kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c, branch v6.1.22

drm/amdgpu: fix userptr HMM range handling v2

2022-11-21T21:40:30+00:00

The basic problem here is that it's not allowed to page fault while holding the reservation lock. So it can happen that multiple processes try to validate an userptr at the same time. Work around that by putting the HMM range object into the mutex protected bo list for now. v2: make sure range is set to NULL in case of an error Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Felix Kuehling CC: stable@vger.kernel.org Signed-off-by: Alex Deucher

Merge tag 'amd-drm-fixes-6.1-2022-11-16' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

2022-11-18T01:09:04+00:00

amd-drm-fixes-6.1-2022-11-16: amdgpu: - Fix a possible memory leak in ganng submit error path - DP tunneling fixes - DCN 3.1 page flip fix - DCN 3.2.x fixes - DCN 3.1.4 fixes - Don't expose degamma on hardware that doesn't support it - BACO fixes for SMU 11.x - BACO fixes for SMU 13.x - Virtual display fix for devices with no display hardware amdkfd: - Memory limit regression fix Signed-off-by: Dave Airlie From: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20221117040416.6100-1-alexander.deucher@amd.com

Merge tag 'drm-misc-fixes-2022-11-17' of git://anongit.freedesktop.org/drm/drm-misc into drm-fixes

2022-11-17T21:08:57+00:00

drm-misc-fixes for v6.1-rc6: - Fix error handling in vc4_atomic_commit_tail() - Set bpc for logictechno panels. - Fix potential memory leak in drm_dev_init() - Fix potential null-ptr-deref in drm_vblank_destroy_worker() - Set lima's clkname corrrectly when regulator is missing. - Small amdgpu fix to gang submission. - Revert hiding unregistered connectors from userspace, as it breaks on DP-MST. - Add workaround for DP++ dual mode adaptors that don't support i2c subaddressing. Signed-off-by: Dave Airlie From: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/c7d02936-c550-199b-6cb7-cbf6cf104e4a@linux.intel.com

drm/amdgpu: Fix memory leak in amdgpu_cs_pass1

2022-11-15T18:03:59+00:00

When p->gang_size equals 0, amdgpu_cs_pass1() will return directly without freeing chunk_array, which will cause a memory leak issue, this patch fixes it. Fixes: 4624459c84d7 ("drm/amdgpu: add gang submit frontend v6") Reviewed-by: Luben Tuikov Signed-off-by: Dong Chenchen Signed-off-by: Alex Deucher

drm/amdgpu: use the last IB as gang leader v2

2022-11-15T14:27:18+00:00

It turned out that not the last IB specified is the gang leader, but instead the last job allocated. This is a bit unfortunate and not very intuitive for the CS interface, so try to fix this. Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20221115094206.6181-1-christian.koenig@amd.com Tested-by: Timur Kristóf Acked-by: Timur Kristóf Reviewed-by: Alex Deucher Fixes: 4624459c84d7 ("drm/amdgpu: add gang submit frontend v6")

drm/amdgpu: Unlock bo_list_mutex after error handling

2022-11-09T23:05:16+00:00

Get below kernel WARNING backtrace when pressing ctrl-C to kill kfdtest application. If amdgpu_cs_parser_bos returns error after taking bo_list_mutex, as caller amdgpu_cs_ioctl will not unlock bo_list_mutex, this generates the kernel WARNING. Add unlock bo_list_mutex after amdgpu_cs_parser_bos error handling to cleanup bo_list userptr bo. WARNING: kfdtest/2930 still has locks held! 1 lock held by kfdtest/2930: (&list->bo_list_mutex){+.+.}-{3:3}, at: amdgpu_cs_ioctl+0xce5/0x1f10 [amdgpu] stack backtrace: dump_stack_lvl+0x44/0x57 get_signal+0x79f/0xd00 arch_do_signal_or_restart+0x36/0x7b0 exit_to_user_mode_prepare+0xfd/0x1b0 syscall_exit_to_user_mode+0x19/0x40 do_syscall_64+0x40/0x80 Signed-off-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: properly initialize return value during CS

2022-09-20T16:41:08+00:00

The return value is no longer initialized before the loop because of moving code around. Signed-off-by: Christian König Fixes: c2b08e7a6d27 ("drm/amdgpu: move entity selection and job init earlier during CS") Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher

drm/amdgpu: add gang submit frontend v6

2022-09-20T16:40:46+00:00

Allows submitting jobs as gang which needs to run on multiple engines at the same time. All members of the gang get the same implicit, explicit and VM dependencies. So no gang member will start running until everything else is ready. The last job is considered the gang leader (usually a submission to the GFX ring) and used for signaling output dependencies. Each job is remembered individually as user of a buffer object, so there is no joining of work at the end. v2: rebase and fix review comments from Andrey and Yogesh v3: use READ instead of BOOKKEEP for now because of VM unmaps, set gang leader only when necessary v4: fix order of pushing jobs and adding fences found by Trigger. v5: fix job index calculation and adding IBs to jobs v6: fix typo found by Alex Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: move entity selection and job init earlier during CS

2022-09-19T19:18:23+00:00

Initialize the entity for the CS and scheduler job much earlier. v2: fix job initialisation order and use correct scheduler instance Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: cleanup error handling in amdgpu_cs_parser_bos

2022-09-19T19:18:16+00:00

Return early on success and so remove all those "if (r)" in the error path. Signed-off-by: Christian König Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher