The i915 driver implements a prune function which is called when it is very likely that the fences inside the dma_resv object can be removed because they are all signaled.
Move that function into the dma-resv.c code since the behavior of pruning fences is something internal to the object.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 18 ++++++++++++++++++ drivers/gpu/drm/i915/Makefile | 1 - drivers/gpu/drm/i915/dma_resv_utils.c | 17 ----------------- drivers/gpu/drm/i915/dma_resv_utils.h | 13 ------------- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 3 +-- drivers/gpu/drm/i915/gem/i915_gem_wait.c | 3 +-- include/linux/dma-resv.h | 1 + 7 files changed, 21 insertions(+), 35 deletions(-) delete mode 100644 drivers/gpu/drm/i915/dma_resv_utils.c delete mode 100644 drivers/gpu/drm/i915/dma_resv_utils.h
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index ff3c0558b3b8..64d4f95778c4 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -324,6 +324,24 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) } EXPORT_SYMBOL(dma_resv_add_excl_fence);
+/** + * dma_resv_prune_unlocked - try to remove signaled fences + * @obj: The dma_resv object to prune + * + * Try to lock the object, test if it is signaled and if yes then remove all the + * signaled fences. + */ +void dma_resv_prune_unlocked(struct dma_resv *obj) +{ + if (!dma_resv_trylock(obj)) + return; + + if (dma_resv_test_signaled(obj, true)) + dma_resv_add_excl_fence(obj, NULL); + dma_resv_unlock(obj); +} +EXPORT_SYMBOL(dma_resv_prune_unlocked); + /** * dma_resv_iter_restart_unlocked - restart the unlocked iterator * @cursor: The dma_resv_iter object to restart diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 660bb03de6fc..5c1af130cb6d 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -60,7 +60,6 @@ i915-y += i915_drv.o \
# core library code i915-y += \ - dma_resv_utils.o \ i915_memcpy.o \ i915_mm.o \ i915_sw_fence.o \ diff --git a/drivers/gpu/drm/i915/dma_resv_utils.c b/drivers/gpu/drm/i915/dma_resv_utils.c deleted file mode 100644 index 7df91b7e4ca8..000000000000 --- a/drivers/gpu/drm/i915/dma_resv_utils.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: MIT -/* - * Copyright © 2020 Intel Corporation - */ - -#include <linux/dma-resv.h> - -#include "dma_resv_utils.h" - -void dma_resv_prune(struct dma_resv *resv) -{ - if (dma_resv_trylock(resv)) { - if (dma_resv_test_signaled(resv, true)) - dma_resv_add_excl_fence(resv, NULL); - dma_resv_unlock(resv); - } -} diff --git a/drivers/gpu/drm/i915/dma_resv_utils.h b/drivers/gpu/drm/i915/dma_resv_utils.h deleted file mode 100644 index b9d8fb5f8367..000000000000 --- a/drivers/gpu/drm/i915/dma_resv_utils.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright © 2020 Intel Corporation - */ - -#ifndef DMA_RESV_UTILS_H -#define DMA_RESV_UTILS_H - -struct dma_resv; - -void dma_resv_prune(struct dma_resv *resv); - -#endif /* DMA_RESV_UTILS_H */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 5ab136ffdeb2..48029bbda682 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -15,7 +15,6 @@
#include "gt/intel_gt_requests.h"
-#include "dma_resv_utils.h" #include "i915_trace.h"
static bool swap_available(void) @@ -229,7 +228,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, i915_gem_object_unlock(obj); }
- dma_resv_prune(obj->base.resv); + dma_resv_prune_unlocked(obj->base.resv);
scanned += obj->base.size >> PAGE_SHIFT; skip: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index 569658c7859c..1915d203a72d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -10,7 +10,6 @@
#include "gt/intel_engine.h"
-#include "dma_resv_utils.h" #include "i915_gem_ioctls.h" #include "i915_gem_object.h"
@@ -53,7 +52,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, * signaled. */ if (timeout > 0) - dma_resv_prune(resv); + dma_resv_prune_unlocked(resv);
return timeout; } diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index eebf04325b34..e0558429a5ee 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -458,6 +458,7 @@ void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(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_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); +void dma_resv_prune_unlocked(struct dma_resv *obj); int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, unsigned *pshared_count, struct dma_fence ***pshared); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src);
Just grab all fences for the display flip in one go.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 6 +----- 2 files changed, 1 insertion(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d58e37fd01f4..4da7eb65e744 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -457,7 +457,6 @@ struct amdgpu_flip_work { uint64_t base; struct drm_pending_vblank_event *event; struct amdgpu_bo *old_abo; - struct dma_fence *excl; unsigned shared_count; struct dma_fence **shared; struct dma_fence_cb cb; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index dc50c05f23fc..68108f151dad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -83,9 +83,6 @@ static void amdgpu_display_flip_work_func(struct work_struct *__work) unsigned i; int vpos, hpos;
- if (amdgpu_display_flip_handle_fence(work, &work->excl)) - return; - for (i = 0; i < work->shared_count; ++i) if (amdgpu_display_flip_handle_fence(work, &work->shared[i])) return; @@ -203,7 +200,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, goto unpin; }
- r = dma_resv_get_fences(new_abo->tbo.base.resv, &work->excl, + r = dma_resv_get_fences(new_abo->tbo.base.resv, NULL, &work->shared_count, &work->shared); if (unlikely(r != 0)) { DRM_ERROR("failed to get fences for buffer\n"); @@ -253,7 +250,6 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
cleanup: amdgpu_bo_unref(&work->old_abo); - dma_fence_put(work->excl); for (i = 0; i < work->shared_count; ++i) dma_fence_put(work->shared[i]); kfree(work->shared);
Just grab all fences in one go.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 8dc93863bf96..b5e8ce86dbe7 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -189,7 +189,7 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) continue;
if (bo->flags & ETNA_SUBMIT_BO_WRITE) { - ret = dma_resv_get_fences(robj, &bo->excl, + ret = dma_resv_get_fences(robj, NULL, &bo->nr_shared, &bo->shared); if (ret)
Am Donnerstag, dem 28.10.2021 um 15:26 +0200 schrieb Christian König:
Just grab all fences in one go.
Signed-off-by: Christian König christian.koenig@amd.com
Reviewed-by: Lucas Stach l.stach@pengutronix.de
drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 8dc93863bf96..b5e8ce86dbe7 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -189,7 +189,7 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) continue;
if (bo->flags & ETNA_SUBMIT_BO_WRITE) {
ret = dma_resv_get_fences(robj, &bo->excl,
ret = dma_resv_get_fences(robj, NULL, &bo->nr_shared, &bo->shared); if (ret)
Returning the exclusive fence separately is no longer used.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 43 +++++++------------- drivers/dma-buf/st-dma-resv.c | 26 +++--------- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 2 +- drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c | 3 +- include/linux/dma-resv.h | 4 +- 6 files changed, 26 insertions(+), 56 deletions(-)
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 64d4f95778c4..fb02860312fc 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -561,26 +561,21 @@ 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 - * @fence_excl: the returned exclusive fence (or NULL) - * @shared_count: the number of shared fences returned - * @shared: the array of shared fence ptrs returned (array is krealloc'd to - * the required size, and must be freed by caller) + * @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) * - * Retrieve all fences from the reservation object. If the pointer for the - * exclusive fence is not specified the fence is put into the array of the - * shared fences as well. Returns either zero or -ENOMEM. + * Retrieve all fences from the reservation object. + * Returns either zero or -ENOMEM. */ -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, - unsigned int *shared_count, struct dma_fence ***shared) +int dma_resv_get_fences(struct dma_resv *obj, unsigned int *num_fences, + struct dma_fence ***fences) { struct dma_resv_iter cursor; struct dma_fence *fence;
- *shared_count = 0; - *shared = NULL; - - if (fence_excl) - *fence_excl = NULL; + *num_fences = 0; + *fences = NULL;
dma_resv_iter_begin(&cursor, obj, true); dma_resv_for_each_fence_unlocked(&cursor, fence) { @@ -588,30 +583,22 @@ int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, if (dma_resv_iter_is_restarted(&cursor)) { unsigned int count;
- while (*shared_count) - dma_fence_put((*shared)[--(*shared_count)]); - - if (fence_excl) - dma_fence_put(*fence_excl); + while (*num_fences) + dma_fence_put((*fences)[--(*num_fences)]);
- count = cursor.shared_count; - count += fence_excl ? 0 : 1; + count = cursor.shared_count + 1;
/* Eventually re-allocate the array */ - *shared = krealloc_array(*shared, count, + *fences = krealloc_array(*fences, count, sizeof(void *), GFP_KERNEL); - if (count && !*shared) { + if (count && !*fences) { dma_resv_iter_end(&cursor); return -ENOMEM; } }
- dma_fence_get(fence); - if (dma_resv_iter_is_exclusive(&cursor) && fence_excl) - *fence_excl = fence; - else - (*shared)[(*shared_count)++] = fence; + (*fences)[(*num_fences)++] = dma_fence_get(fence); } dma_resv_iter_end(&cursor);
diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c index bc32b3eedcb6..fd742a60f7e0 100644 --- a/drivers/dma-buf/st-dma-resv.c +++ b/drivers/dma-buf/st-dma-resv.c @@ -275,7 +275,7 @@ static int test_shared_for_each_unlocked(void *arg)
static int test_get_fences(void *arg, bool shared) { - struct dma_fence *f, *excl = NULL, **fences = NULL; + struct dma_fence *f, **fences = NULL; struct dma_resv resv; int r, i;
@@ -304,35 +304,19 @@ static int test_get_fences(void *arg, bool shared) } dma_resv_unlock(&resv);
- r = dma_resv_get_fences(&resv, &excl, &i, &fences); + r = dma_resv_get_fences(&resv, &i, &fences); if (r) { pr_err("get_fences failed\n"); goto err_free; }
- if (shared) { - if (excl != NULL) { - pr_err("get_fences returned unexpected excl fence\n"); - goto err_free; - } - if (i != 1 || fences[0] != f) { - pr_err("get_fences returned unexpected shared fence\n"); - goto err_free; - } - } else { - if (excl != f) { - pr_err("get_fences returned unexpected excl fence\n"); - goto err_free; - } - if (i != 0) { - pr_err("get_fences returned unexpected shared fence\n"); - goto err_free; - } + if (i != 1 || fences[0] != f) { + pr_err("get_fences returned unexpected fence\n"); + goto err_free; }
dma_fence_signal(f); err_free: - dma_fence_put(excl); while (i--) dma_fence_put(fences[i]); kfree(fences); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 68108f151dad..b8cf3740dd28 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -200,8 +200,8 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, goto unpin; }
- r = dma_resv_get_fences(new_abo->tbo.base.resv, NULL, - &work->shared_count, &work->shared); + r = dma_resv_get_fences(new_abo->tbo.base.resv, &work->shared_count, + &work->shared); if (unlikely(r != 0)) { DRM_ERROR("failed to get fences for buffer\n"); goto unpin; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index b7fb72bff2c1..4500d6b4fcd3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -112,7 +112,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, unsigned count; int r;
- r = dma_resv_get_fences(resv, NULL, &count, &fences); + r = dma_resv_get_fences(resv, &count, &fences); if (r) goto fallback;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index b5e8ce86dbe7..982bd7135a66 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -189,8 +189,7 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) continue;
if (bo->flags & ETNA_SUBMIT_BO_WRITE) { - ret = dma_resv_get_fences(robj, NULL, - &bo->nr_shared, + ret = dma_resv_get_fences(robj, &bo->nr_shared, &bo->shared); if (ret) return ret; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e0558429a5ee..cde0147e8830 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -459,8 +459,8 @@ int dma_resv_reserve_shared(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_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_prune_unlocked(struct dma_resv *obj); -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, - unsigned *pshared_count, struct dma_fence ***pshared); +int dma_resv_get_fences(struct dma_resv *obj, unsigned int *num_fences, + struct dma_fence ***fences); 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);
Use dma_resv_wait() instead of extracting the exclusive fence and waiting on it manually.
