earlycon= [KNL] Output early console device and options.
- When used with no options, the early console is
- determined by the stdout-path property in device
- tree's chosen node.
+ [ARM64] The early console is determined by the
+ stdout-path property in device tree's chosen node,
+ or determined by the ACPI SPCR table.
+
+ [X86] When used with no options the early console is
+ determined by the ACPI SPCR table.
cdns,<addr>[,options]
Start an early, polled-mode console on a Cadence
--- /dev/null
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
+=============
+ID Allocation
+=============
+
+:Author: Matthew Wilcox
+
+Overview
+========
+
+A common problem to solve is allocating identifiers (IDs); generally
+small numbers which identify a thing. Examples include file descriptors,
+process IDs, packet identifiers in networking protocols, SCSI tags
+and device instance numbers. The IDR and the IDA provide a reasonable
+solution to the problem to avoid everybody inventing their own. The IDR
+provides the ability to map an ID to a pointer, while the IDA provides
+only ID allocation, and as a result is much more memory-efficient.
+
+IDR usage
+=========
+
+Start by initialising an IDR, either with :c:func:`DEFINE_IDR`
+for statically allocated IDRs or :c:func:`idr_init` for dynamically
+allocated IDRs.
+
+You can call :c:func:`idr_alloc` to allocate an unused ID. Look up
+the pointer you associated with the ID by calling :c:func:`idr_find`
+and free the ID by calling :c:func:`idr_remove`.
+
+If you need to change the pointer associated with an ID, you can call
+:c:func:`idr_replace`. One common reason to do this is to reserve an
+ID by passing a ``NULL`` pointer to the allocation function; initialise the
+object with the reserved ID and finally insert the initialised object
+into the IDR.
+
+Some users need to allocate IDs larger than ``INT_MAX``. So far all of
+these users have been content with a ``UINT_MAX`` limit, and they use
+:c:func:`idr_alloc_u32`. If you need IDs that will not fit in a u32,
+we will work with you to address your needs.
+
+If you need to allocate IDs sequentially, you can use
+:c:func:`idr_alloc_cyclic`. The IDR becomes less efficient when dealing
+with larger IDs, so using this function comes at a slight cost.
+
+To perform an action on all pointers used by the IDR, you can
+either use the callback-based :c:func:`idr_for_each` or the
+iterator-style :c:func:`idr_for_each_entry`. You may need to use
+:c:func:`idr_for_each_entry_continue` to continue an iteration. You can
+also use :c:func:`idr_get_next` if the iterator doesn't fit your needs.
+
+When you have finished using an IDR, you can call :c:func:`idr_destroy`
+to release the memory used by the IDR. This will not free the objects
+pointed to from the IDR; if you want to do that, use one of the iterators
+to do it.
+
+You can use :c:func:`idr_is_empty` to find out whether there are any
+IDs currently allocated.
+
+If you need to take a lock while allocating a new ID from the IDR,
+you may need to pass a restrictive set of GFP flags, which can lead
+to the IDR being unable to allocate memory. To work around this,
+you can call :c:func:`idr_preload` before taking the lock, and then
+:c:func:`idr_preload_end` after the allocation.
+
+.. kernel-doc:: include/linux/idr.h
+ :doc: idr sync
+
+IDA usage
+=========
+
+.. kernel-doc:: lib/idr.c
+ :doc: IDA description
+
+Functions and structures
+========================
+
+.. kernel-doc:: include/linux/idr.h
+.. kernel-doc:: lib/idr.c
atomic_ops
refcount-vs-atomic
cpu_hotplug
+ idr
local_ops
workqueue
genericirq
.. kernel-doc:: lib/crc-itu-t.c
:export:
-idr/ida Functions
------------------
-
-.. kernel-doc:: include/linux/idr.h
- :doc: idr sync
-
-.. kernel-doc:: lib/idr.c
- :doc: IDA description
-
-.. kernel-doc:: lib/idr.c
- :export:
-
Math Functions in Linux
=======================
/* Do something with pos */
pos->frequency = ...
}
+
+If you need to work with the position of pos within driver_freq_table,
+do not subtract the pointers, as it is quite costly. Instead, use the
+macros cpufreq_for_each_entry_idx() and cpufreq_for_each_valid_entry_idx().
- "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU.
- "renesas,ipmmu-r8a7794" for the R8A7794 (R-Car E2) IPMMU.
- "renesas,ipmmu-r8a7795" for the R8A7795 (R-Car H3) IPMMU.
+ - "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU.
+ - "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU.
+ - "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU.
- "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU.
- reg: Base address and size of the IPMMU registers.
--- /dev/null
+Binding for MIPS Cluster Power Controller (CPC).
+
+This binding allows a system to specify where the CPC registers are
+located.
+
+Required properties:
+compatible : Should be "mti,mips-cpc".
+regs: Should describe the address & size of the CPC register region.
channel I/O mechanism described here, there are various other methods
(like the diag interface). These are out of the scope of this document.
+The s390 common I/O layer also provides access to some devices that are
+not strictly considered I/O devices. They are considered here as well,
+although they are not the focus of this document.
+
Some additional information can also be found in the kernel source under
Documentation/s390/driver-model.txt.
+The css bus
+===========
+
+The css bus contains the subchannels available on the system. They fall
+into several categories:
+
+* Standard I/O subchannels, for use by the system. They have a child
+ device on the ccw bus and are described below.
+* I/O subchannels bound to the vfio-ccw driver. See
+ Documentation/s390/vfio-ccw.txt.
+* Message subchannels. No Linux driver currently exists.
+* CHSC subchannels (at most one). The chsc subchannel driver can be used
+ to send asynchronous chsc commands.
+* eADM subchannels. Used for talking to storage class memory.
+
The ccw bus
===========
Generic interfaces
==================
-Some interfaces are available to other drivers that do not necessarily
-have anything to do with the busses described above, but still are
-indirectly using basic infrastructure in the common I/O layer. One
-example is the support for adapter interrupts.
+The following section contains interfaces in use not only by drivers
+dealing with ccw devices, but drivers for various other s390 hardware
+as well.
+
+Adapter interrupts
+------------------
+
+The common I/O layer provides helper functions for dealing with adapter
+interrupts and interrupt vectors.
.. kernel-doc:: drivers/s390/cio/airq.c
:export:
- Overview.
- Usage.
- Mountpoints.
+ - Dynamic root.
- Proc filesystem.
- The cell database.
- Security.
umount /afs
+============
+DYNAMIC ROOT
+============
+
+A mount option is available to create a serverless mount that is only usable
+for dynamic lookup. Creating such a mount can be done by, for example:
+
+ mount -t afs none /afs -o dyn
+
+This creates a mount that just has an empty directory at the root. Attempting
+to look up a name in this directory will cause a mountpoint to be created that
+looks up a cell of the same name, for example:
+
+ ls /afs/grand.central.org/
+
+
===============
PROC FILESYSTEM
===============
- Diagnose hypercall description (for IBM S/390)
timekeeping.txt
- timekeeping virtualization for x86-based architectures.
+amd-memory-encryption.txt
+ - notes on AMD Secure Encrypted Virtualization feature and SEV firmware
+ command description
--- /dev/null
+======================================
+Secure Encrypted Virtualization (SEV)
+======================================
+
+Overview
+========
+
+Secure Encrypted Virtualization (SEV) is a feature found on AMD processors.
+
+SEV is an extension to the AMD-V architecture which supports running
+virtual machines (VMs) under the control of a hypervisor. When enabled,
+the memory contents of a VM will be transparently encrypted with a key
+unique to that VM.
+
+The hypervisor can determine the SEV support through the CPUID
+instruction. The CPUID function 0x8000001f reports information related
+to SEV::
+
+ 0x8000001f[eax]:
+ Bit[1] indicates support for SEV
+ ...
+ [ecx]:
+ Bits[31:0] Number of encrypted guests supported simultaneously
+
+If support for SEV is present, MSR 0xc001_0010 (MSR_K8_SYSCFG) and MSR 0xc001_0015
+(MSR_K7_HWCR) can be used to determine if it can be enabled::
+
+ 0xc001_0010:
+ Bit[23] 1 = memory encryption can be enabled
+ 0 = memory encryption can not be enabled
+
+ 0xc001_0015:
+ Bit[0] 1 = memory encryption can be enabled
+ 0 = memory encryption can not be enabled
+
+When SEV support is available, it can be enabled in a specific VM by
+setting the SEV bit before executing VMRUN.::
+
+ VMCB[0x90]:
+ Bit[1] 1 = SEV is enabled
+ 0 = SEV is disabled
+
+SEV hardware uses ASIDs to associate a memory encryption key with a VM.
+Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value
+defined in the CPUID 0x8000001f[ecx] field.
+
+SEV Key Management
+==================
+
+The SEV guest key management is handled by a separate processor called the AMD
+Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure
+key management interface to perform common hypervisor activities such as
+encrypting bootstrap code, snapshot, migrating and debugging the guest. For more
+information, see the SEV Key Management spec [api-spec]_
+
+KVM implements the following commands to support common lifecycle events of SEV
+guests, such as launching, running, snapshotting, migrating and decommissioning.
+
+1. KVM_SEV_INIT
+---------------
+
+The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform
+context. In a typical workflow, this command should be the first command issued.
+
+Returns: 0 on success, -negative on error
+
+2. KVM_SEV_LAUNCH_START
+-----------------------
+
+The KVM_SEV_LAUNCH_START command is used for creating the memory encryption
+context. To create the encryption context, user must provide a guest policy,
+the owner's public Diffie-Hellman (PDH) key and session information.
+
+Parameters: struct kvm_sev_launch_start (in/out)
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_start {
+ __u32 handle; /* if zero then firmware creates a new handle */
+ __u32 policy; /* guest's policy */
+
+ __u64 dh_uaddr; /* userspace address pointing to the guest owner's PDH key */
+ __u32 dh_len;
+
+ __u64 session_addr; /* userspace address which points to the guest session information */
+ __u32 session_len;
+ };
+
+On success, the 'handle' field contains a new handle and on error, a negative value.
+
+For more details, see SEV spec Section 6.2.
+
+3. KVM_SEV_LAUNCH_UPDATE_DATA
+-----------------------------
+
+The KVM_SEV_LAUNCH_UPDATE_DATA is used for encrypting a memory region. It also
+calculates a measurement of the memory contents. The measurement is a signature
+of the memory contents that can be sent to the guest owner as an attestation
+that the memory was encrypted correctly by the firmware.
+
+Parameters (in): struct kvm_sev_launch_update_data
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_update {
+ __u64 uaddr; /* userspace address to be encrypted (must be 16-byte aligned) */
+ __u32 len; /* length of the data to be encrypted (must be 16-byte aligned) */
+ };
+
+For more details, see SEV spec Section 6.3.
+
+4. KVM_SEV_LAUNCH_MEASURE
+-------------------------
+
+The KVM_SEV_LAUNCH_MEASURE command is used to retrieve the measurement of the
+data encrypted by the KVM_SEV_LAUNCH_UPDATE_DATA command. The guest owner may
+wait to provide the guest with confidential information until it can verify the
+measurement. Since the guest owner knows the initial contents of the guest at
+boot, the measurement can be verified by comparing it to what the guest owner
+expects.
+
+Parameters (in): struct kvm_sev_launch_measure
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_measure {
+ __u64 uaddr; /* where to copy the measurement */
+ __u32 len; /* length of measurement blob */
+ };
+
+For more details on the measurement verification flow, see SEV spec Section 6.4.
+
+5. KVM_SEV_LAUNCH_FINISH
+------------------------
+
+After completion of the launch flow, the KVM_SEV_LAUNCH_FINISH command can be
+issued to make the guest ready for the execution.
+
+Returns: 0 on success, -negative on error
+
+6. KVM_SEV_GUEST_STATUS
+-----------------------
+
+The KVM_SEV_GUEST_STATUS command is used to retrieve status information about a
+SEV-enabled guest.
+
+Parameters (out): struct kvm_sev_guest_status
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_guest_status {
+ __u32 handle; /* guest handle */
+ __u32 policy; /* guest policy */
+ __u8 state; /* guest state (see enum below) */
+ };
+
+SEV guest state:
+
+::
+
+ enum {
+ SEV_STATE_INVALID = 0;
+ SEV_STATE_LAUNCHING, /* guest is currently being launched */
+ SEV_STATE_SECRET, /* guest is being launched and ready to accept the ciphertext data */
+ SEV_STATE_RUNNING, /* guest is fully launched and running */
+ SEV_STATE_RECEIVING, /* guest is being migrated in from another SEV machine */
+ SEV_STATE_SENDING /* guest is getting migrated out to another SEV machine */
+ };
+
+7. KVM_SEV_DBG_DECRYPT
+----------------------
+
+The KVM_SEV_DEBUG_DECRYPT command can be used by the hypervisor to request the
+firmware to decrypt the data at the given memory region.
+
+Parameters (in): struct kvm_sev_dbg
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_dbg {
+ __u64 src_uaddr; /* userspace address of data to decrypt */
+ __u64 dst_uaddr; /* userspace address of destination */
+ __u32 len; /* length of memory region to decrypt */
+ };
+
+The command returns an error if the guest policy does not allow debugging.
+
+8. KVM_SEV_DBG_ENCRYPT
+----------------------
+
+The KVM_SEV_DEBUG_ENCRYPT command can be used by the hypervisor to request the
+firmware to encrypt the data at the given memory region.
+
+Parameters (in): struct kvm_sev_dbg
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_dbg {
+ __u64 src_uaddr; /* userspace address of data to encrypt */
+ __u64 dst_uaddr; /* userspace address of destination */
+ __u32 len; /* length of memory region to encrypt */
+ };
+
+The command returns an error if the guest policy does not allow debugging.
+
+9. KVM_SEV_LAUNCH_SECRET
+------------------------
+
+The KVM_SEV_LAUNCH_SECRET command can be used by the hypervisor to inject secret
+data after the measurement has been validated by the guest owner.
+
+Parameters (in): struct kvm_sev_launch_secret
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr; /* userspace address containing the packet header */
+ __u32 hdr_len;
+
+ __u64 guest_uaddr; /* the guest memory region where the secret should be injected */
+ __u32 guest_len;
+
+ __u64 trans_uaddr; /* the hypervisor memory region which contains the secret */
+ __u32 trans_len;
+ };
+
+References
+==========
+
+.. [white-paper] http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf
+.. [api-spec] http://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf
+.. [amd-apm] http://support.amd.com/TechDocs/24593.pdf (section 15.34)
+.. [kvm-forum] http://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf
PPC | KVM_REG_PPC_DBSR | 32
PPC | KVM_REG_PPC_TIDR | 64
PPC | KVM_REG_PPC_PSSCR | 64
+ PPC | KVM_REG_PPC_DEC_EXPIRY | 64
PPC | KVM_REG_PPC_TM_GPR0 | 64
...
PPC | KVM_REG_PPC_TM_GPR31 | 64
or if no page table is present for the addresses (e.g. when using
hugepages).
-4.108 KVM_PPC_GET_CPU_CHAR
+4.109 KVM_PPC_GET_CPU_CHAR
Capability: KVM_CAP_PPC_GET_CPU_CHAR
Architectures: powerpc
These fields use the same bit definitions as the new
H_GET_CPU_CHARACTERISTICS hypercall.
+4.110 KVM_MEMORY_ENCRYPT_OP
+
+Capability: basic
+Architectures: x86
+Type: system
+Parameters: an opaque platform specific structure (in/out)
+Returns: 0 on success; -1 on error
+
+If the platform supports creating encrypted VMs then this ioctl can be used
+for issuing platform-specific memory encryption commands to manage those
+encrypted VMs.
+
+Currently, this ioctl is used for issuing Secure Encrypted Virtualization
+(SEV) commands on AMD Processors. The SEV commands are defined in
+Documentation/virtual/kvm/amd-memory-encryption.txt.
+
+4.111 KVM_MEMORY_ENCRYPT_REG_REGION
+
+Capability: basic
+Architectures: x86
+Type: system
+Parameters: struct kvm_enc_region (in)
+Returns: 0 on success; -1 on error
+
+This ioctl can be used to register a guest memory region which may
+contain encrypted data (e.g. guest RAM, SMRAM etc).
+
+It is used in the SEV-enabled guest. When encryption is enabled, a guest
+memory region may contain encrypted data. The SEV memory encryption
+engine uses a tweak such that two identical plaintext pages, each at
+different locations will have differing ciphertexts. So swapping or
+moving ciphertext of those pages will not result in plaintext being
+swapped. So relocating (or migrating) physical backing pages for the SEV
+guest will require some additional steps.
+
+Note: The current SEV key management spec does not provide commands to
+swap or migrate (move) ciphertext pages. Hence, for now we pin the guest
+memory region registered with the ioctl.
+
+4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION
+
+Capability: basic
+Architectures: x86
+Type: system
+Parameters: struct kvm_enc_region (in)
+Returns: 0 on success; -1 on error
+
+This ioctl can be used to unregister the guest memory region registered
+with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
+
+
5. The kvm_run structure
------------------------
+++ /dev/null
-KVM/ARM VGIC Forwarded Physical Interrupts
-==========================================
-
-The KVM/ARM code implements software support for the ARM Generic
-Interrupt Controller's (GIC's) hardware support for virtualization by
-allowing software to inject virtual interrupts to a VM, which the guest
-OS sees as regular interrupts. The code is famously known as the VGIC.
-
-Some of these virtual interrupts, however, correspond to physical
-interrupts from real physical devices. One example could be the
-architected timer, which itself supports virtualization, and therefore
-lets a guest OS program the hardware device directly to raise an
-interrupt at some point in time. When such an interrupt is raised, the
-host OS initially handles the interrupt and must somehow signal this
-event as a virtual interrupt to the guest. Another example could be a
-passthrough device, where the physical interrupts are initially handled
-by the host, but the device driver for the device lives in the guest OS
-and KVM must therefore somehow inject a virtual interrupt on behalf of
-the physical one to the guest OS.
-
-These virtual interrupts corresponding to a physical interrupt on the
-host are called forwarded physical interrupts, but are also sometimes
-referred to as 'virtualized physical interrupts' and 'mapped interrupts'.
-
-Forwarded physical interrupts are handled slightly differently compared
-to virtual interrupts generated purely by a software emulated device.
-
-
-The HW bit
-----------
-Virtual interrupts are signalled to the guest by programming the List
-Registers (LRs) on the GIC before running a VCPU. The LR is programmed
-with the virtual IRQ number and the state of the interrupt (Pending,
-Active, or Pending+Active). When the guest ACKs and EOIs a virtual
-interrupt, the LR state moves from Pending to Active, and finally to
-inactive.
-
-The LRs include an extra bit, called the HW bit. When this bit is set,
-KVM must also program an additional field in the LR, the physical IRQ
-number, to link the virtual with the physical IRQ.
-
-When the HW bit is set, KVM must EITHER set the Pending OR the Active
-bit, never both at the same time.
-
-Setting the HW bit causes the hardware to deactivate the physical
-interrupt on the physical distributor when the guest deactivates the
-corresponding virtual interrupt.
-
-
-Forwarded Physical Interrupts Life Cycle
-----------------------------------------
-
-The state of forwarded physical interrupts is managed in the following way:
-
- - The physical interrupt is acked by the host, and becomes active on
- the physical distributor (*).
- - KVM sets the LR.Pending bit, because this is the only way the GICV
- interface is going to present it to the guest.
- - LR.Pending will stay set as long as the guest has not acked the interrupt.
- - LR.Pending transitions to LR.Active on the guest read of the IAR, as
- expected.
- - On guest EOI, the *physical distributor* active bit gets cleared,
- but the LR.Active is left untouched (set).
- - KVM clears the LR on VM exits when the physical distributor
- active state has been cleared.
-
-(*): The host handling is slightly more complicated. For some forwarded
-interrupts (shared), KVM directly sets the active state on the physical
-distributor before entering the guest, because the interrupt is never actually
-handled on the host (see details on the timer as an example below). For other
-forwarded interrupts (non-shared) the host does not deactivate the interrupt
-when the host ISR completes, but leaves the interrupt active until the guest
-deactivates it. Leaving the interrupt active is allowed, because Linux
-configures the physical GIC with EOIMode=1, which causes EOI operations to
-perform a priority drop allowing the GIC to receive other interrupts of the
-default priority.
-
-
-Forwarded Edge and Level Triggered PPIs and SPIs
-------------------------------------------------
-Forwarded physical interrupts injected should always be active on the
-physical distributor when injected to a guest.
-
-Level-triggered interrupts will keep the interrupt line to the GIC
-asserted, typically until the guest programs the device to deassert the
-line. This means that the interrupt will remain pending on the physical
-distributor until the guest has reprogrammed the device. Since we
-always run the VM with interrupts enabled on the CPU, a pending
-interrupt will exit the guest as soon as we switch into the guest,
-preventing the guest from ever making progress as the process repeats
-over and over. Therefore, the active state on the physical distributor
-must be set when entering the guest, preventing the GIC from forwarding
-the pending interrupt to the CPU. As soon as the guest deactivates the
-interrupt, the physical line is sampled by the hardware again and the host
-takes a new interrupt if and only if the physical line is still asserted.
-
-Edge-triggered interrupts do not exhibit the same problem with
-preventing guest execution that level-triggered interrupts do. One
-option is to not use HW bit at all, and inject edge-triggered interrupts
-from a physical device as pure virtual interrupts. But that would
-potentially slow down handling of the interrupt in the guest, because a
-physical interrupt occurring in the middle of the guest ISR would
-preempt the guest for the host to handle the interrupt. Additionally,
-if you configure the system to handle interrupts on a separate physical
-core from that running your VCPU, you still have to interrupt the VCPU
-to queue the pending state onto the LR, even though the guest won't use
-this information until the guest ISR completes. Therefore, the HW
-bit should always be set for forwarded edge-triggered interrupts. With
-the HW bit set, the virtual interrupt is injected and additional
-physical interrupts occurring before the guest deactivates the interrupt
-simply mark the state on the physical distributor as Pending+Active. As
-soon as the guest deactivates the interrupt, the host takes another
-interrupt if and only if there was a physical interrupt between injecting
-the forwarded interrupt to the guest and the guest deactivating the
-interrupt.
-
-Consequently, whenever we schedule a VCPU with one or more LRs with the
-HW bit set, the interrupt must also be active on the physical
-distributor.
-
-
-Forwarded LPIs
---------------
-LPIs, introduced in GICv3, are always edge-triggered and do not have an
-active state. They become pending when a device signal them, and as
-soon as they are acked by the CPU, they are inactive again.
-
-It therefore doesn't make sense, and is not supported, to set the HW bit
-for physical LPIs that are forwarded to a VM as virtual interrupts,
-typically virtual SPIs.
-
-For LPIs, there is no other choice than to preempt the VCPU thread if
-necessary, and queue the pending state onto the LR.
-
-
-Putting It Together: The Architected Timer
-------------------------------------------
-The architected timer is a device that signals interrupts with level
-triggered semantics. The timer hardware is directly accessed by VCPUs
-which program the timer to fire at some point in time. Each VCPU on a
-system programs the timer to fire at different times, and therefore the
-hardware is multiplexed between multiple VCPUs. This is implemented by
-context-switching the timer state along with each VCPU thread.
-
-However, this means that a scenario like the following is entirely
-possible, and in fact, typical:
-
-1. KVM runs the VCPU
-2. The guest programs the time to fire in T+100
-3. The guest is idle and calls WFI (wait-for-interrupts)
-4. The hardware traps to the host
-5. KVM stores the timer state to memory and disables the hardware timer
-6. KVM schedules a soft timer to fire in T+(100 - time since step 2)
-7. KVM puts the VCPU thread to sleep (on a waitqueue)
-8. The soft timer fires, waking up the VCPU thread
-9. KVM reprograms the timer hardware with the VCPU's values
-10. KVM marks the timer interrupt as active on the physical distributor
-11. KVM injects a forwarded physical interrupt to the guest
-12. KVM runs the VCPU
-
-Notice that KVM injects a forwarded physical interrupt in step 11 without
-the corresponding interrupt having actually fired on the host. That is
-exactly why we mark the timer interrupt as active in step 10, because
-the active state on the physical distributor is part of the state
-belonging to the timer hardware, which is context-switched along with
-the VCPU thread.
-
-If the guest does not idle because it is busy, the flow looks like this
-instead:
-
-1. KVM runs the VCPU
-2. The guest programs the time to fire in T+100
-4. At T+100 the timer fires and a physical IRQ causes the VM to exit
- (note that this initially only traps to EL2 and does not run the host ISR
- until KVM has returned to the host).
-5. With interrupts still disabled on the CPU coming back from the guest, KVM
- stores the virtual timer state to memory and disables the virtual hw timer.
-6. KVM looks at the timer state (in memory) and injects a forwarded physical
- interrupt because it concludes the timer has expired.
-7. KVM marks the timer interrupt as active on the physical distributor
-7. KVM enables the timer, enables interrupts, and runs the VCPU
-
-Notice that again the forwarded physical interrupt is injected to the
-guest without having actually been handled on the host. In this case it
-is because the physical interrupt is never actually seen by the host because the
-timer is disabled upon guest return, and the virtual forwarded interrupt is
-injected on the KVM guest entry path.
|| || before enabling paravirtualized
|| || spinlock support.
------------------------------------------------------------------------------
+KVM_FEATURE_PV_TLB_FLUSH || 9 || guest checks this feature bit
+ || || before enabling paravirtualized
+ || || tlb flush.
+------------------------------------------------------------------------------
KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side
|| || per-cpu warps are expected in
|| || kvmclock.
KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
M: Christian Borntraeger <borntraeger@de.ibm.com>
-M: Cornelia Huck <cohuck@redhat.com>
+M: Janosch Frank <frankja@linux.vnet.ibm.com>
+R: David Hildenbrand <david@redhat.com>
+R: Cornelia Huck <cohuck@redhat.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
M: Paul Burton <paul.burton@mips.com>
L: linux-mips@linux-mips.org
S: Supported
+F: Documentation/devicetree/bindings/power/mti,mips-cpc.txt
F: arch/mips/generic/
F: arch/mips/tools/generic-board-config.sh
ORANGEFS FILESYSTEM
M: Mike Marshall <hubcap@omnibond.com>
-L: pvfs2-developers@beowulf-underground.org (subscribers-only)
+R: Martin Brandenburg <martin@omnibond.com>
+L: devel@lists.orangefs.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux.git
S: Supported
F: fs/orangefs/
F: drivers/pci/dwc/*spear*
PCMCIA SUBSYSTEM
-P: Linux PCMCIA Team
-L: linux-pcmcia@lists.infradead.org
-W: http://lists.infradead.org/mailman/listinfo/linux-pcmcia
+M: Dominik Brodowski <linux@dominikbrodowski.net>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/brodo/pcmcia.git
-S: Maintained
+S: Odd Fixes
F: Documentation/pcmcia/
F: tools/pcmcia/
F: drivers/pcmcia/
S390 VFIO-CCW DRIVER
M: Cornelia Huck <cohuck@redhat.com>
M: Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+M: Halil Pasic <pasic@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
L: kvm@vger.kernel.org
S: Supported
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
-PATCHLEVEL = 15
+PATCHLEVEL = 16
SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc1
NAME = Fearless Coyote
# *DOCUMENTATION*
ifeq ($(cc-name),clang)
KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
# These warnings generated too much noise in a regular build.
# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
endif
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
ifdef CONFIG_FRAME_POINTER
KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls
else
static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu)
{
unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK;
- return cpsr_mode > USR_MODE;;
+ return cpsr_mode > USR_MODE;
}
static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1)
+DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
static inline void kvm_arm_vhe_guest_enter(void) {}
static inline void kvm_arm_vhe_guest_exit(void) {}
+
+static inline bool kvm_arm_harden_branch_predictor(void)
+{
+ /* No way to detect it yet, pretend it is not there. */
+ return false;
+}
+
#endif /* __ARM_KVM_HOST_H__ */
#include <linux/compiler.h>
#include <linux/kvm_host.h>
#include <asm/cp15.h>
-#include <asm/kvm_mmu.h>
#include <asm/vfp.h>
#define __hyp_text __section(.hyp.text) notrace
#define HIFAR __ACCESS_CP15(c6, 4, c0, 2)
#define HPFAR __ACCESS_CP15(c6, 4, c0, 4)
#define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0)
+#define BPIALLIS __ACCESS_CP15(c7, 0, c1, 6)
+#define ICIMVAU __ACCESS_CP15(c7, 0, c5, 1)
#define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0)
#define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0)
#define TLBIALL __ACCESS_CP15(c8, 0, c7, 0)
#include <linux/highmem.h>
#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/kvm_hyp.h>
#include <asm/pgalloc.h>
#include <asm/stage2_pgtable.h>
return pmd;
}
+static inline pte_t kvm_s2pte_mkexec(pte_t pte)
+{
+ pte_val(pte) &= ~L_PTE_XN;
+ return pte;
+}
+
+static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
+{
+ pmd_val(pmd) &= ~PMD_SECT_XN;
+ return pmd;
+}
+
static inline void kvm_set_s2pte_readonly(pte_t *pte)
{
pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY;
return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY;
}
+static inline bool kvm_s2pte_exec(pte_t *pte)
+{
+ return !(pte_val(*pte) & L_PTE_XN);
+}
+
static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
{
pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY;
return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY;
}
+static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+{
+ return !(pmd_val(*pmd) & PMD_SECT_XN);
+}
+
static inline bool kvm_page_empty(void *ptr)
{
struct page *ptr_page = virt_to_page(ptr);
return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101;
}
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
- kvm_pfn_t pfn,
- unsigned long size)
+static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
+{
+ /*
+ * Clean the dcache to the Point of Coherency.
+ *
+ * We need to do this through a kernel mapping (using the
+ * user-space mapping has proved to be the wrong
+ * solution). For that, we need to kmap one page at a time,
+ * and iterate over the range.
+ */
+
+ VM_BUG_ON(size & ~PAGE_MASK);
+
+ while (size) {
+ void *va = kmap_atomic_pfn(pfn);
+
+ kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+
+ size -= PAGE_SIZE;
+ pfn++;
+
+ kunmap_atomic(va);
+ }
+}
+
+static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
+ unsigned long size)
{
+ u32 iclsz;
+
/*
* If we are going to insert an instruction page and the icache is
* either VIPT or PIPT, there is a potential problem where the host
*
* VIVT caches are tagged using both the ASID and the VMID and doesn't
* need any kind of flushing (DDI 0406C.b - Page B3-1392).
- *
- * We need to do this through a kernel mapping (using the
- * user-space mapping has proved to be the wrong
- * solution). For that, we need to kmap one page at a time,
- * and iterate over the range.
*/
VM_BUG_ON(size & ~PAGE_MASK);
+ if (icache_is_vivt_asid_tagged())
+ return;
+
+ if (!icache_is_pipt()) {
+ /* any kind of VIPT cache */
+ __flush_icache_all();
+ return;
+ }
+
+ /*
+ * CTR IminLine contains Log2 of the number of words in the
+ * cache line, so we can get the number of words as
+ * 2 << (IminLine - 1). To get the number of bytes, we
+ * multiply by 4 (the number of bytes in a 32-bit word), and
+ * get 4 << (IminLine).
+ */
+ iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf);
+
while (size) {
void *va = kmap_atomic_pfn(pfn);
+ void *end = va + PAGE_SIZE;
+ void *addr = va;
- kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+ do {
+ write_sysreg(addr, ICIMVAU);
+ addr += iclsz;
+ } while (addr < end);
- if (icache_is_pipt())
- __cpuc_coherent_user_range((unsigned long)va,
- (unsigned long)va + PAGE_SIZE);
+ dsb(ishst);
+ isb();
size -= PAGE_SIZE;
pfn++;
kunmap_atomic(va);
}
- if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
- /* any kind of VIPT cache */
- __flush_icache_all();
+ /* Check if we need to invalidate the BTB */
+ if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 28) != 4) {
+ write_sysreg(0, BPIALLIS);
+ dsb(ishst);
+ isb();
}
}
+++ /dev/null
-/*
- * Copyright (C) 2012 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM_KVM_PSCI_H__
-#define __ARM_KVM_PSCI_H__
-
-#define KVM_ARM_PSCI_0_1 1
-#define KVM_ARM_PSCI_0_2 2
-
-int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM_KVM_PSCI_H__ */
#define PAGE_HYP_EXEC _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY)
#define PAGE_HYP_RO _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN)
#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
-#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
+#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY | L_PTE_XN)
+#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY | L_PTE_XN)
#define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
#define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
#include <asm/kvm_mmu.h>
-#include <asm/kvm_psci.h>
+#include <kvm/arm_psci.h>
#include <trace/events/kvm.h>
#include "trace.h"
kvm_vcpu_hvc_get_imm(vcpu));
vcpu->stat.hvc_exit_stat++;
- ret = kvm_psci_call(vcpu);
+ ret = kvm_hvc_call_handler(vcpu);
if (ret < 0) {
- kvm_inject_undefined(vcpu);
+ vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
}
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
- kvm_inject_undefined(vcpu);
+ /*
+ * "If an SMC instruction executed at Non-secure EL1 is
+ * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
+ * Trap exception, not a Secure Monitor Call exception [...]"
+ *
+ * We need to advance the PC after the trap, as it would
+ * otherwise return to the same address...
+ */
+ vcpu_set_reg(vcpu, 0, ~0UL);
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 1;
}
#include <asm/kvm_asm.h>
#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
__asm__(".arch_extension virt");
*/
#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
/**
* Flush per-VMID TLBs
depends on ARCH_MULTI_V5
select ARCH_VT8500
select CPU_ARM926T
- help
config ARCH_WM8750
bool "WonderMedia WM8750"
hint #16
.endm
+/*
+ * Value prediction barrier
+ */
+ .macro csdb
+ hint #20
+ .endm
+
+/*
+ * Sanitise a 64-bit bounded index wrt speculation, returning zero if out
+ * of bounds.
+ */
+ .macro mask_nospec64, idx, limit, tmp
+ sub \tmp, \idx, \limit
+ bic \tmp, \tmp, \idx
+ and \idx, \idx, \tmp, asr #63
+ csdb
+ .endm
+
/*
* NOP sequence
*/
dsb \domain
.endm
+/*
+ * Macro to perform an instruction cache maintenance for the interval
+ * [start, end)
+ *
+ * start, end: virtual addresses describing the region
+ * label: A label to branch to on user fault.
+ * Corrupts: tmp1, tmp2
+ */
+ .macro invalidate_icache_by_line start, end, tmp1, tmp2, label
+ icache_line_size \tmp1, \tmp2
+ sub \tmp2, \tmp1, #1
+ bic \tmp2, \start, \tmp2
+9997:
+USER(\label, ic ivau, \tmp2) // invalidate I line PoU
+ add \tmp2, \tmp2, \tmp1
+ cmp \tmp2, \end
+ b.lo 9997b
+ dsb ish
+ isb
+ .endm
+
/*
* reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
*/
* phys: physical address, preserved
* ttbr: returns the TTBR value
*/
- .macro phys_to_ttbr, phys, ttbr
+ .macro phys_to_ttbr, ttbr, phys
#ifdef CONFIG_ARM64_PA_BITS_52
orr \ttbr, \phys, \phys, lsr #46
and \ttbr, \ttbr, #TTBR_BADDR_MASK_52
#endif
.endm
+ .macro phys_to_pte, pte, phys
+#ifdef CONFIG_ARM64_PA_BITS_52
+ /*
+ * We assume \phys is 64K aligned and this is guaranteed by only
+ * supporting this configuration with 64K pages.
+ */
+ orr \pte, \phys, \phys, lsr #36
+ and \pte, \pte, #PTE_ADDR_MASK
+#else
+ mov \pte, \phys
+#endif
+ .endm
+
+ .macro pte_to_phys, phys, pte
+#ifdef CONFIG_ARM64_PA_BITS_52
+ ubfiz \phys, \pte, #(48 - 16 - 12), #16
+ bfxil \phys, \pte, #16, #32
+ lsl \phys, \phys, #16
+#else
+ and \phys, \pte, #PTE_ADDR_MASK
+#endif
+ .endm
+
/**
* Errata workaround prior to disable MMU. Insert an ISB immediately prior
* to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0.
#define dsb(opt) asm volatile("dsb " #opt : : : "memory")
#define psb_csync() asm volatile("hint #17" : : : "memory")
+#define csdb() asm volatile("hint #20" : : : "memory")
#define mb() dsb(sy)
#define rmb() dsb(ld)
#define dma_rmb() dmb(oshld)
#define dma_wmb() dmb(oshst)
+/*
+ * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
+ * and 0 otherwise.
+ */
+#define array_index_mask_nospec array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long idx,
+ unsigned long sz)
+{
+ unsigned long mask;
+
+ asm volatile(
+ " cmp %1, %2\n"
+ " sbc %0, xzr, xzr\n"
+ : "=r" (mask)
+ : "r" (idx), "Ir" (sz)
+ : "cc");
+
+ csdb();
+ return mask;
+}
+
#define __smp_mb() dmb(ish)
#define __smp_rmb() dmb(ishld)
#define __smp_wmb() dmb(ishst)
* - start - virtual start address
* - end - virtual end address
*
+ * invalidate_icache_range(start, end)
+ *
+ * Invalidate the I-cache in the region described by start, end.
+ * - start - virtual start address
+ * - end - virtual end address
+ *
* __flush_cache_user_range(start, end)
*
* Ensure coherency between the I-cache and the D-cache in the
* - size - region size
*/
extern void flush_icache_range(unsigned long start, unsigned long end);
+extern int invalidate_icache_range(unsigned long start, unsigned long end);
extern void __flush_dcache_area(void *addr, size_t len);
extern void __inval_dcache_area(void *addr, size_t len);
extern void __clean_dcache_area_poc(void *addr, size_t len);
} while (0)
static inline int
-arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
{
int oldval = 0, ret, tmp;
+ u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
pagefault_disable();
}
static inline int
-futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
u32 oldval, u32 newval)
{
int ret = 0;
u32 val, tmp;
+ u32 __user *uaddr;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+ if (!access_ok(VERIFY_WRITE, _uaddr, sizeof(u32)))
return -EFAULT;
+ uaddr = __uaccess_mask_ptr(_uaddr);
uaccess_enable();
asm volatile("// futex_atomic_cmpxchg_inatomic\n"
" prfm pstl1strm, %2\n"
/*
* Initial memory map attributes.
*/
-#define _SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define _SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
-
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-#define SWAPPER_PTE_FLAGS (_SWAPPER_PTE_FLAGS | PTE_NG)
-#define SWAPPER_PMD_FLAGS (_SWAPPER_PMD_FLAGS | PMD_SECT_NG)
-#else
-#define SWAPPER_PTE_FLAGS _SWAPPER_PTE_FLAGS
-#define SWAPPER_PMD_FLAGS _SWAPPER_PMD_FLAGS
-#endif
+#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
#if ARM64_SWAPPER_USES_SECTION_MAPS
#define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1)
+DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext);
{
local_daif_restore(DAIF_PROCCTX_NOIRQ);
}
+
+static inline bool kvm_arm_harden_branch_predictor(void)
+{
+ return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR);
+}
+
#endif /* __ARM64_KVM_HOST_H__ */
#include <linux/compiler.h>
#include <linux/kvm_host.h>
-#include <asm/kvm_mmu.h>
#include <asm/sysreg.h>
#define __hyp_text __section(.hyp.text) notrace
return pmd;
}
+static inline pte_t kvm_s2pte_mkexec(pte_t pte)
+{
+ pte_val(pte) &= ~PTE_S2_XN;
+ return pte;
+}
+
+static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
+{
+ pmd_val(pmd) &= ~PMD_S2_XN;
+ return pmd;
+}
+
static inline void kvm_set_s2pte_readonly(pte_t *pte)
{
pteval_t old_pteval, pteval;
return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
}
+static inline bool kvm_s2pte_exec(pte_t *pte)
+{
+ return !(pte_val(*pte) & PTE_S2_XN);
+}
+
static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
{
kvm_set_s2pte_readonly((pte_t *)pmd);
return kvm_s2pte_readonly((pte_t *)pmd);
}
+static inline bool kvm_s2pmd_exec(pmd_t *pmd)
+{
+ return !(pmd_val(*pmd) & PMD_S2_XN);
+}
+
static inline bool kvm_page_empty(void *ptr)
{
struct page *ptr_page = virt_to_page(ptr);
return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
}
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
- kvm_pfn_t pfn,
- unsigned long size)
+static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
void *va = page_address(pfn_to_page(pfn));
kvm_flush_dcache_to_poc(va, size);
+}
+static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
+ unsigned long size)
+{
if (icache_is_aliasing()) {
/* any kind of VIPT cache */
__flush_icache_all();
} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
- flush_icache_range((unsigned long)va,
- (unsigned long)va + size);
+ void *va = page_address(pfn_to_page(pfn));
+
+ invalidate_icache_range((unsigned long)va,
+ (unsigned long)va + size);
}
}
+++ /dev/null
-/*
- * Copyright (C) 2012,2013 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_KVM_PSCI_H__
-#define __ARM64_KVM_PSCI_H__
-
-#define KVM_ARM_PSCI_0_1 1
-#define KVM_ARM_PSCI_0_2 2
-
-int kvm_psci_version(struct kvm_vcpu *vcpu);
-int kvm_psci_call(struct kvm_vcpu *vcpu);
-
-#endif /* __ARM64_KVM_PSCI_H__ */
*/
#define PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[2:1] */
#define PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
+#define PTE_S2_XN (_AT(pteval_t, 2) << 53) /* XN[1:0] */
#define PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[2:1] */
#define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
+#define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */
/*
* Memory Attribute override for Stage-2 (MemAttr[3:0])
#define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
#define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-#define PROT_DEFAULT (_PROT_DEFAULT | PTE_NG)
-#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_SECT_NG)
-#else
-#define PROT_DEFAULT _PROT_DEFAULT
-#define PROT_SECT_DEFAULT _PROT_SECT_DEFAULT
-#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
+#define PTE_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PTE_NG : 0)
+#define PMD_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0)
+
+#define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG)
+#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
#define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
-#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-#define _HYP_PAGE_DEFAULT (_PAGE_DEFAULT & ~PTE_NG)
+#define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT _PAGE_DEFAULT
-#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
+#define PAGE_KERNEL __pgprot(PROT_NORMAL)
+#define PAGE_KERNEL_RO __pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
+#define PAGE_KERNEL_ROX __pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
+#define PAGE_KERNEL_EXEC __pgprot(PROT_NORMAL & ~PTE_PXN)
+#define PAGE_KERNEL_EXEC_CONT __pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
#define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
#define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
#define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
-#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
+#define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
+#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
#define TASK_SIZE_64 (UL(1) << VA_BITS)
+#define KERNEL_DS UL(-1)
+#define USER_DS (TASK_SIZE_64 - 1)
+
#ifndef __ASSEMBLY__
/*
" cbnz %w1, 1f\n"
" add %w1, %w0, %3\n"
" casa %w0, %w1, %2\n"
- " and %w1, %w1, #0xffff\n"
- " eor %w1, %w1, %w0, lsr #16\n"
+ " sub %w1, %w1, %3\n"
+ " eor %w1, %w1, %w0\n"
"1:")
: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
: "I" (1 << TICKET_SHIFT)
#include <asm/compiler.h>
#include <asm/extable.h>
-#define KERNEL_DS (-1UL)
#define get_ds() (KERNEL_DS)
-
-#define USER_DS TASK_SIZE_64
#define get_fs() (current_thread_info()->addr_limit)
static inline void set_fs(mm_segment_t fs)
{
current_thread_info()->addr_limit = fs;
+ /*
+ * Prevent a mispredicted conditional call to set_fs from forwarding
+ * the wrong address limit to access_ok under speculation.
+ */
+ dsb(nsh);
+ isb();
+
/* On user-mode return, check fs is correct */
set_thread_flag(TIF_FSCHECK);
* Returns 1 if the range is valid, 0 otherwise.
*
* This is equivalent to the following test:
- * (u65)addr + (u65)size <= current->addr_limit
- *
- * This needs 65-bit arithmetic.
+ * (u65)addr + (u65)size <= (u65)current->addr_limit + 1
*/
-#define __range_ok(addr, size) \
-({ \
- unsigned long __addr = (unsigned long)(addr); \
- unsigned long flag, roksum; \
- __chk_user_ptr(addr); \
- asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls" \
- : "=&r" (flag), "=&r" (roksum) \
- : "1" (__addr), "Ir" (size), \
- "r" (current_thread_info()->addr_limit) \
- : "cc"); \
- flag; \
-})
+static inline unsigned long __range_ok(unsigned long addr, unsigned long size)
+{
+ unsigned long limit = current_thread_info()->addr_limit;
+
+ __chk_user_ptr(addr);
+ asm volatile(
+ // A + B <= C + 1 for all A,B,C, in four easy steps:
+ // 1: X = A + B; X' = X % 2^64
+ " adds %0, %0, %2\n"
+ // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4
+ " csel %1, xzr, %1, hi\n"
+ // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X'
+ // to compensate for the carry flag being set in step 4. For
+ // X > 2^64, X' merely has to remain nonzero, which it does.
+ " csinv %0, %0, xzr, cc\n"
+ // 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1
+ // comes from the carry in being clear. Otherwise, we are
+ // testing X' - C == 0, subject to the previous adjustments.
+ " sbcs xzr, %0, %1\n"
+ " cset %0, ls\n"
+ : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc");
+
+ return addr;
+}
/*
* When dealing with data aborts, watchpoints, or instruction traps we may end
*/
#define untagged_addr(addr) sign_extend64(addr, 55)
-#define access_ok(type, addr, size) __range_ok(addr, size)
+#define access_ok(type, addr, size) __range_ok((unsigned long)(addr), size)
#define user_addr_max get_fs
#define _ASM_EXTABLE(from, to) \
__uaccess_enable(ARM64_ALT_PAN_NOT_UAO);
}
+/*
+ * Sanitise a uaccess pointer such that it becomes NULL if above the
+ * current addr_limit.
+ */
+#define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
+static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
+{
+ void __user *safe_ptr;
+
+ asm volatile(
+ " bics xzr, %1, %2\n"
+ " csel %0, %1, xzr, eq\n"
+ : "=&r" (safe_ptr)
+ : "r" (ptr), "r" (current_thread_info()->addr_limit)
+ : "cc");
+
+ csdb();
+ return safe_ptr;
+}
+
/*
* The "__xxx" versions of the user access functions do not verify the address
* space - it must have been done previously with a separate "access_ok()"
(x) = (__force __typeof__(*(ptr)))__gu_val; \
} while (0)
-#define __get_user(x, ptr) \
+#define __get_user_check(x, ptr, err) \
({ \
- int __gu_err = 0; \
- __get_user_err((x), (ptr), __gu_err); \
- __gu_err; \
+ __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \
+ __p = uaccess_mask_ptr(__p); \
+ __get_user_err((x), __p, (err)); \
+ } else { \
+ (x) = 0; (err) = -EFAULT; \
+ } \
})
#define __get_user_error(x, ptr, err) \
({ \
- __get_user_err((x), (ptr), (err)); \
+ __get_user_check((x), (ptr), (err)); \
(void)0; \
})
-#define get_user(x, ptr) \
+#define __get_user(x, ptr) \
({ \
- __typeof__(*(ptr)) __user *__p = (ptr); \
- might_fault(); \
- access_ok(VERIFY_READ, __p, sizeof(*__p)) ? \
- __get_user((x), __p) : \
- ((x) = 0, -EFAULT); \
+ int __gu_err = 0; \
+ __get_user_check((x), (ptr), __gu_err); \
+ __gu_err; \
})
+#define get_user __get_user
+
#define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature) \
asm volatile( \
"1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \
uaccess_disable_not_uao(); \
} while (0)
-#define __put_user(x, ptr) \
+#define __put_user_check(x, ptr, err) \
({ \
- int __pu_err = 0; \
- __put_user_err((x), (ptr), __pu_err); \
- __pu_err; \
+ __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \
+ __p = uaccess_mask_ptr(__p); \
+ __put_user_err((x), __p, (err)); \
+ } else { \
+ (err) = -EFAULT; \
+ } \
})
#define __put_user_error(x, ptr, err) \
({ \
- __put_user_err((x), (ptr), (err)); \
+ __put_user_check((x), (ptr), (err)); \
(void)0; \
})
-#define put_user(x, ptr) \
+#define __put_user(x, ptr) \
({ \
- __typeof__(*(ptr)) __user *__p = (ptr); \
- might_fault(); \
- access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ? \
- __put_user((x), __p) : \
- -EFAULT; \
+ int __pu_err = 0; \
+ __put_user_check((x), (ptr), __pu_err); \
+ __pu_err; \
})
+#define put_user __put_user
+
extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
-#define raw_copy_from_user __arch_copy_from_user
+#define raw_copy_from_user(to, from, n) \
+({ \
+ __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \
+})
+
extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
-#define raw_copy_to_user __arch_copy_to_user
-extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
+#define raw_copy_to_user(to, from, n) \
+({ \
+ __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \
+})
+
+extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n);
+#define raw_copy_in_user(to, from, n) \
+({ \
+ __arch_copy_in_user(__uaccess_mask_ptr(to), \
+ __uaccess_mask_ptr(from), (n)); \
+})
+
#define INLINE_COPY_TO_USER
#define INLINE_COPY_FROM_USER
-static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
+extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n);
+static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n)
{
if (access_ok(VERIFY_WRITE, to, n))
- n = __clear_user(to, n);
+ n = __arch_clear_user(__uaccess_mask_ptr(to), n);
return n;
}
+#define clear_user __clear_user
extern long strncpy_from_user(char *dest, const char __user *src, long count);
static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
{
kasan_check_write(dst, size);
- return __copy_user_flushcache(dst, src, size);
+ return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size);
}
#endif
done:
if (acpi_disabled) {
- if (earlycon_init_is_deferred)
+ if (earlycon_acpi_spcr_enable)
early_init_dt_scan_chosen_stdout();
} else {
- parse_spcr(earlycon_init_is_deferred);
+ acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
if (IS_ENABLED(CONFIG_ACPI_BGRT))
acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
}
/* user mem (segment) */
EXPORT_SYMBOL(__arch_copy_from_user);
EXPORT_SYMBOL(__arch_copy_to_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(raw_copy_in_user);
+EXPORT_SYMBOL(__arch_clear_user);
+EXPORT_SYMBOL(__arch_copy_in_user);
/* physical memory */
EXPORT_SYMBOL(memstart_addr);
*/
#include <linux/linkage.h>
+#include <linux/arm-smccc.h>
.macro ventry target
.rept 31
vectors __kvm_hyp_vector
.endr
ENTRY(__bp_harden_hyp_vecs_end)
-ENTRY(__psci_hyp_bp_inval_start)
- sub sp, sp, #(8 * 18)
- stp x16, x17, [sp, #(16 * 0)]
- stp x14, x15, [sp, #(16 * 1)]
- stp x12, x13, [sp, #(16 * 2)]
- stp x10, x11, [sp, #(16 * 3)]
- stp x8, x9, [sp, #(16 * 4)]
- stp x6, x7, [sp, #(16 * 5)]
- stp x4, x5, [sp, #(16 * 6)]
- stp x2, x3, [sp, #(16 * 7)]
- stp x0, x1, [sp, #(16 * 8)]
- mov x0, #0x84000000
- smc #0
- ldp x16, x17, [sp, #(16 * 0)]
- ldp x14, x15, [sp, #(16 * 1)]
- ldp x12, x13, [sp, #(16 * 2)]
- ldp x10, x11, [sp, #(16 * 3)]
- ldp x8, x9, [sp, #(16 * 4)]
- ldp x6, x7, [sp, #(16 * 5)]
- ldp x4, x5, [sp, #(16 * 6)]
- ldp x2, x3, [sp, #(16 * 7)]
- ldp x0, x1, [sp, #(16 * 8)]
- add sp, sp, #(8 * 18)
-ENTRY(__psci_hyp_bp_inval_end)
ENTRY(__qcom_hyp_sanitize_link_stack_start)
stp x29, x30, [sp, #-16]!
.endr
ldp x29, x30, [sp], #16
ENTRY(__qcom_hyp_sanitize_link_stack_end)
+
+.macro smccc_workaround_1 inst
+ sub sp, sp, #(8 * 4)
+ stp x2, x3, [sp, #(8 * 0)]
+ stp x0, x1, [sp, #(8 * 2)]
+ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+ \inst #0
+ ldp x2, x3, [sp, #(8 * 0)]
+ ldp x0, x1, [sp, #(8 * 2)]
+ add sp, sp, #(8 * 4)
+.endm
+
+ENTRY(__smccc_workaround_1_smc_start)
+ smccc_workaround_1 smc
+ENTRY(__smccc_workaround_1_smc_end)
+
+ENTRY(__smccc_workaround_1_hvc_start)
+ smccc_workaround_1 hvc
+ENTRY(__smccc_workaround_1_hvc_end)
#include <asm/virt.h>
.text
-.pushsection .idmap.text, "ax"
+.pushsection .idmap.text, "awx"
/*
* __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
#ifdef CONFIG_KVM
-extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[];
extern char __qcom_hyp_sanitize_link_stack_start[];
extern char __qcom_hyp_sanitize_link_stack_end[];
+extern char __smccc_workaround_1_smc_start[];
+extern char __smccc_workaround_1_smc_end[];
+extern char __smccc_workaround_1_hvc_start[];
+extern char __smccc_workaround_1_hvc_end[];
static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
const char *hyp_vecs_end)
spin_unlock(&bp_lock);
}
#else
-#define __psci_hyp_bp_inval_start NULL
-#define __psci_hyp_bp_inval_end NULL
#define __qcom_hyp_sanitize_link_stack_start NULL
#define __qcom_hyp_sanitize_link_stack_end NULL
+#define __smccc_workaround_1_smc_start NULL
+#define __smccc_workaround_1_smc_end NULL
+#define __smccc_workaround_1_hvc_start NULL
+#define __smccc_workaround_1_hvc_end NULL
static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
const char *hyp_vecs_start,
__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
}
+#include <uapi/linux/psci.h>
+#include <linux/arm-smccc.h>
#include <linux/psci.h>
-static int enable_psci_bp_hardening(void *data)
+static void call_smc_arch_workaround_1(void)
+{
+ arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static void call_hvc_arch_workaround_1(void)
+{
+ arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
+}
+
+static int enable_smccc_arch_workaround_1(void *data)
{
const struct arm64_cpu_capabilities *entry = data;
+ bp_hardening_cb_t cb;
+ void *smccc_start, *smccc_end;
+ struct arm_smccc_res res;
+
+ if (!entry->matches(entry, SCOPE_LOCAL_CPU))
+ return 0;
+
+ if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
+ return 0;
+
+ switch (psci_ops.conduit) {
+ case PSCI_CONDUIT_HVC:
+ arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+ ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+ if (res.a0)
+ return 0;
+ cb = call_hvc_arch_workaround_1;
+ smccc_start = __smccc_workaround_1_hvc_start;
+ smccc_end = __smccc_workaround_1_hvc_end;
+ break;
+
+ case PSCI_CONDUIT_SMC:
+ arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+ ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+ if (res.a0)
+ return 0;
+ cb = call_smc_arch_workaround_1;
+ smccc_start = __smccc_workaround_1_smc_start;
+ smccc_end = __smccc_workaround_1_smc_end;
+ break;
+
+ default:
+ return 0;
+ }
- if (psci_ops.get_version)
- install_bp_hardening_cb(entry,
- (bp_hardening_cb_t)psci_ops.get_version,
- __psci_hyp_bp_inval_start,
- __psci_hyp_bp_inval_end);
+ install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
return 0;
}
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
- .enable = enable_psci_bp_hardening,
+ .enable = enable_smccc_arch_workaround_1,
},
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
- .enable = enable_psci_bp_hardening,
+ .enable = enable_smccc_arch_workaround_1,
},
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
- .enable = enable_psci_bp_hardening,
+ .enable = enable_smccc_arch_workaround_1,
},
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
- .enable = enable_psci_bp_hardening,
+ .enable = enable_smccc_arch_workaround_1,
},
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
- .enable = enable_psci_bp_hardening,
+ .enable = enable_smccc_arch_workaround_1,
},
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
- .enable = enable_psci_bp_hardening,
+ .enable = enable_smccc_arch_workaround_1,
},
#endif
{
static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
int __unused)
{
+ char const *str = "command line option";
u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
- /* Forced on command line? */
+ /*
+ * For reasons that aren't entirely clear, enabling KPTI on Cavium
+ * ThunderX leads to apparent I-cache corruption of kernel text, which
+ * ends as well as you might imagine. Don't even try.
+ */
+ if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456)) {
+ str = "ARM64_WORKAROUND_CAVIUM_27456";
+ __kpti_forced = -1;
+ }
+
+ /* Forced? */
if (__kpti_forced) {
- pr_info_once("kernel page table isolation forced %s by command line option\n",
- __kpti_forced > 0 ? "ON" : "OFF");
+ pr_info_once("kernel page table isolation forced %s by %s\n",
+ __kpti_forced > 0 ? "ON" : "OFF", str);
return __kpti_forced > 0;
}
ID_AA64PFR0_CSV3_SHIFT);
}
+static int kpti_install_ng_mappings(void *__unused)
+{
+ typedef void (kpti_remap_fn)(int, int, phys_addr_t);
+ extern kpti_remap_fn idmap_kpti_install_ng_mappings;
+ kpti_remap_fn *remap_fn;
+
+ static bool kpti_applied = false;
+ int cpu = smp_processor_id();
+
+ if (kpti_applied)
+ return 0;
+
+ remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
+
+ cpu_install_idmap();
+ remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir));
+ cpu_uninstall_idmap();
+
+ if (!cpu)
+ kpti_applied = true;
+
+ return 0;
+}
+
static int __init parse_kpti(char *str)
{
bool enabled;
.capability = ARM64_UNMAP_KERNEL_AT_EL0,
.def_scope = SCOPE_SYSTEM,
.matches = unmap_kernel_at_el0,
+ .enable = kpti_install_ng_mappings,
},
#endif
{
.else
add x21, sp, #S_FRAME_SIZE
get_thread_info tsk
- /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+ /* Save the task's original addr_limit and set USER_DS */
ldr x20, [tsk, #TSK_TI_ADDR_LIMIT]
str x20, [sp, #S_ORIG_ADDR_LIMIT]
- mov x20, #TASK_SIZE_64
+ mov x20, #USER_DS
str x20, [tsk, #TSK_TI_ADDR_LIMIT]
/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
.endif /* \el == 0 */
* x7 is reserved for the system call number in 32-bit mode.
*/
wsc_nr .req w25 // number of system calls
+xsc_nr .req x25 // number of system calls (zero-extended)
wscno .req w26 // syscall number
xscno .req x26 // syscall number (zero-extended)
stbl .req x27 // syscall table pointer
* Stack or PC alignment exception handling
*/
mrs x26, far_el1
- enable_daif
+ enable_da_f
+#ifdef CONFIG_TRACE_IRQFLAGS
+ bl trace_hardirqs_off
+#endif
ct_user_exit
mov x0, x26
mov x1, x25
#endif
ct_user_exit
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+ tbz x22, #55, 1f
+ bl do_el0_irq_bp_hardening
+1:
+#endif
irq_handler
#ifdef CONFIG_TRACE_IRQFLAGS
b.ne __sys_trace
cmp wscno, wsc_nr // check upper syscall limit
b.hs ni_sys
+ mask_nospec64 xscno, xsc_nr, x19 // enforce bounds for syscall number
ldr x16, [stbl, xscno, lsl #3] // address in the syscall table
blr x16 // call sys_* routine
b ret_fast_syscall
orr \tmp, \tmp, #USER_ASID_FLAG
msr ttbr1_el1, \tmp
/*
- * We avoid running the post_ttbr_update_workaround here because the
- * user and kernel ASIDs don't have conflicting mappings, so any
- * "blessing" as described in:
- *
- * http://lkml.kernel.org/r/56BB848A.6060603@caviumnetworks.com
- *
- * will not hurt correctness. Whilst this may partially defeat the
- * point of using split ASIDs in the first place, it avoids
- * the hit of invalidating the entire I-cache on every return to
- * userspace.
+ * We avoid running the post_ttbr_update_workaround here because
+ * it's only needed by Cavium ThunderX, which requires KPTI to be
+ * disabled.
*/
.endm
b __inval_dcache_area // tail call
ENDPROC(preserve_boot_args)
-/*
- * Macro to arrange a physical address in a page table entry, taking care of
- * 52-bit addresses.
- *
- * Preserves: phys
- * Returns: pte
- */
- .macro phys_to_pte, phys, pte
-#ifdef CONFIG_ARM64_PA_BITS_52
- /*
- * We assume \phys is 64K aligned and this is guaranteed by only
- * supporting this configuration with 64K pages.
- */
- orr \pte, \phys, \phys, lsr #36
- and \pte, \pte, #PTE_ADDR_MASK
-#else
- mov \pte, \phys
-#endif
- .endm
-
/*
* Macro to create a table entry to the next page.
*
*/
.macro create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
add \tmp1, \tbl, #PAGE_SIZE
- phys_to_pte \tmp1, \tmp2
+ phys_to_pte \tmp2, \tmp1
orr \tmp2, \tmp2, #PMD_TYPE_TABLE // address of next table and entry type
lsr \tmp1, \virt, #\shift
sub \ptrs, \ptrs, #1
* Returns: rtbl
*/
.macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1
-.Lpe\@: phys_to_pte \rtbl, \tmp1
+.Lpe\@: phys_to_pte \tmp1, \rtbl
orr \tmp1, \tmp1, \flags // tmp1 = table entry
str \tmp1, [\tbl, \index, lsl #3]
add \rtbl, \rtbl, \inc // rtbl = pa next level
* end early head section, begin head code that is also used for
* hotplug and needs to have the same protections as the text region
*/
- .section ".idmap.text","ax"
+ .section ".idmap.text","awx"
ENTRY(kimage_vaddr)
.quad _text - TEXT_OFFSET
update_early_cpu_boot_status 0, x1, x2
adrp x1, idmap_pg_dir
adrp x2, swapper_pg_dir
- phys_to_ttbr x1, x3
- phys_to_ttbr x2, x4
+ phys_to_ttbr x3, x1
+ phys_to_ttbr x4, x2
msr ttbr0_el1, x3 // load TTBR0
msr ttbr1_el1, x4 // load TTBR1
isb
* each stage of the walk.
*/
.macro break_before_make_ttbr_switch zero_page, page_table, tmp
- phys_to_ttbr \zero_page, \tmp
+ phys_to_ttbr \tmp, \zero_page
msr ttbr1_el1, \tmp
isb
tlbi vmalle1
dsb nsh
- phys_to_ttbr \page_table, \tmp
+ phys_to_ttbr \tmp, \page_table
msr ttbr1_el1, \tmp
isb
.endm
ret
ENDPROC(__cpu_suspend_enter)
- .pushsection ".idmap.text", "ax"
+ .pushsection ".idmap.text", "awx"
ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
bl __cpu_setup
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
struct kvm_guest_debug *dbg)
{
+ int ret = 0;
+
+ vcpu_load(vcpu);
+
trace_kvm_set_guest_debug(vcpu, dbg->control);
- if (dbg->control & ~KVM_GUESTDBG_VALID_MASK)
- return -EINVAL;
+ if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
+ ret = -EINVAL;
+ goto out;
+ }
if (dbg->control & KVM_GUESTDBG_ENABLE) {
vcpu->guest_debug = dbg->control;
/* If not enabled clear all flags */
vcpu->guest_debug = 0;
}
- return 0;
+
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <kvm/arm_psci.h>
+
#include <asm/esr.h>
#include <asm/exception.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_coproc.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
-#include <asm/kvm_psci.h>
#include <asm/debug-monitors.h>
#include <asm/traps.h>
kvm_vcpu_hvc_get_imm(vcpu));
vcpu->stat.hvc_exit_stat++;
- ret = kvm_psci_call(vcpu);
+ ret = kvm_hvc_call_handler(vcpu);
if (ret < 0) {
vcpu_set_reg(vcpu, 0, ~0UL);
return 1;
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
+ /*
+ * "If an SMC instruction executed at Non-secure EL1 is
+ * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a
+ * Trap exception, not a Secure Monitor Call exception [...]"
+ *
+ * We need to advance the PC after the trap, as it would
+ * otherwise return to the same address...
+ */
vcpu_set_reg(vcpu, 0, ~0UL);
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
return 1;
}
cmp x0, #HVC_STUB_HCALL_NR
b.lo __kvm_handle_stub_hvc
- phys_to_ttbr x0, x4
+ phys_to_ttbr x4, x0
msr ttbr0_el2, x4
mrs x4, tcr_el1
#include <asm/debug-monitors.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
#define read_debug(r,n) read_sysreg(r##n##_el1)
#define write_debug(v,r,n) write_sysreg(v, r##n##_el1)
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/arm-smccc.h>
#include <linux/linkage.h>
#include <asm/alternative.h>
lsr x0, x1, #ESR_ELx_EC_SHIFT
cmp x0, #ESR_ELx_EC_HVC64
+ ccmp x0, #ESR_ELx_EC_HVC32, #4, ne
b.ne el1_trap
- mrs x1, vttbr_el2 // If vttbr is valid, the 64bit guest
- cbnz x1, el1_trap // called HVC
+ mrs x1, vttbr_el2 // If vttbr is valid, the guest
+ cbnz x1, el1_hvc_guest // called HVC
/* Here, we're pretty sure the host called HVC. */
ldp x0, x1, [sp], #16
eret
+el1_hvc_guest:
+ /*
+ * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1.
+ * The workaround has already been applied on the host,
+ * so let's quickly get back to the guest. We don't bother
+ * restoring x1, as it can be clobbered anyway.
+ */
+ ldr x1, [sp] // Guest's x0
+ eor w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1
+ cbnz w1, el1_trap
+ mov x0, x1
+ add sp, sp, #16
+ eret
+
el1_trap:
/*
* x0: ESR_EC
#include <linux/jump_label.h>
#include <uapi/linux/psci.h>
+#include <kvm/arm_psci.h>
+
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
#include <asm/fpsimd.h>
#include <asm/debug-monitors.h>
if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
goto again;
- if (exit_code == ARM_EXCEPTION_TRAP &&
- (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 ||
- kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) &&
- vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) {
- u64 val = PSCI_RET_NOT_SUPPORTED;
- if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
- val = 2;
-
- vcpu_set_reg(vcpu, 0, val);
- goto again;
- }
-
if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
exit_code == ARM_EXCEPTION_TRAP) {
bool valid;
*/
#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
#include <asm/tlbflush.h>
static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
.text
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: int __arch_clear_user(void *addr, size_t sz)
* Purpose : clear some user memory
* Params : addr - user memory address to clear
* : sz - number of bytes to clear
*
* Alignment fixed up by hardware.
*/
-ENTRY(__clear_user)
+ENTRY(__arch_clear_user)
uaccess_enable_not_uao x2, x3, x4
mov x2, x1 // save the size for fixup return
subs x1, x1, #8
5: mov x0, #0
uaccess_disable_not_uao x2, x3
ret
-ENDPROC(__clear_user)
+ENDPROC(__arch_clear_user)
.section .fixup,"ax"
.align 2
.endm
end .req x5
-ENTRY(raw_copy_in_user)
+
+ENTRY(__arch_copy_in_user)
uaccess_enable_not_uao x3, x4, x5
add end, x0, x2
#include "copy_template.S"
uaccess_disable_not_uao x3, x4
mov x0, #0
ret
-ENDPROC(raw_copy_in_user)
+ENDPROC(__arch_copy_in_user)
.section .fixup,"ax"
.align 2
b.lo 1b
dsb ish
- icache_line_size x2, x3
- sub x3, x2, #1
- bic x4, x0, x3
-1:
-USER(9f, ic ivau, x4 ) // invalidate I line PoU
- add x4, x4, x2
- cmp x4, x1
- b.lo 1b
- dsb ish
- isb
+ invalidate_icache_by_line x0, x1, x2, x3, 9f
mov x0, #0
1:
uaccess_ttbr0_disable x1, x2
ENDPROC(flush_icache_range)
ENDPROC(__flush_cache_user_range)
+/*
+ * invalidate_icache_range(start,end)
+ *
+ * Ensure that the I cache is invalid within specified region.
+ *
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+ENTRY(invalidate_icache_range)
+ uaccess_ttbr0_enable x2, x3, x4
+
+ invalidate_icache_by_line x0, x1, x2, x3, 2f
+ mov x0, xzr
+1:
+ uaccess_ttbr0_disable x1, x2
+ ret
+2:
+ mov x0, #-EFAULT
+ b 1b
+ENDPROC(invalidate_icache_range)
+
/*
* __flush_dcache_area(kaddr, size)
*
if (fsc_type == ESR_ELx_FSC_PERM)
return true;
- if (addr < USER_DS && system_uses_ttbr0_pan())
+ if (addr < TASK_SIZE && system_uses_ttbr0_pan())
return fsc_type == ESR_ELx_FSC_FAULT &&
(regs->pstate & PSR_PAN_BIT);
mm_flags |= FAULT_FLAG_WRITE;
}
- if (addr < USER_DS && is_permission_fault(esr, regs, addr)) {
+ if (addr < TASK_SIZE && is_permission_fault(esr, regs, addr)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
arm64_notify_die("", regs, &info, esr);
}
+asmlinkage void __exception do_el0_irq_bp_hardening(void)
+{
+ /* PC has already been checked in entry.S */
+ arm64_apply_bp_hardening();
+}
+
asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
unsigned int esr,
struct pt_regs *regs)
struct siginfo info;
struct task_struct *tsk = current;
+ if (user_mode(regs)) {
+ if (instruction_pointer(regs) > TASK_SIZE)
+ arm64_apply_bp_hardening();
+ local_irq_enable();
+ }
+
if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
tsk->comm, task_pid_nr(tsk),
if (interrupts_enabled(regs))
trace_hardirqs_off();
+ if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE)
+ arm64_apply_bp_hardening();
+
if (!inf->fn(addr, esr, regs)) {
rv = 1;
} else {
if ((old | new) & PTE_CONT)
return false;
+ /* Transitioning from Global to Non-Global is safe */
+ if (((old ^ new) == PTE_NG) && (new & PTE_NG))
+ return true;
+
return ((old ^ new) & ~mask) == 0;
}
*
* x0: Address of context pointer
*/
- .pushsection ".idmap.text", "ax"
+ .pushsection ".idmap.text", "awx"
ENTRY(cpu_do_resume)
ldp x2, x3, [x0]
ldp x4, x5, [x0, #16]
ENTRY(cpu_do_switch_mm)
mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
- phys_to_ttbr x0, x3
+ phys_to_ttbr x3, x0
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
bfi x3, x1, #48, #16 // set the ASID field in TTBR0
#endif
b post_ttbr_update_workaround // Back to C code...
ENDPROC(cpu_do_switch_mm)
- .pushsection ".idmap.text", "ax"
+ .pushsection ".idmap.text", "awx"
+
+.macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2
+ adrp \tmp1, empty_zero_page
+ phys_to_ttbr \tmp2, \tmp1
+ msr ttbr1_el1, \tmp2
+ isb
+ tlbi vmalle1
+ dsb nsh
+ isb
+.endm
+
/*
* void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd)
*
ENTRY(idmap_cpu_replace_ttbr1)
save_and_disable_daif flags=x2
- adrp x1, empty_zero_page
- phys_to_ttbr x1, x3
+ __idmap_cpu_set_reserved_ttbr1 x1, x3
+
+ phys_to_ttbr x3, x0
msr ttbr1_el1, x3
isb
- tlbi vmalle1
- dsb nsh
+ restore_daif x2
+
+ ret
+ENDPROC(idmap_cpu_replace_ttbr1)
+ .popsection
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ .pushsection ".idmap.text", "awx"
+
+ .macro __idmap_kpti_get_pgtable_ent, type
+ dc cvac, cur_\()\type\()p // Ensure any existing dirty
+ dmb sy // lines are written back before
+ ldr \type, [cur_\()\type\()p] // loading the entry
+ tbz \type, #0, next_\()\type // Skip invalid entries
+ .endm
+
+ .macro __idmap_kpti_put_pgtable_ent_ng, type
+ orr \type, \type, #PTE_NG // Same bit for blocks and pages
+ str \type, [cur_\()\type\()p] // Update the entry and ensure it
+ dc civac, cur_\()\type\()p // is visible to all CPUs.
+ .endm
+
+/*
+ * void __kpti_install_ng_mappings(int cpu, int num_cpus, phys_addr_t swapper)
+ *
+ * Called exactly once from stop_machine context by each CPU found during boot.
+ */
+__idmap_kpti_flag:
+ .long 1
+ENTRY(idmap_kpti_install_ng_mappings)
+ cpu .req w0
+ num_cpus .req w1
+ swapper_pa .req x2
+ swapper_ttb .req x3
+ flag_ptr .req x4
+ cur_pgdp .req x5
+ end_pgdp .req x6
+ pgd .req x7
+ cur_pudp .req x8
+ end_pudp .req x9
+ pud .req x10
+ cur_pmdp .req x11
+ end_pmdp .req x12
+ pmd .req x13
+ cur_ptep .req x14
+ end_ptep .req x15
+ pte .req x16
+
+ mrs swapper_ttb, ttbr1_el1
+ adr flag_ptr, __idmap_kpti_flag
+
+ cbnz cpu, __idmap_kpti_secondary
+
+ /* We're the boot CPU. Wait for the others to catch up */
+ sevl
+1: wfe
+ ldaxr w18, [flag_ptr]
+ eor w18, w18, num_cpus
+ cbnz w18, 1b
+
+ /* We need to walk swapper, so turn off the MMU. */
+ pre_disable_mmu_workaround
+ mrs x18, sctlr_el1
+ bic x18, x18, #SCTLR_ELx_M
+ msr sctlr_el1, x18
isb
- phys_to_ttbr x0, x3
- msr ttbr1_el1, x3
+ /* Everybody is enjoying the idmap, so we can rewrite swapper. */
+ /* PGD */
+ mov cur_pgdp, swapper_pa
+ add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8)
+do_pgd: __idmap_kpti_get_pgtable_ent pgd
+ tbnz pgd, #1, walk_puds
+ __idmap_kpti_put_pgtable_ent_ng pgd
+next_pgd:
+ add cur_pgdp, cur_pgdp, #8
+ cmp cur_pgdp, end_pgdp
+ b.ne do_pgd
+
+ /* Publish the updated tables and nuke all the TLBs */
+ dsb sy
+ tlbi vmalle1is
+ dsb ish
isb
- restore_daif x2
+ /* We're done: fire up the MMU again */
+ mrs x18, sctlr_el1
+ orr x18, x18, #SCTLR_ELx_M
+ msr sctlr_el1, x18
+ isb
+ /* Set the flag to zero to indicate that we're all done */
+ str wzr, [flag_ptr]
ret
-ENDPROC(idmap_cpu_replace_ttbr1)
+
+ /* PUD */
+walk_puds:
+ .if CONFIG_PGTABLE_LEVELS > 3
+ pte_to_phys cur_pudp, pgd
+ add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8)
+do_pud: __idmap_kpti_get_pgtable_ent pud
+ tbnz pud, #1, walk_pmds
+ __idmap_kpti_put_pgtable_ent_ng pud
+next_pud:
+ add cur_pudp, cur_pudp, 8
+ cmp cur_pudp, end_pudp
+ b.ne do_pud
+ b next_pgd
+ .else /* CONFIG_PGTABLE_LEVELS <= 3 */
+ mov pud, pgd
+ b walk_pmds
+next_pud:
+ b next_pgd
+ .endif
+
+ /* PMD */
+walk_pmds:
+ .if CONFIG_PGTABLE_LEVELS > 2
+ pte_to_phys cur_pmdp, pud
+ add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8)
+do_pmd: __idmap_kpti_get_pgtable_ent pmd
+ tbnz pmd, #1, walk_ptes
+ __idmap_kpti_put_pgtable_ent_ng pmd
+next_pmd:
+ add cur_pmdp, cur_pmdp, #8
+ cmp cur_pmdp, end_pmdp
+ b.ne do_pmd
+ b next_pud
+ .else /* CONFIG_PGTABLE_LEVELS <= 2 */
+ mov pmd, pud
+ b walk_ptes
+next_pmd:
+ b next_pud
+ .endif
+
+ /* PTE */
+walk_ptes:
+ pte_to_phys cur_ptep, pmd
+ add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8)
+do_pte: __idmap_kpti_get_pgtable_ent pte
+ __idmap_kpti_put_pgtable_ent_ng pte
+next_pte:
+ add cur_ptep, cur_ptep, #8
+ cmp cur_ptep, end_ptep
+ b.ne do_pte
+ b next_pmd
+
+ /* Secondary CPUs end up here */
+__idmap_kpti_secondary:
+ /* Uninstall swapper before surgery begins */
+ __idmap_cpu_set_reserved_ttbr1 x18, x17
+
+ /* Increment the flag to let the boot CPU we're ready */
+1: ldxr w18, [flag_ptr]
+ add w18, w18, #1
+ stxr w17, w18, [flag_ptr]
+ cbnz w17, 1b
+
+ /* Wait for the boot CPU to finish messing around with swapper */
+ sevl
+1: wfe
+ ldxr w18, [flag_ptr]
+ cbnz w18, 1b
+
+ /* All done, act like nothing happened */
+ msr ttbr1_el1, swapper_ttb
+ isb
+ ret
+
+ .unreq cpu
+ .unreq num_cpus
+ .unreq swapper_pa
+ .unreq swapper_ttb
+ .unreq flag_ptr
+ .unreq cur_pgdp
+ .unreq end_pgdp
+ .unreq pgd
+ .unreq cur_pudp
+ .unreq end_pudp
+ .unreq pud
+ .unreq cur_pmdp
+ .unreq end_pmdp
+ .unreq pmd
+ .unreq cur_ptep
+ .unreq end_ptep
+ .unreq pte
+ENDPROC(idmap_kpti_install_ng_mappings)
.popsection
+#endif
/*
* __cpu_setup
* Initialise the processor for turning the MMU on. Return in x0 the
* value of the SCTLR_EL1 register.
*/
- .pushsection ".idmap.text", "ax"
+ .pushsection ".idmap.text", "awx"
ENTRY(__cpu_setup)
tlbi vmalle1 // Invalidate local TLB
dsb nsh
#ifndef _UAPI__BFIN_POLL_H
#define _UAPI__BFIN_POLL_H
-#ifndef __KERNEL__
#define POLLWRNORM POLLOUT
-#define POLLWRBAND (__force __poll_t)256
-#else
-#define __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- __u16 v = (__force __u16)val;
- /* bit 9 -> bit 8, bit 8 -> bit 2 */
- return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
- return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
- ((v & 4) << 6));
-}
-#endif
+#define POLLWRBAND 256
#include <asm-generic/poll.h>
if ((data & priv->highalarm) ||
(~data & priv->lowalarm)) {
- mask = POLLIN|POLLRDNORM;
+ mask = EPOLLIN|EPOLLRDNORM;
}
out:
poll_wait(file, &port->in_wait_q, wait);
/* Some room to write */
if (port->out_count < OUT_BUFFER_SIZE)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
/* At least an inbufchunk of data */
if (sync_data_avail(port) >= port->inbufchunk)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
DEBUGPOLL(if (mask != prev_mask)
printk(KERN_DEBUG "sync_serial_poll: mask 0x%08X %s %s\n",
mask,
- mask & POLLOUT ? "POLLOUT" : "",
- mask & POLLIN ? "POLLIN" : "");
+ mask & EPOLLOUT ? "POLLOUT" : "",
+ mask & EPOLLIN ? "POLLIN" : "");
prev_mask = mask;
);
return mask;
/* No active transfer, descriptors are available */
if (port->output && !port->tr_running)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
/* Descriptor and buffer space available. */
if (port->output &&
port->active_tr_descr != port->catch_tr_descr &&
port->out_buf_count < OUT_BUFFER_SIZE)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
/* At least an inbufchunk of data */
if (port->input && sync_data_avail(port) >= port->inbufchunk)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
DEBUGPOLL(
if (mask != prev_mask)
pr_info("sync_serial_poll: mask 0x%08X %s %s\n",
mask,
- mask & POLLOUT ? "POLLOUT" : "",
- mask & POLLIN ? "POLLIN" : "");
+ mask & EPOLLOUT ? "POLLOUT" : "",
+ mask & EPOLLIN ? "POLLIN" : "");
prev_mask = mask;
);
return mask;
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the CRIS port.
+#
+
+CPPFLAGS_vmlinux.lds := -DDRAM_VIRTUAL_BASE=0x$(CONFIG_ETRAX_DRAM_VIRTUAL_BASE)
+extra-y := vmlinux.lds
+
+obj-y := process.o traps.o irq.o ptrace.o setup.o time.o sys_cris.o
+obj-y += stacktrace.o
+
+obj-$(CONFIG_MODULES) += crisksyms.o
+obj-$(CONFIG_MODULES) += module.o
+obj-$(CONFIG_SYSTEM_PROFILER) += profile.o
+
+clean:
+
#include <linux/of_fdt.h>
#include <asm/setup.h>
#include <arch/system.h>
+#include <asm/sections.h>
/*
* Setup options
struct screen_info screen_info;
extern int root_mountflags;
-extern char _etext, _edata, _end;
char __initdata cris_command_line[COMMAND_LINE_SIZE] = { 0, };
#ifndef _ASM_POLL_H
#define _ASM_POLL_H
-#ifndef __KERNEL__
#define POLLWRNORM POLLOUT
-#define POLLWRBAND (__force __poll_t)256
-#else
-#define __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- __u16 v = (__force __u16)val;
- /* bit 9 -> bit 8, bit 8 -> bit 2 */
- return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
- return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
- ((v & 4) << 6));
-}
-#endif
+#define POLLWRBAND 256
#include <asm-generic/poll.h>
#undef POLLREMOVE
PROTECT_CTX(ctx, flags);
if (PFM_CTXQ_EMPTY(ctx) == 0)
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
UNPROTECT_CTX(ctx, flags);
#ifndef __m68k_POLL_H
#define __m68k_POLL_H
-#ifndef __KERNEL__
#define POLLWRNORM POLLOUT
-#define POLLWRBAND (__force __poll_t)256
-#else
-#define __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- __u16 v = (__force __u16)val;
- /* bit 9 -> bit 8, bit 8 -> bit 2 */
- return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
- return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
- ((v & 4) << 6));
-}
-#endif
+#define POLLWRBAND 256
#include <asm-generic/poll.h>
config MIPS_VPE_APSP_API
bool "Enable support for AP/SP API (RTLX)"
depends on MIPS_VPE_LOADER
- help
config MIPS_VPE_APSP_API_CMP
bool
config BOARD_BCM963XX
bool "Generic Broadcom 963xx boards"
select SSB
- help
endchoice
#ifndef __ASM_POLL_H
#define __ASM_POLL_H
-#ifndef __KERNEL__
#define POLLWRNORM POLLOUT
-#define POLLWRBAND (__force __poll_t)0x0100
-#else
-#define __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- __u16 v = (__force __u16)val;
- /* bit 9 -> bit 8, bit 8 -> bit 2 */
- return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
- return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
- ((v & 4) << 6));
-}
-#endif
+#define POLLWRBAND 0x0100
#include <asm-generic/poll.h>
#include <linux/errno.h>
#include <linux/percpu.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
#include <linux/spinlock.h>
#include <asm/mips-cps.h>
phys_addr_t __weak mips_cpc_default_phys_base(void)
{
+ struct device_node *cpc_node;
+ struct resource res;
+ int err;
+
+ cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc");
+ if (cpc_node) {
+ err = of_address_to_resource(cpc_node, 0, &res);
+ if (!err)
+ return res.start;
+ }
+
return 0;
}
/* data available to read? */
if (rtlx_read_poll(minor, 0))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* space to write */
if (rtlx_write_poll(minor))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
select PREEMPT_NOTIFIERS
select ANON_INODES
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ select HAVE_KVM_VCPU_ASYNC_IOCTL
select KVM_MMIO
select MMU_NOTIFIER
select SRCU
{
int r = -EINTR;
+ vcpu_load(vcpu);
+
kvm_sigset_activate(vcpu);
if (vcpu->mmio_needed) {
out:
kvm_sigset_deactivate(vcpu);
+ vcpu_put(vcpu);
return r;
}
return r;
}
+long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl,
+ unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+
+ if (ioctl == KVM_INTERRUPT) {
+ struct kvm_mips_interrupt irq;
+
+ if (copy_from_user(&irq, argp, sizeof(irq)))
+ return -EFAULT;
+ kvm_debug("[%d] %s: irq: %d\n", vcpu->vcpu_id, __func__,
+ irq.irq);
+
+ return kvm_vcpu_ioctl_interrupt(vcpu, &irq);
+ }
+
+ return -ENOIOCTLCMD;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
void __user *argp = (void __user *)arg;
long r;
+ vcpu_load(vcpu);
+
switch (ioctl) {
case KVM_SET_ONE_REG:
case KVM_GET_ONE_REG: {
struct kvm_one_reg reg;
+ r = -EFAULT;
if (copy_from_user(®, argp, sizeof(reg)))
- return -EFAULT;
+ break;
if (ioctl == KVM_SET_ONE_REG)
- return kvm_mips_set_reg(vcpu, ®);
+ r = kvm_mips_set_reg(vcpu, ®);
else
- return kvm_mips_get_reg(vcpu, ®);
+ r = kvm_mips_get_reg(vcpu, ®);
+ break;
}
case KVM_GET_REG_LIST: {
struct kvm_reg_list __user *user_list = argp;
struct kvm_reg_list reg_list;
unsigned n;
+ r = -EFAULT;
if (copy_from_user(®_list, user_list, sizeof(reg_list)))
- return -EFAULT;
+ break;
n = reg_list.n;
reg_list.n = kvm_mips_num_regs(vcpu);
if (copy_to_user(user_list, ®_list, sizeof(reg_list)))
- return -EFAULT;
+ break;
+ r = -E2BIG;
if (n < reg_list.n)
- return -E2BIG;
- return kvm_mips_copy_reg_indices(vcpu, user_list->reg);
- }
- case KVM_INTERRUPT:
- {
- struct kvm_mips_interrupt irq;
-
- if (copy_from_user(&irq, argp, sizeof(irq)))
- return -EFAULT;
- kvm_debug("[%d] %s: irq: %d\n", vcpu->vcpu_id, __func__,
- irq.irq);
-
- r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
break;
- }
+ r = kvm_mips_copy_reg_indices(vcpu, user_list->reg);
+ break;
+ }
case KVM_ENABLE_CAP: {
struct kvm_enable_cap cap;
+ r = -EFAULT;
if (copy_from_user(&cap, argp, sizeof(cap)))
- return -EFAULT;
+ break;
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
break;
}
default:
r = -ENOIOCTLCMD;
}
+
+ vcpu_put(vcpu);
return r;
}
{
int i;
+ vcpu_load(vcpu);
+
for (i = 1; i < ARRAY_SIZE(vcpu->arch.gprs); i++)
vcpu->arch.gprs[i] = regs->gpr[i];
vcpu->arch.gprs[0] = 0; /* zero is special, and cannot be set. */
vcpu->arch.lo = regs->lo;
vcpu->arch.pc = regs->pc;
+ vcpu_put(vcpu);
return 0;
}
{
int i;
+ vcpu_load(vcpu);
+
for (i = 0; i < ARRAY_SIZE(vcpu->arch.gprs); i++)
regs->gpr[i] = vcpu->arch.gprs[i];
regs->lo = vcpu->arch.lo;
regs->pc = vcpu->arch.pc;
+ vcpu_put(vcpu);
return 0;
}
config ADVANCED_OPTIONS
bool "Prompt for advanced kernel configuration options"
- help
comment "Default settings for advanced configuration options are used"
depends on !ADVANCED_OPTIONS
#address-cells = <1>;
#size-cells = <0>;
- cpu: cpu@0x0 {
+ cpu: cpu@0 {
device_type = "cpu";
compatible = "altr,nios2-1.0";
reg = <0x00000000>;
compatible = "altr,avalon", "simple-bus";
bus-frequency = <125000000>;
- pb_cpu_to_io: bridge@0x8000000 {
+ pb_cpu_to_io: bridge@8000000 {
compatible = "simple-bus";
reg = <0x08000000 0x00800000>;
#address-cells = <1>;
<0x00008000 0x08008000 0x00000020>,
<0x00400000 0x08400000 0x00000020>;
- timer_1ms: timer@0x400000 {
+ timer_1ms: timer@400000 {
compatible = "altr,timer-1.0";
reg = <0x00400000 0x00000020>;
interrupt-parent = <&cpu>;
clock-frequency = <125000000>;
};
- timer_0: timer@0x8000 {
+ timer_0: timer@8000 {
compatible = "altr,timer-1.0";
reg = < 0x00008000 0x00000020 >;
interrupt-parent = < &cpu >;
clock-frequency = < 125000000 >;
};
- jtag_uart: serial@0x4d50 {
+ jtag_uart: serial@4d50 {
compatible = "altr,juart-1.0";
reg = <0x00004d50 0x00000008>;
interrupt-parent = <&cpu>;
interrupts = <1>;
};
- tse_mac: ethernet@0x4000 {
+ tse_mac: ethernet@4000 {
compatible = "altr,tse-1.0";
reg = <0x00004000 0x00000400>,
<0x00004400 0x00000040>,
};
};
- uart: serial@0x4c80 {
+ uart: serial@4c80 {
compatible = "altr,uart-1.0";
reg = <0x00004c80 0x00000020>;
interrupt-parent = <&cpu>;
};
};
- cfi_flash_64m: flash@0x0 {
+ cfi_flash_64m: flash@0 {
compatible = "cfi-flash";
reg = <0x00000000 0x04000000>;
bank-width = <2>;
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
extern void kvmppc_pr_init_default_hcalls(struct kvm *kvm);
extern int kvmppc_hcall_impl_pr(unsigned long cmd);
extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd);
-extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
- struct kvm_vcpu *vcpu);
-extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
- struct kvmppc_book3s_shadow_vcpu *svcpu);
+extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu);
+extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu);
extern int kvm_irq_bypass;
static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
lphi = (l >> 16) & 0xf;
switch ((l >> 12) & 0xf) {
case 0:
- return !lphi ? 24 : -1; /* 16MB */
+ return !lphi ? 24 : 0; /* 16MB */
break;
case 1:
return 16; /* 64kB */
break;
case 3:
- return !lphi ? 34 : -1; /* 16GB */
+ return !lphi ? 34 : 0; /* 16GB */
break;
case 7:
return (16 << 8) + 12; /* 64kB in 4kB */
return (24 << 8) + 12; /* 16MB in 4kB */
break;
}
- return -1;
+ return 0;
}
static inline int kvmppc_hpte_base_page_shift(unsigned long h, unsigned long l)
static inline unsigned long kvmppc_actual_pgsz(unsigned long v, unsigned long r)
{
- return 1ul << kvmppc_hpte_actual_page_shift(v, r);
+ int shift = kvmppc_hpte_actual_page_shift(v, r);
+
+ if (shift)
+ return 1ul << shift;
+ return 0;
}
static inline int kvmppc_pgsize_lp_encoding(int base_shift, int actual_shift)
va_low ^= v >> (SID_SHIFT_1T - 16);
va_low &= 0x7ff;
- if (b_pgshift == 12) {
+ if (b_pgshift <= 12) {
if (a_pgshift > 12) {
sllp = (a_pgshift == 16) ? 5 : 4;
rb |= sllp << 5; /* AP field */
u8 mmio_vsx_offset;
u8 mmio_vsx_copy_type;
u8 mmio_vsx_tx_sx_enabled;
+ u8 mmio_vmx_copy_nums;
u8 osi_needed;
u8 osi_enabled;
u8 papr_enabled;
u8 ceded;
u8 prodded;
u8 doorbell_request;
+ u8 irq_pending; /* Used by XIVE to signal pending guest irqs */
u32 last_inst;
struct swait_queue_head *wqp;
struct kvmppc_icp *icp; /* XICS presentation controller */
struct kvmppc_xive_vcpu *xive_vcpu; /* XIVE virtual CPU data */
__be32 xive_cam_word; /* Cooked W2 in proper endian with valid bit */
- u32 xive_pushed; /* Is the VP pushed on the physical CPU ? */
+ u8 xive_pushed; /* Is the VP pushed on the physical CPU ? */
+ u8 xive_esc_on; /* Is the escalation irq enabled ? */
union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */
+ u64 xive_esc_raddr; /* Escalation interrupt ESB real addr */
+ u64 xive_esc_vaddr; /* Escalation interrupt ESB virt addr */
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#define KVM_MMIO_REG_QPR 0x0040
#define KVM_MMIO_REG_FQPR 0x0060
#define KVM_MMIO_REG_VSX 0x0080
+#define KVM_MMIO_REG_VMX 0x00c0
#define __KVM_HAVE_ARCH_WQP
#define __KVM_HAVE_CREATE_DEVICE
extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned int rt, unsigned int bytes,
int is_default_endian, int mmio_sign_extend);
+extern int kvmppc_handle_load128_by2x64(struct kvm_run *run,
+ struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian);
+extern int kvmppc_handle_store128_by2x64(struct kvm_run *run,
+ struct kvm_vcpu *vcpu, unsigned int rs, int is_default_endian);
extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
u64 val, unsigned int bytes,
int is_default_endian);
/* Flags for OPAL_XIVE_GET/SET_VP_INFO */
enum {
OPAL_XIVE_VP_ENABLED = 0x00000001,
+ OPAL_XIVE_VP_SINGLE_ESCALATION = 0x00000002,
};
/* "Any chip" replacement for chip ID for allocation functions */
#define OP_31_XOP_LFDX 599
#define OP_31_XOP_LFDUX 631
+/* VMX Vector Load Instructions */
+#define OP_31_XOP_LVX 103
+
+/* VMX Vector Store Instructions */
+#define OP_31_XOP_STVX 231
+
#define OP_LWZ 32
#define OP_STFS 52
#define OP_STFSU 53
extern void xive_native_sync_source(u32 hw_irq);
extern bool is_xive_irq(struct irq_chip *chip);
-extern int xive_native_enable_vp(u32 vp_id);
+extern int xive_native_enable_vp(u32 vp_id, bool single_escalation);
extern int xive_native_disable_vp(u32 vp_id);
extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
+extern bool xive_native_has_single_escalation(void);
#else
#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
OFFSET(VCPU_PENDING_EXC, kvm_vcpu, arch.pending_exceptions);
OFFSET(VCPU_CEDED, kvm_vcpu, arch.ceded);
OFFSET(VCPU_PRODDED, kvm_vcpu, arch.prodded);
+ OFFSET(VCPU_IRQ_PENDING, kvm_vcpu, arch.irq_pending);
OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request);
OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr);
OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc);
DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu,
arch.xive_cam_word));
DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed));
+ DEFINE(VCPU_XIVE_ESC_ON, offsetof(struct kvm_vcpu, arch.xive_esc_on));
+ DEFINE(VCPU_XIVE_ESC_RADDR, offsetof(struct kvm_vcpu, arch.xive_esc_raddr));
+ DEFINE(VCPU_XIVE_ESC_VADDR, offsetof(struct kvm_vcpu, arch.xive_esc_vaddr));
#endif
#ifdef CONFIG_KVM_EXIT_TIMING
*/
static int pci_read_irq_line(struct pci_dev *pci_dev)
{
- unsigned int virq = 0;
+ int virq;
pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
memset(&oirq, 0xff, sizeof(oirq));
#endif
/* Try to get a mapping from the device-tree */
- if (!of_irq_parse_and_map_pci(pci_dev, 0, 0)) {
+ virq = of_irq_parse_and_map_pci(pci_dev, 0, 0);
+ if (virq <= 0) {
u8 line, pin;
/* If that fails, lets fallback to what is in the config
{
poll_wait(file, &rtas_log_wait, wait);
if (rtas_log_size)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
select PREEMPT_NOTIFIERS
select ANON_INODES
select HAVE_KVM_EVENTFD
+ select HAVE_KVM_VCPU_ASYNC_IOCTL
select SRCU
select KVM_VFIO
select IRQ_BYPASS_MANAGER
select KVM_BOOK3S_64_HANDLER
select KVM
select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
- select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV)
+ select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_PSERIES || PPC_POWERNV)
---help---
Support running unmodified book3s_64 and book3s_32 guest kernels
in virtual machines on book3s_64 host processors.
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
- return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
+ int ret;
+
+ vcpu_load(vcpu);
+ ret = vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
+ vcpu_put(vcpu);
+
+ return ret;
}
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
- return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
+ int ret;
+
+ vcpu_load(vcpu);
+ ret = vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
+ vcpu_put(vcpu);
+
+ return ret;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
int i;
+ vcpu_load(vcpu);
+
regs->pc = kvmppc_get_pc(vcpu);
regs->cr = kvmppc_get_cr(vcpu);
regs->ctr = kvmppc_get_ctr(vcpu);
for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
+ vcpu_put(vcpu);
return 0;
}
{
int i;
+ vcpu_load(vcpu);
+
kvmppc_set_pc(vcpu, regs->pc);
kvmppc_set_cr(vcpu, regs->cr);
kvmppc_set_ctr(vcpu, regs->ctr);
for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
struct kvm_guest_debug *dbg)
{
+ vcpu_load(vcpu);
vcpu->guest_debug = dbg->control;
+ vcpu_put(vcpu);
return 0;
}
/* Nothing to do */
goto out;
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ rpte = be64_to_cpu(hptep[1]);
+ vpte = hpte_new_to_old_v(vpte, rpte);
+ }
+
/* Unmap */
rev = &old->rev[idx];
guest_rpte = rev->guest_rpte;
/* Reload PTE after unmap */
vpte = be64_to_cpu(hptep[0]);
-
BUG_ON(vpte & HPTE_V_VALID);
BUG_ON(!(vpte & HPTE_V_ABSENT));
goto out;
rpte = be64_to_cpu(hptep[1]);
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ vpte = hpte_new_to_old_v(vpte, rpte);
+ rpte = hpte_new_to_old_r(rpte);
+ }
+
pshift = kvmppc_hpte_base_page_shift(vpte, rpte);
avpn = HPTE_V_AVPN_VAL(vpte) & ~(((1ul << pshift) - 1) >> 23);
pteg = idx / HPTES_PER_GROUP;
}
new_pteg = hash & new_hash_mask;
- if (vpte & HPTE_V_SECONDARY) {
- BUG_ON(~pteg != (hash & old_hash_mask));
- new_pteg = ~new_pteg;
- } else {
- BUG_ON(pteg != (hash & old_hash_mask));
- }
+ if (vpte & HPTE_V_SECONDARY)
+ new_pteg = ~hash & new_hash_mask;
new_idx = new_pteg * HPTES_PER_GROUP + (idx % HPTES_PER_GROUP);
new_hptep = (__be64 *)(new->virt + (new_idx << 4));
replace_vpte = be64_to_cpu(new_hptep[0]);
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ unsigned long replace_rpte = be64_to_cpu(new_hptep[1]);
+ replace_vpte = hpte_new_to_old_v(replace_vpte, replace_rpte);
+ }
if (replace_vpte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
BUG_ON(new->order >= old->order);
/* Discard the previous HPTE */
}
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ rpte = hpte_old_to_new_r(vpte, rpte);
+ vpte = hpte_old_to_new_v(vpte);
+ }
+
new_hptep[1] = cpu_to_be64(rpte);
new->rev[new_idx].guest_rpte = guest_rpte;
/* No need for a barrier, since new HPT isn't active */
unsigned long i;
int rc;
- /*
- * resize_hpt_rehash_hpte() doesn't handle the new-format HPTEs
- * that POWER9 uses, and could well hit a BUG_ON on POWER9.
- */
- if (cpu_has_feature(CPU_FTR_ARCH_300))
- return -EIO;
for (i = 0; i < kvmppc_hpt_npte(&kvm->arch.hpt); i++) {
rc = resize_hpt_rehash_hpte(resize, i);
if (rc != 0)
synchronize_srcu_expedited(&kvm->srcu);
+ if (cpu_has_feature(CPU_FTR_ARCH_300))
+ kvmppc_setup_partition_table(kvm);
+
resize_hpt_debug(resize, "resize_hpt_pivot() done\n");
}
j = i + 1;
if (npages) {
set_dirty_bits(map, i, npages);
- i = j + npages;
+ j = i + npages;
}
}
return 0;
MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
#endif
+/* If set, the threads on each CPU core have to be in the same MMU mode */
+static bool no_mixing_hpt_and_radix;
+
static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tvcpu;
- if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return EMULATE_FAIL;
if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE)
return RESUME_GUEST;
if (get_op(inst) != 31)
return RESUME_GUEST;
}
+/* Called with vcpu->arch.vcore->lock held */
static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
struct task_struct *tsk)
{
swab32(vcpu->arch.emul_inst) :
vcpu->arch.emul_inst;
if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
+ /* Need vcore unlocked to call kvmppc_get_last_inst */
+ spin_unlock(&vcpu->arch.vcore->lock);
r = kvmppc_emulate_debug_inst(run, vcpu);
+ spin_lock(&vcpu->arch.vcore->lock);
} else {
kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
r = RESUME_GUEST;
*/
case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
r = EMULATE_FAIL;
- if ((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG)
+ if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) &&
+ cpu_has_feature(CPU_FTR_ARCH_300)) {
+ /* Need vcore unlocked to call kvmppc_get_last_inst */
+ spin_unlock(&vcpu->arch.vcore->lock);
r = kvmppc_emulate_doorbell_instr(vcpu);
+ spin_lock(&vcpu->arch.vcore->lock);
+ }
if (r == EMULATE_FAIL) {
kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
r = RESUME_GUEST;
case KVM_REG_PPC_ARCH_COMPAT:
*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
break;
+ case KVM_REG_PPC_DEC_EXPIRY:
+ *val = get_reg_val(id, vcpu->arch.dec_expires +
+ vcpu->arch.vcore->tb_offset);
+ break;
default:
r = -EINVAL;
break;
case KVM_REG_PPC_ARCH_COMPAT:
r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
break;
+ case KVM_REG_PPC_DEC_EXPIRY:
+ vcpu->arch.dec_expires = set_reg_val(id, *val) -
+ vcpu->arch.vcore->tb_offset;
+ break;
default:
r = -EINVAL;
break;
static bool subcore_config_ok(int n_subcores, int n_threads)
{
/*
- * POWER9 "SMT4" cores are permanently in what is effectively a 4-way split-core
- * mode, with one thread per subcore.
+ * POWER9 "SMT4" cores are permanently in what is effectively a 4-way
+ * split-core mode, with one thread per subcore.
*/
if (cpu_has_feature(CPU_FTR_ARCH_300))
return n_subcores <= 4 && n_threads == 1;
if (!cpu_has_feature(CPU_FTR_ARCH_207S))
return false;
- /* POWER9 currently requires all threads to be in the same MMU mode */
- if (cpu_has_feature(CPU_FTR_ARCH_300) &&
+ /* Some POWER9 chips require all threads to be in the same MMU mode */
+ if (no_mixing_hpt_and_radix &&
kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm))
return false;
* threads are offline. Also check if the number of threads in this
* guest are greater than the current system threads per guest.
* On POWER9, we need to be not in independent-threads mode if
- * this is a HPT guest on a radix host.
+ * this is a HPT guest on a radix host machine where the
+ * CPU threads may not be in different MMU modes.
*/
- hpt_on_radix = radix_enabled() && !kvm_is_radix(vc->kvm);
+ hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() &&
+ !kvm_is_radix(vc->kvm);
if (((controlled_threads > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) ||
(hpt_on_radix && vc->kvm->arch.threads_indep)) {
*/
if (!thr0_done)
kvmppc_start_thread(NULL, pvc);
- thr += pvc->num_threads;
}
/*
/* make sure updates to secondary vcpu structs are visible now */
smp_mb();
+ preempt_enable();
+
for (sub = 0; sub < core_info.n_subcores; ++sub) {
pvc = core_info.vc[sub];
post_guest_process(pvc, pvc == vc);
}
spin_lock(&vc->lock);
- preempt_enable();
out:
vc->vcore_state = VCORE_INACTIVE;
{
if (!xive_enabled())
return false;
- return vcpu->arch.xive_saved_state.pipr <
+ return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr <
vcpu->arch.xive_saved_state.cppr;
}
#else
* this thread straight away and have it join in.
*/
if (!signal_pending(current)) {
- if (vc->vcore_state == VCORE_PIGGYBACK) {
- if (spin_trylock(&vc->lock)) {
- if (vc->vcore_state == VCORE_RUNNING &&
- !VCORE_IS_EXITING(vc)) {
- kvmppc_create_dtl_entry(vcpu, vc);
- kvmppc_start_thread(vcpu, vc);
- trace_kvm_guest_enter(vcpu);
- }
- spin_unlock(&vc->lock);
- }
- } else if (vc->vcore_state == VCORE_RUNNING &&
+ if ((vc->vcore_state == VCORE_PIGGYBACK ||
+ vc->vcore_state == VCORE_RUNNING) &&
!VCORE_IS_EXITING(vc)) {
kvmppc_create_dtl_entry(vcpu, vc);
kvmppc_start_thread(vcpu, vc);
if (kvmppc_radix_possible())
r = kvmppc_radix_init();
+
+ /*
+ * POWER9 chips before version 2.02 can't have some threads in
+ * HPT mode and some in radix mode on the same core.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ unsigned int pvr = mfspr(SPRN_PVR);
+ if ((pvr >> 16) == PVR_POWER9 &&
+ (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) ||
+ ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101)))
+ no_mixing_hpt_and_radix = true;
+ }
+
return r;
}
/* On P9 we use the split_info for coordinating LPCR changes */
lwz r4, KVM_SPLIT_DO_SET(r6)
cmpwi r4, 0
- beq 63f
+ beq 1f
mr r3, r6
bl kvmhv_p9_set_lpcr
nop
+1:
ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
63:
/* Order load of vcpu after load of vcore */
lbz r0, KVM_RADIX(r9)
cmpwi cr7, r0, 0
- /* Clear out SLB if hash */
- bne cr7, 2f
- li r6,0
- slbmte r6,r6
- slbia
- ptesync
-2:
/*
* POWER7/POWER8 host -> guest partition switch code.
* We don't have to lock against concurrent tlbies,
10: cmpdi r4, 0
beq kvmppc_primary_no_guest
kvmppc_got_guest:
-
- /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
- lwz r5,VCPU_SLB_MAX(r4)
- cmpwi r5,0
- beq 9f
- mtctr r5
- addi r6,r4,VCPU_SLB
-1: ld r8,VCPU_SLB_E(r6)
- ld r9,VCPU_SLB_V(r6)
- slbmte r9,r8
- addi r6,r6,VCPU_SLB_SIZE
- bdnz 1b
-9:
/* Increment yield count if they have a VPA */
ld r3, VCPU_VPA(r4)
cmpdi r3, 0
mftb r7
subf r3,r7,r8
mtspr SPRN_DEC,r3
- std r3,VCPU_DEC(r4)
ld r5, VCPU_SPRG0(r4)
ld r6, VCPU_SPRG1(r4)
cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
+ /* For hash guest, clear out and reload the SLB */
+ ld r6, VCPU_KVM(r4)
+ lbz r0, KVM_RADIX(r6)
+ cmpwi r0, 0
+ bne 9f
+ li r6, 0
+ slbmte r6, r6
+ slbia
+ ptesync
+
+ /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */
+ lwz r5,VCPU_SLB_MAX(r4)
+ cmpwi r5,0
+ beq 9f
+ mtctr r5
+ addi r6,r4,VCPU_SLB
+1: ld r8,VCPU_SLB_E(r6)
+ ld r9,VCPU_SLB_V(r6)
+ slbmte r9,r8
+ addi r6,r6,VCPU_SLB_SIZE
+ bdnz 1b
+9:
+
#ifdef CONFIG_KVM_XICS
/* We are entering the guest on that thread, push VCPU to XIVE */
ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
li r9, TM_QW1_OS + TM_WORD2
stwcix r11,r9,r10
li r9, 1
- stw r9, VCPU_XIVE_PUSHED(r4)
+ stb r9, VCPU_XIVE_PUSHED(r4)
eieio
+
+ /*
+ * We clear the irq_pending flag. There is a small chance of a
+ * race vs. the escalation interrupt happening on another
+ * processor setting it again, but the only consequence is to
+ * cause a spurrious wakeup on the next H_CEDE which is not an
+ * issue.
+ */
+ li r0,0
+ stb r0, VCPU_IRQ_PENDING(r4)
+
+ /*
+ * In single escalation mode, if the escalation interrupt is
+ * on, we mask it.
+ */
+ lbz r0, VCPU_XIVE_ESC_ON(r4)
+ cmpwi r0,0
+ beq 1f
+ ld r10, VCPU_XIVE_ESC_RADDR(r4)
+ li r9, XIVE_ESB_SET_PQ_01
+ ldcix r0, r10, r9
+ sync
+
+ /* We have a possible subtle race here: The escalation interrupt might
+ * have fired and be on its way to the host queue while we mask it,
+ * and if we unmask it early enough (re-cede right away), there is
+ * a theorical possibility that it fires again, thus landing in the
+ * target queue more than once which is a big no-no.
+ *
+ * Fortunately, solving this is rather easy. If the above load setting
+ * PQ to 01 returns a previous value where P is set, then we know the
+ * escalation interrupt is somewhere on its way to the host. In that
+ * case we simply don't clear the xive_esc_on flag below. It will be
+ * eventually cleared by the handler for the escalation interrupt.
+ *
+ * Then, when doing a cede, we check that flag again before re-enabling
+ * the escalation interrupt, and if set, we abort the cede.
+ */
+ andi. r0, r0, XIVE_ESB_VAL_P
+ bne- 1f
+
+ /* Now P is 0, we can clear the flag */
+ li r0, 0
+ stb r0, VCPU_XIVE_ESC_ON(r4)
+1:
no_xive:
#endif /* CONFIG_KVM_XICS */
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
#endif
- b guest_exit_cont
+ b guest_bypass
/******************************************************************************
* *
blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
+ /* Save more register state */
+ mfdar r6
+ mfdsisr r7
+ std r6, VCPU_DAR(r9)
+ stw r7, VCPU_DSISR(r9)
+ /* don't overwrite fault_dar/fault_dsisr if HDSI */
+ cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
+ beq mc_cont
+ std r6, VCPU_FAULT_DAR(r9)
+ stw r7, VCPU_FAULT_DSISR(r9)
+
+ /* See if it is a machine check */
+ cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+ beq machine_check_realmode
+mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+ addi r3, r9, VCPU_TB_RMEXIT
+ mr r4, r9
+ bl kvmhv_accumulate_time
+#endif
#ifdef CONFIG_KVM_XICS
/* We are exiting, pull the VP from the XIVE */
- lwz r0, VCPU_XIVE_PUSHED(r9)
+ lbz r0, VCPU_XIVE_PUSHED(r9)
cmpwi cr0, r0, 0
beq 1f
li r7, TM_SPC_PULL_OS_CTX
li r6, TM_QW1_OS
mfmsr r0
- andi. r0, r0, MSR_IR /* in real mode? */
+ andi. r0, r0, MSR_DR /* in real mode? */
beq 2f
ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
cmpldi cr0, r10, 0
/* Fixup some of the state for the next load */
li r10, 0
li r0, 0xff
- stw r10, VCPU_XIVE_PUSHED(r9)
+ stb r10, VCPU_XIVE_PUSHED(r9)
stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
eieio
1:
#endif /* CONFIG_KVM_XICS */
- /* Save more register state */
- mfdar r6
- mfdsisr r7
- std r6, VCPU_DAR(r9)
- stw r7, VCPU_DSISR(r9)
- /* don't overwrite fault_dar/fault_dsisr if HDSI */
- cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
- beq mc_cont
- std r6, VCPU_FAULT_DAR(r9)
- stw r7, VCPU_FAULT_DSISR(r9)
- /* See if it is a machine check */
- cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK
- beq machine_check_realmode
-mc_cont:
-#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
- addi r3, r9, VCPU_TB_RMEXIT
- mr r4, r9
- bl kvmhv_accumulate_time
-#endif
+ /* For hash guest, read the guest SLB and save it away */
+ ld r5, VCPU_KVM(r9)
+ lbz r0, KVM_RADIX(r5)
+ li r5, 0
+ cmpwi r0, 0
+ bne 3f /* for radix, save 0 entries */
+ lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */
+ mtctr r0
+ li r6,0
+ addi r7,r9,VCPU_SLB
+1: slbmfee r8,r6
+ andis. r0,r8,SLB_ESID_V@h
+ beq 2f
+ add r8,r8,r6 /* put index in */
+ slbmfev r3,r6
+ std r8,VCPU_SLB_E(r7)
+ std r3,VCPU_SLB_V(r7)
+ addi r7,r7,VCPU_SLB_SIZE
+ addi r5,r5,1
+2: addi r6,r6,1
+ bdnz 1b
+ /* Finally clear out the SLB */
+ li r0,0
+ slbmte r0,r0
+ slbia
+ ptesync
+3: stw r5,VCPU_SLB_MAX(r9)
+guest_bypass:
mr r3, r12
/* Increment exit count, poke other threads to exit */
bl kvmhv_commence_exit
ori r6,r6,1
mtspr SPRN_CTRLT,r6
4:
- /* Check if we are running hash or radix and store it in cr2 */
- ld r5, VCPU_KVM(r9)
- lbz r0, KVM_RADIX(r5)
- cmpwi cr2,r0,0
-
- /* Read the guest SLB and save it away */
- li r5, 0
- bne cr2, 3f /* for radix, save 0 entries */
- lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */
- mtctr r0
- li r6,0
- addi r7,r9,VCPU_SLB
-1: slbmfee r8,r6
- andis. r0,r8,SLB_ESID_V@h
- beq 2f
- add r8,r8,r6 /* put index in */
- slbmfev r3,r6
- std r8,VCPU_SLB_E(r7)
- std r3,VCPU_SLB_V(r7)
- addi r7,r7,VCPU_SLB_SIZE
- addi r5,r5,1
-2: addi r6,r6,1
- bdnz 1b
-3: stw r5,VCPU_SLB_MAX(r9)
-
/*
* Save the guest PURR/SPURR
*/
ld r5, VCPU_KVM(r9)
lbz r0, KVM_RADIX(r5)
cmpwi cr2, r0, 0
- beq cr2, 3f
+ beq cr2, 4f
/* Radix: Handle the case where the guest used an illegal PID */
LOAD_REG_ADDR(r4, mmu_base_pid)
BEGIN_FTR_SECTION
PPC_INVALIDATE_ERAT
END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
- b 4f
+4:
#endif /* CONFIG_PPC_RADIX_MMU */
- /* Hash: clear out SLB */
-3: li r5,0
- slbmte r5,r5
- slbia
- ptesync
-4:
/*
* POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
/* we've ceded but we want to give control to the host */
kvm_cede_exit:
ld r9, HSTATE_KVM_VCPU(r13)
- b guest_exit_cont
+#ifdef CONFIG_KVM_XICS
+ /* Abort if we still have a pending escalation */
+ lbz r5, VCPU_XIVE_ESC_ON(r9)
+ cmpwi r5, 0
+ beq 1f
+ li r0, 0
+ stb r0, VCPU_CEDED(r9)
+1: /* Enable XIVE escalation */
+ li r5, XIVE_ESB_SET_PQ_00
+ mfmsr r0
+ andi. r0, r0, MSR_DR /* in real mode? */
+ beq 1f
+ ld r10, VCPU_XIVE_ESC_VADDR(r9)
+ cmpdi r10, 0
+ beq 3f
+ ldx r0, r10, r5
+ b 2f
+1: ld r10, VCPU_XIVE_ESC_RADDR(r9)
+ cmpdi r10, 0
+ beq 3f
+ ldcix r0, r10, r5
+2: sync
+ li r0, 1
+ stb r0, VCPU_XIVE_ESC_ON(r9)
+#endif /* CONFIG_KVM_XICS */
+3: b guest_exit_cont
/* Try to handle a machine check in real mode */
machine_check_realmode:
kvm_start_lightweight:
/* Copy registers into shadow vcpu so we can access them in real mode */
- GET_SHADOW_VCPU(r3)
+ mr r3, r4
bl FUNC(kvmppc_copy_to_svcpu)
nop
REST_GPR(4, r1)
stw r12, VCPU_TRAP(r3)
/* Transfer reg values from shadow vcpu back to vcpu struct */
- /* On 64-bit, interrupts are still off at this point */
- GET_SHADOW_VCPU(r4)
bl FUNC(kvmppc_copy_from_svcpu)
nop
#ifdef CONFIG_PPC_BOOK3S_64
struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
if (svcpu->in_use) {
- kvmppc_copy_from_svcpu(vcpu, svcpu);
+ kvmppc_copy_from_svcpu(vcpu);
}
memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
}
/* Copy data needed by real-mode code from vcpu to shadow vcpu */
-void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
- struct kvm_vcpu *vcpu)
+void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu)
{
+ struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+
svcpu->gpr[0] = vcpu->arch.gpr[0];
svcpu->gpr[1] = vcpu->arch.gpr[1];
svcpu->gpr[2] = vcpu->arch.gpr[2];
if (cpu_has_feature(CPU_FTR_ARCH_207S))
vcpu->arch.entry_ic = mfspr(SPRN_IC);
svcpu->in_use = true;
+
+ svcpu_put(svcpu);
}
/* Copy data touched by real-mode code from shadow vcpu back to vcpu */
-void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
- struct kvmppc_book3s_shadow_vcpu *svcpu)
+void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu)
{
- /*
- * vcpu_put would just call us again because in_use hasn't
- * been updated yet.
- */
- preempt_disable();
+ struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
/*
* Maybe we were already preempted and synced the svcpu from
svcpu->in_use = false;
out:
- preempt_enable();
+ svcpu_put(svcpu);
}
static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu *vcpu = data;
- /* We use the existing H_PROD mechanism to wake up the target */
- vcpu->arch.prodded = 1;
+ vcpu->arch.irq_pending = 1;
smp_mb();
if (vcpu->arch.ceded)
kvmppc_fast_vcpu_kick(vcpu);
+ /* Since we have the no-EOI flag, the interrupt is effectively
+ * disabled now. Clearing xive_esc_on means we won't bother
+ * doing so on the next entry.
+ *
+ * This also allows the entry code to know that if a PQ combination
+ * of 10 is observed while xive_esc_on is true, it means the queue
+ * contains an unprocessed escalation interrupt. We don't make use of
+ * that knowledge today but might (see comment in book3s_hv_rmhandler.S)
+ */
+ vcpu->arch.xive_esc_on = false;
+
return IRQ_HANDLED;
}
return -EIO;
}
- /*
- * Future improvement: start with them disabled
- * and handle DD2 and later scheme of merged escalation
- * interrupts
- */
- name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
- vcpu->kvm->arch.lpid, xc->server_num, prio);
+ if (xc->xive->single_escalation)
+ name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
+ vcpu->kvm->arch.lpid, xc->server_num);
+ else
+ name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
+ vcpu->kvm->arch.lpid, xc->server_num, prio);
if (!name) {
pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n",
prio, xc->server_num);
rc = -ENOMEM;
goto error;
}
+
+ pr_devel("Escalation %s irq %d (prio %d)\n", name, xc->esc_virq[prio], prio);
+
rc = request_irq(xc->esc_virq[prio], xive_esc_irq,
IRQF_NO_THREAD, name, vcpu);
if (rc) {
goto error;
}
xc->esc_virq_names[prio] = name;
+
+ /* In single escalation mode, we grab the ESB MMIO of the
+ * interrupt and mask it. Also populate the VCPU v/raddr
+ * of the ESB page for use by asm entry/exit code. Finally
+ * set the XIVE_IRQ_NO_EOI flag which will prevent the
+ * core code from performing an EOI on the escalation
+ * interrupt, thus leaving it effectively masked after
+ * it fires once.
+ */
+ if (xc->xive->single_escalation) {
+ struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]);
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
+ vcpu->arch.xive_esc_raddr = xd->eoi_page;
+ vcpu->arch.xive_esc_vaddr = (__force u64)xd->eoi_mmio;
+ xd->flags |= XIVE_IRQ_NO_EOI;
+ }
+
return 0;
error:
irq_dispose_mapping(xc->esc_virq[prio]);
pr_devel("Provisioning prio... %d\n", prio);
- /* Provision each VCPU and enable escalations */
+ /* Provision each VCPU and enable escalations if needed */
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!vcpu->arch.xive_vcpu)
continue;
rc = xive_provision_queue(vcpu, prio);
- if (rc == 0)
+ if (rc == 0 && !xive->single_escalation)
xive_attach_escalation(vcpu, prio);
if (rc)
return rc;
/* Allocate IPI */
xc->vp_ipi = xive_native_alloc_irq();
if (!xc->vp_ipi) {
+ pr_err("Failed to allocate xive irq for VCPU IPI\n");
r = -EIO;
goto bail;
}
if (r)
goto bail;
+ /*
+ * Enable the VP first as the single escalation mode will
+ * affect escalation interrupts numbering
+ */
+ r = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+ if (r) {
+ pr_err("Failed to enable VP in OPAL, err %d\n", r);
+ goto bail;
+ }
+
/*
* Initialize queues. Initially we set them all for no queueing
* and we enable escalation for queue 0 only which we'll use for
* our mfrr change notifications. If the VCPU is hot-plugged, we
- * do handle provisioning however.
+ * do handle provisioning however based on the existing "map"
+ * of enabled queues.
*/
for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
struct xive_q *q = &xc->queues[i];
+ /* Single escalation, no queue 7 */
+ if (i == 7 && xive->single_escalation)
+ break;
+
/* Is queue already enabled ? Provision it */
if (xive->qmap & (1 << i)) {
r = xive_provision_queue(vcpu, i);
- if (r == 0)
+ if (r == 0 && !xive->single_escalation)
xive_attach_escalation(vcpu, i);
if (r)
goto bail;
if (r)
goto bail;
- /* Enable the VP */
- r = xive_native_enable_vp(xc->vp_id);
- if (r)
- goto bail;
-
/* Route the IPI */
r = xive_native_configure_irq(xc->vp_ipi, xc->vp_id, 0, XICS_IPI);
if (!r)
pr_devel(" val=0x016%llx (server=0x%x, guest_prio=%d)\n",
val, server, guest_prio);
+
/*
* If the source doesn't already have an IPI, allocate
* one and get the corresponding data
if (xive->vp_base == XIVE_INVALID_VP)
ret = -ENOMEM;
+ xive->single_escalation = xive_native_has_single_escalation();
+
if (ret) {
kfree(xive);
return ret;
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ unsigned int i;
if (!xc)
continue;
xc->server_num, xc->cppr, xc->hw_cppr,
xc->mfrr, xc->pending,
xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+ u32 i0, i1, idx;
+
+ if (!q->qpage && !xc->esc_virq[i])
+ continue;
+
+ seq_printf(m, " [q%d]: ", i);
+
+ if (q->qpage) {
+ idx = q->idx;
+ i0 = be32_to_cpup(q->qpage + idx);
+ idx = (idx + 1) & q->msk;
+ i1 = be32_to_cpup(q->qpage + idx);
+ seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1);
+ }
+ if (xc->esc_virq[i]) {
+ struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
+ seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
+ (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
+ (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
+ xc->esc_virq[i], pq, xd->eoi_page);
+ seq_printf(m, "\n");
+ }
+ }
t_rm_h_xirr += xc->stat_rm_h_xirr;
t_rm_h_ipoll += xc->stat_rm_h_ipoll;
u32 q_order;
u32 q_page_order;
+ /* Flags */
+ u8 single_escalation;
};
#define KVMPPC_XIVE_Q_COUNT 8
* is as follow.
*
* Guest request for 0...6 are honored. Guest request for anything
- * higher results in a priority of 7 being applied.
- *
- * However, when XIRR is returned via H_XIRR, 7 is translated to 0xb
- * in order to match AIX expectations
+ * higher results in a priority of 6 being applied.
*
* Similar mapping is done for CPPR values
*/
static inline u8 xive_prio_from_guest(u8 prio)
{
- if (prio == 0xff || prio < 8)
+ if (prio == 0xff || prio < 6)
return prio;
- return 7;
+ return 6;
}
static inline u8 xive_prio_to_guest(u8 prio)
{
- if (prio == 0xff || prio < 7)
- return prio;
- return 0xb;
+ return prio;
}
static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
{
int i;
+ vcpu_load(vcpu);
+
regs->pc = vcpu->arch.pc;
regs->cr = kvmppc_get_cr(vcpu);
regs->ctr = vcpu->arch.ctr;
for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
+ vcpu_put(vcpu);
return 0;
}
{
int i;
+ vcpu_load(vcpu);
+
vcpu->arch.pc = regs->pc;
kvmppc_set_cr(vcpu, regs->cr);
vcpu->arch.ctr = regs->ctr;
for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
+ int ret;
+
+ vcpu_load(vcpu);
+
sregs->pvr = vcpu->arch.pvr;
get_sregs_base(vcpu, sregs);
get_sregs_arch206(vcpu, sregs);
- return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
+ ret = vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs);
+
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
- int ret;
+ int ret = -EINVAL;
+ vcpu_load(vcpu);
if (vcpu->arch.pvr != sregs->pvr)
- return -EINVAL;
+ goto out;
ret = set_sregs_base(vcpu, sregs);
if (ret < 0)
- return ret;
+ goto out;
ret = set_sregs_arch206(vcpu, sregs);
if (ret < 0)
- return ret;
+ goto out;
- return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
+ ret = vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
+
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
{
int r;
+ vcpu_load(vcpu);
r = kvmppc_core_vcpu_translate(vcpu, tr);
+ vcpu_put(vcpu);
return r;
}
{
struct debug_reg *dbg_reg;
int n, b = 0, w = 0;
+ int ret = 0;
+
+ vcpu_load(vcpu);
if (!(dbg->control & KVM_GUESTDBG_ENABLE)) {
vcpu->arch.dbg_reg.dbcr0 = 0;
vcpu->guest_debug = 0;
kvm_guest_protect_msr(vcpu, MSR_DE, false);
- return 0;
+ goto out;
}
kvm_guest_protect_msr(vcpu, MSR_DE, true);
#endif
if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
- return 0;
+ goto out;
+ ret = -EINVAL;
for (n = 0; n < (KVMPPC_BOOKE_IAC_NUM + KVMPPC_BOOKE_DAC_NUM); n++) {
uint64_t addr = dbg->arch.bp[n].addr;
uint32_t type = dbg->arch.bp[n].type;
if (type & ~(KVMPPC_DEBUG_WATCH_READ |
KVMPPC_DEBUG_WATCH_WRITE |
KVMPPC_DEBUG_BREAKPOINT))
- return -EINVAL;
+ goto out;
if (type & KVMPPC_DEBUG_BREAKPOINT) {
/* Setting H/W breakpoint */
if (kvmppc_booke_add_breakpoint(dbg_reg, addr, b++))
- return -EINVAL;
+ goto out;
} else {
/* Setting H/W watchpoint */
if (kvmppc_booke_add_watchpoint(dbg_reg, addr,
type, w++))
- return -EINVAL;
+ goto out;
}
}
- return 0;
+ ret = 0;
+out:
+ vcpu_put(vcpu);
+ return ret;
}
void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
#endif /* CONFIG_VSX */
+#ifdef CONFIG_ALTIVEC
+static bool kvmppc_check_altivec_disabled(struct kvm_vcpu *vcpu)
+{
+ if (!(kvmppc_get_msr(vcpu) & MSR_VEC)) {
+ kvmppc_core_queue_vec_unavail(vcpu);
+ return true;
+ }
+
+ return false;
+}
+#endif /* CONFIG_ALTIVEC */
+
/*
* XXX to do:
* lfiwax, lfiwzx
vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_NONE;
vcpu->arch.mmio_sp64_extend = 0;
vcpu->arch.mmio_sign_extend = 0;
+ vcpu->arch.mmio_vmx_copy_nums = 0;
switch (get_op(inst)) {
case 31:
rs, 4, 1);
break;
#endif /* CONFIG_VSX */
+
+#ifdef CONFIG_ALTIVEC
+ case OP_31_XOP_LVX:
+ if (kvmppc_check_altivec_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.vaddr_accessed &= ~0xFULL;
+ vcpu->arch.paddr_accessed &= ~0xFULL;
+ vcpu->arch.mmio_vmx_copy_nums = 2;
+ emulated = kvmppc_handle_load128_by2x64(run, vcpu,
+ KVM_MMIO_REG_VMX|rt, 1);
+ break;
+
+ case OP_31_XOP_STVX:
+ if (kvmppc_check_altivec_disabled(vcpu))
+ return EMULATE_DONE;
+ vcpu->arch.vaddr_accessed &= ~0xFULL;
+ vcpu->arch.paddr_accessed &= ~0xFULL;
+ vcpu->arch.mmio_vmx_copy_nums = 2;
+ emulated = kvmppc_handle_store128_by2x64(run, vcpu,
+ rs, 1);
+ break;
+#endif /* CONFIG_ALTIVEC */
+
default:
emulated = EMULATE_FAIL;
break;
r = 1;
break;
case KVM_CAP_SPAPR_RESIZE_HPT:
- /* Disable this on POWER9 until code handles new HPTE format */
- r = !!hv_enabled && !cpu_has_feature(CPU_FTR_ARCH_300);
+ r = !!hv_enabled;
break;
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
- vcpu->arch.dec_expires = ~(u64)0;
+ vcpu->arch.dec_expires = get_tb();
#ifdef CONFIG_KVM_EXIT_TIMING
mutex_init(&vcpu->arch.exit_timing_lock);
}
#endif /* CONFIG_VSX */
+#ifdef CONFIG_ALTIVEC
+static inline void kvmppc_set_vmx_dword(struct kvm_vcpu *vcpu,
+ u64 gpr)
+{
+ int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
+ u32 hi, lo;
+ u32 di;
+
+#ifdef __BIG_ENDIAN
+ hi = gpr >> 32;
+ lo = gpr & 0xffffffff;
+#else
+ lo = gpr >> 32;
+ hi = gpr & 0xffffffff;
+#endif
+
+ di = 2 - vcpu->arch.mmio_vmx_copy_nums; /* doubleword index */
+ if (di > 1)
+ return;
+
+ if (vcpu->arch.mmio_host_swabbed)
+ di = 1 - di;
+
+ VCPU_VSX_VR(vcpu, index).u[di * 2] = hi;
+ VCPU_VSX_VR(vcpu, index).u[di * 2 + 1] = lo;
+}
+#endif /* CONFIG_ALTIVEC */
+
#ifdef CONFIG_PPC_FPU
static inline u64 sp_to_dp(u32 fprs)
{
KVMPPC_VSX_COPY_DWORD_LOAD_DUMP)
kvmppc_set_vsr_dword_dump(vcpu, gpr);
break;
+#endif
+#ifdef CONFIG_ALTIVEC
+ case KVM_MMIO_REG_VMX:
+ kvmppc_set_vmx_dword(vcpu, gpr);
+ break;
#endif
default:
BUG();
{
enum emulation_result emulated = EMULATE_DONE;
- /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */
- if ( (vcpu->arch.mmio_vsx_copy_nums > 4) ||
- (vcpu->arch.mmio_vsx_copy_nums < 0) ) {
+ /* Currently, mmio_vsx_copy_nums only allowed to be 4 or less */
+ if (vcpu->arch.mmio_vsx_copy_nums > 4)
return EMULATE_FAIL;
- }
while (vcpu->arch.mmio_vsx_copy_nums) {
emulated = __kvmppc_handle_load(run, vcpu, rt, bytes,
vcpu->arch.io_gpr = rs;
- /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */
- if ( (vcpu->arch.mmio_vsx_copy_nums > 4) ||
- (vcpu->arch.mmio_vsx_copy_nums < 0) ) {
+ /* Currently, mmio_vsx_copy_nums only allowed to be 4 or less */
+ if (vcpu->arch.mmio_vsx_copy_nums > 4)
return EMULATE_FAIL;
- }
while (vcpu->arch.mmio_vsx_copy_nums) {
if (kvmppc_get_vsr_data(vcpu, rs, &val) == -1)
}
#endif /* CONFIG_VSX */
+#ifdef CONFIG_ALTIVEC
+/* handle quadword load access in two halves */
+int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rt, int is_default_endian)
+{
+ enum emulation_result emulated;
+
+ while (vcpu->arch.mmio_vmx_copy_nums) {
+ emulated = __kvmppc_handle_load(run, vcpu, rt, 8,
+ is_default_endian, 0);
+
+ if (emulated != EMULATE_DONE)
+ break;
+
+ vcpu->arch.paddr_accessed += run->mmio.len;
+ vcpu->arch.mmio_vmx_copy_nums--;
+ }
+
+ return emulated;
+}
+
+static inline int kvmppc_get_vmx_data(struct kvm_vcpu *vcpu, int rs, u64 *val)
+{
+ vector128 vrs = VCPU_VSX_VR(vcpu, rs);
+ u32 di;
+ u64 w0, w1;
+
+ di = 2 - vcpu->arch.mmio_vmx_copy_nums; /* doubleword index */
+ if (di > 1)
+ return -1;
+
+ if (vcpu->arch.mmio_host_swabbed)
+ di = 1 - di;
+
+ w0 = vrs.u[di * 2];
+ w1 = vrs.u[di * 2 + 1];
+
+#ifdef __BIG_ENDIAN
+ *val = (w0 << 32) | w1;
+#else
+ *val = (w1 << 32) | w0;
+#endif
+ return 0;
+}
+
+/* handle quadword store in two halves */
+int kvmppc_handle_store128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
+ unsigned int rs, int is_default_endian)
+{
+ u64 val = 0;
+ enum emulation_result emulated = EMULATE_DONE;
+
+ vcpu->arch.io_gpr = rs;
+
+ while (vcpu->arch.mmio_vmx_copy_nums) {
+ if (kvmppc_get_vmx_data(vcpu, rs, &val) == -1)
+ return EMULATE_FAIL;
+
+ emulated = kvmppc_handle_store(run, vcpu, val, 8,
+ is_default_endian);
+ if (emulated != EMULATE_DONE)
+ break;
+
+ vcpu->arch.paddr_accessed += run->mmio.len;
+ vcpu->arch.mmio_vmx_copy_nums--;
+ }
+
+ return emulated;
+}
+
+static int kvmppc_emulate_mmio_vmx_loadstore(struct kvm_vcpu *vcpu,
+ struct kvm_run *run)
+{
+ enum emulation_result emulated = EMULATE_FAIL;
+ int r;
+
+ vcpu->arch.paddr_accessed += run->mmio.len;
+
+ if (!vcpu->mmio_is_write) {
+ emulated = kvmppc_handle_load128_by2x64(run, vcpu,
+ vcpu->arch.io_gpr, 1);
+ } else {
+ emulated = kvmppc_handle_store128_by2x64(run, vcpu,
+ vcpu->arch.io_gpr, 1);
+ }
+
+ switch (emulated) {
+ case EMULATE_DO_MMIO:
+ run->exit_reason = KVM_EXIT_MMIO;
+ r = RESUME_HOST;
+ break;
+ case EMULATE_FAIL:
+ pr_info("KVM: MMIO emulation failed (VMX repeat)\n");
+ run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ r = RESUME_HOST;
+ break;
+ default:
+ r = RESUME_GUEST;
+ break;
+ }
+ return r;
+}
+#endif /* CONFIG_ALTIVEC */
+
int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
{
int r = 0;
{
int r;
+ vcpu_load(vcpu);
+
if (vcpu->mmio_needed) {
vcpu->mmio_needed = 0;
if (!vcpu->mmio_is_write)
r = kvmppc_emulate_mmio_vsx_loadstore(vcpu, run);
if (r == RESUME_HOST) {
vcpu->mmio_needed = 1;
- return r;
+ goto out;
+ }
+ }
+#endif
+#ifdef CONFIG_ALTIVEC
+ if (vcpu->arch.mmio_vmx_copy_nums > 0)
+ vcpu->arch.mmio_vmx_copy_nums--;
+
+ if (vcpu->arch.mmio_vmx_copy_nums > 0) {
+ r = kvmppc_emulate_mmio_vmx_loadstore(vcpu, run);
+ if (r == RESUME_HOST) {
+ vcpu->mmio_needed = 1;
+ goto out;
}
}
#endif
kvm_sigset_deactivate(vcpu);
+out:
+ vcpu_put(vcpu);
return r;
}
return -EINVAL;
}
-long kvm_arch_vcpu_ioctl(struct file *filp,
- unsigned int ioctl, unsigned long arg)
+long kvm_arch_vcpu_async_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
- long r;
- switch (ioctl) {
- case KVM_INTERRUPT: {
+ if (ioctl == KVM_INTERRUPT) {
struct kvm_interrupt irq;
- r = -EFAULT;
if (copy_from_user(&irq, argp, sizeof(irq)))
- goto out;
- r = kvm_vcpu_ioctl_interrupt(vcpu, &irq);
- goto out;
+ return -EFAULT;
+ return kvm_vcpu_ioctl_interrupt(vcpu, &irq);
}
+ return -ENOIOCTLCMD;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ long r;
+
+ vcpu_load(vcpu);
+ switch (ioctl) {
case KVM_ENABLE_CAP:
{
struct kvm_enable_cap cap;
}
out:
+ vcpu_put(vcpu);
return r;
}
int i;
u64 min, max, sum, sum_quad;
- seq_printf(m, "%s", "type count min max sum sum_squared\n");
-
+ seq_puts(m, "type count min max sum sum_squared\n");
for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) {
but first mark any pending interrupts as done so
we don't get woken up unnecessarily */
- if (events & (POLLIN | POLLRDNORM)) {
+ if (events & (EPOLLIN | EPOLLRDNORM)) {
if (stat & 0xff0000)
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
else {
ctx->csa.priv1.int_stat_class2_RW &=
~CLASS2_MAILBOX_INTR;
CLASS2_ENABLE_MAILBOX_INTR;
}
}
- if (events & (POLLOUT | POLLWRNORM)) {
+ if (events & (EPOLLOUT | EPOLLWRNORM)) {
if (stat & 0x00ff00)
- ret = POLLOUT | POLLWRNORM;
+ ret = EPOLLOUT | EPOLLWRNORM;
else {
ctx->csa.priv1.int_stat_class2_RW &=
~CLASS2_MAILBOX_THRESHOLD_INTR;
* that poll should not sleep. Will be fixed later.
*/
mutex_lock(&ctx->state_mutex);
- mask = ctx->ops->mbox_stat_poll(ctx, POLLIN | POLLRDNORM);
+ mask = ctx->ops->mbox_stat_poll(ctx, EPOLLIN | EPOLLRDNORM);
spu_release(ctx);
return mask;
* that poll should not sleep. Will be fixed later.
*/
mutex_lock(&ctx->state_mutex);
- mask = ctx->ops->mbox_stat_poll(ctx, POLLOUT | POLLWRNORM);
+ mask = ctx->ops->mbox_stat_poll(ctx, EPOLLOUT | EPOLLWRNORM);
spu_release(ctx);
return mask;
mask = 0;
if (free_elements & 0xffff)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (tagstatus & ctx->tagwait)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
pr_debug("%s: free %d tagstatus %d tagwait %d\n", __func__,
free_elements, tagstatus, ctx->tagwait);
return rc;
if (spufs_switch_log_used(ctx) > 0)
- mask |= POLLIN;
+ mask |= EPOLLIN;
spu_release(ctx);
but first mark any pending interrupts as done so
we don't get woken up unnecessarily */
- if (events & (POLLIN | POLLRDNORM)) {
+ if (events & (EPOLLIN | EPOLLRDNORM)) {
if (stat & 0xff0000)
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
else {
spu_int_stat_clear(spu, 2, CLASS2_MAILBOX_INTR);
spu_int_mask_or(spu, 2, CLASS2_ENABLE_MAILBOX_INTR);
}
}
- if (events & (POLLOUT | POLLWRNORM)) {
+ if (events & (EPOLLOUT | EPOLLWRNORM)) {
if (stat & 0x00ff00)
- ret = POLLOUT | POLLWRNORM;
+ ret = EPOLLOUT | EPOLLWRNORM;
else {
spu_int_stat_clear(spu, 2,
CLASS2_MAILBOX_THRESHOLD_INTR);
poll_wait(file, &opal_prd_msg_wait, wait);
if (!opal_msg_queue_empty())
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
static u32 xive_queue_shift;
static u32 xive_pool_vps = XIVE_INVALID_VP;
static struct kmem_cache *xive_provision_cache;
+static bool xive_has_single_esc;
int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
{
break;
}
+ /* Do we support single escalation */
+ if (of_get_property(np, "single-escalation-support", NULL) != NULL)
+ xive_has_single_esc = true;
+
/* Configure Thread Management areas for KVM */
for_each_possible_cpu(cpu)
kvmppc_set_xive_tima(cpu, r.start, tima);
}
EXPORT_SYMBOL_GPL(xive_native_free_vp_block);
-int xive_native_enable_vp(u32 vp_id)
+int xive_native_enable_vp(u32 vp_id, bool single_escalation)
{
s64 rc;
+ u64 flags = OPAL_XIVE_VP_ENABLED;
+ if (single_escalation)
+ flags |= OPAL_XIVE_VP_SINGLE_ESCALATION;
for (;;) {
- rc = opal_xive_set_vp_info(vp_id, OPAL_XIVE_VP_ENABLED, 0);
+ rc = opal_xive_set_vp_info(vp_id, flags, 0);
if (rc != OPAL_BUSY)
break;
msleep(1);
return 0;
}
EXPORT_SYMBOL_GPL(xive_native_get_vp_info);
+
+bool xive_native_has_single_escalation(void)
+{
+ return xive_has_single_esc;
+}
+EXPORT_SYMBOL_GPL(xive_native_has_single_escalation);
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
- select ARCH_WANTS_PROT_NUMA_PROT_NONE
select ARCH_WANTS_UBSAN_NO_NULL
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT
If unsure, say Y.
+config KERNEL_NOBP
+ def_bool n
+ prompt "Enable modified branch prediction for the kernel by default"
+ help
+ If this option is selected the kernel will switch to a modified
+ branch prediction mode if the firmware interface is available.
+ The modified branch prediction mode improves the behaviour in
+ regard to speculative execution.
+
+ With the option enabled the kernel parameter "nobp=0" or "nospec"
+ can be used to run the kernel in the normal branch prediction mode.
+
+ With the option disabled the modified branch prediction mode is
+ enabled with the "nobp=1" kernel parameter.
+
+ If unsure, say N.
+
+config EXPOLINE
+ def_bool n
+ prompt "Avoid speculative indirect branches in the kernel"
+ help
+ Compile the kernel with the expoline compiler options to guard
+ against kernel-to-user data leaks by avoiding speculative indirect
+ branches.
+ Requires a compiler with -mindirect-branch=thunk support for full
+ protection. The kernel may run slower.
+
+ If unsure, say N.
+
+choice
+ prompt "Expoline default"
+ depends on EXPOLINE
+ default EXPOLINE_FULL
+
+config EXPOLINE_OFF
+ bool "spectre_v2=off"
+
+config EXPOLINE_MEDIUM
+ bool "spectre_v2=auto"
+
+config EXPOLINE_FULL
+ bool "spectre_v2=on"
+
+endchoice
+
endmenu
menu "Memory setup"
cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
endif
+ifdef CONFIG_EXPOLINE
+ ifeq ($(call cc-option-yn,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),y)
+ CC_FLAGS_EXPOLINE := -mindirect-branch=thunk
+ CC_FLAGS_EXPOLINE += -mfunction-return=thunk
+ CC_FLAGS_EXPOLINE += -mindirect-branch-table
+ export CC_FLAGS_EXPOLINE
+ cflags-y += $(CC_FLAGS_EXPOLINE)
+ endif
+endif
+
ifdef CONFIG_FUNCTION_TRACER
# make use of hotpatch feature if the compiler supports it
cc_hotpatch := -mhotpatch=0,3
#define __smp_mb__before_atomic() barrier()
#define __smp_mb__after_atomic() barrier()
+/**
+ * array_index_mask_nospec - generate a mask for array_idx() that is
+ * ~0UL when the bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ */
+#define array_index_mask_nospec array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+ unsigned long size)
+{
+ unsigned long mask;
+
+ if (__builtin_constant_p(size) && size > 0) {
+ asm(" clgr %2,%1\n"
+ " slbgr %0,%0\n"
+ :"=d" (mask) : "d" (size-1), "d" (index) :"cc");
+ return mask;
+ }
+ asm(" clgr %1,%2\n"
+ " slbgr %0,%0\n"
+ :"=d" (mask) : "d" (size), "d" (index) :"cc");
+ return ~mask;
+}
+
#include <asm-generic/barrier.h>
#endif /* __ASM_BARRIER_H */
return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
+static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr)
+{
+ return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
+}
+
static inline void __set_bit_inv(unsigned long nr, volatile unsigned long *ptr)
{
return __set_bit(nr ^ (BITS_PER_LONG - 1), ptr);
u32 aif_tdd : 1; /* bit 56 */
u32 : 1;
u32 qebsm : 1; /* bit 58 */
- u32 : 8;
+ u32 : 2;
+ u32 aiv : 1; /* bit 61 */
+ u32 : 5;
u32 aif_osa : 1; /* bit 67 */
u32 : 12;
u32 eadm_rf : 1; /* bit 80 */
#include <linux/types.h>
#include <linux/device.h>
-#include <linux/blkdev.h>
+#include <linux/blk_types.h>
struct arqb {
u64 data;
#define MAX_FACILITY_BIT (sizeof(((struct lowcore *)0)->stfle_fac_list) * 8)
+static inline void __set_facility(unsigned long nr, void *facilities)
+{
+ unsigned char *ptr = (unsigned char *) facilities;
+
+ if (nr >= MAX_FACILITY_BIT)
+ return;
+ ptr[nr >> 3] |= 0x80 >> (nr & 7);
+}
+
+static inline void __clear_facility(unsigned long nr, void *facilities)
+{
+ unsigned char *ptr = (unsigned char *) facilities;
+
+ if (nr >= MAX_FACILITY_BIT)
+ return;
+ ptr[nr >> 3] &= ~(0x80 >> (nr & 7));
+}
+
static inline int __test_facility(unsigned long nr, void *facilities)
{
unsigned char *ptr;
/*
* definition for kernel virtual machines on s390
*
- * Copyright IBM Corp. 2008, 2009
+ * Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
*/
#define ECA_IB 0x40000000
#define ECA_SIGPI 0x10000000
#define ECA_MVPGI 0x01000000
+#define ECA_AIV 0x00200000
#define ECA_VX 0x00020000
#define ECA_PROTEXCI 0x00002000
#define ECA_SII 0x00000001
__u8 epdx; /* 0x0069 */
__u8 reserved6a[2]; /* 0x006a */
__u32 todpr; /* 0x006c */
- __u8 reserved70[16]; /* 0x0070 */
+#define GISA_FORMAT1 0x00000001
+ __u32 gd; /* 0x0070 */
+ __u8 reserved74[12]; /* 0x0074 */
__u64 mso; /* 0x0080 */
__u64 msl; /* 0x0088 */
psw_t gpsw; /* 0x0090 */
u64 deliver_program_int;
u64 deliver_io_int;
u64 exit_wait_state;
+ u64 instruction_epsw;
+ u64 instruction_gs;
+ u64 instruction_io_other;
+ u64 instruction_lpsw;
+ u64 instruction_lpswe;
u64 instruction_pfmf;
+ u64 instruction_ptff;
+ u64 instruction_sck;
+ u64 instruction_sckpf;
u64 instruction_stidp;
u64 instruction_spx;
u64 instruction_stpx;
u64 instruction_stap;
- u64 instruction_storage_key;
+ u64 instruction_iske;
+ u64 instruction_ri;
+ u64 instruction_rrbe;
+ u64 instruction_sske;
u64 instruction_ipte_interlock;
- u64 instruction_stsch;
- u64 instruction_chsc;
u64 instruction_stsi;
u64 instruction_stfl;
+ u64 instruction_tb;
+ u64 instruction_tpi;
u64 instruction_tprot;
+ u64 instruction_tsch;
u64 instruction_sie;
u64 instruction_essa;
u64 instruction_sthyi;
u64 diagnose_258;
u64 diagnose_308;
u64 diagnose_500;
+ u64 diagnose_other;
};
#define PGM_OPERATION 0x01
#define PGM_PER 0x80
#define PGM_CRYPTO_OPERATION 0x119
-/* irq types in order of priority */
+/* irq types in ascend order of priorities */
enum irq_types {
- IRQ_PEND_MCHK_EX = 0,
- IRQ_PEND_SVC,
- IRQ_PEND_PROG,
- IRQ_PEND_MCHK_REP,
- IRQ_PEND_EXT_IRQ_KEY,
- IRQ_PEND_EXT_MALFUNC,
- IRQ_PEND_EXT_EMERGENCY,
- IRQ_PEND_EXT_EXTERNAL,
- IRQ_PEND_EXT_CLOCK_COMP,
- IRQ_PEND_EXT_CPU_TIMER,
- IRQ_PEND_EXT_TIMING,
- IRQ_PEND_EXT_SERVICE,
- IRQ_PEND_EXT_HOST,
- IRQ_PEND_PFAULT_INIT,
- IRQ_PEND_PFAULT_DONE,
- IRQ_PEND_VIRTIO,
- IRQ_PEND_IO_ISC_0,
- IRQ_PEND_IO_ISC_1,
- IRQ_PEND_IO_ISC_2,
- IRQ_PEND_IO_ISC_3,
- IRQ_PEND_IO_ISC_4,
- IRQ_PEND_IO_ISC_5,
- IRQ_PEND_IO_ISC_6,
- IRQ_PEND_IO_ISC_7,
- IRQ_PEND_SIGP_STOP,
+ IRQ_PEND_SET_PREFIX = 0,
IRQ_PEND_RESTART,
- IRQ_PEND_SET_PREFIX,
+ IRQ_PEND_SIGP_STOP,
+ IRQ_PEND_IO_ISC_7,
+ IRQ_PEND_IO_ISC_6,
+ IRQ_PEND_IO_ISC_5,
+ IRQ_PEND_IO_ISC_4,
+ IRQ_PEND_IO_ISC_3,
+ IRQ_PEND_IO_ISC_2,
+ IRQ_PEND_IO_ISC_1,
+ IRQ_PEND_IO_ISC_0,
+ IRQ_PEND_VIRTIO,
+ IRQ_PEND_PFAULT_DONE,
+ IRQ_PEND_PFAULT_INIT,
+ IRQ_PEND_EXT_HOST,
+ IRQ_PEND_EXT_SERVICE,
+ IRQ_PEND_EXT_TIMING,
+ IRQ_PEND_EXT_CPU_TIMER,
+ IRQ_PEND_EXT_CLOCK_COMP,
+ IRQ_PEND_EXT_EXTERNAL,
+ IRQ_PEND_EXT_EMERGENCY,
+ IRQ_PEND_EXT_MALFUNC,
+ IRQ_PEND_EXT_IRQ_KEY,
+ IRQ_PEND_MCHK_REP,
+ IRQ_PEND_PROG,
+ IRQ_PEND_SVC,
+ IRQ_PEND_MCHK_EX,
IRQ_PEND_COUNT
};
struct kvm_s390_local_interrupt {
spinlock_t lock;
- struct kvm_s390_float_interrupt *float_int;
- struct swait_queue_head *wq;
- atomic_t *cpuflags;
DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
struct kvm_s390_irq_payload irq;
unsigned long pending_irqs;
struct kvm_s390_apcb1 apcb1; /* 0x0080 */
};
+struct kvm_s390_gisa {
+ union {
+ struct { /* common to all formats */
+ u32 next_alert;
+ u8 ipm;
+ u8 reserved01[2];
+ u8 iam;
+ };
+ struct { /* format 0 */
+ u32 next_alert;
+ u8 ipm;
+ u8 reserved01;
+ u8 : 6;
+ u8 g : 1;
+ u8 c : 1;
+ u8 iam;
+ u8 reserved02[4];
+ u32 airq_count;
+ } g0;
+ struct { /* format 1 */
+ u32 next_alert;
+ u8 ipm;
+ u8 simm;
+ u8 nimm;
+ u8 iam;
+ u8 aism[8];
+ u8 : 6;
+ u8 g : 1;
+ u8 c : 1;
+ u8 reserved03[11];
+ u32 airq_count;
+ } g1;
+ };
+};
+
/*
- * sie_page2 has to be allocated as DMA because fac_list and crycb need
- * 31bit addresses in the sie control block.
+ * sie_page2 has to be allocated as DMA because fac_list, crycb and
+ * gisa need 31bit addresses in the sie control block.
*/
struct sie_page2 {
__u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */
struct kvm_s390_crypto_cb crycb; /* 0x0800 */
- u8 reserved900[0x1000 - 0x900]; /* 0x0900 */
+ struct kvm_s390_gisa gisa; /* 0x0900 */
+ u8 reserved920[0x1000 - 0x920]; /* 0x0920 */
};
struct kvm_s390_vsie {
struct kvm_s390_migration_state *migration_state;
/* subset of available cpu features enabled by user space */
DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
+ struct kvm_s390_gisa *gisa;
};
#define KVM_HVA_ERR_BAD (-1UL)
__u64 vdso_per_cpu_data; /* 0x03b8 */
__u64 machine_flags; /* 0x03c0 */
__u64 gmap; /* 0x03c8 */
- __u8 pad_0x03d0[0x0e00-0x03d0]; /* 0x03d0 */
+ __u8 pad_0x03d0[0x0400-0x03d0]; /* 0x03d0 */
+
+ /* br %r1 trampoline */
+ __u16 br_r1_trampoline; /* 0x0400 */
+ __u8 pad_0x0402[0x0e00-0x0402]; /* 0x0402 */
/*
* 0xe00 contains the address of the IPL Parameter Information
__u8 pad_0x0e20[0x0f00-0x0e20]; /* 0x0e20 */
/* Extended facility list */
- __u64 stfle_fac_list[32]; /* 0x0f00 */
+ __u64 stfle_fac_list[16]; /* 0x0f00 */
+ __u64 alt_stfle_fac_list[16]; /* 0x0f80 */
__u8 pad_0x1000[0x11b0-0x1000]; /* 0x1000 */
/* Pointer to the machine check extended save area */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_EXPOLINE_H
+#define _ASM_S390_EXPOLINE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+extern int nospec_call_disable;
+extern int nospec_return_disable;
+
+void nospec_init_branches(void);
+void nospec_call_revert(s32 *start, s32 *end);
+void nospec_return_revert(s32 *start, s32 *end);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_S390_EXPOLINE_H */
extern const struct seq_operations cpuinfo_op;
extern int sysctl_ieee_emulation_warnings;
extern void execve_tail(void);
+extern void __bpon(void);
/*
* User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.
memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \
} while (0)
+extern int s390_isolate_bp(void);
+extern int s390_isolate_bp_guest(void);
+
#endif /* __ASSEMBLY__ */
#endif /* __ASM_S390_PROCESSOR_H */
#ifndef _RUNTIME_INSTR_H
#define _RUNTIME_INSTR_H
-#define S390_RUNTIME_INSTR_START 0x1
-#define S390_RUNTIME_INSTR_STOP 0x2
-
-struct runtime_instr_cb {
- __u64 rca;
- __u64 roa;
- __u64 rla;
-
- __u32 v : 1;
- __u32 s : 1;
- __u32 k : 1;
- __u32 h : 1;
- __u32 a : 1;
- __u32 reserved1 : 3;
- __u32 ps : 1;
- __u32 qs : 1;
- __u32 pc : 1;
- __u32 qc : 1;
- __u32 reserved2 : 1;
- __u32 g : 1;
- __u32 u : 1;
- __u32 l : 1;
- __u32 key : 4;
- __u32 reserved3 : 8;
- __u32 t : 1;
- __u32 rgs : 3;
-
- __u32 m : 4;
- __u32 n : 1;
- __u32 mae : 1;
- __u32 reserved4 : 2;
- __u32 c : 1;
- __u32 r : 1;
- __u32 b : 1;
- __u32 j : 1;
- __u32 e : 1;
- __u32 x : 1;
- __u32 reserved5 : 2;
- __u32 bpxn : 1;
- __u32 bpxt : 1;
- __u32 bpti : 1;
- __u32 bpni : 1;
- __u32 reserved6 : 2;
-
- __u32 d : 1;
- __u32 f : 1;
- __u32 ic : 4;
- __u32 dc : 4;
-
- __u64 reserved7;
- __u64 sf;
- __u64 rsic;
- __u64 reserved8;
-} __packed __aligned(8);
+#include <uapi/asm/runtime_instr.h>
extern struct runtime_instr_cb runtime_instr_empty_cb;
-static inline void load_runtime_instr_cb(struct runtime_instr_cb *cb)
-{
- asm volatile(".insn rsy,0xeb0000000060,0,0,%0" /* LRIC */
- : : "Q" (*cb));
-}
-
-static inline void store_runtime_instr_cb(struct runtime_instr_cb *cb)
-{
- asm volatile(".insn rsy,0xeb0000000061,0,0,%0" /* STRIC */
- : "=Q" (*cb) : : "cc");
-}
-
static inline void save_ri_cb(struct runtime_instr_cb *cb_prev)
{
if (cb_prev)
unsigned char has_ibs : 1;
unsigned char has_skey : 1;
unsigned char has_kss : 1;
+ unsigned char has_gisaf : 1;
unsigned int ibc;
unsigned int mtid;
unsigned int mtid_cp;
unsigned char :8;
unsigned char ccr;
unsigned char cai;
- char reserved_0[28];
+ char reserved_0[20];
+ unsigned long lic;
char manufacturer[16];
char type[4];
char reserved_1[12];
#define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */
#define TIF_PATCH_PENDING 5 /* pending live patching update */
#define TIF_PGSTE 6 /* New mm's will use 4K page tables */
+#define TIF_ISOLATE_BP 8 /* Run process with isolated BP */
+#define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */
#define TIF_31BIT 16 /* 32bit process */
#define TIF_MEMDIE 17 /* is terminating due to OOM killer */
#define _TIF_UPROBE _BITUL(TIF_UPROBE)
#define _TIF_GUARDED_STORAGE _BITUL(TIF_GUARDED_STORAGE)
#define _TIF_PATCH_PENDING _BITUL(TIF_PATCH_PENDING)
+#define _TIF_ISOLATE_BP _BITUL(TIF_ISOLATE_BP)
+#define _TIF_ISOLATE_BP_GUEST _BITUL(TIF_ISOLATE_BP_GUEST)
#define _TIF_31BIT _BITUL(TIF_31BIT)
#define _TIF_SINGLE_STEP _BITUL(TIF_SINGLE_STEP)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _S390_UAPI_RUNTIME_INSTR_H
+#define _S390_UAPI_RUNTIME_INSTR_H
+
+#include <linux/types.h>
+
+#define S390_RUNTIME_INSTR_START 0x1
+#define S390_RUNTIME_INSTR_STOP 0x2
+
+struct runtime_instr_cb {
+ __u64 rca;
+ __u64 roa;
+ __u64 rla;
+
+ __u32 v : 1;
+ __u32 s : 1;
+ __u32 k : 1;
+ __u32 h : 1;
+ __u32 a : 1;
+ __u32 reserved1 : 3;
+ __u32 ps : 1;
+ __u32 qs : 1;
+ __u32 pc : 1;
+ __u32 qc : 1;
+ __u32 reserved2 : 1;
+ __u32 g : 1;
+ __u32 u : 1;
+ __u32 l : 1;
+ __u32 key : 4;
+ __u32 reserved3 : 8;
+ __u32 t : 1;
+ __u32 rgs : 3;
+
+ __u32 m : 4;
+ __u32 n : 1;
+ __u32 mae : 1;
+ __u32 reserved4 : 2;
+ __u32 c : 1;
+ __u32 r : 1;
+ __u32 b : 1;
+ __u32 j : 1;
+ __u32 e : 1;
+ __u32 x : 1;
+ __u32 reserved5 : 2;
+ __u32 bpxn : 1;
+ __u32 bpxt : 1;
+ __u32 bpti : 1;
+ __u32 bpni : 1;
+ __u32 reserved6 : 2;
+
+ __u32 d : 1;
+ __u32 f : 1;
+ __u32 ic : 4;
+ __u32 dc : 4;
+
+ __u64 reserved7;
+ __u64 sf;
+ __u64 rsic;
+ __u64 reserved8;
+} __packed __aligned(8);
+
+static inline void load_runtime_instr_cb(struct runtime_instr_cb *cb)
+{
+ asm volatile(".insn rsy,0xeb0000000060,0,0,%0" /* LRIC */
+ : : "Q" (*cb));
+}
+
+static inline void store_runtime_instr_cb(struct runtime_instr_cb *cb)
+{
+ asm volatile(".insn rsy,0xeb0000000061,0,0,%0" /* STRIC */
+ : "=Q" (*cb) : : "cc");
+}
+
+#endif /* _S390_UAPI_RUNTIME_INSTR_H */
#
ifneq ($(CC_FLAGS_MARCH),-march=z900)
CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH)
+CFLAGS_REMOVE_als.o += $(CC_FLAGS_EXPOLINE)
CFLAGS_als.o += -march=z900
AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH)
AFLAGS_head.o += -march=z900
extra-y += head.o head64.o vmlinux.lds
+obj-$(CONFIG_EXPOLINE) += nospec-branch.o
+CFLAGS_REMOVE_expoline.o += $(CC_FLAGS_EXPOLINE)
+
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_SCHED_TOPOLOGY) += topology.o
early_param("noaltinstr", disable_alternative_instructions);
+static int __init nobp_setup_early(char *str)
+{
+ bool enabled;
+ int rc;
+
+ rc = kstrtobool(str, &enabled);
+ if (rc)
+ return rc;
+ if (enabled && test_facility(82))
+ __set_facility(82, S390_lowcore.alt_stfle_fac_list);
+ else
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+ return 0;
+}
+early_param("nobp", nobp_setup_early);
+
+static int __init nospec_setup_early(char *str)
+{
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+ return 0;
+}
+early_param("nospec", nospec_setup_early);
+
struct brcl_insn {
u16 opc;
s32 disp;
instr = (u8 *)&a->instr_offset + a->instr_offset;
replacement = (u8 *)&a->repl_offset + a->repl_offset;
- if (!test_facility(a->facility))
+ if (!__test_facility(a->facility,
+ S390_lowcore.alt_stfle_fac_list))
continue;
if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) {
{
stfle(S390_lowcore.stfle_fac_list,
ARRAY_SIZE(S390_lowcore.stfle_fac_list));
+ memcpy(S390_lowcore.alt_stfle_fac_list,
+ S390_lowcore.stfle_fac_list,
+ sizeof(S390_lowcore.alt_stfle_fac_list));
+ if (!IS_ENABLED(CONFIG_KERNEL_NOBP))
+ __clear_facility(82, S390_lowcore.alt_stfle_fac_list);
}
static __init void detect_diag9c(void)
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 3f
1: UPDATE_VTIME %r14,%r15,\timer
+ BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
2: lg %r15,__LC_ASYNC_STACK # load async stack
3: la %r11,STACK_FRAME_OVERHEAD(%r15)
.endm
tm off+\addr, \mask
.endm
+ .macro BPOFF
+ .pushsection .altinstr_replacement, "ax"
+660: .long 0xb2e8c000
+ .popsection
+661: .long 0x47000000
+ .pushsection .altinstructions, "a"
+ .long 661b - .
+ .long 660b - .
+ .word 82
+ .byte 4
+ .byte 4
+ .popsection
+ .endm
+
+ .macro BPON
+ .pushsection .altinstr_replacement, "ax"
+662: .long 0xb2e8d000
+ .popsection
+663: .long 0x47000000
+ .pushsection .altinstructions, "a"
+ .long 663b - .
+ .long 662b - .
+ .word 82
+ .byte 4
+ .byte 4
+ .popsection
+ .endm
+
+ .macro BPENTER tif_ptr,tif_mask
+ .pushsection .altinstr_replacement, "ax"
+662: .word 0xc004, 0x0000, 0x0000 # 6 byte nop
+ .word 0xc004, 0x0000, 0x0000 # 6 byte nop
+ .popsection
+664: TSTMSK \tif_ptr,\tif_mask
+ jz . + 8
+ .long 0xb2e8d000
+ .pushsection .altinstructions, "a"
+ .long 664b - .
+ .long 662b - .
+ .word 82
+ .byte 12
+ .byte 12
+ .popsection
+ .endm
+
+ .macro BPEXIT tif_ptr,tif_mask
+ TSTMSK \tif_ptr,\tif_mask
+ .pushsection .altinstr_replacement, "ax"
+662: jnz . + 8
+ .long 0xb2e8d000
+ .popsection
+664: jz . + 8
+ .long 0xb2e8c000
+ .pushsection .altinstructions, "a"
+ .long 664b - .
+ .long 662b - .
+ .word 82
+ .byte 8
+ .byte 8
+ .popsection
+ .endm
+
+#ifdef CONFIG_EXPOLINE
+
+ .macro GEN_BR_THUNK name,reg,tmp
+ .section .text.\name,"axG",@progbits,\name,comdat
+ .globl \name
+ .hidden \name
+ .type \name,@function
+\name:
+ .cfi_startproc
+#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
+ exrl 0,0f
+#else
+ larl \tmp,0f
+ ex 0,0(\tmp)
+#endif
+ j .
+0: br \reg
+ .cfi_endproc
+ .endm
+
+ GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
+ GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1
+ GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11
+
+ .macro BASR_R14_R9
+0: brasl %r14,__s390x_indirect_jump_r1use_r9
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 0b-.
+ .popsection
+ .endm
+
+ .macro BR_R1USE_R14
+0: jg __s390x_indirect_jump_r1use_r14
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 0b-.
+ .popsection
+ .endm
+
+ .macro BR_R11USE_R14
+0: jg __s390x_indirect_jump_r11use_r14
+ .pushsection .s390_indirect_branches,"a",@progbits
+ .long 0b-.
+ .popsection
+ .endm
+
+#else /* CONFIG_EXPOLINE */
+
+ .macro BASR_R14_R9
+ basr %r14,%r9
+ .endm
+
+ .macro BR_R1USE_R14
+ br %r14
+ .endm
+
+ .macro BR_R11USE_R14
+ br %r14
+ .endm
+
+#endif /* CONFIG_EXPOLINE */
+
+
.section .kprobes.text, "ax"
.Ldummy:
/*
*/
nop 0
+ENTRY(__bpon)
+ .globl __bpon
+ BPON
+ BR_R1USE_R14
+
/*
* Scheduler resume function, called by switch_to
* gpr2 = (task_struct *) prev
mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next
lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPP
- bzr %r14
+ jz 0f
.insn s,0xb2800000,__LC_LPP # set program parameter
- br %r14
+0: BR_R1USE_R14
.L__critical_start:
*/
ENTRY(sie64a)
stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers
+ lg %r12,__LC_CURRENT
stg %r2,__SF_EMPTY(%r15) # save control block pointer
stg %r3,__SF_EMPTY+8(%r15) # save guest register save area
xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # reason code = 0
+ mvc __SF_EMPTY+24(8,%r15),__TI_flags(%r12) # copy thread flags
TSTMSK __LC_CPU_FLAGS,_CIF_FPU # load guest fp/vx registers ?
jno .Lsie_load_guest_gprs
brasl %r14,load_fpu_regs # load guest fp/vx regs
jnz .Lsie_skip
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lsie_skip # exit if fp/vx regs changed
+ BPEXIT __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
.Lsie_entry:
sie 0(%r14)
+.Lsie_exit:
+ BPOFF
+ BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
.Lsie_skip:
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
sie_exit:
lg %r14,__SF_EMPTY+8(%r15) # load guest register save area
stmg %r0,%r13,0(%r14) # save guest gprs 0-13
+ xgr %r0,%r0 # clear guest registers to
+ xgr %r1,%r1 # prevent speculative use
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers
lg %r2,__SF_EMPTY+16(%r15) # return exit reason code
- br %r14
+ BR_R1USE_R14
.Lsie_fault:
lghi %r14,-EFAULT
stg %r14,__SF_EMPTY+16(%r15) # set exit reason code
stpt __LC_SYNC_ENTER_TIMER
.Lsysc_stmg:
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
+ BPOFF
lg %r12,__LC_CURRENT
lghi %r13,__TASK_thread
lghi %r14,_PIF_SYSCALL
la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
.Lsysc_vtime:
UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
+ BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled register to prevent speculative use
+ xgr %r0,%r0
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW
mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC
lgf %r9,0(%r8,%r10) # get system call add.
TSTMSK __TI_flags(%r12),_TIF_TRACE
jnz .Lsysc_tracesys
- basr %r14,%r9 # call sys_xxxx
+ BASR_R14_R9 # call sys_xxxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_return:
jnz .Lsysc_work # check for work
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lsysc_work
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
.Lsysc_restore:
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
lmg %r3,%r7,__PT_R3(%r11)
stg %r7,STACK_FRAME_OVERHEAD(%r15)
lg %r2,__PT_ORIG_GPR2(%r11)
- basr %r14,%r9 # call sys_xxx
+ BASR_R14_R9 # call sys_xxx
stg %r2,__PT_R2(%r11) # store return value
.Lsysc_tracenogo:
TSTMSK __TI_flags(%r12),_TIF_TRACE
lmg %r9,%r10,__PT_R9(%r11) # load gprs
ENTRY(kernel_thread_starter)
la %r2,0(%r10)
- basr %r14,%r9
+ BASR_R14_R9
j .Lsysc_tracenogo
/*
ENTRY(pgm_check_handler)
stpt __LC_SYNC_ENTER_TIMER
+ BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
lg %r10,__LC_LAST_BREAK
lg %r12,__LC_CURRENT
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 4f
2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+ BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lg %r15,__LC_KERNEL_STACK
lgr %r14,%r12
aghi %r14,__TASK_thread # pointer to thread_struct
4: lgr %r13,%r11
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC
nill %r10,0x007f
sll %r10,2
je .Lpgm_return
- lgf %r1,0(%r10,%r1) # load address of handler routine
+ lgf %r9,0(%r10,%r1) # load address of handler routine
lgr %r2,%r11 # pass pointer to pt_regs
- basr %r14,%r1 # branch to interrupt-handler
+ BASR_R14_R9 # branch to interrupt-handler
.Lpgm_return:
LOCKDEP_SYS_EXIT
tm __PT_PSW+1(%r11),0x01 # returning to user ?
ENTRY(io_int_handler)
STCK __LC_INT_CLOCK
stpt __LC_ASYNC_ENTER_TIMER
+ BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_ASYNC
lg %r12,__LC_CURRENT
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_IO_OLD_PSW
SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
+ xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
lg %r14,__LC_VDSO_PER_CPU
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
+ tm __PT_PSW+1(%r11),0x01 # returning to user ?
+ jno .Lio_exit_kernel
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
.Lio_exit_timer:
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
+.Lio_exit_kernel:
lmg %r11,%r15,__PT_R11(%r11)
lpswe __LC_RETURN_PSW
.Lio_done:
ENTRY(ext_int_handler)
STCK __LC_INT_CLOCK
stpt __LC_ASYNC_ENTER_TIMER
+ BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_ASYNC
lg %r12,__LC_CURRENT
larl %r13,cleanup_critical
lmg %r8,%r9,__LC_EXT_OLD_PSW
SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
+ xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
lghi %r1,__LC_EXT_PARAMS2
.Lpsw_idle_stcctm:
#endif
oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT
+ BPON
STCK __CLOCK_IDLE_ENTER(%r2)
stpt __TIMER_IDLE_ENTER(%r2)
.Lpsw_idle_lpsw:
lpswe __SF_EMPTY(%r15)
- br %r14
+ BR_R1USE_R14
.Lpsw_idle_end:
/*
lg %r2,__LC_CURRENT
aghi %r2,__TASK_thread
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
- bor %r14
+ jo .Lsave_fpu_regs_exit
stfpc __THREAD_FPU_fpc(%r2)
lg %r3,__THREAD_FPU_regs(%r2)
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
std 15,120(%r3)
.Lsave_fpu_regs_done:
oi __LC_CPU_FLAGS+7,_CIF_FPU
- br %r14
+.Lsave_fpu_regs_exit:
+ BR_R1USE_R14
.Lsave_fpu_regs_end:
EXPORT_SYMBOL(save_fpu_regs)
lg %r4,__LC_CURRENT
aghi %r4,__TASK_thread
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
- bnor %r14
+ jno .Lload_fpu_regs_exit
lfpc __THREAD_FPU_fpc(%r4)
TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX
lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area
ld 15,120(%r4)
.Lload_fpu_regs_done:
ni __LC_CPU_FLAGS+7,255-_CIF_FPU
- br %r14
+.Lload_fpu_regs_exit:
+ BR_R1USE_R14
.Lload_fpu_regs_end:
.L__critical_end:
*/
ENTRY(mcck_int_handler)
STCK __LC_MCCK_CLOCK
+ BPOFF
la %r1,4095 # validate r1
spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer
sckc __LC_CLOCK_COMPARATOR # validate comparator
.Lmcck_skip:
lghi %r14,__LC_GPREGS_SAVE_AREA+64
stmg %r0,%r7,__PT_R0(%r11)
+ # clear user controlled registers to prevent speculative use
+ xgr %r0,%r0
+ xgr %r1,%r1
+ xgr %r2,%r2
+ xgr %r3,%r3
+ xgr %r4,%r4
+ xgr %r5,%r5
+ xgr %r6,%r6
+ xgr %r7,%r7
+ xgr %r10,%r10
mvc __PT_R8(64,%r11),0(%r14)
stmg %r8,%r9,__PT_PSW(%r11)
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
jno 0f
+ BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
0: lmg %r11,%r15,__PT_R11(%r11)
jl 0f
clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end
jl .Lcleanup_load_fpu_regs
-0: br %r14
+0: BR_R11USE_R14
.align 8
.Lcleanup_table:
clg %r9,BASED(.Lsie_crit_mcck_length)
jh 1f
oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST
-1: lg %r9,__SF_EMPTY(%r15) # get control block pointer
+1: BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
+ lg %r9,__SF_EMPTY(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
- br %r14
+ BR_R11USE_R14
#endif
.Lcleanup_system_call:
stg %r15,56(%r11) # r15 stack pointer
# set new psw address and exit
larl %r9,.Lsysc_do_svc
- br %r14
+ BR_R11USE_R14
.Lcleanup_system_call_insn:
.quad system_call
.quad .Lsysc_stmg
.Lcleanup_sysc_tif:
larl %r9,.Lsysc_tif
- br %r14
+ BR_R11USE_R14
.Lcleanup_sysc_restore:
# check if stpt has been executed
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
- br %r14
+ BR_R11USE_R14
.Lcleanup_sysc_restore_insn:
.quad .Lsysc_exit_timer
.quad .Lsysc_done - 4
.Lcleanup_io_tif:
larl %r9,.Lio_tif
- br %r14
+ BR_R11USE_R14
.Lcleanup_io_restore:
# check if stpt has been executed
mvc 0(64,%r11),__PT_R8(%r9)
lmg %r0,%r7,__PT_R0(%r9)
1: lmg %r8,%r9,__LC_RETURN_PSW
- br %r14
+ BR_R11USE_R14
.Lcleanup_io_restore_insn:
.quad .Lio_exit_timer
.quad .Lio_done - 4
# prepare return psw
nihh %r8,0xfcfd # clear irq & wait state bits
lg %r9,48(%r11) # return from psw_idle
- br %r14
+ BR_R11USE_R14
.Lcleanup_idle_insn:
.quad .Lpsw_idle_lpsw
.Lcleanup_save_fpu_regs:
larl %r9,save_fpu_regs
- br %r14
+ BR_R11USE_R14
.Lcleanup_load_fpu_regs:
larl %r9,load_fpu_regs
- br %r14
+ BR_R11USE_R14
/*
* Integer constants
.Lsie_crit_mcck_length:
.quad .Lsie_skip - .Lsie_entry
#endif
-
.section .rodata, "a"
#define SYSCALL(esame,emu) .long esame
.globl sys_call_table
static void __ipl_run(void *unused)
{
+ __bpon();
diag308(DIAG308_LOAD_CLEAR, NULL);
if (MACHINE_IS_VM)
__cpcmd("IPL", NULL, 0, NULL);
* is a BUG. The code path resides in the .kprobes.text
* section and is executed with interrupts disabled.
*/
- printk(KERN_EMERG "Invalid kprobe detected at %p.\n", p->addr);
+ pr_err("Invalid kprobe detected.\n");
dump_kprobe(p);
BUG();
}
#include <linux/moduleloader.h>
#include <linux/bug.h>
#include <asm/alternative.h>
+#include <asm/nospec-branch.h>
+#include <asm/facility.h>
#if 0
#define DEBUGP printk
me->arch.got_offset = me->core_layout.size;
me->core_layout.size += me->arch.got_size;
me->arch.plt_offset = me->core_layout.size;
- me->core_layout.size += me->arch.plt_size;
+ if (me->arch.plt_size) {
+ if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_call_disable)
+ me->arch.plt_size += PLT_ENTRY_SIZE;
+ me->core_layout.size += me->arch.plt_size;
+ }
return 0;
}
unsigned int *ip;
ip = me->core_layout.base + me->arch.plt_offset +
info->plt_offset;
- ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */
- ip[1] = 0x100a0004;
- ip[2] = 0x07f10000;
+ ip[0] = 0x0d10e310; /* basr 1,0 */
+ ip[1] = 0x100a0004; /* lg 1,10(1) */
+ if (IS_ENABLED(CONFIG_EXPOLINE) &&
+ !nospec_call_disable) {
+ unsigned int *ij;
+ ij = me->core_layout.base +
+ me->arch.plt_offset +
+ me->arch.plt_size - PLT_ENTRY_SIZE;
+ ip[2] = 0xa7f40000 + /* j __jump_r1 */
+ (unsigned int)(u16)
+ (((unsigned long) ij - 8 -
+ (unsigned long) ip) / 2);
+ } else {
+ ip[2] = 0x07f10000; /* br %r1 */
+ }
ip[3] = (unsigned int) (val >> 32);
ip[4] = (unsigned int) val;
info->plt_initialized = 1;
struct module *me)
{
const Elf_Shdr *s;
- char *secstrings;
+ char *secstrings, *secname;
+ void *aseg;
+
+ if (IS_ENABLED(CONFIG_EXPOLINE) &&
+ !nospec_call_disable && me->arch.plt_size) {
+ unsigned int *ij;
+
+ ij = me->core_layout.base + me->arch.plt_offset +
+ me->arch.plt_size - PLT_ENTRY_SIZE;
+ if (test_facility(35)) {
+ ij[0] = 0xc6000000; /* exrl %r0,.+10 */
+ ij[1] = 0x0005a7f4; /* j . */
+ ij[2] = 0x000007f1; /* br %r1 */
+ } else {
+ ij[0] = 0x44000000 | (unsigned int)
+ offsetof(struct lowcore, br_r1_trampoline);
+ ij[1] = 0xa7f40000; /* j . */
+ }
+ }
secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
- if (!strcmp(".altinstructions", secstrings + s->sh_name)) {
- /* patch .altinstructions */
- void *aseg = (void *)s->sh_addr;
+ aseg = (void *) s->sh_addr;
+ secname = secstrings + s->sh_name;
+ if (!strcmp(".altinstructions", secname))
+ /* patch .altinstructions */
apply_alternatives(aseg, aseg + s->sh_size);
- }
+
+ if (IS_ENABLED(CONFIG_EXPOLINE) &&
+ (!strcmp(".nospec_call_table", secname)))
+ nospec_call_revert(aseg, aseg + s->sh_size);
+
+ if (IS_ENABLED(CONFIG_EXPOLINE) &&
+ (!strcmp(".nospec_return_table", secname)))
+ nospec_return_revert(aseg, aseg + s->sh_size);
}
jump_label_apply_nops(me);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/module.h>
+#include <asm/nospec-branch.h>
+
+int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF);
+int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL);
+
+static int __init nospectre_v2_setup_early(char *str)
+{
+ nospec_call_disable = 1;
+ nospec_return_disable = 1;
+ return 0;
+}
+early_param("nospectre_v2", nospectre_v2_setup_early);
+
+static int __init spectre_v2_setup_early(char *str)
+{
+ if (str && !strncmp(str, "on", 2)) {
+ nospec_call_disable = 0;
+ nospec_return_disable = 0;
+ }
+ if (str && !strncmp(str, "off", 3)) {
+ nospec_call_disable = 1;
+ nospec_return_disable = 1;
+ }
+ if (str && !strncmp(str, "auto", 4)) {
+ nospec_call_disable = 0;
+ nospec_return_disable = 1;
+ }
+ return 0;
+}
+early_param("spectre_v2", spectre_v2_setup_early);
+
+static void __init_or_module __nospec_revert(s32 *start, s32 *end)
+{
+ enum { BRCL_EXPOLINE, BRASL_EXPOLINE } type;
+ u8 *instr, *thunk, *br;
+ u8 insnbuf[6];
+ s32 *epo;
+
+ /* Second part of the instruction replace is always a nop */
+ memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4);
+ for (epo = start; epo < end; epo++) {
+ instr = (u8 *) epo + *epo;
+ if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04)
+ type = BRCL_EXPOLINE; /* brcl instruction */
+ else if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x05)
+ type = BRASL_EXPOLINE; /* brasl instruction */
+ else
+ continue;
+ thunk = instr + (*(int *)(instr + 2)) * 2;
+ if (thunk[0] == 0xc6 && thunk[1] == 0x00)
+ /* exrl %r0,<target-br> */
+ br = thunk + (*(int *)(thunk + 2)) * 2;
+ else if (thunk[0] == 0xc0 && (thunk[1] & 0x0f) == 0x00 &&
+ thunk[6] == 0x44 && thunk[7] == 0x00 &&
+ (thunk[8] & 0x0f) == 0x00 && thunk[9] == 0x00 &&
+ (thunk[1] & 0xf0) == (thunk[8] & 0xf0))
+ /* larl %rx,<target br> + ex %r0,0(%rx) */
+ br = thunk + (*(int *)(thunk + 2)) * 2;
+ else
+ continue;
+ if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0)
+ continue;
+ switch (type) {
+ case BRCL_EXPOLINE:
+ /* brcl to thunk, replace with br + nop */
+ insnbuf[0] = br[0];
+ insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+ break;
+ case BRASL_EXPOLINE:
+ /* brasl to thunk, replace with basr + nop */
+ insnbuf[0] = 0x0d;
+ insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f);
+ break;
+ }
+
+ s390_kernel_write(instr, insnbuf, 6);
+ }
+}
+
+void __init_or_module nospec_call_revert(s32 *start, s32 *end)
+{
+ if (nospec_call_disable)
+ __nospec_revert(start, end);
+}
+
+void __init_or_module nospec_return_revert(s32 *start, s32 *end)
+{
+ if (nospec_return_disable)
+ __nospec_revert(start, end);
+}
+
+extern s32 __nospec_call_start[], __nospec_call_end[];
+extern s32 __nospec_return_start[], __nospec_return_end[];
+void __init nospec_init_branches(void)
+{
+ nospec_call_revert(__nospec_call_start, __nospec_call_end);
+ nospec_return_revert(__nospec_return_start, __nospec_return_end);
+}
CPUMF_EVENT_ATTR(cf_z14, BCD_DFP_EXECUTION_SLOTS, 0x00e0);
CPUMF_EVENT_ATTR(cf_z14, VX_BCD_EXECUTION_SLOTS, 0x00e1);
CPUMF_EVENT_ATTR(cf_z14, DECIMAL_INSTRUCTIONS, 0x00e2);
-CPUMF_EVENT_ATTR(cf_z14, LAST_HOST_TRANSLATIONS, 0x00e9);
+CPUMF_EVENT_ATTR(cf_z14, LAST_HOST_TRANSLATIONS, 0x00e8);
CPUMF_EVENT_ATTR(cf_z14, TX_NC_TABORT, 0x00f3);
CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4);
CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5);
.stop = c_stop,
.show = show_cpuinfo,
};
+
+int s390_isolate_bp(void)
+{
+ if (!test_facility(82))
+ return -EOPNOTSUPP;
+ set_thread_flag(TIF_ISOLATE_BP);
+ return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp);
+
+int s390_isolate_bp_guest(void)
+{
+ if (!test_facility(82))
+ return -EOPNOTSUPP;
+ set_thread_flag(TIF_ISOLATE_BP_GUEST);
+ return 0;
+}
+EXPORT_SYMBOL(s390_isolate_bp_guest);
#include <asm/cpu_mf.h>
#include <asm/irq.h>
+#include "entry.h"
+
/* empty control block to disable RI by loading it */
struct runtime_instr_cb runtime_instr_empty_cb;
cb->v = 1;
}
-SYSCALL_DEFINE1(s390_runtime_instr, int, command)
+/*
+ * The signum argument is unused. In older kernels it was used to
+ * specify a real-time signal. For backwards compatibility user space
+ * should pass a valid real-time signal number (the signum argument
+ * was checked in older kernels).
+ */
+SYSCALL_DEFINE2(s390_runtime_instr, int, command, int, signum)
{
struct runtime_instr_cb *cb;
#include <asm/sysinfo.h>
#include <asm/numa.h>
#include <asm/alternative.h>
+#include <asm/nospec-branch.h>
#include "entry.h"
/*
lc->preempt_count = S390_lowcore.preempt_count;
lc->stfl_fac_list = S390_lowcore.stfl_fac_list;
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
- MAX_FACILITY_BIT/8);
+ sizeof(lc->stfle_fac_list));
+ memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
+ sizeof(lc->alt_stfle_fac_list));
nmi_alloc_boot_cpu(lc);
vdso_alloc_boot_cpu(lc);
lc->sync_enter_timer = S390_lowcore.sync_enter_timer;
lc->spinlock_index = 0;
arch_spin_lock_setup(0);
#endif
+ lc->br_r1_trampoline = 0x07f1; /* br %r1 */
set_prefix((u32)(unsigned long) lc);
lowcore_ptr[0] = lc;
set_preferred_console();
apply_alternative_instructions();
+ if (IS_ENABLED(CONFIG_EXPOLINE))
+ nospec_init_branches();
/* Setup zfcpdump support */
setup_zfcpdump();
lc->cpu_nr = cpu;
lc->spinlock_lockval = arch_spin_lockval(cpu);
lc->spinlock_index = 0;
+ lc->br_r1_trampoline = 0x07f1; /* br %r1 */
if (nmi_alloc_per_cpu(lc))
goto out;
if (vdso_alloc_per_cpu(lc))
__ctl_store(lc->cregs_save_area, 0, 15);
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
- MAX_FACILITY_BIT/8);
+ sizeof(lc->stfle_fac_list));
+ memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list,
+ sizeof(lc->alt_stfle_fac_list));
arch_spin_lock_setup(cpu);
}
mem_assign_absolute(lc->restart_fn, (unsigned long) func);
mem_assign_absolute(lc->restart_data, (unsigned long) data);
mem_assign_absolute(lc->restart_source, source_cpu);
+ __bpon();
asm volatile(
"0: sigp 0,%0,%2 # sigp restart to target cpu\n"
" brc 2,0b # busy, try again\n"
void __noreturn cpu_die(void)
{
idle_task_exit();
+ __bpon();
pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0);
for (;;) ;
}
EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap));
seq_printf(m, "Manufacturer: %-16.16s\n", info->manufacturer);
seq_printf(m, "Type: %-4.4s\n", info->type);
+ if (info->lic)
+ seq_printf(m, "LIC Identifier: %016lx\n", info->lic);
/*
* Sigh: the model field has been renamed with System z9
* to model_capacity and a new model field has been added
*(.altinstr_replacement)
}
+ /*
+ * Table with the patch locations to undo expolines
+ */
+ .nospec_call_table : {
+ __nospec_call_start = . ;
+ *(.s390_indirect*)
+ __nospec_call_end = . ;
+ }
+ .nospec_return_table : {
+ __nospec_return_start = . ;
+ *(.s390_return*)
+ __nospec_return_end = . ;
+ }
+
/* early.c uses stsi, which requires page aligned data. */
. = ALIGN(PAGE_SIZE);
INIT_DATA_SECTION(0x100)
select PREEMPT_NOTIFIERS
select ANON_INODES
select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select HAVE_KVM_VCPU_ASYNC_IOCTL
select HAVE_KVM_EVENTFD
select KVM_ASYNC_PF
select KVM_ASYNC_PF_SYNC
case 0x500:
return __diag_virtio_hypercall(vcpu);
default:
+ vcpu->stat.diagnose_other++;
return -EOPNOTSUPP;
}
}
{
int c, scn;
- if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+ if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND))
return 0;
BUG_ON(!kvm_s390_use_sca_entries());
/* another external call is pending */
return -EBUSY;
}
- atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
return 0;
}
static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
{
- struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc, expect;
if (!kvm_s390_use_sca_entries())
return;
- atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
static inline int is_ioirq(unsigned long irq_type)
{
- return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
- (irq_type <= IRQ_PEND_IO_ISC_7));
+ return ((irq_type >= IRQ_PEND_IO_ISC_7) &&
+ (irq_type <= IRQ_PEND_IO_ISC_0));
}
static uint64_t isc_to_isc_bits(int isc)
return (0x80 >> isc) << 24;
}
+static inline u32 isc_to_int_word(u8 isc)
+{
+ return ((u32)isc << 27) | 0x80000000;
+}
+
static inline u8 int_word_to_isc(u32 int_word)
{
return (int_word & 0x38000000) >> 27;
}
+/*
+ * To use atomic bitmap functions, we have to provide a bitmap address
+ * that is u64 aligned. However, the ipm might be u32 aligned.
+ * Therefore, we logically start the bitmap at the very beginning of the
+ * struct and fixup the bit number.
+ */
+#define IPM_BIT_OFFSET (offsetof(struct kvm_s390_gisa, ipm) * BITS_PER_BYTE)
+
+static inline void kvm_s390_gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline u8 kvm_s390_gisa_get_ipm(struct kvm_s390_gisa *gisa)
+{
+ return READ_ONCE(gisa->ipm);
+}
+
+static inline void kvm_s390_gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+ return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
{
return vcpu->kvm->arch.float_int.pending_irqs |
- vcpu->arch.local_int.pending_irqs;
+ vcpu->arch.local_int.pending_irqs |
+ kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7;
}
static inline int isc_to_irq_type(unsigned long isc)
{
- return IRQ_PEND_IO_ISC_0 + isc;
+ return IRQ_PEND_IO_ISC_0 - isc;
}
static inline int irq_type_to_isc(unsigned long irq_type)
{
- return irq_type - IRQ_PEND_IO_ISC_0;
+ return IRQ_PEND_IO_ISC_0 - irq_type;
}
static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
- atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
- set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
+ set_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
- atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
- clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
+ clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
}
static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
{
- atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
- &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IO_INT | CPUSTAT_EXT_INT |
+ CPUSTAT_STOP_INT);
vcpu->arch.sie_block->lctl = 0x0000;
vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
}
}
-static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
-{
- atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
-}
-
static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
{
if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
return;
else if (psw_ioint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_IO_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR6;
}
if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
return;
if (psw_extint_disabled(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR0;
}
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
if (kvm_s390_is_stop_irq_pending(vcpu))
- __set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
}
/* Set interception request for non-deliverable interrupts */
return rc ? -EFAULT : 0;
}
+static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io)
+{
+ int rc;
+
+ rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID);
+ rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR);
+ rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM);
+ rc |= put_guest_lc(vcpu, io->io_int_word, (u32 *)__LC_IO_INT_WORD);
+ rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
+ &vcpu->arch.sie_block->gpsw,
+ sizeof(psw_t));
+ return rc ? -EFAULT : 0;
+}
+
static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
unsigned long irq_type)
{
struct list_head *isc_list;
struct kvm_s390_float_interrupt *fi;
struct kvm_s390_interrupt_info *inti = NULL;
+ struct kvm_s390_io_info io;
+ u32 isc;
int rc = 0;
fi = &vcpu->kvm->arch.float_int;
spin_lock(&fi->lock);
- isc_list = &fi->lists[irq_type_to_isc(irq_type)];
+ isc = irq_type_to_isc(irq_type);
+ isc_list = &fi->lists[isc];
inti = list_first_entry_or_null(isc_list,
struct kvm_s390_interrupt_info,
list);
spin_unlock(&fi->lock);
if (inti) {
- rc = put_guest_lc(vcpu, inti->io.subchannel_id,
- (u16 *)__LC_SUBCHANNEL_ID);
- rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
- (u16 *)__LC_SUBCHANNEL_NR);
- rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
- (u32 *)__LC_IO_INT_PARM);
- rc |= put_guest_lc(vcpu, inti->io.io_int_word,
- (u32 *)__LC_IO_INT_WORD);
- rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
- rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
- &vcpu->arch.sie_block->gpsw,
- sizeof(psw_t));
+ rc = __do_deliver_io(vcpu, &(inti->io));
kfree(inti);
+ goto out;
}
- return rc ? -EFAULT : 0;
+ if (vcpu->kvm->arch.gisa &&
+ kvm_s390_gisa_tac_ipm_gisc(vcpu->kvm->arch.gisa, isc)) {
+ /*
+ * in case an adapter interrupt was not delivered
+ * in SIE context KVM will handle the delivery
+ */
+ VCPU_EVENT(vcpu, 4, "%s isc %u", "deliver: I/O (AI/gisa)", isc);
+ memset(&io, 0, sizeof(io));
+ io.io_int_word = isc_to_int_word(isc);
+ vcpu->stat.deliver_io_int++;
+ trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+ KVM_S390_INT_IO(1, 0, 0, 0),
+ ((__u32)io.subchannel_id << 16) |
+ io.subchannel_nr,
+ ((__u64)io.io_int_parm << 32) |
+ io.io_int_word);
+ rc = __do_deliver_io(vcpu, &io);
+ }
+out:
+ return rc;
}
typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
while ((irqs = deliverable_irqs(vcpu)) && !rc) {
- /* bits are in the order of interrupt priority */
- irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
+ /* bits are in the reverse order of interrupt priority */
+ irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT);
if (is_ioirq(irq_type)) {
rc = __deliver_io(vcpu, irq_type);
} else {
li->irq.ext = irq->u.ext;
set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
return -EBUSY;
*extcall = irq->u.extcall;
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs))
return -EBUSY;
stop->flags = irq->u.stop.flags;
- __set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
return 0;
}
set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
0, 0);
set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
0, 0);
set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
return 0;
}
return NULL;
}
+static struct kvm_s390_interrupt_info *get_top_io_int(struct kvm *kvm,
+ u64 isc_mask, u32 schid)
+{
+ struct kvm_s390_interrupt_info *inti = NULL;
+ int isc;
+
+ for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
+ if (isc_mask & isc_to_isc_bits(isc))
+ inti = get_io_int(kvm, isc, schid);
+ }
+ return inti;
+}
+
+static int get_top_gisa_isc(struct kvm *kvm, u64 isc_mask, u32 schid)
+{
+ unsigned long active_mask;
+ int isc;
+
+ if (schid)
+ goto out;
+ if (!kvm->arch.gisa)
+ goto out;
+
+ active_mask = (isc_mask & kvm_s390_gisa_get_ipm(kvm->arch.gisa) << 24) << 32;
+ while (active_mask) {
+ isc = __fls(active_mask) ^ (BITS_PER_LONG - 1);
+ if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, isc))
+ return isc;
+ clear_bit_inv(isc, &active_mask);
+ }
+out:
+ return -EINVAL;
+}
+
/*
* Dequeue and return an I/O interrupt matching any of the interruption
* subclasses as designated by the isc mask in cr6 and the schid (if != 0).
+ * Take into account the interrupts pending in the interrupt list and in GISA.
+ *
+ * Note that for a guest that does not enable I/O interrupts
+ * but relies on TPI, a flood of classic interrupts may starve
+ * out adapter interrupts on the same isc. Linux does not do
+ * that, and it is possible to work around the issue by configuring
+ * different iscs for classic and adapter interrupts in the guest,
+ * but we may want to revisit this in the future.
*/
struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
u64 isc_mask, u32 schid)
{
- struct kvm_s390_interrupt_info *inti = NULL;
+ struct kvm_s390_interrupt_info *inti, *tmp_inti;
int isc;
- for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
- if (isc_mask & isc_to_isc_bits(isc))
- inti = get_io_int(kvm, isc, schid);
+ inti = get_top_io_int(kvm, isc_mask, schid);
+
+ isc = get_top_gisa_isc(kvm, isc_mask, schid);
+ if (isc < 0)
+ /* no AI in GISA */
+ goto out;
+
+ if (!inti)
+ /* AI in GISA but no classical IO int */
+ goto gisa_out;
+
+ /* both types of interrupts present */
+ if (int_word_to_isc(inti->io.io_int_word) <= isc) {
+ /* classical IO int with higher priority */
+ kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ goto out;
}
+gisa_out:
+ tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (tmp_inti) {
+ tmp_inti->type = KVM_S390_INT_IO(1, 0, 0, 0);
+ tmp_inti->io.io_int_word = isc_to_int_word(isc);
+ if (inti)
+ kvm_s390_reinject_io_int(kvm, inti);
+ inti = tmp_inti;
+ } else
+ kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+out:
return inti;
}
struct list_head *list;
int isc;
+ isc = int_word_to_isc(inti->io.io_int_word);
+
+ if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) {
+ VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc);
+ kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+ kfree(inti);
+ return 0;
+ }
+
fi = &kvm->arch.float_int;
spin_lock(&fi->lock);
if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) {
inti->io.subchannel_id >> 8,
inti->io.subchannel_id >> 1 & 0x3,
inti->io.subchannel_nr);
- isc = int_word_to_isc(inti->io.io_int_word);
list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
list_add_tail(&inti->list, list);
set_bit(isc_to_irq_type(isc), &fi->pending_irqs);
static void __floating_irq_kick(struct kvm *kvm, u64 type)
{
struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
- struct kvm_s390_local_interrupt *li;
struct kvm_vcpu *dst_vcpu;
int sigcpu, online_vcpus, nr_tries = 0;
dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
/* make the VCPU drop out of the SIE, or wake it up if sleeping */
- li = &dst_vcpu->arch.local_int;
- spin_lock(&li->lock);
switch (type) {
case KVM_S390_MCHK:
- atomic_or(CPUSTAT_STOP_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT);
break;
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
- atomic_or(CPUSTAT_IO_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
break;
default:
- atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
+ kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT);
break;
}
- spin_unlock(&li->lock);
kvm_s390_vcpu_wakeup(dst_vcpu);
}
for (i = 0; i < FIRQ_MAX_COUNT; i++)
fi->counters[i] = 0;
spin_unlock(&fi->lock);
+ kvm_s390_gisa_clear(kvm);
};
static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
max_irqs = len / sizeof(struct kvm_s390_irq);
+ if (kvm->arch.gisa &&
+ kvm_s390_gisa_get_ipm(kvm->arch.gisa)) {
+ for (i = 0; i <= MAX_ISC; i++) {
+ if (n == max_irqs) {
+ /* signal userspace to try again */
+ ret = -ENOMEM;
+ goto out_nolock;
+ }
+ if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, i)) {
+ irq = (struct kvm_s390_irq *) &buf[n];
+ irq->type = KVM_S390_INT_IO(1, 0, 0, 0);
+ irq->u.io.io_int_word = isc_to_int_word(i);
+ n++;
+ }
+ }
+ }
fi = &kvm->arch.float_int;
spin_lock(&fi->lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++) {
out:
spin_unlock(&fi->lock);
+out_nolock:
if (!ret && n > 0) {
if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
ret = -EFAULT;
struct kvm_s390_interrupt s390int = {
.type = KVM_S390_INT_IO(1, 0, 0, 0),
.parm = 0,
- .parm64 = (adapter->isc << 27) | 0x80000000,
+ .parm64 = isc_to_int_word(adapter->isc),
};
int ret = 0;
return n;
}
+
+void kvm_s390_gisa_clear(struct kvm *kvm)
+{
+ if (kvm->arch.gisa) {
+ memset(kvm->arch.gisa, 0, sizeof(struct kvm_s390_gisa));
+ kvm->arch.gisa->next_alert = (u32)(u64)kvm->arch.gisa;
+ VM_EVENT(kvm, 3, "gisa 0x%pK cleared", kvm->arch.gisa);
+ }
+}
+
+void kvm_s390_gisa_init(struct kvm *kvm)
+{
+ if (css_general_characteristics.aiv) {
+ kvm->arch.gisa = &kvm->arch.sie_page2->gisa;
+ VM_EVENT(kvm, 3, "gisa 0x%pK initialized", kvm->arch.gisa);
+ kvm_s390_gisa_clear(kvm);
+ }
+}
+
+void kvm_s390_gisa_destroy(struct kvm *kvm)
+{
+ if (!kvm->arch.gisa)
+ return;
+ kvm->arch.gisa = NULL;
+}
/*
* hosting IBM Z kernel virtual machines (s390x)
*
- * Copyright IBM Corp. 2008, 2017
+ * Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+ { "instruction_epsw", VCPU_STAT(instruction_epsw) },
+ { "instruction_gs", VCPU_STAT(instruction_gs) },
+ { "instruction_io_other", VCPU_STAT(instruction_io_other) },
+ { "instruction_lpsw", VCPU_STAT(instruction_lpsw) },
+ { "instruction_lpswe", VCPU_STAT(instruction_lpswe) },
{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
+ { "instruction_ptff", VCPU_STAT(instruction_ptff) },
{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
+ { "instruction_sck", VCPU_STAT(instruction_sck) },
+ { "instruction_sckpf", VCPU_STAT(instruction_sckpf) },
{ "instruction_spx", VCPU_STAT(instruction_spx) },
{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
{ "instruction_stap", VCPU_STAT(instruction_stap) },
- { "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+ { "instruction_iske", VCPU_STAT(instruction_iske) },
+ { "instruction_ri", VCPU_STAT(instruction_ri) },
+ { "instruction_rrbe", VCPU_STAT(instruction_rrbe) },
+ { "instruction_sske", VCPU_STAT(instruction_sske) },
{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
- { "instruction_stsch", VCPU_STAT(instruction_stsch) },
- { "instruction_chsc", VCPU_STAT(instruction_chsc) },
{ "instruction_essa", VCPU_STAT(instruction_essa) },
{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+ { "instruction_tb", VCPU_STAT(instruction_tb) },
+ { "instruction_tpi", VCPU_STAT(instruction_tpi) },
{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
+ { "instruction_tsch", VCPU_STAT(instruction_tsch) },
{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
{ "instruction_sie", VCPU_STAT(instruction_sie) },
{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
- { "diagnose_10", VCPU_STAT(diagnose_10) },
- { "diagnose_44", VCPU_STAT(diagnose_44) },
- { "diagnose_9c", VCPU_STAT(diagnose_9c) },
- { "diagnose_258", VCPU_STAT(diagnose_258) },
- { "diagnose_308", VCPU_STAT(diagnose_308) },
- { "diagnose_500", VCPU_STAT(diagnose_500) },
+ { "instruction_diag_10", VCPU_STAT(diagnose_10) },
+ { "instruction_diag_44", VCPU_STAT(diagnose_44) },
+ { "instruction_diag_9c", VCPU_STAT(diagnose_9c) },
+ { "instruction_diag_258", VCPU_STAT(diagnose_258) },
+ { "instruction_diag_308", VCPU_STAT(diagnose_308) },
+ { "instruction_diag_500", VCPU_STAT(diagnose_500) },
+ { "instruction_diag_other", VCPU_STAT(diagnose_other) },
{ NULL }
};
case KVM_CAP_S390_GS:
r = -EINVAL;
mutex_lock(&kvm->lock);
- if (atomic_read(&kvm->online_vcpus)) {
+ if (kvm->created_vcpus) {
r = -EBUSY;
} else if (test_facility(133)) {
set_kvm_facility(kvm->arch.model.fac_mask, 133);
struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_feat data;
- int ret = -EBUSY;
if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data)))
return -EFAULT;
return -EINVAL;
mutex_lock(&kvm->lock);
- if (!atomic_read(&kvm->online_vcpus)) {
- bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
- KVM_S390_VM_CPU_FEAT_NR_BITS);
- ret = 0;
+ if (kvm->created_vcpus) {
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
}
+ bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
+ KVM_S390_VM_CPU_FEAT_NR_BITS);
mutex_unlock(&kvm->lock);
- return ret;
+ VM_EVENT(kvm, 3, "SET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
+ data.feat[0],
+ data.feat[1],
+ data.feat[2]);
+ return 0;
}
static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
KVM_S390_VM_CPU_FEAT_NR_BITS);
if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
return -EFAULT;
+ VM_EVENT(kvm, 3, "GET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
+ data.feat[0],
+ data.feat[1],
+ data.feat[2]);
return 0;
}
KVM_S390_VM_CPU_FEAT_NR_BITS);
if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
return -EFAULT;
+ VM_EVENT(kvm, 3, "GET: host feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
+ data.feat[0],
+ data.feat[1],
+ data.feat[2]);
return 0;
}
if (!kvm->arch.dbf)
goto out_err;
+ BUILD_BUG_ON(sizeof(struct sie_page2) != 4096);
kvm->arch.sie_page2 =
(struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
if (!kvm->arch.sie_page2)
spin_lock_init(&kvm->arch.start_stop_lock);
kvm_s390_vsie_init(kvm);
+ kvm_s390_gisa_init(kvm);
KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
kvm_free_vcpus(kvm);
sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
+ kvm_s390_gisa_destroy(kvm);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_remove(kvm->arch.gmap);
{
gmap_enable(vcpu->arch.enabled_gmap);
- atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING);
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__start_cpu_timer_accounting(vcpu);
vcpu->cpu = cpu;
vcpu->cpu = -1;
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__stop_cpu_timer_accounting(vcpu);
- atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_RUNNING);
vcpu->arch.enabled_gmap = gmap_get_enabled();
gmap_disable(vcpu->arch.enabled_gmap);
CPUSTAT_STOPPED);
if (test_kvm_facility(vcpu->kvm, 78))
- atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED2);
else if (test_kvm_facility(vcpu->kvm, 8))
- atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED);
kvm_s390_vcpu_setup_model(vcpu);
if (test_kvm_facility(vcpu->kvm, 139))
vcpu->arch.sie_block->ecd |= ECD_MEF;
+ if (vcpu->arch.sie_block->gd) {
+ vcpu->arch.sie_block->eca |= ECA_AIV;
+ VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u",
+ vcpu->arch.sie_block->gd & 0x3, vcpu->vcpu_id);
+ }
vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx)
| SDNXC;
vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
if (sclp.has_kss)
- atomic_or(CPUSTAT_KSS, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_KSS);
else
vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
vcpu->arch.sie_block->icpua = id;
spin_lock_init(&vcpu->arch.local_int.lock);
- vcpu->arch.local_int.float_int = &kvm->arch.float_int;
- vcpu->arch.local_int.wq = &vcpu->wq;
- vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+ vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa;
+ if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
+ vcpu->arch.sie_block->gd |= GISA_FORMAT1;
seqcount_init(&vcpu->arch.cputm_seqcount);
rc = kvm_vcpu_init(vcpu, kvm, id);
* return immediately. */
void exit_sie(struct kvm_vcpu *vcpu)
{
- atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
cpu_relax();
}
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ vcpu_load(vcpu);
memcpy(&vcpu->run->s.regs.gprs, ®s->gprs, sizeof(regs->gprs));
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ vcpu_load(vcpu);
memcpy(®s->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
+ vcpu_load(vcpu);
+
memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
+
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
+ vcpu_load(vcpu);
+
memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
+
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- if (test_fp_ctl(fpu->fpc))
- return -EINVAL;
+ int ret = 0;
+
+ vcpu_load(vcpu);
+
+ if (test_fp_ctl(fpu->fpc)) {
+ ret = -EINVAL;
+ goto out;
+ }
vcpu->run->s.regs.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
(freg_t *) fpu->fprs);
else
memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
- return 0;
+
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
+ vcpu_load(vcpu);
+
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
else
memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = vcpu->run->s.regs.fpc;
+
+ vcpu_put(vcpu);
return 0;
}
{
int rc = 0;
+ vcpu_load(vcpu);
+
vcpu->guest_debug = 0;
kvm_s390_clear_bp_data(vcpu);
- if (dbg->control & ~VALID_GUESTDBG_FLAGS)
- return -EINVAL;
- if (!sclp.has_gpere)
- return -EINVAL;
+ if (dbg->control & ~VALID_GUESTDBG_FLAGS) {
+ rc = -EINVAL;
+ goto out;
+ }
+ if (!sclp.has_gpere) {
+ rc = -EINVAL;
+ goto out;
+ }
if (dbg->control & KVM_GUESTDBG_ENABLE) {
vcpu->guest_debug = dbg->control;
/* enforce guest PER */
- atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_P);
if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
rc = kvm_s390_import_bp_data(vcpu, dbg);
} else {
- atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P);
vcpu->arch.guestdbg.last_bp = 0;
}
if (rc) {
vcpu->guest_debug = 0;
kvm_s390_clear_bp_data(vcpu);
- atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P);
}
+out:
+ vcpu_put(vcpu);
return rc;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ int ret;
+
+ vcpu_load(vcpu);
+
/* CHECK_STOP and LOAD are not supported yet */
- return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
- KVM_MP_STATE_OPERATING;
+ ret = is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
+ KVM_MP_STATE_OPERATING;
+
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
{
int rc = 0;
+ vcpu_load(vcpu);
+
/* user space knows about this interface - let it control the state */
vcpu->kvm->arch.user_cpu_state_ctrl = 1;
rc = -ENXIO;
}
+ vcpu_put(vcpu);
return rc;
}
static bool ibs_enabled(struct kvm_vcpu *vcpu)
{
- return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
+ return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
}
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
if (!ibs_enabled(vcpu)) {
trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
- atomic_or(CPUSTAT_IBS,
- &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_IBS);
}
goto retry;
}
if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
if (ibs_enabled(vcpu)) {
trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
- atomic_andnot(CPUSTAT_IBS,
- &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IBS);
}
goto retry;
}
if (kvm_run->immediate_exit)
return -EINTR;
+ vcpu_load(vcpu);
+
if (guestdbg_exit_pending(vcpu)) {
kvm_s390_prepare_debug_exit(vcpu);
- return 0;
+ rc = 0;
+ goto out;
}
kvm_sigset_activate(vcpu);
} else if (is_vcpu_stopped(vcpu)) {
pr_err_ratelimited("can't run stopped vcpu %d\n",
vcpu->vcpu_id);
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
sync_regs(vcpu, kvm_run);
kvm_sigset_deactivate(vcpu);
vcpu->stat.exit_userspace++;
+out:
+ vcpu_put(vcpu);
return rc;
}
__disable_ibs_on_all_vcpus(vcpu->kvm);
}
- atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED);
/*
* Another VCPU might have used IBS while we were offline.
* Let's play safe and flush the VCPU at startup.
/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
kvm_s390_clear_stop_irq(vcpu);
- atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
__disable_ibs_on_vcpu(vcpu);
for (i = 0; i < online_vcpus; i++) {
return r;
}
-long kvm_arch_vcpu_ioctl(struct file *filp,
- unsigned int ioctl, unsigned long arg)
+long kvm_arch_vcpu_async_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
- int idx;
- long r;
switch (ioctl) {
case KVM_S390_IRQ: {
struct kvm_s390_irq s390irq;
- r = -EFAULT;
if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
- break;
- r = kvm_s390_inject_vcpu(vcpu, &s390irq);
- break;
+ return -EFAULT;
+ return kvm_s390_inject_vcpu(vcpu, &s390irq);
}
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
struct kvm_s390_irq s390irq;
- r = -EFAULT;
if (copy_from_user(&s390int, argp, sizeof(s390int)))
- break;
+ return -EFAULT;
if (s390int_to_s390irq(&s390int, &s390irq))
return -EINVAL;
- r = kvm_s390_inject_vcpu(vcpu, &s390irq);
- break;
+ return kvm_s390_inject_vcpu(vcpu, &s390irq);
+ }
}
+ return -ENOIOCTLCMD;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg)
+{
+ struct kvm_vcpu *vcpu = filp->private_data;
+ void __user *argp = (void __user *)arg;
+ int idx;
+ long r;
+
+ vcpu_load(vcpu);
+
+ switch (ioctl) {
case KVM_S390_STORE_STATUS:
idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvm_s390_vcpu_store_status(vcpu, arg);
default:
r = -ENOTTY;
}
+
+ vcpu_put(vcpu);
return r;
}
d_args); \
} while (0)
+static inline void kvm_s390_set_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+ atomic_or(flags, &vcpu->arch.sie_block->cpuflags);
+}
+
+static inline void kvm_s390_clear_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+ atomic_andnot(flags, &vcpu->arch.sie_block->cpuflags);
+}
+
+static inline bool kvm_s390_test_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+ return (atomic_read(&vcpu->arch.sie_block->cpuflags) & flags) == flags;
+}
+
static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
{
- return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
+ return kvm_s390_test_cpuflags(vcpu, CPUSTAT_STOPPED);
}
static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
{
- return test_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+ return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
}
static inline int kvm_is_ucontrol(struct kvm *kvm)
void __user *buf, int len);
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu,
__u8 __user *buf, int len);
+void kvm_s390_gisa_init(struct kvm *kvm);
+void kvm_s390_gisa_clear(struct kvm *kvm);
+void kvm_s390_gisa_destroy(struct kvm *kvm);
/* implemented in guestdbg.c */
void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
/*
* handling privileged instructions
*
- * Copyright IBM Corp. 2008, 2013
+ * Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
static int handle_ri(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.instruction_ri++;
+
if (test_kvm_facility(vcpu->kvm, 64)) {
VCPU_EVENT(vcpu, 3, "%s", "ENABLE: RI (lazy)");
vcpu->arch.sie_block->ecb3 |= ECB3_RI;
static int handle_gs(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.instruction_gs++;
+
if (test_kvm_facility(vcpu->kvm, 133)) {
VCPU_EVENT(vcpu, 3, "%s", "ENABLE: GS (lazy)");
preempt_disable();
u8 ar;
u64 op2, val;
+ vcpu->stat.instruction_sck++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
trace_kvm_s390_skey_related_inst(vcpu);
if (!(sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)) &&
- !(atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS))
+ !kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS))
return rc;
rc = s390_enable_skey();
VCPU_EVENT(vcpu, 3, "enabling storage keys for guest: %d", rc);
if (!rc) {
- if (atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS)
- atomic_andnot(CPUSTAT_KSS, &sie_block->cpuflags);
+ if (kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS))
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_KSS);
else
sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE |
ICTL_RRBE);
{
int rc;
- vcpu->stat.instruction_storage_key++;
rc = kvm_s390_skey_check_enable(vcpu);
if (rc)
return rc;
int reg1, reg2;
int rc;
+ vcpu->stat.instruction_iske++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
int reg1, reg2;
int rc;
+ vcpu->stat.instruction_rrbe++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
int reg1, reg2;
int rc;
+ vcpu->stat.instruction_sske++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
gpa_t addr;
int reg2;
+ vcpu->stat.instruction_tb++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
u64 addr;
u8 ar;
+ vcpu->stat.instruction_tpi++;
+
addr = kvm_s390_get_base_disp_s(vcpu, &ar);
if (addr & 3)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
struct kvm_s390_interrupt_info *inti = NULL;
const u64 isc_mask = 0xffUL << 24; /* all iscs set */
+ vcpu->stat.instruction_tsch++;
+
/* a valid schid has at least one bit set */
if (vcpu->run->s.regs.gprs[1])
inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask,
if (vcpu->arch.sie_block->ipa == 0xb235)
return handle_tsch(vcpu);
/* Handle in userspace. */
+ vcpu->stat.instruction_io_other++;
return -EOPNOTSUPP;
} else {
/*
int rc;
u8 ar;
+ vcpu->stat.instruction_lpsw++;
+
if (gpsw->mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
int rc;
u8 ar;
+ vcpu->stat.instruction_lpswe++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
{
int reg1, reg2;
+ vcpu->stat.instruction_epsw++;
+
kvm_s390_get_regs_rre(vcpu, ®1, ®2);
/* This basically extracts the mask half of the psw. */
{
u32 value;
+ vcpu->stat.instruction_sckpf++;
+
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
static int handle_ptff(struct kvm_vcpu *vcpu)
{
+ vcpu->stat.instruction_ptff++;
+
/* we don't emulate any control instructions yet */
kvm_s390_set_psw_cc(vcpu, 3);
return 0;
static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
u64 *reg)
{
- struct kvm_s390_local_interrupt *li;
- int cpuflags;
+ const bool stopped = kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED);
int rc;
int ext_call_pending;
- li = &dst_vcpu->arch.local_int;
-
- cpuflags = atomic_read(li->cpuflags);
ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu);
- if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending)
+ if (!stopped && !ext_call_pending)
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
else {
*reg &= 0xffffffff00000000UL;
if (ext_call_pending)
*reg |= SIGP_STATUS_EXT_CALL_PENDING;
- if (cpuflags & CPUSTAT_STOPPED)
+ if (stopped)
*reg |= SIGP_STATUS_STOPPED;
rc = SIGP_CC_STATUS_STORED;
}
struct kvm_vcpu *dst_vcpu,
u32 addr, u64 *reg)
{
- int flags;
int rc;
- flags = atomic_read(dst_vcpu->arch.local_int.cpuflags);
- if (!(flags & CPUSTAT_STOPPED)) {
+ if (!kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED)) {
*reg &= 0xffffffff00000000UL;
*reg |= SIGP_STATUS_INCORRECT_STATE;
return SIGP_CC_STATUS_STORED;
static int __sigp_sense_running(struct kvm_vcpu *vcpu,
struct kvm_vcpu *dst_vcpu, u64 *reg)
{
- struct kvm_s390_local_interrupt *li;
int rc;
if (!test_kvm_facility(vcpu->kvm, 9)) {
return SIGP_CC_STATUS_STORED;
}
- li = &dst_vcpu->arch.local_int;
- if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+ if (kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_RUNNING)) {
/* running */
rc = SIGP_CC_ORDER_CODE_ACCEPTED;
} else {
* the same offset as that in struct sie_page!
*/
struct mcck_volatile_info mcck_info; /* 0x0200 */
- /* the pinned originial scb */
+ /*
+ * The pinned original scb. Be aware that other VCPUs can modify
+ * it while we read from it. Values that are used for conditions or
+ * are reused conditionally, should be accessed via READ_ONCE.
+ */
struct kvm_s390_sie_block *scb_o; /* 0x0218 */
/* the shadow gmap in use by the vsie_page */
struct gmap *gmap; /* 0x0220 */
/* address of the last reported fault to guest2 */
unsigned long fault_addr; /* 0x0228 */
- __u8 reserved[0x0700 - 0x0230]; /* 0x0230 */
+ /* calculated guest addresses of satellite control blocks */
+ gpa_t sca_gpa; /* 0x0230 */
+ gpa_t itdba_gpa; /* 0x0238 */
+ gpa_t gvrd_gpa; /* 0x0240 */
+ gpa_t riccbd_gpa; /* 0x0248 */
+ gpa_t sdnx_gpa; /* 0x0250 */
+ __u8 reserved[0x0700 - 0x0258]; /* 0x0258 */
struct kvm_s390_crypto_cb crycb; /* 0x0700 */
__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */
};
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
- u32 crycb_addr = scb_o->crycbd & 0x7ffffff8U;
+ const uint32_t crycbd_o = READ_ONCE(scb_o->crycbd);
+ const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
unsigned long *b1, *b2;
u8 ecb3_flags;
scb_s->crycbd = 0;
- if (!(scb_o->crycbd & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
+ if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
return 0;
/* format-1 is supported with message-security-assist extension 3 */
if (!test_kvm_facility(vcpu->kvm, 76))
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+ /* READ_ONCE does not work on bitfields - use a temporary variable */
+ const uint32_t __new_ibc = scb_o->ibc;
+ const uint32_t new_ibc = READ_ONCE(__new_ibc) & 0x0fffU;
__u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU;
scb_s->ibc = 0;
/* ibc installed in g2 and requested for g3 */
- if (vcpu->kvm->arch.model.ibc && (scb_o->ibc & 0x0fffU)) {
- scb_s->ibc = scb_o->ibc & 0x0fffU;
+ if (vcpu->kvm->arch.model.ibc && new_ibc) {
+ scb_s->ibc = new_ibc;
/* takte care of the minimum ibc level of the machine */
if (scb_s->ibc < min_ibc)
scb_s->ibc = min_ibc;
{
struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+ /* READ_ONCE does not work on bitfields - use a temporary variable */
+ const uint32_t __new_prefix = scb_o->prefix;
+ const uint32_t new_prefix = READ_ONCE(__new_prefix);
+ const bool wants_tx = READ_ONCE(scb_o->ecb) & ECB_TE;
bool had_tx = scb_s->ecb & ECB_TE;
unsigned long new_mso = 0;
int rc;
scb_s->icpua = scb_o->icpua;
if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM))
- new_mso = scb_o->mso & 0xfffffffffff00000UL;
+ new_mso = READ_ONCE(scb_o->mso) & 0xfffffffffff00000UL;
/* if the hva of the prefix changes, we have to remap the prefix */
- if (scb_s->mso != new_mso || scb_s->prefix != scb_o->prefix)
+ if (scb_s->mso != new_mso || scb_s->prefix != new_prefix)
prefix_unmapped(vsie_page);
/* SIE will do mso/msl validity and exception checks for us */
scb_s->msl = scb_o->msl & 0xfffffffffff00000UL;
scb_s->mso = new_mso;
- scb_s->prefix = scb_o->prefix;
+ scb_s->prefix = new_prefix;
/* We have to definetly flush the tlb if this scb never ran */
if (scb_s->ihcpu != 0xffffU)
if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
/* transactional execution */
- if (test_kvm_facility(vcpu->kvm, 73)) {
+ if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
/* remap the prefix is tx is toggled on */
- if ((scb_o->ecb & ECB_TE) && !had_tx)
+ if (!had_tx)
prefix_unmapped(vsie_page);
- scb_s->ecb |= scb_o->ecb & ECB_TE;
+ scb_s->ecb |= ECB_TE;
}
/* branch prediction */
if (test_kvm_facility(vcpu->kvm, 82))
/* unpin all blocks previously pinned by pin_blocks(), marking them dirty */
static void unpin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
- struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
hpa_t hpa;
- gpa_t gpa;
hpa = (u64) scb_s->scaoh << 32 | scb_s->scaol;
if (hpa) {
- gpa = scb_o->scaol & ~0xfUL;
- if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
- gpa |= (u64) scb_o->scaoh << 32;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->sca_gpa, hpa);
+ vsie_page->sca_gpa = 0;
scb_s->scaol = 0;
scb_s->scaoh = 0;
}
hpa = scb_s->itdba;
if (hpa) {
- gpa = scb_o->itdba & ~0xffUL;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->itdba_gpa, hpa);
+ vsie_page->itdba_gpa = 0;
scb_s->itdba = 0;
}
hpa = scb_s->gvrd;
if (hpa) {
- gpa = scb_o->gvrd & ~0x1ffUL;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->gvrd_gpa, hpa);
+ vsie_page->gvrd_gpa = 0;
scb_s->gvrd = 0;
}
hpa = scb_s->riccbd;
if (hpa) {
- gpa = scb_o->riccbd & ~0x3fUL;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->riccbd_gpa, hpa);
+ vsie_page->riccbd_gpa = 0;
scb_s->riccbd = 0;
}
hpa = scb_s->sdnxo;
if (hpa) {
- gpa = scb_o->sdnxo;
- unpin_guest_page(vcpu->kvm, gpa, hpa);
+ unpin_guest_page(vcpu->kvm, vsie_page->sdnx_gpa, hpa);
+ vsie_page->sdnx_gpa = 0;
scb_s->sdnxo = 0;
}
}
gpa_t gpa;
int rc = 0;
- gpa = scb_o->scaol & ~0xfUL;
+ gpa = READ_ONCE(scb_o->scaol) & ~0xfUL;
if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
- gpa |= (u64) scb_o->scaoh << 32;
+ gpa |= (u64) READ_ONCE(scb_o->scaoh) << 32;
if (gpa) {
if (!(gpa & ~0x1fffUL))
rc = set_validity_icpt(scb_s, 0x0038U);
}
if (rc)
goto unpin;
+ vsie_page->sca_gpa = gpa;
scb_s->scaoh = (u32)((u64)hpa >> 32);
scb_s->scaol = (u32)(u64)hpa;
}
- gpa = scb_o->itdba & ~0xffUL;
+ gpa = READ_ONCE(scb_o->itdba) & ~0xffUL;
if (gpa && (scb_s->ecb & ECB_TE)) {
if (!(gpa & ~0x1fffU)) {
rc = set_validity_icpt(scb_s, 0x0080U);
rc = set_validity_icpt(scb_s, 0x0080U);
goto unpin;
}
+ vsie_page->itdba_gpa = gpa;
scb_s->itdba = hpa;
}
- gpa = scb_o->gvrd & ~0x1ffUL;
+ gpa = READ_ONCE(scb_o->gvrd) & ~0x1ffUL;
if (gpa && (scb_s->eca & ECA_VX) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
if (!(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x1310U);
rc = set_validity_icpt(scb_s, 0x1310U);
goto unpin;
}
+ vsie_page->gvrd_gpa = gpa;
scb_s->gvrd = hpa;
}
- gpa = scb_o->riccbd & ~0x3fUL;
+ gpa = READ_ONCE(scb_o->riccbd) & ~0x3fUL;
if (gpa && (scb_s->ecb3 & ECB3_RI)) {
if (!(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x0043U);
goto unpin;
}
/* Validity 0x0044 will be checked by SIE */
+ vsie_page->riccbd_gpa = gpa;
scb_s->riccbd = hpa;
}
if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
unsigned long sdnxc;
- gpa = scb_o->sdnxo & ~0xfUL;
- sdnxc = scb_o->sdnxo & 0xfUL;
+ gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL;
+ sdnxc = READ_ONCE(scb_o->sdnxo) & 0xfUL;
if (!gpa || !(gpa & ~0x1fffUL)) {
rc = set_validity_icpt(scb_s, 0x10b0U);
goto unpin;
rc = set_validity_icpt(scb_s, 0x10b0U);
goto unpin;
}
+ vsie_page->sdnx_gpa = gpa;
scb_s->sdnxo = hpa | sdnxc;
}
return 0;
static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
{
struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
- __u32 fac = vsie_page->scb_o->fac & 0x7ffffff8U;
+ __u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;
if (fac && test_kvm_facility(vcpu->kvm, 7)) {
retry_vsie_icpt(vsie_page);
* External calls have to lead to a kick of the vcpu and
* therefore the vsie -> Simulate Wait state.
*/
- atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
/*
* We have to adjust the g3 epoch by the g2 epoch. The epoch will
* automatically be adjusted on tod clock changes via kvm_sync_clock.
*/
static void unregister_shadow_scb(struct kvm_vcpu *vcpu)
{
- atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+ kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
WRITE_ONCE(vcpu->arch.vsie_block, NULL);
}
* @ptl: pointer to the spinlock pointer
*
* Returns a pointer to the locked pte for a guest address, or NULL
- *
- * Note: Can also be called for shadow gmaps.
*/
static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr,
spinlock_t **ptl)
{
unsigned long *table;
- if (gmap_is_shadow(gmap))
- spin_lock(&gmap->guest_table_lock);
+ BUG_ON(gmap_is_shadow(gmap));
/* Walk the gmap page table, lock and get pte pointer */
table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */
- if (!table || *table & _SEGMENT_ENTRY_INVALID) {
- if (gmap_is_shadow(gmap))
- spin_unlock(&gmap->guest_table_lock);
+ if (!table || *table & _SEGMENT_ENTRY_INVALID)
return NULL;
- }
- if (gmap_is_shadow(gmap)) {
- *ptl = &gmap->guest_table_lock;
- return pte_offset_map((pmd_t *) table, gaddr);
- }
return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl);
}
* -EFAULT if gaddr is invalid (or mapping for shadows is missing).
*
* Called with sg->mm->mmap_sem in read.
- *
- * Note: Can also be called for shadow gmaps.
*/
static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
unsigned long len, int prot, unsigned long bits)
pte_t *ptep;
int rc;
+ BUG_ON(gmap_is_shadow(gmap));
while (len) {
rc = -EAGAIN;
ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
* @val: pointer to the unsigned long value to return
*
* Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT
- * if reading using the virtual address failed.
+ * if reading using the virtual address failed. -EINVAL if called on a gmap
+ * shadow.
*
* Called with gmap->mm->mmap_sem in read.
*/
pte_t *ptep, pte;
int rc;
+ if (gmap_is_shadow(gmap))
+ return -EINVAL;
+
while (1) {
rc = -EAGAIN;
ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
}
/**
- * gmap_protect_rmap - modify access rights to memory and create an rmap
+ * gmap_protect_rmap - restrict access rights to memory (RO) and create an rmap
* @sg: pointer to the shadow guest address space structure
* @raddr: rmap address in the shadow gmap
* @paddr: address in the parent guest address space
* @len: length of the memory area to protect
- * @prot: indicates access rights: none, read-only or read-write
*
* Returns 0 if successfully protected and the rmap was created, -ENOMEM
* if out of memory and -EFAULT if paddr is invalid.
*/
static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr,
- unsigned long paddr, unsigned long len, int prot)
+ unsigned long paddr, unsigned long len)
{
struct gmap *parent;
struct gmap_rmap *rmap;
ptep = gmap_pte_op_walk(parent, paddr, &ptl);
if (ptep) {
spin_lock(&sg->guest_table_lock);
- rc = ptep_force_prot(parent->mm, paddr, ptep, prot,
+ rc = ptep_force_prot(parent->mm, paddr, ptep, PROT_READ,
PGSTE_VSIE_BIT);
if (!rc)
gmap_insert_rmap(sg, vmaddr, rmap);
radix_tree_preload_end();
if (rc) {
kfree(rmap);
- rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot);
+ rc = gmap_pte_op_fixup(parent, paddr, vmaddr, PROT_READ);
if (rc)
return rc;
continue;
origin = r2t & _REGION_ENTRY_ORIGIN;
offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
- rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 4);
origin = r3t & _REGION_ENTRY_ORIGIN;
offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
- rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 3);
origin = sgt & _REGION_ENTRY_ORIGIN;
offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE;
len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset;
- rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin + offset, len);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 2);
/* Make pgt read-only in parent gmap page table (not the pgste) */
raddr = (saddr & _SEGMENT_MASK) | _SHADOW_RMAP_SEGMENT;
origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK;
- rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE, PROT_READ);
+ rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE);
spin_lock(&sg->guest_table_lock);
if (!rc) {
table = gmap_table_walk(sg, saddr, 1);
* Called with sg->parent->shadow_lock.
*/
static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr,
- unsigned long gaddr, pte_t *pte)
+ unsigned long gaddr)
{
struct gmap_rmap *rmap, *rnext, *head;
unsigned long start, end, bits, raddr;
spin_lock(&gmap->shadow_lock);
list_for_each_entry_safe(sg, next,
&gmap->children, list)
- gmap_shadow_notify(sg, vmaddr, gaddr, pte);
+ gmap_shadow_notify(sg, vmaddr, gaddr);
spin_unlock(&gmap->shadow_lock);
}
if (bits & PGSTE_IN_BIT)
#ifndef __SPARC_POLL_H
#define __SPARC_POLL_H
-#ifndef __KERNEL__
#define POLLWRNORM POLLOUT
-#define POLLWRBAND (__force __poll_t)256
-#define POLLMSG (__force __poll_t)512
-#define POLLREMOVE (__force __poll_t)1024
-#define POLLRDHUP (__force __poll_t)2048
-#else
-#define __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- __u16 v = (__force __u16)val;
- /* bit 9 -> bit 8, bit 8 -> bit 2, bit 13 -> bit 11 */
- return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6) |
- ((v & 0x2000) >> 2);
-
-
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
- return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
- ((v & 4) << 6) | ((v & 0x800) << 2));
-}
-#endif
+#define POLLWRBAND 256
+#define POLLMSG 512
+#define POLLREMOVE 1024
+#define POLLRDHUP 2048
#include <asm-generic/poll.h>
struct file *file;
int first_chunk = 1;
char *ptr = req->request.data;
+ loff_t pos = 0;
ptr += strlen("proc");
ptr = skip_spaces(ptr);
}
do {
- len = kernel_read(file, buf, PAGE_SIZE - 1, &file->f_pos);
+ len = kernel_read(file, buf, PAGE_SIZE - 1, &pos);
if (len < 0) {
mconsole_reply(req, "Read of file failed", 1, 0);
goto out_free;
{
unsigned int j;
- state->lens[0] = 0;
- state->lens[1] = 1;
- state->lens[2] = 2;
- state->lens[3] = 3;
+ /* initially all lanes are unused */
+ state->lens[0] = 0xFFFFFFFF00000000;
+ state->lens[1] = 0xFFFFFFFF00000001;
+ state->lens[2] = 0xFFFFFFFF00000002;
+ state->lens[3] = 0xFFFFFFFF00000003;
+
state->unused_lanes = 0xFF03020100;
for (j = 0; j < 4; j++)
state->ldata[j].job_in_lane = NULL;
BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
hyperv_vector_handler)
+BUILD_INTERRUPT3(hyperv_reenlightenment_vector, HYPERV_REENLIGHTENMENT_VECTOR,
+ hyperv_reenlightenment_intr)
+
#endif /* CONFIG_HYPERV */
ENTRY(page_fault)
#if IS_ENABLED(CONFIG_HYPERV)
apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
hyperv_callback_vector hyperv_vector_handler
+
+apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
+ hyperv_reenlightenment_vector hyperv_reenlightenment_intr
#endif /* CONFIG_HYPERV */
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
*/
#include <linux/types.h>
+#include <asm/apic.h>
+#include <asm/desc.h>
#include <asm/hypervisor.h>
#include <asm/hyperv.h>
#include <asm/mshyperv.h>
{
return tsc_pg;
}
+EXPORT_SYMBOL_GPL(hv_get_tsc_page);
static u64 read_hv_clock_tsc(struct clocksource *arg)
{
return 0;
}
+static void (*hv_reenlightenment_cb)(void);
+
+static void hv_reenlightenment_notify(struct work_struct *dummy)
+{
+ struct hv_tsc_emulation_status emu_status;
+
+ rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+
+ /* Don't issue the callback if TSC accesses are not emulated */
+ if (hv_reenlightenment_cb && emu_status.inprogress)
+ hv_reenlightenment_cb();
+}
+static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify);
+
+void hyperv_stop_tsc_emulation(void)
+{
+ u64 freq;
+ struct hv_tsc_emulation_status emu_status;
+
+ rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ emu_status.inprogress = 0;
+ wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+
+ rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+ tsc_khz = div64_u64(freq, 1000);
+}
+EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
+
+static inline bool hv_reenlightenment_available(void)
+{
+ /*
+ * Check for required features and priviliges to make TSC frequency
+ * change notifications work.
+ */
+ return ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
+ ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE &&
+ ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT;
+}
+
+__visible void __irq_entry hyperv_reenlightenment_intr(struct pt_regs *regs)
+{
+ entering_ack_irq();
+
+ inc_irq_stat(irq_hv_reenlightenment_count);
+
+ schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
+
+ exiting_irq();
+}
+
+void set_hv_tscchange_cb(void (*cb)(void))
+{
+ struct hv_reenlightenment_control re_ctrl = {
+ .vector = HYPERV_REENLIGHTENMENT_VECTOR,
+ .enabled = 1,
+ .target_vp = hv_vp_index[smp_processor_id()]
+ };
+ struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
+
+ if (!hv_reenlightenment_available()) {
+ pr_warn("Hyper-V: reenlightenment support is unavailable\n");
+ return;
+ }
+
+ hv_reenlightenment_cb = cb;
+
+ /* Make sure callback is registered before we write to MSRs */
+ wmb();
+
+ wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
+}
+EXPORT_SYMBOL_GPL(set_hv_tscchange_cb);
+
+void clear_hv_tscchange_cb(void)
+{
+ struct hv_reenlightenment_control re_ctrl;
+
+ if (!hv_reenlightenment_available())
+ return;
+
+ rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+ re_ctrl.enabled = 0;
+ wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+
+ hv_reenlightenment_cb = NULL;
+}
+EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb);
+
+static int hv_cpu_die(unsigned int cpu)
+{
+ struct hv_reenlightenment_control re_ctrl;
+ unsigned int new_cpu;
+
+ if (hv_reenlightenment_cb == NULL)
+ return 0;
+
+ rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ if (re_ctrl.target_vp == hv_vp_index[cpu]) {
+ /* Reassign to some other online CPU */
+ new_cpu = cpumask_any_but(cpu_online_mask, cpu);
+
+ re_ctrl.target_vp = hv_vp_index[new_cpu];
+ wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ }
+
+ return 0;
+}
+
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
*/
void hyperv_init(void)
{
- u64 guest_id;
+ u64 guest_id, required_msrs;
union hv_x64_msr_hypercall_contents hypercall_msr;
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
return;
+ /* Absolutely required MSRs */
+ required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE |
+ HV_X64_MSR_VP_INDEX_AVAILABLE;
+
+ if ((ms_hyperv.features & required_msrs) != required_msrs)
+ return;
+
/* Allocate percpu VP index */
hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
GFP_KERNEL);
return;
if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
- hv_cpu_init, NULL) < 0)
+ hv_cpu_init, hv_cpu_die) < 0)
goto free_vp_index;
/*
#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
+#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */
#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
unsigned int irq_hv_callback_count;
#endif
+#if IS_ENABLED(CONFIG_HYPERV)
+ unsigned int irq_hv_reenlightenment_count;
+#endif
} ____cacheline_aligned irq_cpustat_t;
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
#endif
#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef
-#define LOCAL_TIMER_VECTOR 0xee
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR 0xee
+#endif
+
+#define LOCAL_TIMER_VECTOR 0xed
#define NR_VECTORS 256
| X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
| X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
| X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
- | X86_CR4_SMAP | X86_CR4_PKE))
+ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
int mp_state;
u64 ia32_misc_enable_msr;
u64 smbase;
+ u64 smi_count;
bool tpr_access_reporting;
u64 ia32_xss;
KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */
};
+struct kvm_sev_info {
+ bool active; /* SEV enabled guest */
+ unsigned int asid; /* ASID used for this guest */
+ unsigned int handle; /* SEV firmware handle */
+ int fd; /* SEV device fd */
+ unsigned long pages_locked; /* Number of pages locked */
+ struct list_head regions_list; /* List of registered regions */
+};
+
struct kvm_arch {
unsigned int n_used_mmu_pages;
unsigned int n_requested_mmu_pages;
bool x2apic_format;
bool x2apic_broadcast_quirk_disabled;
+
+ struct kvm_sev_info sev_info;
};
struct kvm_vm_stat {
u64 request_irq_exits;
u64 irq_exits;
u64 host_state_reload;
- u64 efer_reload;
u64 fpu_reload;
u64 insn_emulation;
u64 insn_emulation_fail;
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
- void (*tlb_flush)(struct kvm_vcpu *vcpu);
+ void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
void (*run)(struct kvm_vcpu *vcpu);
int (*handle_exit)(struct kvm_vcpu *vcpu);
void (*handle_external_intr)(struct kvm_vcpu *vcpu);
bool (*mpx_supported)(void);
bool (*xsaves_supported)(void);
+ bool (*umip_emulated)(void);
int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
+
+ int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
+ int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+ int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
};
struct kvm_arch_async_pf {
#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)
void hyperv_callback_vector(void);
+void hyperv_reenlightenment_vector(void);
#ifdef CONFIG_TRACING
#define trace_hyperv_callback_vector hyperv_callback_vector
#endif
void hyperv_report_panic(struct pt_regs *regs, long err);
bool hv_is_hyperv_initialized(void);
void hyperv_cleanup(void);
+
+void hyperv_reenlightenment_intr(struct pt_regs *regs);
+void set_hv_tscchange_cb(void (*cb)(void));
+void clear_hv_tscchange_cb(void);
+void hyperv_stop_tsc_emulation(void);
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
static inline bool hv_is_hyperv_initialized(void) { return false; }
static inline void hyperv_cleanup(void) {}
static inline void hyperv_setup_mmu_ops(void) {}
+static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
+static inline void clear_hv_tscchange_cb(void) {}
+static inline void hyperv_stop_tsc_emulation(void) {};
#endif /* CONFIG_HYPERV */
#ifdef CONFIG_HYPERV_TSCPAGE
struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+ u64 *cur_tsc)
{
- u64 scale, offset, cur_tsc;
+ u64 scale, offset;
u32 sequence;
/*
scale = READ_ONCE(tsc_pg->tsc_scale);
offset = READ_ONCE(tsc_pg->tsc_offset);
- cur_tsc = rdtsc_ordered();
+ *cur_tsc = rdtsc_ordered();
/*
* Make sure we read sequence after we read all other values
} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
- return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+ return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
+}
+
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+ u64 cur_tsc;
+
+ return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
}
#else
{
return NULL;
}
+
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+ u64 *cur_tsc)
+{
+ BUG();
+ return U64_MAX;
+}
#endif
#endif
#define MSR_K7_PERFCTR3 0xc0010007
#define MSR_K7_CLK_CTL 0xc001001b
#define MSR_K7_HWCR 0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT 0
+#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
void io_free_memtype(resource_size_t start, resource_size_t end);
+bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
+
#endif /* _ASM_X86_PAT_H */
#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
+#define SVM_NESTED_CTL_NP_ENABLE BIT(0)
+#define SVM_NESTED_CTL_SEV_ENABLE BIT(1)
+
struct __attribute__ ((__packed__)) vmcb_seg {
u16 selector;
u16 attrib;
*/
#define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11)
+/* AccessReenlightenmentControls privilege */
+#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13)
+
/*
* Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
* and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
#define HV_X64_MSR_CRASH_PARAMS \
(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
+/* TSC emulation after migration */
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
+
+struct hv_reenlightenment_control {
+ u64 vector:8;
+ u64 reserved1:8;
+ u64 enabled:1;
+ u64 reserved2:15;
+ u64 target_vp:32;
+};
+
+#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107
+#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108
+
+struct hv_tsc_emulation_control {
+ u64 enabled:1;
+ u64 reserved:63;
+};
+
+struct hv_tsc_emulation_status {
+ u64 inprogress:1;
+ u64 reserved:63;
+};
+
#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \
#define KVM_FEATURE_STEAL_TIME 5
#define KVM_FEATURE_PV_EOI 6
#define KVM_FEATURE_PV_UNHALT 7
+#define KVM_FEATURE_PV_TLB_FLUSH 9
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
__u32 pad[11];
};
+#define KVM_VCPU_PREEMPTED (1 << 0)
+#define KVM_VCPU_FLUSH_TLB (1 << 1)
+
#define KVM_CLOCK_PAIRING_WALLCLOCK 0
struct kvm_clock_pairing {
__s64 sec;
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/efi-bgrt.h>
+#include <linux/serial_core.h>
#include <asm/e820/api.h>
#include <asm/irqdomain.h>
if (!acpi_noirq)
x86_init.pci.init = pci_acpi_init;
+ /* Do not enable ACPI SPCR console by default */
+ acpi_parse_spcr(earlycon_acpi_spcr_enable, false);
return 0;
}
return 0;
poll_wait(fp, &apm_waitqueue, wait);
if (!queue_empty(as))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
if (HZ != 100)
idle_period = (idle_period * HZ) / 100;
if (idle_threshold < 100) {
+ cpuidle_poll_state_init(&apm_idle_driver);
if (!cpuidle_register_driver(&apm_idle_driver))
if (cpuidle_register_device(&apm_cpuidle_device))
cpuidle_unregister_driver(&apm_idle_driver);
}
}
+static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
+{
+ u64 msr;
+
+ /*
+ * BIOS support is required for SME and SEV.
+ * For SME: If BIOS has enabled SME then adjust x86_phys_bits by
+ * the SME physical address space reduction value.
+ * If BIOS has not enabled SME then don't advertise the
+ * SME feature (set in scattered.c).
+ * For SEV: If BIOS has not enabled SEV then don't advertise the
+ * SEV feature (set in scattered.c).
+ *
+ * In all cases, since support for SME and SEV requires long mode,
+ * don't advertise the feature under CONFIG_X86_32.
+ */
+ if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
+ /* Check if memory encryption is enabled */
+ rdmsrl(MSR_K8_SYSCFG, msr);
+ if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+ goto clear_all;
+
+ /*
+ * Always adjust physical address bits. Even though this
+ * will be a value above 32-bits this is still done for
+ * CONFIG_X86_32 so that accurate values are reported.
+ */
+ c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
+
+ if (IS_ENABLED(CONFIG_X86_32))
+ goto clear_all;
+
+ rdmsrl(MSR_K7_HWCR, msr);
+ if (!(msr & MSR_K7_HWCR_SMMLOCK))
+ goto clear_sev;
+
+ return;
+
+clear_all:
+ clear_cpu_cap(c, X86_FEATURE_SME);
+clear_sev:
+ clear_cpu_cap(c, X86_FEATURE_SEV);
+ }
+}
+
static void early_init_amd(struct cpuinfo_x86 *c)
{
u32 dummy;
if (cpu_has_amd_erratum(c, amd_erratum_400))
set_cpu_bug(c, X86_BUG_AMD_E400);
- /*
- * BIOS support is required for SME. If BIOS has enabled SME then
- * adjust x86_phys_bits by the SME physical address space reduction
- * value. If BIOS has not enabled SME then don't advertise the
- * feature (set in scattered.c). Also, since the SME support requires
- * long mode, don't advertise the feature under CONFIG_X86_32.
- */
- if (cpu_has(c, X86_FEATURE_SME)) {
- u64 msr;
-
- /* Check if SME is enabled */
- rdmsrl(MSR_K8_SYSCFG, msr);
- if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) {
- c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f;
- if (IS_ENABLED(CONFIG_X86_32))
- clear_cpu_cap(c, X86_FEATURE_SME);
- } else {
- clear_cpu_cap(c, X86_FEATURE_SME);
- }
- }
+ early_detect_mem_encrypt(c);
}
static void init_amd_k8(struct cpuinfo_x86 *c)
{
poll_wait(file, &mce_chrdev_wait, wait);
if (READ_ONCE(mcelog.next))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (!mce_apei_read_done && apei_check_mce())
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
hyperv_setup_mmu_ops();
/* Setup the IDT for hypervisor callback */
alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
+ /* Setup the IDT for reenlightenment notifications */
+ if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT)
+ alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR,
+ hyperv_reenlightenment_vector);
+
#endif
}
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
{ X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 },
+ { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 },
{ 0, 0, 0, 0, 0 }
};
irq_stats(j)->irq_hv_callback_count);
seq_puts(p, " Hypervisor callback interrupts\n");
}
+#endif
+#if IS_ENABLED(CONFIG_HYPERV)
+ if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) {
+ seq_printf(p, "%*s: ", prec, "HRE");
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ",
+ irq_stats(j)->irq_hv_reenlightenment_count);
+ seq_puts(p, " Hyper-V reenlightenment interrupts\n");
+ }
#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
update_intr_gate(X86_TRAP_PF, async_page_fault);
}
+static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask);
+
+static void kvm_flush_tlb_others(const struct cpumask *cpumask,
+ const struct flush_tlb_info *info)
+{
+ u8 state;
+ int cpu;
+ struct kvm_steal_time *src;
+ struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask);
+
+ cpumask_copy(flushmask, cpumask);
+ /*
+ * We have to call flush only on online vCPUs. And
+ * queue flush_on_enter for pre-empted vCPUs
+ */
+ for_each_cpu(cpu, flushmask) {
+ src = &per_cpu(steal_time, cpu);
+ state = READ_ONCE(src->preempted);
+ if ((state & KVM_VCPU_PREEMPTED)) {
+ if (try_cmpxchg(&src->preempted, &state,
+ state | KVM_VCPU_FLUSH_TLB))
+ __cpumask_clear_cpu(cpu, flushmask);
+ }
+ }
+
+ native_flush_tlb_others(flushmask, info);
+}
+
static void __init kvm_guest_init(void)
{
int i;
pv_time_ops.steal_clock = kvm_steal_clock;
}
+ if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+ pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
+
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
apic_set_eoi_write(kvm_guest_apic_eoi_write);
}
arch_initcall(activate_jump_labels);
+static __init int kvm_setup_pv_tlb_flush(void)
+{
+ int cpu;
+
+ if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+ for_each_possible_cpu(cpu) {
+ zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+ }
+ pr_info("KVM setup pv remote TLB flush\n");
+ }
+
+ return 0;
+}
+arch_initcall(kvm_setup_pv_tlb_flush);
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
{
struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
- return !!src->preempted;
+ return !!(src->preempted & KVM_VCPU_PREEMPTED);
}
PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
To compile this as a module, choose M here: the module
will be called kvm-amd.
+config KVM_AMD_SEV
+ def_bool y
+ bool "AMD Secure Encrypted Virtualization (SEV) support"
+ depends on KVM_AMD && X86_64
+ depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP
+ ---help---
+ Provides support for launching Encrypted VMs on AMD processors.
+
config KVM_MMU_AUDIT
bool "Audit KVM MMU"
depends on KVM && TRACEPOINTS
{
switch (func) {
case 0:
- entry->eax = 1; /* only one leaf currently */
+ entry->eax = 7;
++*nent;
break;
case 1:
entry->ecx = F(MOVBE);
++*nent;
break;
+ case 7:
+ entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ if (index == 0)
+ entry->ecx = F(RDPID);
+ ++*nent;
default:
break;
}
unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0;
unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
+ unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
/* cpuid 1.edx */
const u32 kvm_cpuid_1_edx_x86_features =
F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) |
- 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
+ 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) |
+ F(TOPOEXT);
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
/* cpuid 7.0.ecx*/
const u32 kvm_cpuid_7_0_ecx_x86_features =
- F(AVX512VBMI) | F(LA57) | F(PKU) |
- 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ);
+ F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
+ F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
+ F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG);
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
entry->ebx |= F(TSC_ADJUST);
entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
cpuid_mask(&entry->ecx, CPUID_7_ECX);
+ entry->ecx |= f_umip;
/* PKU is not yet implemented for shadow paging. */
if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
entry->ecx &= ~F(PKU);
(1 << KVM_FEATURE_ASYNC_PF) |
(1 << KVM_FEATURE_PV_EOI) |
(1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
- (1 << KVM_FEATURE_PV_UNHALT);
+ (1 << KVM_FEATURE_PV_UNHALT) |
+ (1 << KVM_FEATURE_PV_TLB_FLUSH);
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
entry->edx = 0;
break;
case 0x80000000:
- entry->eax = min(entry->eax, 0x8000001a);
+ entry->eax = min(entry->eax, 0x8000001f);
break;
case 0x80000001:
entry->edx &= kvm_cpuid_8000_0001_edx_x86_features;
return X86EMUL_CONTINUE;
}
+static int em_rdpid(struct x86_emulate_ctxt *ctxt)
+{
+ u64 tsc_aux = 0;
+
+ if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux))
+ return emulate_gp(ctxt, 0);
+ ctxt->dst.val = tsc_aux;
+ return X86EMUL_CONTINUE;
+}
+
static int em_rdtsc(struct x86_emulate_ctxt *ctxt)
{
u64 tsc = 0;
return X86EMUL_CONTINUE;
}
-static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt)
+static int em_store_sreg(struct x86_emulate_ctxt *ctxt, int segment)
{
- if (ctxt->modrm_reg > VCPU_SREG_GS)
- return emulate_ud(ctxt);
+ if (segment > VCPU_SREG_GS &&
+ (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) &&
+ ctxt->ops->cpl(ctxt) > 0)
+ return emulate_gp(ctxt, 0);
- ctxt->dst.val = get_segment_selector(ctxt, ctxt->modrm_reg);
+ ctxt->dst.val = get_segment_selector(ctxt, segment);
if (ctxt->dst.bytes == 4 && ctxt->dst.type == OP_MEM)
ctxt->dst.bytes = 2;
return X86EMUL_CONTINUE;
}
+static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt)
+{
+ if (ctxt->modrm_reg > VCPU_SREG_GS)
+ return emulate_ud(ctxt);
+
+ return em_store_sreg(ctxt, ctxt->modrm_reg);
+}
+
static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt)
{
u16 sel = ctxt->src.val;
return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg);
}
+static int em_sldt(struct x86_emulate_ctxt *ctxt)
+{
+ return em_store_sreg(ctxt, VCPU_SREG_LDTR);
+}
+
static int em_lldt(struct x86_emulate_ctxt *ctxt)
{
u16 sel = ctxt->src.val;
return load_segment_descriptor(ctxt, sel, VCPU_SREG_LDTR);
}
+static int em_str(struct x86_emulate_ctxt *ctxt)
+{
+ return em_store_sreg(ctxt, VCPU_SREG_TR);
+}
+
static int em_ltr(struct x86_emulate_ctxt *ctxt)
{
u16 sel = ctxt->src.val;
{
struct desc_ptr desc_ptr;
+ if ((ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) &&
+ ctxt->ops->cpl(ctxt) > 0)
+ return emulate_gp(ctxt, 0);
+
if (ctxt->mode == X86EMUL_MODE_PROT64)
ctxt->op_bytes = 8;
get(ctxt, &desc_ptr);
static int em_smsw(struct x86_emulate_ctxt *ctxt)
{
+ if ((ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) &&
+ ctxt->ops->cpl(ctxt) > 0)
+ return emulate_gp(ctxt, 0);
+
if (ctxt->dst.type == OP_MEM)
ctxt->dst.bytes = 2;
ctxt->dst.val = ctxt->ops->get_cr(ctxt, 0);
};
static const struct opcode group6[] = {
- DI(Prot | DstMem, sldt),
- DI(Prot | DstMem, str),
+ II(Prot | DstMem, em_sldt, sldt),
+ II(Prot | DstMem, em_str, str),
II(Prot | Priv | SrcMem16, em_lldt, lldt),
II(Prot | Priv | SrcMem16, em_ltr, ltr),
N, N, N, N,
F(DstMem | SrcImmByte | Lock | PageTable, em_btc),
};
+/*
+ * The "memory" destination is actually always a register, since we come
+ * from the register case of group9.
+ */
+static const struct gprefix pfx_0f_c7_7 = {
+ N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp),
+};
+
+
static const struct group_dual group9 = { {
N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N,
}, {
- N, N, N, N, N, N, N, N,
+ N, N, N, N, N, N, N,
+ GP(0, &pfx_0f_c7_7),
} };
static const struct opcode group11[] = {
if (kvm_cpu_has_extint(v))
return 1;
- if (kvm_vcpu_apicv_active(v))
+ if (!is_guest_mode(v) && kvm_vcpu_apicv_active(v))
return 0;
return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
return count;
}
-int __kvm_apic_update_irr(u32 *pir, void *regs)
+bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
{
u32 i, vec;
- u32 pir_val, irr_val;
- int max_irr = -1;
+ u32 pir_val, irr_val, prev_irr_val;
+ int max_updated_irr;
+
+ max_updated_irr = -1;
+ *max_irr = -1;
for (i = vec = 0; i <= 7; i++, vec += 32) {
pir_val = READ_ONCE(pir[i]);
irr_val = *((u32 *)(regs + APIC_IRR + i * 0x10));
if (pir_val) {
+ prev_irr_val = irr_val;
irr_val |= xchg(&pir[i], 0);
*((u32 *)(regs + APIC_IRR + i * 0x10)) = irr_val;
+ if (prev_irr_val != irr_val) {
+ max_updated_irr =
+ __fls(irr_val ^ prev_irr_val) + vec;
+ }
}
if (irr_val)
- max_irr = __fls(irr_val) + vec;
+ *max_irr = __fls(irr_val) + vec;
}
- return max_irr;
+ return ((max_updated_irr != -1) &&
+ (max_updated_irr == *max_irr));
}
EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
-int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- return __kvm_apic_update_irr(pir, apic->regs);
+ return __kvm_apic_update_irr(pir, apic->regs, max_irr);
}
EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
{
int highest_irr;
- if (kvm_x86_ops->sync_pir_to_irr && apic->vcpu->arch.apicv_active)
+ if (apic->vcpu->arch.apicv_active)
highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu);
else
highest_irr = apic_find_highest_irr(apic);
bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, unsigned int dest, int dest_mode);
-int __kvm_apic_update_irr(u32 *pir, void *regs);
-int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
+bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
#include <linux/kern_levels.h>
#include <asm/page.h>
+#include <asm/pat.h>
#include <asm/cmpxchg.h>
#include <asm/io.h>
#include <asm/vmx.h>
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
-void kvm_mmu_clear_all_pte_masks(void)
+static void kvm_mmu_clear_all_pte_masks(void)
{
shadow_user_mask = 0;
shadow_accessed_mask = 0;
static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
{
if (pfn_valid(pfn))
- return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+ return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) &&
+ /*
+ * Some reserved pages, such as those from NVDIMM
+ * DAX devices, are not for MMIO, and can be mapped
+ * with cached memory type for better performance.
+ * However, the above check misconceives those pages
+ * as MMIO, and results in KVM mapping them with UC
+ * memory type, which would hurt the performance.
+ * Therefore, we check the host memory type in addition
+ * and only treat UC/UC-/WC pages as MMIO.
+ */
+ (!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn));
return true;
}
if (mmio_info_in_cache(vcpu, cr2, direct))
emulation_type = 0;
emulate:
+ /*
+ * On AMD platforms, under certain conditions insn_len may be zero on #NPF.
+ * This can happen if a guest gets a page-fault on data access but the HW
+ * table walker is not able to read the instruction page (e.g instruction
+ * page is not present in memory). In those cases we simply restart the
+ * guest.
+ */
+ if (unlikely(insn && !insn_len))
+ return 1;
+
er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
switch (er) {
#include <linux/ratelimit.h>
-char const *audit_point_name[] = {
+static char const *audit_point_name[] = {
"pre page fault",
"post page fault",
"pre pte write",
#include <linux/amd-iommu.h>
#include <linux/hashtable.h>
#include <linux/frame.h>
+#include <linux/psp-sev.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
#include <asm/apic.h>
#include <asm/perf_event.h>
*/
struct list_head ir_list;
spinlock_t ir_list_lock;
+
+ /* which host CPU was used for running this vcpu */
+ unsigned int last_cpu;
};
/*
static int vgif = true;
module_param(vgif, int, 0444);
+/* enable/disable SEV support */
+static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT);
+module_param(sev, int, 0444);
+
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-static void svm_flush_tlb(struct kvm_vcpu *vcpu);
+static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
static void svm_complete_interrupts(struct vcpu_svm *svm);
static int nested_svm_exit_handled(struct vcpu_svm *svm);
#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
+static unsigned int max_sev_asid;
+static unsigned int min_sev_asid;
+static unsigned long *sev_asid_bitmap;
+#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
+
+struct enc_region {
+ struct list_head list;
+ unsigned long npages;
+ struct page **pages;
+ unsigned long uaddr;
+ unsigned long size;
+};
+
+static inline bool svm_sev_enabled(void)
+{
+ return max_sev_asid;
+}
+
+static inline bool sev_guest(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+
+ return sev->active;
+}
+
+static inline int sev_get_asid(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+
+ return sev->asid;
+}
+
static inline void mark_all_dirty(struct vmcb *vmcb)
{
vmcb->control.clean = 0;
u64 asid_generation;
u32 max_asid;
u32 next_asid;
+ u32 min_asid;
struct kvm_ldttss_desc *tss_desc;
struct page *save_area;
struct vmcb *current_vmcb;
+
+ /* index = sev_asid, value = vmcb pointer */
+ struct vmcb **sev_vmcbs;
};
static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
sd->asid_generation = 1;
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
+ sd->min_asid = max_sev_asid + 1;
gdt = get_current_gdt_rw();
sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
return;
per_cpu(svm_data, raw_smp_processor_id()) = NULL;
+ kfree(sd->sev_vmcbs);
__free_page(sd->save_area);
kfree(sd);
}
if (!sd)
return -ENOMEM;
sd->cpu = cpu;
- sd->save_area = alloc_page(GFP_KERNEL);
r = -ENOMEM;
+ sd->save_area = alloc_page(GFP_KERNEL);
if (!sd->save_area)
goto err_1;
+ if (svm_sev_enabled()) {
+ r = -ENOMEM;
+ sd->sev_vmcbs = kmalloc((max_sev_asid + 1) * sizeof(void *), GFP_KERNEL);
+ if (!sd->sev_vmcbs)
+ goto err_1;
+ }
+
per_cpu(svm_data, cpu) = sd;
return 0;
return 0;
}
+static __init int sev_hardware_setup(void)
+{
+ struct sev_user_data_status *status;
+ int rc;
+
+ /* Maximum number of encrypted guests supported simultaneously */
+ max_sev_asid = cpuid_ecx(0x8000001F);
+
+ if (!max_sev_asid)
+ return 1;
+
+ /* Minimum ASID value that should be used for SEV guest */
+ min_sev_asid = cpuid_edx(0x8000001F);
+
+ /* Initialize SEV ASID bitmap */
+ sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid),
+ sizeof(unsigned long), GFP_KERNEL);
+ if (!sev_asid_bitmap)
+ return 1;
+
+ status = kmalloc(sizeof(*status), GFP_KERNEL);
+ if (!status)
+ return 1;
+
+ /*
+ * Check SEV platform status.
+ *
+ * PLATFORM_STATUS can be called in any state, if we failed to query
+ * the PLATFORM status then either PSP firmware does not support SEV
+ * feature or SEV firmware is dead.
+ */
+ rc = sev_platform_status(status, NULL);
+ if (rc)
+ goto err;
+
+ pr_info("SEV supported\n");
+
+err:
+ kfree(status);
+ return rc;
+}
+
static __init int svm_hardware_setup(void)
{
int cpu;
kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
}
+ if (sev) {
+ if (boot_cpu_has(X86_FEATURE_SEV) &&
+ IS_ENABLED(CONFIG_KVM_AMD_SEV)) {
+ r = sev_hardware_setup();
+ if (r)
+ sev = false;
+ } else {
+ sev = false;
+ }
+ }
+
for_each_possible_cpu(cpu) {
r = svm_cpu_init(cpu);
if (r)
{
int cpu;
+ if (svm_sev_enabled())
+ kfree(sev_asid_bitmap);
+
for_each_possible_cpu(cpu)
svm_cpu_uninit(cpu);
if (npt_enabled) {
/* Setup VMCB for Nested Paging */
- control->nested_ctl = 1;
+ control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE;
clr_intercept(svm, INTERCEPT_INVLPG);
clr_exception_intercept(svm, PF_VECTOR);
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
}
+ if (sev_guest(svm->vcpu.kvm)) {
+ svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
+ clr_exception_intercept(svm, UD_VECTOR);
+ }
+
mark_all_dirty(svm->vmcb);
enable_gif(svm);
return 0;
}
+static void __sev_asid_free(int asid)
+{
+ struct svm_cpu_data *sd;
+ int cpu, pos;
+
+ pos = asid - 1;
+ clear_bit(pos, sev_asid_bitmap);
+
+ for_each_possible_cpu(cpu) {
+ sd = per_cpu(svm_data, cpu);
+ sd->sev_vmcbs[pos] = NULL;
+ }
+}
+
+static void sev_asid_free(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+
+ __sev_asid_free(sev->asid);
+}
+
+static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
+{
+ struct sev_data_decommission *decommission;
+ struct sev_data_deactivate *data;
+
+ if (!handle)
+ return;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return;
+
+ /* deactivate handle */
+ data->handle = handle;
+ sev_guest_deactivate(data, NULL);
+
+ wbinvd_on_all_cpus();
+ sev_guest_df_flush(NULL);
+ kfree(data);
+
+ decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
+ if (!decommission)
+ return;
+
+ /* decommission handle */
+ decommission->handle = handle;
+ sev_guest_decommission(decommission, NULL);
+
+ kfree(decommission);
+}
+
+static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
+ unsigned long ulen, unsigned long *n,
+ int write)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ unsigned long npages, npinned, size;
+ unsigned long locked, lock_limit;
+ struct page **pages;
+ int first, last;
+
+ /* Calculate number of pages. */
+ first = (uaddr & PAGE_MASK) >> PAGE_SHIFT;
+ last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT;
+ npages = (last - first + 1);
+
+ locked = sev->pages_locked + npages;
+ lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
+ pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit);
+ return NULL;
+ }
+
+ /* Avoid using vmalloc for smaller buffers. */
+ size = npages * sizeof(struct page *);
+ if (size > PAGE_SIZE)
+ pages = vmalloc(size);
+ else
+ pages = kmalloc(size, GFP_KERNEL);
+
+ if (!pages)
+ return NULL;
+
+ /* Pin the user virtual address. */
+ npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
+ if (npinned != npages) {
+ pr_err("SEV: Failure locking %lu pages.\n", npages);
+ goto err;
+ }
+
+ *n = npages;
+ sev->pages_locked = locked;
+
+ return pages;
+
+err:
+ if (npinned > 0)
+ release_pages(pages, npinned);
+
+ kvfree(pages);
+ return NULL;
+}
+
+static void sev_unpin_memory(struct kvm *kvm, struct page **pages,
+ unsigned long npages)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+
+ release_pages(pages, npages);
+ kvfree(pages);
+ sev->pages_locked -= npages;
+}
+
+static void sev_clflush_pages(struct page *pages[], unsigned long npages)
+{
+ uint8_t *page_virtual;
+ unsigned long i;
+
+ if (npages == 0 || pages == NULL)
+ return;
+
+ for (i = 0; i < npages; i++) {
+ page_virtual = kmap_atomic(pages[i]);
+ clflush_cache_range(page_virtual, PAGE_SIZE);
+ kunmap_atomic(page_virtual);
+ }
+}
+
+static void __unregister_enc_region_locked(struct kvm *kvm,
+ struct enc_region *region)
+{
+ /*
+ * The guest may change the memory encryption attribute from C=0 -> C=1
+ * or vice versa for this memory range. Lets make sure caches are
+ * flushed to ensure that guest data gets written into memory with
+ * correct C-bit.
+ */
+ sev_clflush_pages(region->pages, region->npages);
+
+ sev_unpin_memory(kvm, region->pages, region->npages);
+ list_del(®ion->list);
+ kfree(region);
+}
+
+static void sev_vm_destroy(struct kvm *kvm)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct list_head *head = &sev->regions_list;
+ struct list_head *pos, *q;
+
+ if (!sev_guest(kvm))
+ return;
+
+ mutex_lock(&kvm->lock);
+
+ /*
+ * if userspace was terminated before unregistering the memory regions
+ * then lets unpin all the registered memory.
+ */
+ if (!list_empty(head)) {
+ list_for_each_safe(pos, q, head) {
+ __unregister_enc_region_locked(kvm,
+ list_entry(pos, struct enc_region, list));
+ }
+ }
+
+ mutex_unlock(&kvm->lock);
+
+ sev_unbind_asid(kvm, sev->handle);
+ sev_asid_free(kvm);
+}
+
static void avic_vm_destroy(struct kvm *kvm)
{
unsigned long flags;
spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
}
+static void svm_vm_destroy(struct kvm *kvm)
+{
+ avic_vm_destroy(kvm);
+ sev_vm_destroy(kvm);
+}
+
static int avic_vm_init(struct kvm *kvm)
{
unsigned long flags;
return 1;
if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
vcpu->arch.cr4 = cr4;
if (!npt_enabled)
{
if (sd->next_asid > sd->max_asid) {
++sd->asid_generation;
- sd->next_asid = 1;
+ sd->next_asid = sd->min_asid;
svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
}
static int pf_interception(struct vcpu_svm *svm)
{
- u64 fault_address = svm->vmcb->control.exit_info_2;
+ u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
u64 error_code = svm->vmcb->control.exit_info_1;
return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address,
- svm->vmcb->control.insn_bytes,
+ static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
+ svm->vmcb->control.insn_bytes : NULL,
svm->vmcb->control.insn_len);
}
static int npf_interception(struct vcpu_svm *svm)
{
- u64 fault_address = svm->vmcb->control.exit_info_2;
+ u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
u64 error_code = svm->vmcb->control.exit_info_1;
trace_kvm_page_fault(fault_address, error_code);
return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code,
- svm->vmcb->control.insn_bytes,
+ static_cpu_has(X86_FEATURE_DECODEASSISTS) ?
+ svm->vmcb->control.insn_bytes : NULL,
svm->vmcb->control.insn_len);
}
svm->vmcb->control.nested_cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_NPT);
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
}
static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
if (vmcb->control.asid == 0)
return false;
- if (vmcb->control.nested_ctl && !npt_enabled)
+ if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) &&
+ !npt_enabled)
return false;
return true;
else
svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
- if (nested_vmcb->control.nested_ctl) {
+ if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) {
kvm_mmu_unload(&svm->vcpu);
svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3;
nested_svm_init_mmu_context(&svm->vcpu);
svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions;
svm->nested.intercept = nested_vmcb->control.intercept;
- svm_flush_tlb(&svm->vcpu);
+ svm_flush_tlb(&svm->vcpu, true);
svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
svm->vcpu.arch.hflags |= HF_VINTR_MASK;
load_TR_desc();
}
+static void pre_sev_run(struct vcpu_svm *svm, int cpu)
+{
+ struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ int asid = sev_get_asid(svm->vcpu.kvm);
+
+ /* Assign the asid allocated with this SEV guest */
+ svm->vmcb->control.asid = asid;
+
+ /*
+ * Flush guest TLB:
+ *
+ * 1) when different VMCB for the same ASID is to be run on the same host CPU.
+ * 2) or this VMCB was executed on different host CPU in previous VMRUNs.
+ */
+ if (sd->sev_vmcbs[asid] == svm->vmcb &&
+ svm->last_cpu == cpu)
+ return;
+
+ svm->last_cpu = cpu;
+ sd->sev_vmcbs[asid] = svm->vmcb;
+ svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
+ mark_dirty(svm->vmcb, VMCB_ASID);
+}
+
static void pre_svm_run(struct vcpu_svm *svm)
{
int cpu = raw_smp_processor_id();
struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ if (sev_guest(svm->vcpu.kvm))
+ return pre_sev_run(svm, cpu);
+
/* FIXME: handle wraparound of asid_generation */
if (svm->asid_generation != sd->asid_generation)
new_asid(svm, sd);
return 0;
}
-static void svm_flush_tlb(struct kvm_vcpu *vcpu)
+static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
{
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->save.cr3 = __sme_set(root);
mark_dirty(svm->vmcb, VMCB_CR);
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
}
static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
svm->vmcb->save.cr3 = kvm_read_cr3(vcpu);
mark_dirty(svm->vmcb, VMCB_CR);
- svm_flush_tlb(vcpu);
+ svm_flush_tlb(vcpu, true);
}
static int is_disabled(void)
entry->edx |= SVM_FEATURE_NPT;
break;
+ case 0x8000001F:
+ /* Support memory encryption cpuid if host supports it */
+ if (boot_cpu_has(X86_FEATURE_SEV))
+ cpuid(0x8000001f, &entry->eax, &entry->ebx,
+ &entry->ecx, &entry->edx);
+
}
}
return false;
}
+static bool svm_umip_emulated(void)
+{
+ return false;
+}
+
static bool svm_has_wbinvd_exit(void)
{
return true;
return 0;
}
+static int sev_asid_new(void)
+{
+ int pos;
+
+ /*
+ * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
+ */
+ pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
+ if (pos >= max_sev_asid)
+ return -EBUSY;
+
+ set_bit(pos, sev_asid_bitmap);
+ return pos + 1;
+}
+
+static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ int asid, ret;
+
+ ret = -EBUSY;
+ asid = sev_asid_new();
+ if (asid < 0)
+ return ret;
+
+ ret = sev_platform_init(&argp->error);
+ if (ret)
+ goto e_free;
+
+ sev->active = true;
+ sev->asid = asid;
+ INIT_LIST_HEAD(&sev->regions_list);
+
+ return 0;
+
+e_free:
+ __sev_asid_free(asid);
+ return ret;
+}
+
+static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
+{
+ struct sev_data_activate *data;
+ int asid = sev_get_asid(kvm);
+ int ret;
+
+ wbinvd_on_all_cpus();
+
+ ret = sev_guest_df_flush(error);
+ if (ret)
+ return ret;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* activate ASID on the given handle */
+ data->handle = handle;
+ data->asid = asid;
+ ret = sev_guest_activate(data, error);
+ kfree(data);
+
+ return ret;
+}
+
+static int __sev_issue_cmd(int fd, int id, void *data, int *error)
+{
+ struct fd f;
+ int ret;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = sev_issue_cmd_external_user(f.file, id, data, error);
+
+ fdput(f);
+ return ret;
+}
+
+static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+
+ return __sev_issue_cmd(sev->fd, id, data, error);
+}
+
+static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct sev_data_launch_start *start;
+ struct kvm_sev_launch_start params;
+ void *dh_blob, *session_blob;
+ int *error = &argp->error;
+ int ret;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ return -EFAULT;
+
+ start = kzalloc(sizeof(*start), GFP_KERNEL);
+ if (!start)
+ return -ENOMEM;
+
+ dh_blob = NULL;
+ if (params.dh_uaddr) {
+ dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len);
+ if (IS_ERR(dh_blob)) {
+ ret = PTR_ERR(dh_blob);
+ goto e_free;
+ }
+
+ start->dh_cert_address = __sme_set(__pa(dh_blob));
+ start->dh_cert_len = params.dh_len;
+ }
+
+ session_blob = NULL;
+ if (params.session_uaddr) {
+ session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len);
+ if (IS_ERR(session_blob)) {
+ ret = PTR_ERR(session_blob);
+ goto e_free_dh;
+ }
+
+ start->session_address = __sme_set(__pa(session_blob));
+ start->session_len = params.session_len;
+ }
+
+ start->handle = params.handle;
+ start->policy = params.policy;
+
+ /* create memory encryption context */
+ ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, start, error);
+ if (ret)
+ goto e_free_session;
+
+ /* Bind ASID to this guest */
+ ret = sev_bind_asid(kvm, start->handle, error);
+ if (ret)
+ goto e_free_session;
+
+ /* return handle to userspace */
+ params.handle = start->handle;
+ if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) {
+ sev_unbind_asid(kvm, start->handle);
+ ret = -EFAULT;
+ goto e_free_session;
+ }
+
+ sev->handle = start->handle;
+ sev->fd = argp->sev_fd;
+
+e_free_session:
+ kfree(session_blob);
+e_free_dh:
+ kfree(dh_blob);
+e_free:
+ kfree(start);
+ return ret;
+}
+
+static int get_num_contig_pages(int idx, struct page **inpages,
+ unsigned long npages)
+{
+ unsigned long paddr, next_paddr;
+ int i = idx + 1, pages = 1;
+
+ /* find the number of contiguous pages starting from idx */
+ paddr = __sme_page_pa(inpages[idx]);
+ while (i < npages) {
+ next_paddr = __sme_page_pa(inpages[i++]);
+ if ((paddr + PAGE_SIZE) == next_paddr) {
+ pages++;
+ paddr = next_paddr;
+ continue;
+ }
+ break;
+ }
+
+ return pages;
+}
+
+static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ unsigned long vaddr, vaddr_end, next_vaddr, npages, size;
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct kvm_sev_launch_update_data params;
+ struct sev_data_launch_update_data *data;
+ struct page **inpages;
+ int i, ret, pages;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ return -EFAULT;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ vaddr = params.uaddr;
+ size = params.len;
+ vaddr_end = vaddr + size;
+
+ /* Lock the user memory. */
+ inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1);
+ if (!inpages) {
+ ret = -ENOMEM;
+ goto e_free;
+ }
+
+ /*
+ * The LAUNCH_UPDATE command will perform in-place encryption of the
+ * memory content (i.e it will write the same memory region with C=1).
+ * It's possible that the cache may contain the data with C=0, i.e.,
+ * unencrypted so invalidate it first.
+ */
+ sev_clflush_pages(inpages, npages);
+
+ for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) {
+ int offset, len;
+
+ /*
+ * If the user buffer is not page-aligned, calculate the offset
+ * within the page.
+ */
+ offset = vaddr & (PAGE_SIZE - 1);
+
+ /* Calculate the number of pages that can be encrypted in one go. */
+ pages = get_num_contig_pages(i, inpages, npages);
+
+ len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size);
+
+ data->handle = sev->handle;
+ data->len = len;
+ data->address = __sme_page_pa(inpages[i]) + offset;
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error);
+ if (ret)
+ goto e_unpin;
+
+ size -= len;
+ next_vaddr = vaddr + len;
+ }
+
+e_unpin:
+ /* content of memory is updated, mark pages dirty */
+ for (i = 0; i < npages; i++) {
+ set_page_dirty_lock(inpages[i]);
+ mark_page_accessed(inpages[i]);
+ }
+ /* unlock the user pages */
+ sev_unpin_memory(kvm, inpages, npages);
+e_free:
+ kfree(data);
+ return ret;
+}
+
+static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct sev_data_launch_measure *data;
+ struct kvm_sev_launch_measure params;
+ void *blob = NULL;
+ int ret;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ return -EFAULT;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* User wants to query the blob length */
+ if (!params.len)
+ goto cmd;
+
+ if (params.uaddr) {
+ if (params.len > SEV_FW_BLOB_MAX_SIZE) {
+ ret = -EINVAL;
+ goto e_free;
+ }
+
+ if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) {
+ ret = -EFAULT;
+ goto e_free;
+ }
+
+ ret = -ENOMEM;
+ blob = kmalloc(params.len, GFP_KERNEL);
+ if (!blob)
+ goto e_free;
+
+ data->address = __psp_pa(blob);
+ data->len = params.len;
+ }
+
+cmd:
+ data->handle = sev->handle;
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, data, &argp->error);
+
+ /*
+ * If we query the session length, FW responded with expected data.
+ */
+ if (!params.len)
+ goto done;
+
+ if (ret)
+ goto e_free_blob;
+
+ if (blob) {
+ if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len))
+ ret = -EFAULT;
+ }
+
+done:
+ params.len = data->len;
+ if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params)))
+ ret = -EFAULT;
+e_free_blob:
+ kfree(blob);
+e_free:
+ kfree(data);
+ return ret;
+}
+
+static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct sev_data_launch_finish *data;
+ int ret;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->handle = sev->handle;
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error);
+
+ kfree(data);
+ return ret;
+}
+
+static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct kvm_sev_guest_status params;
+ struct sev_data_guest_status *data;
+ int ret;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->handle = sev->handle;
+ ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error);
+ if (ret)
+ goto e_free;
+
+ params.policy = data->policy;
+ params.state = data->state;
+ params.handle = data->handle;
+
+ if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params)))
+ ret = -EFAULT;
+e_free:
+ kfree(data);
+ return ret;
+}
+
+static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src,
+ unsigned long dst, int size,
+ int *error, bool enc)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct sev_data_dbg *data;
+ int ret;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->handle = sev->handle;
+ data->dst_addr = dst;
+ data->src_addr = src;
+ data->len = size;
+
+ ret = sev_issue_cmd(kvm,
+ enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT,
+ data, error);
+ kfree(data);
+ return ret;
+}
+
+static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
+ unsigned long dst_paddr, int sz, int *err)
+{
+ int offset;
+
+ /*
+ * Its safe to read more than we are asked, caller should ensure that
+ * destination has enough space.
+ */
+ src_paddr = round_down(src_paddr, 16);
+ offset = src_paddr & 15;
+ sz = round_up(sz + offset, 16);
+
+ return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
+}
+
+static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr,
+ unsigned long __user dst_uaddr,
+ unsigned long dst_paddr,
+ int size, int *err)
+{
+ struct page *tpage = NULL;
+ int ret, offset;
+
+ /* if inputs are not 16-byte then use intermediate buffer */
+ if (!IS_ALIGNED(dst_paddr, 16) ||
+ !IS_ALIGNED(paddr, 16) ||
+ !IS_ALIGNED(size, 16)) {
+ tpage = (void *)alloc_page(GFP_KERNEL);
+ if (!tpage)
+ return -ENOMEM;
+
+ dst_paddr = __sme_page_pa(tpage);
+ }
+
+ ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err);
+ if (ret)
+ goto e_free;
+
+ if (tpage) {
+ offset = paddr & 15;
+ if (copy_to_user((void __user *)(uintptr_t)dst_uaddr,
+ page_address(tpage) + offset, size))
+ ret = -EFAULT;
+ }
+
+e_free:
+ if (tpage)
+ __free_page(tpage);
+
+ return ret;
+}
+
+static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr,
+ unsigned long __user vaddr,
+ unsigned long dst_paddr,
+ unsigned long __user dst_vaddr,
+ int size, int *error)
+{
+ struct page *src_tpage = NULL;
+ struct page *dst_tpage = NULL;
+ int ret, len = size;
+
+ /* If source buffer is not aligned then use an intermediate buffer */
+ if (!IS_ALIGNED(vaddr, 16)) {
+ src_tpage = alloc_page(GFP_KERNEL);
+ if (!src_tpage)
+ return -ENOMEM;
+
+ if (copy_from_user(page_address(src_tpage),
+ (void __user *)(uintptr_t)vaddr, size)) {
+ __free_page(src_tpage);
+ return -EFAULT;
+ }
+
+ paddr = __sme_page_pa(src_tpage);
+ }
+
+ /*
+ * If destination buffer or length is not aligned then do read-modify-write:
+ * - decrypt destination in an intermediate buffer
+ * - copy the source buffer in an intermediate buffer
+ * - use the intermediate buffer as source buffer
+ */
+ if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) {
+ int dst_offset;
+
+ dst_tpage = alloc_page(GFP_KERNEL);
+ if (!dst_tpage) {
+ ret = -ENOMEM;
+ goto e_free;
+ }
+
+ ret = __sev_dbg_decrypt(kvm, dst_paddr,
+ __sme_page_pa(dst_tpage), size, error);
+ if (ret)
+ goto e_free;
+
+ /*
+ * If source is kernel buffer then use memcpy() otherwise
+ * copy_from_user().
+ */
+ dst_offset = dst_paddr & 15;
+
+ if (src_tpage)
+ memcpy(page_address(dst_tpage) + dst_offset,
+ page_address(src_tpage), size);
+ else {
+ if (copy_from_user(page_address(dst_tpage) + dst_offset,
+ (void __user *)(uintptr_t)vaddr, size)) {
+ ret = -EFAULT;
+ goto e_free;
+ }
+ }
+
+ paddr = __sme_page_pa(dst_tpage);
+ dst_paddr = round_down(dst_paddr, 16);
+ len = round_up(size, 16);
+ }
+
+ ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true);
+
+e_free:
+ if (src_tpage)
+ __free_page(src_tpage);
+ if (dst_tpage)
+ __free_page(dst_tpage);
+ return ret;
+}
+
+static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
+{
+ unsigned long vaddr, vaddr_end, next_vaddr;
+ unsigned long dst_vaddr, dst_vaddr_end;
+ struct page **src_p, **dst_p;
+ struct kvm_sev_dbg debug;
+ unsigned long n;
+ int ret, size;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
+ return -EFAULT;
+
+ vaddr = debug.src_uaddr;
+ size = debug.len;
+ vaddr_end = vaddr + size;
+ dst_vaddr = debug.dst_uaddr;
+ dst_vaddr_end = dst_vaddr + size;
+
+ for (; vaddr < vaddr_end; vaddr = next_vaddr) {
+ int len, s_off, d_off;
+
+ /* lock userspace source and destination page */
+ src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0);
+ if (!src_p)
+ return -EFAULT;
+
+ dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1);
+ if (!dst_p) {
+ sev_unpin_memory(kvm, src_p, n);
+ return -EFAULT;
+ }
+
+ /*
+ * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the
+ * memory content (i.e it will write the same memory region with C=1).
+ * It's possible that the cache may contain the data with C=0, i.e.,
+ * unencrypted so invalidate it first.
+ */
+ sev_clflush_pages(src_p, 1);
+ sev_clflush_pages(dst_p, 1);
+
+ /*
+ * Since user buffer may not be page aligned, calculate the
+ * offset within the page.
+ */
+ s_off = vaddr & ~PAGE_MASK;
+ d_off = dst_vaddr & ~PAGE_MASK;
+ len = min_t(size_t, (PAGE_SIZE - s_off), size);
+
+ if (dec)
+ ret = __sev_dbg_decrypt_user(kvm,
+ __sme_page_pa(src_p[0]) + s_off,
+ dst_vaddr,
+ __sme_page_pa(dst_p[0]) + d_off,
+ len, &argp->error);
+ else
+ ret = __sev_dbg_encrypt_user(kvm,
+ __sme_page_pa(src_p[0]) + s_off,
+ vaddr,
+ __sme_page_pa(dst_p[0]) + d_off,
+ dst_vaddr,
+ len, &argp->error);
+
+ sev_unpin_memory(kvm, src_p, 1);
+ sev_unpin_memory(kvm, dst_p, 1);
+
+ if (ret)
+ goto err;
+
+ next_vaddr = vaddr + len;
+ dst_vaddr = dst_vaddr + len;
+ size -= len;
+ }
+err:
+ return ret;
+}
+
+static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct sev_data_launch_secret *data;
+ struct kvm_sev_launch_secret params;
+ struct page **pages;
+ void *blob, *hdr;
+ unsigned long n;
+ int ret;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+ return -EFAULT;
+
+ pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1);
+ if (!pages)
+ return -ENOMEM;
+
+ /*
+ * The secret must be copied into contiguous memory region, lets verify
+ * that userspace memory pages are contiguous before we issue command.
+ */
+ if (get_num_contig_pages(0, pages, n) != n) {
+ ret = -EINVAL;
+ goto e_unpin_memory;
+ }
+
+ ret = -ENOMEM;
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ goto e_unpin_memory;
+
+ blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len);
+ if (IS_ERR(blob)) {
+ ret = PTR_ERR(blob);
+ goto e_free;
+ }
+
+ data->trans_address = __psp_pa(blob);
+ data->trans_len = params.trans_len;
+
+ hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len);
+ if (IS_ERR(hdr)) {
+ ret = PTR_ERR(hdr);
+ goto e_free_blob;
+ }
+ data->trans_address = __psp_pa(blob);
+ data->trans_len = params.trans_len;
+
+ data->handle = sev->handle;
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error);
+
+ kfree(hdr);
+
+e_free_blob:
+ kfree(blob);
+e_free:
+ kfree(data);
+e_unpin_memory:
+ sev_unpin_memory(kvm, pages, n);
+ return ret;
+}
+
+static int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
+{
+ struct kvm_sev_cmd sev_cmd;
+ int r;
+
+ if (!svm_sev_enabled())
+ return -ENOTTY;
+
+ if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd)))
+ return -EFAULT;
+
+ mutex_lock(&kvm->lock);
+
+ switch (sev_cmd.id) {
+ case KVM_SEV_INIT:
+ r = sev_guest_init(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_LAUNCH_START:
+ r = sev_launch_start(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_LAUNCH_UPDATE_DATA:
+ r = sev_launch_update_data(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_LAUNCH_MEASURE:
+ r = sev_launch_measure(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_LAUNCH_FINISH:
+ r = sev_launch_finish(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_GUEST_STATUS:
+ r = sev_guest_status(kvm, &sev_cmd);
+ break;
+ case KVM_SEV_DBG_DECRYPT:
+ r = sev_dbg_crypt(kvm, &sev_cmd, true);
+ break;
+ case KVM_SEV_DBG_ENCRYPT:
+ r = sev_dbg_crypt(kvm, &sev_cmd, false);
+ break;
+ case KVM_SEV_LAUNCH_SECRET:
+ r = sev_launch_secret(kvm, &sev_cmd);
+ break;
+ default:
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd)))
+ r = -EFAULT;
+
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int svm_register_enc_region(struct kvm *kvm,
+ struct kvm_enc_region *range)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct enc_region *region;
+ int ret = 0;
+
+ if (!sev_guest(kvm))
+ return -ENOTTY;
+
+ region = kzalloc(sizeof(*region), GFP_KERNEL);
+ if (!region)
+ return -ENOMEM;
+
+ region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1);
+ if (!region->pages) {
+ ret = -ENOMEM;
+ goto e_free;
+ }
+
+ /*
+ * The guest may change the memory encryption attribute from C=0 -> C=1
+ * or vice versa for this memory range. Lets make sure caches are
+ * flushed to ensure that guest data gets written into memory with
+ * correct C-bit.
+ */
+ sev_clflush_pages(region->pages, region->npages);
+
+ region->uaddr = range->addr;
+ region->size = range->size;
+
+ mutex_lock(&kvm->lock);
+ list_add_tail(®ion->list, &sev->regions_list);
+ mutex_unlock(&kvm->lock);
+
+ return ret;
+
+e_free:
+ kfree(region);
+ return ret;
+}
+
+static struct enc_region *
+find_enc_region(struct kvm *kvm, struct kvm_enc_region *range)
+{
+ struct kvm_sev_info *sev = &kvm->arch.sev_info;
+ struct list_head *head = &sev->regions_list;
+ struct enc_region *i;
+
+ list_for_each_entry(i, head, list) {
+ if (i->uaddr == range->addr &&
+ i->size == range->size)
+ return i;
+ }
+
+ return NULL;
+}
+
+
+static int svm_unregister_enc_region(struct kvm *kvm,
+ struct kvm_enc_region *range)
+{
+ struct enc_region *region;
+ int ret;
+
+ mutex_lock(&kvm->lock);
+
+ if (!sev_guest(kvm)) {
+ ret = -ENOTTY;
+ goto failed;
+ }
+
+ region = find_enc_region(kvm, range);
+ if (!region) {
+ ret = -EINVAL;
+ goto failed;
+ }
+
+ __unregister_enc_region_locked(kvm, region);
+
+ mutex_unlock(&kvm->lock);
+ return 0;
+
+failed:
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.vcpu_reset = svm_vcpu_reset,
.vm_init = avic_vm_init,
- .vm_destroy = avic_vm_destroy,
+ .vm_destroy = svm_vm_destroy,
.prepare_guest_switch = svm_prepare_guest_switch,
.vcpu_load = svm_vcpu_load,
.load_eoi_exitmap = svm_load_eoi_exitmap,
.hwapic_irr_update = svm_hwapic_irr_update,
.hwapic_isr_update = svm_hwapic_isr_update,
+ .sync_pir_to_irr = kvm_lapic_find_highest_irr,
.apicv_post_state_restore = avic_post_state_restore,
.set_tss_addr = svm_set_tss_addr,
.invpcid_supported = svm_invpcid_supported,
.mpx_supported = svm_mpx_supported,
.xsaves_supported = svm_xsaves_supported,
+ .umip_emulated = svm_umip_emulated,
.set_supported_cpuid = svm_set_supported_cpuid,
.pre_enter_smm = svm_pre_enter_smm,
.pre_leave_smm = svm_pre_leave_smm,
.enable_smi_window = enable_smi_window,
+
+ .mem_enc_op = svm_mem_enc_op,
+ .mem_enc_reg_region = svm_register_enc_region,
+ .mem_enc_unreg_region = svm_unregister_enc_region,
};
static int __init svm_init(void)
*/
#define VMCS12_SIZE 0x1000
+/*
+ * VMCS12_MAX_FIELD_INDEX is the highest index value used in any
+ * supported VMCS12 field encoding.
+ */
+#define VMCS12_MAX_FIELD_INDEX 0x17
+
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu.
* data hold by vmcs12
*/
bool sync_shadow_vmcs;
+ bool dirty_vmcs12;
bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
u32 host_pkru;
+ unsigned long host_debugctlmsr;
+
/*
* Only bits masked by msr_ia32_feature_control_valid_bits can be set in
* msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
return &(to_vmx(vcpu)->pi_desc);
}
+#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n)))))
#define VMCS12_OFFSET(x) offsetof(struct vmcs12, x)
-#define FIELD(number, name) [number] = VMCS12_OFFSET(name)
-#define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \
- [number##_HIGH] = VMCS12_OFFSET(name)+4
+#define FIELD(number, name) [ROL16(number, 6)] = VMCS12_OFFSET(name)
+#define FIELD64(number, name) \
+ FIELD(number, name), \
+ [ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32)
-static unsigned long shadow_read_only_fields[] = {
- /*
- * We do NOT shadow fields that are modified when L0
- * traps and emulates any vmx instruction (e.g. VMPTRLD,
- * VMXON...) executed by L1.
- * For example, VM_INSTRUCTION_ERROR is read
- * by L1 if a vmx instruction fails (part of the error path).
- * Note the code assumes this logic. If for some reason
- * we start shadowing these fields then we need to
- * force a shadow sync when L0 emulates vmx instructions
- * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified
- * by nested_vmx_failValid)
- */
- VM_EXIT_REASON,
- VM_EXIT_INTR_INFO,
- VM_EXIT_INSTRUCTION_LEN,
- IDT_VECTORING_INFO_FIELD,
- IDT_VECTORING_ERROR_CODE,
- VM_EXIT_INTR_ERROR_CODE,
- EXIT_QUALIFICATION,
- GUEST_LINEAR_ADDRESS,
- GUEST_PHYSICAL_ADDRESS
+static u16 shadow_read_only_fields[] = {
+#define SHADOW_FIELD_RO(x) x,
+#include "vmx_shadow_fields.h"
};
static int max_shadow_read_only_fields =
ARRAY_SIZE(shadow_read_only_fields);
-static unsigned long shadow_read_write_fields[] = {
- TPR_THRESHOLD,
- GUEST_RIP,
- GUEST_RSP,
- GUEST_CR0,
- GUEST_CR3,
- GUEST_CR4,
- GUEST_INTERRUPTIBILITY_INFO,
- GUEST_RFLAGS,
- GUEST_CS_SELECTOR,
- GUEST_CS_AR_BYTES,
- GUEST_CS_LIMIT,
- GUEST_CS_BASE,
- GUEST_ES_BASE,
- GUEST_BNDCFGS,
- CR0_GUEST_HOST_MASK,
- CR0_READ_SHADOW,
- CR4_READ_SHADOW,
- TSC_OFFSET,
- EXCEPTION_BITMAP,
- CPU_BASED_VM_EXEC_CONTROL,
- VM_ENTRY_EXCEPTION_ERROR_CODE,
- VM_ENTRY_INTR_INFO_FIELD,
- VM_ENTRY_INSTRUCTION_LEN,
- VM_ENTRY_EXCEPTION_ERROR_CODE,
- HOST_FS_BASE,
- HOST_GS_BASE,
- HOST_FS_SELECTOR,
- HOST_GS_SELECTOR
+static u16 shadow_read_write_fields[] = {
+#define SHADOW_FIELD_RW(x) x,
+#include "vmx_shadow_fields.h"
};
static int max_shadow_read_write_fields =
ARRAY_SIZE(shadow_read_write_fields);
{
const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table);
unsigned short offset;
+ unsigned index;
+
+ if (field >> 15)
+ return -ENOENT;
- BUILD_BUG_ON(size > SHRT_MAX);
- if (field >= size)
+ index = ROL16(field, 6);
+ if (index >= size)
return -ENOENT;
- field = array_index_nospec(field, size);
- offset = vmcs_field_to_offset_table[field];
+ index = array_index_nospec(index, size);
+ offset = vmcs_field_to_offset_table[index];
if (offset == 0)
return -ENOENT;
return offset;
static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
enum {
- VMX_IO_BITMAP_A,
- VMX_IO_BITMAP_B,
VMX_VMREAD_BITMAP,
VMX_VMWRITE_BITMAP,
VMX_BITMAP_NR
static unsigned long *vmx_bitmap[VMX_BITMAP_NR];
-#define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A])
-#define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B])
#define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP])
#define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP])
vmx_vcpu_pi_load(vcpu, cpu);
vmx->host_pkru = read_pkru();
+ vmx->host_debugctlmsr = get_debugctlmsr();
}
static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
rdmsrl(MSR_IA32_VMX_CR4_FIXED1, vmx->nested.nested_vmx_cr4_fixed1);
/* highest index: VMX_PREEMPTION_TIMER_VALUE */
- vmx->nested.nested_vmx_vmcs_enum = 0x2e;
+ vmx->nested.nested_vmx_vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1;
}
/*
*/
static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
struct shared_msr_entry *msr;
switch (msr_info->index) {
msr_info->data = vmcs_readl(GUEST_GS_BASE);
break;
case MSR_KERNEL_GS_BASE:
- vmx_load_host_state(to_vmx(vcpu));
- msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
+ vmx_load_host_state(vmx);
+ msr_info->data = vmx->msr_guest_kernel_gs_base;
break;
#endif
case MSR_EFER:
break;
case MSR_IA32_MCG_EXT_CTL:
if (!msr_info->host_initiated &&
- !(to_vmx(vcpu)->msr_ia32_feature_control &
+ !(vmx->msr_ia32_feature_control &
FEATURE_CONTROL_LMCE))
return 1;
msr_info->data = vcpu->arch.mcg_ext_ctl;
break;
case MSR_IA32_FEATURE_CONTROL:
- msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control;
+ msr_info->data = vmx->msr_ia32_feature_control;
break;
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
if (!nested_vmx_allowed(vcpu))
return 1;
/* Otherwise falls through */
default:
- msr = find_msr_entry(to_vmx(vcpu), msr_info->index);
+ msr = find_msr_entry(vmx, msr_info->index);
if (msr) {
msr_info->data = msr->data;
break;
#endif
CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING |
- CPU_BASED_USE_IO_BITMAPS |
+ CPU_BASED_UNCOND_IO_EXITING |
CPU_BASED_MOV_DR_EXITING |
CPU_BASED_USE_TSC_OFFSETING |
CPU_BASED_INVLPG_EXITING |
SECONDARY_EXEC_ENABLE_EPT |
SECONDARY_EXEC_UNRESTRICTED_GUEST |
SECONDARY_EXEC_PAUSE_LOOP_EXITING |
+ SECONDARY_EXEC_DESC |
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_ENABLE_INVPCID |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
}
}
-enum vmcs_field_type {
- VMCS_FIELD_TYPE_U16 = 0,
- VMCS_FIELD_TYPE_U64 = 1,
- VMCS_FIELD_TYPE_U32 = 2,
- VMCS_FIELD_TYPE_NATURAL_WIDTH = 3
+enum vmcs_field_width {
+ VMCS_FIELD_WIDTH_U16 = 0,
+ VMCS_FIELD_WIDTH_U64 = 1,
+ VMCS_FIELD_WIDTH_U32 = 2,
+ VMCS_FIELD_WIDTH_NATURAL_WIDTH = 3
};
-static inline int vmcs_field_type(unsigned long field)
+static inline int vmcs_field_width(unsigned long field)
{
if (0x1 & field) /* the *_HIGH fields are all 32 bit */
- return VMCS_FIELD_TYPE_U32;
+ return VMCS_FIELD_WIDTH_U32;
return (field >> 13) & 0x3 ;
}
{
int i, j;
- /* No checks for read only fields yet */
+ for (i = j = 0; i < max_shadow_read_only_fields; i++) {
+ u16 field = shadow_read_only_fields[i];
+ if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
+ (i + 1 == max_shadow_read_only_fields ||
+ shadow_read_only_fields[i + 1] != field + 1))
+ pr_err("Missing field from shadow_read_only_field %x\n",
+ field + 1);
+
+ clear_bit(field, vmx_vmread_bitmap);
+#ifdef CONFIG_X86_64
+ if (field & 1)
+ continue;
+#endif
+ if (j < i)
+ shadow_read_only_fields[j] = field;
+ j++;
+ }
+ max_shadow_read_only_fields = j;
for (i = j = 0; i < max_shadow_read_write_fields; i++) {
- switch (shadow_read_write_fields[i]) {
- case GUEST_BNDCFGS:
- if (!kvm_mpx_supported())
+ u16 field = shadow_read_write_fields[i];
+ if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
+ (i + 1 == max_shadow_read_write_fields ||
+ shadow_read_write_fields[i + 1] != field + 1))
+ pr_err("Missing field from shadow_read_write_field %x\n",
+ field + 1);
+
+ /*
+ * PML and the preemption timer can be emulated, but the
+ * processor cannot vmwrite to fields that don't exist
+ * on bare metal.
+ */
+ switch (field) {
+ case GUEST_PML_INDEX:
+ if (!cpu_has_vmx_pml())
+ continue;
+ break;
+ case VMX_PREEMPTION_TIMER_VALUE:
+ if (!cpu_has_vmx_preemption_timer())
+ continue;
+ break;
+ case GUEST_INTR_STATUS:
+ if (!cpu_has_vmx_apicv())
continue;
break;
default:
break;
}
+ clear_bit(field, vmx_vmwrite_bitmap);
+ clear_bit(field, vmx_vmread_bitmap);
+#ifdef CONFIG_X86_64
+ if (field & 1)
+ continue;
+#endif
if (j < i)
- shadow_read_write_fields[j] =
- shadow_read_write_fields[i];
+ shadow_read_write_fields[j] = field;
j++;
}
max_shadow_read_write_fields = j;
-
- /* shadowed fields guest access without vmexit */
- for (i = 0; i < max_shadow_read_write_fields; i++) {
- unsigned long field = shadow_read_write_fields[i];
-
- clear_bit(field, vmx_vmwrite_bitmap);
- clear_bit(field, vmx_vmread_bitmap);
- if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) {
- clear_bit(field + 1, vmx_vmwrite_bitmap);
- clear_bit(field + 1, vmx_vmread_bitmap);
- }
- }
- for (i = 0; i < max_shadow_read_only_fields; i++) {
- unsigned long field = shadow_read_only_fields[i];
-
- clear_bit(field, vmx_vmread_bitmap);
- if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64)
- clear_bit(field + 1, vmx_vmread_bitmap);
- }
}
static __init int alloc_kvm_area(void)
#endif
-static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid)
+static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
+ bool invalidate_gpa)
{
- if (enable_ept) {
+ if (enable_ept && (invalidate_gpa || !enable_vpid)) {
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
}
}
-static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
+static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
{
- __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
+ __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
}
static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
{
if (enable_ept)
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
ept_load_pdptrs(vcpu);
}
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
vmcs_writel(GUEST_CR3, guest_cr3);
}
(to_vmx(vcpu)->rmode.vm86_active ?
KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+ if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+ hw_cr4 &= ~X86_CR4_UMIP;
+ } else
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+
if (cr4 & X86_CR4_VMXE) {
/*
* To use VMXON (and later other VMX instructions), a guest
{
int f = sizeof(unsigned long);
- if (!cpu_has_vmx_msr_bitmap()) {
- WARN_ON(1);
- return;
- }
-
/*
* See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
* have the write-low and read-high bitmap offsets the wrong way round.
max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
if (max_irr != 256) {
vapic_page = kmap(vmx->nested.virtual_apic_page);
- __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
+ __kvm_apic_update_irr(vmx->nested.pi_desc->pir,
+ vapic_page, &max_irr);
kunmap(vmx->nested.virtual_apic_page);
status = vmcs_read16(GUEST_INTR_STATUS);
if (is_guest_mode(vcpu) &&
vector == vmx->nested.posted_intr_nv) {
- /* the PIR and ON have been set by L1. */
- kvm_vcpu_trigger_posted_interrupt(vcpu, true);
/*
* If a posted intr is not recognized by hardware,
* we will accomplish it in the next vmentry.
*/
vmx->nested.pi_pending = true;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ /* the PIR and ON have been set by L1. */
+ if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
+ kvm_vcpu_kick(vcpu);
return 0;
}
return -1;
struct kvm_vcpu *vcpu = &vmx->vcpu;
u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
+
if (!cpu_need_virtualize_apic_accesses(vcpu))
exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if (vmx->vpid == 0)
exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+
+ /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP,
+ * in vmx_set_cr4. */
+ exec_control &= ~SECONDARY_EXEC_DESC;
+
/* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD
(handle_vmptrld).
We can NOT enable shadow_vmcs here because we don't have yet
#endif
int i;
- /* I/O */
- vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a));
- vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b));
-
if (enable_shadow_vmcs) {
vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
return kvm_set_cr4(vcpu, val);
}
+static int handle_desc(struct kvm_vcpu *vcpu)
+{
+ WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
+ return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+}
+
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
if (!is_guest_mode(vcpu) &&
!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
trace_kvm_fast_mmio(gpa);
- return kvm_skip_emulated_instruction(vcpu);
+ /*
+ * Doing kvm_skip_emulated_instruction() depends on undefined
+ * behavior: Intel's manual doesn't mandate
+ * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG
+ * occurs and while on real hardware it was observed to be set,
+ * other hypervisors (namely Hyper-V) don't set it, we end up
+ * advancing IP with some random value. Disable fast mmio when
+ * running nested and keep it for real hardware in hope that
+ * VM_EXIT_INSTRUCTION_LEN will always be set correctly.
+ */
+ if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+ return kvm_skip_emulated_instruction(vcpu);
+ else
+ return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP,
+ NULL, 0) == EMULATE_DONE;
}
ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
- memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
-
- memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
-
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
goto out;
!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
enable_vpid = 0;
- if (!cpu_has_vmx_shadow_vmcs())
- enable_shadow_vmcs = 0;
- if (enable_shadow_vmcs)
- init_vmcs_shadow_fields();
-
if (!cpu_has_vmx_ept() ||
!cpu_has_vmx_ept_4levels() ||
!cpu_has_vmx_ept_mt_wb() ||
kvm_x86_ops->cancel_hv_timer = NULL;
}
+ if (!cpu_has_vmx_shadow_vmcs())
+ enable_shadow_vmcs = 0;
+ if (enable_shadow_vmcs)
+ init_vmcs_shadow_fields();
+
kvm_set_posted_intr_wakeup_handler(wakeup_handler);
kvm_mce_cap_supported |= MCG_LMCE_P;
p = ((char *)(get_vmcs12(vcpu))) + offset;
- switch (vmcs_field_type(field)) {
- case VMCS_FIELD_TYPE_NATURAL_WIDTH:
+ switch (vmcs_field_width(field)) {
+ case VMCS_FIELD_WIDTH_NATURAL_WIDTH:
*ret = *((natural_width *)p);
return 0;
- case VMCS_FIELD_TYPE_U16:
+ case VMCS_FIELD_WIDTH_U16:
*ret = *((u16 *)p);
return 0;
- case VMCS_FIELD_TYPE_U32:
+ case VMCS_FIELD_WIDTH_U32:
*ret = *((u32 *)p);
return 0;
- case VMCS_FIELD_TYPE_U64:
+ case VMCS_FIELD_WIDTH_U64:
*ret = *((u64 *)p);
return 0;
default:
if (offset < 0)
return offset;
- switch (vmcs_field_type(field)) {
- case VMCS_FIELD_TYPE_U16:
+ switch (vmcs_field_width(field)) {
+ case VMCS_FIELD_WIDTH_U16:
*(u16 *)p = field_value;
return 0;
- case VMCS_FIELD_TYPE_U32:
+ case VMCS_FIELD_WIDTH_U32:
*(u32 *)p = field_value;
return 0;
- case VMCS_FIELD_TYPE_U64:
+ case VMCS_FIELD_WIDTH_U64:
*(u64 *)p = field_value;
return 0;
- case VMCS_FIELD_TYPE_NATURAL_WIDTH:
+ case VMCS_FIELD_WIDTH_NATURAL_WIDTH:
*(natural_width *)p = field_value;
return 0;
default:
unsigned long field;
u64 field_value;
struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
- const unsigned long *fields = shadow_read_write_fields;
+ const u16 *fields = shadow_read_write_fields;
const int num_fields = max_shadow_read_write_fields;
preempt_disable();
for (i = 0; i < num_fields; i++) {
field = fields[i];
- switch (vmcs_field_type(field)) {
- case VMCS_FIELD_TYPE_U16:
- field_value = vmcs_read16(field);
- break;
- case VMCS_FIELD_TYPE_U32:
- field_value = vmcs_read32(field);
- break;
- case VMCS_FIELD_TYPE_U64:
- field_value = vmcs_read64(field);
- break;
- case VMCS_FIELD_TYPE_NATURAL_WIDTH:
- field_value = vmcs_readl(field);
- break;
- default:
- WARN_ON(1);
- continue;
- }
+ field_value = __vmcs_readl(field);
vmcs12_write_any(&vmx->vcpu, field, field_value);
}
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
{
- const unsigned long *fields[] = {
+ const u16 *fields[] = {
shadow_read_write_fields,
shadow_read_only_fields
};
for (i = 0; i < max_fields[q]; i++) {
field = fields[q][i];
vmcs12_read_any(&vmx->vcpu, field, &field_value);
-
- switch (vmcs_field_type(field)) {
- case VMCS_FIELD_TYPE_U16:
- vmcs_write16(field, (u16)field_value);
- break;
- case VMCS_FIELD_TYPE_U32:
- vmcs_write32(field, (u32)field_value);
- break;
- case VMCS_FIELD_TYPE_U64:
- vmcs_write64(field, (u64)field_value);
- break;
- case VMCS_FIELD_TYPE_NATURAL_WIDTH:
- vmcs_writel(field, (long)field_value);
- break;
- default:
- WARN_ON(1);
- break;
- }
+ __vmcs_writel(field, field_value);
}
}
{
unsigned long field;
gva_t gva;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+
/* The value to write might be 32 or 64 bits, depending on L1's long
* mode, and eventually we need to write that into a field of several
* possible lengths. The code below first zero-extends the value to 64
return kvm_skip_emulated_instruction(vcpu);
}
+ switch (field) {
+#define SHADOW_FIELD_RW(x) case x:
+#include "vmx_shadow_fields.h"
+ /*
+ * The fields that can be updated by L1 without a vmexit are
+ * always updated in the vmcs02, the others go down the slow
+ * path of prepare_vmcs02.
+ */
+ break;
+ default:
+ vmx->nested.dirty_vmcs12 = true;
+ break;
+ }
+
nested_vmx_succeed(vcpu);
return kvm_skip_emulated_instruction(vcpu);
}
__pa(vmx->vmcs01.shadow_vmcs));
vmx->nested.sync_shadow_vmcs = true;
}
+ vmx->nested.dirty_vmcs12 = true;
}
/* Emulate the VMPTRLD instruction */
return kvm_skip_emulated_instruction(vcpu);
}
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02);
+ __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
nested_vmx_succeed(vcpu);
return kvm_skip_emulated_instruction(vcpu);
[EXIT_REASON_XSETBV] = handle_xsetbv,
[EXIT_REASON_TASK_SWITCH] = handle_task_switch,
[EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check,
+ [EXIT_REASON_GDTR_IDTR] = handle_desc,
+ [EXIT_REASON_LDTR_TR] = handle_desc,
[EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
{
- if (!is_guest_mode(vcpu)) {
- vmx_set_rvi(max_irr);
- return;
- }
-
- if (max_irr == -1)
- return;
-
- /*
- * In guest mode. If a vmexit is needed, vmx_check_nested_events
- * handles it.
- */
- if (nested_exit_on_intr(vcpu))
- return;
-
/*
- * Else, fall back to pre-APICv interrupt injection since L2
- * is run without virtual interrupt delivery.
+ * When running L2, updating RVI is only relevant when
+ * vmcs12 virtual-interrupt-delivery enabled.
+ * However, it can be enabled only when L1 also
+ * intercepts external-interrupts and in that case
+ * we should not update vmcs02 RVI but instead intercept
+ * interrupt. Therefore, do nothing when running L2.
*/
- if (!kvm_event_needs_reinjection(vcpu) &&
- vmx_interrupt_allowed(vcpu)) {
- kvm_queue_interrupt(vcpu, max_irr, false);
- vmx_inject_irq(vcpu);
- }
+ if (!is_guest_mode(vcpu))
+ vmx_set_rvi(max_irr);
}
static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int max_irr;
+ bool max_irr_updated;
WARN_ON(!vcpu->arch.apicv_active);
if (pi_test_on(&vmx->pi_desc)) {
* But on x86 this is just a compiler barrier anyway.
*/
smp_mb__after_atomic();
- max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
+ max_irr_updated =
+ kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
+
+ /*
+ * If we are running L2 and L1 has a new pending interrupt
+ * which can be injected, we should re-evaluate
+ * what should be done with this new L1 interrupt.
+ * If L1 intercepts external-interrupts, we should
+ * exit from L2 to L1. Otherwise, interrupt should be
+ * delivered directly to L2.
+ */
+ if (is_guest_mode(vcpu) && max_irr_updated) {
+ if (nested_exit_on_intr(vcpu))
+ kvm_vcpu_exiting_guest_mode(vcpu);
+ else
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
} else {
max_irr = kvm_lapic_find_highest_irr(vcpu);
}
SECONDARY_EXEC_XSAVES;
}
+static bool vmx_umip_emulated(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_DESC;
+}
+
static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long debugctlmsr, cr3, cr4;
+ unsigned long cr3, cr4;
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!enable_vnmi &&
__write_pkru(vcpu->arch.pkru);
atomic_switch_perf_msrs(vmx);
- debugctlmsr = get_debugctlmsr();
vmx_arm_hv_timer(vcpu);
vmexit_fill_RSB();
/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
- if (debugctlmsr)
- update_debugctlmsr(debugctlmsr);
+ if (vmx->host_debugctlmsr)
+ update_debugctlmsr(vmx->host_debugctlmsr);
#ifndef CONFIG_X86_64
/*
static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- int r;
- r = vcpu_load(vcpu);
- BUG_ON(r);
+ vcpu_load(vcpu);
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
free_nested(vmx);
vcpu_put(vcpu);
u32 mask =
SECONDARY_EXEC_SHADOW_VMCS |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_DESC;
u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
}
}
-static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12);
+static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12);
static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
(unsigned long)(vmcs12->posted_intr_desc_addr &
(PAGE_SIZE - 1)));
}
- if (cpu_has_vmx_msr_bitmap() &&
- nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) &&
- nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
- ;
- else
+ if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12))
vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
CPU_BASED_USE_MSR_BITMAPS);
}
* Merge L0's and L1's MSR bitmap, return false to indicate that
* we do not use the hardware.
*/
-static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12)
+static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
{
int msr;
struct page *page;
bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
+ /* Nothing to do if the MSR bitmap is not in use. */
+ if (!cpu_has_vmx_msr_bitmap() ||
+ !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+ return false;
+
if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
!pred_cmd && !spec_ctrl)
return false;
page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
if (is_error_page(page))
return false;
- msr_bitmap_l1 = (unsigned long *)kmap(page);
- memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+ msr_bitmap_l1 = (unsigned long *)kmap(page);
+ if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+ /*
+ * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
+ * just lets the processor take the value from the virtual-APIC page;
+ * take those 256 bits directly from the L1 bitmap.
+ */
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+ msr_bitmap_l0[word] = msr_bitmap_l1[word];
+ msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
+ }
+ } else {
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+ msr_bitmap_l0[word] = ~0;
+ msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
+ }
+ }
- if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
- if (nested_cpu_has_apic_reg_virt(vmcs12))
- for (msr = 0x800; msr <= 0x8ff; msr++)
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- msr, MSR_TYPE_R);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_TASKPRI),
+ MSR_TYPE_W);
+ if (nested_cpu_has_vid(vmcs12)) {
nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- APIC_BASE_MSR + (APIC_TASKPRI >> 4),
- MSR_TYPE_R | MSR_TYPE_W);
-
- if (nested_cpu_has_vid(vmcs12)) {
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- APIC_BASE_MSR + (APIC_EOI >> 4),
- MSR_TYPE_W);
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
- MSR_TYPE_W);
- }
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_EOI),
+ MSR_TYPE_W);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_SELF_IPI),
+ MSR_TYPE_W);
}
if (spec_ctrl)
return 0;
}
-/*
- * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
- * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
- * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
- * guest in a way that will both be appropriate to L1's requests, and our
- * needs. In addition to modifying the active vmcs (which is vmcs02), this
- * function also has additional necessary side-effects, like setting various
- * vcpu->arch fields.
