Drivers should never touch this directly.

v2: drop kerneldoc for now internal handling

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-resv.c | 11 +++++++++++ include/linux/dma-resv.h | 26 +------------------------- 2 files changed, 12 insertions(+), 25 deletions(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 2230b8c4a595..bc652ce4e9a9 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -56,6 +56,12 @@ DEFINE_WD_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class);

+struct dma_resv_list { + struct rcu_head rcu; + u32 shared_count, shared_max; + struct dma_fence __rcu *shared[]; +}; + /** * dma_resv_list_alloc - allocate fence list * @shared_max: number of fences we need space for @@ -133,6 +139,11 @@ void dma_resv_fini(struct dma_resv *obj) } EXPORT_SYMBOL(dma_resv_fini);

+static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fence, dma_resv_held(obj)); +} + /** * dma_resv_reserve_shared - Reserve space to add shared fences to * a dma_resv. diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 3f53177bdb46..202cc65d0621 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -47,18 +47,7 @@

extern struct ww_class reservation_ww_class;

-/** - * struct dma_resv_list - a list of shared fences - * @rcu: for internal use - * @shared_count: table of shared fences - * @shared_max: for growing shared fence table - * @shared: shared fence table - */ -struct dma_resv_list { - struct rcu_head rcu; - u32 shared_count, shared_max; - struct dma_fence __rcu *shared[]; -}; +struct dma_resv_list;

/** * struct dma_resv - a reservation object manages fences for a buffer @@ -451,19 +440,6 @@ dma_resv_excl_fence(struct dma_resv *obj) return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); }

-/** - * dma_resv_shared_list - get the reservation object's shared fence list - * @obj: the reservation object - * - * Returns the shared fence list. Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - */ -static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence, dma_resv_held(obj)); -} - void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences);

Use dma_resv_wait() instead of extracting the exclusive fence and waiting on it manually.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch Cc: Jason Gunthorpe jgg@ziepe.ca Cc: Leon Romanovsky leon@kernel.org Cc: Maor Gottlieb maorg@nvidia.com Cc: Gal Pressman galpress@amazon.com Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org --- drivers/infiniband/core/umem_dmabuf.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c index f0760741f281..d32cd7538835 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -16,7 +16,6 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) { struct sg_table *sgt; struct scatterlist *sg; - struct dma_fence *fence; unsigned long start, end, cur = 0; unsigned int nmap = 0; int i; @@ -68,11 +67,8 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) * may be not up-to-date. Wait for the exporter to finish * the migration. */ - fence = dma_resv_excl_fence(umem_dmabuf->attach->dmabuf->resv); - if (fence) - return dma_fence_wait(fence, false); - - return 0; + return dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv, false, + false, MAX_SCHEDULE_TIMEOUT); } EXPORT_SYMBOL(ib_umem_dmabuf_map_pages);

Instead use the new dma_resv_get_singleton function.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch Cc: Ben Skeggs bskeggs@redhat.com Cc: Karol Herbst kherbst@redhat.com Cc: Lyude Paul lyude@redhat.com Cc: nouveau@lists.freedesktop.org --- drivers/gpu/drm/nouveau/nouveau_bo.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index fa73fe57f97b..74f8652d2bd3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -959,7 +959,14 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct drm_device *dev = drm->dev; - struct dma_fence *fence = dma_resv_excl_fence(bo->base.resv); + struct dma_fence *fence; + int ret; + + /* TODO: This is actually a memory management dependency */ + ret = dma_resv_get_singleton(bo->base.resv, false, &fence); + if (ret) + dma_resv_wait_timeout(bo->base.resv, false, false, + MAX_SCHEDULE_TIMEOUT);

nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile;

Instead use the new dma_resv_get_singleton function.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch Cc: amd-gfx@lists.freedesktop.org --- drivers/gpu/drm/radeon/radeon_display.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index b9a07677a71e..f60e826cd292 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -533,7 +533,12 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc, DRM_ERROR("failed to pin new rbo buffer before flip\n"); goto cleanup; } - work->fence = dma_fence_get(dma_resv_excl_fence(new_rbo->tbo.base.resv)); + r = dma_resv_get_singleton(new_rbo->tbo.base.resv, false, &work->fence); + if (r) { + radeon_bo_unreserve(new_rbo); + DRM_ERROR("failed to get new rbo buffer fences\n"); + goto cleanup; + } radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL); radeon_bo_unreserve(new_rbo);

Drivers should never touch this directly.

v2: fix rebase clash

Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 6 ++++++ include/linux/dma-resv.h | 17 ----------------- 2 files changed, 6 insertions(+), 17 deletions(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 005fbe61103e..16ad98fd3130 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -140,6 +140,12 @@ void dma_resv_fini(struct dma_resv *obj) } EXPORT_SYMBOL(dma_resv_fini);

+static inline struct dma_fence * +dma_resv_excl_fence(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); +} + static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) { return rcu_dereference_check(obj->fence, dma_resv_held(obj)); diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 08512c1e215d..20e13f36710a 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -423,23 +423,6 @@ static inline void dma_resv_unlock(struct dma_resv *obj) ww_mutex_unlock(&obj->lock); }

-/** - * dma_resv_excl_fence - return the object's exclusive fence - * @obj: the reservation object - * - * Returns the exclusive fence (if any). Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - * - * RETURNS - * The exclusive fence or NULL - */ -static inline struct dma_fence * -dma_resv_excl_fence(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); -} - void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences);

Audit all the users of dma_resv_add_excl_fence() and make sure they reserve a shared slot also when only trying to add an exclusive fence.

This is the next step towards handling the exclusive fence like a shared one.

v2: fix missed case in amdgpu v3: and two more radeon, rename function

Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 10 +-- drivers/dma-buf/st-dma-resv.c | 64 +++++++++---------- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 8 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 8 +-- drivers/gpu/drm/i915/gem/i915_gem_clflush.c | 3 +- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 10 ++- drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c | 6 +- .../drm/i915/gem/selftests/i915_gem_migrate.c | 5 +- drivers/gpu/drm/i915/i915_vma.c | 8 ++- .../drm/i915/selftests/intel_memory_region.c | 7 ++ drivers/gpu/drm/lima/lima_gem.c | 10 ++- drivers/gpu/drm/msm/msm_gem_submit.c | 18 +++--- drivers/gpu/drm/nouveau/nouveau_fence.c | 8 +-- drivers/gpu/drm/panfrost/panfrost_job.c | 4 ++ drivers/gpu/drm/qxl/qxl_release.c | 2 +- drivers/gpu/drm/radeon/radeon_cs.c | 4 ++ drivers/gpu/drm/radeon/radeon_object.c | 8 +++ drivers/gpu/drm/radeon/radeon_vm.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 4 +- drivers/gpu/drm/ttm/ttm_bo_util.c | 12 +++- drivers/gpu/drm/ttm/ttm_execbuf_util.c | 15 ++--- drivers/gpu/drm/v3d/v3d_gem.c | 15 +++-- drivers/gpu/drm/vc4/vc4_gem.c | 2 +- drivers/gpu/drm/vgem/vgem_fence.c | 12 ++-- drivers/gpu/drm/virtio/virtgpu_gem.c | 9 +++ drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 16 +++-- include/linux/dma-resv.h | 4 +- 30 files changed, 171 insertions(+), 113 deletions(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index e04afc30bc0a..ccef5e53f8e7 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -152,7 +152,7 @@ static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) }

/** - * dma_resv_reserve_shared - Reserve space to add shared fences to + * dma_resv_reserve_fences - Reserve space to add shared fences to * a dma_resv. * @obj: reservation object * @num_fences: number of fences we want to add @@ -167,7 +167,7 @@ static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) * RETURNS * Zero for success, or -errno */ -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences) { struct dma_resv_list *old, *new; unsigned int i, j, k, max; @@ -230,7 +230,7 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences)

return 0; } -EXPORT_SYMBOL(dma_resv_reserve_shared); +EXPORT_SYMBOL(dma_resv_reserve_fences);

#ifdef CONFIG_DEBUG_MUTEXES /** @@ -238,7 +238,7 @@ EXPORT_SYMBOL(dma_resv_reserve_shared); * @obj: the dma_resv object to reset * * Reset the number of pre-reserved shared slots to test that drivers do - * correct slot allocation using dma_resv_reserve_shared(). See also + * correct slot allocation using dma_resv_reserve_fences(). See also * &dma_resv_list.shared_max. */ void dma_resv_reset_shared_max(struct dma_resv *obj) @@ -260,7 +260,7 @@ EXPORT_SYMBOL(dma_resv_reset_shared_max); * @fence: the shared fence to add * * Add a fence to a shared slot, @obj must be locked with dma_resv_lock(), and - * dma_resv_reserve_shared() has been called. + * dma_resv_reserve_fences() has been called. * * See also &dma_resv.fence for a discussion of the semantics. */ diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c index cbe999c6e7a6..d2e61f6ae989 100644 --- a/drivers/dma-buf/st-dma-resv.c +++ b/drivers/dma-buf/st-dma-resv.c @@ -75,17 +75,16 @@ static int test_signaling(void *arg, bool shared) goto err_free; }

- if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - goto err_unlock; - } + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; + }

+ if (shared) dma_resv_add_shared_fence(&resv, f); - } else { + else dma_resv_add_excl_fence(&resv, f); - }

if (dma_resv_test_signaled(&resv, shared)) { pr_err("Resv unexpectedly signaled\n"); @@ -134,17 +133,16 @@ static int test_for_each(void *arg, bool shared) goto err_free; }

- if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - goto err_unlock; - } + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; + }

+ if (shared) dma_resv_add_shared_fence(&resv, f); - } else { + else dma_resv_add_excl_fence(&resv, f); - }

r = -ENOENT; dma_resv_for_each_fence(&cursor, &resv, shared, fence) { @@ -206,18 +204,17 @@ static int test_for_each_unlocked(void *arg, bool shared) goto err_free; }

- if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - dma_resv_unlock(&resv); - goto err_free; - } + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_free; + }

+ if (shared) dma_resv_add_shared_fence(&resv, f); - } else { + else dma_resv_add_excl_fence(&resv, f); - } dma_resv_unlock(&resv);

r = -ENOENT; @@ -290,18 +287,17 @@ static int test_get_fences(void *arg, bool shared) goto err_resv; }

- if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - dma_resv_unlock(&resv); - goto err_resv; - } + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_resv; + }

+ if (shared) dma_resv_add_shared_fence(&resv, f); - } else { + else dma_resv_add_excl_fence(&resv, f); - } dma_resv_unlock(&resv);

r = dma_resv_get_fences(&resv, shared, &i, &fences); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index b6f266f612ea..7de8f67f7dde 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1220,7 +1220,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, AMDGPU_FENCE_OWNER_KFD, false); if (ret) goto wait_pd_fail; - ret = dma_resv_reserve_shared(vm->root.bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(vm->root.bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; amdgpu_bo_fence(vm->root.bo, @@ -2530,7 +2530,7 @@ int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem * Add process eviction fence to bo so they can * evict each other. */ - ret = dma_resv_reserve_shared(gws_bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(gws_bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; amdgpu_bo_fence(gws_bo, &process_info->eviction_fence->base, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 5661b82d84d4..ea63a0d13621 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1384,6 +1384,14 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, bool shared) { struct dma_resv *resv = bo->tbo.base.resv; + int r; + + r = dma_resv_reserve_fences(resv, 1); + if (r) { + /* As last resort on OOM we block for the fence */ + dma_fence_wait(fence, false); + return; + }

if (shared) dma_resv_add_shared_fence(resv, fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b37fc7d7d2c7..0ab85280e8ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2968,7 +2968,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) if (r) goto error_free_root;

- r = dma_resv_reserve_shared(root_bo->tbo.base.resv, 1); + r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1); if (r) goto error_unreserve;

@@ -3411,7 +3411,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, value = 0; }

- r = dma_resv_reserve_shared(root->tbo.base.resv, 1); + r = dma_resv_reserve_fences(root->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve fence slot\n", r); goto error_unlock; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f2805ba74c80..7b878221f1d3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -543,7 +543,7 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, goto reserve_bo_failed; }

- r = dma_resv_reserve_shared(bo->tbo.base.resv, 1); + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve bo\n", r); amdgpu_bo_unreserve(bo); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 385ea141c23e..b808ddb9da48 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -179,11 +179,9 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) struct etnaviv_gem_submit_bo *bo = &submit->bos[i]; struct dma_resv *robj = bo->obj->base.resv;

- if (!(bo->flags & ETNA_SUBMIT_BO_WRITE)) { - ret = dma_resv_reserve_shared(robj, 1); - if (ret) - return ret; - } + ret = dma_resv_reserve_fences(robj, 1); + if (ret) + return ret;

if (submit->flags & ETNA_SUBMIT_NO_IMPLICIT) continue; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index 8a248003dfae..8a2223eb0ba9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -106,7 +106,8 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, trace_i915_gem_object_clflush(obj);

clflush = NULL; - if (!(flags & I915_CLFLUSH_SYNC)) + if (!(flags & I915_CLFLUSH_SYNC) && + dma_resv_reserve_fences(obj->base.resv, 1) == 0) clflush = clflush_work_create(obj); if (clflush) { i915_sw_fence_await_reservation(&clflush->base.chain, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 3a5b247be738..e8eb6ee83f24 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -994,11 +994,9 @@ static int eb_validate_vmas(struct i915_execbuffer *eb) } }

- if (!(ev->flags & EXEC_OBJECT_WRITE)) { - err = dma_resv_reserve_shared(vma->obj->base.resv, 1); - if (err) - return err; - } + err = dma_resv_reserve_fences(vma->obj->base.resv, 1); + if (err) + return err;

GEM_BUG_ON(drm_mm_node_allocated(&vma->node) && eb_vma_misplaced(&eb->exec[i], vma, ev->flags)); @@ -2297,7 +2295,7 @@ static int eb_parse(struct i915_execbuffer *eb) goto err_trampoline; }

- err = dma_resv_reserve_shared(shadow->obj->base.resv, 1); + err = dma_resv_reserve_fences(shadow->obj->base.resv, 1); if (err) goto err_trampoline;

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index ee9612a3ee5e..4de6500f3c55 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -596,7 +596,11 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, assert_object_held(src); i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);

- ret = dma_resv_reserve_shared(src_bo->base.resv, 1); + ret = dma_resv_reserve_fences(src_bo->base.resv, 1); + if (ret) + return ret; + + ret = dma_resv_reserve_fences(dst_bo->base.resv, 1); if (ret) return ret;

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c index ecb691c81d1e..f9b369ed4b50 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c @@ -180,7 +180,10 @@ static int igt_lmem_pages_migrate(void *arg) i915_gem_object_is_lmem(obj), 0xdeadbeaf, &rq); if (rq) { - dma_resv_add_excl_fence(obj->base.resv, &rq->fence); + err = dma_resv_reserve_fences(obj->base.resv, 1); + if (!err) + dma_resv_add_excl_fence(obj->base.resv, + &rq->fence); i915_request_put(rq); } if (err) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index c0d6d5526abe..fe9f89289418 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1633,6 +1633,12 @@ int _i915_vma_move_to_active(struct i915_vma *vma, intel_frontbuffer_put(front); }

+ if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { + err = dma_resv_reserve_fences(vma->obj->base.resv, 1); + if (unlikely(err)) + return err; + } + if (fence) { dma_resv_add_excl_fence(vma->obj->base.resv, fence); obj->write_domain = I915_GEM_DOMAIN_RENDER; @@ -1640,7 +1646,7 @@ int _i915_vma_move_to_active(struct i915_vma *vma, } } else { if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { - err = dma_resv_reserve_shared(vma->obj->base.resv, 1); + err = dma_resv_reserve_fences(vma->obj->base.resv, 1); if (unlikely(err)) return err; } diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 7acba1d2135e..7f40502b2c1e 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -895,6 +895,13 @@ static int igt_lmem_write_cpu(void *arg) }

i915_gem_object_lock(obj, NULL); + + err = dma_resv_reserve_fences(obj->base.resv, 1); + if (err) { + i915_gem_object_unlock(obj); + goto out_put; + } + /* Put the pages into a known state -- from the gpu for added fun */ intel_engine_pm_get(engine); err = intel_context_migrate_clear(engine->gt->migrate.context, NULL, diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index f9a9198ef198..656812f0bf38 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -255,13 +255,11 @@ int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset) static int lima_gem_sync_bo(struct lima_sched_task *task, struct lima_bo *bo, bool write, bool explicit) { - int err = 0; + int err;

- if (!write) { - err = dma_resv_reserve_shared(lima_bo_resv(bo), 1); - if (err) - return err; - } + err = dma_resv_reserve_fences(lima_bo_resv(bo), 1); + if (err) + return err;

/* explicit sync use user passed dep fence */ if (explicit) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 6cfa984dee6a..993dbcd7a586 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -320,16 +320,14 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) struct drm_gem_object *obj = &submit->bos[i].obj->base; bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE;

- if (!write) { - /* NOTE: _reserve_shared() must happen before - * _add_shared_fence(), which makes this a slightly - * strange place to call it. OTOH this is a - * convenient can-fail point to hook it in. - */ - ret = dma_resv_reserve_shared(obj->resv, 1); - if (ret) - return ret; - } + /* NOTE: _reserve_shared() must happen before + * _add_shared_fence(), which makes this a slightly + * strange place to call it. OTOH this is a + * convenient can-fail point to hook it in. + */ + ret = dma_resv_reserve_fences(obj->resv, 1); + if (ret) + return ret;

/* exclusive fences must be ordered */ if (no_implicit && !write) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index a3a04e0d76ec..0268259e97eb 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -346,11 +346,9 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, struct dma_resv *resv = nvbo->bo.base.resv; int i, ret;

- if (!exclusive) { - ret = dma_resv_reserve_shared(resv, 1); - if (ret) - return ret; - } + ret = dma_resv_reserve_fences(resv, 1); + if (ret) + return ret;

/* Waiting for the exclusive fence first causes performance regressions * under some circumstances. So manually wait for the shared ones first. diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 908d79520853..cca50cbb7f0b 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -247,6 +247,10 @@ static int panfrost_acquire_object_fences(struct drm_gem_object **bos, int i, ret;

for (i = 0; i < bo_count; i++) { + ret = dma_resv_reserve_fences(bos[i]->resv, 1); + if (ret) + return ret; + /* panfrost always uses write mode in its current uapi */ ret = drm_sched_job_add_implicit_dependencies(job, bos[i], true); diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index 469979cd0341..cde1e8ddaeaa 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -200,7 +200,7 @@ static int qxl_release_validate_bo(struct qxl_bo *bo) return ret; }

- ret = dma_resv_reserve_shared(bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (ret) return ret;

diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 9ed2b2700e0a..446f7bae54c4 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -535,6 +535,10 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, return r;

radeon_sync_fence(&p->ib.sync, bo_va->last_pt_update); + + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); + if (r) + return r; }

return radeon_vm_clear_invalids(rdev, vm); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 56ede9d63b12..870b13635dbf 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -808,6 +808,14 @@ void radeon_bo_fence(struct radeon_bo *bo, struct radeon_fence *fence, bool shared) { struct dma_resv *resv = bo->tbo.base.resv; + int r; + + r = dma_resv_reserve_fences(resv, 1); + if (r) { + /* As last resort on OOM we block for the fence */ + dma_fence_wait(&fence->base, false); + return; + }

if (shared) dma_resv_add_shared_fence(resv, &fence->base); diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index bb53016f3138..987cabbf1318 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -831,7 +831,7 @@ static int radeon_vm_update_ptes(struct radeon_device *rdev, int r;

radeon_sync_resv(rdev, &ib->sync, pt->tbo.base.resv, true); - r = dma_resv_reserve_shared(pt->tbo.base.resv, 1); + r = dma_resv_reserve_fences(pt->tbo.base.resv, 1); if (r) return r;

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index db3dc7ef5382..1dd6f13bb03c 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -762,7 +762,7 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,

dma_resv_add_shared_fence(bo->base.resv, fence);

