kernel/linux.git/drivers/gpu/drm/xe/xe_exec.c, branch v6.11.8

drm/xe: Drop VM dma-resv lock on xe_sync_in_fence_get failure in exec IOCTL

2024-11-14T12:21:05+00:00

commit 64a2b6ed4bfd890a0e91955dd8ef8422a3944ed9 upstream. Upon failure all locks need to be dropped before returning to the user. Fixes: 58480c1c912f ("drm/xe: Skip VMAs pin when requesting signal to the last XE_EXEC") Cc: Signed-off-by: Matthew Brost Reviewed-by: Tejas Upadhyay Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20241105043524.4062774-3-matthew.brost@intel.com (cherry picked from commit 7d1a4258e602ffdce529f56686925034c1b3b095) Signed-off-by: Lucas De Marchi Signed-off-by: Greg Kroah-Hartman

drm/xe: Fix possible exec queue leak in exec IOCTL

2024-11-14T12:21:05+00:00

commit af797b831d8975cb4610f396dcb7f03f4b9908e7 upstream. In a couple of places after an exec queue is looked up the exec IOCTL returns on input errors without dropping the exec queue ref. Fix this ensuring the exec queue ref is dropped on input error. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Signed-off-by: Matthew Brost Reviewed-by: Tejas Upadhyay Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20241105043524.4062774-2-matthew.brost@intel.com (cherry picked from commit 07064a200b40ac2195cb6b7b779897d9377e5e6f) Signed-off-by: Lucas De Marchi Signed-off-by: Greg Kroah-Hartman

drm/xe: Use bookkeep slots for external BO's in exec IOCTL

2024-11-01T01:02:31+00:00

[ Upstream commit e7518276e9388d36f103e8c1c7e99898a30d11f5 ] Fix external BO's dma-resv usage in exec IOCTL using bookkeep slots rather than write slots. This leaves syncing to user space rather than the KMD blindly enforcing write semantics on every external BO. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: José Roberto de Souza Cc: Kenneth Graunke Cc: Paulo Zanoni Reported-by: Simona Vetter Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2673 Signed-off-by: Matthew Brost Reviewed-by: José Roberto de Souza Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20240911152622.903058-1-matthew.brost@intel.com (cherry picked from commit b8b1163248759ba18509f7443a2d19b15b4c1df8) Signed-off-by: Lucas De Marchi Signed-off-by: Sasha Levin

drm/xe/exec: Fix minor bug related to xe_sync_entry_cleanup

2024-07-18T14:25:17+00:00

Increment num_syncs after xe_sync_entry_parse() is successful to ensure the xe_sync_entry_cleanup() logic under "err_syncs" label works correctly. v2: Use the same pattern as that in xe_vm.c (Matt Brost) Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Ashutosh Dixit Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240711211203.3728180-1-ashutosh.dixit@intel.com (cherry picked from commit 43a6faa6d9b5e9139758200a79fe9c8f4aaa0c8d) Signed-off-by: Rodrigo Vivi

drm/xe/sched_job: Promote xe_sched_job_add_deps()

2024-06-14T20:51:43+00:00

Move it out of the xe_migrate compilation unit so it can be re-used in other places. Cc: Matthew Brost Signed-off-by: Francois Dugast Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20240614094433.775866-1-francois.dugast@intel.com Signed-off-by: Rodrigo Vivi

drm/xe: Drop EXEC_QUEUE_FLAG_BANNED

2024-06-07T16:16:36+00:00

Clean up laying violation of setting q->flags EXEC_QUEUE_FLAG_BANNED bit in GuC backend. Move banned to GuC owned bit and report banned status to upper layers via reset_status vfunc. This is a slight change in behavior as reset_status returns true if wedged or killed bits set too, but in all of these cases submission to queue is no longer allowed. Signed-off-by: Matthew Brost Reviewed-by: Jonathan Cavitt Link: https://patchwork.freedesktop.org/patch/msgid/20240604184700.1946918-1-matthew.brost@intel.com Signed-off-by: Rodrigo Vivi

drm/xe: Move vma rebinding to the drm_exec locking loop

2024-03-28T07:39:30+00:00

Rebinding might allocate page-table bos, causing evictions. To support blocking locking during these evictions, perform the rebinding in the drm_exec locking loop. Also Reserve fence slots where actually needed rather than trying to predict how many fence slots will be needed over a complete wound-wait transaction. v2: - Remove a leftover call to xe_vm_rebind() (Matt Brost) - Add a helper function xe_vm_validate_rebind() (Matt Brost) v3: - Add comments and squash with previous patch (Matt Brost) Fixes: 24f947d58fe5 ("drm/xe: Use DRM GPUVM helpers for external- and evicted objects") Fixes: 29f424eb8702 ("drm/xe/exec: move fence reservation") Cc: Matthew Auld Signed-off-by: Thomas Hellström Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240327091136.3271-5-thomas.hellstrom@linux.intel.com

drm/xe: Rework rebinding

2024-03-28T07:39:28+00:00

Instead of handling the vm's rebind fence separately, which is error prone if they are not strictly ordered, attach rebind fences as kernel fences to the vm's resv. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Rodrigo Vivi Cc: Matthew Brost Cc: # v6.8+ Signed-off-by: Thomas Hellström Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240327091136.3271-3-thomas.hellstrom@linux.intel.com

drm/xe: Create a helper function to init job's user fence

2024-03-26T22:40:19+00:00

Refactor xe_sync_entry_signal so it doesn't have to modify xe_sched_job struct instead create a new helper function to set user fence values for a job. v2: Move the sync type check to xe_sched_job_init_user_fence(Lucas) Cc: Lucas De Marchi Cc: Matthew Auld Cc: Matthew Brost Cc: Michal Wajdeczko Signed-off-by: Nirmoy Das Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20240321161142.4954-1-nirmoy.das@intel.com Signed-off-by: Lucas De Marchi

drm/xe: Skip VMAs pin when requesting signal to the last XE_EXEC

2024-03-13T22:46:26+00:00

Doing a XE_EXEC with num_batch_buffer == 0 makes signals passed as argument to be signaled when the last real XE_EXEC is completed. But to do that it was first pinning all VMAs in drm_gpuvm_exec_lock(), this patch remove this pinning as it is not required. This change also help Mesa implementing memory over-commiting recovery as it needs to unbind not needed VMAs when the whole VM can't fit in GPU memory but it can only do the unbiding when the last XE_EXEC is completed. So with this change Mesa can get the signal it want without getting out-of-memory errors. Fixes: eb9702ad2986 ("drm/xe: Allow num_batch_buffer / num_binds == 0 in IOCTLs") Cc: Thomas Hellstrom Co-developed-by: Matthew Brost Signed-off-by: José Roberto de Souza Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240313171318.121066-1-jose.souza@intel.com