- * Returns 0 on success, 1 on failure. Invalid state exit qualification code
- * is assigned to entry_failure_code on failure.
- */
-static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- bool from_vmentry, u32 *entry_failure_code)
+static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+ bool from_vmentry)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 exec_control, vmcs12_exec_ctrl;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
- vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
- vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
- vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
- vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
- vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+ vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+ vmcs12->guest_pending_dbg_exceptions);
+ vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
+ vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+
+ if (nested_cpu_has_xsaves(vmcs12))
+ vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
+
+ if (cpu_has_vmx_posted_intr())
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
+
+ /*
+ * Whether page-faults are trapped is determined by a combination of
+ * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
+ * If enable_ept, L0 doesn't care about page faults and we should
+ * set all of these to L1's desires. However, if !enable_ept, L0 does
+ * care about (at least some) page faults, and because it is not easy
+ * (if at all possible?) to merge L0 and L1's desires, we simply ask
+ * to exit on each and every L2 page fault. This is done by setting
+ * MASK=MATCH=0 and (see below) EB.PF=1.
+ * Note that below we don't need special code to set EB.PF beyond the
+ * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
+ * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
+ * !enable_ept, EB.PF is 1, so the "or" will always be 1.
+ */
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
+ enable_ept ? vmcs12->page_fault_error_code_mask : 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
+ enable_ept ? vmcs12->page_fault_error_code_match : 0);
+
+ /* All VMFUNCs are currently emulated through L0 vmexits. */
+ if (cpu_has_vmx_vmfunc())
+ vmcs_write64(VM_FUNCTION_CONTROL, 0);
+
+ if (cpu_has_vmx_apicv()) {
+ vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
+ vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
+ vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
+ vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
+ }
+
+ /*
+ * Set host-state according to L0's settings (vmcs12 is irrelevant here)
+ * Some constant fields are set here by vmx_set_constant_host_state().
+ * Other fields are different per CPU, and will be set later when
+ * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
+ */
+ vmx_set_constant_host_state(vmx);
+
+ /*
+ * Set the MSR load/store lists to match L0's settings.
+ */
+ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+
+ set_cr4_guest_host_mask(vmx);
+
+ if (vmx_mpx_supported())
+ vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+
+ if (enable_vpid) {
+ if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
+ else
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+ }
+
+ /*
+ * L1 may access the L2's PDPTR, so save them to construct vmcs12
+ */
+ if (enable_ept) {
+ vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+ vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+ vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+ vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ }
+
+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+}
+
+/*
+ * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
+ * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
+ * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
+ * guest in a way that will both be appropriate to L1's requests, and our
+ * needs. In addition to modifying the active vmcs (which is vmcs02), this
+ * function also has additional necessary side-effects, like setting various
+ * vcpu->arch fields.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+ bool from_vmentry, u32 *entry_failure_code)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 exec_control, vmcs12_exec_ctrl;
+
+ /*
+ * First, the fields that are shadowed. This must be kept in sync
+ * with vmx_shadow_fields.h.
+ */
+
+ vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
+ vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
+ vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
+ vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
+ vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
+
+ /*
+ * Not in vmcs02: GUEST_PML_INDEX, HOST_FS_SELECTOR, HOST_GS_SELECTOR,
+ * HOST_FS_BASE, HOST_GS_BASE.
+ */
+
if (from_vmentry &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
} else {
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}
- vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
vmx_set_rflags(vcpu, vmcs12->guest_rflags);
- vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
- vmcs12->guest_pending_dbg_exceptions);
- vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
- vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
-
- if (nested_cpu_has_xsaves(vmcs12))
- vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
- vmcs_write64(VMCS_LINK_POINTER, -1ull);
exec_control = vmcs12->pin_based_vm_exec_control;
if (nested_cpu_has_posted_intr(vmcs12)) {
vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
vmx->nested.pi_pending = false;
- vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
} else {
exec_control &= ~PIN_BASED_POSTED_INTR;
}
if (nested_cpu_has_preemption_timer(vmcs12))
vmx_start_preemption_timer(vcpu);
- /*
- * Whether page-faults are trapped is determined by a combination of
- * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
- * If enable_ept, L0 doesn't care about page faults and we should
- * set all of these to L1's desires. However, if !enable_ept, L0 does
- * care about (at least some) page faults, and because it is not easy
- * (if at all possible?) to merge L0 and L1's desires, we simply ask
- * to exit on each and every L2 page fault. This is done by setting
- * MASK=MATCH=0 and (see below) EB.PF=1.
- * Note that below we don't need special code to set EB.PF beyond the
- * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
- * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
- * !enable_ept, EB.PF is 1, so the "or" will always be 1.
- */
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
- enable_ept ? vmcs12->page_fault_error_code_mask : 0);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
- enable_ept ? vmcs12->page_fault_error_code_match : 0);
-
if (cpu_has_secondary_exec_ctrls()) {
exec_control = vmx->secondary_exec_control;
exec_control |= vmcs12_exec_ctrl;
}
- /* All VMFUNCs are currently emulated through L0 vmexits. */
- if (exec_control & SECONDARY_EXEC_ENABLE_VMFUNC)
- vmcs_write64(VM_FUNCTION_CONTROL, 0);
-
- if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
- vmcs_write64(EOI_EXIT_BITMAP0,
- vmcs12->eoi_exit_bitmap0);
- vmcs_write64(EOI_EXIT_BITMAP1,
- vmcs12->eoi_exit_bitmap1);
- vmcs_write64(EOI_EXIT_BITMAP2,
- vmcs12->eoi_exit_bitmap2);
- vmcs_write64(EOI_EXIT_BITMAP3,
- vmcs12->eoi_exit_bitmap3);
+ if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
vmcs_write16(GUEST_INTR_STATUS,
vmcs12->guest_intr_status);
- }
/*
* Write an illegal value to APIC_ACCESS_ADDR. Later,
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}
-
- /*
- * Set host-state according to L0's settings (vmcs12 is irrelevant here)
- * Some constant fields are set here by vmx_set_constant_host_state().
- * Other fields are different per CPU, and will be set later when
- * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
- */
- vmx_set_constant_host_state(vmx);
-
- /*
- * Set the MSR load/store lists to match L0's settings.
- */
- vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
-
/*
* HOST_RSP is normally set correctly in vmx_vcpu_run() just before
* entry, but only if the current (host) sp changed from the value
}
/*
- * Merging of IO bitmap not currently supported.
- * Rather, exit every time.
+ * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
+ * for I/O port accesses.
*/
exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
exec_control |= CPU_BASED_UNCOND_IO_EXITING;
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
}
- set_cr4_guest_host_mask(vmx);
-
- if (from_vmentry &&
- vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)
- vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
-
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vmcs_write64(TSC_OFFSET,
vcpu->arch.tsc_offset + vmcs12->tsc_offset);
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
- if (cpu_has_vmx_msr_bitmap())
- vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
-
if (enable_vpid) {
/*
* There is no direct mapping between vpid02 and vpid12, the
* even if spawn a lot of nested vCPUs.
*/
if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
- vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
vmx->nested.last_vpid = vmcs12->virtual_processor_id;
- __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
+ __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true);
}
} else {
- vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
-
}
if (enable_pml) {
/* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
vmx_set_efer(vcpu, vcpu->arch.efer);
+ if (vmx->nested.dirty_vmcs12) {
+ prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
+ vmx->nested.dirty_vmcs12 = false;
+ }
+
/* Shadow page tables on either EPT or shadow page tables. */
if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
entry_failure_code))
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
- /*
- * L1 may access the L2's PDPTR, so save them to construct vmcs12
- */
- if (enable_ept) {
- vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
- vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
- vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
- vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
- }
-
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
return 0;
if (block_nested_events)
return -EBUSY;
nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
- vcpu->arch.exception.pending = false;
return 0;
}
* L1's vpid. TODO: move to a more elaborate solution, giving
* each L2 its own vpid and exposing the vpid feature to L1.
*/
- vmx_flush_tlb(vcpu);
+ vmx_flush_tlb(vcpu, true);
}
- /* Restore posted intr vector. */
- if (nested_cpu_has_posted_intr(vmcs12))
- vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
struct x86_instruction_info *info,
enum x86_intercept_stage stage)
{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+ /*
+ * RDPID causes #UD if disabled through secondary execution controls.
+ * Because it is marked as EmulateOnUD, we need to intercept it here.
+ */
+ if (info->intercept == x86_intercept_rdtscp &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+ ctxt->exception.vector = UD_VECTOR;
+ ctxt->exception.error_code_valid = false;
+ return X86EMUL_PROPAGATE_FAULT;
+ }
+
+ /* TODO: check more intercepts... */
return X86EMUL_CONTINUE;
}
.handle_external_intr = vmx_handle_external_intr,
.mpx_supported = vmx_mpx_supported,
.xsaves_supported = vmx_xsaves_supported,
+ .umip_emulated = vmx_umip_emulated,
.check_nested_events = vmx_check_nested_events,
--- /dev/null
+#ifndef SHADOW_FIELD_RO
+#define SHADOW_FIELD_RO(x)
+#endif
+#ifndef SHADOW_FIELD_RW
+#define SHADOW_FIELD_RW(x)
+#endif
+
+/*
+ * We do NOT shadow fields that are modified when L0
+ * traps and emulates any vmx instruction (e.g. VMPTRLD,
+ * VMXON...) executed by L1.
+ * For example, VM_INSTRUCTION_ERROR is read
+ * by L1 if a vmx instruction fails (part of the error path).
+ * Note the code assumes this logic. If for some reason
+ * we start shadowing these fields then we need to
+ * force a shadow sync when L0 emulates vmx instructions
+ * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified
+ * by nested_vmx_failValid)
+ *
+ * When adding or removing fields here, note that shadowed
+ * fields must always be synced by prepare_vmcs02, not just
+ * prepare_vmcs02_full.
+ */
+
+/*
+ * Keeping the fields ordered by size is an attempt at improving
+ * branch prediction in vmcs_read_any and vmcs_write_any.
+ */
+
+/* 16-bits */
+SHADOW_FIELD_RW(GUEST_CS_SELECTOR)
+SHADOW_FIELD_RW(GUEST_INTR_STATUS)
+SHADOW_FIELD_RW(GUEST_PML_INDEX)
+SHADOW_FIELD_RW(HOST_FS_SELECTOR)
+SHADOW_FIELD_RW(HOST_GS_SELECTOR)
+
+/* 32-bits */
+SHADOW_FIELD_RO(VM_EXIT_REASON)
+SHADOW_FIELD_RO(VM_EXIT_INTR_INFO)
+SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN)
+SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD)
+SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE)
+SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE)
+SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL)
+SHADOW_FIELD_RW(EXCEPTION_BITMAP)
+SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE)
+SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD)
+SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN)
+SHADOW_FIELD_RW(TPR_THRESHOLD)
+SHADOW_FIELD_RW(GUEST_CS_LIMIT)
+SHADOW_FIELD_RW(GUEST_CS_AR_BYTES)
+SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO)
+SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE)
+
+/* Natural width */
+SHADOW_FIELD_RO(EXIT_QUALIFICATION)
+SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS)
+SHADOW_FIELD_RW(GUEST_RIP)
+SHADOW_FIELD_RW(GUEST_RSP)
+SHADOW_FIELD_RW(GUEST_CR0)
+SHADOW_FIELD_RW(GUEST_CR3)
+SHADOW_FIELD_RW(GUEST_CR4)
+SHADOW_FIELD_RW(GUEST_RFLAGS)
+SHADOW_FIELD_RW(GUEST_CS_BASE)
+SHADOW_FIELD_RW(GUEST_ES_BASE)
+SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK)
+SHADOW_FIELD_RW(CR0_READ_SHADOW)
+SHADOW_FIELD_RW(CR4_READ_SHADOW)
+SHADOW_FIELD_RW(HOST_FS_BASE)
+SHADOW_FIELD_RW(HOST_GS_BASE)
+
+/* 64-bit */
+SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS)
+SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH)
+
+#undef SHADOW_FIELD_RO
+#undef SHADOW_FIELD_RW
#include <asm/pvclock.h>
#include <asm/div64.h>
#include <asm/irq_remapping.h>
+#include <asm/mshyperv.h>
+#include <asm/hypervisor.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
{ "request_irq", VCPU_STAT(request_irq_exits) },
{ "irq_exits", VCPU_STAT(irq_exits) },
{ "host_state_reload", VCPU_STAT(host_state_reload) },
- { "efer_reload", VCPU_STAT(efer_reload) },
{ "fpu_reload", VCPU_STAT(fpu_reload) },
{ "insn_emulation", VCPU_STAT(insn_emulation) },
{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
/* kvm_set_xcr() also depends on this */
- xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
+ if (vcpu->arch.xcr0 != host_xcr0)
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
vcpu->guest_xcr0_loaded = 1;
}
}
if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
return 1;
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+ return 1;
+
if (is_long_mode(vcpu)) {
if (!(cr4 & X86_CR4_PAE))
return 1;
MSR_IA32_MCG_CTL,
MSR_IA32_MCG_EXT_CTL,
MSR_IA32_SMBASE,
+ MSR_SMI_COUNT,
MSR_PLATFORM_INFO,
MSR_MISC_FEATURES_ENABLES,
};
return tsc;
}
+static inline int gtod_is_based_on_tsc(int mode)
+{
+ return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK;
+}
+
static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
* perform request to enable masterclock.
*/
if (ka->use_master_clock ||
- (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
+ (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
vcpu->arch.tsc_offset = offset;
}
+static inline bool kvm_check_tsc_unstable(void)
+{
+#ifdef CONFIG_X86_64
+ /*
+ * TSC is marked unstable when we're running on Hyper-V,
+ * 'TSC page' clocksource is good.
+ */
+ if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK)
+ return false;
+#endif
+ return check_tsc_unstable();
+}
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct kvm *kvm = vcpu->kvm;
*/
if (synchronizing &&
vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
- if (!check_tsc_unstable()) {
+ if (!kvm_check_tsc_unstable()) {
offset = kvm->arch.cur_tsc_offset;
pr_debug("kvm: matched tsc offset for %llu\n", data);
} else {
return last;
}
-static inline u64 vgettsc(u64 *cycle_now)
+static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
{
long v;
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+ u64 tsc_pg_val;
+
+ switch (gtod->clock.vclock_mode) {
+ case VCLOCK_HVCLOCK:
+ tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
+ tsc_timestamp);
+ if (tsc_pg_val != U64_MAX) {
+ /* TSC page valid */
+ *mode = VCLOCK_HVCLOCK;
+ v = (tsc_pg_val - gtod->clock.cycle_last) &
+ gtod->clock.mask;
+ } else {
+ /* TSC page invalid */
+ *mode = VCLOCK_NONE;
+ }
+ break;
+ case VCLOCK_TSC:
+ *mode = VCLOCK_TSC;
+ *tsc_timestamp = read_tsc();
+ v = (*tsc_timestamp - gtod->clock.cycle_last) &
+ gtod->clock.mask;
+ break;
+ default:
+ *mode = VCLOCK_NONE;
+ }
- *cycle_now = read_tsc();
+ if (*mode == VCLOCK_NONE)
+ *tsc_timestamp = v = 0;
- v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask;
return v * gtod->clock.mult;
}
-static int do_monotonic_boot(s64 *t, u64 *cycle_now)
+static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
{
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
unsigned long seq;
do {
seq = read_seqcount_begin(>od->seq);
- mode = gtod->clock.vclock_mode;
ns = gtod->nsec_base;
- ns += vgettsc(cycle_now);
+ ns += vgettsc(tsc_timestamp, &mode);
ns >>= gtod->clock.shift;
ns += gtod->boot_ns;
} while (unlikely(read_seqcount_retry(>od->seq, seq)));
return mode;
}
-static int do_realtime(struct timespec *ts, u64 *cycle_now)
+static int do_realtime(struct timespec *ts, u64 *tsc_timestamp)
{
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
unsigned long seq;
do {
seq = read_seqcount_begin(>od->seq);
- mode = gtod->clock.vclock_mode;
ts->tv_sec = gtod->wall_time_sec;
ns = gtod->nsec_base;
- ns += vgettsc(cycle_now);
+ ns += vgettsc(tsc_timestamp, &mode);
ns >>= gtod->clock.shift;
} while (unlikely(read_seqcount_retry(>od->seq, seq)));
return mode;
}
-/* returns true if host is using tsc clocksource */
-static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
+/* returns true if host is using TSC based clocksource */
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
{
/* checked again under seqlock below */
- if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
return false;
- return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
+ return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+ tsc_timestamp));
}
-/* returns true if host is using tsc clocksource */
+/* returns true if host is using TSC based clocksource */
static bool kvm_get_walltime_and_clockread(struct timespec *ts,
- u64 *cycle_now)
+ u64 *tsc_timestamp)
{
/* checked again under seqlock below */
- if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
return false;
- return do_realtime(ts, cycle_now) == VCLOCK_TSC;
+ return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp));
}
#endif
vcpu->arch.pv_time_enabled = false;
}
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
+{
+ ++vcpu->stat.tlb_flush;
+ kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa);
+}
+
static void record_steal_time(struct kvm_vcpu *vcpu)
{
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
- vcpu->arch.st.steal.preempted = 0;
+ /*
+ * Doing a TLB flush here, on the guest's behalf, can avoid
+ * expensive IPIs.
+ */
+ if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+ kvm_vcpu_flush_tlb(vcpu, false);
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
return 1;
vcpu->arch.smbase = data;
break;
+ case MSR_SMI_COUNT:
+ if (!msr_info->host_initiated)
+ return 1;
+ vcpu->arch.smi_count = data;
+ break;
case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
return 1;
msr_info->data = vcpu->arch.smbase;
break;
+ case MSR_SMI_COUNT:
+ msr_info->data = vcpu->arch.smi_count;
+ break;
case MSR_IA32_PERF_STATUS:
/* TSC increment by tick */
msr_info->data = 1000ULL;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
}
- if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
+ if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
rdtsc() - vcpu->arch.last_host_tsc;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (check_tsc_unstable()) {
+ if (kvm_check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_vcpu_write_tsc_offset(vcpu, offset);
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
- vcpu->arch.st.steal.preempted = 1;
+ vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal.preempted,
pagefault_enable();
kvm_x86_ops->vcpu_put(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
+ /*
+ * If userspace has set any breakpoints or watchpoints, dr6 is restored
+ * on every vmexit, but if not, we might have a stale dr6 from the
+ * guest. do_debug expects dr6 to be cleared after it runs, do the same.
+ */
+ set_debugreg(0, 6);
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
+ if (vcpu->arch.apicv_active)
kvm_x86_ops->sync_pir_to_irr(vcpu);
return kvm_apic_get_state(vcpu, s);
void *buffer;
} u;
+ vcpu_load(vcpu);
+
u.buffer = NULL;
switch (ioctl) {
case KVM_GET_LAPIC: {
if (!lapic_in_kernel(vcpu))
goto out;
u.lapic = memdup_user(argp, sizeof(*u.lapic));
- if (IS_ERR(u.lapic))
- return PTR_ERR(u.lapic);
+ if (IS_ERR(u.lapic)) {
+ r = PTR_ERR(u.lapic);
+ goto out_nofree;
+ }
r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
break;
}
case KVM_SET_XSAVE: {
u.xsave = memdup_user(argp, sizeof(*u.xsave));
- if (IS_ERR(u.xsave))
- return PTR_ERR(u.xsave);
+ if (IS_ERR(u.xsave)) {
+ r = PTR_ERR(u.xsave);
+ goto out_nofree;
+ }
r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave);
break;
}
case KVM_SET_XCRS: {
u.xcrs = memdup_user(argp, sizeof(*u.xcrs));
- if (IS_ERR(u.xcrs))
- return PTR_ERR(u.xcrs);
+ if (IS_ERR(u.xcrs)) {
+ r = PTR_ERR(u.xcrs);
+ goto out_nofree;
+ }
r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs);
break;
}
out:
kfree(u.buffer);
+out_nofree:
+ vcpu_put(vcpu);
return r;
}
r = kvm_vm_ioctl_enable_cap(kvm, &cap);
break;
}
+ case KVM_MEMORY_ENCRYPT_OP: {
+ r = -ENOTTY;
+ if (kvm_x86_ops->mem_enc_op)
+ r = kvm_x86_ops->mem_enc_op(kvm, argp);
+ break;
+ }
+ case KVM_MEMORY_ENCRYPT_REG_REGION: {
+ struct kvm_enc_region region;
+
+ r = -EFAULT;
+ if (copy_from_user(®ion, argp, sizeof(region)))
+ goto out;
+
+ r = -ENOTTY;
+ if (kvm_x86_ops->mem_enc_reg_region)
+ r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion);
+ break;
+ }
+ case KVM_MEMORY_ENCRYPT_UNREG_REGION: {
+ struct kvm_enc_region region;
+
+ r = -EFAULT;
+ if (copy_from_user(®ion, argp, sizeof(region)))
+ goto out;
+
+ r = -ENOTTY;
+ if (kvm_x86_ops->mem_enc_unreg_region)
+ r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion);
+ break;
+ }
default:
r = -ENOTTY;
}
* handle watchpoints yet, those would be handled in
* the emulate_ops.
*/
- if (kvm_vcpu_check_breakpoint(vcpu, &r))
+ if (!(emulation_type & EMULTYPE_SKIP) &&
+ kvm_vcpu_check_breakpoint(vcpu, &r))
return r;
ctxt->interruptibility = 0;
__this_cpu_write(cpu_tsc_khz, khz);
}
+#ifdef CONFIG_X86_64
+static void kvm_hyperv_tsc_notifier(void)
+{
+ struct kvm *kvm;
+ struct kvm_vcpu *vcpu;
+ int cpu;
+
+ spin_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list)
+ kvm_make_mclock_inprogress_request(kvm);
+
+ hyperv_stop_tsc_emulation();
+
+ /* TSC frequency always matches when on Hyper-V */
+ for_each_present_cpu(cpu)
+ per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+ kvm_max_guest_tsc_khz = tsc_khz;
+
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ struct kvm_arch *ka = &kvm->arch;
+
+ spin_lock(&ka->pvclock_gtod_sync_lock);
+
+ pvclock_update_vm_gtod_copy(kvm);
+
+ kvm_for_each_vcpu(cpu, vcpu, kvm)
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+
+ kvm_for_each_vcpu(cpu, vcpu, kvm)
+ kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
+
+ spin_unlock(&ka->pvclock_gtod_sync_lock);
+ }
+ spin_unlock(&kvm_lock);
+}
+#endif
+
static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
update_pvclock_gtod(tk);
/* disable master clock if host does not trust, or does not
- * use, TSC clocksource
+ * use, TSC based clocksource.
*/
- if (gtod->clock.vclock_mode != VCLOCK_TSC &&
+ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) &&
atomic_read(&kvm_guest_has_master_clock) != 0)
queue_work(system_long_wq, &pvclock_gtod_work);
kvm_lapic_init();
#ifdef CONFIG_X86_64
pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
+
+ if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
+ set_hv_tscchange_cb(kvm_hyperv_tsc_notifier);
#endif
return 0;
void kvm_arch_exit(void)
{
+#ifdef CONFIG_X86_64
+ if (hypervisor_is_type(X86_HYPER_MS_HYPERV))
+ clear_hv_tscchange_cb();
+#endif
kvm_lapic_exit();
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
kvm_x86_ops->queue_exception(vcpu);
} else if (vcpu->arch.smi_pending && !is_smm(vcpu) && kvm_x86_ops->smi_allowed(vcpu)) {
vcpu->arch.smi_pending = false;
+ ++vcpu->arch.smi_count;
enter_smm(vcpu);
} else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
--vcpu->arch.nmi_pending;
if (irqchip_split(vcpu->kvm))
kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
else {
- if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
+ if (vcpu->arch.apicv_active)
kvm_x86_ops->sync_pir_to_irr(vcpu);
kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
}
kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
}
-static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
-{
- ++vcpu->stat.tlb_flush;
- kvm_x86_ops->tlb_flush(vcpu);
-}
-
void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
unsigned long start, unsigned long end)
{
if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
kvm_mmu_sync_roots(vcpu);
if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
- kvm_vcpu_flush_tlb(vcpu);
+ kvm_vcpu_flush_tlb(vcpu, true);
if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
r = 0;
* This handles the case where a posted interrupt was
* notified with kvm_vcpu_kick.
*/
- if (kvm_lapic_enabled(vcpu)) {
- if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
- kvm_x86_ops->sync_pir_to_irr(vcpu);
- }
+ if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
+ kvm_x86_ops->sync_pir_to_irr(vcpu);
if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu)
|| need_resched() || signal_pending(current)) {
}
trace_kvm_entry(vcpu->vcpu_id);
- wait_lapic_expire(vcpu);
+ if (lapic_timer_advance_ns)
+ wait_lapic_expire(vcpu);
guest_enter_irqoff();
if (unlikely(vcpu->arch.switch_db_regs)) {
{
int r;
+ vcpu_load(vcpu);
kvm_sigset_activate(vcpu);
-
kvm_load_guest_fpu(vcpu);
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
post_kvm_run_save(vcpu);
kvm_sigset_deactivate(vcpu);
+ vcpu_put(vcpu);
return r;
}
int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ vcpu_load(vcpu);
+
if (vcpu->arch.emulate_regs_need_sync_to_vcpu) {
/*
* We are here if userspace calls get_regs() in the middle of
regs->rip = kvm_rip_read(vcpu);
regs->rflags = kvm_get_rflags(vcpu);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
+ vcpu_load(vcpu);
+
vcpu->arch.emulate_regs_need_sync_from_vcpu = true;
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ vcpu_put(vcpu);
return 0;
}
{
struct desc_ptr dt;
+ vcpu_load(vcpu);
+
kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES);
set_bit(vcpu->arch.interrupt.nr,
(unsigned long *)sregs->interrupt_bitmap);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ vcpu_load(vcpu);
+
kvm_apic_accept_events(vcpu);
if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
vcpu->arch.pv.pv_unhalted)
else
mp_state->mp_state = vcpu->arch.mp_state;
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ int ret = -EINVAL;
+
+ vcpu_load(vcpu);
+
if (!lapic_in_kernel(vcpu) &&
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
- return -EINVAL;
+ goto out;
/* INITs are latched while in SMM */
if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
(mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
- return -EINVAL;
+ goto out;
if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
} else
vcpu->arch.mp_state = mp_state->mp_state;
kvm_make_request(KVM_REQ_EVENT, vcpu);
- return 0;
+
+ ret = 0;
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
int mmu_reset_needed = 0;
int pending_vec, max_bits, idx;
struct desc_ptr dt;
+ int ret = -EINVAL;
+
+ vcpu_load(vcpu);
if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
(sregs->cr4 & X86_CR4_OSXSAVE))
- return -EINVAL;
+ goto out;
if (kvm_valid_sregs(vcpu, sregs))
- return -EINVAL;
+ goto out;
apic_base_msr.data = sregs->apic_base;
apic_base_msr.host_initiated = true;
if (kvm_set_apic_base(vcpu, &apic_base_msr))
- return -EINVAL;
+ goto out;
dt.size = sregs->idt.limit;
dt.address = sregs->idt.base;
kvm_make_request(KVM_REQ_EVENT, vcpu);
- return 0;
+ ret = 0;
+out:
+ vcpu_put(vcpu);
+ return ret;
}
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
unsigned long rflags;
int i, r;
+ vcpu_load(vcpu);
+
if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
r = -EBUSY;
if (vcpu->arch.exception.pending)
r = 0;
out:
-
+ vcpu_put(vcpu);
return r;
}
gpa_t gpa;
int idx;
+ vcpu_load(vcpu);
+
idx = srcu_read_lock(&vcpu->kvm->srcu);
gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
tr->writeable = 1;
tr->usermode = 0;
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxregs_state *fxsave =
- &vcpu->arch.guest_fpu.state.fxsave;
+ struct fxregs_state *fxsave;
+
+ vcpu_load(vcpu);
+ fxsave = &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
fpu->fsw = fxsave->swd;
fpu->last_dp = fxsave->rdp;
memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space);
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxregs_state *fxsave =
- &vcpu->arch.guest_fpu.state.fxsave;
+ struct fxregs_state *fxsave;
+
+ vcpu_load(vcpu);
+
+ fxsave = &vcpu->arch.guest_fpu.state.fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
fxsave->rdp = fpu->last_dp;
memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space);
+ vcpu_put(vcpu);
return 0;
}
{
struct kvm_vcpu *vcpu;
- if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
+ if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
printk_once(KERN_WARNING
"kvm: SMP vm created on host with unstable TSC; "
"guest TSC will not be reliable\n");
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
- int r;
-
kvm_vcpu_mtrr_init(vcpu);
- r = vcpu_load(vcpu);
- if (r)
- return r;
+ vcpu_load(vcpu);
kvm_vcpu_reset(vcpu, false);
kvm_mmu_setup(vcpu);
vcpu_put(vcpu);
- return r;
+ return 0;
}
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
kvm_hv_vcpu_postcreate(vcpu);
- if (vcpu_load(vcpu))
+ if (mutex_lock_killable(&vcpu->mutex))
return;
+ vcpu_load(vcpu);
msr.data = 0x0;
msr.index = MSR_IA32_TSC;
msr.host_initiated = true;
kvm_write_tsc(vcpu, &msr);
vcpu_put(vcpu);
+ mutex_unlock(&vcpu->mutex);
if (!kvmclock_periodic_sync)
return;
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
- int r;
vcpu->arch.apf.msr_val = 0;
- r = vcpu_load(vcpu);
- BUG_ON(r);
+ vcpu_load(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
vcpu->arch.hflags = 0;
vcpu->arch.smi_pending = 0;
+ vcpu->arch.smi_count = 0;
atomic_set(&vcpu->arch.nmi_queued, 0);
vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
return ret;
local_tsc = rdtsc();
- stable = !check_tsc_unstable();
+ stable = !kvm_check_tsc_unstable();
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!stable && vcpu->cpu == smp_processor_id())
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
- int r;
- r = vcpu_load(vcpu);
- BUG_ON(r);
+ vcpu_load(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
}
static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.exception.pending = false;
vcpu->arch.exception.injected = false;
}
static inline bool kvm_mwait_in_guest(void)
{
- unsigned int eax, ebx, ecx, edx;
-
- if (!cpu_has(&boot_cpu_data, X86_FEATURE_MWAIT))
- return false;
-
- switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
- /* All AMD CPUs have a working MWAIT implementation */
- return true;
- case X86_VENDOR_INTEL:
- /* Handle Intel below */
- break;
- default:
- return false;
- }
-
- /*
- * Intel CPUs without CPUID5_ECX_INTERRUPT_BREAK are problematic as
- * they would allow guest to stop the CPU completely by disabling
- * interrupts then invoking MWAIT.
- */
- if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
- return false;
-
- cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
-
- if (!(ecx & CPUID5_ECX_INTERRUPT_BREAK))
- return false;
-
- return true;
+ return boot_cpu_has(X86_FEATURE_MWAIT) &&
+ !boot_cpu_has_bug(X86_BUG_MONITOR);
}
#endif
return rettype;
}
+/**
+ * pat_pfn_immune_to_uc_mtrr - Check whether the PAT memory type
+ * of @pfn cannot be overridden by UC MTRR memory type.
+ *
+ * Only to be called when PAT is enabled.
+ *
+ * Returns true, if the PAT memory type of @pfn is UC, UC-, or WC.
+ * Returns false in other cases.
+ */
+bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn)
+{
+ enum page_cache_mode cm = lookup_memtype(PFN_PHYS(pfn));
+
+ return cm == _PAGE_CACHE_MODE_UC ||
+ cm == _PAGE_CACHE_MODE_UC_MINUS ||
+ cm == _PAGE_CACHE_MODE_WC;
+}
+EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr);
+
/**
* io_reserve_memtype - Request a memory type mapping for a region of memory
* @start: start (physical address) of the region
int i, ret = 0;
pte_t *pte;
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return 0;
+
if (kmap_ops) {
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref,
kmap_ops, count);
{
int i, ret = 0;
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return 0;
+
for (i = 0; i < count; i++) {
unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
unsigned long pfn = page_to_pfn(pages[i]);
#include <asm/boot.h>
#include <asm/asm.h>
+#include <asm/msr.h>
#include <asm/page_types.h>
+#include <asm/percpu.h>
#include <asm/unwind_hints.h>
#include <xen/interface/elfnote.h>
mov %_ASM_SI, xen_start_info
mov $init_thread_union+THREAD_SIZE, %_ASM_SP
+#ifdef CONFIG_X86_64
+ /* Set up %gs.
+ *
+ * The base of %gs always points to the bottom of the irqstack
+ * union. If the stack protector canary is enabled, it is
+ * located at %gs:40. Note that, on SMP, the boot cpu uses
+ * init data section till per cpu areas are set up.
+ */
+ movl $MSR_GS_BASE,%ecx
+ movq $INIT_PER_CPU_VAR(irq_stack_union),%rax
+ cdq
+ wrmsr
+#endif
+
jmp xen_start_kernel
END(startup_xen)
__FINIT
#include <linux/sizes.h>
#include <asm/kmem_layout.h>
+#define KASAN_SHADOW_SCALE_SHIFT 3
+
/* Start of area covered by KASAN */
#define KASAN_START_VADDR __XTENSA_UL_CONST(0x90000000)
/* Start of the shadow map */
#ifndef _XTENSA_POLL_H
#define _XTENSA_POLL_H
-#ifndef __KERNEL__
#define POLLWRNORM POLLOUT
-#define POLLWRBAND (__force __poll_t)0x0100
-#define POLLREMOVE (__force __poll_t)0x0800
-#else
-#define __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- __u16 v = (__force __u16)val;
- /* bit 9 -> bit 8, bit 8 -> bit 2 */
- return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6);
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */
- return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) |
- ((v & 4) << 6));
-}
-#endif
+#define POLLWRBAND 0x0100
+#define POLLREMOVE 0x0800
#include <asm-generic/poll.h>
}
/*
- * We exploit the bfq_finish_request hook to decrement
- * rq_in_driver, but bfq_finish_request will not be
- * invoked on this request. So, to avoid unbalance,
- * just start this request, without incrementing
- * rq_in_driver. As a negative consequence,
- * rq_in_driver is deceptively lower than it should be
- * while this request is in service. This may cause
- * bfq_schedule_dispatch to be invoked uselessly.
+ * We exploit the bfq_finish_requeue_request hook to
+ * decrement rq_in_driver, but
+ * bfq_finish_requeue_request will not be invoked on
+ * this request. So, to avoid unbalance, just start
+ * this request, without incrementing rq_in_driver. As
+ * a negative consequence, rq_in_driver is deceptively
+ * lower than it should be while this request is in
+ * service. This may cause bfq_schedule_dispatch to be
+ * invoked uselessly.
*
* As for implementing an exact solution, the
- * bfq_finish_request hook, if defined, is probably
- * invoked also on this request. So, by exploiting
- * this hook, we could 1) increment rq_in_driver here,
- * and 2) decrement it in bfq_finish_request. Such a
- * solution would let the value of the counter be
- * always accurate, but it would entail using an extra
- * interface function. This cost seems higher than the
- * benefit, being the frequency of non-elevator-private
+ * bfq_finish_requeue_request hook, if defined, is
+ * probably invoked also on this request. So, by
+ * exploiting this hook, we could 1) increment
+ * rq_in_driver here, and 2) decrement it in
+ * bfq_finish_requeue_request. Such a solution would
+ * let the value of the counter be always accurate,
+ * but it would entail using an extra interface
+ * function. This cost seems higher than the benefit,
+ * being the frequency of non-elevator-private
* requests very low.
*/
goto start_rq;
unsigned int cmd_flags) {}
#endif
+static void bfq_prepare_request(struct request *rq, struct bio *bio);
+
static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
bool at_head)
{
else
list_add_tail(&rq->queuelist, &bfqd->dispatch);
} else {
+ if (WARN_ON_ONCE(!bfqq)) {
+ /*
+ * This should never happen. Most likely rq is
+ * a requeued regular request, being
+ * re-inserted without being first
+ * re-prepared. Do a prepare, to avoid
+ * failure.
+ */
+ bfq_prepare_request(rq, rq->bio);
+ bfqq = RQ_BFQQ(rq);
+ }
+
idle_timer_disabled = __bfq_insert_request(bfqd, rq);
/*
* Update bfqq, because, if a queue merge has occurred
bfq_schedule_dispatch(bfqd);
}
-static void bfq_finish_request_body(struct bfq_queue *bfqq)
+static void bfq_finish_requeue_request_body(struct bfq_queue *bfqq)
{
bfqq->allocated--;
bfq_put_queue(bfqq);
}
-static void bfq_finish_request(struct request *rq)
+/*
+ * Handle either a requeue or a finish for rq. The things to do are
+ * the same in both cases: all references to rq are to be dropped. In
+ * particular, rq is considered completed from the point of view of
+ * the scheduler.
+ */
+static void bfq_finish_requeue_request(struct request *rq)
{
- struct bfq_queue *bfqq;
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
struct bfq_data *bfqd;
- if (!rq->elv.icq)
+ /*
+ * Requeue and finish hooks are invoked in blk-mq without
+ * checking whether the involved request is actually still
+ * referenced in the scheduler. To handle this fact, the
+ * following two checks make this function exit in case of
+ * spurious invocations, for which there is nothing to do.
+ *
+ * First, check whether rq has nothing to do with an elevator.
+ */
+ if (unlikely(!(rq->rq_flags & RQF_ELVPRIV)))
+ return;
+
+ /*
+ * rq either is not associated with any icq, or is an already
+ * requeued request that has not (yet) been re-inserted into
+ * a bfq_queue.
+ */
+ if (!rq->elv.icq || !bfqq)
return;
- bfqq = RQ_BFQQ(rq);
bfqd = bfqq->bfqd;
if (rq->rq_flags & RQF_STARTED)
spin_lock_irqsave(&bfqd->lock, flags);
bfq_completed_request(bfqq, bfqd);
- bfq_finish_request_body(bfqq);
+ bfq_finish_requeue_request_body(bfqq);
spin_unlock_irqrestore(&bfqd->lock, flags);
} else {
/*
* Request rq may be still/already in the scheduler,
- * in which case we need to remove it. And we cannot
+ * in which case we need to remove it (this should
+ * never happen in case of requeue). And we cannot
* defer such a check and removal, to avoid
* inconsistencies in the time interval from the end
* of this function to the start of the deferred work.
bfqg_stats_update_io_remove(bfqq_group(bfqq),
rq->cmd_flags);
}
- bfq_finish_request_body(bfqq);
+ bfq_finish_requeue_request_body(bfqq);
}
+ /*
+ * Reset private fields. In case of a requeue, this allows
+ * this function to correctly do nothing if it is spuriously
+ * invoked again on this same request (see the check at the
+ * beginning of the function). Probably, a better general
+ * design would be to prevent blk-mq from invoking the requeue
+ * or finish hooks of an elevator, for a request that is not
+ * referred by that elevator.
+ *
+ * Resetting the following fields would break the
+ * request-insertion logic if rq is re-inserted into a bfq
+ * internal queue, without a re-preparation. Here we assume
+ * that re-insertions of requeued requests, without
+ * re-preparation, can happen only for pass_through or at_head
+ * requests (which are not re-inserted into bfq internal
+ * queues).
+ */
rq->elv.priv[0] = NULL;
rq->elv.priv[1] = NULL;
}
.ops.mq = {
.limit_depth = bfq_limit_depth,
.prepare_request = bfq_prepare_request,
- .finish_request = bfq_finish_request,
+ .requeue_request = bfq_finish_requeue_request,
+ .finish_request = bfq_finish_requeue_request,
.exit_icq = bfq_exit_icq,
.insert_requests = bfq_insert_requests,
.dispatch_request = bfq_dispatch_request,
#include <linux/pm_runtime.h>
#include <linux/blk-cgroup.h>
#include <linux/debugfs.h>
+#include <linux/bpf.h>
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
return false;
}
+static noinline int should_fail_bio(struct bio *bio)
+{
+ if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
+ return -EIO;
+ return 0;
+}
+ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO);
+
/*
* Remap block n of partition p to block n+start(p) of the disk.
*/
if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
goto not_supported;
- if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
+ if (should_fail_bio(bio))
goto end_io;
if (!bio->bi_partno) {
static int wbt_data_dir(const struct request *rq)
{
- return rq_data_dir(rq);
+ const int op = req_op(rq);
+
+ if (op == REQ_OP_READ)
+ return READ;
+ else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH)
+ return WRITE;
+
+ /* don't account */
+ return -1;
}
int wbt_init(struct request_queue *q)
spin_lock_irq(&bd->lock);
if (!list_empty(&bd->done_list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (bd->queued_cmds < bd->max_queue)
- mask |= POLLOUT;
+ mask |= EPOLLOUT;
spin_unlock_irq(&bd->lock);
return mask;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
- POLLRDNORM |
- POLLRDBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
+ EPOLLRDNORM |
+ EPOLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
rcu_read_unlock();
}
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
- POLLRDNORM |
- POLLRDBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
+ EPOLLRDNORM |
+ EPOLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
rcu_read_unlock();
}
mask = 0;
if (!ctx->more || ctx->used)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (af_alg_writable(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
return mask;
}
#include <crypto/sha3.h>
#include <asm/unaligned.h>
+/*
+ * On some 32-bit architectures (mn10300 and h8300), GCC ends up using
+ * over 1 KB of stack if we inline the round calculation into the loop
+ * in keccakf(). On the other hand, on 64-bit architectures with plenty
+ * of [64-bit wide] general purpose registers, not inlining it severely
+ * hurts performance. So let's use 64-bitness as a heuristic to decide
+ * whether to inline or not.
+ */
+#ifdef CONFIG_64BIT
+#define SHA3_INLINE inline
+#else
+#define SHA3_INLINE noinline
+#endif
+
#define KECCAK_ROUNDS 24
static const u64 keccakf_rndc[24] = {
/* update the state with given number of rounds */
-static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25])
+static SHA3_INLINE void keccakf_round(u64 st[25])
{
u64 t[5], tt, bc[5];
- int round;
- for (round = 0; round < KECCAK_ROUNDS; round++) {
+ /* Theta */
+ bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
+ bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21];
+ bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22];
+ bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
+ bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
+
+ t[0] = bc[4] ^ rol64(bc[1], 1);
+ t[1] = bc[0] ^ rol64(bc[2], 1);
+ t[2] = bc[1] ^ rol64(bc[3], 1);
+ t[3] = bc[2] ^ rol64(bc[4], 1);
+ t[4] = bc[3] ^ rol64(bc[0], 1);
+
+ st[0] ^= t[0];
+
+ /* Rho Pi */
+ tt = st[1];
+ st[ 1] = rol64(st[ 6] ^ t[1], 44);
+ st[ 6] = rol64(st[ 9] ^ t[4], 20);
+ st[ 9] = rol64(st[22] ^ t[2], 61);
+ st[22] = rol64(st[14] ^ t[4], 39);
+ st[14] = rol64(st[20] ^ t[0], 18);
+ st[20] = rol64(st[ 2] ^ t[2], 62);
+ st[ 2] = rol64(st[12] ^ t[2], 43);
+ st[12] = rol64(st[13] ^ t[3], 25);
+ st[13] = rol64(st[19] ^ t[4], 8);
+ st[19] = rol64(st[23] ^ t[3], 56);
+ st[23] = rol64(st[15] ^ t[0], 41);
+ st[15] = rol64(st[ 4] ^ t[4], 27);
+ st[ 4] = rol64(st[24] ^ t[4], 14);
+ st[24] = rol64(st[21] ^ t[1], 2);
+ st[21] = rol64(st[ 8] ^ t[3], 55);
+ st[ 8] = rol64(st[16] ^ t[1], 45);
+ st[16] = rol64(st[ 5] ^ t[0], 36);
+ st[ 5] = rol64(st[ 3] ^ t[3], 28);
+ st[ 3] = rol64(st[18] ^ t[3], 21);
+ st[18] = rol64(st[17] ^ t[2], 15);
+ st[17] = rol64(st[11] ^ t[1], 10);
+ st[11] = rol64(st[ 7] ^ t[2], 6);
+ st[ 7] = rol64(st[10] ^ t[0], 3);
+ st[10] = rol64( tt ^ t[1], 1);
+
+ /* Chi */
+ bc[ 0] = ~st[ 1] & st[ 2];
+ bc[ 1] = ~st[ 2] & st[ 3];
+ bc[ 2] = ~st[ 3] & st[ 4];
+ bc[ 3] = ~st[ 4] & st[ 0];
+ bc[ 4] = ~st[ 0] & st[ 1];
+ st[ 0] ^= bc[ 0];
+ st[ 1] ^= bc[ 1];
+ st[ 2] ^= bc[ 2];
+ st[ 3] ^= bc[ 3];
+ st[ 4] ^= bc[ 4];
+
+ bc[ 0] = ~st[ 6] & st[ 7];
+ bc[ 1] = ~st[ 7] & st[ 8];
+ bc[ 2] = ~st[ 8] & st[ 9];
+ bc[ 3] = ~st[ 9] & st[ 5];
+ bc[ 4] = ~st[ 5] & st[ 6];
+ st[ 5] ^= bc[ 0];
+ st[ 6] ^= bc[ 1];
+ st[ 7] ^= bc[ 2];
+ st[ 8] ^= bc[ 3];
+ st[ 9] ^= bc[ 4];
+
+ bc[ 0] = ~st[11] & st[12];
+ bc[ 1] = ~st[12] & st[13];
+ bc[ 2] = ~st[13] & st[14];
+ bc[ 3] = ~st[14] & st[10];
+ bc[ 4] = ~st[10] & st[11];
+ st[10] ^= bc[ 0];
+ st[11] ^= bc[ 1];
+ st[12] ^= bc[ 2];
+ st[13] ^= bc[ 3];
+ st[14] ^= bc[ 4];
+
+ bc[ 0] = ~st[16] & st[17];
+ bc[ 1] = ~st[17] & st[18];
+ bc[ 2] = ~st[18] & st[19];
+ bc[ 3] = ~st[19] & st[15];
+ bc[ 4] = ~st[15] & st[16];
+ st[15] ^= bc[ 0];
+ st[16] ^= bc[ 1];
+ st[17] ^= bc[ 2];
+ st[18] ^= bc[ 3];
+ st[19] ^= bc[ 4];
+
+ bc[ 0] = ~st[21] & st[22];
+ bc[ 1] = ~st[22] & st[23];
+ bc[ 2] = ~st[23] & st[24];
+ bc[ 3] = ~st[24] & st[20];
+ bc[ 4] = ~st[20] & st[21];
+ st[20] ^= bc[ 0];
+ st[21] ^= bc[ 1];
+ st[22] ^= bc[ 2];
+ st[23] ^= bc[ 3];
+ st[24] ^= bc[ 4];
+}
- /* Theta */
- bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
- bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21];
- bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22];
- bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
- bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
-
- t[0] = bc[4] ^ rol64(bc[1], 1);
- t[1] = bc[0] ^ rol64(bc[2], 1);
- t[2] = bc[1] ^ rol64(bc[3], 1);
- t[3] = bc[2] ^ rol64(bc[4], 1);
- t[4] = bc[3] ^ rol64(bc[0], 1);
-
- st[0] ^= t[0];
-
- /* Rho Pi */
- tt = st[1];
- st[ 1] = rol64(st[ 6] ^ t[1], 44);
- st[ 6] = rol64(st[ 9] ^ t[4], 20);
- st[ 9] = rol64(st[22] ^ t[2], 61);
- st[22] = rol64(st[14] ^ t[4], 39);
- st[14] = rol64(st[20] ^ t[0], 18);
- st[20] = rol64(st[ 2] ^ t[2], 62);
- st[ 2] = rol64(st[12] ^ t[2], 43);
- st[12] = rol64(st[13] ^ t[3], 25);
- st[13] = rol64(st[19] ^ t[4], 8);
- st[19] = rol64(st[23] ^ t[3], 56);
- st[23] = rol64(st[15] ^ t[0], 41);
- st[15] = rol64(st[ 4] ^ t[4], 27);
- st[ 4] = rol64(st[24] ^ t[4], 14);
- st[24] = rol64(st[21] ^ t[1], 2);
- st[21] = rol64(st[ 8] ^ t[3], 55);
- st[ 8] = rol64(st[16] ^ t[1], 45);
- st[16] = rol64(st[ 5] ^ t[0], 36);
- st[ 5] = rol64(st[ 3] ^ t[3], 28);
- st[ 3] = rol64(st[18] ^ t[3], 21);
- st[18] = rol64(st[17] ^ t[2], 15);
- st[17] = rol64(st[11] ^ t[1], 10);
- st[11] = rol64(st[ 7] ^ t[2], 6);
- st[ 7] = rol64(st[10] ^ t[0], 3);
- st[10] = rol64( tt ^ t[1], 1);
-
- /* Chi */
- bc[ 0] = ~st[ 1] & st[ 2];
- bc[ 1] = ~st[ 2] & st[ 3];
- bc[ 2] = ~st[ 3] & st[ 4];
- bc[ 3] = ~st[ 4] & st[ 0];
- bc[ 4] = ~st[ 0] & st[ 1];
- st[ 0] ^= bc[ 0];
- st[ 1] ^= bc[ 1];
- st[ 2] ^= bc[ 2];
- st[ 3] ^= bc[ 3];
- st[ 4] ^= bc[ 4];
-
- bc[ 0] = ~st[ 6] & st[ 7];
- bc[ 1] = ~st[ 7] & st[ 8];
- bc[ 2] = ~st[ 8] & st[ 9];
- bc[ 3] = ~st[ 9] & st[ 5];
- bc[ 4] = ~st[ 5] & st[ 6];
- st[ 5] ^= bc[ 0];
- st[ 6] ^= bc[ 1];
- st[ 7] ^= bc[ 2];
- st[ 8] ^= bc[ 3];
- st[ 9] ^= bc[ 4];
-
- bc[ 0] = ~st[11] & st[12];
- bc[ 1] = ~st[12] & st[13];
- bc[ 2] = ~st[13] & st[14];
- bc[ 3] = ~st[14] & st[10];
- bc[ 4] = ~st[10] & st[11];
- st[10] ^= bc[ 0];
- st[11] ^= bc[ 1];
- st[12] ^= bc[ 2];
- st[13] ^= bc[ 3];
- st[14] ^= bc[ 4];
-
- bc[ 0] = ~st[16] & st[17];
- bc[ 1] = ~st[17] & st[18];
- bc[ 2] = ~st[18] & st[19];
- bc[ 3] = ~st[19] & st[15];
- bc[ 4] = ~st[15] & st[16];
- st[15] ^= bc[ 0];
- st[16] ^= bc[ 1];
- st[17] ^= bc[ 2];
- st[18] ^= bc[ 3];
- st[19] ^= bc[ 4];
-
- bc[ 0] = ~st[21] & st[22];
- bc[ 1] = ~st[22] & st[23];
- bc[ 2] = ~st[23] & st[24];
- bc[ 3] = ~st[24] & st[20];
- bc[ 4] = ~st[20] & st[21];
- st[20] ^= bc[ 0];
- st[21] ^= bc[ 1];
- st[22] ^= bc[ 2];
- st[23] ^= bc[ 3];
- st[24] ^= bc[ 4];
+static void __optimize("O3") keccakf(u64 st[25])
+{
+ int round;
+ for (round = 0; round < KECCAK_ROUNDS; round++) {
+ keccakf_round(st);
/* Iota */
st[0] ^= keccakf_rndc[round];
}
endif
config ACPI_SPCR_TABLE
- bool
+ bool "ACPI Serial Port Console Redirection Support"
+ default y if X86
+ help
+ Enable support for Serial Port Console Redirection (SPCR) Table.
+ This table provides information about the configuration of the
+ earlycon console.
config ACPI_LPIT
bool
poll_wait(file, &acpi_aml_io.wait, wait);
if (acpi_aml_user_readable())
- masks |= POLLIN | POLLRDNORM;
+ masks |= EPOLLIN | EPOLLRDNORM;
if (acpi_aml_user_writable())
- masks |= POLLOUT | POLLWRNORM;
+ masks |= EPOLLOUT | EPOLLWRNORM;
return masks;
}
MODULE_DESCRIPTION("ACPI Video Driver");
MODULE_LICENSE("GPL");
-static bool brightness_switch_enabled = 1;
+static bool brightness_switch_enabled = true;
module_param(brightness_switch_enabled, bool, 0644);
/*
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* Common info for tool signons */
#define ACPICA_NAME "Intel ACPI Component Architecture"
-#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2017 Intel Corporation"
+#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2018 Intel Corporation"
#if ACPI_MACHINE_WIDTH == 64
#define ACPI_WIDTH " (64-bit version)"
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
******************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
DMI_MATCH(DMI_PRODUCT_NAME, "UX305LA"),
},
},
+ {
+ .callback = battery_full_discharging_quirk,
+ .ident = "ASUS UX360UA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "UX360UA"),
+ },
+ },
+ {
+ .callback = battery_full_discharging_quirk,
+ .ident = "ASUS UX410UAK",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "UX410UAK"),
+ },
+ },
{},
};
return 0;
}
#endif
+static int set_gbl_term_list(const struct dmi_system_id *id)
+{
+ acpi_gbl_parse_table_as_term_list = 1;
+ return 0;
+}
-static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
+static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
+ /*
+ * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C
+ * mode.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=198515
+ */
+ {
+ .callback = set_gbl_term_list,
+ .ident = "Dell Precision M5530",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"),
+ },
+ },
+ {
+ .callback = set_gbl_term_list,
+ .ident = "Dell XPS 15 9570",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"),
+ },
+ },
/*
* Invoke DSDT corruption work-around on all Toshiba Satellite.
+ * DSDT will be copied to memory.
* https://bugzilla.kernel.org/show_bug.cgi?id=14679
*/
{
{}
};
#else
-static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
+static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
{}
};
#endif
}
return status;
}
+EXPORT_SYMBOL_GPL(acpi_bus_get_status_handle);
int acpi_bus_get_status(struct acpi_device *device)
{
return 0;
}
+ /* Battery devices must have their deps met before calling _STA */
+ if (acpi_device_is_battery(device) && device->dep_unmet) {
+ acpi_set_device_status(device, 0);
+ return 0;
+ }
+
status = acpi_bus_get_status_handle(device->handle, &sta);
if (ACPI_FAILURE(status))
return -ENODEV;
acpi_permanent_mmap = true;
- /*
- * If the machine falls into the DMI check table,
- * DSDT will be copied to memory
- */
- dmi_check_system(dsdt_dmi_table);
+ /* Check machine-specific quirks */
+ dmi_check_system(acpi_quirks_dmi_table);
status = acpi_reallocate_root_table();
if (ACPI_FAILURE(status)) {
* to PCC commands. Keeping it high enough to cover emulators where
* the processors run painfully slow.
*/
-#define NUM_RETRIES 500
+#define NUM_RETRIES 500ULL
struct cppc_attr {
struct attribute attr;
pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
pr->power.states[ACPI_STATE_C1].valid = 1;
pr->power.states[ACPI_STATE_C1].entry_method = ACPI_CSTATE_HALT;
+
+ snprintf(pr->power.states[ACPI_STATE_C1].desc,
+ ACPI_CX_DESC_LEN, "ACPI HLT");
}
/* the C0 state only exists as a filler in our array */
pr->power.states[ACPI_STATE_C0].valid = 1;
{
int ret;
- if (ignore_ppc) {
+ if (ignore_ppc || !pr->performance) {
/*
* Only when it is notification event, the _OST object
* will be evaluated. Otherwise it is skipped.
device->driver_data = hc;
acpi_ec_add_query_handler(hc->ec, hc->query_bit, NULL, smbus_alarm, hc);
- printk(KERN_INFO PREFIX "SBS HC: EC = 0x%p, offset = 0x%0x, query_bit = 0x%0x\n",
- hc->ec, hc->offset, hc->query_bit);
+ dev_info(&device->dev, "SBS HC: offset = 0x%0x, query_bit = 0x%0x\n",
+ hc->offset, hc->query_bit);
return 0;
}
device_initialize(&device->dev);
dev_set_uevent_suppress(&device->dev, true);
acpi_init_coherency(device);
+ /* Assume there are unmet deps until acpi_device_dep_initialize() runs */
+ device->dep_unmet = 1;
}
void acpi_device_add_finalize(struct acpi_device *device)
}
acpi_init_device_object(device, handle, type, sta);
+ /*
+ * For ACPI_BUS_TYPE_DEVICE getting the status is delayed till here so
+ * that we can call acpi_bus_get_status() and use its quirk handling.
+ * Note this must be done before the get power-/wakeup_dev-flags calls.
+ */
+ if (type == ACPI_BUS_TYPE_DEVICE)
+ acpi_bus_get_status(device);
+
acpi_bus_get_power_flags(device);
acpi_bus_get_wakeup_device_flags(device);
return -ENODEV;
*type = ACPI_BUS_TYPE_DEVICE;
- status = acpi_bus_get_status_handle(handle, sta);
- if (ACPI_FAILURE(status))
- *sta = 0;
+ /*
+ * acpi_add_single_object updates this once we've an acpi_device
+ * so that acpi_bus_get_status' quirk handling can be used.
+ */
+ *sta = 0;
break;
case ACPI_TYPE_PROCESSOR:
*type = ACPI_BUS_TYPE_PROCESSOR;
acpi_status status;
int i;
+ adev->dep_unmet = 0;
+
if (!acpi_has_method(adev->handle, "_DEP"))
return;
* occasionally getting stuck as 1. To avoid the potential for a hang, check
* TXFE == 0 instead of BUSY == 1. This may not be suitable for all UART
* implementations, so only do so if an affected platform is detected in
- * parse_spcr().
+ * acpi_parse_spcr().
*/
bool qdf2400_e44_present;
EXPORT_SYMBOL(qdf2400_e44_present);
}
/**
- * parse_spcr() - parse ACPI SPCR table and add preferred console
+ * acpi_parse_spcr() - parse ACPI SPCR table and add preferred console
*
- * @earlycon: set up earlycon for the console specified by the table
+ * @enable_earlycon: set up earlycon for the console specified by the table
+ * @enable_console: setup the console specified by the table.
*
* For the architectures with support for ACPI, CONFIG_ACPI_SPCR_TABLE may be
* defined to parse ACPI SPCR table. As a result of the parsing preferred
- * console is registered and if @earlycon is true, earlycon is set up.
+ * console is registered and if @enable_earlycon is true, earlycon is set up.
+ * If @enable_console is true the system console is also configured.
*
* When CONFIG_ACPI_SPCR_TABLE is defined, this function should be called
* from arch initialization code as soon as the DT/ACPI decision is made.
*
*/
-int __init parse_spcr(bool earlycon)
+int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console)
{
static char opts[64];
struct acpi_table_spcr *table;
if (ACPI_FAILURE(status))
return -ENOENT;
- if (table->header.revision < 2) {
- err = -ENOENT;
- pr_err("wrong table version\n");
- goto done;
- }
+ if (table->header.revision < 2)
+ pr_info("SPCR table version %d\n", table->header.revision);
if (table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
switch (ACPI_ACCESS_BIT_WIDTH((
*/
if (qdf2400_erratum_44_present(&table->header)) {
qdf2400_e44_present = true;
- if (earlycon)
+ if (enable_earlycon)
uart = "qdf2400_e44";
}
pr_info("console: %s\n", opts);
- if (earlycon)
+ if (enable_earlycon)
setup_earlycon(opts);
- err = add_preferred_console(uart, 0, opts + strlen(uart) + 1);
-
+ if (enable_console)
+ err = add_preferred_console(uart, 0, opts + strlen(uart) + 1);
+ else
+ err = 0;
done:
acpi_put_table((struct acpi_table_header *)table);
return err;
ACPI_SIG_SLIC, ACPI_SIG_SPCR, ACPI_SIG_SPMI, ACPI_SIG_TCPA,
ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT,
ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT,
- ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL };
+ ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, ACPI_SIG_IORT,
+ NULL };
#define ACPI_HEADER_SIZE sizeof(struct acpi_table_header)
*/
if ((thread->looper & BINDER_LOOPER_STATE_POLL) &&
waitqueue_active(&thread->wait)) {
- wake_up_poll(&thread->wait, POLLHUP | POLLFREE);
+ wake_up_poll(&thread->wait, EPOLLHUP | POLLFREE);
}
binder_inner_proc_unlock(thread->proc);
poll_wait(filp, &thread->wait, wait);
if (binder_has_work(thread, wait_for_proc_work))
- return POLLIN;
+ return EPOLLIN;
return 0;
}
#else
/* this is pretty, but avoids _divdu3 and is mostly correct */
mult = he_dev->atm_dev->link_rate / ATM_OC3_PCR;
- if (rate_cps > (272 * mult))
+ if (rate_cps > (272ULL * mult))
buf = 4;
- else if (rate_cps > (204 * mult))
+ else if (rate_cps > (204ULL * mult))
buf = 3;
- else if (rate_cps > (136 * mult))
+ else if (rate_cps > (136ULL * mult))
buf = 2;
- else if (rate_cps > (68 * mult))
+ else if (rate_cps > (68ULL * mult))
buf = 1;
else
buf = 0;
return 0;
}
+static int genpd_iterate_idle_states(struct device_node *dn,
+ struct genpd_power_state *states)
+{
+ int ret;
+ struct of_phandle_iterator it;
+ struct device_node *np;
+ int i = 0;
+
+ ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
+ if (ret <= 0)
+ return ret;
+
+ /* Loop over the phandles until all the requested entry is found */
+ of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) {
+ np = it.node;
+ if (!of_match_node(idle_state_match, np))
+ continue;
+ if (states) {
+ ret = genpd_parse_state(&states[i], np);
+ if (ret) {
+ pr_err("Parsing idle state node %pOF failed with err %d\n",
+ np, ret);
+ of_node_put(np);
+ return ret;
+ }
+ }
+ i++;
+ }
+
+ return i;
+}
+
/**
* of_genpd_parse_idle_states: Return array of idle states for the genpd.
*
*
* Returns the device states parsed from the OF node. The memory for the states
* is allocated by this function and is the responsibility of the caller to
- * free the memory after use.
+ * free the memory after use. If no domain idle states is found it returns
+ * -EINVAL and in case of errors, a negative error code.
*/
int of_genpd_parse_idle_states(struct device_node *dn,
struct genpd_power_state **states, int *n)
{
struct genpd_power_state *st;
- struct device_node *np;
- int i = 0;
- int err, ret;
- int count;
- struct of_phandle_iterator it;
- const struct of_device_id *match_id;
+ int ret;
- count = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
- if (count <= 0)
- return -EINVAL;
+ ret = genpd_iterate_idle_states(dn, NULL);
+ if (ret <= 0)
+ return ret < 0 ? ret : -EINVAL;
- st = kcalloc(count, sizeof(*st), GFP_KERNEL);
+ st = kcalloc(ret, sizeof(*st), GFP_KERNEL);
if (!st)
return -ENOMEM;
- /* Loop over the phandles until all the requested entry is found */
- of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) {
- np = it.node;
- match_id = of_match_node(idle_state_match, np);
- if (!match_id)
- continue;
- ret = genpd_parse_state(&st[i++], np);
- if (ret) {
- pr_err
- ("Parsing idle state node %pOF failed with err %d\n",
- np, ret);
- of_node_put(np);
- kfree(st);
- return ret;
- }
+ ret = genpd_iterate_idle_states(dn, st);
+ if (ret <= 0) {
+ kfree(st);
+ return ret < 0 ? ret : -EINVAL;
}
- *n = i;
- if (!i)
- kfree(st);
- else
- *states = st;
+ *states = st;
+ *n = ret;
return 0;
}
#define RBD_FEATURE_STRIPINGV2 (1ULL<<1)
#define RBD_FEATURE_EXCLUSIVE_LOCK (1ULL<<2)
#define RBD_FEATURE_DATA_POOL (1ULL<<7)
+#define RBD_FEATURE_OPERATIONS (1ULL<<8)
#define RBD_FEATURES_ALL (RBD_FEATURE_LAYERING | \
RBD_FEATURE_STRIPINGV2 | \
RBD_FEATURE_EXCLUSIVE_LOCK | \
- RBD_FEATURE_DATA_POOL)
+ RBD_FEATURE_DATA_POOL | \
+ RBD_FEATURE_OPERATIONS)
/* Features supported by this (client software) implementation. */
int result;
rbd_obj_callback_t callback;
- struct completion completion;
struct kref kref;
};
{
dout("%s: obj %p cb %p\n", __func__, obj_request,
obj_request->callback);
- if (obj_request->callback)
- obj_request->callback(obj_request);
- else
- complete_all(&obj_request->completion);
+ obj_request->callback(obj_request);
}
static void rbd_obj_request_error(struct rbd_obj_request *obj_request, int err)
obj_request->which = BAD_WHICH;
obj_request->type = type;
INIT_LIST_HEAD(&obj_request->links);
- init_completion(&obj_request->completion);
kref_init(&obj_request->kref);
dout("%s %p\n", __func__, obj_request);
{
struct rbd_img_request *img_request;
- img_request = kmem_cache_alloc(rbd_img_request_cache, GFP_NOIO);
+ img_request = kmem_cache_zalloc(rbd_img_request_cache, GFP_NOIO);
if (!img_request)
return NULL;
- img_request->rq = NULL;
img_request->rbd_dev = rbd_dev;
img_request->offset = offset;
img_request->length = length;
- img_request->flags = 0;
if (op_type == OBJ_OP_DISCARD) {
img_request_discard_set(img_request);
img_request->snapc = snapc;
}
if (rbd_dev_parent_get(rbd_dev))
img_request_layered_set(img_request);
+
spin_lock_init(&img_request->completion_lock);
- img_request->next_completion = 0;
- img_request->callback = NULL;
- img_request->result = 0;
- img_request->obj_request_count = 0;
INIT_LIST_HEAD(&img_request->obj_requests);
kref_init(&img_request->kref);
parent_request->copyup_pages = NULL;
parent_request->copyup_page_count = 0;
- parent_request->obj_request = NULL;
- rbd_obj_request_put(obj_request);
out_err:
if (pages)
ceph_release_page_vector(pages, page_count);
static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
-static void virtblk_config_changed_work(struct work_struct *work)
+/* The queue's logical block size must be set before calling this */
+static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize)
{
- struct virtio_blk *vblk =
- container_of(work, struct virtio_blk, config_work);
struct virtio_device *vdev = vblk->vdev;
struct request_queue *q = vblk->disk->queue;
char cap_str_2[10], cap_str_10[10];
- char *envp[] = { "RESIZE=1", NULL };
unsigned long long nblocks;
u64 capacity;
STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
dev_notice(&vdev->dev,
- "new size: %llu %d-byte logical blocks (%s/%s)\n",
+ "[%s] %s%llu %d-byte logical blocks (%s/%s)\n",
+ vblk->disk->disk_name,
+ resize ? "new size: " : "",
nblocks,
queue_logical_block_size(q),
cap_str_10,
cap_str_2);
set_capacity(vblk->disk, capacity);
+}
+
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+ struct virtio_blk *vblk =
+ container_of(work, struct virtio_blk, config_work);
+ char *envp[] = { "RESIZE=1", NULL };
+
+ virtblk_update_capacity(vblk, true);
revalidate_disk(vblk->disk);
kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
}
struct request_queue *q;
int err, index;
- u64 cap;
u32 v, blk_size, sg_elems, opt_io_size;
u16 min_io_size;
u8 physical_block_exp, alignment_offset;
if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))
set_disk_ro(vblk->disk, 1);
- /* Host must always specify the capacity. */
- virtio_cread(vdev, struct virtio_blk_config, capacity, &cap);
-
- /* If capacity is too big, truncate with warning. */
- if ((sector_t)cap != cap) {
- dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
- (unsigned long long)cap);
- cap = (sector_t)-1;
- }
- set_capacity(vblk->disk, cap);
-
/* We can handle whatever the host told us to handle. */
blk_queue_max_segments(q, vblk->sg_elems-2);
if (!err && opt_io_size)
blk_queue_io_opt(q, blk_size * opt_io_size);
+ virtblk_update_capacity(vblk, false);
virtio_device_ready(vdev);
device_add_disk(&vdev->dev, vblk->disk);
poll_wait(file, &data->read_wait, wait);
if (!skb_queue_empty(&data->readq))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
- return POLLOUT | POLLWRNORM;
+ return EPOLLOUT | EPOLLWRNORM;
}
static void vhci_open_timeout(struct work_struct *work)
struct apm_user *as = fp->private_data;
poll_wait(fp, &apm_waitqueue, wait);
- return queue_empty(&as->queue) ? 0 : POLLIN | POLLRDNORM;
+ return queue_empty(&as->queue) ? 0 : EPOLLIN | EPOLLRDNORM;
}
/*
{
case DSP56K_DEV_56001:
/* poll_wait(file, ???, wait); */
- return POLLIN | POLLRDNORM | POLLOUT;
+ return EPOLLIN | EPOLLRDNORM | EPOLLOUT;
default:
printk("DSP56k driver: Unknown minor device: %d\n", dev);
#include <linux/uaccess.h> /* for get_user, etc. */
#include <linux/wait.h> /* for wait_queue */
#include <linux/init.h> /* for __init, module_{init,exit} */
-#include <linux/poll.h> /* for POLLIN, etc. */
+#include <linux/poll.h> /* for EPOLLIN, etc. */
#include <linux/dtlk.h> /* local header file for DoubleTalk values */
#ifdef TRACING
if (dtlk_has_indexing && dtlk_readable()) {
del_timer(&dtlk_timer);
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
}
if (dtlk_writeable()) {
del_timer(&dtlk_timer);
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
/* there are no exception conditions */
spin_unlock_irq(&hpet_lock);
if (v != 0)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
ctrl = bt_inb(bt_bmc, BT_CTRL);
if (ctrl & BT_CTRL_H2B_ATN)
- mask |= POLLIN;
+ mask |= EPOLLIN;
if (!(ctrl & (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN)))
- mask |= POLLOUT;
+ mask |= EPOLLOUT;
return mask;
}
spin_lock_irqsave(&priv->recv_msg_lock, flags);
if (!list_empty(&(priv->recv_msgs)))
- mask |= (POLLIN | POLLRDNORM);
+ mask |= (EPOLLIN | EPOLLRDNORM);
spin_unlock_irqrestore(&priv->recv_msg_lock, flags);
spin_lock(&ipmi_read_lock);
if (data_to_read)
- mask |= (POLLIN | POLLRDNORM);
+ mask |= (EPOLLIN | EPOLLRDNORM);
spin_unlock(&ipmi_read_lock);
return mask;
poll_wait(filp, &dev->poll_wait, wait);
if (test_and_clear_bit(BS_READABLE, &dev->buffer_status))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (test_and_clear_bit(BS_WRITABLE, &dev->buffer_status))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
DEBUGP(2, dev, "<- cm4040_poll(%u)\n", mask);
poll_wait(file, &pp->irq_wait, wait);
if (atomic_read(&pp->irqc))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &random_write_wait, wait);
mask = 0;
if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
spin_unlock_irq(&rtc_lock);
if (l != 0)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
#endif
if (status > 0) {
if (status & SAL_IROUTER_INTR_RECV) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (status & SAL_IROUTER_INTR_XMIT) {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
}
{
poll_wait(file, &sonypi_device.fifo_proc_list, wait);
if (kfifo_len(&sonypi_device.fifo))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(filp, &proxy_dev->wq, wait);
- ret = POLLOUT;
+ ret = EPOLLOUT;
mutex_lock(&proxy_dev->buf_lock);
if (proxy_dev->req_len)
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
if (!(proxy_dev->state & STATE_OPENED_FLAG))
- ret |= POLLHUP;
+ ret |= EPOLLHUP;
mutex_unlock(&proxy_dev->buf_lock);
if (!port->guest_connected) {
/* Port got unplugged */
- return POLLHUP;
+ return EPOLLHUP;
}
ret = 0;
if (!will_read_block(port))
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
if (!will_write_block(port))
- ret |= POLLOUT;
+ ret |= EPOLLOUT;
if (!port->host_connected)
- ret |= POLLHUP;
+ ret |= EPOLLHUP;
return ret;
}
spin_lock_irqsave(&channel->wr_spinlock, flags);
if (!channel->wr_empty || channel->wr_ready)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (channel->wr_hangup)
/*
- * Not POLLHUP, because its behavior is in the
- * mist, and POLLIN does what we want: Wake up
+ * Not EPOLLHUP, because its behavior is in the
+ * mist, and EPOLLIN does what we want: Wake up
* the read file descriptor so it sees EOF.
*/
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&channel->wr_spinlock, flags);
}
spin_lock_irqsave(&channel->rd_spinlock, flags);
if (!channel->rd_full)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
spin_unlock_irqrestore(&channel->rd_spinlock, flags);
}
if (channel->endpoint->fatal_error)
- mask |= POLLERR;
+ mask |= EPOLLERR;
return mask;
}
source "drivers/cpufreq/Kconfig.powerpc"
endif
-if AVR32
-config AVR32_AT32AP_CPUFREQ
- bool "CPU frequency driver for AT32AP"
- depends on PLATFORM_AT32AP
- default n
- help
- This enables the CPU frequency driver for AT32AP processors.
- If in doubt, say N.
-endif
-
if IA64
config IA64_ACPI_CPUFREQ
tristate "ACPI Processor P-States driver"
##################################################################################
# Other platform drivers
-obj-$(CONFIG_AVR32_AT32AP_CPUFREQ) += at32ap-cpufreq.o
obj-$(CONFIG_BFIN_CPU_FREQ) += blackfin-cpufreq.o
obj-$(CONFIG_BMIPS_CPUFREQ) += bmips-cpufreq.o
obj-$(CONFIG_CRIS_MACH_ARTPEC3) += cris-artpec3-cpufreq.o
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
+#include <linux/pci.h>
#include <linux/percpu-defs.h>
#include <linux/init.h>
#include <linux/mod_devicetable.h>
static int __init amd_freq_sensitivity_init(void)
{
u64 val;
+ struct pci_dev *pcidev;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
return -ENODEV;
- if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK))
- return -ENODEV;
+ pcidev = pci_get_device(PCI_VENDOR_ID_AMD,
+ PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL);
+
+ if (!pcidev) {
+ if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK))
+ return -ENODEV;
+ }
if (rdmsrl_safe(MSR_AMD64_FREQ_SENSITIVITY_ACTUAL, &val))
return -ENODEV;
+++ /dev/null
-/*
- * Copyright (C) 2004-2007 Atmel Corporation
- *
- * Based on MIPS implementation arch/mips/kernel/time.c
- * Copyright 2001 MontaVista Software Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*#define DEBUG*/
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/cpufreq.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-
-static struct cpufreq_frequency_table *freq_table;
-
-static unsigned int ref_freq;
-static unsigned long loops_per_jiffy_ref;
-
-static int at32_set_target(struct cpufreq_policy *policy, unsigned int index)
-{
- unsigned int old_freq, new_freq;
-
- old_freq = policy->cur;
- new_freq = freq_table[index].frequency;
-
- if (!ref_freq) {
- ref_freq = old_freq;
- loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy;
- }
-
- if (old_freq < new_freq)
- boot_cpu_data.loops_per_jiffy = cpufreq_scale(
- loops_per_jiffy_ref, ref_freq, new_freq);
- clk_set_rate(policy->clk, new_freq * 1000);
- if (new_freq < old_freq)
- boot_cpu_data.loops_per_jiffy = cpufreq_scale(
- loops_per_jiffy_ref, ref_freq, new_freq);
-
- return 0;
-}
-
-static int at32_cpufreq_driver_init(struct cpufreq_policy *policy)
-{
- unsigned int frequency, rate, min_freq;
- struct clk *cpuclk;
- int retval, steps, i;
-
- if (policy->cpu != 0)
- return -EINVAL;
-
- cpuclk = clk_get(NULL, "cpu");
- if (IS_ERR(cpuclk)) {
- pr_debug("cpufreq: could not get CPU clk\n");
- retval = PTR_ERR(cpuclk);
- goto out_err;
- }
-
- min_freq = (clk_round_rate(cpuclk, 1) + 500) / 1000;
- frequency = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
- policy->cpuinfo.transition_latency = 0;
-
- /*
- * AVR32 CPU frequency rate scales in power of two between maximum and
- * minimum, also add space for the table end marker.
- *
- * Further validate that the frequency is usable, and append it to the
- * frequency table.
- */
- steps = fls(frequency / min_freq) + 1;
- freq_table = kzalloc(steps * sizeof(struct cpufreq_frequency_table),
- GFP_KERNEL);
- if (!freq_table) {
- retval = -ENOMEM;
- goto out_err_put_clk;
- }
-
- for (i = 0; i < (steps - 1); i++) {
- rate = clk_round_rate(cpuclk, frequency * 1000) / 1000;
-
- if (rate != frequency)
- freq_table[i].frequency = CPUFREQ_ENTRY_INVALID;
- else
- freq_table[i].frequency = frequency;
-
- frequency /= 2;
- }
-
- policy->clk = cpuclk;
- freq_table[steps - 1].frequency = CPUFREQ_TABLE_END;
-
- retval = cpufreq_table_validate_and_show(policy, freq_table);
- if (!retval) {
- printk("cpufreq: AT32AP CPU frequency driver\n");
- return 0;
- }
-
- kfree(freq_table);
-out_err_put_clk:
- clk_put(cpuclk);
-out_err:
- return retval;
-}
-
-static struct cpufreq_driver at32_driver = {
- .name = "at32ap",
- .init = at32_cpufreq_driver_init,
- .verify = cpufreq_generic_frequency_table_verify,
- .target_index = at32_set_target,
- .get = cpufreq_generic_get,
- .flags = CPUFREQ_STICKY,
-};
-
-static int __init at32_cpufreq_init(void)
-{
- return cpufreq_register_driver(&at32_driver);
-}
-late_initcall(at32_cpufreq_init);
if (!cpufreq_driver)
return;
+ if (unlikely(!cpufreq_suspended))
+ return;
+
cpufreq_suspended = false;
if (!has_target() && !cpufreq_driver->resume)
static int init_div_table(void)
{
struct cpufreq_frequency_table *pos, *freq_tbl = dvfs_info->freq_table;
- unsigned int tmp, clk_div, ema_div, freq, volt_id;
+ unsigned int tmp, clk_div, ema_div, freq, volt_id, idx;
struct dev_pm_opp *opp;
- cpufreq_for_each_entry(pos, freq_tbl) {
+ cpufreq_for_each_entry_idx(pos, freq_tbl, idx) {
opp = dev_pm_opp_find_freq_exact(dvfs_info->dev,
pos->frequency * 1000, true);
if (IS_ERR(opp)) {
tmp = (clk_div | ema_div | (volt_id << P0_7_VDD_SHIFT)
| ((freq / FREQ_UNIT) << P0_7_FREQ_SHIFT));
- __raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 *
- (pos - freq_tbl));
+ __raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 * idx);
dev_pm_opp_put(opp);
}
break;
}
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, i) {
freq = pos->frequency;
- i = pos - table;
if ((freq < policy->min) || (freq > policy->max))
continue;
if (freq == target_freq) {
unsigned int freq)
{
struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+ int idx;
if (unlikely(!table)) {
pr_debug("%s: Unable to find frequency table\n", __func__);
return -ENOENT;
}
- cpufreq_for_each_valid_entry(pos, table)
+ cpufreq_for_each_valid_entry_idx(pos, table, idx)
if (pos->frequency == freq)
- return pos - table;
+ return idx;
return -EINVAL;
}
};
module_platform_driver(imx6q_cpufreq_platdrv);
+MODULE_ALIAS("platform:imx6q-cpufreq");
MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
MODULE_DESCRIPTION("Freescale i.MX6Q cpufreq driver");
MODULE_LICENSE("GPL");
return 0;
}
+static void intel_pstate_hwp_enable(struct cpudata *cpudata);
+
static int intel_pstate_resume(struct cpufreq_policy *policy)
{
if (!hwp_active)
mutex_lock(&intel_pstate_limits_lock);
+ if (policy->cpu == 0)
+ intel_pstate_hwp_enable(all_cpu_data[policy->cpu]);
+
all_cpu_data[policy->cpu]->epp_policy = 0;
intel_pstate_hwp_set(policy->cpu);
/* Calculate kHz for one voltage step */
kHz_step = (highest_speed - min_vid_speed) / numvscales;
- cpufreq_for_each_entry(freq_pos, longhaul_table) {
+ cpufreq_for_each_entry_idx(freq_pos, longhaul_table, j) {
speed = freq_pos->frequency;
if (speed > min_vid_speed)
pos = (speed - min_vid_speed) / kHz_step + minvid.pos;
freq_pos->driver_data |= mV_vrm_table[pos] << 8;
vid = vrm_mV_table[mV_vrm_table[pos]];
pr_info("f: %d kHz, index: %d, vid: %d mV\n",
- speed, (int)(freq_pos - longhaul_table), vid.mV);
+ speed, j, vid.mV);
}
can_scale_voltage = 1;
struct cpufreq_frequency_table *pos;
const u32 *max_freqp;
u32 max_freq;
- int cur_astate;
+ int cur_astate, idx;
struct resource res;
struct device_node *cpu, *dn;
int err = -ENODEV;
pr_debug("initializing frequency table\n");
/* initialize frequency table */
- cpufreq_for_each_entry(pos, pas_freqs) {
+ cpufreq_for_each_entry_idx(pos, pas_freqs, idx) {
pos->frequency = get_astate_freq(pos->driver_data) * 100000;
- pr_debug("%d: %d\n", (int)(pos - pas_freqs), pos->frequency);
+ pr_debug("%d: %d\n", idx, pos->frequency);
}
cur_astate = get_cur_astate(policy->cpu);
if (IS_ERR(priv->clk)) {
dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d\n",
__func__, cpu_dev->id);
+ ret = PTR_ERR(priv->clk);
goto out_free_cpufreq_table;
}
static void scpi_cpufreq_ready(struct cpufreq_policy *policy)
{
struct scpi_data *priv = policy->driver_data;
- struct thermal_cooling_device *cdev;
- cdev = of_cpufreq_cooling_register(policy);
- if (!IS_ERR(cdev))
- priv->cdev = cdev;
+ priv->cdev = of_cpufreq_cooling_register(policy);
}
static struct cpufreq_driver scpi_cpufreq_driver = {
* without any error (HW optimizations for later
* CAAM eras), then try again.
*/
+ if (ret)
+ break;
+
rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK;
if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) ||
- !(rdsta_val & (1 << sh_idx)))
+ !(rdsta_val & (1 << sh_idx))) {
ret = -EAGAIN;
- if (ret)
break;
+ }
+
dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx);
/* Clear the contents before recreating the descriptor */
memset(desc, 0x00, CAAM_CMD_SZ * 7);
config CRYPTO_DEV_CCP_DD
tristate "Secure Processor device driver"
+ depends on CPU_SUP_AMD || ARM64
default m
help
Provides AMD Secure Processor device driver.
Support for using the cryptographic API with the AMD Cryptographic
Coprocessor. This module supports offload of SHA and AES algorithms.
If you choose 'M' here, this module will be called ccp_crypto.
+
+config CRYPTO_DEV_SP_PSP
+ bool "Platform Security Processor (PSP) device"
+ default y
+ depends on CRYPTO_DEV_CCP_DD && X86_64
+ help
+ Provide support for the AMD Platform Security Processor (PSP).
+ The PSP is a dedicated processor that provides support for key
+ management commands in Secure Encrypted Virtualization (SEV) mode,
+ along with software-based Trusted Execution Environment (TEE) to
+ enable third-party trusted applications.
ccp-dmaengine.o \
ccp-debugfs.o
ccp-$(CONFIG_PCI) += sp-pci.o
+ccp-$(CONFIG_CRYPTO_DEV_SP_PSP) += psp-dev.o
obj-$(CONFIG_CRYPTO_DEV_CCP_CRYPTO) += ccp-crypto.o
ccp-crypto-objs := ccp-crypto-main.o \
--- /dev/null
+/*
+ * AMD Platform Security Processor (PSP) interface
+ *
+ * Copyright (C) 2016-2017 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <linux/hw_random.h>
+#include <linux/ccp.h>
+
+#include "sp-dev.h"
+#include "psp-dev.h"
+
+#define DEVICE_NAME "sev"
+
+static DEFINE_MUTEX(sev_cmd_mutex);
+static struct sev_misc_dev *misc_dev;
+static struct psp_device *psp_master;
+
+static struct psp_device *psp_alloc_struct(struct sp_device *sp)
+{
+ struct device *dev = sp->dev;
+ struct psp_device *psp;
+
+ psp = devm_kzalloc(dev, sizeof(*psp), GFP_KERNEL);
+ if (!psp)
+ return NULL;
+
+ psp->dev = dev;
+ psp->sp = sp;
+
+ snprintf(psp->name, sizeof(psp->name), "psp-%u", sp->ord);
+
+ return psp;
+}
+
+static irqreturn_t psp_irq_handler(int irq, void *data)
+{
+ struct psp_device *psp = data;
+ unsigned int status;
+ int reg;
+
+ /* Read the interrupt status: */
+ status = ioread32(psp->io_regs + PSP_P2CMSG_INTSTS);
+
+ /* Check if it is command completion: */
+ if (!(status & BIT(PSP_CMD_COMPLETE_REG)))
+ goto done;
+
+ /* Check if it is SEV command completion: */
+ reg = ioread32(psp->io_regs + PSP_CMDRESP);
+ if (reg & PSP_CMDRESP_RESP) {
+ psp->sev_int_rcvd = 1;
+ wake_up(&psp->sev_int_queue);
+ }
+
+done:
+ /* Clear the interrupt status by writing the same value we read. */
+ iowrite32(status, psp->io_regs + PSP_P2CMSG_INTSTS);
+
+ return IRQ_HANDLED;
+}
+
+static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg)
+{
+ psp->sev_int_rcvd = 0;
+
+ wait_event(psp->sev_int_queue, psp->sev_int_rcvd);
+ *reg = ioread32(psp->io_regs + PSP_CMDRESP);
+}
+
+static int sev_cmd_buffer_len(int cmd)
+{
+ switch (cmd) {
+ case SEV_CMD_INIT: return sizeof(struct sev_data_init);
+ case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status);
+ case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr);
+ case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import);
+ case SEV_CMD_PDH_CERT_EXPORT: return sizeof(struct sev_data_pdh_cert_export);
+ case SEV_CMD_LAUNCH_START: return sizeof(struct sev_data_launch_start);
+ case SEV_CMD_LAUNCH_UPDATE_DATA: return sizeof(struct sev_data_launch_update_data);
+ case SEV_CMD_LAUNCH_UPDATE_VMSA: return sizeof(struct sev_data_launch_update_vmsa);
+ case SEV_CMD_LAUNCH_FINISH: return sizeof(struct sev_data_launch_finish);
+ case SEV_CMD_LAUNCH_MEASURE: return sizeof(struct sev_data_launch_measure);
+ case SEV_CMD_ACTIVATE: return sizeof(struct sev_data_activate);
+ case SEV_CMD_DEACTIVATE: return sizeof(struct sev_data_deactivate);
+ case SEV_CMD_DECOMMISSION: return sizeof(struct sev_data_decommission);
+ case SEV_CMD_GUEST_STATUS: return sizeof(struct sev_data_guest_status);
+ case SEV_CMD_DBG_DECRYPT: return sizeof(struct sev_data_dbg);
+ case SEV_CMD_DBG_ENCRYPT: return sizeof(struct sev_data_dbg);
+ case SEV_CMD_SEND_START: return sizeof(struct sev_data_send_start);
+ case SEV_CMD_SEND_UPDATE_DATA: return sizeof(struct sev_data_send_update_data);
+ case SEV_CMD_SEND_UPDATE_VMSA: return sizeof(struct sev_data_send_update_vmsa);
+ case SEV_CMD_SEND_FINISH: return sizeof(struct sev_data_send_finish);
+ case SEV_CMD_RECEIVE_START: return sizeof(struct sev_data_receive_start);
+ case SEV_CMD_RECEIVE_FINISH: return sizeof(struct sev_data_receive_finish);
+ case SEV_CMD_RECEIVE_UPDATE_DATA: return sizeof(struct sev_data_receive_update_data);
+ case SEV_CMD_RECEIVE_UPDATE_VMSA: return sizeof(struct sev_data_receive_update_vmsa);
+ case SEV_CMD_LAUNCH_UPDATE_SECRET: return sizeof(struct sev_data_launch_secret);
+ default: return 0;
+ }
+
+ return 0;
+}
+
+static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
+{
+ struct psp_device *psp = psp_master;
+ unsigned int phys_lsb, phys_msb;
+ unsigned int reg, ret = 0;
+
+ if (!psp)
+ return -ENODEV;
+
+ /* Get the physical address of the command buffer */
+ phys_lsb = data ? lower_32_bits(__psp_pa(data)) : 0;
+ phys_msb = data ? upper_32_bits(__psp_pa(data)) : 0;
+
+ dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x\n",
+ cmd, phys_msb, phys_lsb);
+
+ print_hex_dump_debug("(in): ", DUMP_PREFIX_OFFSET, 16, 2, data,
+ sev_cmd_buffer_len(cmd), false);
+
+ iowrite32(phys_lsb, psp->io_regs + PSP_CMDBUFF_ADDR_LO);
+ iowrite32(phys_msb, psp->io_regs + PSP_CMDBUFF_ADDR_HI);
+
+ reg = cmd;
+ reg <<= PSP_CMDRESP_CMD_SHIFT;
+ reg |= PSP_CMDRESP_IOC;
+ iowrite32(reg, psp->io_regs + PSP_CMDRESP);
+
+ /* wait for command completion */
+ sev_wait_cmd_ioc(psp, ®);
+
+ if (psp_ret)
+ *psp_ret = reg & PSP_CMDRESP_ERR_MASK;
+
+ if (reg & PSP_CMDRESP_ERR_MASK) {
+ dev_dbg(psp->dev, "sev command %#x failed (%#010x)\n",
+ cmd, reg & PSP_CMDRESP_ERR_MASK);
+ ret = -EIO;
+ }
+
+ print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data,
+ sev_cmd_buffer_len(cmd), false);
+
+ return ret;
+}
+
+static int sev_do_cmd(int cmd, void *data, int *psp_ret)
+{
+ int rc;
+
+ mutex_lock(&sev_cmd_mutex);
+ rc = __sev_do_cmd_locked(cmd, data, psp_ret);
+ mutex_unlock(&sev_cmd_mutex);
+
+ return rc;
+}
+
+static int __sev_platform_init_locked(int *error)
+{
+ struct psp_device *psp = psp_master;
+ int rc = 0;
+
+ if (!psp)
+ return -ENODEV;
+
+ if (psp->sev_state == SEV_STATE_INIT)
+ return 0;
+
+ rc = __sev_do_cmd_locked(SEV_CMD_INIT, &psp->init_cmd_buf, error);
+ if (rc)
+ return rc;
+
+ psp->sev_state = SEV_STATE_INIT;
+ dev_dbg(psp->dev, "SEV firmware initialized\n");
+
+ return rc;
+}
+
+int sev_platform_init(int *error)
+{
+ int rc;
+
+ mutex_lock(&sev_cmd_mutex);
+ rc = __sev_platform_init_locked(error);
+ mutex_unlock(&sev_cmd_mutex);
+
+ return rc;
+}
+EXPORT_SYMBOL_GPL(sev_platform_init);
+
+static int __sev_platform_shutdown_locked(int *error)
+{
+ int ret;
+
+ ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, 0, error);
+ if (ret)
+ return ret;
+
+ psp_master->sev_state = SEV_STATE_UNINIT;
+ dev_dbg(psp_master->dev, "SEV firmware shutdown\n");
+
+ return ret;
+}
+
+static int sev_platform_shutdown(int *error)
+{
+ int rc;
+
+ mutex_lock(&sev_cmd_mutex);
+ rc = __sev_platform_shutdown_locked(NULL);
+ mutex_unlock(&sev_cmd_mutex);
+
+ return rc;
+}
+
+static int sev_get_platform_state(int *state, int *error)
+{
+ int rc;
+
+ rc = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS,
+ &psp_master->status_cmd_buf, error);
+ if (rc)
+ return rc;
+
+ *state = psp_master->status_cmd_buf.state;
+ return rc;
+}
+
+static int sev_ioctl_do_reset(struct sev_issue_cmd *argp)
+{
+ int state, rc;
+
+ /*
+ * The SEV spec requires that FACTORY_RESET must be issued in
+ * UNINIT state. Before we go further lets check if any guest is
+ * active.
+ *
+ * If FW is in WORKING state then deny the request otherwise issue
+ * SHUTDOWN command do INIT -> UNINIT before issuing the FACTORY_RESET.
+ *
+ */
+ rc = sev_get_platform_state(&state, &argp->error);
+ if (rc)
+ return rc;
+
+ if (state == SEV_STATE_WORKING)
+ return -EBUSY;
+
+ if (state == SEV_STATE_INIT) {
+ rc = __sev_platform_shutdown_locked(&argp->error);
+ if (rc)
+ return rc;
+ }
+
+ return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, 0, &argp->error);
+}
+
+static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp)
+{
+ struct sev_user_data_status *data = &psp_master->status_cmd_buf;
+ int ret;
+
+ ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, data, &argp->error);
+ if (ret)
+ return ret;
+
+ if (copy_to_user((void __user *)argp->data, data, sizeof(*data)))
+ ret = -EFAULT;
+
+ return ret;
+}
+
+static int sev_ioctl_do_pek_pdh_gen(int cmd, struct sev_issue_cmd *argp)
+{
+ int rc;
+
+ if (psp_master->sev_state == SEV_STATE_UNINIT) {
+ rc = __sev_platform_init_locked(&argp->error);
+ if (rc)
+ return rc;
+ }
+
+ return __sev_do_cmd_locked(cmd, 0, &argp->error);
+}
+
+static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp)
+{
+ struct sev_user_data_pek_csr input;
+ struct sev_data_pek_csr *data;
+ void *blob = NULL;
+ int ret;
+
+ if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
+ return -EFAULT;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* userspace wants to query CSR length */
+ if (!input.address || !input.length)
+ goto cmd;
+
+ /* allocate a physically contiguous buffer to store the CSR blob */
+ if (!access_ok(VERIFY_WRITE, input.address, input.length) ||
+ input.length > SEV_FW_BLOB_MAX_SIZE) {
+ ret = -EFAULT;
+ goto e_free;
+ }
+
+ blob = kmalloc(input.length, GFP_KERNEL);
+ if (!blob) {
+ ret = -ENOMEM;
+ goto e_free;
+ }
+
+ data->address = __psp_pa(blob);
+ data->len = input.length;
+
+cmd:
+ if (psp_master->sev_state == SEV_STATE_UNINIT) {
+ ret = __sev_platform_init_locked(&argp->error);
+ if (ret)
+ goto e_free_blob;
+ }
+
+ ret = __sev_do_cmd_locked(SEV_CMD_PEK_CSR, data, &argp->error);
+
+ /* If we query the CSR length, FW responded with expected data. */
+ input.length = data->len;
+
+ if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) {
+ ret = -EFAULT;
+ goto e_free_blob;
+ }
+
+ if (blob) {
+ if (copy_to_user((void __user *)input.address, blob, input.length))
+ ret = -EFAULT;
+ }
+
+e_free_blob:
+ kfree(blob);
+e_free:
+ kfree(data);
+ return ret;
+}
+
+void *psp_copy_user_blob(u64 __user uaddr, u32 len)
+{
+ void *data;
+
+ if (!uaddr || !len)
+ return ERR_PTR(-EINVAL);
+
+ /* verify that blob length does not exceed our limit */
+ if (len > SEV_FW_BLOB_MAX_SIZE)
+ return ERR_PTR(-EINVAL);
+
+ data = kmalloc(len, GFP_KERNEL);
+ if (!data)
+ return ERR_PTR(-ENOMEM);
+
+ if (copy_from_user(data, (void __user *)(uintptr_t)uaddr, len))
+ goto e_free;
+
+ return data;
+
+e_free:
+ kfree(data);
+ return ERR_PTR(-EFAULT);
+}
+EXPORT_SYMBOL_GPL(psp_copy_user_blob);
+
+static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp)
+{
+ struct sev_user_data_pek_cert_import input;
+ struct sev_data_pek_cert_import *data;
+ void *pek_blob, *oca_blob;
+ int ret;
+
+ if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
+ return -EFAULT;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* copy PEK certificate blobs from userspace */
+ pek_blob = psp_copy_user_blob(input.pek_cert_address, input.pek_cert_len);
+ if (IS_ERR(pek_blob)) {
+ ret = PTR_ERR(pek_blob);
+ goto e_free;
+ }
+
+ data->pek_cert_address = __psp_pa(pek_blob);
+ data->pek_cert_len = input.pek_cert_len;
+
+ /* copy PEK certificate blobs from userspace */
+ oca_blob = psp_copy_user_blob(input.oca_cert_address, input.oca_cert_len);
+ if (IS_ERR(oca_blob)) {
+ ret = PTR_ERR(oca_blob);
+ goto e_free_pek;
+ }
+
+ data->oca_cert_address = __psp_pa(oca_blob);
+ data->oca_cert_len = input.oca_cert_len;
+
+ /* If platform is not in INIT state then transition it to INIT */
+ if (psp_master->sev_state != SEV_STATE_INIT) {
+ ret = __sev_platform_init_locked(&argp->error);
+ if (ret)
+ goto e_free_oca;
+ }
+
+ ret = __sev_do_cmd_locked(SEV_CMD_PEK_CERT_IMPORT, data, &argp->error);
+
+e_free_oca:
+ kfree(oca_blob);
+e_free_pek:
+ kfree(pek_blob);
+e_free:
+ kfree(data);
+ return ret;
+}
+
+static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp)
+{
+ struct sev_user_data_pdh_cert_export input;
+ void *pdh_blob = NULL, *cert_blob = NULL;
+ struct sev_data_pdh_cert_export *data;
+ int ret;
+
+ if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
+ return -EFAULT;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* Userspace wants to query the certificate length. */
+ if (!input.pdh_cert_address ||
+ !input.pdh_cert_len ||
+ !input.cert_chain_address)
+ goto cmd;
+
+ /* Allocate a physically contiguous buffer to store the PDH blob. */
+ if ((input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) ||
+ !access_ok(VERIFY_WRITE, input.pdh_cert_address, input.pdh_cert_len)) {
+ ret = -EFAULT;
+ goto e_free;
+ }
+
+ /* Allocate a physically contiguous buffer to store the cert chain blob. */
+ if ((input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE) ||
+ !access_ok(VERIFY_WRITE, input.cert_chain_address, input.cert_chain_len)) {
+ ret = -EFAULT;
+ goto e_free;
+ }
+
+ pdh_blob = kmalloc(input.pdh_cert_len, GFP_KERNEL);
+ if (!pdh_blob) {
+ ret = -ENOMEM;
+ goto e_free;
+ }
+
+ data->pdh_cert_address = __psp_pa(pdh_blob);
+ data->pdh_cert_len = input.pdh_cert_len;
+
+ cert_blob = kmalloc(input.cert_chain_len, GFP_KERNEL);
+ if (!cert_blob) {
+ ret = -ENOMEM;
+ goto e_free_pdh;
+ }
+
+ data->cert_chain_address = __psp_pa(cert_blob);
+ data->cert_chain_len = input.cert_chain_len;
+
+cmd:
+ /* If platform is not in INIT state then transition it to INIT. */
+ if (psp_master->sev_state != SEV_STATE_INIT) {
+ ret = __sev_platform_init_locked(&argp->error);
+ if (ret)
+ goto e_free_cert;
+ }
+
+ ret = __sev_do_cmd_locked(SEV_CMD_PDH_CERT_EXPORT, data, &argp->error);
+
+ /* If we query the length, FW responded with expected data. */
+ input.cert_chain_len = data->cert_chain_len;
+ input.pdh_cert_len = data->pdh_cert_len;
+
+ if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) {
+ ret = -EFAULT;
+ goto e_free_cert;
+ }
+
+ if (pdh_blob) {
+ if (copy_to_user((void __user *)input.pdh_cert_address,
+ pdh_blob, input.pdh_cert_len)) {
+ ret = -EFAULT;
+ goto e_free_cert;
+ }
+ }
+
+ if (cert_blob) {
+ if (copy_to_user((void __user *)input.cert_chain_address,
+ cert_blob, input.cert_chain_len))
+ ret = -EFAULT;
+ }
+
+e_free_cert:
+ kfree(cert_blob);
+e_free_pdh:
+ kfree(pdh_blob);
+e_free:
+ kfree(data);
+ return ret;
+}
+
+static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct sev_issue_cmd input;
+ int ret = -EFAULT;
+
+ if (!psp_master)
+ return -ENODEV;
+
+ if (ioctl != SEV_ISSUE_CMD)
+ return -EINVAL;
+
+ if (copy_from_user(&input, argp, sizeof(struct sev_issue_cmd)))
+ return -EFAULT;
+
+ if (input.cmd > SEV_MAX)
+ return -EINVAL;
+
+ mutex_lock(&sev_cmd_mutex);
+
+ switch (input.cmd) {
+
+ case SEV_FACTORY_RESET:
+ ret = sev_ioctl_do_reset(&input);
+ break;
+ case SEV_PLATFORM_STATUS:
+ ret = sev_ioctl_do_platform_status(&input);
+ break;
+ case SEV_PEK_GEN:
+ ret = sev_ioctl_do_pek_pdh_gen(SEV_CMD_PEK_GEN, &input);
+ break;
+ case SEV_PDH_GEN:
+ ret = sev_ioctl_do_pek_pdh_gen(SEV_CMD_PDH_GEN, &input);
+ break;
+ case SEV_PEK_CSR:
+ ret = sev_ioctl_do_pek_csr(&input);
+ break;
+ case SEV_PEK_CERT_IMPORT:
+ ret = sev_ioctl_do_pek_import(&input);
+ break;
+ case SEV_PDH_CERT_EXPORT:
+ ret = sev_ioctl_do_pdh_export(&input);
+ break;
+ default:
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (copy_to_user(argp, &input, sizeof(struct sev_issue_cmd)))
+ ret = -EFAULT;
+out:
+ mutex_unlock(&sev_cmd_mutex);
+
+ return ret;
+}
+
+static const struct file_operations sev_fops = {
+ .owner = THIS_MODULE,
+ .unlocked_ioctl = sev_ioctl,
+};
+
+int sev_platform_status(struct sev_user_data_status *data, int *error)
+{
+ return sev_do_cmd(SEV_CMD_PLATFORM_STATUS, data, error);
+}
+EXPORT_SYMBOL_GPL(sev_platform_status);
+
+int sev_guest_deactivate(struct sev_data_deactivate *data, int *error)
+{
+ return sev_do_cmd(SEV_CMD_DEACTIVATE, data, error);
+}
+EXPORT_SYMBOL_GPL(sev_guest_deactivate);
+
+int sev_guest_activate(struct sev_data_activate *data, int *error)
+{
+ return sev_do_cmd(SEV_CMD_ACTIVATE, data, error);
+}
+EXPORT_SYMBOL_GPL(sev_guest_activate);
+
+int sev_guest_decommission(struct sev_data_decommission *data, int *error)
+{
+ return sev_do_cmd(SEV_CMD_DECOMMISSION, data, error);
+}
+EXPORT_SYMBOL_GPL(sev_guest_decommission);
+
+int sev_guest_df_flush(int *error)
+{
+ return sev_do_cmd(SEV_CMD_DF_FLUSH, 0, error);
+}
+EXPORT_SYMBOL_GPL(sev_guest_df_flush);
+
+static void sev_exit(struct kref *ref)
+{
+ struct sev_misc_dev *misc_dev = container_of(ref, struct sev_misc_dev, refcount);
+
+ misc_deregister(&misc_dev->misc);
+}
+
+static int sev_misc_init(struct psp_device *psp)
+{
+ struct device *dev = psp->dev;
+ int ret;
+
+ /*
+ * SEV feature support can be detected on multiple devices but the SEV
+ * FW commands must be issued on the master. During probe, we do not
+ * know the master hence we create /dev/sev on the first device probe.
+ * sev_do_cmd() finds the right master device to which to issue the
+ * command to the firmware.
+ */
+ if (!misc_dev) {
+ struct miscdevice *misc;
+
+ misc_dev = devm_kzalloc(dev, sizeof(*misc_dev), GFP_KERNEL);
+ if (!misc_dev)
+ return -ENOMEM;
+
+ misc = &misc_dev->misc;
+ misc->minor = MISC_DYNAMIC_MINOR;
+ misc->name = DEVICE_NAME;
+ misc->fops = &sev_fops;
+
+ ret = misc_register(misc);
+ if (ret)
+ return ret;
+
+ kref_init(&misc_dev->refcount);
+ } else {
+ kref_get(&misc_dev->refcount);
+ }
+
+ init_waitqueue_head(&psp->sev_int_queue);
+ psp->sev_misc = misc_dev;
+ dev_dbg(dev, "registered SEV device\n");
+
+ return 0;
+}
+
+static int sev_init(struct psp_device *psp)
+{
+ /* Check if device supports SEV feature */
+ if (!(ioread32(psp->io_regs + PSP_FEATURE_REG) & 1)) {
+ dev_dbg(psp->dev, "device does not support SEV\n");
+ return 1;
+ }
+
+ return sev_misc_init(psp);
+}
+
+int psp_dev_init(struct sp_device *sp)
+{
+ struct device *dev = sp->dev;
+ struct psp_device *psp;
+ int ret;
+
+ ret = -ENOMEM;
+ psp = psp_alloc_struct(sp);
+ if (!psp)
+ goto e_err;
+
+ sp->psp_data = psp;
+
+ psp->vdata = (struct psp_vdata *)sp->dev_vdata->psp_vdata;
+ if (!psp->vdata) {
+ ret = -ENODEV;
+ dev_err(dev, "missing driver data\n");
+ goto e_err;
+ }
+
+ psp->io_regs = sp->io_map + psp->vdata->offset;
+
+ /* Disable and clear interrupts until ready */
+ iowrite32(0, psp->io_regs + PSP_P2CMSG_INTEN);
+ iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTSTS);
+
+ /* Request an irq */
+ ret = sp_request_psp_irq(psp->sp, psp_irq_handler, psp->name, psp);
+ if (ret) {
+ dev_err(dev, "psp: unable to allocate an IRQ\n");
+ goto e_err;
+ }
+
+ ret = sev_init(psp);
+ if (ret)
+ goto e_irq;
+
+ if (sp->set_psp_master_device)
+ sp->set_psp_master_device(sp);
+
+ /* Enable interrupt */
+ iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTEN);
+
+ return 0;
+
+e_irq:
+ sp_free_psp_irq(psp->sp, psp);
+e_err:
+ sp->psp_data = NULL;
+
+ dev_notice(dev, "psp initialization failed\n");
+
+ return ret;
+}
+
+void psp_dev_destroy(struct sp_device *sp)
+{
+ struct psp_device *psp = sp->psp_data;
+
+ if (psp->sev_misc)
+ kref_put(&misc_dev->refcount, sev_exit);
+
+ sp_free_psp_irq(sp, psp);
+}
+
+int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd,
+ void *data, int *error)
+{
+ if (!filep || filep->f_op != &sev_fops)
+ return -EBADF;
+
+ return sev_do_cmd(cmd, data, error);
+}
+EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user);
+
+void psp_pci_init(void)
+{
+ struct sev_user_data_status *status;
+ struct sp_device *sp;
+ int error, rc;
+
+ sp = sp_get_psp_master_device();
+ if (!sp)
+ return;
+
+ psp_master = sp->psp_data;
+
+ /* Initialize the platform */
+ rc = sev_platform_init(&error);
+ if (rc) {
+ dev_err(sp->dev, "SEV: failed to INIT error %#x\n", error);
+ goto err;
+ }
+
+ /* Display SEV firmware version */
+ status = &psp_master->status_cmd_buf;
+ rc = sev_platform_status(status, &error);
+ if (rc) {
+ dev_err(sp->dev, "SEV: failed to get status error %#x\n", error);
+ goto err;
+ }
+
+ dev_info(sp->dev, "SEV API:%d.%d build:%d\n", status->api_major,
+ status->api_minor, status->build);
+ return;
+
+err:
+ psp_master = NULL;
+}
+
+void psp_pci_exit(void)
+{
+ if (!psp_master)
+ return;
+
+ sev_platform_shutdown(NULL);
+}
--- /dev/null
+/*
+ * AMD Platform Security Processor (PSP) interface driver
+ *
+ * Copyright (C) 2017 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __PSP_DEV_H__
+#define __PSP_DEV_H__
+
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/wait.h>
+#include <linux/dmapool.h>
+#include <linux/hw_random.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/dmaengine.h>
+#include <linux/psp-sev.h>
+#include <linux/miscdevice.h>
+
+#include "sp-dev.h"
+
+#define PSP_C2PMSG(_num) ((_num) << 2)
+#define PSP_CMDRESP PSP_C2PMSG(32)
+#define PSP_CMDBUFF_ADDR_LO PSP_C2PMSG(56)
+#define PSP_CMDBUFF_ADDR_HI PSP_C2PMSG(57)
+#define PSP_FEATURE_REG PSP_C2PMSG(63)
+
+#define PSP_P2CMSG(_num) ((_num) << 2)
+#define PSP_CMD_COMPLETE_REG 1
+#define PSP_CMD_COMPLETE PSP_P2CMSG(PSP_CMD_COMPLETE_REG)
+
+#define PSP_P2CMSG_INTEN 0x0110
+#define PSP_P2CMSG_INTSTS 0x0114
+
+#define PSP_C2PMSG_ATTR_0 0x0118
+#define PSP_C2PMSG_ATTR_1 0x011c
+#define PSP_C2PMSG_ATTR_2 0x0120
+#define PSP_C2PMSG_ATTR_3 0x0124
+#define PSP_P2CMSG_ATTR_0 0x0128
+
+#define PSP_CMDRESP_CMD_SHIFT 16
+#define PSP_CMDRESP_IOC BIT(0)
+#define PSP_CMDRESP_RESP BIT(31)
+#define PSP_CMDRESP_ERR_MASK 0xffff
+
+#define MAX_PSP_NAME_LEN 16
+
+struct sev_misc_dev {
+ struct kref refcount;
+ struct miscdevice misc;
+};
+
+struct psp_device {
+ struct list_head entry;
+
+ struct psp_vdata *vdata;
+ char name[MAX_PSP_NAME_LEN];
+
+ struct device *dev;
+ struct sp_device *sp;
+
+ void __iomem *io_regs;
+
+ int sev_state;
+ unsigned int sev_int_rcvd;
+ wait_queue_head_t sev_int_queue;
+ struct sev_misc_dev *sev_misc;
+ struct sev_user_data_status status_cmd_buf;
+ struct sev_data_init init_cmd_buf;
+};
+
+#endif /* __PSP_DEV_H */
if (sp->dev_vdata->ccp_vdata)
ccp_dev_init(sp);
+ if (sp->dev_vdata->psp_vdata)
+ psp_dev_init(sp);
return 0;
}
if (sp->dev_vdata->ccp_vdata)
ccp_dev_destroy(sp);
+ if (sp->dev_vdata->psp_vdata)
+ psp_dev_destroy(sp);
+
sp_del_device(sp);
}
}
#endif
+struct sp_device *sp_get_psp_master_device(void)
+{
+ struct sp_device *i, *ret = NULL;
+ unsigned long flags;
+
+ write_lock_irqsave(&sp_unit_lock, flags);
+ if (list_empty(&sp_units))
+ goto unlock;
+
+ list_for_each_entry(i, &sp_units, entry) {
+ if (i->psp_data)
+ break;
+ }
+
+ if (i->get_psp_master_device)
+ ret = i->get_psp_master_device();
+unlock:
+ write_unlock_irqrestore(&sp_unit_lock, flags);
+ return ret;
+}
+
static int __init sp_mod_init(void)
{
#ifdef CONFIG_X86
if (ret)
return ret;
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+ psp_pci_init();
+#endif
+
return 0;
#endif
static void __exit sp_mod_exit(void)
{
#ifdef CONFIG_X86
+
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+ psp_pci_exit();
+#endif
+
sp_pci_exit();
#endif
const unsigned int offset;
const unsigned int rsamax;
};
+
+struct psp_vdata {
+ const unsigned int offset;
+};
+
/* Structure to hold SP device data */
struct sp_dev_vdata {
const unsigned int bar;
const struct ccp_vdata *ccp_vdata;
- void *psp_vdata;
+ const struct psp_vdata *psp_vdata;
};
struct sp_device {
/* DMA caching attribute support */
unsigned int axcache;
+ /* get and set master device */
+ struct sp_device*(*get_psp_master_device)(void);
+ void (*set_psp_master_device)(struct sp_device *);
+
bool irq_registered;
bool use_tasklet;
int sp_request_psp_irq(struct sp_device *sp, irq_handler_t handler,
const char *name, void *data);
void sp_free_psp_irq(struct sp_device *sp, void *data);
+struct sp_device *sp_get_psp_master_device(void);
#ifdef CONFIG_CRYPTO_DEV_SP_CCP
}
#endif /* CONFIG_CRYPTO_DEV_SP_CCP */
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+
+int psp_dev_init(struct sp_device *sp);
+void psp_pci_init(void);
+void psp_dev_destroy(struct sp_device *sp);
+void psp_pci_exit(void);
+
+#else /* !CONFIG_CRYPTO_DEV_SP_PSP */
+
+static inline int psp_dev_init(struct sp_device *sp) { return 0; }
+static inline void psp_pci_init(void) { }
+static inline void psp_dev_destroy(struct sp_device *sp) { }
+static inline void psp_pci_exit(void) { }
+
+#endif /* CONFIG_CRYPTO_DEV_SP_PSP */
+
#endif
#include <linux/ccp.h>
#include "ccp-dev.h"
+#include "psp-dev.h"
#define MSIX_VECTORS 2
int msix_count;
struct msix_entry msix_entry[MSIX_VECTORS];
};
+static struct sp_device *sp_dev_master;
static int sp_get_msix_irqs(struct sp_device *sp)
{
sp->psp_irq = 0;
}
+static bool sp_pci_is_master(struct sp_device *sp)
+{
+ struct device *dev_cur, *dev_new;
+ struct pci_dev *pdev_cur, *pdev_new;
+
+ dev_new = sp->dev;
+ dev_cur = sp_dev_master->dev;
+
+ pdev_new = to_pci_dev(dev_new);
+ pdev_cur = to_pci_dev(dev_cur);
+
+ if (pdev_new->bus->number < pdev_cur->bus->number)
+ return true;
+
+ if (PCI_SLOT(pdev_new->devfn) < PCI_SLOT(pdev_cur->devfn))
+ return true;
+
+ if (PCI_FUNC(pdev_new->devfn) < PCI_FUNC(pdev_cur->devfn))
+ return true;
+
+ return false;
+}
+
+static void psp_set_master(struct sp_device *sp)
+{
+ if (!sp_dev_master) {
+ sp_dev_master = sp;
+ return;
+ }
+
+ if (sp_pci_is_master(sp))
+ sp_dev_master = sp;
+}
+
+static struct sp_device *psp_get_master(void)
+{
+ return sp_dev_master;
+}
+
static int sp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct sp_device *sp;
goto e_err;
pci_set_master(pdev);
+ sp->set_psp_master_device = psp_set_master;
+ sp->get_psp_master_device = psp_get_master;
ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
if (ret) {
}
#endif
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+static const struct psp_vdata psp_entry = {
+ .offset = 0x10500,
+};
+#endif
+
static const struct sp_dev_vdata dev_vdata[] = {
{
.bar = 2,
.bar = 2,
#ifdef CONFIG_CRYPTO_DEV_SP_CCP
.ccp_vdata = &ccpv5a,
+#endif
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+ .psp_vdata = &psp_entry
#endif
},
{
algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng);
ss = algt->ss;
- spin_lock(&ss->slock);
+ spin_lock_bh(&ss->slock);
writel(mode, ss->base + SS_CTL);
}
writel(0, ss->base + SS_CTL);
- spin_unlock(&ss->slock);
- return dlen;
+ spin_unlock_bh(&ss->slock);
+ return 0;
}
struct talitos_private *priv = dev_get_drvdata(dev);
bool is_sec1 = has_ftr_sec1(priv);
+ if (!src) {
+ to_talitos_ptr(ptr, 0, 0, is_sec1);
+ return 1;
+ }
if (sg_count == 1) {
to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1);
return sg_count;
* Userspace can query the state of these implicitly tracked fences using poll()
* and related system calls:
*
- * - Checking for POLLIN, i.e. read access, can be use to query the state of the
+ * - Checking for EPOLLIN, i.e. read access, can be use to query the state of the
* most recent write or exclusive fence.
*
- * - Checking for POLLOUT, i.e. write access, can be used to query the state of
+ * - Checking for EPOLLOUT, i.e. write access, can be used to query the state of
* all attached fences, shared and exclusive ones.
*
* Note that this only signals the completion of the respective fences, i.e. the
dmabuf = file->private_data;
if (!dmabuf || !dmabuf->resv)
- return POLLERR;
+ return EPOLLERR;
resv = dmabuf->resv;
poll_wait(file, &dmabuf->poll, poll);
- events = poll_requested_events(poll) & (POLLIN | POLLOUT);
+ events = poll_requested_events(poll) & (EPOLLIN | EPOLLOUT);
if (!events)
return 0;
goto retry;
}
- if (fence_excl && (!(events & POLLOUT) || shared_count == 0)) {
+ if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) {
struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl;
- __poll_t pevents = POLLIN;
+ __poll_t pevents = EPOLLIN;
if (shared_count == 0)
- pevents |= POLLOUT;
+ pevents |= EPOLLOUT;
spin_lock_irq(&dmabuf->poll.lock);
if (dcb->active) {
}
}
- if ((events & POLLOUT) && shared_count > 0) {
+ if ((events & EPOLLOUT) && shared_count > 0) {
struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared;
int i;
/* Only queue a new callback if no event has fired yet */
spin_lock_irq(&dmabuf->poll.lock);
if (dcb->active)
- events &= ~POLLOUT;
+ events &= ~EPOLLOUT;
else
- dcb->active = POLLOUT;
+ dcb->active = EPOLLOUT;
spin_unlock_irq(&dmabuf->poll.lock);
- if (!(events & POLLOUT))
+ if (!(events & EPOLLOUT))
goto out;
for (i = 0; i < shared_count; ++i) {
*
* call dma_buf_poll_cb and force a recheck!
*/
- events &= ~POLLOUT;
+ events &= ~EPOLLOUT;
dma_buf_poll_cb(NULL, &dcb->cb);
break;
}
if (!dma_fence_add_callback(fence, &dcb->cb,
dma_buf_poll_cb)) {
dma_fence_put(fence);
- events &= ~POLLOUT;
+ events &= ~EPOLLOUT;
break;
}
dma_fence_put(fence);
wake_up_all(&sync_file->wq);
}
- return dma_fence_is_signaled(sync_file->fence) ? POLLIN : 0;
+ return dma_fence_is_signaled(sync_file->fence) ? EPOLLIN : 0;
}
static long sync_file_ioctl_merge(struct sync_file *sync_file,
poll_wait(file, &client->wait, pt);
if (fw_device_is_shutdown(client->device))
- mask |= POLLHUP | POLLERR;
+ mask |= EPOLLHUP | EPOLLERR;
if (!list_empty(&client->event_list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &client->buffer.wait, pt);
if (atomic_read(&client->buffer.size) > 0)
- ret = POLLIN | POLLRDNORM;
+ ret = EPOLLIN | EPOLLRDNORM;
if (list_empty(&client->lynx->link))
- ret |= POLLHUP;
+ ret |= EPOLLHUP;
return ret;
}
return cpu == resident_cpu;
}
-struct psci_operations psci_ops;
+struct psci_operations psci_ops = {
+ .conduit = PSCI_CONDUIT_NONE,
+ .smccc_version = SMCCC_VERSION_1_0,
+};
typedef unsigned long (psci_fn)(unsigned long, unsigned long,
unsigned long, unsigned long);
0, 0, 0);
}
+static void set_conduit(enum psci_conduit conduit)
+{
+ switch (conduit) {
+ case PSCI_CONDUIT_HVC:
+ invoke_psci_fn = __invoke_psci_fn_hvc;
+ break;
+ case PSCI_CONDUIT_SMC:
+ invoke_psci_fn = __invoke_psci_fn_smc;
+ break;
+ default:
+ WARN(1, "Unexpected PSCI conduit %d\n", conduit);
+ }
+
+ psci_ops.conduit = conduit;
+}
+
static int get_set_conduit_method(struct device_node *np)
{
const char *method;
}
if (!strcmp("hvc", method)) {
- invoke_psci_fn = __invoke_psci_fn_hvc;
+ set_conduit(PSCI_CONDUIT_HVC);
} else if (!strcmp("smc", method)) {
- invoke_psci_fn = __invoke_psci_fn_smc;
+ set_conduit(PSCI_CONDUIT_SMC);
} else {
pr_warn("invalid \"method\" property: %s\n", method);
return -EINVAL;
pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
}
+static void __init psci_init_smccc(void)
+{
+ u32 ver = ARM_SMCCC_VERSION_1_0;
+ int feature;
+
+ feature = psci_features(ARM_SMCCC_VERSION_FUNC_ID);
+
+ if (feature != PSCI_RET_NOT_SUPPORTED) {
+ u32 ret;
+ ret = invoke_psci_fn(ARM_SMCCC_VERSION_FUNC_ID, 0, 0, 0);
+ if (ret == ARM_SMCCC_VERSION_1_1) {
+ psci_ops.smccc_version = SMCCC_VERSION_1_1;
+ ver = ret;
+ }
+ }
+
+ /*
+ * Conveniently, the SMCCC and PSCI versions are encoded the
+ * same way. No, this isn't accidental.
+ */
+ pr_info("SMC Calling Convention v%d.%d\n",
+ PSCI_VERSION_MAJOR(ver), PSCI_VERSION_MINOR(ver));
+
+}
+
static void __init psci_0_2_set_functions(void)
{
pr_info("Using standard PSCI v0.2 function IDs\n");
psci_init_migrate();
if (PSCI_VERSION_MAJOR(ver) >= 1) {
+ psci_init_smccc();
psci_init_cpu_suspend();
psci_init_system_suspend();
}
pr_info("probing for conduit method from ACPI.\n");
if (acpi_psci_use_hvc())
- invoke_psci_fn = __invoke_psci_fn_hvc;
+ set_conduit(PSCI_CONDUIT_HVC);
else
- invoke_psci_fn = __invoke_psci_fn_smc;
+ set_conduit(PSCI_CONDUIT_SMC);
return psci_probe();
}
*/
fw_cfg_cmdline_dev = platform_device_register_simple("fw_cfg",
PLATFORM_DEVID_NONE, res, processed);
- if (IS_ERR(fw_cfg_cmdline_dev))
- return PTR_ERR(fw_cfg_cmdline_dev);
- return 0;
+ return PTR_ERR_OR_ZERO(fw_cfg_cmdline_dev);
}
static int fw_cfg_cmdline_get(char *buf, const struct kernel_param *kp)
poll_wait(filep, &le->wait, wait);
if (!kfifo_is_empty(&le->events))
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
return events;
}
ret = kfifo_put(&le->events, ge);
if (ret != 0)
- wake_up_poll(&le->wait, POLLIN);
+ wake_up_poll(&le->wait, EPOLLIN);
return IRQ_HANDLED;
}
amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue);
- /* Using pipes 2/3 from MEC 2 seems cause problems */
- if (mec == 1 && pipe > 1)
+ /*
+ * 1. Using pipes 2/3 from MEC 2 seems cause problems.
+ * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN
+ * only can be issued on queue 0.
+ */
+ if ((mec == 1 && pipe > 1) || queue != 0)
continue;
ring->me = mec + 1;
{
const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE,
AMDGPU_VM_PTE_COUNT(adev) * 8);
+ uint64_t init_pde_value = 0, flags;
unsigned ring_instance;
struct amdgpu_ring *ring;
struct drm_sched_rq *rq;
+ unsigned long size;
int r, i;
- u64 flags;
- uint64_t init_pde_value = 0;
vm->va = RB_ROOT_CACHED;
for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
AMDGPU_GEM_CREATE_SHADOW);
- r = amdgpu_bo_create(adev,
- amdgpu_vm_bo_size(adev, adev->vm_manager.root_level),
- align, true,
- AMDGPU_GEM_DOMAIN_VRAM,
- flags,
- NULL, NULL, init_pde_value, &vm->root.base.bo);
+ size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
+ r = amdgpu_bo_create(adev, size, align, true, AMDGPU_GEM_DOMAIN_VRAM,
+ flags, NULL, NULL, init_pde_value,
+ &vm->root.base.bo);
if (r)
goto error_free_sched_entity;
+ r = amdgpu_bo_reserve(vm->root.base.bo, true);
+ if (r)
+ goto error_free_root;
+
vm->root.base.vm = vm;
list_add_tail(&vm->root.base.bo_list, &vm->root.base.bo->va);
- INIT_LIST_HEAD(&vm->root.base.vm_status);
-
- if (vm->use_cpu_for_update) {
- r = amdgpu_bo_reserve(vm->root.base.bo, false);
- if (r)
- goto error_free_root;
-
- r = amdgpu_bo_kmap(vm->root.base.bo, NULL);
- amdgpu_bo_unreserve(vm->root.base.bo);
- if (r)
- goto error_free_root;
- }
+ list_add_tail(&vm->root.base.vm_status, &vm->evicted);
+ amdgpu_bo_unreserve(vm->root.base.bo);
if (pasid) {
unsigned long flags;
/* Track retry faults in per-VM fault FIFO. */
spin_lock(&adev->vm_manager.pasid_lock);
vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
- spin_unlock(&adev->vm_manager.pasid_lock);
- if (WARN_ON_ONCE(!vm)) {
+ if (!vm) {
/* VM not found, process it normally */
+ spin_unlock(&adev->vm_manager.pasid_lock);
amdgpu_ih_clear_fault(adev, key);
return true;
}
r = kfifo_put(&vm->faults, key);
if (!r) {
/* FIFO is full. Ignore it until there is space */
+ spin_unlock(&adev->vm_manager.pasid_lock);
amdgpu_ih_clear_fault(adev, key);
goto ignore_iv;
}
+ spin_unlock(&adev->vm_manager.pasid_lock);
/* It's the first fault for this address, process it normally */
return true;
AMD_CG_SUPPORT_GFX_CP_LS |
AMD_CG_SUPPORT_GFX_CGTS |
AMD_CG_SUPPORT_GFX_CGTS_LS |
- AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_BIF_LS |
AMD_CG_SUPPORT_HDP_MGCG |
poll_wait(filp, &file_priv->event_wait, wait);
if (!list_empty(&file_priv->event_list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
if (map == vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].tracked)
return 0;
- if (map) {
- vgpu->gm.aperture_va = memremap(aperture_pa, aperture_sz,
- MEMREMAP_WC);
- if (!vgpu->gm.aperture_va)
- return -ENOMEM;
- } else {
- memunmap(vgpu->gm.aperture_va);
- vgpu->gm.aperture_va = NULL;
- }
-
val = vgpu_cfg_space(vgpu)[PCI_BASE_ADDRESS_2];
if (val & PCI_BASE_ADDRESS_MEM_TYPE_64)
val = *(u64 *)(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_2);
aperture_pa >> PAGE_SHIFT,
aperture_sz >> PAGE_SHIFT,
map);
- if (ret) {
- memunmap(vgpu->gm.aperture_va);
- vgpu->gm.aperture_va = NULL;
+ if (ret)
return ret;
- }
vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].tracked = map;
return 0;
ret = PTR_ERR(dmabuf);
goto out_free_gem;
}
- obj->base.dma_buf = dmabuf;
i915_gem_object_put(obj);
ctx_status_ptr_reg = execlist_ring_mmio(vgpu->gvt, ring_id,
_EL_OFFSET_STATUS_PTR);
-
ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
ctx_status_ptr.read_ptr = 0;
ctx_status_ptr.write_ptr = 0x7;
vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
}
-static void clean_execlist(struct intel_vgpu *vgpu)
+static void clean_execlist(struct intel_vgpu *vgpu, unsigned long engine_mask)
{
- enum intel_engine_id i;
+ unsigned int tmp;
+ struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
struct intel_engine_cs *engine;
+ struct intel_vgpu_submission *s = &vgpu->submission;
- for_each_engine(engine, vgpu->gvt->dev_priv, i) {
- struct intel_vgpu_submission *s = &vgpu->submission;
-
- kfree(s->ring_scan_buffer[i]);
- s->ring_scan_buffer[i] = NULL;
- s->ring_scan_buffer_size[i] = 0;
+ for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+ kfree(s->ring_scan_buffer[engine->id]);
+ s->ring_scan_buffer[engine->id] = NULL;
+ s->ring_scan_buffer_size[engine->id] = 0;
}
}
init_vgpu_execlist(vgpu, engine->id);
}
-static int init_execlist(struct intel_vgpu *vgpu)
+static int init_execlist(struct intel_vgpu *vgpu,
+ unsigned long engine_mask)
{
- reset_execlist(vgpu, ALL_ENGINES);
+ reset_execlist(vgpu, engine_mask);
return 0;
}
static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt)
{
struct intel_vgpu *vgpu = spt->vgpu;
+ struct intel_gvt *gvt = vgpu->gvt;
+ struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops;
struct intel_vgpu_ppgtt_spt *s;
struct intel_gvt_gtt_entry se, ge;
- unsigned long i;
+ unsigned long gfn, i;
int ret;
trace_spt_change(spt->vgpu->id, "born", spt,
if (gtt_type_is_pte_pt(spt->shadow_page.type)) {
for_each_present_guest_entry(spt, &ge, i) {
- ret = gtt_entry_p2m(vgpu, &ge, &se);
- if (ret)
- goto fail;
+ gfn = ops->get_pfn(&ge);
+ if (!intel_gvt_hypervisor_is_valid_gfn(vgpu, gfn) ||
+ gtt_entry_p2m(vgpu, &ge, &se))
+ ops->set_pfn(&se, gvt->gtt.scratch_mfn);
ppgtt_set_shadow_entry(spt, &se, i);
}
return 0;
struct intel_vgpu_mm *ggtt_mm = vgpu->gtt.ggtt_mm;
struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops;
unsigned long g_gtt_index = off >> info->gtt_entry_size_shift;
- unsigned long gma;
+ unsigned long gma, gfn;
struct intel_gvt_gtt_entry e, m;
int ret;
bytes);
if (ops->test_present(&e)) {
+ gfn = ops->get_pfn(&e);
+
+ /* one PTE update may be issued in multiple writes and the
+ * first write may not construct a valid gfn
+ */
+ if (!intel_gvt_hypervisor_is_valid_gfn(vgpu, gfn)) {
+ ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+ goto out;
+ }
+
ret = gtt_entry_p2m(vgpu, &e, &m);
if (ret) {
gvt_vgpu_err("fail to translate guest gtt entry\n");
ops->set_pfn(&m, gvt->gtt.scratch_mfn);
}
+out:
ggtt_set_shadow_entry(ggtt_mm, &m, g_gtt_index);
gtt_invalidate(gvt->dev_priv);
ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index);
struct intel_vgpu_gm {
u64 aperture_sz;
u64 hidden_sz;
- void *aperture_va;
struct drm_mm_node low_gm_node;
struct drm_mm_node high_gm_node;
};
struct intel_vgpu_opregion {
bool mapped;
void *va;
- void *va_gopregion;
u32 gfn[INTEL_GVT_OPREGION_PAGES];
};
struct intel_vgpu_submission_ops {
const char *name;
- int (*init)(struct intel_vgpu *vgpu);
- void (*clean)(struct intel_vgpu *vgpu);
+ int (*init)(struct intel_vgpu *vgpu, unsigned long engine_mask);
+ void (*clean)(struct intel_vgpu *vgpu, unsigned long engine_mask);
void (*reset)(struct intel_vgpu *vgpu, unsigned long engine_mask);
};
static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes)
{
- struct intel_vgpu_submission *s = &vgpu->submission;
u32 data = *(u32 *)p_data;
int ring_id = intel_gvt_render_mmio_to_ring_id(vgpu->gvt, offset);
bool enable_execlist;
if (!enable_execlist)
return 0;
- if (s->active)
- return 0;
-
ret = intel_vgpu_select_submission_ops(vgpu,
- INTEL_VGPU_EXECLIST_SUBMISSION);
+ ENGINE_MASK(ring_id),
+ INTEL_VGPU_EXECLIST_SUBMISSION);
if (ret)
return ret;
MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_A)), D_SKL_PLUS);
MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_B)), D_SKL_PLUS);
MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_C)), D_SKL_PLUS);
+ MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_A)), D_SKL_PLUS);
+ MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_B)), D_SKL_PLUS);
+ MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_C)), D_SKL_PLUS);
MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_A)), D_SKL_PLUS);
MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_B)), D_SKL_PLUS);
MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_C)), D_SKL_PLUS);
int (*set_opregion)(void *vgpu);
int (*get_vfio_device)(void *vgpu);
void (*put_vfio_device)(void *vgpu);
+ bool (*is_valid_gfn)(unsigned long handle, unsigned long gfn);
};
extern struct intel_gvt_mpt xengt_mpt;
return ret;
}
+static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, uint64_t off)
+{
+ return off >= vgpu_aperture_offset(vgpu) &&
+ off < vgpu_aperture_offset(vgpu) + vgpu_aperture_sz(vgpu);
+}
+
+static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t off,
+ void *buf, unsigned long count, bool is_write)
+{
+ void *aperture_va;
+
+ if (!intel_vgpu_in_aperture(vgpu, off) ||
+ !intel_vgpu_in_aperture(vgpu, off + count)) {
+ gvt_vgpu_err("Invalid aperture offset %llu\n", off);
+ return -EINVAL;
+ }
+
+ aperture_va = io_mapping_map_wc(&vgpu->gvt->dev_priv->ggtt.iomap,
+ ALIGN_DOWN(off, PAGE_SIZE),
+ count + offset_in_page(off));
+ if (!aperture_va)
+ return -EIO;
+
+ if (is_write)
+ memcpy(aperture_va + offset_in_page(off), buf, count);
+ else
+ memcpy(buf, aperture_va + offset_in_page(off), count);
+
+ io_mapping_unmap(aperture_va);
+
+ return 0;
+}
+
static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
size_t count, loff_t *ppos, bool is_write)
{
buf, count, is_write);
break;
case VFIO_PCI_BAR2_REGION_INDEX:
- ret = intel_vgpu_bar_rw(vgpu, PCI_BASE_ADDRESS_2, pos,
- buf, count, is_write);
+ ret = intel_vgpu_aperture_rw(vgpu, pos, buf, count, is_write);
break;
case VFIO_PCI_BAR1_REGION_INDEX:
case VFIO_PCI_BAR3_REGION_INDEX:
return PFN_DOWN(__pa(addr));
}
+static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn)
+{
+ struct kvmgt_guest_info *info;
+ struct kvm *kvm;
+
+ if (!handle_valid(handle))
+ return false;
+
+ info = (struct kvmgt_guest_info *)handle;
+ kvm = info->kvm;
+
+ return kvm_is_visible_gfn(kvm, gfn);
+
+}
+
struct intel_gvt_mpt kvmgt_mpt = {
.host_init = kvmgt_host_init,
.host_exit = kvmgt_host_exit,
.set_opregion = kvmgt_set_opregion,
.get_vfio_device = kvmgt_get_vfio_device,
.put_vfio_device = kvmgt_put_vfio_device,
+ .is_valid_gfn = kvmgt_is_valid_gfn,
};
EXPORT_SYMBOL_GPL(kvmgt_mpt);
(reg >= gvt->device_info.gtt_start_offset \
&& reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt))
-static bool vgpu_gpa_is_aperture(struct intel_vgpu *vgpu, uint64_t gpa)
-{
- u64 aperture_gpa = intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_2);
- u64 aperture_sz = vgpu_aperture_sz(vgpu);
-
- return gpa >= aperture_gpa && gpa < aperture_gpa + aperture_sz;
-}
-
-static int vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t gpa,
- void *pdata, unsigned int size, bool is_read)
-{
- u64 aperture_gpa = intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_2);
- u64 offset = gpa - aperture_gpa;
-
- if (!vgpu_gpa_is_aperture(vgpu, gpa + size - 1)) {
- gvt_vgpu_err("Aperture rw out of range, offset %llx, size %d\n",
- offset, size);
- return -EINVAL;
- }
-
- if (!vgpu->gm.aperture_va) {
- gvt_vgpu_err("BAR is not enabled\n");
- return -ENXIO;
- }
-
- if (is_read)
- memcpy(pdata, vgpu->gm.aperture_va + offset, size);
- else
- memcpy(vgpu->gm.aperture_va + offset, pdata, size);
- return 0;
-}
-
static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
void *p_data, unsigned int bytes, bool read)
{
}
mutex_lock(&gvt->lock);
- if (vgpu_gpa_is_aperture(vgpu, pa)) {
- ret = vgpu_aperture_rw(vgpu, pa, p_data, bytes, true);
- goto out;
- }
-
offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
if (WARN_ON(bytes > 8))
mutex_lock(&gvt->lock);
- if (vgpu_gpa_is_aperture(vgpu, pa)) {
- ret = vgpu_aperture_rw(vgpu, pa, p_data, bytes, false);
- goto out;
- }
-
offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
if (WARN_ON(bytes > 8))
{BCS, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */
{BCS, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */
{BCS, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */
- { /* Terminated */ }
+ {RCS, INVALID_MMIO_REG, 0, false } /* Terminated */
};
static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
{RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
{RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
{RCS, FF_SLICE_CS_CHICKEN2, 0xffff, false}, /* 0x20e4 */
- { /* Terminated */ }
+ {RCS, INVALID_MMIO_REG, 0, false } /* Terminated */
};
static struct {
};
int ring_id, i;
- for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
+ for (ring_id = 0; ring_id < ARRAY_SIZE(regs); ring_id++) {
offset.reg = regs[ring_id];
for (i = 0; i < 64; i++) {
gen9_render_mocs.control_table[ring_id][i] =
if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
switch_mocs(pre, next, ring_id);
- mmio = dev_priv->gvt->engine_mmio_list;
- while (i915_mmio_reg_offset((mmio++)->reg)) {
+ for (mmio = dev_priv->gvt->engine_mmio_list;
+ i915_mmio_reg_valid(mmio->reg); mmio++) {
if (mmio->ring_id != ring_id)
continue;
// save
intel_gvt_host.mpt->put_vfio_device(vgpu);
}
+/**
+ * intel_gvt_hypervisor_is_valid_gfn - check if a visible gfn
+ * @vgpu: a vGPU
+ * @gfn: guest PFN
+ *
+ * Returns:
+ * true on valid gfn, false on not.
+ */
+static inline bool intel_gvt_hypervisor_is_valid_gfn(
+ struct intel_vgpu *vgpu, unsigned long gfn)
+{
+ if (!intel_gvt_host.mpt->is_valid_gfn)
+ return true;
+
+ return intel_gvt_host.mpt->is_valid_gfn(vgpu->handle, gfn);
+}
+
#endif /* _GVT_MPT_H_ */
{
int i, ret = 0;
- unsigned long pfn;
gvt_dbg_core("emulate opregion from kernel\n");
switch (intel_gvt_host.hypervisor_type) {
case INTEL_GVT_HYPERVISOR_KVM:
- pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, gpa >> PAGE_SHIFT);
- vgpu_opregion(vgpu)->va_gopregion = memremap(pfn << PAGE_SHIFT,
- INTEL_GVT_OPREGION_SIZE,
- MEMREMAP_WB);
- if (!vgpu_opregion(vgpu)->va_gopregion) {
- gvt_vgpu_err("failed to map guest opregion\n");
- ret = -EFAULT;
- }
- vgpu_opregion(vgpu)->mapped = true;
+ for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++)
+ vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i;
break;
case INTEL_GVT_HYPERVISOR_XEN:
/**
if (vgpu_opregion(vgpu)->mapped)
map_vgpu_opregion(vgpu, false);
} else if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_KVM) {
- if (vgpu_opregion(vgpu)->mapped) {
- memunmap(vgpu_opregion(vgpu)->va_gopregion);
- vgpu_opregion(vgpu)->va_gopregion = NULL;
- }
+ /* Guest opregion is released by VFIO */
}
free_pages((unsigned long)vgpu_opregion(vgpu)->va,
get_order(INTEL_GVT_OPREGION_SIZE));
*/
int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci)
{
- u32 *scic, *parm;
+ u32 scic, parm;
u32 func, subfunc;
+ u64 scic_pa = 0, parm_pa = 0;
+ int ret;
switch (intel_gvt_host.hypervisor_type) {
case INTEL_GVT_HYPERVISOR_XEN:
- scic = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_SCIC;
- parm = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_PARM;
+ scic = *((u32 *)vgpu_opregion(vgpu)->va +
+ INTEL_GVT_OPREGION_SCIC);
+ parm = *((u32 *)vgpu_opregion(vgpu)->va +
+ INTEL_GVT_OPREGION_PARM);
break;
case INTEL_GVT_HYPERVISOR_KVM:
- scic = vgpu_opregion(vgpu)->va_gopregion +
- INTEL_GVT_OPREGION_SCIC;
- parm = vgpu_opregion(vgpu)->va_gopregion +
- INTEL_GVT_OPREGION_PARM;
+ scic_pa = (vgpu_opregion(vgpu)->gfn[0] << PAGE_SHIFT) +
+ INTEL_GVT_OPREGION_SCIC;
+ parm_pa = (vgpu_opregion(vgpu)->gfn[0] << PAGE_SHIFT) +
+ INTEL_GVT_OPREGION_PARM;
+
+ ret = intel_gvt_hypervisor_read_gpa(vgpu, scic_pa,
+ &scic, sizeof(scic));
+ if (ret) {
+ gvt_vgpu_err("guest opregion read error %d, gpa 0x%llx, len %lu\n",
+ ret, scic_pa, sizeof(scic));
+ return ret;
+ }
+
+ ret = intel_gvt_hypervisor_read_gpa(vgpu, parm_pa,
+ &parm, sizeof(parm));
+ if (ret) {
+ gvt_vgpu_err("guest opregion read error %d, gpa 0x%llx, len %lu\n",
+ ret, scic_pa, sizeof(scic));
+ return ret;
+ }
+
break;
default:
gvt_vgpu_err("not supported hypervisor\n");
return 0;
}
- func = GVT_OPREGION_FUNC(*scic);
- subfunc = GVT_OPREGION_SUBFUNC(*scic);
- if (!querying_capabilities(*scic)) {
+ func = GVT_OPREGION_FUNC(scic);
+ subfunc = GVT_OPREGION_SUBFUNC(scic);
+ if (!querying_capabilities(scic)) {
gvt_vgpu_err("requesting runtime service: func \"%s\","
" subfunc \"%s\"\n",
opregion_func_name(func),
* emulate exit status of function call, '0' means
* "failure, generic, unsupported or unknown cause"
*/
- *scic &= ~OPREGION_SCIC_EXIT_MASK;
- return 0;
+ scic &= ~OPREGION_SCIC_EXIT_MASK;
+ goto out;
+ }
+
+ scic = 0;
+ parm = 0;
+
+out:
+ switch (intel_gvt_host.hypervisor_type) {
+ case INTEL_GVT_HYPERVISOR_XEN:
+ *((u32 *)vgpu_opregion(vgpu)->va +
+ INTEL_GVT_OPREGION_SCIC) = scic;
+ *((u32 *)vgpu_opregion(vgpu)->va +
+ INTEL_GVT_OPREGION_PARM) = parm;
+ break;
+ case INTEL_GVT_HYPERVISOR_KVM:
+ ret = intel_gvt_hypervisor_write_gpa(vgpu, scic_pa,
+ &scic, sizeof(scic));
+ if (ret) {
+ gvt_vgpu_err("guest opregion write error %d, gpa 0x%llx, len %lu\n",
+ ret, scic_pa, sizeof(scic));
+ return ret;
+ }
+
+ ret = intel_gvt_hypervisor_write_gpa(vgpu, parm_pa,
+ &parm, sizeof(parm));
+ if (ret) {
+ gvt_vgpu_err("guest opregion write error %d, gpa 0x%llx, len %lu\n",
+ ret, scic_pa, sizeof(scic));
+ return ret;
+ }
+
+ break;
+ default:
+ gvt_vgpu_err("not supported hypervisor\n");
+ return -EINVAL;
}
- *scic = 0;
- *parm = 0;
return 0;
}
struct vgpu_sched_data {
struct list_head lru_list;
struct intel_vgpu *vgpu;
+ bool active;
ktime_t sched_in_time;
ktime_t sched_out_time;
static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu)
{
+ struct intel_gvt *gvt = vgpu->gvt;
+ struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
+
kfree(vgpu->sched_data);
vgpu->sched_data = NULL;
+
+ /* this vgpu id has been removed */
+ if (idr_is_empty(&gvt->vgpu_idr))
+ hrtimer_cancel(&sched_data->timer);
}
static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
if (!hrtimer_active(&sched_data->timer))
hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(),
sched_data->period), HRTIMER_MODE_ABS);
+ vgpu_data->active = true;
}
static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu)
struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
list_del_init(&vgpu_data->lru_list);
+ vgpu_data->active = false;
}
static struct intel_gvt_sched_policy_ops tbs_schedule_ops = {
void intel_vgpu_start_schedule(struct intel_vgpu *vgpu)
{
- gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
+ struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
- vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
+ if (!vgpu_data->active) {
+ gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
+ vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
+ }
}
void intel_gvt_kick_schedule(struct intel_gvt *gvt)
struct intel_gvt_workload_scheduler *scheduler =
&vgpu->gvt->scheduler;
int ring_id;
+ struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+
+ if (!vgpu_data->active)
+ return;
gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
{
struct intel_vgpu_submission *s = &vgpu->submission;
- intel_vgpu_select_submission_ops(vgpu, 0);
+ intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0);
i915_gem_context_put(s->shadow_ctx);
kmem_cache_destroy(s->workloads);
}
*
*/
int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
+ unsigned long engine_mask,
unsigned int interface)
{
struct intel_vgpu_submission *s = &vgpu->submission;
if (WARN_ON(interface >= ARRAY_SIZE(ops)))
return -EINVAL;
- if (s->active) {
- s->ops->clean(vgpu);
- s->active = false;
- gvt_dbg_core("vgpu%d: de-select ops [ %s ] \n",
- vgpu->id, s->ops->name);
- }
+ if (WARN_ON(interface == 0 && engine_mask != ALL_ENGINES))
+ return -EINVAL;
+
+ if (s->active)
+ s->ops->clean(vgpu, engine_mask);
if (interface == 0) {
s->ops = NULL;
s->virtual_submission_interface = 0;
- gvt_dbg_core("vgpu%d: no submission ops\n", vgpu->id);
+ s->active = false;
+ gvt_dbg_core("vgpu%d: remove submission ops\n", vgpu->id);
return 0;
}
- ret = ops[interface]->init(vgpu);
+ ret = ops[interface]->init(vgpu, engine_mask);
if (ret)
return ret;
void intel_vgpu_clean_submission(struct intel_vgpu *vgpu);
int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
+ unsigned long engine_mask,
unsigned int interface);
extern const struct intel_vgpu_submission_ops
intel_gvt_debugfs_remove_vgpu(vgpu);
idr_remove(&gvt->vgpu_idr, vgpu->id);
+ if (idr_is_empty(&gvt->vgpu_idr))
+ intel_gvt_clean_irq(gvt);
intel_vgpu_clean_sched_policy(vgpu);
intel_vgpu_clean_submission(vgpu);
intel_vgpu_clean_display(vgpu);
intel_vgpu_reset_submission(vgpu, resetting_eng);
/* full GPU reset or device model level reset */
if (engine_mask == ALL_ENGINES || dmlr) {
- intel_vgpu_select_submission_ops(vgpu, 0);
-
+ intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0);
/*fence will not be reset during virtual reset */
if (dmlr) {
intel_vgpu_reset_gtt(vgpu);
const struct drm_i915_reg_table *table = engine->reg_tables;
int count = engine->reg_table_count;
- do {
+ for (; count > 0; ++table, --count) {
if (!table->master || is_master) {
const struct drm_i915_reg_descriptor *reg;
if (reg != NULL)
return reg;
}
- } while (table++, --count);
+ }
return NULL;
}
continue;
}
+ if (desc->bits[i].offset >= length) {
+ DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
+ *cmd, engine->name);
+ return false;
+ }
+
dword = cmd[desc->bits[i].offset] &
desc->bits[i].mask;
if (IS_GEN9_LP(dev_priv) ||
!(dev_priv->suspended_to_idle && dev_priv->csr.dmc_payload))
intel_power_domains_init_hw(dev_priv, true);
+ else
+ intel_display_set_init_power(dev_priv, true);
i915_gem_sanitize(dev_priv);
struct intel_display_error_state *error);
int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val);
-int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val);
+int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv, u32 mbox,
+ u32 val, int timeout_us);
+#define sandybridge_pcode_write(dev_priv, mbox, val) \
+ sandybridge_pcode_write_timeout(dev_priv, mbox, val, 500)
+
int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request,
u32 reply_mask, u32 reply, int timeout_base_ms);
mutex_unlock(&dev->struct_mutex);
}
- /* Keep the retire handler running until we are finally idle.
+ /*
+ * Keep the retire handler running until we are finally idle.
* We do not need to do this test under locking as in the worst-case
* we queue the retire worker once too often.
*/
- if (READ_ONCE(dev_priv->gt.awake)) {
- i915_queue_hangcheck(dev_priv);
+ if (READ_ONCE(dev_priv->gt.awake))
queue_delayed_work(dev_priv->wq,
&dev_priv->gt.retire_work,
round_jiffies_up_relative(HZ));
- }
}
static inline bool
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
mutex_unlock(&dev_priv->drm.struct_mutex);
+ intel_uc_fini_wq(dev_priv);
+
if (ret != -EIO)
i915_gem_cleanup_userptr(dev_priv);
static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
{
struct pagevec *pvec = &vm->free_pages;
+ struct pagevec stash;
if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
i915_gem_shrink_all(vm->i915);
if (likely(pvec->nr))
return pvec->pages[--pvec->nr];
- /* Otherwise batch allocate pages to amoritize cost of set_pages_wc. */
+ /*
+ * Otherwise batch allocate pages to amoritize cost of set_pages_wc.
+ *
+ * We have to be careful as page allocation may trigger the shrinker
+ * (via direct reclaim) which will fill up the WC stash underneath us.
+ * So we add our WB pages into a temporary pvec on the stack and merge
+ * them into the WC stash after all the allocations are complete.