- ret = dma_resv_reserve_shared(bo->base.resv, 1); + ret = dma_resv_reserve_fences(bo->base.resv, 1); if (unlikely(ret)) { dma_fence_put(fence); return ret; @@ -821,7 +821,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, bool type_found = false; int i, ret;

- ret = dma_resv_reserve_shared(bo->base.resv, 1); + ret = dma_resv_reserve_fences(bo->base.resv, 1); if (unlikely(ret)) return ret;

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 544a84fa6589..862d2f22412a 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -221,9 +221,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,

fbo->base = *bo;

- ttm_bo_get(bo); - fbo->bo = bo; - /** * Fix up members that we shouldn't copy directly: * TODO: Explicit member copy would probably be better here. @@ -251,6 +248,15 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, ret = dma_resv_trylock(&fbo->base.base._resv); WARN_ON(!ret);

+ ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1); + if (ret) { + kfree(fbo); + return ret; + } + + ttm_bo_get(bo); + fbo->bo = bo; + ttm_bo_move_to_lru_tail_unlocked(&fbo->base);

*new_obj = &fbo->base; diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c index 071c48d672c6..789c645f004e 100644 --- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c +++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c @@ -90,6 +90,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,

list_for_each_entry(entry, list, head) { struct ttm_buffer_object *bo = entry->bo; + unsigned int num_fences;

ret = ttm_bo_reserve(bo, intr, (ticket == NULL), ticket); if (ret == -EALREADY && dups) { @@ -100,12 +101,10 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, continue; }

+ num_fences = min(entry->num_shared, 1u); if (!ret) { - if (!entry->num_shared) - continue; - - ret = dma_resv_reserve_shared(bo->base.resv, - entry->num_shared); + ret = dma_resv_reserve_fences(bo->base.resv, + num_fences); if (!ret) continue; } @@ -120,9 +119,9 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, ret = ttm_bo_reserve_slowpath(bo, intr, ticket); }

- if (!ret && entry->num_shared) - ret = dma_resv_reserve_shared(bo->base.resv, - entry->num_shared); + if (!ret) + ret = dma_resv_reserve_fences(bo->base.resv, + num_fences);

if (unlikely(ret != 0)) { if (ticket) { diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 92bc0faee84f..961812d33827 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -259,16 +259,21 @@ v3d_lock_bo_reservations(struct v3d_job *job, return ret;

for (i = 0; i < job->bo_count; i++) { + ret = dma_resv_reserve_fences(job->bo[i]->resv, 1); + if (ret) + goto fail; + ret = drm_sched_job_add_implicit_dependencies(&job->base, job->bo[i], true); - if (ret) { - drm_gem_unlock_reservations(job->bo, job->bo_count, - acquire_ctx); - return ret; - } + if (ret) + goto fail; }

return 0; + +fail: + drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); + return ret; }

/** diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 445d3bab89e0..4aacc5de2199 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -641,7 +641,7 @@ vc4_lock_bo_reservations(struct drm_device *dev, for (i = 0; i < exec->bo_count; i++) { bo = &exec->bo[i]->base;

- ret = dma_resv_reserve_shared(bo->resv, 1); + ret = dma_resv_reserve_fences(bo->resv, 1); if (ret) { vc4_unlock_bo_reservations(dev, exec, acquire_ctx); return ret; diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index bd6f75285fd9..2ddbebca87d9 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -157,12 +157,14 @@ int vgem_fence_attach_ioctl(struct drm_device *dev, }

/* Expose the fence via the dma-buf */ - ret = 0; dma_resv_lock(resv, NULL); - if (arg->flags & VGEM_FENCE_WRITE) - dma_resv_add_excl_fence(resv, fence); - else if ((ret = dma_resv_reserve_shared(resv, 1)) == 0) - dma_resv_add_shared_fence(resv, fence); + ret = dma_resv_reserve_fences(resv, 1); + if (!ret) { + if (arg->flags & VGEM_FENCE_WRITE) + dma_resv_add_excl_fence(resv, fence); + else + dma_resv_add_shared_fence(resv, fence); + } dma_resv_unlock(resv);

/* Record the fence in our idr for later signaling */ diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 48d3c9955f0d..1820ca6cf673 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -214,6 +214,7 @@ void virtio_gpu_array_add_obj(struct virtio_gpu_object_array *objs,

int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs) { + unsigned int i; int ret;

if (objs->nents == 1) { @@ -222,6 +223,14 @@ int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs) ret = drm_gem_lock_reservations(objs->objs, objs->nents, &objs->ticket); } + if (ret) + return ret; + + for (i = 0; i < objs->nents; ++i) { + ret = dma_resv_reserve_fences(objs->objs[i]->resv, 1); + if (ret) + return ret; + } return ret; }

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 31aecc46624b..fe13aa8b4a64 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -747,16 +747,22 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo, struct vmw_fence_obj *fence) { struct ttm_device *bdev = bo->bdev; - struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev); + int ret;

- if (fence == NULL) { + if (fence == NULL) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL); + else + dma_fence_get(&fence->base); + + ret = dma_resv_reserve_fences(bo->base.resv, 1); + if (!ret) dma_resv_add_excl_fence(bo->base.resv, &fence->base); - dma_fence_put(&fence->base); - } else - dma_resv_add_excl_fence(bo->base.resv, &fence->base); + else + /* Last resort fallback when we are OOM */ + dma_fence_wait(&fence->base, false); + dma_fence_put(&fence->base); }

diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index ecb697d4d861..5fa04d0fccad 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -117,7 +117,7 @@ struct dma_resv { * A new fence is added by calling dma_resv_add_shared_fence(). Since * this often needs to be done past the point of no return in command * submission it cannot fail, and therefore sufficient slots need to be - * reserved by calling dma_resv_reserve_shared(). + * reserved by calling dma_resv_reserve_fences(). * * Note that actual semantics of what an exclusive or shared fence mean * is defined by the user, for reservation objects shared across drivers @@ -413,7 +413,7 @@ static inline void dma_resv_unlock(struct dma_resv *obj)

void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, struct dma_fence *fence);

Use dma_resv_get_singleton() here to eventually get more than one write fence as single fence.

Signed-off-by: Christian König christian.koenig@amd.com Reviewed-by: Daniel Vetter daniel.vetter@ffwll.ch Cc: Thomas Zimmermann tzimmermann@suse.de Cc: Laurent Pinchart laurent.pinchart@ideasonboard.com Cc: Maxime Ripard maxime@cerno.tech Cc: Lyude Paul lyude@redhat.com Cc: nouveau@lists.freedesktop.org --- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 133c8736426a..b55a8a723581 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -536,8 +536,6 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) struct nouveau_bo *nvbo; struct nv50_head_atom *asyh; struct nv50_wndw_ctxdma *ctxdma; - struct dma_resv_iter cursor; - struct dma_fence *fence; int ret;

NV_ATOMIC(drm, "%s prepare: %p\n", plane->name, fb); @@ -560,13 +558,11 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.handle[0] = ctxdma->object.handle; }

- dma_resv_iter_begin(&cursor, nvbo->bo.base.resv, false); - dma_resv_for_each_fence_unlocked(&cursor, fence) { - /* TODO: We only use the first writer here */ - asyw->state.fence = dma_fence_get(fence); - break; - } - dma_resv_iter_end(&cursor); + ret = dma_resv_get_singleton(nvbo->bo.base.resv, false, + &asyw->state.fence); + if (ret) + return ret; + asyw->image.offset[0] = nvbo->offset;

if (wndw->func->prepare) {

We can now add multiple writers to the dma_resv object.

Also enable the check for not adding containers in dma_resv.c again.

Signed-off-by: Christian König christian.koenig@amd.com Cc: amd-gfx@lists.freedesktop.org --- drivers/dma-buf/dma-resv.c | 6 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 51 ++------------------- 3 files changed, 8 insertions(+), 50 deletions(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 821ef47c3a24..9484690a440a 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -308,10 +308,10 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,

dma_resv_assert_held(obj);

- /* TODO: Drivers should not add containers here, instead add each fence - * individually. Disabled for now until we cleaned up amdgpu/ttm. + /* Drivers should not add containers here, instead add each fence + * individually. */ - /* WARN_ON(dma_fence_is_container(fence)); */ + WARN_ON(dma_fence_is_container(fence));

fobj = dma_resv_fences_list(obj); count = fobj->num_fences; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index 044b41f0bfd9..529d52a204cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -34,7 +34,6 @@ struct amdgpu_fpriv; struct amdgpu_bo_list_entry { struct ttm_validate_buffer tv; struct amdgpu_bo_va *bo_va; - struct dma_fence_chain *chain; uint32_t priority; struct page **user_pages; bool user_invalidated; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index c21ae6694df7..5227c2f4fead 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -575,14 +575,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);

e->bo_va = amdgpu_vm_bo_find(vm, bo); - - if (bo->tbo.base.dma_buf && !amdgpu_bo_explicit_sync(bo)) { - e->chain = dma_fence_chain_alloc(); - if (!e->chain) { - r = -ENOMEM; - goto error_validate; - } - } }

amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold, @@ -633,13 +625,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, }

error_validate: - if (r) { - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - dma_fence_chain_free(e->chain); - e->chain = NULL; - } + if (r) ttm_eu_backoff_reservation(&p->ticket, &p->validated); - } out: return r; } @@ -679,17 +666,9 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, { unsigned i;

- if (error && backoff) { - struct amdgpu_bo_list_entry *e; - - amdgpu_bo_list_for_each_entry(e, parser->bo_list) { - dma_fence_chain_free(e->chain); - e->chain = NULL; - } - + if (error && backoff) ttm_eu_backoff_reservation(&parser->ticket, &parser->validated); - }

for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); @@ -1264,29 +1243,9 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,

amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm);

- amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct dma_resv *resv = e->tv.bo->base.resv; - struct dma_fence_chain *chain = e->chain; - struct dma_resv_iter cursor; - struct dma_fence *fence; - - if (!chain) - continue; - - /* - * Work around dma_resv shortcommings by wrapping up the - * submission in a dma_fence_chain and add it as exclusive - * fence. - */ - dma_resv_for_each_fence(&cursor, resv, - DMA_RESV_USAGE_WRITE, - fence) { - break; - } - dma_fence_chain_init(chain, fence, dma_fence_get(p->fence), 1); - dma_resv_add_fence(resv, &chain->base, DMA_RESV_USAGE_WRITE); - e->chain = NULL; - } + /* Make sure all BOs are remembered as writers */ + amdgpu_bo_list_for_each_entry(e, p->bo_list) + e->tv.num_shared = 0;

ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); mutex_unlock(&p->adev->notifier_lock);

Add an usage for submissions independent of implicit sync but still interesting for memory management.

v2: cleanup the kerneldoc a bit

Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 2 +- drivers/dma-buf/st-dma-resv.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 4 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 +++--- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 2 +- drivers/gpu/drm/qxl/qxl_debugfs.c | 2 +- drivers/gpu/drm/radeon/radeon_gem.c | 2 +- drivers/gpu/drm/radeon/radeon_mn.c | 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 14 +++++++------- include/linux/dma-resv.h | 13 ++++++++++++- 15 files changed, 35 insertions(+), 24 deletions(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 9484690a440a..fb2b69d9714c 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -542,7 +542,7 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)

list = NULL;

- dma_resv_iter_begin(&cursor, src, DMA_RESV_USAGE_READ); + dma_resv_iter_begin(&cursor, src, DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, f) {

if (dma_resv_iter_is_restarted(&cursor)) { diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c index 062b57d63fa6..8ace9e84c845 100644 --- a/drivers/dma-buf/st-dma-resv.c +++ b/drivers/dma-buf/st-dma-resv.c @@ -296,7 +296,7 @@ int dma_resv(void) int r;

spin_lock_init(&fence_lock); - for (usage = DMA_RESV_USAGE_KERNEL; usage <= DMA_RESV_USAGE_READ; + for (usage = DMA_RESV_USAGE_KERNEL; usage <= DMA_RESV_USAGE_BOOKKEEP; ++usage) { r = subtests(tests, (void *)(unsigned long)usage); if (r) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index ab5d6b630a49..b461c3aab877 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -263,7 +263,7 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, */ replacement = dma_fence_get_stub(); dma_resv_replace_fences(bo->tbo.base.resv, ef->base.context, - replacement, DMA_RESV_USAGE_READ); + replacement, DMA_RESV_USAGE_BOOKKEEP); dma_fence_put(replacement); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 490d2a7a3e2b..ddf46802b1ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -111,7 +111,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, struct dma_fence *fence; int r;

- r = dma_resv_get_singleton(resv, DMA_RESV_USAGE_READ, &fence); + r = dma_resv_get_singleton(resv, DMA_RESV_USAGE_BOOKKEEP, &fence); if (r) goto fallback;

@@ -139,7 +139,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, /* Not enough memory for the delayed delete, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout(resv, DMA_RESV_USAGE_READ, + dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); amdgpu_pasid_free(pasid); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 86f5248676b0..b86c0b8252a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -75,7 +75,7 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni,

mmu_interval_set_seq(mni, cur_seq);

- r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_READ, + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); mutex_unlock(&adev->notifier_lock); if (r <= 0) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 744e144e5fc2..11c46b3e4c60 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -260,7 +260,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, return -EINVAL;

/* TODO: Use DMA_RESV_USAGE_READ here */ - dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_READ, f) { + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, f) { dma_fence_chain_for_each(f, f) { struct dma_fence *tmp = dma_fence_chain_contained(f);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index f64680d30150..d451b5c6e37b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1357,7 +1357,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, * be resident to run successfully */ dma_resv_for_each_fence(&resv_cursor, bo->base.resv, - DMA_RESV_USAGE_READ, f) { + DMA_RESV_USAGE_BOOKKEEP, f) { if (amdkfd_fence_check_mm(f, current->mm)) return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index f3235aad7282..b4f0679f8797 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2105,7 +2105,7 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_READ, fence) { + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) { /* Add a callback for each fence in the reservation object */ amdgpu_vm_prt_get(adev); amdgpu_vm_add_prt_cb(adev, fence); @@ -2707,7 +2707,7 @@ bool amdgpu_vm_evictable(struct amdgpu_bo *bo) return true;

/* Don't evict VM page tables while they are busy */ - if (!dma_resv_test_signaled(bo->tbo.base.resv, DMA_RESV_USAGE_READ)) + if (!dma_resv_test_signaled(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP)) return false;

/* Try to block ongoing updates */ @@ -2888,7 +2888,7 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) { timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, - DMA_RESV_USAGE_READ, + DMA_RESV_USAGE_BOOKKEEP, true, timeout); if (timeout <= 0) return timeout; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index a200d3e66573..4115a222a853 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -66,7 +66,7 @@ bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) struct intel_memory_region *mr = READ_ONCE(obj->mm.region);

#ifdef CONFIG_LOCKDEP - GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, DMA_RESV_USAGE_READ) && + GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP) && i915_gem_object_evictable(obj)); #endif return mr && (mr->type == INTEL_MEMORY_LOCAL || diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 60feff9160de..1ddd81623691 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -85,7 +85,7 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni, return true;

/* we will unbind on next submission, still have userptr pins */ - r = dma_resv_wait_timeout(obj->base.resv, DMA_RESV_USAGE_READ, false, + r = dma_resv_wait_timeout(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) drm_err(&i915->drm, "(%ld) failed to wait for idle\n", r); diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c index 33e5889d6608..2d9ed3b94574 100644 --- a/drivers/gpu/drm/qxl/qxl_debugfs.c +++ b/drivers/gpu/drm/qxl/qxl_debugfs.c @@ -62,7 +62,7 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data) int rel = 0;

dma_resv_iter_begin(&cursor, bo->tbo.base.resv, - DMA_RESV_USAGE_READ); + DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) rel = 0; diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 71bf9299e45c..9587ab88bedd 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -162,7 +162,7 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj, if (domain == RADEON_GEM_DOMAIN_CPU) { /* Asking for cpu access wait for object idle */ r = dma_resv_wait_timeout(robj->tbo.base.resv, - DMA_RESV_USAGE_READ, + DMA_RESV_USAGE_BOOKKEEP, true, 30 * HZ); if (!r) r = -EBUSY; diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index 68ebeb1bdfff..29fe8423bd90 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -66,7 +66,7 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn, return true; }

- r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_READ, + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 0f0aa96fb051..8fea9f88d118 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -272,7 +272,7 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_READ); + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (!fence->ops->signaled) dma_fence_enable_sw_signaling(fence); @@ -301,7 +301,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, struct dma_resv *resv = &bo->base._resv; int ret;

- if (dma_resv_test_signaled(resv, DMA_RESV_USAGE_READ)) + if (dma_resv_test_signaled(resv, DMA_RESV_USAGE_BOOKKEEP)) ret = 0; else ret = -EBUSY; @@ -313,7 +313,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, dma_resv_unlock(bo->base.resv); spin_unlock(&bo->bdev->lru_lock);

- lret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_READ, + lret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, interruptible, 30 * HZ);

@@ -418,7 +418,7 @@ static void ttm_bo_release(struct kref *kref) * fences block for the BO to become idle */ dma_resv_wait_timeout(bo->base.resv, - DMA_RESV_USAGE_READ, false, + DMA_RESV_USAGE_BOOKKEEP, false, 30 * HZ); }

@@ -429,7 +429,7 @@ static void ttm_bo_release(struct kref *kref) ttm_mem_io_free(bdev, bo->resource); }

- if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_READ) || + if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP) || !dma_resv_trylock(bo->base.resv)) { /* The BO is not idle, resurrect it for delayed destroy */ ttm_bo_flush_all_fences(bo); @@ -1074,13 +1074,13 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, long timeout = 15 * HZ;

if (no_wait) { - if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_READ)) + if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP)) return 0; else return -EBUSY; }

- timeout = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_READ, + timeout = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, interruptible, timeout); if (timeout < 0) return timeout; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 543e25d5116a..56ae1df8d159 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -55,7 +55,7 @@ struct dma_resv_list; * This enum describes the different use cases for a dma_resv object and * controls which fences are returned when queried. * - * An important fact is that there is the order KERNEL<WRITE<READ and + * An important fact is that there is the order KERNEL<WRITE<READ<BOOKKEEP and * when the dma_resv object is asked for fences for one use case the fences * for the lower use case are returned as well. * @@ -93,6 +93,17 @@ enum dma_resv_usage { * an implicit read dependency. */ DMA_RESV_USAGE_READ, + + /** + * @DMA_RESV_USAGE_BOOKKEEP: No implicit sync. + * + * This should be used by submissions which don't want to participate in + * implicit synchronization. + * + * The most common case are preemption fences as well as page table + * updates. + */ + DMA_RESV_USAGE_BOOKKEEP };

/**

That should now be handled by the common dma_resv framework.

Signed-off-by: Christian König christian.koenig@amd.com Cc: intel-gfx@lists.freedesktop.org --- drivers/gpu/drm/i915/gem/i915_gem_object.c | 29 ++++++-------------- drivers/gpu/drm/i915/gem/i915_gem_object.h | 5 ++-- drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c | 15 +--------- drivers/gpu/drm/i915/i915_vma.c | 9 +++++- 4 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index d87b508b59b1..fd240435ffef 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -742,18 +742,19 @@ static const struct drm_gem_object_funcs i915_gem_object_funcs = { /** * i915_gem_object_get_moving_fence - Get the object's moving fence if any * @obj: The object whose moving fence to get. + * @fence: The resulting fence * * A non-signaled moving fence means that there is an async operation * pending on the object that needs to be waited on before setting up * any GPU- or CPU PTEs to the object's pages. * - * Return: A refcounted pointer to the object's moving fence if any, - * NULL otherwise. + * Return: Negative error code or 0 for success. */ -struct dma_fence * -i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj) +int i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj, + struct dma_fence **fence) { - return dma_fence_get(i915_gem_to_ttm(obj)->moving); + return dma_resv_get_singleton(obj->base.resv, DMA_RESV_USAGE_KERNEL, + fence); }

/** @@ -771,23 +772,9 @@ i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj) int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, bool intr) { - struct dma_fence *fence = i915_gem_to_ttm(obj)->moving; - int ret; - assert_object_held(obj); - if (!fence) - return 0; - - ret = dma_fence_wait(fence, intr); - if (ret) - return ret; - - if (fence->error) - return fence->error; - - i915_gem_to_ttm(obj)->moving = NULL; - dma_fence_put(fence); - return 0; + return dma_resv_wait_timeout(obj->base. resv, DMA_RESV_USAGE_KERNEL, + intr, MAX_SCHEDULE_TIMEOUT); }

#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index f66d46882ea7..be57af8bfb31 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -521,9 +521,8 @@ i915_gem_object_finish_access(struct drm_i915_gem_object *obj) i915_gem_object_unpin_pages(obj); }

-struct dma_fence * -i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj); - +int i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj, + struct dma_fence **fence); int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, bool intr);

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index e4a232e22f9d..4d5d0cd64f23 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -452,19 +452,6 @@ __i915_ttm_move(struct ttm_buffer_object *bo, return fence; }

-static int -prev_deps(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct i915_deps *deps) -{ - int ret; - - ret = i915_deps_add_dependency(deps, bo->moving, ctx); - if (!ret) - ret = i915_deps_add_resv(deps, bo->base.resv, ctx); - - return ret; -} - /** * i915_ttm_move - The TTM move callback used by i915. * @bo: The buffer object. @@ -519,7 +506,7 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, struct i915_deps deps;

i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - ret = prev_deps(bo, ctx, &deps); + ret = i915_deps_add_resv(&deps, bo->base.resv, ctx); if (ret) { i915_refct_sgt_put(dst_rsgt); return ret; diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 52fd6705a518..8737159f4706 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1247,10 +1247,17 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (err) return err;

+ if (vma->obj) { + err = i915_gem_object_get_moving_fence(vma->obj, &moving); + if (err) + return err; + } else { + moving = NULL; + } + if (flags & PIN_GLOBAL) wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);

- moving = vma->obj ? i915_gem_object_get_moving_fence(vma->obj) : NULL; if (flags & vma->vm->bind_async_flags || moving) { /* lock VM */ err = i915_vm_lock_objects(vma->vm, ww);

This change adds the dma_resv_usage enum and allows us to specify why a dma_resv object is queried for its containing fences.

Additional to that a dma_resv_usage_rw() helper function is added to aid retrieving the fences for a read or write userspace submission.

This is then deployed to the different query functions of the dma_resv object and all of their users. When the write paratermer was previously true we now use DMA_RESV_USAGE_WRITE and DMA_RESV_USAGE_READ otherwise.

v2: add KERNEL/OTHER in separate patch v3: some kerneldoc suggestions by Daniel

Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-buf.c | 3 +- drivers/dma-buf/dma-resv.c | 33 +++++---- drivers/dma-buf/st-dma-resv.c | 48 ++++++------- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 5 +- drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +- drivers/gpu/drm/drm_gem.c | 6 +- drivers/gpu/drm/drm_gem_atomic_helper.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_gem.c | 6 +- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 7 +- .../gpu/drm/i915/display/intel_atomic_plane.c | 3 +- drivers/gpu/drm/i915/gem/i915_gem_busy.c | 4 +- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_wait.c | 6 +- .../drm/i915/gem/selftests/i915_gem_dmabuf.c | 3 +- drivers/gpu/drm/i915/i915_request.c | 3 +- drivers/gpu/drm/i915/i915_sw_fence.c | 2 +- drivers/gpu/drm/msm/msm_gem.c | 3 +- drivers/gpu/drm/nouveau/dispnv50/wndw.c | 3 +- drivers/gpu/drm/nouveau/nouveau_bo.c | 8 +-- drivers/gpu/drm/nouveau/nouveau_fence.c | 8 ++- drivers/gpu/drm/nouveau/nouveau_gem.c | 3 +- drivers/gpu/drm/panfrost/panfrost_drv.c | 3 +- drivers/gpu/drm/qxl/qxl_debugfs.c | 3 +- drivers/gpu/drm/radeon/radeon_display.c | 3 +- drivers/gpu/drm/radeon/radeon_gem.c | 9 ++- drivers/gpu/drm/radeon/radeon_mn.c | 4 +- drivers/gpu/drm/radeon/radeon_sync.c | 2 +- drivers/gpu/drm/radeon/radeon_uvd.c | 4 +- drivers/gpu/drm/scheduler/sched_main.c | 3 +- drivers/gpu/drm/ttm/ttm_bo.c | 18 ++--- drivers/gpu/drm/vgem/vgem_fence.c | 4 +- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 5 +- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 4 +- drivers/infiniband/core/umem_dmabuf.c | 3 +- include/linux/dma-resv.h | 69 +++++++++++++++---- 46 files changed, 208 insertions(+), 127 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 602b12d7470d..528983d3ba64 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1124,7 +1124,8 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, long ret;

/* Wait on any implicit rendering fences */ - ret = dma_resv_wait_timeout(resv, write, true, MAX_SCHEDULE_TIMEOUT); + ret = dma_resv_wait_timeout(resv, dma_resv_usage_rw(write), + true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret;

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index ccef5e53f8e7..0180348f32f8 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -382,7 +382,7 @@ static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) cursor->seq = read_seqcount_begin(&cursor->obj->seq); cursor->index = -1; cursor->shared_count = 0; - if (cursor->all_fences) { + if (cursor->usage >= DMA_RESV_USAGE_READ) { cursor->fences = dma_resv_shared_list(cursor->obj); if (cursor->fences) cursor->shared_count = cursor->fences->shared_count; @@ -494,7 +494,7 @@ struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor) dma_resv_assert_held(cursor->obj);

cursor->index = 0; - if (cursor->all_fences) + if (cursor->usage >= DMA_RESV_USAGE_READ) cursor->fences = dma_resv_shared_list(cursor->obj); else cursor->fences = NULL; @@ -549,7 +549,7 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) list = NULL; excl = NULL;

- dma_resv_iter_begin(&cursor, src, true); + dma_resv_iter_begin(&cursor, src, DMA_RESV_USAGE_READ); dma_resv_for_each_fence_unlocked(&cursor, f) {

if (dma_resv_iter_is_restarted(&cursor)) { @@ -595,7 +595,7 @@ EXPORT_SYMBOL(dma_resv_copy_fences); * dma_resv_get_fences - Get an object's shared and exclusive * fences without update side lock held * @obj: the reservation object - * @write: true if we should return all fences + * @usage: controls which fences to include, see enum dma_resv_usage. * @num_fences: the number of fences returned * @fences: the array of fence ptrs returned (array is krealloc'd to the * required size, and must be freed by caller) @@ -603,7 +603,7 @@ EXPORT_SYMBOL(dma_resv_copy_fences); * Retrieve all fences from the reservation object. * Returns either zero or -ENOMEM. */ -int dma_resv_get_fences(struct dma_resv *obj, bool write, +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, unsigned int *num_fences, struct dma_fence ***fences) { struct dma_resv_iter cursor; @@ -612,7 +612,7 @@ int dma_resv_get_fences(struct dma_resv *obj, bool write, *num_fences = 0; *fences = NULL;

- dma_resv_iter_begin(&cursor, obj, write); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) {

if (dma_resv_iter_is_restarted(&cursor)) { @@ -644,7 +644,7 @@ EXPORT_SYMBOL_GPL(dma_resv_get_fences); /** * dma_resv_get_singleton - Get a single fence for all the fences * @obj: the reservation object - * @write: true if we should return all fences + * @usage: controls which fences to include, see enum dma_resv_usage. * @fence: the resulting fence * * Get a single fence representing all the fences inside the resv object. @@ -654,7 +654,7 @@ EXPORT_SYMBOL_GPL(dma_resv_get_fences); * object since that can lead to stack corruption when finalizing the * dma_fence_array. */ -int dma_resv_get_singleton(struct dma_resv *obj, bool write, +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, struct dma_fence **fence) { struct dma_fence_array *array; @@ -662,7 +662,7 @@ int dma_resv_get_singleton(struct dma_resv *obj, bool write, unsigned count; int r;

- r = dma_resv_get_fences(obj, write, &count, &fences); + r = dma_resv_get_fences(obj, usage, &count, &fences); if (r) return r;

@@ -696,7 +696,7 @@ EXPORT_SYMBOL_GPL(dma_resv_get_singleton); * dma_resv_wait_timeout - Wait on reservation's objects * shared and/or exclusive fences. * @obj: the reservation object - * @wait_all: if true, wait on all fences, else wait on just exclusive fence + * @usage: controls which fences to include, see enum dma_resv_usage. * @intr: if true, do interruptible wait * @timeout: timeout value in jiffies or zero to return immediately * @@ -706,14 +706,14 @@ EXPORT_SYMBOL_GPL(dma_resv_get_singleton); * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or * greater than zer on success. */ -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout) +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout) { long ret = timeout ? timeout : 1; struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_iter_begin(&cursor, obj, wait_all); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) {

ret = dma_fence_wait_timeout(fence, intr, ret); @@ -733,8 +733,7 @@ EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); * dma_resv_test_signaled - Test if a reservation object's fences have been * signaled. * @obj: the reservation object - * @test_all: if true, test all fences, otherwise only test the exclusive - * fence + * @usage: controls which fences to include, see enum dma_resv_usage. * * Callers are not required to hold specific locks, but maybe hold * dma_resv_lock() already. @@ -743,12 +742,12 @@ EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); * * True if all fences signaled, else false. */ -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage) { struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_iter_begin(&cursor, obj, test_all); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { dma_resv_iter_end(&cursor); return false; diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c index d2e61f6ae989..d097981061b1 100644 --- a/drivers/dma-buf/st-dma-resv.c +++ b/drivers/dma-buf/st-dma-resv.c @@ -58,7 +58,7 @@ static int sanitycheck(void *arg) return r; }

-static int test_signaling(void *arg, bool shared) +static int test_signaling(void *arg, enum dma_resv_usage usage) { struct dma_resv resv; struct dma_fence *f; @@ -81,18 +81,18 @@ static int test_signaling(void *arg, bool shared) goto err_unlock; }

- if (shared) + if (usage >= DMA_RESV_USAGE_READ) dma_resv_add_shared_fence(&resv, f); else dma_resv_add_excl_fence(&resv, f);

- if (dma_resv_test_signaled(&resv, shared)) { + if (dma_resv_test_signaled(&resv, usage)) { pr_err("Resv unexpectedly signaled\n"); r = -EINVAL; goto err_unlock; } dma_fence_signal(f); - if (!dma_resv_test_signaled(&resv, shared)) { + if (!dma_resv_test_signaled(&resv, usage)) { pr_err("Resv not reporting signaled\n"); r = -EINVAL; goto err_unlock; @@ -107,15 +107,15 @@ static int test_signaling(void *arg, bool shared)

static int test_excl_signaling(void *arg) { - return test_signaling(arg, false); + return test_signaling(arg, DMA_RESV_USAGE_WRITE); }

static int test_shared_signaling(void *arg) { - return test_signaling(arg, true); + return test_signaling(arg, DMA_RESV_USAGE_READ); }

-static int test_for_each(void *arg, bool shared) +static int test_for_each(void *arg, enum dma_resv_usage usage) { struct dma_resv_iter cursor; struct dma_fence *f, *fence; @@ -139,13 +139,13 @@ static int test_for_each(void *arg, bool shared) goto err_unlock; }

- if (shared) + if (usage >= DMA_RESV_USAGE_READ) dma_resv_add_shared_fence(&resv, f); else dma_resv_add_excl_fence(&resv, f);

r = -ENOENT; - dma_resv_for_each_fence(&cursor, &resv, shared, fence) { + dma_resv_for_each_fence(&cursor, &resv, usage, fence) { if (!r) { pr_err("More than one fence found\n"); r = -EINVAL; @@ -156,7 +156,8 @@ static int test_for_each(void *arg, bool shared) r = -EINVAL; goto err_unlock; } - if (dma_resv_iter_is_exclusive(&cursor) != !shared) { + if (dma_resv_iter_is_exclusive(&cursor) != + (usage >= DMA_RESV_USAGE_READ)) { pr_err("Unexpected fence usage\n"); r = -EINVAL; goto err_unlock; @@ -178,15 +179,15 @@ static int test_for_each(void *arg, bool shared)

static int test_excl_for_each(void *arg) { - return test_for_each(arg, false); + return test_for_each(arg, DMA_RESV_USAGE_WRITE); }

static int test_shared_for_each(void *arg) { - return test_for_each(arg, true); + return test_for_each(arg, DMA_RESV_USAGE_READ); }

-static int test_for_each_unlocked(void *arg, bool shared) +static int test_for_each_unlocked(void *arg, enum dma_resv_usage usage) { struct dma_resv_iter cursor; struct dma_fence *f, *fence; @@ -211,14 +212,14 @@ static int test_for_each_unlocked(void *arg, bool shared) goto err_free; }

- if (shared) + if (usage >= DMA_RESV_USAGE_READ) dma_resv_add_shared_fence(&resv, f); else dma_resv_add_excl_fence(&resv, f); dma_resv_unlock(&resv);

r = -ENOENT; - dma_resv_iter_begin(&cursor, &resv, shared); + dma_resv_iter_begin(&cursor, &resv, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (!r) { pr_err("More than one fence found\n"); @@ -234,7 +235,8 @@ static int test_for_each_unlocked(void *arg, bool shared) r = -EINVAL; goto err_iter_end; } - if (dma_resv_iter_is_exclusive(&cursor) != !shared) { + if (dma_resv_iter_is_exclusive(&cursor) != + (usage >= DMA_RESV_USAGE_READ)) { pr_err("Unexpected fence usage\n"); r = -EINVAL; goto err_iter_end; @@ -262,15 +264,15 @@ static int test_for_each_unlocked(void *arg, bool shared)

static int test_excl_for_each_unlocked(void *arg) { - return test_for_each_unlocked(arg, false); + return test_for_each_unlocked(arg, DMA_RESV_USAGE_WRITE); }

static int test_shared_for_each_unlocked(void *arg) { - return test_for_each_unlocked(arg, true); + return test_for_each_unlocked(arg, DMA_RESV_USAGE_READ); }

-static int test_get_fences(void *arg, bool shared) +static int test_get_fences(void *arg, enum dma_resv_usage usage) { struct dma_fence *f, **fences = NULL; struct dma_resv resv; @@ -294,13 +296,13 @@ static int test_get_fences(void *arg, bool shared) goto err_resv; }

- if (shared) + if (usage >= DMA_RESV_USAGE_READ) dma_resv_add_shared_fence(&resv, f); else dma_resv_add_excl_fence(&resv, f); dma_resv_unlock(&resv);

- r = dma_resv_get_fences(&resv, shared, &i, &fences); + r = dma_resv_get_fences(&resv, usage, &i, &fences); if (r) { pr_err("get_fences failed\n"); goto err_free; @@ -324,12 +326,12 @@ static int test_get_fences(void *arg, bool shared)

static int test_excl_get_fences(void *arg) { - return test_get_fences(arg, false); + return test_get_fences(arg, DMA_RESV_USAGE_WRITE); }

static int test_shared_get_fences(void *arg) { - return test_get_fences(arg, true); + return test_get_fences(arg, DMA_RESV_USAGE_READ); }

int dma_resv(void) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index ae83df4d0c10..95c4370a0549 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1278,7 +1278,9 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, * submission in a dma_fence_chain and add it as exclusive * fence. */ - dma_resv_for_each_fence(&cursor, resv, false, fence) { + dma_resv_for_each_fence(&cursor, resv, + DMA_RESV_USAGE_WRITE, + fence) { break; } dma_fence_chain_init(chain, fence, dma_fence_get(p->fence), 1); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index e76b96d55551..cefa404d7842 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -200,8 +200,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, goto unpin; }

- /* TODO: Unify this with other drivers */ - r = dma_resv_get_fences(new_abo->tbo.base.resv, true, + r = dma_resv_get_fences(new_abo->tbo.base.resv, DMA_RESV_USAGE_WRITE, &work->shared_count, &work->shared); if (unlikely(r != 0)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 9b12cab5e606..3a5fe05c7a7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -526,7 +526,8 @@ int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data, return -ENOENT; } robj = gem_to_amdgpu_bo(gobj); - ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, timeout); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, DMA_RESV_USAGE_READ, + true, timeout);

/* ret == 0 means not signaled, * ret > 0 means signaled diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 888d97143177..490d2a7a3e2b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -111,7 +111,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, struct dma_fence *fence; int r;

- r = dma_resv_get_singleton(resv, true, &fence); + r = dma_resv_get_singleton(resv, DMA_RESV_USAGE_READ, &fence); if (r) goto fallback;

@@ -139,7 +139,8 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, /* Not enough memory for the delayed delete, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout(resv, true, false, MAX_SCHEDULE_TIMEOUT); + dma_resv_wait_timeout(resv, DMA_RESV_USAGE_READ, + false, MAX_SCHEDULE_TIMEOUT); amdgpu_pasid_free(pasid); }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 4b153daf283d..86f5248676b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -75,8 +75,8 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni,

mmu_interval_set_seq(mni, cur_seq);

- r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_READ, + false, MAX_SCHEDULE_TIMEOUT); mutex_unlock(&adev->notifier_lock); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index ea63a0d13621..168bac660ae2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -765,8 +765,8 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) return 0; }

- r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_WRITE, + false, MAX_SCHEDULE_TIMEOUT); if (r < 0) return r;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 40e06745fae9..744e144e5fc2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -259,7 +259,8 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, if (resv == NULL) return -EINVAL;

- dma_resv_for_each_fence(&cursor, resv, true, f) { + /* TODO: Use DMA_RESV_USAGE_READ here */ + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_READ, f) { dma_fence_chain_for_each(f, f) { struct dma_fence *tmp = dma_fence_chain_contained(f);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index d178fbec7048..f64680d30150 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1356,7 +1356,8 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, * If true, then return false as any KFD process needs all its BOs to * be resident to run successfully */ - dma_resv_for_each_fence(&resv_cursor, bo->base.resv, true, f) { + dma_resv_for_each_fence(&resv_cursor, bo->base.resv, + DMA_RESV_USAGE_READ, f) { if (amdkfd_fence_check_mm(f, current->mm)) return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 6f8de11a17f1..33deb0df62fd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1162,7 +1162,8 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, ib->length_dw = 16;

if (direct) { - r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + r = dma_resv_wait_timeout(bo->tbo.base.resv, + DMA_RESV_USAGE_WRITE, false, msecs_to_jiffies(10)); if (r == 0) r = -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 0ab85280e8ed..f3235aad7282 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2105,7 +2105,7 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_for_each_fence(&cursor, resv, true, fence) { + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_READ, fence) { /* Add a callback for each fence in the reservation object */ amdgpu_vm_prt_get(adev); amdgpu_vm_add_prt_cb(adev, fence); @@ -2707,7 +2707,7 @@ bool amdgpu_vm_evictable(struct amdgpu_bo *bo) return true;

/* Don't evict VM page tables while they are busy */ - if (!dma_resv_test_signaled(bo->tbo.base.resv, true)) + if (!dma_resv_test_signaled(bo->tbo.base.resv, DMA_RESV_USAGE_READ)) return false;

/* Try to block ongoing updates */ @@ -2887,7 +2887,8 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, */ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) { - timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, true, + timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, + DMA_RESV_USAGE_READ, true, timeout); if (timeout <= 0) return timeout; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0eeb394e949c..c9532642559c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9199,7 +9199,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * deadlock during GPU reset when this fence will not signal * but we hold reservation lock for the BO. */ - r = dma_resv_wait_timeout(abo->tbo.base.resv, true, false, + r = dma_resv_wait_timeout(abo->tbo.base.resv, + DMA_RESV_USAGE_WRITE, false, msecs_to_jiffies(5000)); if (unlikely(r <= 0)) DRM_ERROR("Waiting for fences timed out!"); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 3c888db59ea4..54079d762051 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -771,7 +771,8 @@ long drm_gem_dma_resv_wait(struct drm_file *filep, u32 handle, return -EINVAL; }

- ret = dma_resv_wait_timeout(obj->resv, wait_all, true, timeout); + ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(wait_all), + true, timeout); if (ret == 0) ret = -ETIME; else if (ret > 0) @@ -1345,7 +1346,8 @@ int drm_gem_fence_array_add_implicit(struct xarray *fence_array, struct dma_fence *fence; int ret = 0;

- dma_resv_for_each_fence(&cursor, obj->resv, write, fence) { + dma_resv_for_each_fence(&cursor, obj->resv, dma_resv_usage_rw(write), + fence) { ret = drm_gem_fence_array_add(fence_array, fence); if (ret) break; diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index 9338ddb7edff..a6d89aed0bda 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -151,7 +151,7 @@ int drm_gem_plane_helper_prepare_fb(struct drm_plane *plane, struct drm_plane_st return 0;

obj = drm_gem_fb_get_obj(state->fb, 0); - ret = dma_resv_get_singleton(obj->resv, false, &fence); + ret = dma_resv_get_singleton(obj->resv, DMA_RESV_USAGE_WRITE, &fence); if (ret) return ret;

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index d5314aa28ff7..507172e2780b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -380,12 +380,14 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, }

if (op & ETNA_PREP_NOSYNC) { - if (!dma_resv_test_signaled(obj->resv, write)) + if (!dma_resv_test_signaled(obj->resv, + dma_resv_usage_rw(write))) return -EBUSY; } else { unsigned long remain = etnaviv_timeout_to_jiffies(timeout);

- ret = dma_resv_wait_timeout(obj->resv, write, true, remain); + ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write), + true, remain); if (ret <= 0) return ret == 0 ? -ETIMEDOUT : ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index b808ddb9da48..d7cd26dfaf8a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -178,6 +178,7 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) for (i = 0; i < submit->nr_bos; i++) { struct etnaviv_gem_submit_bo *bo = &submit->bos[i]; struct dma_resv *robj = bo->obj->base.resv; + enum dma_resv_usage usage;

ret = dma_resv_reserve_fences(robj, 1); if (ret) @@ -186,9 +187,9 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) if (submit->flags & ETNA_SUBMIT_NO_IMPLICIT) continue;

- ret = dma_resv_get_fences(robj, - bo->flags & ETNA_SUBMIT_BO_WRITE, - &bo->nr_shared, &bo->shared); + usage = dma_resv_usage_rw(bo->flags & ETNA_SUBMIT_BO_WRITE); + ret = dma_resv_get_fences(robj, usage, &bo->nr_shared, + &bo->shared); if (ret) return ret; } diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index c2c512cd8ec0..2c3bb8aecd07 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -799,7 +799,8 @@ intel_prepare_plane_fb(struct drm_plane *_plane, if (ret < 0) goto unpin_fb;

- dma_resv_iter_begin(&cursor, obj->base.resv, false); + dma_resv_iter_begin(&cursor, obj->base.resv, + DMA_RESV_USAGE_WRITE); dma_resv_for_each_fence_unlocked(&cursor, fence) { add_rps_boost_after_vblank(new_plane_state->hw.crtc, fence); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 470fdfd61a0f..14a1c0ad8c3c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -138,12 +138,12 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, * Alternatively, we can trade that extra information on read/write * activity with * args->busy = - * !dma_resv_test_signaled(obj->resv, true); + * !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ); * to report the overall busyness. This is what the wait-ioctl does. * */ args->busy = 0; - dma_resv_iter_begin(&cursor, obj->base.resv, true); + dma_resv_iter_begin(&cursor, obj->base.resv, DMA_RESV_USAGE_READ); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) args->busy = 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 444f8268b9c5..a200d3e66573 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -66,7 +66,7 @@ bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) struct intel_memory_region *mr = READ_ONCE(obj->mm.region);

#ifdef CONFIG_LOCKDEP - GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, true) && + GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, DMA_RESV_USAGE_READ) && i915_gem_object_evictable(obj)); #endif return mr && (mr->type == INTEL_MEMORY_LOCAL || diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 3cc01c30dd62..60feff9160de 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -85,7 +85,7 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni, return true;

/* we will unbind on next submission, still have userptr pins */ - r = dma_resv_wait_timeout(obj->base.resv, true, false, + r = dma_resv_wait_timeout(obj->base.resv, DMA_RESV_USAGE_READ, false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) drm_err(&i915->drm, "(%ld) failed to wait for idle\n", r); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index dab3d30c09a0..319936f91ac5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -40,7 +40,8 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, struct dma_fence *fence; long ret = timeout ?: 1;

- dma_resv_iter_begin(&cursor, resv, flags & I915_WAIT_ALL); + dma_resv_iter_begin(&cursor, resv, + dma_resv_usage_rw(flags & I915_WAIT_ALL)); dma_resv_for_each_fence_unlocked(&cursor, fence) { ret = i915_gem_object_wait_fence(fence, flags, timeout); if (ret <= 0) @@ -117,7 +118,8 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_iter_begin(&cursor, obj->base.resv, flags & I915_WAIT_ALL); + dma_resv_iter_begin(&cursor, obj->base.resv, + dma_resv_usage_rw(flags & I915_WAIT_ALL)); dma_resv_for_each_fence_unlocked(&cursor, fence) i915_gem_fence_wait_priority(fence, attr); dma_resv_iter_end(&cursor); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index 3cc74b0fed06..342df658e0fc 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -219,7 +219,8 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, goto out_detach; }

- timeout = dma_resv_wait_timeout(dmabuf->resv, false, true, 5 * HZ); + timeout = dma_resv_wait_timeout(dmabuf->resv, DMA_RESV_USAGE_WRITE, + true, 5 * HZ); if (!timeout) { pr_err("dmabuf wait for exclusive fence timed out.\n"); timeout = -ETIME; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 76cf5ac91e94..17d7216ce221 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1594,7 +1594,8 @@ i915_request_await_object(struct i915_request *to, struct dma_fence *fence; int ret = 0;

- dma_resv_for_each_fence(&cursor, obj->base.resv, write, fence) { + dma_resv_for_each_fence(&cursor, obj->base.resv, + dma_resv_usage_rw(write), fence) { ret = i915_request_await_dma_fence(to, fence); if (ret) break; diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 2a74a9a1cafe..ae984c66c48a 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -585,7 +585,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, debug_fence_assert(fence); might_sleep_if(gfpflags_allow_blocking(gfp));

- dma_resv_iter_begin(&cursor, resv, write); + dma_resv_iter_begin(&cursor, resv, dma_resv_usage_rw(write)); dma_resv_for_each_fence_unlocked(&cursor, f) { pending = i915_sw_fence_await_dma_fence(fence, f, timeout, gfp); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 02b9ae65a96a..01bbb5f2d462 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -848,7 +848,8 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout); long ret;

- ret = dma_resv_wait_timeout(obj->resv, write, true, remain); + ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write), + true, remain); if (ret == 0) return remain == 0 ? -EBUSY : -ETIMEDOUT; else if (ret < 0) diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index b55a8a723581..53baf9aae4b1 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -558,7 +558,8 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.handle[0] = ctxdma->object.handle; }

- ret = dma_resv_get_singleton(nvbo->bo.base.resv, false, + ret = dma_resv_get_singleton(nvbo->bo.base.resv, + DMA_RESV_USAGE_WRITE, &asyw->state.fence); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 74f8652d2bd3..c6bb4dbcd735 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -962,11 +962,11 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, struct dma_fence *fence; int ret;

- /* TODO: This is actually a memory management dependency */ - ret = dma_resv_get_singleton(bo->base.resv, false, &fence); + ret = dma_resv_get_singleton(bo->base.resv, DMA_RESV_USAGE_WRITE, + &fence); if (ret) - dma_resv_wait_timeout(bo->base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); + dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_WRITE, + false, MAX_SCHEDULE_TIMEOUT);

nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 0268259e97eb..d5e81ccee01c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -350,14 +350,16 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, if (ret) return ret;

- /* Waiting for the exclusive fence first causes performance regressions - * under some circumstances. So manually wait for the shared ones first. + /* Waiting for the writes first causes performance regressions + * under some circumstances. So manually wait for the reads first. */ for (i = 0; i < 2; ++i) { struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_for_each_fence(&cursor, resv, exclusive, fence) { + dma_resv_for_each_fence(&cursor, resv, + dma_resv_usage_rw(exclusive), + fence) { struct nouveau_fence *f;

if (i == 0 && dma_resv_iter_is_exclusive(&cursor)) diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 9416bee92141..fab542a758ff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -962,7 +962,8 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data, return -ENOENT; nvbo = nouveau_gem_object(gem);

- lret = dma_resv_wait_timeout(nvbo->bo.base.resv, write, true, + lret = dma_resv_wait_timeout(nvbo->bo.base.resv, + dma_resv_usage_rw(write), true, no_wait ? 0 : 30 * HZ); if (!lret) ret = -EBUSY; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 96bb5a465627..0deb2d21422f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -316,7 +316,8 @@ panfrost_ioctl_wait_bo(struct drm_device *dev, void *data, if (!gem_obj) return -ENOENT;

- ret = dma_resv_wait_timeout(gem_obj->resv, true, true, timeout); + ret = dma_resv_wait_timeout(gem_obj->resv, DMA_RESV_USAGE_READ, + true, timeout); if (!ret) ret = timeout ? -ETIMEDOUT : -EBUSY;

diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c index 6a36b0fd845c..33e5889d6608 100644 --- a/drivers/gpu/drm/qxl/qxl_debugfs.c +++ b/drivers/gpu/drm/qxl/qxl_debugfs.c @@ -61,7 +61,8 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data) struct dma_fence *fence; int rel = 0;

- dma_resv_iter_begin(&cursor, bo->tbo.base.resv, true); + dma_resv_iter_begin(&cursor, bo->tbo.base.resv, + DMA_RESV_USAGE_READ); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) rel = 0; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index f60e826cd292..57ff2b723c87 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -533,7 +533,8 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc, DRM_ERROR("failed to pin new rbo buffer before flip\n"); goto cleanup; } - r = dma_resv_get_singleton(new_rbo->tbo.base.resv, false, &work->fence); + r = dma_resv_get_singleton(new_rbo->tbo.base.resv, DMA_RESV_USAGE_WRITE, + &work->fence); if (r) { radeon_bo_unreserve(new_rbo); DRM_ERROR("failed to get new rbo buffer fences\n"); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index a36a4f2c76b0..71bf9299e45c 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -161,7 +161,9 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj, } if (domain == RADEON_GEM_DOMAIN_CPU) { /* Asking for cpu access wait for object idle */ - r = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); + r = dma_resv_wait_timeout(robj->tbo.base.resv, + DMA_RESV_USAGE_READ, + true, 30 * HZ); if (!r) r = -EBUSY;

@@ -523,7 +525,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj);

- r = dma_resv_test_signaled(robj->tbo.base.resv, true); + r = dma_resv_test_signaled(robj->tbo.base.resv, DMA_RESV_USAGE_READ); if (r == 0) r = -EBUSY; else @@ -552,7 +554,8 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj);

- ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, DMA_RESV_USAGE_READ, + true, 30 * HZ); if (ret == 0) r = -EBUSY; else if (ret < 0) diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index 9fa88549c89e..68ebeb1bdfff 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -66,8 +66,8 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn, return true; }

- r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_READ, + false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r);

diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index b991ba1bcd51..49bbb2266c0f 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -96,7 +96,7 @@ int radeon_sync_resv(struct radeon_device *rdev, struct dma_fence *f; int r = 0;

- dma_resv_for_each_fence(&cursor, resv, shared, f) { + dma_resv_for_each_fence(&cursor, resv, dma_resv_usage_rw(shared), f) { fence = to_radeon_fence(f); if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 377f9cdb5b53..4000ad2f39ba 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -478,8 +478,8 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; }

- r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_WRITE, + false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) { DRM_ERROR("Failed waiting for UVD message (%d)!\n", r); return r ? r : -ETIME; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index f91fb31ab7a7..3aeb28ad0f3f 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -703,7 +703,8 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, struct dma_fence *fence; int ret;

- dma_resv_for_each_fence(&cursor, obj->resv, write, fence) { + dma_resv_for_each_fence(&cursor, obj->resv, dma_resv_usage_rw(write), + fence) { /* Make sure to grab an additional ref on the added fence */ dma_fence_get(fence); ret = drm_sched_job_add_dependency(job, fence); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 1dd6f13bb03c..d4b2695606e2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -272,7 +272,7 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) struct dma_resv_iter cursor; struct dma_fence *fence;

- dma_resv_iter_begin(&cursor, resv, true); + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_READ); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (!fence->ops->signaled) dma_fence_enable_sw_signaling(fence); @@ -301,7 +301,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, struct dma_resv *resv = &bo->base._resv; int ret;

- if (dma_resv_test_signaled(resv, true)) + if (dma_resv_test_signaled(resv, DMA_RESV_USAGE_READ)) ret = 0; else ret = -EBUSY; @@ -313,7 +313,8 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, dma_resv_unlock(bo->base.resv); spin_unlock(&bo->bdev->lru_lock);

- lret = dma_resv_wait_timeout(resv, true, interruptible, + lret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_READ, + interruptible, 30 * HZ);

if (lret < 0) @@ -416,7 +417,8 @@ static void ttm_bo_release(struct kref *kref) /* Last resort, if we fail to allocate memory for the * fences block for the BO to become idle */ - dma_resv_wait_timeout(bo->base.resv, true, false, + dma_resv_wait_timeout(bo->base.resv, + DMA_RESV_USAGE_READ, false, 30 * HZ); }

@@ -427,7 +429,7 @@ static void ttm_bo_release(struct kref *kref) ttm_mem_io_free(bdev, bo->resource); }

- if (!dma_resv_test_signaled(bo->base.resv, true) || + if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_READ) || !dma_resv_trylock(bo->base.resv)) { /* The BO is not idle, resurrect it for delayed destroy */ ttm_bo_flush_all_fences(bo); @@ -1072,14 +1074,14 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, long timeout = 15 * HZ;

if (no_wait) { - if (dma_resv_test_signaled(bo->base.resv, true)) + if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_READ)) return 0; else return -EBUSY; }

- timeout = dma_resv_wait_timeout(bo->base.resv, true, interruptible, - timeout); + timeout = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_READ, + interruptible, timeout); if (timeout < 0) return timeout;

diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index 2ddbebca87d9..91fc4940c65a 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -130,6 +130,7 @@ int vgem_fence_attach_ioctl(struct drm_device *dev, struct vgem_file *vfile = file->driver_priv; struct dma_resv *resv; struct drm_gem_object *obj; + enum dma_resv_usage usage; struct dma_fence *fence; int ret;

@@ -151,7 +152,8 @@ int vgem_fence_attach_ioctl(struct drm_device *dev,

/* Check for a conflicting fence */ resv = obj->resv; - if (!dma_resv_test_signaled(resv, arg->flags & VGEM_FENCE_WRITE)) { + usage = dma_resv_usage_rw(arg->flags & VGEM_FENCE_WRITE); + if (!dma_resv_test_signaled(resv, usage)) { ret = -EBUSY; goto err_fence; } diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index c708bab555c6..5577cc7408b2 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -518,9 +518,10 @@ static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data, return -ENOENT;

if (args->flags & VIRTGPU_WAIT_NOWAIT) { - ret = dma_resv_test_signaled(obj->resv, true); + ret = dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ); } else { - ret = dma_resv_wait_timeout(obj->resv, true, true, timeout); + ret = dma_resv_wait_timeout(obj->resv, DMA_RESV_USAGE_READ, + true, timeout); } if (ret == 0) ret = -EBUSY; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index fe13aa8b4a64..b96884f7d03d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -528,8 +528,8 @@ static int vmw_user_bo_synccpu_grab(struct vmw_buffer_object *vmw_bo, if (flags & drm_vmw_synccpu_allow_cs) { long lret;

- lret = dma_resv_wait_timeout(bo->base.resv, true, true, - nonblock ? 0 : + lret = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_READ, + true, nonblock ? 0 : MAX_SCHEDULE_TIMEOUT); if (!lret) return -EBUSY; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 36c3b5db7e69..39081dbf9ac8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -1166,8 +1166,8 @@ int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start, if (bo->moving) dma_fence_put(bo->moving);

- /* TODO: This is actually a memory management dependency */ - return dma_resv_get_singleton(bo->base.resv, false, + return dma_resv_get_singleton(bo->base.resv, + DMA_RESV_USAGE_WRITE, &bo->moving); }

diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c index d32cd7538835..f9901d273b8e 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -67,7 +67,8 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) * may be not up-to-date. Wait for the exporter to finish * the migration. */ - return dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv, false, + return dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv, + DMA_RESV_USAGE_WRITE, false, MAX_SCHEDULE_TIMEOUT); } EXPORT_SYMBOL(ib_umem_dmabuf_map_pages); diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 5fa04d0fccad..658674c4b7b9 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -49,6 +49,49 @@ extern struct ww_class reservation_ww_class;

struct dma_resv_list;

+/** + * enum dma_resv_usage - how the fences from a dma_resv obj are used + * + * This enum describes the different use cases for a dma_resv object and + * controls which fences are returned when queried. + */ +enum dma_resv_usage { + /** + * @DMA_RESV_USAGE_WRITE: Implicit write synchronization. + * + * This should only be used for userspace command submissions which add + * an implicit write dependency. + */ + DMA_RESV_USAGE_WRITE, + + /** + * @DMA_RESV_USAGE_READ: Implicit read synchronization. + * + * This should only be used for userspace command submissions which add + * an implicit read dependency. + */ + DMA_RESV_USAGE_READ, +}; + +/** + * dma_resv_usage_rw - helper for implicit sync + * @write: true if we create a new implicit sync write + * + * This returns the implicit synchronization usage for write or read accesses, + * see enum dma_resv_usage. + */ +static inline enum dma_resv_usage dma_resv_usage_rw(bool write) +{ + /* This looks confusing at first sight, but is indeed correct. + * + * The rational is that new write operations needs to wait for the + * existing read and write operations to finish. + * But a new read operation only needs to wait for the existing write + * operations to finish. + */ + return write ? DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE; +} + /** * struct dma_resv - a reservation object manages fences for a buffer * @@ -142,8 +185,8 @@ struct dma_resv_iter { /** @obj: The dma_resv object we iterate over */ struct dma_resv *obj;

- /** @all_fences: If all fences should be returned */ - bool all_fences; + /** @usage: Controls which fences are returned */ + enum dma_resv_usage usage;

/** @fence: the currently handled fence */ struct dma_fence *fence; @@ -173,14 +216,14 @@ struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor); * dma_resv_iter_begin - initialize a dma_resv_iter object * @cursor: The dma_resv_iter object to initialize * @obj: The dma_resv object which we want to iterate over - * @all_fences: If all fences should be returned or just the exclusive one + * @usage: controls which fences to include, see enum dma_resv_usage. */ static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, struct dma_resv *obj, - bool all_fences) + enum dma_resv_usage usage) { cursor->obj = obj; - cursor->all_fences = all_fences; + cursor->usage = usage; cursor->fence = NULL; }

@@ -241,7 +284,7 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * dma_resv_for_each_fence - fence iterator * @cursor: a struct dma_resv_iter pointer * @obj: a dma_resv object pointer - * @all_fences: true if all fences should be returned + * @usage: controls which fences to return * @fence: the current fence * * Iterate over the fences in a struct dma_resv object while holding the @@ -250,8 +293,8 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * valid as long as the lock is held and so no extra reference to the fence is * taken. */ -#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ - for (dma_resv_iter_begin(cursor, obj, all_fences), \ +#define dma_resv_for_each_fence(cursor, obj, usage, fence) \ + for (dma_resv_iter_begin(cursor, obj, usage), \ fence = dma_resv_iter_first(cursor); fence; \ fence = dma_resv_iter_next(cursor))

@@ -418,14 +461,14 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, struct dma_fence *fence); void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); -int dma_resv_get_fences(struct dma_resv *obj, bool write, +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, unsigned int *num_fences, struct dma_fence ***fences); -int dma_resv_get_singleton(struct dma_resv *obj, bool write, +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, struct dma_fence **fence); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage); void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq);

#endif /* _LINUX_RESERVATION_H */