drm/amdgpu: Store CU info from all XCCs for GFX v9.4.3

Currently, we store CU info only for a single XCC assuming
that it is the same for all XCCs. However, that may not be
true. As a result, store

drm/amdgpu: Store CU info from all XCCs for GFX v9.4.3

Currently, we store CU info only for a single XCC assuming
that it is the same for all XCCs. However, that may not be
true. As a result, store CU info for all XCCs. This info is
later used for CU masking.

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>

show more ...

drm/amdkfd: use correct method to get clock under SRIOV

[What]
Current SRIOV still using adev->clock.default_XX which gets from
atomfirmware. But these fields are abandoned in atomfirmware long ago.

drm/amdkfd: use correct method to get clock under SRIOV

[What]
Current SRIOV still using adev->clock.default_XX which gets from
atomfirmware. But these fields are abandoned in atomfirmware long ago.
Which may cause function to return a 0 value.

[How]
We don't need to check whether SR-IOV. For SR-IOV one-vf-mode,
pm is enabled and VF is able to read dpm clock
from pmfw, so we can use dpm clock interface directly. For
multi-VF mode, VF pm is disabled, so driver can just react as pm
disabled. One-vf-mode is introduced from GFX9 so it shall not have
any backward compatibility issue.

Signed-off-by: Horace Chen <horace.chen@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdkfd: drop IOMMUv2 support

Now that we use the dGPU path for all APUs, drop the
IOMMUv2 support.

v2: drop the now unused queue manager functions for gfx7/8 APUs

Reviewed-by: Felix Kuehling <

drm/amdkfd: drop IOMMUv2 support

Now that we use the dGPU path for all APUs, drop the
IOMMUv2 support.

v2: drop the now unused queue manager functions for gfx7/8 APUs

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdkfd: Fix stack size in 'amdgpu_amdkfd_unmap_hiq'

Dynamically allocate large local variable instead of putting it onto the
stack to avoid exceeding the stack size:
drivers/gpu/drm/amd/amdgpu/a

drm/amdkfd: Fix stack size in 'amdgpu_amdkfd_unmap_hiq'

Dynamically allocate large local variable instead of putting it onto the
stack to avoid exceeding the stack size:
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c: In function ‘amdgpu_amdkfd_unmap_hiq’:
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c:868:1: warning: the frame size of 1280 bytes is larger than 1024 bytes [-Wframe-larger-than=]

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202307080505.V12qS0oz-lkp@intel.com
Suggested-by: Guchun Chen <guchun.chen@amd.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Mukul Joshi <mukul.joshi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdkfd: Use KIQ to unmap HIQ

Currently, we unmap HIQ by directly writing to HQD
registers. This doesn't work for GFX9.4.3. Instead,
use KIQ to unmap HIQ, similar to how we use KIQ to
map HIQ. Us

drm/amdkfd: Use KIQ to unmap HIQ

Currently, we unmap HIQ by directly writing to HQD
registers. This doesn't work for GFX9.4.3. Instead,
use KIQ to unmap HIQ, similar to how we use KIQ to
map HIQ. Using KIQ to unmap HIQ works for all GFX
series post GFXv9.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

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

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

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

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>

show more ...

drm/amdkfd: update process interrupt handling for debug events

The debugger must be notified by any debugger subscribed exception
that comes from hardware interrupts.

If a debugger session exits, a

drm/amdkfd: update process interrupt handling for debug events

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>

show more ...

drm/amdkfd: Align partition memory size to page size

The compute partition memory size calculated from KFD_XCP_MEMORY_SIZE
may not align to page size if xcp_mgr->num_xcp_per_mem_partition is 6.

Cha

drm/amdkfd: Align partition memory size to page size

The compute partition memory size calculated from KFD_XCP_MEMORY_SIZE
may not align to page size if xcp_mgr->num_xcp_per_mem_partition is 6.

Change the KFD_XCP_MEMORY_SIZE macro to return page align size, so KFD
node memory size reported in sysfs is page align size, to avoid
application VRAM allocation failure because application may use the size
directly and Thunk requires the memory allocation size is page size
align.

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>

show more ...

drm/amdgpu/gmc9: fix 64 bit division in partition code

Rework logic or use do_div() to avoid problems on 32 bit.

v2: add a missing case for XCP macro
v3: fix out of bounds array access
v4: fix xcp

drm/amdgpu/gmc9: fix 64 bit division in partition code

Rework logic or use do_div() to avoid problems on 32 bit.

v2: add a missing case for XCP macro
v3: fix out of bounds array access
v4: fix xcp handling harder

Acked-by: Guchun Chen <guchun.chen@amd.com> (v1)
Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> (v3)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdgpu: Do not access members of xcp w/o check (v2)

Not all the asic needs xcp. ensure check xcp availabity
before accessing its member.

v2: add missing change in kfd_topology.c

Signed-off-by:

drm/amdgpu: Do not access members of xcp w/o check (v2)

Not all the asic needs xcp. ensure check xcp availabity
before accessing its member.

v2: add missing change in kfd_topology.c

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdkfd: Move local_mem_info to kfd_node

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 f

drm/amdkfd: Move local_mem_info to kfd_node

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>

show more ...

drm/amdgpu: KFD graphics interop support compute partition

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 th

drm/amdgpu: KFD graphics interop support compute partition

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>

show more ...

drm/amdkfd: Add device repartition support

GFX9.4.3 will support dynamic repartitioning of the GPU through sysfs.
Add device repartitioning support in KFD to repartition GPU from one
mode to other.

drm/amdkfd: Add device repartition support

GFX9.4.3 will support dynamic repartitioning of the GPU through sysfs.
Add device repartitioning support in KFD to repartition GPU from one
mode to other.

v2: squash in fix ("drm/amdkfd: Fix warning kgd2kfd_unlock_kfd defined but not used")

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>

show more ...

drm/amdgpu: Add XCC inst to PASID TLB flushing

Add XCC instance to select the correct KIQ ring when
flushing TLBs on a multi-XCC setup.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Tested-by: A

drm/amdgpu: Add XCC inst to PASID TLB flushing

Add XCC instance to select the correct KIQ ring when
flushing TLBs on a multi-XCC setup.

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>

show more ...

drm/amdgpu: add bitmask to iterate vmhubs

As the layout of VMHUB definition has been changed to cover multiple
XCD/AID case, the original num_vmhubs is not appropriate to do vmhub
iteration any more

drm/amdgpu: add bitmask to iterate vmhubs

As the layout of VMHUB definition has been changed to cover multiple
XCD/AID case, the original num_vmhubs is not appropriate to do vmhub
iteration any more.

Drop num_vmhubs and introduce vmhubs_mask instead.

v2: switch to the new VMHUB layout
v3: use DECLARE_BITMAP to define vmhubs_mask

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdgpu: introduce vmhub definition for multi-partition cases (v3)

v1: Each partition has its own gfxhub or mmhub. adjust
the num of MAX_VMHUBS and the GFXHUB/MMHUB layout (Le)

v2: re-design the

drm/amdgpu: introduce vmhub definition for multi-partition cases (v3)

v1: Each partition has its own gfxhub or mmhub. adjust
the num of MAX_VMHUBS and the GFXHUB/MMHUB layout (Le)

v2: re-design the AMDGPU_GFXHUB/AMDGPU_MMHUB layout (Le)

v3: apply the gfxhub/mmhub layout to new IPs (Hawking)

v4: fix up gmc11 (Alex)

v5: rebase (Alex)

Signed-off-by: Le Ma <le.ma@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdkfd: Update KFD TTM mem limit

Use the helper function in TTM to get TTM memory
limit and set KFD's internal mem limit. This ensures
that KFD's TTM mem limit and actual TTM mem limit are
exact

drm/amdkfd: Update KFD TTM mem limit

Use the helper function in TTM to get TTM memory
limit and set KFD's internal mem limit. This ensures
that KFD's TTM mem limit and actual TTM mem limit are
exactly same.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdgpu: move queue_bitmap to an independent structure (v3)

To allocate independent queue_bitmap for each XCD,
then the old bitmap policy can be continued to use
with a clear logic.

Use mec_bitm

drm/amdgpu: move queue_bitmap to an independent structure (v3)

To allocate independent queue_bitmap for each XCD,
then the old bitmap policy can be continued to use
with a clear logic.

Use mec_bitmap[0] as default for all non-GC 9.4.3 IPs.

v2: squash commits to avoid breaking the build
v3: unify naming style

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdgpu: rename num_doorbells

Rename doorbell.num_doorbells to doorbell.num_kernel_doorbells to
make it more readable.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian Koenig <christia

drm/amdgpu: rename num_doorbells

Rename doorbell.num_doorbells to doorbell.num_kernel_doorbells to
make it more readable.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian Koenig <christian.koenig@amd.com>
Acked-by: Christian Koenig <christian.koenig@amd.com>
Signed-off-by: Shashank Sharma <shashank.sharma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdgpu: cleanup scheduler job initialization v2

Init the DRM scheduler base class while allocating the job.

This makes the whole handling much more cleaner.

v2: fix coding style

Signed-off-by

drm/amdgpu: cleanup scheduler job initialization v2

Init the DRM scheduler base class while allocating the job.

This makes the whole handling much more cleaner.

v2: fix coding style

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221014084641.128280-7-christian.koenig@amd.com

show more ...

drm/amdgpu: disable GFXOFF during compute for GFX11

Temporary workaround to fix issues observed in some compute applications
when GFXOFF is enabled on GFX11.

Signed-off-by: Graham Sider <Graham.Sid

drm/amdgpu: disable GFXOFF during compute for GFX11

Temporary workaround to fix issues observed in some compute applications
when GFXOFF is enabled on GFX11.

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.0.x

show more ...

drm/amdkfd: Cleanup kfd_dev struct

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

drm/amdkfd: Cleanup kfd_dev struct

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>

show more ...

drm/amdgpu: disable GFXOFF during compute for GFX11

Temporary workaround to fix issues observed in some compute applications
when GFXOFF is enabled on GFX11.

Signed-off-by: Graham Sider <Graham.Sid

drm/amdgpu: disable GFXOFF during compute for GFX11

Temporary workaround to fix issues observed in some compute applications
when GFXOFF is enabled on GFX11.

Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

drm/amdgpu: remove ras_error_status parameter for UMC poison handler

Make the code simpler.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off

drm/amdgpu: remove ras_error_status parameter for UMC poison handler

Make the code simpler.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...

Revert "drm/amdgpu: let mode2 reset fallback to default when failure"

This reverts commit dac6b80818ac2353631c5a33d140d8d5508e2957.

This commit reverted the AMDGPU_SKIP_MODE2_RESET as it conflicts

Revert "drm/amdgpu: let mode2 reset fallback to default when failure"

This reverts commit dac6b80818ac2353631c5a33d140d8d5508e2957.

This commit reverted the AMDGPU_SKIP_MODE2_RESET as it conflicts with
the original design of reset handler. Will redesign it.

Fixes: dac6b80818ac23 ("drm/amdgpu: let mode2 reset fallback to default when failure")
Signed-off-by: Victor Zhao <Victor.Zhao@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

show more ...