+ */
+ pagevec_init(&stash);
do {
struct page *page;
if (unlikely(!page))
break;
- pvec->pages[pvec->nr++] = page;
- } while (pagevec_space(pvec));
+ stash.pages[stash.nr++] = page;
+ } while (stash.nr < pagevec_space(pvec));
- if (unlikely(!pvec->nr))
- return NULL;
+ if (stash.nr) {
+ int nr = min_t(int, stash.nr, pagevec_space(pvec));
+ struct page **pages = stash.pages + stash.nr - nr;
- set_pages_array_wc(pvec->pages, pvec->nr);
+ if (nr && !set_pages_array_wc(pages, nr)) {
+ memcpy(pvec->pages + pvec->nr,
+ pages, sizeof(pages[0]) * nr);
+ pvec->nr += nr;
+ stash.nr -= nr;
+ }
- return pvec->pages[--pvec->nr];
+ pagevec_release(&stash);
+ }
+
+ return likely(pvec->nr) ? pvec->pages[--pvec->nr] : NULL;
}
static void vm_free_pages_release(struct i915_address_space *vm,
int count = gen8_pte_count(start, length);
if (pt == vm->scratch_pt) {
+ pd->used_pdes++;
+
pt = alloc_pt(vm);
- if (IS_ERR(pt))
+ if (IS_ERR(pt)) {
+ pd->used_pdes--;
goto unwind;
+ }
if (count < GEN8_PTES || intel_vgpu_active(vm->i915))
gen8_initialize_pt(vm, pt);
gen8_ppgtt_set_pde(vm, pd, pt, pde);
- pd->used_pdes++;
GEM_BUG_ON(pd->used_pdes > I915_PDES);
}
gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
if (pd == vm->scratch_pd) {
+ pdp->used_pdpes++;
+
pd = alloc_pd(vm);
- if (IS_ERR(pd))
+ if (IS_ERR(pd)) {
+ pdp->used_pdpes--;
goto unwind;
+ }
gen8_initialize_pd(vm, pd);
gen8_ppgtt_set_pdpe(vm, pdp, pd, pdpe);
- pdp->used_pdpes++;
GEM_BUG_ON(pdp->used_pdpes > i915_pdpes_per_pdp(vm));
mark_tlbs_dirty(i915_vm_to_ppgtt(vm));
u32 fault = I915_READ(GEN8_RING_FAULT_REG);
if (fault & RING_FAULT_VALID) {
+ u32 fault_data0, fault_data1;
+ u64 fault_addr;
+
+ fault_data0 = I915_READ(GEN8_FAULT_TLB_DATA0);
+ fault_data1 = I915_READ(GEN8_FAULT_TLB_DATA1);
+ fault_addr = ((u64)(fault_data1 & FAULT_VA_HIGH_BITS) << 44) |
+ ((u64)fault_data0 << 12);
+
DRM_DEBUG_DRIVER("Unexpected fault\n"
- "\tAddr: 0x%08lx\n"
+ "\tAddr: 0x%08x_%08x\n"
+ "\tAddress space: %s\n"
"\tEngine ID: %d\n"
"\tSource ID: %d\n"
"\tType: %d\n",
- fault & PAGE_MASK,
+ upper_32_bits(fault_addr),
+ lower_32_bits(fault_addr),
+ fault_data1 & FAULT_GTT_SEL ? "GGTT" : "PPGTT",
GEN8_RING_FAULT_ENGINE_ID(fault),
RING_FAULT_SRCID(fault),
RING_FAULT_FAULT_TYPE(fault));
intel_engines_unpark(i915);
+ i915_queue_hangcheck(i915);
+
queue_delayed_work(i915->wq,
&i915->gt.retire_work,
round_jiffies_up_relative(HZ));
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_PURGEABLE);
- if (freed < sc->nr_to_scan)
+ if (sc->nr_scanned < sc->nr_to_scan)
freed += i915_gem_shrink(i915,
sc->nr_to_scan - sc->nr_scanned,
&sc->nr_scanned,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND);
- if (freed < sc->nr_to_scan && current_is_kswapd()) {
+ if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) {
intel_runtime_pm_get(i915);
freed += i915_gem_shrink(i915,
sc->nr_to_scan - sc->nr_scanned,
GEN_DEFAULT_PAGE_SIZES, \
CURSOR_OFFSETS
-static const struct intel_device_info intel_i830_info __initconst = {
+static const struct intel_device_info intel_i830_info = {
GEN2_FEATURES,
.platform = INTEL_I830,
.is_mobile = 1, .cursor_needs_physical = 1,
.num_pipes = 2, /* legal, last one wins */
};
-static const struct intel_device_info intel_i845g_info __initconst = {
+static const struct intel_device_info intel_i845g_info = {
GEN2_FEATURES,
.platform = INTEL_I845G,
};
-static const struct intel_device_info intel_i85x_info __initconst = {
+static const struct intel_device_info intel_i85x_info = {
GEN2_FEATURES,
.platform = INTEL_I85X, .is_mobile = 1,
.num_pipes = 2, /* legal, last one wins */
.has_fbc = 1,
};
-static const struct intel_device_info intel_i865g_info __initconst = {
+static const struct intel_device_info intel_i865g_info = {
GEN2_FEATURES,
.platform = INTEL_I865G,
};
GEN_DEFAULT_PAGE_SIZES, \
CURSOR_OFFSETS
-static const struct intel_device_info intel_i915g_info __initconst = {
+static const struct intel_device_info intel_i915g_info = {
GEN3_FEATURES,
.platform = INTEL_I915G, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.unfenced_needs_alignment = 1,
};
-static const struct intel_device_info intel_i915gm_info __initconst = {
+static const struct intel_device_info intel_i915gm_info = {
GEN3_FEATURES,
.platform = INTEL_I915GM,
.is_mobile = 1,
.unfenced_needs_alignment = 1,
};
-static const struct intel_device_info intel_i945g_info __initconst = {
+static const struct intel_device_info intel_i945g_info = {
GEN3_FEATURES,
.platform = INTEL_I945G,
.has_hotplug = 1, .cursor_needs_physical = 1,
.unfenced_needs_alignment = 1,
};
-static const struct intel_device_info intel_i945gm_info __initconst = {
+static const struct intel_device_info intel_i945gm_info = {
GEN3_FEATURES,
.platform = INTEL_I945GM, .is_mobile = 1,
.has_hotplug = 1, .cursor_needs_physical = 1,
.unfenced_needs_alignment = 1,
};
-static const struct intel_device_info intel_g33_info __initconst = {
+static const struct intel_device_info intel_g33_info = {
GEN3_FEATURES,
.platform = INTEL_G33,
.has_hotplug = 1,
.has_overlay = 1,
};
-static const struct intel_device_info intel_pineview_info __initconst = {
+static const struct intel_device_info intel_pineview_info = {
GEN3_FEATURES,
.platform = INTEL_PINEVIEW, .is_mobile = 1,
.has_hotplug = 1,
GEN_DEFAULT_PAGE_SIZES, \
CURSOR_OFFSETS
-static const struct intel_device_info intel_i965g_info __initconst = {
+static const struct intel_device_info intel_i965g_info = {
GEN4_FEATURES,
.platform = INTEL_I965G,
.has_overlay = 1,
.has_snoop = false,
};
-static const struct intel_device_info intel_i965gm_info __initconst = {
+static const struct intel_device_info intel_i965gm_info = {
GEN4_FEATURES,
.platform = INTEL_I965GM,
.is_mobile = 1, .has_fbc = 1,
.has_snoop = false,
};
-static const struct intel_device_info intel_g45_info __initconst = {
+static const struct intel_device_info intel_g45_info = {
GEN4_FEATURES,
.platform = INTEL_G45,
.ring_mask = RENDER_RING | BSD_RING,
};
-static const struct intel_device_info intel_gm45_info __initconst = {
+static const struct intel_device_info intel_gm45_info = {
GEN4_FEATURES,
.platform = INTEL_GM45,
.is_mobile = 1, .has_fbc = 1,
GEN_DEFAULT_PAGE_SIZES, \
CURSOR_OFFSETS
-static const struct intel_device_info intel_ironlake_d_info __initconst = {
+static const struct intel_device_info intel_ironlake_d_info = {
GEN5_FEATURES,
.platform = INTEL_IRONLAKE,
};
-static const struct intel_device_info intel_ironlake_m_info __initconst = {
+static const struct intel_device_info intel_ironlake_m_info = {
GEN5_FEATURES,
.platform = INTEL_IRONLAKE,
.is_mobile = 1, .has_fbc = 1,
GEN6_FEATURES, \
.platform = INTEL_SANDYBRIDGE
-static const struct intel_device_info intel_sandybridge_d_gt1_info __initconst = {
+static const struct intel_device_info intel_sandybridge_d_gt1_info = {
SNB_D_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_sandybridge_d_gt2_info __initconst = {
+static const struct intel_device_info intel_sandybridge_d_gt2_info = {
SNB_D_PLATFORM,
.gt = 2,
};
.is_mobile = 1
-static const struct intel_device_info intel_sandybridge_m_gt1_info __initconst = {
+static const struct intel_device_info intel_sandybridge_m_gt1_info = {
SNB_M_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_sandybridge_m_gt2_info __initconst = {
+static const struct intel_device_info intel_sandybridge_m_gt2_info = {
SNB_M_PLATFORM,
.gt = 2,
};
.platform = INTEL_IVYBRIDGE, \
.has_l3_dpf = 1
-static const struct intel_device_info intel_ivybridge_d_gt1_info __initconst = {
+static const struct intel_device_info intel_ivybridge_d_gt1_info = {
IVB_D_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_ivybridge_d_gt2_info __initconst = {
+static const struct intel_device_info intel_ivybridge_d_gt2_info = {
IVB_D_PLATFORM,
.gt = 2,
};
.is_mobile = 1, \
.has_l3_dpf = 1
-static const struct intel_device_info intel_ivybridge_m_gt1_info __initconst = {
+static const struct intel_device_info intel_ivybridge_m_gt1_info = {
IVB_M_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_ivybridge_m_gt2_info __initconst = {
+static const struct intel_device_info intel_ivybridge_m_gt2_info = {
IVB_M_PLATFORM,
.gt = 2,
};
-static const struct intel_device_info intel_ivybridge_q_info __initconst = {
+static const struct intel_device_info intel_ivybridge_q_info = {
GEN7_FEATURES,
.platform = INTEL_IVYBRIDGE,
.gt = 2,
.has_l3_dpf = 1,
};
-static const struct intel_device_info intel_valleyview_info __initconst = {
+static const struct intel_device_info intel_valleyview_info = {
.platform = INTEL_VALLEYVIEW,
.gen = 7,
.is_lp = 1,
.platform = INTEL_HASWELL, \
.has_l3_dpf = 1
-static const struct intel_device_info intel_haswell_gt1_info __initconst = {
+static const struct intel_device_info intel_haswell_gt1_info = {
HSW_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_haswell_gt2_info __initconst = {
+static const struct intel_device_info intel_haswell_gt2_info = {
HSW_PLATFORM,
.gt = 2,
};
-static const struct intel_device_info intel_haswell_gt3_info __initconst = {
+static const struct intel_device_info intel_haswell_gt3_info = {
HSW_PLATFORM,
.gt = 3,
};
.gen = 8, \
.platform = INTEL_BROADWELL
-static const struct intel_device_info intel_broadwell_gt1_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt1_info = {
BDW_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_broadwell_gt2_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt2_info = {
BDW_PLATFORM,
.gt = 2,
};
-static const struct intel_device_info intel_broadwell_rsvd_info __initconst = {
+static const struct intel_device_info intel_broadwell_rsvd_info = {
BDW_PLATFORM,
.gt = 3,
/* According to the device ID those devices are GT3, they were
*/
};
-static const struct intel_device_info intel_broadwell_gt3_info __initconst = {
+static const struct intel_device_info intel_broadwell_gt3_info = {
BDW_PLATFORM,
.gt = 3,
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
};
-static const struct intel_device_info intel_cherryview_info __initconst = {
+static const struct intel_device_info intel_cherryview_info = {
.gen = 8, .num_pipes = 3,
.has_hotplug = 1,
.is_lp = 1,
.gen = 9, \
.platform = INTEL_SKYLAKE
-static const struct intel_device_info intel_skylake_gt1_info __initconst = {
+static const struct intel_device_info intel_skylake_gt1_info = {
SKL_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_skylake_gt2_info __initconst = {
+static const struct intel_device_info intel_skylake_gt2_info = {
SKL_PLATFORM,
.gt = 2,
};
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING
-static const struct intel_device_info intel_skylake_gt3_info __initconst = {
+static const struct intel_device_info intel_skylake_gt3_info = {
SKL_GT3_PLUS_PLATFORM,
.gt = 3,
};
-static const struct intel_device_info intel_skylake_gt4_info __initconst = {
+static const struct intel_device_info intel_skylake_gt4_info = {
SKL_GT3_PLUS_PLATFORM,
.gt = 4,
};
IVB_CURSOR_OFFSETS, \
BDW_COLORS
-static const struct intel_device_info intel_broxton_info __initconst = {
+static const struct intel_device_info intel_broxton_info = {
GEN9_LP_FEATURES,
.platform = INTEL_BROXTON,
.ddb_size = 512,
};
-static const struct intel_device_info intel_geminilake_info __initconst = {
+static const struct intel_device_info intel_geminilake_info = {
GEN9_LP_FEATURES,
.platform = INTEL_GEMINILAKE,
.ddb_size = 1024,
.gen = 9, \
.platform = INTEL_KABYLAKE
-static const struct intel_device_info intel_kabylake_gt1_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt1_info = {
KBL_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_kabylake_gt2_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt2_info = {
KBL_PLATFORM,
.gt = 2,
};
-static const struct intel_device_info intel_kabylake_gt3_info __initconst = {
+static const struct intel_device_info intel_kabylake_gt3_info = {
KBL_PLATFORM,
.gt = 3,
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
.gen = 9, \
.platform = INTEL_COFFEELAKE
-static const struct intel_device_info intel_coffeelake_gt1_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt1_info = {
CFL_PLATFORM,
.gt = 1,
};
-static const struct intel_device_info intel_coffeelake_gt2_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt2_info = {
CFL_PLATFORM,
.gt = 2,
};
-static const struct intel_device_info intel_coffeelake_gt3_info __initconst = {
+static const struct intel_device_info intel_coffeelake_gt3_info = {
CFL_PLATFORM,
.gt = 3,
.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
.ddb_size = 1024, \
GLK_COLORS
-static const struct intel_device_info intel_cannonlake_gt2_info __initconst = {
+static const struct intel_device_info intel_cannonlake_gt2_info = {
GEN10_FEATURES,
.is_alpha_support = 1,
.platform = INTEL_CANNONLAKE,
* The two separate pointers let us decouple read()s from tail pointer aging.
*
* The tail pointers are checked and updated at a limited rate within a hrtimer
- * callback (the same callback that is used for delivering POLLIN events)
+ * callback (the same callback that is used for delivering EPOLLIN events)
*
* Initially the tails are marked invalid with %INVALID_TAIL_PTR which
* indicates that an updated tail pointer is needed.
mutex_unlock(&dev_priv->perf.lock);
}
- /* We allow the poll checking to sometimes report false positive POLLIN
+ /* We allow the poll checking to sometimes report false positive EPOLLIN
* events where we might actually report EAGAIN on read() if there's
* not really any data available. In this situation though we don't
- * want to enter a busy loop between poll() reporting a POLLIN event
+ * want to enter a busy loop between poll() reporting a EPOLLIN event
* and read() returning -EAGAIN. Clearing the oa.pollin state here
* effectively ensures we back off until the next hrtimer callback
- * before reporting another POLLIN event.
+ * before reporting another EPOLLIN event.
*/
if (ret >= 0 || ret == -EAGAIN) {
/* Maybe make ->pollin per-stream state if we support multiple
* samples to read.
*/
if (dev_priv->perf.oa.pollin)
- events |= POLLIN;
+ events |= EPOLLIN;
return events;
}
#define GEN8_FAULT_TLB_DATA0 _MMIO(0x4b10)
#define GEN8_FAULT_TLB_DATA1 _MMIO(0x4b14)
+#define FAULT_VA_HIGH_BITS (0xf << 0)
+#define FAULT_GTT_SEL (1 << 4)
#define FPGA_DBG _MMIO(0x42300)
#define FPGA_DBG_RM_NOCLAIM (1<<31)
{
struct intel_encoder *encoder;
- if (WARN_ON(pipe >= INTEL_INFO(dev_priv)->num_pipes))
+ if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map)))
return NULL;
/* MST */
}
static const u8 cnp_ddc_pin_map[] = {
+ [0] = 0, /* N/A */
[DDC_BUS_DDI_B] = GMBUS_PIN_1_BXT,
[DDC_BUS_DDI_C] = GMBUS_PIN_2_BXT,
[DDC_BUS_DDI_D] = GMBUS_PIN_4_CNP, /* sic */
static u8 map_ddc_pin(struct drm_i915_private *dev_priv, u8 vbt_pin)
{
- if (HAS_PCH_CNP(dev_priv) &&
- vbt_pin > 0 && vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map))
- return cnp_ddc_pin_map[vbt_pin];
+ if (HAS_PCH_CNP(dev_priv)) {
+ if (vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) {
+ return cnp_ddc_pin_map[vbt_pin];
+ } else {
+ DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", vbt_pin);
+ return 0;
+ }
+ }
return vbt_pin;
}
expected_size = LEGACY_CHILD_DEVICE_CONFIG_SIZE;
} else if (bdb->version == 195) {
expected_size = 37;
- } else if (bdb->version <= 197) {
+ } else if (bdb->version <= 215) {
expected_size = 38;
+ } else if (bdb->version <= 216) {
+ expected_size = 39;
} else {
- expected_size = 38;
- BUILD_BUG_ON(sizeof(*child) < 38);
+ expected_size = sizeof(*child);
+ BUILD_BUG_ON(sizeof(*child) < 39);
DRM_DEBUG_DRIVER("Expected child device config size for VBT version %u not known; assuming %u\n",
bdb->version, expected_size);
}
return;
mod_timer(&b->fake_irq, jiffies + 1);
-
- /* Ensure that even if the GPU hangs, we get woken up.
- *
- * However, note that if no one is waiting, we never notice
- * a gpu hang. Eventually, we will have to wait for a resource
- * held by the GPU and so trigger a hangcheck. In the most
- * pathological case, this will be upon memory starvation! To
- * prevent this, we also queue the hangcheck from the retire
- * worker.
- */
- i915_queue_hangcheck(engine->i915);
}
static void irq_enable(struct intel_engine_cs *engine)
break;
}
- /* Inform power controller of upcoming frequency change */
+ /*
+ * Inform power controller of upcoming frequency change. BSpec
+ * requires us to wait up to 150usec, but that leads to timeouts;
+ * the 2ms used here is based on experiment.
+ */
mutex_lock(&dev_priv->pcu_lock);
- ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
- 0x80000000);
+ ret = sandybridge_pcode_write_timeout(dev_priv,
+ HSW_PCODE_DE_WRITE_FREQ_REQ,
+ 0x80000000, 2000);
mutex_unlock(&dev_priv->pcu_lock);
if (ret) {
I915_WRITE(CDCLK_CTL, val);
mutex_lock(&dev_priv->pcu_lock);
- ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ,
- cdclk_state->voltage_level);
+ /*
+ * The timeout isn't specified, the 2ms used here is based on
+ * experiment.
+ * FIXME: Waiting for the request completion could be delayed until
+ * the next PCODE request based on BSpec.
+ */
+ ret = sandybridge_pcode_write_timeout(dev_priv,
+ HSW_PCODE_DE_WRITE_FREQ_REQ,
+ cdclk_state->voltage_level, 2000);
mutex_unlock(&dev_priv->pcu_lock);
if (ret) {
if (!crtc_state->base.active)
return 0;
- mask = BIT(POWER_DOMAIN_PIPE(pipe));
- mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder));
+ mask = BIT_ULL(POWER_DOMAIN_PIPE(pipe));
+ mask |= BIT_ULL(POWER_DOMAIN_TRANSCODER(transcoder));
if (crtc_state->pch_pfit.enabled ||
crtc_state->pch_pfit.force_thru)
mask |= BIT_ULL(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
}
if (HAS_DDI(dev_priv) && crtc_state->has_audio)
- mask |= BIT(POWER_DOMAIN_AUDIO);
+ mask |= BIT_ULL(POWER_DOMAIN_AUDIO);
if (crtc_state->shared_dpll)
mask |= BIT_ULL(POWER_DOMAIN_PLLS);
return;
failure_handling:
- DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
- intel_connector->base.base.id,
- intel_connector->base.name,
- intel_dp->link_rate, intel_dp->lane_count);
- if (!intel_dp_get_link_train_fallback_values(intel_dp,
- intel_dp->link_rate,
- intel_dp->lane_count))
- /* Schedule a Hotplug Uevent to userspace to start modeset */
- schedule_work(&intel_connector->modeset_retry_work);
+ /* Dont fallback and prune modes if its eDP */
+ if (!intel_dp_is_edp(intel_dp)) {
+ DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
+ intel_connector->base.base.id,
+ intel_connector->base.name,
+ intel_dp->link_rate, intel_dp->lane_count);
+ if (!intel_dp_get_link_train_fallback_values(intel_dp,
+ intel_dp->link_rate,
+ intel_dp->lane_count))
+ /* Schedule a Hotplug Uevent to userspace to start modeset */
+ schedule_work(&intel_connector->modeset_retry_work);
+ } else {
+ DRM_ERROR("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d",
+ intel_connector->base.base.id,
+ intel_connector->base.name,
+ intel_dp->link_rate, intel_dp->lane_count);
+ }
return;
}
spin_lock_irqsave(&engine->stats.lock, flags);
if (engine->stats.enabled == ~0)
goto busy;
- if (engine->stats.enabled++ == 0)
+ if (engine->stats.enabled++ == 0) {
+ struct intel_engine_execlists *execlists = &engine->execlists;
+ const struct execlist_port *port = execlists->port;
+ unsigned int num_ports = execlists_num_ports(execlists);
+
engine->stats.enabled_at = ktime_get();
+
+ /* XXX submission method oblivious? */
+ while (num_ports-- && port_isset(port)) {
+ engine->stats.active++;
+ port++;
+ }
+
+ if (engine->stats.active)
+ engine->stats.start = engine->stats.enabled_at;
+ }
spin_unlock_irqrestore(&engine->stats.lock, flags);
return 0;
#define KBL_FW_MAJOR 9
#define KBL_FW_MINOR 39
-#define GLK_FW_MAJOR 10
-#define GLK_FW_MINOR 56
-
#define GUC_FW_PATH(platform, major, minor) \
"i915/" __stringify(platform) "_guc_ver" __stringify(major) "_" __stringify(minor) ".bin"
#define I915_KBL_GUC_UCODE GUC_FW_PATH(kbl, KBL_FW_MAJOR, KBL_FW_MINOR)
MODULE_FIRMWARE(I915_KBL_GUC_UCODE);
-#define I915_GLK_GUC_UCODE GUC_FW_PATH(glk, GLK_FW_MAJOR, GLK_FW_MINOR)
-
static void guc_fw_select(struct intel_uc_fw *guc_fw)
{
struct intel_guc *guc = container_of(guc_fw, struct intel_guc, fw);
guc_fw->path = I915_KBL_GUC_UCODE;
guc_fw->major_ver_wanted = KBL_FW_MAJOR;
guc_fw->minor_ver_wanted = KBL_FW_MINOR;
- } else if (IS_GEMINILAKE(dev_priv)) {
- guc_fw->path = I915_GLK_GUC_UCODE;
- guc_fw->major_ver_wanted = GLK_FW_MAJOR;
- guc_fw->minor_ver_wanted = GLK_FW_MINOR;
} else {
DRM_WARN("%s: No firmware known for this platform!\n",
intel_uc_fw_type_repr(guc_fw->type));
struct intel_engine_cs *engine;
enum intel_engine_id id;
unsigned int hung = 0, stuck = 0;
- int busy_count = 0;
if (!i915_modparams.enable_hangcheck)
return;
intel_uncore_arm_unclaimed_mmio_detection(dev_priv);
for_each_engine(engine, dev_priv, id) {
- const bool busy = intel_engine_has_waiter(engine);
struct intel_engine_hangcheck hc;
semaphore_clear_deadlocks(dev_priv);
if (hc.action != ENGINE_DEAD)
stuck |= intel_engine_flag(engine);
}
-
- busy_count += busy;
}
if (hung)
hangcheck_declare_hang(dev_priv, hung, stuck);
/* Reset timer in case GPU hangs without another request being added */
- if (busy_count)
- i915_queue_hangcheck(dev_priv);
+ i915_queue_hangcheck(dev_priv);
}
void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
struct edid *edid;
bool connected = false;
+ struct i2c_adapter *i2c;
intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
- edid = drm_get_edid(connector,
- intel_gmbus_get_adapter(dev_priv,
- intel_hdmi->ddc_bus));
+ i2c = intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
+
+ edid = drm_get_edid(connector, i2c);
+
+ if (!edid && !intel_gmbus_is_forced_bit(i2c)) {
+ DRM_DEBUG_KMS("HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n");
+ intel_gmbus_force_bit(i2c, true);
+ edid = drm_get_edid(connector, i2c);
+ intel_gmbus_force_bit(i2c, false);
+ }
intel_hdmi_dp_dual_mode_detect(connector, edid != NULL);
#define KBL_HUC_FW_MINOR 00
#define KBL_BLD_NUM 1810
-#define GLK_HUC_FW_MAJOR 02
-#define GLK_HUC_FW_MINOR 00
-#define GLK_BLD_NUM 1748
-
#define HUC_FW_PATH(platform, major, minor, bld_num) \
"i915/" __stringify(platform) "_huc_ver" __stringify(major) "_" \
__stringify(minor) "_" __stringify(bld_num) ".bin"
KBL_HUC_FW_MINOR, KBL_BLD_NUM)
MODULE_FIRMWARE(I915_KBL_HUC_UCODE);
-#define I915_GLK_HUC_UCODE HUC_FW_PATH(glk, GLK_HUC_FW_MAJOR, \
- GLK_HUC_FW_MINOR, GLK_BLD_NUM)
-
static void huc_fw_select(struct intel_uc_fw *huc_fw)
{
struct intel_huc *huc = container_of(huc_fw, struct intel_huc, fw);
huc_fw->path = I915_KBL_HUC_UCODE;
huc_fw->major_ver_wanted = KBL_HUC_FW_MAJOR;
huc_fw->minor_ver_wanted = KBL_HUC_FW_MINOR;
- } else if (IS_GEMINILAKE(dev_priv)) {
- huc_fw->path = I915_GLK_HUC_UCODE;
- huc_fw->major_ver_wanted = GLK_HUC_FW_MAJOR;
- huc_fw->minor_ver_wanted = GLK_HUC_FW_MINOR;
} else {
DRM_WARN("%s: No firmware known for this platform!\n",
intel_uc_fw_type_repr(huc_fw->type));
return 0;
}
-int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
- u32 mbox, u32 val)
+int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv,
+ u32 mbox, u32 val, int timeout_us)
{
int status;
if (__intel_wait_for_register_fw(dev_priv,
GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0,
- 500, 0, NULL)) {
+ timeout_us, 0, NULL)) {
DRM_ERROR("timeout waiting for pcode write of 0x%08x to mbox %x to finish for %ps\n",
val, mbox, __builtin_return_address(0));
return -ETIMEDOUT;
if (!USES_GUC(dev_priv))
return;
- GEM_BUG_ON(!HAS_GUC(dev_priv));
-
intel_guc_fini_wq(&dev_priv->guc);
}
u16 dp_gpio_pin_num; /* 195 */
u8 dp_iboost_level:4; /* 196 */
u8 hdmi_iboost_level:4; /* 196 */
+ u8 dp_max_link_rate:2; /* 216 CNL+ */
+ u8 dp_max_link_rate_reserved:6; /* 216 */
} __packed;
struct bdb_general_definitions {
int gf100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gf108_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gk104_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int gk110_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gk20a_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gm107_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gm200_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gm200_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
int gm20b_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
int gp102_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
+int gp108_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
int gp10b_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **);
#endif
NVKM_THERM_ATTR_THRS_SHUTDOWN_HYST = 17,
};
+struct nvkm_therm_clkgate_init {
+ u32 addr;
+ u8 count;
+ u32 data;
+};
+
+struct nvkm_therm_clkgate_pack {
+ const struct nvkm_therm_clkgate_init *init;
+};
+
struct nvkm_therm {
const struct nvkm_therm_func *func;
struct nvkm_subdev subdev;
int (*attr_get)(struct nvkm_therm *, enum nvkm_therm_attr_type);
int (*attr_set)(struct nvkm_therm *, enum nvkm_therm_attr_type, int);
+
+ bool clkgating_enabled;
};
int nvkm_therm_temp_get(struct nvkm_therm *);
int nvkm_therm_fan_sense(struct nvkm_therm *);
int nvkm_therm_cstate(struct nvkm_therm *, int, int);
+void nvkm_therm_clkgate_init(struct nvkm_therm *,
+ const struct nvkm_therm_clkgate_pack *);
+void nvkm_therm_clkgate_enable(struct nvkm_therm *);
+void nvkm_therm_clkgate_fini(struct nvkm_therm *, bool);
int nv40_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int nv50_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int g84_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int gt215_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int gf119_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
+int gk104_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int gm107_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int gm200_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
int gp100_therm_new(struct nvkm_device *, int, struct nvkm_therm **);
return ioptr;
}
+static inline void
+nouveau_bo_unmap_unpin_unref(struct nouveau_bo **pnvbo)
+{
+ if (*pnvbo) {
+ nouveau_bo_unmap(*pnvbo);
+ nouveau_bo_unpin(*pnvbo);
+ nouveau_bo_ref(NULL, pnvbo);
+ }
+}
+
+static inline int
+nouveau_bo_new_pin_map(struct nouveau_cli *cli, u64 size, int align, u32 flags,
+ struct nouveau_bo **pnvbo)
+{
+ int ret = nouveau_bo_new(cli, size, align, flags,
+ 0, 0, NULL, NULL, pnvbo);
+ if (ret == 0) {
+ ret = nouveau_bo_pin(*pnvbo, flags, true);
+ if (ret == 0) {
+ ret = nouveau_bo_map(*pnvbo);
+ if (ret == 0)
+ return ret;
+ nouveau_bo_unpin(*pnvbo);
+ }
+ nouveau_bo_ref(NULL, pnvbo);
+ }
+ return ret;
+}
#endif
} cursor;
struct {
- struct nouveau_bo *nvbo;
int depth;
} lut;
int nouveau_nofbaccel = 0;
module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400);
+MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)");
+static int nouveau_fbcon_bpp;
+module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400);
+
static void
nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
{
{
struct nouveau_drm *drm = nouveau_drm(dev);
struct nouveau_fbdev *fbcon;
- int preferred_bpp;
+ int preferred_bpp = nouveau_fbcon_bpp;
int ret;
if (!dev->mode_config.num_crtc ||
if (ret)
goto fini;
- if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
- preferred_bpp = 8;
- else
- if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
- preferred_bpp = 16;
- else
- preferred_bpp = 32;
+ if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) {
+ if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
+ preferred_bpp = 8;
+ else
+ if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
+ preferred_bpp = 16;
+ else
+ preferred_bpp = 32;
+ }
/* disable all the possible outputs/crtcs before entering KMS mode */
if (!drm_drv_uses_atomic_modeset(dev))
} mode;
struct {
+ bool visible;
u32 handle;
u64 offset:40;
+ u8 mode:4;
} lut;
struct {
union {
struct {
+ bool ilut:1;
bool core:1;
bool curs:1;
};
union {
struct {
+ bool ilut:1;
bool core:1;
bool curs:1;
bool view:1;
struct nv50_head {
struct nouveau_crtc base;
+ struct {
+ struct nouveau_bo *nvbo[2];
+ int next;
+ } lut;
struct nv50_ovly ovly;
struct nv50_oimm oimm;
};
}
}
+static void
+nv50_head_lut_load(struct drm_property_blob *blob, int mode,
+ struct nouveau_bo *nvbo)
+{
+ struct drm_color_lut *in = (struct drm_color_lut *)blob->data;
+ void __iomem *lut = (u8 *)nvbo_kmap_obj_iovirtual(nvbo);
+ const int size = blob->length / sizeof(*in);
+ int bits, shift, i;
+ u16 zero, r, g, b;
+
+ /* This can't happen.. But it shuts the compiler up. */
+ if (WARN_ON(size != 256))
+ return;
+
+ switch (mode) {
+ case 0: /* LORES. */
+ case 1: /* HIRES. */
+ bits = 11;
+ shift = 3;
+ zero = 0x0000;
+ break;
+ case 7: /* INTERPOLATE_257_UNITY_RANGE. */
+ bits = 14;
+ shift = 0;
+ zero = 0x6000;
+ break;
+ default:
+ WARN_ON(1);
+ return;
+ }
+
+ for (i = 0; i < size; i++) {
+ r = (drm_color_lut_extract(in[i]. red, bits) + zero) << shift;
+ g = (drm_color_lut_extract(in[i].green, bits) + zero) << shift;
+ b = (drm_color_lut_extract(in[i]. blue, bits) + zero) << shift;
+ writew(r, lut + (i * 0x08) + 0);
+ writew(g, lut + (i * 0x08) + 2);
+ writew(b, lut + (i * 0x08) + 4);
+ }
+
+ /* INTERPOLATE modes require a "next" entry to interpolate with,
+ * so we replicate the last entry to deal with this for now.
+ */
+ writew(r, lut + (i * 0x08) + 0);
+ writew(g, lut + (i * 0x08) + 2);
+ writew(b, lut + (i * 0x08) + 4);
+}
+
static void
nv50_head_lut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
{
if ((push = evo_wait(core, 7))) {
if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) {
evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
- evo_data(push, 0xc0000000);
+ evo_data(push, 0x80000000 | asyh->lut.mode << 30);
evo_data(push, asyh->lut.offset >> 8);
} else
if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) {
evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2);
- evo_data(push, 0xc0000000);
+ evo_data(push, 0x80000000 | asyh->lut.mode << 30);
evo_data(push, asyh->lut.offset >> 8);
evo_mthd(push, 0x085c + (head->base.index * 0x400), 1);
evo_data(push, asyh->lut.handle);
} else {
evo_mthd(push, 0x0440 + (head->base.index * 0x300), 4);
- evo_data(push, 0x83000000);
+ evo_data(push, 0x80000000 | asyh->lut.mode << 24);
evo_data(push, asyh->lut.offset >> 8);
evo_data(push, 0x00000000);
evo_data(push, 0x00000000);
static void
nv50_head_flush_clr(struct nv50_head *head, struct nv50_head_atom *asyh, bool y)
{
- if (asyh->clr.core && (!asyh->set.core || y))
+ if (asyh->clr.ilut && (!asyh->set.ilut || y))
nv50_head_lut_clr(head);
if (asyh->clr.core && (!asyh->set.core || y))
nv50_head_core_clr(head);
{
if (asyh->set.view ) nv50_head_view (head, asyh);
if (asyh->set.mode ) nv50_head_mode (head, asyh);
- if (asyh->set.core ) nv50_head_lut_set (head, asyh);
+ if (asyh->set.ilut ) {
+ struct nouveau_bo *nvbo = head->lut.nvbo[head->lut.next];
+ struct drm_property_blob *blob = asyh->state.gamma_lut;
+ if (blob)
+ nv50_head_lut_load(blob, asyh->lut.mode, nvbo);
+ asyh->lut.offset = nvbo->bo.offset;
+ head->lut.next ^= 1;
+ nv50_head_lut_set(head, asyh);
+ }
if (asyh->set.core ) nv50_head_core_set(head, asyh);
if (asyh->set.curs ) nv50_head_curs_set(head, asyh);
if (asyh->set.base ) nv50_head_base (head, asyh);
asyh->set.view = true;
}
+static void
+nv50_head_atomic_check_lut(struct nv50_head *head,
+ struct nv50_head_atom *armh,
+ struct nv50_head_atom *asyh)
+{
+ struct nv50_disp *disp = nv50_disp(head->base.base.dev);
+
+ /* An I8 surface without an input LUT makes no sense, and
+ * EVO will throw an error if you try.
+ *
+ * Legacy clients actually cause this due to the order in
+ * which they call ioctls, so we will enable the LUT with
+ * whatever contents the buffer already contains to avoid
+ * triggering the error check.
+ */
+ if (!asyh->state.gamma_lut && asyh->base.cpp != 1) {
+ asyh->lut.handle = 0;
+ asyh->clr.ilut = armh->lut.visible;
+ return;
+ }
+
+ if (disp->disp->oclass < GF110_DISP) {
+ asyh->lut.mode = (asyh->base.cpp == 1) ? 0 : 1;
+ asyh->set.ilut = true;
+ } else {
+ asyh->lut.mode = 7;
+ asyh->set.ilut = asyh->state.color_mgmt_changed;
+ }
+ asyh->lut.handle = disp->mast.base.vram.handle;
+}
+
static void
nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh)
{
if (asyh->state.mode_changed)
nv50_head_atomic_check_mode(head, asyh);
+ if (asyh->state.color_mgmt_changed ||
+ asyh->base.cpp != armh->base.cpp)
+ nv50_head_atomic_check_lut(head, armh, asyh);
+ asyh->lut.visible = asyh->lut.handle != 0;
+
if (asyc) {
if (asyc->set.scaler)
nv50_head_atomic_check_view(armh, asyh, asyc);
asyh->core.w = asyh->base.w;
asyh->core.h = asyh->base.h;
} else
- if ((asyh->core.visible = asyh->curs.visible)) {
+ if ((asyh->core.visible = asyh->curs.visible) ||
+ (asyh->core.visible = asyh->lut.visible)) {
/*XXX: We need to either find some way of having the
* primary base layer appear black, while still
* being able to display the other layers, or we
asyh->core.layout = 1;
asyh->core.block = 0;
asyh->core.pitch = ALIGN(asyh->core.w, 64) * 4;
- asyh->lut.handle = disp->mast.base.vram.handle;
- asyh->lut.offset = head->base.lut.nvbo->bo.offset;
asyh->set.base = armh->base.cpp != asyh->base.cpp;
asyh->set.ovly = armh->ovly.cpp != asyh->ovly.cpp;
} else {
+ asyh->lut.visible = false;
asyh->core.visible = false;
asyh->curs.visible = false;
asyh->base.cpp = 0;
asyh->clr.curs = true;
}
} else {
+ asyh->clr.ilut = armh->lut.visible;
asyh->clr.core = armh->core.visible;
asyh->clr.curs = armh->curs.visible;
+ asyh->set.ilut = asyh->lut.visible;
asyh->set.core = asyh->core.visible;
asyh->set.curs = asyh->curs.visible;
}
return 0;
}
-static void
-nv50_head_lut_load(struct drm_crtc *crtc)
-{
- struct nv50_disp *disp = nv50_disp(crtc->dev);
- struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
- void __iomem *lut = nvbo_kmap_obj_iovirtual(nv_crtc->lut.nvbo);
- u16 *r, *g, *b;
- int i;
-
- r = crtc->gamma_store;
- g = r + crtc->gamma_size;
- b = g + crtc->gamma_size;
-
- for (i = 0; i < 256; i++) {
- if (disp->disp->oclass < GF110_DISP) {
- writew((*r++ >> 2) + 0x0000, lut + (i * 0x08) + 0);
- writew((*g++ >> 2) + 0x0000, lut + (i * 0x08) + 2);
- writew((*b++ >> 2) + 0x0000, lut + (i * 0x08) + 4);
- } else {
- /* 0x6000 interferes with the 14-bit color??? */
- writew((*r++ >> 2) + 0x6000, lut + (i * 0x20) + 0);
- writew((*g++ >> 2) + 0x6000, lut + (i * 0x20) + 2);
- writew((*b++ >> 2) + 0x6000, lut + (i * 0x20) + 4);
- }
- }
-}
-
static const struct drm_crtc_helper_funcs
nv50_head_help = {
.atomic_check = nv50_head_atomic_check,
};
-static int
-nv50_head_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b,
- uint32_t size,
- struct drm_modeset_acquire_ctx *ctx)
-{
- nv50_head_lut_load(crtc);
- return 0;
-}
-
static void
nv50_head_atomic_destroy_state(struct drm_crtc *crtc,
struct drm_crtc_state *state)
static void
nv50_head_destroy(struct drm_crtc *crtc)
{
- struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc);
struct nv50_disp *disp = nv50_disp(crtc->dev);
struct nv50_head *head = nv50_head(crtc);
+ int i;
nv50_dmac_destroy(&head->ovly.base, disp->disp);
nv50_pioc_destroy(&head->oimm.base);
- nouveau_bo_unmap(nv_crtc->lut.nvbo);
- if (nv_crtc->lut.nvbo)
- nouveau_bo_unpin(nv_crtc->lut.nvbo);
- nouveau_bo_ref(NULL, &nv_crtc->lut.nvbo);
+ for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++)
+ nouveau_bo_unmap_unpin_unref(&head->lut.nvbo[i]);
drm_crtc_cleanup(crtc);
kfree(crtc);
static const struct drm_crtc_funcs
nv50_head_func = {
.reset = nv50_head_reset,
- .gamma_set = nv50_head_gamma_set,
+ .gamma_set = drm_atomic_helper_legacy_gamma_set,
.destroy = nv50_head_destroy,
.set_config = drm_atomic_helper_set_config,
.page_flip = drm_atomic_helper_page_flip,
struct nv50_base *base;
struct nv50_curs *curs;
struct drm_crtc *crtc;
- int ret;
+ int ret, i;
head = kzalloc(sizeof(*head), GFP_KERNEL);
if (!head)
drm_crtc_helper_add(crtc, &nv50_head_help);
drm_mode_crtc_set_gamma_size(crtc, 256);
- ret = nouveau_bo_new(&drm->client, 8192, 0x100, TTM_PL_FLAG_VRAM,
- 0, 0x0000, NULL, NULL, &head->base.lut.nvbo);
- if (!ret) {
- ret = nouveau_bo_pin(head->base.lut.nvbo, TTM_PL_FLAG_VRAM, true);
- if (!ret) {
- ret = nouveau_bo_map(head->base.lut.nvbo);
- if (ret)
- nouveau_bo_unpin(head->base.lut.nvbo);
- }
+ for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++) {
+ ret = nouveau_bo_new_pin_map(&drm->client, 1025 * 8, 0x100,
+ TTM_PL_FLAG_VRAM,
+ &head->lut.nvbo[i]);
if (ret)
- nouveau_bo_ref(NULL, &head->base.lut.nvbo);
+ goto out;
}
- if (ret)
- goto out;
-
/* allocate overlay resources */
ret = nv50_oimm_create(device, disp->disp, index, &head->oimm);
if (ret)
{
struct drm_encoder *encoder;
struct drm_plane *plane;
- struct drm_crtc *crtc;
u32 *push;
push = evo_wait(nv50_mast(dev), 32);
}
}
- drm_for_each_crtc(crtc, dev) {
- nv50_head_lut_load(crtc);
- }
-
drm_for_each_plane(plane, dev) {
struct nv50_wndw *wndw = nv50_wndw(plane);
if (plane->funcs != &nv50_wndw)
#include <core/option.h>
#include <subdev/bios.h>
+#include <subdev/therm.h>
static DEFINE_MUTEX(nv_devices_mutex);
static LIST_HEAD(nv_devices);
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk104_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk104_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk104_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.bus = gf100_bus_new,
.clk = gk104_clk_new,
.devinit = gf100_devinit_new,
- .fb = gk104_fb_new,
+ .fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
.i2c = gk104_i2c_new,
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk110_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.bus = gf100_bus_new,
.clk = gk104_clk_new,
.devinit = gf100_devinit_new,
- .fb = gk104_fb_new,
+ .fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
.i2c = gk104_i2c_new,
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk110_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.bus = gf100_bus_new,
.clk = gk104_clk_new,
.devinit = gf100_devinit_new,
- .fb = gk104_fb_new,
+ .fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
.i2c = gk104_i2c_new,
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk208_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.bus = gf100_bus_new,
.clk = gk104_clk_new,
.devinit = gf100_devinit_new,
- .fb = gk104_fb_new,
+ .fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
.i2c = gk104_i2c_new,
.mxm = nv50_mxm_new,
.pci = gk104_pci_new,
.pmu = gk208_pmu_new,
- .therm = gf119_therm_new,
+ .therm = gk104_therm_new,
.timer = nv41_timer_new,
.top = gk104_top_new,
.volt = gk104_volt_new,
.mc = gp100_mc_new,
.mmu = gp100_mmu_new,
.therm = gp100_therm_new,
+ .secboot = gp108_secboot_new,
.pci = gp100_pci_new,
.pmu = gp102_pmu_new,
.timer = gk20a_timer_new,
.disp = gp102_disp_new,
.dma = gf119_dma_new,
.fifo = gp100_fifo_new,
+ .gr = gp107_gr_new,
+ .nvdec = gp102_nvdec_new,
+ .sec2 = gp102_sec2_new,
+ .sw = gf100_sw_new,
};
static const struct nvkm_device_chip
}
}
+ nvkm_therm_clkgate_fini(device->therm, suspend);
if (device->func->fini)
device->func->fini(device, suspend);
}
nvkm_acpi_init(device);
+ nvkm_therm_clkgate_enable(device->therm);
time = ktime_to_us(ktime_get()) - time;
nvdev_trace(device, "init completed in %lldus\n", time);
int (*rops)(struct gf100_gr *);
int ppc_nr;
const struct gf100_grctx_func *grctx;
+ const struct nvkm_therm_clkgate_pack *clkgate_pack;
struct nvkm_sclass sclass[];
};
* Authors: Ben Skeggs <bskeggs@redhat.com>
*/
#include "gf100.h"
+#include "gk104.h"
#include "ctxgf100.h"
#include <nvif/class.h>
{}
};
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_main_0[] = {
+ { 0x4041f0, 1, 0x00004046 },
+ { 0x409890, 1, 0x00000045 },
+ { 0x4098b0, 1, 0x0000007f },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rstr2d_0[] = {
+ { 0x4078c0, 1, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_unk_0[] = {
+ { 0x406000, 1, 0x00004044 },
+ { 0x405860, 1, 0x00004042 },
+ { 0x40590c, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gcc_0[] = {
+ { 0x408040, 1, 0x00004044 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_sked_0[] = {
+ { 0x407000, 1, 0x00004044 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_unk_1[] = {
+ { 0x405bf0, 1, 0x00004044 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_ctxctl_0[] = {
+ { 0x41a890, 1, 0x00000042 },
+ { 0x41a8b0, 1, 0x0000007f },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_unk_0[] = {
+ { 0x418500, 1, 0x00004042 },
+ { 0x418608, 1, 0x00004042 },
+ { 0x418688, 1, 0x00004042 },
+ { 0x418718, 1, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_esetup_0[] = {
+ { 0x418828, 1, 0x00000044 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_tpbus_0[] = {
+ { 0x418bbc, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_zcull_0[] = {
+ { 0x418970, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_tpconf_0[] = {
+ { 0x418c70, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_unk_1[] = {
+ { 0x418cf0, 1, 0x00004042 },
+ { 0x418d70, 1, 0x00004042 },
+ { 0x418f0c, 1, 0x00004042 },
+ { 0x418e0c, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_gcc_0[] = {
+ { 0x419020, 1, 0x00004042 },
+ { 0x419038, 1, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_ffb_0[] = {
+ { 0x418898, 1, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_tex_0[] = {
+ { 0x419a40, 9, 0x00004042 },
+ { 0x419acc, 1, 0x00004047 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_poly_0[] = {
+ { 0x419868, 1, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_l1c_0[] = {
+ { 0x419ccc, 3, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_unk_2[] = {
+ { 0x419c70, 1, 0x00004045 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_mp_0[] = {
+ { 0x419fd0, 1, 0x00004043 },
+ { 0x419fd8, 1, 0x00004049 },
+ { 0x419fe0, 2, 0x00004042 },
+ { 0x419ff0, 1, 0x00004046 },
+ { 0x419ff8, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_gpc_ppc_0[] = {
+ { 0x41be28, 1, 0x00000042 },
+ { 0x41bfe8, 1, 0x00004042 },
+ { 0x41bed0, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rop_zrop_0[] = {
+ { 0x408810, 2, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rop_0[] = {
+ { 0x408a80, 6, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_rop_crop_0[] = {
+ { 0x4089a8, 1, 0x00004042 },
+ { 0x4089b0, 1, 0x00000042 },
+ { 0x4089b8, 1, 0x00004042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_clkgate_blcg_init_pxbar_0[] = {
+ { 0x13c820, 1, 0x0001007f },
+ { 0x13cbe0, 1, 0x00000042 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk104_clkgate_pack[] = {
+ { gk104_clkgate_blcg_init_main_0 },
+ { gk104_clkgate_blcg_init_rstr2d_0 },
+ { gk104_clkgate_blcg_init_unk_0 },
+ { gk104_clkgate_blcg_init_gcc_0 },
+ { gk104_clkgate_blcg_init_sked_0 },
+ { gk104_clkgate_blcg_init_unk_1 },
+ { gk104_clkgate_blcg_init_gpc_ctxctl_0 },
+ { gk104_clkgate_blcg_init_gpc_unk_0 },
+ { gk104_clkgate_blcg_init_gpc_esetup_0 },
+ { gk104_clkgate_blcg_init_gpc_tpbus_0 },
+ { gk104_clkgate_blcg_init_gpc_zcull_0 },
+ { gk104_clkgate_blcg_init_gpc_tpconf_0 },
+ { gk104_clkgate_blcg_init_gpc_unk_1 },
+ { gk104_clkgate_blcg_init_gpc_gcc_0 },
+ { gk104_clkgate_blcg_init_gpc_ffb_0 },
+ { gk104_clkgate_blcg_init_gpc_tex_0 },
+ { gk104_clkgate_blcg_init_gpc_poly_0 },
+ { gk104_clkgate_blcg_init_gpc_l1c_0 },
+ { gk104_clkgate_blcg_init_gpc_unk_2 },
+ { gk104_clkgate_blcg_init_gpc_mp_0 },
+ { gk104_clkgate_blcg_init_gpc_ppc_0 },
+ { gk104_clkgate_blcg_init_rop_zrop_0 },
+ { gk104_clkgate_blcg_init_rop_0 },
+ { gk104_clkgate_blcg_init_rop_crop_0 },
+ { gk104_clkgate_blcg_init_pxbar_0 },
+ {}
+};
+
/*******************************************************************************
* PGRAPH engine/subdev functions
******************************************************************************/
gr->func->init_gpc_mmu(gr);
gf100_gr_mmio(gr, gr->func->mmio);
+ if (gr->func->clkgate_pack)
+ nvkm_therm_clkgate_init(gr->base.engine.subdev.device->therm,
+ gr->func->clkgate_pack);
nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001);
.rops = gf100_gr_rops,
.ppc_nr = 1,
.grctx = &gk104_grctx,
+ .clkgate_pack = gk104_clkgate_pack,
.sclass = {
{ -1, -1, FERMI_TWOD_A },
{ -1, -1, KEPLER_INLINE_TO_MEMORY_A },
--- /dev/null
+/*
+ * Copyright 2018 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.
+ *
+ * Authors: Lyude Paul <lyude@redhat.com>
+ */
+#ifndef __GK104_GR_H__
+#define __GK104_GR_H__
+
+#include <subdev/therm.h>
+
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_main_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rstr2d_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_unk_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gcc_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_sked_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_unk_1[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ctxctl_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_esetup_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tpbus_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_zcull_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tpconf_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_1[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_gcc_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ffb_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tex_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_poly_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_l1c_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_2[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_mp_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ppc_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_zrop_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_crop_0[];
+extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_pxbar_0[];
+
+#endif
* Authors: Ben Skeggs <bskeggs@redhat.com>
*/
#include "gf100.h"
+#include "gk104.h"
#include "ctxgf100.h"
#include <subdev/timer.h>
{}
};
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_sked_0[] = {
+ { 0x407000, 1, 0x00004041 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_gpc_gcc_0[] = {
+ { 0x419020, 1, 0x00000042 },
+ { 0x419038, 1, 0x00000042 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_gpc_l1c_0[] = {
+ { 0x419cd4, 2, 0x00004042 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_blcg_init_gpc_mp_0[] = {
+ { 0x419fd0, 1, 0x00004043 },
+ { 0x419fd8, 1, 0x00004049 },
+ { 0x419fe0, 2, 0x00004042 },
+ { 0x419ff0, 1, 0x00000046 },
+ { 0x419ff8, 1, 0x00004042 },
+ { 0x419f90, 1, 0x00004042 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_main_0[] = {
+ { 0x4041f4, 1, 0x00000000 },
+ { 0x409894, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_unk_0[] = {
+ { 0x406004, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_sked_0[] = {
+ { 0x407004, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_ctxctl_0[] = {
+ { 0x41a894, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_unk_0[] = {
+ { 0x418504, 1, 0x00000000 },
+ { 0x41860c, 1, 0x00000000 },
+ { 0x41868c, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_esetup_0[] = {
+ { 0x41882c, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_zcull_0[] = {
+ { 0x418974, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_l1c_0[] = {
+ { 0x419cd8, 2, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_unk_1[] = {
+ { 0x419c74, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_mp_0[] = {
+ { 0x419fd4, 1, 0x00004a4a },
+ { 0x419fdc, 1, 0x00000014 },
+ { 0x419fe4, 1, 0x00000000 },
+ { 0x419ff4, 1, 0x00001724 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_gpc_ppc_0[] = {
+ { 0x41be2c, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_init
+gk110_clkgate_slcg_init_pcounter_0[] = {
+ { 0x1be018, 1, 0x000001ff },
+ { 0x1bc018, 1, 0x000001ff },
+ { 0x1b8018, 1, 0x000001ff },
+ { 0x1b4124, 1, 0x00000000 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk110_clkgate_pack[] = {
+ { gk104_clkgate_blcg_init_main_0 },
+ { gk104_clkgate_blcg_init_rstr2d_0 },
+ { gk104_clkgate_blcg_init_unk_0 },
+ { gk104_clkgate_blcg_init_gcc_0 },
+ { gk110_clkgate_blcg_init_sked_0 },
+ { gk104_clkgate_blcg_init_unk_1 },
+ { gk104_clkgate_blcg_init_gpc_ctxctl_0 },
+ { gk104_clkgate_blcg_init_gpc_unk_0 },
+ { gk104_clkgate_blcg_init_gpc_esetup_0 },
+ { gk104_clkgate_blcg_init_gpc_tpbus_0 },
+ { gk104_clkgate_blcg_init_gpc_zcull_0 },
+ { gk104_clkgate_blcg_init_gpc_tpconf_0 },
+ { gk104_clkgate_blcg_init_gpc_unk_1 },
+ { gk110_clkgate_blcg_init_gpc_gcc_0 },
+ { gk104_clkgate_blcg_init_gpc_ffb_0 },
+ { gk104_clkgate_blcg_init_gpc_tex_0 },
+ { gk104_clkgate_blcg_init_gpc_poly_0 },
+ { gk110_clkgate_blcg_init_gpc_l1c_0 },
+ { gk104_clkgate_blcg_init_gpc_unk_2 },
+ { gk110_clkgate_blcg_init_gpc_mp_0 },
+ { gk104_clkgate_blcg_init_gpc_ppc_0 },
+ { gk104_clkgate_blcg_init_rop_zrop_0 },
+ { gk104_clkgate_blcg_init_rop_0 },
+ { gk104_clkgate_blcg_init_rop_crop_0 },
+ { gk104_clkgate_blcg_init_pxbar_0 },
+ { gk110_clkgate_slcg_init_main_0 },
+ { gk110_clkgate_slcg_init_unk_0 },
+ { gk110_clkgate_slcg_init_sked_0 },
+ { gk110_clkgate_slcg_init_gpc_ctxctl_0 },
+ { gk110_clkgate_slcg_init_gpc_unk_0 },
+ { gk110_clkgate_slcg_init_gpc_esetup_0 },
+ { gk110_clkgate_slcg_init_gpc_zcull_0 },
+ { gk110_clkgate_slcg_init_gpc_l1c_0 },
+ { gk110_clkgate_slcg_init_gpc_unk_1 },
+ { gk110_clkgate_slcg_init_gpc_mp_0 },
+ { gk110_clkgate_slcg_init_gpc_ppc_0 },
+ { gk110_clkgate_slcg_init_pcounter_0 },
+ {}
+};
+
/*******************************************************************************
* PGRAPH engine/subdev functions
******************************************************************************/
.rops = gf100_gr_rops,
.ppc_nr = 2,
.grctx = &gk110_grctx,
+ .clkgate_pack = gk110_clkgate_pack,
.sclass = {
{ -1, -1, FERMI_TWOD_A },
{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
args->v0.id = di;
args->v0.signal_nr = nvkm_perfdom_count_perfsig(dom);
- strncpy(args->v0.name, dom->name, sizeof(args->v0.name));
+ strncpy(args->v0.name, dom->name, sizeof(args->v0.name) - 1);
/* Currently only global counters (PCOUNTER) are implemented
* but this will be different for local counters (MP). */
"/%s/%02x", dom->name, si);
} else {
strncpy(args->v0.name, sig->name,
- sizeof(args->v0.name));
+ sizeof(args->v0.name) - 1);
}
args->v0.signal = si;
args->v0.source = sig->source[si];
args->v0.mask = src->mask;
- strncpy(args->v0.name, src->name, sizeof(args->v0.name));
+ strncpy(args->v0.name, src->name, sizeof(args->v0.name) - 1);
}
if (++si < source_nr) {
ret = msgqueue_0137bca5_new(falcon, sb, queue);
break;
case 0x0148cdec:
+ case 0x015ccf3e:
ret = msgqueue_0148cdec_new(falcon, sb, queue);
break;
default:
struct nvkm_device *device = clk->base.subdev.device;
u32 ctrl = nvkm_rd32(device, pll + 0);
u32 sclk = 0, P = 1, N = 1, M = 1;
+ u32 MP;
if (!(ctrl & 0x00000008)) {
if (ctrl & 0x00000001) {
sclk = read_clk(clk, 0x10 + idx, false);
}
- if (M * P)
- return sclk * N / (M * P);
+ MP = M * P;
- return 0;
+ if (!MP)
+ return 0;
+
+ return sclk * N / MP;
}
static int
nvkm-y += nvkm/subdev/fb/gf100.o
nvkm-y += nvkm/subdev/fb/gf108.o
nvkm-y += nvkm/subdev/fb/gk104.o
+nvkm-y += nvkm/subdev/fb/gk110.o
nvkm-y += nvkm/subdev/fb/gk20a.o
nvkm-y += nvkm/subdev/fb/gm107.o
nvkm-y += nvkm/subdev/fb/gm200.o
#include <core/memory.h>
#include <core/option.h>
+#include <subdev/therm.h>
void
gf100_fb_intr(struct nvkm_fb *base)
if (fb->r100c10_page)
nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8);
+
+ if (base->func->clkgate_pack) {
+ nvkm_therm_clkgate_init(device->therm,
+ base->func->clkgate_pack);
+ }
}
void *
* OTHER DEALINGS IN THE SOFTWARE.
*
* Authors: Ben Skeggs
+ * Lyude Paul
*/
+#include "gk104.h"
#include "gf100.h"
#include "ram.h"
+/*
+ *******************************************************************************
+ * PGRAPH registers for clockgating
+ *******************************************************************************
+ */
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_unk_0[] = {
+ { 0x100d10, 1, 0x0000c244 },
+ { 0x100d30, 1, 0x0000c242 },
+ { 0x100d3c, 1, 0x00000242 },
+ { 0x100d48, 1, 0x00000242 },
+ { 0x100d1c, 1, 0x00000042 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_vm_0[] = {
+ { 0x100c98, 1, 0x00000242 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_main_0[] = {
+ { 0x10f000, 1, 0x00000042 },
+ { 0x17e030, 1, 0x00000044 },
+ { 0x17e040, 1, 0x00000044 },
+ {}
+};
+
+const struct nvkm_therm_clkgate_init
+gk104_fb_clkgate_blcg_init_bcast_0[] = {
+ { 0x17ea60, 4, 0x00000044 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk104_fb_clkgate_pack[] = {
+ { gk104_fb_clkgate_blcg_init_unk_0 },
+ { gk104_fb_clkgate_blcg_init_vm_0 },
+ { gk104_fb_clkgate_blcg_init_main_0 },
+ { gk104_fb_clkgate_blcg_init_bcast_0 },
+ {}
+};
+
static const struct nvkm_fb_func
gk104_fb = {
.dtor = gf100_fb_dtor,
.intr = gf100_fb_intr,
.ram_new = gk104_ram_new,
.default_bigpage = 17,
+ .clkgate_pack = gk104_fb_clkgate_pack,
};
int
--- /dev/null
+/*
+ * Copyright 2018 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.
+ *
+ * Authors: Lyude Paul
+ */
+
+#ifndef __GK104_FB_H__
+#define __GK104_FB_H__
+
+#include <subdev/therm.h>
+
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_unk_0[];
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_vm_0[];
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_main_0[];
+extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_bcast_0[];
+
+#endif
--- /dev/null
+/*
+ * Copyright 2017 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.
+ *
+ * Authors: Lyude Paul
+ */
+#include "gf100.h"
+#include "gk104.h"
+#include "ram.h"
+#include <subdev/therm.h>
+#include <subdev/fb.h>
+
+/*
+ *******************************************************************************
+ * PGRAPH registers for clockgating
+ *******************************************************************************
+ */
+
+static const struct nvkm_therm_clkgate_init
+gk110_fb_clkgate_blcg_init_unk_0[] = {
+ { 0x100d10, 1, 0x0000c242 },
+ { 0x100d30, 1, 0x0000c242 },
+ { 0x100d3c, 1, 0x00000242 },
+ { 0x100d48, 1, 0x0000c242 },
+ { 0x100d1c, 1, 0x00000042 },
+ {}
+};
+
+static const struct nvkm_therm_clkgate_pack
+gk110_fb_clkgate_pack[] = {
+ { gk110_fb_clkgate_blcg_init_unk_0 },
+ { gk104_fb_clkgate_blcg_init_vm_0 },
+ { gk104_fb_clkgate_blcg_init_main_0 },
+ { gk104_fb_clkgate_blcg_init_bcast_0 },
+ {}
+};
+
+static const struct nvkm_fb_func
+gk110_fb = {
+ .dtor = gf100_fb_dtor,
+ .oneinit = gf100_fb_oneinit,
+ .init = gf100_fb_init,
+ .init_page = gf100_fb_init_page,
+ .intr = gf100_fb_intr,
+ .ram_new = gk104_ram_new,
+ .default_bigpage = 17,
+ .clkgate_pack = gk110_fb_clkgate_pack,
+};
+
+int
+gk110_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+ return gf100_fb_new_(&gk110_fb, device, index, pfb);
+}
#define __NVKM_FB_PRIV_H__
#define nvkm_fb(p) container_of((p), struct nvkm_fb, subdev)
#include <subdev/fb.h>
+#include <subdev/therm.h>
struct nvkm_bios;
struct nvkm_fb_func {
int (*ram_new)(struct nvkm_fb *, struct nvkm_ram **);
u8 default_bigpage;
+ const struct nvkm_therm_clkgate_pack *clkgate_pack;
};
void nvkm_fb_ctor(const struct nvkm_fb_func *, struct nvkm_device *device,
} else
return ret;
- if (IS_ERR((memory = nvkm_umem_search(client, handle)))) {
+ memory = nvkm_umem_search(client, handle);
+ if (IS_ERR(memory)) {
VMM_DEBUG(vmm, "memory %016llx %ld\n", handle, PTR_ERR(memory));
return PTR_ERR(memory);
}
else
block = (size >> page[i].shift) << page[i].shift;
} else {
- block = (size >> page[i].shift) << page[i].shift;;
+ block = (size >> page[i].shift) << page[i].shift;
}
/* Perform operation. */
0x00000000,
0x00000000,
0x584d454d,
- 0x00000756,
- 0x00000748,
+ 0x00000754,
+ 0x00000746,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x46524550,
- 0x0000075a,
0x00000758,
+ 0x00000756,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x5f433249,
- 0x00000b8a,
- 0x00000a2d,
+ 0x00000b88,
+ 0x00000a2b,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x54534554,
- 0x00000bb3,
- 0x00000b8c,
+ 0x00000bb1,
+ 0x00000b8a,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x454c4449,
- 0x00000bbf,
0x00000bbd,
+ 0x00000bbb,
0x00000000,
0x00000000,
0x00000000,
0x000005d3,
0x00000003,
0x00000002,
- 0x0000069d,
+ 0x0000069b,
0x00040004,
0x00000000,
- 0x000006b9,
+ 0x000006b7,
0x00010005,
0x00000000,
- 0x000006d6,
+ 0x000006d4,
0x00010006,
0x00000000,
0x0000065b,
0x00000007,
0x00000000,
- 0x000006e1,
+ 0x000006df,
/* 0x03c4: memx_func_tail */
/* 0x03c4: memx_ts_start */
0x00000000,
/* 0x065b: memx_func_wait_vblank */
0x9800f840,
0x66b00016,
- 0x130bf400,
+ 0x120bf400,
0xf40166b0,
0x0ef4060b,
/* 0x066d: memx_func_wait_vblank_head1 */
- 0x2077f12e,
- 0x070ef400,
-/* 0x0674: memx_func_wait_vblank_head0 */
- 0x000877f1,
-/* 0x0678: memx_func_wait_vblank_0 */
- 0x07c467f1,
- 0xcf0664b6,
- 0x67fd0066,
- 0xf31bf404,
-/* 0x0688: memx_func_wait_vblank_1 */
- 0x07c467f1,
- 0xcf0664b6,
- 0x67fd0066,
- 0xf30bf404,
-/* 0x0698: memx_func_wait_vblank_fini */
- 0xf80410b6,
-/* 0x069d: memx_func_wr32 */
- 0x00169800,
- 0xb6011598,
- 0x60f90810,
- 0xd0fc50f9,
- 0x21f4e0fc,
- 0x0242b640,
- 0xf8e91bf4,
-/* 0x06b9: memx_func_wait */
- 0x2c87f000,
- 0xcf0684b6,
- 0x1e980088,
- 0x011d9800,
- 0x98021c98,
- 0x10b6031b,
- 0xa321f410,
-/* 0x06d6: memx_func_delay */
- 0x1e9800f8,
- 0x0410b600,
- 0xf87e21f4,
-/* 0x06e1: memx_func_train */
-/* 0x06e3: memx_exec */
- 0xf900f800,
- 0xb9d0f9e0,
- 0xb2b902c1,
-/* 0x06ed: memx_exec_next */
- 0x00139802,
- 0xe70410b6,
- 0xe701f034,
- 0xb601e033,
- 0x30f00132,
- 0xde35980c,
- 0x12b855f9,
- 0xe41ef406,
- 0x98f10b98,
- 0xcbbbf20c,
- 0xc4b7f102,
- 0x06b4b607,
- 0xfc00bbcf,
- 0xf5e0fcd0,
- 0xf8033621,
-/* 0x0729: memx_info */
- 0x01c67000,
-/* 0x072f: memx_info_data */
- 0xf10e0bf4,
- 0xf103ccc7,
- 0xf40800b7,
-/* 0x073a: memx_info_train */
- 0xc7f10b0e,
- 0xb7f10bcc,
-/* 0x0742: memx_info_send */
- 0x21f50100,
- 0x00f80336,
-/* 0x0748: memx_recv */
- 0xf401d6b0,
- 0xd6b0980b,
- 0xd80bf400,
-/* 0x0756: memx_init */
- 0x00f800f8,
-/* 0x0758: perf_recv */
-/* 0x075a: perf_init */
+ 0x2077f02c,
+/* 0x0673: memx_func_wait_vblank_head0 */
+ 0xf0060ef4,
+/* 0x0676: memx_func_wait_vblank_0 */
+ 0x67f10877,
+ 0x64b607c4,
+ 0x0066cf06,
+ 0xf40467fd,
+/* 0x0686: memx_func_wait_vblank_1 */
+ 0x67f1f31b,
+ 0x64b607c4,
+ 0x0066cf06,
+ 0xf40467fd,
+/* 0x0696: memx_func_wait_vblank_fini */
+ 0x10b6f30b,
+/* 0x069b: memx_func_wr32 */
+ 0x9800f804,
+ 0x15980016,
+ 0x0810b601,
+ 0x50f960f9,
+ 0xe0fcd0fc,
+ 0xb64021f4,
+ 0x1bf40242,
+/* 0x06b7: memx_func_wait */
+ 0xf000f8e9,
+ 0x84b62c87,
+ 0x0088cf06,
+ 0x98001e98,
+ 0x1c98011d,
+ 0x031b9802,
+ 0xf41010b6,
+ 0x00f8a321,
+/* 0x06d4: memx_func_delay */
+ 0xb6001e98,
+ 0x21f40410,
+/* 0x06df: memx_func_train */
+ 0xf800f87e,
+/* 0x06e1: memx_exec */
+ 0xf9e0f900,
+ 0x02c1b9d0,
+/* 0x06eb: memx_exec_next */
+ 0x9802b2b9,
+ 0x10b60013,
+ 0xf034e704,
+ 0xe033e701,
+ 0x0132b601,
+ 0x980c30f0,
+ 0x55f9de35,
+ 0xf40612b8,
+ 0x0b98e41e,
+ 0xf20c98f1,
+ 0xf102cbbb,
+ 0xb607c4b7,
+ 0xbbcf06b4,
+ 0xfcd0fc00,
+ 0x3621f5e0,
+/* 0x0727: memx_info */
+ 0x7000f803,
+ 0x0bf401c6,
+/* 0x072d: memx_info_data */
+ 0xccc7f10e,
+ 0x00b7f103,
+ 0x0b0ef408,
+/* 0x0738: memx_info_train */
+ 0x0bccc7f1,
+ 0x0100b7f1,
+/* 0x0740: memx_info_send */
+ 0x033621f5,
+/* 0x0746: memx_recv */
+ 0xd6b000f8,
+ 0x980bf401,
+ 0xf400d6b0,
+ 0x00f8d80b,
+/* 0x0754: memx_init */
+/* 0x0756: perf_recv */
0x00f800f8,
-/* 0x075c: i2c_drive_scl */
- 0xf40036b0,
- 0x07f1110b,
- 0x04b607e0,
- 0x0001d006,
- 0x00f804bd,
-/* 0x0770: i2c_drive_scl_lo */
- 0x07e407f1,
- 0xd00604b6,
- 0x04bd0001,
-/* 0x077e: i2c_drive_sda */
+/* 0x0758: perf_init */
+/* 0x075a: i2c_drive_scl */
0x36b000f8,
0x110bf400,
0x07e007f1,
0xd00604b6,
- 0x04bd0002,
-/* 0x0792: i2c_drive_sda_lo */
+ 0x04bd0001,
+/* 0x076e: i2c_drive_scl_lo */
0x07f100f8,
0x04b607e4,
+ 0x0001d006,
+ 0x00f804bd,
+/* 0x077c: i2c_drive_sda */
+ 0xf40036b0,
+ 0x07f1110b,
+ 0x04b607e0,
0x0002d006,
0x00f804bd,
-/* 0x07a0: i2c_sense_scl */
- 0xf10132f4,
- 0xb607c437,
- 0x33cf0634,
- 0x0431fd00,
- 0xf4060bf4,
-/* 0x07b6: i2c_sense_scl_done */
- 0x00f80131,
-/* 0x07b8: i2c_sense_sda */
- 0xf10132f4,
- 0xb607c437,
- 0x33cf0634,
- 0x0432fd00,
- 0xf4060bf4,
-/* 0x07ce: i2c_sense_sda_done */
- 0x00f80131,
-/* 0x07d0: i2c_raise_scl */
- 0x47f140f9,
- 0x37f00898,
- 0x5c21f501,
-/* 0x07dd: i2c_raise_scl_wait */
- 0xe8e7f107,
- 0x7e21f403,
- 0x07a021f5,
- 0xb60901f4,
- 0x1bf40142,
-/* 0x07f1: i2c_raise_scl_done */
- 0xf840fcef,
-/* 0x07f5: i2c_start */
- 0xa021f500,
- 0x0d11f407,
- 0x07b821f5,
- 0xf40611f4,
-/* 0x0806: i2c_start_rep */
- 0x37f0300e,
- 0x5c21f500,
- 0x0137f007,
- 0x077e21f5,
- 0xb60076bb,
- 0x50f90465,
- 0xbb046594,
- 0x50bd0256,
- 0xfc0475fd,
- 0xd021f550,
- 0x0464b607,
-/* 0x0833: i2c_start_send */
- 0xf01f11f4,
+/* 0x0790: i2c_drive_sda_lo */
+ 0x07e407f1,
+ 0xd00604b6,
+ 0x04bd0002,
+/* 0x079e: i2c_sense_scl */
+ 0x32f400f8,
+ 0xc437f101,
+ 0x0634b607,
+ 0xfd0033cf,
+ 0x0bf40431,
+ 0x0131f406,
+/* 0x07b4: i2c_sense_scl_done */
+/* 0x07b6: i2c_sense_sda */
+ 0x32f400f8,
+ 0xc437f101,
+ 0x0634b607,
+ 0xfd0033cf,
+ 0x0bf40432,
+ 0x0131f406,
+/* 0x07cc: i2c_sense_sda_done */
+/* 0x07ce: i2c_raise_scl */
+ 0x40f900f8,
+ 0x089847f1,
+ 0xf50137f0,
+/* 0x07db: i2c_raise_scl_wait */
+ 0xf1075a21,
+ 0xf403e8e7,
+ 0x21f57e21,
+ 0x01f4079e,
+ 0x0142b609,
+/* 0x07ef: i2c_raise_scl_done */
+ 0xfcef1bf4,
+/* 0x07f3: i2c_start */
+ 0xf500f840,
+ 0xf4079e21,
+ 0x21f50d11,
+ 0x11f407b6,
+ 0x300ef406,
+/* 0x0804: i2c_start_rep */
+ 0xf50037f0,
+ 0xf0075a21,
+ 0x21f50137,
+ 0x76bb077c,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0xf550fc04,
+ 0xb607ce21,
+ 0x11f40464,
+/* 0x0831: i2c_start_send */
+ 0x0037f01f,
+ 0x077c21f5,
+ 0x1388e7f1,
+ 0xf07e21f4,
0x21f50037,
- 0xe7f1077e,
+ 0xe7f1075a,
0x21f41388,
- 0x0037f07e,
- 0x075c21f5,
- 0x1388e7f1,
-/* 0x084f: i2c_start_out */
- 0xf87e21f4,
-/* 0x0851: i2c_stop */
- 0x0037f000,
- 0x075c21f5,
- 0xf50037f0,
- 0xf1077e21,
- 0xf403e8e7,
- 0x37f07e21,
- 0x5c21f501,
- 0x88e7f107,
- 0x7e21f413,
+/* 0x084d: i2c_start_out */
+/* 0x084f: i2c_stop */
+ 0xf000f87e,
+ 0x21f50037,
+ 0x37f0075a,
+ 0x7c21f500,
+ 0xe8e7f107,
+ 0x7e21f403,
0xf50137f0,
- 0xf1077e21,
+ 0xf1075a21,
0xf41388e7,
- 0x00f87e21,
-/* 0x0884: i2c_bitw */
- 0x077e21f5,
- 0x03e8e7f1,
- 0xbb7e21f4,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x07d021f5,
- 0xf40464b6,
- 0xe7f11811,
- 0x21f41388,
- 0x0037f07e,
- 0x075c21f5,
- 0x1388e7f1,
-/* 0x08c3: i2c_bitw_out */
- 0xf87e21f4,
-/* 0x08c5: i2c_bitr */
- 0x0137f000,
- 0x077e21f5,
- 0x03e8e7f1,
- 0xbb7e21f4,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x07d021f5,
- 0xf40464b6,
- 0x21f51b11,
- 0x37f007b8,
- 0x5c21f500,
+ 0x37f07e21,
+ 0x7c21f501,
0x88e7f107,
0x7e21f413,
- 0xf4013cf0,
-/* 0x090a: i2c_bitr_done */
- 0x00f80131,
-/* 0x090c: i2c_get_byte */
- 0xf00057f0,
-/* 0x0912: i2c_get_byte_next */
- 0x54b60847,
- 0x0076bb01,
+/* 0x0882: i2c_bitw */
+ 0x21f500f8,
+ 0xe7f1077c,
+ 0x21f403e8,
+ 0x0076bb7e,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
0x21f550fc,
- 0x64b608c5,
- 0x2b11f404,
- 0xb60553fd,
- 0x1bf40142,
- 0x0137f0d8,
- 0xb60076bb,
- 0x50f90465,
- 0xbb046594,
- 0x50bd0256,
- 0xfc0475fd,
- 0x8421f550,
- 0x0464b608,
-/* 0x095c: i2c_get_byte_done */
-/* 0x095e: i2c_put_byte */
- 0x47f000f8,
-/* 0x0961: i2c_put_byte_next */
- 0x0142b608,
- 0xbb3854ff,
+ 0x64b607ce,
+ 0x1811f404,
+ 0x1388e7f1,
+ 0xf07e21f4,
+ 0x21f50037,
+ 0xe7f1075a,
+ 0x21f41388,
+/* 0x08c1: i2c_bitw_out */
+/* 0x08c3: i2c_bitr */
+ 0xf000f87e,
+ 0x21f50137,
+ 0xe7f1077c,
+ 0x21f403e8,
+ 0x0076bb7e,
+ 0xf90465b6,
+ 0x04659450,
+ 0xbd0256bb,
+ 0x0475fd50,
+ 0x21f550fc,
+ 0x64b607ce,
+ 0x1b11f404,
+ 0x07b621f5,
+ 0xf50037f0,
+ 0xf1075a21,
+ 0xf41388e7,
+ 0x3cf07e21,
+ 0x0131f401,
+/* 0x0908: i2c_bitr_done */
+/* 0x090a: i2c_get_byte */
+ 0x57f000f8,
+ 0x0847f000,
+/* 0x0910: i2c_get_byte_next */
+ 0xbb0154b6,
0x65b60076,
0x9450f904,
0x56bb0465,
0xfd50bd02,
0x50fc0475,
- 0x088421f5,
+ 0x08c321f5,
0xf40464b6,
- 0x46b03411,
- 0xd81bf400,
- 0xb60076bb,
- 0x50f90465,
- 0xbb046594,
- 0x50bd0256,
- 0xfc0475fd,
- 0xc521f550,
- 0x0464b608,
- 0xbb0f11f4,
- 0x36b00076,
- 0x061bf401,
-/* 0x09b7: i2c_put_byte_done */
- 0xf80132f4,
-/* 0x09b9: i2c_addr */
- 0x0076bb00,
+ 0x53fd2b11,
+ 0x0142b605,
+ 0xf0d81bf4,
+ 0x76bb0137,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0xf550fc04,
+ 0xb6088221,
+/* 0x095a: i2c_get_byte_done */
+ 0x00f80464,
+/* 0x095c: i2c_put_byte */
+/* 0x095f: i2c_put_byte_next */
+ 0xb60847f0,
+ 0x54ff0142,
+ 0x0076bb38,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
0x21f550fc,
- 0x64b607f5,
- 0x2911f404,
- 0x012ec3e7,
- 0xfd0134b6,
- 0x76bb0553,
+ 0x64b60882,
+ 0x3411f404,
+ 0xf40046b0,
+ 0x76bbd81b,
0x0465b600,
0x659450f9,
0x0256bb04,
0x75fd50bd,
0xf550fc04,
- 0xb6095e21,
-/* 0x09fe: i2c_addr_done */
- 0x00f80464,
-/* 0x0a00: i2c_acquire_addr */
- 0xb6f8cec7,
- 0xe0b702e4,
- 0xee980d1c,
-/* 0x0a0f: i2c_acquire */
- 0xf500f800,
- 0xf40a0021,
- 0xd9f00421,
- 0x4021f403,
-/* 0x0a1e: i2c_release */
- 0x21f500f8,
- 0x21f40a00,
- 0x03daf004,
- 0xf84021f4,
-/* 0x0a2d: i2c_recv */
- 0x0132f400,
- 0xb6f8c1c7,
- 0x16b00214,
- 0x3a1ff528,
- 0xf413a001,
- 0x0032980c,
- 0x0ccc13a0,
- 0xf4003198,
- 0xd0f90231,
- 0xd0f9e0f9,
- 0x000067f1,
- 0x100063f1,
- 0xbb016792,
+ 0xb608c321,
+ 0x11f40464,
+ 0x0076bb0f,
+ 0xf40136b0,
+ 0x32f4061b,
+/* 0x09b5: i2c_put_byte_done */
+/* 0x09b7: i2c_addr */
+ 0xbb00f801,
0x65b60076,
0x9450f904,
0x56bb0465,
0xfd50bd02,
0x50fc0475,
- 0x0a0f21f5,
- 0xfc0464b6,
- 0x00d6b0d0,
- 0x00b31bf5,
- 0xbb0057f0,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x09b921f5,
- 0xf50464b6,
- 0xc700d011,
- 0x76bbe0c5,
- 0x0465b600,
- 0x659450f9,
- 0x0256bb04,
- 0x75fd50bd,
- 0xf550fc04,
- 0xb6095e21,
- 0x11f50464,
- 0x57f000ad,
+ 0x07f321f5,
+ 0xf40464b6,
+ 0xc3e72911,
+ 0x34b6012e,
+ 0x0553fd01,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x5c21f550,
+ 0x0464b609,
+/* 0x09fc: i2c_addr_done */
+/* 0x09fe: i2c_acquire_addr */
+ 0xcec700f8,
+ 0x02e4b6f8,
+ 0x0d1ce0b7,
+ 0xf800ee98,
+/* 0x0a0d: i2c_acquire */
+ 0xfe21f500,
+ 0x0421f409,
+ 0xf403d9f0,
+ 0x00f84021,
+/* 0x0a1c: i2c_release */
+ 0x09fe21f5,
+ 0xf00421f4,
+ 0x21f403da,
+/* 0x0a2b: i2c_recv */
+ 0xf400f840,
+ 0xc1c70132,
+ 0x0214b6f8,
+ 0xf52816b0,
+ 0xa0013a1f,
+ 0x980cf413,
+ 0x13a00032,
+ 0x31980ccc,
+ 0x0231f400,
+ 0xe0f9d0f9,
+ 0x67f1d0f9,
+ 0x63f10000,
+ 0x67921000,
0x0076bb01,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
0x21f550fc,
- 0x64b609b9,
- 0x8a11f504,
+ 0x64b60a0d,
+ 0xb0d0fc04,
+ 0x1bf500d6,
+ 0x57f000b3,
0x0076bb00,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
0x21f550fc,
- 0x64b6090c,
- 0x6a11f404,
- 0xbbe05bcb,
+ 0x64b609b7,
+ 0xd011f504,
+ 0xe0c5c700,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x5c21f550,
+ 0x0464b609,
+ 0x00ad11f5,
+ 0xbb0157f0,
0x65b60076,
0x9450f904,
0x56bb0465,
0xfd50bd02,
0x50fc0475,
- 0x085121f5,
- 0xb90464b6,
- 0x74bd025b,
-/* 0x0b33: i2c_recv_not_rd08 */
- 0xb0430ef4,
- 0x1bf401d6,
- 0x0057f03d,
- 0x09b921f5,
- 0xc73311f4,
- 0x21f5e0c5,
- 0x11f4095e,
- 0x0057f029,
- 0x09b921f5,
- 0xc71f11f4,
- 0x21f5e0b5,
- 0x11f4095e,
- 0x5121f515,
- 0xc774bd08,
- 0x1bf408c5,
- 0x0232f409,
-/* 0x0b73: i2c_recv_not_wr08 */
-/* 0x0b73: i2c_recv_done */
- 0xc7030ef4,
- 0x21f5f8ce,
- 0xe0fc0a1e,
- 0x12f4d0fc,
- 0x027cb90a,
- 0x033621f5,
-/* 0x0b88: i2c_recv_exit */
-/* 0x0b8a: i2c_init */
- 0x00f800f8,
-/* 0x0b8c: test_recv */
- 0x05d817f1,
+ 0x09b721f5,
+ 0xf50464b6,
+ 0xbb008a11,
+ 0x65b60076,
+ 0x9450f904,
+ 0x56bb0465,
+ 0xfd50bd02,
+ 0x50fc0475,
+ 0x090a21f5,
+ 0xf40464b6,
+ 0x5bcb6a11,
+ 0x0076bbe0,
+ 0xf90465b6,
+ 0x04659450,
+ 0xbd0256bb,
+ 0x0475fd50,
+ 0x21f550fc,
+ 0x64b6084f,
+ 0x025bb904,
+ 0x0ef474bd,
+/* 0x0b31: i2c_recv_not_rd08 */
+ 0x01d6b043,
+ 0xf03d1bf4,
+ 0x21f50057,
+ 0x11f409b7,
+ 0xe0c5c733,
+ 0x095c21f5,
+ 0xf02911f4,
+ 0x21f50057,
+ 0x11f409b7,
+ 0xe0b5c71f,
+ 0x095c21f5,
+ 0xf51511f4,
+ 0xbd084f21,
+ 0x08c5c774,
+ 0xf4091bf4,
+ 0x0ef40232,
+/* 0x0b71: i2c_recv_not_wr08 */
+/* 0x0b71: i2c_recv_done */
+ 0xf8cec703,
+ 0x0a1c21f5,
+ 0xd0fce0fc,
+ 0xb90a12f4,
+ 0x21f5027c,
+/* 0x0b86: i2c_recv_exit */
+ 0x00f80336,
+/* 0x0b88: i2c_init */
+/* 0x0b8a: test_recv */
+ 0x17f100f8,
+ 0x14b605d8,
+ 0x0011cf06,
+ 0xf10110b6,
+ 0xb605d807,
+ 0x01d00604,
+ 0xf104bd00,
+ 0xf1d900e7,
+ 0xf5134fe3,
+ 0xf8025621,
+/* 0x0bb1: test_init */
+ 0x00e7f100,
+ 0x5621f508,
+/* 0x0bbb: idle_recv */
+ 0xf800f802,
+/* 0x0bbd: idle */
+ 0x0031f400,
+ 0x05d417f1,
0xcf0614b6,
0x10b60011,
- 0xd807f101,
+ 0xd407f101,
0x0604b605,
0xbd0001d0,
- 0x00e7f104,
- 0x4fe3f1d9,
- 0x5621f513,
-/* 0x0bb3: test_init */
- 0xf100f802,
- 0xf50800e7,
- 0xf8025621,
-/* 0x0bbd: idle_recv */
-/* 0x0bbf: idle */
- 0xf400f800,
- 0x17f10031,
- 0x14b605d4,
- 0x0011cf06,
- 0xf10110b6,
- 0xb605d407,
- 0x01d00604,
-/* 0x0bdb: idle_loop */
- 0xf004bd00,
- 0x32f45817,
-/* 0x0be1: idle_proc */
-/* 0x0be1: idle_proc_exec */
- 0xb910f902,
- 0x21f5021e,
- 0x10fc033f,
- 0xf40911f4,
- 0x0ef40231,
-/* 0x0bf5: idle_proc_next */
- 0x5810b6ef,
- 0xf4061fb8,
- 0x02f4e61b,
- 0x0028f4dd,
- 0x00bb0ef4,
+/* 0x0bd9: idle_loop */
+ 0x5817f004,
+/* 0x0bdf: idle_proc */
+/* 0x0bdf: idle_proc_exec */
+ 0xf90232f4,
+ 0x021eb910,
+ 0x033f21f5,
+ 0x11f410fc,
+ 0x0231f409,
+/* 0x0bf3: idle_proc_next */
+ 0xb6ef0ef4,
+ 0x1fb85810,
+ 0xe61bf406,
+ 0xf4dd02f4,
+ 0x0ef40028,
+ 0x000000bb,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x584d454d,
- 0x000005f3,
- 0x000005e5,
+ 0x000005ee,
+ 0x000005e0,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x46524550,
- 0x000005f7,
- 0x000005f5,
+ 0x000005f2,
+ 0x000005f0,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x5f433249,
- 0x000009f8,
- 0x000008a2,
+ 0x000009f3,
+ 0x0000089d,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x54534554,
- 0x00000a16,
- 0x000009fa,
+ 0x00000a11,
+ 0x000009f5,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x454c4449,
- 0x00000a21,
- 0x00000a1f,
+ 0x00000a1c,
+ 0x00000a1a,
0x00000000,
0x00000000,
0x00000000,
/* 0x037c: memx_func_next */
0x00000002,
0x00000000,
- 0x000004cf,
+ 0x000004cc,
0x00000003,
0x00000002,
- 0x00000546,
+ 0x00000541,
0x00040004,
0x00000000,
- 0x00000563,
+ 0x0000055e,
0x00010005,
0x00000000,
- 0x0000057d,
+ 0x00000578,
0x00010006,
0x00000000,
- 0x00000541,
+ 0x0000053c,
0x00000007,
0x00000000,
- 0x00000589,
+ 0x00000584,
/* 0x03c4: memx_func_tail */
/* 0x03c4: memx_ts_start */
0x00000000,
0x0001f604,
0x00f804bd,
/* 0x045c: memx_func_enter */
- 0x162067f1,
- 0xf55d77f1,
- 0x047e6eb2,
- 0xd8b20000,
- 0xf90487fd,
- 0xfc80f960,
- 0x7ee0fcd0,
- 0x0700002d,
- 0x7e6eb2fe,
+ 0x47162046,
+ 0x6eb2f55d,
+ 0x0000047e,
+ 0x87fdd8b2,
+ 0xf960f904,
+ 0xfcd0fc80,
+ 0x002d7ee0,
+ 0xb2fe0700,
+ 0x00047e6e,
+ 0xfdd8b200,
+ 0x60f90487,
+ 0xd0fc80f9,
+ 0x2d7ee0fc,
+ 0xf0460000,
+ 0x7e6eb226,
0xb2000004,
0x0487fdd8,
0x80f960f9,
0xe0fcd0fc,
0x00002d7e,
- 0x26f067f1,
- 0x047e6eb2,
- 0xd8b20000,
- 0xf90487fd,
- 0xfc80f960,
- 0x7ee0fcd0,
- 0x0600002d,
- 0x07e04004,
- 0xbd0006f6,
-/* 0x04b9: memx_func_enter_wait */
- 0x07c04604,
- 0xf00066cf,
- 0x0bf40464,
- 0xcf2c06f7,
- 0x06b50066,
-/* 0x04cf: memx_func_leave */
- 0x0600f8f1,
- 0x0066cf2c,
- 0x06f206b5,
- 0x07e44004,
- 0xbd0006f6,
-/* 0x04e1: memx_func_leave_wait */
- 0x07c04604,
- 0xf00066cf,
- 0x1bf40464,
- 0xf067f1f7,
+ 0xe0400406,
+ 0x0006f607,
+/* 0x04b6: memx_func_enter_wait */
+ 0xc04604bd,
+ 0x0066cf07,
+ 0xf40464f0,
+ 0x2c06f70b,
+ 0xb50066cf,
+ 0x00f8f106,
+/* 0x04cc: memx_func_leave */
+ 0x66cf2c06,
+ 0xf206b500,
+ 0xe4400406,
+ 0x0006f607,
+/* 0x04de: memx_func_leave_wait */
+ 0xc04604bd,
+ 0x0066cf07,
+ 0xf40464f0,
+ 0xf046f71b,
0xb2010726,
0x00047e6e,
0xfdd8b200,
0x60f90587,
0xd0fc80f9,
0x2d7ee0fc,
- 0x67f10000,
- 0x6eb21620,
- 0x0000047e,
- 0x87fdd8b2,
- 0xf960f905,
- 0xfcd0fc80,
- 0x002d7ee0,
- 0x0aa24700,
- 0x047e6eb2,
- 0xd8b20000,
- 0xf90587fd,
- 0xfc80f960,
- 0x7ee0fcd0,
- 0xf800002d,
-/* 0x0541: memx_func_wait_vblank */
+ 0x20460000,
+ 0x7e6eb216,
+ 0xb2000004,
+ 0x0587fdd8,
+ 0x80f960f9,
+ 0xe0fcd0fc,
+ 0x00002d7e,
+ 0xb20aa247,
+ 0x00047e6e,
+ 0xfdd8b200,
+ 0x60f90587,
+ 0xd0fc80f9,
+ 0x2d7ee0fc,
+ 0x00f80000,
+/* 0x053c: memx_func_wait_vblank */
+ 0xf80410b6,
+/* 0x0541: memx_func_wr32 */
+ 0x00169800,
+ 0xb6011598,
+ 0x60f90810,
+ 0xd0fc50f9,
+ 0x2d7ee0fc,
+ 0x42b60000,
+ 0xe81bf402,
+/* 0x055e: memx_func_wait */
+ 0x2c0800f8,
+ 0x980088cf,
+ 0x1d98001e,
+ 0x021c9801,
+ 0xb6031b98,
+ 0x747e1010,
+ 0x00f80000,
+/* 0x0578: memx_func_delay */
+ 0xb6001e98,
+ 0x587e0410,
+ 0x00f80000,
+/* 0x0584: memx_func_train */
+/* 0x0586: memx_exec */
+ 0xe0f900f8,
+ 0xc1b2d0f9,
+/* 0x058e: memx_exec_next */
+ 0x1398b2b2,
0x0410b600,
-/* 0x0546: memx_func_wr32 */
- 0x169800f8,
- 0x01159800,
- 0xf90810b6,
- 0xfc50f960,
+ 0x01f034e7,
+ 0x01e033e7,
+ 0xf00132b6,
+ 0x35980c30,
+ 0xa655f9de,
+ 0xe51ef412,
+ 0x98f10b98,
+ 0xcbbbf20c,
+ 0x07c44b02,
+ 0xfc00bbcf,
0x7ee0fcd0,
- 0xb600002d,
- 0x1bf40242,
-/* 0x0563: memx_func_wait */
- 0x0800f8e8,
- 0x0088cf2c,
- 0x98001e98,
- 0x1c98011d,
- 0x031b9802,
- 0x7e1010b6,
- 0xf8000074,
-/* 0x057d: memx_func_delay */
- 0x001e9800,
- 0x7e0410b6,
- 0xf8000058,
-/* 0x0589: memx_func_train */
-/* 0x058b: memx_exec */
- 0xf900f800,
- 0xb2d0f9e0,
-/* 0x0593: memx_exec_next */
- 0x98b2b2c1,
- 0x10b60013,
- 0xf034e704,
- 0xe033e701,
- 0x0132b601,
- 0x980c30f0,
- 0x55f9de35,
- 0x1ef412a6,
- 0xf10b98e5,
- 0xbbf20c98,
- 0xc44b02cb,
- 0x00bbcf07,
- 0xe0fcd0fc,
- 0x00029f7e,
-/* 0x05ca: memx_info */
- 0xc67000f8,
- 0x0c0bf401,
-/* 0x05d0: memx_info_data */
- 0x4b03cc4c,
- 0x0ef40800,
-/* 0x05d9: memx_info_train */
- 0x0bcc4c09,
-/* 0x05df: memx_info_send */
- 0x7e01004b,
0xf800029f,
-/* 0x05e5: memx_recv */
- 0x01d6b000,
- 0xb0a30bf4,
- 0x0bf400d6,
-/* 0x05f3: memx_init */
- 0xf800f8dc,
-/* 0x05f5: perf_recv */
-/* 0x05f7: perf_init */
- 0xf800f800,
-/* 0x05f9: i2c_drive_scl */
- 0x0036b000,
- 0x400d0bf4,
- 0x01f607e0,
- 0xf804bd00,
-/* 0x0609: i2c_drive_scl_lo */
- 0x07e44000,
- 0xbd0001f6,
-/* 0x0613: i2c_drive_sda */
- 0xb000f804,
- 0x0bf40036,
- 0x07e0400d,
- 0xbd0002f6,
-/* 0x0623: i2c_drive_sda_lo */
- 0x4000f804,
- 0x02f607e4,
- 0xf804bd00,
-/* 0x062d: i2c_sense_scl */
- 0x0132f400,
- 0xcf07c443,
- 0x31fd0033,
- 0x060bf404,
-/* 0x063f: i2c_sense_scl_done */
- 0xf80131f4,
-/* 0x0641: i2c_sense_sda */
- 0x0132f400,
- 0xcf07c443,
- 0x32fd0033,
- 0x060bf404,
-/* 0x0653: i2c_sense_sda_done */
- 0xf80131f4,
-/* 0x0655: i2c_raise_scl */
- 0x4440f900,
- 0x01030898,
- 0x0005f97e,
-/* 0x0660: i2c_raise_scl_wait */
- 0x7e03e84e,
- 0x7e000058,
- 0xf400062d,
- 0x42b60901,
- 0xef1bf401,
-/* 0x0674: i2c_raise_scl_done */
- 0x00f840fc,
-/* 0x0678: i2c_start */
- 0x00062d7e,
- 0x7e0d11f4,
- 0xf4000641,
- 0x0ef40611,
-/* 0x0689: i2c_start_rep */
- 0x7e00032e,
- 0x030005f9,
- 0x06137e01,
+/* 0x05c5: memx_info */
+ 0x01c67000,
+/* 0x05cb: memx_info_data */
+ 0x4c0c0bf4,
+ 0x004b03cc,
+ 0x090ef408,
+/* 0x05d4: memx_info_train */
+ 0x4b0bcc4c,
+/* 0x05da: memx_info_send */
+ 0x9f7e0100,
+ 0x00f80002,
+/* 0x05e0: memx_recv */
+ 0xf401d6b0,
+ 0xd6b0a30b,
+ 0xdc0bf400,
+/* 0x05ee: memx_init */
+ 0x00f800f8,
+/* 0x05f0: perf_recv */
+/* 0x05f2: perf_init */
+ 0x00f800f8,
+/* 0x05f4: i2c_drive_scl */
+ 0xf40036b0,
+ 0xe0400d0b,
+ 0x0001f607,
+ 0x00f804bd,
+/* 0x0604: i2c_drive_scl_lo */
+ 0xf607e440,
+ 0x04bd0001,
+/* 0x060e: i2c_drive_sda */
+ 0x36b000f8,
+ 0x0d0bf400,
+ 0xf607e040,
+ 0x04bd0002,
+/* 0x061e: i2c_drive_sda_lo */
+ 0xe44000f8,
+ 0x0002f607,
+ 0x00f804bd,
+/* 0x0628: i2c_sense_scl */
+ 0x430132f4,
+ 0x33cf07c4,
+ 0x0431fd00,
+ 0xf4060bf4,
+/* 0x063a: i2c_sense_scl_done */
+ 0x00f80131,
+/* 0x063c: i2c_sense_sda */
+ 0x430132f4,
+ 0x33cf07c4,
+ 0x0432fd00,
+ 0xf4060bf4,
+/* 0x064e: i2c_sense_sda_done */
+ 0x00f80131,
+/* 0x0650: i2c_raise_scl */
+ 0x984440f9,
+ 0x7e010308,
+/* 0x065b: i2c_raise_scl_wait */
+ 0x4e0005f4,
+ 0x587e03e8,
+ 0x287e0000,
+ 0x01f40006,
+ 0x0142b609,
+/* 0x066f: i2c_raise_scl_done */
+ 0xfcef1bf4,
+/* 0x0673: i2c_start */
+ 0x7e00f840,
+ 0xf4000628,
+ 0x3c7e0d11,
+ 0x11f40006,
+ 0x2e0ef406,
+/* 0x0684: i2c_start_rep */
+ 0xf47e0003,
+ 0x01030005,
+ 0x00060e7e,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x06507e50,
+ 0x0464b600,
+/* 0x06af: i2c_start_send */
+ 0x031d11f4,
+ 0x060e7e00,
+ 0x13884e00,
+ 0x0000587e,
+ 0xf47e0003,
+ 0x884e0005,
+ 0x00587e13,
+/* 0x06c9: i2c_start_out */
+/* 0x06cb: i2c_stop */
+ 0x0300f800,
+ 0x05f47e00,
+ 0x7e000300,
+ 0x4e00060e,
+ 0x587e03e8,
+ 0x01030000,
+ 0x0005f47e,
+ 0x7e13884e,
+ 0x03000058,
+ 0x060e7e01,
+ 0x13884e00,
+ 0x0000587e,
+/* 0x06fa: i2c_bitw */
+ 0x0e7e00f8,
+ 0xe84e0006,
+ 0x00587e03,
0x0076bb00,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
- 0x557e50fc,
+ 0x507e50fc,
0x64b60006,
- 0x1d11f404,
-/* 0x06b4: i2c_start_send */
- 0x137e0003,
- 0x884e0006,
- 0x00587e13,
- 0x7e000300,
- 0x4e0005f9,
- 0x587e1388,
-/* 0x06ce: i2c_start_out */
- 0x00f80000,
-/* 0x06d0: i2c_stop */
- 0xf97e0003,
- 0x00030005,
- 0x0006137e,
- 0x7e03e84e,
+ 0x1711f404,
+ 0x7e13884e,
0x03000058,
- 0x05f97e01,
+ 0x05f47e00,
0x13884e00,
0x0000587e,
- 0x137e0103,
- 0x884e0006,
- 0x00587e13,
-/* 0x06ff: i2c_bitw */
- 0x7e00f800,
- 0x4e000613,
- 0x587e03e8,
- 0x76bb0000,
+/* 0x0738: i2c_bitw_out */
+/* 0x073a: i2c_bitr */
+ 0x010300f8,
+ 0x00060e7e,
+ 0x7e03e84e,
+ 0xbb000058,
+ 0x65b60076,
+ 0x9450f904,
+ 0x56bb0465,
+ 0xfd50bd02,
+ 0x50fc0475,
+ 0x0006507e,
+ 0xf40464b6,
+ 0x3c7e1a11,
+ 0x00030006,
+ 0x0005f47e,
+ 0x7e13884e,
+ 0xf0000058,
+ 0x31f4013c,
+/* 0x077d: i2c_bitr_done */
+/* 0x077f: i2c_get_byte */
+ 0x0500f801,
+/* 0x0783: i2c_get_byte_next */
+ 0xb6080400,
+ 0x76bb0154,
0x0465b600,
0x659450f9,
0x0256bb04,
0x75fd50bd,
0x7e50fc04,
- 0xb6000655,
+ 0xb600073a,
0x11f40464,
- 0x13884e17,
- 0x0000587e,
- 0xf97e0003,
- 0x884e0005,
- 0x00587e13,
-/* 0x073d: i2c_bitw_out */
-/* 0x073f: i2c_bitr */
- 0x0300f800,
- 0x06137e01,
- 0x03e84e00,
- 0x0000587e,
+ 0x0553fd2a,
+ 0xf40142b6,
+ 0x0103d81b,
0xb60076bb,
0x50f90465,
0xbb046594,
0x50bd0256,
0xfc0475fd,
- 0x06557e50,
+ 0x06fa7e50,
0x0464b600,
- 0x7e1a11f4,
- 0x03000641,
- 0x05f97e00,
- 0x13884e00,
- 0x0000587e,
- 0xf4013cf0,
-/* 0x0782: i2c_bitr_done */
- 0x00f80131,
-/* 0x0784: i2c_get_byte */
- 0x08040005,
-/* 0x0788: i2c_get_byte_next */
- 0xbb0154b6,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x00073f7e,
- 0xf40464b6,
- 0x53fd2a11,
- 0x0142b605,
- 0x03d81bf4,
- 0x0076bb01,
- 0xf90465b6,
- 0x04659450,
- 0xbd0256bb,
- 0x0475fd50,
- 0xff7e50fc,
- 0x64b60006,
-/* 0x07d1: i2c_get_byte_done */
-/* 0x07d3: i2c_put_byte */
- 0x0400f804,
-/* 0x07d5: i2c_put_byte_next */
- 0x0142b608,
- 0xbb3854ff,
+/* 0x07cc: i2c_get_byte_done */
+/* 0x07ce: i2c_put_byte */
+ 0x080400f8,
+/* 0x07d0: i2c_put_byte_next */
+ 0xff0142b6,
+ 0x76bb3854,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0x7e50fc04,
+ 0xb60006fa,
+ 0x11f40464,
+ 0x0046b034,
+ 0xbbd81bf4,
0x65b60076,
0x9450f904,
0x56bb0465,
0xfd50bd02,
0x50fc0475,
- 0x0006ff7e,
+ 0x00073a7e,
0xf40464b6,
- 0x46b03411,
- 0xd81bf400,
+ 0x76bb0f11,
+ 0x0136b000,
+ 0xf4061bf4,
+/* 0x0826: i2c_put_byte_done */
+ 0x00f80132,
+/* 0x0828: i2c_addr */
0xb60076bb,
0x50f90465,
0xbb046594,
0x50bd0256,
0xfc0475fd,
- 0x073f7e50,
+ 0x06737e50,
0x0464b600,
- 0xbb0f11f4,
- 0x36b00076,
- 0x061bf401,
-/* 0x082b: i2c_put_byte_done */
- 0xf80132f4,
-/* 0x082d: i2c_addr */
- 0x0076bb00,
+ 0xe72911f4,
+ 0xb6012ec3,
+ 0x53fd0134,
+ 0x0076bb05,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
- 0x787e50fc,
- 0x64b60006,
- 0x2911f404,
- 0x012ec3e7,
- 0xfd0134b6,
- 0x76bb0553,
- 0x0465b600,
- 0x659450f9,
- 0x0256bb04,
- 0x75fd50bd,
- 0x7e50fc04,
- 0xb60007d3,
-/* 0x0872: i2c_addr_done */
- 0x00f80464,
-/* 0x0874: i2c_acquire_addr */
- 0xb6f8cec7,
- 0xe0b705e4,
- 0x00f8d014,
-/* 0x0880: i2c_acquire */
- 0x0008747e,
+ 0xce7e50fc,
+ 0x64b60007,
+/* 0x086d: i2c_addr_done */
+/* 0x086f: i2c_acquire_addr */
+ 0xc700f804,
+ 0xe4b6f8ce,
+ 0x14e0b705,
+/* 0x087b: i2c_acquire */
+ 0x7e00f8d0,
+ 0x7e00086f,
+ 0xf0000004,
+ 0x2d7e03d9,
+ 0x00f80000,
+/* 0x088c: i2c_release */
+ 0x00086f7e,
0x0000047e,
- 0x7e03d9f0,
+ 0x7e03daf0,
0xf800002d,
-/* 0x0891: i2c_release */
- 0x08747e00,
- 0x00047e00,
- 0x03daf000,
- 0x00002d7e,
-/* 0x08a2: i2c_recv */
- 0x32f400f8,
- 0xf8c1c701,
- 0xb00214b6,
- 0x1ff52816,
- 0x13b80134,
- 0x98000cf4,
- 0x13b80032,
- 0x98000ccc,
- 0x31f40031,
- 0xf9d0f902,
- 0xd6d0f9e0,
- 0x10000000,
- 0xbb016792,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x0008807e,
- 0xfc0464b6,
- 0x00d6b0d0,
- 0x00b01bf5,
- 0x76bb0005,
+/* 0x089d: i2c_recv */
+ 0x0132f400,
+ 0xb6f8c1c7,
+ 0x16b00214,
+ 0x341ff528,
+ 0xf413b801,
+ 0x3298000c,
+ 0xcc13b800,
+ 0x3198000c,
+ 0x0231f400,
+ 0xe0f9d0f9,
+ 0x00d6d0f9,
+ 0x92100000,
+ 0x76bb0167,
0x0465b600,
0x659450f9,
0x0256bb04,
0x75fd50bd,
0x7e50fc04,
- 0xb600082d,
- 0x11f50464,
- 0xc5c700cc,
- 0x0076bbe0,
- 0xf90465b6,
- 0x04659450,
- 0xbd0256bb,
- 0x0475fd50,
- 0xd37e50fc,
- 0x64b60007,
- 0xa911f504,
- 0xbb010500,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x00082d7e,
- 0xf50464b6,
- 0xbb008711,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x0007847e,
- 0xf40464b6,
- 0x5bcb6711,
- 0x0076bbe0,
+ 0xb600087b,
+ 0xd0fc0464,
+ 0xf500d6b0,
+ 0x0500b01b,
+ 0x0076bb00,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
- 0xd07e50fc,
- 0x64b60006,
- 0xbd5bb204,
- 0x410ef474,
-/* 0x09a4: i2c_recv_not_rd08 */
- 0xf401d6b0,
- 0x00053b1b,
- 0x00082d7e,
- 0xc73211f4,
- 0xd37ee0c5,
- 0x11f40007,
- 0x7e000528,
- 0xf400082d,
- 0xb5c71f11,
- 0x07d37ee0,
- 0x1511f400,
- 0x0006d07e,
- 0xc5c774bd,
- 0x091bf408,
- 0xf40232f4,
-/* 0x09e2: i2c_recv_not_wr08 */
-/* 0x09e2: i2c_recv_done */
- 0xcec7030e,
- 0x08917ef8,
- 0xfce0fc00,
- 0x0912f4d0,
- 0x9f7e7cb2,
-/* 0x09f6: i2c_recv_exit */
- 0x00f80002,
-/* 0x09f8: i2c_init */
-/* 0x09fa: test_recv */
- 0x584100f8,
- 0x0011cf04,
- 0x400110b6,
- 0x01f60458,
- 0xde04bd00,
- 0x134fd900,
- 0x0001de7e,
-/* 0x0a16: test_init */
- 0x004e00f8,
- 0x01de7e08,
-/* 0x0a1f: idle_recv */
+ 0x287e50fc,
+ 0x64b60008,
+ 0xcc11f504,
+ 0xe0c5c700,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x07ce7e50,
+ 0x0464b600,
+ 0x00a911f5,
+ 0x76bb0105,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0x7e50fc04,
+ 0xb6000828,
+ 0x11f50464,
+ 0x76bb0087,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0x7e50fc04,
+ 0xb600077f,
+ 0x11f40464,
+ 0xe05bcb67,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x06cb7e50,
+ 0x0464b600,
+ 0x74bd5bb2,
+/* 0x099f: i2c_recv_not_rd08 */
+ 0xb0410ef4,
+ 0x1bf401d6,
+ 0x7e00053b,
+ 0xf4000828,
+ 0xc5c73211,
+ 0x07ce7ee0,
+ 0x2811f400,
+ 0x287e0005,
+ 0x11f40008,
+ 0xe0b5c71f,
+ 0x0007ce7e,
+ 0x7e1511f4,
+ 0xbd0006cb,
+ 0x08c5c774,
+ 0xf4091bf4,
+ 0x0ef40232,
+/* 0x09dd: i2c_recv_not_wr08 */
+/* 0x09dd: i2c_recv_done */
+ 0xf8cec703,
+ 0x00088c7e,
+ 0xd0fce0fc,
+ 0xb20912f4,
+ 0x029f7e7c,
+/* 0x09f1: i2c_recv_exit */
+/* 0x09f3: i2c_init */
0xf800f800,
-/* 0x0a21: idle */
- 0x0031f400,
- 0xcf045441,
- 0x10b60011,
- 0x04544001,
- 0xbd0001f6,
-/* 0x0a35: idle_loop */
- 0xf4580104,
-/* 0x0a3a: idle_proc */
-/* 0x0a3a: idle_proc_exec */
- 0x10f90232,
- 0xa87e1eb2,
- 0x10fc0002,
- 0xf40911f4,
- 0x0ef40231,
-/* 0x0a4d: idle_proc_next */
- 0x5810b6f0,
- 0x1bf41fa6,
- 0xe002f4e8,
- 0xf40028f4,
- 0x0000c60e,
+/* 0x09f5: test_recv */
+ 0x04584100,
+ 0xb60011cf,
+ 0x58400110,
+ 0x0001f604,
+ 0x00de04bd,
+ 0x7e134fd9,
+ 0xf80001de,
+/* 0x0a11: test_init */
+ 0x08004e00,
+ 0x0001de7e,
+/* 0x0a1a: idle_recv */
+ 0x00f800f8,
+/* 0x0a1c: idle */
+ 0x410031f4,
+ 0x11cf0454,
+ 0x0110b600,
+ 0xf6045440,
+ 0x04bd0001,
+/* 0x0a30: idle_loop */
+ 0x32f45801,
+/* 0x0a35: idle_proc */
+/* 0x0a35: idle_proc_exec */
+ 0xb210f902,
+ 0x02a87e1e,
+ 0xf410fc00,
+ 0x31f40911,
+ 0xf00ef402,
+/* 0x0a48: idle_proc_next */
+ 0xa65810b6,
+ 0xe81bf41f,
+ 0xf4e002f4,
+ 0x0ef40028,
+ 0x000000c6,
+ 0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x584d454d,
- 0x0000083a,
- 0x0000082c,
+ 0x00000833,
+ 0x00000825,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x46524550,
- 0x0000083e,
- 0x0000083c,
+ 0x00000837,
+ 0x00000835,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x5f433249,
- 0x00000c6e,
- 0x00000b11,
+ 0x00000c67,
+ 0x00000b0a,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x54534554,
- 0x00000c97,
- 0x00000c70,
+ 0x00000c90,
+ 0x00000c69,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x00000000,
0x454c4449,
- 0x00000ca3,
- 0x00000ca1,
+ 0x00000c9c,
+ 0x00000c9a,
0x00000000,
0x00000000,
0x00000000,
/* 0x037c: memx_func_next */
0x00000002,
0x00000000,
- 0x000005a0,
+ 0x0000059f,
0x00000003,
0x00000002,
- 0x00000632,
+ 0x0000062f,
0x00040004,
0x00000000,
- 0x0000064e,
+ 0x0000064b,
0x00010005,
0x00000000,
- 0x0000066b,
+ 0x00000668,
0x00010006,
0x00000000,
- 0x000005f0,
+ 0x000005ef,
0x00000007,
0x00000000,
- 0x00000676,
+ 0x00000673,
/* 0x03c4: memx_func_tail */
/* 0x03c4: memx_ts_start */
0x00000000,
0x67f102d7,
0x63f1fffc,
0x76fdffff,
- 0x0267f104,
- 0x0576fd00,
- 0x70f980f9,
- 0xe0fcd0fc,
- 0xf04021f4,
+ 0x0267f004,
+ 0xf90576fd,
+ 0xfc70f980,
+ 0xf4e0fcd0,
+ 0x67f04021,
+ 0xe007f104,
+ 0x0604b607,
+ 0xbd0006d0,
+/* 0x0581: memx_func_enter_wait */
+ 0xc067f104,
+ 0x0664b607,
+ 0xf00066cf,
+ 0x0bf40464,
+ 0x2c67f0f3,
+ 0xcf0664b6,
+ 0x06800066,
+/* 0x059f: memx_func_leave */
+ 0xf000f8f1,
+ 0x64b62c67,
+ 0x0066cf06,
+ 0xf0f20680,
0x07f10467,
- 0x04b607e0,
+ 0x04b607e4,
0x0006d006,
-/* 0x0582: memx_func_enter_wait */
+/* 0x05ba: memx_func_leave_wait */
0x67f104bd,
0x64b607c0,
0x0066cf06,
0xf40464f0,
- 0x67f0f30b,
- 0x0664b62c,
- 0x800066cf,
- 0x00f8f106,
-/* 0x05a0: memx_func_leave */
- 0xb62c67f0,
- 0x66cf0664,
- 0xf2068000,
- 0xf10467f0,
- 0xb607e407,
- 0x06d00604,
-/* 0x05bb: memx_func_leave_wait */
- 0xf104bd00,
- 0xb607c067,
- 0x66cf0664,
- 0x0464f000,
- 0xf1f31bf4,
- 0xb9161087,
- 0x21f4028e,
- 0x02d7b904,
- 0xffcc67f1,
- 0xffff63f1,
- 0xf90476fd,
- 0xfc70f980,
- 0xf4e0fcd0,
- 0x00f84021,
-/* 0x05f0: memx_func_wait_vblank */
- 0xb0001698,
- 0x0bf40066,
- 0x0166b013,
- 0xf4060bf4,
-/* 0x0602: memx_func_wait_vblank_head1 */
- 0x77f12e0e,
- 0x0ef40020,
-/* 0x0609: memx_func_wait_vblank_head0 */
- 0x0877f107,
-/* 0x060d: memx_func_wait_vblank_0 */
- 0xc467f100,
- 0x0664b607,
- 0xfd0066cf,
- 0x1bf40467,
-/* 0x061d: memx_func_wait_vblank_1 */
- 0xc467f1f3,
- 0x0664b607,
- 0xfd0066cf,
- 0x0bf40467,
-/* 0x062d: memx_func_wait_vblank_fini */
- 0x0410b6f3,
-/* 0x0632: memx_func_wr32 */
- 0x169800f8,
- 0x01159800,
- 0xf90810b6,
- 0xfc50f960,
- 0xf4e0fcd0,
- 0x42b64021,
- 0xe91bf402,
-/* 0x064e: memx_func_wait */
- 0x87f000f8,
- 0x0684b62c,
- 0x980088cf,
- 0x1d98001e,
- 0x021c9801,
- 0xb6031b98,
- 0x21f41010,
-/* 0x066b: memx_func_delay */
- 0x9800f8a3,
- 0x10b6001e,
- 0x7e21f404,
-/* 0x0676: memx_func_train */
- 0x57f100f8,
- 0x77f10003,
- 0x97f10000,
- 0x93f00000,
- 0x029eb970,
- 0xb90421f4,
- 0xe7f102d8,
- 0x21f42710,
-/* 0x0695: memx_func_train_loop_outer */
- 0x0158e07e,
- 0x0083f101,
- 0xe097f102,
- 0x1193f011,
- 0x80f990f9,
+ 0x87f1f31b,
+ 0x8eb91610,
+ 0x0421f402,
+ 0xf102d7b9,
+ 0xf1ffcc67,
+ 0xfdffff63,
+ 0x80f90476,
+ 0xd0fc70f9,
+ 0x21f4e0fc,
+/* 0x05ef: memx_func_wait_vblank */
+ 0x9800f840,
+ 0x66b00016,
+ 0x120bf400,
+ 0xf40166b0,
+ 0x0ef4060b,
+/* 0x0601: memx_func_wait_vblank_head1 */
+ 0x2077f02c,
+/* 0x0607: memx_func_wait_vblank_head0 */
+ 0xf0060ef4,
+/* 0x060a: memx_func_wait_vblank_0 */
+ 0x67f10877,
+ 0x64b607c4,
+ 0x0066cf06,
+ 0xf40467fd,
+/* 0x061a: memx_func_wait_vblank_1 */
+ 0x67f1f31b,
+ 0x64b607c4,
+ 0x0066cf06,
+ 0xf40467fd,
+/* 0x062a: memx_func_wait_vblank_fini */
+ 0x10b6f30b,
+/* 0x062f: memx_func_wr32 */
+ 0x9800f804,
+ 0x15980016,
+ 0x0810b601,
+ 0x50f960f9,
0xe0fcd0fc,
- 0xf94021f4,
- 0x0067f150,
-/* 0x06b5: memx_func_train_loop_inner */
- 0x1187f100,
- 0x9068ff11,
- 0xfd109894,
- 0x97f10589,
- 0x93f00720,
- 0xf990f910,
- 0xfcd0fc80,
- 0x4021f4e0,
- 0x008097f1,
- 0xb91093f0,
- 0x21f4029e,
- 0x02d8b904,
- 0xf92088c5,
+ 0xb64021f4,
+ 0x1bf40242,
+/* 0x064b: memx_func_wait */
+ 0xf000f8e9,
+ 0x84b62c87,
+ 0x0088cf06,
+ 0x98001e98,
+ 0x1c98011d,
+ 0x031b9802,
+ 0xf41010b6,
+ 0x00f8a321,
+/* 0x0668: memx_func_delay */
+ 0xb6001e98,
+ 0x21f40410,
+/* 0x0673: memx_func_train */
+ 0xf000f87e,
+ 0x77f00357,
+ 0x0097f100,
+ 0x7093f000,
+ 0xf4029eb9,
+ 0xd8b90421,
+ 0x10e7f102,
+ 0x7e21f427,
+/* 0x0690: memx_func_train_loop_outer */
+ 0x010158e0,
+ 0x020083f1,
+ 0x11e097f1,
+ 0xf91193f0,
+ 0xfc80f990,
+ 0xf4e0fcd0,
+ 0x50f94021,
+/* 0x06af: memx_func_train_loop_inner */
+ 0xf10067f0,
+ 0xff111187,
+ 0x98949068,
+ 0x0589fd10,
+ 0x072097f1,
+ 0xf91093f0,
0xfc80f990,
0xf4e0fcd0,
0x97f14021,
- 0x93f0053c,
- 0x0287f110,
- 0x0083f130,
- 0xf990f980,
+ 0x93f00080,
+ 0x029eb910,
+ 0xb90421f4,
+ 0x88c502d8,
+ 0xf990f920,
0xfcd0fc80,
0x4021f4e0,
- 0x0560e7f1,
- 0xf110e3f0,
- 0xf10000d7,
- 0x908000d3,
- 0xb7f100dc,
- 0xb3f08480,
- 0xa321f41e,
- 0x000057f1,
- 0xffff97f1,
- 0x830093f1,
-/* 0x0734: memx_func_train_loop_4x */
- 0x0080a7f1,
- 0xb910a3f0,
- 0x21f402ae,
- 0x02d8b904,
- 0xffdfb7f1,
- 0xffffb3f1,
- 0xf9048bfd,
- 0xfc80f9a0,
+ 0x053c97f1,
+ 0xf11093f0,
+ 0xf1300287,
+ 0xf9800083,
+ 0xfc80f990,
0xf4e0fcd0,
- 0xa7f14021,
- 0xa3f0053c,
- 0x0287f110,
- 0x0083f130,
- 0xf9a0f980,
- 0xfcd0fc80,
- 0x4021f4e0,
- 0x0560e7f1,
- 0xf110e3f0,
- 0xf10000d7,
- 0xb98000d3,
- 0xb7f102dc,
- 0xb3f02710,
- 0xa321f400,
- 0xf402eeb9,
- 0xddb90421,
- 0x949dff02,
+ 0xe7f14021,
+ 0xe3f00560,
+ 0x00d7f110,
+ 0x00d3f100,
+ 0x00dc9080,
+ 0x8480b7f1,
+ 0xf41eb3f0,
+ 0x57f0a321,
+ 0xff97f100,
+ 0x0093f1ff,
+/* 0x072d: memx_func_train_loop_4x */
+ 0x80a7f183,
+ 0x10a3f000,
+ 0xf402aeb9,
+ 0xd8b90421,
+ 0xdfb7f102,
+ 0xffb3f1ff,
+ 0x048bfdff,
+ 0x80f9a0f9,
+ 0xe0fcd0fc,
+ 0xf14021f4,
+ 0xf0053ca7,
+ 0x87f110a3,
+ 0x83f13002,
+ 0xa0f98000,
+ 0xd0fc80f9,
+ 0x21f4e0fc,
+ 0x60e7f140,
+ 0x10e3f005,
+ 0x0000d7f1,
+ 0x8000d3f1,
+ 0xf102dcb9,
+ 0xf02710b7,
+ 0x21f400b3,
+ 0x02eeb9a3,
+ 0xb90421f4,
+ 0x9dff02dd,
+ 0x0150b694,
+ 0xf4045670,
+ 0x7aa0921e,
+ 0xa9800bcc,
+ 0x0160b600,
+ 0x700470b6,
+ 0x1ef51066,
+ 0x50fcff01,
0x700150b6,
- 0x1ef40456,
- 0xcc7aa092,
- 0x00a9800b,
- 0xb60160b6,
- 0x66700470,
- 0x001ef510,
- 0xb650fcff,
- 0x56700150,
- 0xd41ef507,
-/* 0x07c7: memx_exec */
- 0xf900f8fe,
- 0xb9d0f9e0,
- 0xb2b902c1,
-/* 0x07d1: memx_exec_next */
- 0x00139802,
- 0xe70410b6,
- 0xe701f034,
- 0xb601e033,
- 0x30f00132,
- 0xde35980c,
- 0x12b855f9,
- 0xe41ef406,
- 0x98f10b98,
- 0xcbbbf20c,
- 0xc4b7f102,
- 0x06b4b607,
- 0xfc00bbcf,
- 0xf5e0fcd0,
+ 0x1ef50756,
+ 0x00f8fed6,
+/* 0x07c0: memx_exec */
+ 0xd0f9e0f9,
+ 0xb902c1b9,
+/* 0x07ca: memx_exec_next */
+ 0x139802b2,
+ 0x0410b600,
+ 0x01f034e7,
+ 0x01e033e7,
+ 0xf00132b6,
+ 0x35980c30,
+ 0xb855f9de,
+ 0x1ef40612,
+ 0xf10b98e4,
+ 0xbbf20c98,
+ 0xb7f102cb,
+ 0xb4b607c4,
+ 0x00bbcf06,
+ 0xe0fcd0fc,
+ 0x033621f5,
+/* 0x0806: memx_info */
+ 0xc67000f8,
+ 0x0e0bf401,
+/* 0x080c: memx_info_data */
+ 0x03ccc7f1,
+ 0x0800b7f1,
+/* 0x0817: memx_info_train */
+ 0xf10b0ef4,
+ 0xf10bccc7,
+/* 0x081f: memx_info_send */
+ 0xf50100b7,
0xf8033621,
-/* 0x080d: memx_info */
- 0x01c67000,
-/* 0x0813: memx_info_data */
- 0xf10e0bf4,
- 0xf103ccc7,
- 0xf40800b7,
-/* 0x081e: memx_info_train */
- 0xc7f10b0e,
- 0xb7f10bcc,
-/* 0x0826: memx_info_send */
- 0x21f50100,
- 0x00f80336,
-/* 0x082c: memx_recv */
- 0xf401d6b0,
- 0xd6b0980b,
- 0xd80bf400,
-/* 0x083a: memx_init */
- 0x00f800f8,
-/* 0x083c: perf_recv */
-/* 0x083e: perf_init */
- 0x00f800f8,
-/* 0x0840: i2c_drive_scl */
- 0xf40036b0,
- 0x07f1110b,
- 0x04b607e0,
- 0x0001d006,
- 0x00f804bd,
-/* 0x0854: i2c_drive_scl_lo */
- 0x07e407f1,
- 0xd00604b6,
- 0x04bd0001,
-/* 0x0862: i2c_drive_sda */
- 0x36b000f8,
- 0x110bf400,
- 0x07e007f1,
- 0xd00604b6,
- 0x04bd0002,
-/* 0x0876: i2c_drive_sda_lo */
- 0x07f100f8,
- 0x04b607e4,
- 0x0002d006,
- 0x00f804bd,
-/* 0x0884: i2c_sense_scl */
- 0xf10132f4,
- 0xb607c437,
- 0x33cf0634,
- 0x0431fd00,
- 0xf4060bf4,
-/* 0x089a: i2c_sense_scl_done */
- 0x00f80131,
-/* 0x089c: i2c_sense_sda */
- 0xf10132f4,
- 0xb607c437,
- 0x33cf0634,
- 0x0432fd00,
- 0xf4060bf4,
-/* 0x08b2: i2c_sense_sda_done */
- 0x00f80131,
-/* 0x08b4: i2c_raise_scl */
- 0x47f140f9,
- 0x37f00898,
- 0x4021f501,
-/* 0x08c1: i2c_raise_scl_wait */
+/* 0x0825: memx_recv */
+ 0x01d6b000,
+ 0xb0980bf4,
+ 0x0bf400d6,
+/* 0x0833: memx_init */
+ 0xf800f8d8,
+/* 0x0835: perf_recv */
+/* 0x0837: perf_init */
+ 0xf800f800,
+/* 0x0839: i2c_drive_scl */
+ 0x0036b000,
+ 0xf1110bf4,
+ 0xb607e007,
+ 0x01d00604,
+ 0xf804bd00,
+/* 0x084d: i2c_drive_scl_lo */
+ 0xe407f100,
+ 0x0604b607,
+ 0xbd0001d0,
+/* 0x085b: i2c_drive_sda */
+ 0xb000f804,
+ 0x0bf40036,
+ 0xe007f111,
+ 0x0604b607,
+ 0xbd0002d0,
+/* 0x086f: i2c_drive_sda_lo */
+ 0xf100f804,
+ 0xb607e407,
+ 0x02d00604,
+ 0xf804bd00,
+/* 0x087d: i2c_sense_scl */
+ 0x0132f400,
+ 0x07c437f1,
+ 0xcf0634b6,
+ 0x31fd0033,
+ 0x060bf404,
+/* 0x0893: i2c_sense_scl_done */
+ 0xf80131f4,
+/* 0x0895: i2c_sense_sda */
+ 0x0132f400,
+ 0x07c437f1,
+ 0xcf0634b6,
+ 0x32fd0033,
+ 0x060bf404,
+/* 0x08ab: i2c_sense_sda_done */
+ 0xf80131f4,
+/* 0x08ad: i2c_raise_scl */
+ 0xf140f900,
+ 0xf0089847,
+ 0x21f50137,
+/* 0x08ba: i2c_raise_scl_wait */
+ 0xe7f10839,
+ 0x21f403e8,
+ 0x7d21f57e,
+ 0x0901f408,
+ 0xf40142b6,
+/* 0x08ce: i2c_raise_scl_done */
+ 0x40fcef1b,
+/* 0x08d2: i2c_start */
+ 0x21f500f8,
+ 0x11f4087d,
+ 0x9521f50d,
+ 0x0611f408,
+/* 0x08e3: i2c_start_rep */
+ 0xf0300ef4,
+ 0x21f50037,
+ 0x37f00839,
+ 0x5b21f501,
+ 0x0076bb08,
+ 0xf90465b6,
+ 0x04659450,
+ 0xbd0256bb,
+ 0x0475fd50,
+ 0x21f550fc,
+ 0x64b608ad,
+ 0x1f11f404,
+/* 0x0910: i2c_start_send */
+ 0xf50037f0,
+ 0xf1085b21,
+ 0xf41388e7,
+ 0x37f07e21,
+ 0x3921f500,
+ 0x88e7f108,
+ 0x7e21f413,
+/* 0x092c: i2c_start_out */
+/* 0x092e: i2c_stop */
+ 0x37f000f8,
+ 0x3921f500,
+ 0x0037f008,
+ 0x085b21f5,
+ 0x03e8e7f1,
+ 0xf07e21f4,
+ 0x21f50137,
+ 0xe7f10839,
+ 0x21f41388,
+ 0x0137f07e,
+ 0x085b21f5,
+ 0x1388e7f1,
+ 0xf87e21f4,
+/* 0x0961: i2c_bitw */
+ 0x5b21f500,
0xe8e7f108,
0x7e21f403,
- 0x088421f5,
- 0xb60901f4,
- 0x1bf40142,
-/* 0x08d5: i2c_raise_scl_done */
- 0xf840fcef,
-/* 0x08d9: i2c_start */
- 0x8421f500,
- 0x0d11f408,
- 0x089c21f5,
- 0xf40611f4,
-/* 0x08ea: i2c_start_rep */
- 0x37f0300e,
- 0x4021f500,
- 0x0137f008,
- 0x086221f5,
0xb60076bb,
0x50f90465,
0xbb046594,
0x50bd0256,
0xfc0475fd,
- 0xb421f550,
+ 0xad21f550,
0x0464b608,
-/* 0x0917: i2c_start_send */
- 0xf01f11f4,
- 0x21f50037,
- 0xe7f10862,
- 0x21f41388,
- 0x0037f07e,
- 0x084021f5,
- 0x1388e7f1,
-/* 0x0933: i2c_start_out */
- 0xf87e21f4,
-/* 0x0935: i2c_stop */
- 0x0037f000,
- 0x084021f5,
- 0xf50037f0,
- 0xf1086221,
- 0xf403e8e7,
+ 0xf11811f4,
+ 0xf41388e7,
0x37f07e21,
- 0x4021f501,
+ 0x3921f500,
0x88e7f108,
0x7e21f413,
- 0xf50137f0,
- 0xf1086221,
- 0xf41388e7,
- 0x00f87e21,
-/* 0x0968: i2c_bitw */
- 0x086221f5,
- 0x03e8e7f1,
- 0xbb7e21f4,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x08b421f5,
- 0xf40464b6,
- 0xe7f11811,
+/* 0x09a0: i2c_bitw_out */
+/* 0x09a2: i2c_bitr */
+ 0x37f000f8,
+ 0x5b21f501,
+ 0xe8e7f108,
+ 0x7e21f403,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0xad21f550,
+ 0x0464b608,
+ 0xf51b11f4,
+ 0xf0089521,
+ 0x21f50037,
+ 0xe7f10839,
0x21f41388,
- 0x0037f07e,
- 0x084021f5,
- 0x1388e7f1,
-/* 0x09a7: i2c_bitw_out */
- 0xf87e21f4,
-/* 0x09a9: i2c_bitr */
- 0x0137f000,
- 0x086221f5,
- 0x03e8e7f1,
- 0xbb7e21f4,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x08b421f5,
- 0xf40464b6,
- 0x21f51b11,
- 0x37f0089c,
- 0x4021f500,
- 0x88e7f108,
- 0x7e21f413,
- 0xf4013cf0,
-/* 0x09ee: i2c_bitr_done */
- 0x00f80131,
-/* 0x09f0: i2c_get_byte */
- 0xf00057f0,
-/* 0x09f6: i2c_get_byte_next */
- 0x54b60847,
+ 0x013cf07e,
+/* 0x09e7: i2c_bitr_done */
+ 0xf80131f4,
+/* 0x09e9: i2c_get_byte */
+ 0x0057f000,
+/* 0x09ef: i2c_get_byte_next */
+ 0xb60847f0,
+ 0x76bb0154,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0xf550fc04,
+ 0xb609a221,
+ 0x11f40464,
+ 0x0553fd2b,
+ 0xf40142b6,
+ 0x37f0d81b,
0x0076bb01,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
0x21f550fc,
- 0x64b609a9,
- 0x2b11f404,
- 0xb60553fd,
- 0x1bf40142,
- 0x0137f0d8,
- 0xb60076bb,
- 0x50f90465,
- 0xbb046594,
- 0x50bd0256,
- 0xfc0475fd,
- 0x6821f550,
- 0x0464b609,
-/* 0x0a40: i2c_get_byte_done */
-/* 0x0a42: i2c_put_byte */
- 0x47f000f8,
-/* 0x0a45: i2c_put_byte_next */
- 0x0142b608,
- 0xbb3854ff,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x096821f5,
- 0xf40464b6,
- 0x46b03411,
- 0xd81bf400,
+ 0x64b60961,
+/* 0x0a39: i2c_get_byte_done */
+/* 0x0a3b: i2c_put_byte */
+ 0xf000f804,
+/* 0x0a3e: i2c_put_byte_next */
+ 0x42b60847,
+ 0x3854ff01,
0xb60076bb,
0x50f90465,
0xbb046594,
0x50bd0256,
0xfc0475fd,
- 0xa921f550,
+ 0x6121f550,
0x0464b609,
- 0xbb0f11f4,
- 0x36b00076,
- 0x061bf401,
-/* 0x0a9b: i2c_put_byte_done */
- 0xf80132f4,
-/* 0x0a9d: i2c_addr */
- 0x0076bb00,
+ 0xb03411f4,
+ 0x1bf40046,
+ 0x0076bbd8,
0xf90465b6,
0x04659450,
0xbd0256bb,
0x0475fd50,
0x21f550fc,
- 0x64b608d9,
- 0x2911f404,
- 0x012ec3e7,
- 0xfd0134b6,
- 0x76bb0553,
+ 0x64b609a2,
+ 0x0f11f404,
+ 0xb00076bb,
+ 0x1bf40136,
+ 0x0132f406,
+/* 0x0a94: i2c_put_byte_done */
+/* 0x0a96: i2c_addr */
+ 0x76bb00f8,
0x0465b600,
0x659450f9,
0x0256bb04,
0x75fd50bd,
0xf550fc04,
- 0xb60a4221,
-/* 0x0ae2: i2c_addr_done */
- 0x00f80464,
-/* 0x0ae4: i2c_acquire_addr */
- 0xb6f8cec7,
- 0xe0b702e4,
- 0xee980d1c,
-/* 0x0af3: i2c_acquire */
- 0xf500f800,
- 0xf40ae421,
- 0xd9f00421,
- 0x4021f403,
-/* 0x0b02: i2c_release */
- 0x21f500f8,
- 0x21f40ae4,
- 0x03daf004,
- 0xf84021f4,
-/* 0x0b11: i2c_recv */
- 0x0132f400,
- 0xb6f8c1c7,
- 0x16b00214,
- 0x3a1ff528,
- 0xf413a001,
- 0x0032980c,
- 0x0ccc13a0,
- 0xf4003198,
- 0xd0f90231,
- 0xd0f9e0f9,
- 0x000067f1,
- 0x100063f1,
- 0xbb016792,
+ 0xb608d221,
+ 0x11f40464,
+ 0x2ec3e729,
+ 0x0134b601,
+ 0xbb0553fd,
0x65b60076,
0x9450f904,
0x56bb0465,
0xfd50bd02,
0x50fc0475,
- 0x0af321f5,
- 0xfc0464b6,
- 0x00d6b0d0,
- 0x00b31bf5,
- 0xbb0057f0,
+ 0x0a3b21f5,
+/* 0x0adb: i2c_addr_done */
+ 0xf80464b6,
+/* 0x0add: i2c_acquire_addr */
+ 0xf8cec700,
+ 0xb702e4b6,
+ 0x980d1ce0,
+ 0x00f800ee,
+/* 0x0aec: i2c_acquire */
+ 0x0add21f5,
+ 0xf00421f4,
+ 0x21f403d9,
+/* 0x0afb: i2c_release */
+ 0xf500f840,
+ 0xf40add21,
+ 0xdaf00421,
+ 0x4021f403,
+/* 0x0b0a: i2c_recv */
+ 0x32f400f8,
+ 0xf8c1c701,
+ 0xb00214b6,
+ 0x1ff52816,
+ 0x13a0013a,
+ 0x32980cf4,
+ 0xcc13a000,
+ 0x0031980c,
+ 0xf90231f4,
+ 0xf9e0f9d0,
+ 0x0067f1d0,
+ 0x0063f100,
+ 0x01679210,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0xec21f550,
+ 0x0464b60a,
+ 0xd6b0d0fc,
+ 0xb31bf500,
+ 0x0057f000,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x9621f550,
+ 0x0464b60a,
+ 0x00d011f5,
+ 0xbbe0c5c7,
0x65b60076,
0x9450f904,
0x56bb0465,
0xfd50bd02,
0x50fc0475,
- 0x0a9d21f5,
+ 0x0a3b21f5,
0xf50464b6,
- 0xc700d011,
- 0x76bbe0c5,
+ 0xf000ad11,
+ 0x76bb0157,
0x0465b600,
0x659450f9,
0x0256bb04,
0x75fd50bd,
0xf550fc04,
- 0xb60a4221,
+ 0xb60a9621,
0x11f50464,
- 0x57f000ad,
- 0x0076bb01,
- 0xf90465b6,
- 0x04659450,
- 0xbd0256bb,
- 0x0475fd50,
- 0x21f550fc,
- 0x64b60a9d,
- 0x8a11f504,
- 0x0076bb00,
- 0xf90465b6,
- 0x04659450,
- 0xbd0256bb,
- 0x0475fd50,
- 0x21f550fc,
- 0x64b609f0,
- 0x6a11f404,
- 0xbbe05bcb,
- 0x65b60076,
- 0x9450f904,
- 0x56bb0465,
- 0xfd50bd02,
- 0x50fc0475,
- 0x093521f5,
- 0xb90464b6,
- 0x74bd025b,
-/* 0x0c17: i2c_recv_not_rd08 */
- 0xb0430ef4,
- 0x1bf401d6,
- 0x0057f03d,
- 0x0a9d21f5,
- 0xc73311f4,
- 0x21f5e0c5,
- 0x11f40a42,
- 0x0057f029,
- 0x0a9d21f5,
- 0xc71f11f4,
- 0x21f5e0b5,
- 0x11f40a42,
- 0x3521f515,
- 0xc774bd09,
- 0x1bf408c5,
- 0x0232f409,
-/* 0x0c57: i2c_recv_not_wr08 */
-/* 0x0c57: i2c_recv_done */
- 0xc7030ef4,
- 0x21f5f8ce,
- 0xe0fc0b02,
- 0x12f4d0fc,
- 0x027cb90a,
- 0x033621f5,
-/* 0x0c6c: i2c_recv_exit */
-/* 0x0c6e: i2c_init */
+ 0x76bb008a,
+ 0x0465b600,
+ 0x659450f9,
+ 0x0256bb04,
+ 0x75fd50bd,
+ 0xf550fc04,
+ 0xb609e921,
+ 0x11f40464,
+ 0xe05bcb6a,
+ 0xb60076bb,
+ 0x50f90465,
+ 0xbb046594,
+ 0x50bd0256,
+ 0xfc0475fd,
+ 0x2e21f550,
+ 0x0464b609,
+ 0xbd025bb9,
+ 0x430ef474,
+/* 0x0c10: i2c_recv_not_rd08 */
+ 0xf401d6b0,
+ 0x57f03d1b,
+ 0x9621f500,
+ 0x3311f40a,
+ 0xf5e0c5c7,
+ 0xf40a3b21,
+ 0x57f02911,
+ 0x9621f500,
+ 0x1f11f40a,
+ 0xf5e0b5c7,
+ 0xf40a3b21,
+ 0x21f51511,
+ 0x74bd092e,
+ 0xf408c5c7,
+ 0x32f4091b,
+ 0x030ef402,
+/* 0x0c50: i2c_recv_not_wr08 */
+/* 0x0c50: i2c_recv_done */
+ 0xf5f8cec7,
+ 0xfc0afb21,
+ 0xf4d0fce0,
+ 0x7cb90a12,
+ 0x3621f502,
+/* 0x0c65: i2c_recv_exit */
+/* 0x0c67: i2c_init */
+ 0xf800f803,
+/* 0x0c69: test_recv */
+ 0xd817f100,
+ 0x0614b605,
+ 0xb60011cf,
+ 0x07f10110,
+ 0x04b605d8,
+ 0x0001d006,
+ 0xe7f104bd,
+ 0xe3f1d900,
+ 0x21f5134f,
+ 0x00f80256,
+/* 0x0c90: test_init */
+ 0x0800e7f1,
+ 0x025621f5,
+/* 0x0c9a: idle_recv */
0x00f800f8,
-/* 0x0c70: test_recv */
- 0x05d817f1,
- 0xcf0614b6,
- 0x10b60011,
- 0xd807f101,
- 0x0604b605,
- 0xbd0001d0,
- 0x00e7f104,
- 0x4fe3f1d9,
- 0x5621f513,
-/* 0x0c97: test_init */
- 0xf100f802,
- 0xf50800e7,
- 0xf8025621,
-/* 0x0ca1: idle_recv */
-/* 0x0ca3: idle */
- 0xf400f800,
- 0x17f10031,
- 0x14b605d4,
- 0x0011cf06,
- 0xf10110b6,
- 0xb605d407,
- 0x01d00604,
-/* 0x0cbf: idle_loop */
- 0xf004bd00,
- 0x32f45817,
-/* 0x0cc5: idle_proc */
-/* 0x0cc5: idle_proc_exec */
- 0xb910f902,
- 0x21f5021e,
- 0x10fc033f,
- 0xf40911f4,
- 0x0ef40231,
-/* 0x0cd9: idle_proc_next */
- 0x5810b6ef,
- 0xf4061fb8,
- 0x02f4e61b,
- 0x0028f4dd,
- 0x00bb0ef4,
+/* 0x0c9c: idle */
+ 0xf10031f4,
+ 0xb605d417,
+ 0x11cf0614,
+ 0x0110b600,
+ 0x05d407f1,
+ 0xd00604b6,
+ 0x04bd0001,
+/* 0x0cb8: idle_loop */
+ 0xf45817f0,
+/* 0x0cbe: idle_proc */
+/* 0x0cbe: idle_proc_exec */
+ 0x10f90232,
+ 0xf5021eb9,
+ 0xfc033f21,
+ 0x0911f410,
+ 0xf40231f4,
+/* 0x0cd2: idle_proc_next */
+ 0x10b6ef0e,
+ 0x061fb858,
+ 0xf4e61bf4,
+ 0x28f4dd02,
+ 0xbb0ef400,
+ 0x00000000,
+ 0x00000000,
0x00000000,
0x00000000,
0x00000000,
// $r0 - zero
memx_func_enter:
#if NVKM_PPWR_CHIPSET == GT215
- movw $r8 0x1610
+ mov $r8 0x1610
nv_rd32($r7, $r8)
imm32($r6, 0xfffffffc)
and $r7 $r6
- movw $r6 0x2
+ mov $r6 0x2
or $r7 $r6
nv_wr32($r8, $r7)
#else
- movw $r6 0x001620
+ mov $r6 0x001620
imm32($r7, ~0x00000aa2);
nv_rd32($r8, $r6)
and $r8 $r7
and $r8 $r7
nv_wr32($r6, $r8)
- movw $r6 0x0026f0
+ mov $r6 0x0026f0
nv_rd32($r8, $r6)
and $r8 $r7
nv_wr32($r6, $r8)
bra nz #memx_func_leave_wait
#if NVKM_PPWR_CHIPSET == GT215
- movw $r8 0x1610
+ mov $r8 0x1610
nv_rd32($r7, $r8)
imm32($r6, 0xffffffcc)
and $r7 $r6
nv_wr32($r8, $r7)
#else
- movw $r6 0x0026f0
+ mov $r6 0x0026f0
imm32($r7, 0x00000001)
nv_rd32($r8, $r6)
or $r8 $r7
nv_wr32($r6, $r8)
- movw $r6 0x001620
+ mov $r6 0x001620
nv_rd32($r8, $r6)
or $r8 $r7
nv_wr32($r6, $r8)
bra #memx_func_wait_vblank_fini
memx_func_wait_vblank_head1:
- movw $r7 0x20
+ mov $r7 0x20
bra #memx_func_wait_vblank_0
memx_func_wait_vblank_head0:
- movw $r7 0x8
+ mov $r7 0x8
memx_func_wait_vblank_0:
nv_iord($r6, NV_PPWR_INPUT)
// $r5 - outer loop counter
// $r6 - inner loop counter
// $r7 - entry counter (#memx_train_head + $r7)
- movw $r5 0x3
- movw $r7 0x0
+ mov $r5 0x3
+ mov $r7 0x0
// Read random memory to wake up... things
imm32($r9, 0x700000)
nv_rd32($r8,$r9)
- movw $r14 0x2710
+ mov $r14 0x2710
call(nsec)
memx_func_train_loop_outer:
nv_wr32($r9, $r8)
push $r5
- movw $r6 0x0
+ mov $r6 0x0
memx_func_train_loop_inner:
- movw $r8 0x1111
+ mov $r8 0x1111
mulu $r9 $r6 $r8
shl b32 $r8 $r9 0x10
or $r8 $r9
// $r5 - inner inner loop counter
// $r9 - result
- movw $r5 0
+ mov $r5 0
imm32($r9, 0x8300ffff)
memx_func_train_loop_4x:
imm32($r10, 0x100080)
nvkm-y += nvkm/subdev/secboot/acr_r361.o
nvkm-y += nvkm/subdev/secboot/acr_r364.o
nvkm-y += nvkm/subdev/secboot/acr_r367.o
+nvkm-y += nvkm/subdev/secboot/acr_r370.o
nvkm-y += nvkm/subdev/secboot/acr_r375.o
nvkm-y += nvkm/subdev/secboot/gm200.o
nvkm-y += nvkm/subdev/secboot/gm20b.o
nvkm-y += nvkm/subdev/secboot/gp102.o
+nvkm-y += nvkm/subdev/secboot/gp108.o
nvkm-y += nvkm/subdev/secboot/gp10b.o
struct nvkm_acr *acr_r361_new(unsigned long);
struct nvkm_acr *acr_r364_new(unsigned long);
struct nvkm_acr *acr_r367_new(enum nvkm_secboot_falcon, unsigned long);
+struct nvkm_acr *acr_r370_new(enum nvkm_secboot_falcon, unsigned long);
struct nvkm_acr *acr_r375_new(enum nvkm_secboot_falcon, unsigned long);
#endif
--- /dev/null
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ *
+ * 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 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.
+ */
+
+#include "acr_r370.h"
+#include "acr_r367.h"
+
+#include <core/msgqueue.h>
+#include <engine/falcon.h>
+#include <engine/sec2.h>
+
+static void
+acr_r370_generate_flcn_bl_desc(const struct nvkm_acr *acr,
+ const struct ls_ucode_img *img, u64 wpr_addr,
+ void *_desc)
+{
+ struct acr_r370_flcn_bl_desc *desc = _desc;
+ const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
+ u64 base, addr_code, addr_data;
+
+ base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
+ addr_code = base + pdesc->app_resident_code_offset;
+ addr_data = base + pdesc->app_resident_data_offset;
+
+ desc->ctx_dma = FALCON_DMAIDX_UCODE;
+ desc->code_dma_base = u64_to_flcn64(addr_code);
+ desc->non_sec_code_off = pdesc->app_resident_code_offset;
+ desc->non_sec_code_size = pdesc->app_resident_code_size;
+ desc->code_entry_point = pdesc->app_imem_entry;
+ desc->data_dma_base = u64_to_flcn64(addr_data);
+ desc->data_size = pdesc->app_resident_data_size;
+}
+
+const struct acr_r352_ls_func
+acr_r370_ls_fecs_func = {
+ .load = acr_ls_ucode_load_fecs,
+ .generate_bl_desc = acr_r370_generate_flcn_bl_desc,
+ .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+};
+
+const struct acr_r352_ls_func
+acr_r370_ls_gpccs_func = {
+ .load = acr_ls_ucode_load_gpccs,
+ .generate_bl_desc = acr_r370_generate_flcn_bl_desc,
+ .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+ /* GPCCS will be loaded using PRI */
+ .lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
+};
+
+static void
+acr_r370_generate_sec2_bl_desc(const struct nvkm_acr *acr,
+ const struct ls_ucode_img *img, u64 wpr_addr,
+ void *_desc)
+{
+ const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
+ const struct nvkm_sec2 *sec = acr->subdev->device->sec2;
+ struct acr_r370_flcn_bl_desc *desc = _desc;
+ u64 base, addr_code, addr_data;
+ u32 addr_args;
+
+ base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
+ /* For some reason we should not add app_resident_code_offset here */
+ addr_code = base;
+ addr_data = base + pdesc->app_resident_data_offset;
+ addr_args = sec->falcon->data.limit;
+ addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
+
+ desc->ctx_dma = FALCON_SEC2_DMAIDX_UCODE;
+ desc->code_dma_base = u64_to_flcn64(addr_code);
+ desc->non_sec_code_off = pdesc->app_resident_code_offset;
+ desc->non_sec_code_size = pdesc->app_resident_code_size;
+ desc->code_entry_point = pdesc->app_imem_entry;
+ desc->data_dma_base = u64_to_flcn64(addr_data);
+ desc->data_size = pdesc->app_resident_data_size;
+ desc->argc = 1;
+ /* args are stored at the beginning of EMEM */
+ desc->argv = 0x01000000;
+}
+
+const struct acr_r352_ls_func
+acr_r370_ls_sec2_func = {
+ .load = acr_ls_ucode_load_sec2,
+ .generate_bl_desc = acr_r370_generate_sec2_bl_desc,
+ .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+ .post_run = acr_ls_sec2_post_run,
+};
+
+void
+acr_r370_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
+ u64 offset)
+{
+ struct acr_r370_flcn_bl_desc *bl_desc = _bl_desc;
+
+ bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
+ bl_desc->non_sec_code_off = hdr->non_sec_code_off;
+ bl_desc->non_sec_code_size = hdr->non_sec_code_size;
+ bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
+ bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
+ bl_desc->code_entry_point = 0;
+ bl_desc->code_dma_base = u64_to_flcn64(offset);
+ bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
+ bl_desc->data_size = hdr->data_size;
+}
+
+const struct acr_r352_func
+acr_r370_func = {
+ .fixup_hs_desc = acr_r367_fixup_hs_desc,
+ .generate_hs_bl_desc = acr_r370_generate_hs_bl_desc,
+ .hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
+ .shadow_blob = true,
+ .ls_ucode_img_load = acr_r367_ls_ucode_img_load,
+ .ls_fill_headers = acr_r367_ls_fill_headers,
+ .ls_write_wpr = acr_r367_ls_write_wpr,
+ .ls_func = {
+ [NVKM_SECBOOT_FALCON_SEC2] = &acr_r370_ls_sec2_func,
+ [NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func,
+ [NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func,
+ },
+};
+
+struct nvkm_acr *
+acr_r370_new(enum nvkm_secboot_falcon boot_falcon,
+ unsigned long managed_falcons)
+{
+ return acr_r352_new_(&acr_r370_func, boot_falcon, managed_falcons);
+}
--- /dev/null
+/*
+ * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * 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 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 __NVKM_SECBOOT_ACR_R370_H__
+#define __NVKM_SECBOOT_ACR_R370_H__
+
+#include "priv.h"
+struct hsf_load_header;
+
+/* Same as acr_r361_flcn_bl_desc, plus argc/argv */
+struct acr_r370_flcn_bl_desc {
+ u32 reserved[4];
+ u32 signature[4];
+ u32 ctx_dma;
+ struct flcn_u64 code_dma_base;
+ u32 non_sec_code_off;
+ u32 non_sec_code_size;
+ u32 sec_code_off;
+ u32 sec_code_size;
+ u32 code_entry_point;
+ struct flcn_u64 data_dma_base;
+ u32 data_size;
+ u32 argc;
+ u32 argv;
+};
+
+void acr_r370_generate_hs_bl_desc(const struct hsf_load_header *, void *, u64);
+extern const struct acr_r352_ls_func acr_r370_ls_fecs_func;
+extern const struct acr_r352_ls_func acr_r370_ls_gpccs_func;
+#endif
* DEALINGS IN THE SOFTWARE.
*/
+#include "acr_r370.h"
#include "acr_r367.h"
-#include <engine/falcon.h>
#include <core/msgqueue.h>
#include <subdev/pmu.h>
-/*
- * r375 ACR: similar to r367, but with a unified bootloader descriptor
- * structure for GR and PMU falcons.
- */
-
-/* Same as acr_r361_flcn_bl_desc, plus argc/argv */
-struct acr_r375_flcn_bl_desc {
- u32 reserved[4];
- u32 signature[4];
- u32 ctx_dma;
- struct flcn_u64 code_dma_base;
- u32 non_sec_code_off;
- u32 non_sec_code_size;
- u32 sec_code_off;
- u32 sec_code_size;
- u32 code_entry_point;
- struct flcn_u64 data_dma_base;
- u32 data_size;
- u32 argc;
- u32 argv;
-};
-
-static void
-acr_r375_generate_flcn_bl_desc(const struct nvkm_acr *acr,
- const struct ls_ucode_img *img, u64 wpr_addr,
- void *_desc)
-{
- struct acr_r375_flcn_bl_desc *desc = _desc;
- const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
- u64 base, addr_code, addr_data;
-
- base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
- addr_code = base + pdesc->app_resident_code_offset;
- addr_data = base + pdesc->app_resident_data_offset;
-
- desc->ctx_dma = FALCON_DMAIDX_UCODE;
- desc->code_dma_base = u64_to_flcn64(addr_code);
- desc->non_sec_code_off = pdesc->app_resident_code_offset;
- desc->non_sec_code_size = pdesc->app_resident_code_size;
- desc->code_entry_point = pdesc->app_imem_entry;
- desc->data_dma_base = u64_to_flcn64(addr_data);
- desc->data_size = pdesc->app_resident_data_size;
-}
-
-static void
-acr_r375_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
- u64 offset)
-{
- struct acr_r375_flcn_bl_desc *bl_desc = _bl_desc;
-
- bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
- bl_desc->non_sec_code_off = hdr->non_sec_code_off;
- bl_desc->non_sec_code_size = hdr->non_sec_code_size;
- bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
- bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
- bl_desc->code_entry_point = 0;
- bl_desc->code_dma_base = u64_to_flcn64(offset);
- bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
- bl_desc->data_size = hdr->data_size;
-}
-
-const struct acr_r352_ls_func
-acr_r375_ls_fecs_func = {
- .load = acr_ls_ucode_load_fecs,
- .generate_bl_desc = acr_r375_generate_flcn_bl_desc,
- .bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r375_ls_gpccs_func = {
- .load = acr_ls_ucode_load_gpccs,
- .generate_bl_desc = acr_r375_generate_flcn_bl_desc,
- .bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
- /* GPCCS will be loaded using PRI */
- .lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
-};
-
-
static void
acr_r375_generate_pmu_bl_desc(const struct nvkm_acr *acr,
const struct ls_ucode_img *img, u64 wpr_addr,
{
const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
const struct nvkm_pmu *pmu = acr->subdev->device->pmu;
- struct acr_r375_flcn_bl_desc *desc = _desc;
+ struct acr_r370_flcn_bl_desc *desc = _desc;
u64 base, addr_code, addr_data;
u32 addr_args;
acr_r375_ls_pmu_func = {
.load = acr_ls_ucode_load_pmu,
.generate_bl_desc = acr_r375_generate_pmu_bl_desc,
- .bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
+ .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
.post_run = acr_ls_pmu_post_run,
};
-
const struct acr_r352_func
acr_r375_func = {
.fixup_hs_desc = acr_r367_fixup_hs_desc,
- .generate_hs_bl_desc = acr_r375_generate_hs_bl_desc,
- .hs_bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc),
+ .generate_hs_bl_desc = acr_r370_generate_hs_bl_desc,
+ .hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
.shadow_blob = true,
.ls_ucode_img_load = acr_r367_ls_ucode_img_load,
.ls_fill_headers = acr_r367_ls_fill_headers,
.ls_write_wpr = acr_r367_ls_write_wpr,
.ls_func = {
- [NVKM_SECBOOT_FALCON_FECS] = &acr_r375_ls_fecs_func,
- [NVKM_SECBOOT_FALCON_GPCCS] = &acr_r375_ls_gpccs_func,
+ [NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func,
+ [NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func,
[NVKM_SECBOOT_FALCON_PMU] = &acr_r375_ls_pmu_func,
},
};
return gm200_secboot_run_blob(sb, blob, falcon);
}
-static const struct nvkm_secboot_func
+const struct nvkm_secboot_func
gp102_secboot = {
.dtor = gm200_secboot_dtor,
.oneinit = gm200_secboot_oneinit,
--- /dev/null
+/*
+ * Copyright 2017 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 "gm200.h"
+#include "acr.h"
+
+int
+gp108_secboot_new(struct nvkm_device *device, int index,
+ struct nvkm_secboot **psb)
+{
+ struct gm200_secboot *gsb;
+ struct nvkm_acr *acr;
+
+ acr = acr_r370_new(NVKM_SECBOOT_FALCON_SEC2,
+ BIT(NVKM_SECBOOT_FALCON_FECS) |
+ BIT(NVKM_SECBOOT_FALCON_GPCCS) |
+ BIT(NVKM_SECBOOT_FALCON_SEC2));
+ if (IS_ERR(acr))
+ return PTR_ERR(acr);
+
+ if (!(gsb = kzalloc(sizeof(*gsb), GFP_KERNEL))) {
+ acr->func->dtor(acr);
+ return -ENOMEM;
+ }
+ *psb = &gsb->base;
+
+ return nvkm_secboot_ctor(&gp102_secboot, acr, device, index, &gsb->base);
+}
+
+MODULE_FIRMWARE("nvidia/gp108/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/ucode_load.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_method_init.bin");
+MODULE_FIRMWARE("nvidia/gp108/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin");
int nvkm_secboot_falcon_reset(struct nvkm_secboot *);
int nvkm_secboot_falcon_run(struct nvkm_secboot *);
+extern const struct nvkm_secboot_func gp102_secboot;
+
struct flcn_u64 {
u32 lo;
u32 hi;
nvkm-y += nvkm/subdev/therm/nv50.o
nvkm-y += nvkm/subdev/therm/g84.o
nvkm-y += nvkm/subdev/therm/gt215.o
+nvkm-y += nvkm/subdev/therm/gf100.o
nvkm-y += nvkm/subdev/therm/gf119.o
+nvkm-y += nvkm/subdev/therm/gk104.o
nvkm-y += nvkm/subdev/therm/gm107.o
nvkm-y += nvkm/subdev/therm/gm200.o
nvkm-y += nvkm/subdev/therm/gp100.o
*
* Authors: Martin Peres
*/
+#include <nvkm/core/option.h>
#include "priv.h"
int
return -EINVAL;
}
+void
+nvkm_therm_clkgate_enable(struct nvkm_therm *therm)
+{
+ if (!therm->func->clkgate_enable || !therm->clkgating_enabled)
+ return;
+
+ nvkm_debug(&therm->subdev,
+ "Enabling clockgating\n");
+ therm->func->clkgate_enable(therm);
+}
+
+void
+nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend)
+{
+ if (!therm->func->clkgate_fini || !therm->clkgating_enabled)
+ return;
+
+ nvkm_debug(&therm->subdev,
+ "Preparing clockgating for %s\n",
+ suspend ? "suspend" : "fini");
+ therm->func->clkgate_fini(therm, suspend);
+}
+
+static void
+nvkm_therm_clkgate_oneinit(struct nvkm_therm *therm)
+{
+ if (!therm->func->clkgate_enable || !therm->clkgating_enabled)
+ return;
+
+ nvkm_info(&therm->subdev, "Clockgating enabled\n");
+}
+
static void
nvkm_therm_intr(struct nvkm_subdev *subdev)
{
nvkm_therm_fan_ctor(therm);
nvkm_therm_fan_mode(therm, NVKM_THERM_CTRL_AUTO);
nvkm_therm_sensor_preinit(therm);
+ nvkm_therm_clkgate_oneinit(therm);
return 0;
}
return 0;
}
+void
+nvkm_therm_clkgate_init(struct nvkm_therm *therm,
+ const struct nvkm_therm_clkgate_pack *p)
+{
+ if (!therm->func->clkgate_init || !therm->clkgating_enabled)
+ return;
+
+ therm->func->clkgate_init(therm, p);
+}
+
static void *
nvkm_therm_dtor(struct nvkm_subdev *subdev)
{
.intr = nvkm_therm_intr,
};
-int
-nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device,
- int index, struct nvkm_therm **ptherm)
+void
+nvkm_therm_ctor(struct nvkm_therm *therm, struct nvkm_device *device,
+ int index, const struct nvkm_therm_func *func)
{
- struct nvkm_therm *therm;
-
- if (!(therm = *ptherm = kzalloc(sizeof(*therm), GFP_KERNEL)))
- return -ENOMEM;
-
nvkm_subdev_ctor(&nvkm_therm, device, index, &therm->subdev);
therm->func = func;
therm->attr_get = nvkm_therm_attr_get;
therm->attr_set = nvkm_therm_attr_set;
therm->mode = therm->suspend = -1; /* undefined */
+
+ therm->clkgating_enabled = nvkm_boolopt(device->cfgopt,
+ "NvPmEnableGating", false);
+}
+
+int
+nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device,
+ int index, struct nvkm_therm **ptherm)
+{
+ struct nvkm_therm *therm;
+
+ if (!(therm = *ptherm = kzalloc(sizeof(*therm), GFP_KERNEL)))
+ return -ENOMEM;
+
+ nvkm_therm_ctor(therm, device, index, func);
return 0;
}
--- /dev/null
+/*
+ * Copyright 2018 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.
+ *
+ * Authors: Lyude Paul
+ */
+#include <core/device.h>
+
+#include "priv.h"
+
+#define pack_for_each_init(init, pack, head) \
+ for (pack = head; pack && pack->init; pack++) \
+ for (init = pack->init; init && init->count; init++)
+void
+gf100_clkgate_init(struct nvkm_therm *therm,
+ const struct nvkm_therm_clkgate_pack *p)
+{
+ struct nvkm_device *device = therm->subdev.device;
+ const struct nvkm_therm_clkgate_pack *pack;
+ const struct nvkm_therm_clkgate_init *init;
+ u32 next, addr;
+
+ pack_for_each_init(init, pack, p) {
+ next = init->addr + init->count * 8;
+ addr = init->addr;
+
+ nvkm_trace(&therm->subdev, "{ 0x%06x, %d, 0x%08x }\n",
+ init->addr, init->count, init->data);
+ while (addr < next) {
+ nvkm_trace(&therm->subdev, "\t0x%06x = 0x%08x\n",
+ addr, init->data);
+ nvkm_wr32(device, addr, init->data);
+ addr += 8;
+ }
+ }
+}
+
+/*
+ * TODO: Fermi clockgating isn't understood fully yet, so we don't specify any
+ * clockgate functions to use
+ */
--- /dev/null
+/*
+ * Copyright 2018 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.
+ *
+ * Authors: Lyude Paul
+ */
+
+#ifndef __GF100_THERM_H__
+#define __GF100_THERM_H__
+
+#include <core/device.h>
+
+struct gf100_idle_filter {
+ u32 fecs;
+ u32 hubmmu;
+};
+
+#endif
return -ENODEV;
}
-static int
+int
gf119_fan_pwm_ctrl(struct nvkm_therm *therm, int line, bool enable)
{
struct nvkm_device *device = therm->subdev.device;
return 0;
}
-static int
+int
gf119_fan_pwm_get(struct nvkm_therm *therm, int line, u32 *divs, u32 *duty)
{
struct nvkm_device *device = therm->subdev.device;
return -EINVAL;
}
-static int
+int
gf119_fan_pwm_set(struct nvkm_therm *therm, int line, u32 divs, u32 duty)
{
struct nvkm_device *device = therm->subdev.device;
return 0;
}
-static int
+int
gf119_fan_pwm_clock(struct nvkm_therm *therm, int line)
{
struct nvkm_device *device = therm->subdev.device;
--- /dev/null
+/*
+ * Copyright 2018 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.
+ *
+ * Authors: Lyude Paul
+ */
+#include <core/device.h>
+
+#include "priv.h"
+#include "gk104.h"
+
+void
+gk104_clkgate_enable(struct nvkm_therm *base)
+{
+ struct gk104_therm *therm = gk104_therm(base);
+ struct nvkm_device *dev = therm->base.subdev.device;
+ const struct gk104_clkgate_engine_info *order = therm->clkgate_order;
+ int i;
+
+ /* Program ENG_MANT, ENG_FILTER */
+ for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) {
+ if (!nvkm_device_subdev(dev, order[i].engine))
+ continue;
+
+ nvkm_mask(dev, 0x20200 + order[i].offset, 0xff00, 0x4500);
+ }
+
+ /* magic */
+ nvkm_wr32(dev, 0x020288, therm->idle_filter->fecs);
+ nvkm_wr32(dev, 0x02028c, therm->idle_filter->hubmmu);
+
+ /* Enable clockgating (ENG_CLK = RUN->AUTO) */
+ for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) {
+ if (!nvkm_device_subdev(dev, order[i].engine))
+ continue;
+
+ nvkm_mask(dev, 0x20200 + order[i].offset, 0x00ff, 0x0045);
+ }
+}
+
+void
+gk104_clkgate_fini(struct nvkm_therm *base, bool suspend)
+{
+ struct gk104_therm *therm = gk104_therm(base);
+ struct nvkm_device *dev = therm->base.subdev.device;
+ const struct gk104_clkgate_engine_info *order = therm->clkgate_order;
+ int i;
+
+ /* ENG_CLK = AUTO->RUN, ENG_PWR = RUN->AUTO */
+ for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) {
+ if (!nvkm_device_subdev(dev, order[i].engine))
+ continue;
+
+ nvkm_mask(dev, 0x20200 + order[i].offset, 0xff, 0x54);
+ }
+}
+
+const struct gk104_clkgate_engine_info gk104_clkgate_engine_info[] = {
+ { NVKM_ENGINE_GR, 0x00 },
+ { NVKM_ENGINE_MSPDEC, 0x04 },
+ { NVKM_ENGINE_MSPPP, 0x08 },
+ { NVKM_ENGINE_MSVLD, 0x0c },
+ { NVKM_ENGINE_CE0, 0x10 },
+ { NVKM_ENGINE_CE1, 0x14 },
+ { NVKM_ENGINE_MSENC, 0x18 },
+ { NVKM_ENGINE_CE2, 0x1c },
+ { NVKM_SUBDEV_NR, 0 },
+};
+
+const struct gf100_idle_filter gk104_idle_filter = {
+ .fecs = 0x00001000,
+ .hubmmu = 0x00001000,
+};
+
+static const struct nvkm_therm_func
+gk104_therm_func = {
+ .init = gf119_therm_init,
+ .fini = g84_therm_fini,
+ .pwm_ctrl = gf119_fan_pwm_ctrl,
+ .pwm_get = gf119_fan_pwm_get,
+ .pwm_set = gf119_fan_pwm_set,
+ .pwm_clock = gf119_fan_pwm_clock,
+ .temp_get = g84_temp_get,
+ .fan_sense = gt215_therm_fan_sense,
+ .program_alarms = nvkm_therm_program_alarms_polling,
+ .clkgate_init = gf100_clkgate_init,
+ .clkgate_enable = gk104_clkgate_enable,
+ .clkgate_fini = gk104_clkgate_fini,
+};
+
+static int
+gk104_therm_new_(const struct nvkm_therm_func *func,
+ struct nvkm_device *device,
+ int index,
+ const struct gk104_clkgate_engine_info *clkgate_order,
+ const struct gf100_idle_filter *idle_filter,
+ struct nvkm_therm **ptherm)
+{
+ struct gk104_therm *therm = kzalloc(sizeof(*therm), GFP_KERNEL);
+
+ if (!therm)
+ return -ENOMEM;
+
+ nvkm_therm_ctor(&therm->base, device, index, func);
+ *ptherm = &therm->base;
+ therm->clkgate_order = clkgate_order;
+ therm->idle_filter = idle_filter;
+
+ return 0;
+}
+
+int
+gk104_therm_new(struct nvkm_device *device,
+ int index, struct nvkm_therm **ptherm)
+{
+ return gk104_therm_new_(&gk104_therm_func, device, index,
+ gk104_clkgate_engine_info, &gk104_idle_filter,
+ ptherm);
+}
--- /dev/null
+/*
+ * Copyright 2018 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.
+ *
+ * Authors: Lyude Paul
+ */
+
+#ifndef __GK104_THERM_H__
+#define __GK104_THERM_H__
+#define gk104_therm(p) (container_of((p), struct gk104_therm, base))
+
+#include <subdev/therm.h>
+#include "priv.h"
+#include "gf100.h"
+
+struct gk104_clkgate_engine_info {
+ enum nvkm_devidx engine;
+ u8 offset;
+};
+
+struct gk104_therm {
+ struct nvkm_therm base;
+
+ const struct gk104_clkgate_engine_info *clkgate_order;
+ const struct gf100_idle_filter *idle_filter;
+};
+
+extern const struct gk104_clkgate_engine_info gk104_clkgate_engine_info[];
+extern const struct gf100_idle_filter gk104_idle_filter;
+
+#endif
return -ENODEV;
}
-static void
+void
gt215_therm_init(struct nvkm_therm *therm)
{
struct nvkm_device *device = therm->subdev.device;
int nvkm_therm_new_(const struct nvkm_therm_func *, struct nvkm_device *,
int index, struct nvkm_therm **);
+void nvkm_therm_ctor(struct nvkm_therm *therm, struct nvkm_device *device,
+ int index, const struct nvkm_therm_func *func);
struct nvkm_fan {
struct nvkm_therm *parent;
int nvkm_therm_fan_user_get(struct nvkm_therm *);
int nvkm_therm_fan_user_set(struct nvkm_therm *, int percent);
-int nvkm_therm_preinit(struct nvkm_therm *);
-
int nvkm_therm_sensor_init(struct nvkm_therm *);
int nvkm_therm_sensor_fini(struct nvkm_therm *, bool suspend);
void nvkm_therm_sensor_preinit(struct nvkm_therm *);
int (*fan_sense)(struct nvkm_therm *);
void (*program_alarms)(struct nvkm_therm *);
+
+ void (*clkgate_init)(struct nvkm_therm *,
+ const struct nvkm_therm_clkgate_pack *);
+ void (*clkgate_enable)(struct nvkm_therm *);
+ void (*clkgate_fini)(struct nvkm_therm *, bool);
};
void nv40_therm_intr(struct nvkm_therm *);
int gt215_therm_fan_sense(struct nvkm_therm *);
+void gf100_clkgate_init(struct nvkm_therm *,
+ const struct nvkm_therm_clkgate_pack *);
+
void g84_therm_init(struct nvkm_therm *);
+
+int gf119_fan_pwm_ctrl(struct nvkm_therm *, int, bool);
+int gf119_fan_pwm_get(struct nvkm_therm *, int, u32 *, u32 *);
+int gf119_fan_pwm_set(struct nvkm_therm *, int, u32, u32);
+int gf119_fan_pwm_clock(struct nvkm_therm *, int);
void gf119_therm_init(struct nvkm_therm *);
+void gk104_therm_init(struct nvkm_therm *);
+void gk104_clkgate_enable(struct nvkm_therm *);
+void gk104_clkgate_fini(struct nvkm_therm *, bool);
+
int nvkm_fanpwm_create(struct nvkm_therm *, struct dcb_gpio_func *);
int nvkm_fantog_create(struct nvkm_therm *, struct dcb_gpio_func *);
int nvkm_fannil_create(struct nvkm_therm *);
/* calc dclk divider with current vco freq */
dclk_div = radeon_uvd_calc_upll_post_div(vco_freq, dclk,
pd_min, pd_even);
- if (vclk_div > pd_max)
+ if (dclk_div > pd_max)
break; /* vco is too big, it has to stop */
/* calc score with current vco freq */
kref_get(&bo->list_kref);
if (!list_empty(&bo->ddestroy)) {
- ret = ttm_bo_cleanup_refs(bo, false, false, true);
+ ret = ttm_bo_cleanup_refs(bo, false, false, locked);
kref_put(&bo->list_kref, ttm_bo_release_list);
return ret;
}
static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
unsigned long offset,
- void *buf, int len, int write)
+ uint8_t *buf, int len, int write)
{
unsigned long page = offset >> PAGE_SHIFT;
unsigned long bytes_left = len;
ttm_bo_kunmap(&map);
page++;
+ buf += bytes;
bytes_left -= bytes;
offset = 0;
} while (bytes_left);
pr_debug("%s\n", __func__);
poll_wait(file, &vga_wait_queue, wait);
- return POLLIN;
+ return EPOLLIN;
}
static int vga_arb_open(struct inode *inode, struct file *file)
poll_wait(file, &list->hdev->debug_wait, wait);
if (list->head != list->tail)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (!list->hdev->debug)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
return 0;
}
struct roccat_reader *reader = file->private_data;
poll_wait(file, &reader->device->wait, wait);
if (reader->cbuf_start != reader->device->cbuf_end)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (!reader->device->exist)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
return 0;
}
poll_wait(file, &sensor_inst->wait, wait);
if (!kfifo_is_empty(&sensor_inst->data_fifo))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &list->hidraw->wait, wait);
if (list->head != list->tail)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (!list->hidraw->exist)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
return 0;
}
poll_wait(file, &uhid->waitq, wait);
if (uhid->head != uhid->tail)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(file, &list->hiddev->wait, wait);
if (list->head != list->tail)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (!list->hiddev->exist)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
return 0;
}
poll_wait(file, &cs_char_data.wait, wait);
spin_lock_bh(&csdata->lock);
if (!list_empty(&csdata->chardev_queue))
- ret = POLLIN | POLLRDNORM;
+ ret = EPOLLIN | EPOLLRDNORM;
else if (!list_empty(&csdata->dataind_queue))
- ret = POLLIN | POLLRDNORM;
+ ret = EPOLLIN | EPOLLRDNORM;
spin_unlock_bh(&csdata->lock);
return ret;
poll_wait(file, &hvt->outmsg_q, wait);
if (hvt->mode == HVUTIL_TRANSPORT_DESTROY)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
if (hvt->outmsg_len > 0)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
spin_unlock_irqrestore(&queue->list_lock, flags);
iio_buffer_block_put_atomic(block);
- wake_up_interruptible_poll(&queue->buffer.pollq, POLLIN | POLLRDNORM);
+ wake_up_interruptible_poll(&queue->buffer.pollq, EPOLLIN | EPOLLRDNORM);
}
EXPORT_SYMBOL_GPL(iio_dma_buffer_block_done);
}
spin_unlock_irqrestore(&queue->list_lock, flags);
- wake_up_interruptible_poll(&queue->buffer.pollq, POLLIN | POLLRDNORM);
+ wake_up_interruptible_poll(&queue->buffer.pollq, EPOLLIN | EPOLLRDNORM);
}
EXPORT_SYMBOL_GPL(iio_dma_buffer_block_list_abort);
* @wait: Poll table structure pointer for which the driver adds
* a wait queue
*
- * Return: (POLLIN | POLLRDNORM) if data is available for reading
+ * Return: (EPOLLIN | EPOLLRDNORM) if data is available for reading
* or 0 for other cases
*/
__poll_t iio_buffer_poll(struct file *filp,
poll_wait(filp, &rb->pollq, wait);
if (iio_buffer_ready(indio_dev, rb, rb->watermark, 0))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
* We can't just test for watermark to decide if we wake the poll queue
* because read may request less samples than the watermark.
*/
- wake_up_interruptible_poll(&buffer->pollq, POLLIN | POLLRDNORM);
+ wake_up_interruptible_poll(&buffer->pollq, EPOLLIN | EPOLLRDNORM);
return 0;
}
copied = kfifo_put(&ev_int->det_events, ev);
if (copied != 0)
- wake_up_poll(&ev_int->wait, POLLIN);
+ wake_up_poll(&ev_int->wait, EPOLLIN);
}
return 0;
* @filep: File structure pointer to identify the device
* @wait: Poll table pointer to add the wait queue on
*
- * Return: (POLLIN | POLLRDNORM) if data is available for reading
+ * Return: (EPOLLIN | EPOLLRDNORM) if data is available for reading
* or a negative error code on failure
*/
static __poll_t iio_event_poll(struct file *filep,
poll_wait(filep, &ev_int->wait, wait);
if (!kfifo_is_empty(&ev_int->det_events))
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
return events;
}
poll_wait(filp, &file->poll_wait, wait);
if (!list_empty(&file->events))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(filp, &file->poll_wait, wait);
if (!list_empty(&file->event_list))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
return mask;
}
struct ib_umad_file *file = filp->private_data;
/* we will always be able to post a MAD send */
- __poll_t mask = POLLOUT | POLLWRNORM;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM;
poll_wait(filp, &file->recv_wait, wait);
if (!list_empty(&file->recv_list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
spin_lock_irq(&ev_queue->lock);
if (!list_empty(&ev_queue->event_list))
- pollflags = POLLIN | POLLRDNORM;
+ pollflags = EPOLLIN | EPOLLRDNORM;
spin_unlock_irq(&ev_queue->lock);
return pollflags;
uctxt = ((struct hfi1_filedata *)fp->private_data)->uctxt;
if (!uctxt)
- pollflag = POLLERR;
+ pollflag = EPOLLERR;
else if (uctxt->poll_type == HFI1_POLL_TYPE_URGENT)
pollflag = poll_urgent(fp, pt);
else if (uctxt->poll_type == HFI1_POLL_TYPE_ANYRCV)
pollflag = poll_next(fp, pt);
else /* invalid */
- pollflag = POLLERR;
+ pollflag = EPOLLERR;
return pollflag;
}
spin_lock_irq(&dd->uctxt_lock);
if (uctxt->urgent != uctxt->urgent_poll) {
- pollflag = POLLIN | POLLRDNORM;
+ pollflag = EPOLLIN | EPOLLRDNORM;
uctxt->urgent_poll = uctxt->urgent;
} else {
pollflag = 0;
hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_ENB, uctxt);
pollflag = 0;
} else {
- pollflag = POLLIN | POLLRDNORM;
+ pollflag = EPOLLIN | EPOLLRDNORM;
}
spin_unlock_irq(&dd->uctxt_lock);
spin_lock_irq(&dd->uctxt_lock);
if (rcd->urgent != rcd->urgent_poll) {
- pollflag = POLLIN | POLLRDNORM;
+ pollflag = EPOLLIN | EPOLLRDNORM;
rcd->urgent_poll = rcd->urgent;
} else {
pollflag = 0;
dd->f_rcvctrl(rcd->ppd, QIB_RCVCTRL_INTRAVAIL_ENB, rcd->ctxt);
pollflag = 0;
} else
- pollflag = POLLIN | POLLRDNORM;
+ pollflag = EPOLLIN | EPOLLRDNORM;
spin_unlock_irq(&dd->uctxt_lock);
return pollflag;
rcd = ctxt_fp(fp);
if (!rcd)
- pollflag = POLLERR;
+ pollflag = EPOLLERR;
else if (rcd->poll_type == QIB_POLL_TYPE_URGENT)
pollflag = qib_poll_urgent(rcd, fp, pt);
else if (rcd->poll_type == QIB_POLL_TYPE_ANYRCV)
pollflag = qib_poll_next(rcd, fp, pt);
else /* invalid */
- pollflag = POLLERR;
+ pollflag = EPOLLERR;
return pollflag;
}
iser_info("iser conn %p rc = %d\n", iser_conn, rc);
if (rc > 0)
- return 1; /* success, this is the equivalent of POLLOUT */
+ return 1; /* success, this is the equivalent of EPOLLOUT */
else if (!rc)
return 0; /* timeout */
else
poll_wait(file, &evdev->wait, wait);
if (evdev->exist && !client->revoked)
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
else
- mask = POLLHUP | POLLERR;
+ mask = EPOLLHUP | EPOLLERR;
if (client->packet_head != client->tail)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &input_devices_poll_wait, wait);
if (file->f_version != input_devices_state) {
file->f_version = input_devices_state;
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
return 0;
struct joydev *joydev = client->joydev;
poll_wait(file, &joydev->wait, wait);
- return (joydev_data_pending(client) ? (POLLIN | POLLRDNORM) : 0) |
- (joydev->exist ? 0 : (POLLHUP | POLLERR));
+ return (joydev_data_pending(client) ? (EPOLLIN | EPOLLRDNORM) : 0) |
+ (joydev->exist ? 0 : (EPOLLHUP | EPOLLERR));
}
static int joydev_handle_JSIOCSAXMAP(struct joydev *joydev,
l = 0;
if (l != 0)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(file, &udev->waitq, wait);
if (udev->head != udev->tail)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(file, &mousedev->wait, wait);
- mask = mousedev->exist ? POLLOUT | POLLWRNORM : POLLHUP | POLLERR;
+ mask = mousedev->exist ? EPOLLOUT | EPOLLWRNORM : EPOLLHUP | EPOLLERR;
if (client->ready || client->buffer)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &serio_raw->wait, wait);
- mask = serio_raw->dead ? POLLHUP | POLLERR : POLLOUT | POLLWRNORM;
+ mask = serio_raw->dead ? EPOLLHUP | EPOLLERR : EPOLLOUT | EPOLLWRNORM;
if (serio_raw->head != serio_raw->tail)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &userio->waitq, wait);
if (userio->head != userio->tail)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
address, flags);
break;
default:
- printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type);
+ printk(KERN_ERR "UNKNOWN type=0x%02x event[0]=0x%08x "
+ "event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
+ type, event[0], event[1], event[2], event[3]);
}
memset(__evt, 0, 4 * sizeof(u32));
return domain->flags & PD_DMA_OPS_MASK;
}
-static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
+static void set_dte_entry(u16 devid, struct protection_domain *domain,
+ bool ats, bool ppr)
{
u64 pte_root = 0;
u64 flags = 0;
if (ats)
flags |= DTE_FLAG_IOTLB;
+ if (ppr) {
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+ if (iommu_feature(iommu, FEATURE_EPHSUP))
+ pte_root |= 1ULL << DEV_ENTRY_PPR;
+ }
+
if (domain->flags & PD_IOMMUV2_MASK) {
u64 gcr3 = iommu_virt_to_phys(domain->gcr3_tbl);
u64 glx = domain->glx;
domain->dev_cnt += 1;
/* Update device table */
- set_dte_entry(dev_data->devid, domain, ats);
+ set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2);
if (alias != dev_data->devid)
- set_dte_entry(alias, domain, ats);
+ set_dte_entry(alias, domain, ats, dev_data->iommu_v2);
device_flush_dte(dev_data);
}
struct iommu_dev_data *dev_data;
list_for_each_entry(dev_data, &domain->dev_list, list) {
- set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled);
+ set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled,
+ dev_data->iommu_v2);
if (dev_data->devid == dev_data->alias)
continue;
/* There is an alias, update device table entry for it */
- set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled);
+ set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled,
+ dev_data->iommu_v2);
}
}
#define FEATURE_HE (1ULL<<8)
#define FEATURE_PC (1ULL<<9)
#define FEATURE_GAM_VAPIC (1ULL<<21)
+#define FEATURE_EPHSUP (1ULL<<50)
#define FEATURE_PASID_SHIFT 32
#define FEATURE_PASID_MASK (0x1fULL << FEATURE_PASID_SHIFT)
/* macros and definitions for device table entries */
#define DEV_ENTRY_VALID 0x00
#define DEV_ENTRY_TRANSLATION 0x01
+#define DEV_ENTRY_PPR 0x34
#define DEV_ENTRY_IR 0x3d
#define DEV_ENTRY_IW 0x3e
#define DEV_ENTRY_NO_PAGE_FAULT 0x62
};
module_platform_driver(arm_smmu_driver);
-IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", NULL);
+IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3");
MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
};
module_platform_driver(arm_smmu_driver);
-IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1", NULL);
-IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2", NULL);
-IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400", NULL);
-IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", NULL);
-IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", NULL);
-IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", NULL);
+IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1");
+IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2");
+IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400");
+IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401");
+IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500");
+IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2");
MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
static int __init exynos_iommu_init(void)
{
+ struct device_node *np;
int ret;
+ np = of_find_matching_node(NULL, sysmmu_of_match);
+ if (!np)
+ return 0;
+
+ of_node_put(np);
+
lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
if (!lv2table_kmem_cache) {
}
core_initcall(exynos_iommu_init);
-IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu", NULL);
+IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu");
#define IOAPIC_RANGE_END (0xfeefffff)
#define IOVA_START_ADDR (0x1000)
-#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48
+#define DEFAULT_DOMAIN_ADDRESS_WIDTH 57
#define MAX_AGAW_WIDTH 64
#define MAX_AGAW_PFN_WIDTH (MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
* flush. However, device IOTLB doesn't need to be flushed in this case.
*/
if (!cap_caching_mode(iommu->cap) || !map)
- iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
- addr, mask);
+ iommu_flush_dev_iotlb(domain, addr, mask);
}
static void iommu_flush_iova(struct iova_domain *iovad)
#include <linux/interrupt.h>
#include <asm/page.h>
+#define PASID_ENTRY_P BIT_ULL(0)
+#define PASID_ENTRY_FLPM_5LP BIT_ULL(9)
+#define PASID_ENTRY_SRE BIT_ULL(11)
+
static irqreturn_t prq_event_thread(int irq, void *d);
struct pasid_entry {
struct page *pages;
int order;
+ if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
+ !cap_fl1gp_support(iommu->cap))
+ return -EINVAL;
+
+ if (cpu_feature_enabled(X86_FEATURE_LA57) &&
+ !cap_5lp_support(iommu->cap))
+ return -EINVAL;
+
/* Start at 2 because it's defined as 2^(1+PSS) */
iommu->pasid_max = 2 << ecap_pss(iommu->ecap);
pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n",
iommu->name);
dmar_free_hwirq(irq);
+ iommu->pr_irq = 0;
goto err;
}
dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
dmar_writeq(iommu->reg + DMAR_PQA_REG, 0ULL);
- free_irq(iommu->pr_irq, iommu);
- dmar_free_hwirq(iommu->pr_irq);
- iommu->pr_irq = 0;
+ if (iommu->pr_irq) {
+ free_irq(iommu->pr_irq, iommu);
+ dmar_free_hwirq(iommu->pr_irq);
+ iommu->pr_irq = 0;
+ }
free_pages((unsigned long)iommu->prq, PRQ_ORDER);
iommu->prq = NULL;
struct intel_svm_dev *sdev;
struct intel_svm *svm = NULL;
struct mm_struct *mm = NULL;
+ u64 pasid_entry_val;
int pasid_max;
int ret;
kfree(sdev);
goto out;
}
- iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1;
+ pasid_entry_val = (u64)__pa(mm->pgd) | PASID_ENTRY_P;
} else
- iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11);
+ pasid_entry_val = (u64)__pa(init_mm.pgd) |
+ PASID_ENTRY_P | PASID_ENTRY_SRE;
+ if (cpu_feature_enabled(X86_FEATURE_LA57))
+ pasid_entry_val |= PASID_ENTRY_FLPM_5LP;
+
+ iommu->pasid_table[svm->pasid].val = pasid_entry_val;
+
wmb();
/* In caching mode, we still have to flush with PASID 0 when
* a PASID table entry becomes present. Not entirely clear
int ret;
group = iommu_group_get(dev);
+ if (!group)
+ return -ENODEV;
+
/*
* Lock the group to make sure the device-count doesn't
* change while we are attaching
struct iommu_group *group;
group = iommu_group_get(dev);
+ if (!group)
+ return;
mutex_lock(&group->mutex);
if (iommu_group_device_count(group) != 1) {
subsys_initcall(ipmmu_init);
module_exit(ipmmu_exit);
-#ifdef CONFIG_IOMMU_DMA
-static int __init ipmmu_vmsa_iommu_of_setup(struct device_node *np)
-{
- ipmmu_init();
- return 0;
-}
-
-IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa",
- ipmmu_vmsa_iommu_of_setup);
-IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795",
- ipmmu_vmsa_iommu_of_setup);
-#endif
+IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa");
+IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795");
MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU");
MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
goto fail;
}
+ bus_set_iommu(&platform_bus_type, &msm_iommu_ops);
+
pr_info("device mapped at %p, irq %d with %d ctx banks\n",
iommu->base, iommu->irq, iommu->ncb);
subsys_initcall(msm_iommu_driver_init);
module_exit(msm_iommu_driver_exit);
-static int __init msm_iommu_init(void)
-{
- bus_set_iommu(&platform_bus_type, &msm_iommu_ops);
- return 0;
-}
-
-static int __init msm_iommu_of_setup(struct device_node *np)
-{
- msm_iommu_init();
- return 0;
-}
-
-IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu", msm_iommu_of_setup);
+IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>");
return ops;
}
-
-static int __init of_iommu_init(void)
-{
- struct device_node *np;
- const struct of_device_id *match, *matches = &__iommu_of_table;
-
- for_each_matching_node_and_match(np, matches, &match) {
- const of_iommu_init_fn init_fn = match->data;
-
- if (init_fn && init_fn(np))
- pr_err("Failed to initialise IOMMU %pOF\n", np);
- }
-
- return 0;
-}
-postcore_initcall_sync(of_iommu_init);
if (!obj->debug_dir)
return;
- d = debugfs_create_u8("nr_tlb_entries", 0400, obj->debug_dir,
- (u8 *)&obj->nr_tlb_entries);
+ d = debugfs_create_u32("nr_tlb_entries", 0400, obj->debug_dir,
+ &obj->nr_tlb_entries);
if (!d)
return;
module_init(qcom_iommu_init);
module_exit(qcom_iommu_exit);
-IOMMU_OF_DECLARE(qcom_iommu_dev, "qcom,msm-iommu-v1", NULL);
+IOMMU_OF_DECLARE(qcom_iommu_dev, "qcom,msm-iommu-v1");
MODULE_DESCRIPTION("IOMMU API for QCOM IOMMU v1 implementations");
MODULE_LICENSE("GPL v2");
__poll_t mask = 0;
if (!cdev->ap.applid)
- return POLLERR;
+ return EPOLLERR;
poll_wait(file, &(cdev->recvwait), wait);
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
if (!skb_queue_empty(&cdev->recvqueue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
__poll_t mask = 0;
poll_wait(file, &(rd_queue), wait);
- /* mask = POLLOUT | POLLWRNORM; */
+ /* mask = EPOLLOUT | EPOLLWRNORM; */
if (*((struct divert_info **) file->private_data)) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
return mask;
} /* isdn_divert_poll */
__poll_t mask = 0;
poll_wait(file, &msgwaitq, wait);
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
if (file->private_data || diva_dbg_q_length()) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
return (mask);
}
diva_um_idi_os_context_t *p_os;
if (!file->private_data) {
- return (POLLERR);
+ return (EPOLLERR);
}
if ((!(p_os =
(diva_um_idi_os_context_t *)
diva_um_id_get_os_context(file->private_data)))
|| p_os->aborted) {
- return (POLLERR);
+ return (EPOLLERR);
}
poll_wait(file, &p_os->read_wait, wait);
if (p_os->aborted) {
- return (POLLERR);
+ return (EPOLLERR);
}
switch (diva_user_mode_idi_ind_ready(file->private_data, file)) {
case (-1):
- return (POLLERR);
+ return (EPOLLERR);
case 0:
return (0);
}
- return (POLLIN | POLLRDNORM);
+ return (EPOLLIN | EPOLLRDNORM);
}
static int um_idi_open(struct inode *inode, struct file *file)
static __poll_t divas_poll(struct file *file, poll_table *wait)
{
if (!file->private_data) {
- return (POLLERR);
+ return (EPOLLERR);
}
- return (POLLIN | POLLRDNORM);
+ return (EPOLLIN | EPOLLRDNORM);
}
static const struct file_operations divas_fops = {
static __poll_t divas_poll(struct file *file, poll_table *wait)
{
- return (POLLERR);
+ return (EPOLLERR);
}
static int divas_open(struct inode *inode, struct file *file)
poll_wait(file, &(pd->rd_queue), wait);
if (*((struct log_data **) file->private_data))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
} /* hysdn_log_poll */
mutex_lock(&isdn_mutex);
if (minor == ISDN_MINOR_STATUS) {
poll_wait(file, &(dev->info_waitq), wait);
- /* mask = POLLOUT | POLLWRNORM; */
+ /* mask = EPOLLOUT | EPOLLWRNORM; */
if (file->private_data) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
goto out;
}
if (minor >= ISDN_MINOR_CTRL && minor <= ISDN_MINOR_CTRLMAX) {
if (drvidx < 0) {
/* driver deregistered while file open */
- mask = POLLHUP;
+ mask = EPOLLHUP;
goto out;
}
poll_wait(file, &(dev->drv[drvidx]->st_waitq), wait);
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
if (dev->drv[drvidx]->stavail) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
goto out;
}
goto out;
}
#endif
- mask = POLLERR;
+ mask = EPOLLERR;
out:
mutex_unlock(&isdn_mutex);
return mask;
if (!(is->state & IPPP_OPEN)) {
if (is->state == IPPP_CLOSEWAIT)
- return POLLHUP;
+ return EPOLLHUP;
printk(KERN_DEBUG "isdn_ppp: device not open\n");
- return POLLERR;
+ return EPOLLERR;
}
/* we're always ready to send .. */
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
spin_lock_irqsave(&is->buflock, flags);
bl = is->last;
*/
if (bf->next != bl || (is->state & IPPP_NOBLOCK)) {
is->state &= ~IPPP_NOBLOCK;
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
spin_unlock_irqrestore(&is->buflock, flags);
return mask;
mISDN_poll(struct file *filep, poll_table *wait)
{
struct mISDNtimerdev *dev = filep->private_data;
- __poll_t mask = POLLERR;
+ __poll_t mask = EPOLLERR;
if (*debug & DEBUG_TIMER)
printk(KERN_DEBUG "%s(%p, %p)\n", __func__, filep, wait);
poll_wait(filep, &dev->wait, wait);
mask = 0;
if (dev->work || !list_empty(&dev->expired))
- mask |= (POLLIN | POLLRDNORM);
+ mask |= (EPOLLIN | EPOLLRDNORM);
if (*debug & DEBUG_TIMER)
printk(KERN_DEBUG "%s work(%d) empty(%d)\n", __func__,
dev->work, list_empty(&dev->expired));
poll_wait(file, &udev->waitq, wait);
if (udev->new_data)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
spin_lock_irqsave(&pp->lock, flags);
if (pp->busy && pp->cmd.status != 1)
- mask |= POLLIN;
+ mask |= EPOLLIN;
spin_unlock_irqrestore(&pp->lock, flags);
}
if (pp->mode == smu_file_events) {
poll_wait(filp, &pp->wait, wait);
spin_lock_irqsave(&pp->lock, flags);
if (pp->rb_get != pp->rb_put)
- mask |= POLLIN;
+ mask |= EPOLLIN;
spin_unlock_irqrestore(&pp->lock, flags);
return mask;
}
poll_wait(filp, &tdev->waitq, wait);
if (mbox_test_message_data_ready(tdev))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
break; \
\
mutex_unlock(&(ca)->set->bucket_lock); \
- if (kthread_should_stop()) \
+ if (kthread_should_stop()) { \
+ set_current_state(TASK_RUNNING); \
return 0; \
+ } \
\
schedule(); \
mutex_lock(&(ca)->set->bucket_lock); \
atomic_long_t writeback_keys_done;
atomic_long_t writeback_keys_failed;
+ atomic_long_t reclaim;
+ atomic_long_t flush_write;
+ atomic_long_t retry_flush_write;
+
enum {
ON_ERROR_UNREGISTER,
ON_ERROR_PANIC,
} on_error;
+#define DEFAULT_IO_ERROR_LIMIT 8
unsigned error_limit;
unsigned error_decay;
#define BUCKET_HASH_BITS 12
struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS];
+
+ DECLARE_HEAP(struct btree *, flush_btree);
};
struct bbio {
int bch_flash_dev_create(struct cache_set *c, uint64_t size);
-int bch_cached_dev_attach(struct cached_dev *, struct cache_set *);
+int bch_cached_dev_attach(struct cached_dev *, struct cache_set *, uint8_t *);
void bch_cached_dev_detach(struct cached_dev *);
void bch_cached_dev_run(struct cached_dev *);
void bcache_device_stop(struct bcache_device *);
*/
for_each_cache(ca, c, i) {
for_each_bucket(b, ca) {
- if (fifo_full(&ca->free[RESERVE_PRIO]))
+ if (fifo_full(&ca->free[RESERVE_PRIO]) &&
+ fifo_full(&ca->free[RESERVE_BTREE]))
break;
if (bch_can_invalidate_bucket(ca, b) &&
!GC_MARK(b)) {
__bch_invalidate_one_bucket(ca, b);
- fifo_push(&ca->free[RESERVE_PRIO],
- b - ca->buckets);
+ if (!fifo_push(&ca->free[RESERVE_PRIO],
+ b - ca->buckets))
+ fifo_push(&ca->free[RESERVE_BTREE],
+ b - ca->buckets);
}
}
}
}
/* Journalling */
+#define journal_max_cmp(l, r) \
+ (fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
+ fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
+#define journal_min_cmp(l, r) \
+ (fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
+ fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
static void btree_flush_write(struct cache_set *c)
{
* Try to find the btree node with that references the oldest journal
* entry, best is our current candidate and is locked if non NULL:
*/
- struct btree *b, *best;
- unsigned i;
+ struct btree *b;
+ int i;
+
+ atomic_long_inc(&c->flush_write);
+
retry:
- best = NULL;
-
- for_each_cached_btree(b, c, i)
- if (btree_current_write(b)->journal) {
- if (!best)
- best = b;
- else if (journal_pin_cmp(c,
- btree_current_write(best)->journal,
- btree_current_write(b)->journal)) {
- best = b;
+ spin_lock(&c->journal.lock);
+ if (heap_empty(&c->flush_btree)) {
+ for_each_cached_btree(b, c, i)
+ if (btree_current_write(b)->journal) {
+ if (!heap_full(&c->flush_btree))
+ heap_add(&c->flush_btree, b,
+ journal_max_cmp);
+ else if (journal_max_cmp(b,
+ heap_peek(&c->flush_btree))) {
+ c->flush_btree.data[0] = b;
+ heap_sift(&c->flush_btree, 0,
+ journal_max_cmp);
+ }
}
- }
- b = best;
+ for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
+ heap_sift(&c->flush_btree, i, journal_min_cmp);
+ }
+
+ b = NULL;
+ heap_pop(&c->flush_btree, b, journal_min_cmp);
+ spin_unlock(&c->journal.lock);
+
if (b) {
mutex_lock(&b->write_lock);
if (!btree_current_write(b)->journal) {
mutex_unlock(&b->write_lock);
/* We raced */
+ atomic_long_inc(&c->retry_flush_write);
goto retry;
}
unsigned iter, n = 0;
atomic_t p;
+ atomic_long_inc(&c->reclaim);
+
while (!atomic_read(&fifo_front(&c->journal.pin)))
fifo_pop(&c->journal.pin, p);
j->w[0].c = c;
j->w[1].c = c;
- if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
+ if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
+ !(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
!(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
!(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
return -ENOMEM;
cached_dev_put(dc);
}
-int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c)
+int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
+ uint8_t *set_uuid)
{
uint32_t rtime = cpu_to_le32(get_seconds());
struct uuid_entry *u;
bdevname(dc->bdev, buf);
- if (memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16))
+ if ((set_uuid && memcmp(set_uuid, c->sb.set_uuid, 16)) ||
+ (!set_uuid && memcmp(dc->sb.set_uuid, c->sb.set_uuid, 16)))
return -ENOENT;
if (dc->disk.c) {
list_add(&dc->list, &uncached_devices);
list_for_each_entry(c, &bch_cache_sets, list)
- bch_cached_dev_attach(dc, c);
+ bch_cached_dev_attach(dc, c, NULL);
if (BDEV_STATE(&dc->sb) == BDEV_STATE_NONE ||
BDEV_STATE(&dc->sb) == BDEV_STATE_STALE)
c->congested_read_threshold_us = 2000;
c->congested_write_threshold_us = 20000;
- c->error_limit = 8 << IO_ERROR_SHIFT;
+ c->error_limit = DEFAULT_IO_ERROR_LIMIT;
return c;
err:
bcache_write_super(c);
list_for_each_entry_safe(dc, t, &uncached_devices, list)
- bch_cached_dev_attach(dc, c);
+ bch_cached_dev_attach(dc, c, NULL);
flash_devs_run(c);
static int cache_alloc(struct cache *ca)
{
size_t free;
+ size_t btree_buckets;
struct bucket *b;
__module_get(THIS_MODULE);
bio_init(&ca->journal.bio, ca->journal.bio.bi_inline_vecs, 8);
+ /*
+ * when ca->sb.njournal_buckets is not zero, journal exists,
+ * and in bch_journal_replay(), tree node may split,
+ * so bucket of RESERVE_BTREE type is needed,
+ * the worst situation is all journal buckets are valid journal,
+ * and all the keys need to replay,
+ * so the number of RESERVE_BTREE type buckets should be as much
+ * as journal buckets
+ */
+ btree_buckets = ca->sb.njournal_buckets ?: 8;
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
- if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
+ if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) ||
!init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
read_attribute(state);
read_attribute(cache_read_races);
+read_attribute(reclaim);
+read_attribute(flush_write);
+read_attribute(retry_flush_write);
read_attribute(writeback_keys_done);
read_attribute(writeback_keys_failed);
read_attribute(io_errors);
{
struct cached_dev *dc = container_of(kobj, struct cached_dev,
disk.kobj);
- ssize_t v = size;
+ ssize_t v;
struct cache_set *c;
struct kobj_uevent_env *env;
sysfs_strtoul_clamp(writeback_rate,
dc->writeback_rate.rate, 1, INT_MAX);
- d_strtoul_nonzero(writeback_rate_update_seconds);
+ sysfs_strtoul_clamp(writeback_rate_update_seconds,
+ dc->writeback_rate_update_seconds,
+ 1, WRITEBACK_RATE_UPDATE_SECS_MAX);
d_strtoul(writeback_rate_i_term_inverse);
d_strtoul_nonzero(writeback_rate_p_term_inverse);
}
if (attr == &sysfs_attach) {
- if (bch_parse_uuid(buf, dc->sb.set_uuid) < 16)
+ uint8_t set_uuid[16];
+
+ if (bch_parse_uuid(buf, set_uuid) < 16)
return -EINVAL;
+ v = -ENOENT;
list_for_each_entry(c, &bch_cache_sets, list) {
- v = bch_cached_dev_attach(dc, c);
+ v = bch_cached_dev_attach(dc, c, set_uuid);
if (!v)
return size;
}
pr_err("Can't attach %s: cache set not found", buf);
- size = v;
+ return v;
}
if (attr == &sysfs_detach && dc->disk.c)
sysfs_print(cache_read_races,
atomic_long_read(&c->cache_read_races));
+ sysfs_print(reclaim,
+ atomic_long_read(&c->reclaim));
+
+ sysfs_print(flush_write,
+ atomic_long_read(&c->flush_write));
+
+ sysfs_print(retry_flush_write,
+ atomic_long_read(&c->retry_flush_write));
+
sysfs_print(writeback_keys_done,
atomic_long_read(&c->writeback_keys_done));
sysfs_print(writeback_keys_failed,
/* See count_io_errors for why 88 */
sysfs_print(io_error_halflife, c->error_decay * 88);
- sysfs_print(io_error_limit, c->error_limit >> IO_ERROR_SHIFT);
+ sysfs_print(io_error_limit, c->error_limit);
sysfs_hprint(congested,
((uint64_t) bch_get_congested(c)) << 9);
}
if (attr == &sysfs_io_error_limit)
- c->error_limit = strtoul_or_return(buf) << IO_ERROR_SHIFT;
+ c->error_limit = strtoul_or_return(buf);
/* See count_io_errors() for why 88 */
if (attr == &sysfs_io_error_halflife)
&sysfs_bset_tree_stats,
&sysfs_cache_read_races,
+ &sysfs_reclaim,
+ &sysfs_flush_write,
+ &sysfs_retry_flush_write,
&sysfs_writeback_keys_done,
&sysfs_writeback_keys_failed,
#define heap_full(h) ((h)->used == (h)->size)
+#define heap_empty(h) ((h)->used == 0)
+
#define DECLARE_FIFO(type, name) \
struct { \
size_t front, back, size, mask; \
while (!kthread_should_stop()) {
down_write(&dc->writeback_lock);
+ set_current_state(TASK_INTERRUPTIBLE);
if (!atomic_read(&dc->has_dirty) ||
(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) &&
!dc->writeback_running)) {
up_write(&dc->writeback_lock);
- set_current_state(TASK_INTERRUPTIBLE);
- if (kthread_should_stop())
+ if (kthread_should_stop()) {
+ set_current_state(TASK_RUNNING);
return 0;
+ }
schedule();
continue;
}
+ set_current_state(TASK_RUNNING);
searched_full_index = refill_dirty(dc);
dc->writeback_rate.rate = 1024;
dc->writeback_rate_minimum = 8;
- dc->writeback_rate_update_seconds = 5;
+ dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
dc->writeback_rate_p_term_inverse = 40;
dc->writeback_rate_i_term_inverse = 10000;
#define MAX_WRITEBACKS_IN_PASS 5
#define MAX_WRITESIZE_IN_PASS 5000 /* *512b */
+#define WRITEBACK_RATE_UPDATE_SECS_MAX 60
+#define WRITEBACK_RATE_UPDATE_SECS_DEFAULT 5
+
/*
* 14 (16384ths) is chosen here as something that each backing device
* should be a reasonable fraction of the share, and not to blow up
poll_wait(filp, &dm_global_eventq, wait);
if ((int)(atomic_read(&dm_global_event_nr) - priv->global_event_nr) > 0)
- mask |= POLLIN;
+ mask |= EPOLLIN;
return mask;
}
__poll_t mask;
if (md_unloading)
- return POLLIN|POLLRDNORM|POLLERR|POLLPRI;
+ return EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI;
poll_wait(filp, &md_event_waiters, wait);
/* always allow read */
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
if (seq->poll_event != atomic_read(&md_event_count))
- mask |= POLLERR | POLLPRI;
+ mask |= EPOLLERR | EPOLLPRI;
return mask;
}
__poll_t res = 0;
if (!cec_is_registered(adap))
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
mutex_lock(&adap->lock);
if (adap->is_configured &&
adap->transmit_queue_sz < CEC_MAX_MSG_TX_QUEUE_SZ)
- res |= POLLOUT | POLLWRNORM;
+ res |= EPOLLOUT | EPOLLWRNORM;
if (fh->queued_msgs)
- res |= POLLIN | POLLRDNORM;
+ res |= EPOLLIN | EPOLLRDNORM;
if (fh->total_queued_events)
- res |= POLLPRI;
+ res |= EPOLLPRI;
poll_wait(filp, &fh->wait, poll);
mutex_unlock(&adap->lock);
return res;
if (vdev->vfl_type == VFL_TYPE_VBI) {
if (fh->dev->ext_vv_data->capabilities & V4L2_CAP_SLICED_VBI_OUTPUT)
- return res | POLLOUT | POLLWRNORM;
+ return res | EPOLLOUT | EPOLLWRNORM;
if( 0 == fh->vbi_q.streaming )
return res | videobuf_poll_stream(file, &fh->vbi_q, wait);
q = &fh->vbi_q;
if (!buf) {
DEB_D("buf == NULL!\n");
- return res | POLLERR;
+ return res | EPOLLERR;
}
poll_wait(file, &buf->done, wait);
if (buf->state == VIDEOBUF_DONE || buf->state == VIDEOBUF_ERROR) {
DEB_D("poll succeeded!\n");
- return res | POLLIN | POLLRDNORM;
+ return res | EPOLLIN | EPOLLRDNORM;
}
DEB_D("nothing to poll for, buf->state:%d\n", buf->state);
rc = smsdvb_stats_wait_read(debug_data);
kref_put(&debug_data->refcount, smsdvb_debugfs_data_release);
- return rc > 0 ? POLLIN | POLLRDNORM : 0;
+ return rc > 0 ? EPOLLIN | EPOLLRDNORM : 0;
}
static ssize_t smsdvb_stats_read(struct file *file, char __user *user_buf,
struct vb2_buffer *vb = NULL;
unsigned long flags;
- if (!q->is_output && !(req_events & (POLLIN | POLLRDNORM)))
+ if (!q->is_output && !(req_events & (EPOLLIN | EPOLLRDNORM)))
return 0;
- if (q->is_output && !(req_events & (POLLOUT | POLLWRNORM)))
+ if (q->is_output && !(req_events & (EPOLLOUT | EPOLLWRNORM)))
return 0;
/*
*/
if (q->num_buffers == 0 && !vb2_fileio_is_active(q)) {
if (!q->is_output && (q->io_modes & VB2_READ) &&
- (req_events & (POLLIN | POLLRDNORM))) {
+ (req_events & (EPOLLIN | EPOLLRDNORM))) {
if (__vb2_init_fileio(q, 1))
- return POLLERR;
+ return EPOLLERR;
}
if (q->is_output && (q->io_modes & VB2_WRITE) &&
- (req_events & (POLLOUT | POLLWRNORM))) {
+ (req_events & (EPOLLOUT | EPOLLWRNORM))) {
if (__vb2_init_fileio(q, 0))
- return POLLERR;
+ return EPOLLERR;
/*
* Write to OUTPUT queue can be done immediately.
*/
- return POLLOUT | POLLWRNORM;
+ return EPOLLOUT | EPOLLWRNORM;
}
}
* error flag is set.
*/
if (!vb2_is_streaming(q) || q->error)
- return POLLERR;
+ return EPOLLERR;
/*
* If this quirk is set and QBUF hasn't been called yet then
- * return POLLERR as well. This only affects capture queues, output
+ * return EPOLLERR as well. This only affects capture queues, output
* queues will always initialize waiting_for_buffers to false.
* This quirk is set by V4L2 for backwards compatibility reasons.
*/
if (q->quirk_poll_must_check_waiting_for_buffers &&
- q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM)))
- return POLLERR;
+ q->waiting_for_buffers && (req_events & (EPOLLIN | EPOLLRDNORM)))
+ return EPOLLERR;
/*
* For output streams you can call write() as long as there are fewer
* buffers queued than there are buffers available.
*/
if (q->is_output && q->fileio && q->queued_count < q->num_buffers)
- return POLLOUT | POLLWRNORM;
+ return EPOLLOUT | EPOLLWRNORM;
if (list_empty(&q->done_list)) {
/*
* return immediately. DQBUF will return -EPIPE.
*/
if (q->last_buffer_dequeued)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
poll_wait(file, &q->done_wq, wait);
}
if (vb && (vb->state == VB2_BUF_STATE_DONE
|| vb->state == VB2_BUF_STATE_ERROR)) {
return (q->is_output) ?
- POLLOUT | POLLWRNORM :
- POLLIN | POLLRDNORM;
+ EPOLLOUT | EPOLLWRNORM :
+ EPOLLIN | EPOLLRDNORM;
}
return 0;
}
== V4L2_BUF_FLAG_TIMESTAMP_COPY;
/*
* For compatibility with vb1: if QBUF hasn't been called yet, then
- * return POLLERR as well. This only affects capture queues, output
+ * return EPOLLERR as well. This only affects capture queues, output
* queues will always initialize waiting_for_buffers to false.
*/
q->quirk_poll_must_check_waiting_for_buffers = true;
struct v4l2_fh *fh = file->private_data;
if (v4l2_event_pending(fh))
- res = POLLPRI;
- else if (req_events & POLLPRI)
+ res = EPOLLPRI;
+ else if (req_events & EPOLLPRI)
poll_wait(file, &fh->wait, wait);
}
WARN_ON(!lock);
if (lock && mutex_lock_interruptible(lock))
- return POLLERR;
+ return EPOLLERR;
fileio = q->fileio;
__poll_t mask = 0;
if ((!dmxdevfilter) || dmxdevfilter->dev->exit)
- return POLLERR;
+ return EPOLLERR;
if (dvb_vb2_is_streaming(&dmxdevfilter->vb2_ctx))
return dvb_vb2_poll(&dmxdevfilter->vb2_ctx, file, wait);
return 0;
if (dmxdevfilter->buffer.error)
- mask |= (POLLIN | POLLRDNORM | POLLPRI | POLLERR);
+ mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI | EPOLLERR);
if (!dvb_ringbuffer_empty(&dmxdevfilter->buffer))
- mask |= (POLLIN | POLLRDNORM | POLLPRI);
+ mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI);
return mask;
}
dprintk("%s\n", __func__);
if (dmxdev->exit)
- return POLLERR;
+ return EPOLLERR;
if (dvb_vb2_is_streaming(&dmxdev->dvr_vb2_ctx))
return dvb_vb2_poll(&dmxdev->dvr_vb2_ctx, file, wait);
#endif
if (need_ringbuffer) {
if (dmxdev->dvr_buffer.error)
- mask |= (POLLIN | POLLRDNORM | POLLPRI | POLLERR);
+ mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI | EPOLLERR);
if (!dvb_ringbuffer_empty(&dmxdev->dvr_buffer))
- mask |= (POLLIN | POLLRDNORM | POLLPRI);
+ mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI);
} else
- mask |= (POLLOUT | POLLWRNORM | POLLPRI);
+ mask |= (EPOLLOUT | EPOLLWRNORM | EPOLLPRI);
return mask;
}
dprintk("%s\n", __func__);
if (dvb_ca_en50221_io_read_condition(ca, &result, &slot) == 1)
- mask |= POLLIN;
+ mask |= EPOLLIN;
/* if there is something, return now */
if (mask)
poll_wait(file, &ca->wait_queue, wait);
if (dvb_ca_en50221_io_read_condition(ca, &result, &slot) == 1)
- mask |= POLLIN;
+ mask |= EPOLLIN;
return mask;
}
poll_wait (file, &fepriv->events.wait_queue, wait);
if (fepriv->events.eventw != fepriv->events.eventr)
- return (POLLIN | POLLRDNORM | POLLPRI);
+ return (EPOLLIN | EPOLLRDNORM | EPOLLPRI);
return 0;
}
static __poll_t fdtv_ca_io_poll(struct file *file, poll_table *wait)
{
- return POLLIN;
+ return EPOLLIN;
}
static const struct file_operations fdtv_ca_fops = {
case SAA6588_CMD_POLL:
a->result = 0;
if (s->data_available_for_read)
- a->result |= POLLIN | POLLRDNORM;
+ a->result |= EPOLLIN | EPOLLRDNORM;
poll_wait(a->instance, &s->read_queue, a->event_list);
break;
struct media_devnode *devnode = media_devnode_data(filp);
if (!media_devnode_is_registered(devnode))
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
if (!devnode->fops->poll)
return DEFAULT_POLLMASK;
return devnode->fops->poll(filp, poll);
__poll_t req_events = poll_requested_events(wait);
if (v4l2_event_pending(&fh->fh))
- rc = POLLPRI;
- else if (req_events & POLLPRI)
+ rc = EPOLLPRI;
+ else if (req_events & EPOLLPRI)
poll_wait(file, &fh->fh.wait, wait);
- if (!(req_events & (POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
return rc;
if (V4L2_BUF_TYPE_VBI_CAPTURE == fh->type) {
if (!check_alloc_btres_lock(fh->btv,fh,RESOURCE_VBI))
- return rc | POLLERR;
+ return rc | EPOLLERR;
return rc | videobuf_poll_stream(file, &fh->vbi, wait);
}
if (check_btres(fh,RESOURCE_VIDEO_STREAM)) {
/* streaming capture */
if (list_empty(&fh->cap.stream))
- return rc | POLLERR;
+ return rc | EPOLLERR;
buf = list_entry(fh->cap.stream.next,struct bttv_buffer,vb.stream);
} else {
/* read() capture */
if (NULL == fh->cap.read_buf) {
/* need to capture a new frame */
if (locked_btres(fh->btv,RESOURCE_VIDEO_STREAM))
- return rc | POLLERR;
+ return rc | EPOLLERR;
fh->cap.read_buf = videobuf_sg_alloc(fh->cap.msize);
if (NULL == fh->cap.read_buf)
- return rc | POLLERR;
+ return rc | EPOLLERR;
fh->cap.read_buf->memory = V4L2_MEMORY_USERPTR;
field = videobuf_next_field(&fh->cap);
if (0 != fh->cap.ops->buf_prepare(&fh->cap,fh->cap.read_buf,field)) {
kfree (fh->cap.read_buf);
fh->cap.read_buf = NULL;
- return rc | POLLERR;
+ return rc | EPOLLERR;
}
fh->cap.ops->buf_queue(&fh->cap,fh->cap.read_buf);
fh->cap.read_off = 0;
poll_wait(file, &buf->vb.done, wait);
if (buf->vb.state == VIDEOBUF_DONE ||
buf->vb.state == VIDEOBUF_ERROR)
- rc = rc | POLLIN|POLLRDNORM;
+ rc = rc | EPOLLIN|EPOLLRDNORM;
return rc;
}
__poll_t res = 0;
if (v4l2_event_pending(&fh->fh))
- res = POLLPRI;
- else if (req_events & POLLPRI)
+ res = EPOLLPRI;
+ else if (req_events & EPOLLPRI)
poll_wait(file, &fh->fh.wait, wait);
radio_enable(btv);
cmd.instance = file;
/* Start a capture if there is none */
if (!eof && !test_bit(CX18_F_S_STREAMING, &s->s_flags) &&
- (req_events & (POLLIN | POLLRDNORM))) {
+ (req_events & (EPOLLIN | EPOLLRDNORM))) {
int rc;
mutex_lock(&cx->serialize_lock);
if (rc) {
CX18_DEBUG_INFO("Could not start capture for %s (%d)\n",
s->name, rc);
- return POLLERR;
+ return EPOLLERR;
}
CX18_DEBUG_FILE("Encoder poll started capture\n");
}
__poll_t videobuf_poll = videobuf_poll_stream(filp, &s->vbuf_q, wait);
if (v4l2_event_pending(&id->fh))
- res |= POLLPRI;
- if (eof && videobuf_poll == POLLERR)
- return res | POLLHUP;
+ res |= EPOLLPRI;
+ if (eof && videobuf_poll == EPOLLERR)
+ return res | EPOLLHUP;
return res | videobuf_poll;
}
/* add stream's waitq to the poll list */
CX18_DEBUG_HI_FILE("Encoder poll\n");
if (v4l2_event_pending(&id->fh))
- res |= POLLPRI;
+ res |= EPOLLPRI;
else
poll_wait(filp, &s->waitq, wait);
if (atomic_read(&s->q_full.depth))
- return res | POLLIN | POLLRDNORM;
+ return res | EPOLLIN | EPOLLRDNORM;
if (eof)
- return res | POLLHUP;
+ return res | EPOLLHUP;
return res;
}
poll_wait(file, &input->dma->wq, wait);
poll_wait(file, &output->dma->wq, wait);
if (ddb_input_avail(input) >= 188)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (ddb_output_free(output) >= 188)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
/* Turn off the old-style vsync events */
clear_bit(IVTV_F_I_EV_VSYNC_ENABLED, &itv->i_flags);
if (v4l2_event_pending(&id->fh))
- res = POLLPRI;
+ res = EPOLLPRI;
} else {
/* This is the old-style API which is here only for backwards
compatibility. */
set_bit(IVTV_F_I_EV_VSYNC_ENABLED, &itv->i_flags);
if (test_bit(IVTV_F_I_EV_VSYNC, &itv->i_flags) ||
test_bit(IVTV_F_I_EV_DEC_STOPPED, &itv->i_flags))
- res = POLLPRI;
+ res = EPOLLPRI;
}
/* Allow write if buffers are available for writing */
if (s->q_free.buffers)
- res |= POLLOUT | POLLWRNORM;
+ res |= EPOLLOUT | EPOLLWRNORM;
return res;
}
/* Start a capture if there is none */
if (!eof && !test_bit(IVTV_F_S_STREAMING, &s->s_flags) &&
s->type != IVTV_ENC_STREAM_TYPE_RAD &&
- (req_events & (POLLIN | POLLRDNORM))) {
+ (req_events & (EPOLLIN | EPOLLRDNORM))) {
int rc;
mutex_lock(&itv->serialize_lock);
if (rc) {
IVTV_DEBUG_INFO("Could not start capture for %s (%d)\n",
s->name, rc);
- return POLLERR;
+ return EPOLLERR;
}
IVTV_DEBUG_FILE("Encoder poll started capture\n");
}
IVTV_DEBUG_HI_FILE("Encoder poll\n");
poll_wait(filp, &s->waitq, wait);
if (v4l2_event_pending(&id->fh))
- res |= POLLPRI;
+ res |= EPOLLPRI;
else
poll_wait(filp, &id->fh.wait, wait);
if (s->q_full.length || s->q_io.length)
- return res | POLLIN | POLLRDNORM;
+ return res | EPOLLIN | EPOLLRDNORM;
if (eof)
- return res | POLLHUP;
+ return res | EPOLLHUP;
return res;
}
mutex_lock(&meye.lock);
poll_wait(file, &meye.proc_list, wait);
if (kfifo_len(&meye.doneq))
- res |= POLLIN | POLLRDNORM;
+ res |= EPOLLIN | EPOLLRDNORM;
mutex_unlock(&meye.lock);
return res;
}
saa7164_histogram_update(&port->poll_interval,
port->last_poll_msecs_diff);
- if (!(req_events & (POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
return mask;
if (atomic_cmpxchg(&fh->v4l_reading, 0, 1) == 0) {
if (atomic_inc_return(&port->v4l_reader_count) == 1) {
if (saa7164_encoder_initialize(port) < 0)
- return mask | POLLERR;
+ return mask | EPOLLERR;
saa7164_encoder_start_streaming(port);
msleep(200);
}
/* Pull the first buffer from the used list */
if (!list_empty(&port->list_buf_used.list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
/* Pull the first buffer from the used list */
if (!list_empty(&port->list_buf_used.list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
poll_wait(file, &av7110->video_events.wait_queue, wait);
if (av7110->video_events.eventw != av7110->video_events.eventr)
- mask = POLLPRI;
+ mask = EPOLLPRI;
if ((file->f_flags & O_ACCMODE) != O_RDONLY) {
if (av7110->playing) {
if (FREE_COND)
- mask |= (POLLOUT | POLLWRNORM);
+ mask |= (EPOLLOUT | EPOLLWRNORM);
} else {
/* if not playing: may play if asked for */
- mask |= (POLLOUT | POLLWRNORM);
+ mask |= (EPOLLOUT | EPOLLWRNORM);
}
}
if (av7110->playing) {
if (dvb_ringbuffer_free(&av7110->aout) >= 20 * 1024)
- mask |= (POLLOUT | POLLWRNORM);
+ mask |= (EPOLLOUT | EPOLLWRNORM);
} else /* if not playing: may play if asked for */
- mask = (POLLOUT | POLLWRNORM);
+ mask = (EPOLLOUT | EPOLLWRNORM);
return mask;
}
poll_wait(file, &wbuf->queue, wait);
if (!dvb_ringbuffer_empty(rbuf))
- mask |= (POLLIN | POLLRDNORM);
+ mask |= (EPOLLIN | EPOLLRDNORM);
if (dvb_ringbuffer_free(wbuf) > 1024)
- mask |= (POLLOUT | POLLWRNORM);
+ mask |= (EPOLLOUT | EPOLLWRNORM);
return mask;
}
/* we should check whether buffers are ready to be synced on
* (w/o waits - O_NONBLOCK) here
- * if ready for read (sync), return POLLIN|POLLRDNORM,
- * if ready for write (sync), return POLLOUT|POLLWRNORM,
- * if error, return POLLERR,
- * if no buffers queued or so, return POLLNVAL
+ * if ready for read (sync), return EPOLLIN|EPOLLRDNORM,
+ * if ready for write (sync), return EPOLLOUT|EPOLLWRNORM,
+ * if error, return EPOLLERR,
+ * if no buffers queued or so, return EPOLLNVAL
*/
switch (fh->map_mode) {
if (fh->buffers.active != ZORAN_FREE &&
/* Buffer ready to DQBUF? */
zr->v4l_buffers.buffer[frame].state == BUZ_STATE_DONE)
- res |= POLLIN | POLLRDNORM;
+ res |= EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&zr->spinlock, flags);
break;
if (fh->buffers.active != ZORAN_FREE &&
zr->jpg_buffers.buffer[frame].state == BUZ_STATE_DONE) {
if (fh->map_mode == ZORAN_MAP_MODE_JPG_REC)
- res |= POLLIN | POLLRDNORM;
+ res |= EPOLLIN | EPOLLRDNORM;
else
- res |= POLLOUT | POLLWRNORM;
+ res |= EPOLLOUT | EPOLLWRNORM;
}
spin_unlock_irqrestore(&zr->spinlock, flags);
KERN_ERR
"%s: %s - internal error, unknown map_mode=%d\n",
ZR_DEVNAME(zr), __func__, fh->map_mode);
- res |= POLLERR;
+ res |= EPOLLERR;
}
return res;
__poll_t res = v4l2_ctrl_poll(file, wait);
if (V4L2_BUF_TYPE_VIDEO_CAPTURE != fh->type)
- return POLLERR;
+ return EPOLLERR;
- if (!(req_events & (POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
return res;
mutex_lock(&dev->lock);
*/
if ((!src_q->streaming || list_empty(&src_q->queued_list))
&& (!dst_q->streaming || list_empty(&dst_q->queued_list))) {
- rc = POLLERR;
+ rc = EPOLLERR;
goto end;
}
mutex_unlock(&dev->mfc_mutex);
poll_wait(file, &dst_q->done_wq, wait);
mutex_lock(&dev->mfc_mutex);
if (v4l2_event_pending(&ctx->fh))
- rc |= POLLPRI;
+ rc |= EPOLLPRI;
spin_lock_irqsave(&src_q->done_lock, flags);
if (!list_empty(&src_q->done_list))
src_vb = list_first_entry(&src_q->done_list, struct vb2_buffer,
done_entry);
if (src_vb && (src_vb->state == VB2_BUF_STATE_DONE
|| src_vb->state == VB2_BUF_STATE_ERROR))
- rc |= POLLOUT | POLLWRNORM;
+ rc |= EPOLLOUT | EPOLLWRNORM;
spin_unlock_irqrestore(&src_q->done_lock, flags);
spin_lock_irqsave(&dst_q->done_lock, flags);
if (!list_empty(&dst_q->done_list))
done_entry);
if (dst_vb && (dst_vb->state == VB2_BUF_STATE_DONE
|| dst_vb->state == VB2_BUF_STATE_ERROR))
- rc |= POLLIN | POLLRDNORM;
+ rc |= EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&dst_q->done_lock, flags);
end:
mutex_unlock(&dev->mfc_mutex);
{
struct soc_camera_device *icd = file->private_data;
struct soc_camera_host *ici = to_soc_camera_host(icd->parent);
- __poll_t res = POLLERR;
+ __poll_t res = EPOLLERR;
if (icd->streamer != file)
- return POLLERR;
+ return EPOLLERR;
mutex_lock(&ici->host_lock);
res = ici->ops->poll(file, pt);
__poll_t vivid_radio_rx_poll(struct file *file, struct poll_table_struct *wait)
{
- return POLLIN | POLLRDNORM | v4l2_ctrl_poll(file, wait);
+ return EPOLLIN | EPOLLRDNORM | v4l2_ctrl_poll(file, wait);
}
int vivid_radio_rx_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band)
__poll_t vivid_radio_tx_poll(struct file *file, struct poll_table_struct *wait)
{
- return POLLOUT | POLLWRNORM | v4l2_ctrl_poll(file, wait);
+ return EPOLLOUT | EPOLLWRNORM | v4l2_ctrl_poll(file, wait);
}
int vidioc_g_modulator(struct file *file, void *fh, struct v4l2_modulator *a)
__poll_t res = v4l2_ctrl_poll(file, wait);
poll_wait(file, &dev->read_queue, wait);
- if (dev->rdsstat == 0 && (req_events & (POLLIN | POLLRDNORM))) {
+ if (dev->rdsstat == 0 && (req_events & (EPOLLIN | EPOLLRDNORM))) {
mutex_lock(&dev->lock);
if (dev->rdsstat == 0)
cadet_start_rds(dev);
mutex_unlock(&dev->lock);
}
if (cadet_has_rds_data(dev))
- res |= POLLIN | POLLRDNORM;
+ res |= EPOLLIN | EPOLLRDNORM;
return res;
}
__poll_t req_events = poll_requested_events(pts);
__poll_t err = v4l2_ctrl_poll(file, pts);
- if (req_events & (POLLIN | POLLRDNORM)) {
+ if (req_events & (EPOLLIN | EPOLLRDNORM)) {
if (atomic_read(&radio->core->is_alive))
poll_wait(file, &radio->core->rds_read_queue, pts);
if (!atomic_read(&radio->core->is_alive))
- err = POLLHUP;
+ err = EPOLLHUP;
if (!kfifo_is_empty(&radio->core->rds_fifo))
- err = POLLIN | POLLRDNORM;
+ err = EPOLLIN | EPOLLRDNORM;
}
return err;
poll_wait(file, &radio->read_queue, pts);
if (radio->rd_index != radio->wr_index)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
} else if (core->mode == WL1273_MODE_TX) {
- return POLLOUT | POLLWRNORM;
+ return EPOLLOUT | EPOLLWRNORM;
}
return 0;
__poll_t req_events = poll_requested_events(pts);
__poll_t retval = v4l2_ctrl_poll(file, pts);
- if (req_events & (POLLIN | POLLRDNORM)) {
+ if (req_events & (EPOLLIN | EPOLLRDNORM)) {
/* switch on rds reception */
if ((radio->registers[SYSCONFIG1] & SYSCONFIG1_RDS) == 0)
si470x_rds_on(radio);
poll_wait(file, &radio->read_queue, pts);
if (radio->rd_index != radio->wr_index)
- retval |= POLLIN | POLLRDNORM;
+ retval |= EPOLLIN | EPOLLRDNORM;
}
return retval;
ret = fmc_is_rds_data_available(fmdev, file, pts);
mutex_unlock(&fmdev->mutex);
if (ret < 0)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
if (LIRC_IS_TIMEOUT(sample) && !fh->send_timeout_reports)
continue;
if (kfifo_put(&fh->rawir, sample))
- wake_up_poll(&fh->wait_poll, POLLIN | POLLRDNORM);
+ wake_up_poll(&fh->wait_poll, EPOLLIN | EPOLLRDNORM);
}
spin_unlock_irqrestore(&dev->lirc_fh_lock, flags);
}
spin_lock_irqsave(&dev->lirc_fh_lock, flags);
list_for_each_entry(fh, &dev->lirc_fh, list) {
if (kfifo_put(&fh->scancodes, *lsc))
- wake_up_poll(&fh->wait_poll, POLLIN | POLLRDNORM);
+ wake_up_poll(&fh->wait_poll, EPOLLIN | EPOLLRDNORM);
}
spin_unlock_irqrestore(&dev->lirc_fh_lock, flags);
}
poll_wait(file, &fh->wait_poll, wait);
if (!rcdev->registered) {
- events = POLLHUP | POLLERR;
+ events = EPOLLHUP | EPOLLERR;
} else if (rcdev->driver_type != RC_DRIVER_IR_RAW_TX) {
if (fh->rec_mode == LIRC_MODE_SCANCODE &&
!kfifo_is_empty(&fh->scancodes))
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
if (fh->rec_mode == LIRC_MODE_MODE2 &&
!kfifo_is_empty(&fh->rawir))
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
}
return events;
spin_lock_irqsave(&dev->lirc_fh_lock, flags);
list_for_each_entry(fh, &dev->lirc_fh, list)
- wake_up_poll(&fh->wait_poll, POLLHUP | POLLERR);
+ wake_up_poll(&fh->wait_poll, EPOLLHUP | EPOLLERR);
spin_unlock_irqrestore(&dev->lirc_fh_lock, flags);
cdev_device_del(&dev->lirc_cdev, &dev->lirc_dev);
{
__poll_t status = v4l2_ctrl_poll(filp, wait);
- if ((poll_requested_events(wait) & (POLLIN | POLLRDNORM)) &&
+ if ((poll_requested_events(wait) & (EPOLLIN | EPOLLRDNORM)) &&
!cam->streaming) {
/* Start streaming */
cpia2_usb_stream_start(cam,
poll_wait(filp, &cam->wq_stream, wait);
if (cam->curbuff->status == FRAME_READY)
- status |= POLLIN | POLLRDNORM;
+ status |= EPOLLIN | EPOLLRDNORM;
return status;
}
__poll_t res = 0;
if (v4l2_event_pending(&fh->fh))
- res |= POLLPRI;
+ res |= EPOLLPRI;
else
poll_wait(file, &fh->fh.wait, wait);
- if (!(req_events & (POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
return res;
mutex_lock(&dev->lock);
rc = check_dev(dev);
if (rc < 0)
- return POLLERR;
+ return EPOLLERR;
rc = res_get(fh);
if (unlikely(rc < 0))
- return POLLERR;
+ return EPOLLERR;
if (v4l2_event_pending(&fh->fh))
- res |= POLLPRI;
+ res |= EPOLLPRI;
else
poll_wait(filp, &fh->fh.wait, wait);
- if (!(req_events & (POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
return res;
if ((V4L2_BUF_TYPE_VIDEO_CAPTURE == fh->type) ||
mutex_unlock(&dev->lock);
return res;
}
- return res | POLLERR;
+ return res | EPOLLERR;
}
/*
gspca_dbg(gspca_dev, D_FRAM, "poll\n");
- if (req_events & POLLPRI)
+ if (req_events & EPOLLPRI)
ret |= v4l2_ctrl_poll(file, wait);
- if (req_events & (POLLIN | POLLRDNORM)) {
+ if (req_events & (EPOLLIN | EPOLLRDNORM)) {
/* if reqbufs is not done, the user would use read() */
if (gspca_dev->memory == GSPCA_MEMORY_NO) {
if (read_alloc(gspca_dev, file) != 0) {
- ret |= POLLERR;
+ ret |= EPOLLERR;
goto out;
}
}
/* check if an image has been received */
if (mutex_lock_interruptible(&gspca_dev->queue_lock) != 0) {
- ret |= POLLERR;
+ ret |= EPOLLERR;
goto out;
}
if (gspca_dev->fr_o != atomic_read(&gspca_dev->fr_i))
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
mutex_unlock(&gspca_dev->queue_lock);
}
out:
if (!gspca_dev->present)
- ret |= POLLHUP;
+ ret |= EPOLLHUP;
return ret;
}
struct hdpvr_device *dev = video_drvdata(filp);
__poll_t mask = v4l2_ctrl_poll(filp, wait);
- if (!(req_events & (POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLIN | EPOLLRDNORM)))
return mask;
mutex_lock(&dev->io_mutex);
buf = hdpvr_get_next_buffer(dev);
}
if (buf && buf->status == BUFSTAT_READY)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
int ret;
if (fh->fw_mode_flag) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
if (!fh->rhp) {
ret = pvr2_v4l2_iosetup(fh);
- if (ret) return POLLERR;
+ if (ret) return EPOLLERR;
}
poll_wait(file,&fh->wait_data,wait);
if (pvr2_ioread_avail(fh->rhp) >= 0) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
return mask;
poll_wait(fp, &dev->wait_frame, wait);
if (!is_present(dev))
- return POLLERR;
+ return EPOLLERR;
if (!list_empty(&dev->sio_full))
- return res | POLLIN | POLLRDNORM;
+ return res | EPOLLIN | EPOLLRDNORM;
return res;
}
__poll_t res = 0;
if (v4l2_event_pending(&fh->fh))
- res = POLLPRI;
- else if (req_events & POLLPRI)
+ res = EPOLLPRI;
+ else if (req_events & EPOLLPRI)
poll_wait(file, &fh->fh.wait, wait);
if (V4L2_BUF_TYPE_VIDEO_CAPTURE != fh->type)
- return res | POLLERR;
+ return res | EPOLLERR;
if (!!is_res_streaming(fh->dev, fh))
- return res | POLLERR;
+ return res | EPOLLERR;
if (!is_res_read(fh->dev, fh)) {
/* streaming capture */
if (list_empty(&fh->vb_vidq.stream))
- return res | POLLERR;
+ return res | EPOLLERR;
buf = list_entry(fh->vb_vidq.stream.next, struct tm6000_buffer, vb.stream);
poll_wait(file, &buf->vb.done, wait);
if (buf->vb.state == VIDEOBUF_DONE ||
buf->vb.state == VIDEOBUF_ERROR)
- return res | POLLIN | POLLRDNORM;
- } else if (req_events & (POLLIN | POLLRDNORM)) {
+ return res | EPOLLIN | EPOLLRDNORM;
+ } else if (req_events & (EPOLLIN | EPOLLRDNORM)) {
/* read() capture */
return res | videobuf_poll_stream(file, &fh->vb_vidq, wait);
}
struct v4l2_fh *fh = file->private_data;
if (v4l2_event_pending(fh))
- return POLLPRI;
+ return EPOLLPRI;
poll_wait(file, &fh->wait, wait);
return 0;
}
static __poll_t v4l2_poll(struct file *filp, struct poll_table_struct *poll)
{
struct video_device *vdev = video_devdata(filp);
- __poll_t res = POLLERR | POLLHUP;
+ __poll_t res = EPOLLERR | EPOLLHUP;
if (!vdev->fops->poll)
return DEFAULT_POLLMASK;
struct v4l2_fh *fh = file->private_data;
if (v4l2_event_pending(fh))
- rc = POLLPRI;
- else if (req_events & POLLPRI)
+ rc = EPOLLPRI;
+ else if (req_events & EPOLLPRI)
poll_wait(file, &fh->wait, wait);
- if (!(req_events & (POLLOUT | POLLWRNORM | POLLIN | POLLRDNORM)))
+ if (!(req_events & (EPOLLOUT | EPOLLWRNORM | EPOLLIN | EPOLLRDNORM)))
return rc;
}
*/
if ((!src_q->streaming || list_empty(&src_q->queued_list))
&& (!dst_q->streaming || list_empty(&dst_q->queued_list))) {
- rc |= POLLERR;
+ rc |= EPOLLERR;
goto end;
}
*/
if (dst_q->last_buffer_dequeued) {
spin_unlock_irqrestore(&dst_q->done_lock, flags);
- return rc | POLLIN | POLLRDNORM;
+ return rc | EPOLLIN | EPOLLRDNORM;
}
poll_wait(file, &dst_q->done_wq, wait);
done_entry);
if (src_vb && (src_vb->state == VB2_BUF_STATE_DONE
|| src_vb->state == VB2_BUF_STATE_ERROR))
- rc |= POLLOUT | POLLWRNORM;
+ rc |= EPOLLOUT | EPOLLWRNORM;
spin_unlock_irqrestore(&src_q->done_lock, flags);
spin_lock_irqsave(&dst_q->done_lock, flags);
done_entry);
if (dst_vb && (dst_vb->state == VB2_BUF_STATE_DONE
|| dst_vb->state == VB2_BUF_STATE_ERROR))
- rc |= POLLIN | POLLRDNORM;
+ rc |= EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&dst_q->done_lock, flags);
end:
struct v4l2_fh *fh = file->private_data;
if (!(sd->flags & V4L2_SUBDEV_FL_HAS_EVENTS))
- return POLLERR;
+ return EPOLLERR;
poll_wait(file, &fh->wait, wait);
if (v4l2_event_pending(fh))
- return POLLPRI;
+ return EPOLLPRI;
return 0;
}
if (!list_empty(&q->stream))
buf = list_entry(q->stream.next,
struct videobuf_buffer, stream);
- } else if (req_events & (POLLIN | POLLRDNORM)) {
+ } else if (req_events & (EPOLLIN | EPOLLRDNORM)) {
if (!q->reading)
__videobuf_read_start(q);
if (!q->reading) {
- rc = POLLERR;
+ rc = EPOLLERR;
} else if (NULL == q->read_buf) {
q->read_buf = list_entry(q->stream.next,
struct videobuf_buffer,
buf = q->read_buf;
}
if (!buf)
- rc = POLLERR;
+ rc = EPOLLERR;
if (0 == rc) {
poll_wait(file, &buf->done, wait);
case V4L2_BUF_TYPE_VBI_OUTPUT:
case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT:
case V4L2_BUF_TYPE_SDR_OUTPUT:
- rc = POLLOUT | POLLWRNORM;
+ rc = EPOLLOUT | EPOLLWRNORM;
break;
default:
- rc = POLLIN | POLLRDNORM;
+ rc = EPOLLIN | EPOLLRDNORM;
break;
}
}
if (irq_abb < num_irqs)
irq_count[irq_abb]++;
/*
- * This makes it possible to use poll for events (POLLPRI | POLLERR)
+ * This makes it possible to use poll for events (EPOLLPRI | EPOLLERR)
* from userspace on sysfs file named <irq-nr>
*/
sprintf(buf, "%d", irq);
spin_lock_irqsave(&ctx->lock, flags);
if (ctx_event_pending(ctx))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
else if (ctx->status == CLOSED)
/* Only error on closed when there are no futher events pending
*/
- mask |= POLLERR;
+ mask |= EPOLLERR;
spin_unlock_irqrestore(&ctx->lock, flags);
pr_devel("afu_poll pe: %i returning %#x\n", ctx->pe, mask);
poll_wait(fp, &data->ccb_waitq, wait);
if (is_channel_reset(driver_ccb))
- return POLLERR;
+ return EPOLLERR;
else if (ilo_pkt_recv(data->ilo_hw, driver_ccb))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(file, &lis3->misc_wait, wait);
if (atomic_read(&lis3->count))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
bool notify_en;
if (WARN_ON(!cl || !cl->dev))
- return POLLERR;
+ return EPOLLERR;
dev = cl->dev;
mutex_lock(&dev->device_lock);
- notify_en = cl->notify_en && (req_events & POLLPRI);
+ notify_en = cl->notify_en && (req_events & EPOLLPRI);
if (dev->dev_state != MEI_DEV_ENABLED ||
!mei_cl_is_connected(cl)) {
- mask = POLLERR;
+ mask = EPOLLERR;
goto out;
}
if (notify_en) {
poll_wait(file, &cl->ev_wait, wait);
if (cl->notify_ev)
- mask |= POLLPRI;
+ mask |= EPOLLPRI;
}
- if (req_events & (POLLIN | POLLRDNORM)) {
+ if (req_events & (EPOLLIN | EPOLLRDNORM)) {
poll_wait(file, &cl->rx_wait, wait);
if (!list_empty(&cl->rd_completed))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
else
mei_cl_read_start(cl, mei_cl_mtu(cl), file);
}
* message being sent to host SCIF. SCIF_DISCNCT message processing on the
* host SCIF sets the host COSM SCIF endpoint state to DISCONNECTED and wakes
* up the host COSM thread blocked in scif_poll(..) resulting in
- * scif_poll(..) returning POLLHUP.
+ * scif_poll(..) returning EPOLLHUP.
* 5. On the card, scif_peer_release_dev is next called which results in an
* SCIF_EXIT message being sent to the host and after receiving the
* SCIF_EXIT_ACK from the host the peer device teardown on the card is
* processing. This results in the COSM endpoint on the card being closed and
* the SCIF host peer device on the card getting unregistered similar to
* steps 3, 4 and 5 for the card shutdown case above. scif_poll(..) on the
- * host returns POLLHUP as a result.
+ * host returns EPOLLHUP as a result.
* 4. On the host, card peer device unregister and SCIF HW remove(..) also
* subsequently complete.
*
* ----------
* If a reset is issued after the card has crashed, there is no SCIF_DISCNT
* message from the card which would result in scif_poll(..) returning
- * POLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE
+ * EPOLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE
* message to itself resulting in the card SCIF peer device being unregistered,
* this results in a scif_peer_release_dev -> scif_cleanup_scifdev->
* scif_invalidate_ep call sequence which sets the endpoint state to
- * DISCONNECTED and results in scif_poll(..) returning POLLHUP.
+ * DISCONNECTED and results in scif_poll(..) returning EPOLLHUP.
*/
#define COSM_SCIF_BACKLOG 16
/*
* Close this cosm_device's endpoint after its peer endpoint on the card has
- * been closed. In all cases except MIC card crash POLLHUP on the host is
+ * been closed. In all cases except MIC card crash EPOLLHUP on the host is
* triggered by the client's endpoint being closed.
*/
static void cosm_scif_close(struct cosm_device *cdev)
while (1) {
pollepd.epd = cdev->epd;
- pollepd.events = POLLIN;
+ pollepd.events = EPOLLIN;
/* Drop the mutex before blocking in scif_poll(..) */
mutex_unlock(&cdev->cosm_mutex);
}
/* There is a message from the card */
- if (pollepd.revents & POLLIN)
+ if (pollepd.revents & EPOLLIN)
cosm_scif_recv(cdev);
/* The peer endpoint is closed or this endpoint disconnected */
- if (pollepd.revents & POLLHUP) {
+ if (pollepd.revents & EPOLLHUP) {
cosm_scif_close(cdev);
break;
}
while (!kthread_should_stop()) {
pollepd.epd = client_epd;
- pollepd.events = POLLIN;
+ pollepd.events = EPOLLIN;
rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_SEND_MSEC);
if (rc < 0) {
continue;
}
- if (pollepd.revents & POLLIN)
+ if (pollepd.revents & EPOLLIN)
cosm_client_recv();
msg.id = COSM_MSG_HEARTBEAT;
if (ep->state == SCIFEP_CONNECTED ||
ep->state == SCIFEP_DISCONNECTED ||
ep->conn_err)
- mask |= POLLOUT;
+ mask |= EPOLLOUT;
goto exit;
}
}
_scif_poll_wait(f, &ep->conwq, wait, ep);
if (ep->state == SCIFEP_LISTENING) {
if (ep->conreqcnt)
- mask |= POLLIN;
+ mask |= EPOLLIN;
goto exit;
}
}
/* Endpoint is connected or disconnected */
if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED) {
- if (poll_requested_events(wait) & POLLIN)
+ if (poll_requested_events(wait) & EPOLLIN)
_scif_poll_wait(f, &ep->recvwq, wait, ep);
- if (poll_requested_events(wait) & POLLOUT)
+ if (poll_requested_events(wait) & EPOLLOUT)
_scif_poll_wait(f, &ep->sendwq, wait, ep);
if (ep->state == SCIFEP_CONNECTED ||
ep->state == SCIFEP_DISCONNECTED) {
/* Data can be read without blocking */
if (scif_rb_count(&ep->qp_info.qp->inbound_q, 1))
- mask |= POLLIN;
+ mask |= EPOLLIN;
/* Data can be written without blocking */
if (scif_rb_space(&ep->qp_info.qp->outbound_q))
- mask |= POLLOUT;
- /* Return POLLHUP if endpoint is disconnected */
+ mask |= EPOLLOUT;
+ /* Return EPOLLHUP if endpoint is disconnected */
if (ep->state == SCIFEP_DISCONNECTED)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
goto exit;
}
}
- /* Return POLLERR if the endpoint is in none of the above states */
- mask |= POLLERR;
+ /* Return EPOLLERR if the endpoint is in none of the above states */
+ mask |= EPOLLERR;
exit:
spin_unlock(&ep->lock);
return mask;
pt = &table.pt;
while (1) {
for (i = 0; i < nfds; i++) {
- pt->_key = ufds[i].events | POLLERR | POLLHUP;
+ pt->_key = ufds[i].events | EPOLLERR | EPOLLHUP;
mask = __scif_pollfd(ufds[i].epd->anon,
pt, ufds[i].epd);
- mask &= ufds[i].events | POLLERR | POLLHUP;
+ mask &= ufds[i].events | EPOLLERR | EPOLLHUP;
if (mask) {
count++;
pt->_qproc = NULL;
static void vop_virtio_release_dev(struct device *_d)
{
- /*
- * No need for a release method similar to virtio PCI.
- * Provide an empty one to avoid getting a warning from core.
- */
+ struct virtio_device *vdev =
+ container_of(_d, struct virtio_device, dev);
+ struct _vop_vdev *vop_vdev =
+ container_of(vdev, struct _vop_vdev, vdev);
+
+ kfree(vop_vdev);
}
/*
unsigned int offset, struct vop_device *vpdev,
int dnode)
{
- struct _vop_vdev *vdev;
+ struct _vop_vdev *vdev, *reg_dev = NULL;
int ret;
u8 type = ioread8(&d->type);
vdev->c2h_vdev_db = ioread8(&vdev->dc->c2h_vdev_db);
ret = register_virtio_device(&vdev->vdev);
+ reg_dev = vdev;
if (ret) {
dev_err(_vop_dev(vdev),
"Failed to register vop device %u type %u\n",
free_irq:
vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev);
kfree:
- kfree(vdev);
+ if (reg_dev)
+ put_device(&vdev->vdev.dev);
+ else
+ kfree(vdev);
return ret;
}
iowrite8(-1, &dc->h2c_vdev_db);
if (status & VIRTIO_CONFIG_S_DRIVER_OK)
wait_for_completion(&vdev->reset_done);
- kfree(vdev);
+ put_device(&vdev->vdev.dev);
iowrite8(1, &dc->guest_ack);
dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n",
__func__, __LINE__, ioread8(&dc->guest_ack));
}
/*
- * We return POLLIN | POLLOUT from poll when new buffers are enqueued, and
+ * We return EPOLLIN | EPOLLOUT from poll when new buffers are enqueued, and
* not when previously enqueued buffers may be available. This means that
* in the card->host (TX) path, when userspace is unblocked by poll it
* must drain all available descriptors or it can stall.
mutex_lock(&vdev->vdev_mutex);
if (vop_vdev_inited(vdev)) {
- mask = POLLERR;
+ mask = EPOLLERR;
goto done;
}
poll_wait(f, &vdev->waitq, wait);
if (vop_vdev_inited(vdev)) {
- mask = POLLERR;
+ mask = EPOLLERR;
} else if (vdev->poll_wake) {
vdev->poll_wake = 0;
- mask = POLLIN | POLLOUT;
+ mask = EPOLLIN | EPOLLOUT;
}
done:
mutex_unlock(&vdev->vdev_mutex);
mutex_unlock(&ctx->status_mutex);
if (afu_events_pending(ctx))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
else if (closed)
- mask = POLLERR;
+ mask = EPOLLERR;
return mask;
}
poll_wait(file, &dev->wait, wait);
if (!(dev->status & PHB_RUNNING))
- mask = POLLERR;
+ mask = EPOLLERR;
else if (atomic_read(&dev->counter))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
pr_debug("phantom_poll end: %x/%d\n", mask, atomic_read(&dev->counter));
if (context->pending_datagrams > 0 ||
vmci_handle_arr_get_size(
context->pending_doorbell_array) > 0) {
- mask = POLLIN;
+ mask = EPOLLIN;
}
spin_unlock(&context->lock);
}
config MMC_TOSHIBA_PCI
tristate "Toshiba Type A SD/MMC Card Interface Driver"
depends on PCI
- help
config MMC_BCM2835
tristate "Broadcom BCM2835 SDHOST MMC Controller support"
struct q_desc_mem {
dma_addr_t dma;
u64 size;
- u16 q_len;
+ u32 q_len;
dma_addr_t phys_base;
void *base;
void *unalign_base;
adapter->regs = regs;
err = t4_wait_dev_ready(regs);
if (err < 0)
- goto out_unmap_bar0;
+ goto out_free_adapter;
/* We control everything through one PF */
whoami = readl(regs + PL_WHOAMI_A);
{
kfree(adapter->tx_stats_buffers);
kfree(adapter->rx_stats_buffers);
+ adapter->tx_stats_buffers = NULL;
+ adapter->rx_stats_buffers = NULL;
}
static int init_stats_buffers(struct ibmvnic_adapter *adapter)
kfree(adapter->vpd->buff);
kfree(adapter->vpd);
+
+ adapter->vpd = NULL;
}
static void release_tx_pools(struct ibmvnic_adapter *adapter)
if (dma_mapping_error(dev, adapter->vpd->dma_addr)) {
dev_err(dev, "Could not map VPD buffer\n");
kfree(adapter->vpd->buff);
+ adapter->vpd->buff = NULL;
return -ENOMEM;
}
hdrs += 2;
}
/* determine if l2/3/4 headers are sent to firmware */
- if ((*hdrs >> 7) & 1 &&
- (skb->protocol == htons(ETH_P_IP) ||
- skb->protocol == htons(ETH_P_IPV6) ||
- skb->protocol == htons(ETH_P_ARP))) {
+ if ((*hdrs >> 7) & 1) {
build_hdr_descs_arr(tx_buff, &num_entries, *hdrs);
tx_crq.v1.n_crq_elem = num_entries;
tx_buff->indir_arr[0] = tx_crq;
return rc;
} else if (adapter->req_rx_queues != old_num_rx_queues ||
adapter->req_tx_queues != old_num_tx_queues) {
+ adapter->map_id = 1;
release_rx_pools(adapter);
release_tx_pools(adapter);
init_rx_pools(netdev);
u16 offset;
u8 flags = 0;
- if (unlikely(adapter->resetting)) {
+ if (unlikely(adapter->resetting &&
+ adapter->reset_reason != VNIC_RESET_NON_FATAL)) {
enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]);
napi_complete_done(napi, frames_processed);
return frames_processed;
cpu_to_be64(u64_crq[1]));
if (rc) {
- if (rc == H_CLOSED)
+ if (rc == H_CLOSED) {
dev_warn(dev, "CRQ Queue closed\n");
+ if (adapter->resetting)
+ ibmvnic_reset(adapter, VNIC_RESET_FATAL);
+ }
+
dev_warn(dev, "Send error (rc=%d)\n", rc);
}
struct i40e_pf *pf = vsi->back;
u16 sections = 0;
u8 netdev_tc = 0;
- u16 numtc = 0;
+ u16 numtc = 1;
u16 qcount;
u8 offset;
u16 qmap;
sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
offset = 0;
+ /* Number of queues per enabled TC */
+ num_tc_qps = vsi->alloc_queue_pairs;
if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
/* Find numtc from enabled TC bitmap */
- for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
if (enabled_tc & BIT(i)) /* TC is enabled */
numtc++;
}
dev_warn(&pf->pdev->dev, "DCB is enabled but no TC enabled, forcing TC0\n");
numtc = 1;
}
- } else {
- /* At least TC0 is enabled in non-DCB, non-MQPRIO case */
- numtc = 1;
+ num_tc_qps = num_tc_qps / numtc;
+ num_tc_qps = min_t(int, num_tc_qps,
+ i40e_pf_get_max_q_per_tc(pf));
}
vsi->tc_config.numtc = numtc;
vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1;
- /* Number of queues per enabled TC */
- qcount = vsi->alloc_queue_pairs;
-
- num_tc_qps = qcount / numtc;
- num_tc_qps = min_t(int, num_tc_qps, i40e_pf_get_max_q_per_tc(pf));
/* Do not allow use more TC queue pairs than MSI-X vectors exist */
if (pf->flags & I40E_FLAG_MSIX_ENABLED)
switch (vsi->type) {
case I40E_VSI_MAIN:
- qcount = min_t(int, pf->alloc_rss_size,
- num_tc_qps);
- break;
+ if (!(pf->flags & (I40E_FLAG_FD_SB_ENABLED |
+ I40E_FLAG_FD_ATR_ENABLED)) ||
+ vsi->tc_config.enabled_tc != 1) {
+ qcount = min_t(int, pf->alloc_rss_size,
+ num_tc_qps);
+ break;
+ }
case I40E_VSI_FDIR:
case I40E_VSI_SRIOV:
case I40E_VSI_VMDQ2:
#include "../nfpcore/nfp_cpp.h"
#include "../nfpcore/nfp_nffw.h"
+#include "../nfpcore/nfp_nsp.h"
#include "../nfp_app.h"
#include "../nfp_main.h"
#include "../nfp_net.h"
static int
nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
{
+ struct nfp_pf *pf = app->pf;
struct nfp_bpf_vnic *bv;
int err;
+ if (!pf->eth_tbl) {
+ nfp_err(pf->cpp, "No ETH table\n");
+ return -EINVAL;
+ }
+ if (pf->max_data_vnics != pf->eth_tbl->count) {
+ nfp_err(pf->cpp, "ETH entries don't match vNICs (%d vs %d)\n",
+ pf->max_data_vnics, pf->eth_tbl->count);
+ return -EINVAL;
+ }
+
bv = kzalloc(sizeof(*bv), GFP_KERNEL);
if (!bv)
return -ENOMEM;
return err;
bv->tc_prog = cls_bpf->prog;
+ nn->port->tc_offload_cnt = !!bv->tc_prog;
return 0;
}
}
}
-static bool nfp_bpf_tc_busy(struct nfp_app *app, struct nfp_net *nn)
-{
- struct nfp_bpf_vnic *bv = nn->app_priv;
-
- return !!bv->tc_prog;
-}
-
static int
nfp_bpf_change_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu)
{
.ctrl_msg_rx = nfp_bpf_ctrl_msg_rx,
.setup_tc = nfp_bpf_setup_tc,
- .tc_busy = nfp_bpf_tc_busy,
.bpf = nfp_ndo_bpf,
.xdp_offload = nfp_bpf_xdp_offload,
};
struct tc_cls_flower_offload *flow, bool egress)
{
enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
+ struct nfp_port *port = nfp_port_from_netdev(netdev);
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_payload *flow_pay;
struct nfp_fl_key_ls *key_layer;
INIT_HLIST_NODE(&flow_pay->link);
flow_pay->tc_flower_cookie = flow->cookie;
hash_add_rcu(priv->flow_table, &flow_pay->link, flow->cookie);
+ port->tc_offload_cnt++;
/* Deallocate flow payload when flower rule has been destroyed. */
kfree(key_layer);
nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
struct tc_cls_flower_offload *flow)
{
+ struct nfp_port *port = nfp_port_from_netdev(netdev);
struct nfp_fl_payload *nfp_flow;
int err;
err_free_flow:
hash_del_rcu(&nfp_flow->link);
+ port->tc_offload_cnt--;
kfree(nfp_flow->action_data);
kfree(nfp_flow->mask_data);
kfree(nfp_flow->unmasked_data);
* @stop: stop application logic
* @ctrl_msg_rx: control message handler
* @setup_tc: setup TC ndo
- * @tc_busy: TC HW offload busy (rules loaded)
* @bpf: BPF ndo offload-related calls
* @xdp_offload: offload an XDP program
* @eswitch_mode_get: get SR-IOV eswitch mode
int (*setup_tc)(struct nfp_app *app, struct net_device *netdev,
enum tc_setup_type type, void *type_data);
- bool (*tc_busy)(struct nfp_app *app, struct nfp_net *nn);
int (*bpf)(struct nfp_app *app, struct nfp_net *nn,
struct netdev_bpf *xdp);
int (*xdp_offload)(struct nfp_app *app, struct nfp_net *nn,
return app && app->type->setup_tc;
}
-static inline bool nfp_app_tc_busy(struct nfp_app *app, struct nfp_net *nn)
-{
- if (!app || !app->type->tc_busy)
- return false;
- return app->type->tc_busy(app, nn);
-}
-
static inline int nfp_app_setup_tc(struct nfp_app *app,
struct net_device *netdev,
enum tc_setup_type type, void *type_data)
if (!unreg_is_imm(reg))
reg = FIELD_GET(OP_IMMED_B_SRC, instr);
- return (reg & 0xff) | FIELD_GET(OP_IMMED_IMM, instr);
+ return (reg & 0xff) | FIELD_GET(OP_IMMED_IMM, instr) << 8;
}
void immed_set_value(u64 *instr, u16 immed)
MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("The Netronome Flow Processor (NFP) driver.");
+MODULE_VERSION(UTS_RELEASE);
new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER;
}
- if (changed & NETIF_F_HW_TC && nfp_app_tc_busy(nn->app, nn)) {
- nn_err(nn, "Cannot disable HW TC offload while in use\n");
- return -EBUSY;
- }
+ err = nfp_port_set_features(netdev, features);
+ if (err)
+ return err;
nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n",
netdev->features, features, changed);
netdev->features = netdev->hw_features;
- if (nfp_app_has_tc(nn->app))
+ if (nfp_app_has_tc(nn->app) && nn->port)
netdev->hw_features |= NETIF_F_HW_TC;
/* Advertise but disable TSO by default. */
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = nn->max_mtu;
+ netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
+
netif_carrier_off(netdev);
nfp_net_set_ethtool_ops(netdev);
#define NFP_NET_RX_OFFSET 32
/**
- * Maximum header size supported for LSO frames
+ * LSO parameters
+ * %NFP_NET_LSO_MAX_HDR_SZ: Maximum header size supported for LSO frames
+ * %NFP_NET_LSO_MAX_SEGS: Maximum number of segments LSO frame can produce
*/
#define NFP_NET_LSO_MAX_HDR_SZ 255
+#define NFP_NET_LSO_MAX_SEGS 64
/**
* Prepend field types
.ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk,
.ndo_get_vf_config = nfp_app_get_vf_config,
.ndo_set_vf_link_state = nfp_app_set_vf_link_state,
+ .ndo_set_features = nfp_port_set_features,
};
static void nfp_repr_clean(struct nfp_repr *repr)
*/
#include <linux/lockdep.h>
+#include <linux/netdevice.h>
#include <net/switchdev.h>
#include "nfpcore/nfp_cpp.h"
return nfp_app_setup_tc(port->app, netdev, type, type_data);
}
+int nfp_port_set_features(struct net_device *netdev, netdev_features_t features)
+{
+ struct nfp_port *port;
+
+ port = nfp_port_from_netdev(netdev);
+ if (!port)
+ return 0;
+
+ if ((netdev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC) &&
+ port->tc_offload_cnt) {
+ netdev_err(netdev, "Cannot disable HW TC offload while offloads active\n");
+ return -EBUSY;
+ }
+
+ return 0;
+}
+
struct nfp_port *
nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id)
{
* @netdev: backpointer to associated netdev
* @type: what port type does the entity represent
* @flags: port flags
+ * @tc_offload_cnt: number of active TC offloads, how offloads are counted
+ * is not defined, use as a boolean
* @app: backpointer to the app structure
* @dl_port: devlink port structure
* @eth_id: for %NFP_PORT_PHYS_PORT port ID in NFP enumeration scheme
enum nfp_port_type type;
unsigned long flags;
+ unsigned long tc_offload_cnt;
struct nfp_app *app;
return port->type == NFP_PORT_PF_PORT || port->type == NFP_PORT_VF_PORT;
}
+int
+nfp_port_set_features(struct net_device *netdev, netdev_features_t features);
+
struct nfp_port *nfp_port_from_netdev(struct net_device *netdev);
struct nfp_port *
nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id);
/* Mask GMAC interrupts */
value = GMAC_INT_DEFAULT_MASK;
- if (hw->pmt)
- value &= ~GMAC_INT_DISABLE_PMT;
if (hw->pcs)
value &= ~GMAC_INT_DISABLE_PCS;
#define GMAC_PCS_IRQ_DEFAULT (GMAC_INT_RGSMIIS | GMAC_INT_PCS_LINK | \
GMAC_INT_PCS_ANE)
-#define GMAC_INT_DEFAULT_MASK (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN)
+#define GMAC_INT_DEFAULT_ENABLE (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN)
enum dwmac4_irq_status {
time_stamp_irq = 0x00001000,
writel(value, ioaddr + GMAC_CONFIG);
- /* Mask GMAC interrupts */
- value = GMAC_INT_DEFAULT_MASK;
- if (hw->pmt)
- value |= GMAC_INT_PMT_EN;
+ /* Enable GMAC interrupts */
+ value = GMAC_INT_DEFAULT_ENABLE;
+
if (hw->pcs)
value |= GMAC_PCS_IRQ_DEFAULT;
struct stmmac_extra_stats *x)
{
void __iomem *ioaddr = hw->pcsr;
- u32 intr_status;
+ u32 intr_status = readl(ioaddr + GMAC_INT_STATUS);
+ u32 intr_enable = readl(ioaddr + GMAC_INT_EN);
int ret = 0;
- intr_status = readl(ioaddr + GMAC_INT_STATUS);
+ /* Discard disabled bits */
+ intr_status &= intr_enable;
/* Not used events (e.g. MMC interrupts) are not handled. */
if ((intr_status & mmc_tx_irq))
+# SPDX-License-Identifier: GPL-2.0
#
# Sun network device configuration
#
+// SPDX-License-Identifier: GPL-2.0
/* cassini.c: Sun Microsystems Cassini(+) ethernet driver.
*
* Copyright (C) 2004 Sun Microsystems Inc.
+/* SPDX-License-Identifier: GPL-2.0 */
/* $Id: cassini.h,v 1.16 2004/08/17 21:15:16 zaumen Exp $
* cassini.h: Definitions for Sun Microsystems Cassini(+) ethernet driver.
*
+// SPDX-License-Identifier: GPL-2.0
/* ldmvsw.c: Sun4v LDOM Virtual Switch Driver.
*
* Copyright (C) 2016-2017 Oracle. All rights reserved.
+// SPDX-License-Identifier: GPL-2.0
/* niu.c: Neptune ethernet driver.
*
* Copyright (C) 2007, 2008 David S. Miller (davem@davemloft.net)
+// SPDX-License-Identifier: GPL-2.0
/* sunbmac.c: Driver for Sparc BigMAC 100baseT ethernet adapters.
*
* Copyright (C) 1997, 1998, 1999, 2003, 2008 David S. Miller (davem@davemloft.net)
+// SPDX-License-Identifier: GPL-2.0
/* $Id: sungem.c,v 1.44.2.22 2002/03/13 01:18:12 davem Exp $
* sungem.c: Sun GEM ethernet driver.
*
+// SPDX-License-Identifier: GPL-2.0
/* sunhme.c: Sparc HME/BigMac 10/100baseT half/full duplex auto switching,
* auto carrier detecting ethernet driver. Also known as the
* "Happy Meal Ethernet" found on SunSwift SBUS cards.
+// SPDX-License-Identifier: GPL-2.0
/* sunqe.c: Sparc QuadEthernet 10baseT SBUS card driver.
* Once again I am out to prove that every ethernet
* controller out there can be most efficiently programmed
+// SPDX-License-Identifier: GPL-2.0
/* sunvnet.c: Sun LDOM Virtual Network Driver.
*
* Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
+// SPDX-License-Identifier: GPL-2.0
/* sunvnet.c: Sun LDOM Virtual Network Driver.
*
* Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
q_idx = q_idx % cpsw->tx_ch_num;
txch = cpsw->txv[q_idx].ch;
+ txq = netdev_get_tx_queue(ndev, q_idx);
ret = cpsw_tx_packet_submit(priv, skb, txch);
if (unlikely(ret != 0)) {
cpsw_err(priv, tx_err, "desc submit failed\n");
* tell the kernel to stop sending us tx frames.
*/
if (unlikely(!cpdma_check_free_tx_desc(txch))) {
- txq = netdev_get_tx_queue(ndev, q_idx);
netif_tx_stop_queue(txq);
+
+ /* Barrier, so that stop_queue visible to other cpus */
+ smp_mb__after_atomic();
+
+ if (cpdma_check_free_tx_desc(txch))
+ netif_tx_wake_queue(txq);
}
return NETDEV_TX_OK;
fail:
ndev->stats.tx_dropped++;
- txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
netif_tx_stop_queue(txq);
+
+ /* Barrier, so that stop_queue visible to other cpus */
+ smp_mb__after_atomic();
+
+ if (cpdma_check_free_tx_desc(txch))
+ netif_tx_wake_queue(txq);
+
return NETDEV_TX_BUSY;
}
poll_wait(filp, &priv->test.readq, ptable);
if (!kfifo_is_empty(&priv->test.up_fifo))
- return_flags |= (POLLIN | POLLRDNORM);
+ return_flags |= (EPOLLIN | EPOLLRDNORM);
if (wait_event_interruptible(
priv->test.readq,
!kfifo_is_empty(&priv->test.up_fifo))) {
- return POLLERR;
+ return EPOLLERR;
}
return return_flags;
}
phy_resume(phydev);
/* make sure interrupts are re-enabled for the PHY */
- if (phydev->irq != PHY_POLL) {
+ if (phy_interrupt_is_valid(phydev)) {
err = phy_enable_interrupts(phydev);
if (err < 0)
break;
if (!pf)
return 0;
poll_wait(file, &pf->rwait, wait);
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
if (skb_peek(&pf->rq))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (pf->dead)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
else if (pf->kind == INTERFACE) {
/* see comment in ppp_read */
struct ppp *ppp = PF_TO_PPP(pf);
ppp_recv_lock(ppp);
if (ppp->n_channels == 0 &&
(ppp->flags & SC_LOOP_TRAFFIC) == 0)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
ppp_recv_unlock(ppp);
}
}
wake_up:
- wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND);
+ wake_up_interruptible_poll(sk_sleep(&q->sk), EPOLLIN | EPOLLRDNORM | EPOLLRDBAND);
return RX_HANDLER_CONSUMED;
drop:
wqueue = sk_sleep(sk);
if (wqueue && waitqueue_active(wqueue))
- wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
+ wake_up_interruptible_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
}
static void tap_sock_destruct(struct sock *sk)
static __poll_t tap_poll(struct file *file, poll_table *wait)
{
struct tap_queue *q = file->private_data;
- __poll_t mask = POLLERR;
+ __poll_t mask = EPOLLERR;
if (!q)
goto out;
poll_wait(file, &q->wq.wait, wait);
if (!ptr_ring_empty(&q->ring))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (sock_writeable(&q->sk) ||
(!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) &&
sock_writeable(&q->sk)))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
out:
return mask;
struct tun_struct *detached;
struct ptr_ring tx_ring;
struct xdp_rxq_info xdp_rxq;
+ int xdp_pending_pkts;
};
struct tun_flow_entry {
__poll_t mask = 0;
if (!tun)
- return POLLERR;
+ return EPOLLERR;
sk = tfile->socket.sk;
poll_wait(file, sk_sleep(sk), wait);
if (!ptr_ring_empty(&tfile->tx_ring))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (tun->dev->flags & IFF_UP &&
(sock_writeable(sk) ||
(!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
sock_writeable(sk))))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (tun->dev->reg_state != NETREG_REGISTERED)
- mask = POLLERR;
+ mask = EPOLLERR;
tun_put(tun);
return mask;
case XDP_REDIRECT:
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
+ ++tfile->xdp_pending_pkts;
err = xdp_do_redirect(tun->dev, &xdp, xdp_prog);
if (err)
goto err_redirect;
result = tun_get_user(tun, tfile, NULL, from,
file->f_flags & O_NONBLOCK, false);
+ if (tfile->xdp_pending_pkts) {
+ tfile->xdp_pending_pkts = 0;
+ xdp_do_flush_map();
+ }
+
tun_put(tun);
return result;
}
wqueue = sk_sleep(sk);
if (wqueue && waitqueue_active(wqueue))
- wake_up_interruptible_sync_poll(wqueue, POLLOUT |
- POLLWRNORM | POLLWRBAND);
+ wake_up_interruptible_sync_poll(wqueue, EPOLLOUT |
+ EPOLLWRNORM | EPOLLWRBAND);
tfile = container_of(sk, struct tun_file, sk);
kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
m->msg_flags & MSG_DONTWAIT,
m->msg_flags & MSG_MORE);
+
+ if (tfile->xdp_pending_pkts >= NAPI_POLL_WEIGHT ||
+ !(m->msg_flags & MSG_MORE)) {
+ tfile->xdp_pending_pkts = 0;
+ xdp_do_flush_map();
+ }
+
tun_put(tun);
return ret;
}
sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring));
+ tfile->xdp_pending_pkts = 0;
return 0;
}
.target_64bit = false,
.rx_ring_fill_level = HTT_RX_RING_FILL_LEVEL,
},
+ {
+ .id = QCA988X_HW_2_0_VERSION,
+ .dev_id = QCA988X_2_0_DEVICE_ID_UBNT,
+ .name = "qca988x hw2.0 ubiquiti",
+ .patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
+ .uart_pin = 7,
+ .cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL,
+ .otp_exe_param = 0,
+ .channel_counters_freq_hz = 88000,
+ .max_probe_resp_desc_thres = 0,
+ .cal_data_len = 2116,
+ .fw = {
+ .dir = QCA988X_HW_2_0_FW_DIR,
+ .board = QCA988X_HW_2_0_BOARD_DATA_FILE,
+ .board_size = QCA988X_BOARD_DATA_SZ,
+ .board_ext_size = QCA988X_BOARD_EXT_DATA_SZ,
+ },
+ .hw_ops = &qca988x_ops,
+ .decap_align_bytes = 4,
+ .spectral_bin_discard = 0,
+ .vht160_mcs_rx_highest = 0,
+ .vht160_mcs_tx_highest = 0,
+ .n_cipher_suites = 8,
+ .num_peers = TARGET_TLV_NUM_PEERS,
+ .ast_skid_limit = 0x10,
+ .num_wds_entries = 0x20,
+ .target_64bit = false,
+ .rx_ring_fill_level = HTT_RX_RING_FILL_LEVEL,
+ },
{
.id = QCA9887_HW_1_0_VERSION,
.dev_id = QCA9887_1_0_DEVICE_ID,
len -= sizeof(*hdr);
data = hdr->data;
- /* jump over the padding */
- ie_len = ALIGN(ie_len, 4);
-
- if (len < ie_len) {
+ if (len < ALIGN(ie_len, 4)) {
ath10k_err(ar, "invalid length for board ie_id %d ie_len %zu len %zu\n",
ie_id, ie_len, len);
ret = -EINVAL;
goto out;
}
+ /* jump over the padding */
+ ie_len = ALIGN(ie_len, 4);
+
len -= ie_len;
data += ie_len;
}
len -= sizeof(*hdr);
data += sizeof(*hdr);
- /* jump over the padding */
- ie_len = ALIGN(ie_len, 4);
-
if (len < ie_len) {
ath10k_err(ar, "invalid length for FW IE %d (%zu < %zu)\n",
ie_id, len, ie_len);
break;
}
+ /* jump over the padding */
+ ie_len = ALIGN(ie_len, 4);
+
len -= ie_len;
data += ie_len;
}
/*
* Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
*
* Permission to use, copy, modify, and/or distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
{
.type = ATH10K_MEM_REGION_TYPE_DRAM,
.start = 0x400000,
- .len = 0x90000,
+ .len = 0xa8000,
.name = "DRAM",
.section_table = {
.sections = NULL,
/*
* Copyright (c) 2005-2011 Atheros Communications Inc.
* Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
*
* Permission to use, copy, modify, and/or distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
void ath10k_debug_print_board_info(struct ath10k *ar)
{
char boardinfo[100];
+ const struct firmware *board;
+ u32 crc;
if (ar->id.bmi_ids_valid)
scnprintf(boardinfo, sizeof(boardinfo), "%d:%d",
else
scnprintf(boardinfo, sizeof(boardinfo), "N/A");
+ board = ar->normal_mode_fw.board;
+ if (!IS_ERR_OR_NULL(board))
+ crc = crc32_le(0, board->data, board->size);
+ else
+ crc = 0;
+
ath10k_info(ar, "board_file api %d bmi_id %s crc32 %08x",
ar->bd_api,
boardinfo,
- crc32_le(0, ar->normal_mode_fw.board->data,
- ar->normal_mode_fw.board->size));
+ crc);
}
void ath10k_debug_print_boot_info(struct ath10k *ar)
#define ATH10K_FW_DIR "ath10k"
+#define QCA988X_2_0_DEVICE_ID_UBNT (0x11ac)
#define QCA988X_2_0_DEVICE_ID (0x003c)
#define QCA6164_2_1_DEVICE_ID (0x0041)
#define QCA6174_2_1_DEVICE_ID (0x003e)
#define ATH10K_DIAG_TRANSFER_LIMIT 0x5000
static const struct pci_device_id ath10k_pci_id_table[] = {
+ /* PCI-E QCA988X V2 (Ubiquiti branded) */
+ { PCI_VDEVICE(UBIQUITI, QCA988X_2_0_DEVICE_ID_UBNT) },
+
{ PCI_VDEVICE(ATHEROS, QCA988X_2_0_DEVICE_ID) }, /* PCI-E QCA988X V2 */
{ PCI_VDEVICE(ATHEROS, QCA6164_2_1_DEVICE_ID) }, /* PCI-E QCA6164 V2.1 */
{ PCI_VDEVICE(ATHEROS, QCA6174_2_1_DEVICE_ID) }, /* PCI-E QCA6174 V2.1 */
* hacks. ath10k doesn't have them and these devices crash horribly
* because of that.
*/
+ { QCA988X_2_0_DEVICE_ID_UBNT, QCA988X_HW_2_0_CHIP_ID_REV },
{ QCA988X_2_0_DEVICE_ID, QCA988X_HW_2_0_CHIP_ID_REV },
{ QCA6164_2_1_DEVICE_ID, QCA6174_HW_2_1_CHIP_ID_REV },
struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
switch (ar_pci->pdev->device) {
+ case QCA988X_2_0_DEVICE_ID_UBNT:
case QCA988X_2_0_DEVICE_ID:
case QCA99X0_2_0_DEVICE_ID:
case QCA9888_2_0_DEVICE_ID:
u32 (*targ_cpu_to_ce_addr)(struct ath10k *ar, u32 addr);
switch (pci_dev->device) {
+ case QCA988X_2_0_DEVICE_ID_UBNT:
case QCA988X_2_0_DEVICE_ID:
hw_rev = ATH10K_HW_QCA988X;
pci_ps = false;
s16 ath9k_hw_getchan_noise(struct ath_hw *ah, struct ath9k_channel *chan,
s16 nf)
{
- s8 noise = ath9k_hw_get_default_nf(ah, chan, 0);
+ s8 noise = ATH_DEFAULT_NOISE_FLOOR;
if (nf) {
s8 delta = nf - ATH9K_NF_CAL_NOISE_THRESH -
{ USB_DEVICE(0x0cf3, 0x9271) }, /* Atheros */
{ USB_DEVICE(0x0cf3, 0x1006) }, /* Atheros */
{ USB_DEVICE(0x0846, 0x9030) }, /* Netgear N150 */
+ { USB_DEVICE(0x07b8, 0x9271) }, /* Altai WA1011N-GU */
{ USB_DEVICE(0x07D1, 0x3A10) }, /* Dlink Wireless 150 */
{ USB_DEVICE(0x13D3, 0x3327) }, /* Azurewave */
{ USB_DEVICE(0x13D3, 0x3328) }, /* Azurewave */
reorder_work.work);
struct mt76_dev *dev = tid->dev;
struct sk_buff_head frames;
+ int nframes;
__skb_queue_head_init(&frames);
spin_lock(&tid->lock);
mt76_rx_aggr_check_release(tid, &frames);
+ nframes = tid->nframes;
spin_unlock(&tid->lock);
- ieee80211_queue_delayed_work(tid->dev->hw, &tid->reorder_work, REORDER_TIMEOUT);
+ if (nframes)
+ ieee80211_queue_delayed_work(tid->dev->hw, &tid->reorder_work,
+ REORDER_TIMEOUT);
mt76_rx_complete(dev, &frames, -1);
local_bh_enable();
}
+static void
+mt76_rx_aggr_check_ctl(struct sk_buff *skb, struct sk_buff_head *frames)
+{
+ struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
+ struct ieee80211_bar *bar = (struct ieee80211_bar *) skb->data;
+ struct mt76_wcid *wcid = status->wcid;
+ struct mt76_rx_tid *tid;
+ u16 seqno;
+
+ if (!ieee80211_is_ctl(bar->frame_control))
+ return;
+
+ if (!ieee80211_is_back_req(bar->frame_control))
+ return;
+
+ status->tid = le16_to_cpu(bar->control) >> 12;
+ seqno = le16_to_cpu(bar->start_seq_num) >> 4;
+ tid = rcu_dereference(wcid->aggr[status->tid]);
+ if (!tid)
+ return;
+
+ spin_lock_bh(&tid->lock);
+ mt76_rx_aggr_release_frames(tid, frames, seqno);
+ mt76_rx_aggr_release_head(tid, frames);
+ spin_unlock_bh(&tid->lock);
+}
+
void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames)
{
struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
__skb_queue_tail(frames, skb);
sta = wcid_to_sta(wcid);
- if (!sta || !status->aggr)
+ if (!sta)
return;
+ if (!status->aggr) {
+ mt76_rx_aggr_check_ctl(skb, frames);
+ return;
+ }
+
tid = rcu_dereference(wcid->aggr[status->tid]);
if (!tid)
return;
ieee80211_hw_set(hw, TX_AMSDU);
ieee80211_hw_set(hw, TX_FRAG_LIST);
ieee80211_hw_set(hw, MFP_CAPABLE);
+ ieee80211_hw_set(hw, AP_LINK_PS);
wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
return 0;
}
+static void
+mt76_check_ps(struct mt76_dev *dev, struct sk_buff *skb)
+{
+ struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+ struct ieee80211_sta *sta;
+ struct mt76_wcid *wcid = status->wcid;
+ bool ps;
+
+ if (!wcid || !wcid->sta)
+ return;
+
+ sta = container_of((void *) wcid, struct ieee80211_sta, drv_priv);
+
+ if (!test_bit(MT_WCID_FLAG_CHECK_PS, &wcid->flags))
+ return;
+
+ if (ieee80211_is_pspoll(hdr->frame_control)) {
+ ieee80211_sta_pspoll(sta);
+ return;
+ }
+
+ if (ieee80211_has_morefrags(hdr->frame_control) ||
+ !(ieee80211_is_mgmt(hdr->frame_control) ||
+ ieee80211_is_data(hdr->frame_control)))
+ return;
+
+ ps = ieee80211_has_pm(hdr->frame_control);
+
+ if (ps && (ieee80211_is_data_qos(hdr->frame_control) ||
+ ieee80211_is_qos_nullfunc(hdr->frame_control)))
+ ieee80211_sta_uapsd_trigger(sta, status->tid);
+
+ if (!!test_bit(MT_WCID_FLAG_PS, &wcid->flags) == ps)
+ return;
+
+ if (ps) {
+ set_bit(MT_WCID_FLAG_PS, &wcid->flags);
+ mt76_stop_tx_queues(dev, sta, true);
+ } else {
+ clear_bit(MT_WCID_FLAG_PS, &wcid->flags);
+ }
+
+ ieee80211_sta_ps_transition(sta, ps);
+ dev->drv->sta_ps(dev, sta, ps);
+}
+
void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
int queue)
{
__skb_queue_head_init(&frames);
- while ((skb = __skb_dequeue(&dev->rx_skb[q])) != NULL)
+ while ((skb = __skb_dequeue(&dev->rx_skb[q])) != NULL) {
+ mt76_check_ps(dev, skb);
mt76_rx_aggr_reorder(skb, &frames);
+ }
mt76_rx_complete(dev, &frames, q);
}
void (*kick)(struct mt76_dev *dev, struct mt76_queue *q);
};
+enum mt76_wcid_flags {
+ MT_WCID_FLAG_CHECK_PS,
+ MT_WCID_FLAG_PS,
+};
+
struct mt76_wcid {
struct mt76_rx_tid __rcu *aggr[IEEE80211_NUM_TIDS];
struct work_struct aggr_work;
+ unsigned long flags;
+
u8 idx;
u8 hw_key_idx;
struct sk_buff *skb);
void (*rx_poll_complete)(struct mt76_dev *dev, enum mt76_rxq_id q);
+
+ void (*sta_ps)(struct mt76_dev *dev, struct ieee80211_sta *sta,
+ bool ps);
};
struct mt76_channel_state {
void mt76x2_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
struct sk_buff *skb);
+void mt76x2_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps);
+
void mt76x2_update_channel(struct mt76_dev *mdev);
s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
.tx_complete_skb = mt76x2_tx_complete_skb,
.rx_skb = mt76x2_queue_rx_skb,
.rx_poll_complete = mt76x2_rx_poll_complete,
+ .sta_ps = mt76x2_sta_ps,
};
struct ieee80211_hw *hw;
struct mt76x2_dev *dev;
mt76x2_remove_hdr_pad(skb, pad_len);
- if (rxinfo & MT_RXINFO_BA)
+ if ((rxinfo & MT_RXINFO_BA) && !(rxinfo & MT_RXINFO_NULL))
status->aggr = true;
if (WARN_ON_ONCE(len > skb->len))
for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
mt76x2_txq_init(dev, sta->txq[i]);
+ if (vif->type == NL80211_IFTYPE_AP)
+ set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
+
rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
out:
return 0;
}
-static void
-mt76x2_sta_notify(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
- enum sta_notify_cmd cmd, struct ieee80211_sta *sta)
+void
+mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
{
struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
- struct mt76x2_dev *dev = hw->priv;
+ struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
int idx = msta->wcid.idx;
- switch (cmd) {
- case STA_NOTIFY_SLEEP:
- mt76x2_mac_wcid_set_drop(dev, idx, true);
- mt76_stop_tx_queues(&dev->mt76, sta, true);
- break;
- case STA_NOTIFY_AWAKE:
- mt76x2_mac_wcid_set_drop(dev, idx, false);
- break;
- }
+ mt76x2_mac_wcid_set_drop(dev, idx, ps);
}
static int
mutex_unlock(&dev->mutex);
}
+static int
+mt76x2_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set)
+{
+ return 0;
+}
+
const struct ieee80211_ops mt76x2_ops = {
.tx = mt76x2_tx,
.start = mt76x2_start,
.bss_info_changed = mt76x2_bss_info_changed,
.sta_add = mt76x2_sta_add,
.sta_remove = mt76x2_sta_remove,
- .sta_notify = mt76x2_sta_notify,
.set_key = mt76x2_set_key,
.conf_tx = mt76x2_conf_tx,
.sw_scan_start = mt76x2_sw_scan,
.release_buffered_frames = mt76_release_buffered_frames,
.set_coverage_class = mt76x2_set_coverage_class,
.get_survey = mt76_get_survey,
+ .set_tim = mt76x2_set_tim,
};
poll_wait(file, &intf->frame_dump_waitqueue, wait);
if (!skb_queue_empty(&intf->frame_dump_skbqueue))
- return POLLOUT | POLLWRNORM;
+ return EPOLLOUT | EPOLLWRNORM;
return 0;
}
}
if (0 == tmp) {
read_addr = REG_DBI_RDATA + addr % 4;
- ret = rtl_read_word(rtlpriv, read_addr);
+ ret = rtl_read_byte(rtlpriv, read_addr);
}
return ret;
}
}
tmp = _rtl8821ae_dbi_read(rtlpriv, 0x70f);
- _rtl8821ae_dbi_write(rtlpriv, 0x70f, tmp | BIT(7));
+ _rtl8821ae_dbi_write(rtlpriv, 0x70f, tmp | BIT(7) |
+ ASPM_L1_LATENCY << 3);
tmp = _rtl8821ae_dbi_read(rtlpriv, 0x719);
_rtl8821ae_dbi_write(rtlpriv, 0x719, tmp | BIT(3) | BIT(4));
#define RTL_USB_MAX_RX_COUNT 100
#define QBSS_LOAD_SIZE 5
#define MAX_WMMELE_LENGTH 64
+#define ASPM_L1_LATENCY 7
#define TOTAL_CAM_ENTRY 32
unsigned int i = 0;
struct netfront_queue *queue = NULL;
+ if (!np->queues)
+ return -ENODEV;
+
for (i = 0; i < num_queues; ++i) {
queue = &np->queues[i];
napi_enable(&queue->napi);
#ifdef CONFIG_SYSFS
info->netdev->sysfs_groups[0] = &xennet_dev_group;
#endif
- err = register_netdev(info->netdev);
- if (err) {
- pr_warn("%s: register_netdev err=%d\n", __func__, err);
- goto fail;
- }
return 0;
-
- fail:
- xennet_free_netdev(netdev);
- dev_set_drvdata(&dev->dev, NULL);
- return err;
}
static void xennet_end_access(int ref, void *page)
{
unsigned int i;
- rtnl_lock();
-
for (i = 0; i < info->netdev->real_num_tx_queues; i++) {
struct netfront_queue *queue = &info->queues[i];
netif_napi_del(&queue->napi);
}
- rtnl_unlock();
-
kfree(info->queues);
info->queues = NULL;
}
if (!info->queues)
return -ENOMEM;
- rtnl_lock();
-
for (i = 0; i < *num_queues; i++) {
struct netfront_queue *queue = &info->queues[i];
ret = xennet_init_queue(queue);
if (ret < 0) {
- dev_warn(&info->netdev->dev,
+ dev_warn(&info->xbdev->dev,
"only created %d queues\n", i);
*num_queues = i;
break;
netif_set_real_num_tx_queues(info->netdev, *num_queues);
- rtnl_unlock();
-
if (*num_queues == 0) {
- dev_err(&info->netdev->dev, "no queues\n");
+ dev_err(&info->xbdev->dev, "no queues\n");
return -EINVAL;
}
return 0;
goto out;
}
+ rtnl_lock();
if (info->queues)
xennet_destroy_queues(info);
info->queues = NULL;
goto out;
}
+ rtnl_unlock();
/* Create shared ring, alloc event channel -- for each queue */
for (i = 0; i < num_queues; ++i) {
xenbus_transaction_end(xbt, 1);
destroy_ring:
xennet_disconnect_backend(info);
+ rtnl_lock();
xennet_destroy_queues(info);
out:
+ rtnl_unlock();
device_unregister(&dev->dev);
return err;
}
netdev_update_features(dev);
rtnl_unlock();
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ err = register_netdev(dev);
+ if (err) {
+ pr_warn("%s: register_netdev err=%d\n", __func__, err);
+ device_unregister(&np->xbdev->dev);
+ return err;
+ }
+ }
+
/*
* All public and private state should now be sane. Get
* ready to start sending and receiving packets and give the driver
xennet_disconnect_backend(info);
- unregister_netdev(info->netdev);
+ if (info->netdev->reg_state == NETREG_REGISTERED)
+ unregister_netdev(info->netdev);
- if (info->queues)
+ if (info->queues) {
+ rtnl_lock();
xennet_destroy_queues(info);
+ rtnl_unlock();
+ }
xennet_free_netdev(info->netdev);
return 0;
u32 lvl, void *context, void **rv)
{
acpi_handle *phandle = (acpi_handle *)context;
+ unsigned long long current_status = 0;
acpi_status status;
struct acpi_device_info *info;
int retval = 0;
return retval;
}
- if (info->current_status && (info->valid & ACPI_VALID_HID) &&
+ acpi_bus_get_status_handle(handle, ¤t_status);
+
+ if (current_status && (info->valid & ACPI_VALID_HID) &&
(!strcmp(info->hardware_id.string, IBM_HARDWARE_ID1) ||
!strcmp(info->hardware_id.string, IBM_HARDWARE_ID2))) {
pr_debug("found hardware: %s, handle: %p\n",
poll_wait(filp, &stdev->event_wq, wait);
if (lock_mutex_and_test_alive(stdev))
- return POLLIN | POLLRDHUP | POLLOUT | POLLERR | POLLHUP;
+ return EPOLLIN | EPOLLRDHUP | EPOLLOUT | EPOLLERR | EPOLLHUP;
mutex_unlock(&stdev->mrpc_mutex);
if (try_wait_for_completion(&stuser->comp))
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
if (stuser->event_cnt != atomic_read(&stdev->event_cnt))
- ret |= POLLPRI | POLLRDBAND;
+ ret |= EPOLLPRI | EPOLLRDBAND;
return ret;
}
}
}
- dev_dbg(&s->dev, "cs: memory probe 0x%06lx-0x%06lx: %p %p %u %u %u",
+ dev_dbg(&s->dev, "cs: memory probe 0x%06lx-0x%06lx: %pr %pr %u %u %u",
base, base+size-1, res1, res2, ret, info1, info2);
free_region(res2);
{
int ret = 0, i;
- clk_prepare_enable(skt->clk);
+ ret = clk_prepare_enable(skt->clk);
+ if (ret)
+ return ret;
if (skt->ops->hw_init) {
ret = skt->ops->hw_init(skt);
- if (ret)
+ if (ret) {
+ clk_disable_unprepare(skt->clk);
return ret;
+ }
}
for (i = 0; i < ARRAY_SIZE(skt->stat); i++) {
return ret;
}
-static struct chromeos_laptop samsung_series_5_550 = {
+static const struct chromeos_laptop samsung_series_5_550 = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS },
},
};
-static struct chromeos_laptop samsung_series_5 = {
+static const struct chromeos_laptop samsung_series_5 = {
.i2c_peripherals = {
/* Light Sensor. */
{ .add = setup_tsl2583_als, I2C_ADAPTER_SMBUS },
},
};
-static struct chromeos_laptop chromebook_pixel = {
+static const struct chromeos_laptop chromebook_pixel = {
.i2c_peripherals = {
/* Touch Screen. */
{ .add = setup_atmel_1664s_ts, I2C_ADAPTER_PANEL },
},
};
-static struct chromeos_laptop hp_chromebook_14 = {
+static const struct chromeos_laptop hp_chromebook_14 = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 },
},
};
-static struct chromeos_laptop dell_chromebook_11 = {
+static const struct chromeos_laptop dell_chromebook_11 = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 },
},
};
-static struct chromeos_laptop toshiba_cb35 = {
+static const struct chromeos_laptop toshiba_cb35 = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 },
},
};
-static struct chromeos_laptop acer_c7_chromebook = {
+static const struct chromeos_laptop acer_c7_chromebook = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS },
},
};
-static struct chromeos_laptop acer_ac700 = {
+static const struct chromeos_laptop acer_ac700 = {
.i2c_peripherals = {
/* Light Sensor. */
{ .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS },
},
};
-static struct chromeos_laptop acer_c720 = {
+static const struct chromeos_laptop acer_c720 = {
.i2c_peripherals = {
/* Touchscreen. */
{ .add = setup_atmel_1664s_ts, I2C_ADAPTER_DESIGNWARE_1 },
},
};
-static struct chromeos_laptop hp_pavilion_14_chromebook = {
+static const struct chromeos_laptop hp_pavilion_14_chromebook = {
.i2c_peripherals = {
/* Touchpad. */
{ .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS },
},
};
-static struct chromeos_laptop cr48 = {
+static const struct chromeos_laptop cr48 = {
.i2c_peripherals = {
/* Light Sensor. */
{ .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS },
if (CIRC_CNT(debug_info->log_buffer.head,
debug_info->log_buffer.tail,
LOG_SIZE))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
mutex_unlock(&debug_info->log_mutex);
return mask;
#define DRV_NAME "cros_ec_lpcs"
#define ACPI_DRV_NAME "GOOG0004"
+/* True if ACPI device is present */
+static bool cros_ec_lpc_acpi_device_found;
+
static int ec_response_timed_out(void)
{
unsigned long one_second = jiffies + HZ;
static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec,
struct cros_ec_command *msg)
{
- struct ec_host_request *request;
struct ec_host_response response;
u8 sum;
int ret = 0;
/* Write buffer */
cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_PACKET, ret, ec->dout);
- request = (struct ec_host_request *)ec->dout;
-
/* Here we go */
sum = EC_COMMAND_PROTOCOL_3;
cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_CMD, 1, &sum);
DMI_MATCH(DMI_PRODUCT_NAME, "Peppy"),
},
},
+ {
+ /* x86-glimmer, the Lenovo Thinkpad Yoga 11e. */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Glimmer"),
+ },
+ },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(dmi, cros_ec_lpc_dmi_table);
.remove = cros_ec_lpc_remove,
};
+static struct platform_device cros_ec_lpc_device = {
+ .name = DRV_NAME
+};
+
+static acpi_status cros_ec_lpc_parse_device(acpi_handle handle, u32 level,
+ void *context, void **retval)
+{
+ *(bool *)context = true;
+ return AE_CTRL_TERMINATE;
+}
+
static int __init cros_ec_lpc_init(void)
{
int ret;
+ acpi_status status;
if (!dmi_check_system(cros_ec_lpc_dmi_table)) {
pr_err(DRV_NAME ": unsupported system.\n");
return ret;
}
- return 0;
+ status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device,
+ &cros_ec_lpc_acpi_device_found, NULL);
+ if (ACPI_FAILURE(status))
+ pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME);
+
+ if (!cros_ec_lpc_acpi_device_found) {
+ /* Register the device, and it'll get hooked up automatically */
+ ret = platform_device_register(&cros_ec_lpc_device);
+ if (ret) {
+ pr_err(DRV_NAME ": can't register device: %d\n", ret);
+ platform_driver_unregister(&cros_ec_lpc_driver);
+ cros_ec_lpc_reg_destroy();
+ }
+ }
+
+ return ret;
}
static void __exit cros_ec_lpc_exit(void)
{
+ if (!cros_ec_lpc_acpi_device_found)
+ platform_device_unregister(&cros_ec_lpc_device);
platform_driver_unregister(&cros_ec_lpc_driver);
cros_ec_lpc_reg_destroy();
}
struct cros_ec_command *msg)
{
int ret;
+ int (*xfer_fxn)(struct cros_ec_device *ec, struct cros_ec_command *msg);
if (ec_dev->proto_version > 2)
- ret = ec_dev->pkt_xfer(ec_dev, msg);
+ xfer_fxn = ec_dev->pkt_xfer;
else
- ret = ec_dev->cmd_xfer(ec_dev, msg);
+ xfer_fxn = ec_dev->cmd_xfer;
+ ret = (*xfer_fxn)(ec_dev, msg);
if (msg->result == EC_RES_IN_PROGRESS) {
int i;
struct cros_ec_command *status_msg;
for (i = 0; i < EC_COMMAND_RETRIES; i++) {
usleep_range(10000, 11000);
- ret = ec_dev->cmd_xfer(ec_dev, status_msg);
+ ret = (*xfer_fxn)(ec_dev, status_msg);
if (ret < 0)
break;
count += scnprintf(buf + count, PAGE_SIZE - count,
"Build info: EC error %d\n", msg->result);
else {
- msg->data[sizeof(msg->data) - 1] = '\0';
+ msg->data[EC_HOST_PARAM_SIZE - 1] = '\0';
count += scnprintf(buf + count, PAGE_SIZE - count,
"Build info: %s\n", msg->data);
}
return -ERESTARTSYS;
if (status & PIPE_POLL_IN)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (status & PIPE_POLL_OUT)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (status & PIPE_POLL_HUP)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (test_bit(BIT_CLOSED_ON_HOST, &pipe->flags))
- mask |= POLLERR;
+ mask |= EPOLLERR;
return mask;
}
{
struct mlxreg_core_data *data = item->data;
u32 regval;
- int i, ret;
+ int i, ret = 0;
for (i = 0; i < item->count; i++, data++) {
/* Mask event. */
#define MLXPLAT_CPLD_AGGR_FAN_MASK_DEF 0x40
#define MLXPLAT_CPLD_AGGR_MASK_DEF (MLXPLAT_CPLD_AGGR_PSU_MASK_DEF | \
MLXPLAT_CPLD_AGGR_FAN_MASK_DEF)
+#define MLXPLAT_CPLD_AGGR_MASK_NG_DEF 0x04
+#define MLXPLAT_CPLD_LOW_AGGR_MASK_LOW 0xc0
#define MLXPLAT_CPLD_AGGR_MASK_MSN21XX 0x04
#define MLXPLAT_CPLD_PSU_MASK GENMASK(1, 0)
#define MLXPLAT_CPLD_PWR_MASK GENMASK(1, 0)
#define MLXPLAT_CPLD_FAN_MASK GENMASK(3, 0)
+#define MLXPLAT_CPLD_FAN_NG_MASK GENMASK(5, 0)
/* Start channel numbers */
#define MLXPLAT_CPLD_CH1 2
/* Number of LPC attached MUX platform devices */
#define MLXPLAT_CPLD_LPC_MUX_DEVS 2
+/* Hotplug devices adapter numbers */
+#define MLXPLAT_CPLD_NR_NONE -1
+#define MLXPLAT_CPLD_PSU_DEFAULT_NR 10
+#define MLXPLAT_CPLD_PSU_MSNXXXX_NR 4
+#define MLXPLAT_CPLD_FAN1_DEFAULT_NR 11
+#define MLXPLAT_CPLD_FAN2_DEFAULT_NR 12
+#define MLXPLAT_CPLD_FAN3_DEFAULT_NR 13
+#define MLXPLAT_CPLD_FAN4_DEFAULT_NR 14
+
/* mlxplat_priv - platform private data
* @pdev_i2c - i2c controller platform device
* @pdev_mux - array of mux platform devices
},
};
+static struct i2c_board_info mlxplat_mlxcpld_ng_psu[] = {
+ {
+ I2C_BOARD_INFO("24c32", 0x51),
+ },
+ {
+ I2C_BOARD_INFO("24c32", 0x50),
+ },
+};
+
static struct i2c_board_info mlxplat_mlxcpld_pwr[] = {
{
I2C_BOARD_INFO("dps460", 0x59),
.reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
.mask = BIT(0),
.hpdev.brdinfo = &mlxplat_mlxcpld_psu[0],
- .hpdev.nr = 10,
+ .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR,
},
{
.label = "psu2",
.reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
.mask = BIT(1),
.hpdev.brdinfo = &mlxplat_mlxcpld_psu[1],
- .hpdev.nr = 10,
+ .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR,
},
};
.reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
.mask = BIT(0),
.hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0],
- .hpdev.nr = 10,
+ .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR,
},
{
.label = "pwr2",
.reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
.mask = BIT(1),
.hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1],
- .hpdev.nr = 10,
+ .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR,
},
};
.reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
.mask = BIT(0),
.hpdev.brdinfo = &mlxplat_mlxcpld_fan[0],
- .hpdev.nr = 11,
+ .hpdev.nr = MLXPLAT_CPLD_FAN1_DEFAULT_NR,
},
{
.label = "fan2",
.reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
.mask = BIT(1),
.hpdev.brdinfo = &mlxplat_mlxcpld_fan[1],
- .hpdev.nr = 12,
+ .hpdev.nr = MLXPLAT_CPLD_FAN2_DEFAULT_NR,
},
{
.label = "fan3",
.reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
.mask = BIT(2),
.hpdev.brdinfo = &mlxplat_mlxcpld_fan[2],
- .hpdev.nr = 13,
+ .hpdev.nr = MLXPLAT_CPLD_FAN3_DEFAULT_NR,
},
{
.label = "fan4",
.reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
.mask = BIT(3),
.hpdev.brdinfo = &mlxplat_mlxcpld_fan[3],
- .hpdev.nr = 14,
+ .hpdev.nr = MLXPLAT_CPLD_FAN4_DEFAULT_NR,
},
};
.mask = MLXPLAT_CPLD_AGGR_MASK_DEF,
};
+static struct mlxreg_core_data mlxplat_mlxcpld_msn21xx_pwr_items_data[] = {
+ {
+ .label = "pwr1",
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = BIT(0),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "pwr2",
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = BIT(1),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+};
+
/* Platform hotplug MSN21xx system family data */
static struct mlxreg_core_item mlxplat_mlxcpld_msn21xx_items[] = {
{
- .data = mlxplat_mlxcpld_default_pwr_items_data,
+ .data = mlxplat_mlxcpld_msn21xx_pwr_items_data,
.aggr_mask = MLXPLAT_CPLD_AGGR_PWR_MASK_DEF,
.reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
.mask = MLXPLAT_CPLD_PWR_MASK,
- .count = ARRAY_SIZE(mlxplat_mlxcpld_pwr),
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_msn21xx_pwr_items_data),
.inversed = 0,
.health = false,
},
.counter = ARRAY_SIZE(mlxplat_mlxcpld_msn21xx_items),
.cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET,
.mask = MLXPLAT_CPLD_AGGR_MASK_DEF,
+ .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET,
+ .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW,
+};
+
+/* Platform hotplug msn274x system family data */
+static struct mlxreg_core_data mlxplat_mlxcpld_msn274x_psu_items_data[] = {
+ {
+ .label = "psu1",
+ .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
+ .mask = BIT(0),
+ .hpdev.brdinfo = &mlxplat_mlxcpld_psu[0],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
+ },
+ {
+ .label = "psu2",
+ .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
+ .mask = BIT(1),
+ .hpdev.brdinfo = &mlxplat_mlxcpld_psu[1],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
+ },
+};
+
+static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_pwr_items_data[] = {
+ {
+ .label = "pwr1",
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = BIT(0),
+ .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
+ },
+ {
+ .label = "pwr2",
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = BIT(1),
+ .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
+ },
+};
+
+static struct mlxreg_core_data mlxplat_mlxcpld_msn274x_fan_items_data[] = {
+ {
+ .label = "fan1",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(0),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan2",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(1),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan3",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(2),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan4",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(3),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+};
+
+static struct mlxreg_core_item mlxplat_mlxcpld_msn274x_items[] = {
+ {
+ .data = mlxplat_mlxcpld_msn274x_psu_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
+ .mask = MLXPLAT_CPLD_PSU_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_msn274x_psu_items_data),
+ .inversed = 1,
+ .health = false,
+ },
+ {
+ .data = mlxplat_mlxcpld_default_ng_pwr_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = MLXPLAT_CPLD_PWR_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_pwr_items_data),
+ .inversed = 0,
+ .health = false,
+ },
+ {
+ .data = mlxplat_mlxcpld_msn274x_fan_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = MLXPLAT_CPLD_FAN_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_msn274x_fan_items_data),
+ .inversed = 1,
+ .health = false,
+ },
+};
+
+static
+struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_msn274x_data = {
+ .items = mlxplat_mlxcpld_msn274x_items,
+ .counter = ARRAY_SIZE(mlxplat_mlxcpld_msn274x_items),
+ .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET,
+ .mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET,
+ .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW,
+};
+
+/* Platform hotplug MSN201x system family data */
+static struct mlxreg_core_data mlxplat_mlxcpld_msn201x_pwr_items_data[] = {
+ {
+ .label = "pwr1",
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = BIT(0),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "pwr2",
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = BIT(1),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+};
+
+static struct mlxreg_core_item mlxplat_mlxcpld_msn201x_items[] = {
+ {
+ .data = mlxplat_mlxcpld_msn201x_pwr_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_PWR_MASK_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = MLXPLAT_CPLD_PWR_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_msn201x_pwr_items_data),
+ .inversed = 0,
+ .health = false,
+ },
+};
+
+static
+struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_msn201x_data = {
+ .items = mlxplat_mlxcpld_msn21xx_items,
+ .counter = ARRAY_SIZE(mlxplat_mlxcpld_msn201x_items),
+ .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET,
+ .mask = MLXPLAT_CPLD_AGGR_MASK_DEF,
+ .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET,
+ .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW,
+};
+
+/* Platform hotplug next generation system family data */
+static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_psu_items_data[] = {
+ {
+ .label = "psu1",
+ .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
+ .mask = BIT(0),
+ .hpdev.brdinfo = &mlxplat_mlxcpld_ng_psu[0],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
+ },
+ {
+ .label = "psu2",
+ .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
+ .mask = BIT(1),
+ .hpdev.brdinfo = &mlxplat_mlxcpld_ng_psu[1],
+ .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR,
+ },
+};
+
+static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_fan_items_data[] = {
+ {
+ .label = "fan1",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(0),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan2",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(1),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan3",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(2),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan4",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(3),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan5",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(4),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+ {
+ .label = "fan6",
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = BIT(5),
+ .hpdev.nr = MLXPLAT_CPLD_NR_NONE,
+ },
+};
+
+static struct mlxreg_core_item mlxplat_mlxcpld_default_ng_items[] = {
+ {
+ .data = mlxplat_mlxcpld_default_ng_psu_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET,
+ .mask = MLXPLAT_CPLD_PSU_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_psu_items_data),
+ .inversed = 1,
+ .health = false,
+ },
+ {
+ .data = mlxplat_mlxcpld_default_ng_pwr_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET,
+ .mask = MLXPLAT_CPLD_PWR_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_pwr_items_data),
+ .inversed = 0,
+ .health = false,
+ },
+ {
+ .data = mlxplat_mlxcpld_default_ng_fan_items_data,
+ .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET,
+ .mask = MLXPLAT_CPLD_FAN_NG_MASK,
+ .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_fan_items_data),
+ .inversed = 1,
+ .health = false,
+ },
+};
+
+static
+struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_default_ng_data = {
+ .items = mlxplat_mlxcpld_default_ng_items,
+ .counter = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_items),
+ .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET,
+ .mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF,
+ .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET,
+ .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW,
};
static bool mlxplat_mlxcpld_writeable_reg(struct device *dev, unsigned int reg)
return 1;
};
+static int __init mlxplat_dmi_msn274x_matched(const struct dmi_system_id *dmi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) {
+ mlxplat_mux_data[i].values = mlxplat_msn21xx_channels;
+ mlxplat_mux_data[i].n_values =
+ ARRAY_SIZE(mlxplat_msn21xx_channels);
+ }
+ mlxplat_hotplug = &mlxplat_mlxcpld_msn274x_data;
+
+ return 1;
+};
+
+static int __init mlxplat_dmi_msn201x_matched(const struct dmi_system_id *dmi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) {
+ mlxplat_mux_data[i].values = mlxplat_msn21xx_channels;
+ mlxplat_mux_data[i].n_values =
+ ARRAY_SIZE(mlxplat_msn21xx_channels);
+ }
+ mlxplat_hotplug = &mlxplat_mlxcpld_msn201x_data;
+
+ return 1;
+};
+
+static int __init mlxplat_dmi_qmb7xx_matched(const struct dmi_system_id *dmi)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) {
+ mlxplat_mux_data[i].values = mlxplat_msn21xx_channels;
+ mlxplat_mux_data[i].n_values =
+ ARRAY_SIZE(mlxplat_msn21xx_channels);
+ }
+ mlxplat_hotplug = &mlxplat_mlxcpld_default_ng_data;
+
+ return 1;
+};
+
static const struct dmi_system_id mlxplat_dmi_table[] __initconst = {
+ {
+ .callback = mlxplat_dmi_msn274x_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSN274"),
+ },
+ },
{
.callback = mlxplat_dmi_default_matched,
.matches = {
DMI_MATCH(DMI_PRODUCT_NAME, "MSN21"),
},
},
+ {
+ .callback = mlxplat_dmi_msn201x_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MSN201"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_qmb7xx_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "QMB7"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_qmb7xx_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "SN37"),
+ },
+ },
+ {
+ .callback = mlxplat_dmi_qmb7xx_matched,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "SN34"),
+ },
+ },
{ }
};
{
poll_wait(file, &sonypi_compat.fifo_proc_list, wait);
if (kfifo_len(&sonypi_compat.fifo))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(file, &pps->queue, wait);
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
static int pps_cdev_fasync(int fd, struct file *file, int on)
poll_wait(fp, &ptp->tsev_wq, wait);
- return queue_cnt(&ptp->tsevq) ? POLLIN : 0;
+ return queue_cnt(&ptp->tsevq) ? EPOLLIN : 0;
}
#define EXTTS_BUFSIZE (PTP_BUF_TIMESTAMPS * sizeof(struct ptp_extts_event))
poll_wait(filp, &priv->event_rx_wait, wait);
if (kfifo_len(&priv->event_fifo))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(filp, &channel->fblockread_event, wait);
if (qcom_smd_get_tx_avail(channel) > 20)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
__poll_t mask = 0;
if (!eptdev->ept)
- return POLLERR;
+ return EPOLLERR;
poll_wait(filp, &eptdev->readq, wait);
if (!skb_queue_empty(&eptdev->queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
mask |= rpmsg_poll(eptdev->ept, filp, wait);
data = rtc->irq_data;
- return (data != 0) ? (POLLIN | POLLRDNORM) : 0;
+ return (data != 0) ? (EPOLLIN | EPOLLRDNORM) : 0;
}
static long rtc_dev_ioctl(struct file *file,
poll_wait(filp, &dasd_eer_read_wait_queue, ptable);
spin_lock_irqsave(&bufferlock, flags);
if (eerb->head != eerb->tail)
- mask = POLLIN | POLLRDNORM ;
+ mask = EPOLLIN | EPOLLRDNORM ;
else
mask = 0;
spin_unlock_irqrestore(&bufferlock, flags);
CFLAGS_sclp_early_core.o += -D__NO_FORTIFY
+CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_EXPOLINE)
+
obj-y += ctrlchar.o keyboard.o defkeymap.o sclp.o sclp_rw.o sclp_quiesce.o \
sclp_cmd.o sclp_config.o sclp_cpi_sys.o sclp_ocf.o sclp_ctl.o \
sclp_early.o sclp_early_core.o
poll_wait(filp, &mon_read_wait_queue, p);
if (unlikely(atomic_read(&monpriv->iucv_severed)))
- return POLLERR;
+ return EPOLLERR;
if (atomic_read(&monpriv->read_ready))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
u8 _pad_112[116 - 112]; /* 112-115 */
u8 fac116; /* 116 */
u8 fac117; /* 117 */
- u8 _pad_118; /* 118 */
+ u8 fac118; /* 118 */
u8 fac119; /* 119 */
u16 hcpua; /* 120-121 */
u8 _pad_122[124 - 122]; /* 122-123 */
sclp.has_esca = !!(sccb->fac116 & 0x08);
sclp.has_pfmfi = !!(sccb->fac117 & 0x40);
sclp.has_ibs = !!(sccb->fac117 & 0x20);
+ sclp.has_gisaf = !!(sccb->fac118 & 0x08);
sclp.has_hvs = !!(sccb->fac119 & 0x80);
sclp.has_kss = !!(sccb->fac98 & 0x01);
if (sccb->fac85 & 0x02)
/**
* chp_update_desc - update channel-path description
- * @chp - channel-path
+ * @chp: channel-path
*
* Update the channel-path description of the specified channel-path
* including channel measurement related information.
/**
* chp_new - register a new channel-path
- * @chpid - channel-path ID
+ * @chpid: channel-path ID
*
* Create and register data structure representing new channel-path. Return
* zero on success, non-zero otherwise.
/**
* chp_cfg_schedule - schedule chpid configuration request
- * @chpid - channel-path ID
- * @configure - Non-zero for configure, zero for deconfigure
+ * @chpid: channel-path ID
+ * @configure: Non-zero for configure, zero for deconfigure
*
* Schedule a channel-path configuration/deconfiguration request.
*/
/**
* chp_cfg_cancel_deconfigure - cancel chpid deconfiguration request
- * @chpid - channel-path ID
+ * @chpid: channel-path ID
*
* Cancel an active channel-path deconfiguration request if it has not yet
* been performed.
/**
* cio_tm_intrg - perform interrogate function
- * @sch - subchannel on which to perform the interrogate function
+ * @sch: subchannel on which to perform the interrogate function
*
* If the specified subchannel is running in transport-mode, perform the
* interrogate function. Return zero on success, non-zero otherwie.
* enable_cmf() - switch on the channel measurement for a specific device
* @cdev: The ccw device to be enabled
*
- * Returns %0 for success or a negative error value.
- * Note: If this is called on a device for which channel measurement is already
- * enabled a reset of the measurement data is triggered.
+ * Enable channel measurements for @cdev. If this is called on a device
+ * for which channel measurement is already enabled a reset of the
+ * measurement data is triggered.
+ * Returns: %0 for success or a negative error value.
* Context:
* non-atomic
*/
* __disable_cmf() - switch off the channel measurement for a specific device
* @cdev: The ccw device to be disabled
*
- * Returns %0 for success or a negative error value.
+ * Returns: %0 for success or a negative error value.
*
* Context:
* non-atomic, device_lock() held.
* disable_cmf() - switch off the channel measurement for a specific device
* @cdev: The ccw device to be disabled
*
- * Returns %0 for success or a negative error value.
+ * Returns: %0 for success or a negative error value.
*
* Context:
* non-atomic
* @cdev: the channel to be read
* @index: the index of the value to be read
*
- * Returns the value read or %0 if the value cannot be read.
+ * Returns: The value read or %0 if the value cannot be read.
*
* Context:
* any
* @cdev: the channel to be read
* @data: a pointer to a data block that will be filled
*
- * Returns %0 on success, a negative error value otherwise.
+ * Returns: %0 on success, a negative error value otherwise.
*
* Context:
* any
#include <asm/fcx.h>
#include <asm/itcw.h>
-/**
+/*
* struct itcw - incremental tcw helper data type
*
* This structure serves as a handle for the incremental construction of a
* @mask: which output queues to process
* @bb: busy bit indicator, set only if SIGA-w/wt could not access a buffer
* @fc: function code to perform
+ * @aob: asynchronous operation block
*
* Returns condition code.
* Note: For IQDC unicast queues only the highest priority queue is processed.
* @response: Response code will be stored at this address
* @cb: Callback function will be executed for each element
* of the address list
- * @priv: Pointer passed from the caller to qdio_pnso_brinfo()
- * @type: Type of the address entry passed to the callback
- * @entry: Entry containg the address of the specified type
* @priv: Pointer to pass to the callback function.
*
* Performs "Store-network-bridging-information list" operation and calls
/**
* cp_iova_pinned() - check if an iova is pinned for a ccw chain.
