drm/ttm: fix busy memory to fail other user v4
Subsystems (5)
PATCH 1/1 drm/ttm: fix busy memory to fail other user v4
heavy gpu job could occupy memory long time, which lead other user fail to get memory.
basically pick up Christian idea:
1. Reserve the BO in DC using a ww_mutex ticket (trivial).
2. If we then run into this EBUSY condition in TTM check if the BO we need memory for (or rather the ww_mutex of its reservation object) has a ticket assigned.
3. If we have a ticket we grab a reference to the first BO on the LRU, drop the LRU lock and try to grab the reservation lock with the ticket.
4. If getting the reservation lock with the ticket succeeded we check if the BO is still the first one on the LRU in question (the BO could have moved).
5. If the BO is still the first one on the LRU in question we try to evict it as we would evict any other BO.
6. If any of the "If's" above fail we just back off and return -EBUSY.
v2: fix some minor check
v3: address Christian v2 comments.
v4: fix some missing
--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 +- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 21 +++++- drivers/gpu/drm/ttm/ttm_bo.c | 70 +++++++++++++++++-- 3 files changed, 88 insertions(+), 9 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +5 -1
@@ -811,7 +811,11 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, u64 min_offset, u64 max_offset) {struct amdgpu_device *adev =amdgpu_ttm_adev (bo->tbo.bdev); -struct ttm_operation_ctx ctx = { false, false }; +struct ttm_operation_ctx ctx = { + .interruptible = false, + .no_wait_gpu = false, + .resv = bo->tbo.resv, + };int r, i;if (amdgpu_ttm_tt_get_usermm (bo->tbo.ttm))
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +18 -3
@@ -4101,6 +4101,9 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,struct amdgpu_device *adev;struct amdgpu_bo *rbo;struct dm_plane_state *dm_plane_state_new, *dm_plane_state_old; +struct list_head list, duplicates; +struct ttm_validate_buffer tv; +struct ww_acquire_ctx ticket;uint64_t tiling_flags;uint32_t domain;int r;
@@ -4120,6 +4123,18 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane, r =amdgpu_bo_reserve (rbo, false);if (unlikely (r !=0 ))return r; +INIT_LIST_HEAD (&list); +INIT_LIST_HEAD (&duplicates); + + tv.bo = &rbo->tbo; + tv.num_shared =1 ; +list_add (&tv.head, &list); + + r =ttm_eu_reserve_buffers (&ticket, &list, false, &duplicates); +if (r) { +dev_err (adev->dev,"fail to reserve bo (%d)\n" , r); +return r; + }if (plane->type !=DRM_PLANE_TYPE_CURSOR ) domain =amdgpu_display_supported_domains (adev);
@@ -4130,21 +4145,21 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,if (unlikely (r !=0 )) {if (r != -ERESTARTSYS )DRM_ERROR ("Failed to pin framebuffer with error %d\n" , r); -amdgpu_bo_unreserve (rbo); +ttm_eu_backoff_reservation (&ticket, &list);return r; } r =amdgpu_ttm_alloc_gart (&rbo->tbo);if (unlikely (r !=0 )) {amdgpu_bo_unpin (rbo); -amdgpu_bo_unreserve (rbo); +ttm_eu_backoff_reservation (&ticket, &list);DRM_ERROR ("%p bind failed\n" , rbo);return r; }amdgpu_bo_get_tiling_flags (rbo, &tiling_flags); -amdgpu_bo_unreserve (rbo); +ttm_eu_backoff_reservation (&ticket, &list); afb->address =amdgpu_bo_gpu_offset (rbo);
drivers/gpu/drm/ttm/ttm_bo.c +65 -5
117 lines not on this page · raw message
Signature · 6 lines
2.17.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel