linux.git/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c, branch v6.5

drm/amdkfd: disable IOMMUv2 support for KV/CZ

2023-08-09T14:58:30+00:00

Use the dGPU path instead.  There were a lot of platform
issues with IOMMU in general on these chips due to windows
not enabling IOMMU at the time.  The dGPU path has been
used for a long time with newer APUs and works fine.  This
also paves the way to simplify the driver significantly.

v2: use the dGPU queue manager functions

Reviewed-by: Felix Kuehling 
Acked-by: Christian König 
Tested-by: Mike Lothian 
Signed-off-by: Alex Deucher

drm/amdkfd: fix trap handling work around for debugging

2023-07-25T20:13:58+00:00

Update the list of devices that require the cwsr trap handling
workaround for debugging use cases.

Signed-off-by: Jonathan Kim 
Acked-by: Ruili Ji 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: decrement queue count on mes queue destroy

2023-06-15T15:06:58+00:00

Queue count should decrement on queue destruction regardless of HWS
support type.

Signed-off-by: Jonathan Kim 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: To enable traps for GC_11_0_4 and up

2023-06-15T15:06:57+00:00

Flag trap_en should be enabled for trap handler.

Signed-off-by: Ruili Ji 
Signed-off-by: Aaron Liu 
Reviewed-by: Alex Deucher 
Signed-off-by: Alex Deucher

drm/amdkfd: fix and enable debugging for gfx11

2023-06-09T16:48:19+00:00

There are a couple of fixes required to enable gfx11 debugging.

First, ADD_QUEUE.trap_en is an inappropriate place to toggle
a per-process register so move it to SET_SHADER_DEBUGGER.trap_en.
When ADD_QUEUE.skip_process_ctx_clear is set, MES will prioritize
the SET_SHADER_DEBUGGER.trap_en setting.

Second, to preserve correct save/restore priviledged wave states
in coordination with the trap enablement setting, resume suspended
waves early in the disable call.

Signed-off-by: Jonathan Kim 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: Fix reserved SDMA queues handling

2023-06-09T16:44:56+00:00

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 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: add debug queue snapshot operation

2023-06-09T16:36:57+00:00

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 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: add debug suspend and resume process queues operation

2023-06-09T16:36:43+00:00

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 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: apply trap workaround for gfx11

2023-06-09T16:35:52+00:00

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 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdgpu: prepare map process for multi-process debug devices

2023-06-09T16:35:39+00:00

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 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher