linux-stable.git/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c, branch linux-5.13.y Linux kernel stable tree drm/amdkfd: Walk through list with dqm lock hold 2021-07-19T08:04:41+00:00 xinhui pan xinhui.pan@amd.com 2021-06-15T07:11:07+00:00 38b73fe18c6b0628bd4156f13775c484f5c650db [ Upstream commit 56f221b6389e7ab99c30bbf01c71998ae92fc584 ] To avoid any list corruption. Signed-off-by: xinhui pan <xinhui.pan@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 56f221b6389e7ab99c30bbf01c71998ae92fc584 ]

To avoid any list corruption.

Signed-off-by: xinhui pan <xinhui.pan@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: Fix circular lock in nocpsch path 2021-07-19T08:04:40+00:00 Amber Lin Amber.Lin@amd.com 2021-06-07T18:46:21+00:00 3382ec34a4d56c02a2c146e9c6c73bfe8d6e2604 [ Upstream commit a7b2451d31cfa2e8aeccf3b35612ce33f02371fc ] Calling free_mqd inside of destroy_queue_nocpsch_locked can cause a circular lock. destroy_queue_nocpsch_locked is called under a DQM lock, which is taken in MMU notifiers, potentially in FS reclaim context. Taking another lock, which is BO reservation lock from free_mqd, while causing an FS reclaim inside the DQM lock creates a problematic circular lock dependency. Therefore move free_mqd out of destroy_queue_nocpsch_locked and call it after unlocking DQM. 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> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit a7b2451d31cfa2e8aeccf3b35612ce33f02371fc ]

Calling free_mqd inside of destroy_queue_nocpsch_locked can cause a
circular lock. destroy_queue_nocpsch_locked is called under a DQM lock,
which is taken in MMU notifiers, potentially in FS reclaim context.
Taking another lock, which is BO reservation lock from free_mqd, while
causing an FS reclaim inside the DQM lock creates a problematic circular
lock dependency. Therefore move free_mqd out of
destroy_queue_nocpsch_locked and call it after unlocking DQM.

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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: fix circular locking on get_wave_state 2021-07-19T08:04:40+00:00 Jonathan Kim jonathan.kim@amd.com 2021-06-11T17:36:34+00:00 161c4c2a19f494cb2aceeaa315b442abab649f7a [ Upstream commit 63f6e01237257e7226efc5087f3f0b525d320f54 ] get_wave_state acquires the mmap_lock on copy_to_user but so do mmu_notifiers. mmu_notifiers allows dqm locking so do get_wave_state outside the dqm_lock to prevent circular locking. v2: squash in unused variable removal. 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> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 63f6e01237257e7226efc5087f3f0b525d320f54 ]

get_wave_state acquires the mmap_lock on copy_to_user but so do
mmu_notifiers.  mmu_notifiers allows dqm locking so do get_wave_state
outside the dqm_lock to prevent circular locking.

v2: squash in unused variable removal.

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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drm/amdkfd: dqm fence memory corruption 2021-04-09T20:47:06+00:00 Qu Huang jinsdb@126.com 2021-01-28T12:14:25+00:00 b010affea45d812d8d386cc49c3b2bafd74b4154 Amdgpu driver uses 4-byte data type as DQM fence memory, and transmits GPU address of fence memory to microcode through query status PM4 message. However, query status PM4 message definition and microcode processing are all processed according to 8 bytes. Fence memory only allocates 4 bytes of memory, but microcode does write 8 bytes of memory, so there is a memory corruption. Changes since v1: * Change dqm->fence_addr as a u64 pointer to fix this issue, also fix up query_status and amdkfd_fence_wait_timeout function uses 64 bit fence value to make them consistent. Signed-off-by: Qu Huang <jinsdb@126.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> 
Amdgpu driver uses 4-byte data type as DQM fence memory,
and transmits GPU address of fence memory to microcode
through query status PM4 message. However, query status
PM4 message definition and microcode processing are all
processed according to 8 bytes. Fence memory only allocates
4 bytes of memory, but microcode does write 8 bytes of memory,
so there is a memory corruption.

Changes since v1:
  * Change dqm->fence_addr as a u64 pointer to fix this issue,
also fix up query_status and amdkfd_fence_wait_timeout function
uses 64 bit fence value to make them consistent.

Signed-off-by: Qu Huang <jinsdb@126.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>
drm/amdkfd: Fix UBSAN shift-out-of-bounds warning 2021-03-24T03:00:57+00:00 Anson Jacob Anson.Jacob@amd.com 2021-03-03T17:33:15+00:00 50e2fc36e72d4ad672032ebf646cecb48656efe0 If get_num_sdma_queues or get_num_xgmi_sdma_queues is 0, we end up doing a shift operation where the number of bits shifted equals number of bits in the operand. This behaviour is undefined. Set num_sdma_queues or num_xgmi_sdma_queues to ULLONG_MAX, if the count is >= number of bits in the operand. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1472 Reported-by: Lyude Paul <lyude@redhat.com> Signed-off-by: Anson Jacob <Anson.Jacob@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: Lyude Paul <lyude@redhat.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
If get_num_sdma_queues or get_num_xgmi_sdma_queues is 0, we end up
doing a shift operation where the number of bits shifted equals
number of bits in the operand. This behaviour is undefined.

Set num_sdma_queues or num_xgmi_sdma_queues to ULLONG_MAX, if the
count is >= number of bits in the operand.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1472

Reported-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Anson Jacob <Anson.Jacob@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Check HIQ's MQD for queue preemption status 2021-03-24T02:59:25+00:00 Oak Zeng Oak.Zeng@amd.com 2020-07-07T23:29:37+00:00 51a0f459f15fca1e1443de8d92431846872ee5cb MEC firmware can silently fail the queue preemption request without time out. In this case, HIQ's MQD's queue_doorbell_id will be set. Check this field to see whether last queue preemption was successful or not. Signed-off-by: Oak Zeng <Oak.Zeng@amd.com> Suggested-by: Jay Cornwall <Jay.Cornwall@amd.com> Acked-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
MEC firmware can silently fail the queue preemption request
without time out. In this case, HIQ's MQD's queue_doorbell_id
will be set. Check this field to see whether last queue preemption
was successful or not.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Suggested-by: Jay Cornwall <Jay.Cornwall@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Add Aldebaran KFD support 2021-03-10T05:02:13+00:00 Yong Zhao Yong.Zhao@amd.com 2019-11-29T18:51:16+00:00 36e22d59dd10e4261079dcec6a44fc22b2a435e0 Add initial KFD support. Signed-off-by: Yong Zhao <Yong.Zhao@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Add initial KFD support.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Move set_trap_handler out of dqm->ops 2021-03-05T20:13:24+00:00 Jay Cornwall jay.cornwall@amd.com 2021-02-25T20:56:35+00:00 7c9631af792b3d104499061b965a8fea224ff63d Trap handler is set per-process per-device and is unrelated to queue management. Move implementation closer to TMA setup code. Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Trap handler is set per-process per-device and is unrelated
to queue management.

Move implementation closer to TMA setup code.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: correct pipe offset calculation 2020-12-10T21:41:49+00:00 Jiansong Chen Jiansong.Chen@amd.com 2020-12-09T11:43:44+00:00 0d801007f90ec023aefc1da19529bf9985050227 Correct pipe offset calculation in is_pipe_enabled function, it should be done in queues. Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Correct pipe offset calculation in is_pipe_enabled function,
it should be done in queues.

Signed-off-by: Jiansong Chen <Jiansong.Chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Merge tag 'amd-drm-next-5.11-2020-11-05' of git://people.freedesktop.org/~agd5f/linux into drm-next 2020-11-10T07:48:47+00:00 Dave Airlie airlied@redhat.com 2020-11-10T07:48:47+00:00 5b8c596976d4338942dd889b66cd06dc766424e1 amd-drm-next-5.11-2020-11-05: amdgpu: - Add initial support for Vangogh - Add support for Green Sardine - Add initial support for Dimgrey Cavefish - Scatter/Gather display support for Renoir - Updates for Sienna Cichlid - Updates for Navy Flounder - SMU7 power improvements - Modifier support for gfx9+ - CI BACO fixes - Arcturus SMU fixes - Lots of code cleanups - DC fixes - Kernel doc fixes - Add more GPU HW client information to page fault error logging - MPO clock tuning for RV - FP fixes for DCN3 on ARM and PPC radeon: - Expose voltage via hwmon on Sumo APUs amdkfd: - Fix unique id handling - Misc fixes From: Alex Deucher <alexdeucher@gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201105222749.201798-1-alexander.deucher@amd.com 
amd-drm-next-5.11-2020-11-05:

amdgpu:
- Add initial support for Vangogh
- Add support for Green Sardine
- Add initial support for Dimgrey Cavefish
- Scatter/Gather display support for Renoir
- Updates for Sienna Cichlid
- Updates for Navy Flounder
- SMU7 power improvements
- Modifier support for gfx9+
- CI BACO fixes
- Arcturus SMU fixes
- Lots of code cleanups
- DC fixes
- Kernel doc fixes
- Add more GPU HW client information to page fault error logging
- MPO clock tuning for RV
- FP fixes for DCN3 on ARM and PPC

radeon:
- Expose voltage via hwmon on Sumo APUs

amdkfd:
- Fix unique id handling
- Misc fixes

From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201105222749.201798-1-alexander.deucher@amd.com