable_privileged(void)
{
- asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
- ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+ __uaccess_enable_tco();
if (uaccess_ttbr0_enable())
return;
DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1));
DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save));
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
- DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
+ DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs));
BLANK();
#ifdef CONFIG_COMPAT
DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
int parange, ipa_max;
unsigned int safe_vmid_bits, vmid_bits;
- if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST))
+ if (!IS_ENABLED(CONFIG_KVM))
return;
safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
*/
.macro ftrace_regs_entry, allregs=0
/* Make room for pt_regs, plus a callee frame */
- sub sp, sp, #(S_FRAME_SIZE + 16)
+ sub sp, sp, #(PT_REGS_SIZE + 16)
/* Save function arguments (and x9 for simplicity) */
stp x0, x1, [sp, #S_X0]
.endif
/* Save the callsite's SP and LR */
- add x10, sp, #(S_FRAME_SIZE + 16)
+ add x10, sp, #(PT_REGS_SIZE + 16)
stp x9, x10, [sp, #S_LR]
/* Save the PC after the ftrace callsite */
str x30, [sp, #S_PC]
/* Create a frame record for the callsite above pt_regs */
- stp x29, x9, [sp, #S_FRAME_SIZE]
- add x29, sp, #S_FRAME_SIZE
+ stp x29, x9, [sp, #PT_REGS_SIZE]
+ add x29, sp, #PT_REGS_SIZE
/* Create our frame record within pt_regs. */
stp x29, x30, [sp, #S_STACKFRAME]
ldr x9, [sp, #S_PC]
/* Restore the callsite's SP */
- add sp, sp, #S_FRAME_SIZE + 16
+ add sp, sp, #PT_REGS_SIZE + 16
ret x9
SYM_CODE_END(ftrace_common)
ldr x0, [sp, #S_PC]
sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
add x1, sp, #S_LR // parent_ip (callsite's LR)
- ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP)
+ ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP)
bl prepare_ftrace_return
b ftrace_common_return
SYM_CODE_END(ftrace_graph_caller)
.endif
#endif
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
#ifdef CONFIG_VMAP_STACK
/*
* Test whether the SP has overflowed, without corrupting a GPR.
* userspace, and can clobber EL0 registers to free up GPRs.
*/
- /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+ /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */
msr tpidr_el0, x0
/* Recover the original x0 value and stash it in tpidrro_el0 */
mrs_s \tmp2, SYS_GCR_EL1
bfi \tmp2, \tmp, #0, #16
msr_s SYS_GCR_EL1, \tmp2
- isb
#endif
.endm
ldr_l \tmp, gcr_kernel_excl
mte_set_gcr \tmp, \tmp2
+ isb
1:
#endif
.endm
scs_load tsk, x20
.else
- add x21, sp, #S_FRAME_SIZE
+ add x21, sp, #PT_REGS_SIZE
get_current_task tsk
.endif /* \el == 0 */
mrs x22, elr_el1
ldp x26, x27, [sp, #16 * 13]
ldp x28, x29, [sp, #16 * 14]
ldr lr, [sp, #S_LR]
- add sp, sp, #S_FRAME_SIZE // restore sp
+ add sp, sp, #PT_REGS_SIZE // restore sp
.if \el == 0
alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
/*
* Store the original GPRs to the new stack. The orginal SP (minus
- * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+ * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry.
*/
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
kernel_entry 1
mrs x0, tpidr_el0
- add x0, x0, #S_FRAME_SIZE
+ add x0, x0, #PT_REGS_SIZE
str x0, [sp, #S_SP]
/* Stash the regs for handle_bad_stack */
#include <linux/platform_device.h>
#include <linux/sched_clock.h>
#include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
/* ARMv8 Cortex-A53 specific event types. */
#define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2
static int __init armv8_pmu_driver_init(void)
{
- int ret;
-
if (acpi_disabled)
- ret = platform_driver_register(&armv8_pmu_driver);
+ return platform_driver_register(&armv8_pmu_driver);
else
- ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
- /*
- * Try to re-initialize lockup detector after PMU init in
- * case PMU events are triggered via NMIs.
- */
- if (ret == 0 && arm_pmu_irq_is_nmi())
- lockup_detector_init();
-
- return ret;
+ return arm_pmu_acpi_probe(armv8_pmuv3_init);
}
device_initcall(armv8_pmu_driver_init)
userpg->cap_user_time_zero = 1;
userpg->cap_user_time_short = 1;
}
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
- unsigned int cpu = smp_processor_id();
- unsigned long max_cpu_freq;
-
- max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
- if (!max_cpu_freq)
- max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
- return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif
stp x24, x25, [sp, #S_X24]
stp x26, x27, [sp, #S_X26]
stp x28, x29, [sp, #S_X28]
- add x0, sp, #S_FRAME_SIZE
+ add x0, sp, #PT_REGS_SIZE
stp lr, x0, [sp, #S_LR]
/*
* Construct a useful saved PSTATE
.endm
SYM_CODE_START(kretprobe_trampoline)
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
save_all_base_regs
restore_all_base_regs
- add sp, sp, #S_FRAME_SIZE
+ add sp, sp, #PT_REGS_SIZE
ret
SYM_CODE_END(kretprobe_trampoline)
asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned long thread_flags)
{
- /*
- * The assembly code enters us with IRQs off, but it hasn't
- * informed the tracing code of that for efficiency reasons.
- * Update the trace code with the current status.
- */
- trace_hardirqs_off();
-
do {
if (thread_flags & _TIF_NEED_RESCHED) {
/* Unmask Debug and SError for the next task */
"CPU: CPUs started in inconsistent modes");
else
pr_info("CPU: All CPU(s) started at EL1\n");
- if (IS_ENABLED(CONFIG_KVM))
+ if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode())
kvm_compute_layout();
}
unsigned int cpu, i;
for (i = 0; i < NR_IPI; i++) {
- unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
prec >= 4 ? " " : "");
for_each_online_cpu(cpu)
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
+#include <asm/exception.h>
#include <asm/fpsimd.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
local_daif_mask();
flags = current_thread_info()->flags;
- if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
- /*
- * We're off to userspace, where interrupts are
- * always enabled after we restore the flags from
- * the SPSR.
- */
- trace_hardirqs_on();
+ if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
return;
- }
local_daif_restore(DAIF_PROCCTX);
}
#include <asm/smp.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
-#include <asm/exception.h>
#include <asm/system_misc.h>
#include <asm/sysreg.h>
# routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
# preparation in build-time C")).
ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
- -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id=sha1 -n \
- $(btildflags-y) -T
+ -Bsymbolic --build-id=sha1 -n $(btildflags-y) -T
ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
PROVIDE (_etext = .);
PROVIDE (etext = .);
- .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
- .eh_frame : { KEEP (*(.eh_frame)) } :text
-
.dynamic : { *(.dynamic) } :text :dynamic
.rodata : { *(.rodata*) } :text
*(.note.GNU-stack)
*(.data .data.* .gnu.linkonce.d.* .sdata*)
*(.bss .sbss .dynbss .dynsbss)
+ *(.eh_frame .eh_frame_hdr)
}
}
text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
note PT_NOTE FLAGS(4); /* PF_R */
- eh_frame_hdr PT_GNU_EH_FRAME;
}
/*
source "virt/kvm/Kconfig"
-config KVM_ARM_PMU
- bool "Virtual Performance Monitoring Unit (PMU) support"
- depends on HW_PERF_EVENTS
- default y
- help
- Adds support for a virtual Performance Monitoring Unit (PMU) in
- virtual machines.
-
endif # KVM
endif # VIRTUALIZATION
vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \
vgic/vgic-its.o vgic/vgic-debug.o
-kvm-$(CONFIG_KVM_ARM_PMU) += pmu-emul.o
+kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o
if (!irqchip_in_kernel(vcpu->kvm))
goto no_vgic;
- if (!vgic_initialized(vcpu->kvm))
- return -ENODEV;
-
+ /*
+ * At this stage, we have the guarantee that the vgic is both
+ * available and initialized.
+ */
if (!timer_irqs_are_valid(vcpu)) {
kvm_debug("incorrectly configured timer irqs\n");
return -EINVAL;
static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
-extern u64 kvm_nvhe_sym(__cpu_logical_map)[NR_CPUS];
-extern u32 kvm_nvhe_sym(kvm_host_psci_version);
-extern struct psci_0_1_function_ids kvm_nvhe_sym(kvm_host_psci_0_1_function_ids);
-
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
* Map the VGIC hardware resources before running a vcpu the
* first time on this VM.
*/
- if (unlikely(!vgic_ready(kvm))) {
- ret = kvm_vgic_map_resources(kvm);
- if (ret)
- return ret;
- }
+ ret = kvm_vgic_map_resources(kvm);
+ if (ret)
+ return ret;
} else {
/*
* Tell the rest of the code that there are userspace irqchip
.notifier_call = hyp_init_cpu_pm_notifier,
};
-static void __init hyp_cpu_pm_init(void)
+static void hyp_cpu_pm_init(void)
{
if (!is_protected_kvm_enabled())
cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
}
-static void __init hyp_cpu_pm_exit(void)
+static void hyp_cpu_pm_exit(void)
{
if (!is_protected_kvm_enabled())
cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb);
* allow any other CPUs from the `possible` set to boot.
*/
for_each_online_cpu(cpu)
- kvm_nvhe_sym(__cpu_logical_map)[cpu] = cpu_logical_map(cpu);
+ hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu);
}
+#define init_psci_0_1_impl_state(config, what) \
+ config.psci_0_1_ ## what ## _implemented = psci_ops.what
+
static bool init_psci_relay(void)
{
/*
return false;
}
- kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version();
- kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids();
+ kvm_host_psci_config.version = psci_ops.get_version();
+
+ if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) {
+ kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids();
+ init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend);
+ init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on);
+ init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off);
+ init_psci_0_1_impl_state(kvm_host_psci_config, migrate);
+ }
return true;
}
}
}
+/*
+ * Skip an instruction while host sysregs are live.
+ * Assumes host is always 64-bit.
+ */
+static inline void kvm_skip_host_instr(void)
+{
+ write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR);
+}
+
#endif
__kvm_hyp_host_forward_smc(host_ctxt);
}
-static void skip_host_instruction(void)
-{
- write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR);
-}
-
static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
{
bool handled;
if (!handled)
default_host_smc_handler(host_ctxt);
- /*
- * Unlike HVC, the return address of an SMC is the instruction's PC.
- * Move the return address past the instruction.
- */
- skip_host_instruction();
+ /* SMC was trapped, move ELR past the current PC. */
+ kvm_skip_host_instr();
}
void handle_trap(struct kvm_cpu_context *host_ctxt)
* Other CPUs should not be allowed to boot because their features were
* not checked against the finalized system capabilities.
*/
-u64 __ro_after_init __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
+u64 __ro_after_init hyp_cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
u64 cpu_logical_map(unsigned int cpu)
{
- if (cpu >= ARRAY_SIZE(__cpu_logical_map))
+ if (cpu >= ARRAY_SIZE(hyp_cpu_logical_map))
hyp_panic();
- return __cpu_logical_map[cpu];
+ return hyp_cpu_logical_map[cpu];
}
unsigned long __hyp_per_cpu_offset(unsigned int cpu)
#include <asm/kvm_asm.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
-#include <kvm/arm_hypercalls.h>
#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
-#include <linux/psci.h>
-#include <kvm/arm_psci.h>
#include <uapi/linux/psci.h>
#include <nvhe/trap_handler.h>
void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
/* Config options set by the host. */
-__ro_after_init u32 kvm_host_psci_version;
-__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids;
-__ro_after_init s64 hyp_physvirt_offset;
+struct kvm_host_psci_config __ro_after_init kvm_host_psci_config;
+s64 __ro_after_init hyp_physvirt_offset;
#define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset)
static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT;
static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT;
-static u64 get_psci_func_id(struct kvm_cpu_context *host_ctxt)
-{
- DECLARE_REG(u64, func_id, host_ctxt, 0);
-
- return func_id;
-}
+#define is_psci_0_1(what, func_id) \
+ (kvm_host_psci_config.psci_0_1_ ## what ## _implemented && \
+ (func_id) == kvm_host_psci_config.function_ids_0_1.what)
static bool is_psci_0_1_call(u64 func_id)
{
- return (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) ||
- (func_id == kvm_host_psci_0_1_function_ids.cpu_on) ||
- (func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
- (func_id == kvm_host_psci_0_1_function_ids.migrate);
+ return (is_psci_0_1(cpu_suspend, func_id) ||
+ is_psci_0_1(cpu_on, func_id) ||
+ is_psci_0_1(cpu_off, func_id) ||
+ is_psci_0_1(migrate, func_id));
}
static bool is_psci_0_2_call(u64 func_id)
(PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31));
}
-static bool is_psci_call(u64 func_id)
-{
- switch (kvm_host_psci_version) {
- case PSCI_VERSION(0, 1):
- return is_psci_0_1_call(func_id);
- default:
- return is_psci_0_2_call(func_id);
- }
-}
-
static unsigned long psci_call(unsigned long fn, unsigned long arg0,
unsigned long arg1, unsigned long arg2)
{
static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
{
- if ((func_id == kvm_host_psci_0_1_function_ids.cpu_off) ||
- (func_id == kvm_host_psci_0_1_function_ids.migrate))
+ if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id))
return psci_forward(host_ctxt);
- else if (func_id == kvm_host_psci_0_1_function_ids.cpu_on)
+ if (is_psci_0_1(cpu_on, func_id))
return psci_cpu_on(func_id, host_ctxt);
- else if (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend)
+ if (is_psci_0_1(cpu_suspend, func_id))
return psci_cpu_suspend(func_id, host_ctxt);
- else
- return PSCI_RET_NOT_SUPPORTED;
+
+ return PSCI_RET_NOT_SUPPORTED;
}
static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt)
bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt)
{
- u64 func_id = get_psci_func_id(host_ctxt);
+ DECLARE_REG(u64, func_id, host_ctxt, 0);
unsigned long ret;
- if (!is_psci_call(func_id))
- return false;
-
- switch (kvm_host_psci_version) {
+ switch (kvm_host_psci_config.version) {
case PSCI_VERSION(0, 1):
+ if (!is_psci_0_1_call(func_id))
+ return false;
ret = psci_0_1_handler(func_id, host_ctxt);
break;
case PSCI_VERSION(0, 2):
+ if (!is_psci_0_2_call(func_id))
+ return false;
ret = psci_0_2_handler(func_id, host_ctxt);
break;
default:
+ if (!is_psci_0_2_call(func_id))
+ return false;
ret = psci_1_0_handler(func_id, host_ctxt);
break;
}
return -EINVAL;
}
- kvm_pmu_vcpu_reset(vcpu);
-
return 0;
}
{
u64 pmcr, val;
+ /* No PMU available, PMCR_EL0 may UNDEF... */
+ if (!kvm_arm_support_pmu_v3())
+ return;
+
pmcr = read_sysreg(pmcr_el0);
/*
* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
#define reg_to_encoding(x) \
sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \
- (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2);
+ (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
}
/*
- * Store a hyp VA <-> PA offset into a hyp-owned variable.
+ * Store a hyp VA <-> PA offset into a EL2-owned variable.
*/
static void init_hyp_physvirt_offset(void)
{
- extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
u64 kern_va, hyp_va;
/* Compute the offset from the hyp VA and PA of a random symbol. */
- kern_va = (u64)kvm_ksym_ref(__hyp_text_start);
+ kern_va = (u64)lm_alias(__hyp_text_start);
hyp_va = __early_kern_hyp_va(kern_va);
- CHOOSE_NVHE_SYM(hyp_physvirt_offset) = (s64)__pa(kern_va) - (s64)hyp_va;
+ hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va;
}
/*
* Map the MMIO regions depending on the VGIC model exposed to the guest
* called on the first VCPU run.
* Also map the virtual CPU interface into the VM.
- * v2/v3 derivatives call vgic_init if not already done.
+ * v2 calls vgic_init() if not already done.
+ * v3 and derivatives return an error if the VGIC is not initialized.
* vgic_ready() returns true if this function has succeeded.
* @kvm: kvm struct pointer
*/
struct vgic_dist *dist = &kvm->arch.vgic;
int ret = 0;
+ if (likely(vgic_ready(kvm)))
+ return 0;
+
mutex_lock(&kvm->lock);
+ if (vgic_ready(kvm))
+ goto out;
+
if (!irqchip_in_kernel(kvm))
goto out;
if (ret)
__kvm_vgic_destroy(kvm);
+ else
+ dist->ready = true;
out:
mutex_unlock(&kvm->lock);
struct vgic_dist *dist = &kvm->arch.vgic;
int ret = 0;
- if (vgic_ready(kvm))
- goto out;
-
if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) {
kvm_err("Need to set vgic cpu and dist addresses first\n");
- ret = -ENXIO;
- goto out;
+ return -ENXIO;
}
if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) {
kvm_err("VGIC CPU and dist frames overlap\n");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
/*
ret = vgic_init(kvm);
if (ret) {
kvm_err("Unable to initialize VGIC dynamic data structures\n");
- goto out;
+ return ret;
}
ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2);
if (ret) {
kvm_err("Unable to register VGIC MMIO regions\n");
- goto out;
+ return ret;
}
if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) {
KVM_VGIC_V2_CPU_SIZE, true);
if (ret) {
kvm_err("Unable to remap VGIC CPU to VCPU\n");
- goto out;
+ return ret;
}
}
- dist->ready = true;
-
-out:
- return ret;
+ return 0;
}
DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap);
int ret = 0;
int c;
- if (vgic_ready(kvm))
- goto out;
-
kvm_for_each_vcpu(c, vcpu, kvm) {
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) {
kvm_debug("vcpu %d redistributor base not set\n", c);
- ret = -ENXIO;
- goto out;
+ return -ENXIO;
}
}
if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) {
kvm_err("Need to set vgic distributor addresses first\n");
- ret = -ENXIO;
- goto out;
+ return -ENXIO;
}
if (!vgic_v3_check_base(kvm)) {
kvm_err("VGIC redist and dist frames overlap\n");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
/*
* the VGIC before we need to use it.
*/
if (!vgic_initialized(kvm)) {
- ret = -EBUSY;
- goto out;
+ return -EBUSY;
}
ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3);
if (ret) {
kvm_err("Unable to register VGICv3 dist MMIO regions\n");
- goto out;
+ return ret;
}
if (kvm_vgic_global_state.has_gicv4_1)
vgic_v4_configure_vsgis(kvm);
- dist->ready = true;
-out:
- return ret;
+ return 0;
}
DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap);
EXPORT_SYMBOL(memstart_addr);
/*
- * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
- * memory as some devices, namely the Raspberry Pi 4, have peripherals with
- * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
- * bit addressable memory area.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
*/
phys_addr_t arm64_dma_phys_limit __ro_after_init;
-static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
#ifdef CONFIG_KEXEC_CORE
/*
if (crash_base == 0) {
/* Current arm64 boot protocol requires 2MB alignment */
- crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+ crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
crash_size, SZ_2M);
if (crash_base == 0) {
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
unsigned int __maybe_unused acpi_zone_dma_bits;
unsigned int __maybe_unused dt_zone_dma_bits;
+ phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
#ifdef CONFIG_ZONE_DMA
acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = dma32_phys_limit;
#endif
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = PHYS_MASK + 1;
max_zone_pfns[ZONE_NORMAL] = max;
free_area_init(max_zone_pfns);
early_init_fdt_scan_reserved_mem();
- if (IS_ENABLED(CONFIG_ZONE_DMA32))
- arm64_dma32_phys_limit = max_zone_phys(32);
- else
- arm64_dma32_phys_limit = PHYS_MASK + 1;
-
reserve_elfcorehdr();
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
- dma_contiguous_reserve(arm64_dma32_phys_limit);
}
void __init bootmem_init(void)
sparse_init();
zone_sizes_init(min, max);
+ /*
+ * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+ */
+ dma_contiguous_reserve(arm64_dma_phys_limit);
+
/*
* request_standard_resources() depends on crashkernel's memory being
* reserved, so do it here.
void __init mem_init(void)
{
if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+ max_pfn > PFN_DOWN(arm64_dma_phys_limit))
swiotlb_init(1);
else
swiotlb_force = SWIOTLB_NO_FORCE;
#endif
#ifdef CONFIG_KASAN_HW_TAGS
-#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1
+#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
#else
#define TCR_KASAN_HW_FLAGS 0
#endif
generic-y += asm-offsets.h
generic-y += gpio.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += qrwlock.h
generic-y += user.h
generic-y += vmlinux.lds.h
generic-y += asm-offsets.h
generic-y += extable.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += parport.h
generic-y += spinlock.h
generic-y += extable.h
generic-y += iomap.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
+++ /dev/null
-#include <asm-generic/local64.h>
#define _ASM_IA64_SPARSEMEM_H
#ifdef CONFIG_SPARSEMEM
+#include <asm/page.h>
/*
* SECTION_SIZE_BITS 2^N: how big each section will be
* MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space
if (map_start < map_end)
memmap_init_zone((unsigned long)(map_end - map_start),
- args->nid, args->zone, page_to_pfn(map_start),
+ args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end),
MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
return 0;
}
unsigned long start_pfn)
{
if (!vmem_map) {
- memmap_init_zone(size, nid, zone, start_pfn,
+ memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size,
MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
} else {
struct page *start;
generated-y += syscall_table.h
generic-y += extable.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += spinlock.h
generated-y += syscall_table.h
generic-y += extable.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += parport.h
generic-y += syscalls.h
#include <linux/libfdt.h>
#include <asm/addrspace.h>
+#include <asm/unaligned.h>
/*
* These two variables specify the free mem region
dtb_size = fdt_totalsize((void *)&__appended_dtb);
/* last four bytes is always image size in little endian */
- image_size = le32_to_cpup((void *)&__image_end - 4);
+ image_size = get_unaligned_le32((void *)&__image_end - 4);
/* copy dtb to where the booted kernel will expect it */
memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
static int __init octeon_irq_init_ciu(
struct device_node *ciu_node, struct device_node *parent)
{
- unsigned int i, r;
+ int i, r;
struct irq_chip *chip;
struct irq_chip *chip_edge;
struct irq_chip *chip_mbox;
generated-y += syscall_table_64_o32.h
generic-y += export.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += parport.h
generic-y += qrwlock.h
#undef ns_to_kernel_old_timeval
#define ns_to_kernel_old_timeval ns_to_old_timeval32
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t compat_long_t
+#define user_siginfo_t compat_siginfo_t
+#define copy_siginfo_to_external copy_siginfo_to_external32
+
#include "../../../fs/binfmt_elf.c"
#undef ns_to_kernel_old_timeval
#define ns_to_kernel_old_timeval ns_to_old_timeval32
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t compat_long_t
+#define user_siginfo_t compat_siginfo_t
+#define copy_siginfo_to_external copy_siginfo_to_external32
+
#include "../../../fs/binfmt_elf.c"
static inline __init unsigned long rotate_xor(unsigned long hash,
const void *area, size_t size)
{
- size_t i;
- unsigned long *ptr = (unsigned long *)area;
+ const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash));
+ size_t diff, i;
+
+ diff = (void *)ptr - area;
+ if (unlikely(size < diff + sizeof(hash)))
+ return hash;
+
+ size = ALIGN_DOWN(size - diff, sizeof(hash));
for (i = 0; i < size / sizeof(hash); i++) {
/* Rotate by odd number of bits and XOR. */
generic-y += export.h
generic-y += gpio.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += parport.h
generic-y += user.h
# SPDX-License-Identifier: GPL-2.0
generic-y += extable.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += qspinlock_types.h
generic-y += qspinlock.h
generated-y += syscall_table_64.h
generated-y += syscall_table_c32.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += user.h
generated-y += syscall_table_spu.h
generic-y += export.h
generic-y += kvm_types.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += qrwlock.h
generic-y += vtime.h
return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz);
}
+#ifdef __powerpc64__
+
static __always_inline
int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
{
return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
}
-#ifdef CONFIG_VDSO32
+#else
#define BUILD_VDSO32 1
+static __always_inline
+int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts);
+}
+
static __always_inline
int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
{
MachineCheck:
EXCEPTION_PROLOG_0
#ifdef CONFIG_PPC_CHRP
+#ifdef CONFIG_VMAP_STACK
+ mtspr SPRN_SPRG_SCRATCH2,r1
+ mfspr r1, SPRN_SPRG_THREAD
+ lwz r1, RTAS_SP(r1)
+ cmpwi cr1, r1, 0
+ bne cr1, 7f
+ mfspr r1, SPRN_SPRG_SCRATCH2
+#else
mfspr r11, SPRN_SPRG_THREAD
lwz r11, RTAS_SP(r11)
cmpwi cr1, r11, 0
bne cr1, 7f
+#endif
#endif /* CONFIG_PPC_CHRP */
EXCEPTION_PROLOG_1 for_rtas=1
7: EXCEPTION_PROLOG_2
ALIGN_FUNCTION();
#endif
/* careful! __ftr_alt_* sections need to be close to .text */
- *(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text);
+ *(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text);
#ifdef CONFIG_PPC64
*(.tramp.ftrace.text);
#endif
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
_sinittext = .;
INIT_TEXT
+
+ /*
+ *.init.text might be RO so we must ensure this section ends on
+ * a page boundary.
+ */
+ . = ALIGN(PAGE_SIZE);
_einittext = .;
#ifdef CONFIG_PPC64
*(.tramp.ftrace.init);
EXIT_TEXT
}
+ . = ALIGN(PAGE_SIZE);
+
INIT_DATA_SECTION(16)
. = ALIGN(8);
config PAGE_OFFSET
hex
- default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
+ default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB
default 0x80000000 if 64BIT && !MMU
default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
choice
prompt "Maximum Physical Memory"
- default MAXPHYSMEM_2GB if 32BIT
+ default MAXPHYSMEM_1GB if 32BIT
default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW
default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY
+ config MAXPHYSMEM_1GB
+ bool "1GiB"
config MAXPHYSMEM_2GB
bool "2GiB"
config MAXPHYSMEM_128GB
phy-mode = "gmii";
phy-handle = <&phy0>;
phy0: ethernet-phy@0 {
+ compatible = "ethernet-phy-id0007.0771";
reg = <0>;
+ reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>;
};
};
CONFIG_HW_RANDOM_VIRTIO=y
CONFIG_SPI=y
CONFIG_SPI_SIFIVE=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SIFIVE=y
# CONFIG_PTP_1588_CLOCK is not set
CONFIG_POWER_RESET=y
CONFIG_DRM=y
generic-y += extable.h
generic-y += flat.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += user.h
generic-y += vmlinux.lds.h
| _PAGE_DIRTY)
#define PAGE_KERNEL __pgprot(_PAGE_KERNEL)
-#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
#define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
#define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \
#include <linux/types.h>
-#ifndef GENERIC_TIME_VSYSCALL
+#ifndef CONFIG_GENERIC_TIME_VSYSCALL
struct vdso_data {
};
#endif
static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
{
- struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id());
+ /*
+ * Using raw_smp_processor_id() elides a preemptability check, but this
+ * is really indicative of a larger problem: the cacheinfo UABI assumes
+ * that cores have a homonogenous view of the cache hierarchy. That
+ * happens to be the case for the current set of RISC-V systems, but
+ * likely won't be true in general. Since there's no way to provide
+ * correct information for these systems via the current UABI we're
+ * just eliding the check for now.
+ */
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
struct cacheinfo *this_leaf;
int index;
REG_L a1, (a1)
jr a1
1:
-#ifdef CONFIG_TRACE_IRQFLAGS
- call trace_hardirqs_on
-#endif
/*
* Exceptions run with interrupts enabled or disabled depending on the
* state of SR_PIE in m/sstatus.
*/
andi t0, s1, SR_PIE
beqz t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+ call trace_hardirqs_on
+#endif
csrs CSR_STATUS, SR_IE
1:
tail do_trap_unknown
handle_syscall:
+#ifdef CONFIG_RISCV_M_MODE
+ /*
+ * When running is M-Mode (no MMU config), MPIE does not get set.
+ * As a result, we need to force enable interrupts here because
+ * handle_exception did not do set SR_IE as it always sees SR_PIE
+ * being cleared.
+ */
+ csrs CSR_STATUS, SR_IE
+#endif
#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
/* Recover a0 - a7 for system calls */
REG_L a0, PT_A0(sp)
* Syscall number held in a7.
* If syscall number is above allowed value, redirect to ni_syscall.
*/
- bge a7, t0, 1f
- /*
- * Check if syscall is rejected by tracer, i.e., a7 == -1.
- * If yes, we pretend it was executed.
- */
- li t1, -1
- beq a7, t1, ret_from_syscall_rejected
- blt a7, t1, 1f
+ bgeu a7, t0, 1f
/* Call syscall */
la s0, sys_call_table
slli t0, a7, RISCV_LGPTR
{
struct memblock_region *region = NULL;
struct resource *res = NULL;
- int ret = 0;
+ struct resource *mem_res = NULL;
+ size_t mem_res_sz = 0;
+ int ret = 0, i = 0;
code_res.start = __pa_symbol(_text);
code_res.end = __pa_symbol(_etext) - 1;
bss_res.end = __pa_symbol(__bss_stop) - 1;
bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+ mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
+ if (!mem_res)
+ panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
/*
* Start by adding the reserved regions, if they overlap
* with /memory regions, insert_resource later on will take
* care of it.
*/
for_each_reserved_mem_region(region) {
- res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
- if (!res)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- sizeof(struct resource));
+ res = &mem_res[i++];
res->name = "Reserved";
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
* Ignore any other reserved regions within
* system memory.
*/
- if (memblock_is_memory(res->start))
+ if (memblock_is_memory(res->start)) {
+ memblock_free((phys_addr_t) res, sizeof(struct resource));
continue;
+ }
ret = add_resource(&iomem_resource, res);
if (ret < 0)
/* Add /memory regions to the resource tree */
for_each_mem_region(region) {
- res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
- if (!res)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- sizeof(struct resource));
+ res = &mem_res[i++];
if (unlikely(memblock_is_nomap(region))) {
res->name = "Reserved";
return;
error:
- memblock_free((phys_addr_t) res, sizeof(struct resource));
/* Better an empty resource tree than an inconsistent one */
release_child_resources(&iomem_resource);
+ memblock_free((phys_addr_t) mem_res, mem_res_sz);
}
#include <asm/stacktrace.h>
-register unsigned long sp_in_global __asm__("sp");
+register const unsigned long sp_in_global __asm__("sp");
#ifdef CONFIG_FRAME_POINTER
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
- const register unsigned long current_sp = sp_in_global;
fp = (unsigned long)__builtin_frame_address(0);
- sp = current_sp;
+ sp = sp_in_global;
pc = (unsigned long)walk_stackframe;
} else {
/* task blocked in __switch_to */
* Copyright (C) 2017 SiFive
*/
+#include <linux/of_clk.h>
#include <linux/clocksource.h>
#include <linux/delay.h>
#include <asm/sbi.h>
riscv_timebase = prop;
lpj_fine = riscv_timebase / HZ;
+
+ of_clk_init(NULL);
timer_probe();
}
#include <linux/binfmts.h>
#include <linux/err.h>
#include <asm/page.h>
-#ifdef GENERIC_TIME_VSYSCALL
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
#include <vdso/datapage.h>
#else
#include <asm/vdso.h>
void __init setup_bootmem(void)
{
phys_addr_t mem_start = 0;
- phys_addr_t start, end = 0;
+ phys_addr_t start, dram_end, end = 0;
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
+ phys_addr_t max_mapped_addr = __pa(~(ulong)0);
u64 i;
/* Find the memory region containing the kernel */
/* Reserve from the start of the kernel to the end of the kernel */
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
- max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+ dram_end = memblock_end_of_DRAM();
+
+ /*
+ * memblock allocator is not aware of the fact that last 4K bytes of
+ * the addressable memory can not be mapped because of IS_ERR_VALUE
+ * macro. Make sure that last 4k bytes are not usable by memblock
+ * if end of dram is equal to maximum addressable memory.
+ */
+ if (max_mapped_addr == (dram_end - 1))
+ memblock_set_current_limit(max_mapped_addr - 4096);
+
+ max_pfn = PFN_DOWN(dram_end);
max_low_pfn = max_pfn;
dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
set_max_mapnr(max_low_pfn);
VMALLOC_END));
for_each_mem_range(i, &_start, &_end) {
- void *start = (void *)_start;
- void *end = (void *)_end;
+ void *start = (void *)__va(_start);
+ void *end = (void *)__va(_end);
if (start >= end)
break;
config S390
def_bool y
+ #
+ # Note: keep this list sorted alphabetically
+ #
+ imply IMA_SECURE_AND_OR_TRUSTED_BOOT
select ARCH_BINFMT_ELF_STATE
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DEBUG_WX
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
+ select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_GIGANTIC_PAGE
select ARCH_HAS_KCOV
select ARCH_HAS_MEM_ENCRYPT
select ARCH_HAS_PTE_SPECIAL
+ select ARCH_HAS_SCALED_CPUTIME
select ARCH_HAS_SET_MEMORY
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_STRICT_MODULE_RWX
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_TABLE_SORT
select CLONE_BACKWARDS2
+ select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select DMA_OPS if PCI
select DYNAMIC_FTRACE if FUNCTION_TRACER
+ select GENERIC_ALLOCATOR
select GENERIC_CPU_AUTOPROBE
select GENERIC_CPU_VULNERABILITIES
select GENERIC_FIND_FIRST_BIT
select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN
select HAVE_ARCH_KASAN_VMALLOC
- select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_SOFT_DIRTY
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_VMAP_STACK
select HAVE_ASM_MODVERSIONS
- select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
select HAVE_CMPXCHG_DOUBLE
select HAVE_CMPXCHG_LOCAL
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
- select HAVE_FAST_GUP
+ select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES
select HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select HAVE_FAST_GUP
select HAVE_FENTRY
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_ERROR_INJECTION
select HAVE_KRETPROBES
select HAVE_KVM
select HAVE_LIVEPATCH
- select HAVE_PERF_REGS
- select HAVE_PERF_USER_STACK_DUMP
select HAVE_MEMBLOCK_PHYS_MAP
- select MMU_GATHER_NO_GATHER
select HAVE_MOD_ARCH_SPECIFIC
+ select HAVE_NMI
select HAVE_NOP_MCOUNT
select HAVE_OPROFILE
select HAVE_PCI
select HAVE_PERF_EVENTS
- select MMU_GATHER_RCU_TABLE_FREE
+ select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE
select HAVE_RSEQ
select HAVE_VIRT_CPU_ACCOUNTING_IDLE
select IOMMU_HELPER if PCI
select IOMMU_SUPPORT if PCI
+ select MMU_GATHER_NO_GATHER
+ select MMU_GATHER_RCU_TABLE_FREE
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE if PCI
select NEED_SG_DMA_LENGTH if PCI
select PCI_MSI if PCI
select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
select SPARSE_IRQ
+ select SWIOTLB
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
select TTY
select VIRT_CPU_ACCOUNTING
- select ARCH_HAS_SCALED_CPUTIME
- select HAVE_NMI
- select ARCH_HAS_FORCE_DMA_UNENCRYPTED
- select SWIOTLB
- select GENERIC_ALLOCATOR
- imply IMA_SECURE_AND_OR_TRUSTED_BOOT
-
+ # Note: keep the above list sorted alphabetically
config SCHED_OMIT_FRAME_POINTER
def_bool y
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_STATIC_KEYS_SELFTEST=y
+CONFIG_SECCOMP_CACHE_DEBUG=y
CONFIG_LOCK_EVENT_COUNTS=y
+# CONFIG_GCC_PLUGINS is not set
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
CONFIG_SCSI_CONSTANTS=y
CONFIG_SCSI_LOGGING=y
CONFIG_SCSI_SPI_ATTRS=m
-CONFIG_SCSI_FC_ATTRS=y
+CONFIG_SCSI_FC_ATTRS=m
CONFIG_SCSI_SAS_LIBSAS=m
CONFIG_SCSI_SRP_ATTRS=m
CONFIG_ISCSI_TCP=m
CONFIG_SCSI_DEBUG=m
-CONFIG_ZFCP=y
+CONFIG_ZFCP=m
CONFIG_SCSI_VIRTIO=m
CONFIG_SCSI_DH=y
CONFIG_SCSI_DH_RDAC=m
CONFIG_DM_MULTIPATH_QL=m
CONFIG_DM_MULTIPATH_ST=m
CONFIG_DM_MULTIPATH_HST=m
+CONFIG_DM_MULTIPATH_IOA=m
CONFIG_DM_DELAY=m
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_NULL_TTY=m
CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_VIRTIO_INPUT=y
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
+# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_S390_CCW_IOMMU=y
CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_CIFS_POSIX=y
# CONFIG_CIFS_DEBUG is not set
CONFIG_CIFS_DFS_UPCALL=y
+CONFIG_CIFS_SWN_UPCALL=y
CONFIG_NLS_DEFAULT="utf8"
CONFIG_NLS_CODEPAGE_437=m
CONFIG_NLS_CODEPAGE_850=m
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
+CONFIG_FTRACE_STARTUP_TEST=y
+# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
CONFIG_DEBUG_USER_ASCE=y
CONFIG_NOTIFIER_ERROR_INJECTION=m
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
+# CONFIG_GCC_PLUGINS is not set
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
CONFIG_PERCPU_STATS=y
-CONFIG_GUP_TEST=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_PACKET_DIAG=m
CONFIG_SCSI_CONSTANTS=y
CONFIG_SCSI_LOGGING=y
CONFIG_SCSI_SPI_ATTRS=m
-CONFIG_SCSI_FC_ATTRS=y
+CONFIG_SCSI_FC_ATTRS=m
CONFIG_SCSI_SAS_LIBSAS=m
CONFIG_SCSI_SRP_ATTRS=m
CONFIG_ISCSI_TCP=m
CONFIG_SCSI_DEBUG=m
-CONFIG_ZFCP=y
+CONFIG_ZFCP=m
CONFIG_SCSI_VIRTIO=m
CONFIG_SCSI_DH=y
CONFIG_SCSI_DH_RDAC=m
CONFIG_DM_MULTIPATH_QL=m
CONFIG_DM_MULTIPATH_ST=m
CONFIG_DM_MULTIPATH_HST=m
+CONFIG_DM_MULTIPATH_IOA=m
CONFIG_DM_DELAY=m
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
-CONFIG_NULL_TTY=m
CONFIG_VIRTIO_CONSOLE=y
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_VIRTIO_INPUT=y
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
+# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_S390_CCW_IOMMU=y
CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_CIFS_POSIX=y
# CONFIG_CIFS_DEBUG is not set
CONFIG_CIFS_DFS_UPCALL=y
+CONFIG_CIFS_SWN_UPCALL=y
CONFIG_NLS_DEFAULT="utf8"
CONFIG_NLS_CODEPAGE_437=m
CONFIG_NLS_CODEPAGE_850=m
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
+CONFIG_DEBUG_USER_ASCE=y
CONFIG_LKDTM=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
# CONFIG_VIRTUALIZATION is not set
# CONFIG_S390_GUEST is not set
# CONFIG_SECCOMP is not set
+# CONFIG_GCC_PLUGINS is not set
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_HID is not set
# CONFIG_VIRTIO_MENU is not set
# CONFIG_VHOST_MENU is not set
+# CONFIG_SURFACE_PLATFORMS is not set
# CONFIG_IOMMU_SUPPORT is not set
# CONFIG_DNOTIFY is not set
# CONFIG_INOTIFY_USER is not set
generic-y += asm-offsets.h
generic-y += export.h
generic-y += kvm_types.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
# SPDX-License-Identifier: GPL-2.0
generated-y += syscall_table.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += parport.h
generated-y += syscall_table_c32.h
generic-y += export.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
select KMAP_LOCAL
select MODULES_USE_ELF_REL
select OLD_SIGACTION
+ select ARCH_SPLIT_ARG64
config X86_64
def_bool y
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>
#include <asm/idtentry.h>
+#include <linux/kexec.h>
#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
+int hyperv_init_cpuhp;
+
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
.resume = hv_resume,
};
+static void (* __initdata old_setup_percpu_clockev)(void);
+
+static void __init hv_stimer_setup_percpu_clockev(void)
+{
+ /*
+ * Ignore any errors in setting up stimer clockevents
+ * as we can run with the LAPIC timer as a fallback.
+ */
+ (void)hv_stimer_alloc();
+
+ /*
+ * Still register the LAPIC timer, because the direct-mode STIMER is
+ * not supported by old versions of Hyper-V. This also allows users
+ * to switch to LAPIC timer via /sys, if they want to.
+ */
+ if (old_setup_percpu_clockev)
+ old_setup_percpu_clockev();
+}
+
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
/*
- * Ignore any errors in setting up stimer clockevents
- * as we can run with the LAPIC timer as a fallback.
+ * hyperv_init() is called before LAPIC is initialized: see
+ * apic_intr_mode_init() -> x86_platform.apic_post_init() and
+ * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER
+ * depends on LAPIC, so hv_stimer_alloc() should be called from
+ * x86_init.timers.setup_percpu_clockev.
*/
- (void)hv_stimer_alloc();
+ old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
+ x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;
hv_apic_init();
register_syscore_ops(&hv_syscore_ops);
+ hyperv_init_cpuhp = cpuhp;
return;
remove_cpuhp_state:
if (!hv_hypercall_pg)
goto do_native;
- if (cpumask_empty(cpus))
- return;
-
local_irq_save(flags);
+ /*
+ * Only check the mask _after_ interrupt has been disabled to avoid the
+ * mask changing under our feet.
+ */
+ if (cpumask_empty(cpus)) {
+ local_irq_restore(flags);
+ return;
+ }
+
flush_pcpu = (struct hv_tlb_flush **)
this_cpu_ptr(hyperv_pcpu_input_arg);
*/
bool tdp_mmu_enabled;
- /* List of struct tdp_mmu_pages being used as roots */
+ /*
+ * List of struct kvmp_mmu_pages being used as roots.
+ * All struct kvm_mmu_pages in the list should have
+ * tdp_mmu_page set.
+ * All struct kvm_mmu_pages in the list should have a positive
+ * root_count except when a thread holds the MMU lock and is removing
+ * an entry from the list.
+ */
struct list_head tdp_mmu_roots;
- /* List of struct tdp_mmu_pages not being used as roots */
+
+ /*
+ * List of struct kvmp_mmu_pages not being used as roots.
+ * All struct kvm_mmu_pages in the list should have
+ * tdp_mmu_page set and a root_count of 0.
+ */
struct list_head tdp_mmu_pages;
};
void (*migrate_timers)(struct kvm_vcpu *vcpu);
void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
+
+ void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
};
struct kvm_x86_nested_ops {
int kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
int kvm_emulate_halt(struct kvm_vcpu *vcpu);
int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
+int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu);
int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+++ /dev/null
-#include <asm-generic/local64.h>
#if IS_ENABLED(CONFIG_HYPERV)
+extern int hyperv_init_cpuhp;
+
extern void *hv_hypercall_pg;
extern void __percpu **hyperv_pcpu_input_arg;
{
if (kexec_in_progress && hv_kexec_handler)
hv_kexec_handler();
+
+ /*
+ * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+ * corrupts the old VP Assist Pages and can crash the kexec kernel.
+ */
+ if (kexec_in_progress && hyperv_init_cpuhp > 0)
+ cpuhp_remove_state(hyperv_init_cpuhp);
+
+ /* The function calls stop_other_cpus(). */
native_machine_shutdown();
+
+ /* Disable the hypercall page when there is only 1 active CPU. */
+ if (kexec_in_progress)
+ hyperv_cleanup();
}
static void hv_machine_crash_shutdown(struct pt_regs *regs)
{
if (hv_crash_handler)
hv_crash_handler(regs);
+
+ /* The function calls crash_smp_send_stop(). */
native_machine_crash_shutdown(regs);
+
+ /* Disable the hypercall page when there is only 1 active CPU. */
+ hyperv_cleanup();
}
#endif /* CONFIG_KEXEC_CORE */
#endif /* CONFIG_HYPERV */
*repeat = 0;
*uniform = 1;
- /* Make end inclusive instead of exclusive */
- end--;
-
prev_match = MTRR_TYPE_INVALID;
for (i = 0; i < num_var_ranges; ++i) {
unsigned short start_state, end_state, inclusive;
int repeat;
u64 partial_end;
+ /* Make end inclusive instead of exclusive */
+ end--;
+
if (!mtrr_state_set)
return MTRR_TYPE_INVALID;
kfree(rdtgrp);
}
-struct task_move_callback {
- struct callback_head work;
- struct rdtgroup *rdtgrp;
-};
-
-static void move_myself(struct callback_head *head)
+static void _update_task_closid_rmid(void *task)
{
- struct task_move_callback *callback;
- struct rdtgroup *rdtgrp;
-
- callback = container_of(head, struct task_move_callback, work);
- rdtgrp = callback->rdtgrp;
-
/*
- * If resource group was deleted before this task work callback
- * was invoked, then assign the task to root group and free the
- * resource group.
+ * If the task is still current on this CPU, update PQR_ASSOC MSR.
+ * Otherwise, the MSR is updated when the task is scheduled in.
*/
- if (atomic_dec_and_test(&rdtgrp->waitcount) &&
- (rdtgrp->flags & RDT_DELETED)) {
- current->closid = 0;
- current->rmid = 0;
- rdtgroup_remove(rdtgrp);
- }
-
- if (unlikely(current->flags & PF_EXITING))
- goto out;
-
- preempt_disable();
- /* update PQR_ASSOC MSR to make resource group go into effect */
- resctrl_sched_in();
- preempt_enable();
+ if (task == current)
+ resctrl_sched_in();
+}
-out:
- kfree(callback);
+static void update_task_closid_rmid(struct task_struct *t)
+{
+ if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
+ smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
+ else
+ _update_task_closid_rmid(t);
}
static int __rdtgroup_move_task(struct task_struct *tsk,
struct rdtgroup *rdtgrp)
{
- struct task_move_callback *callback;
- int ret;
-
- callback = kzalloc(sizeof(*callback), GFP_KERNEL);
- if (!callback)
- return -ENOMEM;
- callback->work.func = move_myself;
- callback->rdtgrp = rdtgrp;
+ /* If the task is already in rdtgrp, no need to move the task. */
+ if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
+ tsk->rmid == rdtgrp->mon.rmid) ||
+ (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
+ tsk->closid == rdtgrp->mon.parent->closid))
+ return 0;
/*
- * Take a refcount, so rdtgrp cannot be freed before the
- * callback has been invoked.
+ * Set the task's closid/rmid before the PQR_ASSOC MSR can be
+ * updated by them.
+ *
+ * For ctrl_mon groups, move both closid and rmid.
+ * For monitor groups, can move the tasks only from
+ * their parent CTRL group.
*/
- atomic_inc(&rdtgrp->waitcount);
- ret = task_work_add(tsk, &callback->work, TWA_RESUME);
- if (ret) {
- /*
- * Task is exiting. Drop the refcount and free the callback.
- * No need to check the refcount as the group cannot be
- * deleted before the write function unlocks rdtgroup_mutex.
- */
- atomic_dec(&rdtgrp->waitcount);
- kfree(callback);
- rdt_last_cmd_puts("Task exited\n");
- } else {
- /*
- * For ctrl_mon groups move both closid and rmid.
- * For monitor groups, can move the tasks only from
- * their parent CTRL group.
- */
- if (rdtgrp->type == RDTCTRL_GROUP) {
- tsk->closid = rdtgrp->closid;
+
+ if (rdtgrp->type == RDTCTRL_GROUP) {
+ tsk->closid = rdtgrp->closid;
+ tsk->rmid = rdtgrp->mon.rmid;
+ } else if (rdtgrp->type == RDTMON_GROUP) {
+ if (rdtgrp->mon.parent->closid == tsk->closid) {
tsk->rmid = rdtgrp->mon.rmid;
- } else if (rdtgrp->type == RDTMON_GROUP) {
- if (rdtgrp->mon.parent->closid == tsk->closid) {
- tsk->rmid = rdtgrp->mon.rmid;
- } else {
- rdt_last_cmd_puts("Can't move task to different control group\n");
- ret = -EINVAL;
- }
+ } else {
+ rdt_last_cmd_puts("Can't move task to different control group\n");
+ return -EINVAL;
}
}
- return ret;
+
+ /*
+ * Ensure the task's closid and rmid are written before determining if
+ * the task is current that will decide if it will be interrupted.
+ */
+ barrier();
+
+ /*
+ * By now, the task's closid and rmid are set. If the task is current
+ * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
+ * group go into effect. If the task is not current, the MSR will be
+ * updated when the task is scheduled in.
+ */
+ update_task_closid_rmid(tsk);
+
+ return 0;
}
static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
case 0xe4:
case 0xe5:
*exitinfo |= IOIO_TYPE_IN;
- *exitinfo |= (u64)insn->immediate.value << 16;
+ *exitinfo |= (u8)insn->immediate.value << 16;
break;
/* OUT immediate opcodes */
case 0xe6:
case 0xe7:
*exitinfo |= IOIO_TYPE_OUT;
- *exitinfo |= (u64)insn->immediate.value << 16;
+ *exitinfo |= (u8)insn->immediate.value << 16;
break;
/* IN register opcodes */
(unsigned long long)vcpu->arch.pv_eoi.msr_val);
return false;
}
- return val & 0x1;
+ return val & KVM_PV_EOI_ENABLED;
}
static void pv_eoi_set_pending(struct kvm_vcpu *vcpu)
/* evaluate pending_events before reading the vector */
smp_rmb();
sipi_vector = apic->sipi_vector;
- kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);
+ kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector);
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
}
if (e < s)
return 0;
- return ((1ULL << (e - s + 1)) - 1) << s;
+ return ((2ULL << (e - s)) - 1) << s;
}
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask);
* Return the level of the lowest level SPTE added to sptes.
* That SPTE may be non-present.
*/
-static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
{
struct kvm_shadow_walk_iterator iterator;
- int leaf = vcpu->arch.mmu->root_level;
+ int leaf = -1;
u64 spte;
-
walk_shadow_page_lockless_begin(vcpu);
- for (shadow_walk_init(&iterator, vcpu, addr);
+ for (shadow_walk_init(&iterator, vcpu, addr),
+ *root_level = iterator.level;
shadow_walk_okay(&iterator);
__shadow_walk_next(&iterator, spte)) {
leaf = iterator.level;
spte = mmu_spte_get_lockless(iterator.sptep);
- sptes[leaf - 1] = spte;
+ sptes[leaf] = spte;
if (!is_shadow_present_pte(spte))
break;
-
}
walk_shadow_page_lockless_end(vcpu);
return leaf;
}
-/* return true if reserved bit is detected on spte. */
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
{
- u64 sptes[PT64_ROOT_MAX_LEVEL];
+ u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
struct rsvd_bits_validate *rsvd_check;
- int root = vcpu->arch.mmu->shadow_root_level;
- int leaf;
- int level;
+ int root, leaf, level;
bool reserved = false;
if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) {
}
if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))
- leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes);
+ leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
else
- leaf = get_walk(vcpu, addr, sptes);
+ leaf = get_walk(vcpu, addr, sptes, &root);
+
+ if (unlikely(leaf < 0)) {
+ *sptep = 0ull;
+ return reserved;
+ }
+
+ *sptep = sptes[leaf];
+
+ /*
+ * Skip reserved bits checks on the terminal leaf if it's not a valid
+ * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by
+ * design, always have reserved bits set. The purpose of the checks is
+ * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+ */
+ if (!is_shadow_present_pte(sptes[leaf]))
+ leaf++;
rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
- for (level = root; level >= leaf; level--) {
- if (!is_shadow_present_pte(sptes[level - 1]))
- break;
+ for (level = root; level >= leaf; level--)
/*
* Use a bitwise-OR instead of a logical-OR to aggregate the
* reserved bit and EPT's invalid memtype/XWR checks to avoid
* adding a Jcc in the loop.
*/
- reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) |
- __is_rsvd_bits_set(rsvd_check, sptes[level - 1],
- level);
- }
+ reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) |
+ __is_rsvd_bits_set(rsvd_check, sptes[level], level);
if (reserved) {
pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
__func__, addr);
for (level = root; level >= leaf; level--)
pr_err("------ spte 0x%llx level %d.\n",
- sptes[level - 1], level);
+ sptes[level], level);
}
- *sptep = sptes[leaf - 1];
-
return reserved;
}
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
}
-#define for_each_tdp_mmu_root(_kvm, _root) \
+static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root)
+{
+ if (kvm_mmu_put_root(kvm, root))
+ kvm_tdp_mmu_free_root(kvm, root);
+}
+
+static inline bool tdp_mmu_next_root_valid(struct kvm *kvm,
+ struct kvm_mmu_page *root)
+{
+ lockdep_assert_held(&kvm->mmu_lock);
+
+ if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link))
+ return false;
+
+ kvm_mmu_get_root(kvm, root);
+ return true;
+
+}
+
+static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
+ struct kvm_mmu_page *root)
+{
+ struct kvm_mmu_page *next_root;
+
+ next_root = list_next_entry(root, link);
+ tdp_mmu_put_root(kvm, root);
+ return next_root;
+}
+
+/*
+ * Note: this iterator gets and puts references to the roots it iterates over.
+ * This makes it safe to release the MMU lock and yield within the loop, but
+ * if exiting the loop early, the caller must drop the reference to the most
+ * recent root. (Unless keeping a live reference is desirable.)
+ */
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \
+ for (_root = list_first_entry(&_kvm->arch.tdp_mmu_roots, \
+ typeof(*_root), link); \
+ tdp_mmu_next_root_valid(_kvm, _root); \
+ _root = tdp_mmu_next_root(_kvm, _root))
+
+#define for_each_tdp_mmu_root(_kvm, _root) \
list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
struct kvm_mmu_page *root;
bool flush = false;
- for_each_tdp_mmu_root(kvm, root) {
- /*
- * Take a reference on the root so that it cannot be freed if
- * this thread releases the MMU lock and yields in this loop.
- */
- kvm_mmu_get_root(kvm, root);
-
+ for_each_tdp_mmu_root_yield_safe(kvm, root)
flush |= zap_gfn_range(kvm, root, start, end, true);
- kvm_mmu_put_root(kvm, root);
- }
-
return flush;
}
int ret = 0;
int as_id;
- for_each_tdp_mmu_root(kvm, root) {
- /*
- * Take a reference on the root so that it cannot be freed if
- * this thread releases the MMU lock and yields in this loop.
- */
- kvm_mmu_get_root(kvm, root);
-
+ for_each_tdp_mmu_root_yield_safe(kvm, root) {
as_id = kvm_mmu_page_as_id(root);
slots = __kvm_memslots(kvm, as_id);
kvm_for_each_memslot(memslot, slots) {
ret |= handler(kvm, memslot, root, gfn_start,
gfn_end, data);
}
-
- kvm_mmu_put_root(kvm, root);
}
return ret;
int root_as_id;
bool spte_set = false;
- for_each_tdp_mmu_root(kvm, root) {
+ for_each_tdp_mmu_root_yield_safe(kvm, root) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
- /*
- * Take a reference on the root so that it cannot be freed if
- * this thread releases the MMU lock and yields in this loop.
- */
- kvm_mmu_get_root(kvm, root);
-
spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages, min_level);
-
- kvm_mmu_put_root(kvm, root);
}
return spte_set;
int root_as_id;
bool spte_set = false;
- for_each_tdp_mmu_root(kvm, root) {
+ for_each_tdp_mmu_root_yield_safe(kvm, root) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
- /*
- * Take a reference on the root so that it cannot be freed if
- * this thread releases the MMU lock and yields in this loop.
- */
- kvm_mmu_get_root(kvm, root);
-
spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages);
-
- kvm_mmu_put_root(kvm, root);
}
return spte_set;
int root_as_id;
bool spte_set = false;
- for_each_tdp_mmu_root(kvm, root) {
+ for_each_tdp_mmu_root_yield_safe(kvm, root) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
- /*
- * Take a reference on the root so that it cannot be freed if
- * this thread releases the MMU lock and yields in this loop.
- */
- kvm_mmu_get_root(kvm, root);
-
spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages);
-
- kvm_mmu_put_root(kvm, root);
}
return spte_set;
}
struct kvm_mmu_page *root;
int root_as_id;
- for_each_tdp_mmu_root(kvm, root) {
+ for_each_tdp_mmu_root_yield_safe(kvm, root) {
root_as_id = kvm_mmu_page_as_id(root);
if (root_as_id != slot->as_id)
continue;
- /*
- * Take a reference on the root so that it cannot be freed if
- * this thread releases the MMU lock and yields in this loop.
- */
- kvm_mmu_get_root(kvm, root);
-
zap_collapsible_spte_range(kvm, root, slot->base_gfn,
slot->base_gfn + slot->npages);
-
- kvm_mmu_put_root(kvm, root);
}
}
* Return the level of the lowest level SPTE added to sptes.
* That SPTE may be non-present.
*/
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ int *root_level)
{
struct tdp_iter iter;
struct kvm_mmu *mmu = vcpu->arch.mmu;
- int leaf = vcpu->arch.mmu->shadow_root_level;
gfn_t gfn = addr >> PAGE_SHIFT;
+ int leaf = -1;
+
+ *root_level = vcpu->arch.mmu->shadow_root_level;
tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
leaf = iter.level;
- sptes[leaf - 1] = iter.old_spte;
+ sptes[leaf] = iter.old_spte;
}
return leaf;
bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
struct kvm_memory_slot *slot, gfn_t gfn);
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes);
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ int *root_level);
+
#endif /* __KVM_X86_MMU_TDP_MMU_H */
static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+
if (!nested_svm_vmrun_msrpm(svm)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror =
svm->nested.vmcb12_gpa = 0;
WARN_ON_ONCE(svm->nested.nested_run_pending);
+ kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
+
/* in case we halted in L2 */
svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
leave_guest_mode(&svm->vcpu);
copy_vmcb_control_area(&vmcb->control, &hsave->control);
nested_svm_uninit_mmu_context(&svm->vcpu);
+ vmcb_mark_all_dirty(svm->vmcb);
}
kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
* in the registers, the save area of the nested state instead
* contains saved L1 state.
*/
+
+ svm->nested.nested_run_pending =
+ !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+
copy_vmcb_control_area(&hsave->control, &svm->vmcb->control);
hsave->save = *save;
goto vmgexit_err;
break;
case SVM_VMGEXIT_NMI_COMPLETE:
+ case SVM_VMGEXIT_AP_HLT_LOOP:
case SVM_VMGEXIT_AP_JUMP_TABLE:
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
break;
case SVM_VMGEXIT_NMI_COMPLETE:
ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET);
break;
+ case SVM_VMGEXIT_AP_HLT_LOOP:
+ ret = kvm_emulate_ap_reset_hold(&svm->vcpu);
+ break;
case SVM_VMGEXIT_AP_JUMP_TABLE: {
struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
* of which one step is to perform a VMLOAD. Since hardware does not
* perform a VMSAVE on VMRUN, the host savearea must be updated.
*/
- asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory");
+ asm volatile(__ex("vmsave %0") : : "a" (__sme_page_pa(sd->save_area)) : "memory");
/*
* Certain MSRs are restored on VMEXIT, only save ones that aren't
wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]);
}
}
+
+void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ /* First SIPI: Use the values as initially set by the VMM */
+ if (!svm->received_first_sipi) {
+ svm->received_first_sipi = true;
+ return;
+ }
+
+ /*
+ * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where
+ * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a
+ * non-zero value.
+ */
+ ghcb_set_sw_exit_info_2(svm->ghcb, 1);
+}
return EXIT_FASTPATH_NONE;
}
-void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
-
static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
struct vcpu_svm *svm)
{
(vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
}
+static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
+{
+ if (!sev_es_guest(vcpu->kvm))
+ return kvm_vcpu_deliver_sipi_vector(vcpu, vector);
+
+ sev_vcpu_deliver_sipi_vector(vcpu, vector);
+}
+
static void svm_vm_destroy(struct kvm *kvm)
{
avic_vm_destroy(kvm);
.msr_filter_changed = svm_msr_filter_changed,
.complete_emulated_msr = svm_complete_emulated_msr,
+
+ .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
};
static struct kvm_x86_init_ops svm_init_ops __initdata = {
struct vmcb_save_area *vmsa;
struct ghcb *ghcb;
struct kvm_host_map ghcb_map;
+ bool received_first_sipi;
/* SEV-ES scratch area support */
void *ghcb_sa;
void sev_es_create_vcpu(struct vcpu_svm *svm);
void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu);
void sev_es_vcpu_put(struct vcpu_svm *svm);
+void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
/* vmenter.S */
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
+ kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
/* Service the TLB flush request for L2 before switching to L1. */
if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
kvm_vcpu_flush_tlb_current(vcpu);
.msr_filter_changed = vmx_msr_filter_changed,
.complete_emulated_msr = kvm_complete_insn_gp,
.cpu_dirty_log_size = vmx_cpu_dirty_log_size,
+
+ .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
};
static __init int hardware_setup(void)
kmem_cache_destroy(x86_fpu_cache);
}
-int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason)
{
++vcpu->stat.halt_exits;
if (lapic_in_kernel(vcpu)) {
- vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+ vcpu->arch.mp_state = state;
return 1;
} else {
- vcpu->run->exit_reason = KVM_EXIT_HLT;
+ vcpu->run->exit_reason = reason;
return 0;
}
}
+
+int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
+{
+ return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT);
+}
EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
int kvm_emulate_halt(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
+int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu)
+{
+ int ret = kvm_skip_emulated_instruction(vcpu);
+
+ return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret;
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold);
+
#ifdef CONFIG_X86_64
static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
unsigned long clock_type)
if (kvm_request_pending(vcpu)) {
if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
- if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
+ if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
+ ;
+ else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
r = 0;
goto out;
}
kvm_apic_accept_events(vcpu);
switch(vcpu->arch.mp_state) {
case KVM_MP_STATE_HALTED:
+ case KVM_MP_STATE_AP_RESET_HOLD:
vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
kvm_load_guest_fpu(vcpu);
kvm_apic_accept_events(vcpu);
- if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
- vcpu->arch.pv.pv_unhalted)
+ if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED ||
+ vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) &&
+ vcpu->arch.pv.pv_unhalted)
mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
else
mp_state->mp_state = vcpu->arch.mp_state;
kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
kvm_rip_write(vcpu, 0);
}
+EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector);
int kvm_arch_hardware_enable(void)
{
}
free_page((unsigned long)pmd_sv);
+
+ pgtable_pmd_page_dtor(virt_to_page(pmd));
free_page((unsigned long)pmd);
return 1;
else
per_cpu(xen_vcpu_id, cpu) = cpu;
rc = xen_vcpu_setup(cpu);
- if (rc)
+ if (rc || !xen_have_vector_callback)
return rc;
- if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+ if (xen_feature(XENFEAT_hvm_safe_pvclock))
xen_setup_timer(cpu);
rc = xen_smp_intr_init(cpu);
return 0;
}
+static bool no_vector_callback __initdata;
+
static void __init xen_hvm_guest_init(void)
{
if (xen_pv_domain())
xen_panic_handler_init();
- if (xen_feature(XENFEAT_hvm_callback_vector))
+ if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector))
xen_have_vector_callback = 1;
xen_hvm_smp_init();
}
early_param("xen_nopv", xen_parse_nopv);
+static __init int xen_parse_no_vector_callback(char *arg)
+{
+ no_vector_callback = true;
+ return 0;
+}
+early_param("xen_no_vector_callback", xen_parse_no_vector_callback);
+
bool __init xen_hvm_need_lapic(void)
{
if (xen_pv_domain())
int cpu;
native_smp_prepare_cpus(max_cpus);
- WARN_ON(xen_smp_intr_init(0));
- xen_init_lock_cpu(0);
+ if (xen_have_vector_callback) {
+ WARN_ON(xen_smp_intr_init(0));
+ xen_init_lock_cpu(0);
+ }
for_each_possible_cpu(cpu) {
if (cpu == 0)
static void xen_hvm_cpu_die(unsigned int cpu)
{
if (common_cpu_die(cpu) == 0) {
- xen_smp_intr_free(cpu);
- xen_uninit_lock_cpu(cpu);
- xen_teardown_timer(cpu);
+ if (xen_have_vector_callback) {
+ xen_smp_intr_free(cpu);
+ xen_uninit_lock_cpu(cpu);
+ xen_teardown_timer(cpu);
+ }
}
}
#else
void __init xen_hvm_smp_init(void)
{
- if (!xen_have_vector_callback)
+ smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
+ smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+ smp_ops.smp_cpus_done = xen_smp_cpus_done;
+ smp_ops.cpu_die = xen_hvm_cpu_die;
+
+ if (!xen_have_vector_callback) {
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+ nopvspin = true;
+#endif
return;
+ }
- smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
- smp_ops.cpu_die = xen_hvm_cpu_die;
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
- smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
- smp_ops.smp_cpus_done = xen_smp_cpus_done;
}
generated-y += syscall_table.h
generic-y += extable.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += param.h
generic-y += qrwlock.h
* limit 'something'.
*/
/* no more than 50% of tags for async I/O */
- bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U);
+ bfqd->word_depths[0][0] = max(bt->sb.depth >> 1, 1U);
/*
* no more than 75% of tags for sync writes (25% extra tags
* w.r.t. async I/O, to prevent async I/O from starving sync
* writes)
*/
- bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U);
+ bfqd->word_depths[0][1] = max((bt->sb.depth * 3) >> 2, 1U);
/*
* In-word depths in case some bfq_queue is being weight-
* shortage.
*/
/* no more than ~18% of tags for async I/O */
- bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U);
+ bfqd->word_depths[1][0] = max((bt->sb.depth * 3) >> 4, 1U);
/* no more than ~37% of tags for sync writes (~20% extra tags) */
- bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U);
+ bfqd->word_depths[1][1] = max((bt->sb.depth * 6) >> 4, 1U);
for (i = 0; i < 2; i++)
for (j = 0; j < 2; j++)
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
+#include <linux/blk-pm.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
/**
* blk_queue_enter() - try to increase q->q_usage_counter
* @q: request queue pointer
- * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PREEMPT
+ * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM
*/
int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags)
{
- const bool pm = flags & BLK_MQ_REQ_PREEMPT;
+ const bool pm = flags & BLK_MQ_REQ_PM;
while (true) {
bool success = false;
* responsible for ensuring that that counter is
* globally visible before the queue is unfrozen.
*/
- if (pm || !blk_queue_pm_only(q)) {
+ if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) ||
+ !blk_queue_pm_only(q)) {
success = true;
} else {
percpu_ref_put(&q->q_usage_counter);
wait_event(q->mq_freeze_wq,
(!q->mq_freeze_depth &&
- (pm || (blk_pm_request_resume(q),
- !blk_queue_pm_only(q)))) ||
+ blk_pm_resume_queue(pm, q)) ||
blk_queue_dying(q));
if (blk_queue_dying(q))
return -ENODEV;
struct request *req;
WARN_ON_ONCE(op & REQ_NOWAIT);
- WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT));
+ WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM));
req = blk_mq_alloc_request(q, op, flags);
if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
bool use_debt, ioc_locked;
unsigned long flags;
- /* bypass IOs if disabled or for root cgroup */
- if (!ioc->enabled || !iocg->level)
+ /* bypass IOs if disabled, still initializing, or for root cgroup */
+ if (!ioc->enabled || !iocg || !iocg->level)
return;
/* calculate the absolute vtime cost */
struct bio *bio)
{
struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg);
- struct ioc *ioc = iocg->ioc;
+ struct ioc *ioc = rqos_to_ioc(rqos);
sector_t bio_end = bio_end_sector(bio);
struct ioc_now now;
u64 vtime, abs_cost, cost;
unsigned long flags;
- /* bypass if disabled or for root cgroup */
- if (!ioc->enabled || !iocg->level)
+ /* bypass if disabled, still initializing, or for root cgroup */
+ if (!ioc->enabled || !iocg || !iocg->level)
return;
abs_cost = calc_vtime_cost(bio, iocg, true);
ioc_refresh_params(ioc, true);
spin_unlock_irq(&ioc->lock);
+ /*
+ * rqos must be added before activation to allow iocg_pd_init() to
+ * lookup the ioc from q. This means that the rqos methods may get
+ * called before policy activation completion, can't assume that the
+ * target bio has an iocg associated and need to test for NULL iocg.
+ */
rq_qos_add(q, rqos);
ret = blkcg_activate_policy(q, &blkcg_policy_iocost);
if (ret) {
QUEUE_FLAG_NAME(PCI_P2PDMA),
QUEUE_FLAG_NAME(ZONE_RESETALL),
QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
+ QUEUE_FLAG_NAME(NOWAIT),
};
#undef QUEUE_FLAG_NAME
HCTX_FLAG_NAME(BLOCKING),
HCTX_FLAG_NAME(NO_SCHED),
HCTX_FLAG_NAME(STACKING),
+ HCTX_FLAG_NAME(TAG_HCTX_SHARED),
};
#undef HCTX_FLAG_NAME
RQF_NAME(MIXED_MERGE),
RQF_NAME(MQ_INFLIGHT),
RQF_NAME(DONTPREP),
- RQF_NAME(PREEMPT),
RQF_NAME(FAILED),
RQF_NAME(QUIET),
RQF_NAME(ELVPRIV),
rq->mq_hctx = data->hctx;
rq->rq_flags = 0;
rq->cmd_flags = data->cmd_flags;
- if (data->flags & BLK_MQ_REQ_PREEMPT)
- rq->rq_flags |= RQF_PREEMPT;
+ if (data->flags & BLK_MQ_REQ_PM)
+ rq->rq_flags |= RQF_PM;
if (blk_queue_io_stat(data->q))
rq->rq_flags |= RQF_IO_STAT;
INIT_LIST_HEAD(&rq->queuelist);
WARN_ON_ONCE(q->rpm_status != RPM_ACTIVE);
+ spin_lock_irq(&q->queue_lock);
+ q->rpm_status = RPM_SUSPENDING;
+ spin_unlock_irq(&q->queue_lock);
+
/*
* Increase the pm_only counter before checking whether any
* non-PM blk_queue_enter() calls are in progress to avoid that any
/* Switch q_usage_counter back to per-cpu mode. */
blk_mq_unfreeze_queue(q);
- spin_lock_irq(&q->queue_lock);
- if (ret < 0)
+ if (ret < 0) {
+ spin_lock_irq(&q->queue_lock);
+ q->rpm_status = RPM_ACTIVE;
pm_runtime_mark_last_busy(q->dev);
- else
- q->rpm_status = RPM_SUSPENDING;
- spin_unlock_irq(&q->queue_lock);
+ spin_unlock_irq(&q->queue_lock);
- if (ret)
blk_clear_pm_only(q);
+ }
return ret;
}
#include <linux/pm_runtime.h>
#ifdef CONFIG_PM
-static inline void blk_pm_request_resume(struct request_queue *q)
+static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q)
{
- if (q->dev && (q->rpm_status == RPM_SUSPENDED ||
- q->rpm_status == RPM_SUSPENDING))
- pm_request_resume(q->dev);
+ if (!q->dev || !blk_queue_pm_only(q))
+ return 1; /* Nothing to do */
+ if (pm && q->rpm_status != RPM_SUSPENDED)
+ return 1; /* Request allowed */
+ pm_request_resume(q->dev);
+ return 0;
}
static inline void blk_pm_mark_last_busy(struct request *rq)
--rq->q->nr_pending;
}
#else
-static inline void blk_pm_request_resume(struct request_queue *q)
+static inline int blk_pm_resume_queue(const bool pm, struct request_queue *q)
{
+ return 1;
}
static inline void blk_pm_mark_last_busy(struct request *rq)
part = rcu_dereference(ptbl->part[piter->idx]);
if (!part)
continue;
+ piter->part = bdgrab(part);
+ if (!piter->part)
+ continue;
if (!bdev_nr_sectors(part) &&
!(piter->flags & DISK_PITER_INCL_EMPTY) &&
!(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
- piter->idx == 0))
+ piter->idx == 0)) {
+ bdput(piter->part);
+ piter->part = NULL;
continue;
+ }
- piter->part = bdgrab(part);
- if (!piter->part)
- continue;
piter->idx += inc;
break;
}
memcpy(cur, e, sizeof(e));
cur += sizeof(e);
/* Zero parameters to satisfy set_pub_key ABI. */
- memset(cur, 0, SETKEY_PARAMS_SIZE);
+ memzero_explicit(cur, SETKEY_PARAMS_SIZE);
return cur - buf;
}
if (ret)
goto error_free_key;
- if (strcmp(sig->pkey_algo, "sm2") == 0 && sig->data_size) {
+ if (sig->pkey_algo && strcmp(sig->pkey_algo, "sm2") == 0 &&
+ sig->data_size) {
ret = cert_sig_digest_update(sig, tfm);
if (ret)
goto error_free_key;
struct ecdh params;
unsigned int ndigits;
- if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0)
+ if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0 ||
+ params.key_size > sizeof(ctx->private_key))
return -EINVAL;
ndigits = ecdh_supported_curve(params.curve_id);
preempt_enable();
// bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s]
+ if (!min)
+ min = 1;
speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
tmpl->speed = speed;
This helps support hotplug of nodes, CPUs, and memory.
- To compile this driver as a module, choose M here:
- the module will be called container.
-
config ACPI_HOTPLUG_MEMORY
bool "Memory Hotplug"
depends on MEMORY_HOTPLUG
removing memory devices at runtime, you need not enable
this driver.
- To compile this driver as a module, choose M here:
- the module will be called acpi_memhotplug.
-
config ACPI_HOTPLUG_IOAPIC
bool
depends on PCI
extern struct list_head acpi_bus_id_list;
struct acpi_device_bus_id {
- char bus_id[15];
+ const char *bus_id;
unsigned int instance_no;
struct list_head node;
};
acpi_device_bus_id->instance_no--;
else {
list_del(&acpi_device_bus_id->node);
+ kfree_const(acpi_device_bus_id->bus_id);
kfree(acpi_device_bus_id);
}
break;
}
if (!found) {
acpi_device_bus_id = new_bus_id;
- strcpy(acpi_device_bus_id->bus_id, acpi_device_hid(device));
+ acpi_device_bus_id->bus_id =
+ kstrdup_const(acpi_device_hid(device), GFP_KERNEL);
+ if (!acpi_device_bus_id->bus_id) {
+ pr_err(PREFIX "Memory allocation error for bus id\n");
+ result = -ENOMEM;
+ goto err_free_new_bus_id;
+ }
+
acpi_device_bus_id->instance_no = 0;
list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
}
if (device->parent)
list_del(&device->node);
list_del(&device->wakeup_list);
+
+ err_free_new_bus_id:
+ if (!found)
+ kfree(new_bus_id);
+
mutex_unlock(&acpi_device_lock);
err_detach:
for (i = 0; i < out_obj->package.count; i++) {
union acpi_object *package = &out_obj->package.elements[i];
- struct lpi_device_info_amd info = { };
- if (package->type == ACPI_TYPE_INTEGER) {
- switch (i) {
- case 0:
- info.revision = package->integer.value;
- break;
- case 1:
- info.count = package->integer.value;
- break;
- }
- } else if (package->type == ACPI_TYPE_PACKAGE) {
+ if (package->type == ACPI_TYPE_PACKAGE) {
lpi_constraints_table = kcalloc(package->package.count,
sizeof(*lpi_constraints_table),
GFP_KERNEL);
for (k = 0; k < info_obj->package.count; ++k) {
union acpi_object *obj = &info_obj->package.elements[k];
- union acpi_object *obj_new;
list = &lpi_constraints_table[lpi_constraints_table_size];
list->min_dstate = -1;
- obj_new = &obj[k];
switch (k) {
case 0:
dev_info.enabled = obj->integer.value;
if ((err = dma_set_mask_and_coherent(&pcidev->dev, DMA_BIT_MASK(32)))) {
printk("idt77252: can't enable DMA for PCI device at %s\n", pci_name(pcidev));
- return err;
+ goto err_out_disable_pdev;
}
card = kzalloc(sizeof(struct idt77252_dev), GFP_KERNEL);
*
* Set the device's firmware node pointer to @fwnode, but if a secondary
* firmware node of the device is present, preserve it.
+ *
+ * Valid fwnode cases are:
+ * - primary --> secondary --> -ENODEV
+ * - primary --> NULL
+ * - secondary --> -ENODEV
+ * - NULL
*/
void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode)
{
} else {
if (fwnode_is_primary(fn)) {
dev->fwnode = fn->secondary;
+ /* Set fn->secondary = NULL, so fn remains the primary fwnode */
if (!(parent && fn == parent->fwnode))
- fn->secondary = ERR_PTR(-ENODEV);
+ fn->secondary = NULL;
} else {
dev->fwnode = NULL;
}
devname = dev_name(map->dev);
if (name) {
- map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
+ if (!map->debugfs_name) {
+ map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
devname, name);
+ if (!map->debugfs_name)
+ return;
+ }
name = map->debugfs_name;
} else {
name = devname;
if (!strcmp(name, "dummy")) {
kfree(map->debugfs_name);
-
map->debugfs_name = kasprintf(GFP_KERNEL, "dummy%d",
dummy_index);
+ if (!map->debugfs_name)
+ return;
name = map->debugfs_name;
dummy_index++;
}
config BLK_DEV_RSXX
tristate "IBM Flash Adapter 900GB Full Height PCIe Device Driver"
depends on PCI
+ select CRC32
help
Device driver for IBM's high speed PCIe SSD
storage device: Flash Adapter 900GB Full Height.
tristate "RDMA Network Block Device driver client"
depends on INFINIBAND_RTRS_CLIENT
select BLK_DEV_RNBD
+ select SG_POOL
help
RNBD client is a network block device driver using rdma transport.
Lutz Pogrell <lutz.pogrell@cloud.ionos.com>
Milind Dumbare <Milind.dumbare@gmail.com>
Roman Penyaev <roman.penyaev@profitbricks.com>
+Swapnil Ingle <ingleswapnil@gmail.com>
init_waitqueue_head(&iu->comp.wait);
iu->comp.errno = INT_MAX;
+ if (sg_alloc_table(&iu->sgt, 1, GFP_KERNEL)) {
+ rnbd_put_permit(sess, permit);
+ kfree(iu);
+ return NULL;
+ }
+
return iu;
}
static void rnbd_put_iu(struct rnbd_clt_session *sess, struct rnbd_iu *iu)
{
if (atomic_dec_and_test(&iu->refcount)) {
+ sg_free_table(&iu->sgt);
rnbd_put_permit(sess, iu->permit);
kfree(iu);
}
iu->buf = NULL;
iu->dev = dev;
- sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
-
msg.hdr.type = cpu_to_le16(RNBD_MSG_CLOSE);
msg.device_id = cpu_to_le32(device_id);
err = errno;
}
- sg_free_table(&iu->sgt);
rnbd_put_iu(sess, iu);
return err;
}
iu->buf = rsp;
iu->dev = dev;
- sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
msg.hdr.type = cpu_to_le16(RNBD_MSG_OPEN);
err = errno;
}
- sg_free_table(&iu->sgt);
rnbd_put_iu(sess, iu);
return err;
}
iu->buf = rsp;
iu->sess = sess;
-
- sg_alloc_table(&iu->sgt, 1, GFP_KERNEL);
sg_init_one(iu->sgt.sgl, rsp, sizeof(*rsp));
msg.hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO);
} else {
err = errno;
}
- sg_free_table(&iu->sgt);
rnbd_put_iu(sess, iu);
return err;
}
*/
list_for_each_entry_safe(sess, sn, &sess_list, list) {
- WARN_ON(!rnbd_clt_get_sess(sess));
+ if (!rnbd_clt_get_sess(sess))
+ continue;
close_rtrs(sess);
list_for_each_entry_safe(dev, tn, &sess->devs_list, list) {
/*
void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev)
{
- mutex_lock(&sess_dev->sess->lock);
- rnbd_srv_destroy_dev_session_sysfs(sess_dev);
- mutex_unlock(&sess_dev->sess->lock);
+ struct rnbd_srv_session *sess = sess_dev->sess;
+
sess_dev->keep_id = true;
+ mutex_lock(&sess->lock);
+ rnbd_srv_destroy_dev_session_sysfs(sess_dev);
+ mutex_unlock(&sess->lock);
}
static int process_msg_close(struct rtrs_srv *rtrs,
{ TEGRA30_CLK_I2S3_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
{ TEGRA30_CLK_I2S4_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
{ TEGRA30_CLK_VIMCLK_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
+ { TEGRA30_CLK_HDA, TEGRA30_CLK_PLL_P, 102000000, 0 },
+ { TEGRA30_CLK_HDA2CODEC_2X, TEGRA30_CLK_PLL_P, 48000000, 0 },
/* must be the last entry */
{ TEGRA30_CLK_CLK_MAX, TEGRA30_CLK_CLK_MAX, 0, 0 },
};
return ret;
}
-static inline int32_t percent_fp(int percent)
-{
- return div_fp(percent, 100);
-}
-
static inline u64 mul_ext_fp(u64 x, u64 y)
{
return (x * y) >> EXT_FRAC_BITS;
return div64_u64(x << EXT_FRAC_BITS, y);
}
-static inline int32_t percent_ext_fp(int percent)
-{
- return div_ext_fp(percent, 100);
-}
-
/**
* struct sample - Store performance sample
* @core_avg_perf: Ratio of APERF/MPERF which is the actual average
unsigned long capacity)
{
struct cpudata *cpu = all_cpu_data[cpunum];
+ u64 hwp_cap = READ_ONCE(cpu->hwp_cap_cached);
int old_pstate = cpu->pstate.current_pstate;
int cap_pstate, min_pstate, max_pstate, target_pstate;
update_turbo_state();
- cap_pstate = global.turbo_disabled ? cpu->pstate.max_pstate :
- cpu->pstate.turbo_pstate;
+ cap_pstate = global.turbo_disabled ? HWP_GUARANTEED_PERF(hwp_cap) :
+ HWP_HIGHEST_PERF(hwp_cap);
/* Optimization: Avoid unnecessary divisions. */
intel_pstate.attr = hwp_cpufreq_attrs;
intel_cpufreq.attr = hwp_cpufreq_attrs;
intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
- intel_cpufreq.fast_switch = NULL;
intel_cpufreq.adjust_perf = intel_cpufreq_adjust_perf;
if (!default_driver)
default_driver = &intel_pstate;
/* Take a frequency, and issue the fid/vid transition command */
static int transition_frequency_fidvid(struct powernow_k8_data *data,
- unsigned int index)
+ unsigned int index,
+ struct cpufreq_policy *policy)
{
- struct cpufreq_policy *policy;
u32 fid = 0;
u32 vid = 0;
int res;
freqs.old = find_khz_freq_from_fid(data->currfid);
freqs.new = find_khz_freq_from_fid(fid);
- policy = cpufreq_cpu_get(smp_processor_id());
- cpufreq_cpu_put(policy);
-
cpufreq_freq_transition_begin(policy, &freqs);
res = transition_fid_vid(data, fid, vid);
cpufreq_freq_transition_end(policy, &freqs, res);
powernow_k8_acpi_pst_values(data, newstate);
- ret = transition_frequency_fidvid(data, newstate);
+ ret = transition_frequency_fidvid(data, newstate, pol);
if (ret) {
pr_err("transition frequency failed\n");
config CRYPTO_DEV_OMAP_SHAM
tristate "Support for OMAP MD5/SHA1/SHA2 hw accelerator"
depends on ARCH_OMAP2PLUS
+ select CRYPTO_ENGINE
select CRYPTO_SHA1
select CRYPTO_MD5
select CRYPTO_SHA256
dmabuf->ops->release(dmabuf);
- mutex_lock(&db_list.lock);
- list_del(&dmabuf->list_node);
- mutex_unlock(&db_list.lock);
-
if (dmabuf->resv == (struct dma_resv *)&dmabuf[1])
dma_resv_fini(dmabuf->resv);
kfree(dmabuf);
}
+static int dma_buf_file_release(struct inode *inode, struct file *file)
+{
+ struct dma_buf *dmabuf;
+
+ if (!is_dma_buf_file(file))
+ return -EINVAL;
+
+ dmabuf = file->private_data;
+
+ mutex_lock(&db_list.lock);
+ list_del(&dmabuf->list_node);
+ mutex_unlock(&db_list.lock);
+
+ return 0;
+}
+
static const struct dentry_operations dma_buf_dentry_ops = {
.d_dname = dmabuffs_dname,
.d_release = dma_buf_release,
}
static const struct file_operations dma_buf_fops = {
+ .release = dma_buf_file_release,
.mmap = dma_buf_mmap_internal,
.llseek = dma_buf_llseek,
.poll = dma_buf_poll,
buffer->vaddr = NULL;
}
+ /* free page list */
+ kfree(buffer->pages);
+ /* release memory */
cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount);
kfree(buffer);
}
if (desc->chunk) {
/* Create and add new element into the linked list */
- desc->chunks_alloc++;
- list_add_tail(&chunk->list, &desc->chunk->list);
if (!dw_edma_alloc_burst(chunk)) {
kfree(chunk);
return NULL;
}
+ desc->chunks_alloc++;
+ list_add_tail(&chunk->list, &desc->chunk->list);
} else {
/* List head */
chunk->burst = NULL;
return 0;
drv_fail:
- for (; i > 0; i--)
+ while (--i >= 0)
driver_unregister(&idxd_drvs[i]->drv);
return rc;
}
return 0;
bus_err:
- for (; i > 0; i--)
+ while (--i >= 0)
bus_unregister(idxd_bus_types[i]);
return rc;
}
return 0;
err_free:
+ mtk_hsdma_hw_deinit(hsdma);
of_dma_controller_free(pdev->dev.of_node);
err_unregister:
dma_async_device_unregister(dd);
ret = dma_async_device_register(ddev);
if (ret)
- return ret;
+ goto disable_xdmac;
ret = of_dma_controller_register(dev->of_node,
of_dma_simple_xlate, mdev);
unregister_dmac:
dma_async_device_unregister(ddev);
+disable_xdmac:
+ disable_xdmac(mdev);
return ret;
}
GFP_NOWAIT);
if (!async_desc)
- goto err_out;
+ return NULL;
if (flags & DMA_PREP_FENCE)
async_desc->flags |= DESC_FLAG_NWD;
}
return vchan_tx_prep(&bchan->vc, &async_desc->vd, flags);
-
-err_out:
- kfree(async_desc);
- return NULL;
}
/**
len = 1 << bit;
ring->alloc_size = (len + (len - 1));
dev_dbg(gpii->gpi_dev->dev,
- "#el:%u el_size:%u len:%u actual_len:%llu alloc_size:%lu\n",
+ "#el:%u el_size:%u len:%u actual_len:%llu alloc_size:%zu\n",
elements, el_size, (elements * el_size), len,
ring->alloc_size);
ring->alloc_size,
&ring->dma_handle, GFP_KERNEL);
if (!ring->pre_aligned) {
- dev_err(gpii->gpi_dev->dev, "could not alloc size:%lu mem for ring\n",
+ dev_err(gpii->gpi_dev->dev, "could not alloc size:%zu mem for ring\n",
ring->alloc_size);
return -ENOMEM;
}
smp_wmb();
dev_dbg(gpii->gpi_dev->dev,
- "phy_pre:0x%0llx phy_alig:0x%0llx len:%u el_size:%u elements:%u\n",
- ring->dma_handle, ring->phys_addr, ring->len,
+ "phy_pre:%pad phy_alig:%pa len:%u el_size:%u elements:%u\n",
+ &ring->dma_handle, &ring->phys_addr, ring->len,
ring->el_size, ring->elements);
return 0;
return ret;
error_start_chan:
- for (i = i - 1; i >= 0; i++) {
+ for (i = i - 1; i >= 0; i--) {
gpi_stop_chan(&gpii->gchan[i]);
gpi_send_cmd(gpii, gchan, GPI_CH_CMD_RESET);
}
#define STM32_MDMA_MAX_CHANNELS 63
#define STM32_MDMA_MAX_REQUESTS 256
#define STM32_MDMA_MAX_BURST 128
-#define STM32_MDMA_VERY_HIGH_PRIORITY 0x11
+#define STM32_MDMA_VERY_HIGH_PRIORITY 0x3
enum stm32_mdma_trigger_mode {
STM32_MDMA_BUFFER,
ud->tchan_tpl.levels = 1;
}
- ud->tchan_tpl.levels = ud->tchan_tpl.levels;
- ud->tchan_tpl.start_idx[0] = ud->tchan_tpl.start_idx[0];
- ud->tchan_tpl.start_idx[1] = ud->tchan_tpl.start_idx[1];
+ ud->rchan_tpl.levels = ud->tchan_tpl.levels;
+ ud->rchan_tpl.start_idx[0] = ud->tchan_tpl.start_idx[0];
+ ud->rchan_tpl.start_idx[1] = ud->tchan_tpl.start_idx[1];
ud->tchan_map = devm_kmalloc_array(dev, BITS_TO_LONGS(ud->tchan_cnt),
sizeof(unsigned long), GFP_KERNEL);
has_dre = false;
if (!has_dre)
- xdev->common.copy_align = fls(width - 1);
+ xdev->common.copy_align = (enum dmaengine_alignment)fls(width - 1);
if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel") ||
of_device_is_compatible(node, "xlnx,axi-dma-mm2s-channel") ||
static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
struct device_node *node)
{
- int ret, i, nr_channels = 1;
+ int ret, i;
+ u32 nr_channels = 1;
ret = of_property_read_u32(node, "dma-channels", &nr_channels);
if (xdev->dma_config->dmatype == XDMA_TYPE_AXIMCDMA && ret < 0)
}
/* Register the DMA engine with the core */
- dma_async_device_register(&xdev->common);
+ err = dma_async_device_register(&xdev->common);
+ if (err) {
+ dev_err(xdev->dev, "failed to register the dma device\n");
+ goto error;
+ }
err = of_dma_controller_register(node, of_dma_xilinx_xlate,
xdev);
union igp_info {
struct atom_integrated_system_info_v1_11 v11;
struct atom_integrated_system_info_v1_12 v12;
+ struct atom_integrated_system_info_v2_1 v21;
};
union umc_info {
if (adev->flags & AMD_IS_APU) {
igp_info = (union igp_info *)
(mode_info->atom_context->bios + data_offset);
- switch (crev) {
- case 11:
- mem_channel_number = igp_info->v11.umachannelnumber;
- /* channel width is 64 */
- if (vram_width)
- *vram_width = mem_channel_number * 64;
- mem_type = igp_info->v11.memorytype;
- if (vram_type)
- *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ switch (frev) {
+ case 1:
+ switch (crev) {
+ case 11:
+ case 12:
+ mem_channel_number = igp_info->v11.umachannelnumber;
+ if (!mem_channel_number)
+ mem_channel_number = 1;
+ /* channel width is 64 */
+ if (vram_width)
+ *vram_width = mem_channel_number * 64;
+ mem_type = igp_info->v11.memorytype;
+ if (vram_type)
+ *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ break;
+ default:
+ return -EINVAL;
+ }
break;
- case 12:
- mem_channel_number = igp_info->v12.umachannelnumber;
- /* channel width is 64 */
- if (vram_width)
- *vram_width = mem_channel_number * 64;
- mem_type = igp_info->v12.memorytype;
- if (vram_type)
- *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ case 2:
+ switch (crev) {
+ case 1:
+ case 2:
+ mem_channel_number = igp_info->v21.umachannelnumber;
+ if (!mem_channel_number)
+ mem_channel_number = 1;
+ /* channel width is 64 */
+ if (vram_width)
+ *vram_width = mem_channel_number * 64;
+ mem_type = igp_info->v21.memorytype;
+ if (vram_type)
+ *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ break;
+ default:
+ return -EINVAL;
+ }
break;
default:
return -EINVAL;
if (adev->gmc.xgmi.num_physical_nodes > 1)
amdgpu_xgmi_remove_device(adev);
- amdgpu_amdkfd_device_fini(adev);
-
amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
+ amdgpu_amdkfd_device_fini(adev);
+
/* need to disable SMC first */
for (i = 0; i < adev->num_ip_blocks; i++) {
if (!adev->ip_blocks[i].status.hw)
#endif
default:
if (amdgpu_dc > 0)
- DRM_INFO("Display Core has been requested via kernel parameter "
+ DRM_INFO_ONCE("Display Core has been requested via kernel parameter "
"but isn't supported by ASIC, ignoring\n");
return false;
}
/* Renoir */
{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+ {0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+ {0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
/* Navi12 */
{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12},
* add workaround to bypass it for sriov now.
* TODO: add version check to make it common
*/
- if (amdgpu_sriov_vf(psp->adev) || !psp->asd_fw)
+ if (amdgpu_sriov_vf(psp->adev) || !psp->asd_ucode_size)
return 0;
cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
if (amdgpu_sriov_vf(psp->adev))
return 0;
- if (!psp->hdcp_context.hdcp_initialized)
- return 0;
+ if (!psp->hdcp_context.hdcp_initialized) {
+ if (psp->hdcp_context.hdcp_shared_buf)
+ goto out;
+ else
+ return 0;
+ }
ret = psp_hdcp_unload(psp);
if (ret)
psp->hdcp_context.hdcp_initialized = false;
+out:
/* free hdcp shared memory */
amdgpu_bo_free_kernel(&psp->hdcp_context.hdcp_shared_bo,
&psp->hdcp_context.hdcp_shared_mc_addr,
if (amdgpu_sriov_vf(psp->adev))
return 0;
- if (!psp->dtm_context.dtm_initialized)
- return 0;
+ if (!psp->dtm_context.dtm_initialized) {
+ if (psp->dtm_context.dtm_shared_buf)
+ goto out;
+ else
+ return 0;
+ }
ret = psp_dtm_unload(psp);
if (ret)
psp->dtm_context.dtm_initialized = false;
+out:
/* free hdcp shared memory */
amdgpu_bo_free_kernel(&psp->dtm_context.dtm_shared_bo,
&psp->dtm_context.dtm_shared_mc_addr,
switch (desc->fw_type) {
case TA_FW_TYPE_PSP_ASD:
- psp->asd_fw_version = le32_to_cpu(desc->fw_version);
+ psp->asd_fw_version = le32_to_cpu(desc->fw_version);
psp->asd_feature_version = le32_to_cpu(desc->fw_version);
- psp->asd_ucode_size = le32_to_cpu(desc->size_bytes);
+ 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);
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
struct ras_err_handler_data *data;
int i = 0;
- int ret = 0;
+ int ret = 0, status;
if (!con || !con->eh_data || !bps || !count)
return -EINVAL;
.size = AMDGPU_GPU_PAGE_SIZE,
.flags = AMDGPU_RAS_RETIRE_PAGE_RESERVED,
};
- ret = amdgpu_vram_mgr_query_page_status(
+ status = amdgpu_vram_mgr_query_page_status(
ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM),
data->bps[i].retired_page);
- if (ret == -EBUSY)
+ if (status == -EBUSY)
(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_PENDING;
- else if (ret == -ENOENT)
+ else if (status == -ENOENT)
(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_FAULT;
}
#define EEPROM_I2C_TARGET_ADDR_VEGA20 0xA0
#define EEPROM_I2C_TARGET_ADDR_ARCTURUS 0xA8
#define EEPROM_I2C_TARGET_ADDR_ARCTURUS_D342 0xA0
+#define EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID 0xA0
/*
* The 2 macros bellow represent the actual size in bytes that
static bool __is_ras_eeprom_supported(struct amdgpu_device *adev)
{
if ((adev->asic_type == CHIP_VEGA20) ||
- (adev->asic_type == CHIP_ARCTURUS))
+ (adev->asic_type == CHIP_ARCTURUS) ||
+ (adev->asic_type == CHIP_SIENNA_CICHLID))
return true;
return false;
case CHIP_ARCTURUS:
return __get_eeprom_i2c_addr_arct(adev, i2c_addr);
+ case CHIP_SIENNA_CICHLID:
+ *i2c_addr = EEPROM_I2C_TARGET_ADDR_SIENNA_CICHLID;
+ break;
+
default:
return false;
}
#define mmGCR_GENERAL_CNTL_Sienna_Cichlid 0x1580
#define mmGCR_GENERAL_CNTL_Sienna_Cichlid_BASE_IDX 0
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh 0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh_BASE_IDX 1
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh 0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh_BASE_IDX 1
#define mmSPI_CONFIG_CNTL_1_Vangogh 0x2441
#define mmSPI_CONFIG_CNTL_1_Vangogh_BASE_IDX 1
#define mmVGT_TF_MEMORY_BASE_HI_Vangogh 0x2261
#define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid 0x15db
#define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid_BASE_IDX 0
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid 0x2030
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid_BASE_IDX 0
+
MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
MODULE_FIRMWARE("amdgpu/navi10_me.bin");
static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev);
static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev);
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev);
static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
{
if (adev->asic_type == CHIP_SIENNA_CICHLID)
gfx_v10_3_program_pbb_mode(adev);
+ if (adev->asic_type >= CHIP_SIENNA_CICHLID)
+ gfx_v10_3_set_power_brake_sequence(adev);
+
return r;
}
amdgpu_gfx_off_ctrl(adev, false);
mutex_lock(&adev->gfx.gpu_clock_mutex);
- clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
- ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+ switch (adev->asic_type) {
+ case CHIP_VANGOGH:
+ clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) |
+ ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
+ break;
+ default:
+ clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
+ ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+ break;
+ }
mutex_unlock(&adev->gfx.gpu_clock_mutex);
amdgpu_gfx_off_ctrl(adev, true);
return clock;
}
}
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev)
+{
+ WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX,
+ (0x1 << GRBM_GFX_INDEX__SA_BROADCAST_WRITES__SHIFT) |
+ (0x1 << GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES__SHIFT) |
+ (0x1 << GRBM_GFX_INDEX__SE_BROADCAST_WRITES__SHIFT));
+
+ WREG32_SOC15(GC, 0, mmGC_CAC_IND_INDEX, ixPWRBRK_STALL_PATTERN_CTRL);
+ WREG32_SOC15(GC, 0, mmGC_CAC_IND_DATA,
+ (0x1 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_STEP_INTERVAL__SHIFT) |
+ (0x12 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_BEGIN_STEP__SHIFT) |
+ (0x13 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_END_STEP__SHIFT) |
+ (0xf << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_THROTTLE_PATTERN_BIT_NUMS__SHIFT));
+
+ WREG32_SOC15(GC, 0, mmGC_THROTTLE_CTRL_Sienna_Cichlid,
+ (0x1 << GC_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT) |
+ (0x1 << GC_THROTTLE_CTRL__PATTERN_MODE__SHIFT) |
+ (0x5 << GC_THROTTLE_CTRL__RELEASE_STEP_INTERVAL__SHIFT));
+
+ WREG32_SOC15(GC, 0, mmDIDT_IND_INDEX, ixDIDT_SQ_THROTTLE_CTRL);
+
+ WREG32_SOC15(GC, 0, mmDIDT_IND_DATA,
+ (0x1 << DIDT_SQ_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT));
+}
+
const struct amdgpu_ip_block_version gfx_v10_0_ip_block =
{
.type = AMD_IP_BLOCK_TYPE_GFX,
/* Send no-retry XNACK on fault to suppress VM fault storm. */
tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
- !amdgpu_noretry);
+ !adev->gmc.noretry);
WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL,
i * hub->ctx_distance, tmp);
WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32,
GFX_CTRL_CMD_ID_DISABLE_INT = 0x00060000, /* disable PSP-to-Gfx interrupt */
GFX_CTRL_CMD_ID_MODE1_RST = 0x00070000, /* trigger the Mode 1 reset */
GFX_CTRL_CMD_ID_GBR_IH_SET = 0x00080000, /* set Gbr IH_RB_CNTL registers */
- GFX_CTRL_CMD_ID_CONSUME_CMD = 0x000A0000, /* send interrupt to psp for updating write pointer of vf */
+ GFX_CTRL_CMD_ID_CONSUME_CMD = 0x00090000, /* send interrupt to psp for updating write pointer of vf */
GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING = 0x000C0000, /* destroy GPCOM ring */
GFX_CTRL_CMD_ID_MAX = 0x000F0000, /* max command ID */
break;
case CHIP_RENOIR:
adev->asic_funcs = &soc15_asic_funcs;
- if (adev->pdev->device == 0x1636)
+ if ((adev->pdev->device == 0x1636) ||
+ (adev->pdev->device == 0x164c))
adev->apu_flags |= AMD_APU_IS_RENOIR;
else
adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
(struct crat_subtype_iolink *)sub_type_hdr);
if (ret < 0)
return ret;
- crat_table->length += (sub_type_hdr->length * entries);
- crat_table->total_entries += entries;
- sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
- sub_type_hdr->length * entries);
+ if (entries) {
+ crat_table->length += (sub_type_hdr->length * entries);
+ crat_table->total_entries += entries;
+
+ sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+ sub_type_hdr->length * entries);
+ }
#else
pr_info("IO link not available for non x86 platforms\n");
#endif
bool "AMD DC - Enable new display engine"
default y
select SND_HDA_COMPONENT if SND_HDA_CORE
- select DRM_AMD_DC_DCN if (X86 || PPC64 || (ARM64 && KERNEL_MODE_NEON)) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+ select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
help
Choose this option if you want to use the new display engine
support for AMDGPU. This adds required support for Vega and
}
#endif
-#ifdef CONFIG_DEBUG_FS
-static int create_crtc_crc_properties(struct amdgpu_display_manager *dm)
-{
- dm->crc_win_x_start_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_X_START", 0, U16_MAX);
- if (!dm->crc_win_x_start_property)
- return -ENOMEM;
-
- dm->crc_win_y_start_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_Y_START", 0, U16_MAX);
- if (!dm->crc_win_y_start_property)
- return -ENOMEM;
-
- dm->crc_win_x_end_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_X_END", 0, U16_MAX);
- if (!dm->crc_win_x_end_property)
- return -ENOMEM;
-
- dm->crc_win_y_end_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_Y_END", 0, U16_MAX);
- if (!dm->crc_win_y_end_property)
- return -ENOMEM;
-
- return 0;
-}
-#endif
-
static int amdgpu_dm_init(struct amdgpu_device *adev)
{
struct dc_init_data init_data;
dc_init_callbacks(adev->dm.dc, &init_params);
}
-#endif
-#ifdef CONFIG_DEBUG_FS
- if (create_crtc_crc_properties(&adev->dm))
- DRM_ERROR("amdgpu: failed to create crc property.\n");
#endif
if (amdgpu_dm_initialize_drm_device(adev)) {
DRM_ERROR(
drm_connector_update_edid_property(connector,
aconnector->edid);
- aconnector->num_modes = drm_add_edid_modes(connector, aconnector->edid);
- drm_connector_list_update(connector);
+ drm_add_edid_modes(connector, aconnector->edid);
if (aconnector->dc_link->aux_mode)
drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
state->crc_src = cur->crc_src;
state->cm_has_degamma = cur->cm_has_degamma;
state->cm_is_degamma_srgb = cur->cm_is_degamma_srgb;
-#ifdef CONFIG_DEBUG_FS
- state->crc_window = cur->crc_window;
-#endif
+
/* TODO Duplicate dc_stream after objects are stream object is flattened */
return &state->base;
}
-#ifdef CONFIG_DEBUG_FS
-static int amdgpu_dm_crtc_atomic_set_property(struct drm_crtc *crtc,
- struct drm_crtc_state *crtc_state,
- struct drm_property *property,
- uint64_t val)
-{
- struct drm_device *dev = crtc->dev;
- struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_crtc_state *dm_new_state =
- to_dm_crtc_state(crtc_state);
-
- if (property == adev->dm.crc_win_x_start_property)
- dm_new_state->crc_window.x_start = val;
- else if (property == adev->dm.crc_win_y_start_property)
- dm_new_state->crc_window.y_start = val;
- else if (property == adev->dm.crc_win_x_end_property)
- dm_new_state->crc_window.x_end = val;
- else if (property == adev->dm.crc_win_y_end_property)
- dm_new_state->crc_window.y_end = val;
- else
- return -EINVAL;
-
- return 0;
-}
-
-static int amdgpu_dm_crtc_atomic_get_property(struct drm_crtc *crtc,
- const struct drm_crtc_state *state,
- struct drm_property *property,
- uint64_t *val)
-{
- struct drm_device *dev = crtc->dev;
- struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_crtc_state *dm_state =
- to_dm_crtc_state(state);
-
- if (property == adev->dm.crc_win_x_start_property)
- *val = dm_state->crc_window.x_start;
- else if (property == adev->dm.crc_win_y_start_property)
- *val = dm_state->crc_window.y_start;
- else if (property == adev->dm.crc_win_x_end_property)
- *val = dm_state->crc_window.x_end;
- else if (property == adev->dm.crc_win_y_end_property)
- *val = dm_state->crc_window.y_end;
- else
- return -EINVAL;
-
- return 0;
-}
-#endif
-
static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
{
enum dc_irq_source irq_source;
.enable_vblank = dm_enable_vblank,
.disable_vblank = dm_disable_vblank,
.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
-#ifdef CONFIG_DEBUG_FS
- .atomic_set_property = amdgpu_dm_crtc_atomic_set_property,
- .atomic_get_property = amdgpu_dm_crtc_atomic_get_property,
-#endif
};
static enum drm_connector_status
return 0;
}
-#ifdef CONFIG_DEBUG_FS
-static void attach_crtc_crc_properties(struct amdgpu_display_manager *dm,
- struct amdgpu_crtc *acrtc)
-{
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_x_start_property,
- 0);
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_y_start_property,
- 0);
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_x_end_property,
- 0);
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_y_end_property,
- 0);
-}
-#endif
-
static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
struct drm_plane *plane,
uint32_t crtc_index)
drm_crtc_enable_color_mgmt(&acrtc->base, MAX_COLOR_LUT_ENTRIES,
true, MAX_COLOR_LUT_ENTRIES);
drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
-#ifdef CONFIG_DEBUG_FS
- attach_crtc_crc_properties(dm, acrtc);
-#endif
+
return 0;
fail:
*/
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
- bool configure_crc = false;
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
dc_stream_retain(dm_new_crtc_state->stream);
acrtc->dm_irq_params.stream = dm_new_crtc_state->stream;
manage_dm_interrupts(adev, acrtc, true);
- }
+
#ifdef CONFIG_DEBUG_FS
- if (new_crtc_state->active &&
- amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
/**
* Frontend may have changed so reapply the CRC capture
* settings for the stream.
*/
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
- dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
-
- if (amdgpu_dm_crc_window_is_default(dm_new_crtc_state)) {
- if (!old_crtc_state->active || drm_atomic_crtc_needs_modeset(new_crtc_state))
- configure_crc = true;
- } else {
- if (amdgpu_dm_crc_window_changed(dm_new_crtc_state, dm_old_crtc_state))
- configure_crc = true;
- }
- if (configure_crc)
+ if (amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
amdgpu_dm_crtc_configure_crc_source(
- crtc, dm_new_crtc_state, dm_new_crtc_state->crc_src);
- }
+ crtc, dm_new_crtc_state,
+ dm_new_crtc_state->crc_src);
+ }
#endif
+ }
}
for_each_new_crtc_in_state(state, crtc, new_crtc_state, j)
*/
const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#ifdef CONFIG_DEBUG_FS
- /**
- * @crc_win_x_start_property:
- *
- * X start of the crc calculation window
- */
- struct drm_property *crc_win_x_start_property;
- /**
- * @crc_win_y_start_property:
- *
- * Y start of the crc calculation window
- */
- struct drm_property *crc_win_y_start_property;
- /**
- * @crc_win_x_end_property:
- *
- * X end of the crc calculation window
- */
- struct drm_property *crc_win_x_end_property;
- /**
- * @crc_win_y_end_property:
- *
- * Y end of the crc calculation window
- */
- struct drm_property *crc_win_y_end_property;
-#endif
/**
* @mst_encoders:
*
struct dc_plane_state *dc_state;
};
-#ifdef CONFIG_DEBUG_FS
-struct crc_rec {
- uint16_t x_start;
- uint16_t y_start;
- uint16_t x_end;
- uint16_t y_end;
- };
-#endif
-
struct dm_crtc_state {
struct drm_crtc_state base;
struct dc_stream_state *stream;
struct dc_info_packet vrr_infopacket;
int abm_level;
-#ifdef CONFIG_DEBUG_FS
- struct crc_rec crc_window;
-#endif
};
#define to_dm_crtc_state(x) container_of(x, struct dm_crtc_state, base)
return pipe_crc_sources;
}
-static void amdgpu_dm_set_crc_window_default(struct dm_crtc_state *dm_crtc_state)
-{
- dm_crtc_state->crc_window.x_start = 0;
- dm_crtc_state->crc_window.y_start = 0;
- dm_crtc_state->crc_window.x_end = 0;
- dm_crtc_state->crc_window.y_end = 0;
-}
-
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state)
-{
- bool ret = true;
-
- if ((dm_crtc_state->crc_window.x_start != 0) ||
- (dm_crtc_state->crc_window.y_start != 0) ||
- (dm_crtc_state->crc_window.x_end != 0) ||
- (dm_crtc_state->crc_window.y_end != 0))
- ret = false;
-
- return ret;
-}
-
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
- struct dm_crtc_state *dm_old_crtc_state)
-{
- bool ret = false;
-
- if ((dm_new_crtc_state->crc_window.x_start != dm_old_crtc_state->crc_window.x_start) ||
- (dm_new_crtc_state->crc_window.y_start != dm_old_crtc_state->crc_window.y_start) ||
- (dm_new_crtc_state->crc_window.x_end != dm_old_crtc_state->crc_window.x_end) ||
- (dm_new_crtc_state->crc_window.y_end != dm_old_crtc_state->crc_window.y_end))
- ret = true;
-
- return ret;
-}
-
int
amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc, const char *src_name,
size_t *values_cnt)
struct dc_stream_state *stream_state = dm_crtc_state->stream;
bool enable = amdgpu_dm_is_valid_crc_source(source);
int ret = 0;
- struct crc_params *crc_window = NULL, tmp_window;
/* Configuration will be deferred to stream enable. */
if (!stream_state)
/* Enable CRTC CRC generation if necessary. */
if (dm_is_crc_source_crtc(source) || source == AMDGPU_DM_PIPE_CRC_SOURCE_NONE) {
- if (!enable)
- amdgpu_dm_set_crc_window_default(dm_crtc_state);
-
- if (!amdgpu_dm_crc_window_is_default(dm_crtc_state)) {
- crc_window = &tmp_window;
-
- tmp_window.windowa_x_start = dm_crtc_state->crc_window.x_start;
- tmp_window.windowa_y_start = dm_crtc_state->crc_window.y_start;
- tmp_window.windowa_x_end = dm_crtc_state->crc_window.x_end;
- tmp_window.windowa_y_end = dm_crtc_state->crc_window.y_end;
- tmp_window.windowb_x_start = dm_crtc_state->crc_window.x_start;
- tmp_window.windowb_y_start = dm_crtc_state->crc_window.y_start;
- tmp_window.windowb_x_end = dm_crtc_state->crc_window.x_end;
- tmp_window.windowb_y_end = dm_crtc_state->crc_window.y_end;
- }
-
if (!dc_stream_configure_crc(stream_state->ctx->dc,
- stream_state, crc_window, enable, enable)) {
+ stream_state, NULL, enable, enable)) {
ret = -EINVAL;
goto unlock;
}
/* amdgpu_dm_crc.c */
#ifdef CONFIG_DEBUG_FS
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state);
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
- struct dm_crtc_state *dm_old_crtc_state);
int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
struct dm_crtc_state *dm_crtc_state,
enum amdgpu_dm_pipe_crc_source source);
calcs_ccflags := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-calcs_rcflags := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
endif
-# prevent build errors:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# this file is unused on arm64, just like on ppc64
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn21/rn_clk_mgr.o := -mgeneral-regs-only
-endif
-
AMD_DAL_CLK_MGR_DCN21 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn21/,$(CLK_MGR_DCN21))
AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN21)
CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn30/dcn30_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
endif
-# prevent build errors:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# this file is unused on arm64, just like on ppc64
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn30/dcn30_clk_mgr.o := -mgeneral-regs-only
-endif
-
AMD_DAL_CLK_MGR_DCN30 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn30/,$(CLK_MGR_DCN30))
AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN30)
CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn301/vg_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
endif
-# prevent build errors:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# this file is unused on arm64, just like on ppc64
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/clk_mgr/dcn301/vg_clk_mgr.o := -mgeneral-regs-only
-endif
-
AMD_DAL_CLK_MGR_DCN301 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn301/,$(CLK_MGR_DCN301))
AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN301)
static struct abm *get_abm_from_stream_res(const struct dc_link *link)
{
int i;
- struct dc *dc = link->ctx->dc;
+ struct dc *dc = NULL;
struct abm *abm = NULL;
+ if (!link || !link->ctx)
+ return NULL;
+
+ dc = link->ctx->dc;
+
for (i = 0; i < MAX_PIPES; i++) {
struct pipe_ctx pipe_ctx = dc->current_state->res_ctx.pipe_ctx[i];
struct dc_stream_state *stream = pipe_ctx.stream;
unsigned int cust_pattern_size)
{
struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
- struct pipe_ctx *pipe_ctx = &pipes[0];
+ struct pipe_ctx *pipe_ctx = NULL;
unsigned int lane;
unsigned int i;
unsigned char link_qual_pattern[LANE_COUNT_DP_MAX] = {0};
memset(&training_pattern, 0, sizeof(training_pattern));
for (i = 0; i < MAX_PIPES; i++) {
+ if (pipes[i].stream == NULL)
+ continue;
+
if (pipes[i].stream->link == link && !pipes[i].top_pipe && !pipes[i].prev_odm_pipe) {
pipe_ctx = &pipes[i];
break;
}
}
+ if (pipe_ctx == NULL)
+ return false;
+
/* Reset CRTC Test Pattern if it is currently running and request is VideoMode */
if (link->test_pattern_enabled && test_pattern ==
DP_TEST_PATTERN_VIDEO_MODE) {
AMD_DAL_DCN10 = $(addprefix $(AMDDALPATH)/dc/dcn10/,$(DCN10))
-# fix:
-# ...: '-mgeneral-regs-only' is incompatible with the use of floating-point types
-# aarch64 does not support soft-float, so use hard-float and handle this in code
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn10/dcn10_resource.o := -mgeneral-regs-only
-endif
-
AMD_DISPLAY_FILES += $(AMD_DAL_DCN10)
unsigned int mpc1_get_mpc_out_mux(struct mpc *mpc, int opp_id)
{
struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
- uint32_t val = 0;
+ uint32_t val = 0xf;
if (opp_id < MAX_OPP && REG(MUX[opp_id]))
REG_GET(MUX[opp_id], MPC_OUT_MUX, &val);
.disable_pplib_clock_request = false,
.disable_pplib_wm_range = false,
.pplib_wm_report_mode = WM_REPORT_DEFAULT,
- .pipe_split_policy = MPC_SPLIT_DYNAMIC,
- .force_single_disp_pipe_split = true,
+ .pipe_split_policy = MPC_SPLIT_AVOID,
+ .force_single_disp_pipe_split = false,
.disable_dcc = DCC_ENABLE,
.voltage_align_fclk = true,
.disable_stereo_support = true,
memcpy(dc->dcn_ip, &dcn10_ip_defaults, sizeof(dcn10_ip_defaults));
memcpy(dc->dcn_soc, &dcn10_soc_defaults, sizeof(dcn10_soc_defaults));
-#if defined(CONFIG_ARM64)
- /* Aarch64 does not support -msoft-float/-mfloat-abi=soft */
- DC_FP_START();
- dcn10_resource_construct_fp(dc);
- DC_FP_END();
-#else
/* Other architectures we build for build this with soft-float */
dcn10_resource_construct_fp(dc);
-#endif
pool->base.pp_smu = dcn10_pp_smu_create(ctx);
CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mgeneral-regs-only
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
.add_stream_to_ctx = dcn30_add_stream_to_ctx,
+ .add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource,
.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
.populate_dml_writeback_from_context = dcn30_populate_dml_writeback_from_context,
.set_mcif_arb_params = dcn30_set_mcif_arb_params,
CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
dml_ccflags := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-dml_rcflags := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
}
if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
- mode_lib->vba.MinActiveDRAMClockChangeMargin > 60 &&
- mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+ mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
mode_lib->vba.DRAMClockChangeWatermark += 25;
for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
- if (mode_lib->vba.DRAMClockChangeWatermark >
- dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
- mode_lib->vba.MinTTUVBlank[k] += 25;
+ if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+ if (mode_lib->vba.DRAMClockChangeWatermark >
+ dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
+ mode_lib->vba.MinTTUVBlank[k] += 25;
+ }
}
mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
dsc_ccflags := -mhard-float -maltivec
endif
-ifdef CONFIG_ARM64
-dsc_rcflags := -mgeneral-regs-only
-endif
-
ifdef CONFIG_CC_IS_GCC
ifeq ($(call cc-ifversion, -lt, 0701, y), y)
IS_OLD_GCC = 1
#include <asm/fpu/api.h>
#define DC_FP_START() kernel_fpu_begin()
#define DC_FP_END() kernel_fpu_end()
-#elif defined(CONFIG_ARM64)
-#include <asm/neon.h>
-#define DC_FP_START() kernel_neon_begin()
-#define DC_FP_END() kernel_neon_end()
#elif defined(CONFIG_PPC64)
#include <asm/switch_to.h>
#include <asm/cputable.h>
smu10_data->gfx_actual_soft_min_freq = clock;
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinGfxClk,
- smu10_data->gfx_actual_soft_min_freq,
+ clock,
NULL);
}
return 0;
/* enable the pp_od_clk_voltage sysfs file */
hwmgr->od_enabled = 1;
-
+ /* disabled fine grain tuning function by default */
+ data->fine_grain_enabled = 0;
return result;
}
uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100;
uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1;
uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1;
+ uint32_t fine_grain_min_freq = 0, fine_grain_max_freq = 0;
if (hwmgr->smu_version < 0x1E3700) {
pr_info("smu firmware version too old, can not set dpm level\n");
switch (level) {
case AMD_DPM_FORCED_LEVEL_HIGH:
case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+ data->fine_grain_enabled = 0;
+
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+ data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+ data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinGfxClk,
data->gfx_max_freq_limit/100,
NULL);
break;
case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+ data->fine_grain_enabled = 0;
+
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+ data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+ data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinGfxClk,
min_sclk,
NULL);
break;
case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+ data->fine_grain_enabled = 0;
+
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+ data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+ data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinFclkByFreq,
min_mclk,
NULL);
break;
case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+ data->fine_grain_enabled = 0;
+
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+ data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+ data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinGfxClk,
SMU10_UMD_PSTATE_GFXCLK,
NULL);
break;
case AMD_DPM_FORCED_LEVEL_AUTO:
+ data->fine_grain_enabled = 0;
+
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+ data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+ data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinGfxClk,
min_sclk,
NULL);
break;
case AMD_DPM_FORCED_LEVEL_LOW:
+ data->fine_grain_enabled = 0;
+
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &fine_grain_min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &fine_grain_max_freq);
+
+ data->gfx_actual_soft_min_freq = fine_grain_min_freq;
+ data->gfx_actual_soft_max_freq = fine_grain_max_freq;
+
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinGfxClk,
data->gfx_min_freq_limit/100,
NULL);
break;
case AMD_DPM_FORCED_LEVEL_MANUAL:
+ data->fine_grain_enabled = 1;
case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
default:
break;
struct smu10_voltage_dependency_table *mclk_table =
data->clock_vol_info.vdd_dep_on_fclk;
uint32_t i, now, size = 0;
+ uint32_t min_freq, max_freq = 0;
+ uint32_t ret = 0;
switch (type) {
case PP_SCLK:
break;
case OD_SCLK:
if (hwmgr->od_enabled) {
- size = sprintf(buf, "%s:\n", "OD_SCLK");
+ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+ if (ret)
+ return ret;
+ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+ if (ret)
+ return ret;
+ size = sprintf(buf, "%s:\n", "OD_SCLK");
size += sprintf(buf + size, "0: %10uMhz\n",
- (data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : data->gfx_min_freq_limit/100);
- size += sprintf(buf + size, "1: %10uMhz\n", data->gfx_max_freq_limit/100);
+ (data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq);
+ size += sprintf(buf + size, "1: %10uMhz\n",
+ (data->gfx_actual_soft_max_freq > 0) ? data->gfx_actual_soft_max_freq : max_freq);
}
break;
case OD_RANGE:
if (hwmgr->od_enabled) {
- uint32_t min_freq, max_freq = 0;
- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+ if (ret)
+ return ret;
+ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+ if (ret)
+ return ret;
size = sprintf(buf, "%s:\n", "OD_RANGE");
size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
enum PP_OD_DPM_TABLE_COMMAND type,
long *input, uint32_t size)
{
+ uint32_t min_freq, max_freq = 0;
+ struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+ int ret = 0;
+
if (!hwmgr->od_enabled) {
pr_err("Fine grain not support\n");
return -EINVAL;
}
- if (size != 2) {
- pr_err("Input parameter number not correct\n");
+ if (!smu10_data->fine_grain_enabled) {
+ pr_err("Fine grain not started\n");
return -EINVAL;
}
if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
- if (input[0] == 0)
- smu10_set_hard_min_gfxclk_by_freq(hwmgr, input[1]);
- else if (input[0] == 1)
- smu10_set_soft_max_gfxclk_by_freq(hwmgr, input[1]);
- else
+ if (size != 2) {
+ pr_err("Input parameter number not correct\n");
return -EINVAL;
+ }
+
+ if (input[0] == 0) {
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+ if (input[1] < min_freq) {
+ pr_err("Fine grain setting minimum sclk (%ld) MHz is less than the minimum allowed (%d) MHz\n",
+ input[1], min_freq);
+ return -EINVAL;
+ }
+ smu10_data->gfx_actual_soft_min_freq = input[1];
+ } else if (input[0] == 1) {
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+ if (input[1] > max_freq) {
+ pr_err("Fine grain setting maximum sclk (%ld) MHz is greater than the maximum allowed (%d) MHz\n",
+ input[1], max_freq);
+ return -EINVAL;
+ }
+ smu10_data->gfx_actual_soft_max_freq = input[1];
+ } else {
+ return -EINVAL;
+ }
+ } else if (type == PP_OD_RESTORE_DEFAULT_TABLE) {
+ if (size != 0) {
+ pr_err("Input parameter number not correct\n");
+ return -EINVAL;
+ }
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+ smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+
+ smu10_data->gfx_actual_soft_min_freq = min_freq;
+ smu10_data->gfx_actual_soft_max_freq = max_freq;
+
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_SetHardMinGfxClk,
+ min_freq,
+ NULL);
+ if (ret)
+ return ret;
+
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_SetSoftMaxGfxClk,
+ max_freq,
+ NULL);
+ if (ret)
+ return ret;
+ } else if (type == PP_OD_COMMIT_DPM_TABLE) {
+ if (size != 0) {
+ pr_err("Input parameter number not correct\n");
+ return -EINVAL;
+ }
+
+ if (smu10_data->gfx_actual_soft_min_freq > smu10_data->gfx_actual_soft_max_freq) {
+ pr_err("The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+ smu10_data->gfx_actual_soft_min_freq, smu10_data->gfx_actual_soft_max_freq);
+ return -EINVAL;
+ }
+
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_SetHardMinGfxClk,
+ smu10_data->gfx_actual_soft_min_freq,
+ NULL);
+ if (ret)
+ return ret;
+
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_SetSoftMaxGfxClk,
+ smu10_data->gfx_actual_soft_max_freq,
+ NULL);
+ if (ret)
+ return ret;
+ } else {
+ return -EINVAL;
}
return 0;
uint32_t vclk_soft_min;
uint32_t dclk_soft_min;
uint32_t gfx_actual_soft_min_freq;
+ uint32_t gfx_actual_soft_max_freq;
uint32_t gfx_min_freq_limit;
uint32_t gfx_max_freq_limit; /* in 10Khz*/
bool need_min_deep_sleep_dcefclk;
uint32_t deep_sleep_dcefclk;
uint32_t num_active_display;
+
+ bool fine_grain_enabled;
};
struct pp_hwmgr;
{
int i;
- req->I2CcontrollerPort = 0;
+ req->I2CcontrollerPort = 1;
req->I2CSpeed = 2;
req->SlaveAddress = address;
req->NumCmds = numbytes;
*value = metrics->UvdActivity;
break;
case METRICS_AVERAGE_SOCKETPOWER:
- *value = metrics->CurrentSocketPower;
+ *value = (metrics->CurrentSocketPower << 8) /
+ 1000 ;
break;
case METRICS_TEMPERATURE_EDGE:
*value = metrics->GfxTemperature / 100 *
return -EINVAL;
*freq = clk_table->SocClocks[dpm_level].Freq;
break;
+ case SMU_UCLK:
case SMU_MCLK:
if (dpm_level >= NUM_FCLK_DPM_LEVELS)
return -EINVAL;
break;
case SMU_FCLK:
case SMU_MCLK:
+ case SMU_UCLK:
ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinFclkByFreq, min, NULL);
if (ret)
return ret;
if (ret)
goto out;
- if (old_fb->format != fb->format) {
+ /*
+ * Only check the FOURCC format code, excluding modifiers. This is
+ * enough for all legacy drivers. Atomic drivers have their own
+ * checks in their ->atomic_check implementation, which will
+ * return -EINVAL if any hw or driver constraint is violated due
+ * to modifier changes.
+ */
+ if (old_fb->format->format != fb->format->format) {
DRM_DEBUG_KMS("Page flip is not allowed to change frame buffer format.\n");
ret = -EINVAL;
goto out;
i915_config.o \
i915_irq.o \
i915_getparam.o \
+ i915_mitigations.o \
i915_params.o \
i915_pci.o \
i915_scatterlist.o \
get_dsi_io_power_domains(i915,
enc_to_intel_dsi(encoder));
-
- if (crtc_state->dsc.compression_enable)
- intel_display_power_get(i915,
- intel_dsc_power_domain(crtc_state));
}
static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
bool ycbcr_444_to_420;
} dfp;
+ /* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
+ struct pm_qos_request pm_qos;
+
/* Display stream compression testing */
bool force_dsc_en;
* lowest possible wakeup latency and so prevent the cpu from going into
* deep sleep states.
*/
- cpu_latency_qos_update_request(&i915->pm_qos, 0);
+ cpu_latency_qos_update_request(&intel_dp->pm_qos, 0);
intel_dp_check_edp(intel_dp);
ret = recv_bytes;
out:
- cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE);
+ cpu_latency_qos_update_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE);
if (vdd)
edp_panel_vdd_off(intel_dp, false);
static void
intel_dp_aux_fini(struct intel_dp *intel_dp)
{
+ if (cpu_latency_qos_request_active(&intel_dp->pm_qos))
+ cpu_latency_qos_remove_request(&intel_dp->pm_qos);
+
kfree(intel_dp->aux.name);
}
encoder->base.name);
intel_dp->aux.transfer = intel_dp_aux_transfer;
+ cpu_latency_qos_add_request(&intel_dp->pm_qos, PM_QOS_DEFAULT_VALUE);
}
bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp)
val = pch_get_backlight(connector);
else
val = lpt_get_backlight(connector);
- val = intel_panel_compute_brightness(connector, val);
- panel->backlight.level = clamp(val, panel->backlight.min,
- panel->backlight.max);
if (cpu_mode) {
drm_dbg_kms(&dev_priv->drm,
"CPU backlight register was enabled, switching to PCH override\n");
/* Write converted CPU PWM value to PCH override register */
- lpt_set_backlight(connector->base.state, panel->backlight.level);
+ lpt_set_backlight(connector->base.state, val);
intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
cpu_ctl2 & ~BLM_PWM_ENABLE);
}
+ val = intel_panel_compute_brightness(connector, val);
+ panel->backlight.level = clamp(val, panel->backlight.min,
+ panel->backlight.max);
+
return 0;
}
intel_dsi_prepare(encoder, pipe_config);
intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
- intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
- /* Deassert reset */
- intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+ /*
+ * Give the panel time to power-on and then deassert its reset.
+ * Depending on the VBT MIPI sequences version the deassert-seq
+ * may contain the necessary delay, intel_dsi_msleep() will skip
+ * the delay in that case. If there is no deassert-seq, then an
+ * unconditional msleep is used to give the panel time to power-on.
+ */
+ if (dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) {
+ intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+ } else {
+ msleep(intel_dsi->panel_on_delay);
+ }
if (IS_GEMINILAKE(dev_priv)) {
glk_cold_boot = glk_dsi_enable_io(encoder);
GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;
- __i915_gem_object_flush_map(obj, 0, sizeof(u32) * (cache->rq_size + 1));
+ i915_gem_object_flush_map(obj);
i915_gem_object_unpin_map(obj);
intel_gt_chipset_flush(cache->rq->engine->gt);
goto err_pool;
}
+ memset32(cmd, 0, pool->obj->base.size / sizeof(u32));
+
batch = i915_vma_instance(pool->obj, vma->vm, NULL);
if (IS_ERR(batch)) {
err = PTR_ERR(batch);
#include "i915_drv.h"
#include "intel_gpu_commands.h"
-#define MAX_URB_ENTRIES 64
-#define STATE_SIZE (4 * 1024)
#define GT3_INLINE_DATA_DELAYS 0x1E00
#define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS))
};
struct batch_vals {
- u32 max_primitives;
- u32 max_urb_entries;
- u32 cmd_size;
- u32 state_size;
+ u32 max_threads;
u32 state_start;
- u32 batch_size;
+ u32 surface_start;
u32 surface_height;
u32 surface_width;
- u32 scratch_size;
- u32 max_size;
+ u32 size;
};
+static inline int num_primitives(const struct batch_vals *bv)
+{
+ /*
+ * We need to saturate the GPU with work in order to dispatch
+ * a shader on every HW thread, and clear the thread-local registers.
+ * In short, we have to dispatch work faster than the shaders can
+ * run in order to fill the EU and occupy each HW thread.
+ */
+ return bv->max_threads;
+}
+
static void
batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv)
{
if (IS_HASWELL(i915)) {
- bv->max_primitives = 280;
- bv->max_urb_entries = MAX_URB_ENTRIES;
+ switch (INTEL_INFO(i915)->gt) {
+ default:
+ case 1:
+ bv->max_threads = 70;
+ break;
+ case 2:
+ bv->max_threads = 140;
+ break;
+ case 3:
+ bv->max_threads = 280;
+ break;
+ }
bv->surface_height = 16 * 16;
bv->surface_width = 32 * 2 * 16;
} else {
- bv->max_primitives = 128;
- bv->max_urb_entries = MAX_URB_ENTRIES / 2;
+ switch (INTEL_INFO(i915)->gt) {
+ default:
+ case 1: /* including vlv */
+ bv->max_threads = 36;
+ break;
+ case 2:
+ bv->max_threads = 128;
+ break;
+ }
bv->surface_height = 16 * 8;
bv->surface_width = 32 * 16;
}
- bv->cmd_size = bv->max_primitives * 4096;
- bv->state_size = STATE_SIZE;
- bv->state_start = bv->cmd_size;
- bv->batch_size = bv->cmd_size + bv->state_size;
- bv->scratch_size = bv->surface_height * bv->surface_width;
- bv->max_size = bv->batch_size + bv->scratch_size;
+ bv->state_start = round_up(SZ_1K + num_primitives(bv) * 64, SZ_4K);
+ bv->surface_start = bv->state_start + SZ_4K;
+ bv->size = bv->surface_start + bv->surface_height * bv->surface_width;
}
static void batch_init(struct batch_chunk *bc,
gen7_fill_binding_table(struct batch_chunk *state,
const struct batch_vals *bv)
{
- u32 surface_start = gen7_fill_surface_state(state, bv->batch_size, bv);
+ u32 surface_start =
+ gen7_fill_surface_state(state, bv->surface_start, bv);
u32 *cs = batch_alloc_items(state, 32, 8);
u32 offset = batch_offset(state, cs);
gen7_emit_state_base_address(struct batch_chunk *batch,
u32 surface_state_base)
{
- u32 *cs = batch_alloc_items(batch, 0, 12);
+ u32 *cs = batch_alloc_items(batch, 0, 10);
- *cs++ = STATE_BASE_ADDRESS | (12 - 2);
+ *cs++ = STATE_BASE_ADDRESS | (10 - 2);
/* general */
*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
/* surface */
*cs++ = BASE_ADDRESS_MODIFY;
*cs++ = 0;
*cs++ = BASE_ADDRESS_MODIFY;
- *cs++ = 0;
- *cs++ = 0;
batch_advance(batch, cs);
}
u32 urb_size, u32 curbe_size,
u32 mode)
{
- u32 urb_entries = bv->max_urb_entries;
- u32 threads = bv->max_primitives - 1;
+ u32 threads = bv->max_threads - 1;
u32 *cs = batch_alloc_items(batch, 32, 8);
*cs++ = MEDIA_VFE_STATE | (8 - 2);
*cs++ = 0;
/* number of threads & urb entries for GPGPU vs Media Mode */
- *cs++ = threads << 16 | urb_entries << 8 | mode << 2;
+ *cs++ = threads << 16 | 1 << 8 | mode << 2;
*cs++ = 0;
{
unsigned int x_offset = (media_object_index % 16) * 64;
unsigned int y_offset = (media_object_index / 16) * 16;
- unsigned int inline_data_size;
- unsigned int media_batch_size;
- unsigned int i;
+ unsigned int pkt = 6 + 3;
u32 *cs;
- inline_data_size = 112 * 8;
- media_batch_size = inline_data_size + 6;
-
- cs = batch_alloc_items(batch, 8, media_batch_size);
+ cs = batch_alloc_items(batch, 8, pkt);
- *cs++ = MEDIA_OBJECT | (media_batch_size - 2);
+ *cs++ = MEDIA_OBJECT | (pkt - 2);
/* interface descriptor offset */
*cs++ = 0;
*cs++ = 0;
/* inline */
- *cs++ = (y_offset << 16) | (x_offset);
+ *cs++ = y_offset << 16 | x_offset;
*cs++ = 0;
*cs++ = GT3_INLINE_DATA_DELAYS;
- for (i = 3; i < inline_data_size; i++)
- *cs++ = 0;
batch_advance(batch, cs);
}
static void gen7_emit_pipeline_flush(struct batch_chunk *batch)
{
- u32 *cs = batch_alloc_items(batch, 0, 5);
+ u32 *cs = batch_alloc_items(batch, 0, 4);
- *cs++ = GFX_OP_PIPE_CONTROL(5);
- *cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE |
- PIPE_CONTROL_GLOBAL_GTT_IVB;
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+ PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+ PIPE_CONTROL_DC_FLUSH_ENABLE |
+ PIPE_CONTROL_CS_STALL;
*cs++ = 0;
*cs++ = 0;
+
+ batch_advance(batch, cs);
+}
+
+static void gen7_emit_pipeline_invalidate(struct batch_chunk *batch)
+{
+ u32 *cs = batch_alloc_items(batch, 0, 8);
+
+ /* ivb: Stall before STATE_CACHE_INVALIDATE */
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_STALL_AT_SCOREBOARD |
+ PIPE_CONTROL_CS_STALL;
+ *cs++ = 0;
+ *cs++ = 0;
+
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE;
*cs++ = 0;
+ *cs++ = 0;
+
batch_advance(batch, cs);
}
const struct batch_vals *bv)
{
struct drm_i915_private *i915 = vma->vm->i915;
- unsigned int desc_count = 64;
- const u32 urb_size = 112;
+ const unsigned int desc_count = 1;
+ const unsigned int urb_size = 1;
struct batch_chunk cmds, state;
- u32 interface_descriptor;
+ u32 descriptors;
unsigned int i;
- batch_init(&cmds, vma, start, 0, bv->cmd_size);
- batch_init(&state, vma, start, bv->state_start, bv->state_size);
+ batch_init(&cmds, vma, start, 0, bv->state_start);
+ batch_init(&state, vma, start, bv->state_start, SZ_4K);
- interface_descriptor =
- gen7_fill_interface_descriptor(&state, bv,
- IS_HASWELL(i915) ?
- &cb_kernel_hsw :
- &cb_kernel_ivb,
- desc_count);
- gen7_emit_pipeline_flush(&cmds);
+ descriptors = gen7_fill_interface_descriptor(&state, bv,
+ IS_HASWELL(i915) ?
+ &cb_kernel_hsw :
+ &cb_kernel_ivb,
+ desc_count);
+
+ gen7_emit_pipeline_invalidate(&cmds);
batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
batch_add(&cmds, MI_NOOP);
- gen7_emit_state_base_address(&cmds, interface_descriptor);
+ gen7_emit_pipeline_invalidate(&cmds);
+
gen7_emit_pipeline_flush(&cmds);
+ gen7_emit_state_base_address(&cmds, descriptors);
+ gen7_emit_pipeline_invalidate(&cmds);
gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
+ gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count);
- gen7_emit_interface_descriptor_load(&cmds,
- interface_descriptor,
- desc_count);
-
- for (i = 0; i < bv->max_primitives; i++)
+ for (i = 0; i < num_primitives(bv); i++)
gen7_emit_media_object(&cmds, i);
batch_add(&cmds, MI_BATCH_BUFFER_END);
batch_get_defaults(engine->i915, &bv);
if (!vma)
- return bv.max_size;
+ return bv.size;
- GEM_BUG_ON(vma->obj->base.size < bv.max_size);
+ GEM_BUG_ON(vma->obj->base.size < bv.size);
batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
if (IS_ERR(batch))
return PTR_ERR(batch);
- emit_batch(vma, memset(batch, 0, bv.max_size), &bv);
+ emit_batch(vma, memset(batch, 0, bv.size), &bv);
i915_gem_object_flush_map(vma->obj);
__i915_gem_object_release_map(vma->obj);
#include "gen6_ppgtt.h"
#include "gen7_renderclear.h"
#include "i915_drv.h"
+#include "i915_mitigations.h"
#include "intel_breadcrumbs.h"
#include "intel_context.h"
#include "intel_gt.h"
GEM_BUG_ON(HAS_EXECLISTS(engine->i915));
if (engine->wa_ctx.vma && ce != engine->kernel_context) {
- if (engine->wa_ctx.vma->private != ce) {
+ if (engine->wa_ctx.vma->private != ce &&
+ i915_mitigate_clear_residuals()) {
ret = clear_residuals(rq);
if (ret)
return ret;
GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma);
- if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) {
+ if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) {
err = gen7_ctx_switch_bb_init(engine);
if (err)
goto err_ring_unpin;
fw_def(ELKHARTLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl, 9, 0, 0)) \
fw_def(ICELAKE, 0, guc_def(icl, 49, 0, 1), huc_def(icl, 9, 0, 0)) \
fw_def(COMETLAKE, 5, guc_def(cml, 49, 0, 1), huc_def(cml, 4, 0, 0)) \
+ fw_def(COMETLAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \
fw_def(COFFEELAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \
fw_def(GEMINILAKE, 0, guc_def(glk, 49, 0, 1), huc_def(glk, 4, 0, 0)) \
fw_def(KABYLAKE, 0, guc_def(kbl, 49, 0, 1), huc_def(kbl, 4, 0, 0)) \
DDI_BUF_CTL_ENABLE);
vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) |= DDI_BUF_IS_IDLE;
}
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~(PORTA_HOTPLUG_ENABLE | PORTA_HOTPLUG_STATUS_MASK);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~(PORTB_HOTPLUG_ENABLE | PORTB_HOTPLUG_STATUS_MASK);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~(PORTC_HOTPLUG_ENABLE | PORTC_HOTPLUG_STATUS_MASK);
+ /* No hpd_invert set in vgpu vbt, need to clear invert mask */
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= ~BXT_DDI_HPD_INVERT_MASK;
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~BXT_DE_PORT_HOTPLUG_MASK;
vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1));
vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)) |=
(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
TRANS_DDI_FUNC_ENABLE);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTA_HOTPLUG_ENABLE;
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
}
(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
(PORT_B << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTB_HOTPLUG_ENABLE;
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
}
(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
(PORT_B << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTC_HOTPLUG_ENABLE;
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
}
PORTD_HOTPLUG_STATUS_MASK;
intel_vgpu_trigger_virtual_event(vgpu, DP_D_HOTPLUG);
} else if (IS_BROXTON(i915)) {
- if (connected) {
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+ if (connected) {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+ } else {
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+ ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
}
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
- vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
- SFUSE_STRAP_DDIB_DETECTED;
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~PORTA_HOTPLUG_STATUS_MASK;
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTA_HOTPLUG_LONG_DETECT;
+ intel_vgpu_trigger_virtual_event(vgpu, DP_A_HOTPLUG);
+ }
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+ if (connected) {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
- }
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
- SFUSE_STRAP_DDIC_DETECTED;
- vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
- GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
- }
- } else {
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+ SFUSE_STRAP_DDIB_DETECTED;
+ } else {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
- ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
- }
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+ ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
~SFUSE_STRAP_DDIB_DETECTED;
- vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
- ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
}
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
- vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
- ~SFUSE_STRAP_DDIC_DETECTED;
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~PORTB_HOTPLUG_STATUS_MASK;
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTB_HOTPLUG_LONG_DETECT;
+ intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
+ }
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+ if (connected) {
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+ vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
+ SFUSE_STRAP_DDIC_DETECTED;
+ } else {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
~GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+ vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
+ ~SFUSE_STRAP_DDIC_DETECTED;
}
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~PORTC_HOTPLUG_STATUS_MASK;
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTC_HOTPLUG_LONG_DETECT;
+ intel_vgpu_trigger_virtual_event(vgpu, DP_C_HOTPLUG);
}
- vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
- PORTB_HOTPLUG_STATUS_MASK;
- intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
}
}
if (ret)
goto out_clean_sched_policy;
- if (IS_BROADWELL(dev_priv))
+ if (IS_BROADWELL(dev_priv) || IS_BROXTON(dev_priv))
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
- /* FixMe: Re-enable APL/BXT once vfio_edid enabled */
- else if (!IS_BROXTON(dev_priv))
+ else
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
if (ret)
goto out_clean_sched_policy;
}
}
if (IS_ERR(src)) {
- unsigned long x, n;
+ unsigned long x, n, remain;
void *ptr;
/*
* We don't care about copying too much here as we only
* validate up to the end of the batch.
*/
+ remain = length;
if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
- length = round_up(length,
+ remain = round_up(remain,
boot_cpu_data.x86_clflush_size);
ptr = dst;
x = offset_in_page(offset);
- for (n = offset >> PAGE_SHIFT; length; n++) {
- int len = min(length, PAGE_SIZE - x);
+ for (n = offset >> PAGE_SHIFT; remain; n++) {
+ int len = min(remain, PAGE_SIZE - x);
src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
if (needs_clflush)
kunmap_atomic(src);
ptr += len;
- length -= len;
+ remain -= len;
x = 0;
}
}
i915_gem_object_unpin_pages(src_obj);
+ memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
+
/* dst_obj is returned with vmap pinned */
return dst;
}
#define LENGTH_BIAS 2
-static bool shadow_needs_clflush(struct drm_i915_gem_object *obj)
-{
- return !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE);
-}
-
/**
* intel_engine_cmd_parser() - parse a batch buffer for privilege violations
* @engine: the engine on which the batch is to execute
ret = 0; /* allow execution */
}
}
-
- if (shadow_needs_clflush(shadow->obj))
- drm_clflush_virt_range(batch_end, 8);
}
- if (shadow_needs_clflush(shadow->obj)) {
- void *ptr = page_mask_bits(shadow->obj->mm.mapping);
-
- drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
- }
+ i915_gem_object_flush_map(shadow->obj);
if (!IS_ERR_OR_NULL(jump_whitelist))
kfree(jump_whitelist);
pci_set_master(pdev);
- cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
-
intel_gt_init_workarounds(dev_priv);
/* On the 945G/GM, the chipset reports the MSI capability on the
err_msi:
if (pdev->msi_enabled)
pci_disable_msi(pdev);
- cpu_latency_qos_remove_request(&dev_priv->pm_qos);
err_mem_regions:
intel_memory_regions_driver_release(dev_priv);
err_ggtt:
if (pdev->msi_enabled)
pci_disable_msi(pdev);
-
- cpu_latency_qos_remove_request(&dev_priv->pm_qos);
}
/**
void i915_driver_shutdown(struct drm_i915_private *i915)
{
+ disable_rpm_wakeref_asserts(&i915->runtime_pm);
+
i915_gem_suspend(i915);
drm_kms_helper_poll_disable(&i915->drm);
intel_suspend_encoders(i915);
intel_shutdown_encoders(i915);
+
+ enable_rpm_wakeref_asserts(&i915->runtime_pm);
}
static bool suspend_to_idle(struct drm_i915_private *dev_priv)
bool display_irqs_enabled;
- /* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
- struct pm_qos_request pm_qos;
-
/* Sideband mailbox protection */
struct mutex sb_lock;
struct pm_qos_request sb_qos;
--- /dev/null
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "i915_drv.h"
+#include "i915_mitigations.h"
+
+static unsigned long mitigations __read_mostly = ~0UL;
+
+enum {
+ CLEAR_RESIDUALS = 0,
+};
+
+static const char * const names[] = {
+ [CLEAR_RESIDUALS] = "residuals",
+};
+
+bool i915_mitigate_clear_residuals(void)
+{
+ return READ_ONCE(mitigations) & BIT(CLEAR_RESIDUALS);
+}
+
+static int mitigations_set(const char *val, const struct kernel_param *kp)
+{
+ unsigned long new = ~0UL;
+ char *str, *sep, *tok;
+ bool first = true;
+ int err = 0;
+
+ BUILD_BUG_ON(ARRAY_SIZE(names) >= BITS_PER_TYPE(mitigations));
+
+ str = kstrdup(val, GFP_KERNEL);
+ if (!str)
+ return -ENOMEM;
+
+ for (sep = str; (tok = strsep(&sep, ","));) {
+ bool enable = true;
+ int i;
+
+ /* Be tolerant of leading/trailing whitespace */
+ tok = strim(tok);
+
+ if (first) {
+ first = false;
+
+ if (!strcmp(tok, "auto"))
+ continue;
+
+ new = 0;
+ if (!strcmp(tok, "off"))
+ continue;
+ }
+
+ if (*tok == '!') {
+ enable = !enable;
+ tok++;
+ }
+
+ if (!strncmp(tok, "no", 2)) {
+ enable = !enable;
+ tok += 2;
+ }
+
+ if (*tok == '\0')
+ continue;
+
+ for (i = 0; i < ARRAY_SIZE(names); i++) {
+ if (!strcmp(tok, names[i])) {
+ if (enable)
+ new |= BIT(i);
+ else
+ new &= ~BIT(i);
+ break;
+ }
+ }
+ if (i == ARRAY_SIZE(names)) {
+ pr_err("Bad \"%s.mitigations=%s\", '%s' is unknown\n",
+ DRIVER_NAME, val, tok);
+ err = -EINVAL;
+ break;
+ }
+ }
+ kfree(str);
+ if (err)
+ return err;
+
+ WRITE_ONCE(mitigations, new);
+ return 0;
+}
+
+static int mitigations_get(char *buffer, const struct kernel_param *kp)
+{
+ unsigned long local = READ_ONCE(mitigations);
+ int count, i;
+ bool enable;
+
+ if (!local)
+ return scnprintf(buffer, PAGE_SIZE, "%s\n", "off");
+
+ if (local & BIT(BITS_PER_LONG - 1)) {
+ count = scnprintf(buffer, PAGE_SIZE, "%s,", "auto");
+ enable = false;
+ } else {
+ enable = true;
+ count = 0;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(names); i++) {
+ if ((local & BIT(i)) != enable)
+ continue;
+
+ count += scnprintf(buffer + count, PAGE_SIZE - count,
+ "%s%s,", enable ? "" : "!", names[i]);
+ }
+
+ buffer[count - 1] = '\n';
+ return count;
+}
+
+static const struct kernel_param_ops ops = {
+ .set = mitigations_set,
+ .get = mitigations_get,
+};
+
+module_param_cb_unsafe(mitigations, &ops, NULL, 0600);
+MODULE_PARM_DESC(mitigations,
+"Selectively enable security mitigations for all Intel® GPUs in the system.\n"
+"\n"
+" auto -- enables all mitigations required for the platform [default]\n"
+" off -- disables all mitigations\n"
+"\n"
+"Individual mitigations can be enabled by passing a comma-separated string,\n"
+"e.g. mitigations=residuals to enable only clearing residuals or\n"
+"mitigations=auto,noresiduals to disable only the clear residual mitigation.\n"
+"Either '!' or 'no' may be used to switch from enabling the mitigation to\n"
+"disabling it.\n"
+"\n"
+"Active mitigations for Ivybridge, Baytrail, Haswell:\n"
+" residuals -- clear all thread-local registers between contexts"
+);
--- /dev/null
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_MITIGATIONS_H__
+#define __I915_MITIGATIONS_H__
+
+#include <linux/types.h>
+
+bool i915_mitigate_clear_residuals(void);
+
+#endif /* __I915_MITIGATIONS_H__ */
if (!gpu->aspace) {
dev_err(dev->dev, "No memory protection without MMU\n");
- ret = -ENXIO;
- goto fail;
+ if (!allow_vram_carveout) {
+ ret = -ENXIO;
+ goto fail;
+ }
}
return gpu;
* implement a cmdstream validator.
*/
DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n");
- ret = -ENXIO;
- goto fail;
+ if (!allow_vram_carveout) {
+ ret = -ENXIO;
+ goto fail;
+ }
}
icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
* implement a cmdstream validator.
*/
DRM_DEV_ERROR(dev->dev, "No memory protection without IOMMU\n");
- ret = -ENXIO;
- goto fail;
+ if (!allow_vram_carveout) {
+ ret = -ENXIO;
+ goto fail;
+ }
}
icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)");
module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600);
+bool allow_vram_carveout = false;
+MODULE_PARM_DESC(allow_vram_carveout, "Allow using VRAM Carveout, in place of IOMMU");
+module_param_named(allow_vram_carveout, allow_vram_carveout, bool, 0600);
+
static const struct adreno_info gpulist[] = {
{
.rev = ADRENO_REV(2, 0, 0, 0),
struct platform_device *pdev)
{
struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
- struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
- struct io_pgtable_domain_attr pgtbl_cfg;
struct iommu_domain *iommu;
struct msm_mmu *mmu;
struct msm_gem_address_space *aspace;
if (!iommu)
return NULL;
- /*
- * This allows GPU to set the bus attributes required to use system
- * cache on behalf of the iommu page table walker.
- */
- if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
- pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
- iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+
+ if (adreno_is_a6xx(adreno_gpu)) {
+ struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+ struct io_pgtable_domain_attr pgtbl_cfg;
+ /*
+ * This allows GPU to set the bus attributes required to use system
+ * cache on behalf of the iommu page table walker.
+ */
+ if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
+ pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
+ iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+ }
}
mmu = msm_iommu_new(&pdev->dev, iommu);
#include "adreno_pm4.xml.h"
extern bool snapshot_debugbus;
+extern bool allow_vram_carveout;
enum {
ADRENO_FW_PM4 = 0,
return gpu->revn == 540;
}
+static inline bool adreno_is_a6xx(struct adreno_gpu *gpu)
+{
+ return ((gpu->revn < 700 && gpu->revn > 599));
+}
+
static inline int adreno_is_a618(struct adreno_gpu *gpu)
{
return gpu->revn == 618;
return 0;
}
+ if (state == ST_CONNECT_PENDING) {
+ /* wait until ST_CONNECTED */
+ dp_add_event(dp, EV_IRQ_HPD_INT, 0, 1); /* delay = 1 */
+ mutex_unlock(&dp->event_mutex);
+ return 0;
+ }
+
ret = dp_display_usbpd_attention_cb(&dp->pdev->dev);
if (ret == -ECONNRESET) { /* cable unplugged */
dp->core_initialized = false;
panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
rc = dp_panel_read_dpcd(dp_panel);
+ if (rc) {
+ DRM_ERROR("read dpcd failed %d\n", rc);
+ return rc;
+ }
+
bw_code = drm_dp_link_rate_to_bw_code(dp_panel->link_info.rate);
- if (rc || !is_link_rate_valid(bw_code) ||
+ if (!is_link_rate_valid(bw_code) ||
!is_lane_count_valid(dp_panel->link_info.num_lanes) ||
(bw_code > dp_panel->max_bw_code)) {
- DRM_ERROR("read dpcd failed %d\n", rc);
- return rc;
+ DRM_ERROR("Illegal link rate=%d lane=%d\n", dp_panel->link_info.rate,
+ dp_panel->link_info.num_lanes);
+ return -EINVAL;
}
if (dp_panel->dfp_present) {
drm_mode_config_init(ddev);
- /* Bind all our sub-components: */
- ret = component_bind_all(dev, ddev);
+ ret = msm_init_vram(ddev);
if (ret)
goto err_destroy_mdss;
- ret = msm_init_vram(ddev);
+ /* Bind all our sub-components: */
+ ret = component_bind_all(dev, ddev);
if (ret)
- goto err_msm_uninit;
+ goto err_destroy_mdss;
dma_set_max_seg_size(dev, UINT_MAX);
{
struct msm_gem_object *msm_obj = to_msm_bo(obj);
+ WARN_ON(!msm_gem_is_locked(obj));
+
if (!msm_obj->pages) {
struct drm_device *dev = obj->dev;
struct page **p;
if (msm_obj->pages)
kvfree(msm_obj->pages);
+ put_iova_vmas(obj);
+
/* dma_buf_detach() grabs resv lock, so we need to unlock
* prior to drm_prime_gem_destroy
*/
} else {
msm_gem_vunmap(obj);
put_pages(obj);
+ put_iova_vmas(obj);
msm_gem_unlock(obj);
}
- put_iova_vmas(obj);
-
drm_gem_object_release(obj);
kfree(msm_obj);
struct msm_gem_vma *vma;
struct page **pages;
+ drm_gem_private_object_init(dev, obj, size);
+
msm_gem_lock(obj);
vma = add_vma(obj, NULL);
to_msm_bo(obj)->vram_node = &vma->node;
- drm_gem_private_object_init(dev, obj, size);
-
+ msm_gem_lock(obj);
pages = get_pages(obj);
+ msm_gem_unlock(obj);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
goto fail;
nouveau-y += dispnv50/wndw.o
nouveau-y += dispnv50/wndwc37e.o
nouveau-y += dispnv50/wndwc57e.o
+nouveau-y += dispnv50/wndwc67e.o
nouveau-y += dispnv50/base.o
nouveau-y += dispnv50/base507c.o
int version;
int (*new)(struct nouveau_drm *, s32, struct nv50_core **);
} cores[] = {
+ { GA102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
{ TU102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
{ GV100_DISP_CORE_CHANNEL_DMA, 0, corec37d_new },
{ GP102_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
int version;
int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
} curses[] = {
+ { GA102_DISP_CURSOR, 0, cursc37a_new },
{ TU102_DISP_CURSOR, 0, cursc37a_new },
{ GV100_DISP_CURSOR, 0, cursc37a_new },
{ GK104_DISP_CURSOR, 0, curs907a_new },
int
nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
- const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
+ const s32 *oclass, u8 head, void *data, u32 size, s64 syncbuf,
struct nv50_dmac *dmac)
{
struct nouveau_cli *cli = (void *)device->object.client;
if (ret)
return ret;
- if (!syncbuf)
+ if (syncbuf < 0)
return 0;
ret = nvif_object_ctor(&dmac->base.user, "kmsSyncCtxDma", NV50_DISP_HANDLE_SYNCBUF,
int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
const s32 *oclass, u8 head, void *data, u32 size,
- u64 syncbuf, struct nv50_dmac *dmac);
+ s64 syncbuf, struct nv50_dmac *dmac);
void nv50_dmac_destroy(struct nv50_dmac *);
/*
int version;
int (*init)(struct nouveau_drm *, s32, struct nv50_wndw *);
} wimms[] = {
+ { GA102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
{ TU102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
{ GV100_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
{}
int ret;
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
- &oclass, 0, &args, sizeof(args), 0,
+ &oclass, 0, &args, sizeof(args), -1,
&wndw->wimm);
if (ret) {
NV_ERROR(drm, "wimm%04x allocation failed: %d\n", oclass, ret);
int (*new)(struct nouveau_drm *, enum drm_plane_type,
int, s32, struct nv50_wndw **);
} wndws[] = {
+ { GA102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc67e_new },
{ TU102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc57e_new },
{ GV100_DISP_WINDOW_CHANNEL_DMA, 0, wndwc37e_new },
{}
int wndwc57e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
struct nv50_wndw **);
+bool wndwc57e_ilut(struct nv50_wndw *, struct nv50_wndw_atom *, int);
+int wndwc57e_ilut_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_ilut_clr(struct nv50_wndw *);
+int wndwc57e_csc_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_csc_clr(struct nv50_wndw *);
+
+int wndwc67e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
+ struct nv50_wndw **);
int nv50_wndw_new(struct nouveau_drm *, enum drm_plane_type, int index,
struct nv50_wndw **);
return 0;
}
-static int
+int
wndwc57e_csc_clr(struct nv50_wndw *wndw)
{
struct nvif_push *push = wndw->wndw.push;
return 0;
}
-static int
+int
wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
{
struct nvif_push *push = wndw->wndw.push;
return 0;
}
-static int
+int
wndwc57e_ilut_clr(struct nv50_wndw *wndw)
{
struct nvif_push *push = wndw->wndw.push;
return 0;
}
-static int
+int
wndwc57e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
{
struct nvif_push *push = wndw->wndw.push;
writew(readw(mem - 4), mem + 4);
}
-static bool
+bool
wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
{
if (size = size ? size : 1024, size != 256 && size != 1024)
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wndw.h"
+#include "atom.h"
+
+#include <nvif/pushc37b.h>
+
+#include <nvhw/class/clc57e.h>
+
+static int
+wndwc67e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+ struct nvif_push *push = wndw->wndw.push;
+ int ret;
+
+ if ((ret = PUSH_WAIT(push, 17)))
+ return ret;
+
+ PUSH_MTHD(push, NVC57E, SET_PRESENT_CONTROL,
+ NVVAL(NVC57E, SET_PRESENT_CONTROL, MIN_PRESENT_INTERVAL, asyw->image.interval) |
+ NVVAL(NVC57E, SET_PRESENT_CONTROL, BEGIN_MODE, asyw->image.mode) |
+ NVDEF(NVC57E, SET_PRESENT_CONTROL, TIMESTAMP_MODE, DISABLE));
+
+ PUSH_MTHD(push, NVC57E, SET_SIZE,
+ NVVAL(NVC57E, SET_SIZE, WIDTH, asyw->image.w) |
+ NVVAL(NVC57E, SET_SIZE, HEIGHT, asyw->image.h),
+
+ SET_STORAGE,
+ NVVAL(NVC57E, SET_STORAGE, BLOCK_HEIGHT, asyw->image.blockh),
+
+ SET_PARAMS,
+ NVVAL(NVC57E, SET_PARAMS, FORMAT, asyw->image.format) |
+ NVDEF(NVC57E, SET_PARAMS, CLAMP_BEFORE_BLEND, DISABLE) |
+ NVDEF(NVC57E, SET_PARAMS, SWAP_UV, DISABLE) |
+ NVDEF(NVC57E, SET_PARAMS, FMT_ROUNDING_MODE, ROUND_TO_NEAREST),
+
+ SET_PLANAR_STORAGE(0),
+ NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.blocks[0]) |
+ NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.pitch[0] >> 6));
+
+ PUSH_MTHD(push, NVC57E, SET_CONTEXT_DMA_ISO(0), asyw->image.handle, 1);
+ PUSH_MTHD(push, NVC57E, SET_OFFSET(0), asyw->image.offset[0] >> 8);
+
+ PUSH_MTHD(push, NVC57E, SET_POINT_IN(0),
+ NVVAL(NVC57E, SET_POINT_IN, X, asyw->state.src_x >> 16) |
+ NVVAL(NVC57E, SET_POINT_IN, Y, asyw->state.src_y >> 16));
+
+ PUSH_MTHD(push, NVC57E, SET_SIZE_IN,
+ NVVAL(NVC57E, SET_SIZE_IN, WIDTH, asyw->state.src_w >> 16) |
+ NVVAL(NVC57E, SET_SIZE_IN, HEIGHT, asyw->state.src_h >> 16));
+
+ PUSH_MTHD(push, NVC57E, SET_SIZE_OUT,
+ NVVAL(NVC57E, SET_SIZE_OUT, WIDTH, asyw->state.crtc_w) |
+ NVVAL(NVC57E, SET_SIZE_OUT, HEIGHT, asyw->state.crtc_h));
+ return 0;
+}
+
+static const struct nv50_wndw_func
+wndwc67e = {
+ .acquire = wndwc37e_acquire,
+ .release = wndwc37e_release,
+ .sema_set = wndwc37e_sema_set,
+ .sema_clr = wndwc37e_sema_clr,
+ .ntfy_set = wndwc37e_ntfy_set,
+ .ntfy_clr = wndwc37e_ntfy_clr,
+ .ntfy_reset = corec37d_ntfy_init,
+ .ntfy_wait_begun = base507c_ntfy_wait_begun,
+ .ilut = wndwc57e_ilut,
+ .ilut_identity = true,
+ .ilut_size = 1024,
+ .xlut_set = wndwc57e_ilut_set,
+ .xlut_clr = wndwc57e_ilut_clr,
+ .csc = base907c_csc,
+ .csc_set = wndwc57e_csc_set,
+ .csc_clr = wndwc57e_csc_clr,
+ .image_set = wndwc67e_image_set,
+ .image_clr = wndwc37e_image_clr,
+ .blend_set = wndwc37e_blend_set,
+ .update = wndwc37e_update,
+};
+
+int
+wndwc67e_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
+ s32 oclass, struct nv50_wndw **pwndw)
+{
+ return wndwc37e_new_(&wndwc67e, drm, type, index, oclass, BIT(index >> 1), pwndw);
+}
#define NV_DEVICE_INFO_V0_PASCAL 0x0a
#define NV_DEVICE_INFO_V0_VOLTA 0x0b
#define NV_DEVICE_INFO_V0_TURING 0x0c
+#define NV_DEVICE_INFO_V0_AMPERE 0x0d
__u8 family;
__u8 pad06[2];
__u64 ram_size;
#define GP102_DISP /* cl5070.h */ 0x00009870
#define GV100_DISP /* cl5070.h */ 0x0000c370
#define TU102_DISP /* cl5070.h */ 0x0000c570
+#define GA102_DISP /* cl5070.h */ 0x0000c670
#define GV100_DISP_CAPS 0x0000c373
#define GK104_DISP_CURSOR /* cl507a.h */ 0x0000917a
#define GV100_DISP_CURSOR /* cl507a.h */ 0x0000c37a
#define TU102_DISP_CURSOR /* cl507a.h */ 0x0000c57a
+#define GA102_DISP_CURSOR /* cl507a.h */ 0x0000c67a
#define NV50_DISP_OVERLAY /* cl507b.h */ 0x0000507b
#define G82_DISP_OVERLAY /* cl507b.h */ 0x0000827b
#define GV100_DISP_WINDOW_IMM_CHANNEL_DMA /* clc37b.h */ 0x0000c37b
#define TU102_DISP_WINDOW_IMM_CHANNEL_DMA /* clc37b.h */ 0x0000c57b
+#define GA102_DISP_WINDOW_IMM_CHANNEL_DMA /* clc37b.h */ 0x0000c67b
#define NV50_DISP_BASE_CHANNEL_DMA /* cl507c.h */ 0x0000507c
#define G82_DISP_BASE_CHANNEL_DMA /* cl507c.h */ 0x0000827c
#define GP102_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000987d
#define GV100_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000c37d
#define TU102_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000c57d
+#define GA102_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000c67d
#define NV50_DISP_OVERLAY_CHANNEL_DMA /* cl507e.h */ 0x0000507e
#define G82_DISP_OVERLAY_CHANNEL_DMA /* cl507e.h */ 0x0000827e
#define GV100_DISP_WINDOW_CHANNEL_DMA /* clc37e.h */ 0x0000c37e
#define TU102_DISP_WINDOW_CHANNEL_DMA /* clc37e.h */ 0x0000c57e
+#define GA102_DISP_WINDOW_CHANNEL_DMA /* clc37e.h */ 0x0000c67e
#define NV50_TESLA 0x00005097
#define G82_TESLA 0x00008297
GP100 = 0x130,
GV100 = 0x140,
TU100 = 0x160,
+ GA100 = 0x170,
} card_type;
u32 chipset;
u8 chiprev;
int gp102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
int gv100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
int tu102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int ga102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
#endif
int gm200_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
int gv100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
int tu102_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
+int ga100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
#endif
int gp102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gp10b_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gv100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
#include <subdev/bios.h>
#include <subdev/bios/ramcfg.h>
int g94_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
int gf119_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
int gk104_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
+int ga102_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
#endif
int gf117_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gf119_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gk104_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
+int gk110_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gm200_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
static inline int
int gp100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
int gp10b_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
int tu102_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
+int ga100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
#endif
case NV_DEVICE_INFO_V0_PASCAL:
case NV_DEVICE_INFO_V0_VOLTA:
case NV_DEVICE_INFO_V0_TURING:
+ case NV_DEVICE_INFO_V0_AMPERE: //XXX: not confirmed
ret = nv50_backlight_init(nv_encoder, &props, &ops);
break;
default:
struct nvif_disp *disp)
{
static const struct nvif_mclass disps[] = {
+ { GA102_DISP, -1 },
{ TU102_DISP, -1 },
{ GV100_DISP, -1 },
{ GP102_DISP, -1 },
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
.fb = gm107_fb_new,
.fuse = gm107_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
.fb = gm107_fb_new,
.fuse = gm107_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
.sec2 = tu102_sec2_new,
};
+static const struct nvkm_device_chip
+nv170_chipset = {
+ .name = "GA100",
+ .bar = tu102_bar_new,
+ .bios = nvkm_bios_new,
+ .devinit = ga100_devinit_new,
+ .fb = ga100_fb_new,
+ .gpio = gk104_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .mc = ga100_mc_new,
+ .mmu = tu102_mmu_new,
+ .pci = gp100_pci_new,
+ .timer = gk20a_timer_new,
+};
+
+static const struct nvkm_device_chip
+nv172_chipset = {
+ .name = "GA102",
+ .bar = tu102_bar_new,
+ .bios = nvkm_bios_new,
+ .devinit = ga100_devinit_new,
+ .fb = ga102_fb_new,
+ .gpio = ga102_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .mc = ga100_mc_new,
+ .mmu = tu102_mmu_new,
+ .pci = gp100_pci_new,
+ .timer = gk20a_timer_new,
+ .disp = ga102_disp_new,
+ .dma = gv100_dma_new,
+};
+
+static const struct nvkm_device_chip
+nv174_chipset = {
+ .name = "GA104",
+ .bar = tu102_bar_new,
+ .bios = nvkm_bios_new,
+ .devinit = ga100_devinit_new,
+ .fb = ga102_fb_new,
+ .gpio = ga102_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .mc = ga100_mc_new,
+ .mmu = tu102_mmu_new,
+ .pci = gp100_pci_new,
+ .timer = gk20a_timer_new,
+ .disp = ga102_disp_new,
+ .dma = gv100_dma_new,
+};
+
static int
nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
struct nvkm_notify *notify)
case 0x130: device->card_type = GP100; break;
case 0x140: device->card_type = GV100; break;
case 0x160: device->card_type = TU100; break;
+ case 0x170: device->card_type = GA100; break;
default:
break;
}
case 0x166: device->chip = &nv166_chipset; break;
case 0x167: device->chip = &nv167_chipset; break;
case 0x168: device->chip = &nv168_chipset; break;
+ case 0x172: device->chip = &nv172_chipset; break;
+ case 0x174: device->chip = &nv174_chipset; break;
default:
- nvdev_error(device, "unknown chipset (%08x)\n", boot0);
- ret = -ENODEV;
- goto done;
+ if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) {
+ switch (device->chipset) {
+ case 0x170: device->chip = &nv170_chipset; break;
+ default:
+ break;
+ }
+ }
+
+ if (!device->chip) {
+ nvdev_error(device, "unknown chipset (%08x)\n", boot0);
+ ret = -ENODEV;
+ goto done;
+ }
+ break;
}
nvdev_info(device, "NVIDIA %s (%08x)\n",
case GP100: args->v0.family = NV_DEVICE_INFO_V0_PASCAL; break;
case GV100: args->v0.family = NV_DEVICE_INFO_V0_VOLTA; break;
case TU100: args->v0.family = NV_DEVICE_INFO_V0_TURING; break;
+ case GA100: args->v0.family = NV_DEVICE_INFO_V0_AMPERE; break;
default:
args->v0.family = 0;
break;
nvkm-y += nvkm/engine/disp/gp102.o
nvkm-y += nvkm/engine/disp/gv100.o
nvkm-y += nvkm/engine/disp/tu102.o
+nvkm-y += nvkm/engine/disp/ga102.o
nvkm-y += nvkm/engine/disp/vga.o
nvkm-y += nvkm/engine/disp/head.o
nvkm-y += nvkm/engine/disp/sorgp100.o
nvkm-y += nvkm/engine/disp/sorgv100.o
nvkm-y += nvkm/engine/disp/sortu102.o
+nvkm-y += nvkm/engine/disp/sorga102.o
nvkm-y += nvkm/engine/disp/outp.o
nvkm-y += nvkm/engine/disp/dp.o
nvkm-y += nvkm/engine/disp/rootgp102.o
nvkm-y += nvkm/engine/disp/rootgv100.o
nvkm-y += nvkm/engine/disp/roottu102.o
+nvkm-y += nvkm/engine/disp/rootga102.o
nvkm-y += nvkm/engine/disp/capsgv100.o
#include <nvif/event.h>
+/* IED scripts are no longer used by UEFI/RM from Ampere, but have been updated for
+ * the x86 option ROM. However, the relevant VBIOS table versions weren't modified,
+ * so we're unable to detect this in a nice way.
+ */
+#define AMPERE_IED_HACK(disp) ((disp)->engine.subdev.device->card_type >= GA100)
+
struct lt_state {
struct nvkm_dp *dp;
u8 stat[6];
dp->dpcd[DPCD_RC02] &= ~DPCD_RC02_TPS3_SUPPORTED;
lt.pc2 = dp->dpcd[DPCD_RC02] & DPCD_RC02_TPS3_SUPPORTED;
+ if (AMPERE_IED_HACK(disp) && (lnkcmp = lt.dp->info.script[0])) {
+ /* Execute BeforeLinkTraining script from DP Info table. */
+ while (ior->dp.bw < nvbios_rd08(bios, lnkcmp))
+ lnkcmp += 3;
+ lnkcmp = nvbios_rd16(bios, lnkcmp + 1);
+
+ nvbios_init(&dp->outp.disp->engine.subdev, lnkcmp,
+ init.outp = &dp->outp.info;
+ init.or = ior->id;
+ init.link = ior->asy.link;
+ );
+ }
+
/* Set desired link configuration on the source. */
if ((lnkcmp = lt.dp->info.lnkcmp)) {
if (dp->version < 0x30) {
);
}
- /* Execute BeforeLinkTraining script from DP Info table. */
- nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
- init.outp = &dp->outp.info;
- init.or = dp->outp.ior->id;
- init.link = dp->outp.ior->asy.link;
- );
+ if (!AMPERE_IED_HACK(dp->outp.disp)) {
+ /* Execute BeforeLinkTraining script from DP Info table. */
+ nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
+ init.outp = &dp->outp.info;
+ init.or = dp->outp.ior->id;
+ init.link = dp->outp.ior->asy.link;
+ );
+ }
}
static const struct dp_rates {
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+#include "head.h"
+#include "ior.h"
+#include "channv50.h"
+#include "rootnv50.h"
+
+static const struct nv50_disp_func
+ga102_disp = {
+ .init = tu102_disp_init,
+ .fini = gv100_disp_fini,
+ .intr = gv100_disp_intr,
+ .uevent = &gv100_disp_chan_uevent,
+ .super = gv100_disp_super,
+ .root = &ga102_disp_root_oclass,
+ .wndw = { .cnt = gv100_disp_wndw_cnt },
+ .head = { .cnt = gv100_head_cnt, .new = gv100_head_new },
+ .sor = { .cnt = gv100_sor_cnt, .new = ga102_sor_new },
+ .ramht_size = 0x2000,
+};
+
+int
+ga102_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+ return nv50_disp_new_(&ga102_disp, device, index, pdisp);
+}
void gv100_sor_dp_audio_sym(struct nvkm_ior *, int, u16, u32);
void gv100_sor_dp_watermark(struct nvkm_ior *, int, u8);
+void tu102_sor_dp_vcpi(struct nvkm_ior *, int, u8, u8, u16, u16);
+
void g84_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
void gt215_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
void gf119_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
int gv100_sor_new(struct nvkm_disp *, int);
int tu102_sor_new(struct nvkm_disp *, int);
+
+int ga102_sor_new(struct nvkm_disp *, int);
#endif
void gv100_disp_super(struct work_struct *);
int gv100_disp_wndw_cnt(struct nvkm_disp *, unsigned long *);
+int tu102_disp_init(struct nv50_disp *);
+
void nv50_disp_dptmds_war_2(struct nv50_disp *, struct dcb_output *);
void nv50_disp_dptmds_war_3(struct nv50_disp *, struct dcb_output *);
void nv50_disp_update_sppll1(struct nv50_disp *);
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "rootnv50.h"
+#include "channv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+ga102_disp_root = {
+ .user = {
+ {{-1,-1,GV100_DISP_CAPS }, gv100_disp_caps_new },
+ {{0,0,GA102_DISP_CURSOR }, gv100_disp_curs_new },
+ {{0,0,GA102_DISP_WINDOW_IMM_CHANNEL_DMA}, gv100_disp_wimm_new },
+ {{0,0,GA102_DISP_CORE_CHANNEL_DMA }, gv100_disp_core_new },
+ {{0,0,GA102_DISP_WINDOW_CHANNEL_DMA }, gv100_disp_wndw_new },
+ {}
+ },
+};
+
+static int
+ga102_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+ void *data, u32 size, struct nvkm_object **pobject)
+{
+ return nv50_disp_root_new_(&ga102_disp_root, disp, oclass, data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+ga102_disp_root_oclass = {
+ .base.oclass = GA102_DISP,
+ .base.minver = -1,
+ .base.maxver = -1,
+ .ctor = ga102_disp_root_new,
+};
extern const struct nvkm_disp_oclass gp102_disp_root_oclass;
extern const struct nvkm_disp_oclass gv100_disp_root_oclass;
extern const struct nvkm_disp_oclass tu102_disp_root_oclass;
+extern const struct nvkm_disp_oclass ga102_disp_root_oclass;
#endif
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ior.h"
+
+#include <subdev/timer.h>
+
+static int
+ga102_sor_dp_links(struct nvkm_ior *sor, struct nvkm_i2c_aux *aux)
+{
+ struct nvkm_device *device = sor->disp->engine.subdev.device;
+ const u32 soff = nv50_ior_base(sor);
+ const u32 loff = nv50_sor_link(sor);
+ u32 dpctrl = 0x00000000;
+ u32 clksor = 0x00000000;
+
+ switch (sor->dp.bw) {
+ case 0x06: clksor |= 0x00000000; break;
+ case 0x0a: clksor |= 0x00040000; break;
+ case 0x14: clksor |= 0x00080000; break;
+ case 0x1e: clksor |= 0x000c0000; break;
+ default:
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ dpctrl |= ((1 << sor->dp.nr) - 1) << 16;
+ if (sor->dp.mst)
+ dpctrl |= 0x40000000;
+ if (sor->dp.ef)
+ dpctrl |= 0x00004000;
+
+ nvkm_mask(device, 0x612300 + soff, 0x007c0000, clksor);
+
+ /*XXX*/
+ nvkm_msec(device, 40, NVKM_DELAY);
+ nvkm_mask(device, 0x612300 + soff, 0x00030000, 0x00010000);
+ nvkm_mask(device, 0x61c10c + loff, 0x00000003, 0x00000001);
+
+ nvkm_mask(device, 0x61c10c + loff, 0x401f4000, dpctrl);
+ return 0;
+}
+
+static void
+ga102_sor_clock(struct nvkm_ior *sor)
+{
+ struct nvkm_device *device = sor->disp->engine.subdev.device;
+ u32 div2 = 0;
+ if (sor->asy.proto == TMDS) {
+ if (sor->tmds.high_speed)
+ div2 = 1;
+ }
+ nvkm_wr32(device, 0x00ec08 + (sor->id * 0x10), 0x00000000);
+ nvkm_wr32(device, 0x00ec04 + (sor->id * 0x10), div2);
+}
+
+static const struct nvkm_ior_func
+ga102_sor_hda = {
+ .route = {
+ .get = gm200_sor_route_get,
+ .set = gm200_sor_route_set,
+ },
+ .state = gv100_sor_state,
+ .power = nv50_sor_power,
+ .clock = ga102_sor_clock,
+ .hdmi = {
+ .ctrl = gv100_hdmi_ctrl,
+ .scdc = gm200_hdmi_scdc,
+ },
+ .dp = {
+ .lanes = { 0, 1, 2, 3 },
+ .links = ga102_sor_dp_links,
+ .power = g94_sor_dp_power,
+ .pattern = gm107_sor_dp_pattern,
+ .drive = gm200_sor_dp_drive,
+ .vcpi = tu102_sor_dp_vcpi,
+ .audio = gv100_sor_dp_audio,
+ .audio_sym = gv100_sor_dp_audio_sym,
+ .watermark = gv100_sor_dp_watermark,
+ },
+ .hda = {
+ .hpd = gf119_hda_hpd,
+ .eld = gf119_hda_eld,
+ .device_entry = gv100_hda_device_entry,
+ },
+};
+
+static const struct nvkm_ior_func
+ga102_sor = {
+ .route = {
+ .get = gm200_sor_route_get,
+ .set = gm200_sor_route_set,
+ },
+ .state = gv100_sor_state,
+ .power = nv50_sor_power,
+ .clock = ga102_sor_clock,
+ .hdmi = {
+ .ctrl = gv100_hdmi_ctrl,
+ .scdc = gm200_hdmi_scdc,
+ },
+ .dp = {
+ .lanes = { 0, 1, 2, 3 },
+ .links = ga102_sor_dp_links,
+ .power = g94_sor_dp_power,
+ .pattern = gm107_sor_dp_pattern,
+ .drive = gm200_sor_dp_drive,
+ .vcpi = tu102_sor_dp_vcpi,
+ .audio = gv100_sor_dp_audio,
+ .audio_sym = gv100_sor_dp_audio_sym,
+ .watermark = gv100_sor_dp_watermark,
+ },
+};
+
+int
+ga102_sor_new(struct nvkm_disp *disp, int id)
+{
+ struct nvkm_device *device = disp->engine.subdev.device;
+ u32 hda = nvkm_rd32(device, 0x08a15c);
+ if (hda & BIT(id))
+ return nvkm_ior_new_(&ga102_sor_hda, disp, SOR, id);
+ return nvkm_ior_new_(&ga102_sor, disp, SOR, id);
+}
#include <subdev/timer.h>
-static void
+void
tu102_sor_dp_vcpi(struct nvkm_ior *sor, int head,
u8 slot, u8 slot_nr, u16 pbn, u16 aligned)
{
#include <core/gpuobj.h>
#include <subdev/timer.h>
-static int
+int
tu102_disp_init(struct nv50_disp *disp)
{
struct nvkm_device *device = disp->base.engine.subdev.device;
nvkm_debug(subdev, "%08x: type %02x, %d bytes\n",
image.base, image.type, image.size);
- if (!shadow_fetch(bios, mthd, image.size)) {
+ if (!shadow_fetch(bios, mthd, image.base + image.size)) {
nvkm_debug(subdev, "%08x: fetch failed\n", image.base);
return 0;
}
return NULL;
/* we can't get the bios image pointer without PDISP */
+ if (device->card_type >= GA100)
+ addr = device->chipset == 0x170; /*XXX: find the fuse reg for this */
+ else
if (device->card_type >= GM100)
addr = nvkm_rd32(device, 0x021c04);
else
nvkm-y += nvkm/subdev/devinit/gm200.o
nvkm-y += nvkm/subdev/devinit/gv100.o
nvkm-y += nvkm/subdev/devinit/tu102.o
+nvkm-y += nvkm/subdev/devinit/ga100.o
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+#include <subdev/clk/pll.h>
+
+static int
+ga100_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
+{
+ struct nvkm_subdev *subdev = &init->subdev;
+ struct nvkm_device *device = subdev->device;
+ struct nvbios_pll info;
+ int head = type - PLL_VPLL0;
+ int N, fN, M, P;
+ int ret;
+
+ ret = nvbios_pll_parse(device->bios, type, &info);
+ if (ret)
+ return ret;
+
+ ret = gt215_pll_calc(subdev, &info, freq, &N, &fN, &M, &P);
+ if (ret < 0)
+ return ret;
+
+ switch (info.type) {
+ case PLL_VPLL0:
+ case PLL_VPLL1:
+ case PLL_VPLL2:
+ case PLL_VPLL3:
+ nvkm_wr32(device, 0x00ef00 + (head * 0x40), 0x02080004);
+ nvkm_wr32(device, 0x00ef18 + (head * 0x40), (N << 16) | fN);
+ nvkm_wr32(device, 0x00ef04 + (head * 0x40), (P << 16) | M);
+ nvkm_wr32(device, 0x00e9c0 + (head * 0x04), 0x00000001);
+ break;
+ default:
+ nvkm_warn(subdev, "%08x/%dKhz unimplemented\n", type, freq);
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static const struct nvkm_devinit_func
+ga100_devinit = {
+ .init = nv50_devinit_init,
+ .post = tu102_devinit_post,
+ .pll_set = ga100_devinit_pll_set,
+};
+
+int
+ga100_devinit_new(struct nvkm_device *device, int index, struct nvkm_devinit **pinit)
+{
+ return nv50_devinit_new_(&ga100_devinit, device, index, pinit);
+}
int index, struct nvkm_devinit *);
int nv04_devinit_post(struct nvkm_devinit *, bool);
+int tu102_devinit_post(struct nvkm_devinit *, bool);
#endif
return ret;
}
-static int
+int
tu102_devinit_post(struct nvkm_devinit *base, bool post)
{
struct nv50_devinit *init = nv50_devinit(base);
nvkm-y += nvkm/subdev/fb/gp102.o
nvkm-y += nvkm/subdev/fb/gp10b.o
nvkm-y += nvkm/subdev/fb/gv100.o
+nvkm-y += nvkm/subdev/fb/ga100.o
+nvkm-y += nvkm/subdev/fb/ga102.o
nvkm-y += nvkm/subdev/fb/ram.o
nvkm-y += nvkm/subdev/fb/ramnv04.o
nvkm-y += nvkm/subdev/fb/ramgm107.o
nvkm-y += nvkm/subdev/fb/ramgm200.o
nvkm-y += nvkm/subdev/fb/ramgp100.o
+nvkm-y += nvkm/subdev/fb/ramga102.o
nvkm-y += nvkm/subdev/fb/sddr2.o
nvkm-y += nvkm/subdev/fb/sddr3.o
nvkm-y += nvkm/subdev/fb/gddr3.o
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga100_fb = {
+ .dtor = gf100_fb_dtor,
+ .oneinit = gf100_fb_oneinit,
+ .init = gp100_fb_init,
+ .init_page = gv100_fb_init_page,
+ .init_unkn = gp100_fb_init_unkn,
+ .ram_new = gp100_ram_new,
+ .default_bigpage = 16,
+};
+
+int
+ga100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+ return gp102_fb_new_(&ga100_fb, device, index, pfb);
+}
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga102_fb = {
+ .dtor = gf100_fb_dtor,
+ .oneinit = gf100_fb_oneinit,
+ .init = gp100_fb_init,
+ .init_page = gv100_fb_init_page,
+ .init_unkn = gp100_fb_init_unkn,
+ .ram_new = ga102_ram_new,
+ .default_bigpage = 16,
+};
+
+int
+ga102_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+ return gp102_fb_new_(&ga102_fb, device, index, pfb);
+}
#include "gf100.h"
#include "ram.h"
-static int
+int
gv100_fb_init_page(struct nvkm_fb *fb)
{
return (fb->page == 16) ? 0 : -EINVAL;
struct nvkm_fb **);
bool gp102_fb_vpr_scrub_required(struct nvkm_fb *);
int gp102_fb_vpr_scrub(struct nvkm_fb *);
+
+int gv100_fb_init_page(struct nvkm_fb *);
#endif
int gm107_ram_new(struct nvkm_fb *, struct nvkm_ram **);
int gm200_ram_new(struct nvkm_fb *, struct nvkm_ram **);
int gp100_ram_new(struct nvkm_fb *, struct nvkm_ram **);
+int ga102_ram_new(struct nvkm_fb *, struct nvkm_ram **);
#endif
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ram.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/init.h>
+#include <subdev/bios/rammap.h>
+
+static const struct nvkm_ram_func
+ga102_ram = {
+};
+
+int
+ga102_ram_new(struct nvkm_fb *fb, struct nvkm_ram **pram)
+{
+ struct nvkm_device *device = fb->subdev.device;
+ enum nvkm_ram_type type = nvkm_fb_bios_memtype(device->bios);
+ u32 size = nvkm_rd32(device, 0x1183a4);
+
+ return nvkm_ram_new_(&ga102_ram, fb, type, (u64)size << 20, pram);
+}
nvkm-y += nvkm/subdev/gpio/g94.o
nvkm-y += nvkm/subdev/gpio/gf119.o
nvkm-y += nvkm/subdev/gpio/gk104.o
+nvkm-y += nvkm/subdev/gpio/ga102.o
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+static void
+ga102_gpio_reset(struct nvkm_gpio *gpio, u8 match)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ struct nvkm_bios *bios = device->bios;
+ u8 ver, len;
+ u16 entry;
+ int ent = -1;
+
+ while ((entry = dcb_gpio_entry(bios, 0, ++ent, &ver, &len))) {
+ u32 data = nvbios_rd32(bios, entry);
+ u8 line = (data & 0x0000003f);
+ u8 defs = !!(data & 0x00000080);
+ u8 func = (data & 0x0000ff00) >> 8;
+ u8 unk0 = (data & 0x00ff0000) >> 16;
+ u8 unk1 = (data & 0x1f000000) >> 24;
+
+ if ( func == DCB_GPIO_UNUSED ||
+ (match != DCB_GPIO_UNUSED && match != func))
+ continue;
+
+ nvkm_gpio_set(gpio, 0, func, line, defs);
+
+ nvkm_mask(device, 0x021200 + (line * 4), 0xff, unk0);
+ if (unk1--)
+ nvkm_mask(device, 0x00d740 + (unk1 * 4), 0xff, line);
+ }
+}
+
+static int
+ga102_gpio_drive(struct nvkm_gpio *gpio, int line, int dir, int out)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ u32 data = ((dir ^ 1) << 13) | (out << 12);
+ nvkm_mask(device, 0x021200 + (line * 4), 0x00003000, data);
+ nvkm_mask(device, 0x00d604, 0x00000001, 0x00000001); /* update? */
+ return 0;
+}
+
+static int
+ga102_gpio_sense(struct nvkm_gpio *gpio, int line)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ return !!(nvkm_rd32(device, 0x021200 + (line * 4)) & 0x00004000);
+}
+
+static void
+ga102_gpio_intr_stat(struct nvkm_gpio *gpio, u32 *hi, u32 *lo)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ u32 intr0 = nvkm_rd32(device, 0x021640);
+ u32 intr1 = nvkm_rd32(device, 0x02164c);
+ u32 stat0 = nvkm_rd32(device, 0x021648) & intr0;
+ u32 stat1 = nvkm_rd32(device, 0x021654) & intr1;
+ *lo = (stat1 & 0xffff0000) | (stat0 >> 16);
+ *hi = (stat1 << 16) | (stat0 & 0x0000ffff);
+ nvkm_wr32(device, 0x021640, intr0);
+ nvkm_wr32(device, 0x02164c, intr1);
+}
+
+static void
+ga102_gpio_intr_mask(struct nvkm_gpio *gpio, u32 type, u32 mask, u32 data)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ u32 inte0 = nvkm_rd32(device, 0x021648);
+ u32 inte1 = nvkm_rd32(device, 0x021654);
+ if (type & NVKM_GPIO_LO)
+ inte0 = (inte0 & ~(mask << 16)) | (data << 16);
+ if (type & NVKM_GPIO_HI)
+ inte0 = (inte0 & ~(mask & 0xffff)) | (data & 0xffff);
+ mask >>= 16;
+ data >>= 16;
+ if (type & NVKM_GPIO_LO)
+ inte1 = (inte1 & ~(mask << 16)) | (data << 16);
+ if (type & NVKM_GPIO_HI)
+ inte1 = (inte1 & ~mask) | data;
+ nvkm_wr32(device, 0x021648, inte0);
+ nvkm_wr32(device, 0x021654, inte1);
+}
+
+static const struct nvkm_gpio_func
+ga102_gpio = {
+ .lines = 32,
+ .intr_stat = ga102_gpio_intr_stat,
+ .intr_mask = ga102_gpio_intr_mask,
+ .drive = ga102_gpio_drive,
+ .sense = ga102_gpio_sense,
+ .reset = ga102_gpio_reset,
+};
+
+int
+ga102_gpio_new(struct nvkm_device *device, int index, struct nvkm_gpio **pgpio)
+{
+ return nvkm_gpio_new_(&ga102_gpio, device, index, pgpio);
+}
nvkm-y += nvkm/subdev/i2c/gf117.o
nvkm-y += nvkm/subdev/i2c/gf119.o
nvkm-y += nvkm/subdev/i2c/gk104.o
+nvkm-y += nvkm/subdev/i2c/gk110.o
nvkm-y += nvkm/subdev/i2c/gm200.o
nvkm-y += nvkm/subdev/i2c/pad.o
#define __NVKM_I2C_AUX_H__
#include "pad.h"
+static inline void
+nvkm_i2c_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+ if (i2c->func->aux_autodpcd)
+ i2c->func->aux_autodpcd(i2c, aux, false);
+}
+
struct nvkm_i2c_aux_func {
bool address_only;
int (*xfer)(struct nvkm_i2c_aux *, bool retry, u8 type,
u8 type, u32 addr, u8 *data, u8 *size)
{
struct g94_i2c_aux *aux = g94_i2c_aux(obj);
- struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+ struct nvkm_i2c *i2c = aux->base.pad->i2c;
+ struct nvkm_device *device = i2c->subdev.device;
const u32 base = aux->ch * 0x50;
u32 ctrl, stat, timeout, retries = 0;
u32 xbuf[4] = {};
goto out;
}
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
if (!(type & 1)) {
memcpy(xbuf, data, *size);
for (i = 0; i < 16; i += 4) {
if (!timeout--) {
AUX_ERR(&aux->base, "timeout %08x", ctrl);
ret = -EIO;
- goto out;
+ goto out_err;
}
} while (ctrl & 0x00010000);
ret = 0;
memcpy(data, xbuf, *size);
*size = stat & 0x0000001f;
}
-
+out_err:
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
out:
g94_i2c_aux_fini(aux);
return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
gm200_i2c_aux_fini(struct gm200_i2c_aux *aux)
{
struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
- nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00310000, 0x00000000);
+ nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00710000, 0x00000000);
}
static int
AUX_ERR(&aux->base, "begin idle timeout %08x", ctrl);
return -EBUSY;
}
- } while (ctrl & 0x03010000);
+ } while (ctrl & 0x07010000);
/* set some magic, and wait up to 1ms for it to appear */
- nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00300000, ureq);
+ nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00700000, ureq);
timeout = 1000;
do {
ctrl = nvkm_rd32(device, 0x00d954 + (aux->ch * 0x50));
gm200_i2c_aux_fini(aux);
return -EBUSY;
}
- } while ((ctrl & 0x03000000) != urep);
+ } while ((ctrl & 0x07000000) != urep);
return 0;
}
u8 type, u32 addr, u8 *data, u8 *size)
{
struct gm200_i2c_aux *aux = gm200_i2c_aux(obj);
- struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+ struct nvkm_i2c *i2c = aux->base.pad->i2c;
+ struct nvkm_device *device = i2c->subdev.device;
const u32 base = aux->ch * 0x50;
u32 ctrl, stat, timeout, retries = 0;
u32 xbuf[4] = {};
goto out;
}
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
if (!(type & 1)) {
memcpy(xbuf, data, *size);
for (i = 0; i < 16; i += 4) {
if (!timeout--) {
AUX_ERR(&aux->base, "timeout %08x", ctrl);
ret = -EIO;
- goto out;
+ goto out_err;
}
} while (ctrl & 0x00010000);
ret = 0;
*size = stat & 0x0000001f;
}
+out_err:
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
out:
gm200_i2c_aux_fini(aux);
return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+#include "pad.h"
+
+static void
+gk110_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+ nvkm_mask(i2c->subdev.device, 0x00e4f8 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
+static const struct nvkm_i2c_func
+gk110_i2c = {
+ .pad_x_new = gf119_i2c_pad_x_new,
+ .pad_s_new = gf119_i2c_pad_s_new,
+ .aux = 4,
+ .aux_stat = gk104_aux_stat,
+ .aux_mask = gk104_aux_mask,
+ .aux_autodpcd = gk110_aux_autodpcd,
+};
+
+int
+gk110_i2c_new(struct nvkm_device *device, int index, struct nvkm_i2c **pi2c)
+{
+ return nvkm_i2c_new_(&gk110_i2c, device, index, pi2c);
+}
#include "priv.h"
#include "pad.h"
+static void
+gm200_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+ nvkm_mask(i2c->subdev.device, 0x00d968 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
static const struct nvkm_i2c_func
gm200_i2c = {
.pad_x_new = gf119_i2c_pad_x_new,
.aux = 8,
.aux_stat = gk104_aux_stat,
.aux_mask = gk104_aux_mask,
+ .aux_autodpcd = gm200_aux_autodpcd,
};
int
/* SPDX-License-Identifier: MIT */
#ifndef __NVKM_I2C_PAD_H__
#define __NVKM_I2C_PAD_H__
-#include <subdev/i2c.h>
+#include "priv.h"
struct nvkm_i2c_pad {
const struct nvkm_i2c_pad_func *func;
/* mask on/off interrupt types for a given set of auxch
*/
void (*aux_mask)(struct nvkm_i2c *, u32, u32, u32);
+
+ /* enable/disable HW-initiated DPCD reads
+ */
+ void (*aux_autodpcd)(struct nvkm_i2c *, int aux, bool enable);
};
void g94_aux_stat(struct nvkm_i2c *, u32 *, u32 *, u32 *, u32 *);
* Authors: Ben Skeggs
*/
#include "priv.h"
+#include <subdev/timer.h>
static void
gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0400));
u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0400));
nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x122128 + (i * 0x0400), 0x00000200, 0x00000000);
}
static void
u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0400));
u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0400));
nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x124128 + (i * 0x0400), 0x00000200, 0x00000000);
}
static void
u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0400));
u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0400));
nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x128128 + (i * 0x0400), 0x00000200, 0x00000000);
}
void
intr1 &= ~stat;
}
}
+
+ nvkm_mask(device, 0x121c4c, 0x0000003f, 0x00000002);
+ nvkm_msec(device, 2000,
+ if (!(nvkm_rd32(device, 0x121c4c) & 0x0000003f))
+ break;
+ );
}
static int
* Authors: Ben Skeggs
*/
#include "priv.h"
+#include <subdev/timer.h>
static void
gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0800));
u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0800));
nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x122128 + (i * 0x0800), 0x00000200, 0x00000000);
}
static void
u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0800));
u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0800));
nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x124128 + (i * 0x0800), 0x00000200, 0x00000000);
}
static void
u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0800));
u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0800));
nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x128128 + (i * 0x0800), 0x00000200, 0x00000000);
}
void
intr1 &= ~stat;
}
}
+
+ nvkm_mask(device, 0x12004c, 0x0000003f, 0x00000002);
+ nvkm_msec(device, 2000,
+ if (!(nvkm_rd32(device, 0x12004c) & 0x0000003f))
+ break;
+ );
}
static int
nvkm-y += nvkm/subdev/mc/gp100.o
nvkm-y += nvkm/subdev/mc/gp10b.o
nvkm-y += nvkm/subdev/mc/tu102.o
+nvkm-y += nvkm/subdev/mc/ga100.o
--- /dev/null
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+static void
+ga100_mc_intr_unarm(struct nvkm_mc *mc)
+{
+ nvkm_wr32(mc->subdev.device, 0xb81610, 0x00000004);
+}
+
+static void
+ga100_mc_intr_rearm(struct nvkm_mc *mc)
+{
+ nvkm_wr32(mc->subdev.device, 0xb81608, 0x00000004);
+}
+
+static void
+ga100_mc_intr_mask(struct nvkm_mc *mc, u32 mask, u32 intr)
+{
+ nvkm_wr32(mc->subdev.device, 0xb81210, mask & intr );
+ nvkm_wr32(mc->subdev.device, 0xb81410, mask & ~(mask & intr));
+}
+
+static u32
+ga100_mc_intr_stat(struct nvkm_mc *mc)
+{
+ u32 intr_top = nvkm_rd32(mc->subdev.device, 0xb81600), intr = 0x00000000;
+ if (intr_top & 0x00000004)
+ intr = nvkm_mask(mc->subdev.device, 0xb81010, 0x00000000, 0x00000000);
+ return intr;
+}
+
+static void
+ga100_mc_init(struct nvkm_mc *mc)
+{
+ nv50_mc_init(mc);
+ nvkm_wr32(mc->subdev.device, 0xb81210, 0xffffffff);
+}
+
+static const struct nvkm_mc_func
+ga100_mc = {
+ .init = ga100_mc_init,
+ .intr = gp100_mc_intr,
+ .intr_unarm = ga100_mc_intr_unarm,
+ .intr_rearm = ga100_mc_intr_rearm,
+ .intr_mask = ga100_mc_intr_mask,
+ .intr_stat = ga100_mc_intr_stat,
+ .reset = gk104_mc_reset,
+};
+
+int
+ga100_mc_new(struct nvkm_device *device, int index, struct nvkm_mc **pmc)
+{
+ return nvkm_mc_new_(&ga100_mc, device, index, pmc);
+}
{
struct nvkm_device *device = mmu->subdev.device;
struct nvkm_mm *mm = &device->fb->ram->vram;
- const u32 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
- const u32 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
- const u32 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
+ const u64 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
+ const u64 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
+ const u64 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
u8 type = NVKM_MEM_KIND * !!mmu->func->kind;
u8 heap = NVKM_MEM_VRAM;
int heapM, heapN, heapU;
}
rdev->mman.initialized = true;
- ttm_pool_init(&rdev->mman.bdev.pool, rdev->dev, rdev->need_swiotlb,
- dma_addressing_limited(&rdev->pdev->dev));
-
r = radeon_ttm_init_vram(rdev);
if (r) {
DRM_ERROR("Failed initializing VRAM heap.\n");
static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
-static spinlock_t shrinker_lock;
+static struct mutex shrinker_lock;
static struct list_head shrinker_list;
static struct shrinker mm_shrinker;
size_t size = (1ULL << order) * PAGE_SIZE;
addr = dma_map_page(pool->dev, p, 0, size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(pool->dev, **dma_addr))
+ if (dma_mapping_error(pool->dev, addr))
return -EFAULT;
}
spin_lock_init(&pt->lock);
INIT_LIST_HEAD(&pt->pages);
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
list_add_tail(&pt->shrinker_list, &shrinker_list);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
}
/* Remove a pool_type from the global shrinker list and free all pages */
{
struct page *p, *tmp;
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
list_del(&pt->shrinker_list);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
list_for_each_entry_safe(p, tmp, &pt->pages, lru)
ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
unsigned int num_freed;
struct page *p;
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
p = ttm_pool_type_take(pt);
}
list_move_tail(&pt->shrinker_list, &shrinker_list);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
return num_freed;
}
ttm_pool_type_init(&pool->caching[i].orders[j],
pool, i, j);
}
-EXPORT_SYMBOL(ttm_pool_init);
/**
* ttm_pool_fini - Cleanup a pool
for (j = 0; j < MAX_ORDER; ++j)
ttm_pool_type_fini(&pool->caching[i].orders[j]);
}
-EXPORT_SYMBOL(ttm_pool_fini);
#ifdef CONFIG_DEBUG_FS
/* Count the number of pages available in a pool_type */
{
unsigned int i;
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
seq_puts(m, "\t ");
for (i = 0; i < MAX_ORDER; ++i)
seq_printf(m, "\ntotal\t: %8lu of %8lu\n",
atomic_long_read(&allocated_pages), page_pool_size);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
return 0;
}
if (!page_pool_size)
page_pool_size = num_pages;
- spin_lock_init(&shrinker_lock);
+ mutex_init(&shrinker_lock);
INIT_LIST_HEAD(&shrinker_list);
for (i = 0; i < MAX_ORDER; ++i) {
depends on NEW_LEDS
depends on LEDS_CLASS
select POWER_SUPPLY
+ select CRC32
help
Support for
for (i = 0; i < cl_data->num_hid_devices; i++) {
cl_data->sensor_virt_addr[i] = dma_alloc_coherent(dev, sizeof(int) * 8,
- &cl_data->sensor_phys_addr[i],
+ &cl_data->sensor_dma_addr[i],
GFP_KERNEL);
cl_data->sensor_sts[i] = 0;
cl_data->sensor_requested_cnt[i] = 0;
}
info.period = msecs_to_jiffies(AMD_SFH_IDLE_LOOP);
info.sensor_idx = cl_idx;
- info.phys_address = cl_data->sensor_phys_addr[i];
+ info.dma_address = cl_data->sensor_dma_addr[i];
cl_data->report_descr[i] = kzalloc(cl_data->report_descr_sz[i], GFP_KERNEL);
if (!cl_data->report_descr[i]) {
if (cl_data->sensor_virt_addr[i]) {
dma_free_coherent(&privdata->pdev->dev, 8 * sizeof(int),
cl_data->sensor_virt_addr[i],
- cl_data->sensor_phys_addr[i]);
+ cl_data->sensor_dma_addr[i]);
}
kfree(cl_data->feature_report[i]);
kfree(cl_data->input_report[i]);
if (cl_data->sensor_virt_addr[i]) {
dma_free_coherent(&privdata->pdev->dev, 8 * sizeof(int),
cl_data->sensor_virt_addr[i],
- cl_data->sensor_phys_addr[i]);
+ cl_data->sensor_dma_addr[i]);
}
}
kfree(cl_data);
int hid_descr_size[MAX_HID_DEVICES];
phys_addr_t phys_addr_base;
u32 *sensor_virt_addr[MAX_HID_DEVICES];
- phys_addr_t sensor_phys_addr[MAX_HID_DEVICES];
+ dma_addr_t sensor_dma_addr[MAX_HID_DEVICES];
u32 sensor_sts[MAX_HID_DEVICES];
u32 sensor_requested_cnt[MAX_HID_DEVICES];
u8 report_type[MAX_HID_DEVICES];
cmd_param.s.buf_layout = 1;
cmd_param.s.buf_length = 16;
- writeq(info.phys_address, privdata->mmio + AMD_C2P_MSG2);
+ writeq(info.dma_address, privdata->mmio + AMD_C2P_MSG2);
writel(cmd_param.ul, privdata->mmio + AMD_C2P_MSG1);
writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0);
}
struct amd_mp2_sensor_info {
u8 sensor_idx;
u32 period;
- phys_addr_t phys_address;
+ dma_addr_t dma_address;
};
void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info);
#define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401
#define USB_DEVICE_ID_HP_X2 0x074d
#define USB_DEVICE_ID_HP_X2_10_COVER 0x0755
+#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706
#define USB_VENDOR_ID_ELECOM 0x056e
#define USB_DEVICE_ID_ELECOM_BM084 0x0061
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD),
HID_BATTERY_QUIRK_IGNORE },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN),
+ HID_BATTERY_QUIRK_IGNORE },
{}
};
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
0xc531),
.driver_data = recvr_type_gaming_hidpp},
+ { /* Logitech G602 receiver (0xc537) */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
+ 0xc537),
+ .driver_data = recvr_type_gaming_hidpp},
{ /* Logitech lightspeed receiver (0xc539) */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1),
{ /* MX Master mouse over Bluetooth */
HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb012),
.driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
+ { /* MX Ergo trackball over Bluetooth */
+ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01d) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01e),
.driver_data = HIDPP_QUIRK_HI_RES_SCROLL_X2121 },
{ /* MX Master 3 mouse over Bluetooth */
HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
USB_VENDOR_ID_SYNAPTICS, 0xce08) },
+ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+ HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+ USB_VENDOR_ID_SYNAPTICS, 0xce09) },
+
/* TopSeed panels */
{ .driver_data = MT_CLS_TOPSEED,
MT_USB_DEVICE(USB_VENDOR_ID_TOPSEED2,
goto cleanup;
} else if (rc < 0) {
hid_err(hdev,
- "failed retrieving string descriptor #%hhu: %d\n",
+ "failed retrieving string descriptor #%u: %d\n",
idx, rc);
goto cleanup;
}
wdata->state.cmd_err = err;
wiimote_cmd_complete(wdata);
} else if (err) {
- hid_warn(wdata->hdev, "Remote error %hhu on req %hhu\n", err,
+ hid_warn(wdata->hdev, "Remote error %u on req %u\n", err,
cmd);
}
}
group);
}
+static void wacom_devm_kfifo_release(struct device *dev, void *res)
+{
+ struct kfifo_rec_ptr_2 *devres = res;
+
+ kfifo_free(devres);
+}
+
+static int wacom_devm_kfifo_alloc(struct wacom *wacom)
+{
+ struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+ struct kfifo_rec_ptr_2 *pen_fifo = &wacom_wac->pen_fifo;
+ int error;
+
+ pen_fifo = devres_alloc(wacom_devm_kfifo_release,
+ sizeof(struct kfifo_rec_ptr_2),
+ GFP_KERNEL);
+
+ if (!pen_fifo)
+ return -ENOMEM;
+
+ error = kfifo_alloc(pen_fifo, WACOM_PKGLEN_MAX, GFP_KERNEL);
+ if (error) {
+ devres_free(pen_fifo);
+ return error;
+ }
+
+ devres_add(&wacom->hdev->dev, pen_fifo);
+
+ return 0;
+}
+
enum led_brightness wacom_leds_brightness_get(struct wacom_led *led)
{
struct wacom *wacom = led->wacom;
if (features->check_for_hid_type && features->hid_type != hdev->type)
return -ENODEV;
- error = kfifo_alloc(&wacom_wac->pen_fifo, WACOM_PKGLEN_MAX, GFP_KERNEL);
+ error = wacom_devm_kfifo_alloc(wacom);
if (error)
return error;
if (wacom->wacom_wac.features.type != REMOTE)
wacom_release_resources(wacom);
-
- kfifo_free(&wacom_wac->pen_fifo);
}
#ifdef CONFIG_PM
/* Make sure conn_state is set as hv_synic_cleanup checks for it */
mb();
cpuhp_remove_state(hyperv_cpuhp_online);
- hyperv_cleanup();
};
static void hv_crash_handler(struct pt_regs *regs)
cpu = smp_processor_id();
hv_stimer_cleanup(cpu);
hv_synic_disable_regs(cpu);
- hyperv_cleanup();
};
static int hv_synic_suspend(void)
*/
cpus = num_present_cpus() / num_siblings;
- s_config = devm_kcalloc(dev, cpus + sockets,
+ s_config = devm_kcalloc(dev, cpus + sockets + 1,
sizeof(u32), GFP_KERNEL);
if (!s_config)
return -ENOMEM;
scnprintf(label_l[i], 10, "Esocket%u", (i - cpus));
}
+ s_config[i] = 0;
return 0;
}
ctx->pwm_value = MAX_PWM;
- /* Set duty cycle to maximum allowed and enable PWM output */
pwm_init_state(ctx->pwm, &state);
+ /*
+ * __set_pwm assumes that MAX_PWM * (period - 1) fits into an unsigned
+ * long. Check this here to prevent the fan running at a too low
+ * frequency.
+ */
+ if (state.period > ULONG_MAX / MAX_PWM + 1) {
+ dev_err(dev, "Configured period too big\n");
+ return -EINVAL;
+ }
+
+ /* Set duty cycle to maximum allowed and enable PWM output */
state.duty_cycle = ctx->pwm->args.period - 1;
state.enabled = true;
/* Register GPIO descriptor lookup table */
lookup = devm_kzalloc(dev,
- struct_size(lookup, table, mux_config->n_gpios),
+ struct_size(lookup, table, mux_config->n_gpios + 1),
GFP_KERNEL);
if (!lookup)
return -ENOMEM;
#define I2C_IO_CONFIG_OPEN_DRAIN 0x0003
#define I2C_IO_CONFIG_PUSH_PULL 0x0000
#define I2C_SOFT_RST 0x0001
+#define I2C_HANDSHAKE_RST 0x0020
#define I2C_FIFO_ADDR_CLR 0x0001
#define I2C_DELAY_LEN 0x0002
#define I2C_TIME_CLR_VALUE 0x0000
#define I2C_WRRD_TRANAC_VALUE 0x0002
#define I2C_RD_TRANAC_VALUE 0x0001
#define I2C_SCL_MIS_COMP_VALUE 0x0000
+#define I2C_CHN_CLR_FLAG 0x0000
#define I2C_DMA_CON_TX 0x0000
#define I2C_DMA_CON_RX 0x0001
#define I2C_DMA_START_EN 0x0001
#define I2C_DMA_INT_FLAG_NONE 0x0000
#define I2C_DMA_CLR_FLAG 0x0000
+#define I2C_DMA_WARM_RST 0x0001
#define I2C_DMA_HARD_RST 0x0002
+#define I2C_DMA_HANDSHAKE_RST 0x0004
#define MAX_SAMPLE_CNT_DIV 8
#define MAX_STEP_CNT_DIV 64
{
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);
+ if (i2c->dev_comp->dma_sync) {
+ writel(I2C_DMA_WARM_RST, i2c->pdmabase + OFFSET_RST);
+ udelay(10);
+ writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+ udelay(10);
+ writel(I2C_DMA_HANDSHAKE_RST | I2C_DMA_HARD_RST,
+ i2c->pdmabase + OFFSET_RST);
+ mtk_i2c_writew(i2c, I2C_HANDSHAKE_RST | I2C_SOFT_RST,
+ OFFSET_SOFTRESET);
+ udelay(10);
+ writel(I2C_DMA_CLR_FLAG, i2c->pdmabase + OFFSET_RST);
+ mtk_i2c_writew(i2c, I2C_CHN_CLR_FLAG, OFFSET_SOFTRESET);
+ } else {
+ 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 */
if (i2c->use_push_pull)
/* timeout (ms) for pm runtime autosuspend */
#define SPRD_I2C_PM_TIMEOUT 1000
+/* timeout (ms) for transfer message */
+#define I2C_XFER_TIMEOUT 1000
/* SPRD i2c data structure */
struct sprd_i2c {
struct i2c_msg *msg, bool is_last_msg)
{
struct sprd_i2c *i2c_dev = i2c_adap->algo_data;
+ unsigned long time_left;
i2c_dev->msg = msg;
i2c_dev->buf = msg->buf;
sprd_i2c_opt_start(i2c_dev);
- wait_for_completion(&i2c_dev->complete);
+ time_left = wait_for_completion_timeout(&i2c_dev->complete,
+ msecs_to_jiffies(I2C_XFER_TIMEOUT));
+ if (!time_left)
+ return -ETIMEDOUT;
return i2c_dev->err;
}
sense_rq->rq_disk = rq->rq_disk;
sense_rq->cmd_flags = REQ_OP_DRV_IN;
ide_req(sense_rq)->type = ATA_PRIV_SENSE;
- sense_rq->rq_flags |= RQF_PREEMPT;
req->cmd[0] = GPCMD_REQUEST_SENSE;
req->cmd[4] = cmd_len;
* above to return us whatever is in the queue. Since we call
* ide_do_request() ourselves, we end up taking requests while
* the queue is blocked...
- *
- * We let requests forced at head of queue with ide-preempt
- * though. I hope that doesn't happen too much, hopefully not
- * unless the subdriver triggers such a thing in its own PM
- * state machine.
*/
if ((drive->dev_flags & IDE_DFLAG_BLOCKED) &&
ata_pm_request(rq) == 0 &&
- (rq->rq_flags & RQF_PREEMPT) == 0) {
+ (rq->rq_flags & RQF_PM) == 0) {
/* there should be no pending command at this point */
ide_unlock_port(hwif);
goto plug_device;
}
memset(&rqpm, 0, sizeof(rqpm));
- rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PREEMPT);
+ rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PM);
ide_req(rq)->type = ATA_PRIV_PM_RESUME;
ide_req(rq)->special = &rqpm;
rqpm.pm_step = IDE_PM_START_RESUME;
.enter = NULL }
};
+/*
+ * Note, depending on HW and FW revision, SnowRidge SoC may or may not support
+ * C6, and this is indicated in the CPUID mwait leaf.
+ */
+static struct cpuidle_state snr_cstates[] __initdata = {
+ {
+ .name = "C1",
+ .desc = "MWAIT 0x00",
+ .flags = MWAIT2flg(0x00),
+ .exit_latency = 2,
+ .target_residency = 2,
+ .enter = &intel_idle,
+ .enter_s2idle = intel_idle_s2idle, },
+ {
+ .name = "C1E",
+ .desc = "MWAIT 0x01",
+ .flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
+ .exit_latency = 15,
+ .target_residency = 25,
+ .enter = &intel_idle,
+ .enter_s2idle = intel_idle_s2idle, },
+ {
+ .name = "C6",
+ .desc = "MWAIT 0x20",
+ .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
+ .exit_latency = 130,
+ .target_residency = 500,
+ .enter = &intel_idle,
+ .enter_s2idle = intel_idle_s2idle, },
+ {
+ .enter = NULL }
+};
+
static const struct idle_cpu idle_cpu_nehalem __initconst = {
.state_table = nehalem_cstates,
.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
.use_acpi = true,
};
+static const struct idle_cpu idle_cpu_snr __initconst = {
+ .state_table = snr_cstates,
+ .disable_promotion_to_c1e = true,
+ .use_acpi = true,
+};
+
static const struct x86_cpu_id intel_idle_ids[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP, &idle_cpu_nhx),
X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &idle_cpu_nehalem),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &idle_cpu_bxt),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &idle_cpu_bxt),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &idle_cpu_dnv),
- X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &idle_cpu_dnv),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &idle_cpu_snr),
{}
};
return ret;
gid_type = ib_cache_gid_parse_type_str(buf);
- if (gid_type < 0)
+ if (gid_type < 0) {
+ cma_configfs_params_put(cma_dev);
return -EINVAL;
+ }
ret = cma_set_default_gid_type(cma_dev, group->port_num, gid_type);
} else {
ret = xa_alloc_cyclic(&rt->xa, &res->id, res, xa_limit_32b,
&rt->next_id, GFP_KERNEL);
+ ret = (ret < 0) ? ret : 0;
}
out:
u64 uid;
struct list_head list;
- /* sync between removal event and id destroy, protected by file mut */
- int destroying;
struct work_struct close_work;
};
static DEFINE_XARRAY_ALLOC(multicast_table);
static const struct file_operations ucma_fops;
-static int __destroy_id(struct ucma_context *ctx);
+static int ucma_destroy_private_ctx(struct ucma_context *ctx);
static inline struct ucma_context *_ucma_find_context(int id,
struct ucma_file *file)
/* once all inflight tasks are finished, we close all underlying
* resources. The context is still alive till its explicit destryoing
- * by its creator.
+ * by its creator. This puts back the xarray's reference.
*/
ucma_put_ctx(ctx);
wait_for_completion(&ctx->comp);
/* No new events will be generated after destroying the id. */
rdma_destroy_id(ctx->cm_id);
- /*
- * At this point ctx->ref is zero so the only place the ctx can be is in
- * a uevent or in __destroy_id(). Since the former doesn't touch
- * ctx->cm_id and the latter sync cancels this, there is no races with
- * this store.
- */
+ /* Reading the cm_id without holding a positive ref is not allowed */
ctx->cm_id = NULL;
}
return NULL;
INIT_WORK(&ctx->close_work, ucma_close_id);
- refcount_set(&ctx->ref, 1);
init_completion(&ctx->comp);
/* So list_del() will work if we don't do ucma_finish_ctx() */
INIT_LIST_HEAD(&ctx->list);
return ctx;
}
+static void ucma_set_ctx_cm_id(struct ucma_context *ctx,
+ struct rdma_cm_id *cm_id)
+{
+ refcount_set(&ctx->ref, 1);
+ ctx->cm_id = cm_id;
+}
+
static void ucma_finish_ctx(struct ucma_context *ctx)
{
lockdep_assert_held(&ctx->file->mut);
ctx = ucma_alloc_ctx(listen_ctx->file);
if (!ctx)
goto err_backlog;
- ctx->cm_id = cm_id;
+ ucma_set_ctx_cm_id(ctx, cm_id);
uevent = ucma_create_uevent(listen_ctx, event);
if (!uevent)
return 0;
err_alloc:
- xa_erase(&ctx_table, ctx->id);
- kfree(ctx);
+ ucma_destroy_private_ctx(ctx);
err_backlog:
atomic_inc(&listen_ctx->backlog);
/* Returning error causes the new ID to be destroyed */
wake_up_interruptible(&ctx->file->poll_wait);
}
- if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL && !ctx->destroying)
- queue_work(system_unbound_wq, &ctx->close_work);
+ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) {
+ xa_lock(&ctx_table);
+ if (xa_load(&ctx_table, ctx->id) == ctx)
+ queue_work(system_unbound_wq, &ctx->close_work);
+ xa_unlock(&ctx_table);
+ }
return 0;
}
ret = PTR_ERR(cm_id);
goto err1;
}
- ctx->cm_id = cm_id;
+ ucma_set_ctx_cm_id(ctx, cm_id);
resp.id = ctx->id;
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp))) {
- xa_erase(&ctx_table, ctx->id);
- __destroy_id(ctx);
+ ucma_destroy_private_ctx(ctx);
return -EFAULT;
}
return 0;
err1:
- xa_erase(&ctx_table, ctx->id);
- kfree(ctx);
+ ucma_destroy_private_ctx(ctx);
return ret;
}
rdma_unlock_handler(mc->ctx->cm_id);
}
-/*
- * ucma_free_ctx is called after the underlying rdma CM-ID is destroyed. At
- * this point, no new events will be reported from the hardware. However, we
- * still need to cleanup the UCMA context for this ID. Specifically, there
- * might be events that have not yet been consumed by the user space software.
- * mutex. After that we release them as needed.
- */
-static int ucma_free_ctx(struct ucma_context *ctx)
+static int ucma_cleanup_ctx_events(struct ucma_context *ctx)
{
int events_reported;
struct ucma_event *uevent, *tmp;
LIST_HEAD(list);
- ucma_cleanup_multicast(ctx);
-
- /* Cleanup events not yet reported to the user. */
+ /* Cleanup events not yet reported to the user.*/
mutex_lock(&ctx->file->mut);
list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) {
- if (uevent->ctx == ctx || uevent->conn_req_ctx == ctx)
+ if (uevent->ctx != ctx)
+ continue;
+
+ if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST &&
+ xa_cmpxchg(&ctx_table, uevent->conn_req_ctx->id,
+ uevent->conn_req_ctx, XA_ZERO_ENTRY,
+ GFP_KERNEL) == uevent->conn_req_ctx) {
list_move_tail(&uevent->list, &list);
+ continue;
+ }
+ list_del(&uevent->list);
+ kfree(uevent);
}
list_del(&ctx->list);
events_reported = ctx->events_reported;
mutex_unlock(&ctx->file->mut);
/*
- * If this was a listening ID then any connections spawned from it
- * that have not been delivered to userspace are cleaned up too.
- * Must be done outside any locks.
+ * If this was a listening ID then any connections spawned from it that
+ * have not been delivered to userspace are cleaned up too. Must be done
+ * outside any locks.
*/
list_for_each_entry_safe(uevent, tmp, &list, list) {
- list_del(&uevent->list);
- if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST &&
- uevent->conn_req_ctx != ctx)
- __destroy_id(uevent->conn_req_ctx);
+ ucma_destroy_private_ctx(uevent->conn_req_ctx);
kfree(uevent);
}
-
- mutex_destroy(&ctx->mutex);
- kfree(ctx);
return events_reported;
}
-static int __destroy_id(struct ucma_context *ctx)
+/*
+ * When this is called the xarray must have a XA_ZERO_ENTRY in the ctx->id (ie
+ * the ctx is not public to the user). This either because:
+ * - ucma_finish_ctx() hasn't been called
+ * - xa_cmpxchg() succeed to remove the entry (only one thread can succeed)
+ */
+static int ucma_destroy_private_ctx(struct ucma_context *ctx)
{
+ int events_reported;
+
/*
- * If the refcount is already 0 then ucma_close_id() has already
- * destroyed the cm_id, otherwise holding the refcount keeps cm_id
- * valid. Prevent queue_work() from being called.
+ * Destroy the underlying cm_id. New work queuing is prevented now by
+ * the removal from the xarray. Once the work is cancled ref will either
+ * be 0 because the work ran to completion and consumed the ref from the
+ * xarray, or it will be positive because we still have the ref from the
+ * xarray. This can also be 0 in cases where cm_id was never set
*/
- if (refcount_inc_not_zero(&ctx->ref)) {
- rdma_lock_handler(ctx->cm_id);
- ctx->destroying = 1;
- rdma_unlock_handler(ctx->cm_id);
- ucma_put_ctx(ctx);
- }
-
cancel_work_sync(&ctx->close_work);
- /* At this point it's guaranteed that there is no inflight closing task */
- if (ctx->cm_id)
+ if (refcount_read(&ctx->ref))
ucma_close_id(&ctx->close_work);
- return ucma_free_ctx(ctx);
+
+ events_reported = ucma_cleanup_ctx_events(ctx);
+ ucma_cleanup_multicast(ctx);
+
+ WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, XA_ZERO_ENTRY, NULL,
+ GFP_KERNEL) != NULL);
+ mutex_destroy(&ctx->mutex);
+ kfree(ctx);
+ return events_reported;
}
static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
xa_lock(&ctx_table);
ctx = _ucma_find_context(cmd.id, file);
- if (!IS_ERR(ctx))
- __xa_erase(&ctx_table, ctx->id);
+ if (!IS_ERR(ctx)) {
+ if (__xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY,
+ GFP_KERNEL) != ctx)
+ ctx = ERR_PTR(-ENOENT);
+ }
xa_unlock(&ctx_table);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- resp.events_reported = __destroy_id(ctx);
+ resp.events_reported = ucma_destroy_private_ctx(ctx);
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp)))
ret = -EFAULT;
* prevented by this being a FD release function. The list_add_tail() in
* ucma_connect_event_handler() can run concurrently, however it only
* adds to the list *after* a listening ID. By only reading the first of
- * the list, and relying on __destroy_id() to block
+ * the list, and relying on ucma_destroy_private_ctx() to block
* ucma_connect_event_handler(), no additional locking is needed.
*/
while (!list_empty(&file->ctx_list)) {
struct ucma_context *ctx = list_first_entry(
&file->ctx_list, struct ucma_context, list);
- xa_erase(&ctx_table, ctx->id);
- __destroy_id(ctx);
+ WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY,
+ GFP_KERNEL) != ctx);
+ ucma_destroy_private_ctx(ctx);
}
kfree(file);
return 0;
*/
if (mask)
pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0);
- return rounddown_pow_of_two(pgsz_bitmap);
+ return pgsz_bitmap ? rounddown_pow_of_two(pgsz_bitmap) : 0;
}
EXPORT_SYMBOL(ib_umem_find_best_pgsz);
err = set_has_smi_cap(dev);
if (err)
- return err;
+ goto err_mp;
if (!mlx5_core_mp_enabled(mdev)) {
for (i = 1; i <= dev->num_ports; i++) {
err = mlx5_alloc_bfreg(dev->mdev, &dev->fp_bfreg, false, true);
if (err)
- mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+ mlx5_free_bfreg(dev->mdev, &dev->bfreg);
return err;
}
pr_err("%s(%d) Freeing in use pdid=0x%x.\n",
__func__, dev->id, pd->id);
}
- kfree(uctx->cntxt_pd);
uctx->cntxt_pd = NULL;
_ocrdma_dealloc_pd(dev, pd);
+ kfree(pd);
}
static struct ocrdma_pd *ocrdma_get_ucontext_pd(struct ocrdma_ucontext *uctx)
}
usnic_uiom_free_dev_list(dev_list);
+ dev_list = NULL;
}
/* Try to find resources on an unused vf */
qp_grp_check:
if (IS_ERR_OR_NULL(qp_grp)) {
usnic_err("Failed to allocate qp_grp\n");
+ if (usnic_ib_share_vf)
+ usnic_uiom_free_dev_list(dev_list);
return ERR_PTR(qp_grp ? PTR_ERR(qp_grp) : -ENOMEM);
}
return qp_grp;
return -ENODEV;
}
/* Allow scaling to be disabled on a per-node basis */
- if (!dn || !of_device_is_available(dn)) {
+ if (!of_device_is_available(dn)) {
dev_warn(dev, "Missing property %s, skip scaling %s\n",
adj->phandle_name, node->name);
+ of_node_put(dn);
return 0;
}
#include <linux/module.h>
#include <linux/platform_device.h>
+#include <linux/interconnect-provider.h>
#include <dt-bindings/interconnect/imx8mq.h>
#include "imx.h"
.remove = imx8mq_icc_remove,
.driver = {
.name = "imx8mq-interconnect",
+ .sync_state = icc_sync_state,
},
};
This is a driver for the Qualcomm Network-on-Chip on qcs404-based
platforms.
+config INTERCONNECT_QCOM_RPMH_POSSIBLE
+ tristate
+ default INTERCONNECT_QCOM
+ depends on QCOM_RPMH || (COMPILE_TEST && !QCOM_RPMH)
+ depends on QCOM_COMMAND_DB || (COMPILE_TEST && !QCOM_COMMAND_DB)
+ depends on OF || COMPILE_TEST
+ help
+ Compile-testing RPMH drivers is possible on other platforms,
+ but in order to avoid link failures, drivers must not be built-in
+ when QCOM_RPMH or QCOM_COMMAND_DB are loadable modules
+
config INTERCONNECT_QCOM_RPMH
tristate
config INTERCONNECT_QCOM_SC7180
tristate "Qualcomm SC7180 interconnect driver"
- depends on INTERCONNECT_QCOM
- depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+ depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
select INTERCONNECT_QCOM_RPMH
select INTERCONNECT_QCOM_BCM_VOTER
help
config INTERCONNECT_QCOM_SDM845
tristate "Qualcomm SDM845 interconnect driver"
- depends on INTERCONNECT_QCOM
- depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+ depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
select INTERCONNECT_QCOM_RPMH
select INTERCONNECT_QCOM_BCM_VOTER
help
config INTERCONNECT_QCOM_SM8150
tristate "Qualcomm SM8150 interconnect driver"
- depends on INTERCONNECT_QCOM
- depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+ depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
select INTERCONNECT_QCOM_RPMH
select INTERCONNECT_QCOM_BCM_VOTER
help
config INTERCONNECT_QCOM_SM8250
tristate "Qualcomm SM8250 interconnect driver"
- depends on INTERCONNECT_QCOM
- depends on (QCOM_RPMH && QCOM_COMMAND_DB && OF) || COMPILE_TEST
+ depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
select INTERCONNECT_QCOM_RPMH
select INTERCONNECT_QCOM_BCM_VOTER
help
return r;
}
- iommu->int_enabled = true;
-
return 0;
}
if (ret)
return ret;
+ iommu->int_enabled = true;
enable_faults:
iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
struct amd_iommu *iommu;
int devid = -1;
+ if (!amd_iommu_irq_remap)
+ return 0;
+
if (x86_fwspec_is_ioapic(fwspec))
devid = get_ioapic_devid(fwspec->param[0]);
else if (x86_fwspec_is_hpet(fwspec))
set_bit(qsmmu->bypass_cbndx, smmu->context_map);
+ arm_smmu_cb_write(smmu, qsmmu->bypass_cbndx, ARM_SMMU_CB_SCTLR, 0);
+
reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, CBAR_TYPE_S1_TRANS_S2_BYPASS);
arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(qsmmu->bypass_cbndx), reg);
}
}
static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
+ { .compatible = "qcom,msm8998-smmu-v2" },
{ .compatible = "qcom,sc7180-smmu-500" },
+ { .compatible = "qcom,sdm630-smmu-v2" },
{ .compatible = "qcom,sdm845-smmu-500" },
{ .compatible = "qcom,sm8150-smmu-500" },
{ .compatible = "qcom,sm8250-smmu-500" },
unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
int i, count = 0;
- /*
- * The Intel graphic driver is used to assume that the returned
- * sg list is not combound. This blocks the efforts of converting
- * Intel IOMMU driver to dma-iommu api's. Add this quirk to make the
- * device driver work and should be removed once it's fixed in i915
- * driver.
- */
- if (IS_ENABLED(CONFIG_DRM_I915) && dev_is_pci(dev) &&
- to_pci_dev(dev)->vendor == PCI_VENDOR_ID_INTEL &&
- (to_pci_dev(dev)->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
- for_each_sg(sg, s, nents, i) {
- unsigned int s_iova_off = sg_dma_address(s);
- unsigned int s_length = sg_dma_len(s);
- unsigned int s_iova_len = s->length;
-
- s->offset += s_iova_off;
- s->length = s_length;
- sg_dma_address(s) = dma_addr + s_iova_off;
- sg_dma_len(s) = s_length;
- dma_addr += s_iova_len;
-
- pr_info_once("sg combining disabled due to i915 driver\n");
- }
-
- return nents;
- }
-
for_each_sg(sg, s, nents, i) {
/* Restore this segment's original unaligned fields first */
unsigned int s_iova_off = sg_dma_address(s);
int mask = ilog2(__roundup_pow_of_two(npages));
unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
- if (WARN_ON_ONCE(!ALIGN(addr, align)))
- addr &= ~(align - 1);
+ if (WARN_ON_ONCE(!IS_ALIGNED(addr, align)))
+ addr = ALIGN_DOWN(addr, align);
desc.qw0 = QI_EIOTLB_PASID(pasid) |
QI_EIOTLB_DID(did) |
#include <linux/dmi.h>
#include <linux/pci-ats.h>
#include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
#include <linux/dma-direct.h>
#include <linux/crash_dump.h>
#include <linux/numa.h>
return nid;
}
+static void domain_update_iotlb(struct dmar_domain *domain);
+
/* Some capabilities may be different across iommus */
static void domain_update_iommu_cap(struct dmar_domain *domain)
{
domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
else
domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
+
+ domain_update_iotlb(domain);
}
struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
assert_spin_locked(&device_domain_lock);
- list_for_each_entry(info, &domain->devices, link) {
- struct pci_dev *pdev;
-
- if (!info->dev || !dev_is_pci(info->dev))
- continue;
-
- pdev = to_pci_dev(info->dev);
- if (pdev->ats_enabled) {
+ list_for_each_entry(info, &domain->devices, link)
+ if (info->ats_enabled) {
has_iotlb_device = true;
break;
}
+
+ if (!has_iotlb_device) {
+ struct subdev_domain_info *sinfo;
+
+ list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+ info = get_domain_info(sinfo->pdev);
+ if (info && info->ats_enabled) {
+ has_iotlb_device = true;
+ break;
+ }
+ }
}
domain->has_iotlb_device = has_iotlb_device;
#endif
}
+static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
+ u64 addr, unsigned int mask)
+{
+ u16 sid, qdep;
+
+ if (!info || !info->ats_enabled)
+ return;
+
+ sid = info->bus << 8 | info->devfn;
+ qdep = info->ats_qdep;
+ qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+ qdep, addr, mask);
+}
+
static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
u64 addr, unsigned mask)
{
- u16 sid, qdep;
unsigned long flags;
struct device_domain_info *info;
+ struct subdev_domain_info *sinfo;
if (!domain->has_iotlb_device)
return;
spin_lock_irqsave(&device_domain_lock, flags);
- list_for_each_entry(info, &domain->devices, link) {
- if (!info->ats_enabled)
- continue;
+ list_for_each_entry(info, &domain->devices, link)
+ __iommu_flush_dev_iotlb(info, addr, mask);
- sid = info->bus << 8 | info->devfn;
- qdep = info->ats_qdep;
- qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
- qdep, addr, mask);
+ list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+ info = get_domain_info(sinfo->pdev);
+ __iommu_flush_dev_iotlb(info, addr, mask);
}
spin_unlock_irqrestore(&device_domain_lock, flags);
}
domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
domain->has_iotlb_device = false;
INIT_LIST_HEAD(&domain->devices);
+ INIT_LIST_HEAD(&domain->subdevices);
return domain;
}
info->iommu = iommu;
info->pasid_table = NULL;
info->auxd_enabled = 0;
- INIT_LIST_HEAD(&info->auxiliary_domains);
+ INIT_LIST_HEAD(&info->subdevices);
if (dev && dev_is_pci(dev)) {
struct pci_dev *pdev = to_pci_dev(info->dev);
domain->type == IOMMU_DOMAIN_UNMANAGED;
}
-static void auxiliary_link_device(struct dmar_domain *domain,
- struct device *dev)
+static inline struct subdev_domain_info *
+lookup_subdev_info(struct dmar_domain *domain, struct device *dev)
+{
+ struct subdev_domain_info *sinfo;
+
+ if (!list_empty(&domain->subdevices)) {
+ list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+ if (sinfo->pdev == dev)
+ return sinfo;
+ }
+ }
+
+ return NULL;
+}
+
+static int auxiliary_link_device(struct dmar_domain *domain,
+ struct device *dev)
{
struct device_domain_info *info = get_domain_info(dev);
+ struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
assert_spin_locked(&device_domain_lock);
if (WARN_ON(!info))
- return;
+ return -EINVAL;
- domain->auxd_refcnt++;
- list_add(&domain->auxd, &info->auxiliary_domains);
+ if (!sinfo) {
+ sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC);
+ sinfo->domain = domain;
+ sinfo->pdev = dev;
+ list_add(&sinfo->link_phys, &info->subdevices);
+ list_add(&sinfo->link_domain, &domain->subdevices);
+ }
+
+ return ++sinfo->users;
}
-static void auxiliary_unlink_device(struct dmar_domain *domain,
- struct device *dev)
+static int auxiliary_unlink_device(struct dmar_domain *domain,
+ struct device *dev)
{
struct device_domain_info *info = get_domain_info(dev);
+ struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
+ int ret;
assert_spin_locked(&device_domain_lock);
- if (WARN_ON(!info))
- return;
+ if (WARN_ON(!info || !sinfo || sinfo->users <= 0))
+ return -EINVAL;
- list_del(&domain->auxd);
- domain->auxd_refcnt--;
+ ret = --sinfo->users;
+ if (!ret) {
+ list_del(&sinfo->link_phys);
+ list_del(&sinfo->link_domain);
+ kfree(sinfo);
+ }
- if (!domain->auxd_refcnt && domain->default_pasid > 0)
- ioasid_put(domain->default_pasid);
+ return ret;
}
static int aux_domain_add_dev(struct dmar_domain *domain,
}
spin_lock_irqsave(&device_domain_lock, flags);
+ ret = auxiliary_link_device(domain, dev);
+ if (ret <= 0)
+ goto link_failed;
+
+ /*
+ * Subdevices from the same physical device can be attached to the
+ * same domain. For such cases, only the first subdevice attachment
+ * needs to go through the full steps in this function. So if ret >
+ * 1, just goto out.
+ */
+ if (ret > 1)
+ goto out;
+
/*
* iommu->lock must be held to attach domain to iommu and setup the
* pasid entry for second level translation.
domain->default_pasid);
if (ret)
goto table_failed;
- spin_unlock(&iommu->lock);
-
- auxiliary_link_device(domain, dev);
+ spin_unlock(&iommu->lock);
+out:
spin_unlock_irqrestore(&device_domain_lock, flags);
return 0;
domain_detach_iommu(domain, iommu);
attach_failed:
spin_unlock(&iommu->lock);
+ auxiliary_unlink_device(domain, dev);
+link_failed:
spin_unlock_irqrestore(&device_domain_lock, flags);
- if (!domain->auxd_refcnt && domain->default_pasid > 0)
+ if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
ioasid_put(domain->default_pasid);
return ret;
info = get_domain_info(dev);
iommu = info->iommu;
- auxiliary_unlink_device(domain, dev);
-
- spin_lock(&iommu->lock);
- intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false);
- domain_detach_iommu(domain, iommu);
- spin_unlock(&iommu->lock);
+ if (!auxiliary_unlink_device(domain, dev)) {
+ spin_lock(&iommu->lock);
+ intel_pasid_tear_down_entry(iommu, dev,
+ domain->default_pasid, false);
+ domain_detach_iommu(domain, iommu);
+ spin_unlock(&iommu->lock);
+ }
spin_unlock_irqrestore(&device_domain_lock, flags);
+
+ if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
+ ioasid_put(domain->default_pasid);
}
static int prepare_domain_attach_device(struct iommu_domain *domain,
irq_data = irq_domain_get_irq_data(domain, virq + i);
irq_cfg = irqd_cfg(irq_data);
if (!irq_data || !irq_cfg) {
+ if (!i)
+ kfree(data);
ret = -EINVAL;
goto out_free_data;
}
iommu->flags |= VTD_FLAG_SVM_CAPABLE;
}
-static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
- unsigned long address, unsigned long pages, int ih)
+static void __flush_svm_range_dev(struct intel_svm *svm,
+ struct intel_svm_dev *sdev,
+ unsigned long address,
+ unsigned long pages, int ih)
{
struct qi_desc desc;
}
desc.qw2 = 0;
desc.qw3 = 0;
- qi_submit_sync(svm->iommu, &desc, 1, 0);
+ qi_submit_sync(sdev->iommu, &desc, 1, 0);
if (sdev->dev_iotlb) {
desc.qw0 = QI_DEV_EIOTLB_PASID(svm->pasid) |
}
desc.qw2 = 0;
desc.qw3 = 0;
- qi_submit_sync(svm->iommu, &desc, 1, 0);
+ qi_submit_sync(sdev->iommu, &desc, 1, 0);
+ }
+}
+
+static void intel_flush_svm_range_dev(struct intel_svm *svm,
+ struct intel_svm_dev *sdev,
+ unsigned long address,
+ unsigned long pages, int ih)
+{
+ unsigned long shift = ilog2(__roundup_pow_of_two(pages));
+ unsigned long align = (1ULL << (VTD_PAGE_SHIFT + shift));
+ unsigned long start = ALIGN_DOWN(address, align);
+ unsigned long end = ALIGN(address + (pages << VTD_PAGE_SHIFT), align);
+
+ while (start < end) {
+ __flush_svm_range_dev(svm, sdev, start, align >> VTD_PAGE_SHIFT, ih);
+ start += align;
}
}
*/
rcu_read_lock();
list_for_each_entry_rcu(sdev, &svm->devs, list)
- intel_pasid_tear_down_entry(svm->iommu, sdev->dev,
+ intel_pasid_tear_down_entry(sdev->iommu, sdev->dev,
svm->pasid, true);
rcu_read_unlock();
struct dmar_domain *dmar_domain;
struct device_domain_info *info;
struct intel_svm *svm = NULL;
+ unsigned long iflags;
int ret = 0;
if (WARN_ON(!iommu) || !data)
}
sdev->dev = dev;
sdev->sid = PCI_DEVID(info->bus, info->devfn);
+ sdev->iommu = iommu;
/* Only count users if device has aux domains */
if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
* each bind of a new device even with an existing PASID, we need to
* call the nested mode setup function here.
*/
- spin_lock(&iommu->lock);
+ spin_lock_irqsave(&iommu->lock, iflags);
ret = intel_pasid_setup_nested(iommu, dev,
(pgd_t *)(uintptr_t)data->gpgd,
data->hpasid, &data->vendor.vtd, dmar_domain,
data->addr_width);
- spin_unlock(&iommu->lock);
+ spin_unlock_irqrestore(&iommu->lock, iflags);
if (ret) {
dev_err_ratelimited(dev, "Failed to set up PASID %llu in nested mode, Err %d\n",
data->hpasid, ret);
struct device_domain_info *info;
struct intel_svm_dev *sdev;
struct intel_svm *svm = NULL;
+ unsigned long iflags;
int pasid_max;
int ret;
goto out;
}
sdev->dev = dev;
+ sdev->iommu = iommu;
ret = intel_iommu_enable_pasid(iommu, dev);
if (ret) {
kfree(sdev);
goto out;
}
- svm->iommu = iommu;
if (pasid_max > intel_pasid_max_id)
pasid_max = intel_pasid_max_id;
}
}
- spin_lock(&iommu->lock);
+ spin_lock_irqsave(&iommu->lock, iflags);
ret = intel_pasid_setup_first_level(iommu, dev,
mm ? mm->pgd : init_mm.pgd,
svm->pasid, FLPT_DEFAULT_DID,
(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
(cpu_feature_enabled(X86_FEATURE_LA57) ?
PASID_FLAG_FL5LP : 0));
- spin_unlock(&iommu->lock);
+ spin_unlock_irqrestore(&iommu->lock, iflags);
if (ret) {
if (mm)
mmu_notifier_unregister(&svm->notifier, mm);
* Binding a new device with existing PASID, need to setup
* the PASID entry.
*/
- spin_lock(&iommu->lock);
+ spin_lock_irqsave(&iommu->lock, iflags);
ret = intel_pasid_setup_first_level(iommu, dev,
mm ? mm->pgd : init_mm.pgd,
svm->pasid, FLPT_DEFAULT_DID,
(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
(cpu_feature_enabled(X86_FEATURE_LA57) ?
PASID_FLAG_FL5LP : 0));
- spin_unlock(&iommu->lock);
+ spin_unlock_irqrestore(&iommu->lock, iflags);
if (ret) {
kfree(sdev);
goto out;
* @iovad: - iova domain in question.
* @pfn: - page frame number
* This function finds and returns an iova belonging to the
- * given doamin which matches the given pfn.
+ * given domain which matches the given pfn.
*/
struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
{
EXPORT_SYMBOL_GPL(queue_iova);
/**
- * put_iova_domain - destroys the iova doamin
+ * put_iova_domain - destroys the iova domain
* @iovad: - iova domain in question.
* All the iova's in that domain are destroyed.
*/
/**
* copy_reserved_iova - copies the reserved between domains
- * @from: - source doamin from where to copy
+ * @from: - source domain from where to copy
* @to: - destination domin where to copy
- * This function copies reserved iova's from one doamin to
+ * This function copies reserved iova's from one domain to
* other.
*/
void
config MISDN_DSP
tristate "Digital Audio Processing of transparent data"
depends on MISDN
+ select BITREVERSE
help
Enable support for digital audio processing capability.
config NVM_PBLK
tristate "Physical Block Device Open-Channel SSD target"
+ select CRC32
help
Allows an open-channel SSD to be exposed as a block device to the
host. The target assumes the device exposes raw flash and must be
select BLK_DEV_INTEGRITY
select DM_BUFIO
select CRYPTO
+ select CRYPTO_SKCIPHER
select ASYNC_XOR
help
This device-mapper target emulates a block device that has
tristate "Drive-managed zoned block device target support"
depends on BLK_DEV_DM
depends on BLK_DEV_ZONED
+ select CRC32
help
This device-mapper target takes a host-managed or host-aware zoned
block device and exposes most of its capacity as a regular block
};
static struct feature feature_list[] = {
- {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LARGE_BUCKET,
+ {BCH_FEATURE_INCOMPAT, BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE,
"large_bucket"},
{0, 0, 0 },
};
/* Feature set definition */
/* Incompat feature set */
-#define BCH_FEATURE_INCOMPAT_LARGE_BUCKET 0x0001 /* 32bit bucket size */
+/* 32bit bucket size, obsoleted */
+#define BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET 0x0001
+/* real bucket size is (1 << bucket_size) */
+#define BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE 0x0002
-#define BCH_FEATURE_COMPAT_SUUP 0
-#define BCH_FEATURE_RO_COMPAT_SUUP 0
-#define BCH_FEATURE_INCOMPAT_SUUP BCH_FEATURE_INCOMPAT_LARGE_BUCKET
+#define BCH_FEATURE_COMPAT_SUPP 0
+#define BCH_FEATURE_RO_COMPAT_SUPP 0
+#define BCH_FEATURE_INCOMPAT_SUPP (BCH_FEATURE_INCOMPAT_OBSO_LARGE_BUCKET| \
+ BCH_FEATURE_INCOMPAT_LOG_LARGE_BUCKET_SIZE)
#define BCH_HAS_COMPAT_FEATURE(sb, mask) \
((sb)->feature_compat & (mask))
~BCH##_FEATURE_INCOMPAT_##flagname; \
}
-BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LARGE_BUCKET);
+BCH_FEATURE_INCOMPAT_FUNCS(obso_large_bucket, OBSO_LARGE_BUCKET);
+BCH_FEATURE_INCOMPAT_FUNCS(large_bucket, LOG_LARGE_BUCKET_SIZE);
+
+static inline bool bch_has_unknown_compat_features(struct cache_sb *sb)
+{
+ return ((sb->feature_compat & ~BCH_FEATURE_COMPAT_SUPP) != 0);
+}
+
+static inline bool bch_has_unknown_ro_compat_features(struct cache_sb *sb)
+{
+ return ((sb->feature_ro_compat & ~BCH_FEATURE_RO_COMPAT_SUPP) != 0);
+}
+
+static inline bool bch_has_unknown_incompat_features(struct cache_sb *sb)
+{
+ return ((sb->feature_incompat & ~BCH_FEATURE_INCOMPAT_SUPP) != 0);
+}
int bch_print_cache_set_feature_compat(struct cache_set *c, char *buf, int size);
int bch_print_cache_set_feature_ro_compat(struct cache_set *c, char *buf, int size);
{
unsigned int bucket_size = le16_to_cpu(s->bucket_size);
- if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES &&
- bch_has_feature_large_bucket(sb))
- bucket_size |= le16_to_cpu(s->bucket_size_hi) << 16;
+ if (sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES) {
+ if (bch_has_feature_large_bucket(sb)) {
+ unsigned int max, order;
+
+ max = sizeof(unsigned int) * BITS_PER_BYTE - 1;
+ order = le16_to_cpu(s->bucket_size);
+ /*
+ * bcache tool will make sure the overflow won't
+ * happen, an error message here is enough.
+ */
+ if (order > max)
+ pr_err("Bucket size (1 << %u) overflows\n",
+ order);
+ bucket_size = 1 << order;
+ } else if (bch_has_feature_obso_large_bucket(sb)) {
+ bucket_size +=
+ le16_to_cpu(s->obso_bucket_size_hi) << 16;
+ }
+ }
return bucket_size;
}
sb->feature_compat = le64_to_cpu(s->feature_compat);
sb->feature_incompat = le64_to_cpu(s->feature_incompat);
sb->feature_ro_compat = le64_to_cpu(s->feature_ro_compat);
+
+ /* Check incompatible features */
+ err = "Unsupported compatible feature found";
+ if (bch_has_unknown_compat_features(sb))
+ goto err;
+
+ err = "Unsupported read-only compatible feature found";
+ if (bch_has_unknown_ro_compat_features(sb))
+ goto err;
+
+ err = "Unsupported incompatible feature found";
+ if (bch_has_unknown_incompat_features(sb))
+ goto err;
+
err = read_super_common(sb, bdev, s);
if (err)
goto err;
bcache_device_link(&dc->disk, c, "bdev");
atomic_inc(&c->attached_dev_nr);
+ if (bch_has_feature_obso_large_bucket(&(c->cache->sb))) {
+ pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n");
+ pr_err("Please update to the latest bcache-tools to create the cache device\n");
+ set_disk_ro(dc->disk.disk, 1);
+ }
+
/* Allow the writeback thread to proceed */
up_write(&dc->writeback_lock);
bcache_device_link(d, c, "volume");
+ if (bch_has_feature_obso_large_bucket(&c->cache->sb)) {
+ pr_err("The obsoleted large bucket layout is unsupported, set the bcache device into read-only\n");
+ pr_err("Please update to the latest bcache-tools to create the cache device\n");
+ set_disk_ro(d->disk, 1);
+ }
+
return 0;
err:
kobject_put(&d->kobj);
c->cache->sb.last_mount = (u32)ktime_get_real_seconds();
bcache_write_super(c);
+ if (bch_has_feature_obso_large_bucket(&c->cache->sb))
+ pr_err("Detect obsoleted large bucket layout, all attached bcache device will be read-only\n");
+
list_for_each_entry_safe(dc, t, &uncached_devices, list)
bch_cached_dev_attach(dc, c, NULL);
}
list_for_each_entry_safe(pdev, tpdev, &pending_devs, list) {
+ char *pdev_set_uuid = pdev->dc->sb.set_uuid;
list_for_each_entry_safe(c, tc, &bch_cache_sets, list) {
- char *pdev_set_uuid = pdev->dc->sb.set_uuid;
char *set_uuid = c->set_uuid;
if (!memcmp(pdev_set_uuid, set_uuid, 16)) {
}
EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c)
+{
+ return c->dm_io;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client);
+
sector_t dm_bufio_get_block_number(struct dm_buffer *b)
{
return b->block;
static void kcryptd_async_done(struct crypto_async_request *async_req,
int error);
-static void crypt_alloc_req_skcipher(struct crypt_config *cc,
+static int crypt_alloc_req_skcipher(struct crypt_config *cc,
struct convert_context *ctx)
{
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
- if (!ctx->r.req)
- ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
+ if (!ctx->r.req) {
+ ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+ if (!ctx->r.req)
+ return -ENOMEM;
+ }
skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
skcipher_request_set_callback(ctx->r.req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
kcryptd_async_done, dmreq_of_req(cc, ctx->r.req));
+
+ return 0;
}
-static void crypt_alloc_req_aead(struct crypt_config *cc,
+static int crypt_alloc_req_aead(struct crypt_config *cc,
struct convert_context *ctx)
{
- if (!ctx->r.req_aead)
- ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
+ if (!ctx->r.req) {
+ ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+ if (!ctx->r.req)
+ return -ENOMEM;
+ }
aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
aead_request_set_callback(ctx->r.req_aead,
CRYPTO_TFM_REQ_MAY_BACKLOG,
kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead));
+
+ return 0;
}
-static void crypt_alloc_req(struct crypt_config *cc,
+static int crypt_alloc_req(struct crypt_config *cc,
struct convert_context *ctx)
{
if (crypt_integrity_aead(cc))
- crypt_alloc_req_aead(cc, ctx);
+ return crypt_alloc_req_aead(cc, ctx);
else
- crypt_alloc_req_skcipher(cc, ctx);
+ return crypt_alloc_req_skcipher(cc, ctx);
}
static void crypt_free_req_skcipher(struct crypt_config *cc,
* Encrypt / decrypt data from one bio to another one (can be the same one)
*/
static blk_status_t crypt_convert(struct crypt_config *cc,
- struct convert_context *ctx, bool atomic)
+ struct convert_context *ctx, bool atomic, bool reset_pending)
{
unsigned int tag_offset = 0;
unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
int r;
- atomic_set(&ctx->cc_pending, 1);
+ /*
+ * if reset_pending is set we are dealing with the bio for the first time,
+ * else we're continuing to work on the previous bio, so don't mess with
+ * the cc_pending counter
+ */
+ if (reset_pending)
+ atomic_set(&ctx->cc_pending, 1);
while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
- crypt_alloc_req(cc, ctx);
+ r = crypt_alloc_req(cc, ctx);
+ if (r) {
+ complete(&ctx->restart);
+ return BLK_STS_DEV_RESOURCE;
+ }
+
atomic_inc(&ctx->cc_pending);
if (crypt_integrity_aead(cc))
* but the driver request queue is full, let's wait.
*/
case -EBUSY:
- wait_for_completion(&ctx->restart);
+ if (in_interrupt()) {
+ if (try_wait_for_completion(&ctx->restart)) {
+ /*
+ * we don't have to block to wait for completion,
+ * so proceed
+ */
+ } else {
+ /*
+ * we can't wait for completion without blocking
+ * exit and continue processing in a workqueue
+ */
+ ctx->r.req = NULL;
+ ctx->cc_sector += sector_step;
+ tag_offset++;
+ return BLK_STS_DEV_RESOURCE;
+ }
+ } else {
+ wait_for_completion(&ctx->restart);
+ }
reinit_completion(&ctx->restart);
fallthrough;
/*
atomic_inc(&io->io_pending);
}
+static void kcryptd_io_bio_endio(struct work_struct *work)
+{
+ struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+ bio_endio(io->base_bio);
+}
+
/*
* One of the bios was finished. Check for completion of
* the whole request and correctly clean up the buffer.
kfree(io->integrity_metadata);
base_bio->bi_status = error;
- bio_endio(base_bio);
+
+ /*
+ * If we are running this function from our tasklet,
+ * we can't call bio_endio() here, because it will call
+ * clone_endio() from dm.c, which in turn will
+ * free the current struct dm_crypt_io structure with
+ * our tasklet. In this case we need to delay bio_endio()
+ * execution to after the tasklet is done and dequeued.
+ */
+ if (tasklet_trylock(&io->tasklet)) {
+ tasklet_unlock(&io->tasklet);
+ bio_endio(base_bio);
+ return;
+ }
+
+ INIT_WORK(&io->work, kcryptd_io_bio_endio);
+ queue_work(cc->io_queue, &io->work);
}
/*
}
}
+static void kcryptd_crypt_write_continue(struct work_struct *work)
+{
+ struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+ struct crypt_config *cc = io->cc;
+ struct convert_context *ctx = &io->ctx;
+ int crypt_finished;
+ sector_t sector = io->sector;
+ blk_status_t r;
+
+ wait_for_completion(&ctx->restart);
+ reinit_completion(&ctx->restart);
+
+ r = crypt_convert(cc, &io->ctx, true, false);
+ if (r)
+ io->error = r;
+ crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
+ if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) {
+ /* Wait for completion signaled by kcryptd_async_done() */
+ wait_for_completion(&ctx->restart);
+ crypt_finished = 1;
+ }
+
+ /* Encryption was already finished, submit io now */
+ if (crypt_finished) {
+ kcryptd_crypt_write_io_submit(io, 0);
+ io->sector = sector;
+ }
+
+ crypt_dec_pending(io);
+}
+
static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
crypt_inc_pending(io);
r = crypt_convert(cc, ctx,
- test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags));
+ test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
+ /*
+ * Crypto API backlogged the request, because its queue was full
+ * and we're in softirq context, so continue from a workqueue
+ * (TODO: is it actually possible to be in softirq in the write path?)
+ */
+ if (r == BLK_STS_DEV_RESOURCE) {
+ INIT_WORK(&io->work, kcryptd_crypt_write_continue);
+ queue_work(cc->crypt_queue, &io->work);
+ return;
+ }
if (r)
io->error = r;
crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
crypt_dec_pending(io);
}
+static void kcryptd_crypt_read_continue(struct work_struct *work)
+{
+ struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+ struct crypt_config *cc = io->cc;
+ blk_status_t r;
+
+ wait_for_completion(&io->ctx.restart);
+ reinit_completion(&io->ctx.restart);
+
+ r = crypt_convert(cc, &io->ctx, true, false);
+ if (r)
+ io->error = r;
+
+ if (atomic_dec_and_test(&io->ctx.cc_pending))
+ kcryptd_crypt_read_done(io);
+
+ crypt_dec_pending(io);
+}
+
static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
io->sector);
r = crypt_convert(cc, &io->ctx,
- test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags));
+ test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+ /*
+ * Crypto API backlogged the request, because its queue was full
+ * and we're in softirq context, so continue from a workqueue
+ */
+ if (r == BLK_STS_DEV_RESOURCE) {
+ INIT_WORK(&io->work, kcryptd_crypt_read_continue);
+ queue_work(cc->crypt_queue, &io->work);
+ return;
+ }
if (r)
io->error = r;
if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) ||
(bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) {
- if (in_irq()) {
- /* Crypto API's "skcipher_walk_first() refuses to work in hard IRQ context */
+ /*
+ * in_irq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context.
+ * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
+ * it is being executed with irqs disabled.
+ */
+ if (in_irq() || irqs_disabled()) {
tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
tasklet_schedule(&io->tasklet);
return;
}
if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
- cc->crypt_queue = alloc_workqueue("kcryptd-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
+ cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
1, devname);
else
- cc->crypt_queue = alloc_workqueue("kcryptd-%s",
- WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM |
- WQ_UNBOUND | WQ_SYSFS,
+ cc->crypt_queue = alloc_workqueue("kcryptd/%s",
+ WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
num_online_cpus(), devname);
if (!cc->crypt_queue) {
ti->error = "Couldn't create kcryptd queue";
#undef MAY_BE_HASH
}
-static void dm_integrity_flush_buffers(struct dm_integrity_c *ic)
+struct flush_request {
+ struct dm_io_request io_req;
+ struct dm_io_region io_reg;
+ struct dm_integrity_c *ic;
+ struct completion comp;
+};
+
+static void flush_notify(unsigned long error, void *fr_)
+{
+ struct flush_request *fr = fr_;
+ if (unlikely(error != 0))
+ dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+ complete(&fr->comp);
+}
+
+static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
{
int r;
+
+ struct flush_request fr;
+
+ if (!ic->meta_dev)
+ flush_data = false;
+ if (flush_data) {
+ fr.io_req.bi_op = REQ_OP_WRITE,
+ fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+ fr.io_req.mem.type = DM_IO_KMEM,
+ fr.io_req.mem.ptr.addr = NULL,
+ fr.io_req.notify.fn = flush_notify,
+ fr.io_req.notify.context = &fr;
+ fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
+ fr.io_reg.bdev = ic->dev->bdev,
+ fr.io_reg.sector = 0,
+ fr.io_reg.count = 0,
+ fr.ic = ic;
+ init_completion(&fr.comp);
+ r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+ BUG_ON(r);
+ }
+
r = dm_bufio_write_dirty_buffers(ic->bufio);
if (unlikely(r))
dm_integrity_io_error(ic, "writing tags", r);
+
+ if (flush_data)
+ wait_for_completion(&fr.comp);
}
static void sleep_on_endio_wait(struct dm_integrity_c *ic)
if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
integrity_metadata(&dio->work);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, false);
dio->in_flight = (atomic_t)ATOMIC_INIT(1);
dio->completion = NULL;
flushes = bio_list_get(&ic->flush_bio_list);
if (unlikely(ic->mode != 'J')) {
spin_unlock_irq(&ic->endio_wait.lock);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
goto release_flush_bios;
}
complete_journal_op(&comp);
wait_for_completion_io(&comp.comp);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
}
static void integrity_writer(struct work_struct *w)
{
int r;
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, false);
if (dm_integrity_failed(ic))
return;
unsigned long limit;
struct bio *bio;
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, false);
range.logical_sector = 0;
range.n_sectors = ic->provided_data_sectors;
add_new_range_and_wait(ic, &range);
spin_unlock_irq(&ic->endio_wait.lock);
- dm_integrity_flush_buffers(ic);
- if (ic->meta_dev)
- blkdev_issue_flush(ic->dev->bdev, GFP_NOIO);
+ dm_integrity_flush_buffers(ic, true);
limit = ic->provided_data_sectors;
if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
if (ic->meta_dev)
queue_work(ic->writer_wq, &ic->writer_work);
drain_workqueue(ic->writer_wq);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
}
if (ic->mode == 'B') {
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
#if 1
/* set to 0 to test bitmap replay code */
init_journal(ic, 0, ic->journal_sections, 0);
unsigned extra_args;
struct dm_arg_set as;
static const struct dm_arg _args[] = {
- {0, 9, "Invalid number of feature args"},
+ {0, 15, "Invalid number of feature args"},
};
unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
bool should_write_sb;
blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
/*
- * RAID1 and RAID10 personalities require bio splitting,
- * RAID0/4/5/6 don't and process large discard bios properly.
+ * RAID0 and RAID10 personalities require bio splitting,
+ * RAID1/4/5/6 don't and process large discard bios properly.
*/
- if (rs_is_raid1(rs) || rs_is_raid10(rs)) {
+ if (rs_is_raid0(rs) || rs_is_raid10(rs)) {
limits->discard_granularity = chunk_size_bytes;
limits->max_discard_sectors = rs->md.chunk_sectors;
}
* for them to be committed.
*/
struct bio_list bios_queued_during_merge;
+
+ /*
+ * Flush data after merge.
+ */
+ struct bio flush_bio;
};
/*
static void error_bios(struct bio *bio);
+static int flush_data(struct dm_snapshot *s)
+{
+ struct bio *flush_bio = &s->flush_bio;
+
+ bio_reset(flush_bio);
+ bio_set_dev(flush_bio, s->origin->bdev);
+ flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+
+ return submit_bio_wait(flush_bio);
+}
+
static void merge_callback(int read_err, unsigned long write_err, void *context)
{
struct dm_snapshot *s = context;
goto shut;
}
+ if (flush_data(s) < 0) {
+ DMERR("Flush after merge failed: shutting down merge");
+ goto shut;
+ }
+
if (s->store->type->commit_merge(s->store,
s->num_merging_chunks) < 0) {
DMERR("Write error in exception store: shutting down merge");
s->first_merging_chunk = 0;
s->num_merging_chunks = 0;
bio_list_init(&s->bios_queued_during_merge);
+ bio_init(&s->flush_bio, NULL, 0);
/* Allocate hash table for COW data */
if (init_hash_tables(s)) {
dm_exception_store_destroy(s->store);
+ bio_uninit(&s->flush_bio);
+
dm_put_device(ti, s->cow);
dm_put_device(ti, s->origin);
* subset of the parent bdev; require extra privileges.
*/
if (!capable(CAP_SYS_RAWIO)) {
- DMWARN_LIMIT(
+ DMDEBUG_LIMIT(
"%s: sending ioctl %x to DM device without required privilege.",
current->comm, cmd);
r = -ENOIOCTLCMD;
cntr = &hdev->aggregated_cs_counters;
cs = kzalloc(sizeof(*cs), GFP_ATOMIC);
- if (!cs)
+ if (!cs) {
+ atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+ atomic64_inc(&cntr->out_of_mem_drop_cnt);
return -ENOMEM;
+ }
cs->ctx = ctx;
cs->submitted = false;
cs_cmpl = kmalloc(sizeof(*cs_cmpl), GFP_ATOMIC);
if (!cs_cmpl) {
+ atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+ atomic64_inc(&cntr->out_of_mem_drop_cnt);
rc = -ENOMEM;
goto free_cs;
}
cs->jobs_in_queue_cnt = kcalloc(hdev->asic_prop.max_queues,
sizeof(*cs->jobs_in_queue_cnt), GFP_ATOMIC);
if (!cs->jobs_in_queue_cnt) {
+ atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+ atomic64_inc(&cntr->out_of_mem_drop_cnt);
rc = -ENOMEM;
goto free_fence;
}
for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++)
flush_workqueue(hdev->cq_wq[i]);
- /* Make sure we don't have leftovers in the H/W queues mirror list */
+ /* Make sure we don't have leftovers in the CS mirror list */
list_for_each_entry_safe(cs, tmp, &hdev->cs_mirror_list, mirror_node) {
cs_get(cs);
cs->aborted = true;
static int hl_cs_copy_chunk_array(struct hl_device *hdev,
struct hl_cs_chunk **cs_chunk_array,
- void __user *chunks, u32 num_chunks)
+ void __user *chunks, u32 num_chunks,
+ struct hl_ctx *ctx)
{
u32 size_to_copy;
if (num_chunks > HL_MAX_JOBS_PER_CS) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
dev_err(hdev->dev,
"Number of chunks can NOT be larger than %d\n",
HL_MAX_JOBS_PER_CS);
*cs_chunk_array = kmalloc_array(num_chunks, sizeof(**cs_chunk_array),
GFP_ATOMIC);
- if (!*cs_chunk_array)
+ if (!*cs_chunk_array) {
+ atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+ atomic64_inc(&hdev->aggregated_cs_counters.out_of_mem_drop_cnt);
return -ENOMEM;
+ }
size_to_copy = num_chunks * sizeof(struct hl_cs_chunk);
if (copy_from_user(*cs_chunk_array, chunks, size_to_copy)) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
dev_err(hdev->dev, "Failed to copy cs chunk array from user\n");
kfree(*cs_chunk_array);
return -EFAULT;
struct hl_device *hdev = hpriv->hdev;
struct hl_cs_chunk *cs_chunk_array;
struct hl_cs_counters_atomic *cntr;
+ struct hl_ctx *ctx = hpriv->ctx;
struct hl_cs_job *job;
struct hl_cs *cs;
struct hl_cb *cb;
cntr = &hdev->aggregated_cs_counters;
*cs_seq = ULLONG_MAX;
- rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks);
+ rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks,
+ hpriv->ctx);
if (rc)
goto out;
rc = validate_queue_index(hdev, chunk, &queue_type,
&is_kernel_allocated_cb);
if (rc) {
- atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt);
- atomic64_inc(&cntr->parsing_drop_cnt);
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
goto free_cs_object;
}
cb = get_cb_from_cs_chunk(hdev, &hpriv->cb_mgr, chunk);
if (!cb) {
atomic64_inc(
- &hpriv->ctx->cs_counters.parsing_drop_cnt);
- atomic64_inc(&cntr->parsing_drop_cnt);
+ &ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
rc = -EINVAL;
goto free_cs_object;
}
job = hl_cs_allocate_job(hdev, queue_type,
is_kernel_allocated_cb);
if (!job) {
- atomic64_inc(
- &hpriv->ctx->cs_counters.out_of_mem_drop_cnt);
+ atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
atomic64_inc(&cntr->out_of_mem_drop_cnt);
dev_err(hdev->dev, "Failed to allocate a new job\n");
rc = -ENOMEM;
rc = cs_parser(hpriv, job);
if (rc) {
- atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt);
+ atomic64_inc(&ctx->cs_counters.parsing_drop_cnt);
atomic64_inc(&cntr->parsing_drop_cnt);
dev_err(hdev->dev,
"Failed to parse JOB %d.%llu.%d, err %d, rejecting the CS\n",
}
if (int_queues_only) {
- atomic64_inc(&hpriv->ctx->cs_counters.parsing_drop_cnt);
- atomic64_inc(&cntr->parsing_drop_cnt);
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
dev_err(hdev->dev,
"Reject CS %d.%llu because only internal queues jobs are present\n",
cs->ctx->asid, cs->sequence);
}
static int cs_ioctl_extract_signal_seq(struct hl_device *hdev,
- struct hl_cs_chunk *chunk, u64 *signal_seq)
+ struct hl_cs_chunk *chunk, u64 *signal_seq, struct hl_ctx *ctx)
{
u64 *signal_seq_arr = NULL;
u32 size_to_copy, signal_seq_arr_len;
/* currently only one signal seq is supported */
if (signal_seq_arr_len != 1) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
dev_err(hdev->dev,
"Wait for signal CS supports only one signal CS seq\n");
return -EINVAL;
signal_seq_arr = kmalloc_array(signal_seq_arr_len,
sizeof(*signal_seq_arr),
GFP_ATOMIC);
- if (!signal_seq_arr)
+ if (!signal_seq_arr) {
+ atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
+ atomic64_inc(&hdev->aggregated_cs_counters.out_of_mem_drop_cnt);
return -ENOMEM;
+ }
size_to_copy = chunk->num_signal_seq_arr * sizeof(*signal_seq_arr);
if (copy_from_user(signal_seq_arr,
u64_to_user_ptr(chunk->signal_seq_arr),
size_to_copy)) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&hdev->aggregated_cs_counters.validation_drop_cnt);
dev_err(hdev->dev,
"Failed to copy signal seq array from user\n");
rc = -EFAULT;
struct hl_device *hdev = hpriv->hdev;
struct hl_cs_compl *sig_waitcs_cmpl;
u32 q_idx, collective_engine_id = 0;
+ struct hl_cs_counters_atomic *cntr;
struct hl_fence *sig_fence = NULL;
struct hl_ctx *ctx = hpriv->ctx;
enum hl_queue_type q_type;
u64 signal_seq;
int rc;
+ cntr = &hdev->aggregated_cs_counters;
*cs_seq = ULLONG_MAX;
- rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks);
+ rc = hl_cs_copy_chunk_array(hdev, &cs_chunk_array, chunks, num_chunks,
+ ctx);
if (rc)
goto out;
chunk = &cs_chunk_array[0];
if (chunk->queue_index >= hdev->asic_prop.max_queues) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
dev_err(hdev->dev, "Queue index %d is invalid\n",
chunk->queue_index);
rc = -EINVAL;
q_type = hw_queue_prop->type;
if (!hw_queue_prop->supports_sync_stream) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
dev_err(hdev->dev,
"Queue index %d does not support sync stream operations\n",
q_idx);
if (cs_type == CS_TYPE_COLLECTIVE_WAIT) {
if (!(hw_queue_prop->collective_mode == HL_COLLECTIVE_MASTER)) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
dev_err(hdev->dev,
"Queue index %d is invalid\n", q_idx);
rc = -EINVAL;
}
if (cs_type == CS_TYPE_WAIT || cs_type == CS_TYPE_COLLECTIVE_WAIT) {
- rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq);
+ rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq, ctx);
if (rc)
goto free_cs_chunk_array;
sig_fence = hl_ctx_get_fence(ctx, signal_seq);
if (IS_ERR(sig_fence)) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
dev_err(hdev->dev,
"Failed to get signal CS with seq 0x%llx\n",
signal_seq);
container_of(sig_fence, struct hl_cs_compl, base_fence);
if (sig_waitcs_cmpl->type != CS_TYPE_SIGNAL) {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
dev_err(hdev->dev,
"CS seq 0x%llx is not of a signal CS\n",
signal_seq);
else if (cs_type == CS_TYPE_COLLECTIVE_WAIT)
rc = hdev->asic_funcs->collective_wait_create_jobs(hdev, ctx,
cs, q_idx, collective_engine_id);
- else
+ else {
+ atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
+ atomic64_inc(&cntr->validation_drop_cnt);
rc = -EINVAL;
+ }
if (rc)
goto free_cs_object;
{
enum hl_device_status status;
- if (hdev->disabled)
- status = HL_DEVICE_STATUS_MALFUNCTION;
- else if (atomic_read(&hdev->in_reset))
+ if (atomic_read(&hdev->in_reset))
status = HL_DEVICE_STATUS_IN_RESET;
else if (hdev->needs_reset)
status = HL_DEVICE_STATUS_NEEDS_RESET;
+ else if (hdev->disabled)
+ status = HL_DEVICE_STATUS_MALFUNCTION;
else
status = HL_DEVICE_STATUS_OPERATIONAL;
GFP_KERNEL);
if (!hdev->kernel_ctx) {
rc = -ENOMEM;
+ hl_mmu_fini(hdev);
goto out_err;
}
"failed to init kernel ctx in hard reset\n");
kfree(hdev->kernel_ctx);
hdev->kernel_ctx = NULL;
+ hl_mmu_fini(hdev);
goto out_err;
}
}
security_status = RREG32(cpu_security_boot_status_reg);
/* We read security status multiple times during boot:
- * 1. preboot - we check if fw security feature is supported
- * 2. boot cpu - we get boot cpu security status
- * 3. FW application - we get FW application security status
+ * 1. preboot - a. Check whether the security status bits are valid
+ * b. Check whether fw security is enabled
+ * c. Check whether hard reset is done by preboot
+ * 2. boot cpu - a. Fetch boot cpu security status
+ * b. Check whether hard reset is done by boot cpu
+ * 3. FW application - a. Fetch fw application security status
+ * b. Check whether hard reset is done by fw app
*
* Preboot:
* Check security status bit (CPU_BOOT_DEV_STS0_ENABLED), if it is set
* check security enabled bit (CPU_BOOT_DEV_STS0_SECURITY_EN)
*/
if (security_status & CPU_BOOT_DEV_STS0_ENABLED) {
- hdev->asic_prop.fw_security_status_valid = 1;
- prop->fw_security_disabled =
- !(security_status & CPU_BOOT_DEV_STS0_SECURITY_EN);
+ prop->fw_security_status_valid = 1;
+
+ if (security_status & CPU_BOOT_DEV_STS0_SECURITY_EN)
+ prop->fw_security_disabled = false;
+ else
+ prop->fw_security_disabled = true;
+
+ if (security_status & CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
+ prop->hard_reset_done_by_fw = true;
} else {
- hdev->asic_prop.fw_security_status_valid = 0;
+ prop->fw_security_status_valid = 0;
prop->fw_security_disabled = true;
}
+ dev_dbg(hdev->dev, "Firmware preboot hard-reset is %s\n",
+ prop->hard_reset_done_by_fw ? "enabled" : "disabled");
+
dev_info(hdev->dev, "firmware-level security is %s\n",
- prop->fw_security_disabled ? "disabled" : "enabled");
+ prop->fw_security_disabled ? "disabled" : "enabled");
return 0;
}
u32 cpu_security_boot_status_reg, u32 boot_err0_reg,
bool skip_bmc, u32 cpu_timeout, u32 boot_fit_timeout)
{
+ struct asic_fixed_properties *prop = &hdev->asic_prop;
u32 status;
int rc;
/* Read U-Boot version now in case we will later fail */
hdev->asic_funcs->read_device_fw_version(hdev, FW_COMP_UBOOT);
+ /* Clear reset status since we need to read it again from boot CPU */
+ prop->hard_reset_done_by_fw = false;
+
/* Read boot_cpu security bits */
- if (hdev->asic_prop.fw_security_status_valid)
- hdev->asic_prop.fw_boot_cpu_security_map =
+ if (prop->fw_security_status_valid) {
+ prop->fw_boot_cpu_security_map =
RREG32(cpu_security_boot_status_reg);
+ if (prop->fw_boot_cpu_security_map &
+ CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
+ prop->hard_reset_done_by_fw = true;
+ }
+
+ dev_dbg(hdev->dev, "Firmware boot CPU hard-reset is %s\n",
+ prop->hard_reset_done_by_fw ? "enabled" : "disabled");
+
if (rc) {
detect_cpu_boot_status(hdev, status);
rc = -EIO;
goto out;
}
+ /* Clear reset status since we need to read again from app */
+ prop->hard_reset_done_by_fw = false;
+
/* Read FW application security bits */
- if (hdev->asic_prop.fw_security_status_valid) {
- hdev->asic_prop.fw_app_security_map =
+ if (prop->fw_security_status_valid) {
+ prop->fw_app_security_map =
RREG32(cpu_security_boot_status_reg);
- if (hdev->asic_prop.fw_app_security_map &
+ if (prop->fw_app_security_map &
CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
- hdev->asic_prop.hard_reset_done_by_fw = true;
+ prop->hard_reset_done_by_fw = true;
}
- dev_dbg(hdev->dev, "Firmware hard-reset is %s\n",
- hdev->asic_prop.hard_reset_done_by_fw ? "enabled" : "disabled");
+ dev_dbg(hdev->dev, "Firmware application CPU hard-reset is %s\n",
+ prop->hard_reset_done_by_fw ? "enabled" : "disabled");
dev_info(hdev->dev, "Successfully loaded firmware to device\n");
u32 (*get_signal_cb_size)(struct hl_device *hdev);
u32 (*get_wait_cb_size)(struct hl_device *hdev);
u32 (*gen_signal_cb)(struct hl_device *hdev, void *data, u16 sob_id,
- u32 size);
+ u32 size, bool eb);
u32 (*gen_wait_cb)(struct hl_device *hdev,
struct hl_gen_wait_properties *prop);
void (*reset_sob)(struct hl_device *hdev, void *data);
* @queue_full_drop_cnt: dropped due to queue full
* @device_in_reset_drop_cnt: dropped due to device in reset
* @max_cs_in_flight_drop_cnt: dropped due to maximum CS in-flight
+ * @validation_drop_cnt: dropped due to error in validation
*/
struct hl_cs_counters_atomic {
atomic64_t out_of_mem_drop_cnt;
atomic64_t queue_full_drop_cnt;
atomic64_t device_in_reset_drop_cnt;
atomic64_t max_cs_in_flight_drop_cnt;
+ atomic64_t validation_drop_cnt;
};
/**
.id_table = ids,
.probe = hl_pci_probe,
.remove = hl_pci_remove,
+ .shutdown = hl_pci_remove,
.driver.pm = &hl_pm_ops,
.err_handler = &hl_pci_err_handler,
};
atomic64_read(&cntr->device_in_reset_drop_cnt);
cs_counters.total_max_cs_in_flight_drop_cnt =
atomic64_read(&cntr->max_cs_in_flight_drop_cnt);
+ cs_counters.total_validation_drop_cnt =
+ atomic64_read(&cntr->validation_drop_cnt);
if (hpriv->ctx) {
cs_counters.ctx_out_of_mem_drop_cnt =
cs_counters.ctx_max_cs_in_flight_drop_cnt =
atomic64_read(
&hpriv->ctx->cs_counters.max_cs_in_flight_drop_cnt);
+ cs_counters.ctx_validation_drop_cnt =
+ atomic64_read(
+ &hpriv->ctx->cs_counters.validation_drop_cnt);
}
return copy_to_user(out, &cs_counters,
static int pll_frequency_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
{
struct hl_device *hdev = hpriv->hdev;
- struct hl_pll_frequency_info freq_info = {0};
+ struct hl_pll_frequency_info freq_info = { {0} };
u32 max_size = args->return_size;
void __user *out = (void __user *) (uintptr_t) args->return_pointer;
int rc;
"generate signal CB, sob_id: %d, sob val: 0x%x, q_idx: %d\n",
cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx);
+ /* we set an EB since we must make sure all oeprations are done
+ * when sending the signal
+ */
hdev->asic_funcs->gen_signal_cb(hdev, job->patched_cb,
- cs_cmpl->hw_sob->sob_id, 0);
+ cs_cmpl->hw_sob->sob_id, 0, true);
kref_get(&hw_sob->kref);
if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE)
return 0;
- if (val & PCI_CONFIG_ELBI_STS_ERR) {
- dev_err(hdev->dev, "Error writing to ELBI\n");
+ if (val & PCI_CONFIG_ELBI_STS_ERR)
return -EIO;
- }
if (!(val & PCI_CONFIG_ELBI_STS_MASK)) {
dev_err(hdev->dev, "ELBI write didn't finish in time\n");
dbi_offset = addr & 0xFFF;
- rc = hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000);
- rc |= hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset,
+ /* Ignore result of writing to pcie_aux_dbi_reg_addr as it could fail
+ * in case the firmware security is enabled
+ */
+ hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000);
+
+ rc = hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset,
data);
if (rc)
rc |= hl_pci_iatu_write(hdev, offset + 0x4, ctrl_reg_val);
- /* Return the DBI window to the default location */
- rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
- rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0);
+ /* Return the DBI window to the default location
+ * Ignore result of writing to pcie_aux_dbi_reg_addr as it could fail
+ * in case the firmware security is enabled
+ */
+ hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
if (rc)
dev_err(hdev->dev, "failed to map bar %u to 0x%08llx\n",
/* Enable */
rc |= hl_pci_iatu_write(hdev, 0x004, 0x80000000);
- /* Return the DBI window to the default location */
- rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
- rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0);
+ /* Return the DBI window to the default location
+ * Ignore result of writing to pcie_aux_dbi_reg_addr as it could fail
+ * in case the firmware security is enabled
+ */
+ hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0);
return rc;
}
[PACKET_LOAD_AND_EXE] = sizeof(struct packet_load_and_exe)
};
-static const u32 gaudi_pll_base_addresses[GAUDI_PLL_MAX] = {
- [CPU_PLL] = mmPSOC_CPU_PLL_NR,
- [PCI_PLL] = mmPSOC_PCI_PLL_NR,
- [SRAM_PLL] = mmSRAM_W_PLL_NR,
- [HBM_PLL] = mmPSOC_HBM_PLL_NR,
- [NIC_PLL] = mmNIC0_PLL_NR,
- [DMA_PLL] = mmDMA_W_PLL_NR,
- [MESH_PLL] = mmMESH_W_PLL_NR,
- [MME_PLL] = mmPSOC_MME_PLL_NR,
- [TPC_PLL] = mmPSOC_TPC_PLL_NR,
- [IF_PLL] = mmIF_W_PLL_NR
-};
-
static inline bool validate_packet_id(enum packet_id id)
{
switch (id) {
static void gaudi_disable_clock_gating(struct hl_device *hdev);
static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid);
static u32 gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
- u32 size);
+ u32 size, bool eb);
static u32 gaudi_gen_wait_cb(struct hl_device *hdev,
struct hl_gen_wait_properties *prop);
if (rc)
goto free_queue_props;
- if (gaudi_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
- dev_info(hdev->dev,
- "H/W state is dirty, must reset before initializing\n");
- hdev->asic_funcs->hw_fini(hdev, true);
- }
-
/* Before continuing in the initialization, we need to read the preboot
* version to determine whether we run with a security-enabled firmware
*/
goto pci_fini;
}
+ if (gaudi_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
+ dev_info(hdev->dev,
+ "H/W state is dirty, must reset before initializing\n");
+ hdev->asic_funcs->hw_fini(hdev, true);
+ }
+
return 0;
pci_fini:
}
/**
- * gaudi_fetch_pll_frequency - Fetch PLL frequency values
+ * gaudi_fetch_psoc_frequency - Fetch PSOC frequency values
*
* @hdev: pointer to hl_device structure
- * @pll_index: index of the pll to fetch frequency from
- * @pll_freq: pointer to store the pll frequency in MHz in each of the available
- * outputs. if a certain output is not available a 0 will be set
*
*/
-static int gaudi_fetch_pll_frequency(struct hl_device *hdev,
- enum gaudi_pll_index pll_index,
- u16 *pll_freq_arr)
+static int gaudi_fetch_psoc_frequency(struct hl_device *hdev)
{
- u32 nr = 0, nf = 0, od = 0, pll_clk = 0, div_fctr, div_sel,
- pll_base_addr = gaudi_pll_base_addresses[pll_index];
- u16 freq = 0;
- int i, rc;
-
- if (hdev->asic_prop.fw_security_status_valid &&
- (hdev->asic_prop.fw_app_security_map &
- CPU_BOOT_DEV_STS0_PLL_INFO_EN)) {
- rc = hl_fw_cpucp_pll_info_get(hdev, pll_index, pll_freq_arr);
+ struct asic_fixed_properties *prop = &hdev->asic_prop;
+ u32 nr = 0, nf = 0, od = 0, div_fctr = 0, pll_clk, div_sel;
+ u16 pll_freq_arr[HL_PLL_NUM_OUTPUTS], freq;
+ int rc;
- if (rc)
- return rc;
- } else if (hdev->asic_prop.fw_security_disabled) {
+ if (hdev->asic_prop.fw_security_disabled) {
/* Backward compatibility */
- nr = RREG32(pll_base_addr + PLL_NR_OFFSET);
- nf = RREG32(pll_base_addr + PLL_NF_OFFSET);
- od = RREG32(pll_base_addr + PLL_OD_OFFSET);
-
- for (i = 0; i < HL_PLL_NUM_OUTPUTS; i++) {
- div_fctr = RREG32(pll_base_addr +
- PLL_DIV_FACTOR_0_OFFSET + i * 4);
- div_sel = RREG32(pll_base_addr +
- PLL_DIV_SEL_0_OFFSET + i * 4);
+ div_fctr = RREG32(mmPSOC_CPU_PLL_DIV_FACTOR_2);
+ div_sel = RREG32(mmPSOC_CPU_PLL_DIV_SEL_2);
+ nr = RREG32(mmPSOC_CPU_PLL_NR);
+ nf = RREG32(mmPSOC_CPU_PLL_NF);
+ od = RREG32(mmPSOC_CPU_PLL_OD);
- if (div_sel == DIV_SEL_REF_CLK ||
+ if (div_sel == DIV_SEL_REF_CLK ||
div_sel == DIV_SEL_DIVIDED_REF) {
- if (div_sel == DIV_SEL_REF_CLK)
- freq = PLL_REF_CLK;
- else
- freq = PLL_REF_CLK / (div_fctr + 1);
- } else if (div_sel == DIV_SEL_PLL_CLK ||
- div_sel == DIV_SEL_DIVIDED_PLL) {
- pll_clk = PLL_REF_CLK * (nf + 1) /
- ((nr + 1) * (od + 1));
- if (div_sel == DIV_SEL_PLL_CLK)
- freq = pll_clk;
- else
- freq = pll_clk / (div_fctr + 1);
- } else {
- dev_warn(hdev->dev,
- "Received invalid div select value: %d",
- div_sel);
- }
-
- pll_freq_arr[i] = freq;
+ if (div_sel == DIV_SEL_REF_CLK)
+ freq = PLL_REF_CLK;
+ else
+ freq = PLL_REF_CLK / (div_fctr + 1);
+ } else if (div_sel == DIV_SEL_PLL_CLK ||
+ div_sel == DIV_SEL_DIVIDED_PLL) {
+ pll_clk = PLL_REF_CLK * (nf + 1) /
+ ((nr + 1) * (od + 1));
+ if (div_sel == DIV_SEL_PLL_CLK)
+ freq = pll_clk;
+ else
+ freq = pll_clk / (div_fctr + 1);
+ } else {
+ dev_warn(hdev->dev,
+ "Received invalid div select value: %d",
+ div_sel);
+ freq = 0;
}
} else {
- dev_err(hdev->dev, "Failed to fetch PLL frequency values\n");
- return -EIO;
- }
+ rc = hl_fw_cpucp_pll_info_get(hdev, CPU_PLL, pll_freq_arr);
- return 0;
-}
-
-/**
- * gaudi_fetch_psoc_frequency - Fetch PSOC frequency values
- *
- * @hdev: pointer to hl_device structure
- *
- */
-static int gaudi_fetch_psoc_frequency(struct hl_device *hdev)
-{
- struct asic_fixed_properties *prop = &hdev->asic_prop;
- u16 pll_freq[HL_PLL_NUM_OUTPUTS];
- int rc;
+ if (rc)
+ return rc;
- rc = gaudi_fetch_pll_frequency(hdev, CPU_PLL, pll_freq);
- if (rc)
- return rc;
+ freq = pll_freq_arr[2];
+ }
- prop->psoc_timestamp_frequency = pll_freq[2];
- prop->psoc_pci_pll_nr = 0;
- prop->psoc_pci_pll_nf = 0;
- prop->psoc_pci_pll_od = 0;
- prop->psoc_pci_pll_div_factor = 0;
+ prop->psoc_timestamp_frequency = freq;
+ prop->psoc_pci_pll_nr = nr;
+ prop->psoc_pci_pll_nf = nf;
+ prop->psoc_pci_pll_od = od;
+ prop->psoc_pci_pll_div_factor = div_fctr;
return 0;
}
size_t fw_size;
void *cpu_addr;
dma_addr_t dma_handle;
- int rc;
+ int rc, count = 5;
+again:
rc = request_firmware(&fw, GAUDI_TPC_FW_FILE, hdev->dev);
+ if (rc == -EINTR && count-- > 0) {
+ msleep(50);
+ goto again;
+ }
+
if (rc) {
- dev_err(hdev->dev, "Firmware file %s is not found!\n",
+ dev_err(hdev->dev, "Failed to load firmware file %s\n",
GAUDI_TPC_FW_FILE);
goto out;
}
prop->collective_sob_id, queue_id);
cb_size += gaudi_gen_signal_cb(hdev, job->user_cb,
- prop->collective_sob_id, cb_size);
+ prop->collective_sob_id, cb_size, false);
}
static void gaudi_collective_wait_init_cs(struct hl_cs *cs)
gaudi_init_e2e(hdev);
gaudi_init_hbm_cred(hdev);
- hdev->asic_funcs->disable_clock_gating(hdev);
-
for (tpc_id = 0, tpc_offset = 0;
tpc_id < TPC_NUMBER_OF_ENGINES;
tpc_id++, tpc_offset += TPC_CFG_OFFSET) {
if (hdev->in_debug)
return;
+ if (!hdev->asic_prop.fw_security_disabled)
+ return;
+
for (i = GAUDI_PCI_DMA_1, qman_offset = 0 ; i < GAUDI_HBM_DMA_1 ; i++) {
enable = !!(hdev->clock_gating_mask &
(BIT_ULL(gaudi_dma_assignment[i])));
u32 qman_offset;
int i;
- if (!(gaudi->hw_cap_initialized & HW_CAP_CLK_GATE))
+ if (!hdev->asic_prop.fw_security_disabled)
return;
for (i = 0, qman_offset = 0 ; i < DMA_NUMBER_OF_CHANNELS ; i++) {
static void gaudi_pre_hw_init(struct hl_device *hdev)
{
/* Perform read from the device to make sure device is up */
- RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+ RREG32(mmHW_STATE);
if (hdev->asic_prop.fw_security_disabled) {
/* Set the access through PCI bars (Linux driver only) as
return rc;
}
+ /* In case the clock gating was enabled in preboot we need to disable
+ * it here before touching the MME/TPC registers.
+ * There is no need to take clk gating mutex because when this function
+ * runs, no other relevant code can run
+ */
+ hdev->asic_funcs->disable_clock_gating(hdev);
+
/* SRAM scrambler must be initialized after CPU is running from HBM */
gaudi_init_scrambler_sram(hdev);
}
/* Perform read from the device to flush all configuration */
- RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+ RREG32(mmHW_STATE);
return 0;
/* I don't know what is the state of the CPU so make sure it is
* stopped in any means necessary
*/
- WREG32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU, KMD_MSG_GOTO_WFE);
+ if (hdev->asic_prop.hard_reset_done_by_fw)
+ WREG32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU, KMD_MSG_RST_DEV);
+ else
+ WREG32(mmPSOC_GLOBAL_CONF_KMD_MSG_TO_CPU, KMD_MSG_GOTO_WFE);
WREG32(mmGIC_DISTRIBUTOR__5_GICD_SETSPI_NSR, GAUDI_EVENT_HALT_MACHINE);
WREG32(mmPSOC_GLOBAL_CONF_SW_ALL_RST,
1 << PSOC_GLOBAL_CONF_SW_ALL_RST_IND_SHIFT);
- }
- dev_info(hdev->dev,
- "Issued HARD reset command, going to wait %dms\n",
- reset_timeout_ms);
+ dev_info(hdev->dev,
+ "Issued HARD reset command, going to wait %dms\n",
+ reset_timeout_ms);
+ } else {
+ dev_info(hdev->dev,
+ "Firmware performs HARD reset, going to wait %dms\n",
+ reset_timeout_ms);
+ }
/*
* After hard reset, we can't poll the BTM_FSM register because the PSOC
}
static u32 gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
- u32 size)
+ u32 size, bool eb)
{
struct hl_cb *cb = (struct hl_cb *) data;
struct packet_msg_short *pkt;
ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_OP_MASK, 0); /* write the value */
ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_BASE_MASK, 3); /* W_S SOB base */
ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_OPCODE_MASK, PACKET_MSG_SHORT);
- ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_EB_MASK, 1);
+ ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_EB_MASK, eb);
ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_RB_MASK, 1);
ctl |= FIELD_PREP(GAUDI_PKT_SHORT_CTL_MB_MASK, 1);
#define MME_ACC_OFFSET (mmMME1_ACC_BASE - mmMME0_ACC_BASE)
#define SRAM_BANK_OFFSET (mmSRAM_Y0_X1_RTR_BASE - mmSRAM_Y0_X0_RTR_BASE)
-#define PLL_NR_OFFSET 0
-#define PLL_NF_OFFSET (mmPSOC_CPU_PLL_NF - mmPSOC_CPU_PLL_NR)
-#define PLL_OD_OFFSET (mmPSOC_CPU_PLL_OD - mmPSOC_CPU_PLL_NR)
-#define PLL_DIV_FACTOR_0_OFFSET (mmPSOC_CPU_PLL_DIV_FACTOR_0 - \
- mmPSOC_CPU_PLL_NR)
-#define PLL_DIV_SEL_0_OFFSET (mmPSOC_CPU_PLL_DIV_SEL_0 - mmPSOC_CPU_PLL_NR)
-
#define NUM_OF_SOB_IN_BLOCK \
(((mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_2047 - \
mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0) + 4) >> 2)
#include "../include/gaudi/gaudi_coresight.h"
#include "../include/gaudi/asic_reg/gaudi_regs.h"
#include "../include/gaudi/gaudi_masks.h"
+#include "../include/gaudi/gaudi_reg_map.h"
#include <uapi/misc/habanalabs.h>
#define SPMU_SECTION_SIZE MME0_ACC_SPMU_MAX_OFFSET
}
/* Perform read from the device to flush all configuration */
- RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG);
+ RREG32(mmHW_STATE);
return rc;
}
if (rc)
goto free_queue_props;
- if (goya_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
- dev_info(hdev->dev,
- "H/W state is dirty, must reset before initializing\n");
- hdev->asic_funcs->hw_fini(hdev, true);
- }
-
/* Before continuing in the initialization, we need to read the preboot
* version to determine whether we run with a security-enabled firmware
*/
goto pci_fini;
}
+ if (goya_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
+ dev_info(hdev->dev,
+ "H/W state is dirty, must reset before initializing\n");
+ hdev->asic_funcs->hw_fini(hdev, true);
+ }
+
if (!hdev->pldm) {
val = RREG32(mmPSOC_GLOBAL_CONF_BOOT_STRAP_PINS);
if (val & PSOC_GLOBAL_CONF_BOOT_STRAP_PINS_SRIOV_EN_MASK)
static void goya_fetch_psoc_frequency(struct hl_device *hdev)
{
struct asic_fixed_properties *prop = &hdev->asic_prop;
- u32 trace_freq = 0;
- u32 pll_clk = 0;
- u32 div_fctr = RREG32(mmPSOC_PCI_PLL_DIV_FACTOR_1);
- u32 div_sel = RREG32(mmPSOC_PCI_PLL_DIV_SEL_1);
- u32 nr = RREG32(mmPSOC_PCI_PLL_NR);
- u32 nf = RREG32(mmPSOC_PCI_PLL_NF);
- u32 od = RREG32(mmPSOC_PCI_PLL_OD);
-
- if (div_sel == DIV_SEL_REF_CLK || div_sel == DIV_SEL_DIVIDED_REF) {
- if (div_sel == DIV_SEL_REF_CLK)
- trace_freq = PLL_REF_CLK;
- else
- trace_freq = PLL_REF_CLK / (div_fctr + 1);
- } else if (div_sel == DIV_SEL_PLL_CLK ||
- div_sel == DIV_SEL_DIVIDED_PLL) {
- pll_clk = PLL_REF_CLK * (nf + 1) / ((nr + 1) * (od + 1));
- if (div_sel == DIV_SEL_PLL_CLK)
- trace_freq = pll_clk;
- else
- trace_freq = pll_clk / (div_fctr + 1);
+ u32 nr = 0, nf = 0, od = 0, div_fctr = 0, pll_clk, div_sel;
+ u16 pll_freq_arr[HL_PLL_NUM_OUTPUTS], freq;
+ int rc;
+
+ if (hdev->asic_prop.fw_security_disabled) {
+ div_fctr = RREG32(mmPSOC_PCI_PLL_DIV_FACTOR_1);
+ div_sel = RREG32(mmPSOC_PCI_PLL_DIV_SEL_1);
+ nr = RREG32(mmPSOC_PCI_PLL_NR);
+ nf = RREG32(mmPSOC_PCI_PLL_NF);
+ od = RREG32(mmPSOC_PCI_PLL_OD);
+
+ if (div_sel == DIV_SEL_REF_CLK ||
+ div_sel == DIV_SEL_DIVIDED_REF) {
+ if (div_sel == DIV_SEL_REF_CLK)
+ freq = PLL_REF_CLK;
+ else
+ freq = PLL_REF_CLK / (div_fctr + 1);
+ } else if (div_sel == DIV_SEL_PLL_CLK ||
+ div_sel == DIV_SEL_DIVIDED_PLL) {
+ pll_clk = PLL_REF_CLK * (nf + 1) /
+ ((nr + 1) * (od + 1));
+ if (div_sel == DIV_SEL_PLL_CLK)
+ freq = pll_clk;
+ else
+ freq = pll_clk / (div_fctr + 1);
+ } else {
+ dev_warn(hdev->dev,
+ "Received invalid div select value: %d",
+ div_sel);
+ freq = 0;
+ }
} else {
- dev_warn(hdev->dev,
- "Received invalid div select value: %d", div_sel);
+ rc = hl_fw_cpucp_pll_info_get(hdev, PCI_PLL, pll_freq_arr);
+
+ if (rc)
+ return;
+
+ freq = pll_freq_arr[1];
}
- prop->psoc_timestamp_frequency = trace_freq;
+ prop->psoc_timestamp_frequency = freq;
prop->psoc_pci_pll_nr = nr;
prop->psoc_pci_pll_nf = nf;
prop->psoc_pci_pll_od = od;
}
static u32 goya_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
- u32 size)
+ u32 size, bool eb)
{
return 0;
}
* implemented. This means that FW will
* perform hard reset procedure on
* receiving the halt-machine event.
- * Initialized in: linux
+ * Initialized in: preboot, u-boot, linux
*
* CPU_BOOT_DEV_STS0_PLL_INFO_EN FW retrieval of PLL info is enabled.
* Initialized in: linux
*
+ * CPU_BOOT_DEV_STS0_CLK_GATE_EN Clock Gating enabled.
+ * FW initialized Clock Gating.
+ * Initialized in: preboot
+ *
* CPU_BOOT_DEV_STS0_ENABLED Device status register enabled.
* This is a main indication that the
* running FW populates the device status
#define CPU_BOOT_DEV_STS0_DRAM_SCR_EN (1 << 9)
#define CPU_BOOT_DEV_STS0_FW_HARD_RST_EN (1 << 10)
#define CPU_BOOT_DEV_STS0_PLL_INFO_EN (1 << 11)
+#define CPU_BOOT_DEV_STS0_CLK_GATE_EN (1 << 13)
#define CPU_BOOT_DEV_STS0_ENABLED (1 << 31)
enum cpu_boot_status {
KMD_MSG_GOTO_WFE,
KMD_MSG_FIT_RDY,
KMD_MSG_SKIP_BMC,
+ RESERVED,
+ KMD_MSG_RST_DEV,
};
enum cpu_msg_status {
struct resource *res;
res = platform_get_mem_or_io(pdev, 0);
- if (res && resource_type(res) == IORESOURCE_IO)
+ if (!res)
+ return -EINVAL;
+
+ switch (resource_type(res)) {
+ case IORESOURCE_IO:
base = devm_ioport_map(dev, res->start, resource_size(res));
- else
+ if (!base)
+ return -ENOMEM;
+ break;
+ case IORESOURCE_MEM:
base = devm_ioremap_resource(dev, res);
- if (IS_ERR(base))
- return PTR_ERR(base);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+ break;
+ default:
+ return -EINVAL;
+ }
atomic_notifier_chain_register(&panic_notifier_list,
&pvpanic_panic_nb);
goto free_dst;
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len +
- BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr);
+ BAREUDP_BASE_HLEN + info->options_len + sizeof(struct ipv6hdr);
err = skb_cow_head(skb, min_headroom);
if (unlikely(err))
SET_NETDEV_DEVTYPE(dev, &bareudp_type);
dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM;
dev->features |= NETIF_F_RXCSUM;
+ dev->features |= NETIF_F_LLTX;
dev->features |= NETIF_F_GSO_SOFTWARE;
dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;
return 0;
}
+static void bareudp_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct bareudp_dev *bareudp = netdev_priv(dev);
+
+ list_del(&bareudp->next);
+ unregister_netdevice_queue(dev, head);
+}
+
static int bareudp_newlink(struct net *net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct bareudp_conf conf;
+ LIST_HEAD(list_kill);
int err;
err = bareudp2info(data, &conf, extack);
err = bareudp_link_config(dev, tb);
if (err)
- return err;
+ goto err_unconfig;
return 0;
-}
-
-static void bareudp_dellink(struct net_device *dev, struct list_head *head)
-{
- struct bareudp_dev *bareudp = netdev_priv(dev);
- list_del(&bareudp->next);
- unregister_netdevice_queue(dev, head);
+err_unconfig:
+ bareudp_dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+ return err;
}
static size_t bareudp_get_size(const struct net_device *dev)
config CAN_KVASER_PCIEFD
depends on PCI
tristate "Kvaser PCIe FD cards"
+ select CRC32
help
This is a driver for the Kvaser PCI Express CAN FD family.
cf->can_id |= CAN_ERR_RESTARTED;
- netif_rx_ni(skb);
-
stats->rx_packets++;
stats->rx_bytes += cf->len;
+ netif_rx_ni(skb);
+
restart:
netdev_dbg(dev, "restarted\n");
priv->can_stats.restarts++;
void m_can_class_unregister(struct m_can_classdev *cdev)
{
unregister_candev(cdev->net);
-
- m_can_clk_stop(cdev);
}
EXPORT_SYMBOL_GPL(m_can_class_unregister);
}
-static struct can_bittiming_const tcan4x5x_bittiming_const = {
- .name = DEVICE_NAME,
- .tseg1_min = 2,
- .tseg1_max = 31,
- .tseg2_min = 2,
- .tseg2_max = 16,
- .sjw_max = 16,
- .brp_min = 1,
- .brp_max = 32,
- .brp_inc = 1,
-};
-
-static struct can_bittiming_const tcan4x5x_data_bittiming_const = {
- .name = DEVICE_NAME,
- .tseg1_min = 1,
- .tseg1_max = 32,
- .tseg2_min = 1,
- .tseg2_max = 16,
- .sjw_max = 16,
- .brp_min = 1,
- .brp_max = 32,
- .brp_inc = 1,
-};
-
static void tcan4x5x_check_wake(struct tcan4x5x_priv *priv)
{
int wake_state = 0;
mcan_class->dev = &spi->dev;
mcan_class->ops = &tcan4x5x_ops;
mcan_class->is_peripheral = true;
- mcan_class->bit_timing = &tcan4x5x_bittiming_const;
- mcan_class->data_timing = &tcan4x5x_data_bittiming_const;
mcan_class->net->irq = spi->irq;
spi_set_drvdata(spi, priv);
# SPDX-License-Identifier: GPL-2.0
config CAN_RCAR
- tristate "Renesas R-Car CAN controller"
+ tristate "Renesas R-Car and RZ/G CAN controller"
depends on ARCH_RENESAS || ARM
help
Say Y here if you want to use CAN controller found on Renesas R-Car
- SoCs.
+ or RZ/G SoCs.
To compile this driver as a module, choose M here: the module will
be called rcar_can.
struct mcp251xfd_tx_ring *tx_ring = priv->tx;
struct spi_transfer *last_xfer;
- tx_ring->tail += len;
-
/* Increment the TEF FIFO tail pointer 'len' times in
* a single SPI message.
- */
-
- /* Note:
+ *
+ * Note:
*
* "cs_change == 1" on the last transfer results in an
* active chip select after the complete SPI
if (err)
return err;
+ tx_ring->tail += len;
+
err = mcp251xfd_check_tef_tail(priv);
if (err)
return err;
else
skb = alloc_can_skb(priv->ndev, (struct can_frame **)&cfd);
- if (!cfd) {
+ if (!skb) {
stats->rx_dropped++;
return 0;
}
/* Increment the RX FIFO tail pointer 'len' times in a
* single SPI message.
- */
- ring->tail += len;
-
- /* Note:
+ *
+ * Note:
*
* "cs_change == 1" on the last transfer results in an
* active chip select after the complete SPI
last_xfer->cs_change = 1;
if (err)
return err;
+
+ ring->tail += len;
}
return 0;
else
memcpy(cfd->data, rm->d, cfd->len);
- peak_usb_netif_rx(skb, &usb_if->time_ref, le32_to_cpu(rm->ts_low));
-
netdev->stats.rx_packets++;
netdev->stats.rx_bytes += cfd->len;
+ peak_usb_netif_rx(skb, &usb_if->time_ref, le32_to_cpu(rm->ts_low));
+
return 0;
}
if (!skb)
return -ENOMEM;
- peak_usb_netif_rx(skb, &usb_if->time_ref, le32_to_cpu(sm->ts_low));
-
netdev->stats.rx_packets++;
netdev->stats.rx_bytes += cf->len;
+ peak_usb_netif_rx(skb, &usb_if->time_ref, le32_to_cpu(sm->ts_low));
+
return 0;
}
struct net_device *peer;
struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
struct net_device_stats *peerstats, *srcstats = &dev->stats;
+ u8 len;
if (can_dropped_invalid_skb(dev, skb))
return NETDEV_TX_OK;
skb->dev = peer;
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ len = cfd->len;
if (netif_rx_ni(skb) == NET_RX_SUCCESS) {
srcstats->tx_packets++;
- srcstats->tx_bytes += cfd->len;
+ srcstats->tx_bytes += len;
peerstats = &peer->stats;
peerstats->rx_packets++;
- peerstats->rx_bytes += cfd->len;
+ peerstats->rx_bytes += len;
}
out_unlock:
!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED))
return -EINVAL;
- if (vlan->vid_end > dev->num_vlans)
+ if (vlan->vid_end >= dev->num_vlans)
return -ERANGE;
b53_enable_vlan(dev, true, ds->vlan_filtering);
depends on HAS_IOMEM
depends on NET_DSA
depends on PTP_1588_CLOCK
+ depends on LEDS_CLASS
select NET_DSA_TAG_HELLCREEK
help
This driver adds support for Hirschmann Hellcreek TSN switches.
GSWIP_MDIO_PHY_FDUP_MASK)
/* GSWIP MII Registers */
-#define GSWIP_MII_CFG0 0x00
-#define GSWIP_MII_CFG1 0x02
-#define GSWIP_MII_CFG5 0x04
+#define GSWIP_MII_CFGp(p) (0x2 * (p))
#define GSWIP_MII_CFG_EN BIT(14)
#define GSWIP_MII_CFG_LDCLKDIS BIT(12)
#define GSWIP_MII_CFG_MODE_MIIP 0x0
static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set,
int port)
{
- switch (port) {
- case 0:
- gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG0);
- break;
- case 1:
- gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG1);
- break;
- case 5:
- gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG5);
- break;
- }
+ /* There's no MII_CFG register for the CPU port */
+ if (!dsa_is_cpu_port(priv->ds, port))
+ gswip_mii_mask(priv, clear, set, GSWIP_MII_CFGp(port));
}
static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set,
gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
/* Disable the xMII link */
- gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 0);
- gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 1);
- gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 5);
+ for (i = 0; i < priv->hw_info->max_ports; i++)
+ gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i);
/* enable special tag insertion on cpu port */
gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
phylink_set(mask, Pause);
phylink_set(mask, Asym_Pause);
- /* With the exclusion of MII and Reverse MII, we support Gigabit,
- * including Half duplex
+ /* With the exclusion of MII, Reverse MII and Reduced MII, we
+ * support Gigabit, including Half duplex
*/
if (state->interface != PHY_INTERFACE_MODE_MII &&
- state->interface != PHY_INTERFACE_MODE_REVMII) {
+ state->interface != PHY_INTERFACE_MODE_REVMII &&
+ state->interface != PHY_INTERFACE_MODE_RMII) {
phylink_set(mask, 1000baseT_Full);
phylink_set(mask, 1000baseT_Half);
}
{
struct gswip_priv *priv = ds->priv;
- /* Enable the xMII interface only for the external PHY */
- if (interface != PHY_INTERFACE_MODE_INTERNAL)
- gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
+ gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
}
static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset,
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[5:4] are located in VTU Operation 9:8
*/
config AQTION
tristate "aQuantia AQtion(tm) Support"
depends on PCI
- depends on X86_64 || ARM64 || COMPILE_TEST
depends on MACSEC || MACSEC=n
help
This enables the support for the aQuantia AQtion(tm) Ethernet card.
priv = netdev_priv(dev);
priv->clk = devm_clk_get_optional(&pdev->dev, "sw_sysport");
- if (IS_ERR(priv->clk))
- return PTR_ERR(priv->clk);
+ if (IS_ERR(priv->clk)) {
+ ret = PTR_ERR(priv->clk);
+ goto err_free_netdev;
+ }
/* Allocate number of TX rings */
priv->tx_rings = devm_kcalloc(&pdev->dev, txq,
NETIF_F_HW_VLAN_CTAG_TX;
dev->hw_features |= dev->features;
dev->vlan_features |= dev->features;
+ dev->max_mtu = UMAC_MAX_MTU_SIZE;
/* Request the WOL interrupt and advertise suspend if available */
priv->wol_irq_disabled = 1;
ctx->tqm_fp_rings_count = resp->tqm_fp_rings_count;
if (!ctx->tqm_fp_rings_count)
ctx->tqm_fp_rings_count = bp->max_q;
+ else if (ctx->tqm_fp_rings_count > BNXT_MAX_TQM_FP_RINGS)
+ ctx->tqm_fp_rings_count = BNXT_MAX_TQM_FP_RINGS;
- tqm_rings = ctx->tqm_fp_rings_count + 1;
+ tqm_rings = ctx->tqm_fp_rings_count + BNXT_MAX_TQM_SP_RINGS;
ctx_pg = kcalloc(tqm_rings, sizeof(*ctx_pg), GFP_KERNEL);
if (!ctx_pg) {
kfree(ctx);
pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl,
pg_dir = &req.tqm_sp_page_dir,
ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP;
- i < 9; i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
+ i < BNXT_MAX_TQM_RINGS;
+ i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) {
if (!(enables & ena))
continue;
*/
static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
{
+ pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
struct net_device *netdev = pci_get_drvdata(pdev);
struct bnxt *bp = netdev_priv(netdev);
int err = 0, off;
- pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT;
netdev_info(bp->dev, "PCI Slot Reset\n");
pci_save_state(pdev);
err = bnxt_hwrm_func_reset(bp);
- if (!err) {
- err = bnxt_hwrm_func_qcaps(bp);
- if (!err && netif_running(netdev))
- err = bnxt_open(netdev);
- }
- bnxt_ulp_start(bp, err);
- if (!err) {
- bnxt_reenable_sriov(bp);
+ if (!err)
result = PCI_ERS_RESULT_RECOVERED;
- }
- }
-
- if (result != PCI_ERS_RESULT_RECOVERED) {
- if (netif_running(netdev))
- dev_close(netdev);
- pci_disable_device(pdev);
}
rtnl_unlock();
static void bnxt_io_resume(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
+ struct bnxt *bp = netdev_priv(netdev);
+ int err;
+ netdev_info(bp->dev, "PCI Slot Resume\n");
rtnl_lock();
- netif_device_attach(netdev);
+ err = bnxt_hwrm_func_qcaps(bp);
+ if (!err && netif_running(netdev))
+ err = bnxt_open(netdev);
+
+ bnxt_ulp_start(bp, err);
+ if (!err) {
+ bnxt_reenable_sriov(bp);
+ netif_device_attach(netdev);
+ }
rtnl_unlock();
}
struct bnxt_ctx_pg_info **ctx_pg_tbl;
};
+#define BNXT_MAX_TQM_SP_RINGS 1
+#define BNXT_MAX_TQM_FP_RINGS 8
+#define BNXT_MAX_TQM_RINGS \
+ (BNXT_MAX_TQM_SP_RINGS + BNXT_MAX_TQM_FP_RINGS)
+
struct bnxt_ctx_mem_info {
u32 qp_max_entries;
u16 qp_min_qp1_entries;
struct bnxt_ctx_pg_info stat_mem;
struct bnxt_ctx_pg_info mrav_mem;
struct bnxt_ctx_pg_info tim_mem;
- struct bnxt_ctx_pg_info *tqm_mem[9];
+ struct bnxt_ctx_pg_info *tqm_mem[BNXT_MAX_TQM_RINGS];
};
struct bnxt_fw_health {
if (rc && ((struct hwrm_err_output *)&resp)->cmd_err ==
NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
- install.flags |=
+ install.flags =
cpu_to_le16(NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
rc = _hwrm_send_message_silent(bp, &install,
* UPDATE directory and try the flash again
*/
defrag_attempted = true;
+ install.flags = 0;
rc = __bnxt_flash_nvram(bp->dev,
BNX_DIR_TYPE_UPDATE,
BNX_DIR_ORDINAL_FIRST,
int bnxt_get_ulp_stat_ctxs(struct bnxt *bp)
{
- if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
- return BNXT_MIN_ROCE_STAT_CTXS;
+ if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) {
+ struct bnxt_en_dev *edev = bp->edev;
+
+ if (edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested)
+ return BNXT_MIN_ROCE_STAT_CTXS;
+ }
return 0;
}
{
long ferr, rate, rate_rounded;
- if (!bp->tx_clk || !(bp->caps & MACB_CAPS_CLK_HW_CHG))
+ if (!bp->tx_clk || (bp->caps & MACB_CAPS_CLK_HW_CHG))
return;
switch (speed) {
#define TCB_L2T_IX_M 0xfffULL
#define TCB_L2T_IX_V(x) ((x) << TCB_L2T_IX_S)
+#define TCB_T_FLAGS_W 1
+#define TCB_T_FLAGS_S 0
+#define TCB_T_FLAGS_M 0xffffffffffffffffULL
+#define TCB_T_FLAGS_V(x) ((__u64)(x) << TCB_T_FLAGS_S)
+
+#define TCB_FIELD_COOKIE_TFLAG 1
+
#define TCB_SMAC_SEL_W 0
#define TCB_SMAC_SEL_S 24
#define TCB_SMAC_SEL_M 0xffULL
void chtls_tcp_push(struct sock *sk, int flags);
int chtls_push_frames(struct chtls_sock *csk, int comp);
int chtls_set_tcb_tflag(struct sock *sk, unsigned int bit_pos, int val);
+void chtls_set_tcb_field_rpl_skb(struct sock *sk, u16 word,
+ u64 mask, u64 val, u8 cookie,
+ int through_l2t);
int chtls_setkey(struct chtls_sock *csk, u32 keylen, u32 mode, int cipher_type);
+void chtls_set_quiesce_ctrl(struct sock *sk, int val);
void skb_entail(struct sock *sk, struct sk_buff *skb, int flags);
unsigned int keyid_to_addr(int start_addr, int keyid);
void free_tls_keyid(struct sock *sk);
#include "chtls.h"
#include "chtls_cm.h"
#include "clip_tbl.h"
+#include "t4_tcb.h"
/*
* State transitions and actions for close. Note that if we are in SYN_SENT
if (sk->sk_state != TCP_SYN_RECV)
chtls_send_abort(sk, mode, skb);
else
- goto out;
+ chtls_set_tcb_field_rpl_skb(sk, TCB_T_FLAGS_W,
+ TCB_T_FLAGS_V(TCB_T_FLAGS_M), 0,
+ TCB_FIELD_COOKIE_TFLAG, 1);
return;
out:
while (!skb_queue_empty(&listen_ctx->synq)) {
struct chtls_sock *csk =
- container_of((struct synq *)__skb_dequeue
+ container_of((struct synq *)skb_peek
(&listen_ctx->synq), struct chtls_sock, synq);
struct sock *child = csk->sk;
const struct cpl_pass_accept_req *req,
struct chtls_dev *cdev)
{
+ struct adapter *adap = pci_get_drvdata(cdev->pdev);
struct neighbour *n = NULL;
struct inet_sock *newinet;
const struct iphdr *iph;
struct dst_entry *dst;
struct tcp_sock *tp;
struct sock *newsk;
+ bool found = false;
u16 port_id;
int rxq_idx;
- int step;
+ int step, i;
iph = (const struct iphdr *)network_hdr;
newsk = tcp_create_openreq_child(lsk, oreq, cdev->askb);
n = dst_neigh_lookup(dst, &ip6h->saddr);
#endif
}
- if (!n)
+ if (!n || !n->dev)
goto free_sk;
ndev = n->dev;
if (is_vlan_dev(ndev))
ndev = vlan_dev_real_dev(ndev);
+ for_each_port(adap, i)
+ if (cdev->ports[i] == ndev)
+ found = true;
+
+ if (!found)
+ goto free_dst;
+
port_id = cxgb4_port_idx(ndev);
csk = chtls_sock_create(cdev);
free_csk:
chtls_sock_release(&csk->kref);
free_dst:
+ neigh_release(n);
dst_release(dst);
free_sk:
inet_csk_prepare_forced_close(newsk);
newsk = chtls_recv_sock(sk, oreq, network_hdr, req, cdev);
if (!newsk)
- goto free_oreq;
+ goto reject;
if (chtls_get_module(newsk))
goto reject;
kfree_skb(skb);
return;
-free_oreq:
- chtls_reqsk_free(oreq);
reject:
mk_tid_release(reply_skb, 0, tid);
cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb);
sk_wake_async(sk, 0, POLL_OUT);
data = lookup_stid(cdev->tids, stid);
+ if (!data) {
+ /* listening server close */
+ kfree_skb(skb);
+ goto unlock;
+ }
lsk = ((struct listen_ctx *)data)->lsk;
bh_lock_sock(lsk);
else if (tcp_sk(sk)->linger2 < 0 &&
!csk_flag_nochk(csk, CSK_ABORT_SHUTDOWN))
chtls_abort_conn(sk, skb);
+ else if (csk_flag_nochk(csk, CSK_TX_DATA_SENT))
+ chtls_set_quiesce_ctrl(sk, 0);
break;
default:
pr_info("close_con_rpl in bad state %d\n", sk->sk_state);
spin_unlock_bh(&cdev->deferq.lock);
}
-static void send_abort_rpl(struct sock *sk, struct sk_buff *skb,
- struct chtls_dev *cdev, int status, int queue)
-{
- struct cpl_abort_req_rss *req = cplhdr(skb);
- struct sk_buff *reply_skb;
- struct chtls_sock *csk;
-
- csk = rcu_dereference_sk_user_data(sk);
-
- reply_skb = alloc_skb(sizeof(struct cpl_abort_rpl),
- GFP_KERNEL);
-
- if (!reply_skb) {
- req->status = (queue << 1);
- t4_defer_reply(skb, cdev, send_defer_abort_rpl);
- return;
- }
-
- set_abort_rpl_wr(reply_skb, GET_TID(req), status);
- kfree_skb(skb);
-
- set_wr_txq(reply_skb, CPL_PRIORITY_DATA, queue);
- if (csk_conn_inline(csk)) {
- struct l2t_entry *e = csk->l2t_entry;
-
- if (e && sk->sk_state != TCP_SYN_RECV) {
- cxgb4_l2t_send(csk->egress_dev, reply_skb, e);
- return;
- }
- }
- cxgb4_ofld_send(cdev->lldi->ports[0], reply_skb);
-}
-
static void chtls_send_abort_rpl(struct sock *sk, struct sk_buff *skb,
struct chtls_dev *cdev,
int status, int queue)
queue = csk->txq_idx;
skb->sk = NULL;
+ chtls_send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev,
+ CPL_ABORT_NO_RST, queue);
do_abort_syn_rcv(child, lsk);
- send_abort_rpl(child, skb, BLOG_SKB_CB(skb)->cdev,
- CPL_ABORT_NO_RST, queue);
}
static int abort_syn_rcv(struct sock *sk, struct sk_buff *skb)
if (!sock_owned_by_user(psk)) {
int queue = csk->txq_idx;
+ chtls_send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue);
do_abort_syn_rcv(sk, psk);
- send_abort_rpl(sk, skb, cdev, CPL_ABORT_NO_RST, queue);
} else {
skb->sk = sk;
BLOG_SKB_CB(skb)->backlog_rcv = bl_abort_syn_rcv;
int queue = csk->txq_idx;
if (is_neg_adv(req->status)) {
- if (sk->sk_state == TCP_SYN_RECV)
- chtls_set_tcb_tflag(sk, 0, 0);
-
kfree_skb(skb);
return;
}
if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb))
return;
- chtls_release_resources(sk);
- chtls_conn_done(sk);
}
chtls_send_abort_rpl(sk, skb, BLOG_SKB_CB(skb)->cdev,
rst_status, queue);
+ chtls_release_resources(sk);
+ chtls_conn_done(sk);
}
static void chtls_abort_rpl_rss(struct sock *sk, struct sk_buff *skb)
return 0;
}
+static int chtls_set_tcb_rpl(struct chtls_dev *cdev, struct sk_buff *skb)
+{
+ struct cpl_set_tcb_rpl *rpl = cplhdr(skb) + RSS_HDR;
+ unsigned int hwtid = GET_TID(rpl);
+ struct sock *sk;
+
+ sk = lookup_tid(cdev->tids, hwtid);
+
+ /* return EINVAL if socket doesn't exist */
+ if (!sk)
+ return -EINVAL;
+
+ /* Reusing the skb as size of cpl_set_tcb_field structure
+ * is greater than cpl_abort_req
+ */
+ if (TCB_COOKIE_G(rpl->cookie) == TCB_FIELD_COOKIE_TFLAG)
+ chtls_send_abort(sk, CPL_ABORT_SEND_RST, NULL);
+
+ kfree_skb(skb);
+ return 0;
+}
+
chtls_handler_func chtls_handlers[NUM_CPL_CMDS] = {
[CPL_PASS_OPEN_RPL] = chtls_pass_open_rpl,
[CPL_CLOSE_LISTSRV_RPL] = chtls_close_listsrv_rpl,
[CPL_CLOSE_CON_RPL] = chtls_conn_cpl,
[CPL_ABORT_REQ_RSS] = chtls_conn_cpl,
[CPL_ABORT_RPL_RSS] = chtls_conn_cpl,
- [CPL_FW4_ACK] = chtls_wr_ack,
+ [CPL_FW4_ACK] = chtls_wr_ack,
+ [CPL_SET_TCB_RPL] = chtls_set_tcb_rpl,
};
return ret < 0 ? ret : 0;
}
+void chtls_set_tcb_field_rpl_skb(struct sock *sk, u16 word,
+ u64 mask, u64 val, u8 cookie,
+ int through_l2t)
+{
+ struct sk_buff *skb;
+ unsigned int wrlen;
+
+ wrlen = sizeof(struct cpl_set_tcb_field) + sizeof(struct ulptx_idata);
+ wrlen = roundup(wrlen, 16);
+
+ skb = alloc_skb(wrlen, GFP_KERNEL | __GFP_NOFAIL);
+ if (!skb)
+ return;
+
+ __set_tcb_field(sk, skb, word, mask, val, cookie, 0);
+ send_or_defer(sk, tcp_sk(sk), skb, through_l2t);
+}
+
/*
* Set one of the t_flags bits in the TCB.
*/
TF_RX_QUIESCE_V(val));
}
+void chtls_set_quiesce_ctrl(struct sock *sk, int val)
+{
+ struct chtls_sock *csk;
+ struct sk_buff *skb;
+ unsigned int wrlen;
+ int ret;
+
+ wrlen = sizeof(struct cpl_set_tcb_field) + sizeof(struct ulptx_idata);
+ wrlen = roundup(wrlen, 16);
+
+ skb = alloc_skb(wrlen, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ csk = rcu_dereference_sk_user_data(sk);
+
+ __set_tcb_field(sk, skb, 1, TF_RX_QUIESCE_V(1), 0, 0, 1);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id);
+ ret = cxgb4_ofld_send(csk->egress_dev, skb);
+ if (ret < 0)
+ kfree_skb(skb);
+}
+
/* TLS Key bitmap processing */
int chtls_init_kmap(struct chtls_dev *cdev, struct cxgb4_lld_info *lldi)
{
ret = mdiobus_register(priv->mdio);
if (ret) {
dev_err(&netdev->dev, "failed to register MDIO bus\n");
- goto free2;
+ goto free3;
}
ret = ethoc_mdio_probe(netdev);
netif_napi_del(&priv->napi);
error:
mdiobus_unregister(priv->mdio);
+free3:
mdiobus_free(priv->mdio);
free2:
clk_disable_unprepare(priv->clk);
};
module_platform_driver(fs_enet_bb_mdio_driver);
+MODULE_LICENSE("GPL");
};
module_platform_driver(fs_enet_fec_mdio_driver);
+MODULE_LICENSE("GPL");
INIT_WORK(&ugeth->timeout_work, ucc_geth_timeout_work);
netif_napi_add(dev, &ugeth->napi, ucc_geth_poll, 64);
dev->mtu = 1500;
+ dev->max_mtu = 1518;
ugeth->msg_enable = netif_msg_init(debug.msg_enable, UGETH_MSG_DEFAULT);
ugeth->phy_interface = phy_interface;
struct device_node *np = ofdev->dev.of_node;
unregister_netdev(dev);
- free_netdev(dev);
ucc_geth_memclean(ugeth);
if (of_phy_is_fixed_link(np))
of_phy_deregister_fixed_link(np);
of_node_put(ugeth->ug_info->tbi_node);
of_node_put(ugeth->ug_info->phy_node);
+ free_netdev(dev);
return 0;
}
u32 vtagtable[0x8]; /* 8 4-byte VLAN tags */
u32 tqptr; /* a base pointer to the Tx Queues Memory
Region */
- u8 res2[0x80 - 0x74];
+ u8 res2[0x78 - 0x74];
+ u64 snums_en;
+ u32 l2l3baseptr; /* top byte consists of a few other bit fields */
+
+ u16 mtu[8];
+ u8 res3[0xa8 - 0x94];
+ u32 wrrtablebase; /* top byte is reserved */
+ u8 res4[0xc0 - 0xac];
} __packed;
/* structure representing Extended Filtering Global Parameters in PRAM */
/* for mutl buffer*/
new_skb = skb_copy(skb, GFP_ATOMIC);
dev_kfree_skb_any(skb);
+ if (!new_skb) {
+ netdev_err(ndev, "skb alloc failed\n");
+ return;
+ }
skb = new_skb;
check_ok = 0;
#define hclge_mbx_ring_ptr_move_crq(crq) \
(crq->next_to_use = (crq->next_to_use + 1) % crq->desc_num)
#define hclge_mbx_tail_ptr_move_arq(arq) \
- (arq.tail = (arq.tail + 1) % HCLGE_MBX_MAX_ARQ_MSG_SIZE)
+ (arq.tail = (arq.tail + 1) % HCLGE_MBX_MAX_ARQ_MSG_NUM)
#define hclge_mbx_head_ptr_move_arq(arq) \
- (arq.head = (arq.head + 1) % HCLGE_MBX_MAX_ARQ_MSG_SIZE)
+ (arq.head = (arq.head + 1) % HCLGE_MBX_MAX_ARQ_MSG_NUM)
#endif
handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK;
handle->flags |= HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK;
- if (hdev->hw.mac.phydev) {
+ if (hdev->hw.mac.phydev && hdev->hw.mac.phydev->drv &&
+ hdev->hw.mac.phydev->drv->set_loopback) {
count += 1;
handle->flags |= HNAE3_SUPPORT_PHY_LOOPBACK;
}
req->ipv4_sctp_en = tuple_sets;
break;
case SCTP_V6_FLOW:
- if ((nfc->data & RXH_L4_B_0_1) ||
- (nfc->data & RXH_L4_B_2_3))
+ if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
+ (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)))
return -EINVAL;
req->ipv6_sctp_en = tuple_sets;
vport[i].rss_tuple_sets.ipv6_udp_en =
HCLGE_RSS_INPUT_TUPLE_OTHER;
vport[i].rss_tuple_sets.ipv6_sctp_en =
+ hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 ?
+ HCLGE_RSS_INPUT_TUPLE_SCTP_NO_PORT :
HCLGE_RSS_INPUT_TUPLE_SCTP;
vport[i].rss_tuple_sets.ipv6_fragment_en =
HCLGE_RSS_INPUT_TUPLE_OTHER;
#define HCLGE_D_IP_BIT BIT(2)
#define HCLGE_S_IP_BIT BIT(3)
#define HCLGE_V_TAG_BIT BIT(4)
+#define HCLGE_RSS_INPUT_TUPLE_SCTP_NO_PORT \
+ (HCLGE_D_IP_BIT | HCLGE_S_IP_BIT | HCLGE_V_TAG_BIT)
#define HCLGE_RSS_TC_SIZE_0 1
#define HCLGE_RSS_TC_SIZE_1 2
req->ipv4_sctp_en = tuple_sets;
break;
case SCTP_V6_FLOW:
- if ((nfc->data & RXH_L4_B_0_1) ||
- (nfc->data & RXH_L4_B_2_3))
+ if (hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 &&
+ (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)))
return -EINVAL;
req->ipv6_sctp_en = tuple_sets;
tuple_sets->ipv4_fragment_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
tuple_sets->ipv6_tcp_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
tuple_sets->ipv6_udp_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
- tuple_sets->ipv6_sctp_en = HCLGEVF_RSS_INPUT_TUPLE_SCTP;
+ tuple_sets->ipv6_sctp_en =
+ hdev->ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2 ?
+ HCLGEVF_RSS_INPUT_TUPLE_SCTP_NO_PORT :
+ HCLGEVF_RSS_INPUT_TUPLE_SCTP;
tuple_sets->ipv6_fragment_en = HCLGEVF_RSS_INPUT_TUPLE_OTHER;
}
#define HCLGEVF_D_IP_BIT BIT(2)
#define HCLGEVF_S_IP_BIT BIT(3)
#define HCLGEVF_V_TAG_BIT BIT(4)
+#define HCLGEVF_RSS_INPUT_TUPLE_SCTP_NO_PORT \
+ (HCLGEVF_D_IP_BIT | HCLGEVF_S_IP_BIT | HCLGEVF_V_TAG_BIT)
#define HCLGEVF_STATS_TIMER_INTERVAL 36U
release_rx_pools(adapter);
release_napi(adapter);
+ release_login_buffer(adapter);
release_login_rsp_buffer(adapter);
}
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(60 * HZ);
}
- } else if (!(rwi->reset_reason == VNIC_RESET_FATAL &&
- adapter->from_passive_init)) {
+ } else {
rc = do_reset(adapter, rwi, reset_state);
}
kfree(rwi);
int rc;
if (!scrq) {
- netdev_dbg(adapter->netdev,
- "Invalid scrq reset. irq (%d) or msgs (%p).\n",
- scrq->irq, scrq->msgs);
+ netdev_dbg(adapter->netdev, "Invalid scrq reset.\n");
return -EINVAL;
}
return -1;
}
+ release_login_buffer(adapter);
release_login_rsp_buffer(adapter);
+
client_data_len = vnic_client_data_len(adapter);
buffer_size =
#define FLAG2_DFLT_CRC_STRIPPING BIT(12)
#define FLAG2_CHECK_RX_HWTSTAMP BIT(13)
#define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14)
+#define FLAG2_ENABLE_S0IX_FLOWS BIT(15)
#define E1000_RX_DESC_PS(R, i) \
(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
int stat_offset;
};
+static const char e1000e_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define E1000E_PRIV_FLAGS_S0IX_ENABLED BIT(0)
+ "s0ix-enabled",
+};
+
+#define E1000E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(e1000e_priv_flags_strings)
+
#define E1000_STAT(str, m) { \
.stat_string = str, \
.type = E1000_STATS, \
return E1000_TEST_LEN;
case ETH_SS_STATS:
return E1000_STATS_LEN;
+ case ETH_SS_PRIV_FLAGS:
+ return E1000E_PRIV_FLAGS_STR_LEN;
default:
return -EOPNOTSUPP;
}
p += ETH_GSTRING_LEN;
}
break;
+ case ETH_SS_PRIV_FLAGS:
+ memcpy(data, e1000e_priv_flags_strings,
+ E1000E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN);
+ break;
}
}
return 0;
}
+static u32 e1000e_get_priv_flags(struct net_device *netdev)
+{
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ u32 priv_flags = 0;
+
+ if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
+ priv_flags |= E1000E_PRIV_FLAGS_S0IX_ENABLED;
+
+ return priv_flags;
+}
+
+static int e1000e_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+ struct e1000_adapter *adapter = netdev_priv(netdev);
+ unsigned int flags2 = adapter->flags2;
+
+ flags2 &= ~FLAG2_ENABLE_S0IX_FLOWS;
+ if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) {
+ struct e1000_hw *hw = &adapter->hw;
+
+ if (hw->mac.type < e1000_pch_cnp)
+ return -EINVAL;
+ flags2 |= FLAG2_ENABLE_S0IX_FLOWS;
+ }
+
+ if (flags2 != adapter->flags2)
+ adapter->flags2 = flags2;
+
+ return 0;
+}
+
static const struct ethtool_ops e1000_ethtool_ops = {
.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS,
.get_drvinfo = e1000_get_drvinfo,
.set_eee = e1000e_set_eee,
.get_link_ksettings = e1000_get_link_ksettings,
.set_link_ksettings = e1000_set_link_ksettings,
+ .get_priv_flags = e1000e_get_priv_flags,
+ .set_priv_flags = e1000e_set_priv_flags,
};
void e1000e_set_ethtool_ops(struct net_device *netdev)
return 0;
if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) {
+ struct e1000_adapter *adapter = hw->adapter;
+ bool firmware_bug = false;
+
if (force) {
/* Request ME un-configure ULP mode in the PHY */
mac_reg = er32(H2ME);
ew32(H2ME, mac_reg);
}
- /* Poll up to 300msec for ME to clear ULP_CFG_DONE. */
+ /* Poll up to 2.5 seconds for ME to clear ULP_CFG_DONE.
+ * If this takes more than 1 second, show a warning indicating a
+ * firmware bug
+ */
while (er32(FWSM) & E1000_FWSM_ULP_CFG_DONE) {
- if (i++ == 30) {
+ if (i++ == 250) {
ret_val = -E1000_ERR_PHY;
goto out;
}
+ if (i > 100 && !firmware_bug)
+ firmware_bug = true;
usleep_range(10000, 11000);
}
- e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
+ if (firmware_bug)
+ e_warn("ULP_CONFIG_DONE took %dmsec. This is a firmware bug\n", i * 10);
+ else
+ e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10);
if (force) {
mac_reg = er32(H2ME);
{0, NULL}
};
-struct e1000e_me_supported {
- u16 device_id; /* supported device ID */
-};
-
-static const struct e1000e_me_supported me_supported[] = {
- {E1000_DEV_ID_PCH_LPT_I217_LM},
- {E1000_DEV_ID_PCH_LPTLP_I218_LM},
- {E1000_DEV_ID_PCH_I218_LM2},
- {E1000_DEV_ID_PCH_I218_LM3},
- {E1000_DEV_ID_PCH_SPT_I219_LM},
- {E1000_DEV_ID_PCH_SPT_I219_LM2},
- {E1000_DEV_ID_PCH_LBG_I219_LM3},
- {E1000_DEV_ID_PCH_SPT_I219_LM4},
- {E1000_DEV_ID_PCH_SPT_I219_LM5},
- {E1000_DEV_ID_PCH_CNP_I219_LM6},
- {E1000_DEV_ID_PCH_CNP_I219_LM7},
- {E1000_DEV_ID_PCH_ICP_I219_LM8},
- {E1000_DEV_ID_PCH_ICP_I219_LM9},
- {E1000_DEV_ID_PCH_CMP_I219_LM10},
- {E1000_DEV_ID_PCH_CMP_I219_LM11},
- {E1000_DEV_ID_PCH_CMP_I219_LM12},
- {E1000_DEV_ID_PCH_TGP_I219_LM13},
- {E1000_DEV_ID_PCH_TGP_I219_LM14},
- {E1000_DEV_ID_PCH_TGP_I219_LM15},
- {0}
-};
-
-static bool e1000e_check_me(u16 device_id)
-{
- struct e1000e_me_supported *id;
-
- for (id = (struct e1000e_me_supported *)me_supported;
- id->device_id; id++)
- if (device_id == id->device_id)
- return true;
-
- return false;
-}
-
/**
* __ew32_prepare - prepare to write to MAC CSR register on certain parts
* @hw: pointer to the HW structure
struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
struct e1000_adapter *adapter = netdev_priv(netdev);
struct pci_dev *pdev = to_pci_dev(dev);
- struct e1000_hw *hw = &adapter->hw;
int rc;
e1000e_flush_lpic(pdev);
e1000e_pm_freeze(dev);
rc = __e1000_shutdown(pdev, false);
- if (rc)
+ if (rc) {
e1000e_pm_thaw(dev);
-
- /* Introduce S0ix implementation */
- if (hw->mac.type >= e1000_pch_cnp &&
- !e1000e_check_me(hw->adapter->pdev->device))
- e1000e_s0ix_entry_flow(adapter);
+ } else {
+ /* Introduce S0ix implementation */
+ if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
+ e1000e_s0ix_entry_flow(adapter);
+ }
return rc;
}
struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
struct e1000_adapter *adapter = netdev_priv(netdev);
struct pci_dev *pdev = to_pci_dev(dev);
- struct e1000_hw *hw = &adapter->hw;
int rc;
/* Introduce S0ix implementation */
- if (hw->mac.type >= e1000_pch_cnp &&
- !e1000e_check_me(hw->adapter->pdev->device))
+ if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
e1000e_s0ix_exit_flow(adapter);
rc = __e1000_resume(pdev);
if (!(adapter->flags & FLAG_HAS_AMT))
e1000e_get_hw_control(adapter);
+ if (hw->mac.type >= e1000_pch_cnp)
+ adapter->flags2 |= FLAG2_ENABLE_S0IX_FLOWS;
+
strlcpy(netdev->name, "eth%d", sizeof(netdev->name));
err = register_netdev(netdev);
if (err)
__I40E_RESET_INTR_RECEIVED,
__I40E_REINIT_REQUESTED,
__I40E_PF_RESET_REQUESTED,
+ __I40E_PF_RESET_AND_REBUILD_REQUESTED,
__I40E_CORE_RESET_REQUESTED,
__I40E_GLOBAL_RESET_REQUESTED,
__I40E_EMP_RESET_INTR_RECEIVED,
};
#define I40E_PF_RESET_FLAG BIT_ULL(__I40E_PF_RESET_REQUESTED)
+#define I40E_PF_RESET_AND_REBUILD_FLAG \
+ BIT_ULL(__I40E_PF_RESET_AND_REBUILD_REQUESTED)
/* VSI state flags */
enum i40e_vsi_state_t {
static void i40e_determine_queue_usage(struct i40e_pf *pf);
static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired);
+static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit,
+ bool lock_acquired);
static int i40e_reset(struct i40e_pf *pf);
static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf);
"FW LLDP is disabled\n" :
"FW LLDP is enabled\n");
+ } else if (reset_flags & I40E_PF_RESET_AND_REBUILD_FLAG) {
+ /* Request a PF Reset
+ *
+ * Resets PF and reinitializes PFs VSI.
+ */
+ i40e_prep_for_reset(pf, lock_acquired);
+ i40e_reset_and_rebuild(pf, true, lock_acquired);
+
} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
int v;
if (num_vfs) {
if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
- i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
+ i40e_do_reset_safe(pf, I40E_PF_RESET_AND_REBUILD_FLAG);
}
ret = i40e_pci_sriov_enable(pdev, num_vfs);
goto sriov_configure_out;
if (!pci_vfs_assigned(pf->pdev)) {
i40e_free_vfs(pf);
pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
- i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
+ i40e_do_reset_safe(pf, I40E_PF_RESET_AND_REBUILD_FLAG);
} else {
dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
ret = -EINVAL;
* SBP is *not* set in PRT_SBPVSI (default not set).
*/
skb = i40e_construct_skb_zc(rx_ring, *bi);
- *bi = NULL;
if (!skb) {
rx_ring->rx_stats.alloc_buff_failed++;
break;
}
+ *bi = NULL;
cleaned_count++;
i40e_inc_ntc(rx_ring);
netif_tx_stop_all_queues(netdev);
if (CLIENT_ALLOWED(adapter)) {
err = iavf_lan_add_device(adapter);
- if (err) {
- rtnl_unlock();
+ if (err)
dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
err);
- }
}
dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
if (netdev->features & NETIF_F_GRO)
struct bpf_prog *old_prog;
if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
- NL_SET_ERR_MSG_MOD(extack, "Jumbo frames not supported on XDP");
+ NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP");
return -EOPNOTSUPP;
}
err = mvneta_port_power_up(pp, pp->phy_interface);
if (err < 0) {
dev_err(&pdev->dev, "can't power up port\n");
- return err;
+ goto err_netdev;
}
/* Armada3700 network controller does not support per-cpu
regmap_read(priv->sysctrl_base, GENCONF_CTRL0, &val);
if (port->gop_id == 2)
- val |= GENCONF_CTRL0_PORT0_RGMII | GENCONF_CTRL0_PORT1_RGMII;
+ val |= GENCONF_CTRL0_PORT0_RGMII;
else if (port->gop_id == 3)
val |= GENCONF_CTRL0_PORT1_RGMII_MII;
regmap_write(priv->sysctrl_base, GENCONF_CTRL0, val);
static void mvpp2_tx_pkts_coal_set(struct mvpp2_port *port,
struct mvpp2_tx_queue *txq)
{
- unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu());
+ unsigned int thread;
u32 val;
if (txq->done_pkts_coal > MVPP2_TXQ_THRESH_MASK)
txq->done_pkts_coal = MVPP2_TXQ_THRESH_MASK;
val = (txq->done_pkts_coal << MVPP2_TXQ_THRESH_OFFSET);
- mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id);
- mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val);
-
- put_cpu();
+ /* PKT-coalescing registers are per-queue + per-thread */
+ for (thread = 0; thread < MVPP2_MAX_THREADS; thread++) {
+ mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id);
+ mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val);
+ }
}
static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz)
struct mvpp2 *priv = port->priv;
struct mvpp2_txq_pcpu *txq_pcpu;
unsigned int thread;
- int queue, err;
+ int queue, err, val;
/* Checks for hardware constraints */
if (port->first_rxq + port->nrxqs >
mvpp2_egress_disable(port);
mvpp2_port_disable(port);
+ if (mvpp2_is_xlg(port->phy_interface)) {
+ val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+ val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_PASS;
+ val |= MVPP22_XLG_CTRL0_FORCE_LINK_DOWN;
+ writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+ } else {
+ val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+ val |= MVPP2_GMAC_FORCE_LINK_DOWN;
+ writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+ }
+
port->tx_time_coal = MVPP2_TXDONE_COAL_USEC;
port->txqs = devm_kcalloc(dev, port->ntxqs, sizeof(*port->txqs),
phylink_set(mask, Autoneg);
phylink_set_port_modes(mask);
- phylink_set(mask, Pause);
- phylink_set(mask, Asym_Pause);
switch (state->interface) {
case PHY_INTERFACE_MODE_10GBASER:
return -EINVAL;
}
+/* Drop flow control pause frames */
+static void mvpp2_prs_drop_fc(struct mvpp2 *priv)
+{
+ unsigned char da[ETH_ALEN] = { 0x01, 0x80, 0xC2, 0x00, 0x00, 0x01 };
+ struct mvpp2_prs_entry pe;
+ unsigned int len;
+
+ memset(&pe, 0, sizeof(pe));
+
+ /* For all ports - drop flow control frames */
+ pe.index = MVPP2_PE_FC_DROP;
+ mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
+
+ /* Set match on DA */
+ len = ETH_ALEN;
+ while (len--)
+ mvpp2_prs_tcam_data_byte_set(&pe, len, da[len], 0xff);
+
+ mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_DROP_MASK,
+ MVPP2_PRS_RI_DROP_MASK);
+
+ mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_GEN_BIT, 1);
+ mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+
+ /* Mask all ports */
+ mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
+
+ /* Update shadow table and hw entry */
+ mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_MAC);
+ mvpp2_prs_hw_write(priv, &pe);
+}
+
/* Enable/disable dropping all mac da's */
static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
{
mvpp2_prs_hw_write(priv, &pe);
/* Create dummy entries for drop all and promiscuous modes */
+ mvpp2_prs_drop_fc(priv);
mvpp2_prs_mac_drop_all_set(priv, 0, false);
mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_UNI_CAST, false);
mvpp2_prs_mac_promisc_set(priv, 0, MVPP2_PRS_L2_MULTI_CAST, false);
mvpp2_prs_sram_next_lu_set(&pe, MVPP2_PRS_LU_IP6);
mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP6,
MVPP2_PRS_RI_L3_PROTO_MASK);
- /* Skip eth_type + 4 bytes of IPv6 header */
- mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + 4,
+ /* Jump to DIP of IPV6 header */
+ mvpp2_prs_sram_shift_set(&pe, MVPP2_ETH_TYPE_LEN + 8 +
+ MVPP2_MAX_L3_ADDR_SIZE,
MVPP2_PRS_SRAM_OP_SEL_SHIFT_ADD);
/* Set L3 offset */
mvpp2_prs_sram_offset_set(&pe, MVPP2_PRS_SRAM_UDF_TYPE_L3,
#define MVPP2_PE_VID_EDSA_FLTR_DEFAULT (MVPP2_PRS_TCAM_SRAM_SIZE - 7)
#define MVPP2_PE_VLAN_DBL (MVPP2_PRS_TCAM_SRAM_SIZE - 6)
#define MVPP2_PE_VLAN_NONE (MVPP2_PRS_TCAM_SRAM_SIZE - 5)
-/* reserved */
+#define MVPP2_PE_FC_DROP (MVPP2_PRS_TCAM_SRAM_SIZE - 4)
#define MVPP2_PE_MAC_MC_PROMISCUOUS (MVPP2_PRS_TCAM_SRAM_SIZE - 3)
#define MVPP2_PE_MAC_UC_PROMISCUOUS (MVPP2_PRS_TCAM_SRAM_SIZE - 2)
#define MVPP2_PE_MAC_NON_PROMISCUOUS (MVPP2_PRS_TCAM_SRAM_SIZE - 1)
if (!lmac)
return -ENOMEM;
lmac->name = kcalloc(1, sizeof("cgx_fwi_xxx_yyy"), GFP_KERNEL);
- if (!lmac->name)
- return -ENOMEM;
+ if (!lmac->name) {
+ err = -ENOMEM;
+ goto err_lmac_free;
+ }
sprintf(lmac->name, "cgx_fwi_%d_%d", cgx->cgx_id, i);
lmac->lmac_id = i;
lmac->cgx = cgx;
CGX_LMAC_FWI + i * 9),
cgx_fwi_event_handler, 0, lmac->name, lmac);
if (err)
- return err;
+ goto err_irq;
/* Enable interrupt */
cgx_write(cgx, lmac->lmac_id, CGXX_CMRX_INT_ENA_W1S,
}
return cgx_lmac_verify_fwi_version(cgx);
+
+err_irq:
+ kfree(lmac->name);
+err_lmac_free:
+ kfree(lmac);
+ return err;
}
static int cgx_lmac_exit(struct cgx *cgx)
int pf = rvu_get_pf(req->hdr.pcifunc);
u8 cgx_id, lmac_id;
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
cgx_lmac_addr_set(cgx_id, lmac_id, req->mac_addr);
int rc = 0, i;
u64 cfg;
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
rsp->hdr.rc = rc;
if (!reg_c0)
return true;
+ /* If reg_c0 is not equal to the default flow tag then skb->mark
+ * is not supported and must be reset back to 0.
+ */
+ skb->mark = 0;
+
priv = netdev_priv(skb->dev);
esw = priv->mdev->priv.eswitch;
u16 zone;
};
-struct mlx5_ct_shared_counter {
+struct mlx5_ct_counter {
struct mlx5_fc *counter;
refcount_t refcount;
+ bool is_shared;
};
struct mlx5_ct_entry {
struct rhash_head node;
struct rhash_head tuple_node;
struct rhash_head tuple_nat_node;
- struct mlx5_ct_shared_counter *shared_counter;
+ struct mlx5_ct_counter *counter;
unsigned long cookie;
unsigned long restore_cookie;
struct mlx5_ct_tuple tuple;
}
static void
-mlx5_tc_ct_shared_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
+mlx5_tc_ct_counter_put(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_entry *entry)
{
- if (!refcount_dec_and_test(&entry->shared_counter->refcount))
+ if (entry->counter->is_shared &&
+ !refcount_dec_and_test(&entry->counter->refcount))
return;
- mlx5_fc_destroy(ct_priv->dev, entry->shared_counter->counter);
- kfree(entry->shared_counter);
+ mlx5_fc_destroy(ct_priv->dev, entry->counter->counter);
+ kfree(entry->counter);
}
static void
attr->dest_ft = ct_priv->post_ct;
attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
attr->outer_match_level = MLX5_MATCH_L4;
- attr->counter = entry->shared_counter->counter;
+ attr->counter = entry->counter->counter;
attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
mlx5_tc_ct_set_tuple_match(netdev_priv(ct_priv->netdev), spec, flow_rule);
return err;
}
-static struct mlx5_ct_shared_counter *
+static struct mlx5_ct_counter *
+mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv)
+{
+ struct mlx5_ct_counter *counter;
+ int ret;
+
+ counter = kzalloc(sizeof(*counter), GFP_KERNEL);
+ if (!counter)
+ return ERR_PTR(-ENOMEM);
+
+ counter->is_shared = false;
+ counter->counter = mlx5_fc_create(ct_priv->dev, true);
+ if (IS_ERR(counter->counter)) {
+ ct_dbg("Failed to create counter for ct entry");
+ ret = PTR_ERR(counter->counter);
+ kfree(counter);
+ return ERR_PTR(ret);
+ }
+
+ return counter;
+}
+
+static struct mlx5_ct_counter *
mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv,
struct mlx5_ct_entry *entry)
{
struct mlx5_ct_tuple rev_tuple = entry->tuple;
- struct mlx5_ct_shared_counter *shared_counter;
- struct mlx5_core_dev *dev = ct_priv->dev;
+ struct mlx5_ct_counter *shared_counter;
struct mlx5_ct_entry *rev_entry;
__be16 tmp_port;
int ret;
rev_entry = rhashtable_lookup_fast(&ct_priv->ct_tuples_ht, &rev_tuple,
tuples_ht_params);
if (rev_entry) {
- if (refcount_inc_not_zero(&rev_entry->shared_counter->refcount)) {
+ if (refcount_inc_not_zero(&rev_entry->counter->refcount)) {
mutex_unlock(&ct_priv->shared_counter_lock);
- return rev_entry->shared_counter;
+ return rev_entry->counter;
}
}
mutex_unlock(&ct_priv->shared_counter_lock);
- shared_counter = kzalloc(sizeof(*shared_counter), GFP_KERNEL);
- if (!shared_counter)
- return ERR_PTR(-ENOMEM);
-
- shared_counter->counter = mlx5_fc_create(dev, true);
- if (IS_ERR(shared_counter->counter)) {
- ct_dbg("Failed to create counter for ct entry");
- ret = PTR_ERR(shared_counter->counter);
- kfree(shared_counter);
+ shared_counter = mlx5_tc_ct_counter_create(ct_priv);
+ if (IS_ERR(shared_counter)) {
+ ret = PTR_ERR(shared_counter);
return ERR_PTR(ret);
}
+ shared_counter->is_shared = true;
refcount_set(&shared_counter->refcount, 1);
return shared_counter;
}
{
int err;
- entry->shared_counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
- if (IS_ERR(entry->shared_counter)) {
- err = PTR_ERR(entry->shared_counter);
- ct_dbg("Failed to create counter for ct entry");
+ if (nf_ct_acct_enabled(dev_net(ct_priv->netdev)))
+ entry->counter = mlx5_tc_ct_counter_create(ct_priv);
+ else
+ entry->counter = mlx5_tc_ct_shared_counter_get(ct_priv, entry);
+
+ if (IS_ERR(entry->counter)) {
+ err = PTR_ERR(entry->counter);
return err;
}
err_nat:
mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
err_orig:
- mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+ mlx5_tc_ct_counter_put(ct_priv, entry);
return err;
}
rhashtable_remove_fast(&ct_priv->ct_tuples_ht, &entry->tuple_node,
tuples_ht_params);
mutex_unlock(&ct_priv->shared_counter_lock);
- mlx5_tc_ct_shared_counter_put(ct_priv, entry);
+ mlx5_tc_ct_counter_put(ct_priv, entry);
}
if (!entry)
return -ENOENT;
- mlx5_fc_query_cached(entry->shared_counter->counter, &bytes, &packets, &lastuse);
+ mlx5_fc_query_cached(entry->counter->counter, &bytes, &packets, &lastuse);
flow_stats_update(&f->stats, bytes, packets, 0, lastuse,
FLOW_ACTION_HW_STATS_DELAYED);
u8 tun_l4_proto;
};
+static inline void mlx5e_eseg_swp_offsets_add_vlan(struct mlx5_wqe_eth_seg *eseg)
+{
+ /* SWP offsets are in 2-bytes words */
+ eseg->swp_outer_l3_offset += VLAN_HLEN / 2;
+ eseg->swp_outer_l4_offset += VLAN_HLEN / 2;
+ eseg->swp_inner_l3_offset += VLAN_HLEN / 2;
+ eseg->swp_inner_l4_offset += VLAN_HLEN / 2;
+}
+
static inline void
mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
struct mlx5e_swp_spec *swp_spec)
}
static inline void
-mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg)
+mlx5e_tx_tunnel_accel(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u16 ihs)
{
struct mlx5e_swp_spec swp_spec = {};
unsigned int offset = 0;
}
mlx5e_set_eseg_swp(skb, eseg, &swp_spec);
+ if (skb_vlan_tag_present(skb) && ihs)
+ mlx5e_eseg_swp_offsets_add_vlan(eseg);
}
#else
static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv,
struct sk_buff *skb,
- struct mlx5_wqe_eth_seg *eseg)
+ struct mlx5_wqe_eth_seg *eseg, u16 ihs)
{
#ifdef CONFIG_MLX5_EN_IPSEC
if (xfrm_offload(skb))
#if IS_ENABLED(CONFIG_GENEVE)
if (skb->encapsulation)
- mlx5e_tx_tunnel_accel(skb, eseg);
+ mlx5e_tx_tunnel_accel(skb, eseg, ihs);
#endif
return true;
return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
}
+static int mlx5e_speed_validate(struct net_device *netdev, bool ext,
+ const unsigned long link_modes, u8 autoneg)
+{
+ /* Extended link-mode has no speed limitations. */
+ if (ext)
+ return 0;
+
+ if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+ autoneg != AUTONEG_ENABLE) {
+ netdev_err(netdev, "%s: 56G link speed requires autoneg enabled\n",
+ __func__);
+ return -EINVAL;
+ }
+ return 0;
+}
+
static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
{
u32 i, ptys_modes = 0;
link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
mlx5e_port_speed2linkmodes(mdev, speed, !ext);
- if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
- autoneg != AUTONEG_ENABLE) {
- netdev_err(priv->netdev, "%s: 56G link speed requires autoneg enabled\n",
- __func__);
- err = -EINVAL;
+ err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
+ if (err)
goto out;
- }
link_modes = link_modes & eproto.cap;
if (!link_modes) {
in = kvzalloc(inlen, GFP_KERNEL);
if (!in) {
kfree(ft->g);
+ ft->g = NULL;
return -ENOMEM;
}
in = kvzalloc(inlen, GFP_KERNEL);
if (!in) {
kfree(ft->g);
+ ft->g = NULL;
return -ENOMEM;
}
ft->g[ft->num_groups] = NULL;
mlx5e_destroy_groups(ft);
kvfree(in);
+ kfree(ft->g);
return err;
}
mlx5_set_port_admin_status(mdev, state);
- if (mlx5_eswitch_mode(mdev) != MLX5_ESWITCH_LEGACY)
+ if (mlx5_eswitch_mode(mdev) == MLX5_ESWITCH_OFFLOADS ||
+ !MLX5_CAP_GEN(mdev, uplink_follow))
return;
if (state == MLX5_PORT_UP)
static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
struct sk_buff *skb, struct mlx5e_accel_tx_state *accel,
- struct mlx5_wqe_eth_seg *eseg)
+ struct mlx5_wqe_eth_seg *eseg, u16 ihs)
{
- if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg)))
+ if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg, ihs)))
return false;
mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg);
if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) {
struct mlx5_wqe_eth_seg eseg = {};
- if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg)))
+ if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg,
+ attr.ihs)))
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, &accel, &wqe->eth)))
+ if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs)))
return NETDEV_TX_OK;
mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more());
return 0;
}
- if (!IS_ERR_OR_NULL(vport->egress.acl))
- return 0;
-
- vport->egress.acl = esw_acl_table_create(esw, vport->vport,
- MLX5_FLOW_NAMESPACE_ESW_EGRESS,
- table_size);
- if (IS_ERR(vport->egress.acl)) {
- err = PTR_ERR(vport->egress.acl);
- vport->egress.acl = NULL;
- goto out;
+ if (!vport->egress.acl) {
+ vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+ MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+ table_size);
+ if (IS_ERR(vport->egress.acl)) {
+ err = PTR_ERR(vport->egress.acl);
+ vport->egress.acl = NULL;
+ goto out;
+ }
+
+ err = esw_acl_egress_lgcy_groups_create(esw, vport);
+ if (err)
+ goto out;
}
- err = esw_acl_egress_lgcy_groups_create(esw, vport);
- if (err)
- goto out;
-
esw_debug(esw->dev,
"vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
vport->vport, vport->info.vlan, vport->info.qos);
struct mlx5_core_dev *tmp_dev;
int i, err;
- if (!MLX5_CAP_GEN(dev, vport_group_manager))
+ if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
+ !MLX5_CAP_GEN(dev, lag_master) ||
+ MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_MAX_PORTS)
return;
tmp_dev = mlx5_get_next_phys_dev(dev);
if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0)
return;
- for (i = 0; i < MLX5_MAX_PORTS; i++) {
- tmp_dev = ldev->pf[i].dev;
- if (!tmp_dev || !MLX5_CAP_GEN(tmp_dev, lag_master) ||
- MLX5_CAP_GEN(tmp_dev, num_lag_ports) != MLX5_MAX_PORTS)
+ for (i = 0; i < MLX5_MAX_PORTS; i++)
+ if (!ldev->pf[i].dev)
break;
- }
if (i >= MLX5_MAX_PORTS)
ldev->flags |= MLX5_LAG_FLAG_READY;
MLX5_COREDEV_VF : MLX5_COREDEV_PF;
dev->priv.adev_idx = mlx5_adev_idx_alloc();
- if (dev->priv.adev_idx < 0)
- return dev->priv.adev_idx;
+ if (dev->priv.adev_idx < 0) {
+ err = dev->priv.adev_idx;
+ goto adev_init_err;
+ }
err = mlx5_mdev_init(dev, prof_sel);
if (err)
mlx5_mdev_uninit(dev);
mdev_init_err:
mlx5_adev_idx_free(dev->priv.adev_idx);
+adev_init_err:
mlx5_devlink_free(devlink);
return err;
static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
{
mlx5_core_roce_gid_set(dev, 0, 0, 0,
- NULL, NULL, false, 0, 0);
+ NULL, NULL, false, 0, 1);
}
static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
#define MLXSW_THERMAL_ASIC_TEMP_NORM 75000 /* 75C */
#define MLXSW_THERMAL_ASIC_TEMP_HIGH 85000 /* 85C */
#define MLXSW_THERMAL_ASIC_TEMP_HOT 105000 /* 105C */
-#define MLXSW_THERMAL_ASIC_TEMP_CRIT 110000 /* 110C */
+#define MLXSW_THERMAL_ASIC_TEMP_CRIT 140000 /* 140C */
#define MLXSW_THERMAL_HYSTERESIS_TEMP 5000 /* 5C */
#define MLXSW_THERMAL_MODULE_TEMP_SHIFT (MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
#define MLXSW_THERMAL_ZONE_MAX_NAME 16
if (err)
return err;
+ if (crit_temp > emerg_temp) {
+ dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n",
+ tz->tzdev->type, crit_temp, emerg_temp);
+ return 0;
+ }
+
/* According to the system thermal requirements, the thermal zones are
* defined with four trip points. The critical and emergency
* temperature thresholds, provided by QSFP module are set as "active"
tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp;
tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp;
tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp;
- if (emerg_temp > crit_temp)
- tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
+ tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
MLXSW_THERMAL_MODULE_TEMP_SHIFT;
- else
- tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp;
return 0;
}
const unsigned char mac[ETH_ALEN],
unsigned int vid, enum macaccess_entry_type type)
{
+ u32 cmd = ANA_TABLES_MACACCESS_VALID |
+ ANA_TABLES_MACACCESS_DEST_IDX(port) |
+ ANA_TABLES_MACACCESS_ENTRYTYPE(type) |
+ ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_LEARN);
+ unsigned int mc_ports;
+
+ /* Set MAC_CPU_COPY if the CPU port is used by a multicast entry */
+ if (type == ENTRYTYPE_MACv4)
+ mc_ports = (mac[1] << 8) | mac[2];
+ else if (type == ENTRYTYPE_MACv6)
+ mc_ports = (mac[0] << 8) | mac[1];
+ else
+ mc_ports = 0;
+
+ if (mc_ports & BIT(ocelot->num_phys_ports))
+ cmd |= ANA_TABLES_MACACCESS_MAC_CPU_COPY;
+
ocelot_mact_select(ocelot, mac, vid);
/* Issue a write command */
- ocelot_write(ocelot, ANA_TABLES_MACACCESS_VALID |
- ANA_TABLES_MACACCESS_DEST_IDX(port) |
- ANA_TABLES_MACACCESS_ENTRYTYPE(type) |
- ANA_TABLES_MACACCESS_MAC_TABLE_CMD(MACACCESS_CMD_LEARN),
- ANA_TABLES_MACACCESS);
+ ocelot_write(ocelot, cmd, ANA_TABLES_MACACCESS);
return ocelot_mact_wait_for_completion(ocelot);
}
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
int ret = 0;
- if (!ocelot_netdevice_dev_check(dev))
- return 0;
-
if (event == NETDEV_PRECHANGEUPPER &&
+ ocelot_netdevice_dev_check(dev) &&
netif_is_lag_master(info->upper_dev)) {
struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
struct netlink_ext_ack *extack;
err = register_netdev(dev);
if (err)
- goto out;
+ goto undo_probe;
return 0;
+undo_probe:
+ dma_free_coherent(lp->device,
+ SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+ lp->descriptors, lp->descriptors_laddr);
out:
free_netdev(dev);
err = register_netdev(ndev);
if (err)
- goto out;
+ goto undo_probe;
nubus_set_drvdata(board, ndev);
return 0;
+undo_probe:
+ dma_free_coherent(lp->device,
+ SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+ lp->descriptors, lp->descriptors_laddr);
out:
free_netdev(ndev);
return err;
sonic_msg_init(dev);
if ((err = register_netdev(dev)))
- goto out1;
+ goto undo_probe1;
return 0;
-out1:
+undo_probe1:
+ dma_free_coherent(lp->device,
+ SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode),
+ lp->descriptors, lp->descriptors_laddr);
release_region(dev->base_addr, SONIC_MEM_SIZE);
out:
free_netdev(dev);
unsigned int i, j;
unsigned int len;
- len = netdev->mtu + ETH_HLEN;
+ len = netdev->mtu + ETH_HLEN + VLAN_HLEN;
nfrags = round_up(len, PAGE_SIZE) / PAGE_SIZE;
for (i = ionic_q_space_avail(q); i; i--) {
depends on PCI
select ZLIB_INFLATE
select CRC8
+ select CRC32
select NET_DEVLINK
help
This enables the support for Marvell FastLinQ adapters family.
.ndo_set_features = netxen_set_features,
};
-static inline bool netxen_function_zero(struct pci_dev *pdev)
-{
- return (PCI_FUNC(pdev->devfn) == 0) ? true : false;
-}
-
static inline void netxen_set_interrupt_mode(struct netxen_adapter *adapter,
u32 mode)
{
netxen_initialize_interrupt_registers(adapter);
netxen_set_msix_bit(pdev, 0);
- if (netxen_function_zero(pdev)) {
+ if (adapter->portnum == 0) {
if (!netxen_setup_msi_interrupts(adapter, num_msix))
netxen_set_interrupt_mode(adapter, NETXEN_MSI_MODE);
else
ntohs(udp_hdr(skb)->dest) != gnv_port))
return features & ~(NETIF_F_CSUM_MASK |
NETIF_F_GSO_MASK);
+ } else if (l4_proto == IPPROTO_IPIP) {
+ /* IPIP tunnels are unknown to the device or at least unsupported natively,
+ * offloads for them can't be done trivially, so disable them for such skb.
+ */
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}
}
}
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26:
+ case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_33:
case RTL_GIGA_MAC_VER_37:
case RTL_GIGA_MAC_VER_39:
case RTL_GIGA_MAC_VER_43:
static void rtl_pll_power_up(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
- case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26:
+ case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_33:
case RTL_GIGA_MAC_VER_37:
case RTL_GIGA_MAC_VER_39:
case RTL_GIGA_MAC_VER_43:
/* Free all the skbuffs in the Rx queue and the DMA buffer. */
sh_eth_ring_free(ndev);
- pm_runtime_put_sync(&mdp->pdev->dev);
-
mdp->is_opened = 0;
+ pm_runtime_put(&mdp->pdev->dev);
+
return 0;
}
return 0;
}
+static int sh_mdiobb_read(struct mii_bus *bus, int phy, int reg)
+{
+ int res;
+
+ pm_runtime_get_sync(bus->parent);
+ res = mdiobb_read(bus, phy, reg);
+ pm_runtime_put(bus->parent);
+
+ return res;
+}
+
+static int sh_mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
+{
+ int res;
+
+ pm_runtime_get_sync(bus->parent);
+ res = mdiobb_write(bus, phy, reg, val);
+ pm_runtime_put(bus->parent);
+
+ return res;
+}
+
/* MDIO bus init function */
static int sh_mdio_init(struct sh_eth_private *mdp,
struct sh_eth_plat_data *pd)
if (!mdp->mii_bus)
return -ENOMEM;
+ /* Wrap accessors with Runtime PM-aware ops */
+ mdp->mii_bus->read = sh_mdiobb_read;
+ mdp->mii_bus->write = sh_mdiobb_write;
+
/* Hook up MII support for ethtool */
mdp->mii_bus->name = "sh_mii";
mdp->mii_bus->parent = dev;
#define PCI_DEVICE_ID_INTEL_EHL_PSE1_RGMII1G_ID 0x4bb0
#define PCI_DEVICE_ID_INTEL_EHL_PSE1_SGMII1G_ID 0x4bb1
#define PCI_DEVICE_ID_INTEL_EHL_PSE1_SGMII2G5_ID 0x4bb2
+#define PCI_DEVICE_ID_INTEL_TGLH_SGMII1G_0_ID 0x43ac
+#define PCI_DEVICE_ID_INTEL_TGLH_SGMII1G_1_ID 0x43a2
#define PCI_DEVICE_ID_INTEL_TGL_SGMII1G_ID 0xa0ac
static const struct pci_device_id intel_eth_pci_id_table[] = {
{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII1G_ID, &ehl_pse1_sgmii1g_info) },
{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII2G5_ID, &ehl_pse1_sgmii1g_info) },
{ PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_info) },
+ { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_info) },
+ { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_info) },
{}
};
MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table);
struct device *dev = dwmac->dev;
static const struct clk_parent_data mux_parents[] = {
{ .fw_name = "clkin0", },
- { .fw_name = "clkin1", },
+ { .index = -1, },
};
static const struct clk_div_table div_table[] = {
{ .div = 2, .val = 2, },
* @variant: reference to the current board variant
* @regmap: regmap for using the syscon
* @internal_phy_powered: Does the internal PHY is enabled
+ * @use_internal_phy: Is the internal PHY selected for use
* @mux_handle: Internal pointer used by mdio-mux lib
*/
struct sunxi_priv_data {
const struct emac_variant *variant;
struct regmap_field *regmap_field;
bool internal_phy_powered;
+ bool use_internal_phy;
void *mux_handle;
};
.dma_interrupt = sun8i_dwmac_dma_interrupt,
};
+static int sun8i_dwmac_power_internal_phy(struct stmmac_priv *priv);
+
static int sun8i_dwmac_init(struct platform_device *pdev, void *priv)
{
+ struct net_device *ndev = platform_get_drvdata(pdev);
struct sunxi_priv_data *gmac = priv;
int ret;
ret = clk_prepare_enable(gmac->tx_clk);
if (ret) {
- if (gmac->regulator)
- regulator_disable(gmac->regulator);
dev_err(&pdev->dev, "Could not enable AHB clock\n");
- return ret;
+ goto err_disable_regulator;
+ }
+
+ if (gmac->use_internal_phy) {
+ ret = sun8i_dwmac_power_internal_phy(netdev_priv(ndev));
+ if (ret)
+ goto err_disable_clk;
}
return 0;
+
+err_disable_clk:
+ clk_disable_unprepare(gmac->tx_clk);
+err_disable_regulator:
+ if (gmac->regulator)
+ regulator_disable(gmac->regulator);
+
+ return ret;
}
static void sun8i_dwmac_core_init(struct mac_device_info *hw,
struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
u32 reg, val;
int ret = 0;
- bool need_power_ephy = false;
if (current_child ^ desired_child) {
regmap_field_read(gmac->regmap_field, ®);
case DWMAC_SUN8I_MDIO_MUX_INTERNAL_ID:
dev_info(priv->device, "Switch mux to internal PHY");
val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SELECT;
-
- need_power_ephy = true;
+ gmac->use_internal_phy = true;
break;
case DWMAC_SUN8I_MDIO_MUX_EXTERNAL_ID:
dev_info(priv->device, "Switch mux to external PHY");
val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SHUTDOWN;
- need_power_ephy = false;
+ gmac->use_internal_phy = false;
break;
default:
dev_err(priv->device, "Invalid child ID %x\n",
return -EINVAL;
}
regmap_field_write(gmac->regmap_field, val);
- if (need_power_ephy) {
+ if (gmac->use_internal_phy) {
ret = sun8i_dwmac_power_internal_phy(priv);
if (ret)
return ret;
return ret;
}
-static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
+static int sun8i_dwmac_set_syscon(struct device *dev,
+ struct plat_stmmacenet_data *plat)
{
- struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
- struct device_node *node = priv->device->of_node;
+ struct sunxi_priv_data *gmac = plat->bsp_priv;
+ struct device_node *node = dev->of_node;
int ret;
u32 reg, val;
ret = regmap_field_read(gmac->regmap_field, &val);
if (ret) {
- dev_err(priv->device, "Fail to read from regmap field.\n");
+ dev_err(dev, "Fail to read from regmap field.\n");
return ret;
}
reg = gmac->variant->default_syscon_value;
if (reg != val)
- dev_warn(priv->device,
+ dev_warn(dev,
"Current syscon value is not the default %x (expect %x)\n",
val, reg);
/* Force EPHY xtal frequency to 24MHz. */
reg |= H3_EPHY_CLK_SEL;
- ret = of_mdio_parse_addr(priv->device, priv->plat->phy_node);
+ ret = of_mdio_parse_addr(dev, plat->phy_node);
if (ret < 0) {
- dev_err(priv->device, "Could not parse MDIO addr\n");
+ dev_err(dev, "Could not parse MDIO addr\n");
return ret;
}
/* of_mdio_parse_addr returns a valid (0 ~ 31) PHY
if (!of_property_read_u32(node, "allwinner,tx-delay-ps", &val)) {
if (val % 100) {
- dev_err(priv->device, "tx-delay must be a multiple of 100\n");
+ dev_err(dev, "tx-delay must be a multiple of 100\n");
return -EINVAL;
}
val /= 100;
- dev_dbg(priv->device, "set tx-delay to %x\n", val);
+ dev_dbg(dev, "set tx-delay to %x\n", val);
if (val <= gmac->variant->tx_delay_max) {
reg &= ~(gmac->variant->tx_delay_max <<
SYSCON_ETXDC_SHIFT);
reg |= (val << SYSCON_ETXDC_SHIFT);
} else {
- dev_err(priv->device, "Invalid TX clock delay: %d\n",
+ dev_err(dev, "Invalid TX clock delay: %d\n",
val);
return -EINVAL;
}
if (!of_property_read_u32(node, "allwinner,rx-delay-ps", &val)) {
if (val % 100) {
- dev_err(priv->device, "rx-delay must be a multiple of 100\n");
+ dev_err(dev, "rx-delay must be a multiple of 100\n");
return -EINVAL;
}
val /= 100;
- dev_dbg(priv->device, "set rx-delay to %x\n", val);
+ dev_dbg(dev, "set rx-delay to %x\n", val);
if (val <= gmac->variant->rx_delay_max) {
reg &= ~(gmac->variant->rx_delay_max <<
SYSCON_ERXDC_SHIFT);
reg |= (val << SYSCON_ERXDC_SHIFT);
} else {
- dev_err(priv->device, "Invalid RX clock delay: %d\n",
+ dev_err(dev, "Invalid RX clock delay: %d\n",
val);
return -EINVAL;
}
if (gmac->variant->support_rmii)
reg &= ~SYSCON_RMII_EN;
- switch (priv->plat->interface) {
+ switch (plat->interface) {
case PHY_INTERFACE_MODE_MII:
/* default */
break;
reg |= SYSCON_RMII_EN | SYSCON_ETCS_EXT_GMII;
break;
default:
- dev_err(priv->device, "Unsupported interface mode: %s",
- phy_modes(priv->plat->interface));
+ dev_err(dev, "Unsupported interface mode: %s",
+ phy_modes(plat->interface));
return -EINVAL;
}
struct sunxi_priv_data *gmac = priv;
if (gmac->variant->soc_has_internal_phy) {
- /* sun8i_dwmac_exit could be called with mdiomux uninit */
- if (gmac->mux_handle)
- mdio_mux_uninit(gmac->mux_handle);
if (gmac->internal_phy_powered)
sun8i_dwmac_unpower_internal_phy(gmac);
}
- sun8i_dwmac_unset_syscon(gmac);
-
- reset_control_put(gmac->rst_ephy);
-
clk_disable_unprepare(gmac->tx_clk);
if (gmac->regulator)
{
struct mac_device_info *mac;
struct stmmac_priv *priv = ppriv;
- int ret;
mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
if (!mac)
return NULL;
- ret = sun8i_dwmac_set_syscon(priv);
- if (ret)
- return NULL;
-
mac->pcsr = priv->ioaddr;
mac->mac = &sun8i_dwmac_ops;
mac->dma = &sun8i_dwmac_dma_ops;
if (ret)
return ret;
- plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
- if (IS_ERR(plat_dat))
- return PTR_ERR(plat_dat);
-
gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL);
if (!gmac)
return -ENOMEM;
ret = of_get_phy_mode(dev->of_node, &interface);
if (ret)
return -EINVAL;
- plat_dat->interface = interface;
+
+ plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+ if (IS_ERR(plat_dat))
+ return PTR_ERR(plat_dat);
/* platform data specifying hardware features and callbacks.
* hardware features were copied from Allwinner drivers.
*/
+ plat_dat->interface = interface;
plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
plat_dat->tx_coe = 1;
plat_dat->has_sun8i = true;
plat_dat->exit = sun8i_dwmac_exit;
plat_dat->setup = sun8i_dwmac_setup;
+ ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat);
+ if (ret)
+ goto dwmac_deconfig;
+
ret = sun8i_dwmac_init(pdev, plat_dat->bsp_priv);
if (ret)
- return ret;
+ goto dwmac_syscon;
ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
if (ret)
if (gmac->variant->soc_has_internal_phy) {
ret = get_ephy_nodes(priv);
if (ret)
- goto dwmac_exit;
+ goto dwmac_remove;
ret = sun8i_dwmac_register_mdio_mux(priv);
if (ret) {
dev_err(&pdev->dev, "Failed to register mux\n");
} else {
ret = sun8i_dwmac_reset(priv);
if (ret)
- goto dwmac_exit;
+ goto dwmac_remove;
}
return ret;
dwmac_mux:
- sun8i_dwmac_unset_syscon(gmac);
+ reset_control_put(gmac->rst_ephy);
+ clk_put(gmac->ephy_clk);
+dwmac_remove:
+ stmmac_dvr_remove(&pdev->dev);
dwmac_exit:
+ sun8i_dwmac_exit(pdev, gmac);
+dwmac_syscon:
+ sun8i_dwmac_unset_syscon(gmac);
+dwmac_deconfig:
+ stmmac_remove_config_dt(pdev, plat_dat);
+
+ return ret;
+}
+
+static int sun8i_dwmac_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct stmmac_priv *priv = netdev_priv(ndev);
+ struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
+
+ if (gmac->variant->soc_has_internal_phy) {
+ mdio_mux_uninit(gmac->mux_handle);
+ sun8i_dwmac_unpower_internal_phy(gmac);
+ reset_control_put(gmac->rst_ephy);
+ clk_put(gmac->ephy_clk);
+ }
+
stmmac_pltfr_remove(pdev);
-return ret;
+ sun8i_dwmac_unset_syscon(gmac);
+
+ return 0;
}
static const struct of_device_id sun8i_dwmac_match[] = {
static struct platform_driver sun8i_dwmac_driver = {
.probe = sun8i_dwmac_probe,
- .remove = stmmac_pltfr_remove,
+ .remove = sun8i_dwmac_remove,
.driver = {
.name = "dwmac-sun8i",
.pm = &stmmac_pltfr_pm_ops,
int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg,
unsigned int ptp_rate)
{
- u32 speed, total_offset, offset, ctrl, ctr_low;
- u32 extcfg = readl(ioaddr + GMAC_EXT_CONFIG);
- u32 mac_cfg = readl(ioaddr + GMAC_CONFIG);
int i, ret = 0x0;
- u64 total_ctr;
-
- if (extcfg & GMAC_CONFIG_EIPG_EN) {
- offset = (extcfg & GMAC_CONFIG_EIPG) >> GMAC_CONFIG_EIPG_SHIFT;
- offset = 104 + (offset * 8);
- } else {
- offset = (mac_cfg & GMAC_CONFIG_IPG) >> GMAC_CONFIG_IPG_SHIFT;
- offset = 96 - (offset * 8);
- }
-
- speed = mac_cfg & (GMAC_CONFIG_PS | GMAC_CONFIG_FES);
- speed = speed >> GMAC_CONFIG_FES_SHIFT;
-
- switch (speed) {
- case 0x0:
- offset = offset * 1000; /* 1G */
- break;
- case 0x1:
- offset = offset * 400; /* 2.5G */
- break;
- case 0x2:
- offset = offset * 100000; /* 10M */
- break;
- case 0x3:
- offset = offset * 10000; /* 100M */
- break;
- default:
- return -EINVAL;
- }
-
- offset = offset / 1000;
+ u32 ctrl;
ret |= dwmac5_est_write(ioaddr, BTR_LOW, cfg->btr[0], false);
ret |= dwmac5_est_write(ioaddr, BTR_HIGH, cfg->btr[1], false);
ret |= dwmac5_est_write(ioaddr, TER, cfg->ter, false);
ret |= dwmac5_est_write(ioaddr, LLR, cfg->gcl_size, false);
+ ret |= dwmac5_est_write(ioaddr, CTR_LOW, cfg->ctr[0], false);
+ ret |= dwmac5_est_write(ioaddr, CTR_HIGH, cfg->ctr[1], false);
if (ret)
return ret;
- total_offset = 0;
for (i = 0; i < cfg->gcl_size; i++) {
- ret = dwmac5_est_write(ioaddr, i, cfg->gcl[i] + offset, true);
+ ret = dwmac5_est_write(ioaddr, i, cfg->gcl[i], true);
if (ret)
return ret;
-
- total_offset += offset;
}
- total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000ULL;
- total_ctr += total_offset;
-
- ctr_low = do_div(total_ctr, 1000000000);
-
- ret |= dwmac5_est_write(ioaddr, CTR_LOW, ctr_low, false);
- ret |= dwmac5_est_write(ioaddr, CTR_HIGH, total_ctr, false);
- if (ret)
- return ret;
-
ctrl = readl(ioaddr + MTL_EST_CONTROL);
ctrl &= ~PTOV;
ctrl |= ((1000000000 / ptp_rate) * 6) << PTOV_SHIFT;
spin_lock_irqsave(&ch->lock, flags);
stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 1, 0);
spin_unlock_irqrestore(&ch->lock, flags);
- __napi_schedule_irqoff(&ch->rx_napi);
+ __napi_schedule(&ch->rx_napi);
}
}
spin_lock_irqsave(&ch->lock, flags);
stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 0, 1);
spin_unlock_irqrestore(&ch->lock, flags);
- __napi_schedule_irqoff(&ch->tx_napi);
+ __napi_schedule(&ch->tx_napi);
}
}
{
struct stmmac_priv *priv = netdev_priv(dev);
int txfifosz = priv->plat->tx_fifo_size;
+ const int mtu = new_mtu;
if (txfifosz == 0)
txfifosz = priv->dma_cap.tx_fifo_size;
if ((txfifosz < new_mtu) || (new_mtu > BUF_SIZE_16KiB))
return -EINVAL;
- dev->mtu = new_mtu;
+ dev->mtu = mtu;
netdev_update_features(dev);
{
u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
struct plat_stmmacenet_data *plat = priv->plat;
- struct timespec64 time;
+ struct timespec64 time, current_time;
+ ktime_t current_time_ns;
bool fpe = false;
int i, ret = 0;
u64 ctr;
}
/* Adjust for real system time */
- time = ktime_to_timespec64(qopt->base_time);
+ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time);
+ current_time_ns = timespec64_to_ktime(current_time);
+ if (ktime_after(qopt->base_time, current_time_ns)) {
+ time = ktime_to_timespec64(qopt->base_time);
+ } else {
+ ktime_t base_time;
+ s64 n;
+
+ n = div64_s64(ktime_sub_ns(current_time_ns, qopt->base_time),
+ qopt->cycle_time);
+ base_time = ktime_add_ns(qopt->base_time,
+ (n + 1) * qopt->cycle_time);
+
+ time = ktime_to_timespec64(base_time);
+ }
+
priv->plat->est->btr[0] = (u32)time.tv_nsec;
priv->plat->est->btr[1] = (u32)time.tv_sec;
ptp_clock_unregister(cpts->clock);
cpts->clock = NULL;
+ cpts->phc_index = -1;
cpts_write32(cpts, 0, int_enable);
cpts_write32(cpts, 0, control);
cpts->cc.read = cpts_systim_read;
cpts->cc.mask = CLOCKSOURCE_MASK(32);
cpts->info = cpts_info;
+ cpts->phc_index = -1;
if (n_ext_ts)
cpts->info.n_ext_ts = n_ext_ts;
}
/* Issue an event ring command and wait for it to complete */
-static int evt_ring_command(struct gsi *gsi, u32 evt_ring_id,
- enum gsi_evt_cmd_opcode opcode)
+static void evt_ring_command(struct gsi *gsi, u32 evt_ring_id,
+ enum gsi_evt_cmd_opcode opcode)
{
struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
struct completion *completion = &evt_ring->completion;
* is issued here. Only permit *this* event ring to trigger
* an interrupt, and only enable the event control IRQ type
* when we expect it to occur.
+ *
+ * There's a small chance that a previous command completed
+ * after the interrupt was disabled, so make sure we have no
+ * pending interrupts before we enable them.
*/
+ iowrite32(~0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_CLR_OFFSET);
+
val = BIT(evt_ring_id);
iowrite32(val, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
gsi_irq_type_enable(gsi, GSI_EV_CTRL);
iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET);
if (success)
- return 0;
+ return;
dev_err(dev, "GSI command %u for event ring %u timed out, state %u\n",
opcode, evt_ring_id, evt_ring->state);
-
- return -ETIMEDOUT;
}
/* Allocate an event ring in NOT_ALLOCATED state */
static int gsi_evt_ring_alloc_command(struct gsi *gsi, u32 evt_ring_id)
{
struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
- int ret;
/* Get initial event ring state */
evt_ring->state = gsi_evt_ring_state(gsi, evt_ring_id);
return -EINVAL;
}
- ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE);
- if (!ret && evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) {
- dev_err(gsi->dev, "event ring %u bad state %u after alloc\n",
- evt_ring_id, evt_ring->state);
- ret = -EIO;
- }
+ evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE);
- return ret;
+ /* If successful the event ring state will have changed */
+ if (evt_ring->state == GSI_EVT_RING_STATE_ALLOCATED)
+ return 0;
+
+ dev_err(gsi->dev, "event ring %u bad state %u after alloc\n",
+ evt_ring_id, evt_ring->state);
+
+ return -EIO;
}
/* Reset a GSI event ring in ALLOCATED or ERROR state. */
{
struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
enum gsi_evt_ring_state state = evt_ring->state;
- int ret;
if (state != GSI_EVT_RING_STATE_ALLOCATED &&
state != GSI_EVT_RING_STATE_ERROR) {
return;
}
- ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET);
- if (!ret && evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED)
- dev_err(gsi->dev, "event ring %u bad state %u after reset\n",
- evt_ring_id, evt_ring->state);
+ evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET);
+
+ /* If successful the event ring state will have changed */
+ if (evt_ring->state == GSI_EVT_RING_STATE_ALLOCATED)
+ return;
+
+ dev_err(gsi->dev, "event ring %u bad state %u after reset\n",
+ evt_ring_id, evt_ring->state);
}
/* Issue a hardware de-allocation request for an allocated event ring */
static void gsi_evt_ring_de_alloc_command(struct gsi *gsi, u32 evt_ring_id)
{
struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id];
- int ret;
if (evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) {
dev_err(gsi->dev, "event ring %u state %u before dealloc\n",
return;
}
- ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC);
- if (!ret && evt_ring->state != GSI_EVT_RING_STATE_NOT_ALLOCATED)
- dev_err(gsi->dev, "event ring %u bad state %u after dealloc\n",
- evt_ring_id, evt_ring->state);
+ evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC);
+
+ /* If successful the event ring state will have changed */
+ if (evt_ring->state == GSI_EVT_RING_STATE_NOT_ALLOCATED)
+ return;
+
+ dev_err(gsi->dev, "event ring %u bad state %u after dealloc\n",
+ evt_ring_id, evt_ring->state);
}
/* Fetch the current state of a channel from hardware */
}
/* Issue a channel command and wait for it to complete */
-static int
+static void
gsi_channel_command(struct gsi_channel *channel, enum gsi_ch_cmd_opcode opcode)
{
struct completion *completion = &channel->completion;
* issued here. So we only permit *this* channel to trigger
* an interrupt and only enable the channel control IRQ type
* when we expect it to occur.
+ *
+ * There's a small chance that a previous command completed
+ * after the interrupt was disabled, so make sure we have no
+ * pending interrupts before we enable them.
*/
+ iowrite32(~0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_CLR_OFFSET);
+
val = BIT(channel_id);
iowrite32(val, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
gsi_irq_type_enable(gsi, GSI_CH_CTRL);
iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET);
if (success)
- return 0;
+ return;
dev_err(dev, "GSI command %u for channel %u timed out, state %u\n",
opcode, channel_id, gsi_channel_state(channel));
-
- return -ETIMEDOUT;
}
/* Allocate GSI channel in NOT_ALLOCATED state */
struct gsi_channel *channel = &gsi->channel[channel_id];
struct device *dev = gsi->dev;
enum gsi_channel_state state;
- int ret;
/* Get initial channel state */
state = gsi_channel_state(channel);
return -EINVAL;
}
- ret = gsi_channel_command(channel, GSI_CH_ALLOCATE);
+ gsi_channel_command(channel, GSI_CH_ALLOCATE);
- /* Channel state will normally have been updated */
+ /* If successful the channel state will have changed */
state = gsi_channel_state(channel);
- if (!ret && state != GSI_CHANNEL_STATE_ALLOCATED) {
- dev_err(dev, "channel %u bad state %u after alloc\n",
- channel_id, state);
- ret = -EIO;
- }
+ if (state == GSI_CHANNEL_STATE_ALLOCATED)
+ return 0;
- return ret;
+ dev_err(dev, "channel %u bad state %u after alloc\n",
+ channel_id, state);
+
+ return -EIO;
}
/* Start an ALLOCATED channel */
{
struct device *dev = channel->gsi->dev;
enum gsi_channel_state state;
- int ret;
state = gsi_channel_state(channel);
if (state != GSI_CHANNEL_STATE_ALLOCATED &&
return -EINVAL;
}
- ret = gsi_channel_command(channel, GSI_CH_START);
+ gsi_channel_command(channel, GSI_CH_START);
- /* Channel state will normally have been updated */
+ /* If successful the channel state will have changed */
state = gsi_channel_state(channel);
- if (!ret && state != GSI_CHANNEL_STATE_STARTED) {
- dev_err(dev, "channel %u bad state %u after start\n",
- gsi_channel_id(channel), state);
- ret = -EIO;
- }
+ if (state == GSI_CHANNEL_STATE_STARTED)
+ return 0;
- return ret;
+ dev_err(dev, "channel %u bad state %u after start\n",
+ gsi_channel_id(channel), state);
+
+ return -EIO;
}
/* Stop a GSI channel in STARTED state */
{
struct device *dev = channel->gsi->dev;
enum gsi_channel_state state;
- int ret;
state = gsi_channel_state(channel);
return -EINVAL;
}
- ret = gsi_channel_command(channel, GSI_CH_STOP);
+ gsi_channel_command(channel, GSI_CH_STOP);
- /* Channel state will normally have been updated */
+ /* If successful the channel state will have changed */
state = gsi_channel_state(channel);
- if (ret || state == GSI_CHANNEL_STATE_STOPPED)
- return ret;
+ if (state == GSI_CHANNEL_STATE_STOPPED)
+ return 0;
/* We may have to try again if stop is in progress */
if (state == GSI_CHANNEL_STATE_STOP_IN_PROC)
{
struct device *dev = channel->gsi->dev;
enum gsi_channel_state state;
- int ret;
msleep(1); /* A short delay is required before a RESET command */
return;
}
- ret = gsi_channel_command(channel, GSI_CH_RESET);
+ gsi_channel_command(channel, GSI_CH_RESET);
- /* Channel state will normally have been updated */
+ /* If successful the channel state will have changed */
state = gsi_channel_state(channel);
- if (!ret && state != GSI_CHANNEL_STATE_ALLOCATED)
+ if (state != GSI_CHANNEL_STATE_ALLOCATED)
dev_err(dev, "channel %u bad state %u after reset\n",
gsi_channel_id(channel), state);
}
struct gsi_channel *channel = &gsi->channel[channel_id];
struct device *dev = gsi->dev;
enum gsi_channel_state state;
- int ret;
state = gsi_channel_state(channel);
if (state != GSI_CHANNEL_STATE_ALLOCATED) {
return;
}
- ret = gsi_channel_command(channel, GSI_CH_DE_ALLOC);
+ gsi_channel_command(channel, GSI_CH_DE_ALLOC);
- /* Channel state will normally have been updated */
+ /* If successful the channel state will have changed */
state = gsi_channel_state(channel);
- if (!ret && state != GSI_CHANNEL_STATE_NOT_ALLOCATED)
+
+ if (state != GSI_CHANNEL_STATE_NOT_ALLOCATED)
dev_err(dev, "channel %u bad state %u after dealloc\n",
channel_id, state);
}
return ret;
data = &clock->interconnect_data[IPA_INTERCONNECT_IMEM];
- ret = icc_set_bw(clock->memory_path, data->average_rate,
+ ret = icc_set_bw(clock->imem_path, data->average_rate,
data->peak_rate);
if (ret)
goto err_memory_path_disable;
data = &clock->interconnect_data[IPA_INTERCONNECT_CONFIG];
- ret = icc_set_bw(clock->memory_path, data->average_rate,
+ ret = icc_set_bw(clock->config_path, data->average_rate,
data->peak_rate);
if (ret)
goto err_imem_path_disable;
ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]->netdev = netdev;
ipa->name_map[IPA_ENDPOINT_AP_MODEM_RX]->netdev = netdev;
+ SET_NETDEV_DEV(netdev, &ipa->pdev->dev);
priv = netdev_priv(netdev);
priv->ipa = ipa;
return dev_addr;
}
-static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
+int mdiobb_read(struct mii_bus *bus, int phy, int reg)
{
struct mdiobb_ctrl *ctrl = bus->priv;
int ret, i;
mdiobb_get_bit(ctrl);
return ret;
}
+EXPORT_SYMBOL(mdiobb_read);
-static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
+int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
{
struct mdiobb_ctrl *ctrl = bus->priv;
mdiobb_get_bit(ctrl);
return 0;
}
+EXPORT_SYMBOL(mdiobb_write);
struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl)
{
/* Make clk optional to keep DTB backward compatibility. */
priv->refclk = clk_get_optional(dev, NULL);
if (IS_ERR(priv->refclk))
- dev_err_probe(dev, PTR_ERR(priv->refclk), "Failed to request clock\n");
+ return dev_err_probe(dev, PTR_ERR(priv->refclk),
+ "Failed to request clock\n");
ret = clk_prepare_enable(priv->refclk);
if (ret)
write_unlock_bh(&pch->upl);
return -EALREADY;
}
+ refcount_inc(&pchb->file.refcnt);
rcu_assign_pointer(pch->bridge, pchb);
write_unlock_bh(&pch->upl);
write_unlock_bh(&pchb->upl);
goto err_unset;
}
+ refcount_inc(&pch->file.refcnt);
rcu_assign_pointer(pchb->bridge, pch);
write_unlock_bh(&pchb->upl);
- refcount_inc(&pch->file.refcnt);
- refcount_inc(&pchb->file.refcnt);
-
return 0;
err_unset:
write_lock_bh(&pch->upl);
+ /* Re-read pch->bridge with upl held in case it was modified concurrently */
+ pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl));
RCU_INIT_POINTER(pch->bridge, NULL);
write_unlock_bh(&pch->upl);
synchronize_rcu();
+
+ if (pchb)
+ if (refcount_dec_and_test(&pchb->file.refcnt))
+ ppp_destroy_channel(pchb);
+
return -EALREADY;
}
int i;
if (it->nr_segs > MAX_SKB_FRAGS + 1)
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(-EMSGSIZE);
local_bh_disable();
skb = napi_get_frags(&tfile->napi);
config USB_RTL8153_ECM
tristate "RTL8153 ECM support"
depends on USB_NET_CDCETHER && (USB_RTL8152 || USB_RTL8152=n)
- default y
help
This option supports ECM mode for RTL8153 ethernet adapter, when
CONFIG_USB_RTL8152 is not set, or the RTL8153 device is not
.driver_info = 0,
},
+/* Lenovo Powered USB-C Travel Hub (4X90S92381, based on Realtek RTL8153) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x721e, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
/* ThinkPad USB-C Dock Gen 2 (based on Realtek RTL8153) */
{
USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa387, USB_CLASS_COMM,
* accordingly. Otherwise, we should check here.
*/
if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
- delayed_ndp_size = ALIGN(ctx->max_ndp_size, ctx->tx_ndp_modulus);
+ delayed_ndp_size = ctx->max_ndp_size +
+ max_t(u32,
+ ctx->tx_ndp_modulus,
+ ctx->tx_modulus + ctx->tx_remainder) - 1;
else
delayed_ndp_size = 0;
if (!(dev->driver_info->flags & FLAG_SEND_ZLP) &&
skb_out->len > ctx->min_tx_pkt) {
padding_count = ctx->tx_curr_size - skb_out->len;
- skb_put_zero(skb_out, padding_count);
+ if (!WARN_ON(padding_count > ctx->tx_curr_size))
+ skb_put_zero(skb_out, padding_count);
} else if (skb_out->len < ctx->tx_curr_size &&
(skb_out->len % dev->maxpacket) == 0) {
skb_put_u8(skb_out, 0); /* force short packet */
uint32_t rx_speed = le32_to_cpu(data->DLBitRRate);
uint32_t tx_speed = le32_to_cpu(data->ULBitRate);
+ /* if the speed hasn't changed, don't report it.
+ * RTL8156 shipped before 2021 sends notification about every 32ms.
+ */
+ if (dev->rx_speed == rx_speed && dev->tx_speed == tx_speed)
+ return;
+
+ dev->rx_speed = rx_speed;
+ dev->tx_speed = tx_speed;
+
/*
* Currently the USB-NET API does not support reporting the actual
* device speed. Do print it instead.
* USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be
* sent by device after USB_CDC_NOTIFY_SPEED_CHANGE.
*/
- netif_info(dev, link, dev->net,
- "network connection: %sconnected\n",
- !!event->wValue ? "" : "dis");
- usbnet_link_change(dev, !!event->wValue, 0);
+ if (netif_carrier_ok(dev->net) != !!event->wValue)
+ usbnet_link_change(dev, !!event->wValue, 0);
break;
case USB_CDC_NOTIFY_SPEED_CHANGE:
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */
+ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0620)}, /* Quectel EM160R-GL */
{QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */
/* 3. Combined interface devices matching on interface number */
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x720c)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7214)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x721e)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0xa387)},
{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff)},
};
static const struct usb_device_id products[] = {
+/* Realtek RTL8153 Based USB 3.0 Ethernet Adapters */
{
USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_REALTEK, 0x8153, USB_CLASS_COMM,
USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&r8153_info,
},
+/* Lenovo Powered USB-C Travel Hub (4X90S92381, based on Realtek RTL8153) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_LENOVO, 0x721e, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&r8153_info,
+},
+
{ }, /* END */
};
MODULE_DEVICE_TABLE(usb, products);
reply_len = sizeof *phym;
retval = rndis_query(dev, intf, u.buf,
RNDIS_OID_GEN_PHYSICAL_MEDIUM,
- 0, (void **) &phym, &reply_len);
+ reply_len, (void **)&phym, &reply_len);
if (retval != 0 || !phym) {
/* OID is optional so don't fail here. */
phym_unspec = cpu_to_le32(RNDIS_PHYSICAL_MEDIUM_UNSPECIFIED);
get_online_cpus();
err = _virtnet_set_queues(vi, queue_pairs);
- if (!err) {
- netif_set_real_num_tx_queues(dev, queue_pairs);
- netif_set_real_num_rx_queues(dev, queue_pairs);
-
- virtnet_set_affinity(vi);
+ if (err) {
+ put_online_cpus();
+ goto err;
}
+ virtnet_set_affinity(vi);
put_online_cpus();
+ netif_set_real_num_tx_queues(dev, queue_pairs);
+ netif_set_real_num_rx_queues(dev, queue_pairs);
+ err:
return err;
}
tristate "Slic Maxim ds26522 card support"
depends on SPI
depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE || COMPILE_TEST
+ select BITREVERSE
help
This module initializes and configures the slic maxim card
in T1 or E1 mode.
unsigned long flags;
spin_lock_irqsave(&ppp->lock, flags);
+ /* mod_timer could be called after we entered this function but
+ * before we got the lock.
+ */
+ if (timer_pending(&proto->timer)) {
+ spin_unlock_irqrestore(&ppp->lock, flags);
+ return;
+ }
switch (proto->state) {
case STOPPING:
case REQ_SENT:
ath11k_hif_ce_irq_disable(ab);
ret = ath11k_hif_suspend(ab);
- if (!ret) {
+ if (ret) {
ath11k_warn(ab, "failed to suspend hif: %d\n", ret);
return ret;
}
{
u8 channel_num;
u32 center_freq;
+ struct ieee80211_channel *channel;
rx_status->freq = 0;
rx_status->rate_idx = 0;
rx_status->band = NL80211_BAND_5GHZ;
} else {
spin_lock_bh(&ar->data_lock);
- rx_status->band = ar->rx_channel->band;
- channel_num =
- ieee80211_frequency_to_channel(ar->rx_channel->center_freq);
+ channel = ar->rx_channel;
+ if (channel) {
+ rx_status->band = channel->band;
+ channel_num =
+ ieee80211_frequency_to_channel(channel->center_freq);
+ }
spin_unlock_bh(&ar->data_lock);
ath11k_dbg_dump(ar->ab, ATH11K_DBG_DATA, NULL, "rx_desc: ",
rx_desc, sizeof(struct hal_rx_desc));
}
if (ab->hw_params.vdev_start_delay &&
+ !arvif->is_started &&
arvif->vdev_type != WMI_VDEV_TYPE_AP) {
ret = ath11k_start_vdev_delay(ar->hw, vif);
if (ret) {
/* for QCA6390 bss peer must be created before vdev_start */
if (ab->hw_params.vdev_start_delay &&
arvif->vdev_type != WMI_VDEV_TYPE_AP &&
- arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
+ arvif->vdev_type != WMI_VDEV_TYPE_MONITOR &&
+ !ath11k_peer_find_by_vdev_id(ab, arvif->vdev_id)) {
memcpy(&arvif->chanctx, ctx, sizeof(*ctx));
ret = 0;
goto out;
goto out;
}
- if (ab->hw_params.vdev_start_delay) {
+ if (ab->hw_params.vdev_start_delay &&
+ (arvif->vdev_type == WMI_VDEV_TYPE_AP ||
+ arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)) {
param.vdev_id = arvif->vdev_id;
param.peer_type = WMI_PEER_TYPE_DEFAULT;
param.peer_addr = ar->mac_addr;
PCIE_QSERDES_COM_SYSCLK_EN_SEL_REG,
PCIE_QSERDES_COM_SYSCLK_EN_SEL_VAL,
PCIE_QSERDES_COM_SYSCLK_EN_SEL_MSK);
- if (!ret) {
+ if (ret) {
ath11k_warn(ab, "failed to set sysclk: %d\n", ret);
return ret;
}
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG1_REG,
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG1_VAL,
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG_MSK);
- if (!ret) {
+ if (ret) {
ath11k_warn(ab, "failed to set dtct config1 error: %d\n", ret);
return ret;
}
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG2_REG,
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG2_VAL,
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG_MSK);
- if (!ret) {
+ if (ret) {
ath11k_warn(ab, "failed to set dtct config2: %d\n", ret);
return ret;
}
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG4_REG,
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG4_VAL,
PCIE_USB3_PCS_MISC_OSC_DTCT_CONFIG_MSK);
- if (!ret) {
+ if (ret) {
ath11k_warn(ab, "failed to set dtct config4: %d\n", ret);
return ret;
}
pci_disable_device(pci_dev);
}
+static void ath11k_pci_aspm_disable(struct ath11k_pci *ab_pci)
+{
+ struct ath11k_base *ab = ab_pci->ab;
+
+ pcie_capability_read_word(ab_pci->pdev, PCI_EXP_LNKCTL,
+ &ab_pci->link_ctl);
+
+ ath11k_dbg(ab, ATH11K_DBG_PCI, "pci link_ctl 0x%04x L0s %d L1 %d\n",
+ ab_pci->link_ctl,
+ u16_get_bits(ab_pci->link_ctl, PCI_EXP_LNKCTL_ASPM_L0S),
+ u16_get_bits(ab_pci->link_ctl, PCI_EXP_LNKCTL_ASPM_L1));
+
+ /* disable L0s and L1 */
+ pcie_capability_write_word(ab_pci->pdev, PCI_EXP_LNKCTL,
+ ab_pci->link_ctl & ~PCI_EXP_LNKCTL_ASPMC);
+
+ set_bit(ATH11K_PCI_ASPM_RESTORE, &ab_pci->flags);
+}
+
+static void ath11k_pci_aspm_restore(struct ath11k_pci *ab_pci)
+{
+ if (test_and_clear_bit(ATH11K_PCI_ASPM_RESTORE, &ab_pci->flags))
+ pcie_capability_write_word(ab_pci->pdev, PCI_EXP_LNKCTL,
+ ab_pci->link_ctl);
+}
+
static int ath11k_pci_power_up(struct ath11k_base *ab)
{
struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
clear_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
ath11k_pci_sw_reset(ab_pci->ab, true);
+ /* Disable ASPM during firmware download due to problems switching
+ * to AMSS state.
+ */
+ ath11k_pci_aspm_disable(ab_pci);
+
ret = ath11k_mhi_start(ab_pci);
if (ret) {
ath11k_err(ab, "failed to start mhi: %d\n", ret);
{
struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
+ /* restore aspm in case firmware bootup fails */
+ ath11k_pci_aspm_restore(ab_pci);
+
ath11k_pci_force_wake(ab_pci->ab);
ath11k_mhi_stop(ab_pci);
clear_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
set_bit(ATH11K_PCI_FLAG_INIT_DONE, &ab_pci->flags);
+ ath11k_pci_aspm_restore(ab_pci);
+
ath11k_pci_ce_irqs_enable(ab);
ath11k_ce_rx_post_buf(ab);
enum ath11k_pci_flags {
ATH11K_PCI_FLAG_INIT_DONE,
ATH11K_PCI_FLAG_IS_MSI_64,
+ ATH11K_PCI_ASPM_RESTORE,
};
struct ath11k_pci {
/* enum ath11k_pci_flags */
unsigned long flags;
+ u16 link_ctl;
};
static inline struct ath11k_pci *ath11k_pci_priv(struct ath11k_base *ab)
return NULL;
}
+struct ath11k_peer *ath11k_peer_find_by_vdev_id(struct ath11k_base *ab,
+ int vdev_id)
+{
+ struct ath11k_peer *peer;
+
+ spin_lock_bh(&ab->base_lock);
+
+ list_for_each_entry(peer, &ab->peers, list) {
+ if (vdev_id == peer->vdev_id) {
+ spin_unlock_bh(&ab->base_lock);
+ return peer;
+ }
+ }
+ spin_unlock_bh(&ab->base_lock);
+ return NULL;
+}
+
void ath11k_peer_unmap_event(struct ath11k_base *ab, u16 peer_id)
{
struct ath11k_peer *peer;
struct ieee80211_sta *sta, struct peer_create_params *param);
int ath11k_wait_for_peer_delete_done(struct ath11k *ar, u32 vdev_id,
const u8 *addr);
+struct ath11k_peer *ath11k_peer_find_by_vdev_id(struct ath11k_base *ab,
+ int vdev_id);
#endif /* _PEER_H_ */
struct qmi_wlanfw_respond_mem_resp_msg_v01 resp;
struct qmi_txn txn = {};
int ret = 0, i;
+ bool delayed;
req = kzalloc(sizeof(*req), GFP_KERNEL);
if (!req)
* failure to FW and FW will then request mulitple blocks of small
* chunk size memory.
*/
- if (!ab->bus_params.fixed_mem_region && ab->qmi.mem_seg_count <= 2) {
+ if (!ab->bus_params.fixed_mem_region && ab->qmi.target_mem_delayed) {
+ delayed = true;
ath11k_dbg(ab, ATH11K_DBG_QMI, "qmi delays mem_request %d\n",
ab->qmi.mem_seg_count);
memset(req, 0, sizeof(*req));
} else {
+ delayed = false;
req->mem_seg_len = ab->qmi.mem_seg_count;
for (i = 0; i < req->mem_seg_len ; i++) {
}
if (resp.resp.result != QMI_RESULT_SUCCESS_V01) {
+ /* the error response is expected when
+ * target_mem_delayed is true.
+ */
+ if (delayed && resp.resp.error == 0)
+ goto out;
+
ath11k_warn(ab, "Respond mem req failed, result: %d, err: %d\n",
resp.resp.result, resp.resp.error);
ret = -EINVAL;
int i;
struct target_mem_chunk *chunk;
+ ab->qmi.target_mem_delayed = false;
+
for (i = 0; i < ab->qmi.mem_seg_count; i++) {
chunk = &ab->qmi.target_mem[i];
chunk->vaddr = dma_alloc_coherent(ab->dev,
&chunk->paddr,
GFP_KERNEL);
if (!chunk->vaddr) {
+ if (ab->qmi.mem_seg_count <= 2) {
+ ath11k_dbg(ab, ATH11K_DBG_QMI,
+ "qmi dma allocation failed (%d B type %u), will try later with small size\n",
+ chunk->size,
+ chunk->type);
+ ath11k_qmi_free_target_mem_chunk(ab);
+ ab->qmi.target_mem_delayed = true;
+ return 0;
+ }
ath11k_err(ab, "failed to alloc memory, size: 0x%x, type: %u\n",
chunk->size,
chunk->type);
ret);
return;
}
- } else if (msg->mem_seg_len > 2) {
+ } else {
ret = ath11k_qmi_alloc_target_mem_chunk(ab);
if (ret) {
ath11k_warn(ab, "qmi failed to alloc target memory: %d\n",
struct target_mem_chunk target_mem[ATH11K_QMI_WLANFW_MAX_NUM_MEM_SEG_V01];
u32 mem_seg_count;
u32 target_mem_mode;
+ bool target_mem_delayed;
u8 cal_done;
struct target_info target;
struct m3_mem_region m3_mem;
len = sizeof(*cmd);
skb = ath11k_wmi_alloc_skb(wmi_ab, len);
+ if (!skb)
+ return -ENOMEM;
+
cmd = (struct wmi_pdev_set_hw_mode_cmd_param *)skb->data;
cmd->tlv_header = FIELD_PREP(WMI_TLV_TAG, WMI_TAG_PDEV_SET_HW_MODE_CMD) |
config WIL6210
tristate "Wilocity 60g WiFi card wil6210 support"
select WANT_DEV_COREDUMP
+ select CRC32
depends on CFG80211
depends on PCI
default n
.types = BIT(NL80211_IFTYPE_ADHOC)
}, {
.max = 16,
- .types = BIT(NL80211_IFTYPE_AP) |
+ .types = BIT(NL80211_IFTYPE_AP)
#ifdef CONFIG_MAC80211_MESH
- BIT(NL80211_IFTYPE_MESH_POINT)
+ | BIT(NL80211_IFTYPE_MESH_POINT)
#endif
}, {
.max = MT7915_MAX_INTERFACES,
static int mt76s_process_tx_queue(struct mt76_dev *dev, struct mt76_queue *q)
{
- bool wake, mcu = q == dev->q_mcu[MT_MCUQ_WM];
struct mt76_queue_entry entry;
int nframes = 0;
+ bool mcu;
+ if (!q)
+ return 0;
+
+ mcu = q == dev->q_mcu[MT_MCUQ_WM];
while (q->queued > 0) {
if (!q->entry[q->tail].done)
break;
nframes++;
}
- wake = q->stopped && q->queued < q->ndesc - 8;
- if (wake)
- q->stopped = false;
-
if (!q->queued)
wake_up(&dev->tx_wait);
- if (mcu)
- goto out;
-
- mt76_txq_schedule(&dev->phy, q->qid);
+ if (!mcu)
+ mt76_txq_schedule(&dev->phy, q->qid);
- if (wake)
- ieee80211_wake_queue(dev->hw, q->qid);
-out:
return nframes;
}
struct mt76_dev *dev = container_of(usb, struct mt76_dev, usb);
struct mt76_queue_entry entry;
struct mt76_queue *q;
- bool wake;
int i;
for (i = 0; i < IEEE80211_NUM_ACS; i++) {
q = dev->phy.q_tx[i];
+ if (!q)
+ continue;
while (q->queued > 0) {
if (!q->entry[q->tail].done)
mt76_queue_tx_complete(dev, q, &entry);
}
- wake = q->stopped && q->queued < q->ndesc - 8;
- if (wake)
- q->stopped = false;
-
if (!q->queued)
wake_up(&dev->tx_wait);
if (dev->drv->tx_status_data &&
!test_and_set_bit(MT76_READING_STATS, &dev->phy.state))
queue_work(dev->wq, &dev->usb.stat_work);
- if (wake)
- ieee80211_wake_queue(dev->hw, i);
}
}
rtl_dbg(rtlpriv, COMP_ERR, DBG_LOUD,
"Firmware callback routine entered!\n");
- complete(&rtlpriv->firmware_loading_complete);
if (!firmware) {
if (rtlpriv->cfg->alt_fw_name) {
err = request_firmware(&firmware,
}
pr_err("Selected firmware is not available\n");
rtlpriv->max_fw_size = 0;
- return;
+ goto exit;
}
found_alt:
if (firmware->size > rtlpriv->max_fw_size) {
pr_err("Firmware is too big!\n");
release_firmware(firmware);
- return;
+ goto exit;
}
if (!is_wow) {
memcpy(rtlpriv->rtlhal.pfirmware, firmware->data,
rtlpriv->rtlhal.wowlan_fwsize = firmware->size;
}
release_firmware(firmware);
+
+exit:
+ complete(&rtlpriv->firmware_loading_complete);
}
void rtl_fw_cb(const struct firmware *firmware, void *context)
}
EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
-int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
{
int ret;
return ret;
}
-EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync);
static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
{
req->__sector = nvme_lba_to_sect(req->q->queuedata,
le64_to_cpu(nvme_req(req)->result.u64));
- nvme_trace_bio_complete(req, status);
+ nvme_trace_bio_complete(req);
blk_mq_end_request(req, status);
}
}
EXPORT_SYMBOL_GPL(nvme_alloc_request);
-struct request *nvme_alloc_request_qid(struct request_queue *q,
+static struct request *nvme_alloc_request_qid(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid)
{
struct request *req;
nvme_init_request(req, cmd);
return req;
}
-EXPORT_SYMBOL_GPL(nvme_alloc_request_qid);
static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
{
NULL,
};
+static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl)
+{
+ return ctrl->opts && ctrl->opts->discovery_nqn;
+}
+
static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
{
}
if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
- (ctrl->opts && ctrl->opts->discovery_nqn))
+ nvme_discovery_ctrl(ctrl))
continue;
dev_err(ctrl->device,
goto out_free;
}
- if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+ if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
dev_err(ctrl->device,
"keep-alive support is mandatory for fabrics\n");
ret = -EINVAL;
if (ret < 0)
return ret;
- if (!ctrl->identified) {
+ if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
ret = nvme_hwmon_init(ctrl);
if (ret < 0)
return ret;
struct blk_mq_tag_set admin_tag_set;
struct blk_mq_tag_set tag_set;
+ struct work_struct ioerr_work;
struct delayed_work connect_work;
struct kref ref;
}
}
+static void
+nvme_fc_ctrl_ioerr_work(struct work_struct *work)
+{
+ struct nvme_fc_ctrl *ctrl =
+ container_of(work, struct nvme_fc_ctrl, ioerr_work);
+
+ nvme_fc_error_recovery(ctrl, "transport detected io error");
+}
+
static void
nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
{
check_error:
if (terminate_assoc)
- nvme_fc_error_recovery(ctrl, "transport detected io error");
+ queue_work(nvme_reset_wq, &ctrl->ioerr_work);
}
static int
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+ cancel_work_sync(&ctrl->ioerr_work);
cancel_delayed_work_sync(&ctrl->connect_work);
/*
* kill the association on the link side. this will block
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->ioerr_work, nvme_fc_ctrl_ioerr_work);
spin_lock_init(&ctrl->lock);
/* io queue count */
fail_ctrl:
nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING);
+ cancel_work_sync(&ctrl->ioerr_work);
cancel_work_sync(&ctrl->ctrl.reset_work);
cancel_delayed_work_sync(&ctrl->connect_work);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, blk_mq_req_flags_t flags);
-struct request *nvme_alloc_request_qid(struct request_queue *q,
- struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
void nvme_cleanup_cmd(struct request *req);
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmd);
int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
-int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
kblockd_schedule_work(&head->requeue_work);
}
-static inline void nvme_trace_bio_complete(struct request *req,
- blk_status_t status)
+static inline void nvme_trace_bio_complete(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
{
}
-static inline void nvme_trace_bio_complete(struct request *req,
- blk_status_t status)
+static inline void nvme_trace_bio_complete(struct request *req)
{
}
static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx)
{
struct nvme_completion *cqe = &nvmeq->cqes[idx];
+ __u16 command_id = READ_ONCE(cqe->command_id);
struct request *req;
/*
* aborts. We don't even bother to allocate a struct request
* for them but rather special case them here.
*/
- if (unlikely(nvme_is_aen_req(nvmeq->qid, cqe->command_id))) {
+ if (unlikely(nvme_is_aen_req(nvmeq->qid, command_id))) {
nvme_complete_async_event(&nvmeq->dev->ctrl,
cqe->status, &cqe->result);
return;
}
- req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id);
+ req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), command_id);
if (unlikely(!req)) {
dev_warn(nvmeq->dev->ctrl.device,
"invalid id %d completed on queue %d\n",
- cqe->command_id, le16_to_cpu(cqe->sq_id));
+ command_id, le16_to_cpu(cqe->sq_id));
return;
}
{ PCI_DEVICE(0x144d, 0xa821), /* Samsung PM1725 */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */
- .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+ NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x1d1d, 0x1f1f), /* LighNVM qemu device */
.driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE(0x1d1d, 0x2807), /* CNEX WL */
static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req)
{
- return min_t(size_t, req->iter.bvec->bv_len - req->iter.iov_offset,
+ return min_t(size_t, iov_iter_single_seg_count(&req->iter),
req->pdu_len - req->pdu_sent);
}
}
}
+static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
+{
+ int ret;
+
+ /* drain the send queue as much as we can... */
+ do {
+ ret = nvme_tcp_try_send(queue);
+ } while (ret > 0);
+}
+
static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
bool sync, bool last)
{
* directly, otherwise queue io_work. Also, only do that if we
* are on the same cpu, so we don't introduce contention.
*/
- if (queue->io_cpu == smp_processor_id() &&
+ if (queue->io_cpu == __smp_processor_id() &&
sync && empty && mutex_trylock(&queue->send_mutex)) {
queue->more_requests = !last;
- nvme_tcp_try_send(queue);
+ nvme_tcp_send_all(queue);
queue->more_requests = false;
mutex_unlock(&queue->send_mutex);
} else if (last) {
fcloop_set_cmd_drop(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
- int opcode, starting, amount;
+ unsigned int opcode;
+ int starting, amount;
if (sscanf(buf, "%x:%d:%d", &opcode, &starting, &amount) != 3)
return -EBADRQC;
static void __exit fcloop_exit(void)
{
- struct fcloop_lport *lport;
- struct fcloop_nport *nport;
+ struct fcloop_lport *lport = NULL;
+ struct fcloop_nport *nport = NULL;
struct fcloop_tport *tport;
struct fcloop_rport *rport;
unsigned long flags;
}
ndev->inline_data_size = nport->inline_data_size;
ndev->inline_page_count = inline_page_count;
+
+ if (nport->pi_enable && !(cm_id->device->attrs.device_cap_flags &
+ IB_DEVICE_INTEGRITY_HANDOVER)) {
+ pr_warn("T10-PI is not supported by device %s. Disabling it\n",
+ cm_id->device->name);
+ nport->pi_enable = false;
+ }
+
ndev->device = cm_id->device;
kref_init(&ndev->ref);
spin_lock_irqsave(&queue->state_lock, flags);
switch (queue->state) {
case NVMET_RDMA_Q_CONNECTING:
+ while (!list_empty(&queue->rsp_wait_list)) {
+ struct nvmet_rdma_rsp *rsp;
+
+ rsp = list_first_entry(&queue->rsp_wait_list,
+ struct nvmet_rdma_rsp,
+ wait_list);
+ list_del(&rsp->wait_list);
+ nvmet_rdma_put_rsp(rsp);
+ }
+ fallthrough;
case NVMET_RDMA_Q_LIVE:
queue->state = NVMET_RDMA_Q_DISCONNECTING;
disconnect = true;
goto out_destroy_id;
}
- if (port->nport->pi_enable &&
- !(cm_id->device->attrs.device_cap_flags &
- IB_DEVICE_INTEGRITY_HANDOVER)) {
- pr_err("T10-PI is not supported for %pISpcs\n", addr);
- ret = -EINVAL;
- goto out_destroy_id;
- }
-
port->cm_id = cm_id;
return 0;
if (IS_ERR(opp_table->clk)) {
ret = PTR_ERR(opp_table->clk);
if (ret == -EPROBE_DEFER)
- goto err;
+ goto remove_opp_dev;
dev_dbg(dev, "%s: Couldn't find clock: %d\n", __func__, ret);
}
ret = dev_pm_opp_of_find_icc_paths(dev, opp_table);
if (ret) {
if (ret == -EPROBE_DEFER)
- goto err;
+ goto put_clk;
dev_warn(dev, "%s: Error finding interconnect paths: %d\n",
__func__, ret);
return opp_table;
+put_clk:
+ if (!IS_ERR(opp_table->clk))
+ clk_put(opp_table->clk);
+remove_opp_dev:
+ _remove_opp_dev(opp_dev, opp_table);
err:
kfree(opp_table);
return ERR_PTR(ret);
return per_cpu(hw_events->irq, cpu);
}
-bool arm_pmu_irq_is_nmi(void)
-{
- return has_nmi;
-}
-
/*
* PMU hardware loses all context when a CPU goes offline.
* When a CPU is hotplugged back in, since some hardware registers are
depends on NETWORK_PHY_TIMESTAMPING
depends on PHYLIB
depends on PTP_1588_CLOCK
+ select CRC32
help
Supports the DP83640 PHYTER with IEEE 1588 features.
config PTP_1588_CLOCK_INES
tristate "ZHAW InES PTP time stamping IP core"
depends on NETWORK_PHY_TIMESTAMPING
+ depends on HAS_IOMEM
depends on PHYLIB
depends on PTP_1588_CLOCK
help
config REGULATOR_QCOM_RPMH
tristate "Qualcomm Technologies, Inc. RPMh regulator driver"
depends on QCOM_RPMH || (QCOM_RPMH=n && COMPILE_TEST)
+ depends on QCOM_COMMAND_DB || (QCOM_COMMAND_DB=n && COMPILE_TEST)
help
This driver supports control of PMIC regulators via the RPMh hardware
block found on Qualcomm Technologies Inc. SoCs. RPMh regulator
#include <linux/regulator/of_regulator.h>
#include <linux/slab.h>
+/* Typical regulator startup times as per data sheet in uS */
+#define BD71847_BUCK1_STARTUP_TIME 144
+#define BD71847_BUCK2_STARTUP_TIME 162
+#define BD71847_BUCK3_STARTUP_TIME 162
+#define BD71847_BUCK4_STARTUP_TIME 240
+#define BD71847_BUCK5_STARTUP_TIME 270
+#define BD71847_BUCK6_STARTUP_TIME 200
+#define BD71847_LDO1_STARTUP_TIME 440
+#define BD71847_LDO2_STARTUP_TIME 370
+#define BD71847_LDO3_STARTUP_TIME 310
+#define BD71847_LDO4_STARTUP_TIME 400
+#define BD71847_LDO5_STARTUP_TIME 530
+#define BD71847_LDO6_STARTUP_TIME 400
+
+#define BD71837_BUCK1_STARTUP_TIME 160
+#define BD71837_BUCK2_STARTUP_TIME 180
+#define BD71837_BUCK3_STARTUP_TIME 180
+#define BD71837_BUCK4_STARTUP_TIME 180
+#define BD71837_BUCK5_STARTUP_TIME 160
+#define BD71837_BUCK6_STARTUP_TIME 240
+#define BD71837_BUCK7_STARTUP_TIME 220
+#define BD71837_BUCK8_STARTUP_TIME 200
+#define BD71837_LDO1_STARTUP_TIME 440
+#define BD71837_LDO2_STARTUP_TIME 370
+#define BD71837_LDO3_STARTUP_TIME 310
+#define BD71837_LDO4_STARTUP_TIME 400
+#define BD71837_LDO5_STARTUP_TIME 310
+#define BD71837_LDO6_STARTUP_TIME 400
+#define BD71837_LDO7_STARTUP_TIME 530
+
/*
* BD718(37/47/50) have two "enable control modes". ON/OFF can either be
* controlled by software - or by PMIC internal HW state machine. Whether
.vsel_mask = DVS_BUCK_RUN_MASK,
.enable_reg = BD718XX_REG_BUCK1_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71847_BUCK1_STARTUP_TIME,
.owner = THIS_MODULE,
.of_parse_cb = buck_set_hw_dvs_levels,
},
.vsel_mask = DVS_BUCK_RUN_MASK,
.enable_reg = BD718XX_REG_BUCK2_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71847_BUCK2_STARTUP_TIME,
.owner = THIS_MODULE,
.of_parse_cb = buck_set_hw_dvs_levels,
},
.linear_range_selectors = bd71847_buck3_volt_range_sel,
.enable_reg = BD718XX_REG_1ST_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71847_BUCK3_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_range_mask = BD71847_BUCK4_RANGE_MASK,
.linear_range_selectors = bd71847_buck4_volt_range_sel,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71847_BUCK4_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_3RD_NODVS_BUCK_MASK,
.enable_reg = BD718XX_REG_3RD_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71847_BUCK5_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_4TH_NODVS_BUCK_MASK,
.enable_reg = BD718XX_REG_4TH_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71847_BUCK6_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.linear_range_selectors = bd718xx_ldo1_volt_range_sel,
.enable_reg = BD718XX_REG_LDO1_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71847_LDO1_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.n_voltages = ARRAY_SIZE(ldo_2_volts),
.enable_reg = BD718XX_REG_LDO2_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71847_LDO2_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_LDO3_MASK,
.enable_reg = BD718XX_REG_LDO3_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71847_LDO3_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_LDO4_MASK,
.enable_reg = BD718XX_REG_LDO4_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71847_LDO4_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.linear_range_selectors = bd71847_ldo5_volt_range_sel,
.enable_reg = BD718XX_REG_LDO5_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71847_LDO5_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_LDO6_MASK,
.enable_reg = BD718XX_REG_LDO6_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71847_LDO6_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = DVS_BUCK_RUN_MASK,
.enable_reg = BD718XX_REG_BUCK1_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK1_STARTUP_TIME,
.owner = THIS_MODULE,
.of_parse_cb = buck_set_hw_dvs_levels,
},
.vsel_mask = DVS_BUCK_RUN_MASK,
.enable_reg = BD718XX_REG_BUCK2_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK2_STARTUP_TIME,
.owner = THIS_MODULE,
.of_parse_cb = buck_set_hw_dvs_levels,
},
.vsel_mask = DVS_BUCK_RUN_MASK,
.enable_reg = BD71837_REG_BUCK3_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK3_STARTUP_TIME,
.owner = THIS_MODULE,
.of_parse_cb = buck_set_hw_dvs_levels,
},
.vsel_mask = DVS_BUCK_RUN_MASK,
.enable_reg = BD71837_REG_BUCK4_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK4_STARTUP_TIME,
.owner = THIS_MODULE,
.of_parse_cb = buck_set_hw_dvs_levels,
},
.linear_range_selectors = bd71837_buck5_volt_range_sel,
.enable_reg = BD718XX_REG_1ST_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK5_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD71837_BUCK6_MASK,
.enable_reg = BD718XX_REG_2ND_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK6_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_3RD_NODVS_BUCK_MASK,
.enable_reg = BD718XX_REG_3RD_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK7_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_4TH_NODVS_BUCK_MASK,
.enable_reg = BD718XX_REG_4TH_NODVS_BUCK_CTRL,
.enable_mask = BD718XX_BUCK_EN,
+ .enable_time = BD71837_BUCK8_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.linear_range_selectors = bd718xx_ldo1_volt_range_sel,
.enable_reg = BD718XX_REG_LDO1_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO1_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.n_voltages = ARRAY_SIZE(ldo_2_volts),
.enable_reg = BD718XX_REG_LDO2_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO2_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_LDO3_MASK,
.enable_reg = BD718XX_REG_LDO3_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO3_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_LDO4_MASK,
.enable_reg = BD718XX_REG_LDO4_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO4_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD71837_LDO5_MASK,
.enable_reg = BD718XX_REG_LDO5_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO5_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD718XX_LDO6_MASK,
.enable_reg = BD718XX_REG_LDO6_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO6_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
.vsel_mask = BD71837_LDO7_MASK,
.enable_reg = BD71837_REG_LDO7_VOLT,
.enable_mask = BD718XX_LDO_EN,
+ .enable_time = BD71837_LDO7_STARTUP_TIME,
.owner = THIS_MODULE,
},
.init = {
}
static const struct of_device_id pf8x00_dt_ids[] = {
- { .compatible = "nxp,pf8x00",},
+ { .compatible = "nxp,pf8100",},
+ { .compatible = "nxp,pf8121a",},
+ { .compatible = "nxp,pf8200",},
{ }
};
MODULE_DEVICE_TABLE(of, pf8x00_dt_ids);
static const struct i2c_device_id pf8x00_i2c_id[] = {
- { "pf8x00", 0 },
+ { "pf8100", 0 },
+ { "pf8121a", 0 },
+ { "pf8200", 0 },
{},
};
MODULE_DEVICE_TABLE(i2c, pf8x00_i2c_id);
static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
.regulator_type = VRM,
.ops = &rpmh_regulator_vrm_ops,
- .voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 1600),
+ .voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 16000),
.n_voltages = 5,
.pmic_mode_map = pmic_mode_map_pmic5_smps,
.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads,
int clear_start_mask);
int qeth_threads_running(struct qeth_card *, unsigned long);
-int qeth_set_offline(struct qeth_card *card, bool resetting);
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+ bool resetting);
int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
int (*reply_cb)
return rc;
}
-static int qeth_set_online(struct qeth_card *card)
+static int qeth_set_online(struct qeth_card *card,
+ const struct qeth_discipline *disc)
{
bool carrier_ok;
int rc;
- mutex_lock(&card->discipline_mutex);
mutex_lock(&card->conf_mutex);
QETH_CARD_TEXT(card, 2, "setonlin");
/* no need for locking / error handling at this early stage: */
qeth_set_real_num_tx_queues(card, qeth_tx_actual_queues(card));
- rc = card->discipline->set_online(card, carrier_ok);
+ rc = disc->set_online(card, carrier_ok);
if (rc)
goto err_online;
kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return 0;
err_online:
qdio_free(CARD_DDEV(card));
mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return rc;
}
-int qeth_set_offline(struct qeth_card *card, bool resetting)
+int qeth_set_offline(struct qeth_card *card, const struct qeth_discipline *disc,
+ bool resetting)
{
int rc, rc2, rc3;
- mutex_lock(&card->discipline_mutex);
mutex_lock(&card->conf_mutex);
QETH_CARD_TEXT(card, 3, "setoffl");
cancel_work_sync(&card->rx_mode_work);
- card->discipline->set_offline(card);
+ disc->set_offline(card);
qeth_qdio_clear_card(card, 0);
qeth_drain_output_queues(card);
kobject_uevent(&card->gdev->dev.kobj, KOBJ_CHANGE);
mutex_unlock(&card->conf_mutex);
- mutex_unlock(&card->discipline_mutex);
return 0;
}
EXPORT_SYMBOL_GPL(qeth_set_offline);
static int qeth_do_reset(void *data)
{
+ const struct qeth_discipline *disc;
struct qeth_card *card = data;
int rc;
+ /* Lock-free, other users will block until we are done. */
+ disc = card->discipline;
+
QETH_CARD_TEXT(card, 2, "recover1");
if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
return 0;
dev_warn(&card->gdev->dev,
"A recovery process has been started for the device\n");
- qeth_set_offline(card, true);
- rc = qeth_set_online(card);
+ qeth_set_offline(card, disc, true);
+ rc = qeth_set_online(card, disc);
if (!rc) {
dev_info(&card->gdev->dev,
"Device successfully recovered!\n");
break;
default:
card->info.layer_enforced = true;
+ /* It's so early that we don't need the discipline_mutex yet. */
rc = qeth_core_load_discipline(card, enforced_disc);
if (rc)
goto err_load;
QETH_CARD_TEXT(card, 2, "removedv");
+ mutex_lock(&card->discipline_mutex);
if (card->discipline) {
card->discipline->remove(gdev);
qeth_core_free_discipline(card);
}
+ mutex_unlock(&card->discipline_mutex);
qeth_free_qdio_queues(card);
int rc = 0;
enum qeth_discipline_id def_discipline;
+ mutex_lock(&card->discipline_mutex);
if (!card->discipline) {
def_discipline = IS_IQD(card) ? QETH_DISCIPLINE_LAYER3 :
QETH_DISCIPLINE_LAYER2;
}
}
- rc = qeth_set_online(card);
+ rc = qeth_set_online(card, card->discipline);
+
err:
+ mutex_unlock(&card->discipline_mutex);
return rc;
}
static int qeth_core_set_offline(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ int rc;
- return qeth_set_offline(card, false);
+ mutex_lock(&card->discipline_mutex);
+ rc = qeth_set_offline(card, card->discipline, false);
+ mutex_unlock(&card->discipline_mutex);
+
+ return rc;
}
static void qeth_core_shutdown(struct ccwgroup_device *gdev)
wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
if (gdev->state == CCWGROUP_ONLINE)
- qeth_set_offline(card, false);
+ qeth_set_offline(card, card->discipline, false);
cancel_work_sync(&card->close_dev_work);
if (card->dev->reg_state == NETREG_REGISTERED)
struct net_device *dev,
netdev_features_t features)
{
- if (qeth_get_ip_version(skb) != 4)
+ if (vlan_get_protocol(skb) != htons(ETH_P_IP))
features &= ~NETIF_F_HW_VLAN_CTAG_TX;
return qeth_features_check(skb, dev, features);
}
wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
if (cgdev->state == CCWGROUP_ONLINE)
- qeth_set_offline(card, false);
+ qeth_set_offline(card, card->discipline, false);
cancel_work_sync(&card->close_dev_work);
if (card->dev->reg_state == NETREG_REGISTERED)
depends on PCI && INET && (IPV6 || IPV6=n)
depends on THERMAL || !THERMAL
depends on ETHERNET
+ depends on TLS || TLS=n
select NET_VENDOR_CHELSIO
select CHELSIO_T4
select CHELSIO_LIB
#include <linux/debugfs.h>
#include <linux/dmapool.h>
#include <linux/iopoll.h>
+#include <linux/irq.h>
#include <linux/lcm.h>
#include <linux/libata.h>
#include <linux/mfd/syscon.h>
struct hisi_sas_hw {
int (*hw_init)(struct hisi_hba *hisi_hba);
+ int (*interrupt_preinit)(struct hisi_hba *hisi_hba);
void (*setup_itct)(struct hisi_hba *hisi_hba,
struct hisi_sas_device *device);
int (*slot_index_alloc)(struct hisi_hba *hisi_hba,
u32 refclk_frequency_mhz;
u8 sas_addr[SAS_ADDR_SIZE];
+ int *irq_map; /* v2 hw */
+
int n_phy;
spinlock_t lock;
struct semaphore sem;
return NULL;
}
+static int hisi_sas_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+ if (hisi_hba->hw->interrupt_preinit)
+ return hisi_hba->hw->interrupt_preinit(hisi_hba);
+ return 0;
+}
+
int hisi_sas_probe(struct platform_device *pdev,
const struct hisi_sas_hw *hw)
{
sha->sas_port[i] = &hisi_hba->port[i].sas_port;
}
+ rc = hisi_sas_interrupt_preinit(hisi_hba);
+ if (rc)
+ goto err_out_ha;
+
rc = scsi_add_host(shost, &pdev->dev);
if (rc)
goto err_out_ha;
fatal_axi_int_v2_hw
};
+#define CQ0_IRQ_INDEX (96)
+
+static int hisi_sas_v2_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+ struct platform_device *pdev = hisi_hba->platform_dev;
+ struct Scsi_Host *shost = hisi_hba->shost;
+ struct irq_affinity desc = {
+ .pre_vectors = CQ0_IRQ_INDEX,
+ .post_vectors = 16,
+ };
+ int resv = desc.pre_vectors + desc.post_vectors, minvec = resv + 1, nvec;
+
+ nvec = devm_platform_get_irqs_affinity(pdev, &desc, minvec, 128,
+ &hisi_hba->irq_map);
+ if (nvec < 0)
+ return nvec;
+
+ shost->nr_hw_queues = hisi_hba->cq_nvecs = nvec - resv;
+
+ return 0;
+}
+
/*
* There is a limitation in the hip06 chipset that we need
* to map in all mbigen interrupts, even if they are not used.
{
struct platform_device *pdev = hisi_hba->platform_dev;
struct device *dev = &pdev->dev;
- int irq, rc = 0, irq_map[128];
+ int irq, rc = 0;
int i, phy_no, fatal_no, queue_no;
- for (i = 0; i < 128; i++)
- irq_map[i] = platform_get_irq(pdev, i);
-
for (i = 0; i < HISI_SAS_PHY_INT_NR; i++) {
- irq = irq_map[i + 1]; /* Phy up/down is irq1 */
+ irq = hisi_hba->irq_map[i + 1]; /* Phy up/down is irq1 */
rc = devm_request_irq(dev, irq, phy_interrupts[i], 0,
DRV_NAME " phy", hisi_hba);
if (rc) {
for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
- irq = irq_map[phy_no + 72];
+ irq = hisi_hba->irq_map[phy_no + 72];
rc = devm_request_irq(dev, irq, sata_int_v2_hw, 0,
DRV_NAME " sata", phy);
if (rc) {
}
for (fatal_no = 0; fatal_no < HISI_SAS_FATAL_INT_NR; fatal_no++) {
- irq = irq_map[fatal_no + 81];
+ irq = hisi_hba->irq_map[fatal_no + 81];
rc = devm_request_irq(dev, irq, fatal_interrupts[fatal_no], 0,
DRV_NAME " fatal", hisi_hba);
if (rc) {
}
}
- for (queue_no = 0; queue_no < hisi_hba->queue_count; queue_no++) {
+ for (queue_no = 0; queue_no < hisi_hba->cq_nvecs; queue_no++) {
struct hisi_sas_cq *cq = &hisi_hba->cq[queue_no];
- cq->irq_no = irq_map[queue_no + 96];
+ cq->irq_no = hisi_hba->irq_map[queue_no + 96];
rc = devm_request_threaded_irq(dev, cq->irq_no,
cq_interrupt_v2_hw,
cq_thread_v2_hw, IRQF_ONESHOT,
DRV_NAME " cq", cq);
if (rc) {
dev_err(dev, "irq init: could not request cq interrupt %d, rc=%d\n",
- irq, rc);
+ cq->irq_no, rc);
rc = -ENOENT;
goto err_out;
}
+ cq->irq_mask = irq_get_affinity_mask(cq->irq_no);
}
-
- hisi_hba->cq_nvecs = hisi_hba->queue_count;
-
err_out:
return rc;
}
NULL
};
+static int map_queues_v2_hw(struct Scsi_Host *shost)
+{
+ struct hisi_hba *hisi_hba = shost_priv(shost);
+ struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+ const struct cpumask *mask;
+ unsigned int queue, cpu;
+
+ for (queue = 0; queue < qmap->nr_queues; queue++) {
+ mask = irq_get_affinity_mask(hisi_hba->irq_map[96 + queue]);
+ if (!mask)
+ continue;
+
+ for_each_cpu(cpu, mask)
+ qmap->mq_map[cpu] = qmap->queue_offset + queue;
+ }
+
+ return 0;
+
+}
+
static struct scsi_host_template sht_v2_hw = {
.name = DRV_NAME,
.proc_name = DRV_NAME,
#endif
.shost_attrs = host_attrs_v2_hw,
.host_reset = hisi_sas_host_reset,
+ .map_queues = map_queues_v2_hw,
+ .host_tagset = 1,
};
static const struct hisi_sas_hw hisi_sas_v2_hw = {
.hw_init = hisi_sas_v2_init,
+ .interrupt_preinit = hisi_sas_v2_interrupt_preinit,
.setup_itct = setup_itct_v2_hw,
.slot_index_alloc = slot_index_alloc_quirk_v2_hw,
.alloc_dev = alloc_dev_quirk_v2_hw,
#include <linux/poll.h>
#include <linux/vmalloc.h>
#include <linux/irq_poll.h>
+#include <linux/blk-mq-pci.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
module_param(enable_sdev_max_qd, int, 0444);
MODULE_PARM_DESC(enable_sdev_max_qd, "Enable sdev max qd as can_queue. Default: 0");
+int host_tagset_enable = 1;
+module_param(host_tagset_enable, int, 0444);
+MODULE_PARM_DESC(host_tagset_enable, "Shared host tagset enable/disable Default: enable(1)");
+
MODULE_LICENSE("GPL");
MODULE_VERSION(MEGASAS_VERSION);
MODULE_AUTHOR("megaraidlinux.pdl@broadcom.com");
return 0;
}
+static int megasas_map_queues(struct Scsi_Host *shost)
+{
+ struct megasas_instance *instance;
+
+ instance = (struct megasas_instance *)shost->hostdata;
+
+ if (shost->nr_hw_queues == 1)
+ return 0;
+
+ return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT],
+ instance->pdev, instance->low_latency_index_start);
+}
+
static void megasas_aen_polling(struct work_struct *work);
/**
.eh_timed_out = megasas_reset_timer,
.shost_attrs = megaraid_host_attrs,
.bios_param = megasas_bios_param,
+ .map_queues = megasas_map_queues,
.change_queue_depth = scsi_change_queue_depth,
.max_segment_size = 0xffffffff,
};
host->max_lun = MEGASAS_MAX_LUN;
host->max_cmd_len = 16;
+ /* Use shared host tagset only for fusion adaptors
+ * if there are managed interrupts (smp affinity enabled case).
+ * Single msix_vectors in kdump, so shared host tag is also disabled.
+ */
+
+ host->host_tagset = 0;
+ host->nr_hw_queues = 1;
+
+ if ((instance->adapter_type != MFI_SERIES) &&
+ (instance->msix_vectors > instance->low_latency_index_start) &&
+ host_tagset_enable &&
+ instance->smp_affinity_enable) {
+ host->host_tagset = 1;
+ host->nr_hw_queues = instance->msix_vectors -
+ instance->low_latency_index_start;
+ }
+
+ dev_info(&instance->pdev->dev,
+ "Max firmware commands: %d shared with nr_hw_queues = %d\n",
+ instance->max_fw_cmds, host->nr_hw_queues);
/*
* Notify the mid-layer about the new controller
*/
{
int sdev_busy;
- /* nr_hw_queue = 1 for MegaRAID */
- struct blk_mq_hw_ctx *hctx =
- scmd->device->request_queue->queue_hw_ctx[0];
-
- sdev_busy = atomic_read(&hctx->nr_active);
+ /* TBD - if sml remove device_busy in future, driver
+ * should track counter in internal structure.
+ */
+ sdev_busy = atomic_read(&scmd->device->device_busy);
if (instance->perf_mode == MR_BALANCED_PERF_MODE &&
- sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH))
+ sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH)) {
cmd->request_desc->SCSIIO.MSIxIndex =
mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) /
MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start);
- else if (instance->msix_load_balance)
+ } else if (instance->msix_load_balance) {
cmd->request_desc->SCSIIO.MSIxIndex =
(mega_mod64(atomic64_add_return(1, &instance->total_io_count),
instance->msix_vectors));
- else
+ } else if (instance->host->nr_hw_queues > 1) {
+ u32 tag = blk_mq_unique_tag(scmd->request);
+
+ cmd->request_desc->SCSIIO.MSIxIndex = blk_mq_unique_tag_to_hwq(tag) +
+ instance->low_latency_index_start;
+ } else {
cmd->request_desc->SCSIIO.MSIxIndex =
instance->reply_map[raw_smp_processor_id()];
+ }
}
/**
if (megasas_alloc_cmdlist_fusion(instance))
goto fail_exit;
- dev_info(&instance->pdev->dev, "Configured max firmware commands: %d\n",
- instance->max_fw_cmds);
-
/* The first 256 bytes (SMID 0) is not used. Don't add to the cmd list */
io_req_base = fusion->io_request_frames + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
io_req_base_phys = fusion->io_request_frames_phys + MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE;
MR_HIGH_IOPS_QUEUE_COUNT) && cur_intr_coalescing)
instance->perf_mode = MR_BALANCED_PERF_MODE;
- dev_info(&instance->pdev->dev, "Performance mode :%s\n",
- MEGASAS_PERF_MODE_2STR(instance->perf_mode));
+ dev_info(&instance->pdev->dev, "Performance mode :%s (latency index = %d)\n",
+ MEGASAS_PERF_MODE_2STR(instance->perf_mode),
+ instance->low_latency_index_start);
instance->fw_sync_cache_support = (scratch_pad_1 &
MR_CAN_HANDLE_SYNC_CACHE_OFFSET) ? 1 : 0;
select SCSI_MPT3SAS
depends on PCI && SCSI
help
- Dummy config option for backwards compatiblity: configure the MPT3SAS
+ Dummy config option for backwards compatibility: configure the MPT3SAS
driver instead.
static void
_base_get_diag_triggers(struct MPT3SAS_ADAPTER *ioc)
{
- u16 trigger_flags;
+ int trigger_flags;
/*
* Default setting of master trigger.
chap_name);
break;
case ISCSI_BOOT_TGT_CHAP_SECRET:
- rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+ rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
chap_secret);
break;
case ISCSI_BOOT_TGT_REV_CHAP_NAME:
mchap_name);
break;
case ISCSI_BOOT_TGT_REV_CHAP_SECRET:
- rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+ rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
mchap_secret);
break;
case ISCSI_BOOT_TGT_FLAGS:
k = sdeb_zbc_model_str(sdeb_zbc_model_s);
if (k < 0) {
ret = k;
- goto free_vm;
+ goto free_q_arr;
}
sdeb_zbc_model = k;
switch (sdeb_zbc_model) {
break;
default:
pr_err("Invalid ZBC model\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto free_q_arr;
}
}
if (sdeb_zbc_model != BLK_ZONED_NONE) {
req = blk_get_request(sdev->request_queue,
data_direction == DMA_TO_DEVICE ?
- REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, BLK_MQ_REQ_PREEMPT);
+ REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+ rq_flags & RQF_PM ? BLK_MQ_REQ_PM : 0);
if (IS_ERR(req))
return ret;
rq = scsi_req(req);
scsi_device_state_check(struct scsi_device *sdev, struct request *req)
{
switch (sdev->sdev_state) {
+ case SDEV_CREATED:
+ return BLK_STS_OK;
case SDEV_OFFLINE:
case SDEV_TRANSPORT_OFFLINE:
/*
return BLK_STS_RESOURCE;
case SDEV_QUIESCE:
/*
- * If the devices is blocked we defer normal commands.
+ * If the device is blocked we only accept power management
+ * commands.
*/
- if (req && !(req->rq_flags & RQF_PREEMPT))
+ if (req && WARN_ON_ONCE(!(req->rq_flags & RQF_PM)))
return BLK_STS_RESOURCE;
return BLK_STS_OK;
default:
/*
* For any other not fully online state we only allow
- * special commands. In particular any user initiated
- * command is not allowed.
+ * power management commands.
*/
- if (req && !(req->rq_flags & RQF_PREEMPT))
+ if (req && !(req->rq_flags & RQF_PM))
return BLK_STS_IOERR;
return BLK_STS_OK;
}
EXPORT_SYMBOL_GPL(sdev_evt_send_simple);
/**
- * scsi_device_quiesce - Block user issued commands.
+ * scsi_device_quiesce - Block all commands except power management.
* @sdev: scsi device to quiesce.
*
* This works by trying to transition to the SDEV_QUIESCE state
* (which must be a legal transition). When the device is in this
- * state, only special requests will be accepted, all others will
- * be deferred. Since special requests may also be requeued requests,
- * a successful return doesn't guarantee the device will be
- * totally quiescent.
+ * state, only power management requests will be accepted, all others will
+ * be deferred.
*
* Must be called with user context, may sleep.
*
* device deleted during suspend)
*/
mutex_lock(&sdev->state_mutex);
+ if (sdev->sdev_state == SDEV_QUIESCE)
+ scsi_device_set_state(sdev, SDEV_RUNNING);
if (sdev->quiesced_by) {
sdev->quiesced_by = NULL;
blk_clear_pm_only(sdev->request_queue);
}
- if (sdev->sdev_state == SDEV_QUIESCE)
- scsi_device_set_state(sdev, SDEV_RUNNING);
mutex_unlock(&sdev->state_mutex);
}
EXPORT_SYMBOL(scsi_device_resume);
sshdr = &sshdr_tmp;
for(i = 0; i < DV_RETRIES; i++) {
+ /*
+ * The purpose of the RQF_PM flag below is to bypass the
+ * SDEV_QUIESCE state.
+ */
result = scsi_execute(sdev, cmd, dir, buffer, bufflen, sense,
sshdr, DV_TIMEOUT, /* retries */ 1,
REQ_FAILFAST_DEV |
REQ_FAILFAST_TRANSPORT |
REQ_FAILFAST_DRIVER,
- 0, NULL);
+ RQF_PM, NULL);
if (driver_byte(result) != DRIVER_SENSE ||
sshdr->sense_key != UNIT_ATTENTION)
break;
*/
lock_system_sleep();
+ if (scsi_autopm_get_device(sdev))
+ goto unlock_system_sleep;
+
if (unlikely(spi_dv_in_progress(starget)))
- goto unlock;
+ goto put_autopm;
if (unlikely(scsi_device_get(sdev)))
- goto unlock;
+ goto put_autopm;
spi_dv_in_progress(starget) = 1;
buffer = kzalloc(len, GFP_KERNEL);
if (unlikely(!buffer))
- goto out_put;
+ goto put_sdev;
/* We need to verify that the actual device will quiesce; the
* later target quiesce is just a nice to have */
if (unlikely(scsi_device_quiesce(sdev)))
- goto out_free;
+ goto free_buffer;
scsi_target_quiesce(starget);
spi_initial_dv(starget) = 1;
- out_free:
+free_buffer:
kfree(buffer);
- out_put:
+
+put_sdev:
spi_dv_in_progress(starget) = 0;
scsi_device_put(sdev);
-unlock:
+put_autopm:
+ scsi_autopm_put_device(sdev);
+
+unlock_system_sleep:
unlock_system_sleep();
}
EXPORT_SYMBOL(spi_dv_device);
}
}
- if (sdp->no_write_same)
+ if (sdp->no_write_same) {
+ rq->rq_flags |= RQF_QUIET;
return BLK_STS_TARGET;
+ }
if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff)
return sd_setup_write_same16_cmnd(cmd, false);
static int sd_remove(struct device *dev)
{
struct scsi_disk *sdkp;
- dev_t devt;
sdkp = dev_get_drvdata(dev);
- devt = disk_devt(sdkp->disk);
scsi_autopm_get_device(sdkp->device);
async_synchronize_full_domain(&scsi_sd_pm_domain);
#undef TRACE_INCLUDE_PATH
#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_PATH ../../drivers/scsi/ufs/
#define TRACE_INCLUDE_FILE ufs-mediatek-trace
#include <trace/define_trace.h>
return !!(host->caps & UFS_MTK_CAP_VA09_PWR_CTRL);
}
+static bool ufs_mtk_is_broken_vcc(struct ufs_hba *hba)
+{
+ struct ufs_mtk_host *host = ufshcd_get_variant(hba);
+
+ return !!(host->caps & UFS_MTK_CAP_BROKEN_VCC);
+}
+
static void ufs_mtk_cfg_unipro_cg(struct ufs_hba *hba, bool enable)
{
u32 tmp;
if (of_property_read_bool(np, "mediatek,ufs-disable-ah8"))
host->caps |= UFS_MTK_CAP_DISABLE_AH8;
+ if (of_property_read_bool(np, "mediatek,ufs-broken-vcc"))
+ host->caps |= UFS_MTK_CAP_BROKEN_VCC;
+
dev_info(hba->dev, "caps: 0x%x", host->caps);
}
static void ufs_mtk_fixup_dev_quirks(struct ufs_hba *hba)
{
ufshcd_fixup_dev_quirks(hba, ufs_mtk_dev_fixups);
+
+ if (ufs_mtk_is_broken_vcc(hba) && hba->vreg_info.vcc &&
+ (hba->dev_quirks & UFS_DEVICE_QUIRK_DELAY_AFTER_LPM)) {
+ hba->vreg_info.vcc->always_on = true;
+ /*
+ * VCC will be kept always-on thus we don't
+ * need any delay during regulator operations
+ */
+ hba->dev_quirks &= ~(UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM |
+ UFS_DEVICE_QUIRK_DELAY_AFTER_LPM);
+ }
}
static void ufs_mtk_event_notify(struct ufs_hba *hba,
UFS_MTK_CAP_BOOST_CRYPT_ENGINE = 1 << 0,
UFS_MTK_CAP_VA09_PWR_CTRL = 1 << 1,
UFS_MTK_CAP_DISABLE_AH8 = 1 << 2,
+ UFS_MTK_CAP_BROKEN_VCC = 1 << 3,
};
struct ufs_mtk_crypt_cfg {
UFS_DEV_WRITE_BOOSTER_SUP = BIT(8),
};
-#define POWER_DESC_MAX_SIZE 0x62
#define POWER_DESC_MAX_ACTV_ICC_LVLS 16
/* Attribute bActiveICCLevel parameter bit masks definitions */
struct ufs_vreg {
struct regulator *reg;
const char *name;
+ bool always_on;
bool enabled;
int min_uV;
int max_uV;
{
struct intel_host *host;
+ hba->caps |= UFSHCD_CAP_RPM_AUTOSUSPEND;
+
host = devm_kzalloc(hba->dev, sizeof(*host), GFP_KERNEL);
if (!host)
return -ENOMEM;
intel_ltr_hide(hba->dev);
}
+static int ufs_intel_resume(struct ufs_hba *hba, enum ufs_pm_op op)
+{
+ /*
+ * To support S4 (suspend-to-disk) with spm_lvl other than 5, the base
+ * address registers must be restored because the restore kernel can
+ * have used different addresses.
+ */
+ ufshcd_writel(hba, lower_32_bits(hba->utrdl_dma_addr),
+ REG_UTP_TRANSFER_REQ_LIST_BASE_L);
+ ufshcd_writel(hba, upper_32_bits(hba->utrdl_dma_addr),
+ REG_UTP_TRANSFER_REQ_LIST_BASE_H);
+ ufshcd_writel(hba, lower_32_bits(hba->utmrdl_dma_addr),
+ REG_UTP_TASK_REQ_LIST_BASE_L);
+ ufshcd_writel(hba, upper_32_bits(hba->utmrdl_dma_addr),
+ REG_UTP_TASK_REQ_LIST_BASE_H);
+
+ if (ufshcd_is_link_hibern8(hba)) {
+ int ret = ufshcd_uic_hibern8_exit(hba);
+
+ if (!ret) {
+ ufshcd_set_link_active(hba);
+ } else {
+ dev_err(hba->dev, "%s: hibern8 exit failed %d\n",
+ __func__, ret);
+ /*
+ * Force reset and restore. Any other actions can lead
+ * to an unrecoverable state.
+ */
+ ufshcd_set_link_off(hba);
+ }
+ }
+
+ return 0;
+}
+
static int ufs_intel_ehl_init(struct ufs_hba *hba)
{
hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8;
.init = ufs_intel_common_init,
.exit = ufs_intel_common_exit,
.link_startup_notify = ufs_intel_link_startup_notify,
+ .resume = ufs_intel_resume,
};
static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = {
.init = ufs_intel_ehl_init,
.exit = ufs_intel_common_exit,
.link_startup_notify = ufs_intel_link_startup_notify,
+ .resume = ufs_intel_resume,
};
#ifdef CONFIG_PM_SLEEP
{
return ufshcd_system_resume(dev_get_drvdata(dev));
}
+
+/**
+ * ufshcd_pci_poweroff - suspend-to-disk poweroff function
+ * @dev: pointer to PCI device handle
+ *
+ * Returns 0 if successful
+ * Returns non-zero otherwise
+ */
+static int ufshcd_pci_poweroff(struct device *dev)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+ int spm_lvl = hba->spm_lvl;
+ int ret;
+
+ /*
+ * For poweroff we need to set the UFS device to PowerDown mode.
+ * Force spm_lvl to ensure that.
+ */
+ hba->spm_lvl = 5;
+ ret = ufshcd_system_suspend(hba);
+ hba->spm_lvl = spm_lvl;
+ return ret;
+}
+
#endif /* !CONFIG_PM_SLEEP */
#ifdef CONFIG_PM
}
static const struct dev_pm_ops ufshcd_pci_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(ufshcd_pci_suspend,
- ufshcd_pci_resume)
+#ifdef CONFIG_PM_SLEEP
+ .suspend = ufshcd_pci_suspend,
+ .resume = ufshcd_pci_resume,
+ .freeze = ufshcd_pci_suspend,
+ .thaw = ufshcd_pci_resume,
+ .poweroff = ufshcd_pci_poweroff,
+ .restore = ufshcd_pci_resume,
+#endif
SET_RUNTIME_PM_OPS(ufshcd_pci_runtime_suspend,
ufshcd_pci_runtime_resume,
ufshcd_pci_runtime_idle)
static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd);
static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
static void ufshcd_hba_exit(struct ufs_hba *hba);
+static int ufshcd_clear_ua_wluns(struct ufs_hba *hba);
static int ufshcd_probe_hba(struct ufs_hba *hba, bool async);
static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on);
static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba);
if (ret)
dev_err(hba->dev, "%s: En WB flush during H8: failed: %d\n",
__func__, ret);
- ufshcd_wb_toggle_flush(hba, true);
+ if (!(hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL))
+ ufshcd_wb_toggle_flush(hba, true);
}
static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba)
hba->pwr_info.hs_rate);
}
+static void ufshcd_device_reset(struct ufs_hba *hba)
+{
+ int err;
+
+ err = ufshcd_vops_device_reset(hba);
+
+ if (!err) {
+ ufshcd_set_ufs_dev_active(hba);
+ if (ufshcd_is_wb_allowed(hba)) {
+ hba->wb_enabled = false;
+ hba->wb_buf_flush_enabled = false;
+ }
+ }
+ if (err != -EOPNOTSUPP)
+ ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
+}
+
void ufshcd_delay_us(unsigned long us, unsigned long tolerance)
{
if (!us)
ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
if (ret)
dev_err(hba->dev,
- "dme-reset: error code %d\n", ret);
+ "dme-enable: error code %d\n", ret);
return ret;
}
spin_unlock_irqrestore(hba->host->host_lock, flags);
/* Reset the attached device */
- ufshcd_vops_device_reset(hba);
+ ufshcd_device_reset(hba);
ret = ufshcd_host_reset_and_restore(hba);
static inline void ufshcd_wb_toggle_flush(struct ufs_hba *hba, bool enable)
{
- if (hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL)
- return;
-
if (enable)
ufshcd_wb_buf_flush_enable(hba);
else
{
struct Scsi_Host *host;
struct ufs_hba *hba;
- unsigned int tag;
u32 pos;
int err;
- u8 resp = 0xF;
- struct ufshcd_lrb *lrbp;
+ u8 resp = 0xF, lun;
unsigned long flags;
host = cmd->device->host;
hba = shost_priv(host);
- tag = cmd->request->tag;
- lrbp = &hba->lrb[tag];
- err = ufshcd_issue_tm_cmd(hba, lrbp->lun, 0, UFS_LOGICAL_RESET, &resp);
+ lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
+ err = ufshcd_issue_tm_cmd(hba, lun, 0, UFS_LOGICAL_RESET, &resp);
if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
if (!err)
err = resp;
/* clear the commands that were pending for corresponding LUN */
for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) {
- if (hba->lrb[pos].lun == lrbp->lun) {
+ if (hba->lrb[pos].lun == lun) {
err = ufshcd_clear_cmd(hba, pos);
if (err)
break;
/* Establish the link again and restore the device */
err = ufshcd_probe_hba(hba, false);
-
+ if (!err)
+ ufshcd_clear_ua_wluns(hba);
out:
if (err)
dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err);
do {
/* Reset the attached device */
- ufshcd_vops_device_reset(hba);
+ ufshcd_device_reset(hba);
err = ufshcd_host_reset_and_restore(hba);
} while (err && --retries);
{
int ret = 0;
- if (!vreg || !vreg->enabled)
+ if (!vreg || !vreg->enabled || vreg->always_on)
goto out;
ret = regulator_disable(vreg->reg);
* handling context.
*/
hba->host->eh_noresume = 1;
- if (hba->wlun_dev_clr_ua) {
- ret = ufshcd_send_request_sense(hba, sdp);
- if (ret)
- goto out;
- /* Unit attention condition is cleared now */
- hba->wlun_dev_clr_ua = false;
- }
+ ufshcd_clear_ua_wluns(hba);
cmd[4] = pwr_mode << 4;
if (!ret)
hba->curr_dev_pwr_mode = pwr_mode;
-out:
+
scsi_device_put(sdp);
hba->host->eh_noresume = 0;
return ret;
ufshcd_wb_need_flush(hba));
}
+ flush_work(&hba->eeh_work);
+
if (req_dev_pwr_mode != hba->curr_dev_pwr_mode) {
if (!ufshcd_is_runtime_pm(pm_op))
/* ensure that bkops is disabled */
}
}
- flush_work(&hba->eeh_work);
-
/*
* In the case of DeepSleep, the device is expected to remain powered
* with the link off, so do not check for bkops.
* further below.
*/
if (ufshcd_is_ufs_dev_deepsleep(hba)) {
- ufshcd_vops_device_reset(hba);
+ ufshcd_device_reset(hba);
WARN_ON(!ufshcd_is_link_off(hba));
}
if (ufshcd_is_link_hibern8(hba) && !ufshcd_uic_hibern8_exit(hba))
set_dev_active:
/* Can also get here needing to exit DeepSleep */
if (ufshcd_is_ufs_dev_deepsleep(hba)) {
- ufshcd_vops_device_reset(hba);
+ ufshcd_device_reset(hba);
ufshcd_host_reset_and_restore(hba);
}
if (!ufshcd_set_dev_pwr_mode(hba, UFS_ACTIVE_PWR_MODE))
if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) ==
hba->curr_dev_pwr_mode) &&
(ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) ==
- hba->uic_link_state))
+ hba->uic_link_state) &&
+ !hba->dev_info.b_rpm_dev_flush_capable)
goto out;
if (pm_runtime_suspended(hba->dev)) {
}
/* Reset the attached device */
- ufshcd_vops_device_reset(hba);
+ ufshcd_device_reset(hba);
ufshcd_init_crypto(hba);
hba->vops->dbg_register_dump(hba);
}
-static inline void ufshcd_vops_device_reset(struct ufs_hba *hba)
+static inline int ufshcd_vops_device_reset(struct ufs_hba *hba)
{
- if (hba->vops && hba->vops->device_reset) {
- int err = hba->vops->device_reset(hba);
-
- if (!err)
- ufshcd_set_ufs_dev_active(hba);
- if (err != -EOPNOTSUPP)
- ufshcd_update_evt_hist(hba, UFS_EVT_DEV_RESET, err);
- }
+ if (hba->vops && hba->vops->device_reset)
+ return hba->vops->device_reset(hba);
+
+ return -EOPNOTSUPP;
}
static inline void ufshcd_vops_config_scaling_param(struct ufs_hba *hba,
/* send the first byte */
altera_spi_tx_word(hw);
- } else {
- while (hw->count < hw->len) {
- altera_spi_tx_word(hw);
- for (;;) {
- altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
- if (val & ALTERA_SPI_STATUS_RRDY_MSK)
- break;
+ return 1;
+ }
+
+ while (hw->count < hw->len) {
+ altera_spi_tx_word(hw);
- cpu_relax();
- }
+ for (;;) {
+ altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
+ if (val & ALTERA_SPI_STATUS_RRDY_MSK)
+ break;
- altera_spi_rx_word(hw);
+ cpu_relax();
}
- spi_finalize_current_transfer(master);
+
+ altera_spi_rx_word(hw);
}
+ spi_finalize_current_transfer(master);
- return t->len;
+ return 0;
}
static irqreturn_t altera_spi_irq(int irq, void *dev)
void __iomem *regs;
struct clk *ref_clk;
struct clk *pclk;
+ unsigned int clk_rate;
u32 speed_hz;
const u8 *txbuf;
u8 *rxbuf;
u32 ctrl_reg, baud_rate_val;
unsigned long frequency;
- frequency = clk_get_rate(xspi->ref_clk);
+ frequency = xspi->clk_rate;
ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR);
master->auto_runtime_pm = true;
master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+ xspi->clk_rate = clk_get_rate(xspi->ref_clk);
/* Set to default valid value */
- master->max_speed_hz = clk_get_rate(xspi->ref_clk) / 4;
+ master->max_speed_hz = xspi->clk_rate / 4;
xspi->speed_hz = master->max_speed_hz;
master->bits_per_word_mask = SPI_BPW_MASK(8);
{
struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
struct fsl_spi_platform_data *pdata;
- bool pol = spi->mode & SPI_CS_HIGH;
struct spi_mpc8xxx_cs *cs = spi->controller_state;
pdata = spi->dev.parent->parent->platform_data;
if (value == BITBANG_CS_INACTIVE) {
if (pdata->cs_control)
- pdata->cs_control(spi, !pol);
+ pdata->cs_control(spi, false);
}
if (value == BITBANG_CS_ACTIVE) {
fsl_spi_change_mode(spi);
if (pdata->cs_control)
- pdata->cs_control(spi, pol);
+ pdata->cs_control(spi, true);
}
}
spinlock_t lock;
int irq;
bool cs_flag;
+ bool abort_failed;
};
static int get_spi_clk_cfg(unsigned int speed_hz,
spin_unlock_irq(&mas->lock);
time_left = wait_for_completion_timeout(&mas->abort_done, HZ);
- if (!time_left)
+ if (!time_left) {
dev_err(mas->dev, "Failed to cancel/abort m_cmd\n");
+
+ /*
+ * No need for a lock since SPI core has a lock and we never
+ * access this from an interrupt.
+ */
+ mas->abort_failed = true;
+ }
+}
+
+static bool spi_geni_is_abort_still_pending(struct spi_geni_master *mas)
+{
+ struct geni_se *se = &mas->se;
+ u32 m_irq, m_irq_en;
+
+ if (!mas->abort_failed)
+ return false;
+
+ /*
+ * The only known case where a transfer times out and then a cancel
+ * times out then an abort times out is if something is blocking our
+ * interrupt handler from running. Avoid starting any new transfers
+ * until that sorts itself out.
+ */
+ spin_lock_irq(&mas->lock);
+ m_irq = readl(se->base + SE_GENI_M_IRQ_STATUS);
+ m_irq_en = readl(se->base + SE_GENI_M_IRQ_EN);
+ spin_unlock_irq(&mas->lock);
+
+ if (m_irq & m_irq_en) {
+ dev_err(mas->dev, "Interrupts pending after abort: %#010x\n",
+ m_irq & m_irq_en);
+ return true;
+ }
+
+ /*
+ * If we're here the problem resolved itself so no need to check more
+ * on future transfers.
+ */
+ mas->abort_failed = false;
+
+ return false;
}
static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
if (set_flag == mas->cs_flag)
return;
- mas->cs_flag = set_flag;
-
pm_runtime_get_sync(mas->dev);
+
+ if (spi_geni_is_abort_still_pending(mas)) {
+ dev_err(mas->dev, "Can't set chip select\n");
+ goto exit;
+ }
+
spin_lock_irq(&mas->lock);
+ if (mas->cur_xfer) {
+ dev_err(mas->dev, "Can't set CS when prev xfer running\n");
+ spin_unlock_irq(&mas->lock);
+ goto exit;
+ }
+
+ mas->cs_flag = set_flag;
reinit_completion(&mas->cs_done);
if (set_flag)
geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0);
spin_unlock_irq(&mas->lock);
time_left = wait_for_completion_timeout(&mas->cs_done, HZ);
- if (!time_left)
+ if (!time_left) {
+ dev_warn(mas->dev, "Timeout setting chip select\n");
handle_fifo_timeout(spi, NULL);
+ }
+exit:
pm_runtime_put(mas->dev);
}
int ret;
struct spi_geni_master *mas = spi_master_get_devdata(spi);
+ if (spi_geni_is_abort_still_pending(mas))
+ return -EBUSY;
+
ret = setup_fifo_params(spi_msg->spi, spi);
if (ret)
dev_err(mas->dev, "Couldn't select mode %d\n", ret);
unsigned int bytes_per_fifo_word = geni_byte_per_fifo_word(mas);
unsigned int i = 0;
+ /* Stop the watermark IRQ if nothing to send */
+ if (!mas->cur_xfer) {
+ writel(0, se->base + SE_GENI_TX_WATERMARK_REG);
+ return false;
+ }
+
max_bytes = (mas->tx_fifo_depth - mas->tx_wm) * bytes_per_fifo_word;
if (mas->tx_rem_bytes < max_bytes)
max_bytes = mas->tx_rem_bytes;
if (rx_last_byte_valid && rx_last_byte_valid < 4)
rx_bytes -= bytes_per_fifo_word - rx_last_byte_valid;
}
+
+ /* Clear out the FIFO and bail if nowhere to put it */
+ if (!mas->cur_xfer) {
+ for (i = 0; i < DIV_ROUND_UP(rx_bytes, bytes_per_fifo_word); i++)
+ readl(se->base + SE_GENI_RX_FIFOn);
+ return;
+ }
+
if (mas->rx_rem_bytes < rx_bytes)
rx_bytes = mas->rx_rem_bytes;
{
struct spi_geni_master *mas = spi_master_get_devdata(spi);
+ if (spi_geni_is_abort_still_pending(mas))
+ return -EBUSY;
+
/* Terminate and return success for 0 byte length transfer */
if (!xfer->len)
return 0;
/* align packet size with data registers access */
if (spi->cur_bpw > 8)
- fthlv -= (fthlv % 2); /* multiple of 2 */
+ fthlv += (fthlv % 2) ? 1 : 0;
else
- fthlv -= (fthlv % 4); /* multiple of 4 */
+ fthlv += (fthlv % 4) ? (4 - (fthlv % 4)) : 0;
if (!fthlv)
fthlv = 1;
{
struct spi_statistics *statm = &ctlr->statistics;
struct spi_statistics *stats = &msg->spi->statistics;
+ u32 speed_hz = xfer->speed_hz;
unsigned long long ms;
if (spi_controller_is_slave(ctlr)) {
return -EINTR;
}
} else {
+ if (!speed_hz)
+ speed_hz = 100000;
+
ms = 8LL * 1000LL * xfer->len;
- do_div(ms, xfer->speed_hz);
+ do_div(ms, speed_hz);
ms += ms + 200; /* some tolerance */
if (ms > UINT_MAX)
if (status)
return status;
- if (!spi->max_speed_hz ||
- spi->max_speed_hz > spi->controller->max_speed_hz)
+ if (spi->controller->max_speed_hz &&
+ (!spi->max_speed_hz ||
+ spi->max_speed_hz > spi->controller->max_speed_hz))
spi->max_speed_hz = spi->controller->max_speed_hz;
mutex_lock(&spi->controller->io_mutex);
v32.chanlist_len = cmd->chanlist_len;
v32.data = ptr_to_compat(cmd->data);
v32.data_len = cmd->data_len;
- return copy_to_user(cmd32, &v32, sizeof(v32));
+ if (copy_to_user(cmd32, &v32, sizeof(v32)))
+ return -EFAULT;
+ return 0;
}
/* Handle 32-bit COMEDI_CMD ioctl. */
iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!iores) {
dev_err(&pdev->dev, "can not get resource!\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto err_put_controller;
}
spmi_controller->base = devm_ioremap(&pdev->dev, iores->start,
resource_size(iores));
if (!spmi_controller->base) {
dev_err(&pdev->dev, "can not remap base addr!\n");
- return -EADDRNOTAVAIL;
+ ret = -EADDRNOTAVAIL;
+ goto err_put_controller;
}
ret = of_property_read_u32(pdev->dev.of_node, "spmi-channel",
&spmi_controller->channel);
if (ret) {
dev_err(&pdev->dev, "can not get channel\n");
- return -ENODEV;
+ ret = -ENODEV;
+ goto err_put_controller;
}
platform_set_drvdata(pdev, spmi_controller);
ctrl->write_cmd = spmi_write_cmd;
ret = spmi_controller_add(ctrl);
- if (ret)
- dev_err(&pdev->dev, "spmi_add_controller failed with error %d!\n", ret);
+ if (ret) {
+ dev_err(&pdev->dev, "spmi_controller_add failed with error %d!\n", ret);
+ goto err_put_controller;
+ }
+
+ return 0;
+err_put_controller:
+ spmi_controller_put(ctrl);
return ret;
}
struct spmi_controller *ctrl = platform_get_drvdata(pdev);
spmi_controller_remove(ctrl);
- kfree(ctrl);
+ spmi_controller_put(ctrl);
return 0;
}
.def = 0,
};
-#if 0 /* #ifdef CONFIG_ION */
-/*
- * Control for ISP ion device fd
- *
- * userspace will open ion device and pass the fd to kernel.
- * this fd will be used to map shared fd to buffer.
- */
-/* V4L2_CID_ATOMISP_ION_DEVICE_FD is not defined */
-static const struct v4l2_ctrl_config ctrl_ion_dev_fd = {
- .ops = &ctrl_ops,
- .id = V4L2_CID_ATOMISP_ION_DEVICE_FD,
- .type = V4L2_CTRL_TYPE_INTEGER,
- .name = "Ion Device Fd",
- .min = -1,
- .max = 1024,
- .step = 1,
- .def = ION_FD_UNSET
-};
-#endif
-
static void atomisp_init_subdev_pipe(struct atomisp_sub_device *asd,
struct atomisp_video_pipe *pipe, enum v4l2_buf_type buf_type)
{
ret = dma_async_device_register(dd);
if (ret) {
dev_err(&pdev->dev, "failed to register dma device\n");
- return ret;
+ goto err_uninit_hsdma;
}
ret = of_dma_controller_register(pdev->dev.of_node,
err_unregister:
dma_async_device_unregister(dd);
+err_uninit_hsdma:
+ mtk_hsdma_uninit(hsdma);
return ret;
}
return 0;
}
-struct xcopy_dev_search_info {
- const unsigned char *dev_wwn;
- struct se_device *found_dev;
-};
-
+/**
+ * target_xcopy_locate_se_dev_e4_iter - compare XCOPY NAA device identifiers
+ *
+ * @se_dev: device being considered for match
+ * @dev_wwn: XCOPY requested NAA dev_wwn
+ * @return: 1 on match, 0 on no-match
+ */
static int target_xcopy_locate_se_dev_e4_iter(struct se_device *se_dev,
- void *data)
+ const unsigned char *dev_wwn)
{
- struct xcopy_dev_search_info *info = data;
unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
int rc;
- if (!se_dev->dev_attrib.emulate_3pc)
+ if (!se_dev->dev_attrib.emulate_3pc) {
+ pr_debug("XCOPY: emulate_3pc disabled on se_dev %p\n", se_dev);
return 0;
+ }
memset(&tmp_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN);
target_xcopy_gen_naa_ieee(se_dev, &tmp_dev_wwn[0]);
- rc = memcmp(&tmp_dev_wwn[0], info->dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN);
- if (rc != 0)
- return 0;
-
- info->found_dev = se_dev;
- pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev);
-
- rc = target_depend_item(&se_dev->dev_group.cg_item);
+ rc = memcmp(&tmp_dev_wwn[0], dev_wwn, XCOPY_NAA_IEEE_REGEX_LEN);
if (rc != 0) {
- pr_err("configfs_depend_item attempt failed: %d for se_dev: %p\n",
- rc, se_dev);
- return rc;
+ pr_debug("XCOPY: skip non-matching: %*ph\n",
+ XCOPY_NAA_IEEE_REGEX_LEN, tmp_dev_wwn);
+ return 0;
}
+ pr_debug("XCOPY 0xe4: located se_dev: %p\n", se_dev);
- pr_debug("Called configfs_depend_item for se_dev: %p se_dev->se_dev_group: %p\n",
- se_dev, &se_dev->dev_group);
return 1;
}
-static int target_xcopy_locate_se_dev_e4(const unsigned char *dev_wwn,
- struct se_device **found_dev)
+static int target_xcopy_locate_se_dev_e4(struct se_session *sess,
+ const unsigned char *dev_wwn,
+ struct se_device **_found_dev,
+ struct percpu_ref **_found_lun_ref)
{
- struct xcopy_dev_search_info info;
- int ret;
-
- memset(&info, 0, sizeof(info));
- info.dev_wwn = dev_wwn;
-
- ret = target_for_each_device(target_xcopy_locate_se_dev_e4_iter, &info);
- if (ret == 1) {
- *found_dev = info.found_dev;
- return 0;
- } else {
- pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
- return -EINVAL;
+ struct se_dev_entry *deve;
+ struct se_node_acl *nacl;
+ struct se_lun *this_lun = NULL;
+ struct se_device *found_dev = NULL;
+
+ /* cmd with NULL sess indicates no associated $FABRIC_MOD */
+ if (!sess)
+ goto err_out;
+
+ pr_debug("XCOPY 0xe4: searching for: %*ph\n",
+ XCOPY_NAA_IEEE_REGEX_LEN, dev_wwn);
+
+ nacl = sess->se_node_acl;
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(deve, &nacl->lun_entry_hlist, link) {
+ struct se_device *this_dev;
+ int rc;
+
+ this_lun = rcu_dereference(deve->se_lun);
+ this_dev = rcu_dereference_raw(this_lun->lun_se_dev);
+
+ rc = target_xcopy_locate_se_dev_e4_iter(this_dev, dev_wwn);
+ if (rc) {
+ if (percpu_ref_tryget_live(&this_lun->lun_ref))
+ found_dev = this_dev;
+ break;
+ }
}
+ rcu_read_unlock();
+ if (found_dev == NULL)
+ goto err_out;
+
+ pr_debug("lun_ref held for se_dev: %p se_dev->se_dev_group: %p\n",
+ found_dev, &found_dev->dev_group);
+ *_found_dev = found_dev;
+ *_found_lun_ref = &this_lun->lun_ref;
+ return 0;
+err_out:
+ pr_debug_ratelimited("Unable to locate 0xe4 descriptor for EXTENDED_COPY\n");
+ return -EINVAL;
}
static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op *xop,
switch (xop->op_origin) {
case XCOL_SOURCE_RECV_OP:
- rc = target_xcopy_locate_se_dev_e4(xop->dst_tid_wwn,
- &xop->dst_dev);
+ rc = target_xcopy_locate_se_dev_e4(se_cmd->se_sess,
+ xop->dst_tid_wwn,
+ &xop->dst_dev,
+ &xop->remote_lun_ref);
break;
case XCOL_DEST_RECV_OP:
- rc = target_xcopy_locate_se_dev_e4(xop->src_tid_wwn,
- &xop->src_dev);
+ rc = target_xcopy_locate_se_dev_e4(se_cmd->se_sess,
+ xop->src_tid_wwn,
+ &xop->src_dev,
+ &xop->remote_lun_ref);
break;
default:
pr_err("XCOPY CSCD descriptor IDs not found in CSCD list - "
static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
{
- struct se_device *remote_dev;
-
if (xop->op_origin == XCOL_SOURCE_RECV_OP)
- remote_dev = xop->dst_dev;
+ pr_debug("putting dst lun_ref for %p\n", xop->dst_dev);
else
- remote_dev = xop->src_dev;
-
- pr_debug("Calling configfs_undepend_item for"
- " remote_dev: %p remote_dev->dev_group: %p\n",
- remote_dev, &remote_dev->dev_group.cg_item);
+ pr_debug("putting src lun_ref for %p\n", xop->src_dev);
- target_undepend_item(&remote_dev->dev_group.cg_item);
+ percpu_ref_put(xop->remote_lun_ref);
}
static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
struct se_device *dst_dev;
unsigned char dst_tid_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
unsigned char local_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN];
+ struct percpu_ref *remote_lun_ref;
sector_t src_lba;
sector_t dst_lba;
help
FDC channel number to use for KGDB.
+config NULL_TTY
+ tristate "NULL TTY driver"
+ help
+ Say Y here if you want a NULL TTY which simply discards messages.
+
+ This is useful to allow userspace applications which expect a console
+ device to work without modifications even when no console is
+ available or desired.
+
+ In order to use this driver, you should redirect the console to this
+ TTY, or boot the kernel with console=ttynull.
+
+ If unsure, say N.
+
config TRACE_ROUTER
tristate "Trace data router for MIPI P1149.7 cJTAG standard"
depends on TRACE_SINK
obj-$(CONFIG_TTY) += tty_io.o n_tty.o tty_ioctl.o tty_ldisc.o \
tty_buffer.o tty_port.o tty_mutex.o \
tty_ldsem.o tty_baudrate.o tty_jobctrl.o \
- n_null.o ttynull.o
+ n_null.o
obj-$(CONFIG_LEGACY_PTYS) += pty.o
obj-$(CONFIG_UNIX98_PTYS) += pty.o
obj-$(CONFIG_AUDIT) += tty_audit.o
obj-$(CONFIG_MOXA_INTELLIO) += moxa.o
obj-$(CONFIG_MOXA_SMARTIO) += mxser.o
obj-$(CONFIG_NOZOMI) += nozomi.o
+obj-$(CONFIG_NULL_TTY) += ttynull.o
obj-$(CONFIG_ROCKETPORT) += rocket.o
obj-$(CONFIG_SYNCLINK_GT) += synclink_gt.o
obj-$(CONFIG_PPC_EPAPR_HV_BYTECHAN) += ehv_bytechan.o
/* Set up clock divider */
ssp->clkin_rate = clk_get_rate(ssp->clk);
ssp->baud_rate = SIFIVE_DEFAULT_BAUD_RATE;
+ ssp->port.uartclk = ssp->baud_rate * 16;
__ssp_update_div(ssp);
platform_set_drvdata(pdev, ssp);
/*
* Copyright (C) 2019 Axis Communications AB
*
- * The console is useful for userspace applications which expect a console
- * device to work without modifications even when no console is available
- * or desired.
- *
- * In order to use this driver, you should redirect the console to this
- * TTY, or boot the kernel with console=ttynull.
- *
* Based on ttyprintk.c:
* Copyright (C) 2010 Samo Pogacnik
*/
.device = ttynull_device,
};
-void __init register_ttynull_console(void)
-{
- if (!ttynull_driver)
- return;
-
- if (add_preferred_console(ttynull_console.name, 0, NULL))
- return;
-
- register_console(&ttynull_console);
-}
-
static int __init ttynull_init(void)
{
struct tty_driver *driver;
misc_pdev = of_find_device_by_node(args.np);
of_node_put(args.np);
- if (!misc_pdev || !platform_get_drvdata(misc_pdev))
+ if (!misc_pdev)
return ERR_PTR(-EPROBE_DEFER);
+ if (!platform_get_drvdata(misc_pdev)) {
+ put_device(&misc_pdev->dev);
+ return ERR_PTR(-EPROBE_DEFER);
+ }
data->dev = &misc_pdev->dev;
/*
{ USB_DEVICE(0x04d8, 0xfd08),
.driver_info = IGNORE_DEVICE,
},
+
+ { USB_DEVICE(0x04d8, 0xf58b),
+ .driver_info = IGNORE_DEVICE,
+ },
#endif
/*Samsung phone in firmware update mode */
if (!desc->resp_count || !--desc->resp_count)
goto out;
+ if (test_bit(WDM_DISCONNECTING, &desc->flags)) {
+ rv = -ENODEV;
+ goto out;
+ }
+ if (test_bit(WDM_RESETTING, &desc->flags)) {
+ rv = -EIO;
+ goto out;
+ }
+
set_bit(WDM_RESPONDING, &desc->flags);
spin_unlock_irq(&desc->iuspin);
rv = usb_submit_urb(desc->response, GFP_KERNEL);
spin_lock_irq(&desc->iuspin);
if (rv) {
- dev_err(&desc->intf->dev,
- "usb_submit_urb failed with result %d\n", rv);
+ if (!test_bit(WDM_DISCONNECTING, &desc->flags))
+ dev_err(&desc->intf->dev,
+ "usb_submit_urb failed with result %d\n", rv);
/* make sure the next notification trigger a submit */
clear_bit(WDM_RESPONDING, &desc->flags);
wake_up_all(&desc->wait);
mutex_lock(&desc->rlock);
mutex_lock(&desc->wlock);
- kill_urbs(desc);
cancel_work_sync(&desc->rxwork);
cancel_work_sync(&desc->service_outs_intr);
+ kill_urbs(desc);
mutex_unlock(&desc->wlock);
mutex_unlock(&desc->rlock);
#define usblp_reset(usblp)\
usblp_ctrl_msg(usblp, USBLP_REQ_RESET, USB_TYPE_CLASS, USB_DIR_OUT, USB_RECIP_OTHER, 0, NULL, 0)
-#define usblp_hp_channel_change_request(usblp, channel, buffer) \
- usblp_ctrl_msg(usblp, USBLP_REQ_HP_CHANNEL_CHANGE_REQUEST, USB_TYPE_VENDOR, USB_DIR_IN, USB_RECIP_INTERFACE, channel, buffer, 1)
+static int usblp_hp_channel_change_request(struct usblp *usblp, int channel, u8 *new_channel)
+{
+ u8 *buf;
+ int ret;
+
+ buf = kzalloc(1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = usblp_ctrl_msg(usblp, USBLP_REQ_HP_CHANNEL_CHANGE_REQUEST,
+ USB_TYPE_VENDOR, USB_DIR_IN, USB_RECIP_INTERFACE,
+ channel, buf, 1);
+ if (ret == 0)
+ *new_channel = buf[0];
+
+ kfree(buf);
+
+ return ret;
+}
/*
* See the description for usblp_select_alts() below for the usage
urb->status = status;
/*
* This function can be called in task context inside another remote
- * coverage collection section, but KCOV doesn't support that kind of
+ * coverage collection section, but kcov doesn't support that kind of
* recursion yet. Only collect coverage in softirq context for now.
*/
- if (in_serving_softirq())
- kcov_remote_start_usb((u64)urb->dev->bus->busnum);
+ kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum);
urb->complete(urb);
- if (in_serving_softirq())
- kcov_remote_stop();
+ kcov_remote_stop_softirq();
usb_anchor_resume_wakeups(anchor);
atomic_dec(&urb->use_count);
/* Global USB2 PHY Vendor Control Register */
#define DWC3_GUSB2PHYACC_NEWREGREQ BIT(25)
+#define DWC3_GUSB2PHYACC_DONE BIT(24)
#define DWC3_GUSB2PHYACC_BUSY BIT(23)
#define DWC3_GUSB2PHYACC_WRITE BIT(22)
#define DWC3_GUSB2PHYACC_ADDR(n) (n << 16)
ret = priv->drvdata->setup_regmaps(priv, base);
if (ret)
- return ret;
+ goto err_disable_clks;
if (priv->vbus) {
ret = regulator_enable(priv->vbus);
list_for_each_entry_safe(r, t, &dep->started_list, list)
dwc3_gadget_move_cancelled_request(r);
+ dep->flags &= ~DWC3_EP_WAIT_TRANSFER_COMPLETE;
+
goto out;
}
}
static void dwc3_gadget_disable_irq(struct dwc3 *dwc);
static void __dwc3_gadget_stop(struct dwc3 *dwc);
+static int __dwc3_gadget_start(struct dwc3 *dwc);
static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on)
{
dwc->ev_buf->lpos = (dwc->ev_buf->lpos + count) %
dwc->ev_buf->length;
}
+ } else {
+ __dwc3_gadget_start(dwc);
}
ret = dwc3_gadget_run_stop(dwc, is_on, false);
}
dwc->gadget_driver = driver;
-
- if (pm_runtime_active(dwc->dev))
- __dwc3_gadget_start(dwc);
-
spin_unlock_irqrestore(&dwc->lock, flags);
return 0;
unsigned long flags;
spin_lock_irqsave(&dwc->lock, flags);
-
- if (pm_runtime_suspended(dwc->dev))
- goto out;
-
- __dwc3_gadget_stop(dwc);
-
-out:
dwc->gadget_driver = NULL;
spin_unlock_irqrestore(&dwc->lock, flags);
* Author: Heikki Krogerus <heikki.krogerus@linux.intel.com>
*/
+#include <linux/delay.h>
+#include <linux/time64.h>
#include <linux/ulpi/regs.h>
#include "core.h"
DWC3_GUSB2PHYACC_ADDR(ULPI_ACCESS_EXTENDED) | \
DWC3_GUSB2PHYACC_EXTEND_ADDR(a) : DWC3_GUSB2PHYACC_ADDR(a))
-static int dwc3_ulpi_busyloop(struct dwc3 *dwc)
+#define DWC3_ULPI_BASE_DELAY DIV_ROUND_UP(NSEC_PER_SEC, 60000000L)
+
+static int dwc3_ulpi_busyloop(struct dwc3 *dwc, u8 addr, bool read)
{
- unsigned int count = 1000;
+ unsigned long ns = 5L * DWC3_ULPI_BASE_DELAY;
+ unsigned int count = 10000;
u32 reg;
+ if (addr >= ULPI_EXT_VENDOR_SPECIFIC)
+ ns += DWC3_ULPI_BASE_DELAY;
+
+ if (read)
+ ns += DWC3_ULPI_BASE_DELAY;
+
+ reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+ if (reg & DWC3_GUSB2PHYCFG_SUSPHY)
+ usleep_range(1000, 1200);
+
while (count--) {
+ ndelay(ns);
reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYACC(0));
- if (!(reg & DWC3_GUSB2PHYACC_BUSY))
+ if (reg & DWC3_GUSB2PHYACC_DONE)
return 0;
cpu_relax();
}
u32 reg;
int ret;
- reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
- if (reg & DWC3_GUSB2PHYCFG_SUSPHY) {
- reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
- dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
- }
-
reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr);
dwc3_writel(dwc->regs, DWC3_GUSB2PHYACC(0), reg);
- ret = dwc3_ulpi_busyloop(dwc);
+ ret = dwc3_ulpi_busyloop(dwc, addr, true);
if (ret)
return ret;
struct dwc3 *dwc = dev_get_drvdata(dev);
u32 reg;
- reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
- if (reg & DWC3_GUSB2PHYCFG_SUSPHY) {
- reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
- dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
- }
-
reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr);
reg |= DWC3_GUSB2PHYACC_WRITE | val;
dwc3_writel(dwc->regs, DWC3_GUSB2PHYACC(0), reg);
- return dwc3_ulpi_busyloop(dwc);
+ return dwc3_ulpi_busyloop(dwc, addr, false);
}
static const struct ulpi_ops dwc3_ulpi_ops = {
depends on NET
select USB_U_ETHER
select USB_F_NCM
+ select CRC32
help
NCM is an advanced protocol for Ethernet encapsulation, allows
grouping of several ethernet frames into one USB transfer and
depends on NET
select USB_U_ETHER
select USB_F_EEM
+ select CRC32
help
CDC EEM is a newer USB standard that is somewhat simpler than CDC ECM
and therefore can be supported by more hardware. Technically ECM and
spin_lock_irqsave(&cdev->lock, flags);
- if (cdev->deactivations == 0)
+ if (cdev->deactivations == 0) {
+ spin_unlock_irqrestore(&cdev->lock, flags);
status = usb_gadget_deactivate(cdev->gadget);
+ spin_lock_irqsave(&cdev->lock, flags);
+ }
if (status == 0)
cdev->deactivations++;
status = -EINVAL;
else {
cdev->deactivations--;
- if (cdev->deactivations == 0)
+ if (cdev->deactivations == 0) {
+ spin_unlock_irqrestore(&cdev->lock, flags);
status = usb_gadget_activate(cdev->gadget);
+ spin_lock_irqsave(&cdev->lock, flags);
+ }
}
spin_unlock_irqrestore(&cdev->lock, flags);
static ssize_t gadget_dev_desc_UDC_show(struct config_item *item, char *page)
{
- char *udc_name = to_gadget_info(item)->composite.gadget_driver.udc_name;
+ struct gadget_info *gi = to_gadget_info(item);
+ char *udc_name;
+ int ret;
+
+ mutex_lock(&gi->lock);
+ udc_name = gi->composite.gadget_driver.udc_name;
+ ret = sprintf(page, "%s\n", udc_name ?: "");
+ mutex_unlock(&gi->lock);
- return sprintf(page, "%s\n", udc_name ?: "");
+ return ret;
}
static int unregister_gadget(struct gadget_info *gi)
cfg = container_of(c, struct config_usb_cfg, c);
- list_for_each_entry_safe(f, tmp, &c->functions, list) {
+ list_for_each_entry_safe_reverse(f, tmp, &c->functions, list) {
- list_move_tail(&f->list, &cfg->func_list);
+ list_move(&f->list, &cfg->func_list);
if (f->unbind) {
dev_dbg(&gi->cdev.gadget->dev,
"unbind function '%s'/%p\n",
.suspend = configfs_composite_suspend,
.resume = configfs_composite_resume,
- .max_speed = USB_SPEED_SUPER,
+ .max_speed = USB_SPEED_SUPER_PLUS,
.driver = {
.owner = THIS_MODULE,
.name = "configfs-gadget",
gi->composite.unbind = configfs_do_nothing;
gi->composite.suspend = NULL;
gi->composite.resume = NULL;
- gi->composite.max_speed = USB_SPEED_SUPER;
+ gi->composite.max_speed = USB_SPEED_SUPER_PLUS;
spin_lock_init(&gi->spinlock);
mutex_init(&gi->lock);
printer_req_free(dev->in_ep, req);
}
+ usb_free_all_descriptors(f);
return ret;
}
.bEndpointAddress = USB_DIR_OUT,
.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
- .wMaxPacketSize = cpu_to_le16(1023),
+ /* .wMaxPacketSize = DYNAMIC */
.bInterval = 1,
};
.bDescriptorType = USB_DT_ENDPOINT,
.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
- .wMaxPacketSize = cpu_to_le16(1024),
+ /* .wMaxPacketSize = DYNAMIC */
.bInterval = 4,
};
.bEndpointAddress = USB_DIR_IN,
.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
- .wMaxPacketSize = cpu_to_le16(1023),
+ /* .wMaxPacketSize = DYNAMIC */
.bInterval = 1,
};
.bDescriptorType = USB_DT_ENDPOINT,
.bmAttributes = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC,
- .wMaxPacketSize = cpu_to_le16(1024),
+ /* .wMaxPacketSize = DYNAMIC */
.bInterval = 4,
};
__le32 dRES;
} __packed;
-static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
+static int set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
struct usb_endpoint_descriptor *ep_desc,
- unsigned int factor, bool is_playback)
+ enum usb_device_speed speed, bool is_playback)
{
int chmask, srate, ssize;
- u16 max_packet_size;
+ u16 max_size_bw, max_size_ep;
+ unsigned int factor;
+
+ switch (speed) {
+ case USB_SPEED_FULL:
+ max_size_ep = 1023;
+ factor = 1000;
+ break;
+
+ case USB_SPEED_HIGH:
+ max_size_ep = 1024;
+ factor = 8000;
+ break;
+
+ default:
+ return -EINVAL;
+ }
if (is_playback) {
chmask = uac2_opts->p_chmask;
ssize = uac2_opts->c_ssize;
}
- max_packet_size = num_channels(chmask) * ssize *
+ max_size_bw = num_channels(chmask) * ssize *
DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1)));
- ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_packet_size,
- le16_to_cpu(ep_desc->wMaxPacketSize)));
+ ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_size_bw,
+ max_size_ep));
+
+ return 0;
}
/* Use macro to overcome line length limitation */
}
/* Calculate wMaxPacketSize according to audio bandwidth */
- set_ep_max_packet_size(uac2_opts, &fs_epin_desc, 1000, true);
- set_ep_max_packet_size(uac2_opts, &fs_epout_desc, 1000, false);
- set_ep_max_packet_size(uac2_opts, &hs_epin_desc, 8000, true);
- set_ep_max_packet_size(uac2_opts, &hs_epout_desc, 8000, false);
+ ret = set_ep_max_packet_size(uac2_opts, &fs_epin_desc, USB_SPEED_FULL,
+ true);
+ if (ret < 0) {
+ dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+ return ret;
+ }
+
+ ret = set_ep_max_packet_size(uac2_opts, &fs_epout_desc, USB_SPEED_FULL,
+ false);
+ if (ret < 0) {
+ dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+ return ret;
+ }
+
+ ret = set_ep_max_packet_size(uac2_opts, &hs_epin_desc, USB_SPEED_HIGH,
+ true);
+ if (ret < 0) {
+ dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+ return ret;
+ }
+
+ ret = set_ep_max_packet_size(uac2_opts, &hs_epout_desc, USB_SPEED_HIGH,
+ false);
+ if (ret < 0) {
+ dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
+ return ret;
+ }
if (EPOUT_EN(uac2_opts)) {
agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
#define UETH__VERSION "29-May-2008"
/* Experiments show that both Linux and Windows hosts allow up to 16k
- * frame sizes. Set the max size to 15k+52 to prevent allocating 32k
+ * frame sizes. Set the max MTU size to 15k+52 to prevent allocating 32k
* blocks and still have efficient handling. */
-#define GETHER_MAX_ETH_FRAME_LEN 15412
+#define GETHER_MAX_MTU_SIZE 15412
+#define GETHER_MAX_ETH_FRAME_LEN (GETHER_MAX_MTU_SIZE + ETH_HLEN)
struct eth_dev {
/* lock is held while accessing port_usb
/* MTU range: 14 - 15412 */
net->min_mtu = ETH_HLEN;
- net->max_mtu = GETHER_MAX_ETH_FRAME_LEN;
+ net->max_mtu = GETHER_MAX_MTU_SIZE;
dev->gadget = g;
SET_NETDEV_DEV(net, &g->dev);
/* MTU range: 14 - 15412 */
net->min_mtu = ETH_HLEN;
- net->max_mtu = GETHER_MAX_ETH_FRAME_LEN;
+ net->max_mtu = GETHER_MAX_MTU_SIZE;
return net;
}
struct usb_descriptor_header *usb_desc;
usb_desc = usb_otg_descriptor_alloc(gadget);
- if (!usb_desc)
+ if (!usb_desc) {
+ status = -ENOMEM;
goto fail_string_ids;
+ }
usb_otg_descriptor_init(gadget, usb_desc);
otg_desc[0] = usb_desc;
otg_desc[1] = NULL;
config USB_FSL_USB2
tristate "Freescale Highspeed USB DR Peripheral Controller"
- depends on FSL_SOC || ARCH_MXC
+ depends on FSL_SOC
help
Some of Freescale PowerPC and i.MX processors have a High Speed
Dual-Role(DR) USB controller, which supports device mode.
obj-$(CONFIG_USB_BCM63XX_UDC) += bcm63xx_udc.o
obj-$(CONFIG_USB_FSL_USB2) += fsl_usb2_udc.o
fsl_usb2_udc-y := fsl_udc_core.o
-fsl_usb2_udc-$(CONFIG_ARCH_MXC) += fsl_mxc_udc.o
obj-$(CONFIG_USB_TEGRA_XUDC) += tegra-xudc.o
obj-$(CONFIG_USB_M66592) += m66592-udc.o
obj-$(CONFIG_USB_R8A66597) += r8a66597-udc.o
*
* Enables the D+ (or potentially D-) pullup. The host will start
* enumerating this gadget when the pullup is active and a VBUS session
- * is active (the link is powered). This pullup is always enabled unless
- * usb_gadget_disconnect() has been used to disable it.
+ * is active (the link is powered).
*
* Returns zero on success, else negative errno.
*/
dum_hcd->port_status &= ~USB_PORT_STAT_POWER;
set_link_state(dum_hcd);
break;
- default:
+ case USB_PORT_FEAT_ENABLE:
+ case USB_PORT_FEAT_C_ENABLE:
+ case USB_PORT_FEAT_C_SUSPEND:
+ /* Not allowed for USB-3 */
+ if (hcd->speed == HCD_USB3)
+ goto error;
+ fallthrough;
+ case USB_PORT_FEAT_C_CONNECTION:
+ case USB_PORT_FEAT_C_RESET:
dum_hcd->port_status &= ~(1 << wValue);
set_link_state(dum_hcd);
+ break;
+ default:
+ /* Disallow INDICATOR and C_OVER_CURRENT */
+ goto error;
}
break;
case GetHubDescriptor:
*/
dum_hcd->re_timeout = jiffies + msecs_to_jiffies(50);
fallthrough;
+ case USB_PORT_FEAT_C_CONNECTION:
+ case USB_PORT_FEAT_C_RESET:
+ case USB_PORT_FEAT_C_ENABLE:
+ case USB_PORT_FEAT_C_SUSPEND:
+ /* Not allowed for USB-3, and ignored for USB-2 */
+ if (hcd->speed == HCD_USB3)
+ goto error;
+ break;
default:
- if (hcd->speed == HCD_USB3) {
- if ((dum_hcd->port_status &
- USB_SS_PORT_STAT_POWER) != 0) {
- dum_hcd->port_status |= (1 << wValue);
- }
- } else
- if ((dum_hcd->port_status &
- USB_PORT_STAT_POWER) != 0) {
- dum_hcd->port_status |= (1 << wValue);
- }
- set_link_state(dum_hcd);
+ /* Disallow TEST, INDICATOR, and C_OVER_CURRENT */
+ goto error;
}
break;
case GetPortErrorCount:
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Copyright (C) 2009
- * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de>
- *
- * Description:
- * Helper routines for i.MX3x SoCs from Freescale, needed by the fsl_usb2_udc.c
- * driver to function correctly on these systems.
- */
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/fsl_devices.h>
-#include <linux/mod_devicetable.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-
-#include "fsl_usb2_udc.h"
-
-static struct clk *mxc_ahb_clk;
-static struct clk *mxc_per_clk;
-static struct clk *mxc_ipg_clk;
-
-/* workaround ENGcm09152 for i.MX35 */
-#define MX35_USBPHYCTRL_OFFSET 0x600
-#define USBPHYCTRL_OTGBASE_OFFSET 0x8
-#define USBPHYCTRL_EVDO (1 << 23)
-
-int fsl_udc_clk_init(struct platform_device *pdev)
-{
- struct fsl_usb2_platform_data *pdata;
- unsigned long freq;
- int ret;
-
- pdata = dev_get_platdata(&pdev->dev);
-
- mxc_ipg_clk = devm_clk_get(&pdev->dev, "ipg");
- if (IS_ERR(mxc_ipg_clk)) {
- dev_err(&pdev->dev, "clk_get(\"ipg\") failed\n");
- return PTR_ERR(mxc_ipg_clk);
- }
-
- mxc_ahb_clk = devm_clk_get(&pdev->dev, "ahb");
- if (IS_ERR(mxc_ahb_clk)) {
- dev_err(&pdev->dev, "clk_get(\"ahb\") failed\n");
- return PTR_ERR(mxc_ahb_clk);
- }
-
- mxc_per_clk = devm_clk_get(&pdev->dev, "per");
- if (IS_ERR(mxc_per_clk)) {
- dev_err(&pdev->dev, "clk_get(\"per\") failed\n");
- return PTR_ERR(mxc_per_clk);
- }
-
- clk_prepare_enable(mxc_ipg_clk);
- clk_prepare_enable(mxc_ahb_clk);
- clk_prepare_enable(mxc_per_clk);
-
- /* make sure USB_CLK is running at 60 MHz +/- 1000 Hz */
- if (!strcmp(pdev->id_entry->name, "imx-udc-mx27")) {
- freq = clk_get_rate(mxc_per_clk);
- if (pdata->phy_mode != FSL_USB2_PHY_ULPI &&
- (freq < 59999000 || freq > 60001000)) {
- dev_err(&pdev->dev, "USB_CLK=%lu, should be 60MHz\n", freq);
- ret = -EINVAL;
- goto eclkrate;
- }
- }
-
- return 0;
-
-eclkrate:
- clk_disable_unprepare(mxc_ipg_clk);
- clk_disable_unprepare(mxc_ahb_clk);
- clk_disable_unprepare(mxc_per_clk);
- mxc_per_clk = NULL;
- return ret;
-}
-
-int fsl_udc_clk_finalize(struct platform_device *pdev)
-{
- struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev);
- int ret = 0;
-
- /* workaround ENGcm09152 for i.MX35 */
- if (pdata->workaround & FLS_USB2_WORKAROUND_ENGCM09152) {
- unsigned int v;
- struct resource *res = platform_get_resource
- (pdev, IORESOURCE_MEM, 0);
- void __iomem *phy_regs = ioremap(res->start +
- MX35_USBPHYCTRL_OFFSET, 512);
- if (!phy_regs) {
- dev_err(&pdev->dev, "ioremap for phy address fails\n");
- ret = -EINVAL;
- goto ioremap_err;
- }
-
- v = readl(phy_regs + USBPHYCTRL_OTGBASE_OFFSET);
- writel(v | USBPHYCTRL_EVDO,
- phy_regs + USBPHYCTRL_OTGBASE_OFFSET);
-
- iounmap(phy_regs);
- }
-
-
-ioremap_err:
- /* ULPI transceivers don't need usbpll */
- if (pdata->phy_mode == FSL_USB2_PHY_ULPI) {
- clk_disable_unprepare(mxc_per_clk);
- mxc_per_clk = NULL;
- }
-
- return ret;
-}
-
-void fsl_udc_clk_release(void)
-{
- if (mxc_per_clk)
- clk_disable_unprepare(mxc_per_clk);
- clk_disable_unprepare(mxc_ahb_clk);
- clk_disable_unprepare(mxc_ipg_clk);
-}
{
unsigned long long timeout_ns;
+ if (xhci->quirks & XHCI_INTEL_HOST)
+ timeout_ns = xhci_calculate_intel_u1_timeout(udev, desc);
+ else
+ timeout_ns = udev->u1_params.sel;
+
/* Prevent U1 if service interval is shorter than U1 exit latency */
if (usb_endpoint_xfer_int(desc) || usb_endpoint_xfer_isoc(desc)) {
- if (xhci_service_interval_to_ns(desc) <= udev->u1_params.mel) {
+ if (xhci_service_interval_to_ns(desc) <= timeout_ns) {
dev_dbg(&udev->dev, "Disable U1, ESIT shorter than exit latency\n");
return USB3_LPM_DISABLED;
}
}
- if (xhci->quirks & XHCI_INTEL_HOST)
- timeout_ns = xhci_calculate_intel_u1_timeout(udev, desc);
- else
- timeout_ns = udev->u1_params.sel;
-
/* The U1 timeout is encoded in 1us intervals.
* Don't return a timeout of zero, because that's USB3_LPM_DISABLED.
*/
{
unsigned long long timeout_ns;
+ if (xhci->quirks & XHCI_INTEL_HOST)
+ timeout_ns = xhci_calculate_intel_u2_timeout(udev, desc);
+ else
+ timeout_ns = udev->u2_params.sel;
+
/* Prevent U2 if service interval is shorter than U2 exit latency */
if (usb_endpoint_xfer_int(desc) || usb_endpoint_xfer_isoc(desc)) {
- if (xhci_service_interval_to_ns(desc) <= udev->u2_params.mel) {
+ if (xhci_service_interval_to_ns(desc) <= timeout_ns) {
dev_dbg(&udev->dev, "Disable U2, ESIT shorter than exit latency\n");
return USB3_LPM_DISABLED;
}
}
- if (xhci->quirks & XHCI_INTEL_HOST)
- timeout_ns = xhci_calculate_intel_u2_timeout(udev, desc);
- else
- timeout_ns = udev->u2_params.sel;
-
/* The U2 timeout is encoded in 256us intervals */
timeout_ns = DIV_ROUND_UP_ULL(timeout_ns, 256 * 1000);
/* If the necessary timeout value is bigger than what we can set in the
timeout = schedule_timeout(YUREX_WRITE_TIMEOUT);
finish_wait(&dev->waitq, &wait);
+ /* make sure URB is idle after timeout or (spurious) CMD_ACK */
+ usb_kill_urb(dev->cntl_urb);
+
mutex_unlock(&dev->io_mutex);
if (retval < 0) {
struct device *dev = &port->dev;
int i;
int status;
- u8 rxcmd = IUU_UART_RX;
+ u8 *rxcmd;
struct iuu_private *priv = usb_get_serial_port_data(port);
if (iuu_led(port, 0xF000, 0, 0, 0xFF) < 0)
return -EIO;
+ rxcmd = kmalloc(1, GFP_KERNEL);
+ if (!rxcmd)
+ return -ENOMEM;
+
+ rxcmd[0] = IUU_UART_RX;
+
for (i = 0; i < 2; i++) {
- status = bulk_immediate(port, &rxcmd, 1);
+ status = bulk_immediate(port, rxcmd, 1);
if (status != IUU_OPERATION_OK) {
dev_dbg(dev, "%s - uart_flush_write error\n", __func__);
- return status;
+ goto out_free;
}
status = read_immediate(port, &priv->len, 1);
if (status != IUU_OPERATION_OK) {
dev_dbg(dev, "%s - uart_flush_read error\n", __func__);
- return status;
+ goto out_free;
}
if (priv->len > 0) {
status = read_immediate(port, priv->buf, priv->len);
if (status != IUU_OPERATION_OK) {
dev_dbg(dev, "%s - uart_flush_read error\n", __func__);
- return status;
+ goto out_free;
}
}
}
dev_dbg(dev, "%s - uart_flush_read OK!\n", __func__);
iuu_led(port, 0, 0xF000, 0, 0xFF);
+
+out_free:
+ kfree(rxcmd);
+
return status;
}
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0620, 0xff, 0xff, 0x30) }, /* EM160R-GL */
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, 0x0620, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) },
{ 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),
{ 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(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */
{ 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 */
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_BROKEN_FUA),
+/* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */
+UNUSUAL_DEV(0x154b, 0xf00b, 0x0000, 0x9999,
+ "PNY",
+ "Pro Elite SSD",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_NO_ATA_1X),
+
/* Reported-by: Thinh Nguyen <thinhn@synopsys.com> */
UNUSUAL_DEV(0x154b, 0xf00d, 0x0000, 0x9999,
"PNY",
to enable support for VirtualLink devices with NVIDIA GPUs.
To compile this driver as a module, choose M here: the
- module will be called typec_displayport.
+ module will be called typec_nvidia.
endmenu
return ret;
sysfs_notify(&partner->dev.kobj, NULL, "number_of_alternate_modes");
+ kobject_uevent(&partner->dev.kobj, KOBJ_CHANGE);
return 0;
}
return ret;
sysfs_notify(&plug->dev.kobj, NULL, "number_of_alternate_modes");
+ kobject_uevent(&plug->dev.kobj, KOBJ_CHANGE);
return 0;
}
pmc_usb_mux_dp_hpd(struct pmc_usb_port *port, struct typec_displayport_data *dp)
{
u8 msg[2] = { };
+ int ret;
msg[0] = PMC_USB_DP_HPD;
msg[0] |= port->usb3_port << PMC_USB_MSG_USB3_PORT_SHIFT;
+ /* Configure HPD first if HPD,IRQ comes together */
+ if (!IOM_PORT_HPD_ASSERTED(port->iom_status) &&
+ dp->status & DP_STATUS_IRQ_HPD &&
+ dp->status & DP_STATUS_HPD_STATE) {
+ msg[1] = PMC_USB_DP_HPD_LVL;
+ ret = pmc_usb_command(port, msg, sizeof(msg));
+ if (ret)
+ return ret;
+ }
+
if (dp->status & DP_STATUS_IRQ_HPD)
msg[1] = PMC_USB_DP_HPD_IRQ;
default:
usbip_dbg_vhci_rh(" ClearPortFeature: default %x\n",
wValue);
+ if (wValue >= 32)
+ goto error;
vhci_hcd->port_status[rhport] &= ~(1 << wValue);
break;
}
size_t len, total_len = 0;
int err;
struct vhost_net_ubuf_ref *ubufs;
+ struct ubuf_info *ubuf;
bool zcopy_used;
int sent_pkts = 0;
/* use msg_control to pass vhost zerocopy ubuf info to skb */
if (zcopy_used) {
- struct ubuf_info *ubuf;
ubuf = nvq->ubuf_info + nvq->upend_idx;
-
vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
ubuf->callback = vhost_zerocopy_callback;
err = sock->ops->sendmsg(sock, &msg, len);
if (unlikely(err < 0)) {
if (zcopy_used) {
- vhost_net_ubuf_put(ubufs);
+ if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS)
+ vhost_net_ubuf_put(ubufs);
nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
% UIO_MAXIOV;
}
#define VHOST_VSOCK_PKT_WEIGHT 256
enum {
- VHOST_VSOCK_FEATURES = VHOST_FEATURES,
+ VHOST_VSOCK_FEATURES = VHOST_FEATURES |
+ (1ULL << VIRTIO_F_ACCESS_PLATFORM)
+};
+
+enum {
+ VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
};
/* Used to track all the vhost_vsock instances on the system. */
if (!vhost_vq_get_backend(vq))
goto out;
+ if (!vq_meta_prefetch(vq))
+ goto out;
+
/* Avoid further vmexits, we're already processing the virtqueue */
vhost_disable_notify(&vsock->dev, vq);
if (!vhost_vq_get_backend(vq))
goto out;
+ if (!vq_meta_prefetch(vq))
+ goto out;
+
vhost_disable_notify(&vsock->dev, vq);
do {
u32 len;
mutex_lock(&vsock->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&vsock->dev)) {
- mutex_unlock(&vsock->dev.mutex);
- return -EFAULT;
+ goto err;
+ }
+
+ if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
+ if (vhost_init_device_iotlb(&vsock->dev, true))
+ goto err;
}
for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
}
mutex_unlock(&vsock->dev.mutex);
return 0;
+
+err:
+ mutex_unlock(&vsock->dev.mutex);
+ return -EFAULT;
}
static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
if (copy_from_user(&features, argp, sizeof(features)))
return -EFAULT;
return vhost_vsock_set_features(vsock, features);
+ case VHOST_GET_BACKEND_FEATURES:
+ features = VHOST_VSOCK_BACKEND_FEATURES;
+ if (copy_to_user(argp, &features, sizeof(features)))
+ return -EFAULT;
+ return 0;
+ case VHOST_SET_BACKEND_FEATURES:
+ if (copy_from_user(&features, argp, sizeof(features)))
+ return -EFAULT;
+ if (features & ~VHOST_VSOCK_BACKEND_FEATURES)
+ return -EOPNOTSUPP;
+ vhost_set_backend_features(&vsock->dev, features);
+ return 0;
default:
mutex_lock(&vsock->dev.mutex);
r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
}
}
+static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct file *file = iocb->ki_filp;
+ struct vhost_vsock *vsock = file->private_data;
+ struct vhost_dev *dev = &vsock->dev;
+ int noblock = file->f_flags & O_NONBLOCK;
+
+ return vhost_chr_read_iter(dev, to, noblock);
+}
+
+static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb,
+ struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct vhost_vsock *vsock = file->private_data;
+ struct vhost_dev *dev = &vsock->dev;
+
+ return vhost_chr_write_iter(dev, from);
+}
+
+static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait)
+{
+ struct vhost_vsock *vsock = file->private_data;
+ struct vhost_dev *dev = &vsock->dev;
+
+ return vhost_chr_poll(file, dev, wait);
+}
+
static const struct file_operations vhost_vsock_fops = {
.owner = THIS_MODULE,
.open = vhost_vsock_dev_open,
.llseek = noop_llseek,
.unlocked_ioctl = vhost_vsock_dev_ioctl,
.compat_ioctl = compat_ptr_ioctl,
+ .read_iter = vhost_vsock_chr_read_iter,
+ .write_iter = vhost_vsock_chr_write_iter,
+ .poll = vhost_vsock_chr_poll,
};
static struct miscdevice vhost_vsock_misc = {
.irq_ack = ack_dynirq,
};
-int xen_set_callback_via(uint64_t via)
-{
- struct xen_hvm_param a;
- a.domid = DOMID_SELF;
- a.index = HVM_PARAM_CALLBACK_IRQ;
- a.value = via;
- return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
-}
-EXPORT_SYMBOL_GPL(xen_set_callback_via);
-
#ifdef CONFIG_XEN_PVHVM
/* Vector callbacks are better than PCI interrupts to receive event
* channel notifications because we can receive vector callbacks on any
dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
goto out;
}
+ /*
+ * It doesn't strictly *have* to run on CPU0 but it sure
+ * as hell better process the event channel ports delivered
+ * to CPU0.
+ */
+ irq_set_affinity(pdev->irq, cpumask_of(0));
+
callback_via = get_callback_via(pdev);
ret = xen_set_callback_via(callback_via);
if (ret) {
ret = gnttab_init();
if (ret)
goto grant_out;
- xenbus_probe(NULL);
return 0;
grant_out:
gnttab_free_auto_xlat_frames();
return 0;
}
-static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
+static long privcmd_ioctl_mmap_resource(struct file *file,
+ struct privcmd_mmap_resource __user *udata)
{
struct privcmd_data *data = file->private_data;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct privcmd_mmap_resource kdata;
xen_pfn_t *pfns = NULL;
- struct xen_mem_acquire_resource xdata;
+ struct xen_mem_acquire_resource xdata = { };
int rc;
if (copy_from_user(&kdata, udata, sizeof(kdata)))
if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
return -EPERM;
+ /* Both fields must be set or unset */
+ if (!!kdata.addr != !!kdata.num)
+ return -EINVAL;
+
+ xdata.domid = kdata.dom;
+ xdata.type = kdata.type;
+ xdata.id = kdata.id;
+
+ if (!kdata.addr && !kdata.num) {
+ /* Query the size of the resource. */
+ rc = HYPERVISOR_memory_op(XENMEM_acquire_resource, &xdata);
+ if (rc)
+ return rc;
+ return __put_user(xdata.nr_frames, &udata->num);
+ }
+
mmap_write_lock(mm);
vma = find_vma(mm, kdata.addr);
} else
vma->vm_private_data = PRIV_VMA_LOCKED;
- memset(&xdata, 0, sizeof(xdata));
- xdata.domid = kdata.dom;
- xdata.type = kdata.type;
- xdata.id = kdata.id;
xdata.frame = kdata.idx;
xdata.nr_frames = kdata.num;
set_xen_guest_handle(xdata.frame_list, pfns);
const char *type,
const char *nodename);
int xenbus_probe_devices(struct xen_bus_type *bus);
+void xenbus_probe(void);
void xenbus_dev_changed(const char *node, struct xen_bus_type *bus);
static int xenbus_irq;
static struct task_struct *xenbus_task;
-static DECLARE_WORK(probe_work, xenbus_probe);
-
-
static irqreturn_t wake_waiting(int irq, void *unused)
{
- if (unlikely(xenstored_ready == 0)) {
- xenstored_ready = 1;
- schedule_work(&probe_work);
- }
-
wake_up(&xb_waitq);
return IRQ_HANDLED;
}
}
EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
-void xenbus_probe(struct work_struct *unused)
+void xenbus_probe(void)
{
xenstored_ready = 1;
+ /*
+ * In the HVM case, xenbus_init() deferred its call to
+ * xs_init() in case callbacks were not operational yet.
+ * So do it now.
+ */
+ if (xen_store_domain_type == XS_HVM)
+ xs_init();
+
/* Notify others that xenstore is up */
blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
}
-EXPORT_SYMBOL_GPL(xenbus_probe);
-static int __init xenbus_probe_initcall(void)
+/*
+ * Returns true when XenStore init must be deferred in order to
+ * allow the PCI platform device to be initialised, before we
+ * can actually have event channel interrupts working.
+ */
+static bool xs_hvm_defer_init_for_callback(void)
{
- if (!xen_domain())
- return -ENODEV;
+#ifdef CONFIG_XEN_PVHVM
+ return xen_store_domain_type == XS_HVM &&
+ !xen_have_vector_callback;
+#else
+ return false;
+#endif
+}
- if (xen_initial_domain() || xen_hvm_domain())
- return 0;
+static int __init xenbus_probe_initcall(void)
+{
+ /*
+ * Probe XenBus here in the XS_PV case, and also XS_HVM unless we
+ * need to wait for the platform PCI device to come up.
+ */
+ if (xen_store_domain_type == XS_PV ||
+ (xen_store_domain_type == XS_HVM &&
+ !xs_hvm_defer_init_for_callback()))
+ xenbus_probe();
- xenbus_probe(NULL);
return 0;
}
-
device_initcall(xenbus_probe_initcall);
+int xen_set_callback_via(uint64_t via)
+{
+ struct xen_hvm_param a;
+ int ret;
+
+ a.domid = DOMID_SELF;
+ a.index = HVM_PARAM_CALLBACK_IRQ;
+ a.value = via;
+
+ ret = HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+ if (ret)
+ return ret;
+
+ /*
+ * If xenbus_probe_initcall() deferred the xenbus_probe()
+ * due to the callback not functioning yet, we can do it now.
+ */
+ if (!xenstored_ready && xs_hvm_defer_init_for_callback())
+ xenbus_probe();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
/* Set up event channel for xenstored which is run as a local process
* (this is normally used only in dom0)
*/
break;
}
- /* Initialize the interface to xenstore. */
- err = xs_init();
- if (err) {
- pr_warn("Error initializing xenstore comms: %i\n", err);
- goto out_error;
+ /*
+ * HVM domains may not have a functional callback yet. In that
+ * case let xs_init() be called from xenbus_probe(), which will
+ * get invoked at an appropriate time.
+ */
+ if (xen_store_domain_type != XS_HVM) {
+ err = xs_init();
+ if (err) {
+ pr_warn("Error initializing xenstore comms: %i\n", err);
+ goto out_error;
+ }
}
if ((xen_store_domain_type != XS_LOCAL) &&
unsigned blkoff)
{
union afs_xdr_dirent *dire;
- unsigned offset, next, curr;
+ unsigned offset, next, curr, nr_slots;
size_t nlen;
int tmp;
offset < AFS_DIR_SLOTS_PER_BLOCK;
offset = next
) {
- next = offset + 1;
-
/* skip entries marked unused in the bitmap */
if (!(block->hdr.bitmap[offset / 8] &
(1 << (offset % 8)))) {
_debug("ENT[%zu.%u]: unused",
blkoff / sizeof(union afs_xdr_dir_block), offset);
+ next = offset + 1;
if (offset >= curr)
ctx->pos = blkoff +
next * sizeof(union afs_xdr_dirent);
nlen = strnlen(dire->u.name,
sizeof(*block) -
offset * sizeof(union afs_xdr_dirent));
+ if (nlen > AFSNAMEMAX - 1) {
+ _debug("ENT[%zu]: name too long (len %u/%zu)",
+ blkoff / sizeof(union afs_xdr_dir_block),
+ offset, nlen);
+ return afs_bad(dvnode, afs_file_error_dir_name_too_long);
+ }
_debug("ENT[%zu.%u]: %s %zu \"%s\"",
blkoff / sizeof(union afs_xdr_dir_block), offset,
(offset < curr ? "skip" : "fill"),
nlen, dire->u.name);
- /* work out where the next possible entry is */
- for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_xdr_dirent)) {
- if (next >= AFS_DIR_SLOTS_PER_BLOCK) {
- _debug("ENT[%zu.%u]:"
- " %u travelled beyond end dir block"
- " (len %u/%zu)",
- blkoff / sizeof(union afs_xdr_dir_block),
- offset, next, tmp, nlen);
- return afs_bad(dvnode, afs_file_error_dir_over_end);
- }
- if (!(block->hdr.bitmap[next / 8] &
- (1 << (next % 8)))) {
- _debug("ENT[%zu.%u]:"
- " %u unmarked extension (len %u/%zu)",
+ nr_slots = afs_dir_calc_slots(nlen);
+ next = offset + nr_slots;
+ if (next > AFS_DIR_SLOTS_PER_BLOCK) {
+ _debug("ENT[%zu.%u]:"
+ " %u extends beyond end dir block"
+ " (len %zu)",
+ blkoff / sizeof(union afs_xdr_dir_block),
+ offset, next, nlen);
+ return afs_bad(dvnode, afs_file_error_dir_over_end);
+ }
+
+ /* Check that the name-extension dirents are all allocated */
+ for (tmp = 1; tmp < nr_slots; tmp++) {
+ unsigned int ix = offset + tmp;
+ if (!(block->hdr.bitmap[ix / 8] & (1 << (ix % 8)))) {
+ _debug("ENT[%zu.u]:"
+ " %u unmarked extension (%u/%u)",
blkoff / sizeof(union afs_xdr_dir_block),
- offset, next, tmp, nlen);
+ offset, tmp, nr_slots);
return afs_bad(dvnode, afs_file_error_dir_unmarked_ext);
}
-
- _debug("ENT[%zu.%u]: ext %u/%zu",
- blkoff / sizeof(union afs_xdr_dir_block),
- next, tmp, nlen);
- next++;
}
/* skip if starts before the current position */
}
/* Work out how many slots we're going to need. */
- need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE);
- need_slots /= AFS_DIR_DIRENT_SIZE;
+ need_slots = afs_dir_calc_slots(name->len);
meta_page = kmap(page0);
meta = &meta_page->blocks[0];
}
/* Work out how many slots we're going to discard. */
- need_slots = round_up(12 + name->len + 1 + 4, AFS_DIR_DIRENT_SIZE);
- need_slots /= AFS_DIR_DIRENT_SIZE;
+ need_slots = afs_dir_calc_slots(name->len);
meta_page = kmap(page0);
meta = &meta_page->blocks[0];
__be16 hash_next;
__be32 vnode;
__be32 unique;
- u8 name[16];
- u8 overflow[4]; /* if any char of the name (inc
- * NUL) reaches here, consume
- * the next dirent too */
+ u8 name[];
+ /* When determining the number of dirent slots needed to
+ * represent a directory entry, name should be assumed to be 16
+ * bytes, due to a now-standardised (mis)calculation, but it is
+ * in fact 20 bytes in size. afs_dir_calc_slots() should be
+ * used for this.
+ *
+ * For names longer than (16 or) 20 bytes, extra slots should
+ * be annexed to this one using the extended_name format.
+ */
} u;
u8 extended_name[32];
} __packed;
union afs_xdr_dir_block blocks[AFS_DIR_BLOCKS_PER_PAGE];
};
+/*
+ * Calculate the number of dirent slots required for any given name length.
+ * The calculation is made assuming the part of the name in the first slot is
+ * 16 bytes, rather than 20, but this miscalculation is now standardised.
+ */
+static inline unsigned int afs_dir_calc_slots(size_t name_len)
+{
+ name_len++; /* NUL-terminated */
+ return 1 + ((name_len + 15) / AFS_DIR_DIRENT_SIZE);
+}
+
#endif /* XDR_FS_H */
error = thaw_super(sb);
if (error)
bdev->bd_fsfreeze_count++;
+ else
+ bdev->bd_fsfreeze_sb = NULL;
out:
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return error;
static struct inode *bdev_alloc_inode(struct super_block *sb)
{
struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
+
if (!ei)
return NULL;
+ memset(&ei->bdev, 0, sizeof(ei->bdev));
+ ei->bdev.bd_bdi = &noop_backing_dev_info;
return &ei->vfs_inode;
}
mapping_set_gfp_mask(&inode->i_data, GFP_USER);
bdev = I_BDEV(inode);
- memset(bdev, 0, sizeof(*bdev));
mutex_init(&bdev->bd_mutex);
mutex_init(&bdev->bd_fsfreeze_mutex);
spin_lock_init(&bdev->bd_size_lock);
bdev->bd_disk = disk;
bdev->bd_partno = partno;
bdev->bd_inode = inode;
- bdev->bd_bdi = &noop_backing_dev_info;
#ifdef CONFIG_SYSFS
INIT_LIST_HEAD(&bdev->bd_holder_disks);
#endif
/**
* bd_abort_claiming - abort claiming of a block device
* @bdev: block device of interest
- * @whole: whole block device
* @holder: holder that has claimed @bdev
*
* Abort claiming of a block device when the exclusive open failed. This can be
/**
* lookup_bdev - lookup a struct block_device by name
* @pathname: special file representing the block device
+ * @dev: return value of the block device's dev_t
*
* Get a reference to the blockdevice at @pathname in the current
* namespace if possible and return it. Return ERR_PTR(error)
list_del_init(&lower->list);
if (lower == node)
node = NULL;
- btrfs_backref_free_node(cache, lower);
+ btrfs_backref_drop_node(cache, lower);
}
btrfs_backref_cleanup_node(cache, node);
* Go through delayed refs for all the stuff we've just kicked off
* and then loop back (just once)
*/
- ret = btrfs_run_delayed_refs(trans, 0);
+ if (!ret)
+ ret = btrfs_run_delayed_refs(trans, 0);
if (!ret && loops == 0) {
loops++;
spin_lock(&cur_trans->dirty_bgs_lock);
* to an inode.
*/
BTRFS_INODE_NO_XATTRS,
+ /*
+ * Set when we are in a context where we need to start a transaction and
+ * have dirty pages with the respective file range locked. This is to
+ * ensure that when reserving space for the transaction, if we are low
+ * on available space and need to flush delalloc, we will not flush
+ * delalloc for this inode, because that could result in a deadlock (on
+ * the file range, inode's io_tree).
+ */
+ BTRFS_INODE_NO_DELALLOC_FLUSH,
};
/* in memory btrfs inode */
* @p: Holds all btree nodes along the search path
* @root: The root node of the tree
* @key: The key we are looking for
- * @ins_len: Indicates purpose of search, for inserts it is 1, for
- * deletions it's -1. 0 for plain searches
+ * @ins_len: Indicates purpose of search:
+ * >0 for inserts it's size of item inserted (*)
+ * <0 for deletions
+ * 0 for plain searches, not modifying the tree
+ *
+ * (*) If size of item inserted doesn't include
+ * sizeof(struct btrfs_item), then p->search_for_extension must
+ * be set.
* @cow: boolean should CoW operations be performed. Must always be 1
* when modifying the tree.
*
if (level == 0) {
p->slots[level] = slot;
+ /*
+ * Item key already exists. In this case, if we are
+ * allowed to insert the item (for example, in dir_item
+ * case, item key collision is allowed), it will be
+ * merged with the original item. Only the item size
+ * grows, no new btrfs item will be added. If
+ * search_for_extension is not set, ins_len already
+ * accounts the size btrfs_item, deduct it here so leaf
+ * space check will be correct.
+ */
+ if (ret == 0 && ins_len > 0 && !p->search_for_extension) {
+ ASSERT(ins_len >= sizeof(struct btrfs_item));
+ ins_len -= sizeof(struct btrfs_item);
+ }
if (ins_len > 0 &&
btrfs_leaf_free_space(b) < ins_len) {
if (write_lock_level < 1) {
* defrag
*/
BTRFS_FS_STATE_REMOUNTING,
+ /* Filesystem in RO mode */
+ BTRFS_FS_STATE_RO,
/* Track if a transaction abort has been reported on this filesystem */
BTRFS_FS_STATE_TRANS_ABORTED,
/*
unsigned int search_commit_root:1;
unsigned int need_commit_sem:1;
unsigned int skip_release_on_error:1;
+ /*
+ * Indicate that new item (btrfs_search_slot) is extending already
+ * existing item and ins_len contains only the data size and not item
+ * header (ie. sizeof(struct btrfs_item) is not included).
+ */
+ unsigned int search_for_extension:1;
};
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
sizeof(struct btrfs_item))
* If we remount the fs to be R/O or umount the fs, the cleaner needn't do
* anything except sleeping. This function is used to check the status of
* the fs.
+ * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount,
+ * since setting and checking for SB_RDONLY in the superblock's flags is not
+ * atomic.
*/
static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
{
- return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info);
+ return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) ||
+ btrfs_fs_closing(fs_info);
+}
+
+static inline void btrfs_set_sb_rdonly(struct super_block *sb)
+{
+ sb->s_flags |= SB_RDONLY;
+ set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
+}
+
+static inline void btrfs_clear_sb_rdonly(struct super_block *sb)
+{
+ sb->s_flags &= ~SB_RDONLY;
+ clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
}
/* tree mod log functions from ctree.c */
u32 min_type);
int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+ bool in_reclaim_context);
int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
unsigned int extra_bits,
struct extent_state **cached_state);
* flush all outstanding I/O and inode extent mappings before the
* copy operation is declared as being finished
*/
- ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+ ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
if (ret) {
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return ret;
static struct btrfs_block_group *peek_discard_list(
struct btrfs_discard_ctl *discard_ctl,
enum btrfs_discard_state *discard_state,
- int *discard_index)
+ int *discard_index, u64 now)
{
struct btrfs_block_group *block_group;
- const u64 now = ktime_get_ns();
spin_lock(&discard_ctl->lock);
again:
block_group = find_next_block_group(discard_ctl, now);
- if (block_group && now > block_group->discard_eligible_time) {
+ if (block_group && now >= block_group->discard_eligible_time) {
if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED &&
block_group->used != 0) {
if (btrfs_is_block_group_data_only(block_group))
block_group->discard_state = BTRFS_DISCARD_EXTENTS;
}
discard_ctl->block_group = block_group;
+ }
+ if (block_group) {
*discard_state = block_group->discard_state;
*discard_index = block_group->discard_index;
- } else {
- block_group = NULL;
}
-
spin_unlock(&discard_ctl->lock);
return block_group;
btrfs_discard_schedule_work(discard_ctl, false);
}
-/**
- * btrfs_discard_schedule_work - responsible for scheduling the discard work
- * @discard_ctl: discard control
- * @override: override the current timer
- *
- * Discards are issued by a delayed workqueue item. @override is used to
- * update the current delay as the baseline delay interval is reevaluated on
- * transaction commit. This is also maxed with any other rate limit.
- */
-void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
- bool override)
+static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+ u64 now, bool override)
{
struct btrfs_block_group *block_group;
- const u64 now = ktime_get_ns();
-
- spin_lock(&discard_ctl->lock);
if (!btrfs_run_discard_work(discard_ctl))
- goto out;
-
+ return;
if (!override && delayed_work_pending(&discard_ctl->work))
- goto out;
+ return;
block_group = find_next_block_group(discard_ctl, now);
if (block_group) {
mod_delayed_work(discard_ctl->discard_workers,
&discard_ctl->work, nsecs_to_jiffies(delay));
}
-out:
+}
+
+/*
+ * btrfs_discard_schedule_work - responsible for scheduling the discard work
+ * @discard_ctl: discard control
+ * @override: override the current timer
+ *
+ * Discards are issued by a delayed workqueue item. @override is used to
+ * update the current delay as the baseline delay interval is reevaluated on
+ * transaction commit. This is also maxed with any other rate limit.
+ */
+void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+ bool override)
+{
+ const u64 now = ktime_get_ns();
+
+ spin_lock(&discard_ctl->lock);
+ __btrfs_discard_schedule_work(discard_ctl, now, override);
spin_unlock(&discard_ctl->lock);
}
int discard_index = 0;
u64 trimmed = 0;
u64 minlen = 0;
+ u64 now = ktime_get_ns();
discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work);
block_group = peek_discard_list(discard_ctl, &discard_state,
- &discard_index);
+ &discard_index, now);
if (!block_group || !btrfs_run_discard_work(discard_ctl))
return;
+ if (now < block_group->discard_eligible_time) {
+ btrfs_discard_schedule_work(discard_ctl, false);
+ return;
+ }
/* Perform discarding */
minlen = discard_minlen[discard_index];
discard_ctl->discard_extent_bytes += trimmed;
}
- /*
- * Updated without locks as this is inside the workfn and nothing else
- * is reading the values
- */
- discard_ctl->prev_discard = trimmed;
- discard_ctl->prev_discard_time = ktime_get_ns();
-
/* Determine next steps for a block_group */
if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) {
if (discard_state == BTRFS_DISCARD_BITMAPS) {
}
}
+ now = ktime_get_ns();
spin_lock(&discard_ctl->lock);
+ discard_ctl->prev_discard = trimmed;
+ discard_ctl->prev_discard_time = now;
discard_ctl->block_group = NULL;
+ __btrfs_discard_schedule_work(discard_ctl, now, false);
spin_unlock(&discard_ctl->lock);
-
- btrfs_discard_schedule_work(discard_ctl, false);
}
/**
root = list_first_entry(&fs_info->allocated_roots,
struct btrfs_root, leak_list);
btrfs_err(fs_info, "leaked root %s refcount %d",
- btrfs_root_name(root->root_key.objectid, buf),
+ btrfs_root_name(&root->root_key, buf),
refcount_read(&root->refs));
while (refcount_read(&root->refs) > 1)
btrfs_put_root(root);
*/
btrfs_delete_unused_bgs(fs_info);
sleep:
- clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
+ clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
if (kthread_should_park())
kthread_parkme();
if (kthread_should_stop())
return -ENOMEM;
btrfs_init_delayed_root(fs_info->delayed_root);
+ if (sb_rdonly(sb))
+ set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
+
return btrfs_alloc_stripe_hash_table(fs_info);
}
}
}
+ ret = btrfs_find_orphan_roots(fs_info);
out:
return ret;
}
}
}
- ret = btrfs_find_orphan_roots(fs_info);
- if (ret)
- goto fail_qgroup;
-
fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
if (IS_ERR(fs_info->fs_root)) {
err = PTR_ERR(fs_info->fs_root);
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
+ /* We shouldn't have any transaction open at this point */
+ ASSERT(list_empty(&fs_info->trans_list));
+
clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
free_root_pointers(fs_info, true);
btrfs_free_fs_roots(fs_info);
want = extent_ref_type(parent, owner);
if (insert) {
extra_size = btrfs_extent_inline_ref_size(want);
+ path->search_for_extension = 1;
path->keep_locks = 1;
} else
extra_size = -1;
out:
if (insert) {
path->keep_locks = 0;
+ path->search_for_extension = 0;
btrfs_unlock_up_safe(path, 1);
}
return err;
goto out_free;
}
- trans = btrfs_start_transaction(tree_root, 0);
+ /*
+ * Use join to avoid potential EINTR from transaction
+ * start. See wait_reserve_ticket and the whole
+ * reservation callchain.
+ */
+ if (for_reloc)
+ trans = btrfs_join_transaction(tree_root);
+ else
+ trans = btrfs_start_transaction(tree_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_free;
static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
{
- struct inode *inode = tree->private_data;
-
- btrfs_panic(btrfs_sb(inode->i_sb), err,
+ btrfs_panic(tree->fs_info, err,
"locking error: extent tree was modified by another thread while locked");
}
}
btrfs_release_path(path);
+ path->search_for_extension = 1;
ret = btrfs_search_slot(trans, root, &file_key, path,
csum_size, 1);
+ path->search_for_extension = 0;
if (ret < 0)
goto out;
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
-static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot)
+static int start_delalloc_inodes(struct btrfs_root *root,
+ struct writeback_control *wbc, bool snapshot,
+ bool in_reclaim_context)
{
struct btrfs_inode *binode;
struct inode *inode;
struct list_head works;
struct list_head splice;
int ret = 0;
+ bool full_flush = wbc->nr_to_write == LONG_MAX;
INIT_LIST_HEAD(&works);
INIT_LIST_HEAD(&splice);
list_move_tail(&binode->delalloc_inodes,
&root->delalloc_inodes);
+
+ if (in_reclaim_context &&
+ test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags))
+ continue;
+
inode = igrab(&binode->vfs_inode);
if (!inode) {
cond_resched_lock(&root->delalloc_lock);
if (snapshot)
set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
&binode->runtime_flags);
- work = btrfs_alloc_delalloc_work(inode);
- if (!work) {
- iput(inode);
- ret = -ENOMEM;
- goto out;
- }
- list_add_tail(&work->list, &works);
- btrfs_queue_work(root->fs_info->flush_workers,
- &work->work);
- if (*nr != U64_MAX) {
- (*nr)--;
- if (*nr == 0)
+ if (full_flush) {
+ work = btrfs_alloc_delalloc_work(inode);
+ if (!work) {
+ iput(inode);
+ ret = -ENOMEM;
+ goto out;
+ }
+ list_add_tail(&work->list, &works);
+ btrfs_queue_work(root->fs_info->flush_workers,
+ &work->work);
+ } else {
+ ret = sync_inode(inode, wbc);
+ if (!ret &&
+ test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ ret = sync_inode(inode, wbc);
+ btrfs_add_delayed_iput(inode);
+ if (ret || wbc->nr_to_write <= 0)
goto out;
}
cond_resched();
int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
{
+ struct writeback_control wbc = {
+ .nr_to_write = LONG_MAX,
+ .sync_mode = WB_SYNC_NONE,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
struct btrfs_fs_info *fs_info = root->fs_info;
- u64 nr = U64_MAX;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
- return start_delalloc_inodes(root, &nr, true);
+ return start_delalloc_inodes(root, &wbc, true, false);
}
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+ bool in_reclaim_context)
{
+ struct writeback_control wbc = {
+ .nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr,
+ .sync_mode = WB_SYNC_NONE,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
struct btrfs_root *root;
struct list_head splice;
int ret;
spin_lock(&fs_info->delalloc_root_lock);
list_splice_init(&fs_info->delalloc_roots, &splice);
while (!list_empty(&splice) && nr) {
+ /*
+ * Reset nr_to_write here so we know that we're doing a full
+ * flush.
+ */
+ if (nr == U64_MAX)
+ wbc.nr_to_write = LONG_MAX;
+
root = list_first_entry(&splice, struct btrfs_root,
delalloc_root);
root = btrfs_grab_root(root);
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = start_delalloc_inodes(root, &nr, false);
+ ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context);
btrfs_put_root(root);
- if (ret < 0)
+ if (ret < 0 || wbc.nr_to_write <= 0)
goto out;
spin_lock(&fs_info->delalloc_root_lock);
}
case BTRFS_IOC_SYNC: {
int ret;
- ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+ ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
if (ret)
return ret;
ret = btrfs_sync_fs(inode->i_sb, 1);
{ BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" },
};
-const char *btrfs_root_name(u64 objectid, char *buf)
+const char *btrfs_root_name(const struct btrfs_key *key, char *buf)
{
int i;
- if (objectid == BTRFS_TREE_RELOC_OBJECTID) {
+ if (key->objectid == BTRFS_TREE_RELOC_OBJECTID) {
snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN,
- "TREE_RELOC offset=%llu", objectid);
+ "TREE_RELOC offset=%llu", key->offset);
return buf;
}
for (i = 0; i < ARRAY_SIZE(root_map); i++) {
- if (root_map[i].id == objectid)
+ if (root_map[i].id == key->objectid)
return root_map[i].name;
}
- snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", objectid);
+ snprintf(buf, BTRFS_ROOT_NAME_BUF_LEN, "%llu", key->objectid);
return buf;
}
void btrfs_print_leaf(struct extent_buffer *l);
void btrfs_print_tree(struct extent_buffer *c, bool follow);
-const char *btrfs_root_name(u64 objectid, char *buf);
+const char *btrfs_root_name(const struct btrfs_key *key, char *buf);
#endif
return ret;
}
+static bool rescan_should_stop(struct btrfs_fs_info *fs_info)
+{
+ return btrfs_fs_closing(fs_info) ||
+ test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+}
+
static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
{
struct btrfs_fs_info *fs_info = container_of(work, struct btrfs_fs_info,
struct btrfs_trans_handle *trans = NULL;
int err = -ENOMEM;
int ret = 0;
+ bool stopped = false;
path = btrfs_alloc_path();
if (!path)
path->skip_locking = 1;
err = 0;
- while (!err && !btrfs_fs_closing(fs_info)) {
+ while (!err && !(stopped = rescan_should_stop(fs_info))) {
trans = btrfs_start_transaction(fs_info->fs_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
}
mutex_lock(&fs_info->qgroup_rescan_lock);
- if (!btrfs_fs_closing(fs_info))
+ if (!stopped)
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
if (trans) {
ret = update_qgroup_status_item(trans);
btrfs_end_transaction(trans);
- if (btrfs_fs_closing(fs_info)) {
+ if (stopped) {
btrfs_info(fs_info, "qgroup scan paused");
} else if (err >= 0) {
btrfs_info(fs_info, "qgroup scan completed%s",
int ret;
bool can_commit = true;
- /*
- * We don't want to run flush again and again, so if there is a running
- * one, we won't try to start a new flush, but exit directly.
- */
- if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
- wait_event(root->qgroup_flush_wait,
- !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
- return 0;
- }
-
/*
* If current process holds a transaction, we shouldn't flush, as we
* assume all space reservation happens before a transaction handle is
current->journal_info != BTRFS_SEND_TRANS_STUB)
can_commit = false;
+ /*
+ * We don't want to run flush again and again, so if there is a running
+ * one, we won't try to start a new flush, but exit directly.
+ */
+ if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
+ /*
+ * We are already holding a transaction, thus we can block other
+ * threads from flushing. So exit right now. This increases
+ * the chance of EDQUOT for heavy load and near limit cases.
+ * But we can argue that if we're already near limit, EDQUOT is
+ * unavoidable anyway.
+ */
+ if (!can_commit)
+ return 0;
+
+ wait_event(root->qgroup_flush_wait,
+ !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
+ return 0;
+ }
+
ret = btrfs_start_delalloc_snapshot(root);
if (ret < 0)
goto out;
if (ret)
goto out_unlock;
+ /*
+ * After dirtying the page our caller will need to start a transaction,
+ * and if we are low on metadata free space, that can cause flushing of
+ * delalloc for all inodes in order to get metadata space released.
+ * However we are holding the range locked for the whole duration of
+ * the clone/dedupe operation, so we may deadlock if that happens and no
+ * other task releases enough space. So mark this inode as not being
+ * possible to flush to avoid such deadlock. We will clear that flag
+ * when we finish cloning all extents, since a transaction is started
+ * after finding each extent to clone.
+ */
+ set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags);
+
if (comp_type == BTRFS_COMPRESS_NONE) {
char *map;
out:
btrfs_free_path(path);
kvfree(buf);
+ clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags);
+
return ret;
}
return 0;
for (i = 0; i < btrfs_header_nritems(leaf); i++) {
+ u8 type;
+
btrfs_item_key_to_cpu(leaf, &key, i);
if (key.type != BTRFS_EXTENT_DATA_KEY)
continue;
ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
- if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG &&
+ type = btrfs_file_extent_type(leaf, ei);
+
+ if ((type == BTRFS_FILE_EXTENT_REG ||
+ type == BTRFS_FILE_EXTENT_PREALLOC) &&
btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) {
found = true;
space_cache_ino = key.objectid;
* after this directory is moved, we can try to rmdir the ino rmdir_ino.
*/
u64 rmdir_ino;
+ u64 rmdir_gen;
bool orphanized;
};
static struct waiting_dir_move *
get_waiting_dir_move(struct send_ctx *sctx, u64 ino);
-static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino);
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen);
static int need_send_hole(struct send_ctx *sctx)
{
fs_path_reset(name);
- if (is_waiting_for_rm(sctx, ino)) {
+ if (is_waiting_for_rm(sctx, ino, gen)) {
ret = gen_unique_name(sctx, ino, gen, name);
if (ret < 0)
goto out;
return ret;
}
-static struct orphan_dir_info *
-add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+static struct orphan_dir_info *add_orphan_dir_info(struct send_ctx *sctx,
+ u64 dir_ino, u64 dir_gen)
{
struct rb_node **p = &sctx->orphan_dirs.rb_node;
struct rb_node *parent = NULL;
while (*p) {
parent = *p;
entry = rb_entry(parent, struct orphan_dir_info, node);
- if (dir_ino < entry->ino) {
+ if (dir_ino < entry->ino)
p = &(*p)->rb_left;
- } else if (dir_ino > entry->ino) {
+ else if (dir_ino > entry->ino)
p = &(*p)->rb_right;
- } else {
+ else if (dir_gen < entry->gen)
+ p = &(*p)->rb_left;
+ else if (dir_gen > entry->gen)
+ p = &(*p)->rb_right;
+ else
return entry;
- }
}
odi = kmalloc(sizeof(*odi), GFP_KERNEL);
if (!odi)
return ERR_PTR(-ENOMEM);
odi->ino = dir_ino;
- odi->gen = 0;
+ odi->gen = dir_gen;
odi->last_dir_index_offset = 0;
rb_link_node(&odi->node, parent, p);
return odi;
}
-static struct orphan_dir_info *
-get_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
+static struct orphan_dir_info *get_orphan_dir_info(struct send_ctx *sctx,
+ u64 dir_ino, u64 gen)
{
struct rb_node *n = sctx->orphan_dirs.rb_node;
struct orphan_dir_info *entry;
n = n->rb_left;
else if (dir_ino > entry->ino)
n = n->rb_right;
+ else if (gen < entry->gen)
+ n = n->rb_left;
+ else if (gen > entry->gen)
+ n = n->rb_right;
else
return entry;
}
return NULL;
}
-static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino)
+static int is_waiting_for_rm(struct send_ctx *sctx, u64 dir_ino, u64 gen)
{
- struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino);
+ struct orphan_dir_info *odi = get_orphan_dir_info(sctx, dir_ino, gen);
return odi != NULL;
}
key.type = BTRFS_DIR_INDEX_KEY;
key.offset = 0;
- odi = get_orphan_dir_info(sctx, dir);
+ odi = get_orphan_dir_info(sctx, dir, dir_gen);
if (odi)
key.offset = odi->last_dir_index_offset;
dm = get_waiting_dir_move(sctx, loc.objectid);
if (dm) {
- odi = add_orphan_dir_info(sctx, dir);
+ odi = add_orphan_dir_info(sctx, dir, dir_gen);
if (IS_ERR(odi)) {
ret = PTR_ERR(odi);
goto out;
odi->gen = dir_gen;
odi->last_dir_index_offset = found_key.offset;
dm->rmdir_ino = dir;
+ dm->rmdir_gen = dir_gen;
ret = 0;
goto out;
}
if (loc.objectid > send_progress) {
- odi = add_orphan_dir_info(sctx, dir);
+ odi = add_orphan_dir_info(sctx, dir, dir_gen);
if (IS_ERR(odi)) {
ret = PTR_ERR(odi);
goto out;
return -ENOMEM;
dm->ino = ino;
dm->rmdir_ino = 0;
+ dm->rmdir_gen = 0;
dm->orphanized = orphanized;
while (*p) {
while (ino != BTRFS_FIRST_FREE_OBJECTID) {
fs_path_reset(name);
- if (is_waiting_for_rm(sctx, ino))
+ if (is_waiting_for_rm(sctx, ino, gen))
break;
if (is_waiting_for_move(sctx, ino)) {
if (*ancestor_ino == 0)
u64 parent_ino, parent_gen;
struct waiting_dir_move *dm = NULL;
u64 rmdir_ino = 0;
+ u64 rmdir_gen;
u64 ancestor;
bool is_orphan;
int ret;
dm = get_waiting_dir_move(sctx, pm->ino);
ASSERT(dm);
rmdir_ino = dm->rmdir_ino;
+ rmdir_gen = dm->rmdir_gen;
is_orphan = dm->orphanized;
free_waiting_dir_move(sctx, dm);
dm = get_waiting_dir_move(sctx, pm->ino);
ASSERT(dm);
dm->rmdir_ino = rmdir_ino;
+ dm->rmdir_gen = rmdir_gen;
}
goto out;
}
struct orphan_dir_info *odi;
u64 gen;
- odi = get_orphan_dir_info(sctx, rmdir_ino);
+ odi = get_orphan_dir_info(sctx, rmdir_ino, rmdir_gen);
if (!odi) {
/* already deleted */
goto finish;
break;
offset += clone_len;
clone_root->offset += clone_len;
+
+ /*
+ * If we are cloning from the file we are currently processing,
+ * and using the send root as the clone root, we must stop once
+ * the current clone offset reaches the current eof of the file
+ * at the receiver, otherwise we would issue an invalid clone
+ * operation (source range going beyond eof) and cause the
+ * receiver to fail. So if we reach the current eof, bail out
+ * and fallback to a regular write.
+ */
+ if (clone_root->root == sctx->send_root &&
+ clone_root->ino == sctx->cur_ino &&
+ clone_root->offset >= sctx->cur_inode_next_write_offset)
+ break;
+
data_offset += clone_len;
next:
path->slots[0]++;
loops = 0;
while ((delalloc_bytes || dio_bytes) && loops < 3) {
- btrfs_start_delalloc_roots(fs_info, items);
+ u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
+
+ btrfs_start_delalloc_roots(fs_info, nr_pages, true);
loops++;
if (wait_ordered && !trans) {
btrfs_discard_stop(fs_info);
/* btrfs handle error by forcing the filesystem readonly */
- sb->s_flags |= SB_RDONLY;
+ btrfs_set_sb_rdonly(sb);
btrfs_info(fs_info, "forced readonly");
/*
* Note that a running device replace operation is not canceled here
/* avoid complains from lockdep et al. */
up(&fs_info->uuid_tree_rescan_sem);
- sb->s_flags |= SB_RDONLY;
+ btrfs_set_sb_rdonly(sb);
/*
* Setting SB_RDONLY will put the cleaner thread to
*/
btrfs_delete_unused_bgs(fs_info);
+ /*
+ * The cleaner task could be already running before we set the
+ * flag BTRFS_FS_STATE_RO (and SB_RDONLY in the superblock).
+ * We must make sure that after we finish the remount, i.e. after
+ * we call btrfs_commit_super(), the cleaner can no longer start
+ * a transaction - either because it was dropping a dead root,
+ * running delayed iputs or deleting an unused block group (the
+ * cleaner picked a block group from the list of unused block
+ * groups before we were able to in the previous call to
+ * btrfs_delete_unused_bgs()).
+ */
+ wait_on_bit(&fs_info->flags, BTRFS_FS_CLEANER_RUNNING,
+ TASK_UNINTERRUPTIBLE);
+
+ /*
+ * We've set the superblock to RO mode, so we might have made
+ * the cleaner task sleep without running all pending delayed
+ * iputs. Go through all the delayed iputs here, so that if an
+ * unmount happens without remounting RW we don't end up at
+ * finishing close_ctree() with a non-empty list of delayed
+ * iputs.
+ */
+ btrfs_run_delayed_iputs(fs_info);
+
btrfs_dev_replace_suspend_for_unmount(fs_info);
btrfs_scrub_cancel(fs_info);
btrfs_pause_balance(fs_info);
+ /*
+ * Pause the qgroup rescan worker if it is running. We don't want
+ * it to be still running after we are in RO mode, as after that,
+ * by the time we unmount, it might have left a transaction open,
+ * so we would leak the transaction and/or crash.
+ */
+ btrfs_qgroup_wait_for_completion(fs_info, false);
+
ret = btrfs_commit_super(fs_info);
if (ret)
goto restore;
if (ret)
goto restore;
- sb->s_flags &= ~SB_RDONLY;
+ btrfs_clear_sb_rdonly(sb);
set_bit(BTRFS_FS_OPEN, &fs_info->flags);
}
/* We've hit an error - don't reset SB_RDONLY */
if (sb_rdonly(sb))
old_flags |= SB_RDONLY;
+ if (!(old_flags & SB_RDONLY))
+ clear_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
sb->s_flags = old_flags;
fs_info->mount_opt = old_opts;
fs_info->compress_type = old_compress_type;
struct inode *inode;
inode = new_inode(test_mnt->mnt_sb);
- if (inode)
- inode_init_owner(inode, NULL, S_IFREG);
+ if (!inode)
+ return NULL;
+
+ inode->i_mode = S_IFREG;
+ BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
+ BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
+ BTRFS_I(inode)->location.offset = 0;
+ inode_init_owner(inode, NULL, S_IFREG);
return inode;
}
return ret;
}
- inode->i_mode = S_IFREG;
- BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
- BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
- BTRFS_I(inode)->location.offset = 0;
-
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
test_std_err(TEST_ALLOC_FS_INFO);
return ret;
}
- BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
- BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
- BTRFS_I(inode)->location.offset = 0;
-
fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
if (!fs_info) {
test_std_err(TEST_ALLOC_FS_INFO);
*/
btrfs_free_log_root_tree(trans, fs_info);
- /*
- * commit_fs_roots() can call btrfs_save_ino_cache(), which generates
- * new delayed refs. Must handle them or qgroup can be wrong.
- */
- ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
- if (ret)
- goto unlock_tree_log;
-
/*
* Since fs roots are all committed, we can get a quite accurate
* new_roots. So let's do quota accounting.
{
struct btrfs_fs_info *fs_info = leaf->fs_info;
u64 length;
+ u64 chunk_end;
u64 stripe_len;
u16 num_stripes;
u16 sub_stripes;
"invalid chunk length, have %llu", length);
return -EUCLEAN;
}
+ if (unlikely(check_add_overflow(logical, length, &chunk_end))) {
+ chunk_err(leaf, chunk, logical,
+"invalid chunk logical start and length, have logical start %llu length %llu",
+ logical, length);
+ return -EUCLEAN;
+ }
if (unlikely(!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN)) {
chunk_err(leaf, chunk, logical,
"invalid chunk stripe length: %llu",
set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
if (seeding_dev) {
- sb->s_flags &= ~SB_RDONLY;
+ btrfs_clear_sb_rdonly(sb);
ret = btrfs_prepare_sprout(fs_info);
if (ret) {
btrfs_abort_transaction(trans, ret);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
error_trans:
if (seeding_dev)
- sb->s_flags |= SB_RDONLY;
+ btrfs_set_sb_rdonly(sb);
if (trans)
btrfs_end_transaction(trans);
error_free_zone:
btrfs_warn(fs_info,
"balance: cannot set exclusive op status, resume manually");
+ btrfs_release_path(path);
+
mutex_lock(&fs_info->balance_mutex);
BUG_ON(fs_info->balance_ctl);
spin_lock(&fs_info->balance_lock);
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
return r;
}
+static void encode_timestamp_and_gids(void **p,
+ const struct ceph_mds_request *req)
+{
+ struct ceph_timespec ts;
+ int i;
+
+ ceph_encode_timespec64(&ts, &req->r_stamp);
+ ceph_encode_copy(p, &ts, sizeof(ts));
+
+ /* gid_list */
+ ceph_encode_32(p, req->r_cred->group_info->ngroups);
+ for (i = 0; i < req->r_cred->group_info->ngroups; i++)
+ ceph_encode_64(p, from_kgid(&init_user_ns,
+ req->r_cred->group_info->gid[i]));
+}
+
/*
* called under mdsc->mutex
*/
u64 ino1 = 0, ino2 = 0;
int pathlen1 = 0, pathlen2 = 0;
bool freepath1 = false, freepath2 = false;
- int len, i;
+ int len;
u16 releases;
void *p, *end;
int ret;
goto out_free1;
}
- if (legacy) {
- /* Old style */
- len = sizeof(*head);
- } else {
- /* New style: add gid_list and any later fields */
- len = sizeof(struct ceph_mds_request_head) + sizeof(u32) +
- (sizeof(u64) * req->r_cred->group_info->ngroups);
- }
-
+ len = legacy ? sizeof(*head) : sizeof(struct ceph_mds_request_head);
len += pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
sizeof(struct ceph_timespec);
+ len += sizeof(u32) + (sizeof(u64) * req->r_cred->group_info->ngroups);
/* calculate (max) length for cap releases */
len += sizeof(struct ceph_mds_request_release) *
msg->hdr.tid = cpu_to_le64(req->r_tid);
/*
- * The old ceph_mds_request_header didn't contain a version field, and
+ * The old ceph_mds_request_head didn't contain a version field, and
* one was added when we moved the message version from 3->4.
*/
if (legacy) {
head->num_releases = cpu_to_le16(releases);
- /* time stamp */
- {
- struct ceph_timespec ts;
- ceph_encode_timespec64(&ts, &req->r_stamp);
- ceph_encode_copy(&p, &ts, sizeof(ts));
- }
-
- /* gid list */
- if (!legacy) {
- ceph_encode_32(&p, req->r_cred->group_info->ngroups);
- for (i = 0; i < req->r_cred->group_info->ngroups; i++)
- ceph_encode_64(&p, from_kgid(&init_user_ns,
- req->r_cred->group_info->gid[i]));
- }
+ encode_timestamp_and_gids(&p, req);
if (WARN_ON_ONCE(p > end)) {
ceph_msg_put(msg);
/* remove cap/dentry releases from message */
rhead->num_releases = 0;
- /* time stamp */
p = msg->front.iov_base + req->r_request_release_offset;
- {
- struct ceph_timespec ts;
- ceph_encode_timespec64(&ts, &req->r_stamp);
- ceph_encode_copy(&p, &ts, sizeof(ts));
- }
+ encode_timestamp_and_gids(&p, req);
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
if (!ses->binding) {
ses->capabilities = server->capabilities;
- if (linuxExtEnabled == 0)
+ if (!linuxExtEnabled)
ses->capabilities &= (~server->vals->cap_unix);
if (ses->auth_key.response) {
vi = find_vol(fullpath);
spin_unlock(&vol_list_lock);
- kref_put(&vi->refcnt, vol_release);
+ if (!IS_ERR(vi))
+ kref_put(&vi->refcnt, vol_release);
}
/**
int
smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx)
{
- int rc = 0;
-
memcpy(new_ctx, ctx, sizeof(*ctx));
new_ctx->prepath = NULL;
new_ctx->mount_options = NULL;
DUP_CTX_STR(nodename);
DUP_CTX_STR(iocharset);
- return rc;
+ return 0;
}
static int
free_rsp_buf(resp_buftype, rsp);
/* retry close in a worker thread if this one is interrupted */
- if (rc == -EINTR) {
+ if (is_interrupt_error(rc)) {
int tmp_rc;
tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid,
__le16 TransformCount;
__u16 Reserved1;
__u32 Reserved2;
- __le16 RDMATransformIds[1];
+ __le16 RDMATransformIds[];
} __packed;
/* Signing algorithms */
}
return err;
}
-
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb)
-{
- struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
- int err = 0;
-
- ext4_superblock_csum_set(sb);
- if (ext4_handle_valid(handle)) {
- err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, line, __func__,
- bh, handle, err);
- } else
- mark_buffer_dirty(bh);
- return err;
-}
handle_t *handle, struct inode *inode,
struct buffer_head *bh);
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb);
-
#define ext4_journal_get_write_access(handle, bh) \
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
#define ext4_handle_dirty_metadata(handle, inode, bh) \
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
(bh))
-#define ext4_handle_dirty_super(handle, sb) \
- __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int blocks, int rsv_blocks,
trace_ext4_fc_track_range(inode, start, end, ret);
}
-static void ext4_fc_submit_bh(struct super_block *sb)
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
{
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))
+ /* Add REQ_FUA | REQ_PREFLUSH only its tail */
+ if (test_opt(sb, BARRIER) && is_tail)
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
set_buffer_dirty(bh);
*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
if (pad_len > 0)
ext4_fc_memzero(sb, tl + 1, pad_len, crc);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, false);
ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
if (ret)
tail.fc_crc = cpu_to_le32(crc);
ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, true);
return 0;
}
list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
&sbi->s_fc_dentry_q[FC_Q_MAIN]);
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
- &sbi->s_fc_q[FC_Q_STAGING]);
+ &sbi->s_fc_q[FC_Q_MAIN]);
ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
entry.len = darg.dname_len;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", darg.ino);
return 0;
}
old_parent = ext4_iget(sb, darg.parent_ino,
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(old_parent)) {
+ if (IS_ERR(old_parent)) {
jbd_debug(1, "Dir with inode %d not found", darg.parent_ino);
iput(inode);
return 0;
darg.parent_ino, darg.dname_len);
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (!IS_ERR_OR_NULL(inode)) {
+ if (!IS_ERR(inode)) {
ext4_ext_clear_bb(inode);
iput(inode);
}
+ inode = NULL;
ext4_fc_record_modified_inode(sb, ino);
/* Given that we just wrote the inode on disk, this SHOULD succeed. */
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return -EFSCORRUPTED;
}
goto out;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "inode %d not found.", darg.ino);
inode = NULL;
ret = -EINVAL;
* dot and dot dot dirents are setup properly.
*/
dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(dir)) {
+ if (IS_ERR(dir)) {
jbd_debug(1, "Dir %d not found.", darg.ino);
goto out;
}
inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
le32_to_cpu(lrange->fc_ino), cur, remaining);
inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
return 0;
}
for (i = 0; i < state->fc_modified_inodes_used; i++) {
inode = ext4_iget(sb, state->fc_modified_inodes[i],
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found.",
state->fc_modified_inodes[i]);
continue;
if (ret > 0) {
path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
- if (!IS_ERR_OR_NULL(path)) {
+ if (!IS_ERR(path)) {
for (j = 0; j < path->p_depth; j++)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 1);
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_journal;
- strlcpy(sbi->s_es->s_last_mounted, cp,
+ lock_buffer(sbi->s_sbh);
+ strncpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
out_journal:
ext4_journal_stop(handle);
out:
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_large_file(sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL,
+ EXT4_SB(sb)->s_sbh);
}
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
+ lock_buffer(sbi->s_sbh);
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
(le32_to_cpu(sbi->s_es->s_inodes_count))) {
/* Insert this inode at the head of the on-disk orphan list */
NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
dirty = true;
}
list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
mutex_unlock(&sbi->s_orphan_lock);
if (dirty) {
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
}
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ ext4_superblock_csum_set(inode->i_sb);
+ unlock_buffer(sbi->s_sbh);
mutex_unlock(&sbi->s_orphan_lock);
- err = ext4_handle_dirty_super(handle, inode->i_sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
return retval2;
}
}
- brelse(ent->bh);
- ent->bh = NULL;
-
return retval;
}
}
}
+ old_file_type = old.de->file_type;
if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
ext4_handle_sync(handle);
force_reread = (new.dir->i_ino == old.dir->i_ino &&
ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
- old_file_type = old.de->file_type;
if (whiteout) {
/*
* Do this before adding a new entry, so the old entry is sure
retval = 0;
end_rename:
- brelse(old.dir_bh);
- brelse(old.bh);
- brelse(new.bh);
if (whiteout) {
- if (retval)
+ if (retval) {
+ ext4_setent(handle, &old,
+ old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ }
unlock_new_inode(whiteout);
iput(whiteout);
+
}
+ brelse(old.dir_bh);
+ brelse(old.bh);
+ brelse(new.bh);
if (handle)
ext4_journal_stop(handle);
return retval;
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree_array_rcu(o_group_desc);
+ lock_buffer(EXT4_SB(sb)->s_sbh);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- err = ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
if (err)
ext4_std_error(sb, err);
return err;
reserved_blocks *= blocks_count;
do_div(reserved_blocks, 100);
+ lock_buffer(sbi->s_sbh);
ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
* active. */
ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
reserved_blocks);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeclusters_counter,
ext4_update_super(sb, flex_gd);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
exit_journal:
err2 = ext4_journal_stop(handle);
goto errout;
}
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_blocks_count_set(es, o_blocks_count + add);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
if (err)
goto errout;
- ext4_handle_dirty_super(handle, sb);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
errout:
if (err)
goto errout;
+ lock_buffer(sbi->s_sbh);
ext4_clear_feature_resize_inode(sb);
ext4_set_feature_meta_bg(sb);
sbi->s_es->s_first_meta_bg =
cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
if (err) {
ext4_std_error(sb, err);
goto errout;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
-static int ext4_commit_super(struct super_block *sb, int sync);
+static void ext4_update_super(struct super_block *sb);
+static int ext4_commit_super(struct super_block *sb);
static int ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_clear_journal_err(struct super_block *sb,
return EXT4_ERR_UNKNOWN;
}
-static void __save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
+static void save_error_info(struct super_block *sb, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- if (bdev_read_only(sb->s_bdev))
- return;
/* We default to EFSCORRUPTED error... */
if (error == 0)
error = EFSCORRUPTED;
spin_unlock(&sbi->s_error_lock);
}
-static void save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
-{
- __save_error_info(sb, error, ino, block, func, line);
- if (!bdev_read_only(sb->s_bdev))
- ext4_commit_super(sb, 1);
-}
-
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
* used to deal with unrecoverable failures such as journal IO errors or ENOMEM
* at a critical moment in log management.
*/
-static void ext4_handle_error(struct super_block *sb, bool force_ro)
+static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
+ bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT)))
+ if (!continue_fs && !sb_rdonly(sb)) {
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
+ if (journal)
+ jbd2_journal_abort(journal, -EIO);
+ }
+
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, error, ino, block, func, line);
+ /*
+ * In case the fs should keep running, we need to writeout
+ * superblock through the journal. Due to lock ordering
+ * constraints, it may not be safe to do it right here so we
+ * defer superblock flushing to a workqueue.
+ */
+ if (continue_fs)
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ else
+ ext4_commit_super(sb);
+ }
+
+ if (sb_rdonly(sb) || continue_fs)
return;
- ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
- if (journal)
- jbd2_journal_abort(journal, -EIO);
/*
* We force ERRORS_RO behavior when system is rebooting. Otherwise we
* could panic during 'reboot -f' as the underlying device got already
{
struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
s_error_work);
+ journal_t *journal = sbi->s_journal;
+ handle_t *handle;
- ext4_commit_super(sbi->s_sb, 1);
+ /*
+ * If the journal is still running, we have to write out superblock
+ * through the journal to avoid collisions of other journalled sb
+ * updates.
+ *
+ * We use directly jbd2 functions here to avoid recursing back into
+ * ext4 error handling code during handling of previous errors.
+ */
+ if (!sb_rdonly(sbi->s_sb) && journal) {
+ handle = jbd2_journal_start(journal, 1);
+ if (IS_ERR(handle))
+ goto write_directly;
+ if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ ext4_update_super(sbi->s_sb);
+ if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ jbd2_journal_stop(handle);
+ return;
+ }
+write_directly:
+ /*
+ * Write through journal failed. Write sb directly to get error info
+ * out and hope for the best.
+ */
+ ext4_commit_super(sbi->s_sb);
}
#define ext4_error_ratelimit(sb) \
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
- save_error_info(sb, error, 0, block, function, line);
- ext4_handle_error(sb, force_ro);
+ ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}
void __ext4_error_inode(struct inode *inode, const char *function,
current->comm, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, error, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb, false);
+ ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
+ function, line);
}
void __ext4_error_file(struct file *file, const char *function,
current->comm, path, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb, false);
+ ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
+ function, line);
}
const char *ext4_decode_error(struct super_block *sb, int errno,
sb->s_id, function, line, errstr);
}
- save_error_info(sb, -errno, 0, 0, function, line);
- ext4_handle_error(sb, false);
+ ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}
void __ext4_msg(struct super_block *sb,
if (test_opt(sb, ERRORS_CONT)) {
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- __save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
- schedule_work(&EXT4_SB(sb)->s_error_work);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, EFSCORRUPTED, ino, block, function,
+ line);
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ }
return;
}
ext4_unlock_group(sb, grp);
- save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
- ext4_handle_error(sb, false);
+ ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
if (!sb_rdonly(sb))
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
rcu_read_lock();
group_desc = rcu_dereference(sbi->s_group_desc);
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) &&
!ext4_has_feature_encrypt(sb)) {
ext4_set_feature_encrypt(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
/*
es->s_journal_dev = cpu_to_le32(journal_devnum);
/* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
return 0;
return err;
}
-static int ext4_commit_super(struct super_block *sb, int sync)
+/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */
+static void ext4_update_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
- int error = 0;
-
- if (!sbh || block_device_ejected(sb))
- return error;
+ struct ext4_super_block *es = sbi->s_es;
+ struct buffer_head *sbh = sbi->s_sbh;
+ lock_buffer(sbh);
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
if (!(sb->s_flags & SB_RDONLY))
ext4_update_tstamp(es, s_wtime);
es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+ cpu_to_le64(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
+ sbi->s_sectors_written_start) >> 1));
+ if (percpu_counter_initialized(&sbi->s_freeclusters_counter))
ext4_free_blocks_count_set(es,
- EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeclusters_counter)));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
+ EXT4_C2B(sbi, percpu_counter_sum_positive(
+ &sbi->s_freeclusters_counter)));
+ if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeinodes_counter));
+ &sbi->s_freeinodes_counter));
/* Copy error information to the on-disk superblock */
spin_lock(&sbi->s_error_lock);
if (sbi->s_add_error_count > 0) {
}
spin_unlock(&sbi->s_error_lock);
- BUFFER_TRACE(sbh, "marking dirty");
ext4_superblock_csum_set(sb);
- if (sync)
- lock_buffer(sbh);
+ unlock_buffer(sbh);
+}
+
+static int ext4_commit_super(struct super_block *sb)
+{
+ struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+ int error = 0;
+
+ if (!sbh || block_device_ejected(sb))
+ return error;
+
+ ext4_update_super(sb);
+
if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
/*
* Oh, dear. A previous attempt to write the
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
+ BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
- if (sync) {
- unlock_buffer(sbh);
- error = __sync_dirty_buffer(sbh,
- REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
- if (buffer_write_io_error(sbh)) {
- ext4_msg(sb, KERN_ERR, "I/O error while writing "
- "superblock");
- clear_buffer_write_io_error(sbh);
- set_buffer_uptodate(sbh);
- }
+ error = __sync_dirty_buffer(sbh,
+ REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
+ if (buffer_write_io_error(sbh)) {
+ ext4_msg(sb, KERN_ERR, "I/O error while writing "
+ "superblock");
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
}
return error;
}
if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
ext4_clear_feature_journal_needs_recovery(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
out:
jbd2_journal_unlock_updates(journal);
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
jbd2_journal_clear_err(journal);
jbd2_journal_update_sb_errno(journal);
ext4_clear_feature_journal_needs_recovery(sb);
}
- error = ext4_commit_super(sb, 1);
+ error = ext4_commit_super(sb);
out:
if (journal)
/* we rely on upper layer to stop further updates */
ext4_set_feature_journal_needs_recovery(sb);
}
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
return 0;
}
}
if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
if (err)
goto restore_opts;
}
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_xattr(sb);
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
}
}
#include <linux/rcupdate.h>
#include <linux/close_range.h>
#include <net/sock.h>
-#include <linux/io_uring.h>
unsigned int sysctl_nr_open __read_mostly = 1024*1024;
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
struct files_struct * files = tsk->files;
if (files) {
- io_uring_files_cancel(files);
task_lock(tsk);
tsk->files = NULL;
task_unlock(tsk);
unsigned int drain_next: 1;
unsigned int eventfd_async: 1;
unsigned int restricted: 1;
+ unsigned int sqo_dead: 1;
/*
* Ring buffer of indices into array of io_uring_sqe, which is
unsigned cq_entries;
unsigned cq_mask;
atomic_t cq_timeouts;
+ unsigned cq_last_tm_flush;
unsigned long cq_check_overflow;
struct wait_queue_head cq_wait;
struct fasync_struct *cq_fasync;
ACCT_PINNED,
};
+static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
+ struct task_struct *task);
+
+static void destroy_fixed_file_ref_node(struct fixed_file_ref_node *ref_node);
+static struct fixed_file_ref_node *alloc_fixed_file_ref_node(
+ struct io_ring_ctx *ctx);
+
static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
struct io_comp_state *cs);
static void io_cqring_fill_event(struct io_kiocb *req, long res);
static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
{
+ if (current->flags & PF_EXITING)
+ return -EFAULT;
+
if (!current->files) {
struct files_struct *files;
struct nsproxy *nsproxy;
{
struct mm_struct *mm;
+ if (current->flags & PF_EXITING)
+ return -EFAULT;
if (current->mm)
return 0;
/* order cqe stores with ring update */
smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
-
- if (wq_has_sleeper(&ctx->cq_wait)) {
- wake_up_interruptible(&ctx->cq_wait);
- kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
- }
}
static void io_put_identity(struct io_uring_task *tctx, struct io_kiocb *req)
spin_unlock_irq(&ctx->inflight_lock);
req->work.flags |= IO_WQ_WORK_FILES;
}
+ if (!(req->work.flags & IO_WQ_WORK_MM) &&
+ (def->work_flags & IO_WQ_WORK_MM)) {
+ if (id->mm != current->mm)
+ return false;
+ mmgrab(id->mm);
+ req->work.flags |= IO_WQ_WORK_MM;
+ }
return true;
}
{
const struct io_op_def *def = &io_op_defs[req->opcode];
struct io_ring_ctx *ctx = req->ctx;
- struct io_identity *id;
io_req_init_async(req);
- id = req->work.identity;
if (req->flags & REQ_F_FORCE_ASYNC)
req->work.flags |= IO_WQ_WORK_CONCURRENT;
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
- /* ->mm can never change on us */
- if (!(req->work.flags & IO_WQ_WORK_MM) &&
- (def->work_flags & IO_WQ_WORK_MM)) {
- mmgrab(id->mm);
- req->work.flags |= IO_WQ_WORK_MM;
- }
-
/* if we fail grabbing identity, we must COW, regrab, and retry */
if (io_grab_identity(req))
return;
static void io_flush_timeouts(struct io_ring_ctx *ctx)
{
- while (!list_empty(&ctx->timeout_list)) {
+ u32 seq;
+
+ if (list_empty(&ctx->timeout_list))
+ return;
+
+ seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+
+ do {
+ u32 events_needed, events_got;
struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
struct io_kiocb, timeout.list);
if (io_is_timeout_noseq(req))
break;
- if (req->timeout.target_seq != ctx->cached_cq_tail
- - atomic_read(&ctx->cq_timeouts))
+
+ /*
+ * Since seq can easily wrap around over time, subtract
+ * the last seq at which timeouts were flushed before comparing.
+ * Assuming not more than 2^31-1 events have happened since,
+ * these subtractions won't have wrapped, so we can check if
+ * target is in [last_seq, current_seq] by comparing the two.
+ */
+ events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
+ events_got = seq - ctx->cq_last_tm_flush;
+ if (events_got < events_needed)
break;
list_del_init(&req->timeout.list);
io_kill_timeout(req);
- }
+ } while (!list_empty(&ctx->timeout_list));
+
+ ctx->cq_last_tm_flush = seq;
}
static void io_commit_cqring(struct io_ring_ctx *ctx)
static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
+ /* see waitqueue_active() comment */
+ smp_mb();
+
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait))
wake_up(&ctx->sq_data->wait);
if (io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
+ if (waitqueue_active(&ctx->cq_wait)) {
+ wake_up_interruptible(&ctx->cq_wait);
+ kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+ }
+}
+
+static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
+{
+ /* see waitqueue_active() comment */
+ smp_mb();
+
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
+ if (waitqueue_active(&ctx->wait))
+ wake_up(&ctx->wait);
+ }
+ if (io_should_trigger_evfd(ctx))
+ eventfd_signal(ctx->cq_ev_fd, 1);
+ if (waitqueue_active(&ctx->cq_wait)) {
+ wake_up_interruptible(&ctx->cq_wait);
+ kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+ }
}
/* Returns true if there are no backlogged entries after the flush */
-static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
- struct task_struct *tsk,
- struct files_struct *files)
+static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
+ struct task_struct *tsk,
+ struct files_struct *files)
{
struct io_rings *rings = ctx->rings;
struct io_kiocb *req, *tmp;
return all_flushed;
}
+static void io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
+ struct task_struct *tsk,
+ struct files_struct *files)
+{
+ if (test_bit(0, &ctx->cq_check_overflow)) {
+ /* iopoll syncs against uring_lock, not completion_lock */
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_lock(&ctx->uring_lock);
+ __io_cqring_overflow_flush(ctx, force, tsk, files);
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_unlock(&ctx->uring_lock);
+ }
+}
+
static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
{
struct io_ring_ctx *ctx = req->ctx;
{
struct io_ring_ctx *ctx = req->ctx;
- if (!__io_sq_thread_acquire_mm(ctx) &&
- !__io_sq_thread_acquire_files(ctx)) {
- mutex_lock(&ctx->uring_lock);
+ mutex_lock(&ctx->uring_lock);
+ if (!ctx->sqo_dead &&
+ !__io_sq_thread_acquire_mm(ctx) &&
+ !__io_sq_thread_acquire_files(ctx))
__io_queue_sqe(req, NULL);
- mutex_unlock(&ctx->uring_lock);
- } else {
+ else
__io_req_task_cancel(req, -EFAULT);
- }
+ mutex_unlock(&ctx->uring_lock);
}
static void io_req_task_submit(struct callback_head *cb)
io_free_req(req);
}
-static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
+static unsigned io_cqring_events(struct io_ring_ctx *ctx)
{
- if (test_bit(0, &ctx->cq_check_overflow)) {
- /*
- * noflush == true is from the waitqueue handler, just ensure
- * we wake up the task, and the next invocation will flush the
- * entries. We cannot safely to it from here.
- */
- if (noflush)
- return -1U;
-
- io_cqring_overflow_flush(ctx, false, NULL, NULL);
- }
-
/* See comment at the top of this file */
smp_rmb();
return __io_cqring_events(ctx);
}
io_commit_cqring(ctx);
- if (ctx->flags & IORING_SETUP_SQPOLL)
- io_cqring_ev_posted(ctx);
+ io_cqring_ev_posted_iopoll(ctx);
io_req_free_batch_finish(ctx, &rb);
if (!list_empty(&again))
* If we do, we can potentially be spinning for commands that
* already triggered a CQE (eg in error).
*/
- if (io_cqring_events(ctx, false))
+ if (test_bit(0, &ctx->cq_check_overflow))
+ __io_cqring_overflow_flush(ctx, false, NULL, NULL);
+ if (io_cqring_events(ctx))
break;
/*
if ((res != -EAGAIN && res != -EOPNOTSUPP) || io_wq_current_is_worker())
return false;
+ lockdep_assert_held(&req->ctx->uring_lock);
+
ret = io_sq_thread_acquire_mm_files(req->ctx, req);
if (io_resubmit_prep(req, ret)) {
tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
req->timeout.target_seq = tail + off;
+ /* Update the last seq here in case io_flush_timeouts() hasn't.
+ * This is safe because ->completion_lock is held, and submissions
+ * and completions are never mixed in the same ->completion_lock section.
+ */
+ ctx->cq_last_tm_flush = tail;
+
/*
* Insertion sort, ensuring the first entry in the list is always
* the one we need first.
/* if we have a backlog and couldn't flush it all, return BUSY */
if (test_bit(0, &ctx->sq_check_overflow)) {
- if (!io_cqring_overflow_flush(ctx, false, NULL, NULL))
+ if (!__io_cqring_overflow_flush(ctx, false, NULL, NULL))
return -EBUSY;
}
if (!list_empty(&ctx->iopoll_list))
io_do_iopoll(ctx, &nr_events, 0);
- if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)))
+ if (to_submit && !ctx->sqo_dead &&
+ likely(!percpu_ref_is_dying(&ctx->refs)))
ret = io_submit_sqes(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
}
if (sqt_spin || !time_after(jiffies, timeout)) {
io_run_task_work();
+ io_sq_thread_drop_mm_files();
cond_resched();
if (sqt_spin)
timeout = jiffies + sqd->sq_thread_idle;
}
io_run_task_work();
+ io_sq_thread_drop_mm_files();
if (cur_css)
io_sq_thread_unassociate_blkcg();
unsigned nr_timeouts;
};
-static inline bool io_should_wake(struct io_wait_queue *iowq, bool noflush)
+static inline bool io_should_wake(struct io_wait_queue *iowq)
{
struct io_ring_ctx *ctx = iowq->ctx;
* started waiting. For timeouts, we always want to return to userspace,
* regardless of event count.
*/
- return io_cqring_events(ctx, noflush) >= iowq->to_wait ||
+ return io_cqring_events(ctx) >= iowq->to_wait ||
atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
}
struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
wq);
- /* use noflush == true, as we can't safely rely on locking context */
- if (!io_should_wake(iowq, true))
- return -1;
-
- return autoremove_wake_function(curr, mode, wake_flags, key);
+ /*
+ * Cannot safely flush overflowed CQEs from here, ensure we wake up
+ * the task, and the next invocation will do it.
+ */
+ if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow))
+ return autoremove_wake_function(curr, mode, wake_flags, key);
+ return -1;
}
static int io_run_task_work_sig(void)
int ret = 0;
do {
- if (io_cqring_events(ctx, false) >= min_events)
+ io_cqring_overflow_flush(ctx, false, NULL, NULL);
+ if (io_cqring_events(ctx) >= min_events)
return 0;
if (!io_run_task_work())
break;
iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
trace_io_uring_cqring_wait(ctx, min_events);
do {
+ io_cqring_overflow_flush(ctx, false, NULL, NULL);
prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
TASK_INTERRUPTIBLE);
/* make sure we run task_work before checking for signals */
continue;
else if (ret < 0)
break;
- if (io_should_wake(&iowq, false))
+ if (io_should_wake(&iowq))
break;
+ if (test_bit(0, &ctx->cq_check_overflow))
+ continue;
if (uts) {
timeout = schedule_timeout(timeout);
if (timeout == 0) {
complete(&data->done);
}
+static void io_sqe_files_set_node(struct fixed_file_data *file_data,
+ struct fixed_file_ref_node *ref_node)
+{
+ spin_lock_bh(&file_data->lock);
+ file_data->node = ref_node;
+ list_add_tail(&ref_node->node, &file_data->ref_list);
+ spin_unlock_bh(&file_data->lock);
+ percpu_ref_get(&file_data->refs);
+}
+
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
struct fixed_file_data *data = ctx->file_data;
- struct fixed_file_ref_node *ref_node = NULL;
+ struct fixed_file_ref_node *backup_node, *ref_node = NULL;
unsigned nr_tables, i;
+ int ret;
if (!data)
return -ENXIO;
+ backup_node = alloc_fixed_file_ref_node(ctx);
+ if (!backup_node)
+ return -ENOMEM;
spin_lock_bh(&data->lock);
ref_node = data->node;
/* wait for all refs nodes to complete */
flush_delayed_work(&ctx->file_put_work);
- wait_for_completion(&data->done);
+ do {
+ ret = wait_for_completion_interruptible(&data->done);
+ if (!ret)
+ break;
+ ret = io_run_task_work_sig();
+ if (ret < 0) {
+ percpu_ref_resurrect(&data->refs);
+ reinit_completion(&data->done);
+ io_sqe_files_set_node(data, backup_node);
+ return ret;
+ }
+ } while (1);
__io_sqe_files_unregister(ctx);
nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
kfree(data);
ctx->file_data = NULL;
ctx->nr_user_files = 0;
+ destroy_fixed_file_ref_node(backup_node);
return 0;
}
ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL);
if (!ref_node)
- return ERR_PTR(-ENOMEM);
+ return NULL;
if (percpu_ref_init(&ref_node->refs, io_file_data_ref_zero,
0, GFP_KERNEL)) {
kfree(ref_node);
- return ERR_PTR(-ENOMEM);
+ return NULL;
}
INIT_LIST_HEAD(&ref_node->node);
INIT_LIST_HEAD(&ref_node->file_list);
}
ref_node = alloc_fixed_file_ref_node(ctx);
- if (IS_ERR(ref_node)) {
+ if (!ref_node) {
io_sqe_files_unregister(ctx);
- return PTR_ERR(ref_node);
+ return -ENOMEM;
}
- file_data->node = ref_node;
- spin_lock_bh(&file_data->lock);
- list_add_tail(&ref_node->node, &file_data->ref_list);
- spin_unlock_bh(&file_data->lock);
- percpu_ref_get(&file_data->refs);
+ io_sqe_files_set_node(file_data, ref_node);
return ret;
out_fput:
for (i = 0; i < ctx->nr_user_files; i++) {
return -EINVAL;
ref_node = alloc_fixed_file_ref_node(ctx);
- if (IS_ERR(ref_node))
- return PTR_ERR(ref_node);
+ if (!ref_node)
+ return -ENOMEM;
done = 0;
fds = u64_to_user_ptr(up->fds);
if (needs_switch) {
percpu_ref_kill(&data->node->refs);
- spin_lock_bh(&data->lock);
- list_add_tail(&ref_node->node, &data->ref_list);
- data->node = ref_node;
- spin_unlock_bh(&data->lock);
- percpu_ref_get(&ctx->file_data->refs);
+ io_sqe_files_set_node(data, ref_node);
} else
destroy_fixed_file_ref_node(ref_node);
smp_rmb();
if (!io_sqring_full(ctx))
mask |= EPOLLOUT | EPOLLWRNORM;
- if (io_cqring_events(ctx, false))
+ io_cqring_overflow_flush(ctx, false, NULL, NULL);
+ if (io_cqring_events(ctx))
mask |= EPOLLIN | EPOLLRDNORM;
return mask;
* as nobody else will be looking for them.
*/
do {
- io_iopoll_try_reap_events(ctx);
+ __io_uring_cancel_task_requests(ctx, NULL);
} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
io_ring_ctx_free(ctx);
}
{
mutex_lock(&ctx->uring_lock);
percpu_ref_kill(&ctx->refs);
+
+ if (WARN_ON_ONCE((ctx->flags & IORING_SETUP_SQPOLL) && !ctx->sqo_dead))
+ ctx->sqo_dead = 1;
+
/* if force is set, the ring is going away. always drop after that */
ctx->cq_overflow_flushed = 1;
if (ctx->rings)
- io_cqring_overflow_flush(ctx, true, NULL, NULL);
+ __io_cqring_overflow_flush(ctx, true, NULL, NULL);
mutex_unlock(&ctx->uring_lock);
io_kill_timeouts(ctx, NULL, NULL);
enum io_wq_cancel cret;
bool ret = false;
- cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true);
- if (cret != IO_WQ_CANCEL_NOTFOUND)
- ret = true;
+ if (ctx->io_wq) {
+ cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb,
+ &cancel, true);
+ ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
+ }
/* SQPOLL thread does its own polling */
if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
}
}
+static void io_disable_sqo_submit(struct io_ring_ctx *ctx)
+{
+ WARN_ON_ONCE(ctx->sqo_task != current);
+
+ mutex_lock(&ctx->uring_lock);
+ ctx->sqo_dead = 1;
+ mutex_unlock(&ctx->uring_lock);
+
+ /* make sure callers enter the ring to get error */
+ if (ctx->rings)
+ io_ring_set_wakeup_flag(ctx);
+}
+
/*
* We need to iteratively cancel requests, in case a request has dependent
* hard links. These persist even for failure of cancelations, hence keep
struct task_struct *task = current;
if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
+ /* for SQPOLL only sqo_task has task notes */
+ io_disable_sqo_submit(ctx);
task = ctx->sq_data->thread;
atomic_inc(&task->io_uring->in_idle);
io_sq_thread_park(ctx->sq_data);
}
io_cancel_defer_files(ctx, task, files);
- io_ring_submit_lock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
io_cqring_overflow_flush(ctx, true, task, files);
- io_ring_submit_unlock(ctx, (ctx->flags & IORING_SETUP_IOPOLL));
if (!files)
__io_uring_cancel_task_requests(ctx, task);
fput(file);
}
-/*
- * Drop task note for this file if we're the only ones that hold it after
- * pending fput()
- */
-static void io_uring_attempt_task_drop(struct file *file)
+static void io_uring_remove_task_files(struct io_uring_task *tctx)
{
- if (!current->io_uring)
- return;
- /*
- * fput() is pending, will be 2 if the only other ref is our potential
- * task file note. If the task is exiting, drop regardless of count.
- */
- if (fatal_signal_pending(current) || (current->flags & PF_EXITING) ||
- atomic_long_read(&file->f_count) == 2)
+ struct file *file;
+ unsigned long index;
+
+ xa_for_each(&tctx->xa, index, file)
io_uring_del_task_file(file);
}
/* make sure overflow events are dropped */
atomic_inc(&tctx->in_idle);
-
- xa_for_each(&tctx->xa, index, file) {
- struct io_ring_ctx *ctx = file->private_data;
-
- io_uring_cancel_task_requests(ctx, files);
- if (files)
- io_uring_del_task_file(file);
- }
-
+ xa_for_each(&tctx->xa, index, file)
+ io_uring_cancel_task_requests(file->private_data, files);
atomic_dec(&tctx->in_idle);
+
+ if (files)
+ io_uring_remove_task_files(tctx);
}
static s64 tctx_inflight(struct io_uring_task *tctx)
finish_wait(&tctx->wait, &wait);
} while (1);
+ finish_wait(&tctx->wait, &wait);
atomic_dec(&tctx->in_idle);
+
+ io_uring_remove_task_files(tctx);
}
static int io_uring_flush(struct file *file, void *data)
{
- io_uring_attempt_task_drop(file);
+ struct io_uring_task *tctx = current->io_uring;
+ struct io_ring_ctx *ctx = file->private_data;
+
+ if (!tctx)
+ return 0;
+
+ /* we should have cancelled and erased it before PF_EXITING */
+ WARN_ON_ONCE((current->flags & PF_EXITING) &&
+ xa_load(&tctx->xa, (unsigned long)file));
+
+ /*
+ * fput() is pending, will be 2 if the only other ref is our potential
+ * task file note. If the task is exiting, drop regardless of count.
+ */
+ if (atomic_long_read(&file->f_count) != 2)
+ return 0;
+
+ if (ctx->flags & IORING_SETUP_SQPOLL) {
+ /* there is only one file note, which is owned by sqo_task */
+ WARN_ON_ONCE((ctx->sqo_task == current) ==
+ !xa_load(&tctx->xa, (unsigned long)file));
+
+ io_disable_sqo_submit(ctx);
+ }
+
+ if (!(ctx->flags & IORING_SETUP_SQPOLL) || ctx->sqo_task == current)
+ io_uring_del_task_file(file);
return 0;
}
#endif /* !CONFIG_MMU */
-static void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
+static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
{
+ int ret = 0;
DEFINE_WAIT(wait);
do {
prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);
+ if (unlikely(ctx->sqo_dead)) {
+ ret = -EOWNERDEAD;
+ goto out;
+ }
+
if (!io_sqring_full(ctx))
break;
} while (!signal_pending(current));
finish_wait(&ctx->sqo_sq_wait, &wait);
+out:
+ return ret;
}
static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
*/
ret = 0;
if (ctx->flags & IORING_SETUP_SQPOLL) {
- if (!list_empty_careful(&ctx->cq_overflow_list)) {
- bool needs_lock = ctx->flags & IORING_SETUP_IOPOLL;
+ io_cqring_overflow_flush(ctx, false, NULL, NULL);
- io_ring_submit_lock(ctx, needs_lock);
- io_cqring_overflow_flush(ctx, false, NULL, NULL);
- io_ring_submit_unlock(ctx, needs_lock);
- }
+ ret = -EOWNERDEAD;
+ if (unlikely(ctx->sqo_dead))
+ goto out;
if (flags & IORING_ENTER_SQ_WAKEUP)
wake_up(&ctx->sq_data->wait);
- if (flags & IORING_ENTER_SQ_WAIT)
- io_sqpoll_wait_sq(ctx);
+ if (flags & IORING_ENTER_SQ_WAIT) {
+ ret = io_sqpoll_wait_sq(ctx);
+ if (ret)
+ goto out;
+ }
submitted = to_submit;
} else if (to_submit) {
ret = io_uring_add_task_file(ctx, f.file);
*/
ret = io_uring_install_fd(ctx, file);
if (ret < 0) {
+ io_disable_sqo_submit(ctx);
/* fput will clean it up */
fput(file);
return ret;
trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
+ io_disable_sqo_submit(ctx);
io_ring_ctx_wait_and_kill(ctx);
return ret;
}
{
struct mount *mnt = real_mount(path->mnt);
- if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
- return -EINVAL;
if (!may_mount())
return -EPERM;
if (path->dentry != path->mnt->mnt_root)
return 0;
}
+// caller is responsible for flags being sane
int path_umount(struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
struct path path;
int ret;
+ // basic validity checks done first
+ if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
+ return -EINVAL;
+
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
ret = user_path_at(AT_FDCWD, name, lookup_flags, &path);
const struct nfs_fh *fhandle)
{
struct nfs_delegation *delegation;
- struct inode *freeme, *res = NULL;
+ struct super_block *freeme = NULL;
+ struct inode *res = NULL;
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
spin_lock(&delegation->lock);
if (delegation->inode != NULL &&
!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
- freeme = igrab(delegation->inode);
- if (freeme && nfs_sb_active(freeme->i_sb))
- res = freeme;
+ if (nfs_sb_active(server->super)) {
+ freeme = server->super;
+ res = igrab(delegation->inode);
+ }
spin_unlock(&delegation->lock);
if (res != NULL)
return res;
if (freeme) {
rcu_read_unlock();
- iput(freeme);
+ nfs_sb_deactive(freeme);
rcu_read_lock();
}
return ERR_PTR(-EAGAIN);
} clone_data;
};
-#define nfs_errorf(fc, fmt, ...) errorf(fc, fmt, ## __VA_ARGS__)
-#define nfs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
-#define nfs_warnf(fc, fmt, ...) warnf(fc, fmt, ## __VA_ARGS__)
+#define nfs_errorf(fc, fmt, ...) ((fc)->log.log ? \
+ errorf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dprintk(fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_ferrorf(fc, fac, fmt, ...) ((fc)->log.log ? \
+ errorf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_invalf(fc, fmt, ...) ((fc)->log.log ? \
+ invalf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dprintk(fmt "\n", ## __VA_ARGS__); -EINVAL; }))
+
+#define nfs_finvalf(fc, fac, fmt, ...) ((fc)->log.log ? \
+ invalf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); -EINVAL; }))
+
+#define nfs_warnf(fc, fmt, ...) ((fc)->log.log ? \
+ warnf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dprintk(fmt "\n", ## __VA_ARGS__); }))
+
+#define nfs_fwarnf(fc, fac, fmt, ...) ((fc)->log.log ? \
+ warnf(fc, fmt, ## __VA_ARGS__) : \
+ ({ dfprintk(fac, fmt "\n", ## __VA_ARGS__); }))
static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc)
{
static inline struct inode *nfs_igrab_and_active(struct inode *inode)
{
- inode = igrab(inode);
- if (inode != NULL && !nfs_sb_active(inode->i_sb)) {
- iput(inode);
- inode = NULL;
+ struct super_block *sb = inode->i_sb;
+
+ if (sb && nfs_sb_active(sb)) {
+ if (igrab(inode))
+ return inode;
+ nfs_sb_deactive(sb);
}
- return inode;
+ return NULL;
}
static inline void nfs_iput_and_deactive(struct inode *inode)
trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (pnfs_roc_done(task, calldata->inode,
- &calldata->arg.lr_args,
- &calldata->res.lr_res,
- &calldata->res.lr_ret) == -EAGAIN)
+ if (pnfs_roc_done(task, &calldata->arg.lr_args, &calldata->res.lr_res,
+ &calldata->res.lr_ret) == -EAGAIN)
goto out_restart;
/* hmm. we are done with the inode, and in the process of freeing
trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
/* Handle Layoutreturn errors */
- if (pnfs_roc_done(task, data->inode,
- &data->args.lr_args,
- &data->res.lr_res,
- &data->res.lr_ret) == -EAGAIN)
+ if (pnfs_roc_done(task, &data->args.lr_args, &data->res.lr_res,
+ &data->res.lr_ret) == -EAGAIN)
goto out_restart;
switch (task->tk_status) {
struct nfs4_delegreturndata *data = calldata;
struct inode *inode = data->inode;
+ if (data->lr.roc)
+ pnfs_roc_release(&data->lr.arg, &data->lr.res,
+ data->res.lr_ret);
if (inode) {
- if (data->lr.roc)
- pnfs_roc_release(&data->lr.arg, &data->lr.res,
- data->res.lr_ret);
nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
nfs_iput_and_deactive(inode);
}
nfs_fattr_init(data->res.fattr);
data->timestamp = jiffies;
data->rpc_status = 0;
- data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, cred);
data->inode = nfs_igrab_and_active(inode);
- if (data->inode) {
+ if (data->inode || issync) {
+ data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res,
+ cred);
if (data->lr.roc) {
data->args.lr_args = &data->lr.arg;
data->res.lr_res = &data->lr.res;
}
- } else if (data->lr.roc) {
- pnfs_roc_release(&data->lr.arg, &data->lr.res, 0);
- data->lr.roc = false;
}
task_setup_data.callback_data = data;
data->arg.new_lock_owner, ret);
} else
data->cancelled = true;
+ trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
rpc_put_task(task);
dprintk("%s: done, ret = %d!\n", __func__, ret);
- trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
return ret;
}
fc, ctx->nfs_server.hostname,
ctx->nfs_server.export_path);
if (err) {
- nfs_errorf(fc, "NFS4: Couldn't follow remote path");
+ nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path");
dfprintk(MOUNT, "<-- nfs4_try_get_tree() = %d [error]\n", err);
} else {
dfprintk(MOUNT, "<-- nfs4_try_get_tree() = 0\n");
fc, ctx->nfs_server.hostname,
ctx->nfs_server.export_path);
if (err) {
- nfs_errorf(fc, "NFS4: Couldn't follow remote path");
+ nfs_ferrorf(fc, MOUNT, "NFS4: Couldn't follow remote path");
dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = %d [error]\n", err);
} else {
dfprintk(MOUNT, "<-- nfs4_get_referral_tree() = 0\n");
LIST_HEAD(freeme);
spin_lock(&inode->i_lock);
- if (!pnfs_layout_is_valid(lo) || !arg_stateid ||
+ if (!pnfs_layout_is_valid(lo) ||
!nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
goto out_unlock;
if (stateid) {
return false;
}
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
- struct nfs4_layoutreturn_args **argpp,
- struct nfs4_layoutreturn_res **respp,
- int *ret)
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret)
{
struct nfs4_layoutreturn_args *arg = *argpp;
int retval = -EAGAIN;
return 0;
case -NFS4ERR_OLD_STATEID:
if (!nfs4_layout_refresh_old_stateid(&arg->stateid,
- &arg->range, inode))
+ &arg->range, arg->inode))
break;
*ret = -NFS4ERR_NOMATCHING_LAYOUT;
return -EAGAIN;
int ret)
{
struct pnfs_layout_hdr *lo = args->layout;
- const nfs4_stateid *arg_stateid = NULL;
+ struct inode *inode = args->inode;
const nfs4_stateid *res_stateid = NULL;
struct nfs4_xdr_opaque_data *ld_private = args->ld_private;
switch (ret) {
case -NFS4ERR_NOMATCHING_LAYOUT:
+ spin_lock(&inode->i_lock);
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&args->stateid, &lo->plh_stateid))
+ pnfs_set_plh_return_info(lo, args->range.iomode, 0);
+ pnfs_clear_layoutreturn_waitbit(lo);
+ spin_unlock(&inode->i_lock);
break;
case 0:
if (res->lrs_present)
res_stateid = &res->stateid;
fallthrough;
default:
- arg_stateid = &args->stateid;
+ pnfs_layoutreturn_free_lsegs(lo, &args->stateid, &args->range,
+ res_stateid);
}
trace_nfs4_layoutreturn_on_close(args->inode, &args->stateid, ret);
- pnfs_layoutreturn_free_lsegs(lo, arg_stateid, &args->range,
- res_stateid);
if (ld_private && ld_private->ops && ld_private->ops->free)
ld_private->ops->free(ld_private);
pnfs_put_layout_hdr(lo);
goto lookup_again;
}
+ /*
+ * Because we free lsegs when sending LAYOUTRETURN, we need to wait
+ * for LAYOUTRETURN.
+ */
+ if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
+ spin_unlock(&ino->i_lock);
+ dprintk("%s wait for layoutreturn\n", __func__);
+ lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
+ if (!IS_ERR(lseg)) {
+ pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg,
+ PNFS_UPDATE_LAYOUT_RETRY);
+ goto lookup_again;
+ }
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_RETURN);
+ goto out_put_layout_hdr;
+ }
+
lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
if (lseg) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
}
- /*
- * Because we free lsegs before sending LAYOUTRETURN, we need to wait
- * for LAYOUTRETURN even if first is true.
- */
- if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
- spin_unlock(&ino->i_lock);
- dprintk("%s wait for layoutreturn\n", __func__);
- lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo));
- if (!IS_ERR(lseg)) {
- if (first)
- pnfs_clear_first_layoutget(lo);
- pnfs_put_layout_hdr(lo);
- dprintk("%s retrying\n", __func__);
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
- lseg, PNFS_UPDATE_LAYOUT_RETRY);
- goto lookup_again;
- }
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_RETURN);
- goto out_put_layout_hdr;
- }
-
if (pnfs_layoutgets_blocked(lo)) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BLOCKED);
&rng, GFP_KERNEL);
if (!lgp) {
pnfs_clear_first_layoutget(lo);
+ nfs_layoutget_end(lo);
pnfs_put_layout_hdr(lo);
return;
}
struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
const struct cred *cred);
-int pnfs_roc_done(struct rpc_task *task, struct inode *inode,
- struct nfs4_layoutreturn_args **argpp,
- struct nfs4_layoutreturn_res **respp,
- int *ret);
+int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp,
+ struct nfs4_layoutreturn_res **respp, int *ret);
void pnfs_roc_release(struct nfs4_layoutreturn_args *args,
struct nfs4_layoutreturn_res *res,
int ret);
}
static inline int
-pnfs_roc_done(struct rpc_task *task, struct inode *inode,
+pnfs_roc_done(struct rpc_task *task,
struct nfs4_layoutreturn_args **argpp,
struct nfs4_layoutreturn_res **respp,
int *ret)
pnfs_generic_clear_request_commit(struct nfs_page *req,
struct nfs_commit_info *cinfo)
{
- struct pnfs_layout_segment *freeme = NULL;
+ struct pnfs_commit_bucket *bucket = NULL;
if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
goto out;
cinfo->ds->nwritten--;
- if (list_is_singular(&req->wb_list)) {
- struct pnfs_commit_bucket *bucket;
-
+ if (list_is_singular(&req->wb_list))
bucket = list_first_entry(&req->wb_list,
- struct pnfs_commit_bucket,
- written);
- freeme = pnfs_free_bucket_lseg(bucket);
- }
+ struct pnfs_commit_bucket, written);
out:
nfs_request_remove_commit_list(req, cinfo);
- pnfs_put_lseg(freeme);
+ if (bucket)
+ pnfs_put_lseg(pnfs_free_bucket_lseg(bucket));
}
EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);
struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo)
{
+ struct pnfs_layout_segment *lseg;
struct list_head *pos;
list_for_each(pos, &bucket->committing)
cinfo->ds->ncommitting--;
list_splice_init(&bucket->committing, head);
- return pnfs_free_bucket_lseg(bucket);
+ lseg = pnfs_free_bucket_lseg(bucket);
+ if (!lseg)
+ lseg = pnfs_get_lseg(bucket->lseg);
+ return lseg;
}
static struct nfs_commit_data *
if (!data)
return NULL;
data->lseg = pnfs_bucket_get_committing(&data->pages, bucket, cinfo);
- if (!data->lseg)
- data->lseg = pnfs_get_lseg(bucket->lseg);
return data;
}
if (isdotent(name, namlen)) {
if (namlen == 2) {
dchild = dget_parent(dparent);
- /* filesystem root - cannot return filehandle for ".." */
+ /*
+ * Don't return filehandle for ".." if we're at
+ * the filesystem or export root:
+ */
if (dchild == dparent)
goto out;
+ if (dparent == exp->ex_path.dentry)
+ goto out;
} else
dchild = dget(dparent);
} else
#include "pnfs.h"
#include "trace.h"
+static bool inter_copy_offload_enable;
+module_param(inter_copy_offload_enable, bool, 0644);
+MODULE_PARM_DESC(inter_copy_offload_enable,
+ "Enable inter server to server copy offload. Default: false");
+
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
#include <linux/security.h>
return p;
}
+static void *
+svcxdr_savemem(struct nfsd4_compoundargs *argp, __be32 *p, u32 len)
+{
+ __be32 *tmp;
+
+ /*
+ * The location of the decoded data item is stable,
+ * so @p is OK to use. This is the common case.
+ */
+ if (p != argp->xdr->scratch.iov_base)
+ return p;
+
+ tmp = svcxdr_tmpalloc(argp, len);
+ if (!tmp)
+ return NULL;
+ memcpy(tmp, p, len);
+ return tmp;
+}
+
/*
* NFSv4 basic data type decoders
*/
p = xdr_inline_decode(argp->xdr, len);
if (!p)
return nfserr_bad_xdr;
- o->data = svcxdr_tmpalloc(argp, len);
+ o->data = svcxdr_savemem(argp, p, len);
if (!o->data)
return nfserr_jukebox;
o->len = len;
- memcpy(o->data, p, len);
return nfs_ok;
}
status = check_filename((char *)p, *lenp);
if (status)
return status;
- *namp = svcxdr_tmpalloc(argp, *lenp);
+ *namp = svcxdr_savemem(argp, p, *lenp);
if (!*namp)
return nfserr_jukebox;
- memcpy(*namp, p, *lenp);
return nfs_ok;
}
p = xdr_inline_decode(argp->xdr, putfh->pf_fhlen);
if (!p)
return nfserr_bad_xdr;
- putfh->pf_fhval = svcxdr_tmpalloc(argp, putfh->pf_fhlen);
+ putfh->pf_fhval = svcxdr_savemem(argp, p, putfh->pf_fhlen);
if (!putfh->pf_fhval)
return nfserr_jukebox;
- memcpy(putfh->pf_fhval, p, putfh->pf_fhlen);
return nfs_ok;
}
p = xdr_inline_decode(argp->xdr, setclientid->se_callback_netid_len);
if (!p)
return nfserr_bad_xdr;
- setclientid->se_callback_netid_val = svcxdr_tmpalloc(argp,
+ setclientid->se_callback_netid_val = svcxdr_savemem(argp, p,
setclientid->se_callback_netid_len);
if (!setclientid->se_callback_netid_val)
return nfserr_jukebox;
- memcpy(setclientid->se_callback_netid_val, p,
- setclientid->se_callback_netid_len);
if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_addr_len) < 0)
return nfserr_bad_xdr;
p = xdr_inline_decode(argp->xdr, setclientid->se_callback_addr_len);
if (!p)
return nfserr_bad_xdr;
- setclientid->se_callback_addr_val = svcxdr_tmpalloc(argp,
+ setclientid->se_callback_addr_val = svcxdr_savemem(argp, p,
setclientid->se_callback_addr_len);
if (!setclientid->se_callback_addr_val)
return nfserr_jukebox;
- memcpy(setclientid->se_callback_addr_val, p,
- setclientid->se_callback_addr_len);
if (xdr_stream_decode_u32(argp->xdr, &setclientid->se_callback_ident) < 0)
return nfserr_bad_xdr;
p = xdr_inline_decode(argp->xdr, verify->ve_attrlen);
if (!p)
return nfserr_bad_xdr;
- verify->ve_attrval = svcxdr_tmpalloc(argp, verify->ve_attrlen);
+ verify->ve_attrval = svcxdr_savemem(argp, p, verify->ve_attrlen);
if (!verify->ve_attrval)
return nfserr_jukebox;
- memcpy(verify->ve_attrval, p, verify->ve_attrlen);
return nfs_ok;
}
p = xdr_inline_decode(argp->xdr, argp->taglen);
if (!p)
return 0;
- argp->tag = svcxdr_tmpalloc(argp, argp->taglen);
+ argp->tag = svcxdr_savemem(argp, p, argp->taglen);
if (!argp->tag)
return 0;
- memcpy(argp->tag, p, argp->taglen);
max_reply += xdr_align_size(argp->taglen);
}
resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof);
if (nfserr)
return nfserr;
+ xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount));
tmp = htonl(NFS4_CONTENT_DATA);
write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4);
write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8);
tmp = htonl(*maxcount);
write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4);
+
+ tmp = xdr_zero;
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp,
+ xdr_pad_size(*maxcount));
return nfs_ok;
}
if (nfserr && segments == 0)
xdr_truncate_encode(xdr, starting_len);
else {
- tmp = htonl(eof);
- write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4);
- tmp = htonl(segments);
- write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
if (nfserr) {
xdr_truncate_encode(xdr, last_segment);
nfserr = nfs_ok;
+ eof = 0;
}
+ tmp = htonl(eof);
+ write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4);
+ tmp = htonl(segments);
+ write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
}
return nfserr;
#define NFSDDBG_FACILITY NFSDDBG_SVC
-bool inter_copy_offload_enable;
-EXPORT_SYMBOL_GPL(inter_copy_offload_enable);
-module_param(inter_copy_offload_enable, bool, 0644);
-MODULE_PARM_DESC(inter_copy_offload_enable,
- "Enable inter server to server copy offload. Default: false");
-
extern struct svc_program nfsd_program;
static int nfsd(void *vrqstp);
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
struct nfs_fh c_fh;
nfs4_stateid stateid;
};
-extern bool inter_copy_offload_enable;
struct nfsd4_seek {
/* request */
return ret;
}
+#ifndef CONFIG_ARCH_SPLIT_ARG64
SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
__u64, mask, int, dfd,
const char __user *, pathname)
{
return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
}
+#endif
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE6(fanotify_mark,
+#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
+SYSCALL32_DEFINE6(fanotify_mark,
int, fanotify_fd, unsigned int, flags,
- __u32, mask0, __u32, mask1, int, dfd,
+ SC_ARG64(mask), int, dfd,
const char __user *, pathname)
{
- return do_fanotify_mark(fanotify_fd, flags,
-#ifdef __BIG_ENDIAN
- ((__u64)mask0 << 32) | mask1,
-#else
- ((__u64)mask1 << 32) | mask0,
-#endif
- dfd, pathname);
+ return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
+ dfd, pathname);
}
#endif
};
#ifdef CONFIG_MEM_SOFT_DIRTY
+
+#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
+
+static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+ struct page *page;
+
+ if (!pte_write(pte))
+ return false;
+ if (!is_cow_mapping(vma->vm_flags))
+ return false;
+ if (likely(!atomic_read(&vma->vm_mm->has_pinned)))
+ return false;
+ page = vm_normal_page(vma, addr, pte);
+ if (!page)
+ return false;
+ return page_maybe_dma_pinned(page);
+}
+
static inline void clear_soft_dirty(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte)
{
if (pte_present(ptent)) {
pte_t old_pte;
+ if (pte_is_pinned(vma, addr, ptent))
+ return;
old_pte = ptep_modify_prot_start(vma, addr, pte);
ptent = pte_wrprotect(old_pte);
ptent = pte_clear_soft_dirty(ptent);
.type = type,
};
+ if (mmap_write_lock_killable(mm)) {
+ count = -EINTR;
+ goto out_mm;
+ }
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
- if (mmap_write_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
-
/*
* Writing 5 to /proc/pid/clear_refs resets the peak
* resident set size to this mm's current rss value.
*/
reset_mm_hiwater_rss(mm);
- mmap_write_unlock(mm);
- goto out_mm;
+ goto out_unlock;
}
- if (mmap_read_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
tlb_gather_mmu(&tlb, mm, 0, -1);
if (type == CLEAR_REFS_SOFT_DIRTY) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
- mmap_read_unlock(mm);
- if (mmap_write_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- vma->vm_flags &= ~VM_SOFTDIRTY;
- vma_set_page_prot(vma);
- }
- mmap_write_downgrade(mm);
- break;
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
}
mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
if (type == CLEAR_REFS_SOFT_DIRTY)
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb, 0, -1);
- mmap_read_unlock(mm);
+out_unlock:
+ mmap_write_unlock(mm);
out_mm:
mmput(mm);
}
fdcount = do_poll(head, &table, end_time);
poll_freewait(&table);
+ if (!user_write_access_begin(ufds, nfds * sizeof(*ufds)))
+ goto out_fds;
+
for (walk = head; walk; walk = walk->next) {
struct pollfd *fds = walk->entries;
int j;
- for (j = 0; j < walk->len; j++, ufds++)
- if (__put_user(fds[j].revents, &ufds->revents))
- goto out_fds;
+ for (j = walk->len; j; fds++, ufds++, j--)
+ unsafe_put_user(fds->revents, &ufds->revents, Efault);
}
+ user_write_access_end();
err = fdcount;
out_fds:
}
return err;
+
+Efault:
+ user_write_access_end();
+ err = -EFAULT;
+ goto out_fds;
}
static long do_restart_poll(struct restart_block *restart_block)
depends on BLOCK
depends on BLK_DEV_ZONED
select FS_IOMAP
+ select CRC32
help
zonefs is a simple file system which exposes zones of a zoned block
device (e.g. host-managed or host-aware SMR disk drives) as files.
mandatory-y += kprobes.h
mandatory-y += linkage.h
mandatory-y += local.h
+mandatory-y += local64.h
mandatory-y += mm-arch-hooks.h
mandatory-y += mmiowb.h
mandatory-y += mmu.h
* See Documentation/atomic_bitops.txt for details.
*/
-static inline void set_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void set_bit(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
}
-static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void clear_bit(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
}
-static inline void change_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void change_bit(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
#define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1)
#define ARMV8_PMU_MAX_COUNTER_PAIRS ((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
-#ifdef CONFIG_KVM_ARM_PMU
+#ifdef CONFIG_HW_PERF_EVENTS
struct kvm_pmc {
u8 idx; /* index into the pmu->pmc array */
return -ENODEV;
}
+static inline struct platform_device *
+acpi_create_platform_device(struct acpi_device *adev,
+ struct property_entry *properties)
+{
+ return NULL;
+}
+
static inline bool acpi_dma_supported(struct acpi_device *adev)
{
return false;
BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0),
/* allocate from reserved pool */
BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1),
- /* set RQF_PREEMPT */
- BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3),
+ /* set RQF_PM */
+ BLK_MQ_REQ_PM = (__force blk_mq_req_flags_t)(1 << 2),
};
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6))
/* don't call prep for this one */
#define RQF_DONTPREP ((__force req_flags_t)(1 << 7))
-/* set for "ide_preempt" requests and also for requests for which the SCSI
- "quiesce" state must be ignored. */
-#define RQF_PREEMPT ((__force req_flags_t)(1 << 8))
/* vaguely specified driver internal error. Ignored by the block layer */
#define RQF_FAILED ((__force req_flags_t)(1 << 10))
/* don't warn about errors */
unsigned long queue_flags;
/*
* Number of contexts that have called blk_set_pm_only(). If this
- * counter is above zero then only RQF_PM and RQF_PREEMPT requests are
- * processed.
+ * counter is above zero then only RQF_PM requests are processed.
*/
atomic_t pm_only;
return q->mq_ops;
}
+#ifdef CONFIG_PM
+static inline enum rpm_status queue_rpm_status(struct request_queue *q)
+{
+ return q->rpm_status;
+}
+#else
+static inline enum rpm_status queue_rpm_status(struct request_queue *q)
+{
+ return RPM_ACTIVE;
+}
+#endif
+
static inline enum blk_zoned_model
blk_queue_zoned_model(struct request_queue *q)
{
#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
-#ifdef __GENKSYMS__
-/* genksyms gets confused by _Static_assert */
-#define _Static_assert(expr, ...)
-#endif
-
#endif /* _LINUX_BUILD_BUG_H */
#define CEPH_MSGR2_INCARNATION_1 (0ull)
#define DEFINE_MSGR2_FEATURE(bit, incarnation, name) \
- static const uint64_t CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
- static const uint64_t CEPH_MSGR2_FEATUREMASK_##name = \
+ static const uint64_t __maybe_unused CEPH_MSGR2_FEATURE_##name = (1ULL << bit); \
+ static const uint64_t __maybe_unused CEPH_MSGR2_FEATUREMASK_##name = \
(1ULL << bit | CEPH_MSGR2_INCARNATION_##incarnation);
#define HAVE_MSGR2_FEATURE(x, name) \
/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
#if GCC_VERSION < 40900
# error Sorry, your version of GCC is too old - please use 4.9 or newer.
+#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100
+/*
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293
+ * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk
+ */
+# error Sorry, your version of GCC is too old - please use 5.1 or newer.
#endif
/*
*/
#define __used __attribute__((__used__))
+/*
+ * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result
+ */
+#define __must_check __attribute__((__warn_unused_result__))
+
/*
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute
unsigned long constant;
};
-#ifdef CONFIG_ENABLE_MUST_CHECK
-#define __must_check __attribute__((__warn_unused_result__))
-#else
-#define __must_check
-#endif
-
#if defined(CC_USING_HOTPATCH)
#define notrace __attribute__((hotpatch(0, 0)))
#elif defined(CC_USING_PATCHABLE_FUNCTION_ENTRY)
extern int braille_unregister_console(struct console *);
#ifdef CONFIG_TTY
extern void console_sysfs_notify(void);
-extern void register_ttynull_console(void);
#else
static inline void console_sysfs_notify(void)
{ }
-static inline void register_ttynull_console(void)
-{ }
#endif
extern bool console_suspend_enabled;
unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c);
sector_t dm_bufio_get_block_number(struct dm_buffer *b);
void *dm_bufio_get_block_data(struct dm_buffer *b);
void *dm_bufio_get_aux_data(struct dm_buffer *b);
/* Domain ids per IOMMU. Use u16 since
* domain ids are 16 bit wide according
* to VT-d spec, section 9.3 */
- unsigned int auxd_refcnt; /* Refcount of auxiliary attaching */
bool has_iotlb_device;
struct list_head devices; /* all devices' list */
- struct list_head auxd; /* link to device's auxiliary list */
+ struct list_head subdevices; /* all subdevices' list */
struct iova_domain iovad; /* iova's that belong to this domain */
struct dma_pte *pgd; /* virtual address */
struct dmar_drhd_unit *drhd;
};
+/* Per subdevice private data */
+struct subdev_domain_info {
+ struct list_head link_phys; /* link to phys device siblings */
+ struct list_head link_domain; /* link to domain siblings */
+ struct device *pdev; /* physical device derived from */
+ struct dmar_domain *domain; /* aux-domain */
+ int users; /* user count */
+};
+
/* PCI domain-device relationship */
struct device_domain_info {
struct list_head link; /* link to domain siblings */
struct list_head global; /* link to global list */
struct list_head table; /* link to pasid table */
- struct list_head auxiliary_domains; /* auxiliary domains
- * attached to this device
- */
+ struct list_head subdevices; /* subdevices sibling */
u32 segment; /* PCI segment number */
u8 bus; /* PCI bus number */
u8 devfn; /* PCI devfn number */
struct list_head list;
struct rcu_head rcu;
struct device *dev;
+ struct intel_iommu *iommu;
struct svm_dev_ops *ops;
struct iommu_sva sva;
u32 pasid;
struct mmu_notifier notifier;
struct mm_struct *mm;
- struct intel_iommu *iommu;
unsigned int flags;
u32 pasid;
int gpasid; /* In case that guest PASID is different from host PASID */
#define KASAN_SHADOW_INIT 0
#endif
+#ifndef PTE_HWTABLE_PTRS
+#define PTE_HWTABLE_PTRS 0
+#endif
+
extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
-extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
+extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS];
extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD];
extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id));
}
+/*
+ * The softirq flavor of kcov_remote_*() functions is introduced as a temporary
+ * work around for kcov's lack of nested remote coverage sections support in
+ * task context. Adding suport for nested sections is tracked in:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=210337
+ */
+
+static inline void kcov_remote_start_usb_softirq(u64 id)
+{
+ if (in_serving_softirq())
+ kcov_remote_start_usb(id);
+}
+
+static inline void kcov_remote_stop_softirq(void)
+{
+ if (in_serving_softirq())
+ kcov_remote_stop();
+}
+
#else
static inline void kcov_task_init(struct task_struct *t) {}
}
static inline void kcov_remote_start_common(u64 id) {}
static inline void kcov_remote_start_usb(u64 id) {}
+static inline void kcov_remote_start_usb_softirq(u64 id) {}
+static inline void kcov_remote_stop_softirq(void) {}
#endif /* CONFIG_KCOV */
#endif /* _LINUX_KCOV_H */
})
/* acceptable for old filesystems */
-static inline bool old_valid_dev(dev_t dev)
+static __always_inline bool old_valid_dev(dev_t dev)
{
return MAJOR(dev) < 256 && MINOR(dev) < 256;
}
-static inline u16 old_encode_dev(dev_t dev)
+static __always_inline u16 old_encode_dev(dev_t dev)
{
return (MAJOR(dev) << 8) | MINOR(dev);
}
-static inline dev_t old_decode_dev(u16 val)
+static __always_inline dev_t old_decode_dev(u16 val)
{
return MKDEV((val >> 8) & 255, val & 255);
}
-static inline u32 new_encode_dev(dev_t dev)
+static __always_inline u32 new_encode_dev(dev_t dev)
{
unsigned major = MAJOR(dev);
unsigned minor = MINOR(dev);
return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12);
}
-static inline dev_t new_decode_dev(u32 dev)
+static __always_inline dev_t new_decode_dev(u32 dev)
{
unsigned major = (dev & 0xfff00) >> 8;
unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00);
return MKDEV(major, minor);
}
-static inline u64 huge_encode_dev(dev_t dev)
+static __always_inline u64 huge_encode_dev(dev_t dev)
{
return new_encode_dev(dev);
}
-static inline dev_t huge_decode_dev(u64 dev)
+static __always_inline dev_t huge_decode_dev(u64 dev)
{
return new_decode_dev(dev);
}
-static inline int sysv_valid_dev(dev_t dev)
+static __always_inline int sysv_valid_dev(dev_t dev)
{
return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18);
}
-static inline u32 sysv_encode_dev(dev_t dev)
+static __always_inline u32 sysv_encode_dev(dev_t dev)
{
return MINOR(dev) | (MAJOR(dev) << 18);
}
-static inline unsigned sysv_major(u32 dev)
+static __always_inline unsigned sysv_major(u32 dev)
{
return (dev >> 18) & 0x3fff;
}
-static inline unsigned sysv_minor(u32 dev)
+static __always_inline unsigned sysv_minor(u32 dev)
{
return dev & 0x3ffff;
}
const struct mdiobb_ops *ops;
};
+int mdiobb_read(struct mii_bus *bus, int phy, int reg);
+int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val);
+
/* The returned bus is not yet registered with the phy layer. */
struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl);
{
struct mem_cgroup *memcg = page_memcg(page);
- VM_WARN_ON_ONCE_PAGE(!memcg, page);
+ VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
return mem_cgroup_lruvec(memcg, pgdat);
}
u8 ece_support[0x1];
u8 reserved_at_a4[0x7];
u8 log_max_srq[0x5];
- u8 reserved_at_b0[0x2];
+ u8 reserved_at_b0[0x1];
+ u8 uplink_follow[0x1];
u8 ts_cqe_to_dest_cqn[0x1];
u8 reserved_at_b3[0xd];
loff_t *);
int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
loff_t *);
+/*
+ * Any attempt to mark this function as static leads to build failure
+ * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked()
+ * is referred to by BPF code. This must be visible for error injection.
+ */
+int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+ pgoff_t index, gfp_t gfp, void **shadowp);
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
#endif
extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
- enum meminit_context, struct vmem_altmap *, int migratetype);
+extern void memmap_init_zone(unsigned long, int, unsigned long,
+ unsigned long, unsigned long, enum meminit_context,
+ struct vmem_altmap *, int migratetype);
extern void setup_per_zone_wmarks(void);
extern int __meminit init_per_zone_wmark_min(void);
extern void mem_init(void);
static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
#endif
-bool arm_pmu_irq_is_nmi(void);
-
/* Internal functions only for core arm_pmu code */
struct arm_pmu *armpmu_alloc(void);
struct arm_pmu *armpmu_alloc_atomic(void);
void rcu_report_dead(unsigned int cpu);
void rcutree_migrate_callbacks(int cpu);
+#ifdef CONFIG_TASKS_RCU_GENERIC
+void rcu_init_tasks_generic(void);
+#else
+static inline void rcu_init_tasks_generic(void) { }
+#endif
+
#ifdef CONFIG_RCU_STALL_COMMON
void rcu_sysrq_start(void);
void rcu_sysrq_end(void);
#define SZ_2G 0x80000000
#define SZ_4G _AC(0x100000000, ULL)
+#define SZ_8G _AC(0x200000000, ULL)
+#define SZ_16G _AC(0x400000000, ULL)
+#define SZ_32G _AC(0x800000000, ULL)
#define SZ_64T _AC(0x400000000000, ULL)
#endif /* __LINUX_SIZES_H__ */
static inline bool skb_frag_must_loop(struct page *p)
{
#if defined(CONFIG_HIGHMEM)
- if (PageHighMem(p))
+ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p))
return true;
#endif
return false;
struct sk_buff *root_skb;
struct sk_buff *cur_skb;
__u8 *frag_data;
+ __u32 frag_off;
};
void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
#endif /* __SYSCALL_DEFINEx */
+/* For split 64-bit arguments on 32-bit architectures */
+#ifdef __LITTLE_ENDIAN
+#define SC_ARG64(name) u32, name##_lo, u32, name##_hi
+#else
+#define SC_ARG64(name) u32, name##_hi, u32, name##_lo
+#endif
+#define SC_VAL64(type, name) ((type) name##_hi << 32 | name##_lo)
+
+#ifdef CONFIG_COMPAT
+#define SYSCALL32_DEFINE1 COMPAT_SYSCALL_DEFINE1
+#define SYSCALL32_DEFINE2 COMPAT_SYSCALL_DEFINE2
+#define SYSCALL32_DEFINE3 COMPAT_SYSCALL_DEFINE3
+#define SYSCALL32_DEFINE4 COMPAT_SYSCALL_DEFINE4
+#define SYSCALL32_DEFINE5 COMPAT_SYSCALL_DEFINE5
+#define SYSCALL32_DEFINE6 COMPAT_SYSCALL_DEFINE6
+#else
+#define SYSCALL32_DEFINE1 SYSCALL_DEFINE1
+#define SYSCALL32_DEFINE2 SYSCALL_DEFINE2
+#define SYSCALL32_DEFINE3 SYSCALL_DEFINE3
+#define SYSCALL32_DEFINE4 SYSCALL_DEFINE4
+#define SYSCALL32_DEFINE5 SYSCALL_DEFINE5
+#define SYSCALL32_DEFINE6 SYSCALL_DEFINE6
+#endif
+
/*
* Called before coming back to user-mode. Returning to user-mode with an
* address limit different than USER_DS can allow to overwrite kernel memory.
# define EVENT_LINK_CHANGE 11
# define EVENT_SET_RX_MODE 12
# define EVENT_NO_IP_ALIGN 13
+ u32 rx_speed; /* in bps - NOT Mbps */
+ u32 tx_speed; /* in bps - NOT Mbps */
};
static inline struct usb_driver *driver_of(struct usb_interface *intf)
/**
- * @struct cfg80211_sar_chan_ranges - sar frequency ranges
+ * struct cfg80211_sar_freq_ranges - sar frequency ranges
* @start_freq: start range edge frequency
* @end_freq: end range edge frequency
*/
* This callback may sleep.
* @reset_tid_config: Reset TID specific configuration for the peer, for the
* given TIDs. This callback may sleep.
+ *
+ * @set_sar_specs: Update the SAR (TX power) settings.
*/
struct cfg80211_ops {
int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
* @max_data_retry_count: maximum supported per TID retry count for
* configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and
* %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes
+ * @sar_capa: SAR control capabilities
*/
struct wiphy {
/* assign these fields before you register the wiphy */
* @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options)
* @icsk_ack: Delayed ACK control data
* @icsk_mtup; MTU probing control data
+ * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack)
+ * @icsk_user_timeout: TCP_USER_TIMEOUT value
*/
struct inet_connection_sock {
/* inet_sock has to be the first member! */
u32 probe_timestamp;
} icsk_mtup;
+ u32 icsk_probes_tstamp;
u32 icsk_user_timeout;
u64 icsk_ca_priv[104 / sizeof(u64)];
* This callback may sleep.
* @sta_set_4addr: Called to notify the driver when a station starts/stops using
* 4-address mode
+ * @set_sar_specs: Update the SAR (TX power) settings.
*/
struct ieee80211_ops {
void (*tx)(struct ieee80211_hw *hw,
v->qcount = -1;
}
-static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog)
+static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log)
{
if (fls(qth_min) + Wlog > 32)
return false;
if (fls(qth_max) + Wlog > 32)
return false;
+ if (Scell_log >= 32)
+ return false;
if (qth_max < qth_min)
return false;
return true;
sk->sk_txhash = net_tx_rndhash();
}
-static inline void sk_rethink_txhash(struct sock *sk)
+static inline bool sk_rethink_txhash(struct sock *sk)
{
- if (sk->sk_txhash)
+ if (sk->sk_txhash) {
sk_set_txhash(sk);
+ return true;
+ }
+ return false;
}
static inline struct dst_entry *
return dst;
}
-static inline void dst_negative_advice(struct sock *sk)
+static inline void __dst_negative_advice(struct sock *sk)
{
struct dst_entry *ndst, *dst = __sk_dst_get(sk);
- sk_rethink_txhash(sk);
-
if (dst && dst->ops->negative_advice) {
ndst = dst->ops->negative_advice(dst);
}
}
+static inline void dst_negative_advice(struct sock *sk)
+{
+ sk_rethink_txhash(sk);
+ __dst_negative_advice(sk);
+}
+
static inline void
__sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
struct xsk_queue *tx ____cacheline_aligned_in_smp;
struct list_head tx_list;
- /* Mutual exclusion of NAPI TX thread and sendmsg error paths
- * in the SKB destructor callback.
- */
- spinlock_t tx_completion_lock;
/* Protects generic receive. */
spinlock_t rx_lock;
bool dma_need_sync;
bool unaligned;
void *addrs;
+ /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
+ * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
+ * sockets share a single cq when the same netdev and queue id is shared.
+ */
+ spinlock_t cq_lock;
struct xdp_buff_xsk *free_heads[];
};
+++ /dev/null
-/*
- * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses. You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- * 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.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef SOC_NPS_COMMON_H
-#define SOC_NPS_COMMON_H
-
-#ifdef CONFIG_SMP
-#define NPS_IPI_IRQ 5
-#endif
-
-#define NPS_HOST_REG_BASE 0xF6000000
-
-#define NPS_MSU_BLKID 0x018
-
-#define CTOP_INST_RSPI_GIC_0_R12 0x3C56117E
-#define CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST 0x5B60
-#define CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM 0x00010422
-
-#ifndef AUX_IENABLE
-#define AUX_IENABLE 0x40c
-#endif
-
-#define CTOP_AUX_IACK (0xFFFFF800 + 0x088)
-
-#ifndef __ASSEMBLY__
-
-/* In order to increase compilation test coverage */
-#ifdef CONFIG_ARC
-static inline void nps_ack_gic(void)
-{
- __asm__ __volatile__ (
- " .word %0\n"
- :
- : "i"(CTOP_INST_RSPI_GIC_0_R12)
- : "memory");
-}
-#else
-static inline void nps_ack_gic(void) { }
-#define write_aux_reg(r, v)
-#define read_aux_reg(r) 0
-#endif
-
-/* CPU global ID */
-struct global_id {
- union {
- struct {
-#ifdef CONFIG_EZNPS_MTM_EXT
- u32 __reserved:20, cluster:4, core:4, thread:4;
-#else
- u32 __reserved:24, cluster:4, core:4;
-#endif
- };
- u32 value;
- };
-};
-
-/*
- * Convert logical to physical CPU IDs
- *
- * The conversion swap bits 1 and 2 of cluster id (out of 4 bits)
- * Now quad of logical clusters id's are adjacent physically,
- * and not like the id's physically came with each cluster.
- * Below table is 4x4 mesh of core clusters as it layout on chip.
- * Cluster ids are in format: logical (physical)
- *
- * ----------------- ------------------
- * 3 | 5 (3) 7 (7) | | 13 (11) 15 (15)|
- *
- * 2 | 4 (2) 6 (6) | | 12 (10) 14 (14)|
- * ----------------- ------------------
- * 1 | 1 (1) 3 (5) | | 9 (9) 11 (13)|
- *
- * 0 | 0 (0) 2 (4) | | 8 (8) 10 (12)|
- * ----------------- ------------------
- * 0 1 2 3
- */
-static inline int nps_cluster_logic_to_phys(int cluster)
-{
-#ifdef __arc__
- __asm__ __volatile__(
- " mov r3,%0\n"
- " .short %1\n"
- " .word %2\n"
- " mov %0,r3\n"
- : "+r"(cluster)
- : "i"(CTOP_INST_MOV2B_FLIP_R3_B1_B2_INST),
- "i"(CTOP_INST_MOV2B_FLIP_R3_B1_B2_LIMM)
- : "r3");
-#endif
-
- return cluster;
-}
-
-#define NPS_CPU_TO_CLUSTER_NUM(cpu) \
- ({ struct global_id gid; gid.value = cpu; \
- nps_cluster_logic_to_phys(gid.cluster); })
-
-struct nps_host_reg_address {
- union {
- struct {
- u32 base:8, cl_x:4, cl_y:4,
- blkid:6, reg:8, __reserved:2;
- };
- u32 value;
- };
-};
-
-struct nps_host_reg_address_non_cl {
- union {
- struct {
- u32 base:7, blkid:11, reg:12, __reserved:2;
- };
- u32 value;
- };
-};
-
-static inline void *nps_host_reg_non_cl(u32 blkid, u32 reg)
-{
- struct nps_host_reg_address_non_cl reg_address;
-
- reg_address.value = NPS_HOST_REG_BASE;
- reg_address.blkid = blkid;
- reg_address.reg = reg;
-
- return (void *)reg_address.value;
-}
-
-static inline void *nps_host_reg(u32 cpu, u32 blkid, u32 reg)
-{
- struct nps_host_reg_address reg_address;
- u32 cl = NPS_CPU_TO_CLUSTER_NUM(cpu);
-
- reg_address.value = NPS_HOST_REG_BASE;
- reg_address.cl_x = (cl >> 2) & 0x3;
- reg_address.cl_y = cl & 0x3;
- reg_address.blkid = blkid;
- reg_address.reg = reg;
-
- return (void *)reg_address.value;
-}
-#endif /* __ASSEMBLY__ */
-
-#endif /* SOC_NPS_COMMON_H */
+++ /dev/null
-/*
- * Copyright (c) 2016, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses. You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- * 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.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef SOC_NPS_MTM_H
-#define SOC_NPS_MTM_H
-
-#define CTOP_INST_HWSCHD_OFF_R3 0x3B6F00BF
-#define CTOP_INST_HWSCHD_RESTORE_R3 0x3E6F70C3
-
-static inline void hw_schd_save(unsigned int *flags)
-{
- __asm__ __volatile__(
- " .word %1\n"
- " st r3,[%0]\n"
- :
- : "r"(flags), "i"(CTOP_INST_HWSCHD_OFF_R3)
- : "r3", "memory");
-}
-
-static inline void hw_schd_restore(unsigned int flags)
-{
- __asm__ __volatile__(
- " mov r3, %0\n"
- " .word %1\n"
- :
- : "r"(flags), "i"(CTOP_INST_HWSCHD_RESTORE_R3)
- : "r3");
-}
-
-#endif /* SOC_NPS_MTM_H */
afs_file_error_dir_bad_magic,
afs_file_error_dir_big,
afs_file_error_dir_missing_page,
+ afs_file_error_dir_name_too_long,
afs_file_error_dir_over_end,
afs_file_error_dir_small,
afs_file_error_dir_unmarked_ext,
EM(afs_file_error_dir_bad_magic, "DIR_BAD_MAGIC") \
EM(afs_file_error_dir_big, "DIR_BIG") \
EM(afs_file_error_dir_missing_page, "DIR_MISSING_PAGE") \
+ EM(afs_file_error_dir_name_too_long, "DIR_NAME_TOO_LONG") \
EM(afs_file_error_dir_over_end, "DIR_ENT_OVER_END") \
EM(afs_file_error_dir_small, "DIR_SMALL") \
EM(afs_file_error_dir_unmarked_ext, "DIR_UNMARKED_EXT") \
)
);
+/* Record an xdr_buf containing a fully-formed RPC message */
+DECLARE_EVENT_CLASS(svc_xdr_msg_class,
+ TP_PROTO(
+ const struct xdr_buf *xdr
+ ),
+
+ TP_ARGS(xdr),
+
+ TP_STRUCT__entry(
+ __field(u32, xid)
+ __field(const void *, head_base)
+ __field(size_t, head_len)
+ __field(const void *, tail_base)
+ __field(size_t, tail_len)
+ __field(unsigned int, page_len)
+ __field(unsigned int, msg_len)
+ ),
+
+ TP_fast_assign(
+ __be32 *p = (__be32 *)xdr->head[0].iov_base;
+
+ __entry->xid = be32_to_cpu(*p);
+ __entry->head_base = p;
+ __entry->head_len = xdr->head[0].iov_len;
+ __entry->tail_base = xdr->tail[0].iov_base;
+ __entry->tail_len = xdr->tail[0].iov_len;
+ __entry->page_len = xdr->page_len;
+ __entry->msg_len = xdr->len;
+ ),
+
+ TP_printk("xid=0x%08x head=[%p,%zu] page=%u tail=[%p,%zu] len=%u",
+ __entry->xid,
+ __entry->head_base, __entry->head_len, __entry->page_len,
+ __entry->tail_base, __entry->tail_len, __entry->msg_len
+ )
+);
+
+#define DEFINE_SVCXDRMSG_EVENT(name) \
+ DEFINE_EVENT(svc_xdr_msg_class, \
+ svc_xdr_##name, \
+ TP_PROTO( \
+ const struct xdr_buf *xdr \
+ ), \
+ TP_ARGS(xdr))
+
+DEFINE_SVCXDRMSG_EVENT(recvfrom);
+
+/* Record an xdr_buf containing arbitrary data, tagged with an XID */
DECLARE_EVENT_CLASS(svc_xdr_buf_class,
TP_PROTO(
- const struct svc_rqst *rqst,
+ __be32 xid,
const struct xdr_buf *xdr
),
- TP_ARGS(rqst, xdr),
+ TP_ARGS(xid, xdr),
TP_STRUCT__entry(
__field(u32, xid)
),
TP_fast_assign(
- __entry->xid = be32_to_cpu(rqst->rq_xid);
+ __entry->xid = be32_to_cpu(xid);
__entry->head_base = xdr->head[0].iov_base;
__entry->head_len = xdr->head[0].iov_len;
__entry->tail_base = xdr->tail[0].iov_base;
DEFINE_EVENT(svc_xdr_buf_class, \
svc_xdr_##name, \
TP_PROTO( \
- const struct svc_rqst *rqst, \
+ __be32 xid, \
const struct xdr_buf *xdr \
), \
- TP_ARGS(rqst, xdr))
+ TP_ARGS(xid, xdr))
-DEFINE_SVCXDRBUF_EVENT(recvfrom);
DEFINE_SVCXDRBUF_EVENT(sendto);
/*
__le16 keys;
};
__le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */
- __le16 bucket_size_hi;
+ __le16 obso_bucket_size_hi; /* obsoleted */
};
/*
*
* @rx_dropped: Number of packets received but not processed,
* e.g. due to lack of resources or unsupported protocol.
- * For hardware interfaces this counter should not include packets
- * dropped by the device which are counted separately in
+ * For hardware interfaces this counter may include packets discarded
+ * due to L2 address filtering but should not include packets dropped
+ * by the device due to buffer exhaustion which are counted separately in
* @rx_missed_errors (since procfs folds those two counters together).
*
* @tx_dropped: Number of packets dropped on their way to transmission,
#define KVM_EXIT_X86_RDMSR 29
#define KVM_EXIT_X86_WRMSR 30
#define KVM_EXIT_DIRTY_RING_FULL 31
+#define KVM_EXIT_AP_RESET_HOLD 32
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
#define KVM_MP_STATE_CHECK_STOP 6
#define KVM_MP_STATE_OPERATING 7
#define KVM_MP_STATE_LOAD 8
+#define KVM_MP_STATE_AP_RESET_HOLD 9
struct kvm_mp_state {
__u32 mp_state;
* @NFT_SET_EVAL: set can be updated from the evaluation path
* @NFT_SET_OBJECT: set contains stateful objects
* @NFT_SET_CONCAT: set contains a concatenation
+ * @NFT_SET_EXPR: set contains expressions
*/
enum nft_set_flags {
NFT_SET_ANONYMOUS = 0x1,
NFT_SET_EVAL = 0x20,
NFT_SET_OBJECT = 0x40,
NFT_SET_CONCAT = 0x80,
+ NFT_SET_EXPR = 0x100,
};
/**
enum nft_dynset_flags {
NFT_DYNSET_F_INV = (1 << 0),
+ NFT_DYNSET_F_EXPR = (1 << 1),
};
/**
#define PPPIOCGCHAN _IOR('t', 55, int) /* get ppp channel number */
#define PPPIOCGL2TPSTATS _IOR('t', 54, struct pppol2tp_ioc_stats)
#define PPPIOCBRIDGECHAN _IOW('t', 53, int) /* bridge one channel to another */
-#define PPPIOCUNBRIDGECHAN _IO('t', 54) /* unbridge channel */
+#define PPPIOCUNBRIDGECHAN _IO('t', 52) /* unbridge channel */
#define SIOCGPPPSTATS (SIOCDEVPRIVATE + 0)
#define SIOCGPPPVER (SIOCDEVPRIVATE + 1) /* NEVER change this!! */
* HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
* HL_INFO_SYNC_MANAGER - Retrieve sync manager info per dcore
* HL_INFO_TOTAL_ENERGY - Retrieve total energy consumption
+ * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency
*/
#define HL_INFO_HW_IP_INFO 0
#define HL_INFO_HW_EVENTS 1
* @ctx_device_in_reset_drop_cnt: context dropped due to device in reset
* @total_max_cs_in_flight_drop_cnt: total dropped due to maximum CS in-flight
* @ctx_max_cs_in_flight_drop_cnt: context dropped due to maximum CS in-flight
+ * @total_validation_drop_cnt: total dropped due to validation error
+ * @ctx_validation_drop_cnt: context dropped due to validation error
*/
struct hl_info_cs_counters {
__u64 total_out_of_mem_drop_cnt;
__u64 ctx_device_in_reset_drop_cnt;
__u64 total_max_cs_in_flight_drop_cnt;
__u64 ctx_max_cs_in_flight_drop_cnt;
+ __u64 total_validation_drop_cnt;
+ __u64 ctx_validation_drop_cnt;
};
enum gaudi_dcores {
struct work_struct;
-void xenbus_probe(struct work_struct *);
+void xenbus_probe(void);
#define XENBUS_IS_ERR_READ(str) ({ \
if (!IS_ERR(str) && strlen(str) == 0) { \
struct file *file = filp_open("/dev/console", O_RDWR, 0);
if (IS_ERR(file)) {
- pr_err("Warning: unable to open an initial console. Fallback to ttynull.\n");
- register_ttynull_console();
-
- file = filp_open("/dev/console", O_RDWR, 0);
- if (IS_ERR(file)) {
- pr_err("Warning: Failed to add ttynull console. No stdin, stdout, and stderr for the init process!\n");
- return;
- }
+ pr_err("Warning: unable to open an initial console.\n");
+ return;
}
init_dup(file);
init_dup(file);
init_mm_internals();
+ rcu_init_tasks_generic();
do_pre_smp_initcalls();
lockup_detector_init();
* bpf_local_storage_update expects the owner to have a
* valid storage pointer.
*/
- if (!inode_storage_ptr(inode))
+ if (!inode || !inode_storage_ptr(inode))
return (unsigned long)NULL;
sdata = inode_storage_lookup(inode, map, true);
if (sdata)
return (unsigned long)sdata->data;
- /* This helper must only called from where the inode is gurranteed
+ /* This helper must only called from where the inode is guaranteed
* to have a refcount and cannot be freed.
*/
if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
BPF_CALL_2(bpf_inode_storage_delete,
struct bpf_map *, map, struct inode *, inode)
{
- /* This helper must only called from where the inode is gurranteed
+ if (!inode)
+ return -EINVAL;
+
+ /* This helper must only called from where the inode is guaranteed
* to have a refcount and cannot be freed.
*/
return inode_storage_delete(inode, map);
* bpf_local_storage_update expects the owner to have a
* valid storage pointer.
*/
- if (!task_storage_ptr(task))
+ if (!task || !task_storage_ptr(task))
return (unsigned long)NULL;
sdata = task_storage_lookup(task, map, true);
BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *,
task)
{
+ if (!task)
+ return -EINVAL;
+
/* This helper must only be called from places where the lifetime of the task
* is guaranteed. Either by being refcounted or by being protected
* by an RCU read-side critical section.
return -ENOTSUPP;
}
- if (btf_data_size == hdr->hdr_len) {
+ if (!btf->base_btf && btf_data_size == hdr->hdr_len) {
btf_verifier_log(env, "No data");
return -EINVAL;
}
if (ctx.optlen != 0) {
*optlen = ctx.optlen;
*kernel_optval = ctx.optval;
+ /* export and don't free sockopt buf */
+ return 0;
}
}
out:
- if (ret)
- sockopt_free_buf(&ctx);
+ sockopt_free_buf(&ctx);
return ret;
}
lockdep_set_class(&htab->buckets[i].lock,
&htab->lockdep_key);
}
+ cond_resched();
}
}
}
const struct bpf_func_proto bpf_map_peek_elem_proto = {
- .func = bpf_map_pop_elem,
+ .func = bpf_map_peek_elem,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
#include <linux/fs.h>
#include <linux/license.h>
#include <linux/filter.h>
-#include <linux/version.h>
#include <linux/kernel.h>
#include <linux/idr.h>
#include <linux/cred.h>
out_put_prog:
if (tgt_prog_fd && tgt_prog)
bpf_prog_put(tgt_prog);
- bpf_prog_put(prog);
return err;
}
tp_name = prog->aux->attach_func_name;
break;
}
- return bpf_tracing_prog_attach(prog, 0, 0);
+ err = bpf_tracing_prog_attach(prog, 0, 0);
+ if (err >= 0)
+ return err;
+ goto out_put_prog;
case BPF_PROG_TYPE_RAW_TRACEPOINT:
case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
if (strncpy_from_user(buf,
if (!task) {
++*tid;
goto retry;
- } else if (skip_if_dup_files && task->tgid != task->pid &&
+ } else if (skip_if_dup_files && !thread_group_leader(task) &&
task->files == task->group_leader->files) {
put_task_struct(task);
task = NULL;
curr_task = info->task;
curr_fd = info->fd;
} else {
- curr_task = task_seq_get_next(ns, &curr_tid, true);
- if (!curr_task) {
- info->task = NULL;
- return NULL;
- }
-
- /* set info->task and info->tid */
+ curr_task = task_seq_get_next(ns, &curr_tid, true);
+ if (!curr_task) {
+ info->task = NULL;
+ info->tid = curr_tid;
+ return NULL;
+ }
+
+ /* set info->task and info->tid */
info->task = curr_task;
if (curr_tid == info->tid) {
curr_fd = info->fd;
case PTR_TO_RDWR_BUF:
case PTR_TO_RDWR_BUF_OR_NULL:
case PTR_TO_PERCPU_BTF_ID:
+ case PTR_TO_MEM:
+ case PTR_TO_MEM_OR_NULL:
return true;
default:
return false;
return res < a;
}
-static bool signed_add32_overflows(s64 a, s64 b)
+static bool signed_add32_overflows(s32 a, s32 b)
{
/* Do the add in u32, where overflow is well-defined */
s32 res = (s32)((u32)a + (u32)b);
return res < a;
}
-static bool signed_sub_overflows(s32 a, s32 b)
+static bool signed_sub_overflows(s64 a, s64 b)
{
/* Do the sub in u64, where overflow is well-defined */
s64 res = (s64)((u64)a - (u64)b);
static bool signed_sub32_overflows(s32 a, s32 b)
{
- /* Do the sub in u64, where overflow is well-defined */
+ /* Do the sub in u32, where overflow is well-defined */
s32 res = (s32)((u32)a - (u32)b);
if (b < 0)
opt = fs_parse(fc, cgroup1_fs_parameters, param, &result);
if (opt == -ENOPARAM) {
if (strcmp(param->key, "source") == 0) {
+ if (fc->source)
+ return invalf(fc, "Multiple sources not supported");
fc->source = param->string;
param->string = NULL;
return 0;
*
* The default hierarchy is the v2 interface of cgroup and this function
* can be used to test whether a cgroup is on the default hierarchy for
- * cases where a subsystem should behave differnetly depending on the
+ * cases where a subsystem should behave differently depending on the
* interface version.
*
* List of changed behaviors:
* "cgroup.procs" instead.
*
* - "cgroup.procs" is not sorted. pids will be unique unless they got
- * recycled inbetween reads.
+ * recycled in-between reads.
*
* - "release_agent" and "notify_on_release" are removed. Replacement
* notification mechanism will be implemented.
return !cgroup_parent(cgrp);
}
-/* can @cgrp become a thread root? should always be true for a thread root */
+/* can @cgrp become a thread root? Should always be true for a thread root */
static bool cgroup_can_be_thread_root(struct cgroup *cgrp)
{
/* mixables don't care */
* the root css is returned, so this function always returns a valid css.
*
* The returned css is not guaranteed to be online, and therefore it is the
- * callers responsiblity to tryget a reference for it.
+ * callers responsibility to try get a reference for it.
*/
struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
struct cgroup_subsys *ss)
; \
else
-/* walk live descendants in preorder */
+/* walk live descendants in pre order */
#define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \
css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \
if (({ lockdep_assert_held(&cgroup_mutex); \
WARN_ON_ONCE(!list_empty(&cset->threaded_csets));
- /* This css_set is dead. unlink it and release cgroup and css refs */
+ /* This css_set is dead. Unlink it and release cgroup and css refs */
for_each_subsys(ss, ssid) {
list_del(&cset->e_cset_node[ssid]);
css_put(cset->subsys[ssid]);
/*
* Build the set of subsystem state objects that we want to see in the
- * new css_set. while subsystems can change globally, the entries here
+ * new css_set. While subsystems can change globally, the entries here
* won't change, so no need for locking.
*/
for_each_subsys(ss, i) {
/*
* Always add links to the tail of the lists so that the lists are
- * in choronological order.
+ * in chronological order.
*/
list_move_tail(&link->cset_link, &cgrp->cset_links);
list_add_tail(&link->cgrp_link, &cset->cgrp_links);
static int cgroup_file_open(struct kernfs_open_file *of)
{
- struct cftype *cft = of->kn->priv;
+ struct cftype *cft = of_cft(of);
if (cft->open)
return cft->open(of);
static void cgroup_file_release(struct kernfs_open_file *of)
{
- struct cftype *cft = of->kn->priv;
+ struct cftype *cft = of_cft(of);
if (cft->release)
cft->release(of);
{
struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
struct cgroup *cgrp = of->kn->parent->priv;
- struct cftype *cft = of->kn->priv;
+ struct cftype *cft = of_cft(of);
struct cgroup_subsys_state *css;
int ret;
static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt)
{
- struct cftype *cft = of->kn->priv;
+ struct cftype *cft = of_cft(of);
if (cft->poll)
return cft->poll(of, pt);
* implies that if we observe !CSS_RELEASED on @pos in this RCU
* critical section, the one pointed to by its next pointer is
* guaranteed to not have finished its RCU grace period even if we
- * have dropped rcu_read_lock() inbetween iterations.
+ * have dropped rcu_read_lock() in-between iterations.
*
* If @pos has CSS_RELEASED set, its next pointer can't be
* dereferenced; however, as each css is given a monotonically
}
/**
- * css_task_iter_advance_css_set - advance a task itererator to the next css_set
+ * css_task_iter_advance_css_set - advance a task iterator to the next css_set
* @it: the iterator to advance
*
* Advance @it to the next css_set to walk.
*
* Find the cgroup at @path on the default hierarchy, increment its
* reference count and return it. Returns pointer to the found cgroup on
- * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR)
+ * success, ERR_PTR(-ENOENT) if @path doesn't exist and ERR_PTR(-ENOTDIR)
* if @path points to a non-directory.
*/
struct cgroup *cgroup_get_from_path(const char *path)
CONFIG_INPUT_MISC=y
CONFIG_INPUT_TABLET=y
CONFIG_INPUT_UINPUT=y
-CONFIG_ION=y
CONFIG_JOYSTICK_XPAD=y
CONFIG_JOYSTICK_XPAD_FF=y
CONFIG_JOYSTICK_XPAD_LEDS=y
#include <linux/random.h>
#include <linux/rcuwait.h>
#include <linux/compat.h>
+#include <linux/io_uring.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
schedule();
}
+ io_uring_files_cancel(tsk->files);
exit_signals(tsk); /* sets PF_EXITING */
/* sync mm's RSS info before statistics gathering */
}
}
-/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */
+/* Spawn RCU-tasks grace-period kthread. */
static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
{
struct task_struct *t;
rcu_spawn_tasks_kthread_generic(&rcu_tasks);
return 0;
}
-core_initcall(rcu_spawn_tasks_kthread);
#if !defined(CONFIG_TINY_RCU)
void show_rcu_tasks_classic_gp_kthread(void)
rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
return 0;
}
-core_initcall(rcu_spawn_tasks_rude_kthread);
#if !defined(CONFIG_TINY_RCU)
void show_rcu_tasks_rude_gp_kthread(void)
static void rcu_tasks_trace_pertask(struct task_struct *t,
struct list_head *hop)
{
+ // During early boot when there is only the one boot CPU, there
+ // is no idle task for the other CPUs. Just return.
+ if (unlikely(t == NULL))
+ return;
+
WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
WRITE_ONCE(t->trc_reader_checked, false);
t->trc_ipi_to_cpu = -1;
rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
return 0;
}
-core_initcall(rcu_spawn_tasks_trace_kthread);
#if !defined(CONFIG_TINY_RCU)
void show_rcu_tasks_trace_gp_kthread(void)
}
#endif /* #ifndef CONFIG_TINY_RCU */
+void __init rcu_init_tasks_generic(void)
+{
+#ifdef CONFIG_TASKS_RCU
+ rcu_spawn_tasks_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+ rcu_spawn_tasks_rude_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+ rcu_spawn_tasks_trace_kthread();
+#endif
+}
+
#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
static inline void rcu_tasks_bootup_oddness(void) {}
void show_rcu_tasks_gp_kthreads(void) {}
struct signal_struct *signal = current->signal;
int signr;
+ if (unlikely(current->task_works))
+ task_work_run();
+
/*
* For non-generic architectures, check for TIF_NOTIFY_SIGNAL so
* that the arch handlers don't all have to do it. If we get here
config KPROBE_EVENTS_ON_NOTRACE
bool "Do NOT protect notrace function from kprobe events"
depends on KPROBE_EVENTS
- depends on KPROBES_ON_FTRACE
+ depends on DYNAMIC_FTRACE
default n
help
This is only for the developers who want to debug ftrace itself
return 0;
}
-#if defined(CONFIG_KPROBES_ON_FTRACE) && \
+#if defined(CONFIG_DYNAMIC_FTRACE) && \
!defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE)
static bool __within_notrace_func(unsigned long addr)
{
* is updated and visible.
*/
if (!freezable || !workqueue_freezing) {
+ bool kick = false;
+
pwq->max_active = wq->saved_max_active;
while (!list_empty(&pwq->delayed_works) &&
- pwq->nr_active < pwq->max_active)
+ pwq->nr_active < pwq->max_active) {
pwq_activate_first_delayed(pwq);
+ kick = true;
+ }
/*
* Need to kick a worker after thawed or an unbound wq's
- * max_active is bumped. It's a slow path. Do it always.
+ * max_active is bumped. In realtime scenarios, always kicking a
+ * worker will cause interference on the isolated cpu cores, so
+ * let's kick iff work items were activated.
*/
- wake_up_worker(pwq->pool);
+ if (kick)
+ wake_up_worker(pwq->pool);
} else {
pwq->max_active = 0;
}
endif # DEBUG_INFO
-config ENABLE_MUST_CHECK
- bool "Enable __must_check logic"
- default y
- help
- Enable the __must_check logic in the kernel build. Disable this to
- suppress the "warning: ignoring return value of 'foo', declared with
- attribute warn_unused_result" messages.
-
config FRAME_WARN
int "Warn for stack frames larger than"
range 0 8192
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc,
0x7f, 0xfc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 95 */
- 0x00, 0x00, 0x1c, 0x00, 0x0e, 0x00, 0x07, 0x00,
- 0x03, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00, 0x1c, 0x00, 0x0e, 0x00,
+ 0x07, 0x00, 0x03, 0x80, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
- 0x7f, 0xf8, 0x7f, 0xfc, 0x03, 0x9e, 0x03, 0x8e,
+ 0x7e, 0xf8, 0x7f, 0xfc, 0x03, 0x9e, 0x03, 0x8e,
0x03, 0x8e, 0x3f, 0x8e, 0x7f, 0xfe, 0xf3, 0xfe,
0xe3, 0x80, 0xe3, 0x80, 0xe3, 0x80, 0xf3, 0xce,
0x7f, 0xfe, 0x3e, 0xfc, 0x00, 0x00, 0x00, 0x00,
* users set the same bit, one user will return remain bits, otherwise
* return 0.
*/
-static int bitmap_set_ll(unsigned long *map, int start, int nr)
+static int bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr)
{
unsigned long *p = map + BIT_WORD(start);
- const int size = start + nr;
+ const unsigned long size = start + nr;
int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
- while (nr - bits_to_set >= 0) {
+ while (nr >= bits_to_set) {
if (set_bits_ll(p, mask_to_set))
return nr;
nr -= bits_to_set;
* users clear the same bit, one user will return remain bits,
* otherwise return 0.
*/
-static int bitmap_clear_ll(unsigned long *map, int start, int nr)
+static unsigned long
+bitmap_clear_ll(unsigned long *map, unsigned long start, unsigned long nr)
{
unsigned long *p = map + BIT_WORD(start);
- const int size = start + nr;
+ const unsigned long size = start + nr;
int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
- while (nr - bits_to_clear >= 0) {
+ while (nr >= bits_to_clear) {
if (clear_bits_ll(p, mask_to_clear))
return nr;
nr -= bits_to_clear;
size_t size, int nid, void *owner)
{
struct gen_pool_chunk *chunk;
- int nbits = size >> pool->min_alloc_order;
- int nbytes = sizeof(struct gen_pool_chunk) +
+ unsigned long nbits = size >> pool->min_alloc_order;
+ unsigned long nbytes = sizeof(struct gen_pool_chunk) +
BITS_TO_LONGS(nbits) * sizeof(long);
chunk = vzalloc_node(nbytes, nid);
struct list_head *_chunk, *_next_chunk;
struct gen_pool_chunk *chunk;
int order = pool->min_alloc_order;
- int bit, end_bit;
+ unsigned long bit, end_bit;
list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
struct gen_pool_chunk *chunk;
unsigned long addr = 0;
int order = pool->min_alloc_order;
- int nbits, start_bit, end_bit, remain;
+ unsigned long nbits, start_bit, end_bit, remain;
#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
BUG_ON(in_nmi());
{
struct gen_pool_chunk *chunk;
int order = pool->min_alloc_order;
- int start_bit, nbits, remain;
+ unsigned long start_bit, nbits, remain;
#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
BUG_ON(in_nmi());
index = bitmap_find_next_zero_area(map, size, start, nr, 0);
while (index < size) {
- int next_bit = find_next_bit(map, size, index + nr);
+ unsigned long next_bit = find_next_bit(map, size, index + nr);
if ((next_bit - index) < len) {
len = next_bit - index;
start_bit = index;
(const struct compat_iovec __user *)uvec;
int ret = -EFAULT, i;
- if (!user_access_begin(uvec, nr_segs * sizeof(*uvec)))
+ if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
return -EFAULT;
for (i = 0; i < nr_segs; i++) {
endif
quiet_cmd_unroll = UNROLL $@
- cmd_unroll = $(AWK) -f$(srctree)/$(src)/unroll.awk -vN=$* < $< > $@
+ cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@
targets += int1.c int2.c int4.c int8.c int16.c int32.c
$(obj)/int%.c: $(src)/int.uc $(src)/unroll.awk FORCE
obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o
-zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o dfltcc_syms.o
+zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o
// SPDX-License-Identifier: Zlib
/* dfltcc.c - SystemZ DEFLATE CONVERSION CALL support. */
-#include <linux/zutil.h>
+#include <linux/export.h>
+#include <linux/module.h>
#include "dfltcc_util.h"
#include "dfltcc.h"
dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE;
dfltcc_state->param.ribm = DFLTCC_RIBM;
}
+EXPORT_SYMBOL(dfltcc_reset);
+
+MODULE_LICENSE("GPL");
#include "dfltcc_util.h"
#include "dfltcc.h"
#include <asm/setup.h>
+#include <linux/export.h>
#include <linux/zutil.h>
/*
return 1;
}
+EXPORT_SYMBOL(dfltcc_can_deflate);
static void dfltcc_gdht(
z_streamp strm
goto again; /* deflate() must use all input or all output */
return 1;
}
+EXPORT_SYMBOL(dfltcc_deflate);
param->ho = (state->write - state->whave) & ((1 << HB_BITS) - 1);
if (param->hl)
param->nt = 0; /* Honor history for the first block */
- param->cv = state->flags ? REVERSE(state->check) : state->check;
+ param->cv = state->check;
/* Inflate */
do {
state->bits = param->sbb;
state->whave = param->hl;
state->write = (param->ho + param->hl) & ((1 << HB_BITS) - 1);
- state->check = state->flags ? REVERSE(param->cv) : param->cv;
+ state->check = param->cv;
if (cc == DFLTCC_CC_OP2_CORRUPT && param->oesc != 0) {
/* Report an error if stream is corrupted */
state->mode = BAD;
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/lib/zlib_dfltcc/dfltcc_syms.c
- *
- * Exported symbols for the s390 zlib dfltcc support.
- *
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/zlib.h>
-#include "dfltcc.h"
-
-EXPORT_SYMBOL(dfltcc_can_deflate);
-EXPORT_SYMBOL(dfltcc_deflate);
-EXPORT_SYMBOL(dfltcc_reset);
-MODULE_LICENSE("GPL");
* may get SIGKILLed if it later faults.
*/
if (outside_reserve) {
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t idx;
+ u32 hash;
+
put_page(old_page);
BUG_ON(huge_pte_none(pte));
+ /*
+ * Drop hugetlb_fault_mutex and i_mmap_rwsem before
+ * unmapping. unmapping needs to hold i_mmap_rwsem
+ * in write mode. Dropping i_mmap_rwsem in read mode
+ * here is OK as COW mappings do not interact with
+ * PMD sharing.
+ *
+ * Reacquire both after unmap operation.
+ */
+ idx = vma_hugecache_offset(h, vma, haddr);
+ hash = hugetlb_fault_mutex_hash(mapping, idx);
+ mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ i_mmap_unlock_read(mapping);
+
unmap_ref_private(mm, vma, old_page, haddr);
- BUG_ON(huge_pte_none(pte));
+
+ i_mmap_lock_read(mapping);
+ mutex_lock(&hugetlb_fault_mutex_table[hash]);
spin_lock(ptl);
ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
if (likely(ptep &&
* So we need to block hugepage fault by PG_hwpoison bit check.
*/
if (unlikely(PageHWPoison(page))) {
- ret = VM_FAULT_HWPOISON |
+ ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto backout_unlocked;
}
cache = page->slab_cache;
object = nearest_obj(cache, page, addr);
alloc_meta = kasan_get_alloc_meta(cache, object);
+ if (!alloc_meta)
+ return;
alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT);
return false;
}
#endif
-pte_t kasan_early_shadow_pte[PTRS_PER_PTE] __page_aligned_bss;
+pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+ __page_aligned_bss;
static inline bool kasan_pte_table(pmd_t pmd)
{
goto retry;
}
} else if (ret == -EIO) {
- pr_info("%s: %#lx: unknown page type: %lx (%pGP)\n",
+ pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n",
__func__, pfn, page->flags, &page->flags);
}
entry = mk_pte(new_page, vma->vm_page_prot);
entry = pte_sw_mkyoung(entry);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+
/*
* Clear the pte entry and flush it first, before updating the
- * pte with the new entry. This will avoid a race condition
- * seen in the presence of one thread doing SMC and another
- * thread doing COW.
+ * pte with the new entry, to keep TLBs on different CPUs in
+ * sync. This code used to set the new PTE then flush TLBs, but
+ * that left a window where the new PTE could be loaded into
+ * some TLBs while the old PTE remains in others.
*/
ptep_clear_flush_notify(vma, vmf->address, vmf->pte);
page_add_new_anon_rmap(new_page, vma, vmf->address, false);
* expects the zone spans the pfn range. All the pages in the range
* are reserved so nobody should be touching them so we should be safe
*/
- memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
+ memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0,
MEMINIT_HOTPLUG, altmap, migratetype);
set_zone_contiguous(zone);
const nodemask_t *to, int flags)
{
int busy = 0;
- int err;
+ int err = 0;
nodemask_t tmp;
migrate_prep();
next = (old_addr + size) & mask;
/* even if next overflowed, extent below will be ok */
- extent = (next > old_end) ? old_end - old_addr : next - old_addr;
+ extent = next - old_addr;
+ if (extent > old_end - old_addr)
+ extent = old_end - old_addr;
next = (new_addr + size) & mask;
if (extent > next - new_addr)
extent = next - new_addr;
*/
void wait_on_page_writeback(struct page *page)
{
- if (PageWriteback(page)) {
+ while (PageWriteback(page)) {
trace_wait_on_page_writeback(page, page_mapping(page));
wait_on_page_bit(page, PG_writeback);
}
if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
return false;
+ if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+ return true;
/*
* We start only with one section of pages, more pages are added as
* needed until the rest of deferred pages are initialized.
{
struct page *page;
-#ifdef CONFIG_CMA
- /*
- * Balance movable allocations between regular and CMA areas by
- * allocating from CMA when over half of the zone's free memory
- * is in the CMA area.
- */
- if (alloc_flags & ALLOC_CMA &&
- zone_page_state(zone, NR_FREE_CMA_PAGES) >
- zone_page_state(zone, NR_FREE_PAGES) / 2) {
- page = __rmqueue_cma_fallback(zone, order);
- if (page)
- return page;
+ if (IS_ENABLED(CONFIG_CMA)) {
+ /*
+ * Balance movable allocations between regular and CMA areas by
+ * allocating from CMA when over half of the zone's free memory
+ * is in the CMA area.
+ */
+ if (alloc_flags & ALLOC_CMA &&
+ zone_page_state(zone, NR_FREE_CMA_PAGES) >
+ zone_page_state(zone, NR_FREE_PAGES) / 2) {
+ page = __rmqueue_cma_fallback(zone, order);
+ if (page)
+ goto out;
+ }
}
-#endif
retry:
page = __rmqueue_smallest(zone, order, migratetype);
if (unlikely(!page)) {
alloc_flags))
goto retry;
}
-
- trace_mm_page_alloc_zone_locked(page, order, migratetype);
+out:
+ if (page)
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
* zone stats (e.g., nr_isolate_pageblock) are touched.
*/
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
- unsigned long start_pfn,
+ unsigned long start_pfn, unsigned long zone_end_pfn,
enum meminit_context context,
struct vmem_altmap *altmap, int migratetype)
{
if (context == MEMINIT_EARLY) {
if (overlap_memmap_init(zone, &pfn))
continue;
- if (defer_init(nid, pfn, end_pfn))
+ if (defer_init(nid, pfn, zone_end_pfn))
break;
}
if (end_pfn > start_pfn) {
size = end_pfn - start_pfn;
- memmap_init_zone(size, nid, zone, start_pfn,
+ memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn,
MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
}
}
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
+#include <linux/compat.h>
#include <linux/sched/mm.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
else
page = __alloc_pages_node(node, flags, order);
- if (page)
- account_slab_page(page, order, s);
-
return page;
}
page->objects = oo_objects(oo);
+ account_slab_page(page, oo_order(oo), s);
+
page->slab_cache = s;
__SetPageSlab(page);
if (page_is_pfmemalloc(page))
t = acquire_slab(s, n, page, object == NULL, &objects);
if (!t)
- break;
+ continue; /* cmpxchg raced */
available += objects;
if (!object) {
return NULL;
}
- if (flags & VM_MAP_PUT_PAGES)
+ if (flags & VM_MAP_PUT_PAGES) {
area->pages = pages;
+ area->nr_pages = count;
+ }
return area->addr;
}
EXPORT_SYMBOL(vmap);
if (!PageSwapCache(page)) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
+ if (page_maybe_dma_pinned(page))
+ goto keep_locked;
if (PageTransHuge(page)) {
/* cannot split THP, skip it */
if (!can_split_huge_page(page, NULL))
return 0;
out_free_newdev:
- if (new_dev->reg_state == NETREG_UNINITIALIZED)
- free_netdev(new_dev);
+ free_netdev(new_dev);
return err;
}
kattr->test.repeat)
return -EINVAL;
- if (ctx_size_in < prog->aux->max_ctx_offset)
+ if (ctx_size_in < prog->aux->max_ctx_offset ||
+ ctx_size_in > MAX_BPF_FUNC_ARGS * sizeof(u64))
return -EINVAL;
if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0)
if (peer)
return -EOPNOTSUPP;
+ memset(addr, 0, sizeof(*addr));
addr->can_family = AF_CAN;
addr->can_ifindex = so->ifindex;
addr->can_addr.tp.rx_id = so->rxid;
void *buf;
int ret;
- buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE, false));
+ buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE,
+ con_secure(con)));
if (!buf)
return -ENOMEM;
return -EINVAL;
}
+/*
+ * Align session_key and con_secret to avoid GFP_ATOMIC allocation
+ * inside crypto_shash_setkey() and crypto_aead_setkey() called from
+ * setup_crypto(). __aligned(16) isn't guaranteed to work for stack
+ * objects, so do it by hand.
+ */
static int process_auth_done(struct ceph_connection *con, void *p, void *end)
{
- u8 session_key[CEPH_KEY_LEN];
- u8 con_secret[CEPH_MAX_CON_SECRET_LEN];
+ u8 session_key_buf[CEPH_KEY_LEN + 16];
+ u8 con_secret_buf[CEPH_MAX_CON_SECRET_LEN + 16];
+ u8 *session_key = PTR_ALIGN(&session_key_buf[0], 16);
+ u8 *con_secret = PTR_ALIGN(&con_secret_buf[0], 16);
int session_key_len, con_secret_len;
int payload_len;
u64 global_id;
}
}
- if ((features & NETIF_F_HW_TLS_TX) && !(features & NETIF_F_HW_CSUM)) {
- netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
- features &= ~NETIF_F_HW_TLS_TX;
+ if (features & NETIF_F_HW_TLS_TX) {
+ bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
+ (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+ bool hw_csum = features & NETIF_F_HW_CSUM;
+
+ if (!ip_csum && !hw_csum) {
+ netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+ features &= ~NETIF_F_HW_TLS_TX;
+ }
+ }
+
+ if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) {
+ netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n");
+ features &= ~NETIF_F_HW_TLS_RX;
}
return features;
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
ret = notifier_to_errno(ret);
if (ret) {
+ /* Expect explicit free_netdev() on failure */
+ dev->needs_free_netdev = false;
rollback_registered(dev);
- rcu_barrier();
-
- dev->reg_state = NETREG_UNREGISTERED;
- /* We should put the kobject that hold in
- * netdev_unregister_kobject(), otherwise
- * the net device cannot be freed when
- * driver calls free_netdev(), because the
- * kobject is being hold.
- */
- kobject_put(&dev->dev.kobj);
+ net_set_todo(dev);
+ goto out;
}
/*
* Prevent userspace races by waiting until the network
struct napi_struct *p, *n;
might_sleep();
+
+ /* When called immediately after register_netdevice() failed the unwind
+ * handling may still be dismantling the device. Handle that case by
+ * deferring the free.
+ */
+ if (dev->reg_state == NETREG_UNREGISTERING) {
+ ASSERT_RTNL();
+ dev->needs_free_netdev = true;
+ return;
+ }
+
netif_free_tx_queues(dev);
netif_free_rx_queues(dev);
static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
struct genl_info *info)
{
- struct devlink_port *devlink_port = info->user_ptr[0];
+ struct devlink_port *devlink_port = info->user_ptr[1];
struct devlink_param_item *param_item;
struct sk_buff *msg;
int err;
static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
struct genl_info *info)
{
- struct devlink_port *devlink_port = info->user_ptr[0];
+ struct devlink_port *devlink_port = info->user_ptr[1];
return __devlink_nl_cmd_param_set_doit(devlink_port->devlink,
devlink_port->index,
u64 rate, brate;
est_fetch_counters(est, &b);
- brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log);
- brate -= (est->avbps >> est->ewma_log);
+ brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log);
+ brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log);
- rate = (b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
- rate -= (est->avpps >> est->ewma_log);
+ rate = (b.packets - est->last_packets) << (10 - est->intvl_log);
+ rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log);
write_seqcount_begin(&est->seq);
est->avbps += brate;
if (parm->interval < -2 || parm->interval > 3)
return -EINVAL;
+ if (parm->ewma_log == 0 || parm->ewma_log >= 31)
+ return -EINVAL;
+
est = kzalloc(sizeof(*est), GFP_KERNEL);
if (!est)
return -ENOBUFS;
void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
struct sk_buff *skb)
{
- unsigned long now = jiffies;
-
- unsigned long sched_next = now + (prandom_u32() %
- NEIGH_VAR(p, PROXY_DELAY));
+ unsigned long sched_next = jiffies +
+ prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
kfree_skb(skb);
static ssize_t xps_cpus_show(struct netdev_queue *queue,
char *buf)
{
+ int cpu, len, ret, num_tc = 1, tc = 0;
struct net_device *dev = queue->dev;
- int cpu, len, num_tc = 1, tc = 0;
struct xps_dev_maps *dev_maps;
cpumask_var_t mask;
unsigned long index;
index = get_netdev_queue_index(queue);
+ if (!rtnl_trylock())
+ return restart_syscall();
+
if (dev->num_tc) {
/* Do not allow XPS on subordinate device directly */
num_tc = dev->num_tc;
- if (num_tc < 0)
- return -EINVAL;
+ if (num_tc < 0) {
+ ret = -EINVAL;
+ goto err_rtnl_unlock;
+ }
/* If queue belongs to subordinate dev use its map */
dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
tc = netdev_txq_to_tc(dev, index);
- if (tc < 0)
- return -EINVAL;
+ if (tc < 0) {
+ ret = -EINVAL;
+ goto err_rtnl_unlock;
+ }
}
- if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
- return -ENOMEM;
+ if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto err_rtnl_unlock;
+ }
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_cpus_map);
}
rcu_read_unlock();
+ rtnl_unlock();
+
len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
free_cpumask_var(mask);
return len < PAGE_SIZE ? len : -EINVAL;
+
+err_rtnl_unlock:
+ rtnl_unlock();
+ return ret;
}
static ssize_t xps_cpus_store(struct netdev_queue *queue,
return err;
}
+ if (!rtnl_trylock()) {
+ free_cpumask_var(mask);
+ return restart_syscall();
+ }
+
err = netif_set_xps_queue(dev, mask, index);
+ rtnl_unlock();
free_cpumask_var(mask);
static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
{
+ int j, len, ret, num_tc = 1, tc = 0;
struct net_device *dev = queue->dev;
struct xps_dev_maps *dev_maps;
unsigned long *mask, index;
- int j, len, num_tc = 1, tc = 0;
index = get_netdev_queue_index(queue);
+ if (!rtnl_trylock())
+ return restart_syscall();
+
if (dev->num_tc) {
num_tc = dev->num_tc;
tc = netdev_txq_to_tc(dev, index);
- if (tc < 0)
- return -EINVAL;
+ if (tc < 0) {
+ ret = -EINVAL;
+ goto err_rtnl_unlock;
+ }
}
mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL);
- if (!mask)
- return -ENOMEM;
+ if (!mask) {
+ ret = -ENOMEM;
+ goto err_rtnl_unlock;
+ }
rcu_read_lock();
dev_maps = rcu_dereference(dev->xps_rxqs_map);
out_no_maps:
rcu_read_unlock();
+ rtnl_unlock();
+
len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
bitmap_free(mask);
return len < PAGE_SIZE ? len : -EINVAL;
+
+err_rtnl_unlock:
+ rtnl_unlock();
+ return ret;
}
static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
return err;
}
+ if (!rtnl_trylock()) {
+ bitmap_free(mask);
+ return restart_syscall();
+ }
+
cpus_read_lock();
err = __netif_set_xps_queue(dev, mask, index, true);
cpus_read_unlock();
+ rtnl_unlock();
+
bitmap_free(mask);
return err ? : len;
}
dev->ifindex = ifm->ifi_index;
- if (ops->newlink) {
+ if (ops->newlink)
err = ops->newlink(link_net ? : net, dev, tb, data, extack);
- /* Drivers should call free_netdev() in ->destructor
- * and unregister it on failure after registration
- * so that device could be finally freed in rtnl_unlock.
- */
- if (err < 0) {
- /* If device is not registered at all, free it now */
- if (dev->reg_state == NETREG_UNINITIALIZED ||
- dev->reg_state == NETREG_UNREGISTERED)
- free_netdev(dev);
- goto out;
- }
- } else {
+ else
err = register_netdevice(dev);
- if (err < 0) {
- free_netdev(dev);
- goto out;
- }
+ if (err < 0) {
+ free_netdev(dev);
+ goto out;
}
+
err = rtnl_configure_link(dev, ifm);
if (err < 0)
goto out_unregister;
len += NET_SKB_PAD;
- if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+ /* If requested length is either too small or too big,
+ * we use kmalloc() for skb->head allocation.
+ */
+ if (len <= SKB_WITH_OVERHEAD(1024) ||
+ len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
(gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
if (!skb)
struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
gfp_t gfp_mask)
{
- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+ struct napi_alloc_cache *nc;
struct sk_buff *skb;
void *data;
len += NET_SKB_PAD + NET_IP_ALIGN;
- if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+ /* If requested length is either too small or too big,
+ * we use kmalloc() for skb->head allocation.
+ */
+ if (len <= SKB_WITH_OVERHEAD(1024) ||
+ len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
(gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
if (!skb)
goto skb_success;
}
+ nc = this_cpu_ptr(&napi_alloc_cache);
len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
len = SKB_DATA_ALIGN(len);
st->root_skb = st->cur_skb = skb;
st->frag_idx = st->stepped_offset = 0;
st->frag_data = NULL;
+ st->frag_off = 0;
}
EXPORT_SYMBOL(skb_prepare_seq_read);
st->stepped_offset += skb_headlen(st->cur_skb);
while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+ unsigned int pg_idx, pg_off, pg_sz;
+
frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
- block_limit = skb_frag_size(frag) + st->stepped_offset;
+ pg_idx = 0;
+ pg_off = skb_frag_off(frag);
+ pg_sz = skb_frag_size(frag);
+
+ if (skb_frag_must_loop(skb_frag_page(frag))) {
+ pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
+ pg_off = offset_in_page(pg_off + st->frag_off);
+ pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
+ PAGE_SIZE - pg_off);
+ }
+
+ block_limit = pg_sz + st->stepped_offset;
if (abs_offset < block_limit) {
if (!st->frag_data)
- st->frag_data = kmap_atomic(skb_frag_page(frag));
+ st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
- *data = (u8 *) st->frag_data + skb_frag_off(frag) +
+ *data = (u8 *)st->frag_data + pg_off +
(abs_offset - st->stepped_offset);
return block_limit - abs_offset;
st->frag_data = NULL;
}
- st->frag_idx++;
- st->stepped_offset += skb_frag_size(frag);
+ st->stepped_offset += pg_sz;
+ st->frag_off += pg_sz;
+ if (st->frag_off == skb_frag_size(frag)) {
+ st->frag_off = 0;
+ st->frag_idx++;
+ }
}
if (st->frag_data) {
unsigned int delta_truesize = 0;
unsigned int delta_len = 0;
struct sk_buff *tail = NULL;
- struct sk_buff *nskb;
+ struct sk_buff *nskb, *tmp;
+ int err;
skb_push(skb, -skb_network_offset(skb) + offset);
nskb = list_skb;
list_skb = list_skb->next;
+ err = 0;
+ if (skb_shared(nskb)) {
+ tmp = skb_clone(nskb, GFP_ATOMIC);
+ if (tmp) {
+ consume_skb(nskb);
+ nskb = tmp;
+ err = skb_unclone(nskb, GFP_ATOMIC);
+ } else {
+ err = -ENOMEM;
+ }
+ }
+
if (!tail)
skb->next = nskb;
else
tail->next = nskb;
+ if (unlikely(err)) {
+ nskb->next = list_skb;
+ goto err_linearize;
+ }
+
tail = nskb;
delta_len += nskb->len;
i = j = reciprocal_scale(hash, socks);
while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
i++;
- if (i >= reuse->num_socks)
+ if (i >= socks)
i = 0;
if (i == j)
goto out;
fn = &reply_funcs[dcb->cmd];
if (!fn->cb)
return -EOPNOTSUPP;
+ if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN))
+ return -EPERM;
if (!tb[DCB_ATTR_IFNAME])
return -EINVAL;
static void dsa_port_teardown(struct dsa_port *dp)
{
+ struct devlink_port *dlp = &dp->devlink_port;
+
if (!dp->setup)
return;
+ devlink_port_type_clear(dlp);
+
switch (dp->type) {
case DSA_PORT_TYPE_UNUSED:
break;
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
+ struct dsa_switch *ds = cpu_dp->ds;
+ struct device_link *consumer_link;
int ret;
+ /* The DSA master must use SET_NETDEV_DEV for this to work. */
+ consumer_link = device_link_add(ds->dev, dev->dev.parent,
+ DL_FLAG_AUTOREMOVE_CONSUMER);
+ if (!consumer_link)
+ netdev_err(dev,
+ "Failed to create a device link to DSA switch %s\n",
+ dev_name(ds->dev));
+
rtnl_lock();
ret = dev_set_mtu(dev, mtu);
rtnl_unlock();
int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
{
u8 *tail;
- u8 *vaddr;
int nfrags;
int esph_offset;
struct page *page;
page = pfrag->page;
get_page(page);
- vaddr = kmap_atomic(page);
-
- tail = vaddr + pfrag->offset;
+ tail = page_address(page) + pfrag->offset;
esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
- kunmap_atomic(vaddr);
-
nfrags = skb_shinfo(skb)->nr_frags;
__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
.daddr = ip_hdr(skb)->saddr,
- .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+ .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK,
.flowi4_scope = scope,
.flowi4_mark = vmark ? skb->mark : 0,
};
* to 0 and sets the configured key in the
* inner erspan header field
*/
- if (greh->protocol == htons(ETH_P_ERSPAN) ||
+ if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) ||
greh->protocol == htons(ETH_P_ERSPAN2)) {
struct erspan_base_hdr *ershdr;
newicsk->icsk_retransmits = 0;
newicsk->icsk_backoff = 0;
newicsk->icsk_probes_out = 0;
+ newicsk->icsk_probes_tstamp = 0;
/* Deinitialize accept_queue to trap illegal accesses. */
memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
if (skb_is_gso(skb))
return ip_finish_output_gso(net, sk, skb, mtu);
- if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+ if (skb->len > mtu || IPCB(skb)->frag_max_size)
return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
return ip_finish_output2(net, sk, skb);
goto tx_error;
}
- if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
- 0, 0, false)) {
+ df = tnl_params->frag_off;
+ if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+ df |= (inner_iph->frag_off & htons(IP_DF));
+
+ if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
ip_rt_put(rt);
goto tx_error;
}
ttl = ip4_dst_hoplimit(&rt->dst);
}
- df = tnl_params->frag_off;
- if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
- df |= (inner_iph->frag_off&htons(IP_DF));
-
max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
if (max_headroom > dev->needed_headroom)
xt_compat_lock(NFPROTO_ARP);
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
struct xt_table_info info;
ret = compat_table_info(private, &info);
xt_compat_lock(AF_INET);
t = xt_find_table_lock(net, AF_INET, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
struct xt_table_info info;
ret = compat_table_info(private, &info);
if (!ret && get.size == info.size)
flow.daddr = iph->saddr;
flow.saddr = rpfilter_get_saddr(iph->daddr);
flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
- flow.flowi4_tos = RT_TOS(iph->tos);
+ flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
if (!tb[i])
continue;
- if (tb[NHA_FDB])
+ if (i == NHA_FDB)
continue;
NL_SET_ERR_MSG(extack,
"No other attributes can be set in nexthop groups");
return nh;
out_no_nh:
- for (; i >= 0; --i)
+ for (i--; i >= 0; --i) {
+ list_del(&nhg->nh_entries[i].nh_list);
nexthop_put(nhg->nh_entries[i].nh);
+ }
kfree(nhg->spare);
kfree(nhg);
icsk->icsk_backoff = 0;
icsk->icsk_probes_out = 0;
+ icsk->icsk_probes_tstamp = 0;
icsk->icsk_rto = TCP_TIMEOUT_INIT;
icsk->icsk_rto_min = TCP_RTO_MIN;
icsk->icsk_delack_max = TCP_DELACK_MAX;
return;
if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
icsk->icsk_backoff = 0;
+ icsk->icsk_probes_tstamp = 0;
inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
/* Socket must be waked up by subsequent tcp_data_snd_check().
* This function is not for random using!
* The receiver remembers and reflects via DSACKs. Leverage the
* DSACK state and change the txhash to re-route speculatively.
*/
- if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) {
- sk_rethink_txhash(sk);
+ if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq &&
+ sk_rethink_txhash(sk))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
- }
}
static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
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;
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
+ u32 tail_gso_size, tail_gso_segs;
struct skb_shared_info *shinfo;
const struct tcphdr *th;
struct tcphdr *thtail;
unsigned int hdrlen;
bool fragstolen;
u32 gso_segs;
+ u32 gso_size;
int delta;
/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
*/
th = (const struct tcphdr *)skb->data;
hdrlen = th->doff * 4;
- shinfo = skb_shinfo(skb);
-
- if (!shinfo->gso_size)
- shinfo->gso_size = skb->len - hdrlen;
-
- if (!shinfo->gso_segs)
- shinfo->gso_segs = 1;
tail = sk->sk_backlog.tail;
if (!tail)
goto no_coalesce;
__skb_pull(skb, hdrlen);
+
+ shinfo = skb_shinfo(skb);
+ gso_size = shinfo->gso_size ?: skb->len;
+ gso_segs = shinfo->gso_segs ?: 1;
+
+ shinfo = skb_shinfo(tail);
+ tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen);
+ tail_gso_segs = shinfo->gso_segs ?: 1;
+
if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq;
}
/* Not as strict as GRO. We only need to carry mss max value */
- skb_shinfo(tail)->gso_size = max(shinfo->gso_size,
- skb_shinfo(tail)->gso_size);
-
- gso_segs = skb_shinfo(tail)->gso_segs + shinfo->gso_segs;
- skb_shinfo(tail)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+ shinfo->gso_size = max(gso_size, tail_gso_size);
+ shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF);
sk->sk_backlog.len += delta;
__NET_INC_STATS(sock_net(sk),
/* Cancel probe timer, if it is not required. */
icsk->icsk_probes_out = 0;
icsk->icsk_backoff = 0;
+ icsk->icsk_probes_tstamp = 0;
return;
}
int retry_until;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
- if (icsk->icsk_retransmits) {
- dst_negative_advice(sk);
- } else {
- sk_rethink_txhash(sk);
- tp->timeout_rehash++;
- __NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPTIMEOUTREHASH);
- }
+ if (icsk->icsk_retransmits)
+ __dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
expired = icsk->icsk_retransmits >= retry_until;
} else {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
- dst_negative_advice(sk);
- } else {
- sk_rethink_txhash(sk);
- tp->timeout_rehash++;
- __NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPTIMEOUTREHASH);
+ __dst_negative_advice(sk);
}
retry_until = net->ipv4.sysctl_tcp_retries2;
return 1;
}
+ if (sk_rethink_txhash(sk)) {
+ tp->timeout_rehash++;
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH);
+ }
+
return 0;
}
if (tp->packets_out || !skb) {
icsk->icsk_probes_out = 0;
+ icsk->icsk_probes_tstamp = 0;
return;
}
* corresponding system limit. We also implement similar policy when
* we use RTO to probe window in tcp_retransmit_timer().
*/
- if (icsk->icsk_user_timeout) {
- u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out,
- tcp_probe0_base(sk));
-
- if (elapsed >= icsk->icsk_user_timeout)
- goto abort;
- }
+ if (!icsk->icsk_probes_tstamp)
+ icsk->icsk_probes_tstamp = tcp_jiffies32;
+ else if (icsk->icsk_user_timeout &&
+ (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
+ msecs_to_jiffies(icsk->icsk_user_timeout))
+ goto abort;
max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
*/
if (!inet_sk(sk)->inet_daddr && in_dev)
return ip_mc_validate_source(skb, iph->daddr,
- iph->saddr, iph->tos,
+ iph->saddr,
+ iph->tos & IPTOS_RT_MASK,
skb->dev, in_dev, &itag);
}
return 0;
.fc_ifindex = dev->ifindex,
.fc_dst_len = 8,
.fc_flags = RTF_UP,
- .fc_type = RTN_UNICAST,
+ .fc_type = RTN_MULTICAST,
.fc_nlinfo.nl_net = dev_net(dev),
+ .fc_protocol = RTPROT_KERNEL,
};
ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0);
int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
{
u8 *tail;
- u8 *vaddr;
int nfrags;
int esph_offset;
struct page *page;
page = pfrag->page;
get_page(page);
- vaddr = kmap_atomic(page);
-
- tail = vaddr + pfrag->offset;
+ tail = page_address(page) + pfrag->offset;
esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
- kunmap_atomic(vaddr);
-
nfrags = skb_shinfo(skb)->nr_frags;
__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
{
struct fib6_table *table = rt->fib6_table;
+ /* Flush all cached dst in exception table */
+ rt6_flush_exceptions(rt);
fib6_drop_pcpu_from(rt, table);
if (rt->nh && !list_empty(&rt->nh_list))
net->ipv6.rt6_stats->fib_rt_entries--;
net->ipv6.rt6_stats->fib_discarded_routes++;
- /* Flush all cached dst in exception table */
- rt6_flush_exceptions(rt);
-
/* Reset round-robin state, if necessary */
if (rcu_access_pointer(fn->rr_ptr) == rt)
fn->rr_ptr = NULL;
return -EINVAL;
}
+static int
+ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
+ struct sk_buff *skb, unsigned int mtu)
+{
+ struct sk_buff *segs, *nskb;
+ netdev_features_t features;
+ int ret = 0;
+
+ /* Please see corresponding comment in ip_finish_output_gso
+ * describing the cases where GSO segment length exceeds the
+ * egress MTU.
+ */
+ features = netif_skb_features(skb);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR_OR_NULL(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ skb_list_walk_safe(segs, segs, nskb) {
+ int err;
+
+ skb_mark_not_on_list(segs);
+ err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+ if (err && ret == 0)
+ ret = err;
+ }
+
+ return ret;
+}
+
static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ unsigned int mtu;
+
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
/* Policy lookup after SNAT yielded a new policy */
if (skb_dst(skb)->xfrm) {
}
#endif
- if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+ mtu = ip6_skb_dst_mtu(skb);
+ if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+ return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+ if ((skb->len > mtu && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
return ip6_fragment(net, sk, skb, ip6_finish_output2);
xt_compat_lock(AF_INET6);
t = xt_find_table_lock(net, AF_INET6, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = t->private;
+ const struct xt_table_info *private = xt_table_get_private_protected(t);
struct xt_table_info info;
ret = compat_table_info(private, &info);
if (!ret && get.size == info.size)
}
#ifdef CONFIG_IPV6_SIT_6RD
- if (ipip6_netlink_6rd_parms(data, &ip6rd))
+ if (ipip6_netlink_6rd_parms(data, &ip6rd)) {
err = ipip6_tunnel_update_6rd(nt, &ip6rd);
+ if (err < 0)
+ unregister_netdevice_queue(dev, NULL);
+ }
#endif
return err;
break;
}
+ lapb_put(lapb);
return NOTIFY_DONE;
}
{
struct ieee80211_local *local = file->private_data;
char buf[100];
- size_t len;
- if (count > sizeof(buf))
+ if (count >= sizeof(buf))
return -EINVAL;
if (copy_from_user(buf, user_buf, count))
return -EFAULT;
- buf[sizeof(buf) - 1] = '\0';
- len = strlen(buf);
- if (len > 0 && buf[len-1] == '\n')
- buf[len-1] = 0;
+ if (count && buf[count - 1] == '\n')
+ buf[count - 1] = '\0';
+ else
+ buf[count] = '\0';
if (sscanf(buf, "fq_limit %u", &local->fq.limit) == 1)
return count;
{
struct ieee80211_local *local = file->private_data;
char buf[16];
- size_t len;
- if (count > sizeof(buf))
+ if (count >= sizeof(buf))
return -EINVAL;
if (copy_from_user(buf, user_buf, count))
return -EFAULT;
- buf[sizeof(buf) - 1] = 0;
- len = strlen(buf);
- if (len > 0 && buf[len - 1] == '\n')
- buf[len - 1] = 0;
+ if (count && buf[count - 1] == '\n')
+ buf[count - 1] = '\0';
+ else
+ buf[count] = '\0';
if (kstrtou16(buf, 0, &local->airtime_flags))
return -EINVAL;
{
struct ieee80211_local *local = file->private_data;
char buf[100];
- size_t len;
u32 ac, q_limit_low, q_limit_high, q_limit_low_old, q_limit_high_old;
struct sta_info *sta;
- if (count > sizeof(buf))
+ if (count >= sizeof(buf))
return -EINVAL;
if (copy_from_user(buf, user_buf, count))
return -EFAULT;
- buf[sizeof(buf) - 1] = 0;
- len = strlen(buf);
- if (len > 0 && buf[len - 1] == '\n')
- buf[len - 1] = 0;
+ if (count && buf[count - 1] == '\n')
+ buf[count - 1] = '\0';
+ else
+ buf[count] = '\0';
if (sscanf(buf, "%u %u %u", &ac, &q_limit_low, &q_limit_high) != 3)
return -EINVAL;
{
struct ieee80211_local *local = file->private_data;
char buf[3];
- size_t len;
- if (count > sizeof(buf))
+ if (count >= sizeof(buf))
return -EINVAL;
if (copy_from_user(buf, user_buf, count))
return -EFAULT;
- buf[sizeof(buf) - 1] = '\0';
- len = strlen(buf);
- if (len > 0 && buf[len - 1] == '\n')
- buf[len - 1] = 0;
+ if (count && buf[count - 1] == '\n')
+ buf[count - 1] = '\0';
+ else
+ buf[count] = '\0';
if (buf[0] == '0' && buf[1] == '\0')
local->force_tx_status = 0;
rcu_read_lock();
key = rcu_dereference(sta->ptk[sta->ptk_idx]);
+ if (!key)
+ key = rcu_dereference(sdata->default_unicast_key);
if (key) {
switch (key->conf.cipher) {
case WLAN_CIPHER_SUITE_TKIP:
if (!skip_hw && tx->key &&
tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)
info->control.hw_key = &tx->key->conf;
- } else if (!ieee80211_is_mgmt(hdr->frame_control) && tx->sta &&
+ } else if (ieee80211_is_data_present(hdr->frame_control) && tx->sta &&
test_sta_flag(tx->sta, WLAN_STA_USES_ENCRYPTION)) {
return TX_DROP;
}
* get immediately moved to the back of the list on the next
* call to ieee80211_next_txq().
*/
- if (txqi->txq.sta &&
+ if (txqi->txq.sta && local->airtime_flags &&
wiphy_ext_feature_isset(local->hw.wiphy,
NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
list_add(&txqi->schedule_order,
struct ethhdr *ehdr = (struct ethhdr *)skb->data;
struct ieee80211_key *key;
struct sta_info *sta;
- bool offload = true;
if (unlikely(skb->len < ETH_HLEN)) {
kfree_skb(skb);
if (unlikely(IS_ERR_OR_NULL(sta) || !sta->uploaded ||
!test_sta_flag(sta, WLAN_STA_AUTHORIZED) ||
- sdata->control_port_protocol == ehdr->h_proto))
- offload = false;
- else if ((key = rcu_dereference(sta->ptk[sta->ptk_idx])) &&
- (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) ||
- key->conf.cipher == WLAN_CIPHER_SUITE_TKIP))
- offload = false;
-
- if (offload)
- ieee80211_8023_xmit(sdata, dev, sta, key, skb);
- else
- ieee80211_subif_start_xmit(skb, dev);
+ sdata->control_port_protocol == ehdr->h_proto))
+ goto skip_offload;
+
+ key = rcu_dereference(sta->ptk[sta->ptk_idx]);
+ if (!key)
+ key = rcu_dereference(sdata->default_unicast_key);
+
+ if (key && (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) ||
+ key->conf.cipher == WLAN_CIPHER_SUITE_TKIP))
+ goto skip_offload;
+
+ ieee80211_8023_xmit(sdata, dev, sta, key, skb);
+ goto out;
+skip_offload:
+ ieee80211_subif_start_xmit(skb, dev);
out:
rcu_read_unlock();
static bool tcp_can_send_ack(const struct sock *ssk)
{
return !((1 << inet_sk_state_load(ssk)) &
- (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE));
+ (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
}
static void mptcp_send_ack(struct mptcp_sock *msk)
struct mptcp_sock *msk = mptcp_sk(sk);
WARN_ON_ONCE(msk->wmem_reserved);
+ if (WARN_ON_ONCE(amount < 0))
+ amount = 0;
+
if (amount <= sk->sk_forward_alloc)
goto reserve;
if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
return -EOPNOTSUPP;
- mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, len));
+ mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, min_t(size_t, 1 << 20, len)));
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
static int mptcp_disconnect(struct sock *sk, int flags)
{
- /* Should never be called.
- * inet_stream_connect() calls ->disconnect, but that
- * refers to the subflow socket, not the mptcp one.
- */
- WARN_ON_ONCE(1);
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+ __mptcp_flush_join_list(msk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+ lock_sock(ssk);
+ tcp_disconnect(ssk, flags);
+ release_sock(ssk);
+ }
return 0;
}
return true;
}
+static void mptcp_shutdown(struct sock *sk, int how)
+{
+ pr_debug("sk=%p, how=%d", sk, how);
+
+ if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
+}
+
static struct proto mptcp_prot = {
.name = "MPTCP",
.owner = THIS_MODULE,
.accept = mptcp_accept,
.setsockopt = mptcp_setsockopt,
.getsockopt = mptcp_getsockopt,
- .shutdown = tcp_shutdown,
+ .shutdown = mptcp_shutdown,
.destroy = mptcp_destroy,
.sendmsg = mptcp_sendmsg,
.recvmsg = mptcp_recvmsg,
return mask;
}
-static int mptcp_shutdown(struct socket *sock, int how)
-{
- struct mptcp_sock *msk = mptcp_sk(sock->sk);
- struct sock *sk = sock->sk;
- int ret = 0;
-
- pr_debug("sk=%p, how=%d", msk, how);
-
- lock_sock(sk);
-
- how++;
- if ((how & ~SHUTDOWN_MASK) || !how) {
- ret = -EINVAL;
- goto out_unlock;
- }
-
- if (sock->state == SS_CONNECTING) {
- if ((1 << sk->sk_state) &
- (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
- sock->state = SS_DISCONNECTING;
- else
- sock->state = SS_CONNECTED;
- }
-
- sk->sk_shutdown |= how;
- if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
- __mptcp_wr_shutdown(sk);
-
- /* Wake up anyone sleeping in poll. */
- sk->sk_state_change(sk);
-
-out_unlock:
- release_sock(sk);
-
- return ret;
-}
-
static const struct proto_ops mptcp_stream_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.ioctl = inet_ioctl,
.gettstamp = sock_gettstamp,
.listen = mptcp_listen,
- .shutdown = mptcp_shutdown,
+ .shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.ioctl = inet6_ioctl,
.gettstamp = sock_gettstamp,
.listen = mptcp_listen,
- .shutdown = mptcp_shutdown,
+ .shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet6_sendmsg,
int payload, i, ret;
/* Find the NCSI device */
- nd = ncsi_find_dev(dev);
+ nd = ncsi_find_dev(orig_dev);
ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL;
if (!ndp)
return -ENODEV;
return hsize * sizeof(struct hbucket *) + sizeof(struct htable);
}
-/* Compute htable_bits from the user input parameter hashsize */
-static u8
-htable_bits(u32 hashsize)
-{
- /* Assume that hashsize == 2^htable_bits */
- u8 bits = fls(hashsize - 1);
-
- if (jhash_size(bits) != hashsize)
- /* Round up to the first 2^n value */
- bits = fls(hashsize);
-
- return bits;
-}
-
#ifdef IP_SET_HASH_WITH_NETS
#if IPSET_NET_COUNT > 1
#define __CIDR(cidr, i) (cidr[i])
struct htype *h = set->data;
struct htable *t, *orig;
u8 htable_bits;
- size_t dsize = set->dsize;
+ size_t hsize, dsize = set->dsize;
#ifdef IP_SET_HASH_WITH_NETS
u8 flags;
struct mtype_elem *tmp;
retry:
ret = 0;
htable_bits++;
- if (!htable_bits) {
- /* In case we have plenty of memory :-) */
- pr_warn("Cannot increase the hashsize of set %s further\n",
- set->name);
- ret = -IPSET_ERR_HASH_FULL;
- goto out;
- }
- t = ip_set_alloc(htable_size(htable_bits));
+ if (!htable_bits)
+ goto hbwarn;
+ hsize = htable_size(htable_bits);
+ if (!hsize)
+ goto hbwarn;
+ t = ip_set_alloc(hsize);
if (!t) {
ret = -ENOMEM;
goto out;
if (ret == -EAGAIN)
goto retry;
goto out;
+
+hbwarn:
+ /* In case we have plenty of memory :-) */
+ pr_warn("Cannot increase the hashsize of set %s further\n", set->name);
+ ret = -IPSET_ERR_HASH_FULL;
+ goto out;
}
/* Get the current number of elements and ext_size in the set */
if (!h)
return -ENOMEM;
- hbits = htable_bits(hashsize);
+ /* Compute htable_bits from the user input parameter hashsize.
+ * Assume that hashsize == 2^htable_bits,
+ * otherwise round up to the first 2^n value.
+ */
+ hbits = fls(hashsize - 1);
hsize = htable_size(hbits);
if (hsize == 0) {
kfree(h);
{
int ret;
+ /* module_param hashsize could have changed value */
+ nf_conntrack_htable_size_user = nf_conntrack_htable_size;
+
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret < 0 || !write)
return ret;
ret = register_pernet_subsys(&nat_net_ops);
if (ret < 0) {
nf_ct_extend_unregister(&nat_extend);
+ kvfree(nf_nat_bysource);
return ret;
}
if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT |
NFT_SET_INTERVAL | NFT_SET_TIMEOUT |
NFT_SET_MAP | NFT_SET_EVAL |
- NFT_SET_OBJECT | NFT_SET_CONCAT))
+ NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR))
return -EOPNOTSUPP;
/* Only one of these operations is supported */
if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) ==
struct nlattr *tmp;
int left;
+ if (!(flags & NFT_SET_EXPR)) {
+ err = -EINVAL;
+ goto err_set_alloc_name;
+ }
i = 0;
nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
if (i == NFT_SET_EXPR_MAX) {
return 0;
err_expr:
- for (k = i - 1; k >= 0; k++)
- nft_expr_destroy(ctx, expr_array[i]);
+ for (k = i - 1; k >= 0; k--)
+ nft_expr_destroy(ctx, expr_array[k]);
return -ENOMEM;
}
enum nft_registers sreg_key:8;
enum nft_registers sreg_data:8;
bool invert;
+ bool expr;
u8 num_exprs;
u64 timeout;
struct nft_expr *expr_array[NFT_SET_EXPR_MAX];
if (tb[NFTA_DYNSET_FLAGS]) {
u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS]));
-
- if (flags & ~NFT_DYNSET_F_INV)
- return -EINVAL;
+ if (flags & ~(NFT_DYNSET_F_INV | NFT_DYNSET_F_EXPR))
+ return -EOPNOTSUPP;
if (flags & NFT_DYNSET_F_INV)
priv->invert = true;
+ if (flags & NFT_DYNSET_F_EXPR)
+ priv->expr = true;
}
set = nft_set_lookup_global(ctx->net, ctx->table,
timeout = 0;
if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
if (!(set->flags & NFT_SET_TIMEOUT))
- return -EINVAL;
+ return -EOPNOTSUPP;
err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout);
if (err)
if (tb[NFTA_DYNSET_SREG_DATA] != NULL) {
if (!(set->flags & NFT_SET_MAP))
- return -EINVAL;
+ return -EOPNOTSUPP;
if (set->dtype == NFT_DATA_VERDICT)
return -EOPNOTSUPP;
struct nlattr *tmp;
int left;
+ if (!priv->expr)
+ return -EINVAL;
+
i = 0;
nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) {
if (i == NFT_SET_EXPR_MAX) {
} cfg;
int ret;
+ if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name))
+ return -ENAMETOOLONG;
+
net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
mutex_lock(&xn->hash_lock);
};
unsigned long opt = 0;
- if (!(ndev->nci_ver & NCI_VER_2_MASK))
+ if (ndev->nci_ver & NCI_VER_2_MASK)
opt = (unsigned long)&nci_init_v2_cmd;
rc = __nci_request(ndev, nci_init_req, opt,
static int packet_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
- seq_puts(seq, "sk RefCnt Type Proto Iface R Rmem User Inode\n");
+ seq_printf(seq,
+ "%*sRefCnt Type Proto Iface R Rmem User Inode\n",
+ IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk");
else {
struct sock *s = sk_entry(v);
const struct packet_sock *po = pkt_sk(s);
queue_work(qrtr_ns.workqueue, &qrtr_ns.work);
}
-void qrtr_ns_init(void)
+int qrtr_ns_init(void)
{
struct sockaddr_qrtr sq;
int ret;
ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM,
PF_QIPCRTR, &qrtr_ns.sock);
if (ret < 0)
- return;
+ return ret;
ret = kernel_getsockname(qrtr_ns.sock, (struct sockaddr *)&sq);
if (ret < 0) {
if (ret < 0)
goto err_wq;
- return;
+ return 0;
err_wq:
destroy_workqueue(qrtr_ns.workqueue);
err_sock:
sock_release(qrtr_ns.sock);
+ return ret;
}
EXPORT_SYMBOL_GPL(qrtr_ns_init);
return rc;
rc = sock_register(&qrtr_family);
- if (rc) {
- proto_unregister(&qrtr_proto);
- return rc;
- }
+ if (rc)
+ goto err_proto;
- qrtr_ns_init();
+ rc = qrtr_ns_init();
+ if (rc)
+ goto err_sock;
+ return 0;
+
+err_sock:
+ sock_unregister(qrtr_family.family);
+err_proto:
+ proto_unregister(&qrtr_proto);
return rc;
}
postcore_initcall(qrtr_proto_init);
int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len);
-void qrtr_ns_init(void);
+int qrtr_ns_init(void);
void qrtr_ns_remove(void);
return;
}
- if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+ if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
unsigned long timo = READ_ONCE(call->next_req_timo);
unsigned long now, expect_req_by;
default: /* we have a ticket we can't encode */
pr_err("Unsupported key token type (%u)\n",
token->security_index);
- continue;
+ return -ENOPKG;
}
_debug("token[%u]: toksize=%u", ntoks, toksize);
break;
default:
- break;
+ pr_err("Unsupported key token type (%u)\n",
+ token->security_index);
+ return -ENOPKG;
}
ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==,
nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+ if (!nla_ok(nla_opt_msk, msk_depth)) {
+ NL_SET_ERR_MSG(extack, "Invalid nested attribute for masks");
+ return -EINVAL;
+ }
}
nla_for_each_attr(nla_opt_key, nla_enc_key,
NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
return -EINVAL;
}
-
- if (msk_depth)
- nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
break;
case TCA_FLOWER_KEY_ENC_OPTS_VXLAN:
if (key->enc_opts.dst_opt_type) {
NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
return -EINVAL;
}
-
- if (msk_depth)
- nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
break;
case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN:
if (key->enc_opts.dst_opt_type) {
NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
return -EINVAL;
}
-
- if (msk_depth)
- nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
break;
default:
NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
return -EINVAL;
}
+
+ if (!msk_depth)
+ continue;
+
+ if (!nla_ok(nla_opt_msk, msk_depth)) {
+ NL_SET_ERR_MSG(extack, "A mask attribute is invalid");
+ return -EINVAL;
+ }
+ nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
}
return 0;
if (tb[TCA_TCINDEX_MASK])
cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
- if (tb[TCA_TCINDEX_SHIFT])
+ if (tb[TCA_TCINDEX_SHIFT]) {
cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-
+ if (cp->shift > 16) {
+ err = -EINVAL;
+ goto errout;
+ }
+ }
if (!cp->hash) {
/* Hash not specified, use perfect hash if the upper limit
* of the hashing index is below the threshold.
{
struct qdisc_rate_table *rtab;
- if (tab == NULL || r->rate == 0 || r->cell_log == 0 ||
+ if (tab == NULL || r->rate == 0 ||
+ r->cell_log == 0 || r->cell_log >= 32 ||
nla_len(tab) != TC_RTAB_SIZE) {
NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching");
return NULL;
ctl = nla_data(tb[TCA_CHOKE_PARMS]);
- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+ if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
return -EINVAL;
if (ctl->limit > CHOKE_MAX_QUEUE)
struct gred_sched *table = qdisc_priv(sch);
struct gred_sched_data *q = table->tab[dp];
- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) {
+ if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) {
NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters");
return -EINVAL;
}
max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
ctl = nla_data(tb[TCA_RED_PARMS]);
- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+ if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
return -EINVAL;
err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS,
}
if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
- ctl_v1->Wlog))
+ ctl_v1->Wlog, ctl_v1->Scell_log))
return -EINVAL;
if (ctl_v1 && ctl_v1->qth_min) {
p = kmalloc(sizeof(*p), GFP_KERNEL);
hrtimer_cancel(&q->advance_timer);
if (q->qdiscs) {
- for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++)
- qdisc_reset(q->qdiscs[i]);
+ for (i = 0; i < dev->num_tx_queues; i++)
+ if (q->qdiscs[i])
+ qdisc_reset(q->qdiscs[i]);
}
sch->qstats.backlog = 0;
sch->q.qlen = 0;
taprio_disable_offload(dev, q, NULL);
if (q->qdiscs) {
- for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++)
+ for (i = 0; i < dev->num_tx_queues; i++)
qdisc_put(q->qdiscs[i]);
kfree(q->qdiscs);
goto errattr;
smc_clc_get_hostname(&host);
if (host) {
- snprintf(hostname, sizeof(hostname), "%s", host);
+ memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN);
+ hostname[SMC_MAX_HOSTNAME_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname))
goto errattr;
}
smc_ism_get_system_eid(smcd_dev, &seid);
mutex_unlock(&smcd_dev_list.mutex);
if (seid && smc_ism_is_v2_capable()) {
- snprintf(smc_seid, sizeof(smc_seid), "%s", seid);
+ memcpy(smc_seid, seid, SMC_MAX_EID_LEN);
+ smc_seid[SMC_MAX_EID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid))
goto errattr;
}
goto errattr;
if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id))
goto errattr;
- snprintf(smc_target, sizeof(smc_target), "%s", lgr->pnet_id);
+ memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN);
+ smc_target[SMC_MAX_PNETID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
goto errattr;
struct sk_buff *skb,
struct netlink_callback *cb)
{
- char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+ char smc_ibname[IB_DEVICE_NAME_MAX];
u8 smc_gid_target[41];
struct nlattr *attrs;
u32 link_uid = 0;
goto errattr;
if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
goto errattr;
- snprintf(smc_pnet, sizeof(smc_pnet), "%s", lgr->smcd->pnetid);
+ memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN);
+ smc_pnet[SMC_MAX_PNETID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
goto errattr;
goto errv2attr;
if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os))
goto errv2attr;
- snprintf(smc_host, sizeof(smc_host), "%s", lgr->peer_hostname);
+ memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN);
+ smc_host[SMC_MAX_HOSTNAME_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host))
goto errv2attr;
- snprintf(smc_eid, sizeof(smc_eid), "%s", lgr->negotiated_eid);
+ memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN);
+ smc_eid[SMC_MAX_EID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid))
goto errv2attr;
if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR,
smcibdev->pnetid_by_user[port]))
goto errattr;
- snprintf(smc_pnet, sizeof(smc_pnet), "%s",
- (char *)&smcibdev->pnetid[port]);
+ memcpy(smc_pnet, &smcibdev->pnetid[port], SMC_MAX_PNETID_LEN);
+ smc_pnet[SMC_MAX_PNETID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
goto errattr;
if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV,
struct sk_buff *skb,
struct netlink_callback *cb)
{
- char smc_ibname[IB_DEVICE_NAME_MAX + 1];
+ char smc_ibname[IB_DEVICE_NAME_MAX];
struct smc_pci_dev smc_pci_dev;
struct pci_dev *pci_dev;
unsigned char is_crit;
goto errattr;
if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user))
goto errportattr;
- snprintf(smc_pnet, sizeof(smc_pnet), "%s", smcd->pnetid);
+ memcpy(smc_pnet, smcd->pnetid, SMC_MAX_PNETID_LEN);
+ smc_pnet[SMC_MAX_PNETID_LEN] = 0;
if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
goto errportattr;
scope_id = dev->ifindex;
dev_put(dev);
} else {
- if (kstrtou32(p, 10, &scope_id) == 0) {
+ if (kstrtou32(p, 10, &scope_id) != 0) {
kfree(p);
return 0;
}
err = -EAGAIN;
if (len <= 0)
goto out_release;
+ trace_svc_xdr_recvfrom(&rqstp->rq_arg);
clear_bit(XPT_OLD, &xprt->xpt_flags);
if (serv->sv_stats)
serv->sv_stats->netcnt++;
- trace_svc_xdr_recvfrom(rqstp, &rqstp->rq_arg);
return len;
out_release:
rqstp->rq_res.len = 0;
xb->len = xb->head[0].iov_len +
xb->page_len +
xb->tail[0].iov_len;
- trace_svc_xdr_sendto(rqstp, xb);
+ trace_svc_xdr_sendto(rqstp->rq_xid, xb);
trace_svc_stats_latency(rqstp);
len = xprt->xpt_ops->xpo_sendto(rqstp);
return 0; /* record not complete */
}
+static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
+ int flags)
+{
+ return kernel_sendpage(sock, virt_to_page(vec->iov_base),
+ offset_in_page(vec->iov_base),
+ vec->iov_len, flags);
+}
+
+/*
+ * kernel_sendpage() is used exclusively to reduce the number of
+ * copy operations in this path. Therefore the caller must ensure
+ * that the pages backing @xdr are unchanging.
+ *
+ * In addition, the logic assumes that * .bv_len is never larger
+ * than PAGE_SIZE.
+ */
+static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
+ struct xdr_buf *xdr, rpc_fraghdr marker,
+ unsigned int *sentp)
+{
+ const struct kvec *head = xdr->head;
+ const struct kvec *tail = xdr->tail;
+ struct kvec rm = {
+ .iov_base = &marker,
+ .iov_len = sizeof(marker),
+ };
+ int flags, ret;
+
+ *sentp = 0;
+ xdr_alloc_bvec(xdr, GFP_KERNEL);
+
+ msg->msg_flags = MSG_MORE;
+ ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ if (ret != rm.iov_len)
+ return -EAGAIN;
+
+ flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0;
+ ret = svc_tcp_send_kvec(sock, head, flags);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ if (ret != head->iov_len)
+ goto out;
+
+ if (xdr->page_len) {
+ unsigned int offset, len, remaining;
+ struct bio_vec *bvec;
+
+ bvec = xdr->bvec;
+ offset = xdr->page_base;
+ remaining = xdr->page_len;
+ flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+ while (remaining > 0) {
+ if (remaining <= PAGE_SIZE && tail->iov_len == 0)
+ flags = 0;
+ len = min(remaining, bvec->bv_len);
+ ret = kernel_sendpage(sock, bvec->bv_page,
+ bvec->bv_offset + offset,
+ len, flags);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ if (ret != len)
+ goto out;
+ remaining -= len;
+ offset = 0;
+ bvec++;
+ }
+ }
+
+ if (tail->iov_len) {
+ ret = svc_tcp_send_kvec(sock, tail, 0);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ }
+
+out:
+ return 0;
+}
+
/**
* svc_tcp_sendto - Send out a reply on a TCP socket
* @rqstp: completed svc_rqst
mutex_lock(&xprt->xpt_mutex);
if (svc_xprt_is_dead(xprt))
goto out_notconn;
- err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
+ err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent);
xdr_free_bvec(xdr);
trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
if (err < 0 || sent != (xdr->len + sizeof(marker)))
int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
struct sk_buff_head *xmitq)
{
- struct tipc_msg *hdr = buf_msg(skb_peek(list));
struct sk_buff_head *backlogq = &l->backlogq;
struct sk_buff_head *transmq = &l->transmq;
struct sk_buff *skb, *_skb;
u16 ack = l->rcv_nxt - 1;
u16 seqno = l->snd_nxt;
int pkt_cnt = skb_queue_len(list);
- int imp = msg_importance(hdr);
unsigned int mss = tipc_link_mss(l);
unsigned int cwin = l->window;
unsigned int mtu = l->mtu;
+ struct tipc_msg *hdr;
bool new_bundle;
int rc = 0;
+ int imp;
+
+ if (pkt_cnt <= 0)
+ return 0;
+ hdr = buf_msg(skb_peek(list));
if (unlikely(msg_size(hdr) > mtu)) {
pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n",
skb_queue_len(list), msg_user(hdr),
return -EMSGSIZE;
}
+ imp = msg_importance(hdr);
/* Allow oversubscription of one data msg per source at congestion */
if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
if (imp == TIPC_SYSTEM_IMPORTANCE) {
}
/**
- * link_reset_stats - reset link statistics
+ * tipc_link_reset_stats - reset link statistics
* @l: pointer to link
*/
void tipc_link_reset_stats(struct tipc_link *l)
}
/**
- * tipc_node_xmit() is the general link level function for message sending
+ * tipc_node_xmit() - general link level function for message sending
* @net: the applicable net namespace
* @list: chain of buffers containing message
* @dnode: address of destination node
tristate "cfg80211 - wireless configuration API"
depends on RFKILL || !RFKILL
select FW_LOADER
+ select CRC32
# may need to update this when certificates are changed and are
# using a different algorithm, though right now they shouldn't
# (this is here rather than below to allow it to be a module)
* Copyright 2008-2011 Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2021 Intel Corporation
*
* Permission to use, copy, modify, and/or distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
return rcu_dereference_rtnl(cfg80211_regdomain);
}
+/*
+ * Returns the regulatory domain associated with the wiphy.
+ *
+ * Requires either RTNL or RCU protection
+ */
const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy)
{
return rcu_dereference_rtnl(wiphy->regd);
if (IS_ERR(new_regd))
return;
+ rtnl_lock();
+
tmp = get_wiphy_regdom(wiphy);
rcu_assign_pointer(wiphy->regd, new_regd);
rcu_free_regdom(tmp);
+
+ rtnl_unlock();
}
EXPORT_SYMBOL(wiphy_apply_custom_regulatory);
void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
{
- if (queue_id < dev->real_num_rx_queues)
+ if (queue_id < dev->num_rx_queues)
dev->_rx[queue_id].pool = NULL;
- if (queue_id < dev->real_num_tx_queues)
+ if (queue_id < dev->num_tx_queues)
dev->_tx[queue_id].pool = NULL;
}
struct xdp_sock *xs = xdp_sk(skb->sk);
unsigned long flags;
- spin_lock_irqsave(&xs->tx_completion_lock, flags);
+ spin_lock_irqsave(&xs->pool->cq_lock, flags);
xskq_prod_submit_addr(xs->pool->cq, addr);
- spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
+ spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
sock_wfree(skb);
}
bool sent_frame = false;
struct xdp_desc desc;
struct sk_buff *skb;
+ unsigned long flags;
int err = 0;
mutex_lock(&xs->mutex);
* if there is space in it. This avoids having to implement
* any buffering in the Tx path.
*/
+ spin_lock_irqsave(&xs->pool->cq_lock, flags);
if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
+ spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
kfree_skb(skb);
goto out;
}
+ spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
skb->dev = xs->dev;
skb->priority = sk->sk_priority;
if (err == NETDEV_TX_BUSY) {
/* Tell user-space to retry the send */
skb->destructor = sock_wfree;
+ spin_lock_irqsave(&xs->pool->cq_lock, flags);
+ xskq_prod_cancel(xs->pool->cq);
+ spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
/* Free skb without triggering the perf drop trace */
consume_skb(skb);
err = -EAGAIN;
}
}
+ /* FQ and CQ are now owned by the buffer pool and cleaned up with it. */
+ xs->fq_tmp = NULL;
+ xs->cq_tmp = NULL;
+
xs->dev = dev;
xs->zc = xs->umem->zc;
xs->queue_id = qid;
xs->state = XSK_READY;
mutex_init(&xs->mutex);
spin_lock_init(&xs->rx_lock);
- spin_lock_init(&xs->tx_completion_lock);
INIT_LIST_HEAD(&xs->map_list);
spin_lock_init(&xs->map_list_lock);
INIT_LIST_HEAD(&pool->free_list);
INIT_LIST_HEAD(&pool->xsk_tx_list);
spin_lock_init(&pool->xsk_tx_list_lock);
+ spin_lock_init(&pool->cq_lock);
refcount_set(&pool->users, 1);
pool->fq = xs->fq_tmp;
pool->cq = xs->cq_tmp;
- xs->fq_tmp = NULL;
- xs->cq_tmp = NULL;
for (i = 0; i < pool->free_heads_cnt; i++) {
xskb = &pool->heads[i];
return xskq_prod_nb_free(q, 1) ? false : true;
}
+static inline void xskq_prod_cancel(struct xsk_queue *q)
+{
+ q->cached_prod--;
+}
+
static inline int xskq_prod_reserve(struct xsk_queue *q)
{
if (xskq_prod_is_full(q))
# }
# }
+# strlcpy uses that should likely be strscpy
+ if ($line =~ /\bstrlcpy\s*\(/) {
+ WARN("STRLCPY",
+ "Prefer strscpy over strlcpy - see: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw\@mail.gmail.com/\n" . $herecurr);
+ }
+
# typecasts on min/max could be min_t/max_t
if ($perl_version_ok &&
defined $stat &&
;;
*)
+ echo "bad command: $CMD" >&2
usage
;;
esac
exit 0
fi
+# legacy behavior: "depmod" in /sbin, no /sbin in PATH
+PATH="$PATH:/sbin"
if [ -z $(command -v $DEPMOD) ]; then
echo "Warning: 'make modules_install' requires $DEPMOD. Please install it." >&2
echo "This is probably in the kmod package." >&2
GCC_PLUGINS_DIR = $(shell $(CC) -print-file-name=plugin)
plugin_cxxflags = -Wp,-MMD,$(depfile) $(KBUILD_HOSTCXXFLAGS) -fPIC \
- -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++98 \
+ -I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \
-fno-rtti -fno-exceptions -fasynchronous-unwind-tables \
- -ggdb -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat \
+ -ggdb -Wno-narrowing -Wno-unused-variable \
-Wno-format-diag
plugin_ldflags = -shared
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m .config $(configfiles)
$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
-PHONY += kvmconfig
-kvmconfig: kvm_guest.config
- @echo >&2 "WARNING: 'make $@' will be removed after Linux 5.10"
- @echo >&2 " Please use 'make $<' instead."
-
-PHONY += xenconfig
-xenconfig: xen.config
- @echo >&2 "WARNING: 'make $@' will be removed after Linux 5.10"
- @echo >&2 " Please use 'make $<' instead."
-
PHONY += tinyconfig
tinyconfig:
$(Q)$(MAKE) -f $(srctree)/Makefile allnoconfig tiny.config
exit 0
fi
-if [ -f /usr/include/ncurses.h ]; then
+# As a final fallback before giving up, check if $HOSTCC knows of a default
+# ncurses installation (e.g. from a vendor-specific sysroot).
+if echo '#include <ncurses.h>' | "${HOSTCC}" -E - >/dev/null 2>&1; then
echo cflags=\"-D_GNU_SOURCE\"
echo libs=\"-lncurses\"
exit 0
struct inode *inode;
audit_log_format(ab, " name=");
+ spin_lock(&a->u.dentry->d_lock);
audit_log_untrustedstring(ab, a->u.dentry->d_name.name);
+ spin_unlock(&a->u.dentry->d_lock);
inode = d_backing_inode(a->u.dentry);
if (inode) {
dentry = d_find_alias(inode);
if (dentry) {
audit_log_format(ab, " name=");
- audit_log_untrustedstring(ab,
- dentry->d_name.name);
+ spin_lock(&dentry->d_lock);
+ audit_log_untrustedstring(ab, dentry->d_name.name);
+ spin_unlock(&dentry->d_lock);
dput(dentry);
}
audit_log_format(ab, " dev=");
/* Set interval to next transaction. */
ff->next_ktime[port] = ktime_add_ns(ktime_get(),
- ff->rx_bytes[port] * 8 * NSEC_PER_SEC / 31250);
+ ff->rx_bytes[port] * 8 * (NSEC_PER_SEC / 31250));
if (quad_count == 1)
tcode = TCODE_WRITE_QUADLET_REQUEST;
/* Set interval to next transaction. */
port->next_ktime = ktime_add_ns(ktime_get(),
- port->consume_bytes * 8 * NSEC_PER_SEC / 31250);
+ port->consume_bytes * 8 * (NSEC_PER_SEC / 31250));
/* Start this transaction. */
port->idling = false;
SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0),
- /* https://bugzilla.redhat.com/show_bug.cgi?id=1581607 */
- SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
SND_PCI_QUIRK(0x1558, 0x6504, "Clevo W65_67SB", 0),
/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
.driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB },
/* ATI HDMI */
{ PCI_DEVICE(0x1002, 0x0002),
- .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+ .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
+ AZX_DCAPS_PM_RUNTIME },
{ PCI_DEVICE(0x1002, 0x1308),
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
{ PCI_DEVICE(0x1002, 0x157a),
{ PCI_DEVICE(0x1002, 0xaab0),
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
{ PCI_DEVICE(0x1002, 0xaac0),
- .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+ .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
+ AZX_DCAPS_PM_RUNTIME },
{ PCI_DEVICE(0x1002, 0xaac8),
- .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+ .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
+ AZX_DCAPS_PM_RUNTIME },
{ PCI_DEVICE(0x1002, 0xaad8),
.driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS |
AZX_DCAPS_PM_RUNTIME },
* in powers of 2, next available ratio is 16 which can be
* used as a limiting factor here.
*/
- if (of_device_is_compatible(np, "nvidia,tegra194-hda"))
+ if (of_device_is_compatible(np, "nvidia,tegra30-hda"))
chip->bus.core.sdo_limit = 16;
/* codec detection */
static const struct hda_device_id snd_hda_id_conexant[] = {
HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
+ HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto),
per_pin->silent_stream = false;
unlock_out:
- mutex_unlock(&spec->pcm_lock);
+ mutex_unlock(&per_pin->lock);
}
/* update ELD and jack state via audio component */
ALC221_FIXUP_HP_FRONT_MIC,
ALC292_FIXUP_TPT460,
ALC298_FIXUP_SPK_VOLUME,
+ ALC298_FIXUP_LENOVO_SPK_VOLUME,
ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
ALC269_FIXUP_ATIV_BOOK_8,
ALC221_FIXUP_HP_MIC_NO_PRESENCE,
.chained = true,
.chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
},
+ [ALC298_FIXUP_LENOVO_SPK_VOLUME] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc298_fixup_speaker_volume,
+ },
[ALC295_FIXUP_DISABLE_DAC3] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc295_fixup_disable_dac3,
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, 0x0a58, "Dell Precision 3650 Tower", ALC255_FIXUP_DELL_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_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, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+ SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_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, 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, 0x8780, "HP ZBook Fury 17 G7 Mobile Workstation",
+ ALC285_FIXUP_HP_GPIO_AMP_INIT),
+ SND_PCI_QUIRK(0x103c, 0x8783, "HP ZBook Fury 15 G7 Mobile Workstation",
+ ALC285_FIXUP_HP_GPIO_AMP_INIT),
+ SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_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(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+ SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+ SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
enum {
VIA_FIXUP_INTMIC_BOOST,
VIA_FIXUP_ASUS_G75,
+ VIA_FIXUP_POWER_SAVE,
};
static void via_fixup_intmic_boost(struct hda_codec *codec,
override_mic_boost(codec, 0x30, 0, 2, 40);
}
+static void via_fixup_power_save(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ codec->power_save_node = 0;
+}
+
static const struct hda_fixup via_fixups[] = {
[VIA_FIXUP_INTMIC_BOOST] = {
.type = HDA_FIXUP_FUNC,
{ }
}
},
+ [VIA_FIXUP_POWER_SAVE] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = via_fixup_power_save,
+ },
};
static const struct snd_pci_quirk vt2002p_fixups[] = {
SND_PCI_QUIRK(0x1043, 0x1487, "Asus G75", VIA_FIXUP_ASUS_G75),
SND_PCI_QUIRK(0x1043, 0x8532, "Asus X202E", VIA_FIXUP_INTMIC_BOOST),
+ SND_PCI_QUIRK(0x1558, 0x3501, "Clevo W35xSS_370SS", VIA_FIXUP_POWER_SAVE),
{}
};
goto release_regions;
}
- /* check for msi interrupt support */
- ret = pci_enable_msi(pci);
- if (ret)
- /* msi is not enabled */
- irqflags = IRQF_SHARED;
- else
- /* msi is enabled */
- irqflags = 0;
+ irqflags = IRQF_SHARED;
addr = pci_resource_start(pci, 0);
adata->acp3x_base = devm_ioremap(&pci->dev, addr,
pci_resource_len(pci, 0));
if (!adata->acp3x_base) {
ret = -ENOMEM;
- goto disable_msi;
+ goto release_regions;
}
pci_set_master(pci);
pci_set_drvdata(pci, adata);
adata->pme_en = rv_readl(adata->acp3x_base + mmACP_PME_EN);
ret = acp3x_init(adata);
if (ret)
- goto disable_msi;
+ goto release_regions;
val = rv_readl(adata->acp3x_base + mmACP_I2S_PIN_CONFIG);
switch (val) {
de_init:
if (acp3x_deinit(adata->acp3x_base))
dev_err(&pci->dev, "ACP de-init failed\n");
-disable_msi:
- pci_disable_msi(pci);
release_regions:
pci_release_regions(pci);
disable_pci:
dev_err(&pci->dev, "ACP de-init failed\n");
pm_runtime_forbid(&pci->dev);
pm_runtime_get_noresume(&pci->dev);
- pci_disable_msi(pci);
pci_release_regions(pci);
pci_disable_device(pci);
}
DMI_EXACT_MATCH(DMI_BOARD_NAME, "LNVNB161216"),
}
},
+ {
+ /* Lenovo ThinkPad E14 Gen 2 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_BOARD_NAME, "20T6CTO1WW"),
+ }
+ },
+ {
+ /* Lenovo ThinkPad X395 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_BOARD_NAME, "20NLCTO1WW"),
+ }
+ },
{}
};
- sama7g5
This S/PDIF TX driver is compliant with IEC-60958 standard and
- includes programable User Data and Channel Status fields.
+ includes programmable User Data and Channel Status fields.
config SND_MCHP_SOC_SPDIFRX
tristate "Microchip ASoC driver for boards using S/PDIF RX"
- sama7g5
This S/PDIF RX driver is compliant with IEC-60958 standard and
- includes programable User Data and Channel Status fields.
+ includes programmable User Data and Channel Status fields.
endif
help
Enable support for the Analog Devices ADAU7118 8 Channel PDM-to-I2S/TDM
Converter. In this mode, the device works in standalone mode which
- means that there is no bus to comunicate with it. Stereo mode is not
+ means that there is no bus to communicate with it. Stereo mode is not
supported in this mode.
To compile this driver as a module, choose M here: the module
#include <sound/tlv.h>
#include "max98373.h"
+static const u32 max98373_i2c_cache_reg[] = {
+ MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK,
+ MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK,
+ MAX98373_R20B6_BDE_CUR_STATE_READBACK,
+};
+
static struct reg_default max98373_reg[] = {
{MAX98373_R2000_SW_RESET, 0x00},
{MAX98373_R2001_INT_RAW1, 0x00},
static int max98373_suspend(struct device *dev)
{
struct max98373_priv *max98373 = dev_get_drvdata(dev);
+ int i;
+
+ /* cache feedback register values before suspend */
+ for (i = 0; i < max98373->cache_num; i++)
+ regmap_read(max98373->regmap, max98373->cache[i].reg, &max98373->cache[i].val);
regcache_cache_only(max98373->regmap, true);
regcache_mark_dirty(max98373->regmap);
{
int ret = 0;
int reg = 0;
+ int i;
struct max98373_priv *max98373 = NULL;
max98373 = devm_kzalloc(&i2c->dev, sizeof(*max98373), GFP_KERNEL);
return ret;
}
+ max98373->cache_num = ARRAY_SIZE(max98373_i2c_cache_reg);
+ max98373->cache = devm_kcalloc(&i2c->dev, max98373->cache_num,
+ sizeof(*max98373->cache),
+ GFP_KERNEL);
+
+ for (i = 0; i < max98373->cache_num; i++)
+ max98373->cache[i].reg = max98373_i2c_cache_reg[i];
+
/* voltage/current slot & gpio configuration */
max98373_slot_config(&i2c->dev, max98373);
struct sdw_stream_runtime *sdw_stream;
};
+static const u32 max98373_sdw_cache_reg[] = {
+ MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK,
+ MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK,
+ MAX98373_R20B6_BDE_CUR_STATE_READBACK,
+};
+
static struct reg_default max98373_reg[] = {
{MAX98373_R0040_SCP_INIT_STAT_1, 0x00},
{MAX98373_R0041_SCP_INIT_MASK_1, 0x00},
static __maybe_unused int max98373_suspend(struct device *dev)
{
struct max98373_priv *max98373 = dev_get_drvdata(dev);
+ int i;
+
+ /* cache feedback register values before suspend */
+ for (i = 0; i < max98373->cache_num; i++)
+ regmap_read(max98373->regmap, max98373->cache[i].reg, &max98373->cache[i].val);
regcache_cache_only(max98373->regmap, true);
{
struct max98373_priv *max98373;
int ret;
+ int i;
struct device *dev = &slave->dev;
/* Allocate and assign private driver data structure */
max98373->regmap = regmap;
max98373->slave = slave;
+ max98373->cache_num = ARRAY_SIZE(max98373_sdw_cache_reg);
+ max98373->cache = devm_kcalloc(dev, max98373->cache_num,
+ sizeof(*max98373->cache),
+ GFP_KERNEL);
+
+ for (i = 0; i < max98373->cache_num; i++)
+ max98373->cache[i].reg = max98373_sdw_cache_reg[i];
+
/* Read voltage and slot configuration */
max98373_slot_config(dev, max98373);
MAX98373_R2051_MEAS_ADC_SAMPLING_RATE, 0,
max98373_ADC_samplerate_text);
+static int max98373_feedback_get(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+{
+ struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+ struct soc_mixer_control *mc =
+ (struct soc_mixer_control *)kcontrol->private_value;
+ struct max98373_priv *max98373 = snd_soc_component_get_drvdata(component);
+ int i;
+
+ if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_OFF) {
+ /*
+ * Register values will be cached before suspend. The cached value
+ * will be a valid value and userspace will happy with that.
+ */
+ for (i = 0; i < max98373->cache_num; i++) {
+ if (mc->reg == max98373->cache[i].reg) {
+ ucontrol->value.integer.value[0] = max98373->cache[i].val;
+ return 0;
+ }
+ }
+ }
+
+ return snd_soc_put_volsw(kcontrol, ucontrol);
+}
+
static const struct snd_kcontrol_new max98373_snd_controls[] = {
SOC_SINGLE("Digital Vol Sel Switch", MAX98373_R203F_AMP_DSP_CFG,
MAX98373_AMP_VOL_SEL_SHIFT, 1, 0),
MAX98373_FLT_EN_SHIFT, 1, 0),
SOC_SINGLE("ADC TEMP FLT Switch", MAX98373_R2053_MEAS_ADC_THERM_FLT_CFG,
MAX98373_FLT_EN_SHIFT, 1, 0),
-SOC_SINGLE("ADC PVDD", MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK, 0, 0xFF, 0),
-SOC_SINGLE("ADC TEMP", MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK, 0, 0xFF, 0),
+SOC_SINGLE_EXT("ADC PVDD", MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK, 0, 0xFF, 0,
+ max98373_feedback_get, NULL),
+SOC_SINGLE_EXT("ADC TEMP", MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK, 0, 0xFF, 0,
+ max98373_feedback_get, NULL),
SOC_SINGLE("ADC PVDD FLT Coeff", MAX98373_R2052_MEAS_ADC_PVDD_FLT_CFG,
0, 0x3, 0),
SOC_SINGLE("ADC TEMP FLT Coeff", MAX98373_R2053_MEAS_ADC_THERM_FLT_CFG,
SOC_SINGLE("BDE LVL2 Thresh", MAX98373_R2098_BDE_L2_THRESH, 0, 0xFF, 0),
SOC_SINGLE("BDE LVL3 Thresh", MAX98373_R2099_BDE_L3_THRESH, 0, 0xFF, 0),
SOC_SINGLE("BDE LVL4 Thresh", MAX98373_R209A_BDE_L4_THRESH, 0, 0xFF, 0),
-SOC_SINGLE("BDE Active Level", MAX98373_R20B6_BDE_CUR_STATE_READBACK, 0, 8, 0),
+SOC_SINGLE_EXT("BDE Active Level", MAX98373_R20B6_BDE_CUR_STATE_READBACK, 0, 8, 0,
+ max98373_feedback_get, NULL),
SOC_SINGLE("BDE Clip Mode Switch", MAX98373_R2092_BDE_CLIPPER_MODE, 0, 1, 0),
SOC_SINGLE("BDE Thresh Hysteresis", MAX98373_R209B_BDE_THRESH_HYST, 0, 0xFF, 0),
SOC_SINGLE("BDE Hold Time", MAX98373_R2090_BDE_LVL_HOLD, 0, 0xFF, 0),
/* MAX98373_R2000_SW_RESET */
#define MAX98373_SOFT_RESET (0x1 << 0)
+struct max98373_cache {
+ u32 reg;
+ u32 val;
+};
+
struct max98373_priv {
struct regmap *regmap;
int reset_gpio;
bool interleave_mode;
unsigned int ch_size;
bool tdm_mode;
+ /* cache for reading a valid fake feedback value */
+ struct max98373_cache *cache;
+ int cache_num;
/* variables to support soundwire */
struct sdw_slave *slave;
bool hw_init;
unsigned int read_ll, read_rl;
int i;
+ mutex_lock(&rt711->calibrate_mutex);
+
/* Can't use update bit function, so read the original value first */
addr_h = mc->reg;
addr_l = mc->rreg;
if (dapm->bias_level <= SND_SOC_BIAS_STANDBY)
regmap_write(rt711->regmap,
RT711_SET_AUDIO_POWER_STATE, AC_PWRST_D3);
+
+ mutex_unlock(&rt711->calibrate_mutex);
return 0;
}
break;
case SND_SOC_BIAS_STANDBY:
+ mutex_lock(&rt711->calibrate_mutex);
regmap_write(rt711->regmap,
RT711_SET_AUDIO_POWER_STATE,
AC_PWRST_D3);
+ mutex_unlock(&rt711->calibrate_mutex);
break;
default:
if ((hdmi_out && hdmi_in) || (!hdmi_out && !hdmi_in)) {
dev_err(&pdev->dev, "Invalid HDMI DAI link\n");
+ ret = -EINVAL;
goto fail;
}
.probe = haswell_audio_probe,
.driver = {
.name = "haswell-audio",
+ .pm = &snd_soc_pm_ops,
},
};
"dsp boot timeout, status=%#x error=%#x\n",
sst_dsp_shim_read(ctx, CNL_ADSP_FW_STATUS),
sst_dsp_shim_read(ctx, CNL_ADSP_ERROR_CODE));
+ ret = -ETIMEDOUT;
goto err;
}
} else {
return ret;
}
+static const struct snd_soc_dapm_widget axg_tdm_iface_dapm_widgets[] = {
+ SND_SOC_DAPM_SIGGEN("Playback Signal"),
+};
+
+static const struct snd_soc_dapm_route axg_tdm_iface_dapm_routes[] = {
+ { "Loopback", NULL, "Playback Signal" },
+};
+
static const struct snd_soc_component_driver axg_tdm_iface_component_drv = {
- .set_bias_level = axg_tdm_iface_set_bias_level,
+ .dapm_widgets = axg_tdm_iface_dapm_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(axg_tdm_iface_dapm_widgets),
+ .dapm_routes = axg_tdm_iface_dapm_routes,
+ .num_dapm_routes = ARRAY_SIZE(axg_tdm_iface_dapm_routes),
+ .set_bias_level = axg_tdm_iface_set_bias_level,
};
static const struct of_device_id axg_tdm_iface_of_match[] = {
};
static const struct axg_tdm_formatter_driver axg_tdmin_drv = {
- .component_drv = &axg_tdmin_component_drv,
- .regmap_cfg = &axg_tdmin_regmap_cfg,
- .ops = &axg_tdmin_ops,
- .quirks = &(const struct axg_tdm_formatter_hw) {
- .skew_offset = 2,
- },
-};
-
-static const struct axg_tdm_formatter_driver g12a_tdmin_drv = {
.component_drv = &axg_tdmin_component_drv,
.regmap_cfg = &axg_tdmin_regmap_cfg,
.ops = &axg_tdmin_ops,
.data = &axg_tdmin_drv,
}, {
.compatible = "amlogic,g12a-tdmin",
- .data = &g12a_tdmin_drv,
+ .data = &axg_tdmin_drv,
}, {
.compatible = "amlogic,sm1-tdmin",
- .data = &g12a_tdmin_drv,
+ .data = &axg_tdmin_drv,
}, {}
};
MODULE_DEVICE_TABLE(of, axg_tdmin_of_match);
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:
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) || reg == LPAIF_RDMACTL_REG(v, i))
+ if (reg == LPAIF_RDMACURR_REG(v, i))
return true;
for (i = 0; i < v->wrdma_channels; ++i)
- if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start) ||
- reg == LPAIF_WRDMACTL_REG(v, i + v->wrdma_channel_start))
+ if (reg == LPAIF_WRDMACURR_REG(v, i + v->wrdma_channel_start))
return true;
return false;
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 - 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:
"error writing to rdmactl reg: %d\n", ret);
return ret;
}
- map = drvdata->hdmiif_map;
reg_irqclr = LPASS_HDMITX_APP_IRQCLEAR_REG(v);
val_irqclr = (LPAIF_IRQ_ALL(ch) |
LPAIF_IRQ_HDMI_REQ_ON_PRELOAD(ch) |
break;
case MI2S_PRIMARY:
case MI2S_SECONDARY:
- map = drvdata->lpaif_map;
reg_irqclr = LPAIF_IRQCLEAR_REG(v, LPAIF_IRQ_PORT_HOST);
val_irqclr = LPAIF_IRQ_ALL(ch);
"error writing to rdmactl reg: %d\n", ret);
return ret;
}
- map = drvdata->hdmiif_map;
reg_irqen = LPASS_HDMITX_APP_IRQEN_REG(v);
val_mask = (LPAIF_IRQ_ALL(ch) |
LPAIF_IRQ_HDMI_REQ_ON_PRELOAD(ch) |
break;
case MI2S_PRIMARY:
case MI2S_SECONDARY:
- map = drvdata->lpaif_map;
reg_irqen = LPAIF_IRQEN_REG(v, LPAIF_IRQ_PORT_HOST);
val_mask = LPAIF_IRQ_ALL(ch);
val_irqen = 0;
}
}
+static int lpass_platform_pcmops_suspend(struct snd_soc_component *component)
+{
+ struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
+ struct regmap *map;
+ unsigned int dai_id = component->id;
+
+ if (dai_id == LPASS_DP_RX)
+ map = drvdata->hdmiif_map;
+ else
+ map = drvdata->lpaif_map;
+
+ regcache_cache_only(map, true);
+ regcache_mark_dirty(map);
+
+ return 0;
+}
+
+static int lpass_platform_pcmops_resume(struct snd_soc_component *component)
+{
+ struct lpass_data *drvdata = snd_soc_component_get_drvdata(component);
+ struct regmap *map;
+ unsigned int dai_id = component->id;
+
+ if (dai_id == LPASS_DP_RX)
+ map = drvdata->hdmiif_map;
+ else
+ map = drvdata->lpaif_map;
+
+ regcache_cache_only(map, false);
+ return regcache_sync(map);
+}
+
+
static const struct snd_soc_component_driver lpass_component_driver = {
.name = DRV_NAME,
.open = lpass_platform_pcmops_open,
.mmap = lpass_platform_pcmops_mmap,
.pcm_construct = lpass_platform_pcm_new,
.pcm_destruct = lpass_platform_pcm_free,
+ .suspend = lpass_platform_pcmops_suspend,
+ .resume = lpass_platform_pcmops_resume,
};
struct rsnd_adg *adg = rsnd_priv_to_adg(priv);
struct device *dev = rsnd_priv_to_dev(priv);
struct clk *clk;
- int i, ret;
+ int i;
for_each_rsnd_clk(clk, adg, i) {
- ret = 0;
if (enable) {
- ret = clk_prepare_enable(clk);
+ int ret = clk_prepare_enable(clk);
/*
* We shouldn't use clk_get_rate() under
* atomic context. Let's keep it when
* rsnd_adg_clk_enable() was called
*/
- adg->clk_rate[i] = clk_get_rate(adg->clk[i]);
+ adg->clk_rate[i] = 0;
+ if (ret < 0)
+ dev_warn(dev, "can't use clk %d\n", i);
+ else
+ adg->clk_rate[i] = clk_get_rate(clk);
} else {
- clk_disable_unprepare(clk);
+ if (adg->clk_rate[i])
+ clk_disable_unprepare(clk);
+ adg->clk_rate[i] = 0;
}
-
- if (ret < 0)
- dev_warn(dev, "can't use clk %d\n", i);
}
}
enum snd_soc_dapm_direction dir;
list_del(&w->list);
+ list_del(&w->dirty);
/*
* remove source and sink paths associated to this widget.
* While removing the path, remove reference to it from both
bool "SOF stop on XRUN"
help
This option forces PCMs to stop on any XRUN event. This is useful to
- preserve any trace data ond pipeline status prior to the XRUN.
+ preserve any trace data and pipeline status prior to the XRUN.
Say Y if you are debugging SOF FW pipeline XRUNs.
If unsure select "N".
static void snd_usb_audio_free(struct snd_card *card)
{
struct snd_usb_audio *chip = card->private_data;
- struct snd_usb_endpoint *ep, *n;
- list_for_each_entry_safe(ep, n, &chip->ep_list, list)
- snd_usb_endpoint_free(ep);
+ snd_usb_endpoint_free_all(chip);
mutex_destroy(&chip->mutex);
if (!atomic_read(&chip->shutdown))
chip->usb_id = usb_id;
INIT_LIST_HEAD(&chip->pcm_list);
INIT_LIST_HEAD(&chip->ep_list);
+ INIT_LIST_HEAD(&chip->iface_ref_list);
INIT_LIST_HEAD(&chip->midi_list);
INIT_LIST_HEAD(&chip->mixer_list);
unsigned int frame_size; /* samples per frame for non-audio */
unsigned char iface; /* interface number */
unsigned char altsetting; /* corresponding alternate setting */
+ unsigned char ep_idx; /* endpoint array index */
unsigned char altset_idx; /* array index of altenate setting */
unsigned char attributes; /* corresponding attributes of cs endpoint */
unsigned char endpoint; /* endpoint */
};
struct snd_usb_substream;
+struct snd_usb_iface_ref;
struct snd_usb_endpoint;
struct snd_usb_power_domain;
struct snd_usb_endpoint {
struct snd_usb_audio *chip;
+ struct snd_usb_iface_ref *iface_ref;
int opened; /* open refcount; protect with chip->mutex */
atomic_t running; /* running status */
#define EP_FLAG_RUNNING 1
#define EP_FLAG_STOPPING 2
+/* interface refcounting */
+struct snd_usb_iface_ref {
+ unsigned char iface;
+ bool need_setup;
+ int opened;
+ struct list_head list;
+};
+
/*
* snd_usb_endpoint is a model that abstracts everything related to an
* USB endpoint and its streaming.
clear_bit(ctx->index, &ep->active_mask);
}
+/*
+ * Find or create a refcount object for the given interface
+ *
+ * The objects are released altogether in snd_usb_endpoint_free_all()
+ */
+static struct snd_usb_iface_ref *
+iface_ref_find(struct snd_usb_audio *chip, int iface)
+{
+ struct snd_usb_iface_ref *ip;
+
+ list_for_each_entry(ip, &chip->iface_ref_list, list)
+ if (ip->iface == iface)
+ return ip;
+
+ ip = kzalloc(sizeof(*ip), GFP_KERNEL);
+ if (!ip)
+ return NULL;
+ ip->iface = iface;
+ list_add_tail(&ip->list, &chip->iface_ref_list);
+ return ip;
+}
+
/*
* Get the existing endpoint object corresponding EP
* Returns NULL if not present.
*
* Returns zero on success or a negative error code.
*
- * New endpoints will be added to chip->ep_list and must be freed by
- * calling snd_usb_endpoint_free().
+ * New endpoints will be added to chip->ep_list and freed by
+ * calling snd_usb_endpoint_free_all().
*
* For SND_USB_ENDPOINT_TYPE_SYNC, the caller needs to guarantee that
* bNumEndpoints > 1 beforehand.
} else {
ep->iface = fp->iface;
ep->altsetting = fp->altsetting;
- ep->ep_idx = 0;
+ ep->ep_idx = fp->ep_idx;
}
usb_audio_dbg(chip, "Open EP 0x%x, iface=%d:%d, idx=%d\n",
ep_num, ep->iface, ep->altsetting, ep->ep_idx);
+ ep->iface_ref = iface_ref_find(chip, ep->iface);
+ if (!ep->iface_ref) {
+ ep = NULL;
+ goto unlock;
+ }
+
ep->cur_audiofmt = fp;
ep->cur_channels = fp->channels;
ep->cur_rate = params_rate(params);
ep->implicit_fb_sync);
} else {
+ if (WARN_ON(!ep->iface_ref)) {
+ ep = NULL;
+ goto unlock;
+ }
+
if (!endpoint_compatible(ep, fp, params)) {
usb_audio_err(chip, "Incompatible EP setup for 0x%x\n",
ep_num);
ep_num, ep->opened);
}
+ if (!ep->iface_ref->opened++)
+ ep->iface_ref->need_setup = true;
+
ep->opened++;
unlock:
mutex_lock(&chip->mutex);
usb_audio_dbg(chip, "Closing EP 0x%x (count %d)\n",
ep->ep_num, ep->opened);
- if (!--ep->opened) {
+
+ if (!--ep->iface_ref->opened)
endpoint_set_interface(chip, ep, false);
+
+ if (!--ep->opened) {
ep->iface = 0;
ep->altsetting = 0;
ep->cur_audiofmt = NULL;
ep->cur_rate = 0;
+ ep->iface_ref = NULL;
usb_audio_dbg(chip, "EP 0x%x closed\n", ep->ep_num);
}
mutex_unlock(&chip->mutex);
void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep)
{
ep->need_setup = true;
+ if (ep->iface_ref)
+ ep->iface_ref->need_setup = true;
}
/*
int err = 0;
mutex_lock(&chip->mutex);
+ if (WARN_ON(!ep->iface_ref))
+ goto unlock;
if (!ep->need_setup)
goto unlock;
- /* No need to (re-)configure the sync EP belonging to the same altset */
- if (ep->ep_idx) {
+ /* If the interface has been already set up, just set EP parameters */
+ if (!ep->iface_ref->need_setup) {
err = snd_usb_endpoint_set_params(chip, ep);
if (err < 0)
goto unlock;
goto unlock;
}
+ ep->iface_ref->need_setup = false;
+
done:
ep->need_setup = false;
err = 1;
}
/**
- * snd_usb_endpoint_free: Free the resources of an snd_usb_endpoint
+ * snd_usb_endpoint_free_all: Free the resources of an snd_usb_endpoint
+ * @card: The chip
*
- * @ep: the endpoint to free
- *
- * This free all resources of the given ep.
+ * This free all endpoints and those resources
*/
-void snd_usb_endpoint_free(struct snd_usb_endpoint *ep)
+void snd_usb_endpoint_free_all(struct snd_usb_audio *chip)
{
- kfree(ep);
+ struct snd_usb_endpoint *ep, *en;
+ struct snd_usb_iface_ref *ip, *in;
+
+ list_for_each_entry_safe(ep, en, &chip->ep_list, list)
+ kfree(ep);
+
+ list_for_each_entry_safe(ip, in, &chip->iface_ref_list, list)
+ kfree(ip);
}
/*
void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep);
int snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
void snd_usb_endpoint_release(struct snd_usb_endpoint *ep);
-void snd_usb_endpoint_free(struct snd_usb_endpoint *ep);
+void snd_usb_endpoint_free_all(struct snd_usb_audio *chip);
int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep,
IMPLICIT_FB_FIXED_DEV(0x0499, 0x172f, 0x81, 2), /* Steinberg UR22C */
IMPLICIT_FB_FIXED_DEV(0x0d9a, 0x00df, 0x81, 2), /* RTX6001 */
IMPLICIT_FB_FIXED_DEV(0x22f0, 0x0006, 0x81, 3), /* Allen&Heath Qu-16 */
- IMPLICIT_FB_FIXED_DEV(0x2b73, 0x000a, 0x82, 0), /* Pioneer DJ DJM-900NXS2 */
- IMPLICIT_FB_FIXED_DEV(0x2b73, 0x0017, 0x82, 0), /* Pioneer DJ DJM-250MK2 */
IMPLICIT_FB_FIXED_DEV(0x1686, 0xf029, 0x82, 2), /* Zoom UAC-2 */
IMPLICIT_FB_FIXED_DEV(0x2466, 0x8003, 0x86, 2), /* Fractal Audio Axe-Fx II */
IMPLICIT_FB_FIXED_DEV(0x0499, 0x172a, 0x86, 2), /* Yamaha MODX */
/* No quirk for playback but with capture quirk (see below) */
IMPLICIT_FB_SKIP_DEV(0x0582, 0x0130), /* BOSS BR-80 */
+ IMPLICIT_FB_SKIP_DEV(0x0582, 0x0171), /* BOSS RC-505 */
IMPLICIT_FB_SKIP_DEV(0x0582, 0x0189), /* BOSS GT-100v2 */
IMPLICIT_FB_SKIP_DEV(0x0582, 0x01d6), /* BOSS GT-1 */
IMPLICIT_FB_SKIP_DEV(0x0582, 0x01d8), /* BOSS Katana */
IMPLICIT_FB_SKIP_DEV(0x0582, 0x01e5), /* BOSS GT-001 */
+ IMPLICIT_FB_SKIP_DEV(0x0582, 0x0203), /* BOSS AD-10 */
{} /* terminator */
};
/* Implicit feedback quirk table for capture: only FIXED type */
static const struct snd_usb_implicit_fb_match capture_implicit_fb_quirks[] = {
IMPLICIT_FB_FIXED_DEV(0x0582, 0x0130, 0x0d, 0x01), /* BOSS BR-80 */
+ IMPLICIT_FB_FIXED_DEV(0x0582, 0x0171, 0x0d, 0x01), /* BOSS RC-505 */
IMPLICIT_FB_FIXED_DEV(0x0582, 0x0189, 0x0d, 0x01), /* BOSS GT-100v2 */
IMPLICIT_FB_FIXED_DEV(0x0582, 0x01d6, 0x0d, 0x01), /* BOSS GT-1 */
IMPLICIT_FB_FIXED_DEV(0x0582, 0x01d8, 0x0d, 0x01), /* BOSS Katana */
IMPLICIT_FB_FIXED_DEV(0x0582, 0x01e5, 0x0d, 0x01), /* BOSS GT-001 */
+ IMPLICIT_FB_FIXED_DEV(0x0582, 0x0203, 0x0d, 0x01), /* BOSS AD-10 */
{} /* terminator */
};
/* set up sync EP information on the audioformat */
static int add_implicit_fb_sync_ep(struct snd_usb_audio *chip,
struct audioformat *fmt,
- int ep, int ifnum,
+ int ep, int ep_idx, int ifnum,
const struct usb_host_interface *alts)
{
struct usb_interface *iface;
fmt->sync_ep = ep;
fmt->sync_iface = ifnum;
fmt->sync_altsetting = alts->desc.bAlternateSetting;
- fmt->sync_ep_idx = 0;
+ fmt->sync_ep_idx = ep_idx;
fmt->implicit_fb = 1;
usb_audio_dbg(chip,
"%d:%d: added %s implicit_fb sync_ep %x, iface %d:%d\n",
(epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
USB_ENDPOINT_USAGE_IMPLICIT_FB)
return 0;
- return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress,
+ return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0,
ifnum, alts);
}
(epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
USB_ENDPOINT_USAGE_IMPLICIT_FB)
return 0;
- return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress,
+ return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0,
ifnum, alts);
}
+/* Pioneer devices: playback and capture streams sharing the same iface/altset
+ */
+static int add_pioneer_implicit_fb(struct snd_usb_audio *chip,
+ struct audioformat *fmt,
+ struct usb_host_interface *alts)
+{
+ struct usb_endpoint_descriptor *epd;
+
+ if (alts->desc.bNumEndpoints != 2)
+ return 0;
+
+ epd = get_endpoint(alts, 1);
+ if (!usb_endpoint_is_isoc_in(epd) ||
+ (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC ||
+ ((epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
+ USB_ENDPOINT_USAGE_DATA &&
+ (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) !=
+ USB_ENDPOINT_USAGE_IMPLICIT_FB))
+ return 0;
+ return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 1,
+ alts->desc.bInterfaceNumber, alts);
+}
static int __add_generic_implicit_fb(struct snd_usb_audio *chip,
struct audioformat *fmt,
if (!usb_endpoint_is_isoc_in(epd) ||
(epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC)
return 0;
- return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress,
+ return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0,
iface, alts);
}
case IMPLICIT_FB_NONE:
return 0; /* No quirk */
case IMPLICIT_FB_FIXED:
- return add_implicit_fb_sync_ep(chip, fmt, p->ep_num,
+ return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, 0,
p->iface, NULL);
}
}
return 1;
}
+ /* Pioneer devices implicit feedback with vendor spec class */
+ if (attr == USB_ENDPOINT_SYNC_ASYNC &&
+ alts->desc.bInterfaceClass == USB_CLASS_VENDOR_SPEC &&
+ USB_ID_VENDOR(chip->usb_id) == 0x2b73 /* Pioneer */) {
+ if (add_pioneer_implicit_fb(chip, fmt, alts))
+ return 1;
+ }
+
/* Try the generic implicit fb if available */
if (chip->generic_implicit_fb)
return add_generic_implicit_fb(chip, fmt, alts);
p = find_implicit_fb_entry(chip, capture_implicit_fb_quirks, alts);
if (p && p->type == IMPLICIT_FB_FIXED)
- return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, p->iface,
- NULL);
+ return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, 0,
+ p->iface, NULL);
return 0;
}
int stream)
{
struct snd_usb_substream *subs;
- const struct audioformat *fp, *sync_fmt;
+ const struct audioformat *fp, *sync_fmt = NULL;
int score, high_score;
- /* When sharing the same altset, use the original audioformat */
+ /* Use the original audioformat as fallback for the shared altset */
if (target->iface == target->sync_iface &&
target->altsetting == target->sync_altsetting)
- return target;
+ sync_fmt = target;
subs = find_matching_substream(chip, stream, target->sync_ep,
target->fmt_type);
if (!subs)
- return NULL;
+ return sync_fmt;
- sync_fmt = NULL;
high_score = 0;
list_for_each_entry(fp, &subs->fmt_list, list) {
score = match_endpoint_audioformats(subs, fp,
ms_ep = find_usb_ms_endpoint_descriptor(hostep);
if (!ms_ep)
continue;
+ if (ms_ep->bNumEmbMIDIJack > 0x10)
+ continue;
if (usb_endpoint_dir_out(ep)) {
if (endpoints[epidx].out_ep) {
if (++epidx >= MIDI_MAX_ENDPOINTS) {
cs_desc[1] == USB_DT_CS_INTERFACE &&
cs_desc[2] == 0xf1 &&
cs_desc[3] == 0x02) {
+ if (cs_desc[4] > 0x10 || cs_desc[5] > 0x10)
+ continue;
endpoint->in_cables = (1 << cs_desc[4]) - 1;
endpoint->out_cables = (1 << cs_desc[5]) - 1;
return snd_usbmidi_detect_endpoints(umidi, endpoint, 1);
.altsetting = 1,
.altset_idx = 1,
.endpoint = 0x86,
+ .ep_idx = 1,
.ep_attr = USB_ENDPOINT_XFER_ISOC|
USB_ENDPOINT_SYNC_ASYNC|
USB_ENDPOINT_USAGE_IMPLICIT_FB,
.altsetting = 1,
.altset_idx = 1,
.endpoint = 0x82,
+ .ep_idx = 1,
.ep_attr = USB_ENDPOINT_XFER_ISOC|
USB_ENDPOINT_SYNC_ASYNC|
USB_ENDPOINT_USAGE_IMPLICIT_FB,
.altsetting = 1,
.altset_idx = 1,
.endpoint = 0x82,
+ .ep_idx = 1,
.ep_attr = USB_ENDPOINT_XFER_ISOC|
USB_ENDPOINT_SYNC_ASYNC|
USB_ENDPOINT_USAGE_IMPLICIT_FB,
.altsetting = 1,
.altset_idx = 1,
.endpoint = 0x82,
+ .ep_idx = 1,
.ep_attr = USB_ENDPOINT_XFER_ISOC|
USB_ENDPOINT_SYNC_ASYNC|
USB_ENDPOINT_USAGE_IMPLICIT_FB,
.altsetting = 1,
.altset_idx = 1,
.endpoint = 0x82,
+ .ep_idx = 1,
.ep_attr = USB_ENDPOINT_XFER_ISOC|
USB_ENDPOINT_SYNC_ASYNC|
USB_ENDPOINT_USAGE_IMPLICIT_FB,
.altsetting = 1,
.altset_idx = 1,
.endpoint = 0x82,
+ .ep_idx = 1,
.ep_attr = USB_ENDPOINT_XFER_ISOC|
USB_ENDPOINT_SYNC_ASYNC|
USB_ENDPOINT_USAGE_IMPLICIT_FB,
return 0;
}
+/* create the audio stream and the corresponding endpoints from the fixed
+ * audioformat object; this is used for quirks with the fixed EPs
+ */
+static int add_audio_stream_from_fixed_fmt(struct snd_usb_audio *chip,
+ struct audioformat *fp)
+{
+ int stream, err;
+
+ stream = (fp->endpoint & USB_DIR_IN) ?
+ SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
+
+ snd_usb_audioformat_set_sync_ep(chip, fp);
+
+ err = snd_usb_add_audio_stream(chip, stream, fp);
+ if (err < 0)
+ return err;
+
+ err = snd_usb_add_endpoint(chip, fp->endpoint,
+ SND_USB_ENDPOINT_TYPE_DATA);
+ if (err < 0)
+ return err;
+
+ if (fp->sync_ep) {
+ err = snd_usb_add_endpoint(chip, fp->sync_ep,
+ fp->implicit_fb ?
+ SND_USB_ENDPOINT_TYPE_DATA :
+ SND_USB_ENDPOINT_TYPE_SYNC);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
/*
* create a stream for an endpoint/altsetting without proper descriptors
*/
struct audioformat *fp;
struct usb_host_interface *alts;
struct usb_interface_descriptor *altsd;
- int stream, err;
unsigned *rate_table = NULL;
+ int err;
fp = kmemdup(quirk->data, sizeof(*fp), GFP_KERNEL);
if (!fp)
fp->rate_table = rate_table;
}
- stream = (fp->endpoint & USB_DIR_IN)
- ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
- err = snd_usb_add_audio_stream(chip, stream, fp);
- if (err < 0)
- goto error;
if (fp->iface != get_iface_desc(&iface->altsetting[0])->bInterfaceNumber ||
fp->altset_idx >= iface->num_altsetting) {
err = -EINVAL;
}
alts = &iface->altsetting[fp->altset_idx];
altsd = get_iface_desc(alts);
- if (altsd->bNumEndpoints < 1) {
+ if (altsd->bNumEndpoints <= fp->ep_idx) {
err = -EINVAL;
goto error;
}
if (fp->datainterval == 0)
fp->datainterval = snd_usb_parse_datainterval(chip, alts);
if (fp->maxpacksize == 0)
- fp->maxpacksize = le16_to_cpu(get_endpoint(alts, 0)->wMaxPacketSize);
+ fp->maxpacksize = le16_to_cpu(get_endpoint(alts, fp->ep_idx)->wMaxPacketSize);
+ if (!fp->fmt_type)
+ fp->fmt_type = UAC_FORMAT_TYPE_I;
+
+ err = add_audio_stream_from_fixed_fmt(chip, fp);
+ if (err < 0)
+ goto error;
+
usb_set_interface(chip->dev, fp->iface, 0);
snd_usb_init_pitch(chip, fp);
snd_usb_init_sample_rate(chip, fp, fp->rate_max);
struct usb_host_interface *alts;
struct usb_interface_descriptor *altsd;
struct audioformat *fp;
- int stream, err;
+ int err;
/* both PCM and MIDI interfaces have 2 or more altsettings */
if (iface->num_altsetting < 2)
return -ENXIO;
}
- stream = (fp->endpoint & USB_DIR_IN)
- ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK;
- err = snd_usb_add_audio_stream(chip, stream, fp);
+ err = add_audio_stream_from_fixed_fmt(chip, fp);
if (err < 0) {
list_del(&fp->list); /* unlink for avoiding double-free */
kfree(fp);
struct list_head pcm_list; /* list of pcm streams */
struct list_head ep_list; /* list of audio-related endpoints */
+ struct list_head iface_ref_list; /* list of interface refcounts */
int pcm_devs;
struct list_head midi_list; /* list of midi interfaces */
set_array_of ${instance}.options ${instancedir}/trace_options
set_value_of ${instance}.trace_clock ${instancedir}/trace_clock
set_value_of ${instance}.cpumask ${instancedir}/tracing_cpumask
+ set_value_of ${instance}.tracing_on ${instancedir}/tracing_on
set_value_of ${instance}.tracer ${instancedir}/current_tracer
set_array_of ${instance}.ftrace.filters \
${instancedir}/set_ftrace_filter
if [ `echo $val | sed -e s/f//g`x != x ]; then
emit_kv $PREFIX.cpumask = $val
fi
+ val=`cat $INSTANCE/tracing_on`
+ if [ `echo $val | sed -e s/f//g`x != x ]; then
+ emit_kv $PREFIX.tracing_on = $val
+ fi
val=
for i in `cat $INSTANCE/set_event`; do
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include <net/if.h>
-#include <linux/if.h>
#include <linux/rtnetlink.h>
#include <linux/socket.h>
#include <linux/tc_act/tc_bpf.h>
#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err(fmt, ...) \
eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+ eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
static bool is_btf_id(const char *name)
{
int nr_funcs = obj->nr_funcs;
int err, type_id;
struct btf *btf;
- __u32 nr;
+ __u32 nr_types;
btf = btf__parse(obj->btf ?: obj->path, NULL);
err = libbpf_get_error(btf);
}
err = -1;
- nr = btf__get_nr_types(btf);
+ nr_types = btf__get_nr_types(btf);
/*
* Iterate all the BTF types and search for collected symbol IDs.
*/
- for (type_id = 1; type_id <= nr; type_id++) {
+ for (type_id = 1; type_id <= nr_types; type_id++) {
const struct btf_type *type;
struct rb_root *root;
struct btf_id *id;
id = btf_id__find(root, str);
if (id) {
- id->id = type_id;
- (*nr)--;
+ if (id->id) {
+ pr_info("WARN: multiple IDs found for '%s': %d, %d - using %d\n",
+ str, id->id, type_id, id->id);
+ } else {
+ id->id = type_id;
+ (*nr)--;
+ }
}
}
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
#endif // static_assert
-#ifdef __GENKSYMS__
-/* genksyms gets confused by _Static_assert */
-#define _Static_assert(expr, ...)
-#endif
-
#endif /* _LINUX_BUILD_BUG_H */
#define KVM_EXIT_X86_RDMSR 29
#define KVM_EXIT_X86_WRMSR 30
#define KVM_EXIT_DIRTY_RING_FULL 31
+#define KVM_EXIT_AP_RESET_HOLD 32
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
#define KVM_MP_STATE_CHECK_STOP 6
#define KVM_MP_STATE_OPERATING 7
#define KVM_MP_STATE_LOAD 8
+#define KVM_MP_STATE_AP_RESET_HOLD 9
struct kvm_mp_state {
__u32 mp_state;
}
meta_left = btf->raw_size - sizeof(*hdr);
- if (!meta_left) {
- pr_debug("BTF has no data\n");
- return -EINVAL;
- }
-
if (meta_left < hdr->str_off + hdr->str_len) {
pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
return -EINVAL;
perf_cpu_map__put(cpus);
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
char path[PATH_MAX];
int id, err, pid, go_pipe[2];
union perf_event *event;
- char bf;
int count = 0;
snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id",
sysfs__mountpoint());
if (filename__read_int(path, &id)) {
+ tests_failed++;
fprintf(stderr, "error: failed to get tracepoint id: %s\n", path);
return -1;
}
pid = fork();
if (!pid) {
int i;
+ char bf;
read(go_pipe[0], &bf, 1);
perf_evlist__enable(evlist);
/* kick the child and wait for it to finish */
- write(go_pipe[1], &bf, 1);
+ write(go_pipe[1], "A", 1);
waitpid(pid, NULL, 0);
/*
test_mmap_cpus();
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
test_stat_thread_enable();
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
perf_thread_map__put(threads);
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
*/
-#include <bpf/bpf.h>
+#include <bpf.h>
#define NSEC_PER_SEC 1000000000L
test_global_aggr()
{
- local cyc
-
perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \
grep -e cycles -e instructions | \
while read num evt hash ipc rest
do
# skip not counted events
- if [[ $num == "<not" ]]; then
+ if [ "$num" = "<not" ]; then
continue
fi
# save cycles count
- if [[ $evt == "cycles" ]]; then
+ if [ "$evt" = "cycles" ]; then
cyc=$num
continue
fi
# skip if no cycles
- if [[ -z $cyc ]]; then
+ if [ -z "$cyc" ]; then
continue
fi
# use printf for rounding and a leading zero
- local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
- if [[ $ipc != $res ]]; then
+ res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+ if [ "$ipc" != "$res" ]; then
echo "IPC is different: $res != $ipc ($num / $cyc)"
exit 1
fi
test_no_aggr()
{
- declare -A results
-
perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \
grep ^CPU | \
while read cpu num evt hash ipc rest
do
# skip not counted events
- if [[ $num == "<not" ]]; then
+ if [ "$num" = "<not" ]; then
continue
fi
# save cycles count
- if [[ $evt == "cycles" ]]; then
- results[$cpu]=$num
+ if [ "$evt" = "cycles" ]; then
+ results="$results $cpu:$num"
continue
fi
+ cyc=${results##* $cpu:}
+ cyc=${cyc%% *}
+
# skip if no cycles
- local cyc=${results[$cpu]}
- if [[ -z $cyc ]]; then
+ if [ -z "$cyc" ]; then
continue
fi
# use printf for rounding and a leading zero
- local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
- if [[ $ipc != $res ]]; then
+ res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+ if [ "$ipc" != "$res" ]; then
echo "IPC is different for $cpu: $res != $ipc ($num / $cyc)"
exit 1
fi
attr_offset = lseek(ff.fd, 0, SEEK_CUR);
evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.size < sizeof(evsel->core.attr)) {
+ /*
+ * We are likely in "perf inject" and have read
+ * from an older file. Update attr size so that
+ * reader gets the right offset to the ids.
+ */
+ evsel->core.attr.size = sizeof(evsel->core.attr);
+ }
f_attr = (struct perf_file_attr){
.attr = evsel->core.attr,
.ids = {
pid_t machine__get_current_tid(struct machine *machine, int cpu)
{
- int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
return -1;
pid_t tid)
{
struct thread *thread;
- int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
if (cpu < 0)
return -EINVAL;
{
int i, err = -1;
struct perf_cpu_map *map;
- int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
for (i = 0; i < PERF_TYPE_MAX; ++i) {
struct evsel *evsel;
#include "evlist.h"
#include "expr.h"
#include "metricgroup.h"
+#include "cgroup.h"
#include <linux/zalloc.h>
/*
enum stat_type type;
int ctx;
int cpu;
+ struct cgroup *cgrp;
struct runtime_stat *stat;
struct stats stats;
u64 metric_total;
if (a->ctx != b->ctx)
return a->ctx - b->ctx;
+ if (a->cgrp != b->cgrp)
+ return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1;
+
if (a->evsel == NULL && b->evsel == NULL) {
if (a->stat == b->stat)
return 0;
bool create,
enum stat_type type,
int ctx,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct cgroup *cgrp)
{
struct rblist *rblist;
struct rb_node *nd;
.type = type,
.ctx = ctx,
.stat = st,
+ .cgrp = cgrp,
};
rblist = &st->value_list;
+ /* don't use context info for clock events */
+ if (type == STAT_NSECS)
+ dm.ctx = 0;
+
nd = rblist__find(rblist, &dm);
if (nd)
return container_of(nd, struct saved_value, rb_node);
reset_stat(st);
}
+struct runtime_stat_data {
+ int ctx;
+ struct cgroup *cgrp;
+};
+
static void update_runtime_stat(struct runtime_stat *st,
enum stat_type type,
- int ctx, int cpu, u64 count)
+ int cpu, u64 count,
+ struct runtime_stat_data *rsd)
{
- struct saved_value *v = saved_value_lookup(NULL, cpu, true,
- type, ctx, st);
+ struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+ rsd->ctx, st, rsd->cgrp);
if (v)
update_stats(&v->stats, count);
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
int cpu, struct runtime_stat *st)
{
- int ctx = evsel_context(counter);
u64 count_ns = count;
struct saved_value *v;
+ struct runtime_stat_data rsd = {
+ .ctx = evsel_context(counter),
+ .cgrp = counter->cgrp,
+ };
count *= counter->scale;
if (evsel__is_clock(counter))
- update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
+ update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
+ update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
+ update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
+ update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
+ update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, APERF))
- update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
+ update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
if (counter->collect_stat) {
- v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
+ v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+ rsd.cgrp);
update_stats(&v->stats, count);
if (counter->metric_leader)
v->metric_total += count;
} else if (counter->metric_leader) {
v = saved_value_lookup(counter->metric_leader,
- cpu, true, STAT_NONE, 0, st);
+ cpu, true, STAT_NONE, 0, st, rsd.cgrp);
v->metric_total += count;
v->metric_other++;
}
}
static double runtime_stat_avg(struct runtime_stat *st,
- enum stat_type type, int ctx, int cpu)
+ enum stat_type type, int cpu,
+ struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
}
static double runtime_stat_n(struct runtime_stat *st,
- enum stat_type type, int ctx, int cpu)
+ enum stat_type type, int cpu,
+ struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
}
static void print_stalled_cycles_frontend(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel, double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_stalled_cycles_backend(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel, double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_branch_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_l1_dcache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
-
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_l1_icache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
-
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_dtlb_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_itlb_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
}
static void print_ll_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
return x;
}
-static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
+static double td_total_slots(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
- return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
+ return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
}
-static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
+static double td_bad_spec(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double bad_spec = 0;
double total_slots;
double total;
- total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
- runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
- runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
+ runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
+ runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
- total_slots = td_total_slots(ctx, cpu, st);
+ total_slots = td_total_slots(cpu, st, rsd);
if (total_slots)
bad_spec = total / total_slots;
return sanitize_val(bad_spec);
}
-static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
+static double td_retiring(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double retiring = 0;
- double total_slots = td_total_slots(ctx, cpu, st);
+ double total_slots = td_total_slots(cpu, st, rsd);
double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
- ctx, cpu);
+ cpu, rsd);
if (total_slots)
retiring = ret_slots / total_slots;
return retiring;
}
-static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_fe_bound(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double fe_bound = 0;
- double total_slots = td_total_slots(ctx, cpu, st);
+ double total_slots = td_total_slots(cpu, st, rsd);
double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
- ctx, cpu);
+ cpu, rsd);
if (total_slots)
fe_bound = fetch_bub / total_slots;
return fe_bound;
}
-static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_be_bound(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
- double sum = (td_fe_bound(ctx, cpu, st) +
- td_bad_spec(ctx, cpu, st) +
- td_retiring(ctx, cpu, st));
+ double sum = (td_fe_bound(cpu, st, rsd) +
+ td_bad_spec(cpu, st, rsd) +
+ td_retiring(cpu, st, rsd));
if (sum == 0)
return 0;
return sanitize_val(1.0 - sum);
* the ratios we need to recreate the sum.
*/
-static double td_metric_ratio(int ctx, int cpu,
- enum stat_type type,
- struct runtime_stat *stat)
+static double td_metric_ratio(int cpu, enum stat_type type,
+ struct runtime_stat *stat,
+ struct runtime_stat_data *rsd)
{
- double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
- runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
- double d = runtime_stat_avg(stat, type, ctx, cpu);
+ double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
+ double d = runtime_stat_avg(stat, type, cpu, rsd);
if (sum)
return d / sum;
* We allow two missing.
*/
-static bool full_td(int ctx, int cpu,
- struct runtime_stat *stat)
+static bool full_td(int cpu, struct runtime_stat *stat,
+ struct runtime_stat_data *rsd)
{
int c = 0;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
c++;
return c >= 2;
}
-static void print_smi_cost(struct perf_stat_config *config,
- int cpu, struct evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config, int cpu,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double smi_num, aperf, cycles, cost = 0.0;
- int ctx = evsel_context(evsel);
const char *color = NULL;
- smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
- aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
- cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
+ aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
+ cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if ((cycles == 0) || (aperf == 0))
return;
scale = 1e-9;
} else {
v = saved_value_lookup(metric_events[i], cpu, false,
- STAT_NONE, 0, st);
+ STAT_NONE, 0, st,
+ metric_events[i]->cgrp);
if (!v)
break;
stats = &v->stats;
print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
const char *color = NULL;
- int ctx = evsel_context(evsel);
+ struct runtime_stat_data rsd = {
+ .ctx = evsel_context(evsel),
+ .cgrp = evsel->cgrp,
+ };
struct metric_event *me;
int num = 1;
if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
if (total) {
ratio = avg / total;
print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
- total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
total = max(total, runtime_stat_avg(st,
STAT_STALLED_CYCLES_BACK,
- ctx, cpu));
+ cpu, &rsd));
if (total && avg) {
out->new_line(config, ctxp);
ratio);
}
} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
- if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
- print_branch_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
+ print_branch_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
- print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
+ print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
} else if (
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
- print_l1_icache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
+ print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
} else if (
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
- print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
+ print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
} else if (
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
- print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
+ print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
} else if (
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
- print_ll_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
+ print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
- total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
if (total)
ratio = avg * 100 / total;
- if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
+ if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
+ print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
+ print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
if (total) {
ratio = avg / total;
print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
if (total)
print_metric(config, ctxp, NULL,
print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
- total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (total2 < avg)
total2 = avg;
else
print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (avg)
ratio = total / avg;
- if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
+ if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (avg)
ratio = total / avg;
else
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(ctx, cpu, st);
+ double fe_bound = td_fe_bound(cpu, st, &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(ctx, cpu, st);
+ double retiring = td_retiring(cpu, st, &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(ctx, cpu, st);
+ double bad_spec = td_bad_spec(cpu, st, &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(ctx, cpu, st);
+ double be_bound = td_be_bound(cpu, st, &rsd);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- if (td_total_slots(ctx, cpu, st) > 0)
+ if (td_total_slots(cpu, st, &rsd) > 0)
print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
- full_td(ctx, cpu, st)) {
- double retiring = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_RETIRING, st);
-
+ full_td(cpu, st, &rsd)) {
+ double retiring = td_metric_ratio(cpu,
+ STAT_TOPDOWN_RETIRING, st,
+ &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
- full_td(ctx, cpu, st)) {
- double fe_bound = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_FE_BOUND, st);
-
+ full_td(cpu, st, &rsd)) {
+ double fe_bound = td_metric_ratio(cpu,
+ STAT_TOPDOWN_FE_BOUND, st,
+ &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
- full_td(ctx, cpu, st)) {
- double be_bound = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_BE_BOUND, st);
-
+ full_td(cpu, st, &rsd)) {
+ double be_bound = td_metric_ratio(cpu,
+ STAT_TOPDOWN_BE_BOUND, st,
+ &rsd);
if (be_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
be_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
- full_td(ctx, cpu, st)) {
- double bad_spec = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_BAD_SPEC, st);
-
+ full_td(cpu, st, &rsd)) {
+ double bad_spec = td_metric_ratio(cpu,
+ STAT_TOPDOWN_BAD_SPEC, st,
+ &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
- } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
+ } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
char unit = 'M';
char unit_buf[10];
- total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
if (total)
ratio = 1000.0 * avg / total;
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(config, cpu, evsel, out, st);
+ print_smi_cost(config, cpu, out, st, &rsd);
} else {
num = 0;
}
return self.validate_config(build_dir)
def run_kernel(self, args=[], build_dir='', timeout=None):
- args.extend(['mem=1G'])
+ args.extend(['mem=1G', 'console=tty'])
self._ops.linux_bin(args, timeout, build_dir)
outfile = get_outfile_path(build_dir)
subprocess.call(['stty', 'sane'])
TARGETS_HOTPLUG = cpu-hotplug
TARGETS_HOTPLUG += memory-hotplug
-# User can optionally provide a TARGETS skiplist.
-SKIP_TARGETS ?=
+# User can optionally provide a TARGETS skiplist. By default we skip
+# BPF since it has cutting edge build time dependencies which require
+# more effort to install.
+SKIP_TARGETS ?= bpf
ifneq ($(SKIP_TARGETS),)
TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS))
override TARGETS := $(TMP)
mov x11, x1 // actual data
mov x12, x2 // data size
- puts "Mistatch: PID="
+ puts "Mismatch: PID="
mov x0, x20
bl putdec
puts ", iteration="
mov x11, x1 // actual data
mov x12, x2 // data size
- puts "Mistatch: PID="
+ puts "Mismatch: PID="
mov x0, x20
bl putdec
puts ", iteration="
/sys/kernel/btf/vmlinux \
/boot/vmlinux-$(shell uname -r)
VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
# to build individual tests.
struct bpf_spin_lock lock;
};
-/* Copies an rm binary to a temp file. dest is a mkstemp template */
-static int copy_rm(char *dest)
-{
- int fd_in, fd_out = -1, ret = 0;
- struct stat stat;
- char *buf = NULL;
-
- fd_in = open("/bin/rm", O_RDONLY);
- if (fd_in < 0)
- return -errno;
-
- fd_out = mkstemp(dest);
- if (fd_out < 0) {
- ret = -errno;
- goto out;
- }
-
- ret = fstat(fd_in, &stat);
- if (ret == -1) {
- ret = -errno;
- goto out;
- }
-
- buf = malloc(stat.st_blksize);
- if (!buf) {
- ret = -errno;
- goto out;
- }
-
- while (ret = read(fd_in, buf, stat.st_blksize), ret > 0) {
- ret = write(fd_out, buf, ret);
- if (ret < 0) {
- ret = -errno;
- goto out;
-
- }
- }
- if (ret < 0) {
- ret = -errno;
- goto out;
-
- }
-
- /* Set executable permission on the copied file */
- ret = chmod(dest, 0100);
- if (ret == -1)
- ret = -errno;
-
-out:
- free(buf);
- close(fd_in);
- close(fd_out);
- return ret;
-}
-
/* Fork and exec the provided rm binary and return the exit code of the
* forked process and its pid.
*/
void test_test_local_storage(void)
{
- char tmp_exec_path[PATH_MAX] = "/tmp/copy_of_rmXXXXXX";
+ char tmp_dir_path[64] = "/tmp/local_storageXXXXXX";
int err, serv_sk = -1, task_fd = -1, rm_fd = -1;
struct local_storage *skel = NULL;
+ char tmp_exec_path[64];
+ char cmd[256];
skel = local_storage__open_and_load();
if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
task_fd))
goto close_prog;
- err = copy_rm(tmp_exec_path);
- if (CHECK(err < 0, "copy_rm", "err %d errno %d\n", err, errno))
+ if (CHECK(!mkdtemp(tmp_dir_path), "mkdtemp",
+ "unable to create tmpdir: %d\n", errno))
goto close_prog;
+ snprintf(tmp_exec_path, sizeof(tmp_exec_path), "%s/copy_of_rm",
+ tmp_dir_path);
+ snprintf(cmd, sizeof(cmd), "cp /bin/rm %s", tmp_exec_path);
+ if (CHECK_FAIL(system(cmd)))
+ goto close_prog_rmdir;
+
rm_fd = open(tmp_exec_path, O_RDONLY);
if (CHECK(rm_fd < 0, "open", "failed to open %s err:%d, errno:%d",
tmp_exec_path, rm_fd, errno))
- goto close_prog;
+ goto close_prog_rmdir;
if (!check_syscall_operations(bpf_map__fd(skel->maps.inode_storage_map),
rm_fd))
- goto close_prog;
+ goto close_prog_rmdir;
/* Sets skel->bss->monitored_pid to the pid of the forked child
* forks a child process that executes tmp_exec_path and tries to
*/
err = run_self_unlink(&skel->bss->monitored_pid, tmp_exec_path);
if (CHECK(err != EPERM, "run_self_unlink", "err %d want EPERM\n", err))
- goto close_prog_unlink;
+ goto close_prog_rmdir;
/* Set the process being monitored to be the current process */
skel->bss->monitored_pid = getpid();
- /* Remove the temporary created executable */
- err = unlink(tmp_exec_path);
- if (CHECK(err != 0, "unlink", "unable to unlink %s: %d", tmp_exec_path,
- errno))
- goto close_prog_unlink;
+ /* Move copy_of_rm to a new location so that it triggers the
+ * inode_rename LSM hook with a new_dentry that has a NULL inode ptr.
+ */
+ snprintf(cmd, sizeof(cmd), "mv %s/copy_of_rm %s/check_null_ptr",
+ tmp_dir_path, tmp_dir_path);
+ if (CHECK_FAIL(system(cmd)))
+ goto close_prog_rmdir;
CHECK(skel->data->inode_storage_result != 0, "inode_storage_result",
"inode_local_storage not set\n");
serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
- goto close_prog;
+ goto close_prog_rmdir;
CHECK(skel->data->sk_storage_result != 0, "sk_storage_result",
"sk_local_storage not set\n");
if (!check_syscall_operations(bpf_map__fd(skel->maps.sk_storage_map),
serv_sk))
- goto close_prog;
+ goto close_prog_rmdir;
-close_prog_unlink:
- unlink(tmp_exec_path);
+close_prog_rmdir:
+ snprintf(cmd, sizeof(cmd), "rm -rf %s", tmp_dir_path);
+ system(cmd);
close_prog:
close(serv_sk);
close(rm_fd);
* Copyright 2020 Google LLC.
*/
-#include "vmlinux.h"
+#include <linux/bpf.h>
#include <errno.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
__u32 pid = bpf_get_current_pid_tgid() >> 32;
struct local_storage *storage;
bool is_self_unlink;
- int err;
if (pid != monitored_pid)
return 0;
return -EPERM;
}
- storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0,
- BPF_LOCAL_STORAGE_GET_F_CREATE);
+ return 0;
+}
+
+SEC("lsm/inode_rename")
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
+{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
+ struct local_storage *storage;
+ int err;
+
+ /* new_dentry->d_inode can be NULL when the inode is renamed to a file
+ * that did not exist before. The helper should be able to handle this
+ * NULL pointer.
+ */
+ bpf_inode_storage_get(&inode_storage_map, new_dentry->d_inode, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+
+ storage = bpf_inode_storage_get(&inode_storage_map, old_dentry->d_inode,
+ 0, 0);
if (!storage)
return 0;
inode_storage_result = -1;
bpf_spin_unlock(&storage->lock);
- err = bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+ err = bpf_inode_storage_delete(&inode_storage_map, old_dentry->d_inode);
if (!err)
inode_storage_result = err;
return 0;
}
-SEC("lsm/file_open")
-int BPF_PROG(file_open, struct file *file)
-{
- __u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct local_storage *storage;
-
- if (pid != monitored_pid)
- return 0;
-
- if (!file->f_inode)
- return 0;
-
- storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0,
- BPF_LOCAL_STORAGE_GET_F_CREATE);
- if (!storage)
- return 0;
-
- bpf_spin_lock(&storage->lock);
- storage->value = DUMMY_STORAGE_VALUE;
- bpf_spin_unlock(&storage->lock);
- return 0;
-}
-
/* This uses the local storage to remember the inode of the binary that a
* process was originally executing.
*/
SEC("lsm/bprm_committed_creds")
void BPF_PROG(exec, struct linux_binprm *bprm)
{
+ __u32 pid = bpf_get_current_pid_tgid() >> 32;
struct local_storage *storage;
+ if (pid != monitored_pid)
+ return;
+
storage = bpf_task_storage_get(&task_storage_map,
bpf_get_current_task_btf(), 0,
BPF_LOCAL_STORAGE_GET_F_CREATE);
storage->exec_inode = bprm->file->f_inode;
bpf_spin_unlock(&storage->lock);
}
+
+ storage = bpf_inode_storage_get(&inode_storage_map, bprm->file->f_inode,
+ 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!storage)
+ return;
+
+ bpf_spin_lock(&storage->lock);
+ storage->value = DUMMY_STORAGE_VALUE;
+ bpf_spin_unlock(&storage->lock);
}
#define DO_UPDATE 1
#define DO_DELETE 0
+#define MAP_RETRIES 20
+
+static int map_update_retriable(int map_fd, const void *key, const void *value,
+ int flags, int attempts)
+{
+ while (bpf_map_update_elem(map_fd, key, value, flags)) {
+ if (!attempts || (errno != EAGAIN && errno != EBUSY))
+ return -errno;
+
+ usleep(1);
+ attempts--;
+ }
+
+ return 0;
+}
+
+static int map_delete_retriable(int map_fd, const void *key, int attempts)
+{
+ while (bpf_map_delete_elem(map_fd, key)) {
+ if (!attempts || (errno != EAGAIN && errno != EBUSY))
+ return -errno;
+
+ usleep(1);
+ attempts--;
+ }
+
+ return 0;
+}
+
static void test_update_delete(unsigned int fn, void *data)
{
int do_update = ((int *)data)[1];
int fd = ((int *)data)[0];
- int i, key, value;
+ int i, key, value, err;
for (i = fn; i < MAP_SIZE; i += TASKS) {
key = value = i;
if (do_update) {
- assert(bpf_map_update_elem(fd, &key, &value,
- BPF_NOEXIST) == 0);
- assert(bpf_map_update_elem(fd, &key, &value,
- BPF_EXIST) == 0);
+ err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES);
+ if (err)
+ printf("error %d %d\n", err, errno);
+ assert(err == 0);
+ err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES);
+ if (err)
+ printf("error %d %d\n", err, errno);
+ assert(err == 0);
} else {
- assert(bpf_map_delete_elem(fd, &key) == 0);
+ err = map_delete_retriable(fd, &key, MAP_RETRIES);
+ if (err)
+ printf("error %d %d\n", err, errno);
+ assert(err == 0);
}
}
}
#define MAX_INSNS BPF_MAXINSNS
#define MAX_TEST_INSNS 1000000
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 20
+#define MAX_NR_MAPS 21
#define MAX_TEST_RUNS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
int fixup_sk_storage_map[MAX_FIXUPS];
int fixup_map_event_output[MAX_FIXUPS];
int fixup_map_reuseport_array[MAX_FIXUPS];
+ int fixup_map_ringbuf[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
uint32_t insn_processed;
int *fixup_sk_storage_map = test->fixup_sk_storage_map;
int *fixup_map_event_output = test->fixup_map_event_output;
int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
+ int *fixup_map_ringbuf = test->fixup_map_ringbuf;
if (test->fill_helper) {
test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
fixup_map_reuseport_array++;
} while (*fixup_map_reuseport_array);
}
+ if (*fixup_map_ringbuf) {
+ map_fds[20] = create_map(BPF_MAP_TYPE_RINGBUF, 0,
+ 0, 4096);
+ do {
+ prog[*fixup_map_ringbuf].imm = map_fds[20];
+ fixup_map_ringbuf++;
+ } while (*fixup_map_ringbuf);
+ }
}
struct libcap {
.result = ACCEPT,
.result_unpriv = ACCEPT,
},
+{
+ "check valid spill/fill, ptr to mem",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = ACCEPT,
+ .result_unpriv = ACCEPT,
+},
{
"check corrupted spill/fill",
.insns = {
int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
if (payload == EOT) {
- ksft_print_msg("End-of-tranmission frame received\n");
+ ksft_print_msg("End-of-transmission frame received\n");
fprintf(stdout, "---------------------------------------\n");
break;
}
}
if (payloadseqnum == EOT) {
- ksft_print_msg("End-of-tranmission frame received: PASS\n");
+ ksft_print_msg("End-of-transmission frame received: PASS\n");
sigvar = 1;
break;
}
__mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null
# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
# is (-2*MTU) about 80K of delay provision.
- __mlnx_qos -i $swp3 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
+ __mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
# bridges
# -------
UNAME_M := s390x
endif
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_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 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 lib/s390x/diag318_test_handler.c
* Copyright (C) 2019, Google, Inc.
*/
-#define _GNU_SOURCE /* for program_invocation_name */
+#define _GNU_SOURCE /* for pipe2 */
#include <stdio.h>
#include <stdlib.h>
-#include <sys/syscall.h>
-#include <unistd.h>
-#include <asm/unistd.h>
#include <time.h>
#include <poll.h>
#include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
#include <linux/userfaultfd.h>
+#include <sys/syscall.h>
-#include "perf_test_util.h"
-#include "processor.h"
+#include "kvm_util.h"
#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
#ifdef __NR_userfaultfd
#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
#endif
+static int nr_vcpus = 1;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
static char *guest_data_prototype;
static void *vcpu_worker(void *data)
{
int ret;
- struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
struct kvm_vm *vm = perf_test_args.vm;
struct kvm_run *run;
return 0;
}
-static void run_test(enum vm_guest_mode mode, bool use_uffd,
- useconds_t uffd_delay)
+struct test_params {
+ bool use_uffd;
+ useconds_t uffd_delay;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
+ struct test_params *p = arg;
pthread_t *vcpu_threads;
pthread_t *uffd_handler_threads = NULL;
struct uffd_handler_args *uffd_args = NULL;
int vcpu_id;
int r;
- vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+ vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
perf_test_args.wr_fract = 1;
vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
TEST_ASSERT(vcpu_threads, "Memory allocation failed");
- add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+ perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
- if (use_uffd) {
+ if (p->use_uffd) {
uffd_handler_threads =
malloc(nr_vcpus * sizeof(*uffd_handler_threads));
TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
r = setup_demand_paging(vm,
&uffd_handler_threads[vcpu_id],
pipefds[vcpu_id * 2],
- uffd_delay, &uffd_args[vcpu_id],
+ p->uffd_delay, &uffd_args[vcpu_id],
vcpu_hva, guest_percpu_mem_size);
if (r < 0)
exit(-r);
pr_info("All vCPU threads joined\n");
- if (use_uffd) {
+ if (p->use_uffd) {
char c;
/* Tell the user fault fd handler threads to quit */
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);
+ perf_test_destroy_vm(vm);
free(guest_data_prototype);
free(vcpu_threads);
- if (use_uffd) {
+ if (p->use_uffd) {
free(uffd_handler_threads);
free(uffd_args);
free(pipefds);
}
}
-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] [-m mode] [-u] [-d uffd_delay_usec]\n"
" [-b memory] [-v vcpus]\n", name);
- printf(" -m: specify the guest mode ID to test\n"
- " (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)" : "");
- }
+ guest_modes_help();
printf(" -u: use User Fault FD to handle vCPU page\n"
" faults.\n");
printf(" -d: add a delay in usec to the User Fault\n"
int main(int argc, char *argv[])
{
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
- bool mode_selected = false;
- unsigned int mode;
- int opt, i;
- bool use_uffd = false;
- useconds_t uffd_delay = 0;
-
-#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
+ struct test_params p = {};
+ int opt;
+
+ guest_modes_append_default();
while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) {
switch (opt) {
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;
+ guest_modes_cmdline(optarg);
break;
case 'u':
- use_uffd = true;
+ p.use_uffd = true;
break;
case 'd':
- uffd_delay = strtoul(optarg, NULL, 0);
- TEST_ASSERT(uffd_delay >= 0,
- "A negative UFFD delay is not supported.");
+ p.uffd_delay = strtoul(optarg, NULL, 0);
+ TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported.");
break;
case 'b':
guest_percpu_mem_size = parse_size(optarg);
}
}
- 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, use_uffd, uffd_delay);
- }
+ for_each_guest_mode(run_test, &p);
return 0;
}
* 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"
+#include "perf_test_util.h"
+#include "guest_modes.h"
/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
#define TEST_HOST_LOOP_N 2UL
+static int nr_vcpus = 1;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
/* Host variables */
static u64 dirty_log_manual_caps;
static bool host_quit;
static uint64_t iteration;
-static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+static uint64_t vcpu_last_completed_iteration[KVM_MAX_VCPUS];
static void *vcpu_worker(void *data)
{
struct timespec ts_diff;
struct timespec total = (struct timespec){0};
struct timespec avg;
- struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
return NULL;
}
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
- uint64_t phys_offset, int wr_fract)
+struct test_params {
+ unsigned long iterations;
+ uint64_t phys_offset;
+ int wr_fract;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
+ struct test_params *p = arg;
pthread_t *vcpu_threads;
struct kvm_vm *vm;
unsigned long *bmap;
struct kvm_enable_cap cap = {};
struct timespec clear_dirty_log_total = (struct timespec){0};
- vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+ vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
- perf_test_args.wr_fract = wr_fract;
+ perf_test_args.wr_fract = p->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);
vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
TEST_ASSERT(vcpu_threads, "Memory allocation failed");
- add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+ perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
sync_global_to_guest(vm, perf_test_args);
/* Enable dirty logging */
clock_gettime(CLOCK_MONOTONIC, &start);
- vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+ vm_mem_region_set_flags(vm, PERF_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) {
+ while (iteration < p->iterations) {
/*
* Incrementing the iteration number will start the vCPUs
* dirtying memory again.
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);
+ kvm_vm_get_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap);
ts_diff = timespec_diff_now(start);
get_dirty_log_total = timespec_add(get_dirty_log_total,
if (dirty_log_manual_caps) {
clock_gettime(CLOCK_MONOTONIC, &start);
- kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+ kvm_vm_clear_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap, 0,
host_num_pages);
ts_diff = timespec_diff_now(start);
/* Disable dirty logging */
clock_gettime(CLOCK_MONOTONIC, &start);
- vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+ vm_mem_region_set_flags(vm, PERF_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);
+ avg = timespec_div(get_dirty_log_total, p->iterations);
pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
- iterations, get_dirty_log_total.tv_sec,
+ p->iterations, get_dirty_log_total.tv_sec,
get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
if (dirty_log_manual_caps) {
- avg = timespec_div(clear_dirty_log_total, iterations);
+ avg = timespec_div(clear_dirty_log_total, p->iterations);
pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
- iterations, clear_dirty_log_total.tv_sec,
+ p->iterations, clear_dirty_log_total.tv_sec,
clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
}
free(bmap);
free(vcpu_threads);
- ucall_uninit(vm);
- kvm_vm_free(vm);
+ perf_test_destroy_vm(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);
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)" : "");
- }
+ guest_modes_help();
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");
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;
+ int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+ struct test_params p = {
+ .iterations = TEST_HOST_LOOP_N,
+ .wr_fract = 1,
+ };
+ int opt;
dirty_log_manual_caps =
kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
KVM_DIRTY_LOG_INITIALLY_SET);
-#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
+ guest_modes_append_default();
while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
switch (opt) {
case 'i':
- iterations = strtol(optarg, NULL, 10);
+ p.iterations = strtol(optarg, NULL, 10);
break;
case 'p':
- phys_offset = strtoull(optarg, NULL, 0);
+ 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;
+ guest_modes_cmdline(optarg);
break;
case 'b':
guest_percpu_mem_size = parse_size(optarg);
break;
case 'f':
- wr_fract = atoi(optarg);
- TEST_ASSERT(wr_fract >= 1,
+ p.wr_fract = atoi(optarg);
+ TEST_ASSERT(p.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);
+ 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(iterations >= 2, "The test should have at least two iterations");
+ TEST_ASSERT(p.iterations >= 2, "The test should have at least two iterations");
- pr_info("Test iterations: %"PRIu64"\n", iterations);
+ pr_info("Test iterations: %"PRIu64"\n", p.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);
- }
+ for_each_guest_mode(run_test, &p);
return 0;
}
#include <stdio.h>
#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
#include <pthread.h>
#include <semaphore.h>
#include <sys/types.h>
#include <linux/bitops.h>
#include <asm/barrier.h>
-#include "test_util.h"
#include "kvm_util.h"
+#include "test_util.h"
+#include "guest_modes.h"
#include "processor.h"
#define VCPU_ID 1
#define DIRTY_MEM_BITS 30 /* 1G */
#define PAGE_SHIFT_4K 12
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
- unsigned long interval, uint64_t phys_offset)
+struct test_params {
+ unsigned long iterations;
+ unsigned long interval;
+ uint64_t phys_offset;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
+ struct test_params *p = arg;
struct kvm_vm *vm;
unsigned long *bmap;
host_page_size = getpagesize();
host_num_pages = vm_num_host_pages(mode, guest_num_pages);
- if (!phys_offset) {
+ if (!p->phys_offset) {
guest_test_phys_mem = (vm_get_max_gfn(vm) -
guest_num_pages) * guest_page_size;
guest_test_phys_mem &= ~(host_page_size - 1);
} else {
- guest_test_phys_mem = phys_offset;
+ guest_test_phys_mem = p->phys_offset;
}
#ifdef __s390x__
pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
- while (iteration < iterations) {
+ while (iteration < p->iterations) {
/* Give the vcpu thread some time to dirty some pages */
- usleep(interval * 1000);
+ usleep(p->interval * 1000);
log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
bmap, host_num_pages);
vm_dirty_log_verify(mode, bmap);
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] [-I interval] "
"[-p offset] [-m mode]\n", name);
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"
- " 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)" : "");
- }
+ guest_modes_help();
puts("");
exit(0);
}
int main(int argc, char *argv[])
{
- unsigned long iterations = TEST_HOST_LOOP_N;
- unsigned long interval = TEST_HOST_LOOP_INTERVAL;
- bool mode_selected = false;
- uint64_t phys_offset = 0;
- unsigned int mode;
- int opt, i, j;
+ struct test_params p = {
+ .iterations = TEST_HOST_LOOP_N,
+ .interval = TEST_HOST_LOOP_INTERVAL,
+ };
+ int opt, i;
sem_init(&dirty_ring_vcpu_stop, 0, 0);
sem_init(&dirty_ring_vcpu_cont, 0, 0);
-#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
+ guest_modes_append_default();
while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
switch (opt) {
test_dirty_ring_count = strtol(optarg, NULL, 10);
break;
case 'i':
- iterations = strtol(optarg, NULL, 10);
+ p.iterations = strtol(optarg, NULL, 10);
break;
case 'I':
- interval = strtol(optarg, NULL, 10);
+ p.interval = strtol(optarg, NULL, 10);
break;
case 'p':
- phys_offset = strtoull(optarg, NULL, 0);
+ 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;
+ guest_modes_cmdline(optarg);
break;
case 'M':
if (!strcmp(optarg, "all")) {
}
}
- TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
- TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+ TEST_ASSERT(p.iterations > 2, "Iterations must be greater than two");
+ TEST_ASSERT(p.interval > 0, "Interval must be greater than zero");
pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
- iterations, interval);
+ p.iterations, p.interval);
srandom(time(0));
- 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));
- 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);
+ if (host_log_mode_option == LOG_MODE_ALL) {
+ /* Run each log mode */
+ for (i = 0; i < LOG_MODE_NUM; i++) {
+ pr_info("Testing Log Mode '%s'\n", log_modes[i].name);
+ host_log_mode = i;
+ for_each_guest_mode(run_test, &p);
}
+ } else {
+ host_log_mode = host_log_mode_option;
+ for_each_guest_mode(run_test, &p);
}
return 0;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+
+struct guest_mode {
+ bool supported;
+ bool enabled;
+};
+
+extern struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_append(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+void guest_modes_append_default(void);
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg);
+void guest_modes_help(void);
+void guest_modes_cmdline(const char *arg);
#include "sparsebit.h"
+#define KVM_MAX_VCPUS 512
/*
* Callers of kvm_util only have an incomplete/opaque description of the
#define vm_guest_mode_string(m) vm_guest_mode_string[m]
extern const char * const vm_guest_mode_string[];
+struct vm_guest_mode_params {
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+extern const struct vm_guest_mode_params vm_guest_mode_params[];
+
enum vm_mem_backing_src_type {
VM_MEM_SRC_ANONYMOUS,
VM_MEM_SRC_ANONYMOUS_THP,
#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;
+#define PERF_TEST_MEM_SLOT_INDEX 1
-struct vcpu_args {
+struct perf_test_vcpu_args {
uint64_t gva;
uint64_t pages;
uint64_t guest_page_size;
int wr_fract;
- struct vcpu_args vcpu_args[MAX_VCPUS];
+ struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
};
-static struct perf_test_args perf_test_args;
+extern struct perf_test_args perf_test_args;
/*
- * Continuously write to the first 8 bytes of each page in the
- * specified region.
+ * 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 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);
-
- 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;
+extern uint64_t guest_test_phys_mem;
- 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);
- }
-}
+struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes);
+void perf_test_destroy_vm(struct kvm_vm *vm);
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes);
#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "guest_modes.h"
+
+struct guest_mode guest_modes[NUM_VM_MODES];
+
+void guest_modes_append_default(void)
+{
+ guest_mode_append(VM_MODE_DEFAULT, true, true);
+
+#ifdef __aarch64__
+ guest_mode_append(VM_MODE_P40V48_64K, true, true);
+ {
+ unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ if (limit >= 52)
+ guest_mode_append(VM_MODE_P52V48_64K, true, true);
+ if (limit >= 48) {
+ guest_mode_append(VM_MODE_P48V48_4K, true, true);
+ guest_mode_append(VM_MODE_P48V48_64K, true, true);
+ }
+ }
+#endif
+}
+
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
+{
+ int i;
+
+ 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));
+ func(i, arg);
+ }
+}
+
+void guest_modes_help(void)
+{
+ int i;
+
+ printf(" -m: specify the guest mode ID to test\n"
+ " (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)" : "");
+ }
+}
+
+void guest_modes_cmdline(const char *arg)
+{
+ static bool mode_selected;
+ unsigned int mode;
+ int i;
+
+ 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;
+}
_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
-struct vm_guest_mode_params {
- unsigned int pa_bits;
- unsigned int va_bits;
- unsigned int page_size;
- unsigned int page_shift;
-};
-
-static const struct vm_guest_mode_params vm_guest_mode_params[] = {
+const struct vm_guest_mode_params vm_guest_mode_params[] = {
{ 52, 48, 0x1000, 12 },
{ 52, 48, 0x10000, 16 },
{ 48, 48, 0x1000, 12 },
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+
+struct perf_test_args perf_test_args;
+
+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;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+ struct perf_test_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);
+ }
+}
+
+struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes)
+{
+ struct kvm_vm *vm;
+ uint64_t guest_num_pages;
+
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+ perf_test_args.host_page_size = getpagesize();
+ perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+
+ guest_num_pages = vm_adjust_num_guest_pages(mode,
+ (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+ "Guest memory size is not host page size aligned.");
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+ "Guest memory size is not guest page size aligned.");
+
+ vm = vm_create_with_vcpus(mode, vcpus,
+ (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
+ 0, guest_code, NULL);
+
+ perf_test_args.vm = vm;
+
+ /*
+ * 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);
+
+ 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,
+ PERF_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;
+}
+
+void perf_test_destroy_vm(struct kvm_vm *vm)
+{
+ ucall_uninit(vm);
+ kvm_vm_free(vm);
+}
+
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+ vm_paddr_t vcpu_gpa;
+ struct perf_test_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];
+
+ 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);
+ }
+}
pid3=$!
ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
pid4=$!
- ip netns exec me mausezahn veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+ ip netns exec me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
pid5=$!
sleep 300
check_route6 "2001:db8:104::1 dev dummy2 proto kernel metric 260"
log_test $? 0 "Set metric with peer route on local side"
- log_test $? 0 "User specified metric on local address"
check_route6 "2001:db8:104::2 dev dummy2 proto kernel metric 260"
log_test $? 0 "Set metric with peer route on peer side"
# - list_flush_ipv6_exception
# Using the same topology as in pmtu_ipv6, create exceptions, and check
# they are shown when listing exception caches, gone after flushing them
-
+#
+# - pmtu_ipv4_route_change
+# Use the same topology as in pmtu_ipv4, but issue a route replacement
+# command and delete the corresponding device afterward. This tests for
+# proper cleanup of the PMTU exceptions by the route replacement path.
+# Device unregistration should complete successfully
+#
+# - pmtu_ipv6_route_change
+# Same as above but with IPv6
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
cleanup_ipv4_exception ipv4: cleanup of cached exceptions 1
cleanup_ipv6_exception ipv6: cleanup of cached exceptions 1
list_flush_ipv4_exception ipv4: list and flush cached exceptions 1
- list_flush_ipv6_exception ipv6: list and flush cached exceptions 1"
+ list_flush_ipv6_exception ipv6: list and flush cached exceptions 1
+ pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1
+ pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1"
NS_A="ns-A"
NS_B="ns-B"
return ${fail}
}
+test_pmtu_ipvX_route_change() {
+ family=${1}
+
+ setup namespaces routing || return 2
+ trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
+ "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
+ "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2
+
+ if [ ${family} -eq 4 ]; then
+ ping=ping
+ dst1="${prefix4}.${b_r1}.1"
+ dst2="${prefix4}.${b_r2}.1"
+ gw="${prefix4}.${a_r1}.2"
+ else
+ ping=${ping6}
+ dst1="${prefix6}:${b_r1}::1"
+ dst2="${prefix6}:${b_r2}::1"
+ gw="${prefix6}:${a_r1}::2"
+ fi
+
+ # Set up initial MTU values
+ mtu "${ns_a}" veth_A-R1 2000
+ mtu "${ns_r1}" veth_R1-A 2000
+ mtu "${ns_r1}" veth_R1-B 1400
+ mtu "${ns_b}" veth_B-R1 1400
+
+ mtu "${ns_a}" veth_A-R2 2000
+ mtu "${ns_r2}" veth_R2-A 2000
+ mtu "${ns_r2}" veth_R2-B 1500
+ mtu "${ns_b}" veth_B-R2 1500
+
+ # Create route exceptions
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1}
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2}
+
+ # Check that exceptions have been created with the correct PMTU
+ pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+ check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+ pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+ check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+ # Replace the route from A to R1
+ run_cmd ${ns_a} ip route change default via ${gw}
+
+ # Delete the device in A
+ run_cmd ${ns_a} ip link del "veth_A-R1"
+}
+
+test_pmtu_ipv4_route_change() {
+ test_pmtu_ipvX_route_change 4
+}
+
+test_pmtu_ipv6_route_change() {
+ test_pmtu_ipvX_route_change 6
+}
+
usage() {
echo
echo "$0 [OPTIONS] [TEST]..."
FIXTURE_VARIANT(tls)
{
- u16 tls_version;
- u16 cipher_type;
+ uint16_t tls_version;
+ uint16_t cipher_type;
};
FIXTURE_VARIANT_ADD(tls, 12_gcm)
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+# set global exit status, but never reset nonzero one.
+check_err()
+{
+ if [ $ret -eq 0 ]; then
+ ret=$1
+ fi
+}
+
cleanup() {
local -r jobs="$(jobs -p)"
local -r ns="$(ip netns list|grep $PEER_NS)"
# Hack: let bg programs complete the startup
sleep 0.1
./udpgso_bench_tx ${tx_args}
+ ret=$?
wait $(jobs -p)
+ return $ret
}
run_test() {
sleep 0.1
./udpgso_bench_tx ${tx_args}
+ ret=$?
kill -INT $pid
wait $(jobs -p)
+ return $ret
}
run_one_2sock() {
sleep 0.1
# first UDP GSO socket should be closed at this point
./udpgso_bench_tx ${tx_args}
+ ret=$?
wait $(jobs -p)
+ return $ret
}
run_nat_test() {
local -r core_args="-l 4"
local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+ ret=0
echo "ipv4"
run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+ check_err $?
# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
# when GRO does not take place
run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+ check_err $?
# the GSO packets are aggregated because:
# * veth schedule napi after each xmit
# * segmentation happens in BH context, veth napi poll is delayed after
# the transmission of the last segment
run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+ check_err $?
run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+ check_err $?
run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+ check_err $?
run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+ check_err $?
run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+ check_err $?
run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+ check_err $?
echo "ipv6"
run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+ check_err $?
run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+ check_err $?
run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+ check_err $?
run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+ check_err $?
run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+ check_err $?
run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+ check_err $?
run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+ check_err $?
run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452"
+ check_err $?
+ return $ret
}
if [ ! -f ../bpf/xdp_dummy.o ]; then
shift
run_one_2sock $@
fi
+
+exit $?
TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
- nft_queue.sh nft_meta.sh
+ nft_queue.sh nft_meta.sh \
+ ipip-conntrack-mtu.sh
LDLIBS = -lmnl
TEST_GEN_FILES = nf-queue
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Conntrack needs to reassemble fragments in order to have complete
+# packets for rule matching. Reassembly can lead to packet loss.
+
+# Consider the following setup:
+# +--------+ +---------+ +--------+
+# |Router A|-------|Wanrouter|-------|Router B|
+# | |.IPIP..| |..IPIP.| |
+# +--------+ +---------+ +--------+
+# / mtu 1400 \
+# / \
+#+--------+ +--------+
+#|Client A| |Client B|
+#| | | |
+#+--------+ +--------+
+
+# Router A and Router B use IPIP tunnel interfaces to tunnel traffic
+# between Client A and Client B over WAN. Wanrouter has MTU 1400 set
+# on its interfaces.
+
+rnd=$(mktemp -u XXXXXXXX)
+rx=$(mktemp)
+
+r_a="ns-ra-$rnd"
+r_b="ns-rb-$rnd"
+r_w="ns-rw-$rnd"
+c_a="ns-ca-$rnd"
+c_b="ns-cb-$rnd"
+
+checktool (){
+ if ! $1 > /dev/null 2>&1; then
+ echo "SKIP: Could not $2"
+ exit $ksft_skip
+ fi
+}
+
+checktool "iptables --version" "run test without iptables"
+checktool "ip -Version" "run test without ip tool"
+checktool "which nc" "run test without nc (netcat)"
+checktool "ip netns add ${r_a}" "create net namespace"
+
+for n in ${r_b} ${r_w} ${c_a} ${c_b};do
+ ip netns add ${n}
+done
+
+cleanup() {
+ for n in ${r_a} ${r_b} ${r_w} ${c_a} ${c_b};do
+ ip netns del ${n}
+ done
+ rm -f ${rx}
+}
+
+trap cleanup EXIT
+
+test_path() {
+ msg="$1"
+
+ ip netns exec ${c_b} nc -n -w 3 -q 3 -u -l -p 5000 > ${rx} < /dev/null &
+
+ sleep 1
+ for i in 1 2 3; do
+ head -c1400 /dev/zero | tr "\000" "a" | ip netns exec ${c_a} nc -n -w 1 -u 192.168.20.2 5000
+ done
+
+ wait
+
+ bytes=$(wc -c < ${rx})
+
+ if [ $bytes -eq 1400 ];then
+ echo "OK: PMTU $msg connection tracking"
+ else
+ echo "FAIL: PMTU $msg connection tracking: got $bytes, expected 1400"
+ exit 1
+ fi
+}
+
+# Detailed setup for Router A
+# ---------------------------
+# Interfaces:
+# eth0: 10.2.2.1/24
+# eth1: 192.168.10.1/24
+# ipip0: No IP address, local 10.2.2.1 remote 10.4.4.1
+# Routes:
+# 192.168.20.0/24 dev ipip0 (192.168.20.0/24 is subnet of Client B)
+# 10.4.4.1 via 10.2.2.254 (Router B via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_a} type veth peer name veth0 netns ${r_w}
+ip link add veth1 netns ${r_a} type veth peer name veth0 netns ${c_a}
+
+l_addr="10.2.2.1"
+r_addr="10.4.4.1"
+ip netns exec ${r_a} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+ ip -net ${r_a} link set $dev up
+done
+
+ip -net ${r_a} addr add 10.2.2.1/24 dev veth0
+ip -net ${r_a} addr add 192.168.10.1/24 dev veth1
+
+ip -net ${r_a} route add 192.168.20.0/24 dev ipip0
+ip -net ${r_a} route add 10.4.4.0/24 via 10.2.2.254
+
+ip netns exec ${r_a} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Detailed setup for Router B
+# ---------------------------
+# Interfaces:
+# eth0: 10.4.4.1/24
+# eth1: 192.168.20.1/24
+# ipip0: No IP address, local 10.4.4.1 remote 10.2.2.1
+# Routes:
+# 192.168.10.0/24 dev ipip0 (192.168.10.0/24 is subnet of Client A)
+# 10.2.2.1 via 10.4.4.254 (Router A via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_b} type veth peer name veth1 netns ${r_w}
+ip link add veth1 netns ${r_b} type veth peer name veth0 netns ${c_b}
+
+l_addr="10.4.4.1"
+r_addr="10.2.2.1"
+
+ip netns exec ${r_b} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+ ip -net ${r_b} link set $dev up
+done
+
+ip -net ${r_b} addr add 10.4.4.1/24 dev veth0
+ip -net ${r_b} addr add 192.168.20.1/24 dev veth1
+
+ip -net ${r_b} route add 192.168.10.0/24 dev ipip0
+ip -net ${r_b} route add 10.2.2.0/24 via 10.4.4.254
+ip netns exec ${r_b} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Client A
+ip -net ${c_a} addr add 192.168.10.2/24 dev veth0
+ip -net ${c_a} link set dev lo up
+ip -net ${c_a} link set dev veth0 up
+ip -net ${c_a} route add default via 192.168.10.1
+
+# Client A
+ip -net ${c_b} addr add 192.168.20.2/24 dev veth0
+ip -net ${c_b} link set dev veth0 up
+ip -net ${c_b} link set dev lo up
+ip -net ${c_b} route add default via 192.168.20.1
+
+# Wan
+ip -net ${r_w} addr add 10.2.2.254/24 dev veth0
+ip -net ${r_w} addr add 10.4.4.254/24 dev veth1
+
+ip -net ${r_w} link set dev lo up
+ip -net ${r_w} link set dev veth0 up mtu 1400
+ip -net ${r_w} link set dev veth1 up mtu 1400
+
+ip -net ${r_a} link set dev veth0 mtu 1400
+ip -net ${r_b} link set dev veth0 mtu 1400
+
+ip netns exec ${r_w} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Path MTU discovery
+# ------------------
+# Running tracepath from Client A to Client B shows PMTU discovery is working
+# as expected:
+#
+# clienta:~# tracepath 192.168.20.2
+# 1?: [LOCALHOST] pmtu 1500
+# 1: 192.168.10.1 0.867ms
+# 1: 192.168.10.1 0.302ms
+# 2: 192.168.10.1 0.312ms pmtu 1480
+# 2: no reply
+# 3: 192.168.10.1 0.510ms pmtu 1380
+# 3: 192.168.20.2 2.320ms reached
+# Resume: pmtu 1380 hops 3 back 3
+
+# ip netns exec ${c_a} traceroute --mtu 192.168.20.2
+
+# Router A has learned PMTU (1400) to Router B from Wanrouter.
+# Client A has learned PMTU (1400 - IPIP overhead = 1380) to Client B
+# from Router A.
+
+#Send large UDP packet
+#---------------------
+#Now we send a 1400 bytes UDP packet from Client A to Client B:
+
+# clienta:~# head -c1400 /dev/zero | tr "\000" "a" | nc -u 192.168.20.2 5000
+test_path "without"
+
+# The IPv4 stack on Client A already knows the PMTU to Client B, so the
+# UDP packet is sent as two fragments (1380 + 20). Router A forwards the
+# fragments between eth1 and ipip0. The fragments fit into the tunnel and
+# reach their destination.
+
+#When sending the large UDP packet again, Router A now reassembles the
+#fragments before routing the packet over ipip0. The resulting IPIP
+#packet is too big (1400) for the tunnel PMTU (1380) to Router B, it is
+#dropped on Router A before sending.
+
+ip netns exec ${r_a} iptables -A FORWARD -m conntrack --ctstate NEW
+test_path "with"
local message=$2
local port=$3
- ip netns exec ${netns} conntrack -L -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp'
+ if echo $message |grep -q 'ipv6';then
+ local family="ipv6"
+ else
+ local family="ipv4"
+ fi
+
+ ip netns exec ${netns} conntrack -L -f $family -p tcp --dport $port 2> /dev/null |grep -q 'helper=ftp'
if [ $? -ne 0 ] ; then
echo "FAIL: ${netns} did not show attached helper $message" 1>&2
ret=1
sleep 3 | ip netns exec ${ns2} nc -w 2 -l -p $port > /dev/null &
- sleep 1
sleep 1 | ip netns exec ${ns1} nc -w 2 10.0.1.2 $port > /dev/null &
+ sleep 1
check_for_helper "$ns1" "ip $msg" $port
check_for_helper "$ns2" "ip $msg" $port
sleep 3 | ip netns exec ${ns2} nc -w 2 -6 -l -p $port > /dev/null &
- sleep 1
sleep 1 | ip netns exec ${ns1} nc -w 2 -6 dead:1::2 $port > /dev/null &
+ sleep 1
check_for_helper "$ns1" "ipv6 $msg" $port
check_for_helper "$ns2" "ipv6 $msg" $port
# SPDX-License-Identifier: GPL-2.0-only
vdso_test
+vdso_test_abi
+vdso_test_clock_getres
+vdso_test_correctness
vdso_test_gettimeofday
vdso_test_getcpu
vdso_standalone_test_x86
return;
}
- printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+ printf("\t%llu.%09lld %llu.%09lld %llu.%09lld\n",
(unsigned long long)start.tv_sec, start.tv_nsec,
(unsigned long long)vdso.tv_sec, vdso.tv_nsec,
(unsigned long long)end.tv_sec, end.tv_nsec);
include local_config.mk
uname_M := $(shell uname -m 2>/dev/null || echo not)
-MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
+MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/')
# Without this, failed build products remain, with up-to-date timestamps,
# thus tricking Make (and you!) into believing that All Is Well, in subsequent
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += userfaultfd
-ifeq ($(ARCH),x86_64)
+ifeq ($(MACHINE),x86_64)
CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c)
CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie)
endif
else
-ifneq (,$(findstring $(ARCH),powerpc))
+ifneq (,$(findstring $(MACHINE),ppc64))
TEST_GEN_FILES += protection_keys
endif
endif
-ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
+ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64))
TEST_GEN_FILES += va_128TBswitch
TEST_GEN_FILES += virtual_address_range
TEST_GEN_FILES += write_to_hugetlbfs
KSFT_KHDR_INSTALL := 1
include ../lib.mk
-ifeq ($(ARCH),x86_64)
+ifeq ($(MACHINE),x86_64)
BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
CONFIG_LOCALVERSION="-debug"
-CONFIG_ENABLE_MUST_CHECK=y
CONFIG_FRAME_POINTER=y
CONFIG_STACK_VALIDATION=y
CONFIG_DEBUG_KERNEL=y
kvm->mmu_notifier_count++;
need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
range->flags);
- need_tlb_flush |= kvm->tlbs_dirty;
/* we've to flush the tlb before the pages can be freed */
- if (need_tlb_flush)
+ if (need_tlb_flush || kvm->tlbs_dirty)
kvm_flush_remote_tlbs(kvm);
spin_unlock(&kvm->mmu_lock);
git.samba.org / sfrench / cifs-2.6.git / commitdiff