- * @cmd: ccwchain command on which to perform the operation
+ * @cp: channel_program on which to perform the operation
* @iova: the iova to check
*
* If the @iova is currently pinned for the ccw chain, return true;
void (*callback) (struct qeth_channel *, struct qeth_cmd_buffer *);
};
+static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
+{
+ return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE);
+}
+
/**
* definition of a qeth channel, used for read and write
*/
*/
static inline int qeth_get_elements_for_range(addr_t start, addr_t end)
{
- return PFN_UP(end - 1) - PFN_DOWN(start);
+ return PFN_UP(end) - PFN_DOWN(start);
}
static inline int qeth_get_micros(void)
unsigned long flags;
struct qeth_reply *reply = NULL;
unsigned long timeout, event_timeout;
- struct qeth_ipa_cmd *cmd;
+ struct qeth_ipa_cmd *cmd = NULL;
QETH_CARD_TEXT(card, 2, "sendctl");
while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
qeth_prepare_control_data(card, len, iob);
- if (IS_IPA(iob->data))
+ if (IS_IPA(iob->data)) {
+ cmd = __ipa_cmd(iob);
event_timeout = QETH_IPA_TIMEOUT;
- else
+ } else {
event_timeout = QETH_TIMEOUT;
+ }
+
timeout = jiffies + event_timeout;
QETH_CARD_TEXT(card, 6, "noirqpnd");
/* we have only one long running ipassist, since we can ensure
process context of this command we can sleep */
- cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE);
- if ((cmd->hdr.command == IPA_CMD_SETIP) &&
- (cmd->hdr.prot_version == QETH_PROT_IPV4)) {
+ if (cmd && cmd->hdr.command == IPA_CMD_SETIP &&
+ cmd->hdr.prot_version == QETH_PROT_IPV4) {
if (!wait_event_timeout(reply->wait_q,
atomic_read(&reply->received), event_timeout))
goto time_err;
poll_wait(file, &megasas_poll_wait, wait);
spin_lock_irqsave(&poll_aen_lock, flags);
if (megasas_poll_wait_aen)
- mask = (POLLIN | POLLRDNORM);
+ mask = (EPOLLIN | EPOLLRDNORM);
else
mask = 0;
megasas_poll_wait_aen = 0;
list_for_each_entry(ioc, &mpt3sas_ioc_list, list) {
if (ioc->aen_event_read_flag) {
spin_unlock(&gioc_lock);
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
}
spin_unlock(&gioc_lock);
sfp = filp->private_data;
if (!sfp)
- return POLLERR;
+ return EPOLLERR;
sdp = sfp->parentdp;
if (!sdp)
- return POLLERR;
+ return EPOLLERR;
poll_wait(filp, &sfp->read_wait, wait);
read_lock_irqsave(&sfp->rq_list_lock, iflags);
list_for_each_entry(srp, &sfp->rq_list, entry) {
/* if any read waiting, flag it */
if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned))
- res = POLLIN | POLLRDNORM;
+ res = EPOLLIN | EPOLLRDNORM;
++count;
}
read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
if (atomic_read(&sdp->detaching))
- res |= POLLHUP;
+ res |= EPOLLHUP;
else if (!sfp->cmd_q) {
if (0 == count)
- res |= POLLOUT | POLLWRNORM;
+ res |= EPOLLOUT | EPOLLWRNORM;
} else if (count < SG_MAX_QUEUE)
- res |= POLLOUT | POLLWRNORM;
+ res |= EPOLLOUT | EPOLLWRNORM;
SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
"sg_poll: res=0x%x\n", (__force u32) res));
return res;
unsigned long rate)
{
struct cpufreq_frequency_table *pos;
+ int idx;
- cpufreq_for_each_valid_entry(pos, freq_table)
+ cpufreq_for_each_valid_entry_idx(pos, freq_table, idx)
if (pos->frequency == rate)
- return pos - freq_table;
+ return idx;
return -ENOENT;
}
config SSB_PCIHOST_POSSIBLE
bool
- depends on SSB && (PCI = y || PCI = SSB) && PCI_DRIVERS_LEGACY
+ depends on SSB && (PCI = y || PCI = SSB) && (PCI_DRIVERS_LEGACY || !MIPS)
default y
config SSB_PCIHOST
if (s->busy != file || !comedi_is_subdevice_running(s) ||
(s->async->cmd.flags & CMDF_WRITE) ||
comedi_buf_read_n_available(s) > 0)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
s = comedi_file_write_subdevice(file);
if (s->busy != file || !comedi_is_subdevice_running(s) ||
!(s->async->cmd.flags & CMDF_WRITE) ||
comedi_buf_write_n_available(s) >= bps)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
done:
__poll_t mask;
mask = f->f_op->poll(f, &table.pt);
- if (mask & (POLLRDNORM | POLLRDBAND | POLLIN |
- POLLHUP | POLLERR)) {
+ if (mask & (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN |
+ EPOLLHUP | EPOLLERR)) {
break;
}
now = ktime_get();
/*
* Threshold below which the tty is woken for writing
* - should be equal to WAKEUP_CHARS in drivers/tty/n_tty.c because
- * even if the writer is woken, n_tty_poll() won't set POLLOUT until
+ * even if the writer is woken, n_tty_poll() won't set EPOLLOUT until
* our fifo is below this level
*/
#define WAKEUP_CHARS 256
goto err;
}
read(t->fds[fds_idx].fd, &dummy, 1);
- t->fds[fds_idx].events = POLLERR|POLLPRI;
+ t->fds[fds_idx].events = EPOLLERR|EPOLLPRI;
t->fds[fds_idx].revents = 0;
fds_idx++;
}
}
for (i = 0; i < t->poll_count; i++) {
- if (t->fds[i].revents & POLLPRI) {
+ if (t->fds[i].revents & EPOLLPRI) {
/* Dummy read to clear the event */
read(t->fds[i].fd, &dummy, 1);
number_of_events++;
clk_put(pclk);
/* IrDA can not set over peripheral_clk */
- cpufreq_for_each_valid_entry(pos, freq_table) {
+ cpufreq_for_each_valid_entry_idx(pos, freq_table, index) {
u32 freq = pos->frequency;
/* IrDA should not over peripheral_clk */
tmp = freq % SCLK_BASE;
if (tmp < min) {
min = tmp;
- index = pos - freq_table;
+ break;
}
}
/* Exceptional events? */
if (sk->sk_err)
- mask |= POLLERR;
+ mask |= EPOLLERR;
if (sk->sk_shutdown & RCV_SHUTDOWN) {
pr_debug("%s(), POLLHUP\n", __func__);
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
}
/* Readable? */
if (!skb_queue_empty(&sk->sk_receive_queue)) {
pr_debug("Socket is readable\n");
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
/* Connection-based need to check for termination and startup */
case SOCK_STREAM:
if (sk->sk_state == TCP_CLOSE) {
pr_debug("%s(), POLLHUP\n", __func__);
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
}
if (sk->sk_state == TCP_ESTABLISHED) {
if ((self->tx_flow == FLOW_START) &&
sock_writeable(sk))
{
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
}
}
break;
if ((self->tx_flow == FLOW_START) &&
sock_writeable(sk))
{
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
}
break;
case SOCK_DGRAM:
if (sock_writeable(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
break;
default:
break;
DENTER(CTRL_TRACE, "(ap=0x%p)\n", ap);
poll_wait(file, &irnet_events.rwait, wait);
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
/* If there is unread events */
if(ap->event_index != irnet_events.index)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
#ifdef INITIAL_DISCOVERY
if(ap->disco_number != -1)
{
irnet_get_discovery_log(ap);
/* Recheck */
if(ap->disco_number != -1)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
#endif /* INITIAL_DISCOVERY */
DENTER(FS_TRACE, "(file=0x%p, ap=0x%p)\n",
file, ap);
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
DABORT(ap == NULL, mask, FS_ERROR, "ap is NULL !!!\n");
/* If we are connected to ppp_generic, let it handle the job */
rt_mutex_lock(&isp->mutex);
if (pipe->capq.streaming != 1) {
rt_mutex_unlock(&isp->mutex);
- return POLLERR;
+ return EPOLLERR;
}
rt_mutex_unlock(&isp->mutex);
poll_wait(file, &bdev->read_queue, pts);
if (bdev->rds_data_available)
- retval = POLLIN | POLLRDNORM;
+ retval = EPOLLIN | EPOLLRDNORM;
return retval;
}
if (c->cfg->direction == MOST_CH_RX) {
if (!kfifo_is_empty(&c->fifo))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
} else {
if (!kfifo_is_empty(&c->fifo) || ch_has_mbo(c))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
return mask;
}
if (!data_ready(mdev))
poll_wait(filp, &mdev->wait_data, wait);
if (data_ready(mdev))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
select WEXT_PRIV
select CRYPTO
select FW_LOADER
- ---help---
select WIRELESS_EXT
select WEXT_PRIV
select CRYPTO
- ---help---
spin_lock_irqsave(&speakup_info.spinlock, flags);
if (!synth_buffer_empty() || speakup_info.flushing)
- ret = POLLIN | POLLRDNORM;
+ ret = EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&speakup_info.spinlock, flags);
return ret;
}
return -ENODEV;
rcu_read_lock();
+ if (!(n->nud_state & NUD_VALID))
+ neigh_event_send(n, NULL);
+
ret = -ENOMEM;
if (n->dev->flags & IFF_LOOPBACK) {
if (iptype == 4)
auth_ret = 0;
out:
kzfree(desc);
- crypto_free_shash(tfm);
+ if (tfm)
+ crypto_free_shash(tfm);
kfree(challenge);
kfree(challenge_binhex);
return auth_ret;
if (test_and_set_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) {
write_unlock_bh(&sk->sk_callback_lock);
pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1, conn: %p >>>>\n", conn);
+ if (iscsi_target_sk_data_ready == conn->orig_data_ready)
+ return;
+ conn->orig_data_ready(sk);
return;
}
static int tcm_loop_show_info(struct seq_file *m, struct Scsi_Host *host)
{
- seq_printf(m, "tcm_loop_proc_info()\n");
+ seq_puts(m, "tcm_loop_proc_info()\n");
return 0;
}
}
tl_nexus = tl_tpg->tl_nexus;
if (!tl_nexus) {
- scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus"
- " does not exist\n");
+ scmd_printk(KERN_ERR, sc,
+ "TCM_Loop I_T Nexus does not exist\n");
set_host_byte(sc, DID_ERROR);
goto out_done;
}
out_done:
kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
sc->scsi_done(sc);
- return;
}
/*
{
struct tcm_loop_cmd *tl_cmd;
- pr_debug("tcm_loop_queuecommand() %d:%d:%d:%llu got CDB: 0x%02x"
- " scsi_buf_len: %u\n", sc->device->host->host_no,
- sc->device->id, sc->device->channel, sc->device->lun,
- sc->cmnd[0], scsi_bufflen(sc));
+ pr_debug("%s() %d:%d:%d:%llu got CDB: 0x%02x scsi_buf_len: %u\n",
+ __func__, sc->device->host->host_no, sc->device->id,
+ sc->device->channel, sc->device->lun, sc->cmnd[0],
+ scsi_bufflen(sc));
tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_ATOMIC);
if (!tl_cmd) {
- pr_err("Unable to allocate struct tcm_loop_cmd\n");
set_host_byte(sc, DID_ERROR);
sc->scsi_done(sc);
return 0;
static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg,
u64 lun, int task, enum tcm_tmreq_table tmr)
{
- struct se_cmd *se_cmd = NULL;
+ struct se_cmd *se_cmd;
struct se_session *se_sess;
struct tcm_loop_nexus *tl_nexus;
- struct tcm_loop_cmd *tl_cmd = NULL;
+ struct tcm_loop_cmd *tl_cmd;
int ret = TMR_FUNCTION_FAILED, rc;
/*
*/
tl_nexus = tl_tpg->tl_nexus;
if (!tl_nexus) {
- pr_err("Unable to perform device reset without"
- " active I_T Nexus\n");
+ pr_err("Unable to perform device reset without active I_T Nexus\n");
return ret;
}
tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL);
- if (!tl_cmd) {
- pr_err("Unable to allocate memory for tl_cmd\n");
+ if (!tl_cmd)
return ret;
- }
init_completion(&tl_cmd->tmr_done);
*/
tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
if (!tl_hba) {
- pr_err("Unable to perform device reset without"
- " active I_T Nexus\n");
+ pr_err("Unable to perform device reset without active I_T Nexus\n");
return FAILED;
}
/*
ret = device_register(&tl_hba->dev);
if (ret) {
- pr_err("device_register() failed for"
- " tl_hba->dev: %d\n", ret);
+ pr_err("device_register() failed for tl_hba->dev: %d\n", ret);
return -ENODEV;
}
ret = driver_register(&tcm_loop_driverfs);
if (ret) {
- pr_err("driver_register() failed for"
- "tcm_loop_driverfs\n");
+ pr_err("driver_register() failed for tcm_loop_driverfs\n");
goto bus_unreg;
}
struct tcm_loop_cmd, tl_se_cmd);
struct scsi_cmnd *sc = tl_cmd->sc;
- pr_debug("tcm_loop_queue_data_in() called for scsi_cmnd: %p"
- " cdb: 0x%02x\n", sc, sc->cmnd[0]);
+ pr_debug("%s() called for scsi_cmnd: %p cdb: 0x%02x\n",
+ __func__, sc, sc->cmnd[0]);
sc->result = SAM_STAT_GOOD;
set_host_byte(sc, DID_OK);
struct tcm_loop_cmd, tl_se_cmd);
struct scsi_cmnd *sc = tl_cmd->sc;
- pr_debug("tcm_loop_queue_status() called for scsi_cmnd: %p"
- " cdb: 0x%02x\n", sc, sc->cmnd[0]);
+ pr_debug("%s() called for scsi_cmnd: %p cdb: 0x%02x\n",
+ __func__, sc, sc->cmnd[0]);
if (se_cmd->sense_buffer &&
((se_cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) ||
sd = scsi_device_lookup(tl_hba->sh, 0, tl_tpg->tl_tpgt,
se_lun->unpacked_lun);
if (!sd) {
- pr_err("Unable to locate struct scsi_device for %d:%d:"
- "%llu\n", 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun);
+ pr_err("Unable to locate struct scsi_device for %d:%d:%llu\n",
+ 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun);
return;
}
/*
return -EEXIST;
}
- tl_nexus = kzalloc(sizeof(struct tcm_loop_nexus), GFP_KERNEL);
- if (!tl_nexus) {
- pr_err("Unable to allocate struct tcm_loop_nexus\n");
+ tl_nexus = kzalloc(sizeof(*tl_nexus), GFP_KERNEL);
+ if (!tl_nexus)
return -ENOMEM;
- }
tl_nexus->se_sess = target_alloc_session(&tl_tpg->tl_se_tpg, 0, 0,
TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
return ret;
}
- pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated"
- " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba),
- name);
+ pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated %s Initiator Port: %s\n",
+ tcm_loop_dump_proto_id(tl_hba), name);
return 0;
}
return -ENODEV;
if (atomic_read(&tpg->tl_tpg_port_count)) {
- pr_err("Unable to remove TCM_Loop I_T Nexus with"
- " active TPG port count: %d\n",
- atomic_read(&tpg->tl_tpg_port_count));
+ pr_err("Unable to remove TCM_Loop I_T Nexus with active TPG port count: %d\n",
+ atomic_read(&tpg->tl_tpg_port_count));
return -EPERM;
}
- pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated"
- " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tpg->tl_hba),
- tl_nexus->se_sess->se_node_acl->initiatorname);
+ pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated %s Initiator Port: %s\n",
+ tcm_loop_dump_proto_id(tpg->tl_hba),
+ tl_nexus->se_sess->se_node_acl->initiatorname);
/*
* Release the SCSI I_T Nexus to the emulated Target Port
*/
* tcm_loop_make_nexus()
*/
if (strlen(page) >= TL_WWN_ADDR_LEN) {
- pr_err("Emulated NAA Sas Address: %s, exceeds"
- " max: %d\n", page, TL_WWN_ADDR_LEN);
+ pr_err("Emulated NAA Sas Address: %s, exceeds max: %d\n",
+ page, TL_WWN_ADDR_LEN);
return -EINVAL;
}
snprintf(&i_port[0], TL_WWN_ADDR_LEN, "%s", page);
ptr = strstr(i_port, "naa.");
if (ptr) {
if (tl_hba->tl_proto_id != SCSI_PROTOCOL_SAS) {
- pr_err("Passed SAS Initiator Port %s does not"
- " match target port protoid: %s\n", i_port,
- tcm_loop_dump_proto_id(tl_hba));
+ pr_err("Passed SAS Initiator Port %s does not match target port protoid: %s\n",
+ i_port, tcm_loop_dump_proto_id(tl_hba));
return -EINVAL;
}
port_ptr = &i_port[0];
ptr = strstr(i_port, "fc.");
if (ptr) {
if (tl_hba->tl_proto_id != SCSI_PROTOCOL_FCP) {
- pr_err("Passed FCP Initiator Port %s does not"
- " match target port protoid: %s\n", i_port,
- tcm_loop_dump_proto_id(tl_hba));
+ pr_err("Passed FCP Initiator Port %s does not match target port protoid: %s\n",
+ i_port, tcm_loop_dump_proto_id(tl_hba));
return -EINVAL;
}
port_ptr = &i_port[3]; /* Skip over "fc." */
ptr = strstr(i_port, "iqn.");
if (ptr) {
if (tl_hba->tl_proto_id != SCSI_PROTOCOL_ISCSI) {
- pr_err("Passed iSCSI Initiator Port %s does not"
- " match target port protoid: %s\n", i_port,
- tcm_loop_dump_proto_id(tl_hba));
+ pr_err("Passed iSCSI Initiator Port %s does not match target port protoid: %s\n",
+ i_port, tcm_loop_dump_proto_id(tl_hba));
return -EINVAL;
}
port_ptr = &i_port[0];
goto check_newline;
}
- pr_err("Unable to locate prefix for emulated Initiator Port:"
- " %s\n", i_port);
+ pr_err("Unable to locate prefix for emulated Initiator Port: %s\n",
+ i_port);
return -EINVAL;
/*
* Clear any trailing newline for the NAA WWN
unsigned long tpgt;
if (strstr(name, "tpgt_") != name) {
- pr_err("Unable to locate \"tpgt_#\" directory"
- " group\n");
+ pr_err("Unable to locate \"tpgt_#\" directory group\n");
return ERR_PTR(-EINVAL);
}
if (kstrtoul(name+5, 10, &tpgt))
return ERR_PTR(-EINVAL);
if (tpgt >= TL_TPGS_PER_HBA) {
- pr_err("Passed tpgt: %lu exceeds TL_TPGS_PER_HBA:"
- " %u\n", tpgt, TL_TPGS_PER_HBA);
+ pr_err("Passed tpgt: %lu exceeds TL_TPGS_PER_HBA: %u\n",
+ tpgt, TL_TPGS_PER_HBA);
return ERR_PTR(-EINVAL);
}
tl_tpg = &tl_hba->tl_hba_tpgs[tpgt];
if (ret < 0)
return ERR_PTR(-ENOMEM);
- pr_debug("TCM_Loop_ConfigFS: Allocated Emulated %s"
- " Target Port %s,t,0x%04lx\n", tcm_loop_dump_proto_id(tl_hba),
- config_item_name(&wwn->wwn_group.cg_item), tpgt);
-
+ pr_debug("TCM_Loop_ConfigFS: Allocated Emulated %s Target Port %s,t,0x%04lx\n",
+ tcm_loop_dump_proto_id(tl_hba),
+ config_item_name(&wwn->wwn_group.cg_item), tpgt);
return &tl_tpg->tl_se_tpg;
}
tl_tpg->tl_hba = NULL;
tl_tpg->tl_tpgt = 0;
- pr_debug("TCM_Loop_ConfigFS: Deallocated Emulated %s"
- " Target Port %s,t,0x%04x\n", tcm_loop_dump_proto_id(tl_hba),
- config_item_name(&wwn->wwn_group.cg_item), tpgt);
+ pr_debug("TCM_Loop_ConfigFS: Deallocated Emulated %s Target Port %s,t,0x%04x\n",
+ tcm_loop_dump_proto_id(tl_hba),
+ config_item_name(&wwn->wwn_group.cg_item), tpgt);
}
/* End items for tcm_loop_naa_cit */
char *ptr;
int ret, off = 0;
- tl_hba = kzalloc(sizeof(struct tcm_loop_hba), GFP_KERNEL);
- if (!tl_hba) {
- pr_err("Unable to allocate struct tcm_loop_hba\n");
+ tl_hba = kzalloc(sizeof(*tl_hba), GFP_KERNEL);
+ if (!tl_hba)
return ERR_PTR(-ENOMEM);
- }
+
/*
* Determine the emulated Protocol Identifier and Target Port Name
* based on the incoming configfs directory name.
}
ptr = strstr(name, "iqn.");
if (!ptr) {
- pr_err("Unable to locate prefix for emulated Target "
- "Port: %s\n", name);
+ pr_err("Unable to locate prefix for emulated Target Port: %s\n",
+ name);
ret = -EINVAL;
goto out;
}
check_len:
if (strlen(name) >= TL_WWN_ADDR_LEN) {
- pr_err("Emulated NAA %s Address: %s, exceeds"
- " max: %d\n", name, tcm_loop_dump_proto_id(tl_hba),
- TL_WWN_ADDR_LEN);
+ pr_err("Emulated NAA %s Address: %s, exceeds max: %d\n",
+ name, tcm_loop_dump_proto_id(tl_hba), TL_WWN_ADDR_LEN);
ret = -EINVAL;
goto out;
}
sh = tl_hba->sh;
tcm_loop_hba_no_cnt++;
- pr_debug("TCM_Loop_ConfigFS: Allocated emulated Target"
- " %s Address: %s at Linux/SCSI Host ID: %d\n",
- tcm_loop_dump_proto_id(tl_hba), name, sh->host_no);
-
+ pr_debug("TCM_Loop_ConfigFS: Allocated emulated Target %s Address: %s at Linux/SCSI Host ID: %d\n",
+ tcm_loop_dump_proto_id(tl_hba), name, sh->host_no);
return &tl_hba->tl_hba_wwn;
out:
kfree(tl_hba);
struct tcm_loop_hba *tl_hba = container_of(wwn,
struct tcm_loop_hba, tl_hba_wwn);
- pr_debug("TCM_Loop_ConfigFS: Deallocating emulated Target"
- " %s Address: %s at Linux/SCSI Host ID: %d\n",
- tcm_loop_dump_proto_id(tl_hba), tl_hba->tl_wwn_address,
- tl_hba->sh->host_no);
+ pr_debug("TCM_Loop_ConfigFS: Deallocating emulated Target %s Address: %s at Linux/SCSI Host ID: %d\n",
+ tcm_loop_dump_proto_id(tl_hba), tl_hba->tl_wwn_address,
+ tl_hba->sh->host_no);
/*
* Call device_unregister() on the original tl_hba->dev.
* tcm_loop_fabric_scsi.c:tcm_loop_release_adapter() will
__alignof__(struct tcm_loop_cmd),
0, NULL);
if (!tcm_loop_cmd_cache) {
- pr_debug("kmem_cache_create() for"
- " tcm_loop_cmd_cache failed\n");
+ pr_debug("kmem_cache_create() for tcm_loop_cmd_cache failed\n");
goto out_destroy_workqueue;
}
snprintf(guid_str, sizeof(guid_str), "%016llx", guid);
sess = kmalloc(sizeof(*sess), GFP_KERNEL);
- if (!sess) {
- pr_err("failed to allocate session descriptor\n");
+ if (!sess)
return ERR_PTR(-ENOMEM);
- }
+
spin_lock_init(&sess->lock);
INIT_LIST_HEAD(&sess->login_list);
INIT_DELAYED_WORK(&sess->maint_work, session_maintenance_work);
}
tpg = kzalloc(sizeof(*tpg), GFP_KERNEL);
- if (!tpg) {
- pr_err("Unable to allocate struct sbp_tpg\n");
+ if (!tpg)
return ERR_PTR(-ENOMEM);
- }
tpg->tport = tport;
tpg->tport_tpgt = tpgt;
return ERR_PTR(-EINVAL);
tport = kzalloc(sizeof(*tport), GFP_KERNEL);
- if (!tport) {
- pr_err("Unable to allocate struct sbp_tport\n");
+ if (!tport)
return ERR_PTR(-ENOMEM);
- }
tport->guid = guid;
sbp_format_wwn(tport->tport_name, SBP_NAMELEN, guid);
EXPORT_SYMBOL(passthrough_attrib_attrs);
TB_CIT_SETUP_DRV(dev_attrib, NULL, NULL);
+TB_CIT_SETUP_DRV(dev_action, NULL, NULL);
/* End functions for struct config_item_type tb_dev_attrib_cit */
config_group_init_type_name(&dev->dev_group, name, &tb->tb_dev_cit);
+ config_group_init_type_name(&dev->dev_action_group, "action",
+ &tb->tb_dev_action_cit);
+ configfs_add_default_group(&dev->dev_action_group, &dev->dev_group);
+
config_group_init_type_name(&dev->dev_attrib.da_group, "attrib",
&tb->tb_dev_attrib_cit);
configfs_add_default_group(&dev->dev_attrib.da_group, &dev->dev_group);
void target_setup_backend_cits(struct target_backend *tb)
{
target_core_setup_dev_cit(tb);
+ target_core_setup_dev_action_cit(tb);
target_core_setup_dev_attrib_cit(tb);
target_core_setup_dev_pr_cit(tb);
target_core_setup_dev_wwn_cit(tb);
ret = core_setup_alua(dev);
if (ret)
- goto out_free_index;
+ goto out_destroy_device;
/*
* Startup the struct se_device processing thread
out_free_alua:
core_alua_free_lu_gp_mem(dev);
+out_destroy_device:
+ dev->transport->destroy_device(dev);
out_free_index:
mutex_lock(&device_mutex);
idr_remove(&devices_idr, dev->dev_index);
static char *iscsi_parse_pr_out_transport_id(
struct se_portal_group *se_tpg,
- const char *buf,
+ char *buf,
u32 *out_tid_len,
char **port_nexus_ptr)
{
}
}
- return (char *)&buf[4];
+ return &buf[4];
}
int target_get_pr_transport_id_len(struct se_node_acl *nacl,
}
const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg,
- const char *buf, u32 *out_tid_len, char **port_nexus_ptr)
+ char *buf, u32 *out_tid_len, char **port_nexus_ptr)
{
u32 offset;
struct config_item_type tb_dev_cit;
struct config_item_type tb_dev_attrib_cit;
+ struct config_item_type tb_dev_action_cit;
struct config_item_type tb_dev_pr_cit;
struct config_item_type tb_dev_wwn_cit;
struct config_item_type tb_dev_alua_tg_pt_gps_cit;
struct t10_pr_registration *pr_reg, int *format_code,
unsigned char *buf);
const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg,
- const char *buf, u32 *out_tid_len, char **port_nexus_ptr);
+ char *buf, u32 *out_tid_len, char **port_nexus_ptr);
/* target_core_hba.c */
struct se_hba *core_alloc_hba(const char *, u32, u32);
dest_rtpi = tmp_lun->lun_rtpi;
i_str = target_parse_pr_out_transport_id(tmp_tpg,
- (const char *)ptr, &tid_len, &iport_ptr);
+ ptr, &tid_len, &iport_ptr);
if (!i_str)
continue;
goto out;
}
initiator_str = target_parse_pr_out_transport_id(dest_se_tpg,
- (const char *)&buf[24], &tmp_tid_len, &iport_ptr);
+ &buf[24], &tmp_tid_len, &iport_ptr);
if (!initiator_str) {
pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate"
" initiator_str from Transport ID\n");
goto err;
}
- ret = ops->execute_unmap(cmd, lba, range);
- if (ret)
- goto err;
+ if (range) {
+ ret = ops->execute_unmap(cmd, lba, range);
+ if (ret)
+ goto err;
+ }
ptr += 16;
size -= 16;
case TCM_OUT_OF_RESOURCES:
cmd->scsi_status = SAM_STAT_TASK_SET_FULL;
goto queue_status;
+ case TCM_LUN_BUSY:
+ cmd->scsi_status = SAM_STAT_BUSY;
+ goto queue_status;
case TCM_RESERVATION_CONFLICT:
/*
* No SENSE Data payload for this case, set SCSI Status
#include <linux/highmem.h>
#include <linux/configfs.h>
#include <linux/mutex.h>
-#include <linux/kthread.h>
+#include <linux/workqueue.h>
#include <net/genetlink.h>
#include <scsi/scsi_common.h>
#include <scsi/scsi_proto.h>
* the total size is 256K * PAGE_SIZE.
*/
#define DATA_BLOCK_SIZE PAGE_SIZE
-#define DATA_BLOCK_BITS (256 * 1024)
+#define DATA_BLOCK_SHIFT PAGE_SHIFT
+#define DATA_BLOCK_BITS_DEF (256 * 1024)
#define DATA_SIZE (DATA_BLOCK_BITS * DATA_BLOCK_SIZE)
-#define DATA_BLOCK_INIT_BITS 128
+
+#define TCMU_MBS_TO_BLOCKS(_mbs) (_mbs << (20 - DATA_BLOCK_SHIFT))
+#define TCMU_BLOCKS_TO_MBS(_blocks) (_blocks >> (20 - DATA_BLOCK_SHIFT))
/* The total size of the ring is 8M + 256K * PAGE_SIZE */
#define TCMU_RING_SIZE (CMDR_SIZE + DATA_SIZE)
-/* Default maximum of the global data blocks(512K * PAGE_SIZE) */
-#define TCMU_GLOBAL_MAX_BLOCKS (512 * 1024)
+/*
+ * Default number of global data blocks(512K * PAGE_SIZE)
+ * when the unmap thread will be started.
+ */
+#define TCMU_GLOBAL_MAX_BLOCKS_DEF (512 * 1024)
static u8 tcmu_kern_cmd_reply_supported;
struct tcmu_dev {
struct list_head node;
struct kref kref;
+
struct se_device se_dev;
char *name;
#define TCMU_DEV_BIT_OPEN 0
#define TCMU_DEV_BIT_BROKEN 1
+#define TCMU_DEV_BIT_BLOCKED 2
unsigned long flags;
struct uio_info uio_info;
/* Must add data_off and mb_addr to get the address */
size_t data_off;
size_t data_size;
+ uint32_t max_blocks;
+ size_t ring_size;
- wait_queue_head_t wait_cmdr;
struct mutex cmdr_lock;
+ struct list_head cmdr_queue;
- bool waiting_global;
uint32_t dbi_max;
uint32_t dbi_thresh;
- DECLARE_BITMAP(data_bitmap, DATA_BLOCK_BITS);
+ unsigned long *data_bitmap;
struct radix_tree_root data_blocks;
struct idr commands;
- spinlock_t commands_lock;
- struct timer_list timeout;
+ struct timer_list cmd_timer;
unsigned int cmd_time_out;
+ struct timer_list qfull_timer;
+ int qfull_time_out;
+
+ struct list_head timedout_entry;
+
spinlock_t nl_cmd_lock;
struct tcmu_nl_cmd curr_nl_cmd;
/* wake up threads waiting on curr_nl_cmd */
struct tcmu_cmd {
struct se_cmd *se_cmd;
struct tcmu_dev *tcmu_dev;
+ struct list_head cmdr_queue_entry;
uint16_t cmd_id;
#define TCMU_CMD_BIT_EXPIRED 0
unsigned long flags;
};
-
-static struct task_struct *unmap_thread;
-static wait_queue_head_t unmap_wait;
+/*
+ * To avoid dead lock the mutex lock order should always be:
+ *
+ * mutex_lock(&root_udev_mutex);
+ * ...
+ * mutex_lock(&tcmu_dev->cmdr_lock);
+ * mutex_unlock(&tcmu_dev->cmdr_lock);
+ * ...
+ * mutex_unlock(&root_udev_mutex);
+ */
static DEFINE_MUTEX(root_udev_mutex);
static LIST_HEAD(root_udev);
-static atomic_t global_db_count = ATOMIC_INIT(0);
+static DEFINE_SPINLOCK(timed_out_udevs_lock);
+static LIST_HEAD(timed_out_udevs);
static struct kmem_cache *tcmu_cmd_cache;
+static atomic_t global_db_count = ATOMIC_INIT(0);
+static struct delayed_work tcmu_unmap_work;
+static int tcmu_global_max_blocks = TCMU_GLOBAL_MAX_BLOCKS_DEF;
+
+static int tcmu_set_global_max_data_area(const char *str,
+ const struct kernel_param *kp)
+{
+ int ret, max_area_mb;
+
+ ret = kstrtoint(str, 10, &max_area_mb);
+ if (ret)
+ return -EINVAL;
+
+ if (max_area_mb <= 0) {
+ pr_err("global_max_data_area must be larger than 0.\n");
+ return -EINVAL;
+ }
+
+ tcmu_global_max_blocks = TCMU_MBS_TO_BLOCKS(max_area_mb);
+ if (atomic_read(&global_db_count) > tcmu_global_max_blocks)
+ schedule_delayed_work(&tcmu_unmap_work, 0);
+ else
+ cancel_delayed_work_sync(&tcmu_unmap_work);
+
+ return 0;
+}
+
+static int tcmu_get_global_max_data_area(char *buffer,
+ const struct kernel_param *kp)
+{
+ return sprintf(buffer, "%d", TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks));
+}
+
+static const struct kernel_param_ops tcmu_global_max_data_area_op = {
+ .set = tcmu_set_global_max_data_area,
+ .get = tcmu_get_global_max_data_area,
+};
+
+module_param_cb(global_max_data_area_mb, &tcmu_global_max_data_area_op, NULL,
+ S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(global_max_data_area_mb,
+ "Max MBs allowed to be allocated to all the tcmu device's "
+ "data areas.");
+
/* multicast group */
enum tcmu_multicast_groups {
TCMU_MCGRP_CONFIG,
page = radix_tree_lookup(&udev->data_blocks, dbi);
if (!page) {
if (atomic_add_return(1, &global_db_count) >
- TCMU_GLOBAL_MAX_BLOCKS) {
- atomic_dec(&global_db_count);
- return false;
- }
+ tcmu_global_max_blocks)
+ schedule_delayed_work(&tcmu_unmap_work, 0);
/* try to get new page from the mm */
page = alloc_page(GFP_KERNEL);
{
int i;
- udev->waiting_global = false;
-
for (i = tcmu_cmd->dbi_cur; i < tcmu_cmd->dbi_cnt; i++) {
if (!tcmu_get_empty_block(udev, tcmu_cmd))
- goto err;
+ return false;
}
return true;
-
-err:
- udev->waiting_global = true;
- /* Try to wake up the unmap thread */
- wake_up(&unmap_wait);
- return false;
}
static inline struct page *
if (!tcmu_cmd)
return NULL;
+ INIT_LIST_HEAD(&tcmu_cmd->cmdr_queue_entry);
tcmu_cmd->se_cmd = se_cmd;
tcmu_cmd->tcmu_dev = udev;
static inline void tcmu_flush_dcache_range(void *vaddr, size_t size)
{
unsigned long offset = offset_in_page(vaddr);
+ void *start = vaddr - offset;
size = round_up(size+offset, PAGE_SIZE);
- vaddr -= offset;
while (size) {
- flush_dcache_page(virt_to_page(vaddr));
+ flush_dcache_page(virt_to_page(start));
+ start += PAGE_SIZE;
size -= PAGE_SIZE;
}
}
return size - head;
}
-static inline void new_iov(struct iovec **iov, int *iov_cnt,
- struct tcmu_dev *udev)
+static inline void new_iov(struct iovec **iov, int *iov_cnt)
{
struct iovec *iovec;
return (size_t)iov->iov_base + iov->iov_len;
}
-static int scatter_data_area(struct tcmu_dev *udev,
+static void scatter_data_area(struct tcmu_dev *udev,
struct tcmu_cmd *tcmu_cmd, struct scatterlist *data_sg,
unsigned int data_nents, struct iovec **iov,
int *iov_cnt, bool copy_data)
to = kmap_atomic(page);
}
- copy_bytes = min_t(size_t, sg_remaining,
- block_remaining);
+ /*
+ * Covert to virtual offset of the ring data area.
+ */
to_offset = get_block_offset_user(udev, dbi,
block_remaining);
+ /*
+ * The following code will gather and map the blocks
+ * to the same iovec when the blocks are all next to
+ * each other.
+ */
+ copy_bytes = min_t(size_t, sg_remaining,
+ block_remaining);
if (*iov_cnt != 0 &&
to_offset == iov_tail(*iov)) {
+ /*
+ * Will append to the current iovec, because
+ * the current block page is next to the
+ * previous one.
+ */
(*iov)->iov_len += copy_bytes;
} else {
- new_iov(iov, iov_cnt, udev);
+ /*
+ * Will allocate a new iovec because we are
+ * first time here or the current block page
+ * is not next to the previous one.
+ */
+ new_iov(iov, iov_cnt);
(*iov)->iov_base = (void __user *)to_offset;
(*iov)->iov_len = copy_bytes;
}
+
if (copy_data) {
offset = DATA_BLOCK_SIZE - block_remaining;
memcpy(to + offset,
copy_bytes);
tcmu_flush_dcache_range(to, copy_bytes);
}
+
sg_remaining -= copy_bytes;
block_remaining -= copy_bytes;
}
kunmap_atomic(from - sg->offset);
}
+
if (to)
kunmap_atomic(to);
-
- return 0;
}
static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
static inline size_t spc_bitmap_free(unsigned long *bitmap, uint32_t thresh)
{
- return DATA_BLOCK_SIZE * (thresh - bitmap_weight(bitmap, thresh));
+ return thresh - bitmap_weight(bitmap, thresh);
}
/*
/* try to check and get the data blocks as needed */
space = spc_bitmap_free(udev->data_bitmap, udev->dbi_thresh);
- if (space < data_needed) {
- unsigned long blocks_left = DATA_BLOCK_BITS - udev->dbi_thresh;
- unsigned long grow;
+ if ((space * DATA_BLOCK_SIZE) < data_needed) {
+ unsigned long blocks_left =
+ (udev->max_blocks - udev->dbi_thresh) + space;
if (blocks_left < blocks_needed) {
pr_debug("no data space: only %lu available, but ask for %zu\n",
return false;
}
- /* Try to expand the thresh */
- if (!udev->dbi_thresh) {
- /* From idle state */
- uint32_t init_thresh = DATA_BLOCK_INIT_BITS;
-
- udev->dbi_thresh = max(blocks_needed, init_thresh);
- } else {
- /*
- * Grow the data area by max(blocks needed,
- * dbi_thresh / 2), but limited to the max
- * DATA_BLOCK_BITS size.
- */
- grow = max(blocks_needed, udev->dbi_thresh / 2);
- udev->dbi_thresh += grow;
- if (udev->dbi_thresh > DATA_BLOCK_BITS)
- udev->dbi_thresh = DATA_BLOCK_BITS;
- }
+ udev->dbi_thresh += blocks_needed;
+ if (udev->dbi_thresh > udev->max_blocks)
+ udev->dbi_thresh = udev->max_blocks;
}
return tcmu_get_empty_blocks(udev, cmd);
return command_size;
}
-static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd)
+static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd, unsigned int tmo,
+ struct timer_list *timer)
{
struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
- unsigned long tmo = udev->cmd_time_out;
int cmd_id;
if (tcmu_cmd->cmd_id)
- return 0;
+ goto setup_timer;
cmd_id = idr_alloc(&udev->commands, tcmu_cmd, 1, USHRT_MAX, GFP_NOWAIT);
if (cmd_id < 0) {
}
tcmu_cmd->cmd_id = cmd_id;
+ pr_debug("allocated cmd %u for dev %s tmo %lu\n", tcmu_cmd->cmd_id,
+ udev->name, tmo / MSEC_PER_SEC);
+
+setup_timer:
if (!tmo)
return 0;
tcmu_cmd->deadline = round_jiffies_up(jiffies + msecs_to_jiffies(tmo));
- mod_timer(&udev->timeout, tcmu_cmd->deadline);
+ mod_timer(timer, tcmu_cmd->deadline);
return 0;
}
-static sense_reason_t
-tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
+static int add_to_cmdr_queue(struct tcmu_cmd *tcmu_cmd)
+{
+ struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
+ unsigned int tmo;
+ int ret;
+
+ /*
+ * For backwards compat if qfull_time_out is not set use
+ * cmd_time_out and if that's not set use the default time out.
+ */
+ if (!udev->qfull_time_out)
+ return -ETIMEDOUT;
+ else if (udev->qfull_time_out > 0)
+ tmo = udev->qfull_time_out;
+ else if (udev->cmd_time_out)
+ tmo = udev->cmd_time_out;
+ else
+ tmo = TCMU_TIME_OUT;
+
+ ret = tcmu_setup_cmd_timer(tcmu_cmd, tmo, &udev->qfull_timer);
+ if (ret)
+ return ret;
+
+ list_add_tail(&tcmu_cmd->cmdr_queue_entry, &udev->cmdr_queue);
+ pr_debug("adding cmd %u on dev %s to ring space wait queue\n",
+ tcmu_cmd->cmd_id, udev->name);
+ return 0;
+}
+
+/**
+ * queue_cmd_ring - queue cmd to ring or internally
+ * @tcmu_cmd: cmd to queue
+ * @scsi_err: TCM error code if failure (-1) returned.
+ *
+ * Returns:
+ * -1 we cannot queue internally or to the ring.
+ * 0 success
+ * 1 internally queued to wait for ring memory to free.
+ */
+static sense_reason_t queue_cmd_ring(struct tcmu_cmd *tcmu_cmd, int *scsi_err)
{
struct tcmu_dev *udev = tcmu_cmd->tcmu_dev;
struct se_cmd *se_cmd = tcmu_cmd->se_cmd;
bool copy_to_data_area;
size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
- if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ *scsi_err = TCM_NO_SENSE;
+
+ if (test_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags)) {
+ *scsi_err = TCM_LUN_BUSY;
+ return -1;
+ }
+
+ if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags)) {
+ *scsi_err = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return -1;
+ }
/*
* Must be a certain minimum size for response sense info, but
base_command_size = tcmu_cmd_get_base_cmd_size(tcmu_cmd->dbi_cnt);
command_size = tcmu_cmd_get_cmd_size(tcmu_cmd, base_command_size);
- mutex_lock(&udev->cmdr_lock);
+ if (!list_empty(&udev->cmdr_queue))
+ goto queue;
mb = udev->mb_addr;
cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */
pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu "
"cmd ring/data area\n", command_size, data_length,
udev->cmdr_size, udev->data_size);
- mutex_unlock(&udev->cmdr_lock);
- return TCM_INVALID_CDB_FIELD;
+ *scsi_err = TCM_INVALID_CDB_FIELD;
+ return -1;
}
- while (!is_ring_space_avail(udev, tcmu_cmd, command_size, data_length)) {
- int ret;
- DEFINE_WAIT(__wait);
-
- prepare_to_wait(&udev->wait_cmdr, &__wait, TASK_INTERRUPTIBLE);
-
- pr_debug("sleeping for ring space\n");
- mutex_unlock(&udev->cmdr_lock);
- if (udev->cmd_time_out)
- ret = schedule_timeout(
- msecs_to_jiffies(udev->cmd_time_out));
- else
- ret = schedule_timeout(msecs_to_jiffies(TCMU_TIME_OUT));
- finish_wait(&udev->wait_cmdr, &__wait);
- if (!ret) {
- pr_warn("tcmu: command timed out\n");
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- }
-
- mutex_lock(&udev->cmdr_lock);
-
- /* We dropped cmdr_lock, cmd_head is stale */
- cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */
+ if (!is_ring_space_avail(udev, tcmu_cmd, command_size, data_length)) {
+ /*
+ * Don't leave commands partially setup because the unmap
+ * thread might need the blocks to make forward progress.
+ */
+ tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cur);
+ tcmu_cmd_reset_dbi_cur(tcmu_cmd);
+ goto queue;
}
/* Insert a PAD if end-of-ring space is too small */
iov_cnt = 0;
copy_to_data_area = (se_cmd->data_direction == DMA_TO_DEVICE
|| se_cmd->se_cmd_flags & SCF_BIDI);
- ret = scatter_data_area(udev, tcmu_cmd, se_cmd->t_data_sg,
- se_cmd->t_data_nents, &iov, &iov_cnt,
- copy_to_data_area);
- if (ret) {
- tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
- mutex_unlock(&udev->cmdr_lock);
-
- pr_err("tcmu: alloc and scatter data failed\n");
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- }
+ scatter_data_area(udev, tcmu_cmd, se_cmd->t_data_sg,
+ se_cmd->t_data_nents, &iov, &iov_cnt,
+ copy_to_data_area);
entry->req.iov_cnt = iov_cnt;
/* Handle BIDI commands */
iov_cnt = 0;
if (se_cmd->se_cmd_flags & SCF_BIDI) {
iov++;
- ret = scatter_data_area(udev, tcmu_cmd,
- se_cmd->t_bidi_data_sg,
- se_cmd->t_bidi_data_nents,
- &iov, &iov_cnt, false);
- if (ret) {
- tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
- mutex_unlock(&udev->cmdr_lock);
-
- pr_err("tcmu: alloc and scatter bidi data failed\n");
- return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- }
+ scatter_data_area(udev, tcmu_cmd, se_cmd->t_bidi_data_sg,
+ se_cmd->t_bidi_data_nents, &iov, &iov_cnt,
+ false);
}
entry->req.iov_bidi_cnt = iov_cnt;
- ret = tcmu_setup_cmd_timer(tcmu_cmd);
+ ret = tcmu_setup_cmd_timer(tcmu_cmd, udev->cmd_time_out,
+ &udev->cmd_timer);
if (ret) {
tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
mutex_unlock(&udev->cmdr_lock);
- return TCM_OUT_OF_RESOURCES;
+
+ *scsi_err = TCM_OUT_OF_RESOURCES;
+ return -1;
}
entry->hdr.cmd_id = tcmu_cmd->cmd_id;
UPDATE_HEAD(mb->cmd_head, command_size, udev->cmdr_size);
tcmu_flush_dcache_range(mb, sizeof(*mb));
- mutex_unlock(&udev->cmdr_lock);
/* TODO: only if FLUSH and FUA? */
uio_event_notify(&udev->uio_info);
- if (udev->cmd_time_out)
- mod_timer(&udev->timeout, round_jiffies_up(jiffies +
- msecs_to_jiffies(udev->cmd_time_out)));
+ return 0;
+
+queue:
+ if (add_to_cmdr_queue(tcmu_cmd)) {
+ *scsi_err = TCM_OUT_OF_RESOURCES;
+ return -1;
+ }
- return TCM_NO_SENSE;
+ return 1;
}
static sense_reason_t
tcmu_queue_cmd(struct se_cmd *se_cmd)
{
+ struct se_device *se_dev = se_cmd->se_dev;
+ struct tcmu_dev *udev = TCMU_DEV(se_dev);
struct tcmu_cmd *tcmu_cmd;
- sense_reason_t ret;
+ sense_reason_t scsi_ret;
+ int ret;
tcmu_cmd = tcmu_alloc_cmd(se_cmd);
if (!tcmu_cmd)
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
- ret = tcmu_queue_cmd_ring(tcmu_cmd);
- if (ret != TCM_NO_SENSE) {
- pr_err("TCMU: Could not queue command\n");
-
+ mutex_lock(&udev->cmdr_lock);
+ ret = queue_cmd_ring(tcmu_cmd, &scsi_ret);
+ mutex_unlock(&udev->cmdr_lock);
+ if (ret < 0)
tcmu_free_cmd(tcmu_cmd);
- }
-
- return ret;
+ return scsi_ret;
}
static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *entry)
}
WARN_ON(tcmu_hdr_get_op(entry->hdr.len_op) != TCMU_OP_CMD);
- spin_lock(&udev->commands_lock);
cmd = idr_remove(&udev->commands, entry->hdr.cmd_id);
- spin_unlock(&udev->commands_lock);
-
if (!cmd) {
- pr_err("cmd_id not found, ring is broken\n");
+ pr_err("cmd_id %u not found, ring is broken\n",
+ entry->hdr.cmd_id);
set_bit(TCMU_DEV_BIT_BROKEN, &udev->flags);
break;
}
handled++;
}
- if (mb->cmd_tail == mb->cmd_head)
- del_timer(&udev->timeout); /* no more pending cmds */
+ if (mb->cmd_tail == mb->cmd_head) {
+ /* no more pending commands */
+ del_timer(&udev->cmd_timer);
- wake_up(&udev->wait_cmdr);
+ if (list_empty(&udev->cmdr_queue)) {
+ /*
+ * no more pending or waiting commands so try to
+ * reclaim blocks if needed.
+ */
+ if (atomic_read(&global_db_count) >
+ tcmu_global_max_blocks)
+ schedule_delayed_work(&tcmu_unmap_work, 0);
+ }
+ }
return handled;
}
static int tcmu_check_expired_cmd(int id, void *p, void *data)
{
struct tcmu_cmd *cmd = p;
+ struct tcmu_dev *udev = cmd->tcmu_dev;
+ u8 scsi_status;
+ struct se_cmd *se_cmd;
+ bool is_running;
if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags))
return 0;
if (!time_after(jiffies, cmd->deadline))
return 0;
- set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags);
- target_complete_cmd(cmd->se_cmd, SAM_STAT_CHECK_CONDITION);
- cmd->se_cmd = NULL;
+ is_running = list_empty(&cmd->cmdr_queue_entry);
+ se_cmd = cmd->se_cmd;
+
+ if (is_running) {
+ /*
+ * If cmd_time_out is disabled but qfull is set deadline
+ * will only reflect the qfull timeout. Ignore it.
+ */
+ if (!udev->cmd_time_out)
+ return 0;
+
+ set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags);
+ /*
+ * target_complete_cmd will translate this to LUN COMM FAILURE
+ */
+ scsi_status = SAM_STAT_CHECK_CONDITION;
+ } else {
+ list_del_init(&cmd->cmdr_queue_entry);
+
+ idr_remove(&udev->commands, id);
+ tcmu_free_cmd(cmd);
+ scsi_status = SAM_STAT_TASK_SET_FULL;
+ }
+
+ pr_debug("Timing out cmd %u on dev %s that is %s.\n",
+ id, udev->name, is_running ? "inflight" : "queued");
+ target_complete_cmd(se_cmd, scsi_status);
return 0;
}
-static void tcmu_device_timedout(struct timer_list *t)
+static void tcmu_device_timedout(struct tcmu_dev *udev)
{
- struct tcmu_dev *udev = from_timer(udev, t, timeout);
- unsigned long flags;
+ spin_lock(&timed_out_udevs_lock);
+ if (list_empty(&udev->timedout_entry))
+ list_add_tail(&udev->timedout_entry, &timed_out_udevs);
+ spin_unlock(&timed_out_udevs_lock);
- spin_lock_irqsave(&udev->commands_lock, flags);
- idr_for_each(&udev->commands, tcmu_check_expired_cmd, NULL);
- spin_unlock_irqrestore(&udev->commands_lock, flags);
+ schedule_delayed_work(&tcmu_unmap_work, 0);
+}
- /* Try to wake up the ummap thread */
- wake_up(&unmap_wait);
+static void tcmu_cmd_timedout(struct timer_list *t)
+{
+ struct tcmu_dev *udev = from_timer(udev, t, cmd_timer);
- /*
- * We don't need to wakeup threads on wait_cmdr since they have their
- * own timeout.
- */
+ pr_debug("%s cmd timeout has expired\n", udev->name);
+ tcmu_device_timedout(udev);
+}
+
+static void tcmu_qfull_timedout(struct timer_list *t)
+{
+ struct tcmu_dev *udev = from_timer(udev, t, qfull_timer);
+
+ pr_debug("%s qfull timeout has expired\n", udev->name);
+ tcmu_device_timedout(udev);
}
static int tcmu_attach_hba(struct se_hba *hba, u32 host_id)
udev->hba = hba;
udev->cmd_time_out = TCMU_TIME_OUT;
+ udev->qfull_time_out = -1;
- init_waitqueue_head(&udev->wait_cmdr);
+ udev->max_blocks = DATA_BLOCK_BITS_DEF;
mutex_init(&udev->cmdr_lock);
+ INIT_LIST_HEAD(&udev->timedout_entry);
+ INIT_LIST_HEAD(&udev->cmdr_queue);
idr_init(&udev->commands);
- spin_lock_init(&udev->commands_lock);
- timer_setup(&udev->timeout, tcmu_device_timedout, 0);
+ timer_setup(&udev->qfull_timer, tcmu_qfull_timedout, 0);
+ timer_setup(&udev->cmd_timer, tcmu_cmd_timedout, 0);
init_waitqueue_head(&udev->nl_cmd_wq);
spin_lock_init(&udev->nl_cmd_lock);
return &udev->se_dev;
}
+static bool run_cmdr_queue(struct tcmu_dev *udev, bool fail)
+{
+ struct tcmu_cmd *tcmu_cmd, *tmp_cmd;
+ LIST_HEAD(cmds);
+ bool drained = true;
+ sense_reason_t scsi_ret;
+ int ret;
+
+ if (list_empty(&udev->cmdr_queue))
+ return true;
+
+ pr_debug("running %s's cmdr queue forcefail %d\n", udev->name, fail);
+
+ list_splice_init(&udev->cmdr_queue, &cmds);
+
+ list_for_each_entry_safe(tcmu_cmd, tmp_cmd, &cmds, cmdr_queue_entry) {
+ list_del_init(&tcmu_cmd->cmdr_queue_entry);
+
+ pr_debug("removing cmd %u on dev %s from queue\n",
+ tcmu_cmd->cmd_id, udev->name);
+
+ if (fail) {
+ idr_remove(&udev->commands, tcmu_cmd->cmd_id);
+ /*
+ * We were not able to even start the command, so
+ * fail with busy to allow a retry in case runner
+ * was only temporarily down. If the device is being
+ * removed then LIO core will do the right thing and
+ * fail the retry.
+ */
+ target_complete_cmd(tcmu_cmd->se_cmd, SAM_STAT_BUSY);
+ tcmu_free_cmd(tcmu_cmd);
+ continue;
+ }
+
+ ret = queue_cmd_ring(tcmu_cmd, &scsi_ret);
+ if (ret < 0) {
+ pr_debug("cmd %u on dev %s failed with %u\n",
+ tcmu_cmd->cmd_id, udev->name, scsi_ret);
+
+ idr_remove(&udev->commands, tcmu_cmd->cmd_id);
+ /*
+ * Ignore scsi_ret for now. target_complete_cmd
+ * drops it.
+ */
+ target_complete_cmd(tcmu_cmd->se_cmd,
+ SAM_STAT_CHECK_CONDITION);
+ tcmu_free_cmd(tcmu_cmd);
+ } else if (ret > 0) {
+ pr_debug("ran out of space during cmdr queue run\n");
+ /*
+ * cmd was requeued, so just put all cmds back in
+ * the queue
+ */
+ list_splice_tail(&cmds, &udev->cmdr_queue);
+ drained = false;
+ goto done;
+ }
+ }
+ if (list_empty(&udev->cmdr_queue))
+ del_timer(&udev->qfull_timer);
+done:
+ return drained;
+}
+
static int tcmu_irqcontrol(struct uio_info *info, s32 irq_on)
{
- struct tcmu_dev *tcmu_dev = container_of(info, struct tcmu_dev, uio_info);
+ struct tcmu_dev *udev = container_of(info, struct tcmu_dev, uio_info);
- mutex_lock(&tcmu_dev->cmdr_lock);
- tcmu_handle_completions(tcmu_dev);
- mutex_unlock(&tcmu_dev->cmdr_lock);
+ mutex_lock(&udev->cmdr_lock);
+ tcmu_handle_completions(udev);
+ run_cmdr_queue(udev, false);
+ mutex_unlock(&udev->cmdr_lock);
return 0;
}
static struct page *tcmu_try_get_block_page(struct tcmu_dev *udev, uint32_t dbi)
{
struct page *page;
- int ret;
mutex_lock(&udev->cmdr_lock);
page = tcmu_get_block_page(udev, dbi);
}
/*
- * Normally it shouldn't be here:
- * Only when the userspace has touched the blocks which
- * are out of the tcmu_cmd's data iov[], and will return
- * one zeroed page.
+ * Userspace messed up and passed in a address not in the
+ * data iov passed to it.
*/
- pr_warn("Block(%u) out of cmd's iov[] has been touched!\n", dbi);
- pr_warn("Mostly it will be a bug of userspace, please have a check!\n");
-
- if (dbi >= udev->dbi_thresh) {
- /* Extern the udev->dbi_thresh to dbi + 1 */
- udev->dbi_thresh = dbi + 1;
- udev->dbi_max = dbi;
- }
-
- page = radix_tree_lookup(&udev->data_blocks, dbi);
- if (!page) {
- page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (!page) {
- mutex_unlock(&udev->cmdr_lock);
- return NULL;
- }
-
- ret = radix_tree_insert(&udev->data_blocks, dbi, page);
- if (ret) {
- mutex_unlock(&udev->cmdr_lock);
- __free_page(page);
- return NULL;
- }
-
- /*
- * Since this case is rare in page fault routine, here we
- * will allow the global_db_count >= TCMU_GLOBAL_MAX_BLOCKS
- * to reduce possible page fault call trace.
- */
- atomic_inc(&global_db_count);
- }
+ pr_err("Invalid addr to data block mapping (dbi %u) on device %s\n",
+ dbi, udev->name);
+ page = NULL;
mutex_unlock(&udev->cmdr_lock);
return page;
dbi = (offset - udev->data_off) / DATA_BLOCK_SIZE;
page = tcmu_try_get_block_page(udev, dbi);
if (!page)
- return VM_FAULT_NOPAGE;
+ return VM_FAULT_SIGBUS;
}
get_page(page);
vma->vm_private_data = udev;
/* Ensure the mmap is exactly the right size */
- if (vma_pages(vma) != (TCMU_RING_SIZE >> PAGE_SHIFT))
+ if (vma_pages(vma) != (udev->ring_size >> PAGE_SHIFT))
return -EINVAL;
return 0;
return -EINVAL;
}
-static void tcmu_blocks_release(struct tcmu_dev *udev)
+static void tcmu_blocks_release(struct radix_tree_root *blocks,
+ int start, int end)
{
int i;
struct page *page;
- /* Try to release all block pages */
- mutex_lock(&udev->cmdr_lock);
- for (i = 0; i <= udev->dbi_max; i++) {
- page = radix_tree_delete(&udev->data_blocks, i);
+ for (i = start; i < end; i++) {
+ page = radix_tree_delete(blocks, i);
if (page) {
__free_page(page);
atomic_dec(&global_db_count);
}
}
- mutex_unlock(&udev->cmdr_lock);
}
static void tcmu_dev_kref_release(struct kref *kref)
vfree(udev->mb_addr);
udev->mb_addr = NULL;
+ spin_lock_bh(&timed_out_udevs_lock);
+ if (!list_empty(&udev->timedout_entry))
+ list_del(&udev->timedout_entry);
+ spin_unlock_bh(&timed_out_udevs_lock);
+
/* Upper layer should drain all requests before calling this */
- spin_lock_irq(&udev->commands_lock);
+ mutex_lock(&udev->cmdr_lock);
idr_for_each_entry(&udev->commands, cmd, i) {
if (tcmu_check_and_free_pending_cmd(cmd) != 0)
all_expired = false;
}
idr_destroy(&udev->commands);
- spin_unlock_irq(&udev->commands_lock);
WARN_ON(!all_expired);
- tcmu_blocks_release(udev);
+ tcmu_blocks_release(&udev->data_blocks, 0, udev->dbi_max + 1);
+ kfree(udev->data_bitmap);
+ mutex_unlock(&udev->cmdr_lock);
call_rcu(&dev->rcu_head, tcmu_dev_call_rcu);
}
wake_up_all(&udev->nl_cmd_wq);
- return ret;;
+ return ret;
}
static int tcmu_netlink_event(struct tcmu_dev *udev, enum tcmu_genl_cmd cmd,
info = &udev->uio_info;
+ udev->data_bitmap = kzalloc(BITS_TO_LONGS(udev->max_blocks) *
+ sizeof(unsigned long), GFP_KERNEL);
+ if (!udev->data_bitmap) {
+ ret = -ENOMEM;
+ goto err_bitmap_alloc;
+ }
+
udev->mb_addr = vzalloc(CMDR_SIZE);
if (!udev->mb_addr) {
ret = -ENOMEM;
/* mailbox fits in first part of CMDR space */
udev->cmdr_size = CMDR_SIZE - CMDR_OFF;
udev->data_off = CMDR_SIZE;
- udev->data_size = DATA_SIZE;
+ udev->data_size = udev->max_blocks * DATA_BLOCK_SIZE;
udev->dbi_thresh = 0; /* Default in Idle state */
- udev->waiting_global = false;
/* Initialise the mailbox of the ring buffer */
mb = udev->mb_addr;
info->mem[0].name = "tcm-user command & data buffer";
info->mem[0].addr = (phys_addr_t)(uintptr_t)udev->mb_addr;
- info->mem[0].size = TCMU_RING_SIZE;
+ info->mem[0].size = udev->ring_size = udev->data_size + CMDR_SIZE;
info->mem[0].memtype = UIO_MEM_NONE;
info->irqcontrol = tcmu_irqcontrol;
vfree(udev->mb_addr);
udev->mb_addr = NULL;
err_vzalloc:
+ kfree(udev->data_bitmap);
+ udev->data_bitmap = NULL;
+err_bitmap_alloc:
kfree(info->name);
info->name = NULL;
{
struct tcmu_dev *udev = TCMU_DEV(dev);
- del_timer_sync(&udev->timeout);
+ del_timer_sync(&udev->cmd_timer);
+ del_timer_sync(&udev->qfull_timer);
mutex_lock(&root_udev_mutex);
list_del(&udev->node);
kref_put(&udev->kref, tcmu_dev_kref_release);
}
+static void tcmu_unblock_dev(struct tcmu_dev *udev)
+{
+ mutex_lock(&udev->cmdr_lock);
+ clear_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags);
+ mutex_unlock(&udev->cmdr_lock);
+}
+
+static void tcmu_block_dev(struct tcmu_dev *udev)
+{
+ mutex_lock(&udev->cmdr_lock);
+
+ if (test_and_set_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags))
+ goto unlock;
+
+ /* complete IO that has executed successfully */
+ tcmu_handle_completions(udev);
+ /* fail IO waiting to be queued */
+ run_cmdr_queue(udev, true);
+
+unlock:
+ mutex_unlock(&udev->cmdr_lock);
+}
+
+static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)
+{
+ struct tcmu_mailbox *mb;
+ struct tcmu_cmd *cmd;
+ int i;
+
+ mutex_lock(&udev->cmdr_lock);
+
+ idr_for_each_entry(&udev->commands, cmd, i) {
+ if (!list_empty(&cmd->cmdr_queue_entry))
+ continue;
+
+ pr_debug("removing cmd %u on dev %s from ring (is expired %d)\n",
+ cmd->cmd_id, udev->name,
+ test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags));
+
+ idr_remove(&udev->commands, i);
+ if (!test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) {
+ if (err_level == 1) {
+ /*
+ * Userspace was not able to start the
+ * command or it is retryable.
+ */
+ target_complete_cmd(cmd->se_cmd, SAM_STAT_BUSY);
+ } else {
+ /* hard failure */
+ target_complete_cmd(cmd->se_cmd,
+ SAM_STAT_CHECK_CONDITION);
+ }
+ }
+ tcmu_cmd_free_data(cmd, cmd->dbi_cnt);
+ tcmu_free_cmd(cmd);
+ }
+
+ mb = udev->mb_addr;
+ tcmu_flush_dcache_range(mb, sizeof(*mb));
+ pr_debug("mb last %u head %u tail %u\n", udev->cmdr_last_cleaned,
+ mb->cmd_tail, mb->cmd_head);
+
+ udev->cmdr_last_cleaned = 0;
+ mb->cmd_tail = 0;
+ mb->cmd_head = 0;
+ tcmu_flush_dcache_range(mb, sizeof(*mb));
+
+ del_timer(&udev->cmd_timer);
+
+ mutex_unlock(&udev->cmdr_lock);
+}
+
enum {
Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_hw_max_sectors,
- Opt_nl_reply_supported, Opt_err,
+ Opt_nl_reply_supported, Opt_max_data_area_mb, Opt_err,
};
static match_table_t tokens = {
{Opt_hw_block_size, "hw_block_size=%u"},
{Opt_hw_max_sectors, "hw_max_sectors=%u"},
{Opt_nl_reply_supported, "nl_reply_supported=%d"},
+ {Opt_max_data_area_mb, "max_data_area_mb=%u"},
{Opt_err, NULL}
};
struct tcmu_dev *udev = TCMU_DEV(dev);
char *orig, *ptr, *opts, *arg_p;
substring_t args[MAX_OPT_ARGS];
- int ret = 0, token;
+ int ret = 0, token, tmpval;
opts = kstrdup(page, GFP_KERNEL);
if (!opts)
if (ret < 0)
pr_err("kstrtoint() failed for nl_reply_supported=\n");
break;
+ case Opt_max_data_area_mb:
+ if (dev->export_count) {
+ pr_err("Unable to set max_data_area_mb while exports exist\n");
+ ret = -EINVAL;
+ break;
+ }
+
+ arg_p = match_strdup(&args[0]);
+ if (!arg_p) {
+ ret = -ENOMEM;
+ break;
+ }
+ ret = kstrtoint(arg_p, 0, &tmpval);
+ kfree(arg_p);
+ if (ret < 0) {
+ pr_err("kstrtoint() failed for max_data_area_mb=\n");
+ break;
+ }
+
+ if (tmpval <= 0) {
+ pr_err("Invalid max_data_area %d\n", tmpval);
+ ret = -EINVAL;
+ break;
+ }
+
+ udev->max_blocks = TCMU_MBS_TO_BLOCKS(tmpval);
+ if (udev->max_blocks > tcmu_global_max_blocks) {
+ pr_err("%d is too large. Adjusting max_data_area_mb to global limit of %u\n",
+ tmpval,
+ TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks));
+ udev->max_blocks = tcmu_global_max_blocks;
+ }
+ break;
default:
break;
}
bl = sprintf(b + bl, "Config: %s ",
udev->dev_config[0] ? udev->dev_config : "NULL");
- bl += sprintf(b + bl, "Size: %zu\n", udev->dev_size);
+ bl += sprintf(b + bl, "Size: %zu ", udev->dev_size);
+ bl += sprintf(b + bl, "MaxDataAreaMB: %u\n",
+ TCMU_BLOCKS_TO_MBS(udev->max_blocks));
return bl;
}
}
CONFIGFS_ATTR(tcmu_, cmd_time_out);
+static ssize_t tcmu_qfull_time_out_show(struct config_item *item, char *page)
+{
+ struct se_dev_attrib *da = container_of(to_config_group(item),
+ struct se_dev_attrib, da_group);
+ struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
+
+ return snprintf(page, PAGE_SIZE, "%ld\n", udev->qfull_time_out <= 0 ?
+ udev->qfull_time_out :
+ udev->qfull_time_out / MSEC_PER_SEC);
+}
+
+static ssize_t tcmu_qfull_time_out_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct se_dev_attrib *da = container_of(to_config_group(item),
+ struct se_dev_attrib, da_group);
+ struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
+ s32 val;
+ int ret;
+
+ ret = kstrtos32(page, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val >= 0) {
+ udev->qfull_time_out = val * MSEC_PER_SEC;
+ } else {
+ printk(KERN_ERR "Invalid qfull timeout value %d\n", val);
+ return -EINVAL;
+ }
+ return count;
+}
+CONFIGFS_ATTR(tcmu_, qfull_time_out);
+
+static ssize_t tcmu_max_data_area_mb_show(struct config_item *item, char *page)
+{
+ struct se_dev_attrib *da = container_of(to_config_group(item),
+ struct se_dev_attrib, da_group);
+ struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
+
+ return snprintf(page, PAGE_SIZE, "%u\n",
+ TCMU_BLOCKS_TO_MBS(udev->max_blocks));
+}
+CONFIGFS_ATTR_RO(tcmu_, max_data_area_mb);
+
static ssize_t tcmu_dev_config_show(struct config_item *item, char *page)
{
struct se_dev_attrib *da = container_of(to_config_group(item),
}
CONFIGFS_ATTR(tcmu_, emulate_write_cache);
+static ssize_t tcmu_block_dev_show(struct config_item *item, char *page)
+{
+ struct se_device *se_dev = container_of(to_config_group(item),
+ struct se_device,
+ dev_action_group);
+ struct tcmu_dev *udev = TCMU_DEV(se_dev);
+
+ if (test_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags))
+ return snprintf(page, PAGE_SIZE, "%s\n", "blocked");
+ else
+ return snprintf(page, PAGE_SIZE, "%s\n", "unblocked");
+}
+
+static ssize_t tcmu_block_dev_store(struct config_item *item, const char *page,
+ size_t count)
+{
+ struct se_device *se_dev = container_of(to_config_group(item),
+ struct se_device,
+ dev_action_group);
+ struct tcmu_dev *udev = TCMU_DEV(se_dev);
+ u8 val;
+ int ret;
+
+ ret = kstrtou8(page, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val > 1) {
+ pr_err("Invalid block value %d\n", val);
+ return -EINVAL;
+ }
+
+ if (!val)
+ tcmu_unblock_dev(udev);
+ else
+ tcmu_block_dev(udev);
+ return count;
+}
+CONFIGFS_ATTR(tcmu_, block_dev);
+
+static ssize_t tcmu_reset_ring_store(struct config_item *item, const char *page,
+ size_t count)
+{
+ struct se_device *se_dev = container_of(to_config_group(item),
+ struct se_device,
+ dev_action_group);
+ struct tcmu_dev *udev = TCMU_DEV(se_dev);
+ u8 val;
+ int ret;
+
+ ret = kstrtou8(page, 0, &val);
+ if (ret < 0)
+ return ret;
+
+ if (val != 1 && val != 2) {
+ pr_err("Invalid reset ring value %d\n", val);
+ return -EINVAL;
+ }
+
+ tcmu_reset_ring(udev, val);
+ return count;
+}
+CONFIGFS_ATTR_WO(tcmu_, reset_ring);
+
static struct configfs_attribute *tcmu_attrib_attrs[] = {
&tcmu_attr_cmd_time_out,
+ &tcmu_attr_qfull_time_out,
+ &tcmu_attr_max_data_area_mb,
&tcmu_attr_dev_config,
&tcmu_attr_dev_size,
&tcmu_attr_emulate_write_cache,
static struct configfs_attribute **tcmu_attrs;
+static struct configfs_attribute *tcmu_action_attrs[] = {
+ &tcmu_attr_block_dev,
+ &tcmu_attr_reset_ring,
+ NULL,
+};
+
static struct target_backend_ops tcmu_ops = {
.name = "user",
.owner = THIS_MODULE,
.show_configfs_dev_params = tcmu_show_configfs_dev_params,
.get_device_type = sbc_get_device_type,
.get_blocks = tcmu_get_blocks,
- .tb_dev_attrib_attrs = NULL,
+ .tb_dev_action_attrs = tcmu_action_attrs,
};
-static int unmap_thread_fn(void *data)
+static void find_free_blocks(void)
{
struct tcmu_dev *udev;
loff_t off;
- uint32_t start, end, block;
- struct page *page;
- int i;
+ u32 start, end, block, total_freed = 0;
- while (!kthread_should_stop()) {
- DEFINE_WAIT(__wait);
+ if (atomic_read(&global_db_count) <= tcmu_global_max_blocks)
+ return;
- prepare_to_wait(&unmap_wait, &__wait, TASK_INTERRUPTIBLE);
- schedule();
- finish_wait(&unmap_wait, &__wait);
+ mutex_lock(&root_udev_mutex);
+ list_for_each_entry(udev, &root_udev, node) {
+ mutex_lock(&udev->cmdr_lock);
- if (kthread_should_stop())
- break;
+ /* Try to complete the finished commands first */
+ tcmu_handle_completions(udev);
- mutex_lock(&root_udev_mutex);
- list_for_each_entry(udev, &root_udev, node) {
- mutex_lock(&udev->cmdr_lock);
+ /* Skip the udevs in idle */
+ if (!udev->dbi_thresh) {
+ mutex_unlock(&udev->cmdr_lock);
+ continue;
+ }
- /* Try to complete the finished commands first */
- tcmu_handle_completions(udev);
+ end = udev->dbi_max + 1;
+ block = find_last_bit(udev->data_bitmap, end);
+ if (block == udev->dbi_max) {
+ /*
+ * The last bit is dbi_max, so it is not possible
+ * reclaim any blocks.
+ */
+ mutex_unlock(&udev->cmdr_lock);
+ continue;
+ } else if (block == end) {
+ /* The current udev will goto idle state */
+ udev->dbi_thresh = start = 0;
+ udev->dbi_max = 0;
+ } else {
+ udev->dbi_thresh = start = block + 1;
+ udev->dbi_max = block;
+ }
- /* Skip the udevs waiting the global pool or in idle */
- if (udev->waiting_global || !udev->dbi_thresh) {
- mutex_unlock(&udev->cmdr_lock);
- continue;
- }
+ /* Here will truncate the data area from off */
+ off = udev->data_off + start * DATA_BLOCK_SIZE;
+ unmap_mapping_range(udev->inode->i_mapping, off, 0, 1);
- end = udev->dbi_max + 1;
- block = find_last_bit(udev->data_bitmap, end);
- if (block == udev->dbi_max) {
- /*
- * The last bit is dbi_max, so there is
- * no need to shrink any blocks.
- */
- mutex_unlock(&udev->cmdr_lock);
- continue;
- } else if (block == end) {
- /* The current udev will goto idle state */
- udev->dbi_thresh = start = 0;
- udev->dbi_max = 0;
- } else {
- udev->dbi_thresh = start = block + 1;
- udev->dbi_max = block;
- }
+ /* Release the block pages */
+ tcmu_blocks_release(&udev->data_blocks, start, end);
+ mutex_unlock(&udev->cmdr_lock);
- /* Here will truncate the data area from off */
- off = udev->data_off + start * DATA_BLOCK_SIZE;
- unmap_mapping_range(udev->inode->i_mapping, off, 0, 1);
-
- /* Release the block pages */
- for (i = start; i < end; i++) {
- page = radix_tree_delete(&udev->data_blocks, i);
- if (page) {
- __free_page(page);
- atomic_dec(&global_db_count);
- }
- }
- mutex_unlock(&udev->cmdr_lock);
- }
+ total_freed += end - start;
+ pr_debug("Freed %u blocks (total %u) from %s.\n", end - start,
+ total_freed, udev->name);
+ }
+ mutex_unlock(&root_udev_mutex);
- /*
- * Try to wake up the udevs who are waiting
- * for the global data pool.
- */
- list_for_each_entry(udev, &root_udev, node) {
- if (udev->waiting_global)
- wake_up(&udev->wait_cmdr);
- }
- mutex_unlock(&root_udev_mutex);
+ if (atomic_read(&global_db_count) > tcmu_global_max_blocks)
+ schedule_delayed_work(&tcmu_unmap_work, msecs_to_jiffies(5000));
+}
+
+static void check_timedout_devices(void)
+{
+ struct tcmu_dev *udev, *tmp_dev;
+ LIST_HEAD(devs);
+
+ spin_lock_bh(&timed_out_udevs_lock);
+ list_splice_init(&timed_out_udevs, &devs);
+
+ list_for_each_entry_safe(udev, tmp_dev, &devs, timedout_entry) {
+ list_del_init(&udev->timedout_entry);
+ spin_unlock_bh(&timed_out_udevs_lock);
+
+ mutex_lock(&udev->cmdr_lock);
+ idr_for_each(&udev->commands, tcmu_check_expired_cmd, NULL);
+ mutex_unlock(&udev->cmdr_lock);
+
+ spin_lock_bh(&timed_out_udevs_lock);
}
- return 0;
+ spin_unlock_bh(&timed_out_udevs_lock);
+}
+
+static void tcmu_unmap_work_fn(struct work_struct *work)
+{
+ check_timedout_devices();
+ find_free_blocks();
}
static int __init tcmu_module_init(void)
BUILD_BUG_ON((sizeof(struct tcmu_cmd_entry) % TCMU_OP_ALIGN_SIZE) != 0);
+ INIT_DELAYED_WORK(&tcmu_unmap_work, tcmu_unmap_work_fn);
+
tcmu_cmd_cache = kmem_cache_create("tcmu_cmd_cache",
sizeof(struct tcmu_cmd),
__alignof__(struct tcmu_cmd),
if (ret)
goto out_attrs;
- init_waitqueue_head(&unmap_wait);
- unmap_thread = kthread_run(unmap_thread_fn, NULL, "tcmu_unmap");
- if (IS_ERR(unmap_thread)) {
- ret = PTR_ERR(unmap_thread);
- goto out_unreg_transport;
- }
-
return 0;
-out_unreg_transport:
- target_backend_unregister(&tcmu_ops);
out_attrs:
kfree(tcmu_attrs);
out_unreg_genl:
static void __exit tcmu_module_exit(void)
{
- kthread_stop(unmap_thread);
+ cancel_delayed_work_sync(&tcmu_unmap_work);
target_backend_unregister(&tcmu_ops);
kfree(tcmu_attrs);
genl_unregister_family(&tcmu_genl_family);
poll_wait(file, &tty->read_wait, wait);
poll_wait(file, &tty->write_wait, wait);
if (tty_hung_up_p(file))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (!tty_is_writelocked(tty) && tty_write_room(tty) > 0)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (gsm->dead)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
return mask;
}
/* set bits for operations that won't block */
if (!list_empty(&n_hdlc->rx_buf_list.list))
- mask |= POLLIN | POLLRDNORM; /* readable */
+ mask |= EPOLLIN | EPOLLRDNORM; /* readable */
if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (tty_hung_up_p(filp))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (!tty_is_writelocked(tty) &&
!list_empty(&n_hdlc->tx_free_buf_list.list))
- mask |= POLLOUT | POLLWRNORM; /* writable */
+ mask |= EPOLLOUT | EPOLLWRNORM; /* writable */
}
return mask;
} /* end of n_hdlc_tty_poll() */
struct r3964_client_info *pClient;
struct r3964_message *pMsg = NULL;
unsigned long flags;
- __poll_t result = POLLOUT;
+ __poll_t result = EPOLLOUT;
TRACE_L("POLL");
pMsg = pClient->first_msg;
spin_unlock_irqrestore(&pInfo->lock, flags);
if (pMsg)
- result |= POLLIN | POLLRDNORM;
+ result |= EPOLLIN | EPOLLRDNORM;
} else {
result = -EINVAL;
}
put_tty_queue(c, ldata);
smp_store_release(&ldata->canon_head, ldata->read_head);
kill_fasync(&tty->fasync, SIGIO, POLL_IN);
- wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+ wake_up_interruptible_poll(&tty->read_wait, EPOLLIN);
return 0;
}
}
if (read_cnt(ldata)) {
kill_fasync(&tty->fasync, SIGIO, POLL_IN);
- wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+ wake_up_interruptible_poll(&tty->read_wait, EPOLLIN);
}
}
poll_wait(file, &tty->read_wait, wait);
poll_wait(file, &tty->write_wait, wait);
if (input_available_p(tty, 1))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
else {
tty_buffer_flush_work(tty->port);
if (input_available_p(tty, 1))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (tty->packet && tty->link->ctrl_status)
- mask |= POLLPRI | POLLIN | POLLRDNORM;
+ mask |= EPOLLPRI | EPOLLIN | EPOLLRDNORM;
if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (tty_hung_up_p(file))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (tty->ops->write && !tty_is_writelocked(tty) &&
tty_chars_in_buffer(tty) < WAKEUP_CHARS &&
tty_write_room(tty) > 0)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
tty->ctrl_status &= ~TIOCPKT_STOP;
tty->ctrl_status |= TIOCPKT_START;
spin_unlock_irqrestore(&tty->ctrl_lock, flags);
- wake_up_interruptible_poll(&tty->link->read_wait, POLLIN);
+ wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN);
}
}
tty->ctrl_status &= ~TIOCPKT_START;
tty->ctrl_status |= TIOCPKT_STOP;
spin_unlock_irqrestore(&tty->ctrl_lock, flags);
- wake_up_interruptible_poll(&tty->link->read_wait, POLLIN);
+ wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN);
}
}
}
/*
- * When CONFIG_ACPI_SPCR_TABLE is defined, "earlycon" without parameters in
- * command line does not start DT earlycon immediately, instead it defers
- * starting it until DT/ACPI decision is made. At that time if ACPI is enabled
- * call parse_spcr(), else call early_init_dt_scan_chosen_stdout()
+ * This defers the initialization of the early console until after ACPI has
+ * been initialized.
*/
-bool earlycon_init_is_deferred __initdata;
+bool earlycon_acpi_spcr_enable __initdata;
/* early_param wrapper for setup_earlycon() */
static int __init param_setup_earlycon(char *buf)
{
int err;
- /*
- * Just 'earlycon' is a valid param for devicetree earlycons;
- * don't generate a warning from parse_early_params() in that case
- */
+ /* Just 'earlycon' is a valid param for devicetree and ACPI SPCR. */
if (!buf || !buf[0]) {
if (IS_ENABLED(CONFIG_ACPI_SPCR_TABLE)) {
- earlycon_init_is_deferred = true;
+ earlycon_acpi_spcr_enable = true;
return 0;
} else if (!buf) {
return early_init_dt_scan_chosen_stdout();
/* No kernel lock held - none needed ;) */
static __poll_t hung_up_tty_poll(struct file *filp, poll_table *wait)
{
- return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM;
+ return EPOLLIN | EPOLLOUT | EPOLLERR | EPOLLHUP | EPOLLRDNORM | EPOLLWRNORM;
}
static long hung_up_tty_ioctl(struct file *file, unsigned int cmd,
tty_ldisc_deref(ld);
}
}
- wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
+ wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT);
}
EXPORT_SYMBOL_GPL(tty_wakeup);
static void tty_write_unlock(struct tty_struct *tty)
{
mutex_unlock(&tty->atomic_write_lock);
- wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
+ wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT);
}
static int tty_write_lock(struct tty_struct *tty, int ndelay)
if (tty->count <= 1) {
if (waitqueue_active(&tty->read_wait)) {
- wake_up_poll(&tty->read_wait, POLLIN);
+ wake_up_poll(&tty->read_wait, EPOLLIN);
do_sleep++;
}
if (waitqueue_active(&tty->write_wait)) {
- wake_up_poll(&tty->write_wait, POLLOUT);
+ wake_up_poll(&tty->write_wait, EPOLLOUT);
do_sleep++;
}
}
if (o_tty && o_tty->count <= 1) {
if (waitqueue_active(&o_tty->read_wait)) {
- wake_up_poll(&o_tty->read_wait, POLLIN);
+ wake_up_poll(&o_tty->read_wait, EPOLLIN);
do_sleep++;
}
if (waitqueue_active(&o_tty->write_wait)) {
- wake_up_poll(&o_tty->write_wait, POLLOUT);
+ wake_up_poll(&o_tty->write_wait, EPOLLOUT);
do_sleep++;
}
}
tty_ldisc_deref(ld);
}
- wake_up_interruptible_poll(&tty->write_wait, POLLOUT);
- wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+ wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT);
+ wake_up_interruptible_poll(&tty->read_wait, EPOLLIN);
/*
* Shutdown the current line discipline, and reset it to
vcs_poll(struct file *file, poll_table *wait)
{
struct vcs_poll_data *poll = vcs_poll_data_get(file);
- __poll_t ret = DEFAULT_POLLMASK|POLLERR|POLLPRI;
+ __poll_t ret = DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
if (poll) {
poll_wait(file, &poll->waitq, wait);
poll_wait(filep, &idev->wait, wait);
if (listener->event_count != atomic_read(&idev->event))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
spin_lock_irqsave(&desc->iuspin, flags);
if (test_bit(WDM_DISCONNECTING, &desc->flags)) {
- mask = POLLHUP | POLLERR;
+ mask = EPOLLHUP | EPOLLERR;
spin_unlock_irqrestore(&desc->iuspin, flags);
goto desc_out;
}
if (test_bit(WDM_READ, &desc->flags))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
if (desc->rerr || desc->werr)
- mask |= POLLERR;
+ mask |= EPOLLERR;
if (!test_bit(WDM_IN_USE, &desc->flags))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
spin_unlock_irqrestore(&desc->iuspin, flags);
poll_wait(file, &desc->wait, wait);
poll_wait(file, &usblp->rwait, wait);
poll_wait(file, &usblp->wwait, wait);
spin_lock_irqsave(&usblp->lock, flags);
- ret = ((usblp->bidir && usblp->rcomplete) ? POLLIN | POLLRDNORM : 0) |
- ((usblp->no_paper || usblp->wcomplete) ? POLLOUT | POLLWRNORM : 0);
+ ret = ((usblp->bidir && usblp->rcomplete) ? EPOLLIN | EPOLLRDNORM : 0) |
+ ((usblp->no_paper || usblp->wcomplete) ? EPOLLOUT | EPOLLWRNORM : 0);
spin_unlock_irqrestore(&usblp->lock, flags);
return ret;
}
mutex_lock(&data->io_mutex);
if (data->zombie) {
- mask = POLLHUP | POLLERR;
+ mask = EPOLLHUP | EPOLLERR;
goto no_poll;
}
poll_wait(file, &data->waitq, wait);
- mask = (atomic_read(&data->srq_asserted)) ? POLLIN | POLLRDNORM : 0;
+ mask = (atomic_read(&data->srq_asserted)) ? EPOLLIN | EPOLLRDNORM : 0;
no_poll:
mutex_unlock(&data->io_mutex);
event_count = atomic_read(&device_event.count);
if (file->f_version != event_count) {
file->f_version = event_count;
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
return 0;
poll_wait(file, &ps->wait, wait);
if (file->f_mode & FMODE_WRITE && !list_empty(&ps->async_completed))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (!connected(ps))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (list_empty(&ps->list))
- mask |= POLLERR;
+ mask |= EPOLLERR;
return mask;
}
static __poll_t ffs_ep0_poll(struct file *file, poll_table *wait)
{
struct ffs_data *ffs = file->private_data;
- __poll_t mask = POLLWRNORM;
+ __poll_t mask = EPOLLWRNORM;
int ret;
poll_wait(file, &ffs->ev.waitq, wait);
switch (ffs->state) {
case FFS_READ_DESCRIPTORS:
case FFS_READ_STRINGS:
- mask |= POLLOUT;
+ mask |= EPOLLOUT;
break;
case FFS_ACTIVE:
switch (ffs->setup_state) {
case FFS_NO_SETUP:
if (ffs->ev.count)
- mask |= POLLIN;
+ mask |= EPOLLIN;
break;
case FFS_SETUP_PENDING:
case FFS_SETUP_CANCELLED:
- mask |= (POLLIN | POLLOUT);
+ mask |= (EPOLLIN | EPOLLOUT);
break;
}
case FFS_CLOSING:
poll_wait(file, &hidg->write_queue, wait);
if (WRITE_COND)
- ret |= POLLOUT | POLLWRNORM;
+ ret |= EPOLLOUT | EPOLLWRNORM;
if (READ_COND)
- ret |= POLLIN | POLLRDNORM;
+ ret |= EPOLLIN | EPOLLRDNORM;
return ret;
}
spin_lock_irqsave(&dev->lock, flags);
if (likely(!list_empty(&dev->tx_reqs)))
- status |= POLLOUT | POLLWRNORM;
+ status |= EPOLLOUT | EPOLLWRNORM;
if (likely(dev->current_rx_bytes) ||
likely(!list_empty(&dev->rx_buffers)))
- status |= POLLIN | POLLRDNORM;
+ status |= EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&dev->lock, flags);
/* report fd mode change before acting on it */
if (dev->setup_abort) {
dev->setup_abort = 0;
- mask = POLLHUP;
+ mask = EPOLLHUP;
goto out;
}
if (dev->state == STATE_DEV_SETUP) {
if (dev->setup_in || dev->setup_can_stall)
- mask = POLLOUT;
+ mask = EPOLLOUT;
} else {
if (dev->ev_next != 0)
- mask = POLLIN;
+ mask = EPOLLIN;
}
out:
spin_unlock_irq(&dev->lock);
__poll_t mask = 0;
if (!dev->present)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
poll_wait(file, &dev->read_wait, wait);
poll_wait(file, &dev->write_wait, wait);
if (!dev->present)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
if (read_index(dev) != -1)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (atomic_read(&dev->write_busy) < MAX_WRITES_IN_FLIGHT)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
dev = file->private_data;
if (!dev->intf)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
poll_wait(file, &dev->read_wait, wait);
poll_wait(file, &dev->write_wait, wait);
if (dev->ring_head != dev->ring_tail)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (!dev->interrupt_out_busy)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
dev = file->private_data;
if (!dev->udev)
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
poll_wait(file, &dev->read_wait, wait);
poll_wait(file, &dev->write_wait, wait);
tower_check_for_read_packet(dev);
if (dev->read_packet_length > 0) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (!dev->interrupt_out_busy) {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
return mask;
spin_lock_irqsave(&rp->b_lock, flags);
if (!MON_RING_EMPTY(rp))
- mask |= POLLIN | POLLRDNORM; /* readable */
+ mask |= EPOLLIN | EPOLLRDNORM; /* readable */
spin_unlock_irqrestore(&rp->b_lock, flags);
return mask;
}
struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
__poll_t flags = key_to_poll(key);
- if (flags & POLLIN) {
+ if (flags & EPOLLIN) {
/* An event has been signaled, call function */
if ((!virqfd->handler ||
virqfd->handler(virqfd->opaque, virqfd->data)) &&
schedule_work(&virqfd->inject);
}
- if (flags & POLLHUP) {
+ if (flags & EPOLLHUP) {
unsigned long flags;
spin_lock_irqsave(&virqfd_lock, flags);
* Check if there was an event already pending on the eventfd
* before we registered and trigger it as if we didn't miss it.
*/
- if (events & POLLIN) {
+ if (events & EPOLLIN) {
if ((!handler || handler(opaque, data)) && thread)
schedule_work(&virqfd->inject);
}
/*
* Do not drop the file until the irqfd is fully initialized,
- * otherwise we might race against the POLLHUP.
+ * otherwise we might race against the EPOLLHUP.
*/
fdput(irqfd);
}
vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
- vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
- vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
+ vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
+ vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
f->private_data = n;
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
vhost_dev_stop(&n->dev);
- vhost_dev_cleanup(&n->dev, false);
+ vhost_dev_cleanup(&n->dev);
vhost_net_vq_reset(n);
if (tx_sock)
sockfd_put(tx_sock);
sg = cmd->tvc_sgl;
prot_sg = cmd->tvc_prot_sgl;
pages = cmd->tvc_upages;
- memset(cmd, 0, sizeof(struct vhost_scsi_cmd));
-
+ memset(cmd, 0, sizeof(*cmd));
cmd->tvc_sgl = sg;
cmd->tvc_prot_sgl = prot_sg;
cmd->tvc_upages = pages;
mutex_unlock(&vs->dev.mutex);
vhost_scsi_clear_endpoint(vs, &t);
vhost_dev_stop(&vs->dev);
- vhost_dev_cleanup(&vs->dev, false);
+ vhost_dev_cleanup(&vs->dev);
/* Jobs can re-queue themselves in evt kick handler. Do extra flush. */
vhost_scsi_flush(vs);
kfree(vs->dev.vqs);
return -EEXIST;
}
- tv_nexus = kzalloc(sizeof(struct vhost_scsi_nexus), GFP_KERNEL);
+ tv_nexus = kzalloc(sizeof(*tv_nexus), GFP_KERNEL);
if (!tv_nexus) {
mutex_unlock(&tpg->tv_tpg_mutex);
pr_err("Unable to allocate struct vhost_scsi_nexus\n");
if (kstrtou16(name + 5, 10, &tpgt) || tpgt >= VHOST_SCSI_MAX_TARGET)
return ERR_PTR(-EINVAL);
- tpg = kzalloc(sizeof(struct vhost_scsi_tpg), GFP_KERNEL);
+ tpg = kzalloc(sizeof(*tpg), GFP_KERNEL);
if (!tpg) {
pr_err("Unable to allocate struct vhost_scsi_tpg");
return ERR_PTR(-ENOMEM);
/* if (vhost_scsi_parse_wwn(name, &wwpn, 1) < 0)
return ERR_PTR(-EINVAL); */
- tport = kzalloc(sizeof(struct vhost_scsi_tport), GFP_KERNEL);
+ tport = kzalloc(sizeof(*tport), GFP_KERNEL);
if (!tport) {
pr_err("Unable to allocate struct vhost_scsi_tport");
return ERR_PTR(-ENOMEM);
vhost_test_stop(n, &private);
vhost_test_flush(n);
- vhost_dev_cleanup(&n->dev, false);
+ vhost_dev_cleanup(&n->dev);
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_test_flush(n);
{
clear_bit(VHOST_WORK_QUEUED, &work->flags);
work->fn = fn;
- init_waitqueue_head(&work->done);
}
EXPORT_SYMBOL_GPL(vhost_work_init);
mask = file->f_op->poll(file, &poll->table);
if (mask)
vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
- if (mask & POLLERR) {
+ if (mask & EPOLLERR) {
if (poll->wqh)
remove_wait_queue(poll->wqh, &poll->wait);
ret = -EINVAL;
vq->acked_features = 0;
vq->log_base = NULL;
vq->error_ctx = NULL;
- vq->error = NULL;
vq->kick = NULL;
vq->call_ctx = NULL;
- vq->call = NULL;
vq->log_ctx = NULL;
vhost_reset_is_le(vq);
vhost_disable_cross_endian(vq);
dev->nvqs = nvqs;
mutex_init(&dev->mutex);
dev->log_ctx = NULL;
- dev->log_file = NULL;
dev->umem = NULL;
dev->iotlb = NULL;
dev->mm = NULL;
vhost_vq_reset(dev, vq);
if (vq->handle_kick)
vhost_poll_init(&vq->poll, vq->handle_kick,
- POLLIN, dev);
+ EPOLLIN, dev);
}
}
EXPORT_SYMBOL_GPL(vhost_dev_init);
{
int i;
- vhost_dev_cleanup(dev, true);
+ vhost_dev_cleanup(dev);
/* Restore memory to default empty mapping. */
INIT_LIST_HEAD(&umem->umem_list);
spin_unlock(&dev->iotlb_lock);
}
-/* Caller should have device mutex if and only if locked is set */
-void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
+void vhost_dev_cleanup(struct vhost_dev *dev)
{
int i;
for (i = 0; i < dev->nvqs; ++i) {
if (dev->vqs[i]->error_ctx)
eventfd_ctx_put(dev->vqs[i]->error_ctx);
- if (dev->vqs[i]->error)
- fput(dev->vqs[i]->error);
if (dev->vqs[i]->kick)
fput(dev->vqs[i]->kick);
if (dev->vqs[i]->call_ctx)
eventfd_ctx_put(dev->vqs[i]->call_ctx);
- if (dev->vqs[i]->call)
- fput(dev->vqs[i]->call);
vhost_vq_reset(dev, dev->vqs[i]);
}
vhost_dev_free_iovecs(dev);
if (dev->log_ctx)
eventfd_ctx_put(dev->log_ctx);
dev->log_ctx = NULL;
- if (dev->log_file)
- fput(dev->log_file);
- dev->log_file = NULL;
/* No one will access memory at this point */
vhost_umem_clean(dev->umem);
dev->umem = NULL;
vhost_umem_clean(dev->iotlb);
dev->iotlb = NULL;
vhost_clear_msg(dev);
- wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM);
+ wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
WARN_ON(!llist_empty(&dev->work_list));
if (dev->worker) {
kthread_stop(dev->worker);
poll_wait(file, &dev->wait, wait);
if (!list_empty(&dev->read_list))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
r = -EFAULT;
break;
}
- eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
- if (IS_ERR(eventfp)) {
- r = PTR_ERR(eventfp);
+ ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd);
+ if (IS_ERR(ctx)) {
+ r = PTR_ERR(ctx);
break;
}
- if (eventfp != vq->call) {
- filep = vq->call;
- ctx = vq->call_ctx;
- vq->call = eventfp;
- vq->call_ctx = eventfp ?
- eventfd_ctx_fileget(eventfp) : NULL;
- } else
- filep = eventfp;
+ swap(ctx, vq->call_ctx);
break;
case VHOST_SET_VRING_ERR:
if (copy_from_user(&f, argp, sizeof f)) {
r = -EFAULT;
break;
}
- eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
- if (IS_ERR(eventfp)) {
- r = PTR_ERR(eventfp);
+ ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd);
+ if (IS_ERR(ctx)) {
+ r = PTR_ERR(ctx);
break;
}
- if (eventfp != vq->error) {
- filep = vq->error;
- vq->error = eventfp;
- ctx = vq->error_ctx;
- vq->error_ctx = eventfp ?
- eventfd_ctx_fileget(eventfp) : NULL;
- } else
- filep = eventfp;
+ swap(ctx, vq->error_ctx);
break;
case VHOST_SET_VRING_ENDIAN:
r = vhost_set_vring_endian(vq, argp);
if (pollstop && vq->handle_kick)
vhost_poll_stop(&vq->poll);
- if (ctx)
+ if (!IS_ERR_OR_NULL(ctx))
eventfd_ctx_put(ctx);
if (filep)
fput(filep);
/* Caller must have device mutex */
long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
{
- struct file *eventfp, *filep = NULL;
- struct eventfd_ctx *ctx = NULL;
+ struct eventfd_ctx *ctx;
u64 p;
long r;
int i, fd;
r = get_user(fd, (int __user *)argp);
if (r < 0)
break;
- eventfp = fd == -1 ? NULL : eventfd_fget(fd);
- if (IS_ERR(eventfp)) {
- r = PTR_ERR(eventfp);
+ ctx = fd == -1 ? NULL : eventfd_ctx_fdget(fd);
+ if (IS_ERR(ctx)) {
+ r = PTR_ERR(ctx);
break;
}
- if (eventfp != d->log_file) {
- filep = d->log_file;
- d->log_file = eventfp;
- ctx = d->log_ctx;
- d->log_ctx = eventfp ?
- eventfd_ctx_fileget(eventfp) : NULL;
- } else
- filep = eventfp;
+ swap(ctx, d->log_ctx);
for (i = 0; i < d->nvqs; ++i) {
mutex_lock(&d->vqs[i]->mutex);
d->vqs[i]->log_ctx = d->log_ctx;
}
if (ctx)
eventfd_ctx_put(ctx);
- if (filep)
- fput(filep);
break;
default:
r = -ENOIOCTLCMD;
list_add_tail(&node->node, head);
spin_unlock(&dev->iotlb_lock);
- wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM);
+ wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
}
EXPORT_SYMBOL_GPL(vhost_enqueue_msg);
struct vhost_work {
struct llist_node node;
vhost_work_fn_t fn;
- wait_queue_head_t done;
- int flushing;
- unsigned queue_seq;
- unsigned done_seq;
unsigned long flags;
};
struct vring_used __user *used;
const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
struct file *kick;
- struct file *call;
- struct file *error;
struct eventfd_ctx *call_ctx;
struct eventfd_ctx *error_ctx;
struct eventfd_ctx *log_ctx;
struct mutex mutex;
struct vhost_virtqueue **vqs;
int nvqs;
- struct file *log_file;
struct eventfd_ctx *log_ctx;
struct llist_head work_list;
struct task_struct *worker;
long vhost_dev_check_owner(struct vhost_dev *);
struct vhost_umem *vhost_dev_reset_owner_prepare(void);
void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *);
-void vhost_dev_cleanup(struct vhost_dev *, bool locked);
+void vhost_dev_cleanup(struct vhost_dev *);
void vhost_dev_stop(struct vhost_dev *);
long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp);
}
spin_unlock_bh(&vsock->send_pkt_list_lock);
- vhost_dev_cleanup(&vsock->dev, false);
+ vhost_dev_cleanup(&vsock->dev);
kfree(vsock->dev.vqs);
vhost_vsock_free(vsock);
return 0;
bool "Enable DDC Support"
depends on FB_I810 && FB_I810_GTF
select FB_DDC
- help
config FB_LE80578
tristate "Intel LE80578 (Vermilion) support"
#include <linux/regulator/consumer.h>
#include <linux/suspend.h>
#include <linux/component.h>
+#include <linux/pinctrl/consumer.h>
#include <video/omapfb_dss.h>
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/seq_file.h>
+
#include <video/omapfb_dss.h>
#include "dss.h"
#include <linux/io.h>
#include <linux/platform_device.h>
#include <linux/clk.h>
+#include <linux/seq_file.h>
#include <video/omapfb_dss.h>
#include <linux/err.h>
#include <linux/io.h>
#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+
#include <video/omapfb_dss.h>
#include "dss.h"
spin_lock_irqsave(&dbq->lock, flags);
poll_wait(filp, &dbq->wait, p);
- mask = (dbq->head == dbq->tail) ? 0 : (POLLIN | POLLRDNORM);
+ mask = (dbq->head == dbq->tail) ? 0 : (EPOLLIN | EPOLLRDNORM);
spin_unlock_irqrestore(&dbq->lock, flags);
bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
or CONFIG_S390_GUEST.
-menu "Virtio drivers"
+menuconfig VIRTIO_MENU
+ bool "Virtio drivers"
+ default y
+
+if VIRTIO_MENU
config VIRTIO_PCI
tristate "PCI driver for virtio devices"
If unsure, say 'N'.
-endmenu
+endif # VIRTIO_MENU
}
EXPORT_SYMBOL_GPL(unregister_virtio_driver);
+/**
+ * register_virtio_device - register virtio device
+ * @dev : virtio device to be registered
+ *
+ * On error, the caller must call put_device on &@dev->dev (and not kfree),
+ * as another code path may have obtained a reference to @dev.
+ *
+ * Returns: 0 on suceess, -error on failure
+ */
int register_virtio_device(struct virtio_device *dev)
{
int err;
dev->dev.bus = &virtio_bus;
+ device_initialize(&dev->dev);
/* Assign a unique device index and hence name. */
err = ida_simple_get(&virtio_index_ida, 0, 0, GFP_KERNEL);
INIT_LIST_HEAD(&dev->vqs);
- /* device_register() causes the bus infrastructure to look for a
- * matching driver. */
- err = device_register(&dev->dev);
+ /*
+ * device_add() causes the bus infrastructure to look for a matching
+ * driver.
+ */
+ err = device_add(&dev->dev);
if (err)
ida_simple_remove(&virtio_index_ida, dev->index);
out:
struct sysinfo i;
unsigned int idx = 0;
long available;
+ unsigned long caches;
all_vm_events(events);
si_meminfo(&i);
available = si_mem_available();
+ caches = global_node_page_state(NR_FILE_PAGES);
#ifdef CONFIG_VM_EVENT_COUNTERS
update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
pages_to_bytes(i.totalram));
update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
pages_to_bytes(available));
+ update_stat(vb, idx++, VIRTIO_BALLOON_S_CACHES,
+ pages_to_bytes(caches));
return idx;
}
pdev = platform_device_register_resndata(&vm_cmdline_parent,
"virtio-mmio", vm_cmdline_id++,
resources, ARRAY_SIZE(resources), NULL, 0);
- if (IS_ERR(pdev))
- return PTR_ERR(pdev);
- return 0;
+ return PTR_ERR_OR_ZERO(pdev);
}
static int vm_cmdline_get_device(struct device *dev, void *data)
/* Platform driver */
-static struct of_device_id virtio_mmio_match[] = {
+static const struct of_device_id virtio_mmio_match[] = {
{ .compatible = "virtio,mmio", },
{},
};
static int virtio_pci_probe(struct pci_dev *pci_dev,
const struct pci_device_id *id)
{
- struct virtio_pci_device *vp_dev;
+ struct virtio_pci_device *vp_dev, *reg_dev = NULL;
int rc;
/* allocate our structure and fill it out */
pci_set_master(pci_dev);
rc = register_virtio_device(&vp_dev->vdev);
+ reg_dev = vp_dev;
if (rc)
goto err_register;
err_probe:
pci_disable_device(pci_dev);
err_enable_device:
- kfree(vp_dev);
+ if (reg_dev)
+ put_device(&vp_dev->vdev.dev);
+ else
+ kfree(vp_dev);
return rc;
}
static __poll_t evtchn_poll(struct file *file, poll_table *wait)
{
- __poll_t mask = POLLOUT | POLLWRNORM;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM;
struct per_user_data *u = file->private_data;
poll_wait(file, &u->evtchn_wait, wait);
if (u->ring_cons != u->ring_prod)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (u->ring_overflow)
- mask = POLLERR;
+ mask = EPOLLERR;
return mask;
}
if (entry->page) {
pr_debug("freeing g.e. %#x (pfn %#lx)\n",
entry->ref, page_to_pfn(entry->page));
- __free_page(entry->page);
+ put_page(entry->page);
} else
pr_info("freeing g.e. %#x\n", entry->ref);
kfree(entry);
if (gnttab_end_foreign_access_ref(ref, readonly)) {
put_free_entry(ref);
if (page != 0)
- free_page(page);
+ put_page(virt_to_page(page));
} else
gnttab_add_deferred(ref, readonly,
page ? virt_to_page(page) : NULL);
poll_wait(file, &xen_mce_chrdev_wait, wait);
if (xen_mcelog.next)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
ret = inet_accept(mappass->sock, sock, O_NONBLOCK, true);
if (ret == -EAGAIN) {
sock_release(sock);
- goto out_error;
+ return;
}
map = pvcalls_new_active_socket(fedata,
if (req_id != PVCALLS_INVALID_ID &&
READ_ONCE(bedata->rsp[req_id].req_id) == req_id)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
poll_wait(file, &map->passive.inflight_accept_req, wait);
return 0;
if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET,
(void *)&map->passive.flags))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
/*
* First check RET, then INFLIGHT. No barriers necessary to
poll_wait(file, &map->active.inflight_conn_req, wait);
if (pvcalls_front_write_todo(map))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (pvcalls_front_read_todo(map))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (in_error != 0 || out_error != 0)
- mask |= POLLERR;
+ mask |= EPOLLERR;
return mask;
}
pvcalls_enter();
if (!pvcalls_front_dev) {
pvcalls_exit();
- return POLLNVAL;
+ return EPOLLNVAL;
}
bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
map = (struct sock_mapping *) sock->sk->sk_send_head;
if (!map) {
pvcalls_exit();
- return POLLNVAL;
+ return EPOLLNVAL;
}
if (map->active_socket)
ret = pvcalls_front_poll_active(file, bedata, map, wait);
struct msghdr *msg,
size_t len,
int flags);
-unsigned int pvcalls_front_poll(struct file *file,
+__poll_t pvcalls_front_poll(struct file *file,
struct socket *sock,
poll_table *wait);
int pvcalls_front_release(struct socket *sock);
poll_wait(file, &u->read_waitq, wait);
if (!list_empty(&u->read_buffers))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
*/
int afs_end_cursor(struct afs_addr_cursor *ac)
{
- if (ac->responded && ac->index != ac->start)
- WRITE_ONCE(ac->alist->index, ac->index);
+ struct afs_addr_list *alist;
+
+ alist = ac->alist;
+ if (alist) {
+ if (ac->responded && ac->index != ac->start)
+ WRITE_ONCE(alist->index, ac->index);
+ afs_put_addrlist(alist);
+ }
- afs_put_addrlist(ac->alist);
+ ac->addr = NULL;
ac->alist = NULL;
+ ac->begun = false;
return ac->error;
}
#include <linux/pagemap.h>
#include <linux/ctype.h>
#include <linux/sched.h>
+#include <linux/dns_resolver.h>
#include "internal.h"
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags);
+static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags);
static int afs_dir_open(struct inode *inode, struct file *file);
static int afs_readdir(struct file *file, struct dir_context *ctx);
static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
.listxattr = afs_listxattr,
};
+const struct file_operations afs_dynroot_file_operations = {
+ .open = dcache_dir_open,
+ .release = dcache_dir_close,
+ .iterate_shared = dcache_readdir,
+ .llseek = dcache_dir_lseek,
+};
+
+const struct inode_operations afs_dynroot_inode_operations = {
+ .lookup = afs_dynroot_lookup,
+};
+
const struct dentry_operations afs_fs_dentry_operations = {
.d_revalidate = afs_d_revalidate,
.d_delete = afs_d_delete,
return 0;
}
+/*
+ * Probe to see if a cell may exist. This prevents positive dentries from
+ * being created unnecessarily.
+ */
+static int afs_probe_cell_name(struct dentry *dentry)
+{
+ struct afs_cell *cell;
+ const char *name = dentry->d_name.name;
+ size_t len = dentry->d_name.len;
+ int ret;
+
+ /* Names prefixed with a dot are R/W mounts. */
+ if (name[0] == '.') {
+ if (len == 1)
+ return -EINVAL;
+ name++;
+ len--;
+ }
+
+ cell = afs_lookup_cell_rcu(afs_d2net(dentry), name, len);
+ if (!IS_ERR(cell)) {
+ afs_put_cell(afs_d2net(dentry), cell);
+ return 0;
+ }
+
+ ret = dns_query("afsdb", name, len, "ipv4", NULL, NULL);
+ if (ret == -ENODATA)
+ ret = -EDESTADDRREQ;
+ return ret;
+}
+
/*
* Try to auto mount the mountpoint with pseudo directory, if the autocell
* operation is setted.
*/
-static struct inode *afs_try_auto_mntpt(
- int ret, struct dentry *dentry, struct inode *dir, struct key *key,
- struct afs_fid *fid)
+static struct inode *afs_try_auto_mntpt(struct dentry *dentry,
+ struct inode *dir, struct afs_fid *fid)
{
- const char *devname = dentry->d_name.name;
struct afs_vnode *vnode = AFS_FS_I(dir);
struct inode *inode;
+ int ret = -ENOENT;
- _enter("%d, %p{%pd}, {%x:%u}, %p",
- ret, dentry, dentry, vnode->fid.vid, vnode->fid.vnode, key);
+ _enter("%p{%pd}, {%x:%u}",
+ dentry, dentry, vnode->fid.vid, vnode->fid.vnode);
+
+ if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))
+ goto out;
- if (ret != -ENOENT ||
- !test_bit(AFS_VNODE_AUTOCELL, &vnode->flags))
+ ret = afs_probe_cell_name(dentry);
+ if (ret < 0)
goto out;
- inode = afs_iget_autocell(dir, devname, strlen(devname), key);
+ inode = afs_iget_pseudo_dir(dir->i_sb, false);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto out;
ret = afs_do_lookup(dir, dentry, &fid, key);
if (ret < 0) {
- inode = afs_try_auto_mntpt(ret, dentry, dir, key, &fid);
- if (!IS_ERR(inode)) {
- key_put(key);
- goto success;
+ if (ret == -ENOENT) {
+ inode = afs_try_auto_mntpt(dentry, dir, &fid);
+ if (!IS_ERR(inode)) {
+ key_put(key);
+ goto success;
+ }
+
+ ret = PTR_ERR(inode);
}
- ret = PTR_ERR(inode);
key_put(key);
if (ret == -ENOENT) {
d_add(dentry, NULL);
return NULL;
}
+/*
+ * Look up an entry in a dynroot directory.
+ */
+static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ struct afs_vnode *vnode;
+ struct afs_fid fid;
+ struct inode *inode;
+ int ret;
+
+ vnode = AFS_FS_I(dir);
+
+ _enter("%pd", dentry);
+
+ ASSERTCMP(d_inode(dentry), ==, NULL);
+
+ if (dentry->d_name.len >= AFSNAMEMAX) {
+ _leave(" = -ENAMETOOLONG");
+ return ERR_PTR(-ENAMETOOLONG);
+ }
+
+ inode = afs_try_auto_mntpt(dentry, dir, &fid);
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ if (ret == -ENOENT) {
+ d_add(dentry, NULL);
+ _leave(" = NULL [negative]");
+ return NULL;
+ }
+ _leave(" = %d [do]", ret);
+ return ERR_PTR(ret);
+ }
+
+ d_add(dentry, inode);
+ _leave(" = 0 { ino=%lu v=%u }",
+ d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
+ return NULL;
+}
+
/*
* check that a dentry lookup hit has found a valid entry
* - NOTE! the hit can be a negative hit too, so we can't assume we have an
*/
static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
+ struct afs_super_info *as = dentry->d_sb->s_fs_info;
struct afs_vnode *vnode, *dir;
struct afs_fid uninitialized_var(fid);
struct dentry *parent;
if (flags & LOOKUP_RCU)
return -ECHILD;
+ if (as->dyn_root)
+ return 1;
+
if (d_really_is_positive(dentry)) {
vnode = AFS_FS_I(d_inode(dentry));
_enter("{v={%x:%u} n=%pd fl=%lx},",
*
* These pseudo inodes don't match anything.
*/
-static int afs_iget5_autocell_test(struct inode *inode, void *opaque)
+static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque)
{
return 0;
}
}
/*
- * inode retrieval for autocell
+ * Create an inode for a dynamic root directory or an autocell dynamic
+ * automount dir.
*/
-struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name,
- int namesz, struct key *key)
+struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
{
struct afs_iget_data data;
struct afs_super_info *as;
struct afs_vnode *vnode;
- struct super_block *sb;
struct inode *inode;
static atomic_t afs_autocell_ino;
- _enter("{%x:%u},%*.*s,",
- AFS_FS_I(dir)->fid.vid, AFS_FS_I(dir)->fid.vnode,
- namesz, namesz, dev_name ?: "");
+ _enter("");
- sb = dir->i_sb;
as = sb->s_fs_info;
- data.volume = as->volume;
- data.fid.vid = as->volume->vid;
- data.fid.unique = 0;
- data.fid.vnode = 0;
+ if (as->volume) {
+ data.volume = as->volume;
+ data.fid.vid = as->volume->vid;
+ }
+ if (root) {
+ data.fid.vnode = 1;
+ data.fid.unique = 1;
+ } else {
+ data.fid.vnode = atomic_inc_return(&afs_autocell_ino);
+ data.fid.unique = 0;
+ }
- inode = iget5_locked(sb, atomic_inc_return(&afs_autocell_ino),
- afs_iget5_autocell_test, afs_iget5_set,
+ inode = iget5_locked(sb, data.fid.vnode,
+ afs_iget5_pseudo_dir_test, afs_iget5_set,
&data);
if (!inode) {
_leave(" = -ENOMEM");
inode->i_size = 0;
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
- inode->i_op = &afs_autocell_inode_operations;
+ if (root) {
+ inode->i_op = &afs_dynroot_inode_operations;
+ inode->i_fop = &afs_dynroot_file_operations;
+ } else {
+ inode->i_op = &afs_autocell_inode_operations;
+ }
set_nlink(inode, 2);
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
inode->i_generation = 0;
set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags);
- set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
- inode->i_flags |= S_AUTOMOUNT | S_NOATIME;
+ if (!root) {
+ set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+ inode->i_flags |= S_AUTOMOUNT;
+ }
+
+ inode->i_flags |= S_NOATIME;
unlock_new_inode(inode);
_leave(" = %p", inode);
return inode;
bool rwpath; /* T if the parent should be considered R/W */
bool force; /* T to force cell type */
bool autocell; /* T if set auto mount operation */
+ bool dyn_root; /* T if dynamic root */
afs_voltype_t type; /* type of volume requested */
int volnamesz; /* size of volume name */
const char *volname; /* name of volume to mount */
struct afs_net *net; /* Network namespace */
struct afs_cell *cell; /* The cell in which the volume resides */
struct afs_volume *volume; /* volume record */
+ bool dyn_root; /* True if dynamic root */
};
static inline struct afs_super_info *AFS_FS_S(struct super_block *sb)
/*
* dir.c
*/
-extern bool afs_dir_check_page(struct inode *, struct page *);
+extern const struct file_operations afs_dir_file_operations;
extern const struct inode_operations afs_dir_inode_operations;
+extern const struct file_operations afs_dynroot_file_operations;
+extern const struct inode_operations afs_dynroot_inode_operations;
extern const struct dentry_operations afs_fs_dentry_operations;
-extern const struct file_operations afs_dir_file_operations;
+
+extern bool afs_dir_check_page(struct inode *, struct page *);
/*
* file.c
*/
extern int afs_fetch_status(struct afs_vnode *, struct key *);
extern int afs_iget5_test(struct inode *, void *);
-extern struct inode *afs_iget_autocell(struct inode *, const char *, int,
- struct key *);
+extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool);
extern struct inode *afs_iget(struct super_block *, struct key *,
struct afs_fid *, struct afs_file_status *,
struct afs_callback *,
*/
static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
{
- struct afs_super_info *super;
+ struct afs_super_info *as;
struct vfsmount *mnt;
struct afs_vnode *vnode;
struct page *page;
goto error_no_page;
if (mntpt->d_name.name[0] == '.') {
- devname[0] = '#';
- memcpy(devname + 1, mntpt->d_name.name, size - 1);
+ devname[0] = '%';
+ memcpy(devname + 1, mntpt->d_name.name + 1, size - 1);
memcpy(devname + size, afs_root_cell,
sizeof(afs_root_cell));
rwpath = true;
} else {
- devname[0] = '%';
+ devname[0] = '#';
memcpy(devname + 1, mntpt->d_name.name, size);
memcpy(devname + size + 1, afs_root_cell,
sizeof(afs_root_cell));
}
/* work out what options we want */
- super = AFS_FS_S(mntpt->d_sb);
- memcpy(options, "cell=", 5);
- strcpy(options + 5, super->volume->cell->name);
- if (super->volume->type == AFSVL_RWVOL || rwpath)
- strcat(options, ",rwpath");
+ as = AFS_FS_S(mntpt->d_sb);
+ if (as->cell) {
+ memcpy(options, "cell=", 5);
+ strcpy(options + 5, as->cell->name);
+ if ((as->volume && as->volume->type == AFSVL_RWVOL) || rwpath)
+ strcat(options, ",rwpath");
+ }
/* try and do the mount */
_debug("--- attempting mount %s -o %s ---", devname, options);
if (!afs_start_fs_iteration(fc, vnode))
goto failed;
- goto use_server;
-
-next_server:
- _debug("next");
- afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
- fc->cbi = NULL;
- fc->index++;
- if (fc->index >= fc->server_list->nr_servers)
- fc->index = 0;
- if (fc->index != fc->start)
- goto use_server;
-
- /* That's all the servers poked to no good effect. Try again if some
- * of them were busy.
- */
- if (fc->flags & AFS_FS_CURSOR_VBUSY)
- goto restart_from_beginning;
-
- fc->ac.error = -EDESTADDRREQ;
- goto failed;
use_server:
_debug("use");
afs_get_addrlist(alist);
read_unlock(&server->fs_lock);
+ memset(&fc->ac, 0, sizeof(fc->ac));
/* Probe the current fileserver if we haven't done so yet. */
if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) {
else
afs_put_addrlist(alist);
- fc->ac.addr = NULL;
fc->ac.start = READ_ONCE(alist->index);
fc->ac.index = fc->ac.start;
- fc->ac.error = 0;
- fc->ac.begun = false;
- goto iterate_address;
iterate_address:
ASSERT(fc->ac.alist);
/* Iterate over the current server's address list to try and find an
* address on which it will respond to us.
*/
- if (afs_iterate_addresses(&fc->ac)) {
- _leave(" = t");
- return true;
- }
+ if (!afs_iterate_addresses(&fc->ac))
+ goto next_server;
+
+ _leave(" = t");
+ return true;
+next_server:
+ _debug("next");
afs_end_cursor(&fc->ac);
- goto next_server;
+ afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
+ fc->cbi = NULL;
+ fc->index++;
+ if (fc->index >= fc->server_list->nr_servers)
+ fc->index = 0;
+ if (fc->index != fc->start)
+ goto use_server;
+
+ /* That's all the servers poked to no good effect. Try again if some
+ * of them were busy.
+ */
+ if (fc->flags & AFS_FS_CURSOR_VBUSY)
+ goto restart_from_beginning;
+
+ fc->ac.error = -EDESTADDRREQ;
+ goto failed;
failed:
fc->flags |= AFS_FS_CURSOR_STOP;
+ afs_end_cursor(&fc->ac);
_leave(" = f [failed %d]", fc->ac.error);
return false;
}
return false;
}
+ memset(&fc->ac, 0, sizeof(fc->ac));
fc->ac.alist = alist;
- fc->ac.addr = NULL;
fc->ac.start = READ_ONCE(alist->index);
fc->ac.index = fc->ac.start;
- fc->ac.error = 0;
- fc->ac.begun = false;
goto iterate_address;
case 0:
return fc->ac.error;
}
-
-#if 0
-/*
- * Set a filesystem server cursor for using a specific FS server.
- */
-int afs_set_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode)
-{
- afs_init_fs_cursor(fc, vnode);
-
- read_seqlock_excl(&vnode->cb_lock);
- if (vnode->cb_interest) {
- if (vnode->cb_interest->server->fs_state == 0)
- fc->server = afs_get_server(vnode->cb_interest->server);
- else
- fc->ac.error = vnode->cb_interest->server->fs_state;
- } else {
- fc->ac.error = -ESTALE;
- }
- read_sequnlock_excl(&vnode->cb_lock);
-
- return fc->ac.error;
-}
-
-/*
- * pick a server to use to try accessing this volume
- * - returns with an elevated usage count on the server chosen
- */
-bool afs_volume_pick_fileserver(struct afs_fs_cursor *fc, struct afs_vnode *vnode)
-{
- struct afs_volume *volume = vnode->volume;
- struct afs_server *server;
- int ret, state, loop;
-
- _enter("%s", volume->vlocation->vldb.name);
-
- /* stick with the server we're already using if we can */
- if (vnode->cb_interest && vnode->cb_interest->server->fs_state == 0) {
- fc->server = afs_get_server(vnode->cb_interest->server);
- goto set_server;
- }
-
- down_read(&volume->server_sem);
-
- /* handle the no-server case */
- if (volume->nservers == 0) {
- fc->ac.error = volume->rjservers ? -ENOMEDIUM : -ESTALE;
- up_read(&volume->server_sem);
- _leave(" = f [no servers %d]", fc->ac.error);
- return false;
- }
-
- /* basically, just search the list for the first live server and use
- * that */
- ret = 0;
- for (loop = 0; loop < volume->nservers; loop++) {
- server = volume->servers[loop];
- state = server->fs_state;
-
- _debug("consider %d [%d]", loop, state);
-
- switch (state) {
- case 0:
- goto picked_server;
-
- case -ENETUNREACH:
- if (ret == 0)
- ret = state;
- break;
-
- case -EHOSTUNREACH:
- if (ret == 0 ||
- ret == -ENETUNREACH)
- ret = state;
- break;
-
- case -ECONNREFUSED:
- if (ret == 0 ||
- ret == -ENETUNREACH ||
- ret == -EHOSTUNREACH)
- ret = state;
- break;
-
- default:
- case -EREMOTEIO:
- if (ret == 0 ||
- ret == -ENETUNREACH ||
- ret == -EHOSTUNREACH ||
- ret == -ECONNREFUSED)
- ret = state;
- break;
- }
- }
-
-error:
- fc->ac.error = ret;
-
- /* no available servers
- * - TODO: handle the no active servers case better
- */
- up_read(&volume->server_sem);
- _leave(" = f [%d]", fc->ac.error);
- return false;
-
-picked_server:
- /* Found an apparently healthy server. We need to register an interest
- * in receiving callbacks before we talk to it.
- */
- ret = afs_register_server_cb_interest(vnode,
- &volume->cb_interests[loop], server);
- if (ret < 0)
- goto error;
-
- fc->server = afs_get_server(server);
- up_read(&volume->server_sem);
-set_server:
- fc->ac.alist = afs_get_addrlist(fc->server->addrs);
- fc->ac.addr = &fc->ac.alist->addrs[0];
- _debug("USING SERVER: %pIS\n", &fc->ac.addr->transport);
- _leave(" = t (picked %pIS)", &fc->ac.addr->transport);
- return true;
-}
-
-/*
- * release a server after use
- * - releases the ref on the server struct that was acquired by picking
- * - records result of using a particular server to access a volume
- * - return true to try again, false if okay or to issue error
- * - the caller must release the server struct if result was false
- */
-bool afs_iterate_fs_cursor(struct afs_fs_cursor *fc,
- struct afs_vnode *vnode)
-{
- struct afs_volume *volume = vnode->volume;
- struct afs_server *server = fc->server;
- unsigned loop;
-
- _enter("%s,%pIS,%d",
- volume->vlocation->vldb.name, &fc->ac.addr->transport,
- fc->ac.error);
-
- switch (fc->ac.error) {
- /* success */
- case 0:
- server->fs_state = 0;
- _leave(" = f");
- return false;
-
- /* the fileserver denied all knowledge of the volume */
- case -ENOMEDIUM:
- down_write(&volume->server_sem);
-
- /* firstly, find where the server is in the active list (if it
- * is) */
- for (loop = 0; loop < volume->nservers; loop++)
- if (volume->servers[loop] == server)
- goto present;
-
- /* no longer there - may have been discarded by another op */
- goto try_next_server_upw;
-
- present:
- volume->nservers--;
- memmove(&volume->servers[loop],
- &volume->servers[loop + 1],
- sizeof(volume->servers[loop]) *
- (volume->nservers - loop));
- volume->servers[volume->nservers] = NULL;
- afs_put_server(afs_v2net(vnode), server);
- volume->rjservers++;
-
- if (volume->nservers > 0)
- /* another server might acknowledge its existence */
- goto try_next_server_upw;
-
- /* handle the case where all the fileservers have rejected the
- * volume
- * - TODO: try asking the fileservers for volume information
- * - TODO: contact the VL server again to see if the volume is
- * no longer registered
- */
- up_write(&volume->server_sem);
- afs_put_server(afs_v2net(vnode), server);
- fc->server = NULL;
- _leave(" = f [completely rejected]");
- return false;
-
- /* problem reaching the server */
- case -ENETUNREACH:
- case -EHOSTUNREACH:
- case -ECONNREFUSED:
- case -ETIME:
- case -ETIMEDOUT:
- case -EREMOTEIO:
- /* mark the server as dead
- * TODO: vary dead timeout depending on error
- */
- spin_lock(&server->fs_lock);
- if (!server->fs_state) {
- server->fs_state = fc->ac.error;
- printk("kAFS: SERVER DEAD state=%d\n", fc->ac.error);
- }
- spin_unlock(&server->fs_lock);
- goto try_next_server;
-
- /* miscellaneous error */
- default:
- case -ENOMEM:
- case -ENONET:
- /* tell the caller to accept the result */
- afs_put_server(afs_v2net(vnode), server);
- fc->server = NULL;
- _leave(" = f [local failure]");
- return false;
- }
-
- /* tell the caller to loop around and try the next server */
-try_next_server_upw:
- up_write(&volume->server_sem);
-try_next_server:
- afs_put_server(afs_v2net(vnode), server);
- _leave(" = t [try next server]");
- return true;
-}
-
-/*
- * Clean up a fileserver cursor.
- */
-int afs_end_fs_cursor(struct afs_fs_cursor *fc, struct afs_net *net)
-{
- afs_end_cursor(&fc->ac);
- afs_put_server(net, fc->server);
- return fc->ac.error;
-}
-
-#endif
server = afs_lookup_server(cell, key, &vldb->fs_server[i]);
if (IS_ERR(server)) {
ret = PTR_ERR(server);
- if (ret == -ENOENT)
+ if (ret == -ENOENT ||
+ ret == -ENOMEDIUM)
continue;
goto error_2;
}
enum {
afs_no_opt,
afs_opt_cell,
+ afs_opt_dyn,
afs_opt_rwpath,
afs_opt_vol,
afs_opt_autocell,
static const match_table_t afs_options_list = {
{ afs_opt_cell, "cell=%s" },
+ { afs_opt_dyn, "dyn" },
{ afs_opt_rwpath, "rwpath" },
{ afs_opt_vol, "vol=%s" },
{ afs_opt_autocell, "autocell" },
const char *suf = "";
char pref = '%';
+ if (as->dyn_root) {
+ seq_puts(m, "none");
+ return 0;
+ }
+
switch (volume->type) {
case AFSVL_RWVOL:
break;
*/
static int afs_show_options(struct seq_file *m, struct dentry *root)
{
+ struct afs_super_info *as = AFS_FS_S(root->d_sb);
+
+ if (as->dyn_root)
+ seq_puts(m, ",dyn");
if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags))
- seq_puts(m, "autocell");
+ seq_puts(m, ",autocell");
return 0;
}
break;
case afs_opt_rwpath:
- params->rwpath = 1;
+ params->rwpath = true;
break;
case afs_opt_vol:
break;
case afs_opt_autocell:
- params->autocell = 1;
+ params->autocell = true;
+ break;
+
+ case afs_opt_dyn:
+ params->dyn_root = true;
break;
default:
int cellnamesz;
_enter(",%s", name);
-
+
if (!name) {
printk(KERN_ERR "kAFS: no volume name specified\n");
return -EINVAL;
struct afs_super_info *as1 = data;
struct afs_super_info *as = AFS_FS_S(sb);
- return as->net == as1->net && as->volume->vid == as1->volume->vid;
+ return (as->net == as1->net &&
+ as->volume &&
+ as->volume->vid == as1->volume->vid);
+}
+
+static int afs_dynroot_test_super(struct super_block *sb, void *data)
+{
+ return false;
}
static int afs_set_super(struct super_block *sb, void *data)
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = AFS_FS_MAGIC;
sb->s_op = &afs_super_ops;
- sb->s_xattr = afs_xattr_handlers;
+ if (!as->dyn_root)
+ sb->s_xattr = afs_xattr_handlers;
ret = super_setup_bdi(sb);
if (ret)
return ret;
sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
- sprintf(sb->s_id, "%u", as->volume->vid);
-
- afs_activate_volume(as->volume);
/* allocate the root inode and dentry */
- fid.vid = as->volume->vid;
- fid.vnode = 1;
- fid.unique = 1;
- inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL);
+ if (as->dyn_root) {
+ inode = afs_iget_pseudo_dir(sb, true);
+ sb->s_flags |= SB_RDONLY;
+ } else {
+ sprintf(sb->s_id, "%u", as->volume->vid);
+ afs_activate_volume(as->volume);
+ fid.vid = as->volume->vid;
+ fid.vnode = 1;
+ fid.unique = 1;
+ inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL);
+ }
+
if (IS_ERR(inode))
return PTR_ERR(inode);
- if (params->autocell)
+ if (params->autocell || params->dyn_root)
set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);
ret = -ENOMEM;
as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
if (as) {
as->net = afs_get_net(params->net);
- as->cell = afs_get_cell(params->cell);
+ if (params->dyn_root)
+ as->dyn_root = true;
+ else
+ as->cell = afs_get_cell(params->cell);
}
return as;
}
goto error;
}
- ret = afs_parse_device_name(¶ms, dev_name);
- if (ret < 0)
- goto error;
+ if (!params.dyn_root) {
+ ret = afs_parse_device_name(¶ms, dev_name);
+ if (ret < 0)
+ goto error;
- /* try and do the mount securely */
- key = afs_request_key(params.cell);
- if (IS_ERR(key)) {
- _leave(" = %ld [key]", PTR_ERR(key));
- ret = PTR_ERR(key);
- goto error;
+ /* try and do the mount securely */
+ key = afs_request_key(params.cell);
+ if (IS_ERR(key)) {
+ _leave(" = %ld [key]", PTR_ERR(key));
+ ret = PTR_ERR(key);
+ goto error;
+ }
+ params.key = key;
}
- params.key = key;
/* allocate a superblock info record */
ret = -ENOMEM;
if (!as)
goto error_key;
- /* Assume we're going to need a volume record; at the very least we can
- * use it to update the volume record if we have one already. This
- * checks that the volume exists within the cell.
- */
- candidate = afs_create_volume(¶ms);
- if (IS_ERR(candidate)) {
- ret = PTR_ERR(candidate);
- goto error_as;
- }
+ if (!params.dyn_root) {
+ /* Assume we're going to need a volume record; at the very
+ * least we can use it to update the volume record if we have
+ * one already. This checks that the volume exists within the
+ * cell.
+ */
+ candidate = afs_create_volume(¶ms);
+ if (IS_ERR(candidate)) {
+ ret = PTR_ERR(candidate);
+ goto error_as;
+ }
- as->volume = candidate;
+ as->volume = candidate;
+ }
/* allocate a deviceless superblock */
- sb = sget(fs_type, afs_test_super, afs_set_super, flags, as);
+ sb = sget(fs_type,
+ as->dyn_root ? afs_dynroot_test_super : afs_test_super,
+ afs_set_super, flags, as);
if (IS_ERR(sb)) {
ret = PTR_ERR(sb);
goto error_as;
/* Clear the callback interests (which will do ilookup5) before
* deactivating the superblock.
*/
- afs_clear_callback_interests(as->net, as->volume->servers);
+ if (as->volume)
+ afs_clear_callback_interests(as->net, as->volume->servers);
kill_anon_super(sb);
- afs_deactivate_volume(as->volume);
+ if (as->volume)
+ afs_deactivate_volume(as->volume);
afs_destroy_sbi(as);
}
*/
static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
+ struct afs_super_info *as = AFS_FS_S(dentry->d_sb);
struct afs_fs_cursor fc;
struct afs_volume_status vs;
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
struct key *key;
int ret;
+ buf->f_type = dentry->d_sb->s_magic;
+ buf->f_bsize = AFS_BLOCK_SIZE;
+ buf->f_namelen = AFSNAMEMAX - 1;
+
+ if (as->dyn_root) {
+ buf->f_blocks = 1;
+ buf->f_bavail = 0;
+ buf->f_bfree = 0;
+ return 0;
+ }
+
key = afs_request_key(vnode->volume->cell);
if (IS_ERR(key))
return PTR_ERR(key);
key_put(key);
if (ret == 0) {
- buf->f_type = dentry->d_sb->s_magic;
- buf->f_bsize = AFS_BLOCK_SIZE;
- buf->f_namelen = AFSNAMEMAX - 1;
-
if (vs.max_quota == 0)
buf->f_blocks = vs.part_max_blocks;
else
struct afs_uvldbentry__xdr *uvldb;
struct afs_vldb_entry *entry;
bool new_only = false;
- u32 tmp;
+ u32 tmp, nr_servers;
int i, ret;
_enter("");
uvldb = call->buffer;
entry = call->reply[0];
+ nr_servers = ntohl(uvldb->nServers);
+ if (nr_servers > AFS_NMAXNSERVERS)
+ nr_servers = AFS_NMAXNSERVERS;
+
for (i = 0; i < ARRAY_SIZE(uvldb->name) - 1; i++)
entry->name[i] = (u8)ntohl(uvldb->name[i]);
entry->name[i] = 0;
/* If there is a new replication site that we can use, ignore all the
* sites that aren't marked as new.
*/
- for (i = 0; i < AFS_NMAXNSERVERS; i++) {
+ for (i = 0; i < nr_servers; i++) {
tmp = ntohl(uvldb->serverFlags[i]);
if (!(tmp & AFS_VLSF_DONTUSE) &&
(tmp & AFS_VLSF_NEWREPSITE))
new_only = true;
}
- for (i = 0; i < AFS_NMAXNSERVERS; i++) {
+ for (i = 0; i < nr_servers; i++) {
struct afs_uuid__xdr *xdr;
struct afs_uuid *uuid;
int j;
unsigned long type_mask)
{
struct afs_server_list *slist;
- struct afs_server *server;
struct afs_volume *volume;
- int ret = -ENOMEM, nr_servers = 0, i, j;
+ int ret = -ENOMEM, nr_servers = 0, i;
for (i = 0; i < vldb->nr_servers; i++)
if (vldb->fs_mask[i] & type_mask)
refcount_set(&slist->usage, 1);
volume->servers = slist;
-
- /* Make sure a records exists for each server this volume occupies. */
- for (i = 0; i < nr_servers; i++) {
- if (!(vldb->fs_mask[i] & type_mask))
- continue;
-
- server = afs_lookup_server(params->cell, params->key,
- &vldb->fs_server[i]);
- if (IS_ERR(server)) {
- ret = PTR_ERR(server);
- if (ret == -ENOENT)
- continue;
- goto error_2;
- }
-
- /* Insertion-sort by server pointer */
- for (j = 0; j < slist->nr_servers; j++)
- if (slist->servers[j].server >= server)
- break;
- if (j < slist->nr_servers) {
- if (slist->servers[j].server == server) {
- afs_put_server(params->net, server);
- continue;
- }
-
- memmove(slist->servers + j + 1,
- slist->servers + j,
- (slist->nr_servers - j) * sizeof(struct afs_server_entry));
- }
-
- slist->servers[j].server = server;
- slist->nr_servers++;
- }
-
- if (slist->nr_servers == 0) {
- ret = -EDESTADDRREQ;
- goto error_2;
- }
-
return volume;
-error_2:
- afs_put_serverlist(params->net, slist);
error_1:
+ afs_put_cell(params->net, volume->cell);
kfree(volume);
error_0:
return ERR_PTR(ret);
/* See if the volume's server list got updated. */
new = afs_alloc_server_list(volume->cell, key,
- vldb, (1 << volume->type));
+ vldb, (1 << volume->type));
if (IS_ERR(new)) {
ret = PTR_ERR(new);
goto error_vldb;
/*
* poll for culling state
- * - use POLLOUT to indicate culling state
+ * - use EPOLLOUT to indicate culling state
*/
static __poll_t cachefiles_daemon_poll(struct file *file,
struct poll_table_struct *poll)
mask = 0;
if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
- mask |= POLLIN;
+ mask |= EPOLLIN;
if (test_bit(CACHEFILES_CULLING, &cache->flags))
- mask |= POLLOUT;
+ mask |= EPOLLOUT;
return mask;
}
* start an async read(ahead) operation. return nr_pages we submitted
* a read for on success, or negative error code.
*/
-static int start_read(struct inode *inode, struct list_head *page_list, int max)
+static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx,
+ struct list_head *page_list, int max)
{
struct ceph_osd_client *osdc =
&ceph_inode_to_client(inode)->client->osdc;
int got = 0;
int ret = 0;
- if (!current->journal_info) {
+ if (!rw_ctx) {
/* caller of readpages does not hold buffer and read caps
* (fadvise, madvise and readahead cases) */
int want = CEPH_CAP_FILE_CACHE;
{
struct inode *inode = file_inode(file);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+ struct ceph_file_info *ci = file->private_data;
+ struct ceph_rw_context *rw_ctx;
int rc = 0;
int max = 0;
if (rc == 0)
goto out;
+ rw_ctx = ceph_find_rw_context(ci);
max = fsc->mount_options->rsize >> PAGE_SHIFT;
- dout("readpages %p file %p nr_pages %d max %d\n",
- inode, file, nr_pages, max);
+ dout("readpages %p file %p ctx %p nr_pages %d max %d\n",
+ inode, file, rw_ctx, nr_pages, max);
while (!list_empty(page_list)) {
- rc = start_read(inode, page_list, max);
+ rc = start_read(inode, rw_ctx, page_list, max);
if (rc < 0)
goto out;
}
struct ceph_fs_client *fsc;
struct ceph_snap_context *snapc, *oldest;
loff_t page_off = page_offset(page);
- long writeback_stat;
int err, len = PAGE_SIZE;
struct ceph_writeback_ctl ceph_wbc;
dout("writepage %p page %p index %lu on %llu~%u snapc %p seq %lld\n",
inode, page, page->index, page_off, len, snapc, snapc->seq);
- writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
- if (writeback_stat >
+ if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
end_page_writeback(page);
ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
ceph_put_snap_context(snapc); /* page's reference */
+
+ if (atomic_long_dec_return(&fsc->writeback_count) <
+ CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+ clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+
return err;
}
if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
ci->i_inline_version == CEPH_INLINE_NONE) {
- current->journal_info = vma->vm_file;
+ CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
+ ceph_add_rw_context(fi, &rw_ctx);
ret = filemap_fault(vmf);
- current->journal_info = NULL;
+ ceph_del_rw_context(fi, &rw_ctx);
} else
ret = -EAGAIN;
spin_unlock(&mdsc->caps_list_lock);
}
-void ceph_reserve_caps(struct ceph_mds_client *mdsc,
+/*
+ * Called under mdsc->mutex.
+ */
+int ceph_reserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx, int need)
{
- int i;
+ int i, j;
struct ceph_cap *cap;
int have;
int alloc = 0;
+ int max_caps;
+ bool trimmed = false;
+ struct ceph_mds_session *s;
LIST_HEAD(newcaps);
dout("reserve caps ctx=%p need=%d\n", ctx, need);
spin_unlock(&mdsc->caps_list_lock);
for (i = have; i < need; i++) {
+retry:
cap = kmem_cache_alloc(ceph_cap_cachep, GFP_NOFS);
- if (!cap)
- break;
+ if (!cap) {
+ if (!trimmed) {
+ for (j = 0; j < mdsc->max_sessions; j++) {
+ s = __ceph_lookup_mds_session(mdsc, j);
+ if (!s)
+ continue;
+ mutex_unlock(&mdsc->mutex);
+
+ mutex_lock(&s->s_mutex);
+ max_caps = s->s_nr_caps - (need - i);
+ ceph_trim_caps(mdsc, s, max_caps);
+ mutex_unlock(&s->s_mutex);
+
+ ceph_put_mds_session(s);
+ mutex_lock(&mdsc->mutex);
+ }
+ trimmed = true;
+ goto retry;
+ } else {
+ pr_warn("reserve caps ctx=%p ENOMEM "
+ "need=%d got=%d\n",
+ ctx, need, have + alloc);
+ goto out_nomem;
+ }
+ }
list_add(&cap->caps_item, &newcaps);
alloc++;
}
- /* we didn't manage to reserve as much as we needed */
- if (have + alloc != need)
- pr_warn("reserve caps ctx=%p ENOMEM need=%d got=%d\n",
- ctx, need, have + alloc);
+ BUG_ON(have + alloc != need);
spin_lock(&mdsc->caps_list_lock);
mdsc->caps_total_count += alloc;
dout("reserve caps ctx=%p %d = %d used + %d resv + %d avail\n",
ctx, mdsc->caps_total_count, mdsc->caps_use_count,
mdsc->caps_reserve_count, mdsc->caps_avail_count);
+ return 0;
+
+out_nomem:
+ while (!list_empty(&newcaps)) {
+ cap = list_first_entry(&newcaps,
+ struct ceph_cap, caps_item);
+ list_del(&cap->caps_item);
+ kmem_cache_free(ceph_cap_cachep, cap);
+ }
+
+ spin_lock(&mdsc->caps_list_lock);
+ mdsc->caps_avail_count += have;
+ mdsc->caps_reserve_count -= have;
+ BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
+ mdsc->caps_reserve_count +
+ mdsc->caps_avail_count);
+ spin_unlock(&mdsc->caps_list_lock);
+ return -ENOMEM;
}
int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
*/
if ((issued & CEPH_CAP_FILE_SHARED) != (had & CEPH_CAP_FILE_SHARED)) {
if (issued & CEPH_CAP_FILE_SHARED)
- ci->i_shared_gen++;
+ atomic_inc(&ci->i_shared_gen);
if (S_ISDIR(ci->vfs_inode.i_mode)) {
dout(" marking %p NOT complete\n", &ci->vfs_inode);
__ceph_dir_clear_complete(ci);
}
}
- if (!ci->i_snap_realm) {
+ if (!ci->i_snap_realm ||
+ ((flags & CEPH_CAP_FLAG_AUTH) &&
+ realmino != (u64)-1 && ci->i_snap_realm->ino != realmino)) {
/*
* add this inode to the appropriate snap realm
*/
struct ceph_snap_realm *realm = ceph_lookup_snap_realm(mdsc,
realmino);
if (realm) {
+ struct ceph_snap_realm *oldrealm = ci->i_snap_realm;
+ if (oldrealm) {
+ spin_lock(&oldrealm->inodes_with_caps_lock);
+ list_del_init(&ci->i_snap_realm_item);
+ spin_unlock(&oldrealm->inodes_with_caps_lock);
+ }
+
spin_lock(&realm->inodes_with_caps_lock);
ci->i_snap_realm = realm;
list_add(&ci->i_snap_realm_item,
&realm->inodes_with_caps);
spin_unlock(&realm->inodes_with_caps_lock);
+
+ if (oldrealm)
+ ceph_put_snap_realm(mdsc, oldrealm);
} else {
pr_err("ceph_add_cap: couldn't find snap realm %llx\n",
realmino);
/*
* called under i_ceph_lock
*/
+static int __ceph_is_single_caps(struct ceph_inode_info *ci)
+{
+ return rb_first(&ci->i_caps) == rb_last(&ci->i_caps);
+}
+
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
return !RB_EMPTY_ROOT(&ci->i_caps);
int mds = -1; /* keep track of how far we've gone through i_caps list
to avoid an infinite loop on retry */
struct rb_node *p;
- int delayed = 0, sent = 0, num;
- bool is_delayed = flags & CHECK_CAPS_NODELAY;
+ int delayed = 0, sent = 0;
+ bool no_delay = flags & CHECK_CAPS_NODELAY;
bool queue_invalidate = false;
- bool force_requeue = false;
bool tried_invalidate = false;
/* if we are unmounting, flush any unused caps immediately. */
if (mdsc->stopping)
- is_delayed = true;
+ no_delay = true;
spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
+ if (!(flags & CHECK_CAPS_AUTHONLY) ||
+ (ci->i_auth_cap && __ceph_is_single_caps(ci)))
+ __cap_delay_cancel(mdsc, ci);
+
goto retry_locked;
retry:
spin_lock(&ci->i_ceph_lock);
* have cached pages, but don't want them, then try to invalidate.
* If we fail, it's because pages are locked.... try again later.
*/
- if ((!is_delayed || mdsc->stopping) &&
+ if ((!no_delay || mdsc->stopping) &&
!S_ISDIR(inode->i_mode) && /* ignore readdir cache */
!(ci->i_wb_ref || ci->i_wrbuffer_ref) && /* no dirty pages... */
inode->i_data.nrpages && /* have cached pages */
!tried_invalidate) {
dout("check_caps trying to invalidate on %p\n", inode);
if (try_nonblocking_invalidate(inode) < 0) {
- if (revoking & (CEPH_CAP_FILE_CACHE|
- CEPH_CAP_FILE_LAZYIO)) {
- dout("check_caps queuing invalidate\n");
- queue_invalidate = true;
- ci->i_rdcache_revoking = ci->i_rdcache_gen;
- } else {
- dout("check_caps failed to invalidate pages\n");
- /* we failed to invalidate pages. check these
- caps again later. */
- force_requeue = true;
- __cap_set_timeouts(mdsc, ci);
- }
+ dout("check_caps queuing invalidate\n");
+ queue_invalidate = true;
+ ci->i_rdcache_revoking = ci->i_rdcache_gen;
}
tried_invalidate = true;
goto retry_locked;
}
- num = 0;
for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
cap = rb_entry(p, struct ceph_cap, ci_node);
- num++;
/* avoid looping forever */
if (mds >= cap->mds ||
cap->mds_wanted == want)
continue; /* nope, all good */
- if (is_delayed)
+ if (no_delay)
goto ack;
/* delay? */
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
- /*
- * Reschedule delayed caps release if we delayed anything,
- * otherwise cancel.
- */
- if (delayed && is_delayed)
- force_requeue = true; /* __send_cap delayed release; requeue */
- if (!delayed && !is_delayed)
- __cap_delay_cancel(mdsc, ci);
- else if (!is_delayed || force_requeue)
+ /* Reschedule delayed caps release if we delayed anything */
+ if (delayed)
__cap_delay_requeue(mdsc, ci);
spin_unlock(&ci->i_ceph_lock);
u64 flush_tid;
int err = 0;
int dirty;
- int wait = wbc->sync_mode == WB_SYNC_ALL;
+ int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync);
dout("write_inode %p wait=%d\n", inode, wait);
if (wait) {
*/
issued = cap->issued;
- WARN_ON(issued != cap->implemented);
+ if (issued != cap->implemented)
+ pr_err_ratelimited("handle_cap_export: issued != implemented: "
+ "ino (%llx.%llx) mds%d seq %d mseq %d "
+ "issued %s implemented %s\n",
+ ceph_vinop(inode), mds, cap->seq, cap->mseq,
+ ceph_cap_string(issued),
+ ceph_cap_string(cap->implemented));
+
tcap = __get_cap_for_mds(ci, target);
if (tcap) {
if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
(ocap->seq != le32_to_cpu(ph->seq) ||
ocap->mseq != le32_to_cpu(ph->mseq))) {
- pr_err("handle_cap_import: mismatched seq/mseq: "
- "ino (%llx.%llx) mds%d seq %d mseq %d "
- "importer mds%d has peer seq %d mseq %d\n",
- ceph_vinop(inode), peer, ocap->seq,
- ocap->mseq, mds, le32_to_cpu(ph->seq),
- le32_to_cpu(ph->mseq));
+ pr_err_ratelimited("handle_cap_import: "
+ "mismatched seq/mseq: ino (%llx.%llx) "
+ "mds%d seq %d mseq %d importer mds%d "
+ "has peer seq %d mseq %d\n",
+ ceph_vinop(inode), peer, ocap->seq,
+ ocap->mseq, mds, le32_to_cpu(ph->seq),
+ le32_to_cpu(ph->mseq));
}
__ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
}
cap = __get_cap_for_mds(ci, mds);
if (cap && __cap_is_valid(cap)) {
- if (force ||
- ((cap->issued & drop) &&
- (cap->issued & unless) == 0)) {
- if ((cap->issued & drop) &&
- (cap->issued & unless) == 0) {
+ unless &= cap->issued;
+ if (unless) {
+ if (unless & CEPH_CAP_AUTH_EXCL)
+ drop &= ~CEPH_CAP_AUTH_SHARED;
+ if (unless & CEPH_CAP_LINK_EXCL)
+ drop &= ~CEPH_CAP_LINK_SHARED;
+ if (unless & CEPH_CAP_XATTR_EXCL)
+ drop &= ~CEPH_CAP_XATTR_SHARED;
+ if (unless & CEPH_CAP_FILE_EXCL)
+ drop &= ~CEPH_CAP_FILE_SHARED;
+ }
+
+ if (force || (cap->issued & drop)) {
+ if (cap->issued & drop) {
int wanted = __ceph_caps_wanted(ci);
if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0)
wanted |= cap->mds_wanted;
*p += sizeof(*rel);
ret = 1;
} else {
- dout("encode_inode_release %p cap %p %s\n",
+ dout("encode_inode_release %p cap %p %s (noop)\n",
inode, cap, ceph_cap_string(cap->issued));
}
}
* the MDS if/when the directory is modified).
*/
static int __dcache_readdir(struct file *file, struct dir_context *ctx,
- u32 shared_gen)
+ int shared_gen)
{
struct ceph_file_info *fi = file->private_data;
struct dentry *parent = file->f_path.dentry;
u64 idx = 0;
int err = 0;
- dout("__dcache_readdir %p v%u at %llx\n", dir, shared_gen, ctx->pos);
+ dout("__dcache_readdir %p v%u at %llx\n", dir, (unsigned)shared_gen, ctx->pos);
/* search start position */
if (ctx->pos > 2) {
goto out;
}
- di = ceph_dentry(dentry);
spin_lock(&dentry->d_lock);
- if (di->lease_shared_gen == shared_gen &&
- d_really_is_positive(dentry) &&
- fpos_cmp(ctx->pos, di->offset) <= 0) {
+ di = ceph_dentry(dentry);
+ if (d_unhashed(dentry) ||
+ d_really_is_negative(dentry) ||
+ di->lease_shared_gen != shared_gen) {
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ err = -EAGAIN;
+ goto out;
+ }
+ if (fpos_cmp(ctx->pos, di->offset) <= 0) {
emit_dentry = true;
}
spin_unlock(&dentry->d_lock);
ceph_snap(inode) != CEPH_SNAPDIR &&
__ceph_dir_is_complete_ordered(ci) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
- u32 shared_gen = ci->i_shared_gen;
+ int shared_gen = atomic_read(&ci->i_shared_gen);
spin_unlock(&ci->i_ceph_lock);
err = __dcache_readdir(file, ctx, shared_gen);
if (err != -EAGAIN)
if (op == CEPH_MDS_OP_READDIR) {
req->r_direct_hash = ceph_frag_value(frag);
__set_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags);
+ req->r_inode_drop = CEPH_CAP_FILE_EXCL;
}
if (fi->last_name) {
req->r_path2 = kstrdup(fi->last_name, GFP_KERNEL);
spin_unlock(&ci->i_ceph_lock);
dout(" dir %p complete, -ENOENT\n", dir);
d_add(dentry, NULL);
- di->lease_shared_gen = ci->i_shared_gen;
+ di->lease_shared_gen = atomic_read(&ci->i_shared_gen);
return NULL;
}
spin_unlock(&ci->i_ceph_lock);
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_args.mknod.mode = cpu_to_le32(mode);
req->r_args.mknod.rdev = cpu_to_le32(rdev);
- req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
+ req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
- req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
+ req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
req->r_parent = dir;
set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
req->r_args.mkdir.mode = cpu_to_le32(mode);
- req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
+ req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
/* release LINK_SHARED on source inode (mds will lock it) */
- req->r_old_inode_drop = CEPH_CAP_LINK_SHARED;
+ req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL;
err = ceph_mdsc_do_request(mdsc, dir, req);
if (err) {
d_drop(dentry);
req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
/* release LINK_RDCACHE on source inode (mds will lock it) */
- req->r_old_inode_drop = CEPH_CAP_LINK_SHARED;
+ req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL;
if (d_really_is_positive(new_dentry))
req->r_inode_drop = drop_caps_for_unlink(d_inode(new_dentry));
err = ceph_mdsc_do_request(mdsc, old_dir, req);
* do_request, above). If there is no trace, we need
* to do it here.
*/
-
- /* d_move screws up sibling dentries' offsets */
- ceph_dir_clear_complete(old_dir);
- ceph_dir_clear_complete(new_dir);
-
d_move(old_dentry, new_dentry);
-
- /* ensure target dentry is invalidated, despite
- rehashing bug in vfs_rename_dir */
- ceph_invalidate_dentry_lease(new_dentry);
}
ceph_mdsc_put_request(req);
return err;
int valid = 0;
spin_lock(&ci->i_ceph_lock);
- if (ci->i_shared_gen == di->lease_shared_gen)
+ if (atomic_read(&ci->i_shared_gen) == di->lease_shared_gen)
valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
spin_unlock(&ci->i_ceph_lock);
dout("dir_lease_is_valid dir %p v%u dentry %p v%u = %d\n",
- dir, (unsigned)ci->i_shared_gen, dentry,
- (unsigned)di->lease_shared_gen, valid);
+ dir, (unsigned)atomic_read(&ci->i_shared_gen),
+ dentry, (unsigned)di->lease_shared_gen, valid);
return valid;
}
*/
static void ceph_d_prune(struct dentry *dentry)
{
- dout("ceph_d_prune %p\n", dentry);
+ struct ceph_inode_info *dir_ci;
+ struct ceph_dentry_info *di;
+
+ dout("ceph_d_prune %pd %p\n", dentry, dentry);
/* do we have a valid parent? */
if (IS_ROOT(dentry))
return;
- /* if we are not hashed, we don't affect dir's completeness */
- if (d_unhashed(dentry))
+ /* we hold d_lock, so d_parent is stable */
+ dir_ci = ceph_inode(d_inode(dentry->d_parent));
+ if (dir_ci->i_vino.snap == CEPH_SNAPDIR)
return;
- if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_SNAPDIR)
+ /* who calls d_delete() should also disable dcache readdir */
+ if (d_really_is_negative(dentry))
return;
- /*
- * we hold d_lock, so d_parent is stable, and d_fsdata is never
- * cleared until d_release
- */
- ceph_dir_clear_complete(d_inode(dentry->d_parent));
+ /* d_fsdata does not get cleared until d_release */
+ if (!d_unhashed(dentry)) {
+ __ceph_dir_clear_complete(dir_ci);
+ return;
+ }
+
+ /* Disable dcache readdir just in case that someone called d_drop()
+ * or d_invalidate(), but MDS didn't revoke CEPH_CAP_FILE_SHARED
+ * properly (dcache readdir is still enabled) */
+ di = ceph_dentry(dentry);
+ if (di->offset > 0 &&
+ di->lease_shared_gen == atomic_read(&dir_ci->i_shared_gen))
+ __ceph_dir_clear_ordered(dir_ci);
}
/*
return -ENOMEM;
}
cf->fmode = fmode;
+
+ spin_lock_init(&cf->rw_contexts_lock);
+ INIT_LIST_HEAD(&cf->rw_contexts);
+
cf->next_offset = 2;
cf->readdir_cache_idx = -1;
file->private_data = cf;
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
if (flags & O_CREAT) {
- req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
+ req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
ceph_mdsc_put_request(cf->last_readdir);
kfree(cf->last_name);
kfree(cf->dir_info);
+ WARN_ON(!list_empty(&cf->rw_contexts));
kmem_cache_free(ceph_file_cachep, cf);
/* wake up anyone waiting for caps on this inode */
retry_op = READ_INLINE;
}
} else {
+ CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
ceph_cap_string(got));
- current->journal_info = filp;
+ ceph_add_rw_context(fi, &rw_ctx);
ret = generic_file_read_iter(iocb, to);
- current->journal_info = NULL;
+ ceph_del_rw_context(fi, &rw_ctx);
}
dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
ci->i_wrbuffer_ref = 0;
ci->i_wrbuffer_ref_head = 0;
atomic_set(&ci->i_filelock_ref, 0);
- ci->i_shared_gen = 0;
+ atomic_set(&ci->i_shared_gen, 0);
ci->i_rdcache_gen = 0;
ci->i_rdcache_revoking = 0;
if (ceph_snap(dir) != CEPH_NOSNAP)
goto out_unlock;
- di->lease_shared_gen = ceph_inode(dir)->i_shared_gen;
+ di->lease_shared_gen = atomic_read(&ceph_inode(dir)->i_shared_gen);
if (duration == 0)
goto out_unlock;
BUG_ON(d_inode(dn));
+ if (S_ISDIR(in->i_mode)) {
+ /* If inode is directory, d_splice_alias() below will remove
+ * 'realdn' from its origin parent. We need to ensure that
+ * origin parent's readdir cache will not reference 'realdn'
+ */
+ realdn = d_find_any_alias(in);
+ if (realdn) {
+ struct ceph_dentry_info *di = ceph_dentry(realdn);
+ spin_lock(&realdn->d_lock);
+
+ realdn->d_op->d_prune(realdn);
+
+ di->time = jiffies;
+ di->lease_shared_gen = 0;
+ di->offset = 0;
+
+ spin_unlock(&realdn->d_lock);
+ dput(realdn);
+ }
+ }
+
/* dn must be unhashed */
if (!d_unhashed(dn))
d_drop(dn);
if (!rinfo->head->is_target) {
dout("fill_trace null dentry\n");
if (d_really_is_positive(dn)) {
- ceph_dir_clear_ordered(dir);
dout("d_delete %p\n", dn);
+ ceph_dir_clear_ordered(dir);
d_delete(dn);
} else if (have_lease) {
if (d_unhashed(dn))
dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
dn, d_inode(dn), ceph_vinop(d_inode(dn)),
ceph_vinop(in));
- ceph_dir_clear_ordered(dir);
d_invalidate(dn);
have_lease = false;
}
} else if (d_really_is_positive(dn) &&
(ceph_ino(d_inode(dn)) != tvino.ino ||
ceph_snap(d_inode(dn)) != tvino.snap)) {
+ struct ceph_dentry_info *di = ceph_dentry(dn);
dout(" dn %p points to wrong inode %p\n",
dn, d_inode(dn));
- __ceph_dir_clear_ordered(ci);
+
+ spin_lock(&dn->d_lock);
+ if (di->offset > 0 &&
+ di->lease_shared_gen ==
+ atomic_read(&ci->i_shared_gen)) {
+ __ceph_dir_clear_ordered(ci);
+ di->offset = 0;
+ }
+ spin_unlock(&dn->d_lock);
+
d_delete(dn);
dput(dn);
goto retry_lookup;
&req->r_caps_reservation);
if (ret < 0) {
pr_err("fill_inode badness on %p\n", in);
- if (d_really_is_positive(dn))
- __ceph_dir_clear_ordered(ci);
- else
+ if (d_really_is_negative(dn))
iput(in);
d_drop(dn);
err = ret;
ceph_encode_timespec(&req->r_args.setattr.atime,
&attr->ia_atime);
mask |= CEPH_SETATTR_ATIME;
- release |= CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_RD |
- CEPH_CAP_FILE_WR;
+ release |= CEPH_CAP_FILE_SHARED |
+ CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
}
}
if (ia_valid & ATTR_MTIME) {
ceph_encode_timespec(&req->r_args.setattr.mtime,
&attr->ia_mtime);
mask |= CEPH_SETATTR_MTIME;
- release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD |
- CEPH_CAP_FILE_WR;
+ release |= CEPH_CAP_FILE_SHARED |
+ CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
}
}
if (ia_valid & ATTR_SIZE) {
req->r_args.setattr.old_size =
cpu_to_le64(inode->i_size);
mask |= CEPH_SETATTR_SIZE;
- release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD |
- CEPH_CAP_FILE_WR;
+ release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL |
+ CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR;
}
}
struct ceph_mds_request *req,
struct inode *dir)
{
+ int ret = 0;
+
req->r_tid = ++mdsc->last_tid;
- if (req->r_num_caps)
- ceph_reserve_caps(mdsc, &req->r_caps_reservation,
- req->r_num_caps);
+ if (req->r_num_caps) {
+ ret = ceph_reserve_caps(mdsc, &req->r_caps_reservation,
+ req->r_num_caps);
+ if (ret < 0) {
+ pr_err("__register_request %p "
+ "failed to reserve caps: %d\n", req, ret);
+ /* set req->r_err to fail early from __do_request */
+ req->r_err = ret;
+ return;
+ }
+ }
dout("__register_request %p tid %lld\n", req, req->r_tid);
ceph_mdsc_get_request(req);
insert_request(&mdsc->request_tree, req);
/*
* Trim session cap count down to some max number.
*/
-static int trim_caps(struct ceph_mds_client *mdsc,
- struct ceph_mds_session *session,
- int max_caps)
+int ceph_trim_caps(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ int max_caps)
{
int trim_caps = session->s_nr_caps - max_caps;
*/
void ceph_invalidate_dir_request(struct ceph_mds_request *req)
{
- struct inode *inode = req->r_parent;
+ struct inode *dir = req->r_parent;
+ struct inode *old_dir = req->r_old_dentry_dir;
- dout("invalidate_dir_request %p (complete, lease(s))\n", inode);
+ dout("invalidate_dir_request %p %p (complete, lease(s))\n", dir, old_dir);
- ceph_dir_clear_complete(inode);
+ ceph_dir_clear_complete(dir);
+ if (old_dir)
+ ceph_dir_clear_complete(old_dir);
if (req->r_dentry)
ceph_invalidate_dentry_lease(req->r_dentry);
if (req->r_old_dentry)
break;
case CEPH_SESSION_RECALL_STATE:
- trim_caps(mdsc, session, le32_to_cpu(h->max_caps));
+ ceph_trim_caps(mdsc, session, le32_to_cpu(h->max_caps));
break;
case CEPH_SESSION_FLUSHMSG:
extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session);
+extern int ceph_trim_caps(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ int max_caps);
#endif
/*
* Move the inode to the new realm
*/
- spin_lock(&realm->inodes_with_caps_lock);
+ oldrealm = ci->i_snap_realm;
+ spin_lock(&oldrealm->inodes_with_caps_lock);
list_del_init(&ci->i_snap_realm_item);
+ spin_unlock(&oldrealm->inodes_with_caps_lock);
+
+ spin_lock(&realm->inodes_with_caps_lock);
list_add(&ci->i_snap_realm_item,
&realm->inodes_with_caps);
- oldrealm = ci->i_snap_realm;
ci->i_snap_realm = realm;
spin_unlock(&realm->inodes_with_caps_lock);
+
spin_unlock(&ci->i_ceph_lock);
ceph_get_snap_realm(mdsc, realm);
*/
struct ceph_dentry_info {
struct ceph_mds_session *lease_session;
- u32 lease_gen, lease_shared_gen;
+ int lease_shared_gen;
+ u32 lease_gen;
u32 lease_seq;
unsigned long lease_renew_after, lease_renew_from;
struct list_head lru;
int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref;
int i_wrbuffer_ref, i_wrbuffer_ref_head;
atomic_t i_filelock_ref;
- u32 i_shared_gen; /* increment each time we get FILE_SHARED */
+ atomic_t i_shared_gen; /* increment each time we get FILE_SHARED */
u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */
u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
extern void ceph_caps_init(struct ceph_mds_client *mdsc);
extern void ceph_caps_finalize(struct ceph_mds_client *mdsc);
extern void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta);
-extern void ceph_reserve_caps(struct ceph_mds_client *mdsc,
+extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx, int need);
extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx);
short fmode; /* initialized on open */
short flags; /* CEPH_F_* */
+ spinlock_t rw_contexts_lock;
+ struct list_head rw_contexts;
+
/* readdir: position within the dir */
u32 frag;
struct ceph_mds_request *last_readdir;
int dir_info_len;
};
+struct ceph_rw_context {
+ struct list_head list;
+ struct task_struct *thread;
+ int caps;
+};
+
+#define CEPH_DEFINE_RW_CONTEXT(_name, _caps) \
+ struct ceph_rw_context _name = { \
+ .thread = current, \
+ .caps = _caps, \
+ }
+
+static inline void ceph_add_rw_context(struct ceph_file_info *cf,
+ struct ceph_rw_context *ctx)
+{
+ spin_lock(&cf->rw_contexts_lock);
+ list_add(&ctx->list, &cf->rw_contexts);
+ spin_unlock(&cf->rw_contexts_lock);
+}
+
+static inline void ceph_del_rw_context(struct ceph_file_info *cf,
+ struct ceph_rw_context *ctx)
+{
+ spin_lock(&cf->rw_contexts_lock);
+ list_del(&ctx->list);
+ spin_unlock(&cf->rw_contexts_lock);
+}
+
+static inline struct ceph_rw_context*
+ceph_find_rw_context(struct ceph_file_info *cf)
+{
+ struct ceph_rw_context *ctx, *found = NULL;
+ spin_lock(&cf->rw_contexts_lock);
+ list_for_each_entry(ctx, &cf->rw_contexts, list) {
+ if (ctx->thread == current) {
+ found = ctx;
+ break;
+ }
+ }
+ spin_unlock(&cf->rw_contexts_lock);
+ return found;
+}
+
struct ceph_readdir_cache_control {
struct page *page;
struct dentry **dentries;
seq_puts(m, " type: CDROM ");
else
seq_printf(m, " type: %d ", dev_type);
+ if (tcon->seal)
+ seq_printf(m, " Encrypted");
+ if (tcon->unix_ext)
+ seq_printf(m, " POSIX Extensions");
if (tcon->ses->server->ops->dump_share_caps)
tcon->ses->server->ops->dump_share_caps(m, tcon);
atomic_read(&server->smbd_conn->mr_used_count));
skip_rdma:
#endif
- seq_printf(m, "\nNumber of credits: %d", server->credits);
+ seq_printf(m, "\nNumber of credits: %d Dialect 0x%x",
+ server->credits, server->dialect);
+ if (server->sign)
+ seq_printf(m, " signed");
i++;
list_for_each(tmp2, &server->smb_ses_list) {
ses = list_entry(tmp2, struct cifs_ses,
pSMB->InformationLevel =
cpu_to_le16(SMB_SET_FILE_EA);
- parm_data =
- (struct fealist *) (((char *) &pSMB->hdr.Protocol) +
- offset);
+ parm_data = (void *)pSMB + offsetof(struct smb_hdr, Protocol) + offset;
pSMB->ParameterOffset = cpu_to_le16(param_offset);
pSMB->DataOffset = cpu_to_le16(offset);
pSMB->SetupCount = 1;
__u8 PathBuffer[0];
} __packed;
+/* SMB 3.1.1 and later dialects. See MS-SMB2 section 2.2.2.1 */
+struct smb2_error_context_rsp {
+ __le32 ErrorDataLength;
+ __le32 ErrorId;
+ __u8 ErrorContextData; /* ErrorDataLength long array */
+} __packed;
+
+/* Defines for Type field below (see MS-SMB2 2.2.2.2.2.1) */
+#define MOVE_DST_IPADDR_V4 cpu_to_le32(0x00000001)
+#define MOVE_DST_IPADDR_V6 cpu_to_le32(0x00000002)
+
+struct move_dst_ipaddr {
+ __le32 Type;
+ __u32 Reserved;
+ __u8 address[16]; /* IPv4 followed by 12 bytes rsvd or IPv6 address */
+} __packed;
+
+struct share_redirect_error_context_rsp {
+ __le32 StructureSize;
+ __le32 NotificationType;
+ __le32 ResourceNameOffset;
+ __le32 ResourceNameLength;
+ __le16 Flags;
+ __le16 TargetType;
+ __le32 IPAddrCount;
+ struct move_dst_ipaddr IpAddrMoveList[0];
+ /* __u8 ResourceName[] */ /* Name of share as counted Unicode string */
+} __packed;
+
#define SMB2_CLIENT_GUID_SIZE 16
struct smb2_negotiate_req {
} __packed;
/* Flags/Reserved for SMB3.1.1 */
-#define SMB2_SHAREFLAG_CLUSTER_RECONNECT 0x0001
+#define SMB2_TREE_CONNECT_FLAG_CLUSTER_RECONNECT cpu_to_le16(0x0001)
+#define SMB2_TREE_CONNECT_FLAG_REDIRECT_TO_OWNER cpu_to_le16(0x0002)
+#define SMB2_TREE_CONNECT_FLAG_EXTENSION_PRESENT cpu_to_le16(0x0004)
struct smb2_tree_connect_req {
struct smb2_sync_hdr sync_hdr;
__u8 Buffer[1]; /* variable length */
} __packed;
+/* See MS-SMB2 section 2.2.9.2 */
+/* Context Types */
+#define SMB2_RESERVED_TREE_CONNECT_CONTEXT_ID 0x0000
+#define SMB2_REMOTED_IDENTITY_TREE_CONNECT_CONTEXT_ID cpu_to_le16(0x0001)
+
+struct tree_connect_contexts {
+ __le16 ContextType;
+ __le16 DataLength;
+ __le32 Reserved;
+ __u8 Data[0];
+} __packed;
+
+/* Remoted identity tree connect context structures - see MS-SMB2 2.2.9.2.1 */
+struct smb3_blob_data {
+ __le16 BlobSize;
+ __u8 BlobData[0];
+} __packed;
+
+/* Valid values for Attr */
+#define SE_GROUP_MANDATORY 0x00000001
+#define SE_GROUP_ENABLED_BY_DEFAULT 0x00000002
+#define SE_GROUP_ENABLED 0x00000004
+#define SE_GROUP_OWNER 0x00000008
+#define SE_GROUP_USE_FOR_DENY_ONLY 0x00000010
+#define SE_GROUP_INTEGRITY 0x00000020
+#define SE_GROUP_INTEGRITY_ENABLED 0x00000040
+#define SE_GROUP_RESOURCE 0x20000000
+#define SE_GROUP_LOGON_ID 0xC0000000
+
+/* struct sid_attr_data is SidData array in BlobData format then le32 Attr */
+
+struct sid_array_data {
+ __le16 SidAttrCount;
+ /* SidAttrList - array of sid_attr_data structs */
+} __packed;
+
+struct luid_attr_data {
+
+} __packed;
+
+/*
+ * struct privilege_data is the same as BLOB_DATA - see MS-SMB2 2.2.9.2.1.5
+ * but with size of LUID_ATTR_DATA struct and BlobData set to LUID_ATTR DATA
+ */
+
+struct privilege_array_data {
+ __le16 PrivilegeCount;
+ /* array of privilege_data structs */
+} __packed;
+
+struct remoted_identity_tcon_context {
+ __le16 TicketType; /* must be 0x0001 */
+ __le16 TicketSize; /* total size of this struct */
+ __le16 User; /* offset to SID_ATTR_DATA struct with user info */
+ __le16 UserName; /* offset to null terminated Unicode username string */
+ __le16 Domain; /* offset to null terminated Unicode domain name */
+ __le16 Groups; /* offset to SID_ARRAY_DATA struct with group info */
+ __le16 RestrictedGroups; /* similar to above */
+ __le16 Privileges; /* offset to PRIVILEGE_ARRAY_DATA struct */
+ __le16 PrimaryGroup; /* offset to SID_ARRAY_DATA struct */
+ __le16 Owner; /* offset to BLOB_DATA struct */
+ __le16 DefaultDacl; /* offset to BLOB_DATA struct */
+ __le16 DeviceGroups; /* offset to SID_ARRAY_DATA struct */
+ __le16 UserClaims; /* offset to BLOB_DATA struct */
+ __le16 DeviceClaims; /* offset to BLOB_DATA struct */
+ __u8 TicketInfo[0]; /* variable length buf - remoted identity data */
+} __packed;
+
+struct smb2_tree_connect_req_extension {
+ __le32 TreeConnectContextOffset;
+ __le16 TreeConnectContextCount;
+ __u8 Reserved[10];
+ __u8 PathName[0]; /* variable sized array */
+ /* followed by array of TreeConnectContexts */
+} __packed;
+
struct smb2_tree_connect_rsp {
struct smb2_hdr hdr;
__le16 StructureSize; /* Must be 16 */
#define SHI1005_FLAGS_ENABLE_HASH_V1 0x00002000
#define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000
#define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000
-#define SHI1005_FLAGS_ALL 0x0000FF33
+#define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */
+#define SHI1005_FLAGS_ALL 0x0004FF33
/* Possible share capabilities */
#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */
#define SMB2_SHARE_CAP_SCALEOUT cpu_to_le32(0x00000020) /* 3.0 */
#define SMB2_SHARE_CAP_CLUSTER cpu_to_le32(0x00000040) /* 3.0 */
#define SMB2_SHARE_CAP_ASYMMETRIC cpu_to_le32(0x00000080) /* 3.02 */
+#define SMB2_SHARE_CAP_REDIRECT_TO_OWNER cpu_to_le32(0x00000100) /* 3.1.1 */
struct smb2_tree_disconnect_req {
struct smb2_sync_hdr sync_hdr;
#define SMB2_LEASE_WRITE_CACHING cpu_to_le32(0x04)
#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET cpu_to_le32(0x00000004)
#define SMB2_LEASE_KEY_SIZE 16
spin_unlock_irqrestore(
&info->reassembly_queue_lock, flags);
put_receive_buffer(info, response);
- }
+ } else
+ spin_unlock_irqrestore(&info->reassembly_queue_lock, flags);
} while (response);
- spin_unlock_irqrestore(&info->reassembly_queue_lock, flags);
+
info->reassembly_data_length = 0;
log_rdma_event(INFO, "free receive buffers\n");
* No need to lock if we are not at the
* end of the queue
*/
- if (!queue_length)
+ if (queue_length)
+ list_del(&response->list);
+ else {
spin_lock_irq(
&info->reassembly_queue_lock);
- list_del(&response->list);
- queue_removed++;
- if (!queue_length)
+ list_del(&response->list);
spin_unlock_irq(
&info->reassembly_queue_lock);
-
+ }
+ queue_removed++;
info->count_reassembly_queue--;
info->count_dequeue_reassembly_queue++;
put_receive_buffer(info, response);
#include <linux/device.h>
#include <linux/pid_namespace.h>
#include <asm/io.h>
-#include <asm/poll.h>
+#include <linux/poll.h>
#include <linux/uaccess.h>
#include <linux/coda.h>
static __poll_t coda_psdev_poll(struct file *file, poll_table * wait)
{
struct venus_comm *vcp = (struct venus_comm *) file->private_data;
- __poll_t mask = POLLOUT | POLLWRNORM;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM;
poll_wait(file, &vcp->vc_waitq, wait);
mutex_lock(&vcp->vc_mutex);
if (!list_empty(&vcp->vc_pending))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
mutex_unlock(&vcp->vc_mutex);
return mask;
config CRAMFS_MTD
bool "Support CramFs image directly mapped in physical memory"
- depends on CRAMFS && MTD
- depends on CRAMFS=m || MTD=y
+ depends on CRAMFS && CRAMFS <= MTD
default y if !CRAMFS_BLOCKDEV
help
This option allows the CramFs driver to load data directly from
#include <linux/slab.h>
#include <linux/atomic.h>
#include <linux/device.h>
-#include <asm/poll.h>
+#include <linux/poll.h>
#include "internal.h"
const struct file_operations *real_fops;
if (debugfs_file_get(dentry))
- return POLLHUP;
+ return EPOLLHUP;
real_fops = debugfs_real_fops(filp);
r = real_fops->poll(filp, wait);
spin_lock(&ops_lock);
if (!list_empty(&send_list))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
spin_unlock(&ops_lock);
return mask;
spin_lock(&proc->asts_spin);
if (!list_empty(&proc->asts)) {
spin_unlock(&proc->asts_spin);
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
spin_unlock(&proc->asts_spin);
return 0;
poll_wait(file, &daemon->wait, pt);
mutex_lock(&daemon->mux);
if (!list_empty(&daemon->msg_ctx_out_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
out_unlock_daemon:
daemon->flags &= ~ECRYPTFS_DAEMON_IN_POLL;
mutex_unlock(&daemon->mux);
*
* This function is supposed to be called by the kernel in paths that do not
* allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
- * value, and we signal this as overflow condition by returning a POLLERR
+ * value, and we signal this as overflow condition by returning a EPOLLERR
* to poll(2).
*
* Returns the amount by which the counter was incremented. This will be less
n = ULLONG_MAX - ctx->count;
ctx->count += n;
if (waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, POLLIN);
+ wake_up_locked_poll(&ctx->wqh, EPOLLIN);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return n;
{
struct eventfd_ctx *ctx = file->private_data;
- wake_up_poll(&ctx->wqh, POLLHUP);
+ wake_up_poll(&ctx->wqh, EPOLLHUP);
eventfd_ctx_put(ctx);
return 0;
}
count = READ_ONCE(ctx->count);
if (count > 0)
- events |= POLLIN;
+ events |= EPOLLIN;
if (count == ULLONG_MAX)
- events |= POLLERR;
+ events |= EPOLLERR;
if (ULLONG_MAX - 1 > count)
- events |= POLLOUT;
+ events |= EPOLLOUT;
return events;
}
eventfd_ctx_do_read(ctx, cnt);
__remove_wait_queue(&ctx->wqh, wait);
if (*cnt != 0 && waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, POLLOUT);
+ wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return *cnt != 0 ? 0 : -EAGAIN;
if (likely(res > 0)) {
eventfd_ctx_do_read(ctx, &ucnt);
if (waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, POLLOUT);
+ wake_up_locked_poll(&ctx->wqh, EPOLLOUT);
}
spin_unlock_irq(&ctx->wqh.lock);
if (likely(res > 0)) {
ctx->count += ucnt;
if (waitqueue_active(&ctx->wqh))
- wake_up_locked_poll(&ctx->wqh, POLLIN);
+ wake_up_locked_poll(&ctx->wqh, EPOLLIN);
}
spin_unlock_irq(&ctx->wqh.lock);
/* Epoll private bits inside the event mask */
#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
-#define EPOLLINOUT_BITS (POLLIN | POLLOUT)
+#define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT)
-#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | POLLERR | POLLHUP | \
+#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \
EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)
/* Maximum number of nesting allowed inside epoll sets */
struct ep_send_events_data {
int maxevents;
struct epoll_event __user *events;
+ int res;
};
/*
wait_queue_head_t *wqueue = (wait_queue_head_t *)cookie;
spin_lock_irqsave_nested(&wqueue->lock, flags, call_nests + 1);
- wake_up_locked_poll(wqueue, POLLIN);
+ wake_up_locked_poll(wqueue, EPOLLIN);
spin_unlock_irqrestore(&wqueue->lock, flags);
return 0;
static void ep_poll_safewake(wait_queue_head_t *wq)
{
- wake_up_poll(wq, POLLIN);
+ wake_up_poll(wq, EPOLLIN);
}
#endif
*
* Returns: The same integer error code returned by the @sproc callback.
*/
-static int ep_scan_ready_list(struct eventpoll *ep,
- int (*sproc)(struct eventpoll *,
+static __poll_t ep_scan_ready_list(struct eventpoll *ep,
+ __poll_t (*sproc)(struct eventpoll *,
struct list_head *, void *),
void *priv, int depth, bool ep_locked)
{
- int error, pwake = 0;
+ __poll_t res;
+ int pwake = 0;
unsigned long flags;
struct epitem *epi, *nepi;
LIST_HEAD(txlist);
/*
* Now call the callback function.
*/
- error = (*sproc)(ep, &txlist, priv);
+ res = (*sproc)(ep, &txlist, priv);
spin_lock_irqsave(&ep->lock, flags);
/*
if (pwake)
ep_poll_safewake(&ep->poll_wait);
- return error;
+ return res;
}
static void epi_rcu_free(struct rcu_head *head)
return 0;
}
-static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
+static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv);
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
poll_table *pt);
* the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
* is correctly annotated.
*/
-static unsigned int ep_item_poll(const struct epitem *epi, poll_table *pt,
+static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
int depth)
{
struct eventpoll *ep;
locked) & epi->event.events;
}
-static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
+static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
{
struct epitem *epi, *tmp;
list_for_each_entry_safe(epi, tmp, head, rdllink) {
if (ep_item_poll(epi, &pt, depth)) {
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
} else {
/*
* Item has been dropped into the ready list by the poll
if ((epi->event.events & EPOLLEXCLUSIVE) &&
!(pollflags & POLLFREE)) {
switch (pollflags & EPOLLINOUT_BITS) {
- case POLLIN:
- if (epi->event.events & POLLIN)
+ case EPOLLIN:
+ if (epi->event.events & EPOLLIN)
ewake = 1;
break;
- case POLLOUT:
- if (epi->event.events & POLLOUT)
+ case EPOLLOUT:
+ if (epi->event.events & EPOLLOUT)
ewake = 1;
break;
case 0:
static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
struct file *tfile, int fd, int full_check)
{
- int error, revents, pwake = 0;
+ int error, pwake = 0;
+ __poll_t revents;
unsigned long flags;
long user_watches;
struct epitem *epi;
return 0;
}
-static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
+static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
{
struct ep_send_events_data *esed = priv;
- int eventcnt;
- unsigned int revents;
+ __poll_t revents;
struct epitem *epi;
struct epoll_event __user *uevent;
struct wakeup_source *ws;
* Items cannot vanish during the loop because ep_scan_ready_list() is
* holding "mtx" during this call.
*/
- for (eventcnt = 0, uevent = esed->events;
- !list_empty(head) && eventcnt < esed->maxevents;) {
+ for (esed->res = 0, uevent = esed->events;
+ !list_empty(head) && esed->res < esed->maxevents;) {
epi = list_first_entry(head, struct epitem, rdllink);
/*
__put_user(epi->event.data, &uevent->data)) {
list_add(&epi->rdllink, head);
ep_pm_stay_awake(epi);
- return eventcnt ? eventcnt : -EFAULT;
+ if (!esed->res)
+ esed->res = -EFAULT;
+ return 0;
}
- eventcnt++;
+ esed->res++;
uevent++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
}
}
- return eventcnt;
+ return 0;
}
static int ep_send_events(struct eventpoll *ep,
esed.maxevents = maxevents;
esed.events = events;
- return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false);
+ ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false);
+ return esed.res;
}
static inline struct timespec64 ep_set_mstimeout(long ms)
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
- epds.events |= POLLERR | POLLHUP;
+ epds.events |= EPOLLERR | EPOLLHUP;
error = ep_insert(ep, &epds, tf.file, fd, full_check);
} else
error = -EEXIST;
case EPOLL_CTL_MOD:
if (epi) {
if (!(epi->event.events & EPOLLEXCLUSIVE)) {
- epds.events |= POLLERR | POLLHUP;
+ epds.events |= EPOLLERR | EPOLLHUP;
error = ep_modify(ep, epi, &epds);
}
} else
#include <linux/shmem_fs.h>
#include <linux/compat.h>
-#include <asm/poll.h>
+#include <linux/poll.h>
#include <asm/siginfo.h>
#include <linux/uaccess.h>
/* Table to convert sigio signal codes into poll band bitmaps */
static const __poll_t band_table[NSIGPOLL] = {
- POLLIN | POLLRDNORM, /* POLL_IN */
- POLLOUT | POLLWRNORM | POLLWRBAND, /* POLL_OUT */
- POLLIN | POLLRDNORM | POLLMSG, /* POLL_MSG */
- POLLERR, /* POLL_ERR */
- POLLPRI | POLLRDBAND, /* POLL_PRI */
- POLLHUP | POLLERR /* POLL_HUP */
+ EPOLLIN | EPOLLRDNORM, /* POLL_IN */
+ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */
+ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */
+ EPOLLERR, /* POLL_ERR */
+ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */
+ EPOLLHUP | EPOLLERR /* POLL_HUP */
};
static inline int sigio_perm(struct task_struct *p,
static __poll_t fuse_dev_poll(struct file *file, poll_table *wait)
{
- __poll_t mask = POLLOUT | POLLWRNORM;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM;
struct fuse_iqueue *fiq;
struct fuse_dev *fud = fuse_get_dev(file);
if (!fud)
- return POLLERR;
+ return EPOLLERR;
fiq = &fud->fc->iq;
poll_wait(file, &fiq->waitq, wait);
spin_lock(&fiq->waitq.lock);
if (!fiq->connected)
- mask = POLLERR;
+ mask = EPOLLERR;
else if (request_pending(fiq))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
spin_unlock(&fiq->waitq.lock);
return mask;
fc->no_poll = 1;
return DEFAULT_POLLMASK;
}
- return POLLERR;
+ return EPOLLERR;
}
EXPORT_SYMBOL_GPL(fuse_file_poll);
{
struct kernfs_open_file *of = kernfs_of(file);
const struct kernfs_ops *ops;
- size_t len;
+ ssize_t len;
char *buf;
if (of->atomic_write_len) {
* the content and then you use 'poll' or 'select' to wait for
* the content to change. When the content changes (assuming the
* manager for the kobject supports notification), poll will
- * return POLLERR|POLLPRI, and select will return the fd whether
+ * return EPOLLERR|EPOLLPRI, and select will return the fd whether
* it is waiting for read, write, or exceptions.
* Once poll/select indicates that the value has changed, you
* need to close and re-open the file, or seek to 0 and read again.
return DEFAULT_POLLMASK;
trigger:
- return DEFAULT_POLLMASK|POLLERR|POLLPRI;
+ return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
}
static void kernfs_notify_workfn(struct work_struct *work)
EXPORT_SYMBOL(__break_lease);
/**
- * lease_get_mtime - get the last modified time of an inode
+ * lease_get_mtime - update modified time of an inode with exclusive lease
* @inode: the inode
- * @time: pointer to a timespec which will contain the last modified time
+ * @time: pointer to a timespec which contains the last modified time
*
* This is to force NFS clients to flush their caches for files with
* exclusive leases. The justification is that if someone has an
if (has_lease)
*time = current_time(inode);
- else
- *time = inode->i_mtime;
}
EXPORT_SYMBOL(lease_get_mtime);
return encode_post_op_attr(rqstp, p, fhp);
}
+/*
+ * Fill in the pre_op attr for the wcc data
+ */
+void fill_pre_wcc(struct svc_fh *fhp)
+{
+ struct inode *inode;
+ struct kstat stat;
+ __be32 err;
+
+ if (fhp->fh_pre_saved)
+ return;
+
+ inode = d_inode(fhp->fh_dentry);
+ err = fh_getattr(fhp, &stat);
+ if (err) {
+ /* Grab the times from inode anyway */
+ stat.mtime = inode->i_mtime;
+ stat.ctime = inode->i_ctime;
+ stat.size = inode->i_size;
+ }
+
+ fhp->fh_pre_mtime = stat.mtime;
+ fhp->fh_pre_ctime = stat.ctime;
+ fhp->fh_pre_size = stat.size;
+ fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode);
+ fhp->fh_pre_saved = true;
+}
+
/*
* Fill in the post_op attr for the wcc data
*/
printk("nfsd: inode locked twice during operation.\n");
err = fh_getattr(fhp, &fhp->fh_post_attr);
- fhp->fh_post_change = nfsd4_change_attribute(d_inode(fhp->fh_dentry));
+ fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr,
+ d_inode(fhp->fh_dentry));
if (err) {
fhp->fh_post_saved = false;
/* Grab the ctime anyway - set_change_info might use it */
const struct nfsd4_layout_ops *ops;
struct nfs4_layout_stateid *ls;
__be32 nfserr;
- int accmode;
+ int accmode = NFSD_MAY_READ_IF_EXEC;
switch (lgp->lg_seg.iomode) {
case IOMODE_READ:
- accmode = NFSD_MAY_READ;
+ accmode |= NFSD_MAY_READ;
break;
case IOMODE_RW:
- accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+ accmode |= NFSD_MAY_READ | NFSD_MAY_WRITE;
break;
default:
dprintk("%s: invalid iomode %d\n",
status = nfserr_minor_vers_mismatch;
if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0)
goto out;
+ status = nfserr_resource;
+ if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
+ goto out;
status = nfs41_check_op_ordering(args);
if (status) {
switch (s->sc_type) {
default:
break;
+ case 0:
case NFS4_CLOSED_STID:
case NFS4_CLOSED_DELEG_STID:
ret = nfserr_bad_stateid;
lockowner(stp->st_stateowner)))
goto out;
- stp->st_stid.sc_type = NFS4_CLOSED_STID;
release_lock_stateid(stp);
ret = nfs_ok;
* If this is a new, never-before-used stateid, and we are
* returning an error, then just go ahead and release it.
*/
- if (status && new) {
- lock_stp->st_stid.sc_type = NFS4_CLOSED_STID;
+ if (status && new)
release_lock_stateid(lock_stp);
- }
mutex_unlock(&lock_stp->st_mutex);
}
label->len = 0;
-#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
- if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
+ if (IS_ENABLED(CONFIG_NFSD_V4_SECURITY_LABEL) &&
+ bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
READ_BUF(4);
len += 4;
dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */
if (!label->data)
return nfserr_jukebox;
}
-#endif
if (bmval[2] & FATTR4_WORD2_MODE_UMASK) {
if (!umask)
goto xdr_error;
if (argp->taglen > NFSD4_MAX_TAGLEN)
goto xdr_error;
- if (argp->opcnt > 100)
- goto xdr_error;
+ /*
+ * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS
+ * here, so we return success at the xdr level so that
+ * nfsd4_proc can handle this is an NFS-level error.
+ */
+ if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND)
+ return 0;
if (argp->opcnt > ARRAY_SIZE(argp->iops)) {
argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL);
*p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time));
*p++ = 0;
} else if (IS_I_VERSION(inode)) {
- p = xdr_encode_hyper(p, nfsd4_change_attribute(inode));
+ p = xdr_encode_hyper(p, nfsd4_change_attribute(stat, inode));
} else {
*p++ = cpu_to_be32(stat->ctime.tv_sec);
*p++ = cpu_to_be32(stat->ctime.tv_nsec);
* By using both ctime and the i_version counter we guarantee that as
* long as time doesn't go backwards we never reuse an old value.
*/
-static inline u64 nfsd4_change_attribute(struct inode *inode)
+static inline u64 nfsd4_change_attribute(struct kstat *stat,
+ struct inode *inode)
{
u64 chattr;
- chattr = inode->i_ctime.tv_sec;
+ chattr = stat->ctime.tv_sec;
chattr <<= 30;
- chattr += inode->i_ctime.tv_nsec;
+ chattr += stat->ctime.tv_nsec;
chattr += inode_query_iversion(inode);
return chattr;
}
-/*
- * Fill in the pre_op attr for the wcc data
- */
-static inline void
-fill_pre_wcc(struct svc_fh *fhp)
-{
- struct inode *inode;
-
- inode = d_inode(fhp->fh_dentry);
- if (!fhp->fh_pre_saved) {
- fhp->fh_pre_mtime = inode->i_mtime;
- fhp->fh_pre_ctime = inode->i_ctime;
- fhp->fh_pre_size = inode->i_size;
- fhp->fh_pre_change = nfsd4_change_attribute(inode);
- fhp->fh_pre_saved = true;
- }
-}
-
-extern void fill_post_wcc(struct svc_fh *);
+extern void fill_pre_wcc(struct svc_fh *fhp);
+extern void fill_post_wcc(struct svc_fh *fhp);
#else
#define fh_clear_wcc(ignored)
#define fill_pre_wcc(ignored)
*p++ = htonl((u32) stat->ino);
*p++ = htonl((u32) stat->atime.tv_sec);
*p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
+ time = stat->mtime;
lease_get_mtime(d_inode(dentry), &time);
*p++ = htonl((u32) time.tv_sec);
*p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0);
poll_wait(file, &group->notification_waitq, wait);
spin_lock(&group->notification_lock);
if (!fsnotify_notify_queue_is_empty(group))
- ret = POLLIN | POLLRDNORM;
+ ret = EPOLLIN | EPOLLRDNORM;
spin_unlock(&group->notification_lock);
return ret;
poll_wait(file, &group->notification_waitq, wait);
spin_lock(&group->notification_lock);
if (!fsnotify_notify_queue_is_empty(group))
- ret = POLLIN | POLLRDNORM;
+ ret = EPOLLIN | EPOLLRDNORM;
spin_unlock(&group->notification_lock);
return ret;
* Over time, dlmfs has added some features that were not part of the
* initial ABI. Unfortunately, some of these features are not detectable
* via standard usage. For example, Linux's default poll always returns
- * POLLIN, so there is no way for a caller of poll(2) to know when dlmfs
+ * EPOLLIN, so there is no way for a caller of poll(2) to know when dlmfs
* added poll support. Instead, we provide this list of new capabilities.
*
* Capabilities is a read-only attribute. We do it as a module parameter
* interaction.
*
* Capabilities:
- * - bast : POLLIN against the file descriptor of a held lock
+ * - bast : EPOLLIN against the file descriptor of a held lock
* signifies a bast fired on the lock.
*/
#define DLMFS_CAPABILITIES "bast stackglue"
spin_lock(&ip->ip_lockres.l_lock);
if (ip->ip_lockres.l_flags & USER_LOCK_BLOCKED)
- event = POLLIN | POLLRDNORM;
+ event = EPOLLIN | EPOLLRDNORM;
spin_unlock(&ip->ip_lockres.l_lock);
return event;
new_op->upcall.req.lookup.parent_refn = parent->refn;
strncpy(new_op->upcall.req.lookup.d_name,
dentry->d_name.name,
- ORANGEFS_NAME_MAX);
+ ORANGEFS_NAME_MAX - 1);
gossip_debug(GOSSIP_DCACHE_DEBUG,
"%s:%s:%d interrupt flag [%d]\n",
return 0;
/* We do not need to continue with negative dentries. */
- if (!dentry->d_inode)
- goto out;
+ if (!dentry->d_inode) {
+ gossip_debug(GOSSIP_DCACHE_DEBUG,
+ "%s: negative dentry or positive dentry and inode valid.\n",
+ __func__);
+ return 1;
+ }
/* Now we must perform a getattr to validate the inode contents. */
__FILE__, __func__, __LINE__);
return 0;
}
- if (ret == 0)
- return 0;
-
-out:
- gossip_debug(GOSSIP_DCACHE_DEBUG,
- "%s: negative dentry or positive dentry and inode valid.\n",
- __func__);
- return 1;
+ return !ret;
}
const struct dentry_operations orangefs_dentry_operations = {
poll_wait(file, &orangefs_request_list_waitq, poll_table);
if (!list_empty(&orangefs_request_list))
- poll_revent_mask |= POLLIN;
+ poll_revent_mask |= EPOLLIN;
return poll_revent_mask;
}
ORANGEFS_TYPE_METAFILE, mode);
strncpy(new_op->upcall.req.create.d_name,
- dentry->d_name.name, ORANGEFS_NAME_MAX);
+ dentry->d_name.name, ORANGEFS_NAME_MAX - 1);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
new_op->upcall.req.lookup.parent_refn = parent->refn;
strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name,
- ORANGEFS_NAME_MAX);
+ ORANGEFS_NAME_MAX - 1);
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: doing lookup on %s under %pU,%d\n",
new_op->upcall.req.remove.parent_refn = parent->refn;
strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name,
- ORANGEFS_NAME_MAX);
+ ORANGEFS_NAME_MAX - 1);
ret = service_operation(new_op, "orangefs_unlink",
get_interruptible_flag(inode));
strncpy(new_op->upcall.req.sym.entry_name,
dentry->d_name.name,
- ORANGEFS_NAME_MAX);
- strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX);
+ ORANGEFS_NAME_MAX - 1);
+ strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX - 1);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
ORANGEFS_TYPE_DIRECTORY, mode);
strncpy(new_op->upcall.req.mkdir.d_name,
- dentry->d_name.name, ORANGEFS_NAME_MAX);
+ dentry->d_name.name, ORANGEFS_NAME_MAX - 1);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
strncpy(new_op->upcall.req.rename.d_old_name,
old_dentry->d_name.name,
- ORANGEFS_NAME_MAX);
+ ORANGEFS_NAME_MAX - 1);
strncpy(new_op->upcall.req.rename.d_new_name,
new_dentry->d_name.name,
- ORANGEFS_NAME_MAX);
+ ORANGEFS_NAME_MAX - 1);
ret = service_operation(new_op,
"orangefs_rename",
/*
* initialize the client-debug file.
*/
-int orangefs_client_debug_init(void)
+static int orangefs_client_debug_init(void)
{
int rc = -ENOMEM;
client_debug_string,
llu(mask_info.mask_value));
} else {
- gossip_lerr("Invalid mask type....\n");
+ gossip_err("Invalid mask type....\n");
return -EINVAL;
}
/* SPDX-License-Identifier: GPL-2.0 */
int orangefs_debugfs_init(int);
void orangefs_debugfs_cleanup(void);
-int orangefs_client_debug_init(void);
int orangefs_prepare_debugfs_help_string(int);
int orangefs_debugfs_new_client_mask(void __user *);
int orangefs_debugfs_new_client_string(void __user *);
#include "orangefs-dev-proto.h"
-#ifdef ORANGEFS_KERNEL_DEBUG
-#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS 10
-#else
#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS 20
-#endif
#define ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS 30
* orangefs kernel memory related flags
*/
-#if ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB))
+#if (defined CONFIG_DEBUG_SLAB)
#define ORANGEFS_CACHE_CREATE_FLAGS SLAB_RED_ZONE
#else
#define ORANGEFS_CACHE_CREATE_FLAGS 0
-#endif /* ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB)) */
+#endif
extern int orangefs_init_acl(struct inode *inode, struct inode *dir);
extern const struct xattr_handler *orangefs_xattr_handlers[];
int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr);
-void orangefs_make_bad_inode(struct inode *inode);
-
int orangefs_unmount_sb(struct super_block *sb);
bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op);
return -1;
}
-static int orangefs_inode_is_stale(struct inode *inode, int new,
+static void orangefs_make_bad_inode(struct inode *inode)
+{
+ if (is_root_handle(inode)) {
+ /*
+ * if this occurs, the pvfs2-client-core was killed but we
+ * can't afford to lose the inode operations and such
+ * associated with the root handle in any case.
+ */
+ gossip_debug(GOSSIP_UTILS_DEBUG,
+ "*** NOT making bad root inode %pU\n",
+ get_khandle_from_ino(inode));
+ } else {
+ gossip_debug(GOSSIP_UTILS_DEBUG,
+ "*** making bad inode %pU\n",
+ get_khandle_from_ino(inode));
+ make_bad_inode(inode);
+ }
+}
+
+static int orangefs_inode_is_stale(struct inode *inode,
struct ORANGEFS_sys_attr_s *attrs, char *link_target)
{
struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
int type = orangefs_inode_type(attrs->objtype);
- if (!new) {
- /*
- * If the inode type or symlink target have changed then this
- * inode is stale.
- */
- if (type == -1 || !(inode->i_mode & type)) {
- orangefs_make_bad_inode(inode);
- return 1;
- }
- if (type == S_IFLNK && strncmp(orangefs_inode->link_target,
- link_target, ORANGEFS_NAME_MAX)) {
- orangefs_make_bad_inode(inode);
- return 1;
- }
+ /*
+ * If the inode type or symlink target have changed then this
+ * inode is stale.
+ */
+ if (type == -1 || !(inode->i_mode & type)) {
+ orangefs_make_bad_inode(inode);
+ return 1;
+ }
+ if (type == S_IFLNK && strncmp(orangefs_inode->link_target,
+ link_target, ORANGEFS_NAME_MAX)) {
+ orangefs_make_bad_inode(inode);
+ return 1;
}
return 0;
}
if (ret != 0)
goto out;
- type = orangefs_inode_type(new_op->
- downcall.resp.getattr.attributes.objtype);
- ret = orangefs_inode_is_stale(inode, new,
- &new_op->downcall.resp.getattr.attributes,
- new_op->downcall.resp.getattr.link_target);
- if (ret) {
- ret = -ESTALE;
- goto out;
+ if (!new) {
+ ret = orangefs_inode_is_stale(inode,
+ &new_op->downcall.resp.getattr.attributes,
+ new_op->downcall.resp.getattr.link_target);
+ if (ret) {
+ ret = -ESTALE;
+ goto out;
+ }
}
+ type = orangefs_inode_type(new_op->
+ downcall.resp.getattr.attributes.objtype);
switch (type) {
case S_IFREG:
inode->i_flags = orangefs_inode_flags(&new_op->
inode->i_link = orangefs_inode->link_target;
}
break;
+ /* i.e. -1 */
+ default:
+ /* XXX: ESTALE? This is what is done if it is not new. */
+ orangefs_make_bad_inode(inode);
+ ret = -ESTALE;
+ goto out;
}
inode->i_uid = make_kuid(&init_user_ns, new_op->
if (ret != 0)
goto out;
- ret = orangefs_inode_is_stale(inode, 0,
+ ret = orangefs_inode_is_stale(inode,
&new_op->downcall.resp.getattr.attributes,
new_op->downcall.resp.getattr.link_target);
out:
return ret;
}
-void orangefs_make_bad_inode(struct inode *inode)
-{
- if (is_root_handle(inode)) {
- /*
- * if this occurs, the pvfs2-client-core was killed but we
- * can't afford to lose the inode operations and such
- * associated with the root handle in any case.
- */
- gossip_debug(GOSSIP_UTILS_DEBUG,
- "*** NOT making bad root inode %pU\n",
- get_khandle_from_ino(inode));
- } else {
- gossip_debug(GOSSIP_UTILS_DEBUG,
- "*** making bad inode %pU\n",
- get_khandle_from_ino(inode));
- make_bad_inode(inode);
- }
-}
-
/*
* The following is a very dirty hack that is now a permanent part of the
* ORANGEFS protocol. See protocol.h for more error definitions.
*/
} else {
gossip_err("orangefs: orangefs_normalize_to_errno: got error code which is not from ORANGEFS.\n");
+ error_code = -EINVAL;
}
return error_code;
}
/* gossip.h *****************************************************************/
-#ifdef GOSSIP_DISABLE_DEBUG
-#define gossip_debug(mask, fmt, ...) \
-do { \
- if (0) \
- printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
-} while (0)
-#else
extern __u64 orangefs_gossip_debug_mask;
/* try to avoid function call overhead by checking masks in macro */
if (orangefs_gossip_debug_mask & (mask)) \
printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
} while (0)
-#endif /* GOSSIP_DISABLE_DEBUG */
-
-/* do file and line number printouts w/ the GNU preprocessor */
-#define gossip_ldebug(mask, fmt, ...) \
- gossip_debug(mask, "%s: " fmt, __func__, ##__VA_ARGS__)
#define gossip_err pr_err
-#define gossip_lerr(fmt, ...) \
- gossip_err("%s line %d: " fmt, \
- __FILE__, __LINE__, ##__VA_ARGS__)
struct orangefs_object_kref refn;
if (*max_len < len) {
- gossip_lerr("fh buffer is too small for encoding\n");
+ gossip_err("fh buffer is too small for encoding\n");
*max_len = len;
type = 255;
goto out;
op->upcall.req.fs_umount.id = id;
op->upcall.req.fs_umount.fs_id = fs_id;
strncpy(op->upcall.req.fs_umount.orangefs_config_server,
- devname, ORANGEFS_MAX_SERVER_ADDR_LEN);
+ devname, ORANGEFS_MAX_SERVER_ADDR_LEN - 1);
r = service_operation(op, "orangefs_fs_umount", 0);
/* Not much to do about an error here. */
if (r)
strncpy(new_op->upcall.req.fs_mount.orangefs_config_server,
devname,
- ORANGEFS_MAX_SERVER_ADDR_LEN);
+ ORANGEFS_MAX_SERVER_ADDR_LEN - 1);
gossip_debug(GOSSIP_SUPER_DEBUG,
"Attempting ORANGEFS Mount via host %s\n",
*/
strncpy(ORANGEFS_SB(sb)->devname,
devname,
- ORANGEFS_MAX_SERVER_ADDR_LEN);
+ ORANGEFS_MAX_SERVER_ADDR_LEN - 1);
/* mount_pending must be cleared */
ORANGEFS_SB(sb)->mount_pending = 0;
break;
}
if (do_wakeup) {
- wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM);
+ wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
pipe_wait(pipe);
/* Signal writers asynchronously that there is more room. */
if (do_wakeup) {
- wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM);
+ wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
if (ret > 0)
break;
}
if (do_wakeup) {
- wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
+ wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
do_wakeup = 0;
}
out:
__pipe_unlock(pipe);
if (do_wakeup) {
- wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM);
+ wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
}
if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) {
nrbufs = pipe->nrbufs;
mask = 0;
if (filp->f_mode & FMODE_READ) {
- mask = (nrbufs > 0) ? POLLIN | POLLRDNORM : 0;
+ mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0;
if (!pipe->writers && filp->f_version != pipe->w_counter)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
}
if (filp->f_mode & FMODE_WRITE) {
- mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0;
+ mask |= (nrbufs < pipe->buffers) ? EPOLLOUT | EPOLLWRNORM : 0;
/*
- * Most Unices do not set POLLERR for FIFOs but on Linux they
+ * Most Unices do not set EPOLLERR for FIFOs but on Linux they
* behave exactly like pipes for poll().
*/
if (!pipe->readers)
- mask |= POLLERR;
+ mask |= EPOLLERR;
}
return mask;
pipe->writers--;
if (pipe->readers || pipe->writers) {
- wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM | POLLERR | POLLHUP);
+ wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM | EPOLLERR | EPOLLHUP);
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
if (!is_pipe && !pipe->writers) {
if ((filp->f_flags & O_NONBLOCK)) {
- /* suppress POLLHUP until we have
+ /* suppress EPOLLHUP until we have
* seen a writer */
filp->f_version = pipe->w_counter;
} else {
{
poll_wait(file, &log_wait, wait);
if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
/* sysctl was unregistered */
if (IS_ERR(head))
- return POLLERR | POLLHUP;
+ return EPOLLERR | EPOLLHUP;
if (!table->proc_handler)
goto out;
if (event != atomic_read(&table->poll->event)) {
filp->private_data = proc_sys_poll_event(table->poll);
- ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI;
+ ret = EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI;
}
out:
struct seq_file *m = file->private_data;
struct proc_mounts *p = m->private;
struct mnt_namespace *ns = p->ns;
- __poll_t res = POLLIN | POLLRDNORM;
+ __poll_t res = EPOLLIN | EPOLLRDNORM;
int event;
poll_wait(file, &p->ns->poll, wait);
event = READ_ONCE(ns->event);
if (m->poll_event != event) {
m->poll_event = event;
- res |= POLLERR | POLLPRI;
+ res |= EPOLLERR | EPOLLPRI;
}
return res;
return max;
}
-#define POLLIN_SET (POLLRDNORM | POLLRDBAND | POLLIN | POLLHUP | POLLERR)
-#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
-#define POLLEX_SET (POLLPRI)
+#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR)
+#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR)
+#define POLLEX_SET (EPOLLPRI)
static inline void wait_key_set(poll_table *wait, unsigned long in,
unsigned long out, unsigned long bit,
fd = pollfd->fd;
if (fd >= 0) {
struct fd f = fdget(fd);
- mask = POLLNVAL;
+ mask = EPOLLNVAL;
if (f.file) {
/* userland u16 ->events contains POLL... bitmap */
__poll_t filter = demangle_poll(pollfd->events) |
- POLLERR | POLLHUP;
+ EPOLLERR | EPOLLHUP;
mask = DEFAULT_POLLMASK;
if (f.file->f_op->poll) {
pwait->_key = filter;
* if request is to read from zero offset, reset iterator to first
* record as it might have been already advanced by previous requests
*/
- if (*ppos == 0)
+ if (*ppos == 0) {
m->index = 0;
+ m->version = 0;
+ m->count = 0;
+ }
/* Don't assume *ppos is where we left it */
if (unlikely(*ppos != m->read_pos)) {
return;
/* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */
- wake_up_poll(wqh, POLLHUP | POLLFREE);
+ wake_up_poll(wqh, EPOLLHUP | POLLFREE);
}
struct signalfd_ctx {
if (next_signal(¤t->pending, &ctx->sigmask) ||
next_signal(¤t->signal->shared_pending,
&ctx->sigmask))
- events |= POLLIN;
+ events |= EPOLLIN;
spin_unlock_irq(¤t->sighand->siglock);
return events;
spin_lock_irqsave(&ctx->wqh.lock, flags);
if (ctx->ticks)
- events |= POLLIN;
+ events |= EPOLLIN;
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
return events;
if (likely(must_wait && !READ_ONCE(ctx->released) &&
(return_to_userland ? !signal_pending(current) :
!fatal_signal_pending(current)))) {
- wake_up_poll(&ctx->fd_wqh, POLLIN);
+ wake_up_poll(&ctx->fd_wqh, EPOLLIN);
schedule();
ret |= VM_FAULT_MAJOR;
spin_unlock(&ctx->event_wqh.lock);
- wake_up_poll(&ctx->fd_wqh, POLLIN);
+ wake_up_poll(&ctx->fd_wqh, EPOLLIN);
schedule();
spin_lock(&ctx->event_wqh.lock);
/* Flush pending events that may still wait on event_wqh */
wake_up_all(&ctx->event_wqh);
- wake_up_poll(&ctx->fd_wqh, POLLHUP);
+ wake_up_poll(&ctx->fd_wqh, EPOLLHUP);
userfaultfd_ctx_put(ctx);
return 0;
}
switch (ctx->state) {
case UFFD_STATE_WAIT_API:
- return POLLERR;
+ return EPOLLERR;
case UFFD_STATE_RUNNING:
/*
* poll() never guarantees that read won't block.
* userfaults can be waken before they're read().
*/
if (unlikely(!(file->f_flags & O_NONBLOCK)))
- return POLLERR;
+ return EPOLLERR;
/*
* lockless access to see if there are pending faults
* __pollwait last action is the add_wait_queue but
ret = 0;
smp_mb();
if (waitqueue_active(&ctx->fault_pending_wqh))
- ret = POLLIN;
+ ret = EPOLLIN;
else if (waitqueue_active(&ctx->event_wqh))
- ret = POLLIN;
+ ret = EPOLLIN;
return ret;
default:
WARN_ON_ONCE(1);
- return POLLERR;
+ return EPOLLERR;
}
}
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* Current ACPICA subsystem version in YYYYMMDD format */
-#define ACPI_CA_VERSION 0x20171215
+#define ACPI_CA_VERSION 0x20180105
#include <acpi/acconfig.h>
#include <acpi/actypes.h>
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/*
* Constants with special meanings
*/
-#define ACPI_ROOT_OBJECT ACPI_ADD_PTR (acpi_handle, NULL, ACPI_MAX_PTR)
+#define ACPI_ROOT_OBJECT ((acpi_handle) ACPI_TO_POINTER (ACPI_MAX_PTR))
#define ACPI_WAIT_FOREVER 0xFFFF /* u16, as per ACPI spec */
#define ACPI_DO_NOT_WAIT 0
#define ACPI_CAST_INDIRECT_PTR(t, p) ((t **) (acpi_uintptr_t) (p))
#define ACPI_ADD_PTR(t, a, b) ACPI_CAST_PTR (t, (ACPI_CAST_PTR (u8, (a)) + (acpi_size)(b)))
#define ACPI_SUB_PTR(t, a, b) ACPI_CAST_PTR (t, (ACPI_CAST_PTR (u8, (a)) - (acpi_size)(b)))
-#define ACPI_PTR_DIFF(a, b) (acpi_size) (ACPI_CAST_PTR (u8, (a)) - ACPI_CAST_PTR (u8, (b)))
+#define ACPI_PTR_DIFF(a, b) ((acpi_size) (ACPI_CAST_PTR (u8, (a)) - ACPI_CAST_PTR (u8, (b))))
/* Pointer/Integer type conversions */
-#define ACPI_TO_POINTER(i) ACPI_ADD_PTR (void, (void *) NULL,(acpi_size) i)
-#define ACPI_TO_INTEGER(p) ACPI_PTR_DIFF (p, (void *) NULL)
-#define ACPI_OFFSET(d, f) ACPI_PTR_DIFF (&(((d *) 0)->f), (void *) NULL)
+#define ACPI_TO_POINTER(i) ACPI_ADD_PTR (void, (void *) 0, (acpi_size) (i))
+#define ACPI_TO_INTEGER(p) ACPI_PTR_DIFF (p, (void *) 0)
+#define ACPI_OFFSET(d, f) ACPI_PTR_DIFF (&(((d *) 0)->f), (void *) 0)
#define ACPI_PHYSADDR_TO_PTR(i) ACPI_TO_POINTER(i)
#define ACPI_PTR_TO_PHYSADDR(i) ACPI_TO_INTEGER(i)
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#define ACPI_FLUSH_CPU_CACHE()
#define ACPI_CAST_PTHREAD_T(pthread) ((acpi_thread_id) (pthread))
-#if defined(__ia64__) || defined(__x86_64__) ||\
+#if defined(__ia64__) || (defined(__x86_64__) && !defined(__ILP32__)) ||\
defined(__aarch64__) || defined(__PPC64__) ||\
defined(__s390x__)
#define ACPI_MACHINE_WIDTH 64
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
void kvm_timer_init_vhe(void);
+bool kvm_arch_timer_get_input_level(int vintid);
+
#define vcpu_vtimer(v) (&(v)->arch.timer_cpu.vtimer)
#define vcpu_ptimer(v) (&(v)->arch.timer_cpu.ptimer)
--- /dev/null
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __KVM_ARM_PSCI_H__
+#define __KVM_ARM_PSCI_H__
+
+#include <linux/kvm_host.h>
+#include <uapi/linux/psci.h>
+
+#define KVM_ARM_PSCI_0_1 PSCI_VERSION(0, 1)
+#define KVM_ARM_PSCI_0_2 PSCI_VERSION(0, 2)
+#define KVM_ARM_PSCI_1_0 PSCI_VERSION(1, 0)
+
+#define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_0
+
+/*
+ * We need the KVM pointer independently from the vcpu as we can call
+ * this from HYP, and need to apply kern_hyp_va on it...
+ */
+static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm)
+{
+ /*
+ * Our PSCI implementation stays the same across versions from
+ * v0.2 onward, only adding the few mandatory functions (such
+ * as FEATURES with 1.0) that are required by newer
+ * revisions. It is thus safe to return the latest.
+ */
+ if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+ return KVM_ARM_PSCI_LATEST;
+
+ return KVM_ARM_PSCI_0_1;
+}
+
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu);
+
+#endif /* __KVM_ARM_PSCI_H__ */
u8 priority;
enum vgic_irq_config config; /* Level or edge */
+ /*
+ * Callback function pointer to in-kernel devices that can tell us the
+ * state of the input level of mapped level-triggered IRQ faster than
+ * peaking into the physical GIC.
+ *
+ * Always called in non-preemptible section and the functions can use
+ * kvm_arm_get_running_vcpu() to get the vcpu pointer for private
+ * IRQs.
+ */
+ bool (*get_input_level)(int vintid);
+
void *owner; /* Opaque pointer to reserve an interrupt
for in-kernel devices. */
};
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level, void *owner);
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
- u32 vintid);
+ u32 vintid, bool (*get_input_level)(int vindid));
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid);
bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid);
#ifdef CONFIG_ACPI_SPCR_TABLE
extern bool qdf2400_e44_present;
-int parse_spcr(bool earlycon);
+int acpi_parse_spcr(bool enable_earlycon, bool enable_console);
#else
-static inline int parse_spcr(bool earlycon) { return 0; }
+static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console)
+{
+ return 0;
+}
#endif
#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
#ifndef __LINUX_ARM_SMCCC_H
#define __LINUX_ARM_SMCCC_H
+#include <uapi/linux/const.h>
+
/*
* This file provides common defines for ARM SMC Calling Convention as
* specified in
* http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
*/
-#define ARM_SMCCC_STD_CALL 0
-#define ARM_SMCCC_FAST_CALL 1
+#define ARM_SMCCC_STD_CALL _AC(0,U)
+#define ARM_SMCCC_FAST_CALL _AC(1,U)
#define ARM_SMCCC_TYPE_SHIFT 31
#define ARM_SMCCC_SMC_32 0
#define ARM_SMCCC_QUIRK_NONE 0
#define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */
+#define ARM_SMCCC_VERSION_1_0 0x10000
+#define ARM_SMCCC_VERSION_1_1 0x10001
+
+#define ARM_SMCCC_VERSION_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 0)
+
+#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 1)
+
+#define ARM_SMCCC_ARCH_WORKAROUND_1 \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ 0, 0x8000)
+
#ifndef __ASSEMBLY__
#include <linux/linkage.h>
#define arm_smccc_hvc_quirk(...) __arm_smccc_hvc(__VA_ARGS__)
+/* SMCCC v1.1 implementation madness follows */
+#ifdef CONFIG_ARM64
+
+#define SMCCC_SMC_INST "smc #0"
+#define SMCCC_HVC_INST "hvc #0"
+
+#elif defined(CONFIG_ARM)
+#include <asm/opcodes-sec.h>
+#include <asm/opcodes-virt.h>
+
+#define SMCCC_SMC_INST __SMC(0)
+#define SMCCC_HVC_INST __HVC(0)
+
+#endif
+
+#define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
+
+#define __count_args(...) \
+ ___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __constraint_write_0 \
+ "+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_1 \
+ "+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3)
+#define __constraint_write_2 \
+ "+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3)
+#define __constraint_write_3 \
+ "+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3)
+#define __constraint_write_4 __constraint_write_3
+#define __constraint_write_5 __constraint_write_4
+#define __constraint_write_6 __constraint_write_5
+#define __constraint_write_7 __constraint_write_6
+
+#define __constraint_read_0
+#define __constraint_read_1
+#define __constraint_read_2
+#define __constraint_read_3
+#define __constraint_read_4 "r" (r4)
+#define __constraint_read_5 __constraint_read_4, "r" (r5)
+#define __constraint_read_6 __constraint_read_5, "r" (r6)
+#define __constraint_read_7 __constraint_read_6, "r" (r7)
+
+#define __declare_arg_0(a0, res) \
+ struct arm_smccc_res *___res = res; \
+ register u32 r0 asm("r0") = a0; \
+ register unsigned long r1 asm("r1"); \
+ register unsigned long r2 asm("r2"); \
+ register unsigned long r3 asm("r3")
+
+#define __declare_arg_1(a0, a1, res) \
+ struct arm_smccc_res *___res = res; \
+ register u32 r0 asm("r0") = a0; \
+ register typeof(a1) r1 asm("r1") = a1; \
+ register unsigned long r2 asm("r2"); \
+ register unsigned long r3 asm("r3")
+
+#define __declare_arg_2(a0, a1, a2, res) \
+ struct arm_smccc_res *___res = res; \
+ register u32 r0 asm("r0") = a0; \
+ register typeof(a1) r1 asm("r1") = a1; \
+ register typeof(a2) r2 asm("r2") = a2; \
+ register unsigned long r3 asm("r3")
+
+#define __declare_arg_3(a0, a1, a2, a3, res) \
+ struct arm_smccc_res *___res = res; \
+ register u32 r0 asm("r0") = a0; \
+ register typeof(a1) r1 asm("r1") = a1; \
+ register typeof(a2) r2 asm("r2") = a2; \
+ register typeof(a3) r3 asm("r3") = a3
+
+#define __declare_arg_4(a0, a1, a2, a3, a4, res) \
+ __declare_arg_3(a0, a1, a2, a3, res); \
+ register typeof(a4) r4 asm("r4") = a4
+
+#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \
+ __declare_arg_4(a0, a1, a2, a3, a4, res); \
+ register typeof(a5) r5 asm("r5") = a5
+
+#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \
+ __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \
+ register typeof(a6) r6 asm("r6") = a6
+
+#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \
+ __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \
+ register typeof(a7) r7 asm("r7") = a7
+
+#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
+#define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__)
+
+#define ___constraints(count) \
+ : __constraint_write_ ## count \
+ : __constraint_read_ ## count \
+ : "memory"
+#define __constraints(count) ___constraints(count)
+
+/*
+ * We have an output list that is not necessarily used, and GCC feels
+ * entitled to optimise the whole sequence away. "volatile" is what
+ * makes it stick.
+ */
+#define __arm_smccc_1_1(inst, ...) \
+ do { \
+ __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \
+ asm volatile(inst "\n" \
+ __constraints(__count_args(__VA_ARGS__))); \
+ if (___res) \
+ *___res = (typeof(*___res)){r0, r1, r2, r3}; \
+ } while (0)
+
+/*
+ * arm_smccc_1_1_smc() - make an SMCCC v1.1 compliant SMC call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro is used to make SMC calls following SMC Calling Convention v1.1.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the SMC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the SMC instruction if not NULL.
+ */
+#define arm_smccc_1_1_smc(...) __arm_smccc_1_1(SMCCC_SMC_INST, __VA_ARGS__)
+
+/*
+ * arm_smccc_1_1_hvc() - make an SMCCC v1.1 compliant HVC call
+ *
+ * This is a variadic macro taking one to eight source arguments, and
+ * an optional return structure.
+ *
+ * @a0-a7: arguments passed in registers 0 to 7
+ * @res: result values from registers 0 to 3
+ *
+ * This macro is used to make HVC calls following SMC Calling Convention v1.1.
+ * The content of the supplied param are copied to registers 0 to 7 prior
+ * to the HVC instruction. The return values are updated with the content
+ * from register 0 to 3 on return from the HVC instruction if not NULL.
+ */
+#define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
+
#endif /*__ASSEMBLY__*/
#endif /*__LINUX_ARM_SMCCC_H*/
#if GCC_VERSION >= 40100
# define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
-
-#define __nostackprotector __attribute__((__optimize__("no-stack-protector")))
#endif
#if GCC_VERSION >= 40300
#endif /* __CHECKER__ */
#endif /* GCC_VERSION >= 40300 */
+#if GCC_VERSION >= 40400
+#define __optimize(level) __attribute__((__optimize__(level)))
+#define __nostackprotector __optimize("no-stack-protector")
+#endif /* GCC_VERSION >= 40400 */
+
#if GCC_VERSION >= 40500
#ifndef __CHECKER__
#endif /* __ASSEMBLY__ */
+#ifndef __optimize
+# define __optimize(level)
+#endif
+
/* Compile time object size, -1 for unknown */
#ifndef __compiletime_object_size
# define __compiletime_object_size(obj) -1
#define cpufreq_for_each_entry(pos, table) \
for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++)
+/*
+ * cpufreq_for_each_entry_idx - iterate over a cpufreq_frequency_table
+ * with index
+ * @pos: the cpufreq_frequency_table * to use as a loop cursor.
+ * @table: the cpufreq_frequency_table * to iterate over.
+ * @idx: the table entry currently being processed
+ */
+
+#define cpufreq_for_each_entry_idx(pos, table, idx) \
+ for (pos = table, idx = 0; pos->frequency != CPUFREQ_TABLE_END; \
+ pos++, idx++)
+
/*
* cpufreq_for_each_valid_entry - iterate over a cpufreq_frequency_table
* excluding CPUFREQ_ENTRY_INVALID frequencies.
continue; \
else
+/*
+ * cpufreq_for_each_valid_entry_idx - iterate with index over a cpufreq
+ * frequency_table excluding CPUFREQ_ENTRY_INVALID frequencies.
+ * @pos: the cpufreq_frequency_table * to use as a loop cursor.
+ * @table: the cpufreq_frequency_table * to iterate over.
+ * @idx: the table entry currently being processed
+ */
+
+#define cpufreq_for_each_valid_entry_idx(pos, table, idx) \
+ cpufreq_for_each_entry_idx(pos, table, idx) \
+ if (pos->frequency == CPUFREQ_ENTRY_INVALID) \
+ continue; \
+ else
+
+
int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table);
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
- struct cpufreq_frequency_table *pos, *best = table - 1;
+ struct cpufreq_frequency_table *pos;
unsigned int freq;
+ int idx, best = -1;
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, idx) {
freq = pos->frequency;
if (freq >= target_freq)
- return pos - table;
+ return idx;
- best = pos;
+ best = idx;
}
- return best - table;
+ return best;
}
/* Find lowest freq at or above target in a table in descending order */
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
- struct cpufreq_frequency_table *pos, *best = table - 1;
+ struct cpufreq_frequency_table *pos;
unsigned int freq;
+ int idx, best = -1;
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, idx) {
freq = pos->frequency;
if (freq == target_freq)
- return pos - table;
+ return idx;
if (freq > target_freq) {
- best = pos;
+ best = idx;
continue;
}
/* No freq found above target_freq */
- if (best == table - 1)
- return pos - table;
+ if (best == -1)
+ return idx;
- return best - table;
+ return best;
}
- return best - table;
+ return best;
}
/* Works only on sorted freq-tables */
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
- struct cpufreq_frequency_table *pos, *best = table - 1;
+ struct cpufreq_frequency_table *pos;
unsigned int freq;
+ int idx, best = -1;
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, idx) {
freq = pos->frequency;
if (freq == target_freq)
- return pos - table;
+ return idx;
if (freq < target_freq) {
- best = pos;
+ best = idx;
continue;
}
/* No freq found below target_freq */
- if (best == table - 1)
- return pos - table;
+ if (best == -1)
+ return idx;
- return best - table;
+ return best;
}
- return best - table;
+ return best;
}
/* Find highest freq at or below target in a table in descending order */
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
- struct cpufreq_frequency_table *pos, *best = table - 1;
+ struct cpufreq_frequency_table *pos;
unsigned int freq;
+ int idx, best = -1;
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, idx) {
freq = pos->frequency;
if (freq <= target_freq)
- return pos - table;
+ return idx;
- best = pos;
+ best = idx;
}
- return best - table;
+ return best;
}
/* Works only on sorted freq-tables */
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
- struct cpufreq_frequency_table *pos, *best = table - 1;
+ struct cpufreq_frequency_table *pos;
unsigned int freq;
+ int idx, best = -1;
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, idx) {
freq = pos->frequency;
if (freq == target_freq)
- return pos - table;
+ return idx;
if (freq < target_freq) {
- best = pos;
+ best = idx;
continue;
}
/* No freq found below target_freq */
- if (best == table - 1)
- return pos - table;
+ if (best == -1)
+ return idx;
/* Choose the closest freq */
- if (target_freq - best->frequency > freq - target_freq)
- return pos - table;
+ if (target_freq - table[best].frequency > freq - target_freq)
+ return idx;
- return best - table;
+ return best;
}
- return best - table;
+ return best;
}
/* Find closest freq to target in a table in descending order */
unsigned int target_freq)
{
struct cpufreq_frequency_table *table = policy->freq_table;
- struct cpufreq_frequency_table *pos, *best = table - 1;
+ struct cpufreq_frequency_table *pos;
unsigned int freq;
+ int idx, best = -1;
- cpufreq_for_each_valid_entry(pos, table) {
+ cpufreq_for_each_valid_entry_idx(pos, table, idx) {
freq = pos->frequency;
if (freq == target_freq)
- return pos - table;
+ return idx;
if (freq > target_freq) {
- best = pos;
+ best = idx;
continue;
}
/* No freq found above target_freq */
- if (best == table - 1)
- return pos - table;
+ if (best == -1)
+ return idx;
/* Choose the closest freq */
- if (best->frequency - target_freq > target_freq - freq)
- return pos - table;
+ if (table[best].frequency - target_freq > target_freq - freq)
+ return idx;
- return best - table;
+ return best;
}
- return best - table;
+ return best;
}
/* Works only on sorted freq-tables */
#ifdef __KERNEL__
struct device;
int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
-unsigned char *arch_get_platform_get_mac_address(void);
+unsigned char *arch_get_platform_mac_address(void);
u32 eth_get_headlen(void *data, unsigned int max_len);
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
extern const struct header_ops eth_header_ops;
#include <linux/radix-tree.h>
#include <linux/gfp.h>
#include <linux/percpu.h>
-#include <linux/bug.h>
struct idr {
struct radix_tree_root idr_rt;
+ unsigned int idr_base;
unsigned int idr_next;
};
/* Set the IDR flag and the IDR_FREE tag */
#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT))
-#define IDR_INIT \
-{ \
- .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER) \
+#define IDR_INIT_BASE(base) { \
+ .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER), \
+ .idr_base = (base), \
+ .idr_next = 0, \
}
+
+/**
+ * IDR_INIT() - Initialise an IDR.
+ *
+ * A freshly-initialised IDR contains no IDs.
+ */
+#define IDR_INIT IDR_INIT_BASE(0)
+
+/**
+ * DEFINE_IDR() - Define a statically-allocated IDR
+ * @name: Name of IDR
+ *
+ * An IDR defined using this macro is ready for use with no additional
+ * initialisation required. It contains no IDs.
+ */
#define DEFINE_IDR(name) struct idr name = IDR_INIT
/**
void idr_preload(gfp_t gfp_mask);
-int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
- unsigned long start, unsigned long end, gfp_t gfp,
- bool ext);
-
-/**
- * idr_alloc - allocate an id
- * @idr: idr handle
- * @ptr: pointer to be associated with the new id
- * @start: the minimum id (inclusive)
- * @end: the maximum id (exclusive)
- * @gfp: memory allocation flags
- *
- * Allocates an unused ID in the range [start, end). Returns -ENOSPC
- * if there are no unused IDs in that range.
- *
- * Note that @end is treated as max when <= 0. This is to always allow
- * using @start + N as @end as long as N is inside integer range.
- *
- * Simultaneous modifications to the @idr are not allowed and should be
- * prevented by the user, usually with a lock. idr_alloc() may be called
- * concurrently with read-only accesses to the @idr, such as idr_find() and
- * idr_for_each_entry().
- */
-static inline int idr_alloc(struct idr *idr, void *ptr,
- int start, int end, gfp_t gfp)
-{
- unsigned long id;
- int ret;
-
- if (WARN_ON_ONCE(start < 0))
- return -EINVAL;
-
- ret = idr_alloc_cmn(idr, ptr, &id, start, end, gfp, false);
-
- if (ret)
- return ret;
-
- return id;
-}
-
-static inline int idr_alloc_ext(struct idr *idr, void *ptr,
- unsigned long *index,
- unsigned long start,
- unsigned long end,
- gfp_t gfp)
-{
- return idr_alloc_cmn(idr, ptr, index, start, end, gfp, true);
-}
-
-int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t);
+int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t);
+int __must_check idr_alloc_u32(struct idr *, void *ptr, u32 *id,
+ unsigned long max, gfp_t);
+int idr_alloc_cyclic(struct idr *, void *ptr, int start, int end, gfp_t);
+void *idr_remove(struct idr *, unsigned long id);
+void *idr_find(const struct idr *, unsigned long id);
int idr_for_each(const struct idr *,
int (*fn)(int id, void *p, void *data), void *data);
void *idr_get_next(struct idr *, int *nextid);
-void *idr_get_next_ext(struct idr *idr, unsigned long *nextid);
-void *idr_replace(struct idr *, void *, int id);
-void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id);
+void *idr_get_next_ul(struct idr *, unsigned long *nextid);
+void *idr_replace(struct idr *, void *, unsigned long id);
void idr_destroy(struct idr *);
-static inline void *idr_remove_ext(struct idr *idr, unsigned long id)
-{
- return radix_tree_delete_item(&idr->idr_rt, id, NULL);
-}
-
-static inline void *idr_remove(struct idr *idr, int id)
+/**
+ * idr_init_base() - Initialise an IDR.
+ * @idr: IDR handle.
+ * @base: The base value for the IDR.
+ *
+ * This variation of idr_init() creates an IDR which will allocate IDs
+ * starting at %base.
+ */
+static inline void idr_init_base(struct idr *idr, int base)
{
- return idr_remove_ext(idr, id);
+ INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER);
+ idr->idr_base = base;
+ idr->idr_next = 0;
}
+/**
+ * idr_init() - Initialise an IDR.
+ * @idr: IDR handle.
+ *
+ * Initialise a dynamically allocated IDR. To initialise a
+ * statically allocated IDR, use DEFINE_IDR().
+ */
static inline void idr_init(struct idr *idr)
{
- INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER);
- idr->idr_next = 0;
+ idr_init_base(idr, 0);
}
+/**
+ * idr_is_empty() - Are there any IDs allocated?
+ * @idr: IDR handle.
+ *
+ * Return: %true if any IDs have been allocated from this IDR.
+ */
static inline bool idr_is_empty(const struct idr *idr)
{
return radix_tree_empty(&idr->idr_rt) &&
}
/**
- * idr_find - return pointer for given id
- * @idr: idr handle
- * @id: lookup key
- *
- * Return the pointer given the id it has been registered with. A %NULL
- * return indicates that @id is not valid or you passed %NULL in
- * idr_get_new().
+ * idr_for_each_entry() - Iterate over an IDR's elements of a given type.
+ * @idr: IDR handle.
+ * @entry: The type * to use as cursor
+ * @id: Entry ID.
*
- * This function can be called under rcu_read_lock(), given that the leaf
- * pointers lifetimes are correctly managed.
+ * @entry and @id do not need to be initialized before the loop, and
+ * after normal termination @entry is left with the value NULL. This
+ * is convenient for a "not found" value.
*/
-static inline void *idr_find_ext(const struct idr *idr, unsigned long id)
-{
- return radix_tree_lookup(&idr->idr_rt, id);
-}
-
-static inline void *idr_find(const struct idr *idr, int id)
-{
- return idr_find_ext(idr, id);
-}
+#define idr_for_each_entry(idr, entry, id) \
+ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id)
/**
- * idr_for_each_entry - iterate over an idr's elements of a given type
- * @idr: idr handle
- * @entry: the type * to use as cursor
- * @id: id entry's key
+ * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type.
+ * @idr: IDR handle.
+ * @entry: The type * to use as cursor.
+ * @id: Entry ID.
*
* @entry and @id do not need to be initialized before the loop, and
- * after normal terminatinon @entry is left with the value NULL. This
+ * after normal termination @entry is left with the value NULL. This
* is convenient for a "not found" value.
*/
-#define idr_for_each_entry(idr, entry, id) \
- for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id)
-#define idr_for_each_entry_ext(idr, entry, id) \
- for (id = 0; ((entry) = idr_get_next_ext(idr, &(id))) != NULL; ++id)
+#define idr_for_each_entry_ul(idr, entry, id) \
+ for (id = 0; ((entry) = idr_get_next_ul(idr, &(id))) != NULL; ++id)
/**
- * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type
- * @idr: idr handle
- * @entry: the type * to use as cursor
- * @id: id entry's key
+ * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type
+ * @idr: IDR handle.
+ * @entry: The type * to use as a cursor.
+ * @id: Entry ID.
*
- * Continue to iterate over list of given type, continuing after
- * the current position.
+ * Continue to iterate over entries, continuing after the current position.
*/
#define idr_for_each_entry_continue(idr, entry, id) \
for ((entry) = idr_get_next((idr), &(id)); \
/*
* Decoding Capability Register
*/
+#define cap_5lp_support(c) (((c) >> 60) & 1)
#define cap_pi_support(c) (((c) >> 59) & 1)
+#define cap_fl1gp_support(c) (((c) >> 56) & 1)
#define cap_read_drain(c) (((c) >> 55) & 1)
#define cap_write_drain(c) (((c) >> 54) & 1)
#define cap_max_amask_val(c) (((c) >> 48) & 0x3f)
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
-int __must_check vcpu_load(struct kvm_vcpu *vcpu);
+void vcpu_load(struct kvm_vcpu *vcpu);
void vcpu_put(struct kvm_vcpu *vcpu);
#ifdef __KVM_HAVE_IOAPIC
}
#endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */
+#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL
+long kvm_arch_vcpu_async_ioctl(struct file *filp,
+ unsigned int ioctl, unsigned long arg);
+#else
+static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
+ unsigned int ioctl,
+ unsigned long arg)
+{
+ return -ENOIOCTLCMD;
+}
+#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
+
#endif
extern struct of_device_id __iommu_of_table;
-typedef int (*of_iommu_init_fn)(struct device_node *);
-
-#define IOMMU_OF_DECLARE(name, compat, fn) \
- _OF_DECLARE(iommu, name, compat, fn, of_iommu_init_fn)
+#define IOMMU_OF_DECLARE(name, compat) OF_DECLARE_1(iommu, name, compat, NULL)
#endif /* __OF_IOMMU_H */
#define PCI_VENDOR_ID_DYNALINK 0x0675
#define PCI_DEVICE_ID_DYNALINK_IS64PH 0x1702
+#define PCI_VENDOR_ID_UBIQUITI 0x0777
+
#define PCI_VENDOR_ID_BERKOM 0x0871
#define PCI_DEVICE_ID_BERKOM_A1T 0xffa1
#define PCI_DEVICE_ID_BERKOM_T_CONCEPT 0xffa2
#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <uapi/linux/poll.h>
+#include <uapi/linux/eventpoll.h>
extern struct ctl_table epoll_table[]; /* for sysctl */
/* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
#define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC)
#define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry))
-#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)
+#define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM)
struct poll_table_struct;
extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec,
long nsec);
+#define __MAP(v, from, to) \
+ (from < to ? (v & from) * (to/from) : (v & from) / (from/to))
+
+static inline __u16 mangle_poll(__poll_t val)
+{
+ __u16 v = (__force __u16)val;
+#define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X)
+ return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) |
+ M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) |
+ M(HUP) | M(RDHUP) | M(MSG);
+#undef M
+}
+
+static inline __poll_t demangle_poll(u16 val)
+{
+#define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X)
+ return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) |
+ M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) |
+ M(HUP) | M(RDHUP) | M(MSG);
+#undef M
+}
+#undef __MAP
+
+
#endif /* _LINUX_POLL_H */
int psci_cpu_init_idle(unsigned int cpu);
int psci_cpu_suspend_enter(unsigned long index);
+enum psci_conduit {
+ PSCI_CONDUIT_NONE,
+ PSCI_CONDUIT_SMC,
+ PSCI_CONDUIT_HVC,
+};
+
+enum smccc_version {
+ SMCCC_VERSION_1_0,
+ SMCCC_VERSION_1_1,
+};
+
struct psci_operations {
u32 (*get_version)(void);
int (*cpu_suspend)(u32 state, unsigned long entry_point);
int (*affinity_info)(unsigned long target_affinity,
unsigned long lowest_affinity_level);
int (*migrate_info_type)(void);
+ enum psci_conduit conduit;
+ enum smccc_version smccc_version;
};
extern struct psci_operations psci_ops;
--- /dev/null
+/*
+ * AMD Secure Encrypted Virtualization (SEV) driver interface
+ *
+ * Copyright (C) 2016-2017 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * SEV spec 0.14 is available at:
+ * http://support.amd.com/TechDocs/55766_SEV-KM API_Specification.pdf
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __PSP_SEV_H__
+#define __PSP_SEV_H__
+
+#include <uapi/linux/psp-sev.h>
+
+#ifdef CONFIG_X86
+#include <linux/mem_encrypt.h>
+
+#define __psp_pa(x) __sme_pa(x)
+#else
+#define __psp_pa(x) __pa(x)
+#endif
+
+#define SEV_FW_BLOB_MAX_SIZE 0x4000 /* 16KB */
+
+/**
+ * SEV platform state
+ */
+enum sev_state {
+ SEV_STATE_UNINIT = 0x0,
+ SEV_STATE_INIT = 0x1,
+ SEV_STATE_WORKING = 0x2,
+
+ SEV_STATE_MAX
+};
+
+/**
+ * SEV platform and guest management commands
+ */
+enum sev_cmd {
+ /* platform commands */
+ SEV_CMD_INIT = 0x001,
+ SEV_CMD_SHUTDOWN = 0x002,
+ SEV_CMD_FACTORY_RESET = 0x003,
+ SEV_CMD_PLATFORM_STATUS = 0x004,
+ SEV_CMD_PEK_GEN = 0x005,
+ SEV_CMD_PEK_CSR = 0x006,
+ SEV_CMD_PEK_CERT_IMPORT = 0x007,
+ SEV_CMD_PDH_CERT_EXPORT = 0x008,
+ SEV_CMD_PDH_GEN = 0x009,
+ SEV_CMD_DF_FLUSH = 0x00A,
+
+ /* Guest commands */
+ SEV_CMD_DECOMMISSION = 0x020,
+ SEV_CMD_ACTIVATE = 0x021,
+ SEV_CMD_DEACTIVATE = 0x022,
+ SEV_CMD_GUEST_STATUS = 0x023,
+
+ /* Guest launch commands */
+ SEV_CMD_LAUNCH_START = 0x030,
+ SEV_CMD_LAUNCH_UPDATE_DATA = 0x031,
+ SEV_CMD_LAUNCH_UPDATE_VMSA = 0x032,
+ SEV_CMD_LAUNCH_MEASURE = 0x033,
+ SEV_CMD_LAUNCH_UPDATE_SECRET = 0x034,
+ SEV_CMD_LAUNCH_FINISH = 0x035,
+
+ /* Guest migration commands (outgoing) */
+ SEV_CMD_SEND_START = 0x040,
+ SEV_CMD_SEND_UPDATE_DATA = 0x041,
+ SEV_CMD_SEND_UPDATE_VMSA = 0x042,
+ SEV_CMD_SEND_FINISH = 0x043,
+
+ /* Guest migration commands (incoming) */
+ SEV_CMD_RECEIVE_START = 0x050,
+ SEV_CMD_RECEIVE_UPDATE_DATA = 0x051,
+ SEV_CMD_RECEIVE_UPDATE_VMSA = 0x052,
+ SEV_CMD_RECEIVE_FINISH = 0x053,
+
+ /* Guest debug commands */
+ SEV_CMD_DBG_DECRYPT = 0x060,
+ SEV_CMD_DBG_ENCRYPT = 0x061,
+
+ SEV_CMD_MAX,
+};
+
+/**
+ * struct sev_data_init - INIT command parameters
+ *
+ * @flags: processing flags
+ * @tmr_address: system physical address used for SEV-ES
+ * @tmr_len: len of tmr_address
+ */
+struct sev_data_init {
+ u32 flags; /* In */
+ u32 reserved; /* In */
+ u64 tmr_address; /* In */
+ u32 tmr_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_pek_csr - PEK_CSR command parameters
+ *
+ * @address: PEK certificate chain
+ * @len: len of certificate
+ */
+struct sev_data_pek_csr {
+ u64 address; /* In */
+ u32 len; /* In/Out */
+} __packed;
+
+/**
+ * struct sev_data_cert_import - PEK_CERT_IMPORT command parameters
+ *
+ * @pek_address: PEK certificate chain
+ * @pek_len: len of PEK certificate
+ * @oca_address: OCA certificate chain
+ * @oca_len: len of OCA certificate
+ */
+struct sev_data_pek_cert_import {
+ u64 pek_cert_address; /* In */
+ u32 pek_cert_len; /* In */
+ u32 reserved; /* In */
+ u64 oca_cert_address; /* In */
+ u32 oca_cert_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_pdh_cert_export - PDH_CERT_EXPORT command parameters
+ *
+ * @pdh_address: PDH certificate address
+ * @pdh_len: len of PDH certificate
+ * @cert_chain_address: PDH certificate chain
+ * @cert_chain_len: len of PDH certificate chain
+ */
+struct sev_data_pdh_cert_export {
+ u64 pdh_cert_address; /* In */
+ u32 pdh_cert_len; /* In/Out */
+ u32 reserved; /* In */
+ u64 cert_chain_address; /* In */
+ u32 cert_chain_len; /* In/Out */
+} __packed;
+
+/**
+ * struct sev_data_decommission - DECOMMISSION command parameters
+ *
+ * @handle: handle of the VM to decommission
+ */
+struct sev_data_decommission {
+ u32 handle; /* In */
+} __packed;
+
+/**
+ * struct sev_data_activate - ACTIVATE command parameters
+ *
+ * @handle: handle of the VM to activate
+ * @asid: asid assigned to the VM
+ */
+struct sev_data_activate {
+ u32 handle; /* In */
+ u32 asid; /* In */
+} __packed;
+
+/**
+ * struct sev_data_deactivate - DEACTIVATE command parameters
+ *
+ * @handle: handle of the VM to deactivate
+ */
+struct sev_data_deactivate {
+ u32 handle; /* In */
+} __packed;
+
+/**
+ * struct sev_data_guest_status - SEV GUEST_STATUS command parameters
+ *
+ * @handle: handle of the VM to retrieve status
+ * @policy: policy information for the VM
+ * @asid: current ASID of the VM
+ * @state: current state of the VM
+ */
+struct sev_data_guest_status {
+ u32 handle; /* In */
+ u32 policy; /* Out */
+ u32 asid; /* Out */
+ u8 state; /* Out */
+} __packed;
+
+/**
+ * struct sev_data_launch_start - LAUNCH_START command parameters
+ *
+ * @handle: handle assigned to the VM
+ * @policy: guest launch policy
+ * @dh_cert_address: physical address of DH certificate blob
+ * @dh_cert_len: len of DH certificate blob
+ * @session_address: physical address of session parameters
+ * @session_len: len of session parameters
+ */
+struct sev_data_launch_start {
+ u32 handle; /* In/Out */
+ u32 policy; /* In */
+ u64 dh_cert_address; /* In */
+ u32 dh_cert_len; /* In */
+ u32 reserved; /* In */
+ u64 session_address; /* In */
+ u32 session_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_launch_update_data - LAUNCH_UPDATE_DATA command parameter
+ *
+ * @handle: handle of the VM to update
+ * @len: len of memory to be encrypted
+ * @address: physical address of memory region to encrypt
+ */
+struct sev_data_launch_update_data {
+ u32 handle; /* In */
+ u32 reserved;
+ u64 address; /* In */
+ u32 len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_launch_update_vmsa - LAUNCH_UPDATE_VMSA command
+ *
+ * @handle: handle of the VM
+ * @address: physical address of memory region to encrypt
+ * @len: len of memory region to encrypt
+ */
+struct sev_data_launch_update_vmsa {
+ u32 handle; /* In */
+ u32 reserved;
+ u64 address; /* In */
+ u32 len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_launch_measure - LAUNCH_MEASURE command parameters
+ *
+ * @handle: handle of the VM to process
+ * @address: physical address containing the measurement blob
+ * @len: len of measurement blob
+ */
+struct sev_data_launch_measure {
+ u32 handle; /* In */
+ u32 reserved;
+ u64 address; /* In */
+ u32 len; /* In/Out */
+} __packed;
+
+/**
+ * struct sev_data_launch_secret - LAUNCH_SECRET command parameters
+ *
+ * @handle: handle of the VM to process
+ * @hdr_address: physical address containing the packet header
+ * @hdr_len: len of packet header
+ * @guest_address: system physical address of guest memory region
+ * @guest_len: len of guest_paddr
+ * @trans_address: physical address of transport memory buffer
+ * @trans_len: len of transport memory buffer
+ */
+struct sev_data_launch_secret {
+ u32 handle; /* In */
+ u32 reserved1;
+ u64 hdr_address; /* In */
+ u32 hdr_len; /* In */
+ u32 reserved2;
+ u64 guest_address; /* In */
+ u32 guest_len; /* In */
+ u32 reserved3;
+ u64 trans_address; /* In */
+ u32 trans_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_launch_finish - LAUNCH_FINISH command parameters
+ *
+ * @handle: handle of the VM to process
+ */
+struct sev_data_launch_finish {
+ u32 handle; /* In */
+} __packed;
+
+/**
+ * struct sev_data_send_start - SEND_START command parameters
+ *
+ * @handle: handle of the VM to process
+ * @policy: policy information for the VM
+ * @pdh_cert_address: physical address containing PDH certificate
+ * @pdh_cert_len: len of PDH certificate
+ * @plat_certs_address: physical address containing platform certificate
+ * @plat_certs_len: len of platform certificate
+ * @amd_certs_address: physical address containing AMD certificate
+ * @amd_certs_len: len of AMD certificate
+ * @session_address: physical address containing Session data
+ * @session_len: len of session data
+ */
+struct sev_data_send_start {
+ u32 handle; /* In */
+ u32 policy; /* Out */
+ u64 pdh_cert_address; /* In */
+ u32 pdh_cert_len; /* In */
+ u32 reserved1;
+ u64 plat_cert_address; /* In */
+ u32 plat_cert_len; /* In */
+ u32 reserved2;
+ u64 amd_cert_address; /* In */
+ u32 amd_cert_len; /* In */
+ u32 reserved3;
+ u64 session_address; /* In */
+ u32 session_len; /* In/Out */
+} __packed;
+
+/**
+ * struct sev_data_send_update - SEND_UPDATE_DATA command
+ *
+ * @handle: handle of the VM to process
+ * @hdr_address: physical address containing packet header
+ * @hdr_len: len of packet header
+ * @guest_address: physical address of guest memory region to send
+ * @guest_len: len of guest memory region to send
+ * @trans_address: physical address of host memory region
+ * @trans_len: len of host memory region
+ */
+struct sev_data_send_update_data {
+ u32 handle; /* In */
+ u32 reserved1;
+ u64 hdr_address; /* In */
+ u32 hdr_len; /* In/Out */
+ u32 reserved2;
+ u64 guest_address; /* In */
+ u32 guest_len; /* In */
+ u32 reserved3;
+ u64 trans_address; /* In */
+ u32 trans_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_send_update - SEND_UPDATE_VMSA command
+ *
+ * @handle: handle of the VM to process
+ * @hdr_address: physical address containing packet header
+ * @hdr_len: len of packet header
+ * @guest_address: physical address of guest memory region to send
+ * @guest_len: len of guest memory region to send
+ * @trans_address: physical address of host memory region
+ * @trans_len: len of host memory region
+ */
+struct sev_data_send_update_vmsa {
+ u32 handle; /* In */
+ u64 hdr_address; /* In */
+ u32 hdr_len; /* In/Out */
+ u32 reserved2;
+ u64 guest_address; /* In */
+ u32 guest_len; /* In */
+ u32 reserved3;
+ u64 trans_address; /* In */
+ u32 trans_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_send_finish - SEND_FINISH command parameters
+ *
+ * @handle: handle of the VM to process
+ */
+struct sev_data_send_finish {
+ u32 handle; /* In */
+} __packed;
+
+/**
+ * struct sev_data_receive_start - RECEIVE_START command parameters
+ *
+ * @handle: handle of the VM to perform receive operation
+ * @pdh_cert_address: system physical address containing PDH certificate blob
+ * @pdh_cert_len: len of PDH certificate blob
+ * @session_address: system physical address containing session blob
+ * @session_len: len of session blob
+ */
+struct sev_data_receive_start {
+ u32 handle; /* In/Out */
+ u32 policy; /* In */
+ u64 pdh_cert_address; /* In */
+ u32 pdh_cert_len; /* In */
+ u32 reserved1;
+ u64 session_address; /* In */
+ u32 session_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_receive_update_data - RECEIVE_UPDATE_DATA command parameters
+ *
+ * @handle: handle of the VM to update
+ * @hdr_address: physical address containing packet header blob
+ * @hdr_len: len of packet header
+ * @guest_address: system physical address of guest memory region
+ * @guest_len: len of guest memory region
+ * @trans_address: system physical address of transport buffer
+ * @trans_len: len of transport buffer
+ */
+struct sev_data_receive_update_data {
+ u32 handle; /* In */
+ u32 reserved1;
+ u64 hdr_address; /* In */
+ u32 hdr_len; /* In */
+ u32 reserved2;
+ u64 guest_address; /* In */
+ u32 guest_len; /* In */
+ u32 reserved3;
+ u64 trans_address; /* In */
+ u32 trans_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_receive_update_vmsa - RECEIVE_UPDATE_VMSA command parameters
+ *
+ * @handle: handle of the VM to update
+ * @hdr_address: physical address containing packet header blob
+ * @hdr_len: len of packet header
+ * @guest_address: system physical address of guest memory region
+ * @guest_len: len of guest memory region
+ * @trans_address: system physical address of transport buffer
+ * @trans_len: len of transport buffer
+ */
+struct sev_data_receive_update_vmsa {
+ u32 handle; /* In */
+ u32 reserved1;
+ u64 hdr_address; /* In */
+ u32 hdr_len; /* In */
+ u32 reserved2;
+ u64 guest_address; /* In */
+ u32 guest_len; /* In */
+ u32 reserved3;
+ u64 trans_address; /* In */
+ u32 trans_len; /* In */
+} __packed;
+
+/**
+ * struct sev_data_receive_finish - RECEIVE_FINISH command parameters
+ *
+ * @handle: handle of the VM to finish
+ */
+struct sev_data_receive_finish {
+ u32 handle; /* In */
+} __packed;
+
+/**
+ * struct sev_data_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters
+ *
+ * @handle: handle of the VM to perform debug operation
+ * @src_addr: source address of data to operate on
+ * @dst_addr: destination address of data to operate on
+ * @len: len of data to operate on
+ */
+struct sev_data_dbg {
+ u32 handle; /* In */
+ u32 reserved;
+ u64 src_addr; /* In */
+ u64 dst_addr; /* In */
+ u32 len; /* In */
+} __packed;
+
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+
+/**
+ * sev_platform_init - perform SEV INIT command
+ *
+ * @error: SEV command return code
+ *
+ * Returns:
+ * 0 if the SEV successfully processed the command
+ * -%ENODEV if the SEV device is not available
+ * -%ENOTSUPP if the SEV does not support SEV
+ * -%ETIMEDOUT if the SEV command timed out
+ * -%EIO if the SEV returned a non-zero return code
+ */
+int sev_platform_init(int *error);
+
+/**
+ * sev_platform_status - perform SEV PLATFORM_STATUS command
+ *
+ * @status: sev_user_data_status structure to be processed
+ * @error: SEV command return code
+ *
+ * Returns:
+ * 0 if the SEV successfully processed the command
+ * -%ENODEV if the SEV device is not available
+ * -%ENOTSUPP if the SEV does not support SEV
+ * -%ETIMEDOUT if the SEV command timed out
+ * -%EIO if the SEV returned a non-zero return code
+ */
+int sev_platform_status(struct sev_user_data_status *status, int *error);
+
+/**
+ * sev_issue_cmd_external_user - issue SEV command by other driver with a file
+ * handle.
+ *
+ * This function can be used by other drivers to issue a SEV command on
+ * behalf of userspace. The caller must pass a valid SEV file descriptor
+ * so that we know that it has access to SEV device.
+ *
+ * @filep - SEV device file pointer
+ * @cmd - command to issue
+ * @data - command buffer
+ * @error: SEV command return code
+ *
+ * Returns:
+ * 0 if the SEV successfully processed the command
+ * -%ENODEV if the SEV device is not available
+ * -%ENOTSUPP if the SEV does not support SEV
+ * -%ETIMEDOUT if the SEV command timed out
+ * -%EIO if the SEV returned a non-zero return code
+ * -%EINVAL if the SEV file descriptor is not valid
+ */
+int sev_issue_cmd_external_user(struct file *filep, unsigned int id,
+ void *data, int *error);
+
+/**
+ * sev_guest_deactivate - perform SEV DEACTIVATE command
+ *
+ * @deactivate: sev_data_deactivate structure to be processed
+ * @sev_ret: sev command return code
+ *
+ * Returns:
+ * 0 if the sev successfully processed the command
+ * -%ENODEV if the sev device is not available
+ * -%ENOTSUPP if the sev does not support SEV
+ * -%ETIMEDOUT if the sev command timed out
+ * -%EIO if the sev returned a non-zero return code
+ */
+int sev_guest_deactivate(struct sev_data_deactivate *data, int *error);
+
+/**
+ * sev_guest_activate - perform SEV ACTIVATE command
+ *
+ * @activate: sev_data_activate structure to be processed
+ * @sev_ret: sev command return code
+ *
+ * Returns:
+ * 0 if the sev successfully processed the command
+ * -%ENODEV if the sev device is not available
+ * -%ENOTSUPP if the sev does not support SEV
+ * -%ETIMEDOUT if the sev command timed out
+ * -%EIO if the sev returned a non-zero return code
+ */
+int sev_guest_activate(struct sev_data_activate *data, int *error);
+
+/**
+ * sev_guest_df_flush - perform SEV DF_FLUSH command
+ *
+ * @sev_ret: sev command return code
+ *
+ * Returns:
+ * 0 if the sev successfully processed the command
+ * -%ENODEV if the sev device is not available
+ * -%ENOTSUPP if the sev does not support SEV
+ * -%ETIMEDOUT if the sev command timed out
+ * -%EIO if the sev returned a non-zero return code
+ */
+int sev_guest_df_flush(int *error);
+
+/**
+ * sev_guest_decommission - perform SEV DECOMMISSION command
+ *
+ * @decommission: sev_data_decommission structure to be processed
+ * @sev_ret: sev command return code
+ *
+ * Returns:
+ * 0 if the sev successfully processed the command
+ * -%ENODEV if the sev device is not available
+ * -%ENOTSUPP if the sev does not support SEV
+ * -%ETIMEDOUT if the sev command timed out
+ * -%EIO if the sev returned a non-zero return code
+ */
+int sev_guest_decommission(struct sev_data_decommission *data, int *error);
+
+void *psp_copy_user_blob(u64 __user uaddr, u32 len);
+
+#else /* !CONFIG_CRYPTO_DEV_SP_PSP */
+
+static inline int
+sev_platform_status(struct sev_user_data_status *status, int *error) { return -ENODEV; }
+
+static inline int sev_platform_init(int *error) { return -ENODEV; }
+
+static inline int
+sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENODEV; }
+
+static inline int
+sev_guest_decommission(struct sev_data_decommission *data, int *error) { return -ENODEV; }
+
+static inline int
+sev_guest_activate(struct sev_data_activate *data, int *error) { return -ENODEV; }
+
+static inline int sev_guest_df_flush(int *error) { return -ENODEV; }
+
+static inline int
+sev_issue_cmd_external_user(struct file *filep, unsigned int id, void *data, int *error) { return -ENODEV; }
+
+static inline void *psp_copy_user_blob(u64 __user uaddr, u32 len) { return ERR_PTR(-EINVAL); }
+
+#endif /* CONFIG_CRYPTO_DEV_SP_PSP */
+
+#endif /* __PSP_SEV_H__ */
__PTR_RING_PEEK_CALL_v; \
})
+/* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See
+ * documentation for vmalloc for which of them are legal.
+ */
static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp)
{
- return kcalloc(size, sizeof(void *), gfp);
+ if (size * sizeof(void *) > KMALLOC_MAX_SIZE)
+ return NULL;
+ return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO);
}
static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
spin_unlock(&(r)->producer_lock);
spin_unlock_irqrestore(&(r)->consumer_lock, flags);
- kfree(old);
+ kvfree(old);
return 0;
}
}
for (i = 0; i < nrings; ++i)
- kfree(queues[i]);
+ kvfree(queues[i]);
kfree(queues);
nomem:
while (--i >= 0)
- kfree(queues[i]);
+ kvfree(queues[i]);
kfree(queues);
if (destroy)
while ((ptr = ptr_ring_consume(r)))
destroy(ptr);
- kfree(r->queue);
+ kvfree(r->queue);
}
#endif /* _LINUX_PTR_RING_H */
int radix_tree_join(struct radix_tree_root *, unsigned long index,
unsigned new_order, void *);
-void __rcu **idr_get_free_cmn(struct radix_tree_root *root,
+void __rcu **idr_get_free(struct radix_tree_root *root,
struct radix_tree_iter *iter, gfp_t gfp,
unsigned long max);
-static inline void __rcu **idr_get_free(struct radix_tree_root *root,
- struct radix_tree_iter *iter,
- gfp_t gfp,
- int end)
-{
- return idr_get_free_cmn(root, iter, gfp, end > 0 ? end - 1 : INT_MAX);
-}
-
-static inline void __rcu **idr_get_free_ext(struct radix_tree_root *root,
- struct radix_tree_iter *iter,
- gfp_t gfp,
- unsigned long end)
-{
- return idr_get_free_cmn(root, iter, gfp, end - 1);
-}
enum {
RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */
* events is a bitmask specifying the events which the application is
* interested in. The field revents is an output parameter, filled by the
* kernel with the events that actually occurred. The bits returned in revents
- * can include any of those specified in events, or one of the values POLLERR,
- * POLLHUP, or POLLNVAL. (These three bits are meaningless in the events
+ * can include any of those specified in events, or one of the values EPOLLERR,
+ * EPOLLHUP, or EPOLLNVAL. (These three bits are meaningless in the events
* field, and will be set in the revents field whenever the corresponding
* condition is true.)
*
* timeout means an infinite timeout.
*
* The following bits may be set in events and returned in revents.
- * POLLIN - Data may be received without blocking. For a connected
+ * EPOLLIN - Data may be received without blocking. For a connected
* endpoint, this means that scif_recv() may be called without blocking. For a
* listening endpoint, this means that scif_accept() may be called without
* blocking.
- * POLLOUT - Data may be sent without blocking. For a connected endpoint, this
- * means that scif_send() may be called without blocking. POLLOUT may also be
+ * EPOLLOUT - Data may be sent without blocking. For a connected endpoint, this
+ * means that scif_send() may be called without blocking. EPOLLOUT may also be
* used to block waiting for a non-blocking connect to complete. This bit value
* has no meaning for a listening endpoint and is ignored if specified.
*
* The following bits are only returned in revents, and are ignored if set in
* events.
- * POLLERR - An error occurred on the endpoint
- * POLLHUP - The connection to the peer endpoint was disconnected
- * POLLNVAL - The specified endpoint descriptor is invalid.
+ * EPOLLERR - An error occurred on the endpoint
+ * EPOLLHUP - The connection to the peer endpoint was disconnected
+ * EPOLLNVAL - The specified endpoint descriptor is invalid.
*
* Return:
* Upon successful completion, scif_poll() returns a non-negative value. A
const char *options);
#ifdef CONFIG_SERIAL_EARLYCON
-extern bool earlycon_init_is_deferred __initdata;
+extern bool earlycon_acpi_spcr_enable __initdata;
int setup_earlycon(char *buf);
#else
-static const bool earlycon_init_is_deferred;
+static const bool earlycon_acpi_spcr_enable;
static inline int setup_earlycon(char *buf) { return 0; }
#endif
struct rpc_task *,
rpc_action action,
int priority);
+void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq,
+ struct rpc_wait_queue *queue,
+ struct rpc_task *task);
void rpc_wake_up_queued_task(struct rpc_wait_queue *,
struct rpc_task *);
void rpc_wake_up(struct rpc_wait_queue *);
extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *);
extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *);
extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
-extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t);
-extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t);
extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
* @fileio_read_once: report EOF after reading the first buffer
* @fileio_write_immediately: queue buffer after each write() call
* @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver
- * @quirk_poll_must_check_waiting_for_buffers: Return %POLLERR at poll when QBUF
+ * @quirk_poll_must_check_waiting_for_buffers: Return %EPOLLERR at poll when QBUF
* has not been called. This is a vb1 idiom that has been adopted
* also by vb2.
* @lock: pointer to a mutex that protects the &struct vb2_queue. The
* @error: a fatal error occurred on the queue
* @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
* buffers. Only set for capture queues if qbuf has not yet been
- * called since poll() needs to return %POLLERR in that situation.
+ * called since poll() needs to return %EPOLLERR in that situation.
* @is_multiplanar: set if buffer type is multiplanar
* @is_output: set if buffer type is output
* @copy_timestamp: set if vb2-core should set timestamps
* @q: pointer to &struct vb2_queue with videobuf2 queue.
*
* Flag that a fatal unrecoverable error has occurred and wake up all processes
- * waiting on the queue. Polling will now set %POLLERR and queuing and dequeuing
+ * waiting on the queue. Polling will now set %EPOLLERR and queuing and dequeuing
* buffers will return %-EIO.
*
* The error flag will be cleared when canceling the queue, either from
static inline __poll_t inet_csk_listen_poll(const struct sock *sk)
{
return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
- (POLLIN | POLLRDNORM) : 0;
+ (EPOLLIN | EPOLLRDNORM) : 0;
}
int inet_csk_listen_start(struct sock *sk, int backlog);
return nf_ct_delete(ct, 0, 0);
}
-/* These are for NAT. Icky. */
-extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
- enum ip_conntrack_dir dir,
- u32 seq);
-
/* Set all unconfirmed conntrack as dying */
void nf_ct_unconfirmed_destroy(struct net *);
struct list_head list;
int family;
void (*gc)(struct work_struct *work);
+ void (*free)(struct nf_flowtable *ft);
const struct rhashtable_params *params;
nf_hookfn *hook;
struct module *owner;
void flow_offload_free(struct flow_offload *flow);
int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
-void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow);
struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table,
struct flow_offload_tuple *tuple);
int nf_flow_table_iterate(struct nf_flowtable *flow_table,
void (*iter)(struct flow_offload *flow, void *data),
void *data);
+
+void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
+
+void nf_flow_table_free(struct nf_flowtable *flow_table);
void nf_flow_offload_work_gc(struct work_struct *work);
extern const struct rhashtable_params nf_flow_offload_rhash_params;
#define TCP_ULP_MAX 128
#define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX)
+enum {
+ TCP_ULP_TLS,
+ TCP_ULP_BPF,
+};
+
struct tcp_ulp_ops {
struct list_head list;
/* cleanup ulp */
void (*release)(struct sock *sk);
+ int uid;
char name[TCP_ULP_NAME_MAX];
+ bool user_visible;
struct module *owner;
};
int tcp_register_ulp(struct tcp_ulp_ops *type);
void tcp_unregister_ulp(struct tcp_ulp_ops *type);
int tcp_set_ulp(struct sock *sk, const char *name);
+int tcp_set_ulp_id(struct sock *sk, const int ulp);
void tcp_get_available_ulp(char *buf, size_t len);
void tcp_cleanup_ulp(struct sock *sk);
void (*free_prot)(struct se_device *);
struct configfs_attribute **tb_dev_attrib_attrs;
+ struct configfs_attribute **tb_dev_action_attrs;
};
struct sbc_ops {
TCM_TOO_MANY_SEGMENT_DESCS = R(0x1b),
TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE = R(0x1c),
TCM_INSUFFICIENT_REGISTRATION_RESOURCES = R(0x1d),
+ TCM_LUN_BUSY = R(0x1e),
#undef R
};
/* T10 SPC-2 + SPC-3 Reservations */
struct t10_reservation t10_pr;
struct se_dev_attrib dev_attrib;
+ struct config_group dev_action_group;
struct config_group dev_group;
struct config_group dev_pr_group;
struct se_dev_stat_grps dev_stat_grps;
#define __ASM_GENERIC_POLL_H
/* These are specified by iBCS2 */
-#define POLLIN (__force __poll_t)0x0001
-#define POLLPRI (__force __poll_t)0x0002
-#define POLLOUT (__force __poll_t)0x0004
-#define POLLERR (__force __poll_t)0x0008
-#define POLLHUP (__force __poll_t)0x0010
-#define POLLNVAL (__force __poll_t)0x0020
+#define POLLIN 0x0001
+#define POLLPRI 0x0002
+#define POLLOUT 0x0004
+#define POLLERR 0x0008
+#define POLLHUP 0x0010
+#define POLLNVAL 0x0020
/* The rest seem to be more-or-less nonstandard. Check them! */
-#define POLLRDNORM (__force __poll_t)0x0040
-#define POLLRDBAND (__force __poll_t)0x0080
+#define POLLRDNORM 0x0040
+#define POLLRDBAND 0x0080
#ifndef POLLWRNORM
-#define POLLWRNORM (__force __poll_t)0x0100
+#define POLLWRNORM 0x0100
#endif
#ifndef POLLWRBAND
-#define POLLWRBAND (__force __poll_t)0x0200
+#define POLLWRBAND 0x0200
#endif
#ifndef POLLMSG
-#define POLLMSG (__force __poll_t)0x0400
+#define POLLMSG 0x0400
#endif
#ifndef POLLREMOVE
-#define POLLREMOVE (__force __poll_t)0x1000
+#define POLLREMOVE 0x1000
#endif
#ifndef POLLRDHUP
-#define POLLRDHUP (__force __poll_t)0x2000
+#define POLLRDHUP 0x2000
#endif
#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */
#define POLL_BUSY_LOOP (__force __poll_t)0x8000
-#ifdef __KERNEL__
-#ifndef __ARCH_HAS_MANGLED_POLL
-static inline __u16 mangle_poll(__poll_t val)
-{
- return (__force __u16)val;
-}
-
-static inline __poll_t demangle_poll(__u16 v)
-{
- return (__force __poll_t)v;
-}
-#endif
-#endif
-
struct pollfd {
int fd;
short events;
#define EPOLL_CTL_MOD 3
/* Epoll event masks */
-#define EPOLLIN 0x00000001
-#define EPOLLPRI 0x00000002
-#define EPOLLOUT 0x00000004
-#define EPOLLERR 0x00000008
-#define EPOLLHUP 0x00000010
-#define EPOLLRDNORM 0x00000040
-#define EPOLLRDBAND 0x00000080
-#define EPOLLWRNORM 0x00000100
-#define EPOLLWRBAND 0x00000200
-#define EPOLLMSG 0x00000400
-#define EPOLLRDHUP 0x00002000
+#define EPOLLIN (__force __poll_t)0x00000001
+#define EPOLLPRI (__force __poll_t)0x00000002
+#define EPOLLOUT (__force __poll_t)0x00000004
+#define EPOLLERR (__force __poll_t)0x00000008
+#define EPOLLHUP (__force __poll_t)0x00000010
+#define EPOLLNVAL (__force __poll_t)0x00000020
+#define EPOLLRDNORM (__force __poll_t)0x00000040
+#define EPOLLRDBAND (__force __poll_t)0x00000080
+#define EPOLLWRNORM (__force __poll_t)0x00000100
+#define EPOLLWRBAND (__force __poll_t)0x00000200
+#define EPOLLMSG (__force __poll_t)0x00000400
+#define EPOLLRDHUP (__force __poll_t)0x00002000
/* Set exclusive wakeup mode for the target file descriptor */
-#define EPOLLEXCLUSIVE (1U << 28)
+#define EPOLLEXCLUSIVE (__force __poll_t)(1U << 28)
/*
* Request the handling of system wakeup events so as to prevent system suspends
*
* Requires CAP_BLOCK_SUSPEND
*/
-#define EPOLLWAKEUP (1U << 29)
+#define EPOLLWAKEUP (__force __poll_t)(1U << 29)
/* Set the One Shot behaviour for the target file descriptor */
-#define EPOLLONESHOT (1U << 30)
+#define EPOLLONESHOT (__force __poll_t)(1U << 30)
/* Set the Edge Triggered behaviour for the target file descriptor */
-#define EPOLLET (1U << 31)
+#define EPOLLET (__force __poll_t)(1U << 31)
/*
* On x86-64 make the 64bit structure have the same alignment as the
#endif
struct epoll_event {
- __u32 events;
+ __poll_t events;
__u64 data;
} EPOLL_PACKED;
/* Available with KVM_CAP_S390_CMMA_MIGRATION */
#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
#define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+/* Memory Encryption Commands */
+#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long)
+
+struct kvm_enc_region {
+ __u64 addr;
+ __u64 size;
+};
+
+#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region)
+#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+ /* Guest initialization commands */
+ KVM_SEV_INIT = 0,
+ KVM_SEV_ES_INIT,
+ /* Guest launch commands */
+ KVM_SEV_LAUNCH_START,
+ KVM_SEV_LAUNCH_UPDATE_DATA,
+ KVM_SEV_LAUNCH_UPDATE_VMSA,
+ KVM_SEV_LAUNCH_SECRET,
+ KVM_SEV_LAUNCH_MEASURE,
+ KVM_SEV_LAUNCH_FINISH,
+ /* Guest migration commands (outgoing) */
+ KVM_SEV_SEND_START,
+ KVM_SEV_SEND_UPDATE_DATA,
+ KVM_SEV_SEND_UPDATE_VMSA,
+ KVM_SEV_SEND_FINISH,
+ /* Guest migration commands (incoming) */
+ KVM_SEV_RECEIVE_START,
+ KVM_SEV_RECEIVE_UPDATE_DATA,
+ KVM_SEV_RECEIVE_UPDATE_VMSA,
+ KVM_SEV_RECEIVE_FINISH,
+ /* Guest status and debug commands */
+ KVM_SEV_GUEST_STATUS,
+ KVM_SEV_DBG_DECRYPT,
+ KVM_SEV_DBG_ENCRYPT,
+ /* Guest certificates commands */
+ KVM_SEV_CERT_EXPORT,
+
+ KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+ __u32 id;
+ __u64 data;
+ __u32 error;
+ __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 dh_uaddr;
+ __u32 dh_len;
+ __u64 session_uaddr;
+ __u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+ __u64 uaddr;
+ __u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+ __u64 uaddr;
+ __u32 len;
+};
+
+struct kvm_sev_guest_status {
+ __u32 handle;
+ __u32 policy;
+ __u32 state;
+};
+
+struct kvm_sev_dbg {
+ __u64 src_uaddr;
+ __u64 dst_uaddr;
+ __u32 len;
+};
#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
(((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
#define PSCI_VERSION_MINOR(ver) \
((ver) & PSCI_VERSION_MINOR_MASK)
+#define PSCI_VERSION(maj, min) \
+ ((((maj) << PSCI_VERSION_MAJOR_SHIFT) & PSCI_VERSION_MAJOR_MASK) | \
+ ((min) & PSCI_VERSION_MINOR_MASK))
/* PSCI features decoding (>=1.0) */
#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT 1
--- /dev/null
+/*
+ * Userspace interface for AMD Secure Encrypted Virtualization (SEV)
+ * platform management commands.
+ *
+ * Copyright (C) 2016-2017 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * SEV spec 0.14 is available at:
+ * http://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __PSP_SEV_USER_H__
+#define __PSP_SEV_USER_H__
+
+#include <linux/types.h>
+
+/**
+ * SEV platform commands
+ */
+enum {
+ SEV_FACTORY_RESET = 0,
+ SEV_PLATFORM_STATUS,
+ SEV_PEK_GEN,
+ SEV_PEK_CSR,
+ SEV_PDH_GEN,
+ SEV_PDH_CERT_EXPORT,
+ SEV_PEK_CERT_IMPORT,
+
+ SEV_MAX,
+};
+
+/**
+ * SEV Firmware status code
+ */
+typedef enum {
+ SEV_RET_SUCCESS = 0,
+ SEV_RET_INVALID_PLATFORM_STATE,
+ SEV_RET_INVALID_GUEST_STATE,
+ SEV_RET_INAVLID_CONFIG,
+ SEV_RET_INVALID_len,
+ SEV_RET_ALREADY_OWNED,
+ SEV_RET_INVALID_CERTIFICATE,
+ SEV_RET_POLICY_FAILURE,
+ SEV_RET_INACTIVE,
+ SEV_RET_INVALID_ADDRESS,
+ SEV_RET_BAD_SIGNATURE,
+ SEV_RET_BAD_MEASUREMENT,
+ SEV_RET_ASID_OWNED,
+ SEV_RET_INVALID_ASID,
+ SEV_RET_WBINVD_REQUIRED,
+ SEV_RET_DFFLUSH_REQUIRED,
+ SEV_RET_INVALID_GUEST,
+ SEV_RET_INVALID_COMMAND,
+ SEV_RET_ACTIVE,
+ SEV_RET_HWSEV_RET_PLATFORM,
+ SEV_RET_HWSEV_RET_UNSAFE,
+ SEV_RET_UNSUPPORTED,
+ SEV_RET_MAX,
+} sev_ret_code;
+
+/**
+ * struct sev_user_data_status - PLATFORM_STATUS command parameters
+ *
+ * @major: major API version
+ * @minor: minor API version
+ * @state: platform state
+ * @flags: platform config flags
+ * @build: firmware build id for API version
+ * @guest_count: number of active guests
+ */
+struct sev_user_data_status {
+ __u8 api_major; /* Out */
+ __u8 api_minor; /* Out */
+ __u8 state; /* Out */
+ __u32 flags; /* Out */
+ __u8 build; /* Out */
+ __u32 guest_count; /* Out */
+} __packed;
+
+/**
+ * struct sev_user_data_pek_csr - PEK_CSR command parameters
+ *
+ * @address: PEK certificate chain
+ * @length: length of certificate
+ */
+struct sev_user_data_pek_csr {
+ __u64 address; /* In */
+ __u32 length; /* In/Out */
+} __packed;
+
+/**
+ * struct sev_user_data_cert_import - PEK_CERT_IMPORT command parameters
+ *
+ * @pek_address: PEK certificate chain
+ * @pek_len: length of PEK certificate
+ * @oca_address: OCA certificate chain
+ * @oca_len: length of OCA certificate
+ */
+struct sev_user_data_pek_cert_import {
+ __u64 pek_cert_address; /* In */
+ __u32 pek_cert_len; /* In */
+ __u64 oca_cert_address; /* In */
+ __u32 oca_cert_len; /* In */
+} __packed;
+
+/**
+ * struct sev_user_data_pdh_cert_export - PDH_CERT_EXPORT command parameters
+ *
+ * @pdh_address: PDH certificate address
+ * @pdh_len: length of PDH certificate
+ * @cert_chain_address: PDH certificate chain
+ * @cert_chain_len: length of PDH certificate chain
+ */
+struct sev_user_data_pdh_cert_export {
+ __u64 pdh_cert_address; /* In */
+ __u32 pdh_cert_len; /* In/Out */
+ __u64 cert_chain_address; /* In */
+ __u32 cert_chain_len; /* In/Out */
+} __packed;
+
+/**
+ * struct sev_issue_cmd - SEV ioctl parameters
+ *
+ * @cmd: SEV commands to execute
+ * @opaque: pointer to the command structure
+ * @error: SEV FW return code on failure
+ */
+struct sev_issue_cmd {
+ __u32 cmd; /* In */
+ __u64 data; /* In */
+ __u32 error; /* Out */
+} __packed;
+
+#define SEV_IOC_TYPE 'S'
+#define SEV_ISSUE_CMD _IOWR(SEV_IOC_TYPE, 0x0, struct sev_issue_cmd)
+
+#endif /* __PSP_USER_SEV_H */
#define VIRTIO_BALLOON_S_MEMFREE 4 /* Total amount of free memory */
#define VIRTIO_BALLOON_S_MEMTOT 5 /* Total amount of memory */
#define VIRTIO_BALLOON_S_AVAIL 6 /* Available memory as in /proc */
-#define VIRTIO_BALLOON_S_NR 7
+#define VIRTIO_BALLOON_S_CACHES 7 /* Disk caches */
+#define VIRTIO_BALLOON_S_NR 8
/*
* Memory statistics structure.
spin_lock(&info->lock);
if (info->attr.mq_curmsgs)
- retval = POLLIN | POLLRDNORM;
+ retval = EPOLLIN | EPOLLRDNORM;
if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
- retval |= POLLOUT | POLLWRNORM;
+ retval |= EPOLLOUT | EPOLLWRNORM;
spin_unlock(&info->lock);
return retval;
struct work_struct tx_work;
struct work_struct gc_work;
+ struct proto *sk_proto;
+ void (*save_close)(struct sock *sk, long timeout);
void (*save_data_ready)(struct sock *sk);
void (*save_write_space)(struct sock *sk);
- void (*save_state_change)(struct sock *sk);
};
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
return rcu_dereference_sk_user_data(sk);
}
+static struct proto tcp_bpf_proto;
+static int bpf_tcp_init(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ if (unlikely(psock->sk_proto)) {
+ rcu_read_unlock();
+ return -EBUSY;
+ }
+
+ psock->save_close = sk->sk_prot->close;
+ psock->sk_proto = sk->sk_prot;
+ sk->sk_prot = &tcp_bpf_proto;
+ rcu_read_unlock();
+ return 0;
+}
+
+static void bpf_tcp_release(struct sock *sk)
+{
+ struct smap_psock *psock;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+
+ if (likely(psock)) {
+ sk->sk_prot = psock->sk_proto;
+ psock->sk_proto = NULL;
+ }
+ rcu_read_unlock();
+}
+
+static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
+
+static void bpf_tcp_close(struct sock *sk, long timeout)
+{
+ void (*close_fun)(struct sock *sk, long timeout);
+ struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock *psock;
+ struct sock *osk;
+
+ rcu_read_lock();
+ psock = smap_psock_sk(sk);
+ if (unlikely(!psock)) {
+ rcu_read_unlock();
+ return sk->sk_prot->close(sk, timeout);
+ }
+
+ /* The psock may be destroyed anytime after exiting the RCU critial
+ * section so by the time we use close_fun the psock may no longer
+ * be valid. However, bpf_tcp_close is called with the sock lock
+ * held so the close hook and sk are still valid.
+ */
+ close_fun = psock->save_close;
+
+ write_lock_bh(&sk->sk_callback_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ osk = cmpxchg(e->entry, sk, NULL);
+ if (osk == sk) {
+ list_del(&e->list);
+ smap_release_sock(psock, sk);
+ }
+ }
+ write_unlock_bh(&sk->sk_callback_lock);
+ rcu_read_unlock();
+ close_fun(sk, timeout);
+}
+
enum __sk_action {
__SK_DROP = 0,
__SK_PASS,
__SK_REDIRECT,
};
+static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = {
+ .name = "bpf_tcp",
+ .uid = TCP_ULP_BPF,
+ .user_visible = false,
+ .owner = NULL,
+ .init = bpf_tcp_init,
+ .release = bpf_tcp_release,
+};
+
+static int bpf_tcp_ulp_register(void)
+{
+ tcp_bpf_proto = tcp_prot;
+ tcp_bpf_proto.close = bpf_tcp_close;
+ return tcp_register_ulp(&bpf_tcp_ulp_ops);
+}
+
static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
{
struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
sk->sk_error_report(sk);
}
-static void smap_release_sock(struct smap_psock *psock, struct sock *sock);
-
-/* Called with lock_sock(sk) held */
-static void smap_state_change(struct sock *sk)
-{
- struct smap_psock_map_entry *e, *tmp;
- struct smap_psock *psock;
- struct socket_wq *wq;
- struct sock *osk;
-
- rcu_read_lock();
-
- /* Allowing transitions into an established syn_recv states allows
- * for early binding sockets to a smap object before the connection
- * is established.
- */
- switch (sk->sk_state) {
- case TCP_SYN_SENT:
- case TCP_SYN_RECV:
- case TCP_ESTABLISHED:
- break;
- case TCP_CLOSE_WAIT:
- case TCP_CLOSING:
- case TCP_LAST_ACK:
- case TCP_FIN_WAIT1:
- case TCP_FIN_WAIT2:
- case TCP_LISTEN:
- break;
- case TCP_CLOSE:
- /* Only release if the map entry is in fact the sock in
- * question. There is a case where the operator deletes
- * the sock from the map, but the TCP sock is closed before
- * the psock is detached. Use cmpxchg to verify correct
- * sock is removed.
- */
- psock = smap_psock_sk(sk);
- if (unlikely(!psock))
- break;
- write_lock_bh(&sk->sk_callback_lock);
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- osk = cmpxchg(e->entry, sk, NULL);
- if (osk == sk) {
- list_del(&e->list);
- smap_release_sock(psock, sk);
- }
- }
- write_unlock_bh(&sk->sk_callback_lock);
- break;
- default:
- psock = smap_psock_sk(sk);
- if (unlikely(!psock))
- break;
- smap_report_sk_error(psock, EPIPE);
- break;
- }
-
- wq = rcu_dereference(sk->sk_wq);
- if (skwq_has_sleeper(wq))
- wake_up_interruptible_all(&wq->wait);
- rcu_read_unlock();
-}
-
static void smap_read_sock_strparser(struct strparser *strp,
struct sk_buff *skb)
{
return;
sk->sk_data_ready = psock->save_data_ready;
sk->sk_write_space = psock->save_write_space;
- sk->sk_state_change = psock->save_state_change;
psock->save_data_ready = NULL;
psock->save_write_space = NULL;
- psock->save_state_change = NULL;
strp_stop(&psock->strp);
psock->strp_enabled = false;
}
if (psock->refcnt)
return;
+ tcp_cleanup_ulp(sock);
smap_stop_sock(psock, sock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
return;
psock->save_data_ready = sk->sk_data_ready;
psock->save_write_space = sk->sk_write_space;
- psock->save_state_change = sk->sk_state_change;
sk->sk_data_ready = smap_data_ready;
sk->sk_write_space = smap_write_space;
- sk->sk_state_change = smap_state_change;
psock->strp_enabled = true;
}
if (attr->value_size > KMALLOC_MAX_SIZE)
return ERR_PTR(-E2BIG);
+ err = bpf_tcp_ulp_register();
+ if (err && err != -EEXIST)
+ return ERR_PTR(err);
+
stab = kzalloc(sizeof(*stab), GFP_USER);
if (!stab)
return ERR_PTR(-ENOMEM);
}
rcu_read_unlock();
- if (stab->bpf_verdict)
- bpf_prog_put(stab->bpf_verdict);
- if (stab->bpf_parse)
- bpf_prog_put(stab->bpf_parse);
-
sock_map_remove_complete(stab);
}
goto out_progs;
}
+ err = tcp_set_ulp_id(sock, TCP_ULP_BPF);
+ if (err)
+ goto out_progs;
+
set_bit(SMAP_TX_RUNNING, &psock->state);
}
return err;
}
+static void sock_map_release(struct bpf_map *map, struct file *map_file)
+{
+ struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct bpf_prog *orig;
+
+ orig = xchg(&stab->bpf_parse, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+ orig = xchg(&stab->bpf_verdict, NULL);
+ if (orig)
+ bpf_prog_put(orig);
+}
+
const struct bpf_map_ops sock_map_ops = {
.map_alloc = sock_map_alloc,
.map_free = sock_map_free,
.map_get_next_key = sock_map_get_next_key,
.map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_map_delete_elem,
+ .map_release = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
CONFIG_KVM_GUEST=y
+CONFIG_S390_GUEST=y
CONFIG_VIRTIO=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_BLK=y
{
struct perf_event *event = file->private_data;
struct ring_buffer *rb;
- __poll_t events = POLLHUP;
+ __poll_t events = EPOLLHUP;
poll_wait(file, &event->waitq, wait);
static void perf_output_wakeup(struct perf_output_handle *handle)
{
- atomic_set(&handle->rb->poll, POLLIN);
+ atomic_set(&handle->rb->poll, EPOLLIN);
handle->event->pending_wakeup = 1;
irq_work_queue(&handle->event->pending);
__poll_t ret = 0;
if (!user)
- return POLLERR|POLLNVAL;
+ return EPOLLERR|EPOLLNVAL;
poll_wait(file, &log_wait, wait);
if (user->seq < log_next_seq) {
/* return error when data has vanished underneath us */
if (user->seq < log_first_seq)
- ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI;
+ ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI;
else
- ret = POLLIN|POLLRDNORM;
+ ret = EPOLLIN|EPOLLRDNORM;
}
logbuf_unlock_irq();
struct rchan_buf *buf = filp->private_data;
if (buf->finalized)
- return POLLERR;
+ return EPOLLERR;
if (filp->f_mode & FMODE_READ) {
poll_wait(filp, &buf->read_wait, wait);
if (!relay_buf_empty(buf))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
return mask;
__poll_t result = 0;
if (!clk)
- return POLLERR;
+ return EPOLLERR;
if (clk->ops.poll)
result = clk->ops.poll(clk, fp, wait);
func_g.type = filter_parse_regex(glob, strlen(glob),
&func_g.search, ¬);
func_g.len = strlen(func_g.search);
- func_g.search = glob;
/* we do not support '!' for function probes */
if (WARN_ON(not))
* as data is added to any of the @buffer's cpu buffers. Otherwise
* it will wait for data to be added to a specific cpu buffer.
*
- * Returns POLLIN | POLLRDNORM if data exists in the buffers,
+ * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers,
* zero otherwise.
*/
__poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
(cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
if (tr->trace_flags & TRACE_ITER_BLOCK)
/*
* Always select as readable when in blocking mode
*/
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
else
return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file,
filp, poll_table);
for (i = 0; i < len; i++) {
if (buff[i] == '*') {
if (!i) {
- *search = buff + 1;
type = MATCH_END_ONLY;
} else if (i == len - 1) {
if (type == MATCH_END_ONLY)
buff[i] = 0;
break;
} else { /* pattern continues, use full glob */
- type = MATCH_GLOB;
- break;
+ return MATCH_GLOB;
}
} else if (strchr("[?\\", buff[i])) {
- type = MATCH_GLOB;
- break;
+ return MATCH_GLOB;
}
}
+ if (buff[0] == '*')
+ *search = buff + 1;
return type;
}
#
config ARCH_WANT_FRAME_POINTERS
bool
- help
config FRAME_POINTER
bool "Compile the kernel with frame pointers"
#include <linux/bitmap.h>
+#include <linux/bug.h>
#include <linux/export.h>
#include <linux/idr.h>
#include <linux/slab.h>
DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap);
static DEFINE_SPINLOCK(simple_ida_lock);
-int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index,
- unsigned long start, unsigned long end, gfp_t gfp,
- bool ext)
+/**
+ * idr_alloc_u32() - Allocate an ID.
+ * @idr: IDR handle.
+ * @ptr: Pointer to be associated with the new ID.
+ * @nextid: Pointer to an ID.
+ * @max: The maximum ID to allocate (inclusive).
+ * @gfp: Memory allocation flags.
+ *
+ * Allocates an unused ID in the range specified by @nextid and @max.
+ * Note that @max is inclusive whereas the @end parameter to idr_alloc()
+ * is exclusive. The new ID is assigned to @nextid before the pointer
+ * is inserted into the IDR, so if @nextid points into the object pointed
+ * to by @ptr, a concurrent lookup will not find an uninitialised ID.
+ *
+ * The caller should provide their own locking to ensure that two
+ * concurrent modifications to the IDR are not possible. Read-only
+ * accesses to the IDR may be done under the RCU read lock or may
+ * exclude simultaneous writers.
+ *
+ * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed,
+ * or -ENOSPC if no free IDs could be found. If an error occurred,
+ * @nextid is unchanged.
+ */
+int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid,
+ unsigned long max, gfp_t gfp)
{
struct radix_tree_iter iter;
void __rcu **slot;
+ int base = idr->idr_base;
+ int id = *nextid;
if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
return -EINVAL;
+ if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR)))
+ idr->idr_rt.gfp_mask |= IDR_RT_MARKER;
- radix_tree_iter_init(&iter, start);
- if (ext)
- slot = idr_get_free_ext(&idr->idr_rt, &iter, gfp, end);
- else
- slot = idr_get_free(&idr->idr_rt, &iter, gfp, end);
+ id = (id < base) ? 0 : id - base;
+ radix_tree_iter_init(&iter, id);
+ slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base);
if (IS_ERR(slot))
return PTR_ERR(slot);
+ *nextid = iter.index + base;
+ /* there is a memory barrier inside radix_tree_iter_replace() */
radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr);
radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE);
- if (index)
- *index = iter.index;
return 0;
}
-EXPORT_SYMBOL_GPL(idr_alloc_cmn);
+EXPORT_SYMBOL_GPL(idr_alloc_u32);
/**
- * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion
- * @idr: idr handle
- * @ptr: pointer to be associated with the new id
- * @start: the minimum id (inclusive)
- * @end: the maximum id (exclusive)
- * @gfp: memory allocation flags
- *
- * Allocates an ID larger than the last ID allocated if one is available.
- * If not, it will attempt to allocate the smallest ID that is larger or
- * equal to @start.
+ * idr_alloc() - Allocate an ID.
+ * @idr: IDR handle.
+ * @ptr: Pointer to be associated with the new ID.
+ * @start: The minimum ID (inclusive).
+ * @end: The maximum ID (exclusive).
+ * @gfp: Memory allocation flags.
+ *
+ * Allocates an unused ID in the range specified by @start and @end. If
+ * @end is <= 0, it is treated as one larger than %INT_MAX. This allows
+ * callers to use @start + N as @end as long as N is within integer range.
+ *
+ * The caller should provide their own locking to ensure that two
+ * concurrent modifications to the IDR are not possible. Read-only
+ * accesses to the IDR may be done under the RCU read lock or may
+ * exclude simultaneous writers.
+ *
+ * Return: The newly allocated ID, -ENOMEM if memory allocation failed,
+ * or -ENOSPC if no free IDs could be found.
*/
-int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
+int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
{
- int id, curr = idr->idr_next;
+ u32 id = start;
+ int ret;
+
+ if (WARN_ON_ONCE(start < 0))
+ return -EINVAL;
+
+ ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp);
+ if (ret)
+ return ret;
+
+ return id;
+}
+EXPORT_SYMBOL_GPL(idr_alloc);
- if (curr < start)
- curr = start;
+/**
+ * idr_alloc_cyclic() - Allocate an ID cyclically.
+ * @idr: IDR handle.
+ * @ptr: Pointer to be associated with the new ID.
+ * @start: The minimum ID (inclusive).
+ * @end: The maximum ID (exclusive).
+ * @gfp: Memory allocation flags.
+ *
+ * Allocates an unused ID in the range specified by @nextid and @end. If
+ * @end is <= 0, it is treated as one larger than %INT_MAX. This allows
+ * callers to use @start + N as @end as long as N is within integer range.
+ * The search for an unused ID will start at the last ID allocated and will
+ * wrap around to @start if no free IDs are found before reaching @end.
+ *
+ * The caller should provide their own locking to ensure that two
+ * concurrent modifications to the IDR are not possible. Read-only
+ * accesses to the IDR may be done under the RCU read lock or may
+ * exclude simultaneous writers.
+ *
+ * Return: The newly allocated ID, -ENOMEM if memory allocation failed,
+ * or -ENOSPC if no free IDs could be found.
+ */
+int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp)
+{
+ u32 id = idr->idr_next;
+ int err, max = end > 0 ? end - 1 : INT_MAX;
- id = idr_alloc(idr, ptr, curr, end, gfp);
- if ((id == -ENOSPC) && (curr > start))
- id = idr_alloc(idr, ptr, start, curr, gfp);
+ if ((int)id < start)
+ id = start;
- if (id >= 0)
- idr->idr_next = id + 1U;
+ err = idr_alloc_u32(idr, ptr, &id, max, gfp);
+ if ((err == -ENOSPC) && (id > start)) {
+ id = start;
+ err = idr_alloc_u32(idr, ptr, &id, max, gfp);
+ }
+ if (err)
+ return err;
+ idr->idr_next = id + 1;
return id;
}
EXPORT_SYMBOL(idr_alloc_cyclic);
/**
- * idr_for_each - iterate through all stored pointers
- * @idr: idr handle
- * @fn: function to be called for each pointer
- * @data: data passed to callback function
+ * idr_remove() - Remove an ID from the IDR.
+ * @idr: IDR handle.
+ * @id: Pointer ID.
+ *
+ * Removes this ID from the IDR. If the ID was not previously in the IDR,
+ * this function returns %NULL.
+ *
+ * Since this function modifies the IDR, the caller should provide their
+ * own locking to ensure that concurrent modification of the same IDR is
+ * not possible.
+ *
+ * Return: The pointer formerly associated with this ID.
+ */
+void *idr_remove(struct idr *idr, unsigned long id)
+{
+ return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL);
+}
+EXPORT_SYMBOL_GPL(idr_remove);
+
+/**
+ * idr_find() - Return pointer for given ID.
+ * @idr: IDR handle.
+ * @id: Pointer ID.
+ *
+ * Looks up the pointer associated with this ID. A %NULL pointer may
+ * indicate that @id is not allocated or that the %NULL pointer was
+ * associated with this ID.
+ *
+ * This function can be called under rcu_read_lock(), given that the leaf
+ * pointers lifetimes are correctly managed.
+ *
+ * Return: The pointer associated with this ID.
+ */
+void *idr_find(const struct idr *idr, unsigned long id)
+{
+ return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base);
+}
+EXPORT_SYMBOL_GPL(idr_find);
+
+/**
+ * idr_for_each() - Iterate through all stored pointers.
+ * @idr: IDR handle.
+ * @fn: Function to be called for each pointer.
+ * @data: Data passed to callback function.
*
* The callback function will be called for each entry in @idr, passing
- * the id, the pointer and the data pointer passed to this function.
+ * the ID, the entry and @data.
*
* If @fn returns anything other than %0, the iteration stops and that
* value is returned from this function.
{
struct radix_tree_iter iter;
void __rcu **slot;
+ int base = idr->idr_base;
radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) {
- int ret = fn(iter.index, rcu_dereference_raw(*slot), data);
+ int ret;
+
+ if (WARN_ON_ONCE(iter.index > INT_MAX))
+ break;
+ ret = fn(iter.index + base, rcu_dereference_raw(*slot), data);
if (ret)
return ret;
}
EXPORT_SYMBOL(idr_for_each);
/**
- * idr_get_next - Find next populated entry
- * @idr: idr handle
- * @nextid: Pointer to lowest possible ID to return
+ * idr_get_next() - Find next populated entry.
+ * @idr: IDR handle.
+ * @nextid: Pointer to an ID.
*
* Returns the next populated entry in the tree with an ID greater than
* or equal to the value pointed to by @nextid. On exit, @nextid is updated
{
struct radix_tree_iter iter;
void __rcu **slot;
+ int base = idr->idr_base;
+ int id = *nextid;
- slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
+ id = (id < base) ? 0 : id - base;
+ slot = radix_tree_iter_find(&idr->idr_rt, &iter, id);
if (!slot)
return NULL;
+ id = iter.index + base;
+
+ if (WARN_ON_ONCE(id > INT_MAX))
+ return NULL;
- *nextid = iter.index;
+ *nextid = id;
return rcu_dereference_raw(*slot);
}
EXPORT_SYMBOL(idr_get_next);
-void *idr_get_next_ext(struct idr *idr, unsigned long *nextid)
+/**
+ * idr_get_next_ul() - Find next populated entry.
+ * @idr: IDR handle.
+ * @nextid: Pointer to an ID.
+ *
+ * Returns the next populated entry in the tree with an ID greater than
+ * or equal to the value pointed to by @nextid. On exit, @nextid is updated
+ * to the ID of the found value. To use in a loop, the value pointed to by
+ * nextid must be incremented by the user.
+ */
+void *idr_get_next_ul(struct idr *idr, unsigned long *nextid)
{
struct radix_tree_iter iter;
void __rcu **slot;
+ unsigned long base = idr->idr_base;
+ unsigned long id = *nextid;
- slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid);
+ id = (id < base) ? 0 : id - base;
+ slot = radix_tree_iter_find(&idr->idr_rt, &iter, id);
if (!slot)
return NULL;
- *nextid = iter.index;
+ *nextid = iter.index + base;
return rcu_dereference_raw(*slot);
}
-EXPORT_SYMBOL(idr_get_next_ext);
+EXPORT_SYMBOL(idr_get_next_ul);
/**
- * idr_replace - replace pointer for given id
- * @idr: idr handle
- * @ptr: New pointer to associate with the ID
- * @id: Lookup key
+ * idr_replace() - replace pointer for given ID.
+ * @idr: IDR handle.
+ * @ptr: New pointer to associate with the ID.
+ * @id: ID to change.
*
* Replace the pointer registered with an ID and return the old value.
* This function can be called under the RCU read lock concurrently with
* the one being replaced!).
*
* Returns: the old value on success. %-ENOENT indicates that @id was not
- * found. %-EINVAL indicates that @id or @ptr were not valid.
+ * found. %-EINVAL indicates that @ptr was not valid.
*/
-void *idr_replace(struct idr *idr, void *ptr, int id)
-{
- if (id < 0)
- return ERR_PTR(-EINVAL);
-
- return idr_replace_ext(idr, ptr, id);
-}
-EXPORT_SYMBOL(idr_replace);
-
-void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id)
+void *idr_replace(struct idr *idr, void *ptr, unsigned long id)
{
struct radix_tree_node *node;
void __rcu **slot = NULL;
if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr)))
return ERR_PTR(-EINVAL);
+ id -= idr->idr_base;
entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot);
if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE))
return entry;
}
-EXPORT_SYMBOL(idr_replace_ext);
+EXPORT_SYMBOL(idr_replace);
/**
* DOC: IDA description
* bitmap, which is excessive.
*/
-#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS)
+#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS - 1)
/**
* ida_get_new_above - allocate new ID above or equal to a start id
#include <linux/bitmap.h>
#include <linux/bitops.h>
+#include <linux/bug.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/export.h>
}
EXPORT_SYMBOL(ida_pre_get);
-void __rcu **idr_get_free_cmn(struct radix_tree_root *root,
+void __rcu **idr_get_free(struct radix_tree_root *root,
struct radix_tree_iter *iter, gfp_t gfp,
unsigned long max)
{
__u32 result;
} test[MAX_SUBTESTS];
int (*fill_helper)(struct bpf_test *self);
+ int expected_errcode; /* used when FLAG_EXPECTED_FAIL is set in the aux */
__u8 frag_data[MAX_DATA];
int stack_depth; /* for eBPF only, since tests don't call verifier */
};
},
CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
{ },
- { }
+ { },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{
"check: div_k_0",
},
CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
{ },
- { }
+ { },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{
"check: unknown insn",
},
CLASSIC | FLAG_EXPECTED_FAIL,
{ },
- { }
+ { },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{
"check: out of range spill/fill",
},
CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
{ },
- { }
+ { },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{
"JUMPS + HOLES",
CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
{ },
{ },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{
"check: LDX + RET X",
CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
{ },
{ },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{ /* Mainly checking JIT here. */
"M[]: alt STX + LDX",
CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
{ },
{ },
+ .fill_helper = NULL,
+ .expected_errcode = -EINVAL,
},
{ /* Passes checker but fails during runtime. */
"LD [SKF_AD_OFF-1]",
{ },
{ },
.fill_helper = bpf_fill_maxinsns4,
+ .expected_errcode = -EINVAL,
},
{ /* Mainly checking JIT here. */
"BPF_MAXINSNS: Very long jump",
{
"BPF_MAXINSNS: Jump, gap, jump, ...",
{ },
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+ CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
CLASSIC | FLAG_NO_DATA,
+#endif
{ },
{ { 0, 0xababcbac } },
.fill_helper = bpf_fill_maxinsns11,
+ .expected_errcode = -ENOTSUPP,
},
{
"BPF_MAXINSNS: ld_abs+get_processor_id",
*err = bpf_prog_create(&fp, &fprog);
if (tests[which].aux & FLAG_EXPECTED_FAIL) {
- if (*err == -EINVAL) {
+ if (*err == tests[which].expected_errcode) {
pr_cont("PASS\n");
/* Verifier rejected filter as expected. */
*err = 0;
}
/*
- * Gets called on POLLHUP on eventfd when user closes it.
+ * Gets called on EPOLLHUP on eventfd when user closes it.
*
* Called with wqh->lock held and interrupts disabled.
*/
struct mem_cgroup *memcg = event->memcg;
__poll_t flags = key_to_poll(key);
- if (flags & POLLHUP) {
+ if (flags & EPOLLHUP) {
/*
* If the event has been detached at cgroup removal, we
* can simply return knowing the other side will cleanup
if (seq->poll_event != atomic_read(&proc_poll_event)) {
seq->poll_event = atomic_read(&proc_poll_event);
- return POLLIN | POLLRDNORM | POLLERR | POLLPRI;
+ return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI;
}
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
/* iterator */
if (!ts) {
if (err)
*err = -EREMOTEIO;
- return POLLERR;
+ return EPOLLERR;
}
if (!ts->rd->f_op->poll)
n = DEFAULT_POLLMASK;
else
n = ts->wr->f_op->poll(ts->wr, pt);
- ret = (ret & ~POLLOUT) | (n & ~POLLIN);
+ ret = (ret & ~EPOLLOUT) | (n & ~EPOLLIN);
}
return ret;
if (!list_empty(&m->req_list)) {
if (test_and_clear_bit(Rpending, &m->wsched))
- n = POLLIN;
+ n = EPOLLIN;
else
n = p9_fd_poll(m->client, NULL, NULL);
- if ((n & POLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) {
+ if ((n & EPOLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) {
p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
schedule_work(&m->rq);
}
if (m->wsize || !list_empty(&m->unsent_req_list)) {
if (test_and_clear_bit(Wpending, &m->wsched))
- n = POLLOUT;
+ n = EPOLLOUT;
else
n = p9_fd_poll(m->client, NULL, NULL);
- if ((n & POLLOUT) &&
+ if ((n & EPOLLOUT) &&
!test_and_set_bit(Wworksched, &m->wsched)) {
p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m);
schedule_work(&m->wq);
init_poll_funcptr(&m->pt, p9_pollwait);
n = p9_fd_poll(client, &m->pt, NULL);
- if (n & POLLIN) {
+ if (n & EPOLLIN) {
p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
set_bit(Rpending, &m->wsched);
}
- if (n & POLLOUT) {
+ if (n & EPOLLOUT) {
p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
set_bit(Wpending, &m->wsched);
}
return;
n = p9_fd_poll(m->client, NULL, &err);
- if (n & (POLLERR | POLLHUP | POLLNVAL)) {
+ if (n & (EPOLLERR | EPOLLHUP | EPOLLNVAL)) {
p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n);
p9_conn_cancel(m, err);
}
- if (n & POLLIN) {
+ if (n & EPOLLIN) {
set_bit(Rpending, &m->wsched);
p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m);
if (!test_and_set_bit(Rworksched, &m->wsched)) {
}
}
- if (n & POLLOUT) {
+ if (n & EPOLLOUT) {
set_bit(Wpending, &m->wsched);
p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m);
if ((m->wsize || !list_empty(&m->unsent_req_list)) &&
spin_unlock(&client->lock);
if (test_and_clear_bit(Wpending, &m->wsched))
- n = POLLOUT;
+ n = EPOLLOUT;
else
n = p9_fd_poll(m->client, NULL, NULL);
- if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
+ if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
schedule_work(&m->wq);
return 0;
/* exceptional events */
if (sk->sk_err)
- mask = POLLERR;
+ mask = EPOLLERR;
if (test_bit(ATM_VF_RELEASED, &vcc->flags) ||
test_bit(ATM_VF_CLOSE, &vcc->flags))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/* readable? */
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* writable? */
if (sock->state == SS_CONNECTING &&
if (vcc->qos.txtp.traffic_class != ATM_NONE &&
vcc_writable(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
return mask;
}
poll_wait(file, &socket_client->queue_wait, wait);
if (socket_client->queue_len > 0)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
poll_wait(file, &debug_log->queue_wait, wait);
if (!batadv_log_empty(debug_log))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
if (sk->sk_state == BT_CONNECTED ||
(test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) &&
sk->sk_state == BT_CONNECT2))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
return 0;
return bt_accept_poll(sk);
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR |
- (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+ mask |= EPOLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (sk->sk_state == BT_CLOSED)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_state == BT_CONNECT ||
sk->sk_state == BT_CONNECT2 ||
return mask;
if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
else
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
caif_disconnect_client(sock_net(sk), &cf_sk->layer);
cf_sk->sk.sk_socket->state = SS_DISCONNECTING;
- wake_up_interruptible_poll(sk_sleep(sk), POLLERR|POLLHUP);
+ wake_up_interruptible_poll(sk_sleep(sk), EPOLLERR|EPOLLHUP);
sock_orphan(sk);
sk_stream_kill_queues(&cf_sk->sk);
/* exceptional events? */
if (sk->sk_err)
- mask |= POLLERR;
+ mask |= EPOLLERR;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP;
+ mask |= EPOLLRDHUP;
/* readable? */
if (!skb_queue_empty(&sk->sk_receive_queue) ||
(sk->sk_shutdown & RCV_SHUTDOWN))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/*
* we set writable also when the other side has shut down the
* connection. This prevents stuck sockets.
*/
if (sock_writeable(sk) && tx_flow_is_on(cf_sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
return mask;
}
opt->name = kstrndup(argstr[0].from,
argstr[0].to-argstr[0].from,
GFP_KERNEL);
+ if (!opt->name) {
+ err = -ENOMEM;
+ goto out;
+ }
break;
case Opt_secret:
opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL);
/*
* Avoid a wakeup if event not interesting for us
*/
- if (key && !(key_to_poll(key) & (POLLIN | POLLERR)))
+ if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
return 0;
return autoremove_wake_function(wait, mode, sync, key);
}
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR |
- (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+ mask |= EPOLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/* readable? */
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (connection_based(sk)) {
if (sk->sk_state == TCP_CLOSE)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/* connection hasn't started yet? */
if (sk->sk_state == TCP_SYN_SENT)
return mask;
/* writable? */
if (sock_writeable(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
else
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
return net;
}
+/* Verify that rtnetlink requests do not pass additional properties
+ * potentially referring to different network namespaces.
+ */
+static int rtnl_ensure_unique_netns(struct nlattr *tb[],
+ struct netlink_ext_ack *extack,
+ bool netns_id_only)
+{
+
+ if (netns_id_only) {
+ if (!tb[IFLA_NET_NS_PID] && !tb[IFLA_NET_NS_FD])
+ return 0;
+
+ NL_SET_ERR_MSG(extack, "specified netns attribute not supported");
+ return -EOPNOTSUPP;
+ }
+
+ if (tb[IFLA_IF_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]))
+ goto invalid_attr;
+
+ if (tb[IFLA_NET_NS_PID] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_FD]))
+ goto invalid_attr;
+
+ if (tb[IFLA_NET_NS_FD] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_PID]))
+ goto invalid_attr;
+
+ return 0;
+
+invalid_attr:
+ NL_SET_ERR_MSG(extack, "multiple netns identifying attributes specified");
+ return -EINVAL;
+}
+
static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
{
if (dev) {
if (err < 0)
goto errout;
+ err = rtnl_ensure_unique_netns(tb, extack, false);
+ if (err < 0)
+ goto errout;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
if (err < 0)
return err;
+ err = rtnl_ensure_unique_netns(tb, extack, true);
+ if (err < 0)
+ return err;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
if (err < 0)
return err;
+ err = rtnl_ensure_unique_netns(tb, extack, false);
+ if (err < 0)
+ return err;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
if (err < 0)
return err;
+ err = rtnl_ensure_unique_netns(tb, extack, true);
+ if (err < 0)
+ return err;
+
if (tb[IFLA_IF_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid);
void __init skb_init(void)
{
- skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
+ skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache",
sizeof(struct sk_buff),
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
+ offsetof(struct sk_buff, cb),
+ sizeof_field(struct sk_buff, cb),
NULL);
skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
sizeof(struct sk_buff_fclones),
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_poll(&wq->wait, POLLERR);
+ wake_up_interruptible_poll(&wq->wait, EPOLLERR);
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
rcu_read_unlock();
}
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
- POLLRDNORM | POLLRDBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
+ EPOLLRDNORM | EPOLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
rcu_read_unlock();
}
if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
- POLLWRNORM | POLLWRBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
+ EPOLLWRNORM | EPOLLWRBAND);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_poll(&wq->wait, POLLOUT |
- POLLWRNORM | POLLWRBAND);
+ wake_up_interruptible_poll(&wq->wait, EPOLLOUT |
+ EPOLLWRNORM | EPOLLWRBAND);
if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
rcu_read_unlock();
mask = 0;
if (sk->sk_err)
- mask = POLLERR;
+ mask = EPOLLERR;
if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLIN | POLLRDNORM | POLLRDHUP;
+ mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected? */
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
if (atomic_read(&sk->sk_rmem_alloc) > 0)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
if (sk_stream_is_writeable(sk)) {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
* IO signal will be lost.
*/
if (sk_stream_is_writeable(sk))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
}
}
__poll_t mask = datagram_poll(file, sock, wait);
if (!skb_queue_empty(&scp->other_receive_queue))
- mask |= POLLRDBAND;
+ mask |= EPOLLRDBAND;
return mask;
}
* @name: Name to look up
* @namelen: Length of name
* @options: Request options (or NULL if no options)
- * @_result: Where to place the returned data.
+ * @_result: Where to place the returned data (or NULL)
* @_expiry: Where to store the result expiry time (or NULL)
*
- * The data will be returned in the pointer at *result, and the caller is
- * responsible for freeing it.
+ * The data will be returned in the pointer at *result, if provided, and the
+ * caller is responsible for freeing it.
*
* The description should be of the form "[<query_type>:]<domain_name>", and
* the options need to be appropriate for the query type requested. If no
kenter("%s,%*.*s,%zu,%s",
type, (int)namelen, (int)namelen, name, namelen, options);
- if (!name || namelen == 0 || !_result)
+ if (!name || namelen == 0)
return -EINVAL;
/* construct the query key description as "[<type>:]<name>" */
upayload = user_key_payload_locked(rkey);
len = upayload->datalen;
- ret = -ENOMEM;
- *_result = kmalloc(len + 1, GFP_KERNEL);
- if (!*_result)
- goto put;
+ if (_result) {
+ ret = -ENOMEM;
+ *_result = kmalloc(len + 1, GFP_KERNEL);
+ if (!*_result)
+ goto put;
- memcpy(*_result, upayload->data, len);
- (*_result)[len] = '\0';
+ memcpy(*_result, upayload->data, len);
+ (*_result)[len] = '\0';
+ }
if (_expiry)
*_expiry = rkey->expiry;
case TCP_CLOSE:
err = -ENOTCONN;
/* Hack to wake up other listeners, who can poll for
- POLLHUP, even on eg. unconnected UDP sockets -- RR */
+ EPOLLHUP, even on eg. unconnected UDP sockets -- RR */
/* fall through */
default:
sk->sk_shutdown |= how;
config NF_FLOW_TABLE_IPV4
tristate "Netfilter flow table IPv4 module"
- depends on NF_CONNTRACK && NF_TABLES
- select NF_FLOW_TABLE
+ depends on NF_FLOW_TABLE
help
This option adds the flow table IPv4 support.
.family = NFPROTO_IPV4,
.params = &nf_flow_offload_rhash_params,
.gc = nf_flow_offload_work_gc,
+ .free = nf_flow_table_free,
.hook = nf_flow_offload_ip_hook,
.owner = THIS_MODULE,
};
mask = 0;
/*
- * POLLHUP is certainly not done right. But poll() doesn't
+ * EPOLLHUP is certainly not done right. But poll() doesn't
* have a notion of HUP in just one direction, and for a
* socket the read side is more interesting.
*
- * Some poll() documentation says that POLLHUP is incompatible
- * with the POLLOUT/POLLWR flags, so somebody should check this
+ * Some poll() documentation says that EPOLLHUP is incompatible
+ * with the EPOLLOUT/POLLWR flags, so somebody should check this
* all. But careful, it tends to be safer to return too many
* bits than too few, and you can easily break real applications
* if you don't tell them that something has hung up!
*
* Check-me.
*
- * Check number 1. POLLHUP is _UNMASKABLE_ event (see UNIX98 and
+ * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and
* our fs/select.c). It means that after we received EOF,
* poll always returns immediately, making impossible poll() on write()
- * in state CLOSE_WAIT. One solution is evident --- to set POLLHUP
+ * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP
* if and only if shutdown has been made in both directions.
* Actually, it is interesting to look how Solaris and DUX
- * solve this dilemma. I would prefer, if POLLHUP were maskable,
+ * solve this dilemma. I would prefer, if EPOLLHUP were maskable,
* then we could set it on SND_SHUTDOWN. BTW examples given
* in Stevens' books assume exactly this behaviour, it explains
- * why POLLHUP is incompatible with POLLOUT. --ANK
+ * why EPOLLHUP is incompatible with EPOLLOUT. --ANK
*
* NOTE. Check for TCP_CLOSE is added. The goal is to prevent
* blocking on fresh not-connected or disconnected socket. --ANK
*/
if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLIN | POLLRDNORM | POLLRDHUP;
+ mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected or passive Fast Open socket? */
if (state != TCP_SYN_SENT &&
target++;
if (tp->rcv_nxt - tp->copied_seq >= target)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
if (sk_stream_is_writeable(sk)) {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
*/
smp_mb__after_atomic();
if (sk_stream_is_writeable(sk))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
} else
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
if (tp->urg_data & TCP_URG_VALID)
- mask |= POLLPRI;
+ mask |= EPOLLPRI;
} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
/* Active TCP fastopen socket with defer_connect
- * Return POLLOUT so application can call write()
+ * Return EPOLLOUT so application can call write()
* in order for kernel to generate SYN+data
*/
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
/* This barrier is coupled with smp_wmb() in tcp_reset() */
smp_rmb();
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR;
+ mask |= EPOLLERR;
return mask;
}
/* Fast Recovery (RFC 5681 3.2) :
* Cubic needs 1.7 factor, rounded to 2 to include
- * extra cushion (application might react slowly to POLLOUT)
+ * extra cushion (application might react slowly to EPOLLOUT)
*/
sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
sndmem *= nr_segs * per_mss;
*/
if (sk) {
arg.bound_dev_if = sk->sk_bound_dev_if;
- trace_tcp_send_reset(sk, skb);
+ if (sk_fullsock(sk))
+ trace_tcp_send_reset(sk, skb);
}
BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
return NULL;
}
+static struct tcp_ulp_ops *tcp_ulp_find_id(const int ulp)
+{
+ struct tcp_ulp_ops *e;
+
+ list_for_each_entry_rcu(e, &tcp_ulp_list, list) {
+ if (e->uid == ulp)
+ return e;
+ }
+
+ return NULL;
+}
+
static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name)
{
const struct tcp_ulp_ops *ulp = NULL;
return ulp;
}
+static const struct tcp_ulp_ops *__tcp_ulp_lookup(const int uid)
+{
+ const struct tcp_ulp_ops *ulp;
+
+ rcu_read_lock();
+ ulp = tcp_ulp_find_id(uid);
+ if (!ulp || !try_module_get(ulp->owner))
+ ulp = NULL;
+ rcu_read_unlock();
+ return ulp;
+}
+
/* Attach new upper layer protocol to the list
* of available protocols.
*/
int ret = 0;
spin_lock(&tcp_ulp_list_lock);
- if (tcp_ulp_find(ulp->name)) {
- pr_notice("%s already registered or non-unique name\n",
- ulp->name);
+ if (tcp_ulp_find(ulp->name))
ret = -EEXIST;
- } else {
+ else
list_add_tail_rcu(&ulp->list, &tcp_ulp_list);
- }
spin_unlock(&tcp_ulp_list_lock);
return ret;
if (!ulp_ops)
return -ENOENT;
+ if (!ulp_ops->user_visible) {
+ module_put(ulp_ops->owner);
+ return -ENOENT;
+ }
+
+ err = ulp_ops->init(sk);
+ if (err) {
+ module_put(ulp_ops->owner);
+ return err;
+ }
+
+ icsk->icsk_ulp_ops = ulp_ops;
+ return 0;
+}
+
+int tcp_set_ulp_id(struct sock *sk, int ulp)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ const struct tcp_ulp_ops *ulp_ops;
+ int err;
+
+ if (icsk->icsk_ulp_ops)
+ return -EEXIST;
+
+ ulp_ops = __tcp_ulp_lookup(ulp);
+ if (!ulp_ops)
+ return -ENOENT;
+
err = ulp_ops->init(sk);
if (err) {
module_put(ulp_ops->owner);
struct sock *sk = sock->sk;
if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Check for false positives due to checksum errors */
- if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
+ if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
- mask &= ~(POLLIN | POLLRDNORM);
+ mask &= ~(EPOLLIN | EPOLLRDNORM);
return mask;
config NF_FLOW_TABLE_IPV6
tristate "Netfilter flow table IPv6 module"
- depends on NF_CONNTRACK && NF_TABLES
- select NF_FLOW_TABLE
+ depends on NF_FLOW_TABLE
help
This option adds the flow table IPv6 support.
* this case. -DaveM
*/
pr_debug("end of fragment not rounded to 8 bytes.\n");
+ inet_frag_kill(&fq->q, &nf_frags);
return -EPROTO;
}
if (end > fq->q.len) {
.family = NFPROTO_IPV6,
.params = &nf_flow_offload_rhash_params,
.gc = nf_flow_offload_work_gc,
+ .free = nf_flow_table_free,
.hook = nf_flow_offload_ipv6_hook,
.owner = THIS_MODULE,
};
struct net_device *dev,
struct netlink_ext_ack *extack)
{
- u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
+ u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
const struct in6_addr *gw_addr = &cfg->fc_gateway;
u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT;
struct rt6_info *grt;
err = 0;
grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
if (grt) {
- if (grt->rt6i_flags & flags || dev != grt->dst.dev) {
- NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
+ if (!grt->dst.error &&
+ (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
+ NL_SET_ERR_MSG(extack,
+ "Nexthop has invalid gateway or device mismatch");
err = -EINVAL;
}
if (sk) {
oif = sk->sk_bound_dev_if;
- trace_tcp_send_reset(sk, skb);
+ if (sk_fullsock(sk))
+ trace_tcp_send_reset(sk, skb);
}
tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0);
sk = (struct sock *) isk;
if (sk->sk_state == IUCV_CONNECTED)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
return 0;
return iucv_accept_poll(sk);
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR |
- (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+ mask |= EPOLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP;
+ mask |= EPOLLRDHUP;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (!skb_queue_empty(&sk->sk_receive_queue) ||
(sk->sk_shutdown & RCV_SHUTDOWN))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (sk->sk_state == IUCV_CLOSED)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_state == IUCV_DISCONN)
- mask |= POLLIN;
+ mask |= EPOLLIN;
if (sock_writeable(sk) && iucv_below_msglim(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
else
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
static void psock_state_change(struct sock *sk)
{
- /* TCP only does a POLLIN for a half close. Do a POLLHUP here
- * since application will normally not poll with POLLIN
+ /* TCP only does a EPOLLIN for a half close. Do a EPOLLHUP here
+ * since application will normally not poll with EPOLLIN
* on the TCP sockets.
*/
/* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
* we set sk_state, otherwise epoll_wait always returns right away with
- * POLLHUP
+ * EPOLLHUP
*/
kcm->sk.sk_state = TCP_ESTABLISHED;
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/netconf.h>
+#include <linux/nospec.h>
#include <linux/vmalloc.h>
#include <linux/percpu.h>
#include <net/ip.h>
return err;
}
-static bool mpls_label_ok(struct net *net, unsigned int index,
+static bool mpls_label_ok(struct net *net, unsigned int *index,
struct netlink_ext_ack *extack)
{
+ bool is_ok = true;
+
/* Reserved labels may not be set */
- if (index < MPLS_LABEL_FIRST_UNRESERVED) {
+ if (*index < MPLS_LABEL_FIRST_UNRESERVED) {
NL_SET_ERR_MSG(extack,
"Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher");
- return false;
+ is_ok = false;
}
/* The full 20 bit range may not be supported. */
- if (index >= net->mpls.platform_labels) {
+ if (is_ok && *index >= net->mpls.platform_labels) {
NL_SET_ERR_MSG(extack,
"Label >= configured maximum in platform_labels");
- return false;
+ is_ok = false;
}
- return true;
+ *index = array_index_nospec(*index, net->mpls.platform_labels);
+ return is_ok;
}
static int mpls_route_add(struct mpls_route_config *cfg,
index = find_free_label(net);
}
- if (!mpls_label_ok(net, index, extack))
+ if (!mpls_label_ok(net, &index, extack))
goto errout;
/* Append makes no sense with mpls */
index = cfg->rc_label;
- if (!mpls_label_ok(net, index, extack))
+ if (!mpls_label_ok(net, &index, extack))
goto errout;
mpls_route_update(net, index, NULL, &cfg->rc_nlinfo);
goto errout;
if (!mpls_label_ok(cfg->rc_nlinfo.nl_net,
- cfg->rc_label, extack))
+ &cfg->rc_label, extack))
goto errout;
break;
}
goto errout;
}
- if (!mpls_label_ok(net, in_label, extack)) {
+ if (!mpls_label_ok(net, &in_label, extack)) {
err = -EINVAL;
goto errout;
}
config NF_FLOW_TABLE_INET
tristate "Netfilter flow table mixed IPv4/IPv6 module"
- depends on NF_FLOW_TABLE_IPV4 && NF_FLOW_TABLE_IPV6
- select NF_FLOW_TABLE
+ depends on NF_FLOW_TABLE_IPV4
+ depends on NF_FLOW_TABLE_IPV6
help
This option adds the flow table mixed IPv4/IPv6 support.
config NF_FLOW_TABLE
tristate "Netfilter flow table module"
- depends on NF_CONNTRACK && NF_TABLES
+ depends on NETFILTER_INGRESS
+ depends on NF_CONNTRACK
+ depends on NF_TABLES
help
This option adds the flow table core infrastructure.
#include <linux/netfilter.h>
#include <linux/rhashtable.h>
#include <linux/netdevice.h>
+#include <net/netfilter/nf_tables.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
e = container_of(flow, struct flow_offload_entry, flow);
- kfree(e);
+ nf_ct_delete(e->ct, 0, 0);
+ nf_ct_put(e->ct);
+ kfree_rcu(e, rcu_head);
}
EXPORT_SYMBOL_GPL(flow_offload_free);
}
EXPORT_SYMBOL_GPL(flow_offload_add);
-void flow_offload_del(struct nf_flowtable *flow_table,
- struct flow_offload *flow)
+static void flow_offload_del(struct nf_flowtable *flow_table,
+ struct flow_offload *flow)
{
- struct flow_offload_entry *e;
-
rhashtable_remove_fast(&flow_table->rhashtable,
&flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
*flow_table->type->params);
&flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
*flow_table->type->params);
- e = container_of(flow, struct flow_offload_entry, flow);
- kfree_rcu(e, rcu_head);
+ flow_offload_free(flow);
}
-EXPORT_SYMBOL_GPL(flow_offload_del);
struct flow_offload_tuple_rhash *
flow_offload_lookup(struct nf_flowtable *flow_table,
}
EXPORT_SYMBOL_GPL(flow_offload_lookup);
-static void nf_flow_release_ct(const struct flow_offload *flow)
-{
- struct flow_offload_entry *e;
-
- e = container_of(flow, struct flow_offload_entry, flow);
- nf_ct_delete(e->ct, 0, 0);
- nf_ct_put(e->ct);
-}
-
int nf_flow_table_iterate(struct nf_flowtable *flow_table,
void (*iter)(struct flow_offload *flow, void *data),
void *data)
return flow->flags & FLOW_OFFLOAD_DYING;
}
-void nf_flow_offload_work_gc(struct work_struct *work)
+static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
{
struct flow_offload_tuple_rhash *tuplehash;
- struct nf_flowtable *flow_table;
struct rhashtable_iter hti;
struct flow_offload *flow;
int err;
- flow_table = container_of(work, struct nf_flowtable, gc_work.work);
-
err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL);
if (err)
- goto schedule;
+ return 0;
rhashtable_walk_start(&hti);
flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
if (nf_flow_has_expired(flow) ||
- nf_flow_is_dying(flow)) {
+ nf_flow_is_dying(flow))
flow_offload_del(flow_table, flow);
- nf_flow_release_ct(flow);
- }
}
out:
rhashtable_walk_stop(&hti);
rhashtable_walk_exit(&hti);
-schedule:
+
+ return 1;
+}
+
+void nf_flow_offload_work_gc(struct work_struct *work)
+{
+ struct nf_flowtable *flow_table;
+
+ flow_table = container_of(work, struct nf_flowtable, gc_work.work);
+ nf_flow_offload_gc_step(flow_table);
queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc);
}
EXPORT_SYMBOL_GPL(nf_flow_dnat_port);
+static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
+{
+ struct net_device *dev = data;
+
+ if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
+ return;
+
+ flow_offload_dead(flow);
+}
+
+static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
+ void *data)
+{
+ nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data);
+ flush_delayed_work(&flowtable->gc_work);
+}
+
+void nf_flow_table_cleanup(struct net *net, struct net_device *dev)
+{
+ nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev);
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
+
+void nf_flow_table_free(struct nf_flowtable *flow_table)
+{
+ nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
+ WARN_ON(!nf_flow_offload_gc_step(flow_table));
+}
+EXPORT_SYMBOL_GPL(nf_flow_table_free);
+
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
.family = NFPROTO_INET,
.params = &nf_flow_offload_rhash_params,
.gc = nf_flow_offload_work_gc,
+ .free = nf_flow_table_free,
.hook = nf_flow_offload_inet_hook,
.owner = THIS_MODULE,
};
struct nft_flowtable *flowtable;
const struct nft_table *table;
- rcu_read_lock();
- list_for_each_entry_rcu(table, &net->nft.tables, list) {
- list_for_each_entry_rcu(flowtable, &table->flowtables, list) {
+ nfnl_lock(NFNL_SUBSYS_NFTABLES);
+ list_for_each_entry(table, &net->nft.tables, list) {
+ list_for_each_entry(flowtable, &table->flowtables, list) {
iter(&flowtable->data, data);
}
}
- rcu_read_unlock();
+ nfnl_unlock(NFNL_SUBSYS_NFTABLES);
}
EXPORT_SYMBOL_GPL(nft_flow_table_iterate);
nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
}
-static void nft_flowtable_destroy(void *ptr, void *arg)
-{
- kfree(ptr);
-}
-
static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
{
cancel_delayed_work_sync(&flowtable->data.gc_work);
kfree(flowtable->name);
- rhashtable_free_and_destroy(&flowtable->data.rhashtable,
- nft_flowtable_destroy, NULL);
+ flowtable->data.type->free(&flowtable->data);
+ rhashtable_destroy(&flowtable->data.rhashtable);
module_put(flowtable->data.type->owner);
}
.owner = THIS_MODULE,
};
-static void flow_offload_iterate_cleanup(struct flow_offload *flow, void *data)
-{
- struct net_device *dev = data;
-
- if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
- return;
-
- flow_offload_dead(flow);
-}
-
-static void nft_flow_offload_iterate_cleanup(struct nf_flowtable *flowtable,
- void *data)
-{
- nf_flow_table_iterate(flowtable, flow_offload_iterate_cleanup, data);
-}
-
static int flow_offload_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
if (event != NETDEV_DOWN)
return NOTIFY_DONE;
- nft_flow_table_iterate(dev_net(dev), nft_flow_offload_iterate_cleanup, dev);
+ nf_flow_table_cleanup(dev_net(dev), dev);
return NOTIFY_DONE;
}
static void __exit nft_flow_offload_module_exit(void)
{
- struct net *net;
-
nft_unregister_expr(&nft_flow_offload_type);
unregister_netdevice_notifier(&flow_offload_netdev_notifier);
- rtnl_lock();
- for_each_net(net)
- nft_flow_table_iterate(net, nft_flow_offload_iterate_cleanup, NULL);
- rtnl_unlock();
}
module_init(nft_flow_offload_module_init);
if ((size >> PAGE_SHIFT) + 2 > totalram_pages)
return NULL;
- info = kvmalloc(sz, GFP_KERNEL);
+ /* __GFP_NORETRY is not fully supported by kvmalloc but it should
+ * work reasonably well if sz is too large and bail out rather
+ * than shoot all processes down before realizing there is nothing
+ * more to reclaim.
+ */
+ info = kvmalloc(sz, GFP_KERNEL | __GFP_NORETRY);
if (!info)
return NULL;
hlist_add_head(&est->list, &rateest_hash[h]);
}
-struct xt_rateest *xt_rateest_lookup(const char *name)
+static struct xt_rateest *__xt_rateest_lookup(const char *name)
{
struct xt_rateest *est;
unsigned int h;
h = xt_rateest_hash(name);
- mutex_lock(&xt_rateest_mutex);
hlist_for_each_entry(est, &rateest_hash[h], list) {
if (strcmp(est->name, name) == 0) {
est->refcnt++;
- mutex_unlock(&xt_rateest_mutex);
return est;
}
}
- mutex_unlock(&xt_rateest_mutex);
+
return NULL;
}
+
+struct xt_rateest *xt_rateest_lookup(const char *name)
+{
+ struct xt_rateest *est;
+
+ mutex_lock(&xt_rateest_mutex);
+ est = __xt_rateest_lookup(name);
+ mutex_unlock(&xt_rateest_mutex);
+ return est;
+}
EXPORT_SYMBOL_GPL(xt_rateest_lookup);
void xt_rateest_put(struct xt_rateest *est)
net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
- est = xt_rateest_lookup(info->name);
+ mutex_lock(&xt_rateest_mutex);
+ est = __xt_rateest_lookup(info->name);
if (est) {
+ mutex_unlock(&xt_rateest_mutex);
/*
* If estimator parameters are specified, they must match the
* existing estimator.
info->est = est;
xt_rateest_hash_insert(est);
+ mutex_unlock(&xt_rateest_mutex);
return 0;
err2:
kfree(est);
err1:
+ mutex_unlock(&xt_rateest_mutex);
return ret;
}
return -EINVAL;
}
+ info->priv = NULL;
if (info->has_path) {
cgrp = cgroup_get_from_path(info->path);
if (IS_ERR(cgrp)) {
{
struct sk_buff *tmp;
struct net *net, *prev = NULL;
+ bool delivered = false;
int err;
for_each_net_rcu(net) {
}
err = nlmsg_multicast(prev->genl_sock, tmp,
portid, group, flags);
- if (err)
+ if (!err)
+ delivered = true;
+ else if (err != -ESRCH)
goto error;
}
prev = net;
}
- return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+ err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags);
+ if (!err)
+ delivered = true;
+ else if (err != -ESRCH)
+ goto error;
+ return delivered ? 0 : -ESRCH;
error:
kfree_skb(skb);
return err;
sk = &llcp_sock->sk;
if (sk->sk_state == LLCP_CONNECTED)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
return 0;
return llcp_accept_poll(sk);
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR |
- (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+ mask |= EPOLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (sk->sk_state == LLCP_CLOSED)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED)
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
else
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (po->rx_ring.pg_vec) {
if (!packet_previous_rx_frame(po, &po->rx_ring,
TP_STATUS_KERNEL))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
po->pressure = 0;
spin_lock_bh(&sk->sk_write_queue.lock);
if (po->tx_ring.pg_vec) {
if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
spin_unlock_bh(&sk->sk_write_queue.lock);
return mask;
poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == TCP_CLOSE)
- return POLLERR;
+ return EPOLLERR;
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (!skb_queue_empty(&pn->ctrlreq_queue))
- mask |= POLLPRI;
+ mask |= EPOLLPRI;
if (!mask && sk->sk_state == TCP_CLOSE_WAIT)
- return POLLHUP;
+ return EPOLLHUP;
if (sk->sk_state == TCP_ESTABLISHED &&
refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf &&
atomic_read(&pn->tx_credits))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
return mask;
}
/*
* RDS' poll is without a doubt the least intuitive part of the interface,
- * as POLLIN and POLLOUT do not behave entirely as you would expect from
+ * as EPOLLIN and EPOLLOUT do not behave entirely as you would expect from
* a network protocol.
*
- * POLLIN is asserted if
+ * EPOLLIN is asserted if
* - there is data on the receive queue.
* - to signal that a previously congested destination may have become
* uncongested
* - A notification has been queued to the socket (this can be a congestion
* update, or a RDMA completion).
*
- * POLLOUT is asserted if there is room on the send queue. This does not mean
+ * EPOLLOUT is asserted if there is room on the send queue. This does not mean
* however, that the next sendmsg() call will succeed. If the application tries
* to send to a congested destination, the system call may still fail (and
* return ENOBUFS).
read_lock_irqsave(&rs->rs_recv_lock, flags);
if (!rs->rs_cong_monitor) {
- /* When a congestion map was updated, we signal POLLIN for
+ /* When a congestion map was updated, we signal EPOLLIN for
* "historical" reasons. Applications can also poll for
* WRBAND instead. */
if (rds_cong_updated_since(&rs->rs_cong_track))
- mask |= (POLLIN | POLLRDNORM | POLLWRBAND);
+ mask |= (EPOLLIN | EPOLLRDNORM | EPOLLWRBAND);
} else {
spin_lock(&rs->rs_lock);
if (rs->rs_cong_notify)
- mask |= (POLLIN | POLLRDNORM);
+ mask |= (EPOLLIN | EPOLLRDNORM);
spin_unlock(&rs->rs_lock);
}
if (!list_empty(&rs->rs_recv_queue) ||
!list_empty(&rs->rs_notify_queue))
- mask |= (POLLIN | POLLRDNORM);
+ mask |= (EPOLLIN | EPOLLRDNORM);
if (rs->rs_snd_bytes < rds_sk_sndbuf(rs))
- mask |= (POLLOUT | POLLWRNORM);
+ mask |= (EPOLLOUT | EPOLLWRNORM);
read_unlock_irqrestore(&rs->rs_recv_lock, flags);
/* clear state any time we wake a seen-congested socket */
rcu_read_lock();
if (!test_and_set_bit(0, &conn->c_map_queued) &&
- !test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) {
+ !rds_destroy_pending(cp->cp_conn)) {
rds_stats_inc(s_cong_update_queued);
/* We cannot inline the call to rds_send_xmit() here
* for two reasons (both pertaining to a TCP transport):
is_outgoing);
conn->c_path[i].cp_index = i;
}
- ret = trans->conn_alloc(conn, gfp);
+ rcu_read_lock();
+ if (rds_destroy_pending(conn))
+ ret = -ENETDOWN;
+ else
+ ret = trans->conn_alloc(conn, gfp);
if (ret) {
+ rcu_read_unlock();
kfree(conn->c_path);
kmem_cache_free(rds_conn_slab, conn);
conn = ERR_PTR(ret);
}
}
spin_unlock_irqrestore(&rds_conn_lock, flags);
+ rcu_read_unlock();
out:
return conn;
{
struct rds_message *rm, *rtmp;
- set_bit(RDS_DESTROY_PENDING, &cp->cp_flags);
-
if (!cp->cp_transport_data)
return;
/* make sure lingering queued work won't try to ref the conn */
- synchronize_rcu();
cancel_delayed_work_sync(&cp->cp_send_w);
cancel_delayed_work_sync(&cp->cp_recv_w);
atomic_set(&cp->cp_state, RDS_CONN_ERROR);
rcu_read_lock();
- if (!destroy && test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) {
+ if (!destroy && rds_destroy_pending(cp->cp_conn)) {
rcu_read_unlock();
return;
}
void rds_conn_path_connect_if_down(struct rds_conn_path *cp)
{
rcu_read_lock();
- if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) {
+ if (rds_destroy_pending(cp->cp_conn)) {
rcu_read_unlock();
return;
}
static unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE;
static unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE;
unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT;
+static atomic_t rds_ib_unloading;
module_param(rds_ib_mr_1m_pool_size, int, 0444);
MODULE_PARM_DESC(rds_ib_mr_1m_pool_size, " Max number of 1M mr per HCA");
flush_workqueue(rds_wq);
}
+static void rds_ib_set_unloading(void)
+{
+ atomic_set(&rds_ib_unloading, 1);
+}
+
+static bool rds_ib_is_unloading(struct rds_connection *conn)
+{
+ struct rds_conn_path *cp = &conn->c_path[0];
+
+ return (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags) ||
+ atomic_read(&rds_ib_unloading) != 0);
+}
+
void rds_ib_exit(void)
{
+ rds_ib_set_unloading();
+ synchronize_rcu();
rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
rds_ib_unregister_client();
rds_ib_destroy_nodev_conns();
.flush_mrs = rds_ib_flush_mrs,
.t_owner = THIS_MODULE,
.t_name = "infiniband",
+ .t_unloading = rds_ib_is_unloading,
.t_type = RDS_TRANS_IB
};
&conn->c_laddr, &conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version));
+ set_bit(RDS_DESTROY_PENDING, &conn->c_path[0].cp_flags);
rds_conn_destroy(conn);
return;
} else {
void (*sync_mr)(void *trans_private, int direction);
void (*free_mr)(void *trans_private, int invalidate);
void (*flush_mrs)(void);
+ bool (*t_unloading)(struct rds_connection *conn);
};
struct rds_sock {
__rds_put_mr_final(mr);
}
+static inline bool rds_destroy_pending(struct rds_connection *conn)
+{
+ return !check_net(rds_conn_net(conn)) ||
+ (conn->c_trans->t_unloading && conn->c_trans->t_unloading(conn));
+}
+
/* stats.c */
DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats);
#define rds_stats_inc_which(which, member) do { \
goto out;
}
- if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) {
+ if (rds_destroy_pending(cp->cp_conn)) {
release_in_xmit(cp);
ret = -ENETUNREACH; /* dont requeue send work */
goto out;
if (batch_count < send_batch_count)
goto restart;
rcu_read_lock();
- if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ if (rds_destroy_pending(cp->cp_conn))
ret = -ENETUNREACH;
else
queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
else
cpath = &conn->c_path[0];
- if (test_bit(RDS_DESTROY_PENDING, &cpath->cp_flags)) {
+ if (rds_destroy_pending(conn)) {
ret = -EAGAIN;
goto out;
}
if (ret == -ENOMEM || ret == -EAGAIN) {
ret = 0;
rcu_read_lock();
- if (test_bit(RDS_DESTROY_PENDING, &cpath->cp_flags))
+ if (rds_destroy_pending(cpath->cp_conn))
ret = -ENETUNREACH;
else
queue_delayed_work(rds_wq, &cpath->cp_send_w, 1);
/* schedule the send work on rds_wq */
rcu_read_lock();
- if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ if (!rds_destroy_pending(cp->cp_conn))
queue_delayed_work(rds_wq, &cp->cp_send_w, 1);
rcu_read_unlock();
/* Track rds_tcp_connection structs so they can be cleaned up */
static DEFINE_SPINLOCK(rds_tcp_conn_lock);
static LIST_HEAD(rds_tcp_conn_list);
+static atomic_t rds_tcp_unloading = ATOMIC_INIT(0);
static struct kmem_cache *rds_tcp_conn_slab;
static void rds_tcp_conn_free(void *arg)
{
struct rds_tcp_connection *tc = arg;
- unsigned long flags;
rdsdebug("freeing tc %p\n", tc);
- spin_lock_irqsave(&rds_tcp_conn_lock, flags);
+ spin_lock_bh(&rds_tcp_conn_lock);
if (!tc->t_tcp_node_detached)
list_del(&tc->t_tcp_node);
- spin_unlock_irqrestore(&rds_tcp_conn_lock, flags);
+ spin_unlock_bh(&rds_tcp_conn_lock);
kmem_cache_free(rds_tcp_conn_slab, tc);
}
tc = kmem_cache_alloc(rds_tcp_conn_slab, gfp);
if (!tc) {
ret = -ENOMEM;
- break;
+ goto fail;
}
mutex_init(&tc->t_conn_path_lock);
tc->t_sock = NULL;
conn->c_path[i].cp_transport_data = tc;
tc->t_cpath = &conn->c_path[i];
+ tc->t_tcp_node_detached = true;
- spin_lock_irq(&rds_tcp_conn_lock);
- tc->t_tcp_node_detached = false;
- list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list);
- spin_unlock_irq(&rds_tcp_conn_lock);
rdsdebug("rds_conn_path [%d] tc %p\n", i,
conn->c_path[i].cp_transport_data);
}
+ spin_lock_bh(&rds_tcp_conn_lock);
+ for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+ tc = conn->c_path[i].cp_transport_data;
+ tc->t_tcp_node_detached = false;
+ list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list);
+ }
+ spin_unlock_bh(&rds_tcp_conn_lock);
+fail:
if (ret) {
for (j = 0; j < i; j++)
rds_tcp_conn_free(conn->c_path[j].cp_transport_data);
return false;
}
+static void rds_tcp_set_unloading(void)
+{
+ atomic_set(&rds_tcp_unloading, 1);
+}
+
+static bool rds_tcp_is_unloading(struct rds_connection *conn)
+{
+ return atomic_read(&rds_tcp_unloading) != 0;
+}
+
static void rds_tcp_destroy_conns(void)
{
struct rds_tcp_connection *tc, *_tc;
.t_type = RDS_TRANS_TCP,
.t_prefer_loopback = 1,
.t_mp_capable = 1,
+ .t_unloading = rds_tcp_is_unloading,
};
static unsigned int rds_tcp_netid;
rtn->rds_tcp_listen_sock = NULL;
rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w);
- spin_lock_irq(&rds_tcp_conn_lock);
+ spin_lock_bh(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
tc->t_tcp_node_detached = true;
}
}
- spin_unlock_irq(&rds_tcp_conn_lock);
+ spin_unlock_bh(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node)
rds_conn_destroy(tc->t_cpath->cp_conn);
}
{
struct rds_tcp_connection *tc, *_tc;
- spin_lock_irq(&rds_tcp_conn_lock);
+ spin_lock_bh(&rds_tcp_conn_lock);
list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
/* reconnect with new parameters */
rds_conn_path_drop(tc->t_cpath, false);
}
- spin_unlock_irq(&rds_tcp_conn_lock);
+ spin_unlock_bh(&rds_tcp_conn_lock);
}
static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write,
static void rds_tcp_exit(void)
{
+ rds_tcp_set_unloading();
+ synchronize_rcu();
rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
unregister_pernet_subsys(&rds_tcp_net_ops);
if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
cp->cp_conn, tc, sock);
if (sock) {
- if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ if (rds_destroy_pending(cp->cp_conn))
rds_tcp_set_linger(sock);
sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN);
lock_sock(sock->sk);
if (rds_tcp_read_sock(cp, GFP_ATOMIC) == -ENOMEM) {
rcu_read_lock();
- if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ if (!rds_destroy_pending(cp->cp_conn))
queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
rcu_read_unlock();
}
rcu_read_lock();
if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf &&
- !test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ !rds_destroy_pending(cp->cp_conn))
queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
rcu_read_unlock();
cp->cp_reconnect_jiffies = 0;
set_bit(0, &cp->cp_conn->c_map_queued);
rcu_read_lock();
- if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) {
+ if (!rds_destroy_pending(cp->cp_conn)) {
queue_delayed_work(rds_wq, &cp->cp_send_w, 0);
queue_delayed_work(rds_wq, &cp->cp_recv_w, 0);
}
if (cp->cp_reconnect_jiffies == 0) {
cp->cp_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies;
rcu_read_lock();
- if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ if (!rds_destroy_pending(cp->cp_conn))
queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
rcu_read_unlock();
return;
rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies,
conn, &conn->c_laddr, &conn->c_faddr);
rcu_read_lock();
- if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags))
+ if (!rds_destroy_pending(cp->cp_conn))
queue_delayed_work(rds_wq, &cp->cp_conn_w,
rand % cp->cp_reconnect_jiffies);
rcu_read_unlock();
static __poll_t rfkill_fop_poll(struct file *file, poll_table *wait)
{
struct rfkill_data *data = file->private_data;
- __poll_t res = POLLOUT | POLLWRNORM;
+ __poll_t res = EPOLLOUT | EPOLLWRNORM;
poll_wait(file, &data->read_wait, wait);
mutex_lock(&data->mtx);
if (!list_empty(&data->events))
- res = POLLIN | POLLRDNORM;
+ res = EPOLLIN | EPOLLRDNORM;
mutex_unlock(&data->mtx);
return res;
/* the socket is readable if there are any messages waiting on the Rx
* queue */
if (!list_empty(&rx->recvmsg_q))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* the socket is writable if there is space to add new data to the
* socket; there is no guarantee that any particular call in progress
* on the socket may have space in the Tx ACK window */
if (rxrpc_writable(sk))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
* can be skipped if we find a follow-on call. The first DATA packet
* of the follow on call will implicitly ACK this call.
*/
- if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
+ if (call->completion == RXRPC_CALL_SUCCEEDED &&
+ test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
unsigned long final_ack_at = jiffies + 2;
WRITE_ONCE(chan->final_ack_at, final_ack_at);
case -EKEYEXPIRED:
case -EKEYREJECTED:
goto protocol_error;
+ case -ENOMEM:
case -EAGAIN:
goto requeue_and_leave;
case -ECONNABORTED:
* through the channel, whilst disposing of the actual call record.
*/
trace_rxrpc_disconnect_call(call);
- if (call->abort_code) {
- chan->last_abort = call->abort_code;
- chan->last_type = RXRPC_PACKET_TYPE_ABORT;
- } else {
+ switch (call->completion) {
+ case RXRPC_CALL_SUCCEEDED:
chan->last_seq = call->rx_hard_ack;
chan->last_type = RXRPC_PACKET_TYPE_ACK;
+ break;
+ case RXRPC_CALL_LOCALLY_ABORTED:
+ chan->last_abort = call->abort_code;
+ chan->last_type = RXRPC_PACKET_TYPE_ABORT;
+ break;
+ default:
+ chan->last_abort = RX_USER_ABORT;
+ chan->last_type = RXRPC_PACKET_TYPE_ABORT;
+ break;
}
+
/* Sync with rxrpc_conn_retransmit(). */
smp_wmb();
chan->last_call = chan->call_id;
{
const struct rxrpc_key_token *token;
struct rxkad_challenge challenge;
- struct rxkad_response resp
- __attribute__((aligned(8))); /* must be aligned for crypto */
+ struct rxkad_response *resp;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
const char *eproto;
u32 version, nonce, min_level, abort_code;
token = conn->params.key->payload.data[0];
/* build the response packet */
- memset(&resp, 0, sizeof(resp));
-
- resp.version = htonl(RXKAD_VERSION);
- resp.encrypted.epoch = htonl(conn->proto.epoch);
- resp.encrypted.cid = htonl(conn->proto.cid);
- resp.encrypted.securityIndex = htonl(conn->security_ix);
- resp.encrypted.inc_nonce = htonl(nonce + 1);
- resp.encrypted.level = htonl(conn->params.security_level);
- resp.kvno = htonl(token->kad->kvno);
- resp.ticket_len = htonl(token->kad->ticket_len);
-
- resp.encrypted.call_id[0] = htonl(conn->channels[0].call_counter);
- resp.encrypted.call_id[1] = htonl(conn->channels[1].call_counter);
- resp.encrypted.call_id[2] = htonl(conn->channels[2].call_counter);
- resp.encrypted.call_id[3] = htonl(conn->channels[3].call_counter);
+ resp = kzalloc(sizeof(struct rxkad_response), GFP_NOFS);
+ if (!resp)
+ return -ENOMEM;
+
+ resp->version = htonl(RXKAD_VERSION);
+ resp->encrypted.epoch = htonl(conn->proto.epoch);
+ resp->encrypted.cid = htonl(conn->proto.cid);
+ resp->encrypted.securityIndex = htonl(conn->security_ix);
+ resp->encrypted.inc_nonce = htonl(nonce + 1);
+ resp->encrypted.level = htonl(conn->params.security_level);
+ resp->kvno = htonl(token->kad->kvno);
+ resp->ticket_len = htonl(token->kad->ticket_len);
+ resp->encrypted.call_id[0] = htonl(conn->channels[0].call_counter);
+ resp->encrypted.call_id[1] = htonl(conn->channels[1].call_counter);
+ resp->encrypted.call_id[2] = htonl(conn->channels[2].call_counter);
+ resp->encrypted.call_id[3] = htonl(conn->channels[3].call_counter);
/* calculate the response checksum and then do the encryption */
- rxkad_calc_response_checksum(&resp);
- rxkad_encrypt_response(conn, &resp, token->kad);
- return rxkad_send_response(conn, &sp->hdr, &resp, token->kad);
+ rxkad_calc_response_checksum(resp);
+ rxkad_encrypt_response(conn, resp, token->kad);
+ ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad);
+ kfree(resp);
+ return ret;
protocol_error:
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
struct sk_buff *skb,
u32 *_abort_code)
{
- struct rxkad_response response
- __attribute__((aligned(8))); /* must be aligned for crypto */
+ struct rxkad_response *response;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt session_key;
const char *eproto;
_enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
+ ret = -ENOMEM;
+ response = kzalloc(sizeof(struct rxkad_response), GFP_NOFS);
+ if (!response)
+ goto temporary_error;
+
eproto = tracepoint_string("rxkad_rsp_short");
abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
- &response, sizeof(response)) < 0)
+ response, sizeof(*response)) < 0)
goto protocol_error;
- if (!pskb_pull(skb, sizeof(response)))
+ if (!pskb_pull(skb, sizeof(*response)))
BUG();
- version = ntohl(response.version);
- ticket_len = ntohl(response.ticket_len);
- kvno = ntohl(response.kvno);
+ version = ntohl(response->version);
+ ticket_len = ntohl(response->ticket_len);
+ kvno = ntohl(response->kvno);
_proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }",
sp->hdr.serial, version, kvno, ticket_len);
ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
&expiry, _abort_code);
if (ret < 0)
- goto temporary_error_free;
+ goto temporary_error_free_resp;
/* use the session key from inside the ticket to decrypt the
* response */
- rxkad_decrypt_response(conn, &response, &session_key);
+ rxkad_decrypt_response(conn, response, &session_key);
eproto = tracepoint_string("rxkad_rsp_param");
abort_code = RXKADSEALEDINCON;
- if (ntohl(response.encrypted.epoch) != conn->proto.epoch)
+ if (ntohl(response->encrypted.epoch) != conn->proto.epoch)
goto protocol_error_free;
- if (ntohl(response.encrypted.cid) != conn->proto.cid)
+ if (ntohl(response->encrypted.cid) != conn->proto.cid)
goto protocol_error_free;
- if (ntohl(response.encrypted.securityIndex) != conn->security_ix)
+ if (ntohl(response->encrypted.securityIndex) != conn->security_ix)
goto protocol_error_free;
- csum = response.encrypted.checksum;
- response.encrypted.checksum = 0;
- rxkad_calc_response_checksum(&response);
+ csum = response->encrypted.checksum;
+ response->encrypted.checksum = 0;
+ rxkad_calc_response_checksum(response);
eproto = tracepoint_string("rxkad_rsp_csum");
- if (response.encrypted.checksum != csum)
+ if (response->encrypted.checksum != csum)
goto protocol_error_free;
spin_lock(&conn->channel_lock);
for (i = 0; i < RXRPC_MAXCALLS; i++) {
struct rxrpc_call *call;
- u32 call_id = ntohl(response.encrypted.call_id[i]);
+ u32 call_id = ntohl(response->encrypted.call_id[i]);
eproto = tracepoint_string("rxkad_rsp_callid");
if (call_id > INT_MAX)
eproto = tracepoint_string("rxkad_rsp_seq");
abort_code = RXKADOUTOFSEQUENCE;
- if (ntohl(response.encrypted.inc_nonce) != conn->security_nonce + 1)
+ if (ntohl(response->encrypted.inc_nonce) != conn->security_nonce + 1)
goto protocol_error_free;
eproto = tracepoint_string("rxkad_rsp_level");
abort_code = RXKADLEVELFAIL;
- level = ntohl(response.encrypted.level);
+ level = ntohl(response->encrypted.level);
if (level > RXRPC_SECURITY_ENCRYPT)
goto protocol_error_free;
conn->params.security_level = level;
* as for a client connection */
ret = rxrpc_get_server_data_key(conn, &session_key, expiry, kvno);
if (ret < 0)
- goto temporary_error_free;
+ goto temporary_error_free_ticket;
kfree(ticket);
+ kfree(response);
_leave(" = 0");
return 0;
protocol_error_free:
kfree(ticket);
protocol_error:
+ kfree(response);
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
*_abort_code = abort_code;
return -EPROTO;
-temporary_error_free:
+temporary_error_free_ticket:
kfree(ticket);
+temporary_error_free_resp:
+ kfree(response);
temporary_error:
/* Ignore the response packet if we got a temporary error such as
* ENOMEM. We just want to send the challenge again. Note that we
static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p)
{
spin_lock_bh(&idrinfo->lock);
- idr_remove_ext(&idrinfo->action_idr, p->tcfa_index);
+ idr_remove(&idrinfo->action_idr, p->tcfa_index);
spin_unlock_bh(&idrinfo->lock);
gen_kill_estimator(&p->tcfa_rate_est);
free_tcf(p);
s_i = cb->args[0];
- idr_for_each_entry_ext(idr, p, id) {
+ idr_for_each_entry_ul(idr, p, id) {
index++;
if (index < s_i)
continue;
if (nla_put_string(skb, TCA_KIND, ops->kind))
goto nla_put_failure;
- idr_for_each_entry_ext(idr, p, id) {
+ idr_for_each_entry_ul(idr, p, id) {
ret = __tcf_idr_release(p, false, true);
if (ret == ACT_P_DELETED) {
module_put(ops->owner);
struct tc_action *p = NULL;
spin_lock_bh(&idrinfo->lock);
- p = idr_find_ext(&idrinfo->action_idr, index);
+ p = idr_find(&idrinfo->action_idr, index);
spin_unlock_bh(&idrinfo->lock);
return p;
struct tcf_idrinfo *idrinfo = tn->idrinfo;
struct idr *idr = &idrinfo->action_idr;
int err = -ENOMEM;
- unsigned long idr_index;
if (unlikely(!p))
return -ENOMEM;
if (cpustats) {
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
- if (!p->cpu_bstats) {
-err1:
- kfree(p);
- return err;
- }
- p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
- if (!p->cpu_qstats) {
-err2:
- free_percpu(p->cpu_bstats);
+ if (!p->cpu_bstats)
goto err1;
- }
+ p->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
+ if (!p->cpu_qstats)
+ goto err2;
}
spin_lock_init(&p->tcfa_lock);
+ idr_preload(GFP_KERNEL);
+ spin_lock_bh(&idrinfo->lock);
/* user doesn't specify an index */
if (!index) {
- idr_preload(GFP_KERNEL);
- spin_lock_bh(&idrinfo->lock);
- err = idr_alloc_ext(idr, NULL, &idr_index, 1, 0,
- GFP_ATOMIC);
- spin_unlock_bh(&idrinfo->lock);
- idr_preload_end();
- if (err) {
-err3:
- free_percpu(p->cpu_qstats);
- goto err2;
- }
- p->tcfa_index = idr_index;
+ index = 1;
+ err = idr_alloc_u32(idr, NULL, &index, UINT_MAX, GFP_ATOMIC);
} else {
- idr_preload(GFP_KERNEL);
- spin_lock_bh(&idrinfo->lock);
- err = idr_alloc_ext(idr, NULL, NULL, index, index + 1,
- GFP_ATOMIC);
- spin_unlock_bh(&idrinfo->lock);
- idr_preload_end();
- if (err)
- goto err3;
- p->tcfa_index = index;
+ err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC);
}
+ spin_unlock_bh(&idrinfo->lock);
+ idr_preload_end();
+ if (err)
+ goto err3;
+ p->tcfa_index = index;
p->tcfa_tm.install = jiffies;
p->tcfa_tm.lastuse = jiffies;
p->tcfa_tm.firstuse = 0;
err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats,
&p->tcfa_rate_est,
&p->tcfa_lock, NULL, est);
- if (err) {
- goto err3;
- }
+ if (err)
+ goto err4;
}
p->idrinfo = idrinfo;
INIT_LIST_HEAD(&p->list);
*a = p;
return 0;
+err4:
+ idr_remove(idr, index);
+err3:
+ free_percpu(p->cpu_qstats);
+err2:
+ free_percpu(p->cpu_bstats);
+err1:
+ kfree(p);
+ return err;
}
EXPORT_SYMBOL(tcf_idr_create);
struct tcf_idrinfo *idrinfo = tn->idrinfo;
spin_lock_bh(&idrinfo->lock);
- idr_replace_ext(&idrinfo->action_idr, a, a->tcfa_index);
+ idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
spin_unlock_bh(&idrinfo->lock);
}
EXPORT_SYMBOL(tcf_idr_insert);
int ret;
unsigned long id = 1;
- idr_for_each_entry_ext(idr, p, id) {
+ idr_for_each_entry_ul(idr, p, id) {
ret = __tcf_idr_release(p, false, true);
if (ret == ACT_P_DELETED)
module_put(ops->owner);
struct tcf_net *tn = net_generic(net, tcf_net_id);
int err;
- err = idr_alloc_ext(&tn->idr, block, NULL, block_index,
- block_index + 1, GFP_KERNEL);
+ err = idr_alloc_u32(&tn->idr, block, &block_index, block_index,
+ GFP_KERNEL);
if (err)
return err;
block->index = block_index;
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
- idr_remove_ext(&tn->idr, block->index);
+ idr_remove(&tn->idr, block->index);
}
static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
{
struct tcf_net *tn = net_generic(net, tcf_net_id);
- return idr_find_ext(&tn->idr, block_index);
+ return idr_find(&tn->idr, block_index);
}
static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block)
list_for_each_entry_safe(f, n, &head->flist, link) {
list_del_rcu(&f->link);
tcf_unbind_filter(tp, &f->res);
- idr_remove_ext(&head->handle_idr, f->handle);
+ idr_remove(&head->handle_idr, f->handle);
if (tcf_exts_get_net(&f->exts))
call_rcu(&f->rcu, basic_delete_filter);
else
list_del_rcu(&f->link);
tcf_unbind_filter(tp, &f->res);
- idr_remove_ext(&head->handle_idr, f->handle);
+ idr_remove(&head->handle_idr, f->handle);
tcf_exts_get_net(&f->exts);
call_rcu(&f->rcu, basic_delete_filter);
*last = list_empty(&head->flist);
struct nlattr *tb[TCA_BASIC_MAX + 1];
struct basic_filter *fold = (struct basic_filter *) *arg;
struct basic_filter *fnew;
- unsigned long idr_index;
if (tca[TCA_OPTIONS] == NULL)
return -EINVAL;
if (err < 0)
goto errout;
- if (handle) {
- fnew->handle = handle;
- if (!fold) {
- err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index,
- handle, handle + 1, GFP_KERNEL);
- if (err)
- goto errout;
- }
- } else {
- err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index,
- 1, 0x7FFFFFFF, GFP_KERNEL);
- if (err)
- goto errout;
- fnew->handle = idr_index;
+ if (!handle) {
+ handle = 1;
+ err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+ INT_MAX, GFP_KERNEL);
+ } else if (!fold) {
+ err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+ handle, GFP_KERNEL);
}
+ if (err)
+ goto errout;
+ fnew->handle = handle;
err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr,
extack);
if (err < 0) {
if (!fold)
- idr_remove_ext(&head->handle_idr, fnew->handle);
+ idr_remove(&head->handle_idr, fnew->handle);
goto errout;
}
*arg = fnew;
if (fold) {
- idr_replace_ext(&head->handle_idr, fnew, fnew->handle);
+ idr_replace(&head->handle_idr, fnew, fnew->handle);
list_replace_rcu(&fold->link, &fnew->link);
tcf_unbind_filter(tp, &fold->res);
tcf_exts_get_net(&fold->exts);
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
- idr_remove_ext(&head->handle_idr, prog->handle);
+ idr_remove(&head->handle_idr, prog->handle);
cls_bpf_stop_offload(tp, prog, extack);
list_del_rcu(&prog->link);
tcf_unbind_filter(tp, &prog->res);
struct cls_bpf_prog *oldprog = *arg;
struct nlattr *tb[TCA_BPF_MAX + 1];
struct cls_bpf_prog *prog;
- unsigned long idr_index;
int ret;
if (tca[TCA_OPTIONS] == NULL)
}
if (handle == 0) {
- ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index,
- 1, 0x7FFFFFFF, GFP_KERNEL);
- if (ret)
- goto errout;
- prog->handle = idr_index;
- } else {
- if (!oldprog) {
- ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index,
- handle, handle + 1, GFP_KERNEL);
- if (ret)
- goto errout;
- }
- prog->handle = handle;
+ handle = 1;
+ ret = idr_alloc_u32(&head->handle_idr, prog, &handle,
+ INT_MAX, GFP_KERNEL);
+ } else if (!oldprog) {
+ ret = idr_alloc_u32(&head->handle_idr, prog, &handle,
+ handle, GFP_KERNEL);
}
+ if (ret)
+ goto errout;
+ prog->handle = handle;
+
ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr,
extack);
if (ret < 0)
prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW;
if (oldprog) {
- idr_replace_ext(&head->handle_idr, prog, handle);
+ idr_replace(&head->handle_idr, prog, handle);
list_replace_rcu(&oldprog->link, &prog->link);
tcf_unbind_filter(tp, &oldprog->res);
tcf_exts_get_net(&oldprog->exts);
cls_bpf_free_parms(prog);
errout_idr:
if (!oldprog)
- idr_remove_ext(&head->handle_idr, prog->handle);
+ idr_remove(&head->handle_idr, prog->handle);
errout:
tcf_exts_destroy(&prog->exts);
kfree(prog);
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
- idr_remove_ext(&head->handle_idr, f->handle);
+ idr_remove(&head->handle_idr, f->handle);
list_del_rcu(&f->list);
if (!tc_skip_hw(f->flags))
fl_hw_destroy_filter(tp, f, extack);
{
struct cls_fl_head *head = rtnl_dereference(tp->root);
- return idr_find_ext(&head->handle_idr, handle);
+ return idr_find(&head->handle_idr, handle);
}
static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
struct cls_fl_filter *fnew;
struct nlattr **tb;
struct fl_flow_mask mask = {};
- unsigned long idr_index;
int err;
if (!tca[TCA_OPTIONS])
goto errout;
if (!handle) {
- err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index,
- 1, 0x80000000, GFP_KERNEL);
- if (err)
- goto errout;
- fnew->handle = idr_index;
- }
-
- /* user specifies a handle and it doesn't exist */
- if (handle && !fold) {
- err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index,
- handle, handle + 1, GFP_KERNEL);
- if (err)
- goto errout;
- fnew->handle = idr_index;
+ handle = 1;
+ err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+ INT_MAX, GFP_KERNEL);
+ } else if (!fold) {
+ /* user specifies a handle and it doesn't exist */
+ err = idr_alloc_u32(&head->handle_idr, fnew, &handle,
+ handle, GFP_KERNEL);
}
+ if (err)
+ goto errout;
+ fnew->handle = handle;
if (tb[TCA_FLOWER_FLAGS]) {
fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]);
*arg = fnew;
if (fold) {
- fnew->handle = handle;
- idr_replace_ext(&head->handle_idr, fnew, fnew->handle);
+ idr_replace(&head->handle_idr, fnew, fnew->handle);
list_replace_rcu(&fold->list, &fnew->list);
tcf_unbind_filter(tp, &fold->res);
tcf_exts_get_net(&fold->exts);
errout_idr:
if (fnew->handle)
- idr_remove_ext(&head->handle_idr, fnew->handle);
+ idr_remove(&head->handle_idr, fnew->handle);
errout:
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
return u32_lookup_key(ht, handle);
}
+/* Protected by rtnl lock */
static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr)
{
- unsigned long idr_index;
- int err;
-
- /* This is only used inside rtnl lock it is safe to increment
- * without read _copy_ update semantics
- */
- err = idr_alloc_ext(&tp_c->handle_idr, ptr, &idr_index,
- 1, 0x7FF, GFP_KERNEL);
- if (err)
+ int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL);
+ if (id < 0)
return 0;
- return (u32)(idr_index | 0x800) << 20;
+ return (id | 0x800U) << 20;
}
static struct hlist_head *tc_u_common_hash;
rtnl_dereference(n->next));
tcf_unbind_filter(tp, &n->res);
u32_remove_hw_knode(tp, n, extack);
- idr_remove_ext(&ht->handle_idr, n->handle);
+ idr_remove(&ht->handle_idr, n->handle);
if (tcf_exts_get_net(&n->exts))
call_rcu(&n->rcu, u32_delete_key_freepf_rcu);
else
if (phn == ht) {
u32_clear_hw_hnode(tp, ht, extack);
idr_destroy(&ht->handle_idr);
- idr_remove_ext(&tp_c->handle_idr, ht->handle);
+ idr_remove(&tp_c->handle_idr, ht->handle);
RCU_INIT_POINTER(*hn, ht->next);
kfree_rcu(ht, rcu);
return 0;
static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid)
{
- unsigned long idr_index;
- u32 start = htid | 0x800;
+ u32 index = htid | 0x800;
u32 max = htid | 0xFFF;
- u32 min = htid;
- if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index,
- start, max + 1, GFP_KERNEL)) {
- if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index,
- min + 1, max + 1, GFP_KERNEL))
- return max;
+ if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) {
+ index = htid + 1;
+ if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max,
+ GFP_KERNEL))
+ index = max;
}
- return (u32)idr_index;
+ return index;
}
static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
if (pins->handle == n->handle)
break;
- idr_replace_ext(&ht->handle_idr, n, n->handle);
+ idr_replace(&ht->handle_idr, n, n->handle);
RCU_INIT_POINTER(n->next, pins->next);
rcu_assign_pointer(*ins, n);
}
return -EINVAL;
}
- if (n->flags != flags) {
+ if ((n->flags ^ flags) &
+ ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW)) {
NL_SET_ERR_MSG_MOD(extack, "Key node flags do not match passed flags");
return -EINVAL;
}
return -ENOMEM;
}
} else {
- err = idr_alloc_ext(&tp_c->handle_idr, ht, NULL,
- handle, handle + 1, GFP_KERNEL);
+ err = idr_alloc_u32(&tp_c->handle_idr, ht, &handle,
+ handle, GFP_KERNEL);
if (err) {
kfree(ht);
return err;
err = u32_replace_hw_hnode(tp, ht, flags, extack);
if (err) {
- idr_remove_ext(&tp_c->handle_idr, handle);
+ idr_remove(&tp_c->handle_idr, handle);
kfree(ht);
return err;
}
return -EINVAL;
}
handle = htid | TC_U32_NODE(handle);
- err = idr_alloc_ext(&ht->handle_idr, NULL, NULL,
- handle, handle + 1,
+ err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle,
GFP_KERNEL);
if (err)
return err;
#endif
kfree(n);
erridr:
- idr_remove_ext(&ht->handle_idr, handle);
+ idr_remove(&ht->handle_idr, handle);
return err;
}
/* default uniform distribution */
if (dist == NULL)
- return (rnd % (2 * sigma)) - sigma + mu;
+ return ((rnd % (2 * sigma)) + mu) - sigma;
t = dist->table[rnd % dist->size];
x = (sigma % NETEM_DIST_SCALE) * t;
struct sctp_chunk *retval;
struct sk_buff *skb;
struct sock *sk;
+ int chunklen;
+
+ chunklen = SCTP_PAD4(sizeof(*chunk_hdr) + paylen);
+ if (chunklen > SCTP_MAX_CHUNK_LEN)
+ goto nodata;
/* No need to allocate LL here, as this is only a chunk. */
- skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp);
+ skb = alloc_skb(chunklen, gfp);
if (!skb)
goto nodata;
*/
if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))
return (!list_empty(&sp->ep->asocs)) ?
- (POLLIN | POLLRDNORM) : 0;
+ (EPOLLIN | EPOLLRDNORM) : 0;
mask = 0;
/* Is there any exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR |
- (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+ mask |= EPOLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/* Is it readable? Reconsider this code with TCP-style support. */
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* The association is either gone or not ready. */
if (!sctp_style(sk, UDP) && sctp_sstate(sk, CLOSED))
/* Is it writable? */
if (sctp_writeable(sk)) {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
} else {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
/*
* in the following code to cover it as well.
*/
if (sctp_writeable(sk))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
return mask;
}
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
- POLLRDNORM | POLLRDBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
+ EPOLLRDNORM | EPOLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
rcu_read_unlock();
}
static __poll_t smc_accept_poll(struct sock *parent)
{
struct smc_sock *isk = smc_sk(parent);
- int mask = 0;
+ __poll_t mask = 0;
spin_lock(&isk->accept_q_lock);
if (!list_empty(&isk->accept_q))
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
spin_unlock(&isk->accept_q_lock);
return mask;
int rc;
if (!sk)
- return POLLNVAL;
+ return EPOLLNVAL;
smc = smc_sk(sock->sk);
sock_hold(sk);
mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
/* if non-blocking connect finished ... */
lock_sock(sk);
- if ((sk->sk_state == SMC_INIT) && (mask & POLLOUT)) {
+ if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) {
sk->sk_err = smc->clcsock->sk->sk_err;
if (sk->sk_err) {
- mask |= POLLERR;
+ mask |= EPOLLERR;
} else {
rc = smc_connect_rdma(smc);
if (rc < 0)
- mask |= POLLERR;
+ mask |= EPOLLERR;
/* success cases including fallback */
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
}
} else {
lock_sock(sk);
}
if (sk->sk_err)
- mask |= POLLERR;
+ mask |= EPOLLERR;
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
(sk->sk_state == SMC_CLOSED))
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_state == SMC_LISTEN) {
/* woken up by sk_data_ready in smc_listen_work() */
mask = smc_accept_poll(sk);
} else {
if (atomic_read(&smc->conn.sndbuf_space) ||
sk->sk_shutdown & SEND_SHUTDOWN) {
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
} else {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
}
if (atomic_read(&smc->conn.bytes_to_rcv))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLIN | POLLRDNORM | POLLRDHUP;
+ mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
if (sk->sk_state == SMC_APPCLOSEWAIT1)
- mask |= POLLIN;
+ mask |= EPOLLIN;
}
}
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI |
- POLLRDNORM | POLLRDBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
+ EPOLLRDNORM | EPOLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
(sk->sk_state == SMC_CLOSED))
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_poll(&wq->wait,
- POLLOUT | POLLWRNORM |
- POLLWRBAND);
+ EPOLLOUT | EPOLLWRNORM |
+ EPOLLWRBAND);
if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
rcu_read_unlock();
poll_wait(filp, &queue_wait, wait);
/* alway allow write */
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
if (!rp)
return mask;
for (cq= &rp->q; &cq->list != &cd->queue;
cq = list_entry(cq->list.next, struct cache_queue, list))
if (!cq->reader) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
break;
}
spin_unlock(&queue_lock);
{
struct inode *inode = file_inode(filp);
struct rpc_inode *rpci = RPC_I(inode);
- __poll_t mask = POLLOUT | POLLWRNORM;
+ __poll_t mask = EPOLLOUT | EPOLLWRNORM;
poll_wait(filp, &rpci->waitq, wait);
inode_lock(inode);
if (rpci->pipe == NULL)
- mask |= POLLERR | POLLHUP;
+ mask |= EPOLLERR | EPOLLHUP;
else if (filp->private_data || !list_empty(&rpci->pipe->pipe))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
inode_unlock(inode);
return mask;
}
rpc_wake_up_task_on_wq_queue_locked(rpciod_workqueue, queue, task);
}
+/*
+ * Wake up a task on a specific queue
+ */
+void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq,
+ struct rpc_wait_queue *queue,
+ struct rpc_task *task)
+{
+ spin_lock_bh(&queue->lock);
+ rpc_wake_up_task_on_wq_queue_locked(wq, queue, task);
+ spin_unlock_bh(&queue->lock);
+}
+
/*
* Wake up a task on a specific queue
*/
* Create the rpciod thread and wait for it to start.
*/
dprintk("RPC: creating workqueue rpciod\n");
- wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 0);
+ wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
if (!wq)
goto out_failed;
rpciod_workqueue = wq;
/* Note: highpri because network receive is latency sensitive */
- wq = alloc_workqueue("xprtiod", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+ wq = alloc_workqueue("xprtiod", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_HIGHPRI, 0);
if (!wq)
goto free_rpciod;
xprtiod_workqueue = wq;
static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
unsigned int rcv)
{
-#if 0
- mm_segment_t oldfs;
- oldfs = get_fs(); set_fs(KERNEL_DS);
- sock_setsockopt(sock, SOL_SOCKET, SO_SNDBUF,
- (char*)&snd, sizeof(snd));
- sock_setsockopt(sock, SOL_SOCKET, SO_RCVBUF,
- (char*)&rcv, sizeof(rcv));
-#else
- /* sock_setsockopt limits use to sysctl_?mem_max,
- * which isn't acceptable. Until that is made conditional
- * on not having CAP_SYS_RESOURCE or similar, we go direct...
- * DaveM said I could!
- */
lock_sock(sock->sk);
sock->sk->sk_sndbuf = snd * 2;
sock->sk->sk_rcvbuf = rcv * 2;
sock->sk->sk_write_space(sock->sk);
release_sock(sock->sk);
-#endif
}
static int svc_sock_secure_port(struct svc_rqst *rqstp)
if (xprt->snd_task) {
dprintk("RPC: write space: waking waiting task on "
"xprt %p\n", xprt);
- rpc_wake_up_queued_task(&xprt->pending, xprt->snd_task);
+ rpc_wake_up_queued_task_on_wq(xprtiod_workqueue,
+ &xprt->pending, xprt->snd_task);
}
spin_unlock_bh(&xprt->transport_lock);
}
if (xdr->page_len) {
remaining = xdr->page_len;
offset = offset_in_page(xdr->page_base);
- count = 0;
+ count = RPCRDMA_MIN_SEND_SGES;
while (remaining) {
remaining -= min_t(unsigned int,
PAGE_SIZE - offset, remaining);
out_notfound:
dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n",
xprt, be32_to_cpu(xid));
-
goto out_unlock;
}
if (ret < 0)
goto out_err;
- ret = svc_rdma_repost_recv(rdma, GFP_NOIO);
- if (ret)
- goto out_err;
-
/* Bump page refcnt so Send completion doesn't release
* the rq_buffer before all retransmits are complete.
*/
struct page *page;
int ret;
- ret = svc_rdma_repost_recv(xprt, GFP_KERNEL);
- if (ret)
- return;
-
page = alloc_page(GFP_KERNEL);
if (!page)
return;
ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p,
&rqstp->rq_arg);
svc_rdma_put_context(ctxt, 0);
- if (ret)
- goto repost;
return ret;
}
out_drop:
svc_rdma_put_context(ctxt, 1);
-repost:
- return svc_rdma_repost_recv(rdma_xprt, GFP_KERNEL);
+ return 0;
}
head->arg.head[0].iov_len - info->ri_position;
head->arg.head[0].iov_len = info->ri_position;
- /* Read chunk may need XDR roundup (see RFC 5666, s. 3.7).
+ /* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
*
- * NFSv2/3 write decoders need the length of the tail to
- * contain the size of the roundup padding.
+ * If the client already rounded up the chunk length, the
+ * length does not change. Otherwise, the length of the page
+ * list is increased to include XDR round-up.
+ *
+ * Currently these chunks always start at page offset 0,
+ * thus the rounded-up length never crosses a page boundary.
*/
- head->arg.tail[0].iov_len += 4 - (info->ri_chunklen & 3);
+ info->ri_chunklen = XDR_QUADLEN(info->ri_chunklen) << 2;
head->arg.page_len = info->ri_chunklen;
head->arg.len += info->ri_chunklen;
svc_rdma_xdr_encode_reply_chunk(rdma_resp, rp_ch, ret);
}
- ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
- if (ret)
- goto err1;
ret = svc_rdma_send_reply_msg(rdma, rdma_argp, rdma_resp, rqstp,
wr_lst, rp_ch);
if (ret < 0)
if (ret != -E2BIG && ret != -EINVAL)
goto err1;
- ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
- if (ret)
- goto err1;
ret = svc_rdma_send_error_msg(rdma, rdma_resp, rqstp);
if (ret < 0)
goto err0;
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
+static int svc_rdma_post_recv(struct svcxprt_rdma *xprt);
static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *, int);
static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
struct net *net,
list_add_tail(&ctxt->list, &xprt->sc_rq_dto_q);
spin_unlock(&xprt->sc_rq_dto_lock);
+ svc_rdma_post_recv(xprt);
+
set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
if (test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags))
goto out;
return cma_xprt;
}
-int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
+static int
+svc_rdma_post_recv(struct svcxprt_rdma *xprt)
{
struct ib_recv_wr recv_wr, *bad_recv_wr;
struct svc_rdma_op_ctxt *ctxt;
pr_err("svcrdma: Too many sges (%d)\n", sge_no);
goto err_put_ctxt;
}
- page = alloc_page(flags);
+ page = alloc_page(GFP_KERNEL);
if (!page)
goto err_put_ctxt;
ctxt->pages[sge_no] = page;
return -ENOMEM;
}
-int svc_rdma_repost_recv(struct svcxprt_rdma *xprt, gfp_t flags)
-{
- int ret = 0;
-
- ret = svc_rdma_post_recv(xprt, flags);
- if (ret) {
- pr_err("svcrdma: could not post a receive buffer, err=%d.\n",
- ret);
- pr_err("svcrdma: closing transport %p.\n", xprt);
- set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
- ret = -ENOTCONN;
- }
- return ret;
-}
-
static void
svc_rdma_parse_connect_private(struct svcxprt_rdma *newxprt,
struct rdma_conn_param *param)
/* Post receive buffers */
for (i = 0; i < newxprt->sc_max_requests; i++) {
- ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
+ ret = svc_rdma_post_recv(newxprt);
if (ret) {
dprintk("svcrdma: failure posting receive buffers\n");
goto errout;
pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge);
return -ENOMEM;
}
- ia->ri_max_send_sges = max_sge - RPCRDMA_MIN_SEND_SGES;
+ ia->ri_max_send_sges = max_sge;
if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) {
dprintk("RPC: %s: insufficient wqe's available\n",
static void
rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb)
{
+ if (!rb)
+ return;
+
if (!rpcrdma_regbuf_is_mapped(rb))
return;
void
rpcrdma_free_regbuf(struct rpcrdma_regbuf *rb)
{
- if (!rb)
- return;
-
rpcrdma_dma_unmap_regbuf(rb);
kfree(rb);
}
smp_mb__after_atomic();
}
-static void xs_sock_mark_closed(struct rpc_xprt *xprt)
-{
- xs_sock_reset_connection_flags(xprt);
- /* Mark transport as closed and wake up all pending tasks */
- xprt_disconnect_done(xprt);
-}
-
/**
* xs_error_report - callback to handle TCP socket state errors
* @sk: socket
err = -sk->sk_err;
if (err == 0)
goto out;
- /* Is this a reset event? */
- if (sk->sk_state == TCP_CLOSE)
- xs_sock_mark_closed(xprt);
dprintk("RPC: xs_error_report client %p, error=%d...\n",
xprt, -err);
trace_rpc_socket_error(xprt, sk->sk_socket, err);
/* Suck it into the iovec, verify checksum if not done by hw. */
if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) {
- __UDPX_INC_STATS(sk, UDP_MIB_INERRORS);
spin_lock(&xprt->recv_lock);
+ __UDPX_INC_STATS(sk, UDP_MIB_INERRORS);
goto out_unpin;
}
- __UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS);
spin_lock_bh(&xprt->transport_lock);
xprt_adjust_cwnd(xprt, task, copied);
spin_unlock_bh(&xprt->transport_lock);
spin_lock(&xprt->recv_lock);
xprt_complete_rqst(task, copied);
+ __UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS);
out_unpin:
xprt_unpin_rqst(rovr);
out_unlock:
if (test_and_clear_bit(XPRT_SOCK_CONNECTING,
&transport->sock_state))
xprt_clear_connecting(xprt);
+ clear_bit(XPRT_CLOSING, &xprt->state);
if (sk->sk_err)
xprt_wake_pending_tasks(xprt, -sk->sk_err);
- xs_sock_mark_closed(xprt);
+ /* Trigger the socket release */
+ xs_tcp_force_close(xprt);
}
out:
read_unlock_bh(&sk->sk_callback_lock);
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct socket *sock = transport->sock;
+ int skst = transport->inet ? transport->inet->sk_state : TCP_CLOSE;
if (sock == NULL)
return;
- if (xprt_connected(xprt)) {
+ switch (skst) {
+ default:
kernel_sock_shutdown(sock, SHUT_RDWR);
trace_rpc_socket_shutdown(xprt, sock);
- } else
+ break;
+ case TCP_CLOSE:
+ case TCP_TIME_WAIT:
xs_reset_transport(transport);
+ }
}
static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt,
int msz, hsz;
/* Ensure that flow control ratio condition is satisfied */
- if (unlikely(skb->truesize / buf_roundup_len(skb) > 4)) {
- skb = skb_copy(skb, GFP_ATOMIC);
+ if (unlikely(skb->truesize / buf_roundup_len(skb) >= 4)) {
+ skb = skb_copy_expand(skb, BUF_HEADROOM, 0, GFP_ATOMIC);
if (!skb)
return false;
kfree_skb(*_skb);
sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- revents |= POLLRDHUP | POLLIN | POLLRDNORM;
+ revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- revents |= POLLHUP;
+ revents |= EPOLLHUP;
switch (sk->sk_state) {
case TIPC_ESTABLISHED:
case TIPC_CONNECTING:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
- revents |= POLLOUT;
+ revents |= EPOLLOUT;
/* fall thru' */
case TIPC_LISTEN:
if (!skb_queue_empty(&sk->sk_receive_queue))
- revents |= POLLIN | POLLRDNORM;
+ revents |= EPOLLIN | EPOLLRDNORM;
break;
case TIPC_OPEN:
if (tsk->group_is_open && !tsk->cong_link_cnt)
- revents |= POLLOUT;
+ revents |= EPOLLOUT;
if (!tipc_sk_type_connectionless(sk))
break;
if (skb_queue_empty(&sk->sk_receive_queue))
break;
- revents |= POLLIN | POLLRDNORM;
+ revents |= EPOLLIN | EPOLLRDNORM;
break;
case TIPC_DISCONNECTING:
- revents = POLLIN | POLLRDNORM | POLLHUP;
+ revents = EPOLLIN | EPOLLRDNORM | EPOLLHUP;
break;
}
return revents;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
- POLLWRNORM | POLLWRBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
+ EPOLLWRNORM | EPOLLWRBAND);
rcu_read_unlock();
}
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
- wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
- POLLRDNORM | POLLRDBAND);
+ wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN |
+ EPOLLRDNORM | EPOLLRDBAND);
rcu_read_unlock();
}
static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
.name = "tls",
+ .uid = TCP_ULP_TLS,
+ .user_visible = true,
.owner = THIS_MODULE,
.init = tls_init,
};
{
unix_dgram_peer_wake_disconnect(sk, other);
wake_up_interruptible_poll(sk_sleep(sk),
- POLLOUT |
- POLLWRNORM |
- POLLWRBAND);
+ EPOLLOUT |
+ EPOLLWRNORM |
+ EPOLLWRBAND);
}
/* preconditions:
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait,
- POLLOUT | POLLWRNORM | POLLWRBAND);
+ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
rcu_read_unlock();
if (wq_has_sleeper(&u->peer_wait))
wake_up_interruptible_sync_poll(&u->peer_wait,
- POLLOUT | POLLWRNORM |
- POLLWRBAND);
+ EPOLLOUT | EPOLLWRNORM |
+ EPOLLWRBAND);
if (msg->msg_name)
unix_copy_addr(msg, skb->sk);
/* exceptional events? */
if (sk->sk_err)
- mask |= POLLERR;
+ mask |= EPOLLERR;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
/* readable? */
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
sk->sk_state == TCP_CLOSE)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/*
* we set writable also when the other side has shut down the
* connection. This prevents stuck sockets.
*/
if (unix_writable(sk))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
return mask;
}
/* exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
- mask |= POLLERR |
- (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+ mask |= EPOLLERR |
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/* readable? */
if (!skb_queue_empty(&sk->sk_receive_queue))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (sk->sk_type == SOCK_SEQPACKET) {
if (sk->sk_state == TCP_CLOSE)
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
/* connection hasn't started yet? */
if (sk->sk_state == TCP_SYN_SENT)
return mask;
}
/* No write status requested, avoid expensive OUT tests. */
- if (!(poll_requested_events(wait) & (POLLWRBAND|POLLWRNORM|POLLOUT)))
+ if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT)))
return mask;
writable = unix_writable(sk);
}
if (writable)
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
else
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
if (sk->sk_err)
/* Signify that there has been an error on this socket. */
- mask |= POLLERR;
+ mask |= EPOLLERR;
/* INET sockets treat local write shutdown and peer write shutdown as a
- * case of POLLHUP set.
+ * case of EPOLLHUP set.
*/
if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
((sk->sk_shutdown & SEND_SHUTDOWN) &&
(vsk->peer_shutdown & SEND_SHUTDOWN))) {
- mask |= POLLHUP;
+ mask |= EPOLLHUP;
}
if (sk->sk_shutdown & RCV_SHUTDOWN ||
vsk->peer_shutdown & SEND_SHUTDOWN) {
- mask |= POLLRDHUP;
+ mask |= EPOLLRDHUP;
}
if (sock->type == SOCK_DGRAM) {
*/
if (!skb_queue_empty(&sk->sk_receive_queue) ||
(sk->sk_shutdown & RCV_SHUTDOWN)) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (!(sk->sk_shutdown & SEND_SHUTDOWN))
- mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+ mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
} else if (sock->type == SOCK_STREAM) {
lock_sock(sk);
*/
if (sk->sk_state == TCP_LISTEN
&& !vsock_is_accept_queue_empty(sk))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
/* If there is something in the queue then we can read. */
if (transport->stream_is_active(vsk) &&
int ret = transport->notify_poll_in(
vsk, 1, &data_ready_now);
if (ret < 0) {
- mask |= POLLERR;
+ mask |= EPOLLERR;
} else {
if (data_ready_now)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
}
*/
if (sk->sk_shutdown & RCV_SHUTDOWN ||
vsk->peer_shutdown & SEND_SHUTDOWN) {
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
/* Connected sockets that can produce data can be written. */
int ret = transport->notify_poll_out(
vsk, 1, &space_avail_now);
if (ret < 0) {
- mask |= POLLERR;
+ mask |= EPOLLERR;
} else {
if (space_avail_now)
- /* Remove POLLWRBAND since INET
+ /* Remove EPOLLWRBAND since INET
* sockets are not setting it.
*/
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
}
}
/* Simulate INET socket poll behaviors, which sets
- * POLLOUT|POLLWRNORM when peer is closed and nothing to read,
+ * EPOLLOUT|EPOLLWRNORM when peer is closed and nothing to read,
* but local send is not shutdown.
*/
if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) {
if (!(sk->sk_shutdown & SEND_SHUTDOWN))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
x = devm_ioport_map(...)
)
+@safe depends on context || org || report exists@
+expression x;
+position p;
+@@
+
+(
+ x = kmalloc(...)
+|
+ x = kvasprintf(...)
+|
+ x = kasprintf(...)
+|
+ x = kzalloc(...)
+|
+ x = kmalloc_array(...)
+|
+ x = kcalloc(...)
+|
+ x = kstrdup(...)
+|
+ x = kmemdup(...)
+|
+ x = get_free_pages(...)
+|
+ x = request_irq(...)
+|
+ x = ioremap(...)
+|
+ x = ioremap_nocache(...)
+|
+ x = ioport_map(...)
+)
+...
+(
+ kfree@p(x)
+|
+ kzfree@p(x)
+|
+ __krealloc@p(x, ...)
+|
+ krealloc@p(x, ...)
+|
+ free_pages@p(x, ...)
+|
+ free_page@p(x)
+|
+ free_irq@p(x)
+|
+ iounmap@p(x)
+|
+ ioport_unmap@p(x)
+)
+
@pb@
expression r.x;
-position p;
+position p != safe.p;
@@
(
// The following three rules are duplicates of ifm, pr1 and pr2 respectively.
// It is need because the previous rule as already made a "change".
-@ifm1@
+@ifm1 depends on context && !org && !report@
expression *E;
statement S1,S2;
position p1;
if@p1 ((E == NULL && ...) || ...) S1 else S2
-@pr11 expression@
+@pr11 depends on context && !org && !report expression@
expression *ifm1.E;
identifier f;
position p1;
(E != NULL && ...) ? <+...E->f@p1...+> : ...
-@pr12 expression@
+@pr12 depends on context && !org && !report expression@
expression *ifm1.E;
identifier f;
position p2;
#include "predict.h"
#include "ipa-utils.h"
+#if BUILDING_GCC_VERSION >= 8000
+#include "stringpool.h"
+#endif
+
#if BUILDING_GCC_VERSION >= 4009
#include "attribs.h"
#include "varasm.h"
return NULL_TREE;
}
-static struct attribute_spec latent_entropy_attr = {
- .name = "latent_entropy",
- .min_length = 0,
- .max_length = 0,
- .decl_required = true,
- .type_required = false,
- .function_type_required = false,
- .handler = handle_latent_entropy_attribute,
-#if BUILDING_GCC_VERSION >= 4007
- .affects_type_identity = false
-#endif
-};
+static struct attribute_spec latent_entropy_attr = { };
static void register_attributes(void *event_data __unused, void *data __unused)
{
+ latent_entropy_attr.name = "latent_entropy";
+ latent_entropy_attr.decl_required = true;
+ latent_entropy_attr.handler = handle_latent_entropy_attribute;
+
register_attribute(&latent_entropy_attr);
}
return;
}
-static struct attribute_spec randomize_layout_attr = {
- .name = "randomize_layout",
- // related to args
- .min_length = 0,
- .max_length = 0,
- .decl_required = false,
- // need type declaration
- .type_required = true,
- .function_type_required = false,
- .handler = handle_randomize_layout_attr,
-#if BUILDING_GCC_VERSION >= 4007
- .affects_type_identity = true
-#endif
-};
+static struct attribute_spec randomize_layout_attr = { };
+static struct attribute_spec no_randomize_layout_attr = { };
+static struct attribute_spec randomize_considered_attr = { };
+static struct attribute_spec randomize_performed_attr = { };
-static struct attribute_spec no_randomize_layout_attr = {
- .name = "no_randomize_layout",
- // related to args
- .min_length = 0,
- .max_length = 0,
- .decl_required = false,
- // need type declaration
- .type_required = true,
- .function_type_required = false,
- .handler = handle_randomize_layout_attr,
+static void register_attributes(void *event_data, void *data)
+{
+ randomize_layout_attr.name = "randomize_layout";
+ randomize_layout_attr.type_required = true;
+ randomize_layout_attr.handler = handle_randomize_layout_attr;
#if BUILDING_GCC_VERSION >= 4007
- .affects_type_identity = true
+ randomize_layout_attr.affects_type_identity = true;
#endif
-};
-static struct attribute_spec randomize_considered_attr = {
- .name = "randomize_considered",
- // related to args
- .min_length = 0,
- .max_length = 0,
- .decl_required = false,
- // need type declaration
- .type_required = true,
- .function_type_required = false,
- .handler = handle_randomize_considered_attr,
+ no_randomize_layout_attr.name = "no_randomize_layout";
+ no_randomize_layout_attr.type_required = true;
+ no_randomize_layout_attr.handler = handle_randomize_layout_attr;
#if BUILDING_GCC_VERSION >= 4007
- .affects_type_identity = false
+ no_randomize_layout_attr.affects_type_identity = true;
#endif
-};
-static struct attribute_spec randomize_performed_attr = {
- .name = "randomize_performed",
- // related to args
- .min_length = 0,
- .max_length = 0,
- .decl_required = false,
- // need type declaration
- .type_required = true,
- .function_type_required = false,
- .handler = handle_randomize_performed_attr,
-#if BUILDING_GCC_VERSION >= 4007
- .affects_type_identity = false
-#endif
-};
+ randomize_considered_attr.name = "randomize_considered";
+ randomize_considered_attr.type_required = true;
+ randomize_considered_attr.handler = handle_randomize_considered_attr;
+
+ randomize_performed_attr.name = "randomize_performed";
+ randomize_performed_attr.type_required = true;
+ randomize_performed_attr.handler = handle_randomize_performed_attr;
-static void register_attributes(void *event_data, void *data)
-{
register_attribute(&randomize_layout_attr);
register_attribute(&no_randomize_layout_attr);
register_attribute(&randomize_considered_attr);
return NULL_TREE;
}
-static struct attribute_spec user_attr = {
- .name = "user",
- .min_length = 0,
- .max_length = 0,
- .decl_required = false,
- .type_required = false,
- .function_type_required = false,
- .handler = handle_user_attribute,
-#if BUILDING_GCC_VERSION >= 4007
- .affects_type_identity = true
-#endif
-};
+static struct attribute_spec user_attr = { };
static void register_attributes(void *event_data, void *data)
{
+ user_attr.name = "user";
+ user_attr.handler = handle_user_attribute;
+#if BUILDING_GCC_VERSION >= 4007
+ user_attr.affects_type_identity = true;
+#endif
+
register_attribute(&user_attr);
}
#
# Generated files
#
-config*
*.lex.c
*.tab.c
*.tab.h
static int indent = 1;
static int tty_stdio;
-static int valid_stdin = 1;
static int sync_kconfig;
static int conf_cnt;
static char line[PATH_MAX];
*p-- = 0;
}
-static void check_stdin(void)
-{
- if (!valid_stdin) {
- printf(_("aborted!\n\n"));
- printf(_("Console input/output is redirected. "));
- printf(_("Run 'make oldconfig' to update configuration.\n\n"));
- exit(1);
- }
-}
-
/* Helper function to facilitate fgets() by Jean Sacren. */
static void xfgets(char *str, int size, FILE *in)
{
if (!fgets(str, size, in))
fprintf(stderr, "\nError in reading or end of file.\n");
+
+ if (!tty_stdio)
+ printf("%s", str);
}
static int conf_askvalue(struct symbol *sym, const char *def)
printf("%s\n", def);
return 0;
}
- check_stdin();
/* fall through */
case oldaskconfig:
fflush(stdout);
xfgets(line, sizeof(line), stdin);
- if (!tty_stdio)
- printf("\n");
return 1;
default:
break;
printf("/m");
if (oldval != yes && sym_tristate_within_range(sym, yes))
printf("/y");
- if (menu_has_help(menu))
- printf("/?");
- printf("] ");
+ printf("/?] ");
if (!conf_askvalue(sym, sym_get_string_value(sym)))
return 0;
strip(line);
printf("[1]: 1\n");
goto conf_childs;
}
- printf("[1-%d", cnt);
- if (menu_has_help(menu))
- printf("?");
- printf("]: ");
+ printf("[1-%d?]: ", cnt);
switch (input_mode) {
case oldconfig:
case silentoldconfig:
printf("%d\n", cnt);
break;
}
- check_stdin();
/* fall through */
case oldaskconfig:
fflush(stdout);
bindtextdomain(PACKAGE, LOCALEDIR);
textdomain(PACKAGE);
- tty_stdio = isatty(0) && isatty(1) && isatty(2);
+ tty_stdio = isatty(0) && isatty(1);
while ((opt = getopt_long(ac, av, "s", long_opts, NULL)) != -1) {
if (opt == 's') {
}
}
if (ac == optind) {
- printf(_("%s: Kconfig file missing\n"), av[0]);
+ fprintf(stderr, _("%s: Kconfig file missing\n"), av[0]);
conf_usage(progname);
exit(1);
}
if (!defconfig_file)
defconfig_file = conf_get_default_confname();
if (conf_read(defconfig_file)) {
- printf(_("***\n"
- "*** Can't find default configuration \"%s\"!\n"
- "***\n"), defconfig_file);
+ fprintf(stderr,
+ _("***\n"
+ "*** Can't find default configuration \"%s\"!\n"
+ "***\n"),
+ defconfig_file);
exit(1);
}
break;
return 1;
}
}
- valid_stdin = tty_stdio;
}
switch (input_mode) {
if (new_size > *n) {
new_size += LINE_GROWTH - 1;
new_size *= 2;
- nline = realloc(*lineptr, new_size);
+ nline = xrealloc(*lineptr, new_size);
if (!nline)
return -1;
e->right.expr = expr_copy(org->right.expr);
break;
default:
- printf("can't copy type %d\n", e->type);
+ fprintf(stderr, "can't copy type %d\n", e->type);
free(e);
e = NULL;
break;
expr_free(e->right.expr);
break;
default:
- printf("how to free type %d?\n", e->type);
+ fprintf(stderr, "how to free type %d?\n", e->type);
break;
}
free(e);
int file_write_dep(const char *name);
void *xmalloc(size_t size);
void *xcalloc(size_t nmemb, size_t size);
+void *xrealloc(void *p, size_t size);
struct gstr {
size_t len;
struct symbol * sym_lookup(const char *name, int flags);
struct symbol * sym_find(const char *name);
-const char * sym_expand_string_value(const char *in);
+char *sym_expand_string_value(const char *in);
const char * sym_escape_string_value(const char *in);
struct symbol ** sym_re_search(const char *pattern);
const char * sym_type_name(enum symbol_type type);
*
*/
#include "nconf.h"
+#include "lkc.h"
/* a list of all the different widgets we use */
attributes_t attributes[ATTR_MAX+1] = {0};
if (strlen(init)+1 > *result_len) {
*result_len = strlen(init)+1;
- *resultp = result = realloc(result, *result_len);
+ *resultp = result = xrealloc(result, *result_len);
}
/* find the widest line of msg: */
sym->curr.tri = no;
return;
}
- if (!sym_is_choice_value(sym))
- sym->flags &= ~SYMBOL_WRITE;
+ sym->flags &= ~SYMBOL_WRITE;
sym_calc_visibility(sym);
+ if (sym->visible != no)
+ sym->flags |= SYMBOL_WRITE;
+
/* set default if recursively called */
sym->curr = newval;
/* if the symbol is visible use the user value
* if available, otherwise try the default value
*/
- sym->flags |= SYMBOL_WRITE;
if (sym_has_value(sym)) {
newval.tri = EXPR_AND(sym->def[S_DEF_USER].tri,
sym->visible);
case S_STRING:
case S_HEX:
case S_INT:
- if (sym->visible != no) {
- sym->flags |= SYMBOL_WRITE;
- if (sym_has_value(sym)) {
- newval.val = sym->def[S_DEF_USER].val;
- break;
- }
+ if (sym->visible != no && sym_has_value(sym)) {
+ newval.val = sym->def[S_DEF_USER].val;
+ break;
}
prop = sym_get_default_prop(sym);
if (prop) {
* name to be expanded shall be prefixed by a '$'. Unknown symbol expands to
* the empty string.
*/
-const char *sym_expand_string_value(const char *in)
+char *sym_expand_string_value(const char *in)
{
const char *src;
char *res;
newlen = strlen(res) + strlen(symval) + strlen(src) + 1;
if (newlen > reslen) {
reslen = newlen;
- res = realloc(res, reslen);
+ res = xrealloc(res, reslen);
}
strcat(res, symval);
default:
break;
}
- printf("Oops! How to check %d?\n", e->type);
+ fprintf(stderr, "Oops! How to check %d?\n", e->type);
return NULL;
}
struct file *file_lookup(const char *name)
{
struct file *file;
- const char *file_name = sym_expand_string_value(name);
+ char *file_name = sym_expand_string_value(name);
for (file = file_list; file; file = file->next) {
if (!strcmp(name, file->name)) {
- free((void *)file_name);
+ free(file_name);
return file;
}
}
if (s) {
l = strlen(gs->s) + strlen(s) + 1;
if (l > gs->len) {
- gs->s = realloc(gs->s, l);
+ gs->s = xrealloc(gs->s, l);
gs->len = l;
}
strcat(gs->s, s);
fprintf(stderr, "Out of memory.\n");
exit(1);
}
+
+void *xrealloc(void *p, size_t size)
+{
+ p = realloc(p, size);
+ if (p)
+ return p;
+ fprintf(stderr, "Out of memory.\n");
+ exit(1);
+}
if (new_size > text_asize) {
new_size += START_STRSIZE - 1;
new_size &= -START_STRSIZE;
- text = realloc(text, new_size);
+ text = xrealloc(text, new_size);
text_asize = new_size;
}
memcpy(text + text_size, str, size);
append_string(yytext, 1);
}
\n {
- printf("%s:%d:warning: multi-line strings not supported\n", zconf_curname(), zconf_lineno());
+ fprintf(stderr,
+ "%s:%d:warning: multi-line strings not supported\n",
+ zconf_curname(), zconf_lineno());
current_file->lineno++;
BEGIN(INITIAL);
return T_EOL;
{
yyin = zconf_fopen(name);
if (!yyin) {
- printf("can't find file %s\n", name);
+ fprintf(stderr, "can't find file %s\n", name);
exit(1);
}
current_buf->state = YY_CURRENT_BUFFER;
yyin = zconf_fopen(file->name);
if (!yyin) {
- printf("%s:%d: can't open file \"%s\"\n",
- zconf_curname(), zconf_lineno(), file->name);
+ fprintf(stderr, "%s:%d: can't open file \"%s\"\n",
+ zconf_curname(), zconf_lineno(), file->name);
exit(1);
}
yy_switch_to_buffer(yy_create_buffer(yyin, YY_BUF_SIZE));
for (iter = current_file->parent; iter; iter = iter->parent ) {
if (!strcmp(current_file->name,iter->name) ) {
- printf("%s:%d: recursive inclusion detected. "
- "Inclusion path:\n current file : '%s'\n",
- zconf_curname(), zconf_lineno(),
- zconf_curname());
+ fprintf(stderr,
+ "%s:%d: recursive inclusion detected. "
+ "Inclusion path:\n current file : '%s'\n",
+ zconf_curname(), zconf_lineno(),
+ zconf_curname());
iter = current_file->parent;
while (iter && \
strcmp(iter->name,current_file->name)) {
- printf(" included from: '%s:%d'\n",
- iter->name, iter->lineno-1);
+ fprintf(stderr, " included from: '%s:%d'\n",
+ iter->name, iter->lineno-1);
iter = iter->parent;
}
if (iter)
- printf(" included from: '%s:%d'\n",
- iter->name, iter->lineno+1);
+ fprintf(stderr, " included from: '%s:%d'\n",
+ iter->name, iter->lineno+1);
exit(1);
}
}
zconfprint("warning: '%s' defined with more than one help text -- only the last one will be used",
current_entry->sym->name ?: "<choice>");
}
+
+ /* Is the help text empty or all whitespace? */
+ if ($2[strspn($2, " \f\n\r\t\v")] == '\0')
+ zconfprint("warning: '%s' defined with blank help text",
+ current_entry->sym->name ?: "<choice>");
+
current_entry->help = $2;
};
mutex_lock_nested(&rev->ns->lock, rev->ns->level);
poll_wait(file, &rev->ns->wait, pt);
if (rev->last_read < rev->ns->revision)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
mutex_unlock(&rev->ns->lock);
}
* @file: Pointer to "struct file".
* @wait: Pointer to "poll_table". Maybe NULL.
*
- * Returns POLLIN | POLLRDNORM when ready to read an audit log.
+ * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log.
*/
__poll_t tomoyo_poll_log(struct file *file, poll_table *wait)
{
if (tomoyo_log_count)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
poll_wait(file, &tomoyo_log_wait, wait);
if (tomoyo_log_count)
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
* @file: Pointer to "struct file".
* @wait: Pointer to "poll_table".
*
- * Returns POLLIN | POLLRDNORM when ready to read, 0 otherwise.
+ * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise.
*
* Waits for access requests which violated policy in enforcing mode.
*/
static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait)
{
if (!list_empty(&tomoyo_query_list))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
poll_wait(file, &tomoyo_query_wait, wait);
if (!list_empty(&tomoyo_query_list))
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
return 0;
}
* @file: Pointer to "struct file".
* @wait: Pointer to "poll_table". Maybe NULL.
*
- * Returns POLLIN | POLLRDNORM | POLLOUT | POLLWRNORM if ready to read/write,
- * POLLOUT | POLLWRNORM otherwise.
+ * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write,
+ * EPOLLOUT | EPOLLWRNORM otherwise.
*/
__poll_t tomoyo_poll_control(struct file *file, poll_table *wait)
{
struct tomoyo_io_buffer *head = file->private_data;
if (head->poll)
- return head->poll(file, wait) | POLLOUT | POLLWRNORM;
- return POLLIN | POLLRDNORM | POLLOUT | POLLWRNORM;
+ return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM;
+ return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM;
}
/**
* @file: Pointer to "struct file".
* @wait: Pointer to "poll_table". Maybe NULL.
*
- * Returns POLLIN | POLLRDNORM | POLLOUT | POLLWRNORM if ready to read/write,
- * POLLOUT | POLLWRNORM otherwise.
+ * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write,
+ * EPOLLOUT | EPOLLWRNORM otherwise.
*/
static __poll_t tomoyo_poll(struct file *file, poll_table *wait)
{
static __poll_t snd_compr_get_poll(struct snd_compr_stream *stream)
{
if (stream->direction == SND_COMPRESS_PLAYBACK)
- return POLLOUT | POLLWRNORM;
+ return EPOLLOUT | EPOLLWRNORM;
else
- return POLLIN | POLLRDNORM;
+ return EPOLLIN | EPOLLRDNORM;
}
static __poll_t snd_compr_poll(struct file *f, poll_table *wait)
__poll_t retval = 0;
if (snd_BUG_ON(!data))
- return POLLERR;
+ return EPOLLERR;
stream = &data->stream;
switch (stream->runtime->state) {
case SNDRV_PCM_STATE_OPEN:
case SNDRV_PCM_STATE_XRUN:
- retval = snd_compr_get_poll(stream) | POLLERR;
+ retval = snd_compr_get_poll(stream) | EPOLLERR;
goto out;
default:
break;
retval = snd_compr_get_poll(stream);
break;
default:
- retval = snd_compr_get_poll(stream) | POLLERR;
+ retval = snd_compr_get_poll(stream) | EPOLLERR;
break;
}
out:
mask = 0;
if (!list_empty(&ctl->events))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
data->file_private_data,
file, wait);
if (entry->c.ops->read)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (entry->c.ops->write)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
static __poll_t snd_disconnect_poll(struct file * file, poll_table * wait)
{
- return POLLERR | POLLNVAL;
+ return EPOLLERR | EPOLLNVAL;
}
static long snd_disconnect_ioctl(struct file *file,
if (runtime->status->state != SNDRV_PCM_STATE_DRAINING &&
(runtime->status->state != SNDRV_PCM_STATE_RUNNING ||
snd_pcm_oss_playback_ready(psubstream)))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
snd_pcm_stream_unlock_irq(psubstream);
}
if (csubstream != NULL) {
snd_pcm_stream_lock_irq(csubstream);
if ((ostate = runtime->status->state) != SNDRV_PCM_STATE_RUNNING ||
snd_pcm_oss_capture_ready(csubstream))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
snd_pcm_stream_unlock_irq(csubstream);
if (ostate != SNDRV_PCM_STATE_RUNNING && runtime->oss.trigger) {
struct snd_pcm_oss_file ofile;
substream = pcm_file->substream;
if (PCM_RUNTIME_CHECK(substream))
- return POLLOUT | POLLWRNORM | POLLERR;
+ return EPOLLOUT | EPOLLWRNORM | EPOLLERR;
runtime = substream->runtime;
poll_wait(file, &runtime->sleep, wait);
case SNDRV_PCM_STATE_PREPARED:
case SNDRV_PCM_STATE_PAUSED:
if (avail >= runtime->control->avail_min) {
- mask = POLLOUT | POLLWRNORM;
+ mask = EPOLLOUT | EPOLLWRNORM;
break;
}
/* Fall through */
mask = 0;
break;
default:
- mask = POLLOUT | POLLWRNORM | POLLERR;
+ mask = EPOLLOUT | EPOLLWRNORM | EPOLLERR;
break;
}
snd_pcm_stream_unlock_irq(substream);
substream = pcm_file->substream;
if (PCM_RUNTIME_CHECK(substream))
- return POLLIN | POLLRDNORM | POLLERR;
+ return EPOLLIN | EPOLLRDNORM | EPOLLERR;
runtime = substream->runtime;
poll_wait(file, &runtime->sleep, wait);
case SNDRV_PCM_STATE_PREPARED:
case SNDRV_PCM_STATE_PAUSED:
if (avail >= runtime->control->avail_min) {
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
break;
}
mask = 0;
break;
case SNDRV_PCM_STATE_DRAINING:
if (avail > 0) {
- mask = POLLIN | POLLRDNORM;
+ mask = EPOLLIN | EPOLLRDNORM;
break;
}
/* Fall through */
default:
- mask = POLLIN | POLLRDNORM | POLLERR;
+ mask = EPOLLIN | EPOLLRDNORM | EPOLLERR;
break;
}
snd_pcm_stream_unlock_irq(substream);
mask = 0;
if (rfile->input != NULL) {
if (snd_rawmidi_ready(rfile->input))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (rfile->output != NULL) {
if (snd_rawmidi_ready(rfile->output))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
return mask;
}
/* input */
if (dp->readq && is_read_mode(dp->file_mode)) {
if (snd_seq_oss_readq_poll(dp->readq, file, wait))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
/* output */
if (dp->writeq && is_write_mode(dp->file_mode)) {
if (snd_seq_kernel_client_write_poll(dp->cseq, file, wait))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
return mask;
}
/* check if data is available in the outqueue */
if (snd_seq_fifo_poll_wait(client->data.user.fifo, file, wait))
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
}
if (snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT) {
/* check if data is available in the pool */
if (!snd_seq_write_pool_allocated(client) ||
snd_seq_pool_poll_wait(client->pool, file, wait))
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
}
return mask;
mask = 0;
spin_lock_irq(&tu->qlock);
if (tu->qused)
- mask |= POLLIN | POLLRDNORM;
+ mask |= EPOLLIN | EPOLLRDNORM;
if (tu->disconnected)
- mask |= POLLERR;
+ mask |= EPOLLERR;
spin_unlock_irq(&tu->qlock);
return mask;
spin_lock_irq(&bebob->lock);
if (bebob->dev_lock_changed)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&bebob->lock);
spin_lock_irq(&dice->lock);
if (dice->dev_lock_changed || dice->notification_bits != 0)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&dice->lock);
spin_lock_irq(&dg00x->lock);
if (dg00x->dev_lock_changed || dg00x->msg)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&dg00x->lock);
spin_lock_irq(&ff->lock);
if (ff->dev_lock_changed)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&ff->lock);
spin_lock_irq(&efw->lock);
if (efw->dev_lock_changed || efw->pull_ptr != efw->push_ptr)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&efw->lock);
- return events | POLLOUT;
+ return events | EPOLLOUT;
}
static int
spin_lock_irq(&motu->lock);
if (motu->dev_lock_changed || motu->msg)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&motu->lock);
- return events | POLLOUT;
+ return events | EPOLLOUT;
}
static int hwdep_get_info(struct snd_motu *motu, void __user *arg)
spin_lock_irq(&oxfw->lock);
if (oxfw->dev_lock_changed)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&oxfw->lock);
spin_lock_irq(&tscm->lock);
if (tscm->dev_lock_changed)
- events = POLLIN | POLLRDNORM;
+ events = EPOLLIN | EPOLLRDNORM;
else
events = 0;
spin_unlock_irq(&tscm->lock);
poll_wait(file, &write_sq.action_queue, wait);
if (file->f_mode & FMODE_WRITE)
if (write_sq.count < write_sq.max_active || write_sq.block_size - write_sq.rear_size > 0)
- mask |= POLLOUT | POLLWRNORM;
+ mask |= EPOLLOUT | EPOLLWRNORM;
return mask;
}
struct usb_mixer_interface *mixer = hw->private_data;
poll_wait(file, &mixer->rc_waitq, wait);
- return mixer->rc_code ? POLLIN | POLLRDNORM : 0;
+ return mixer->rc_code ? EPOLLIN | EPOLLRDNORM : 0;
}
static int snd_usb_soundblaster_remote_init(struct usb_mixer_interface *mixer)
poll_wait(file, &us122l->sk.sleep, wait);
- mask = POLLIN | POLLOUT | POLLWRNORM | POLLERR;
+ mask = EPOLLIN | EPOLLOUT | EPOLLWRNORM | EPOLLERR;
if (mutex_trylock(&us122l->mutex)) {
struct usb_stream *s = us122l->sk.s;
if (s && s->state == usb_stream_ready) {
polled = &us122l->second_periods_polled;
if (*polled != s->periods_done) {
*polled = s->periods_done;
- mask = POLLIN | POLLOUT | POLLWRNORM;
+ mask = EPOLLIN | EPOLLOUT | EPOLLWRNORM;
} else
mask = 0;
}
struct usX2Ydev *us428 = hw->private_data;
struct us428ctls_sharedmem *shm = us428->us428ctls_sharedmem;
if (us428->chip_status & USX2Y_STAT_CHIP_HUP)
- return POLLHUP;
+ return EPOLLHUP;
poll_wait(file, &us428->us428ctls_wait_queue_head, wait);
if (shm != NULL && shm->CtlSnapShotLast != shm->CtlSnapShotRed)
- mask |= POLLIN;
+ mask |= EPOLLIN;
return mask;
}
man: man8
man8: $(DOC_MAN8)
+RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+
$(OUTPUT)%.8: %.rst
+ifndef RST2MAN_DEP
+ $(error "rst2man not found, but required to generate man pages")
+endif
$(QUIET_GEN)rst2man $< > $@
clean:
| **bpftool** **cgroup help**
|
| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
-| *ATTACH_TYPE* := { *ingress* | *egress* | *sock_create* | *sock_ops* | *device* }
-| *ATTACH_FLAGS* := { *multi* | *override* }
+| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** }
+| *ATTACH_FLAGS* := { **multi** | **override** }
DESCRIPTION
===========
| **bpftool** **map help**
|
| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
-| *VALUE* := { *BYTES* | *MAP* | *PROGRAM* }
+| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+| *VALUE* := { *BYTES* | *MAP* | *PROG* }
| *UPDATE_FLAGS* := { **any** | **exist** | **noexist** }
DESCRIPTION
done
}
-# Takes a list of words in argument; adds them all to COMPREPLY if none of them
-# is already present on the command line. Returns no value.
-_bpftool_one_of_list()
+# Takes a list of words as argument; if any of those words is present on the
+# command line, return 0. Otherwise, return 1.
+_bpftool_search_list()
{
local w idx
for w in $*; do
for (( idx=3; idx < ${#words[@]}-1; idx++ )); do
- [[ $w == ${words[idx]} ]] && return 1
+ [[ $w == ${words[idx]} ]] && return 0
done
done
+ return 1
+}
+
+# Takes a list of words in argument; adds them all to COMPREPLY if none of them
+# is already present on the command line. Returns no value.
+_bpftool_one_of_list()
+{
+ _bpftool_search_list $* && return 1
COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) )
}
fi
return 0
;;
+ load)
+ _filedir
+ return 0
+ ;;
*)
[[ $prev == $object ]] && \
- COMPREPLY=( $( compgen -W 'dump help pin show list' -- \
- "$cur" ) )
+ COMPREPLY=( $( compgen -W 'dump help pin load \
+ show list' -- "$cur" ) )
;;
esac
;;
;;
esac
;;
+ cgroup)
+ case $command in
+ show|list)
+ _filedir
+ return 0
+ ;;
+ attach|detach)
+ local ATTACH_TYPES='ingress egress sock_create sock_ops \
+ device'
+ local ATTACH_FLAGS='multi override'
+ local PROG_TYPE='id pinned tag'
+ case $prev in
+ $command)
+ _filedir
+ return 0
+ ;;
+ ingress|egress|sock_create|sock_ops|device)
+ COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \
+ "$cur" ) )
+ return 0
+ ;;
+ id)
+ _bpftool_get_prog_ids
+ return 0
+ ;;
+ *)
+ if ! _bpftool_search_list "$ATTACH_TYPES"; then
+ COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- \
+ "$cur" ) )
+ elif [[ "$command" == "attach" ]]; then
+ # We have an attach type on the command line,
+ # but it is not the previous word, or
+ # "id|pinned|tag" (we already checked for
+ # that). This should only leave the case when
+ # we need attach flags for "attach" commamnd.
+ _bpftool_one_of_list "$ATTACH_FLAGS"
+ fi
+ return 0
+ ;;
+ esac
+ ;;
+ *)
+ [[ $prev == $object ]] && \
+ COMPREPLY=( $( compgen -W 'help attach detach \
+ show list' -- "$cur" ) )
+ ;;
+ esac
+ ;;
esac
} &&
complete -F _bpftool bpftool
/* ld/ldx fields */
#define BPF_SIZE(code) ((code) & 0x18)
-#define BPF_W 0x00
-#define BPF_H 0x08
-#define BPF_B 0x10
+#define BPF_W 0x00 /* 32-bit */
+#define BPF_H 0x08 /* 16-bit */
+#define BPF_B 0x10 /* 8-bit */
+/* eBPF BPF_DW 0x18 64-bit */
#define BPF_MODE(code) ((code) & 0xe0)
#define BPF_IMM 0x00
#define BPF_ABS 0x20
prog->section_name = strdup(section_name);
if (!prog->section_name) {
- pr_warning("failed to alloc name for prog under section %s\n",
- section_name);
+ pr_warning("failed to alloc name for prog under section(%d) %s\n",
+ idx, section_name);
goto errout;
}
return 0;
}
+static bool section_have_execinstr(struct bpf_object *obj, int idx)
+{
+ Elf_Scn *scn;
+ GElf_Shdr sh;
+
+ scn = elf_getscn(obj->efile.elf, idx);
+ if (!scn)
+ return false;
+
+ if (gelf_getshdr(scn, &sh) != &sh)
+ return false;
+
+ if (sh.sh_flags & SHF_EXECINSTR)
+ return true;
+
+ return false;
+}
+
static int bpf_object__elf_collect(struct bpf_object *obj)
{
Elf *elf = obj->efile.elf;
idx++;
if (gelf_getshdr(scn, &sh) != &sh) {
- pr_warning("failed to get section header from %s\n",
- obj->path);
+ pr_warning("failed to get section(%d) header from %s\n",
+ idx, obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto out;
}
name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
if (!name) {
- pr_warning("failed to get section name from %s\n",
- obj->path);
+ pr_warning("failed to get section(%d) name from %s\n",
+ idx, obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto out;
}
data = elf_getdata(scn, 0);
if (!data) {
- pr_warning("failed to get section data from %s(%s)\n",
- name, obj->path);
+ pr_warning("failed to get section(%d) data from %s(%s)\n",
+ idx, name, obj->path);
err = -LIBBPF_ERRNO__FORMAT;
goto out;
}
- pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n",
- name, (unsigned long)data->d_size,
+ pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
+ idx, name, (unsigned long)data->d_size,
(int)sh.sh_link, (unsigned long)sh.sh_flags,
(int)sh.sh_type);
} else if (sh.sh_type == SHT_REL) {
void *reloc = obj->efile.reloc;
int nr_reloc = obj->efile.nr_reloc + 1;
+ int sec = sh.sh_info; /* points to other section */
+
+ /* Only do relo for section with exec instructions */
+ if (!section_have_execinstr(obj, sec)) {
+ pr_debug("skip relo %s(%d) for section(%d)\n",
+ name, idx, sec);
+ continue;
+ }
reloc = realloc(reloc,
sizeof(*obj->efile.reloc) * nr_reloc);
obj->efile.reloc[n].shdr = sh;
obj->efile.reloc[n].data = data;
}
+ } else {
+ pr_debug("skip section(%d) %s\n", idx, name);
}
if (err)
goto out;
prog = bpf_object__find_prog_by_idx(obj, idx);
if (!prog) {
- pr_warning("relocation failed: no %d section\n",
- idx);
+ pr_warning("relocation failed: no section(%d)\n", idx);
return -LIBBPF_ERRNO__RELOC;
}
BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER),
BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE),
BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE),
+ BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS),
+ BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT),
BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT),
BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP),
BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT),
BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB),
BPF_PROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK),
BPF_PROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE),
+ BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN),
+ BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT),
+ BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT),
BPF_PROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS),
BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB),
};
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
*****************************************************************************/
/*
- * Copyright (C) 2000 - 2017, Intel Corp.
+ * Copyright (C) 2000 - 2018, Intel Corp.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
idr_destroy(&idr);
}
-void idr_get_next_test(void)
+void idr_get_next_test(int base)
{
unsigned long i;
int nextid;
DEFINE_IDR(idr);
+ idr_init_base(&idr, base);
int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0};
assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i);
}
assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i, GFP_KERNEL) == -ENOSPC);
+ assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i + 10, GFP_KERNEL) == -ENOSPC);
idr_for_each(&idr, item_idr_free, &idr);
idr_destroy(&idr);
assert(idr_is_empty(&idr));
+ idr_set_cursor(&idr, INT_MAX - 3UL);
+ for (i = INT_MAX - 3UL; i < INT_MAX + 3UL; i++) {
+ struct item *item;
+ unsigned int id;
+ if (i <= INT_MAX)
+ item = item_create(i, 0);
+ else
+ item = item_create(i - INT_MAX - 1, 0);
+
+ id = idr_alloc_cyclic(&idr, item, 0, 0, GFP_KERNEL);
+ assert(id == item->index);
+ }
+
+ idr_for_each(&idr, item_idr_free, &idr);
+ idr_destroy(&idr);
+ assert(idr_is_empty(&idr));
+
for (i = 1; i < 10000; i++) {
struct item *item = item_create(i, 0);
assert(idr_alloc(&idr, item, 1, 20000, GFP_KERNEL) == i);
idr_alloc_test();
idr_null_test();
idr_nowait_test();
- idr_get_next_test();
+ idr_get_next_test(0);
+ idr_get_next_test(1);
+ idr_get_next_test(4);
}
/*
do {
ida_pre_get(&ida, GFP_KERNEL);
err = ida_get_new_above(&ida, bit, &id);
- } while (err == -ENOMEM);
+ } while (err == -EAGAIN);
assert(!err);
assert(id == bit);
}
void ida_thread_tests(void)
{
- pthread_t threads[10];
+ pthread_t threads[20];
int i;
for (i = 0; i < ARRAY_SIZE(threads); i++)
#define pr_debug printk
#define pr_cont printk
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
-
#endif /* _KERNEL_H */
CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf -lrt -lpthread
+# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o
-TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
+# Order correspond to 'make run_tests' order
+TEST_PROGS := test_kmod.sh \
+ test_libbpf.sh \
+ test_xdp_redirect.sh \
+ test_xdp_meta.sh \
test_offload.py
+# Compile but not part of 'make run_tests'
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open
+
include ../lib.mk
BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c
$(TEST_GEN_PROGS): $(BPFOBJ)
+$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
+
.PHONY: force
# force a rebuild of BPFOBJ when its dependencies are updated
echo "[ JIT enabled:$1 hardened:$2 ]"
dmesg -C
- insmod $SRC_TREE/lib/test_bpf.ko 2> /dev/null
- if [ $? -ne 0 ]; then
- rc=1
+ if [ -f ${SRC_TREE}/lib/test_bpf.ko ]; then
+ insmod ${SRC_TREE}/lib/test_bpf.ko 2> /dev/null
+ if [ $? -ne 0 ]; then
+ rc=1
+ fi
+ else
+ # Use modprobe dry run to check for missing test_bpf module
+ if ! /sbin/modprobe -q -n test_bpf; then
+ echo "test_bpf: [SKIP]"
+ elif /sbin/modprobe -q test_bpf; then
+ echo "test_bpf: ok"
+ else
+ echo "test_bpf: [FAIL]"
+ rc=1
+ fi
fi
rmmod test_bpf 2> /dev/null
dmesg | grep FAIL
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+export TESTNAME=test_libbpf
+
+# Determine selftest success via shell exit code
+exit_handler()
+{
+ if (( $? == 0 )); then
+ echo "selftests: $TESTNAME [PASS]";
+ else
+ echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2
+ echo "selftests: $TESTNAME [FAILED]";
+ fi
+}
+
+libbpf_open_file()
+{
+ LAST_LOADED=$1
+ if [ -n "$VERBOSE" ]; then
+ ./test_libbpf_open $1
+ else
+ ./test_libbpf_open --quiet $1
+ fi
+}
+
+# Exit script immediately (well catched by trap handler) if any
+# program/thing exits with a non-zero status.
+set -e
+
+# (Use 'trap -l' to list meaning of numbers)
+trap exit_handler 0 2 3 6 9
+
+libbpf_open_file test_l4lb.o
+
+# TODO: fix libbpf to load noinline functions
+# [warning] libbpf: incorrect bpf_call opcode
+#libbpf_open_file test_l4lb_noinline.o
+
+# TODO: fix test_xdp_meta.c to load with libbpf
+# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
+#libbpf_open_file test_xdp_meta.o
+
+# TODO: fix libbpf to handle .eh_frame
+# [warning] libbpf: relocation failed: no section(10)
+#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
+
+# Success
+exit 0
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc.
+ */
+static const char *__doc__ =
+ "Libbpf test program for loading BPF ELF object files";
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdarg.h>
+#include <bpf/libbpf.h>
+#include <getopt.h>
+
+static const struct option long_options[] = {
+ {"help", no_argument, NULL, 'h' },
+ {"debug", no_argument, NULL, 'D' },
+ {"quiet", no_argument, NULL, 'q' },
+ {0, 0, NULL, 0 }
+};
+
+static void usage(char *argv[])
+{
+ int i;
+
+ printf("\nDOCUMENTATION:\n%s\n\n", __doc__);
+ printf(" Usage: %s (options-see-below) BPF_FILE\n", argv[0]);
+ printf(" Listing options:\n");
+ for (i = 0; long_options[i].name != 0; i++) {
+ printf(" --%-12s", long_options[i].name);
+ printf(" short-option: -%c",
+ long_options[i].val);
+ printf("\n");
+ }
+ printf("\n");
+}
+
+#define DEFINE_PRINT_FN(name, enabled) \
+static int libbpf_##name(const char *fmt, ...) \
+{ \
+ va_list args; \
+ int ret; \
+ \
+ va_start(args, fmt); \
+ if (enabled) { \
+ fprintf(stderr, "[" #name "] "); \
+ ret = vfprintf(stderr, fmt, args); \
+ } \
+ va_end(args); \
+ return ret; \
+}
+DEFINE_PRINT_FN(warning, 1)
+DEFINE_PRINT_FN(info, 1)
+DEFINE_PRINT_FN(debug, 1)
+
+#define EXIT_FAIL_LIBBPF EXIT_FAILURE
+#define EXIT_FAIL_OPTION 2
+
+int test_walk_progs(struct bpf_object *obj, bool verbose)
+{
+ struct bpf_program *prog;
+ int cnt = 0;
+
+ bpf_object__for_each_program(prog, obj) {
+ cnt++;
+ if (verbose)
+ printf("Prog (count:%d) section_name: %s\n", cnt,
+ bpf_program__title(prog, false));
+ }
+ return 0;
+}
+
+int test_walk_maps(struct bpf_object *obj, bool verbose)
+{
+ struct bpf_map *map;
+ int cnt = 0;
+
+ bpf_map__for_each(map, obj) {
+ cnt++;
+ if (verbose)
+ printf("Map (count:%d) name: %s\n", cnt,
+ bpf_map__name(map));
+ }
+ return 0;
+}
+
+int test_open_file(char *filename, bool verbose)
+{
+ struct bpf_object *bpfobj = NULL;
+ long err;
+
+ if (verbose)
+ printf("Open BPF ELF-file with libbpf: %s\n", filename);
+
+ /* Load BPF ELF object file and check for errors */
+ bpfobj = bpf_object__open(filename);
+ err = libbpf_get_error(bpfobj);
+ if (err) {
+ char err_buf[128];
+ libbpf_strerror(err, err_buf, sizeof(err_buf));
+ if (verbose)
+ printf("Unable to load eBPF objects in file '%s': %s\n",
+ filename, err_buf);
+ return EXIT_FAIL_LIBBPF;
+ }
+ test_walk_progs(bpfobj, verbose);
+ test_walk_maps(bpfobj, verbose);
+
+ if (verbose)
+ printf("Close BPF ELF-file with libbpf: %s\n",
+ bpf_object__name(bpfobj));
+ bpf_object__close(bpfobj);
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ char filename[1024] = { 0 };
+ bool verbose = 1;
+ int longindex = 0;
+ int opt;
+
+ libbpf_set_print(libbpf_warning, libbpf_info, NULL);
+
+ /* Parse commands line args */
+ while ((opt = getopt_long(argc, argv, "hDq",
+ long_options, &longindex)) != -1) {
+ switch (opt) {
+ case 'D':
+ libbpf_set_print(libbpf_warning, libbpf_info,
+ libbpf_debug);
+ break;
+ case 'q': /* Use in scripting mode */
+ verbose = 0;
+ break;
+ case 'h':
+ default:
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+ }
+ if (optind >= argc) {
+ usage(argv);
+ printf("ERROR: Expected BPF_FILE argument after options\n");
+ return EXIT_FAIL_OPTION;
+ }
+ snprintf(filename, sizeof(filename), "%s", argv[optind]);
+
+ return test_open_file(filename, verbose);
+}
fi
set +e
+ ip link del veth1 2> /dev/null
ip netns del ns1 2> /dev/null
ip netns del ns2 2> /dev/null
}
fi
set +e
+ ip link del veth1 2> /dev/null
+ ip link del veth2 2> /dev/null
ip netns del ns1 2> /dev/null
ip netns del ns2 2> /dev/null
}
# filter by *, end match
ftrace_filter_check 'schedule*' '^schedule.*$'
+# filter by *mid*end
+ftrace_filter_check '*aw*lock' '.*aw.*lock$'
+
+# filter by start*mid*
+ftrace_filter_check 'mutex*try*' '^mutex.*try.*'
+
# Advanced full-glob matching feature is recently supported.
# Skip the tests if we are sure the kernel does not support it.
if grep -q 'accepts: .* glob-matching-pattern' README ; then
fail "Expected $FUNC1 and $FUNC2"
fi
+test_actual() { # Compares $TMPDIR/expected with set_ftrace_filter
+ cat set_ftrace_filter | grep -v '#' | cut -d' ' -f1 | cut -d':' -f1 | sort -u > $TMPDIR/actual
+ DIFF=`diff $TMPDIR/actual $TMPDIR/expected`
+ test -z "$DIFF"
+}
+
+# Set traceoff trigger for all fuctions with "lock" in their name
+cat available_filter_functions | cut -d' ' -f1 | grep 'lock' | sort -u > $TMPDIR/expected
+echo '*lock*:traceoff' > set_ftrace_filter
+test_actual
+
+# now remove all with 'try' in it, and end with lock
+grep -v 'try.*lock$' $TMPDIR/expected > $TMPDIR/expected2
+mv $TMPDIR/expected2 $TMPDIR/expected
+echo '!*try*lock:traceoff' >> set_ftrace_filter
+test_actual
+
+# remove all that start with "m" and end with "lock"
+grep -v '^m.*lock$' $TMPDIR/expected > $TMPDIR/expected2
+mv $TMPDIR/expected2 $TMPDIR/expected
+echo '!m*lock:traceoff' >> set_ftrace_filter
+test_actual
+
+# remove all that start with "c" and have "unlock"
+grep -v '^c.*unlock' $TMPDIR/expected > $TMPDIR/expected2
+mv $TMPDIR/expected2 $TMPDIR/expected
+echo '!c*unlock*:traceoff' >> set_ftrace_filter
+test_actual
+
+# clear all the rest
+> $TMPDIR/expected
+echo '!*:traceoff' >> set_ftrace_filter
+test_actual
+
+rm $TMPDIR/expected
+rm $TMPDIR/actual
+
do_reset
exit 0
if [ "$tr" = "" ]; then
continue
fi
+ if ! grep -q "$t" set_ftrace_filter; then
+ continue;
+ fi
+ name=`echo $t | cut -d: -f1 | cut -d' ' -f1`
if [ $tr = "enable_event" -o $tr = "disable_event" ]; then
- tr=`echo $t | cut -d: -f1-4`
+ tr=`echo $t | cut -d: -f2-4`
limit=`echo $t | cut -d: -f5`
else
- tr=`echo $t | cut -d: -f1-2`
+ tr=`echo $t | cut -d: -f2`
limit=`echo $t | cut -d: -f3`
fi
if [ "$limit" != "unlimited" ]; then
tr="$tr:$limit"
fi
- echo "!$tr" > set_ftrace_filter
+ echo "!$name:$tr" > set_ftrace_filter
done
}
#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/socket.h>
+#include <sys/resource.h>
#include <unistd.h>
#ifndef ARRAY_SIZE
struct sockaddr * const saddr = new_any_sockaddr(p.send_family, sport);
struct sockaddr * const daddr =
new_loopback_sockaddr(p.send_family, p.recv_port);
- const int fd = socket(p.send_family, p.protocol, 0);
+ const int fd = socket(p.send_family, p.protocol, 0), one = 1;
if (fd < 0)
error(1, errno, "failed to create send socket");
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)))
+ error(1, errno, "failed to set reuseaddr");
+
if (bind(fd, saddr, sockaddr_size()))
error(1, errno, "failed to bind send socket");
}
}
+static struct rlimit rlim_old, rlim_new;
+
+static __attribute__((constructor)) void main_ctor(void)
+{
+ getrlimit(RLIMIT_MEMLOCK, &rlim_old);
+ rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20);
+ rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20);
+ setrlimit(RLIMIT_MEMLOCK, &rlim_new);
+}
+
+static __attribute__((destructor)) void main_dtor(void)
+{
+ setrlimit(RLIMIT_MEMLOCK, &rlim_old);
+}
+
int main(void)
{
fprintf(stderr, "---- IPv4 UDP ----\n");
perror("Unable to allocate ring buffer.\n");
exit(3);
}
- event = malloc(sizeof *event);
+ event = calloc(1, sizeof(*event));
if (!event) {
perror("Unable to allocate event buffer.\n");
exit(3);
}
- memset(event, 0, sizeof *event);
guest.avail_idx = 0;
guest.kicked_avail_idx = -1;
guest.last_used_idx = 0;
ring[i] = desc;
}
guest.num_free = ring_size;
- data = malloc(ring_size * sizeof *data);
+ data = calloc(ring_size, sizeof(*data));
if (!data) {
perror("Unable to allocate data buffer.\n");
exit(3);
}
- memset(data, 0, ring_size * sizeof *data);
}
/* guest side */
void kick_available(void)
{
+ bool need;
+
/* Flush in previous flags write */
/* Barrier C (for pairing) */
smp_mb();
- if (!need_event(event->kick_index,
- guest.avail_idx,
- guest.kicked_avail_idx))
- return;
+ need = need_event(event->kick_index,
+ guest.avail_idx,
+ guest.kicked_avail_idx);
guest.kicked_avail_idx = guest.avail_idx;
- kick();
+ if (need)
+ kick();
}
/* host side */
void call_used(void)
{
+ bool need;
+
/* Flush in previous flags write */
/* Barrier D (for pairing) */
smp_mb();
- if (!need_event(event->call_index,
+
+ need = need_event(event->call_index,
host.used_idx,
- host.called_used_idx))
- return;
+ host.called_used_idx);
host.called_used_idx = host.used_idx;
- call();
+
+ if (need)
+ call();
}
void kick_available(void)
{
+ bool need;
+
/* Flush in previous flags write */
/* Barrier C (for pairing) */
smp_mb();
- if (!vring_need_event(vring_avail_event(&ring),
- guest.avail_idx,
- guest.kicked_avail_idx))
- return;
+ need = vring_need_event(vring_avail_event(&ring),
+ guest.avail_idx,
+ guest.kicked_avail_idx);
guest.kicked_avail_idx = guest.avail_idx;
- kick();
+ if (need)
+ kick();
}
/* host side */
void call_used(void)
{
+ bool need;
+
/* Flush in previous flags write */
/* Barrier D (for pairing) */
smp_mb();
- if (!vring_need_event(vring_used_event(&ring),
- host.used_idx,
- host.called_used_idx))
- return;
+ need = vring_need_event(vring_used_event(&ring),
+ host.used_idx,
+ host.called_used_idx);
host.called_used_idx = host.used_idx;
- call();
+ if (need)
+ call();
}
config HAVE_KVM_IRQ_BYPASS
bool
+
+config HAVE_KVM_VCPU_ASYNC_IOCTL
+ bool
{
struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
struct arch_timer_context *vtimer;
- u32 cnt_ctl;
/*
* We may see a timer interrupt after vcpu_put() has been called which
return IRQ_HANDLED;
vtimer = vcpu_vtimer(vcpu);
- if (!vtimer->irq.level) {
- cnt_ctl = read_sysreg_el0(cntv_ctl);
- cnt_ctl &= ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT |
- ARCH_TIMER_CTRL_IT_MASK;
- if (cnt_ctl == (ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT))
- kvm_timer_update_irq(vcpu, true, vtimer);
- }
+ if (kvm_timer_should_fire(vtimer))
+ kvm_timer_update_irq(vcpu, true, vtimer);
- if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
+ if (static_branch_unlikely(&userspace_irqchip_in_use) &&
+ unlikely(!irqchip_in_kernel(vcpu->kvm)))
kvm_vtimer_update_mask_user(vcpu);
return IRQ_HANDLED;
{
u64 cval, now;
+ if (timer_ctx->loaded) {
+ u32 cnt_ctl;
+
+ /* Only the virtual timer can be loaded so far */
+ cnt_ctl = read_sysreg_el0(cntv_ctl);
+ return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) &&
+ (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) &&
+ !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK);
+ }
+
if (!kvm_timer_irq_can_fire(timer_ctx))
return false;
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
- if (vtimer->irq.level || ptimer->irq.level)
- return true;
-
- /*
- * When this is called from withing the wait loop of kvm_vcpu_block(),
- * the software view of the timer state is up to date (timer->loaded
- * is false), and so we can simply check if the timer should fire now.
- */
- if (!vtimer->loaded && kvm_timer_should_fire(vtimer))
+ if (kvm_timer_should_fire(vtimer))
return true;
return kvm_timer_should_fire(ptimer);
/* Populate the device bitmap with the timer states */
regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER |
KVM_ARM_DEV_EL1_PTIMER);
- if (vtimer->irq.level)
+ if (kvm_timer_should_fire(vtimer))
regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER;
- if (ptimer->irq.level)
+ if (kvm_timer_should_fire(ptimer))
regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
}
trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq,
timer_ctx->irq.level);
- if (likely(irqchip_in_kernel(vcpu->kvm))) {
+ if (!static_branch_unlikely(&userspace_irqchip_in_use) ||
+ likely(irqchip_in_kernel(vcpu->kvm))) {
ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
timer_ctx->irq.irq,
timer_ctx->irq.level,
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
+ bool level;
if (unlikely(!timer->enabled))
return;
- if (kvm_timer_should_fire(vtimer) != vtimer->irq.level)
- kvm_timer_update_irq(vcpu, !vtimer->irq.level, vtimer);
+ /*
+ * The vtimer virtual interrupt is a 'mapped' interrupt, meaning part
+ * of its lifecycle is offloaded to the hardware, and we therefore may
+ * not have lowered the irq.level value before having to signal a new
+ * interrupt, but have to signal an interrupt every time the level is
+ * asserted.
+ */
+ level = kvm_timer_should_fire(vtimer);
+ kvm_timer_update_irq(vcpu, level, vtimer);
if (kvm_timer_should_fire(ptimer) != ptimer->irq.level)
kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer);
phys_timer_emulate(vcpu);
}
+static void __timer_snapshot_state(struct arch_timer_context *timer)
+{
+ timer->cnt_ctl = read_sysreg_el0(cntv_ctl);
+ timer->cnt_cval = read_sysreg_el0(cntv_cval);
+}
+
static void vtimer_save_state(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
if (!vtimer->loaded)
goto out;
- if (timer->enabled) {
- vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl);
- vtimer->cnt_cval = read_sysreg_el0(cntv_cval);
- }
+ if (timer->enabled)
+ __timer_snapshot_state(vtimer);
/* Disable the virtual timer */
write_sysreg_el0(0, cntv_ctl);
bool phys_active;
int ret;
- phys_active = vtimer->irq.level ||
- kvm_vgic_map_is_active(vcpu, vtimer->irq.irq);
+ phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq);
ret = irq_set_irqchip_state(host_vtimer_irq,
IRQCHIP_STATE_ACTIVE,
vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER;
plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER;
- return vtimer->irq.level != vlevel ||
- ptimer->irq.level != plevel;
+ return kvm_timer_should_fire(vtimer) != vlevel ||
+ kvm_timer_should_fire(ptimer) != plevel;
}
void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
set_cntvoff(0);
}
-static void unmask_vtimer_irq(struct kvm_vcpu *vcpu)
+/*
+ * With a userspace irqchip we have to check if the guest de-asserted the
+ * timer and if so, unmask the timer irq signal on the host interrupt
+ * controller to ensure that we see future timer signals.
+ */
+static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
{
struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
if (unlikely(!irqchip_in_kernel(vcpu->kvm))) {
- kvm_vtimer_update_mask_user(vcpu);
- return;
- }
-
- /*
- * If the guest disabled the timer without acking the interrupt, then
- * we must make sure the physical and virtual active states are in
- * sync by deactivating the physical interrupt, because otherwise we
- * wouldn't see the next timer interrupt in the host.
- */
- if (!kvm_vgic_map_is_active(vcpu, vtimer->irq.irq)) {
- int ret;
- ret = irq_set_irqchip_state(host_vtimer_irq,
- IRQCHIP_STATE_ACTIVE,
- false);
- WARN_ON(ret);
+ __timer_snapshot_state(vtimer);
+ if (!kvm_timer_should_fire(vtimer)) {
+ kvm_timer_update_irq(vcpu, false, vtimer);
+ kvm_vtimer_update_mask_user(vcpu);
+ }
}
}
-/**
- * kvm_timer_sync_hwstate - sync timer state from cpu
- * @vcpu: The vcpu pointer
- *
- * Check if any of the timers have expired while we were running in the guest,
- * and inject an interrupt if that was the case.
- */
void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
{
- struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
-
- /*
- * If we entered the guest with the vtimer output asserted we have to
- * check if the guest has modified the timer so that we should lower
- * the line at this point.
- */
- if (vtimer->irq.level) {
- vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl);
- vtimer->cnt_cval = read_sysreg_el0(cntv_cval);
- if (!kvm_timer_should_fire(vtimer)) {
- kvm_timer_update_irq(vcpu, false, vtimer);
- unmask_vtimer_irq(vcpu);
- }
- }
+ unmask_vtimer_irq_user(vcpu);
}
int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
return true;
}
+bool kvm_arch_timer_get_input_level(int vintid)
+{
+ struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu();
+ struct arch_timer_context *timer;
+
+ if (vintid == vcpu_vtimer(vcpu)->irq.irq)
+ timer = vcpu_vtimer(vcpu);
+ else
+ BUG(); /* We only map the vtimer so far */
+
+ return kvm_timer_should_fire(timer);
+}
+
int kvm_timer_enable(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
return -EINVAL;
}
- ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq);
+ ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq,
+ kvm_arch_timer_get_input_level);
if (ret)
return ret;
#include <linux/irqbypass.h>
#include <trace/events/kvm.h>
#include <kvm/arm_pmu.h>
+#include <kvm/arm_psci.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
#include <asm/kvm_mmu.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
-#include <asm/kvm_psci.h>
#include <asm/sections.h>
#ifdef REQUIRES_VIRT
static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
{
- BUG_ON(preemptible());
__this_cpu_write(kvm_arm_running_vcpu, vcpu);
}
+DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
+
/**
* kvm_arm_get_running_vcpu - get the vcpu running on the current CPU.
* Must be called from non-preemptible context
*/
struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
{
- BUG_ON(preemptible());
return __this_cpu_read(kvm_arm_running_vcpu);
}
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
+ if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm)))
+ static_branch_dec(&userspace_irqchip_in_use);
+
kvm_mmu_free_memory_caches(vcpu);
kvm_timer_vcpu_terminate(vcpu);
kvm_pmu_vcpu_destroy(vcpu);
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ vcpu_load(vcpu);
+
if (vcpu->arch.power_off)
mp_state->mp_state = KVM_MP_STATE_STOPPED;
else
mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+ vcpu_put(vcpu);
return 0;
}
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
+ int ret = 0;
+
+ vcpu_load(vcpu);
+
switch (mp_state->mp_state) {
case KVM_MP_STATE_RUNNABLE:
vcpu->arch.power_off = false;
vcpu_power_off(vcpu);
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
- return 0;
+ vcpu_put(vcpu);
+ return ret;
}
/**
vcpu->arch.has_run_once = true;
- /*
- * Map the VGIC hardware resources before running a vcpu the first
- * time on this VM.
- */
- if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) {
- ret = kvm_vgic_map_resources(kvm);
- if (ret)
- return ret;
+ if (likely(irqchip_in_kernel(kvm))) {
+ /*
+ * 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;
+ }
+ } else {
+ /*
+ * Tell the rest of the code that there are userspace irqchip
+ * VMs in the wild.
+ */
+ static_branch_inc(&userspace_irqchip_in_use);
}
ret = kvm_timer_enable(vcpu);
if (unlikely(!kvm_vcpu_initialized(vcpu)))
return -ENOEXEC;
+ vcpu_load(vcpu);
+
ret = kvm_vcpu_first_run_init(vcpu);
if (ret)
- return ret;
+ goto out;
if (run->exit_reason == KVM_EXIT_MMIO) {
ret = kvm_handle_mmio_return(vcpu, vcpu->run);
if (ret)
- return ret;
- if (kvm_arm_handle_step_debug(vcpu, vcpu->run))
- return 0;
+ goto out;
+ if (kvm_arm_handle_step_debug(vcpu, vcpu->run)) {
+ ret = 0;
+ goto out;
+ }
}
- if (run->immediate_exit)
- return -EINTR;
+ if (run->immediate_exit) {
+ ret = -EINTR;
+ goto out;
+ }
kvm_sigset_activate(vcpu);
kvm_vgic_flush_hwstate(vcpu);
/*
- * If we have a singal pending, or need to notify a userspace
- * irqchip about timer or PMU level changes, then we exit (and
- * update the timer level state in kvm_timer_update_run
- * below).
+ * Exit if we have a signal pending so that we can deliver the
+ * signal to user space.
*/
- if (signal_pending(current) ||
- kvm_timer_should_notify_user(vcpu) ||
- kvm_pmu_should_notify_user(vcpu)) {
+ if (signal_pending(current)) {
ret = -EINTR;
run->exit_reason = KVM_EXIT_INTR;
}
+ /*
+ * If we're using a userspace irqchip, then check if we need
+ * to tell a userspace irqchip about timer or PMU level
+ * changes and if so, exit to userspace (the actual level
+ * state gets updated in kvm_timer_update_run and
+ * kvm_pmu_update_run below).
+ */
+ if (static_branch_unlikely(&userspace_irqchip_in_use)) {
+ if (kvm_timer_should_notify_user(vcpu) ||
+ kvm_pmu_should_notify_user(vcpu)) {
+ ret = -EINTR;
+ run->exit_reason = KVM_EXIT_INTR;
+ }
+ }
+
/*
* Ensure we set mode to IN_GUEST_MODE after we disable
* interrupts and before the final VCPU requests check.
kvm_request_pending(vcpu)) {
vcpu->mode = OUTSIDE_GUEST_MODE;
kvm_pmu_sync_hwstate(vcpu);
- kvm_timer_sync_hwstate(vcpu);
+ if (static_branch_unlikely(&userspace_irqchip_in_use))
+ kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
local_irq_enable();
preempt_enable();
* we don't want vtimer interrupts to race with syncing the
* timer virtual interrupt state.
*/
- kvm_timer_sync_hwstate(vcpu);
+ if (static_branch_unlikely(&userspace_irqchip_in_use))
+ kvm_timer_sync_hwstate(vcpu);
/*
* We may have taken a host interrupt in HYP mode (ie
kvm_sigset_deactivate(vcpu);
+out:
+ vcpu_put(vcpu);
return ret;
}
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
struct kvm_device_attr attr;
+ long r;
+
+ vcpu_load(vcpu);
switch (ioctl) {
case KVM_ARM_VCPU_INIT: {
struct kvm_vcpu_init init;
+ r = -EFAULT;
if (copy_from_user(&init, argp, sizeof(init)))
- return -EFAULT;
+ break;
- return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
+ r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
+ break;
}
case KVM_SET_ONE_REG:
case KVM_GET_ONE_REG: {
struct kvm_one_reg reg;
+ r = -ENOEXEC;
if (unlikely(!kvm_vcpu_initialized(vcpu)))
- return -ENOEXEC;
+ break;
+ r = -EFAULT;
if (copy_from_user(®, argp, sizeof(reg)))
- return -EFAULT;
+ break;
+
if (ioctl == KVM_SET_ONE_REG)
- return kvm_arm_set_reg(vcpu, ®);
+ r = kvm_arm_set_reg(vcpu, ®);
else
- return kvm_arm_get_reg(vcpu, ®);
+ r = kvm_arm_get_reg(vcpu, ®);
+ break;
}
case KVM_GET_REG_LIST: {
struct kvm_reg_list __user *user_list = argp;
struct kvm_reg_list reg_list;
unsigned n;
+ r = -ENOEXEC;
if (unlikely(!kvm_vcpu_initialized(vcpu)))
- return -ENOEXEC;
+ break;
+ r = -EFAULT;
if (copy_from_user(®_list, user_list, sizeof(reg_list)))
- return -EFAULT;
+ break;
n = reg_list.n;
reg_list.n = kvm_arm_num_regs(vcpu);
if (copy_to_user(user_list, ®_list, sizeof(reg_list)))
- return -EFAULT;
+ break;
+ r = -E2BIG;
if (n < reg_list.n)
- return -E2BIG;
- return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
+ break;
+ r = kvm_arm_copy_reg_indices(vcpu, user_list->reg);
+ break;
}
case KVM_SET_DEVICE_ATTR: {
+ r = -EFAULT;
if (copy_from_user(&attr, argp, sizeof(attr)))
- return -EFAULT;
- return kvm_arm_vcpu_set_attr(vcpu, &attr);
+ break;
+ r = kvm_arm_vcpu_set_attr(vcpu, &attr);
+ break;
}
case KVM_GET_DEVICE_ATTR: {
+ r = -EFAULT;
if (copy_from_user(&attr, argp, sizeof(attr)))
- return -EFAULT;
- return kvm_arm_vcpu_get_attr(vcpu, &attr);
+ break;
+ r = kvm_arm_vcpu_get_attr(vcpu, &attr);
+ break;
}
case KVM_HAS_DEVICE_ATTR: {
+ r = -EFAULT;
if (copy_from_user(&attr, argp, sizeof(attr)))
- return -EFAULT;
- return kvm_arm_vcpu_has_attr(vcpu, &attr);
+ break;
+ r = kvm_arm_vcpu_has_attr(vcpu, &attr);
+ break;
}
default:
- return -EINVAL;
+ r = -EINVAL;
}
+
+ vcpu_put(vcpu);
+ return r;
}
/**
cpu_hyp_reset();
return NOTIFY_OK;
+ case CPU_PM_ENTER_FAILED:
case CPU_PM_EXIT:
if (__this_cpu_read(kvm_arm_hardware_enabled))
/* The hardware was enabled before suspend. */
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
{
return 0;
}
+static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+{
+ pmd_t *pmdp;
+ pte_t *ptep;
+
+ pmdp = stage2_get_pmd(kvm, NULL, addr);
+ if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp))
+ return false;
+
+ if (pmd_thp_or_huge(*pmdp))
+ return kvm_s2pmd_exec(pmdp);
+
+ ptep = pte_offset_kernel(pmdp, addr);
+ if (!ptep || pte_none(*ptep) || !pte_present(*ptep))
+ return false;
+
+ return kvm_s2pte_exec(ptep);
+}
+
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
phys_addr_t addr, const pte_t *new_pte,
unsigned long flags)
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
-static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,
- unsigned long size)
+static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
- __coherent_cache_guest_page(vcpu, pfn, size);
+ __clean_dcache_guest_page(pfn, size);
+}
+
+static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size)
+{
+ __invalidate_icache_guest_page(pfn, size);
}
static void kvm_send_hwpoison_signal(unsigned long address,
unsigned long fault_status)
{
int ret;
- bool write_fault, writable, hugetlb = false, force_pte = false;
+ bool write_fault, exec_fault, writable, hugetlb = false, force_pte = false;
unsigned long mmu_seq;
gfn_t gfn = fault_ipa >> PAGE_SHIFT;
struct kvm *kvm = vcpu->kvm;
unsigned long flags = 0;
write_fault = kvm_is_write_fault(vcpu);
- if (fault_status == FSC_PERM && !write_fault) {
+ exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+ VM_BUG_ON(write_fault && exec_fault);
+
+ if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
new_pmd = kvm_s2pmd_mkwrite(new_pmd);
kvm_set_pfn_dirty(pfn);
}
- coherent_cache_guest_page(vcpu, pfn, PMD_SIZE);
+
+ if (fault_status != FSC_PERM)
+ clean_dcache_guest_page(pfn, PMD_SIZE);
+
+ if (exec_fault) {
+ new_pmd = kvm_s2pmd_mkexec(new_pmd);
+ invalidate_icache_guest_page(pfn, PMD_SIZE);
+ } else if (fault_status == FSC_PERM) {
+ /* Preserve execute if XN was already cleared */
+ if (stage2_is_exec(kvm, fault_ipa))
+ new_pmd = kvm_s2pmd_mkexec(new_pmd);
+ }
+
ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = pfn_pte(pfn, mem_type);
kvm_set_pfn_dirty(pfn);
mark_page_dirty(kvm, gfn);
}
- coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE);
+
+ if (fault_status != FSC_PERM)
+ clean_dcache_guest_page(pfn, PAGE_SIZE);
+
+ if (exec_fault) {
+ new_pte = kvm_s2pte_mkexec(new_pte);
+ invalidate_icache_guest_page(pfn, PAGE_SIZE);
+ } else if (fault_status == FSC_PERM) {
+ /* Preserve execute if XN was already cleared */
+ if (stage2_is_exec(kvm, fault_ipa))
+ new_pte = kvm_s2pte_mkexec(new_pte);
+ }
+
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
}
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/arm-smccc.h>
#include <linux/preempt.h>
#include <linux/kvm_host.h>
#include <linux/wait.h>
#include <asm/cputype.h>
#include <asm/kvm_emulate.h>
-#include <asm/kvm_psci.h>
#include <asm/kvm_host.h>
-#include <uapi/linux/psci.h>
+#include <kvm/arm_psci.h>
/*
* This is an implementation of the Power State Coordination Interface
#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+static u32 smccc_get_function(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 0);
+}
+
+static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 1);
+}
+
+static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 2);
+}
+
+static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu)
+{
+ return vcpu_get_reg(vcpu, 3);
+}
+
+static void smccc_set_retval(struct kvm_vcpu *vcpu,
+ unsigned long a0,
+ unsigned long a1,
+ unsigned long a2,
+ unsigned long a3)
+{
+ vcpu_set_reg(vcpu, 0, a0);
+ vcpu_set_reg(vcpu, 1, a1);
+ vcpu_set_reg(vcpu, 2, a2);
+ vcpu_set_reg(vcpu, 3, a3);
+}
+
static unsigned long psci_affinity_mask(unsigned long affinity_level)
{
if (affinity_level <= 3)
unsigned long context_id;
phys_addr_t target_pc;
- cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+ cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
if (vcpu_mode_is_32bit(source_vcpu))
cpu_id &= ~((u32) 0);
if (!vcpu)
return PSCI_RET_INVALID_PARAMS;
if (!vcpu->arch.power_off) {
- if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+ if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1)
return PSCI_RET_ALREADY_ON;
else
return PSCI_RET_INVALID_PARAMS;
}
- target_pc = vcpu_get_reg(source_vcpu, 2);
- context_id = vcpu_get_reg(source_vcpu, 3);
+ target_pc = smccc_get_arg2(source_vcpu);
+ context_id = smccc_get_arg3(source_vcpu);
kvm_reset_vcpu(vcpu);
* NOTE: We always update r0 (or x0) because for PSCI v0.1
* the general puspose registers are undefined upon CPU_ON.
*/
- vcpu_set_reg(vcpu, 0, context_id);
+ smccc_set_retval(vcpu, context_id, 0, 0, 0);
vcpu->arch.power_off = false;
smp_mb(); /* Make sure the above is visible */
struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tmp;
- target_affinity = vcpu_get_reg(vcpu, 1);
- lowest_affinity_level = vcpu_get_reg(vcpu, 2);
+ target_affinity = smccc_get_arg1(vcpu);
+ lowest_affinity_level = smccc_get_arg2(vcpu);
/* Determine target affinity mask */
target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
}
-int kvm_psci_version(struct kvm_vcpu *vcpu)
-{
- if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
- return KVM_ARM_PSCI_0_2;
-
- return KVM_ARM_PSCI_0_1;
-}
-
static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+ u32 psci_fn = smccc_get_function(vcpu);
unsigned long val;
int ret = 1;
* Bits[31:16] = Major Version = 0
* Bits[15:0] = Minor Version = 2
*/
- val = 2;
+ val = KVM_ARM_PSCI_0_2;
break;
case PSCI_0_2_FN_CPU_SUSPEND:
case PSCI_0_2_FN64_CPU_SUSPEND:
break;
}
- vcpu_set_reg(vcpu, 0, val);
+ smccc_set_retval(vcpu, val, 0, 0, 0);
+ return ret;
+}
+
+static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu)
+{
+ u32 psci_fn = smccc_get_function(vcpu);
+ u32 feature;
+ unsigned long val;
+ int ret = 1;
+
+ switch(psci_fn) {
+ case PSCI_0_2_FN_PSCI_VERSION:
+ val = KVM_ARM_PSCI_1_0;
+ break;
+ case PSCI_1_0_FN_PSCI_FEATURES:
+ feature = smccc_get_arg1(vcpu);
+ switch(feature) {
+ case PSCI_0_2_FN_PSCI_VERSION:
+ case PSCI_0_2_FN_CPU_SUSPEND:
+ case PSCI_0_2_FN64_CPU_SUSPEND:
+ case PSCI_0_2_FN_CPU_OFF:
+ case PSCI_0_2_FN_CPU_ON:
+ case PSCI_0_2_FN64_CPU_ON:
+ case PSCI_0_2_FN_AFFINITY_INFO:
+ case PSCI_0_2_FN64_AFFINITY_INFO:
+ case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+ case PSCI_0_2_FN_SYSTEM_OFF:
+ case PSCI_0_2_FN_SYSTEM_RESET:
+ case PSCI_1_0_FN_PSCI_FEATURES:
+ case ARM_SMCCC_VERSION_FUNC_ID:
+ val = 0;
+ break;
+ default:
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
+ }
+ break;
+ default:
+ return kvm_psci_0_2_call(vcpu);
+ }
+
+ smccc_set_retval(vcpu, val, 0, 0, 0);
return ret;
}
static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
+ u32 psci_fn = smccc_get_function(vcpu);
unsigned long val;
switch (psci_fn) {
break;
}
- vcpu_set_reg(vcpu, 0, val);
+ smccc_set_retval(vcpu, val, 0, 0, 0);
return 1;
}
* Errors:
* -EINVAL: Unrecognized PSCI function
*/
-int kvm_psci_call(struct kvm_vcpu *vcpu)
+static int kvm_psci_call(struct kvm_vcpu *vcpu)
{
- switch (kvm_psci_version(vcpu)) {
+ switch (kvm_psci_version(vcpu, vcpu->kvm)) {
+ case KVM_ARM_PSCI_1_0:
+ return kvm_psci_1_0_call(vcpu);
case KVM_ARM_PSCI_0_2:
return kvm_psci_0_2_call(vcpu);
case KVM_ARM_PSCI_0_1:
return -EINVAL;
};
}
+
+int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
+{
+ u32 func_id = smccc_get_function(vcpu);
+ u32 val = PSCI_RET_NOT_SUPPORTED;
+ u32 feature;
+
+ switch (func_id) {
+ case ARM_SMCCC_VERSION_FUNC_ID:
+ val = ARM_SMCCC_VERSION_1_1;
+ break;
+ case ARM_SMCCC_ARCH_FEATURES_FUNC_ID:
+ feature = smccc_get_arg1(vcpu);
+ switch(feature) {
+ case ARM_SMCCC_ARCH_WORKAROUND_1:
+ if (kvm_arm_harden_branch_predictor())
+ val = 0;
+ break;
+ }
+ break;
+ default:
+ return kvm_psci_call(vcpu);
+ }
+
+ smccc_set_retval(vcpu, val, 0, 0, 0);
+ return 1;
+}
device = vgic_its_alloc_device(its, device_id, itt_addr,
num_eventid_bits);
- if (IS_ERR(device))
- return PTR_ERR(device);
- return 0;
+ return PTR_ERR_OR_ZERO(device);
}
/*
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <kvm/iodev.h>
+#include <kvm/arm_arch_timer.h>
#include <kvm/arm_vgic.h>
#include "vgic.h"
return value;
}
+/*
+ * This function will return the VCPU that performed the MMIO access and
+ * trapped from within the VM, and will return NULL if this is a userspace
+ * access.
+ *
+ * We can disable preemption locally around accessing the per-CPU variable,
+ * and use the resolved vcpu pointer after enabling preemption again, because
+ * even if the current thread is migrated to another CPU, reading the per-CPU
+ * value later will give us the same value as we update the per-CPU variable
+ * in the preempt notifier handlers.
+ */
+static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void)
+{
+ struct kvm_vcpu *vcpu;
+
+ preempt_disable();
+ vcpu = kvm_arm_get_running_vcpu();
+ preempt_enable();
+ return vcpu;
+}
+
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+ bool is_uaccess)
+{
+ if (is_uaccess)
+ return;
+
+ irq->pending_latch = true;
+ vgic_irq_set_phys_active(irq, true);
+}
+
void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
+ bool is_uaccess = !vgic_get_mmio_requester_vcpu();
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
spin_lock_irqsave(&irq->irq_lock, flags);
- irq->pending_latch = true;
-
+ if (irq->hw)
+ vgic_hw_irq_spending(vcpu, irq, is_uaccess);
+ else
+ irq->pending_latch = true;
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_put_irq(vcpu->kvm, irq);
}
}
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+ bool is_uaccess)
+{
+ if (is_uaccess)
+ return;
+
+ irq->pending_latch = false;
+
+ /*
+ * We don't want the guest to effectively mask the physical
+ * interrupt by doing a write to SPENDR followed by a write to
+ * CPENDR for HW interrupts, so we clear the active state on
+ * the physical side if the virtual interrupt is not active.
+ * This may lead to taking an additional interrupt on the
+ * host, but that should not be a problem as the worst that
+ * can happen is an additional vgic injection. We also clear
+ * the pending state to maintain proper semantics for edge HW
+ * interrupts.
+ */
+ vgic_irq_set_phys_pending(irq, false);
+ if (!irq->active)
+ vgic_irq_set_phys_active(irq, false);
+}
+
void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
{
+ bool is_uaccess = !vgic_get_mmio_requester_vcpu();
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
int i;
unsigned long flags;
spin_lock_irqsave(&irq->irq_lock, flags);
- irq->pending_latch = false;
+ if (irq->hw)
+ vgic_hw_irq_cpending(vcpu, irq, is_uaccess);
+ else
+ irq->pending_latch = false;
spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
return value;
}
+/* Must be called with irq->irq_lock held */
+static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
+ bool active, bool is_uaccess)
+{
+ if (is_uaccess)
+ return;
+
+ irq->active = active;
+ vgic_irq_set_phys_active(irq, active);
+}
+
static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
- bool new_active_state)
+ bool active)
{
- struct kvm_vcpu *requester_vcpu;
unsigned long flags;
- spin_lock_irqsave(&irq->irq_lock, flags);
+ struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu();
- /*
- * The vcpu parameter here can mean multiple things depending on how
- * this function is called; when handling a trap from the kernel it
- * depends on the GIC version, and these functions are also called as
- * part of save/restore from userspace.
- *
- * Therefore, we have to figure out the requester in a reliable way.
- *
- * When accessing VGIC state from user space, the requester_vcpu is
- * NULL, which is fine, because we guarantee that no VCPUs are running
- * when accessing VGIC state from user space so irq->vcpu->cpu is
- * always -1.
- */
- requester_vcpu = kvm_arm_get_running_vcpu();
+ spin_lock_irqsave(&irq->irq_lock, flags);
/*
* If this virtual IRQ was written into a list register, we
* vgic_change_active_prepare) and still has to sync back this IRQ,
* so we release and re-acquire the spin_lock to let the other thread
* sync back the IRQ.
+ *
+ * When accessing VGIC state from user space, requester_vcpu is
+ * NULL, which is fine, because we guarantee that no VCPUs are running
+ * when accessing VGIC state from user space so irq->vcpu->cpu is
+ * always -1.
*/
while (irq->vcpu && /* IRQ may have state in an LR somewhere */
irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */
irq->vcpu->cpu != -1) /* VCPU thread is running */
cond_resched_lock(&irq->irq_lock);
- irq->active = new_active_state;
- if (new_active_state)
+ if (irq->hw)
+ vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
+ else
+ irq->active = active;
+
+ if (irq->active)
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
else
spin_unlock_irqrestore(&irq->irq_lock, flags);
irq->pending_latch = false;
}
+ /*
+ * Level-triggered mapped IRQs are special because we only
+ * observe rising edges as input to the VGIC.
+ *
+ * If the guest never acked the interrupt we have to sample
+ * the physical line and set the line level, because the
+ * device state could have changed or we simply need to
+ * process the still pending interrupt later.
+ *
+ * If this causes us to lower the level, we have to also clear
+ * the physical active state, since we will otherwise never be
+ * told when the interrupt becomes asserted again.
+ */
+ if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) {
+ irq->line_level = vgic_get_phys_line_level(irq);
+
+ if (!irq->line_level)
+ vgic_irq_set_phys_active(irq, false);
+ }
+
spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
val |= GICH_LR_EOI;
}
+ /*
+ * Level-triggered mapped IRQs are special because we only observe
+ * rising edges as input to the VGIC. We therefore lower the line
+ * level here, so that we can take new virtual IRQs. See
+ * vgic_v2_fold_lr_state for more info.
+ */
+ if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT))
+ irq->line_level = false;
+
/* The GICv2 LR only holds five bits of priority. */
val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT;
irq->pending_latch = false;
}
+ /*
+ * Level-triggered mapped IRQs are special because we only
+ * observe rising edges as input to the VGIC.
+ *
+ * If the guest never acked the interrupt we have to sample
+ * the physical line and set the line level, because the
+ * device state could have changed or we simply need to
+ * process the still pending interrupt later.
+ *
+ * If this causes us to lower the level, we have to also clear
+ * the physical active state, since we will otherwise never be
+ * told when the interrupt becomes asserted again.
+ */
+ if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) {
+ irq->line_level = vgic_get_phys_line_level(irq);
+
+ if (!irq->line_level)
+ vgic_irq_set_phys_active(irq, false);
+ }
+
spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
}
val |= ICH_LR_EOI;
}
+ /*
+ * Level-triggered mapped IRQs are special because we only observe
+ * rising edges as input to the VGIC. We therefore lower the line
+ * level here, so that we can take new virtual IRQs. See
+ * vgic_v3_fold_lr_state for more info.
+ */
+ if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT))
+ irq->line_level = false;
+
/*
* We currently only support Group1 interrupts, which is a
* known defect. This needs to be addressed at some point.
kfree(irq);
}
+void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
+{
+ WARN_ON(irq_set_irqchip_state(irq->host_irq,
+ IRQCHIP_STATE_PENDING,
+ pending));
+}
+
+bool vgic_get_phys_line_level(struct vgic_irq *irq)
+{
+ bool line_level;
+
+ BUG_ON(!irq->hw);
+
+ if (irq->get_input_level)
+ return irq->get_input_level(irq->intid);
+
+ WARN_ON(irq_get_irqchip_state(irq->host_irq,
+ IRQCHIP_STATE_PENDING,
+ &line_level));
+ return line_level;
+}
+
+/* Set/Clear the physical active state */
+void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active)
+{
+
+ BUG_ON(!irq->hw);
+ WARN_ON(irq_set_irqchip_state(irq->host_irq,
+ IRQCHIP_STATE_ACTIVE,
+ active));
+}
+
/**
* kvm_vgic_target_oracle - compute the target vcpu for an irq
*
/* @irq->irq_lock must be held */
static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
- unsigned int host_irq)
+ unsigned int host_irq,
+ bool (*get_input_level)(int vindid))
{
struct irq_desc *desc;
struct irq_data *data;
irq->hw = true;
irq->host_irq = host_irq;
irq->hwintid = data->hwirq;
+ irq->get_input_level = get_input_level;
return 0;
}
{
irq->hw = false;
irq->hwintid = 0;
+ irq->get_input_level = NULL;
}
int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
- u32 vintid)
+ u32 vintid, bool (*get_input_level)(int vindid))
{
struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
unsigned long flags;
BUG_ON(!irq);
spin_lock_irqsave(&irq->irq_lock, flags);
- ret = kvm_vgic_map_irq(vcpu, irq, host_irq);
+ ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level);
spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq);
return irq->pending_latch || irq->line_level;
}
+static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq)
+{
+ return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
+}
+
/*
* This struct provides an intermediate representation of the fields contained
* in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
u32 intid);
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq);
+bool vgic_get_phys_line_level(struct vgic_irq *irq);
+void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending);
+void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
unsigned long flags);
void vgic_kick_vcpus(struct kvm *kvm);
unsigned seq;
int idx;
- if (flags & POLLIN) {
+ if (flags & EPOLLIN) {
idx = srcu_read_lock(&kvm->irq_srcu);
do {
seq = read_seqcount_begin(&irqfd->irq_entry_sc);
srcu_read_unlock(&kvm->irq_srcu, idx);
}
- if (flags & POLLHUP) {
+ if (flags & EPOLLHUP) {
/* The eventfd is closing, detach from KVM */
unsigned long flags;
*/
events = f.file->f_op->poll(f.file, &irqfd->pt);
- if (events & POLLIN)
+ if (events & EPOLLIN)
schedule_work(&irqfd->inject);
/*
* do not drop the file until the irqfd is fully initialized, otherwise
- * we might race against the POLLHUP
+ * we might race against the EPOLLHUP
*/
fdput(f);
#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
/*
* Switches to specified vcpu, until a matching vcpu_put()
*/
-int vcpu_load(struct kvm_vcpu *vcpu)
+void vcpu_load(struct kvm_vcpu *vcpu)
{
- int cpu;
-
- if (mutex_lock_killable(&vcpu->mutex))
- return -EINTR;
- cpu = get_cpu();
+ int cpu = get_cpu();
preempt_notifier_register(&vcpu->preempt_notifier);
kvm_arch_vcpu_load(vcpu, cpu);
put_cpu();
- return 0;
}
EXPORT_SYMBOL_GPL(vcpu_load);
kvm_arch_vcpu_put(vcpu);
preempt_notifier_unregister(&vcpu->preempt_notifier);
preempt_enable();
- mutex_unlock(&vcpu->mutex);
}
EXPORT_SYMBOL_GPL(vcpu_put);
static int hva_to_pfn_remapped(struct vm_area_struct *vma,
unsigned long addr, bool *async,
- bool write_fault, kvm_pfn_t *p_pfn)
+ bool write_fault, bool *writable,
+ kvm_pfn_t *p_pfn)
{
unsigned long pfn;
int r;
}
+ if (writable)
+ *writable = true;
/*
* Get a reference here because callers of *hva_to_pfn* and
if (vma == NULL)
pfn = KVM_PFN_ERR_FAULT;
else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
- r = hva_to_pfn_remapped(vma, addr, async, write_fault, &pfn);
+ r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn);
if (r == -EAGAIN)
goto retry;
if (r < 0)
*/
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
- return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
+ char name[8 + 1 + ITOA_MAX_LEN + 1];
+
+ snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id);
+ return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
}
static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
return -EINVAL;
-#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
/*
- * Special cases: vcpu ioctls that are asynchronous to vcpu execution,
- * so vcpu_load() would break it.
+ * Some architectures have vcpu ioctls that are asynchronous to vcpu
+ * execution; mutex_lock() would break them.
*/
- if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_S390_IRQ || ioctl == KVM_INTERRUPT)
- return kvm_arch_vcpu_ioctl(filp, ioctl, arg);
-#endif
-
-
- r = vcpu_load(vcpu);
- if (r)
+ r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg);
+ if (r != -ENOIOCTLCMD)
return r;
+
+ if (mutex_lock_killable(&vcpu->mutex))
+ return -EINTR;
switch (ioctl) {
case KVM_RUN: {
struct pid *oldpid;
r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
}
out:
- vcpu_put(vcpu);
+ mutex_unlock(&vcpu->mutex);
kfree(fpu);
kfree(kvm_sregs);
return r;
return PTR_ERR(kvm);
#ifdef CONFIG_KVM_MMIO
r = kvm_coalesced_mmio_init(kvm);
- if (r < 0) {
- kvm_put_kvm(kvm);
- return r;
- }
+ if (r < 0)
+ goto put_kvm;
#endif
r = get_unused_fd_flags(O_CLOEXEC);
- if (r < 0) {
- kvm_put_kvm(kvm);
- return r;
- }
+ if (r < 0)
+ goto put_kvm;
+
file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
if (IS_ERR(file)) {
put_unused_fd(r);
- kvm_put_kvm(kvm);
- return PTR_ERR(file);
+ r = PTR_ERR(file);
+ goto put_kvm;
}
/*
fd_install(r, file);
return r;
+
+put_kvm:
+ kvm_put_kvm(kvm);
+ return r;
}
static long kvm_dev_ioctl(struct file *filp,