| Age | Commit message (Collapse) | Author |
|---|
|
For GFX 9.4.3, interrupt handling needs to be updated for:
- Interrupt cookie will have a NodeId field. Each KFD
node needs to check the NodeId before processing the
interrupt.
- For CPX mode, there are additional checks of client ID
needed to process the interrupt.
- Add NodeId to the process drain interrupt.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
This patch fixes a regression caused by a bad merge where
the handling of reserved SDMA queues was accidentally removed.
With the fix, the reserved SDMA queues are again correctly
marked as unavailable for allocation.
Fixes: a805889a1531 ("drm/amdkfd: Update SDMA queue management for GFX9.4.3")
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Allow the debugger to get a snapshot of a specified number of queues
containing various queue property information that is copied to the
debugger.
Since the debugger doesn't know how many queues exist at any given time,
allow the debugger to pass the requested number of snapshots as 0 to get
the actual number of potential snapshots to use for a subsequent snapshot
request for actual information.
To prevent future ABI breakage, pass in the requested entry_size.
The KFD will return it's own entry_size in case the debugger still wants
log the information in a core dump on sizing failure.
Also allow the debugger to clear exceptions when doing a snapshot.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Shader read, write and atomic memory operations can be alerted to the
debugger as an address watch exception.
Allow the debugger to pass in a watch point to a particular memory
address per device.
Note that there exists only 4 watch points per devices to date, so have
the KFD keep track of what watch points are allocated or not.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
In order to inspect waves from the saved context at any point during a
debug session, the debugger must be able to preempt queues to trigger
context save by suspending them.
On queue suspend, the KFD will copy the context save header information
so that the debugger can correctly crawl the appropriate size of the saved
context. The debugger must then also be allowed to resume suspended queues.
A queue that is newly created cannot be suspended because queue ids are
recycled after destruction so the debugger needs to know that this has
occurred. Query functions will be later added that will clear a given
queue of its new queue status.
A queue cannot be destroyed while it is suspended to preserve its saved
context during debugger inspection. Have queue destruction block while
a queue is suspended and unblocked when it is resumed. Likewise, if a
queue is about to be destroyed, it cannot be suspended.
Return the number of queues successfully suspended or resumed along with
a per queue status array where the upper bits per queue status show that
the request was invalid (new/destroyed queue suspend request, missing
queue) or an error occurred (HWS in a fatal state so it can't suspend or
resume queues).
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The debugger must be notified by any debugger subscribed exception
that comes from hardware interrupts.
If a debugger session exits, any exceptions it subscribed to may still
have interrupts in the interrupt ring buffer or KGD/KFD pipeline.
To prevent a new session from inheriting stale interrupts, when a new
queue is created, open an interrupt drain and allow the IH ring to drain
from a timestamped checkpoint. Then inject a custom IV so that once
the custom IV is picked up by the KFD, it's safe to close the drain
and proceed with queue creation.
The drain must also be on debug disable as SW interrupts may still
be processed. Drain at this time and clear all the exception status.
The debugger may also not be attached nor subscibed to certain
exceptions so forward them directly to the runtime.
GFX10 also requires its own IV processing, hence the creation of
kfd_int_process_v10.c. This is because the IV from SQ interrupts are
packed into a new continguous format unlike GFX9. To make this clear,
a separate interrupting handling code file was created.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Trap handler behavior will differ when a debugger is attached.
Make the debug trap flag available in the trap handler TMA.
Update it when the debug trap ioctl is invoked.
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The debugger can attach to a process prior to HSA enablement (i.e.
inferior is spawned by the debugger and attached to immediately before
target process has been enabled for HSA dispatches) or it
can attach to a running target that is already HSA enabled. Either
way, the debugger needs to know the enablement status to know when
it can inspect queues.
For the scenario where the debugger spawns the target process,
it will have to wait for ROCr's runtime enable request from the target.
The runtime enable request will be able to see that its process has been
debug attached. ROCr raises an EC_PROCESS_RUNTIME signal to the
debugger then blocks the target process while waiting the debugger's
response. Once the debugger has received the runtime signal, it will
unblock the target process.
For the scenario where the debugger attaches to a running target
process, ROCr will set the target process' runtime status as enabled so
that on an attach request, the debugger will be able to see this
status and will continue with debug enablement as normal.
A secondary requirement is to conditionally enable the trap tempories only
if the user requests it (env var HSA_ENABLE_DEBUG=1) or if the debugger
attaches with HSA runtime enabled. This is because setting up the trap
temporaries incurs a performance overhead that is unacceptable for
microbench performance in normal mode for certain customers.
In the scenario where the debugger spawns the target process, when ROCr
detects that the debugger has attached during the runtime enable
request, it will enable the trap temporaries before it blocks the target
process while waiting for the debugger to respond.
In the scenario where the debugger attaches to a running target process,
it will enable to trap temporaries itself.
Finally, there is an additional restriction that is required to be
enforced with runtime enable and HW debug mode setting. The debugger must
first ensure that HW debug mode has been enabled before permitting HW debug
mode operations.
With single process debug devices, allowing the debugger to set debug
HW modes prior to trap activation means that debug HW mode setting can
occur before the KFD has reserved the debug VMID (0xf) from the hardware
scheduler's VMID allocation resource pool. This can result in the
hardware scheduler assigning VMID 0xf to a non-debugged process and
having that process inherit debug HW mode settings intended for the
debugged target process instead, which is both incorrect and potentially
fatal for normal mode operation.
With multi process debug devices, allowing the debugger to set debug
HW modes prior to trap activation means that non-debugged processes
migrating to a new VMID could inherit unintended debug settings.
All debug operations that touch HW settings must require trap activation
where trap activation is triggered by both debug attach and runtime
enablement (target has KFD opened and is ready to dispatch work).
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Add a debug operation that allows the debugger to send an exception
directly to runtime through a payload address.
For memory violations, normal vmfault signals will be applied to
notify runtime instead after passing in the saved exception data
when a memory violation was raised to the debugger.
For runtime exceptions, this will unblock the runtime enable
function which will be explained and implemented in a follow up
patch.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Exception events can be generated from interrupts or queue activitity.
The raise event function will save exception status of a queue, device
or process then notify the debugger of the status change by writing to
a debugger polled file descriptor that the debugger provides during
debug attach.
For memory violation exceptions, extra exception data will be saved.
The debugger will be able to query the saved exception states by query
operation that will be provided by follow up patches.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Due to a HW bug, waves in only half the shader arrays can enter trap.
When starting a debug session, relocate all waves to the first shader
array of each shader engine and mask off the 2nd shader array as
unavailable.
When ending a debug session, re-enable the 2nd shader array per
shader engine.
User CU masking per queue cannot be guaranteed to remain functional
if requested during debugging (e.g. user cu mask requests only 2nd shader
array as an available resource leading to zero HW resources available)
nor can runtime be alerted of any of these changes during execution.
Make user CU masking and debugging mutual exclusive with respect to
availability.
If the debugger tries to attach to a process with a user cu masked
queue, return the runtime status as enabled but busy.
If the debugger tries to attach and fails to reallocate queue waves to
the first shader array of each shader engine, return the runtime status
as enabled but with an error.
In addition, like any other mutli-process debug supported devices,
disable trap temporary setup per-process to avoid performance impact from
setup overhead.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Unlike single process debug devices, multi-process debug devices allow
debug mode setting per-VMID (non-device-global).
Because the HWS manages PASID-VMID mapping, the new MAP_PROCESS API allows
the KFD to forward the required SPI debug register write requests.
To request a new debug mode setting change, the KFD must be able to
preempt all queues then remap all queues with these new setting
requests for MAP_PROCESS to take effect.
Note that by default, trap enablement in non-debug mode must be disabled
for performance reasons for multi-process debug devices due to setup
overhead in FW.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The HWS schedule allows a grace period for wave completion prior to
preemption for better performance by avoiding CWSR on waves that can
potentially complete quickly. The debugger, on the other hand, will
want to inspect wave status immediately after it actively triggers
preemption (a suspend function to be provided).
To minimize latency between preemption and debugger wave inspection, allow
immediate preemption by setting the grace period to 0.
Note that setting the preepmtion grace period to 0 will result in an
infinite grace period being set due to a CP FW bug so set it to 1 for now.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
The ROCm debugger will attach to a process to debug by PTRACE and will
expect the KFD to prepare a process for the target PID, whether the
target PID has opened the KFD device or not.
This patch is to explicity handle this requirement. Further HW mode
setting and runtime coordination requirements will be handled in
following patches.
In the case where the target process has not opened the KFD device,
a new KFD process must be created for the target PID.
The debugger as well as the target process for this case will have not
acquired any VMs so handle process restoration to correctly account for
this.
To coordinate with HSA runtime, the debugger must be aware of the target
process' runtime enablement status and will copy the runtime status
information into the debugged KFD process for later query.
On enablement, the debugger will subscribe to a set of exceptions where
each exception events will notify the debugger through a pollable FIFO
file descriptor that the debugger provides to the KFD to manage.
Finally on process termination of either the debugger or the target,
debugging must be disabled if it has not been done so.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
We need to track memory usage on a per partition basis. To do
that, store the local memory information in KFD node instead
of kfd device.
v2: squash in fix ("amdkfd: Use mem_id to access mem_partition info")
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
kfd_ioctl_get_dmabuf use the amdgpu bo xcp_id to get the gpu_id of the
KFD node from the exported dmabuf_adev, and then create kfd bo on the
correct adev and KFD node when importing the amdgpu bo to KFD.
Remove function kfd_device_by_adev, it is not needed as it is the same
result as dmabuf_adev->kfd.dev->nodes[0]->id.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
VRAM pgmap resource is allocated every time when switching compute
partitions because kfd_dev is re-initialized by post_partition_switch,
As a result, it causes memory region resource leaking and system
memory usage accounting unbalanced.
pgmap resource should be allocated and registered only once when loading
driver and freed when unloading driver, move it from kfd_dev to
amdgpu_kfd_dev.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Instead of start xcc id and number of xcc per node, use the xcc mask
which is the mask of logical ids of xccs belonging to a parition.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Fetch xcp information from xcp_mgr and also add xcc_mask to kfd node.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
kfd_flush_tlb_after_unmap should return true for GFX v9.4.3, to do TLB
heavyweight flush after unmapping from GPU to guarantee that the GPU
will not access pages after they have been unmapped. This also helps
improve the mapping to GPU performance.
Without this, KFD accidently flush TLB after mapping to GPU because the
vm update sequence number is increased by previous unmapping.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Update interrupt handling in CPX mode for GFX9.4.3 by using the
VMID space instead of SDMA client id to determine if an interrupt
should be processed by a KFD node. This is especially needed for
handling retry faults from MMHUB.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
This work is required for GC 9.4.3, previous to support memory
partitions per node at SVM. When multiple partition is configured,
every BO should be allocated inside one specific partition which
corresponds to the current amdgpu_device and kfd_node.
v2: squash in compilation fix (Alex)
v3: squash in fix for pre-gfx 9.4.3 (Alex)
v4: squash in best_loc fix (Alex)
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Currently, even if kfd_locked is set, a process is first
created and then removed to work around a race condition
in updating kfd_locked flag. Rework kfd_locked handling to
ensure no processes is created if kfd_locked is set. This
is achieved by updating kfd_locked under kfd_processes_mutex.
With this there is no need for kfd_locked to be an atomic
counter. Instead, it can be a regular integer.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
This patch updates SDMA queue management for multi XCC in GFX9.4.3.
- Allocate/deallocate SDMA queues from the correct SDMA engines
based on the partition mode.
- Updates the kgd2kfd interface to fetch the correct SDMA register
addresses.
- It also fixes dumping correct SDMA queue info in debugfs.
v2: squash in fix "drm/amdkfd: Fix XGMI SDMA user-mode queue allocation"
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
In a device that supports multiple XCCs, unlike AQL queues, the PM4 queue
will be only processed in one XCC in the partitioning. This patch
re-purposes the queue percentage variable in create queue and update
queue ioctl for the user space to specify the target XCC.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
This patch introduces multi-partition support in KFD.
This patch includes:
- Support for maximum 8 spatial partitions in KFD.
- Initialize one HIQ per partition.
- Management of VMID range depending on partition mode.
- Management of doorbell aperture space between all
partitions.
- Each partition does its own queue management, interrupt
handling, SMI event reporting.
- IOMMU, if enabled with multiple partitions, will only work
on first partition.
- SPM is only supported on the first partition.
- Currently, there is no support for resetting individual
partitions. All partitions will reset together.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Introduce a new structure, kfd_node, which will now represent
a compute node. kfd_node is carved out of kfd_dev structure.
kfd_dev struct now will become the parent of kfd_node, and will
store common resources such as doorbells, GTT sub-alloctor etc.
kfd_node struct will store all resources specific to a compute
node, such as device queue manager, interrupt handling etc.
This is the first step in adding compute partition support in KFD.
v2: introduce kfd_node struct to gc v11 (Hawking)
v3: make reference to kfd_dev struct through kfd_node (Morris)
v4: use kfd_node instead for kfd isr/mqd functions (Morris)
v5: rebase (Alex)
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
For GC 9.4.3, disable retry as default and XNACK can be different
modes per process.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Handle case when module is unloaded (kfd_exit) before a process space
(mm_struct) is released.
v2: Fixed potential race conditions by removing all kfd_process from
the process table first, then working on releasing the resources.
v3: Fixed loop element access / synchronization. Fixed extra empty lines.
Signed-off-by: David Belanger <david.belanger@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Update queue qpd is done for the first queue creation of the process,
if the device support XNACK mode per process, update qpd setup
sh_mem_config based on the process XNACK mode, to support the process
destroy all queues, change XNACK mode, and then create queues.
Add helper macro KFD_SUPPORT_XNACK_PER_PROCESS to remove duplicate code
and add new ASICs support in future.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Cleanup kfd_dev struct by removing ddev and pdev as both
drm_device and pci_dev can be fetched from amdgpu_device.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
When kfd_ioctl_wait_events needs to restart due to a signal, we need to
update the timeout to account for the time already elapsed. We also need
to undo auto_reset of events that have signaled already, so that the
restarted ioctl will be able to count those signals again.
This fixes infinite hangs when kfd_ioctl_wait_events is interrupted by a
signal.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-and-tested-by: Xiaogang Chen <Xiaogang.Chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Output user queue eviction and restore event. User queue eviction may be
triggered by svm or userptr MMU notifier, TTM eviction, device suspend
and CRIU checkpoint and restore.
User queue restore may be rescheduled if eviction happens again while
restore.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Starting with GFX11, MES requires wptr BOs to be GTT allocated/mapped to
GART for usermode queues in order to support oversubscription. In the
case that work is submitted to an unmapped queue, MES must have a GART
wptr address to determine whether the queue should be mapped.
This change is accompanied with changes in MES and is applicable for
MES_API_VERSION >= 2.
v3:
- Use amdgpu_vm_bo_lookup_mapping for wptr_bo mapping lookup
- Move wptr_bo refcount increment to amdgpu_amdkfd_map_gtt_bo_to_gart
- Remove list_del_init from amdgpu_amdkfd_map_gtt_bo_to_gart
- Cleanup/fix create_queue wptr_bo error handling
v4:
- Add MES version shift/mask defines to amdgpu_mes.h
- Change version check from MES_VERSION to MES_API_VERSION
- Add check in kfd_ioctl_create_queue before wptr bo pin/GART map to
ensure bo is a single page.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-5.19-2022-05-18:
amdgpu:
- Misc code cleanups
- Additional SMU 13.x enablement
- Smartshift fixes
- GFX11 fixes
- Support for SMU 13.0.4
- SMU mutex fix
- Suspend/resume fix
amdkfd:
- static checker fix
- Doorbell/MMIO resource handling fix
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220518205621.5741-1-alexander.deucher@amd.com
|
|
https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-5.19-2022-04-29:
amdgpu
- RAS updates
- SI dpm deadlock fix
- Misc code cleanups
- HDCP fixes
- PSR fixes
- DSC fixes
- SDMA doorbell cleanups
- S0ix fix
- DC FP fix
- Zen dom0 regression fix for APUs
- IP discovery updates
- Initial SoC21 support
- Support for new vbios tables
- Runtime PM fixes
- Add PSP TA debugfs interface
amdkfd:
- Misc code cleanups
- Ignore bogus MEC signals more efficiently
- SVM fixes
- Use bitmap helpers
radeon:
- Misc code cleanups
- Spelling/grammer fixes
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220429144853.5742-1-alexander.deucher@amd.com
|
|
Add initial support for soc21 in KFD compute
driver (Mukul)
- Add new definition for soc21 device.
- Add new file for amdgpu-kfd interface for GFX11 family.
- Add new file for queue management, interrupt handling,
mqd management for GFX11 family in KFD driver.
- Related changes/updates for soc21 device in
KFD driver.
- Repurpose last 2 entries of SDMA MQD for driver use.
v2: Add an optional argument into update queue operation (Mukul)
v3: Switch to ip version check, replace kgd_dev with
amdgpu_device (Hawking)
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Oak Zeng <Oak.Zeng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
[ 168.544078] ======================================================
[ 168.550309] WARNING: possible circular locking dependency detected
[ 168.556523] 5.16.0-kfd-fkuehlin #148 Tainted: G E
[ 168.562558] ------------------------------------------------------
[ 168.568764] kfdtest/3479 is trying to acquire lock:
[ 168.573672] ffffffffc0927a70 (&topology_lock){++++}-{3:3}, at:
kfd_topology_device_by_id+0x16/0x60 [amdgpu] [ 168.583663]
but task is already holding lock:
[ 168.589529] ffff97d303dee668 (&mm->mmap_lock#2){++++}-{3:3}, at:
vm_mmap_pgoff+0xa9/0x180 [ 168.597755]
which lock already depends on the new lock.
[ 168.605970]
the existing dependency chain (in reverse order) is:
[ 168.613487]
-> #3 (&mm->mmap_lock#2){++++}-{3:3}:
[ 168.619700] lock_acquire+0xca/0x2e0
[ 168.623814] down_read+0x3e/0x140
[ 168.627676] do_user_addr_fault+0x40d/0x690
[ 168.632399] exc_page_fault+0x6f/0x270
[ 168.636692] asm_exc_page_fault+0x1e/0x30
[ 168.641249] filldir64+0xc8/0x1e0
[ 168.645115] call_filldir+0x7c/0x110
[ 168.649238] ext4_readdir+0x58e/0x940
[ 168.653442] iterate_dir+0x16a/0x1b0
[ 168.657558] __x64_sys_getdents64+0x83/0x140
[ 168.662375] do_syscall_64+0x35/0x80
[ 168.666492] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 168.672095]
-> #2 (&type->i_mutex_dir_key#6){++++}-{3:3}:
[ 168.679008] lock_acquire+0xca/0x2e0
[ 168.683122] down_read+0x3e/0x140
[ 168.686982] path_openat+0x5b2/0xa50
[ 168.691095] do_file_open_root+0xfc/0x190
[ 168.695652] file_open_root+0xd8/0x1b0
[ 168.702010] kernel_read_file_from_path_initns+0xc4/0x140
[ 168.709542] _request_firmware+0x2e9/0x5e0
[ 168.715741] request_firmware+0x32/0x50
[ 168.721667] amdgpu_cgs_get_firmware_info+0x370/0xdd0 [amdgpu]
[ 168.730060] smu7_upload_smu_firmware_image+0x53/0x190 [amdgpu]
[ 168.738414] fiji_start_smu+0xcf/0x4e0 [amdgpu]
[ 168.745539] pp_dpm_load_fw+0x21/0x30 [amdgpu]
[ 168.752503] amdgpu_pm_load_smu_firmware+0x4b/0x80 [amdgpu]
[ 168.760698] amdgpu_device_fw_loading+0xb8/0x140 [amdgpu]
[ 168.768412] amdgpu_device_init.cold+0xdf6/0x1716 [amdgpu]
[ 168.776285] amdgpu_driver_load_kms+0x15/0x120 [amdgpu]
[ 168.784034] amdgpu_pci_probe+0x19b/0x3a0 [amdgpu]
[ 168.791161] local_pci_probe+0x40/0x80
[ 168.797027] work_for_cpu_fn+0x10/0x20
[ 168.802839] process_one_work+0x273/0x5b0
[ 168.808903] worker_thread+0x20f/0x3d0
[ 168.814700] kthread+0x176/0x1a0
[ 168.819968] ret_from_fork+0x1f/0x30
[ 168.825563]
-> #1 (&adev->pm.mutex){+.+.}-{3:3}:
[ 168.834721] lock_acquire+0xca/0x2e0
[ 168.840364] __mutex_lock+0xa2/0x930
[ 168.846020] amdgpu_dpm_get_mclk+0x37/0x60 [amdgpu]
[ 168.853257] amdgpu_amdkfd_get_local_mem_info+0xba/0xe0 [amdgpu]
[ 168.861547] kfd_create_vcrat_image_gpu+0x1b1/0xbb0 [amdgpu]
[ 168.869478] kfd_create_crat_image_virtual+0x447/0x510 [amdgpu]
[ 168.877884] kfd_topology_add_device+0x5c8/0x6f0 [amdgpu]
[ 168.885556] kgd2kfd_device_init.cold+0x385/0x4c5 [amdgpu]
[ 168.893347] amdgpu_amdkfd_device_init+0x138/0x180 [amdgpu]
[ 168.901177] amdgpu_device_init.cold+0x141b/0x1716 [amdgpu]
[ 168.909025] amdgpu_driver_load_kms+0x15/0x120 [amdgpu]
[ 168.916458] amdgpu_pci_probe+0x19b/0x3a0 [amdgpu]
[ 168.923442] local_pci_probe+0x40/0x80
[ 168.929249] work_for_cpu_fn+0x10/0x20
[ 168.935008] process_one_work+0x273/0x5b0
[ 168.940944] worker_thread+0x20f/0x3d0
[ 168.946623] kthread+0x176/0x1a0
[ 168.951765] ret_from_fork+0x1f/0x30
[ 168.957277]
-> #0 (&topology_lock){++++}-{3:3}:
[ 168.965993] check_prev_add+0x8f/0xbf0
[ 168.971613] __lock_acquire+0x1299/0x1ca0
[ 168.977485] lock_acquire+0xca/0x2e0
[ 168.982877] down_read+0x3e/0x140
[ 168.987975] kfd_topology_device_by_id+0x16/0x60 [amdgpu]
[ 168.995583] kfd_device_by_id+0xa/0x20 [amdgpu]
[ 169.002180] kfd_mmap+0x95/0x200 [amdgpu]
[ 169.008293] mmap_region+0x337/0x5a0
[ 169.013679] do_mmap+0x3aa/0x540
[ 169.018678] vm_mmap_pgoff+0xdc/0x180
[ 169.024095] ksys_mmap_pgoff+0x186/0x1f0
[ 169.029734] do_syscall_64+0x35/0x80
[ 169.035005] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 169.041754]
other info that might help us debug this:
[ 169.053276] Chain exists of:
&topology_lock --> &type->i_mutex_dir_key#6 --> &mm->mmap_lock#2
[ 169.068389] Possible unsafe locking scenario:
[ 169.076661] CPU0 CPU1
[ 169.082383] ---- ----
[ 169.088087] lock(&mm->mmap_lock#2);
[ 169.092922] lock(&type->i_mutex_dir_key#6);
[ 169.100975] lock(&mm->mmap_lock#2);
[ 169.108320] lock(&topology_lock);
[ 169.112957]
*** DEADLOCK ***
This commit fixes the deadlock warning by ensuring pm.mutex is not
held while holding the topology lock. For this, kfd_local_mem_info
is moved into the KFD dev struct and filled during device init.
This cached value can then be used instead of querying the value
again and again.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-5.19-2022-04-22:
amdgpu:
- SMU message documentation update
- Misc code cleanups
- Documenation updates
- PSP TA updates
- Runtime PM regression fix
- SR-IOV header cleanup
- Misc fixes
amdkfd:
- TLB flush fixes
- GWS fixes
- CRIU GWS support
radeon:
- Misc code cleanups
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220422150049.5859-1-alexander.deucher@amd.com
|
|
https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-5.19-2022-04-15:
amdgpu:
- USB-C updates
- GPUVM updates
- TMZ fixes for RV
- DCN 3.1 pstate fixes
- Display z state fixes
- RAS fixes
- Misc code cleanups and spelling fixes
- More DC FP rework
- GPUVM TLB handling rework
- Power management sysfs code cleanup
- Add RAS support for VCN
- Backlight fix
- Add unique id support for more asics
- Misc display updates
- SR-IOV fixes
- Extend CG and PG flags to 64 bits
- Enable VCN clk sysfs nodes for navi12
amdkfd:
- Fix IO link cleanup during device removal
- RAS fixes
- Retry fault fixes
- Asynchronously free events
- SVM fixes
radeon:
- Drop some dead code
- Misc code cleanups
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220415135144.5700-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>
|
|
MEC firmware sometimes sends signal interrupts without a valid context ID
on end of pipe events that don't intend to signal any HSA signals.
This triggers the slow path in kfd_signal_event_interrupt that scans the
entire event page for signaled events. Detect these signals in the top
half interrupt handler to stop processing them as early as possible.
Because we now always treat event ID 0 as invalid, reserve that ID during
process initialization.
v2: Update firmware version checks to support more GPUs
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Add support to checkpoint/restore GWS (Global Wave Sync) queues.
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
To make kfd_flush_tlb_after_unmap visible in kfd_svm.c,
move it into kfd_priv.h. And change it to an inline function.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Currently, the IO-links to the device being removed from topology,
are not cleared. As a result, there would be dangling links left in
the KFD topology. This patch aims to fix the following:
1. Cleanup all IO links to the device being removed.
2. Ensure that node numbering in sysfs and nodes proximity domain
values are consistent after the device is removed:
a. Adding a device and removing a GPU device are made mutually
exclusive.
b. The global proximity domain counter is no longer required to be
an atomic counter. A normal 32-bit counter can be used instead.
3. Update generation_count to let user-mode know that topology has
changed due to device removal.
CC: Shuotao Xu <shuotaoxu@microsoft.com>
Reviewed-by: Shuotao Xu <shuotaoxu@microsoft.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
To support multi-thread update page table.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Instead of trying to figure out if a TLB flush is necessary or not use
the information provided by the VM subsystem now.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Philip Yang<Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
Pull drm updates from Dave Airlie:
"Lots of work all over, Intel improving DG2 support, amdkfd CRIU
support, msm new hw support, and faster fbdev support.
dma-buf:
- rename dma-buf-map to iosys-map
core:
- move buddy allocator to core
- add pci/platform init macros
- improve EDID parser deep color handling
- EDID timing type 7 support
- add GPD Win Max quirk
- add yes/no helpers to string_helpers
- flatten syncobj chains
- add nomodeset support to lots of drivers
- improve fb-helper clipping support
- add default property value interface
fbdev:
- improve fbdev ops speed
ttm:
- add a backpointer from ttm bo->ttm resource
dp:
- move displayport headers
- add a dp helper module
bridge:
- anx7625 atomic support, HDCP support
panel:
- split out panel-lvds and lvds bindings
- find panels in OF subnodes
privacy:
- add chromeos privacy screen support
fb:
- hot unplug fw fb on forced removal
simpledrm:
- request region instead of marking ioresource busy
- add panel oreintation property
udmabuf:
- fix oops with 0 pages
amdgpu:
- power management code cleanup
- Enable freesync video mode by default
- RAS code cleanup
- Improve VRAM access for debug using SDMA
- SR-IOV rework special register access and fixes
- profiling power state request ioctl
- expose IP discovery via sysfs
- Cyan skillfish updates
- GC 10.3.7, SDMA 5.2.7, DCN 3.1.6 updates
- expose benchmark tests via debugfs
- add module param to disable XGMI for testing
- GPU reset debugfs register dumping support
amdkfd:
- CRIU support
- SDMA queue fixes
radeon:
- UVD suspend fix
- iMac backlight fix
i915:
- minimal parallel submission for execlists
- DG2-G12 subplatform added
- DG2 programming workarounds
- DG2 accelerated migration support
- flat CCS and CCS engine support for XeHP
- initial small BAR support
- drop fake LMEM support
- ADL-N PCH support
- bigjoiner updates
- introduce VMA resources and async unbinding
- register definitions cleanups
- multi-FBC refactoring
- DG1 OPROM over SPI support
- ADL-N platform enabling
- opregion mailbox #5 support
- DP MST ESI improvements
- drm device based logging
- async flip optimisation for DG2
- CPU arch abstraction fixes
- improve GuC ADS init to work on aarch64
- tweak TTM LRU priority hint
- GuC 69.0.3 support
- remove short term execbuf pins
nouveau:
- higher DP/eDP bitrates
- backlight fixes
msm:
- dpu + dp support for sc8180x
- dp support for sm8350
- dpu + dsi support for qcm2290
- 10nm dsi phy tuning support
- bridge support for dp encoder
- gpu support for additional 7c3 SKUs
ingenic:
- HDMI support for JZ4780
- aux channel EDID support
ast:
- AST2600 support
- add wide screen support
- create DP/DVI connectors
omapdrm:
- fix implicit dma_buf fencing
vc4:
- add CSC + full range support
- better display firmware handoff
panfrost:
- add initial dual-core GPU support
stm:
- new revision support
- fb handover support
mediatek:
- transfer display binding document to yaml format.
- add mt8195 display device binding.
- allow commands to be sent during video mode.
- add wait_for_event for crtc disable by cmdq.
tegra:
- YUV format support
rcar-du:
- LVDS support for M3-W+ (R8A77961)
exynos:
- BGR pixel format for FIMD device"
* tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm: (1529 commits)
drm/i915/display: Do not re-enable PSR after it was marked as not reliable
drm/i915/display: Fix HPD short pulse handling for eDP
drm/amdgpu: Use drm_mode_copy()
drm/radeon: Use drm_mode_copy()
drm/amdgpu: Use ternary operator in `vcn_v1_0_start()`
drm/amdgpu: Remove pointless on stack mode copies
drm/amd/pm: fix indenting in __smu_cmn_reg_print_error()
drm/amdgpu/dc: fix typos in comments
drm/amdgpu: fix typos in comments
drm/amd/pm: fix typos in comments
drm/amdgpu: Add stolen reserved memory for MI25 SRIOV.
drm/amdgpu: Merge get_reserved_allocation to get_vbios_allocations.
drm/amdkfd: evict svm bo worker handle error
drm/amdgpu/vcn: fix vcn ring test failure in igt reload test
drm/amdgpu: only allow secure submission on rings which support that
drm/amdgpu: fixed the warnings reported by kernel test robot
drm/amd/display: 3.2.177
drm/amd/display: [FW Promotion] Release 0.0.108.0
drm/amd/display: Add save/restore PANEL_PWRSEQ_REF_DIV2
drm/amd/display: Wait for hubp read line for Pollock
...
|
|
Move the check for the actual pgmap types that need the free at refcount
one behavior into the out of line helper, and thus avoid the need to
pull memremap.h into mm.h.
Link: https://lkml.kernel.org/r/20220210072828.2930359-7-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: "Sierra Guiza, Alejandro (Alex)" <alex.sierra@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Chaitanya Kulkarni <kch@nvidia.com>
Cc: Karol Herbst <kherbst@redhat.com>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: "Pan, Xinhui" <Xinhui.Pan@amd.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
|
|
kfd_chardev() doesn't provide much useful information in dev_... messages
on multi-GPU systems because there is only one KFD device, which doesn't
correspond to any particular GPU. Use the actual GPU device to indicate
the GPU that caused a message.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
|
There is a regular need in the kernel to provide a way to declare having
a dynamically sized set of trailing elements in a structure. Kernel code
should always use "flexible array members" for these cases. The older
style of one-element or zero-length arrays should no longer be used.
Reference:
https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays
Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Changcheng Deng <deng.changcheng@zte.com.cn>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