Signed-off-by: Christian König christian.koenig@amd.com --- 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 e824baf4640d..258ba9b8c17d 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -13,7 +13,6 @@ 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; @@ -65,11 +64,8 @@ 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);
Don't touch the exclusive fence manually here, but rather use the general dma_resv function. We did that for better hw reset handling but this doesn't necessary work correctly.
Signed-off-by: Christian König christian.koenig@amd.com --- drivers/gpu/drm/radeon/radeon_uvd.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 2ea86919d953..377f9cdb5b53 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -469,7 +469,6 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, { int32_t *msg, msg_type, handle; unsigned img_size = 0; - struct dma_fence *f; void *ptr;
int i, r; @@ -479,13 +478,11 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; }
- f = dma_resv_excl_fence(bo->tbo.base.resv); - if (f) { - r = radeon_fence_wait((struct radeon_fence *)f, false); - if (r) { - DRM_ERROR("Failed waiting for UVD message (%d)!\n", r); - return r; - } + r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, + MAX_SCHEDULE_TIMEOUT); + if (r <= 0) { + DRM_ERROR("Failed waiting for UVD message (%d)!\n", r); + return r ? r : -ETIME; }
r = radeon_bo_kmap(bo, &ptr);
Ping, Alex do you have a moment for that one here?
Am 28.10.21 um 15:26 schrieb Christian König:
Don't touch the exclusive fence manually here, but rather use the general dma_resv function. We did that for better hw reset handling but this doesn't necessary work correctly.
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/radeon/radeon_uvd.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 2ea86919d953..377f9cdb5b53 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -469,7 +469,6 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, { int32_t *msg, msg_type, handle; unsigned img_size = 0;
struct dma_fence *f; void *ptr;
int i, r;
@@ -479,13 +478,11 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; }
- f = dma_resv_excl_fence(bo->tbo.base.resv);
- if (f) {
r = radeon_fence_wait((struct radeon_fence *)f, false);
if (r) {
DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
return r;
}
r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false,
MAX_SCHEDULE_TIMEOUT);
if (r <= 0) {
DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
return r ? r : -ETIME;
}
r = radeon_bo_kmap(bo, &ptr);
Acked-by: Nirmoy Das nirmoy.das@amd.com
On 10/28/2021 3:26 PM, Christian König wrote:
Don't touch the exclusive fence manually here, but rather use the general dma_resv function. We did that for better hw reset handling but this doesn't necessary work correctly.
Signed-off-by: Christian König christian.koenig@amd.com
drivers/gpu/drm/radeon/radeon_uvd.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 2ea86919d953..377f9cdb5b53 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -469,7 +469,6 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, { int32_t *msg, msg_type, handle; unsigned img_size = 0;
struct dma_fence *f; void *ptr;
int i, r;
@@ -479,13 +478,11 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; }
- f = dma_resv_excl_fence(bo->tbo.base.resv);
- if (f) {
r = radeon_fence_wait((struct radeon_fence *)f, false);
if (r) {
DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
return r;
}
r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false,
MAX_SCHEDULE_TIMEOUT);
if (r <= 0) {
DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
return r ? r : -ETIME;
}
r = radeon_bo_kmap(bo, &ptr);
On 28-10-2021 15:26, Christian König wrote:
The i915 driver implements a prune function which is called when it is very likely that the fences inside the dma_resv object can be removed because they are all signaled.
Move that function into the dma-resv.c code since the behavior of pruning fences is something internal to the object.
Signed-off-by: Christian König christian.koenig@amd.com
drivers/dma-buf/dma-resv.c | 18 ++++++++++++++++++ drivers/gpu/drm/i915/Makefile | 1 - drivers/gpu/drm/i915/dma_resv_utils.c | 17 ----------------- drivers/gpu/drm/i915/dma_resv_utils.h | 13 ------------- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 3 +-- drivers/gpu/drm/i915/gem/i915_gem_wait.c | 3 +-- include/linux/dma-resv.h | 1 + 7 files changed, 21 insertions(+), 35 deletions(-) delete mode 100644 drivers/gpu/drm/i915/dma_resv_utils.c delete mode 100644 drivers/gpu/drm/i915/dma_resv_utils.h
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index ff3c0558b3b8..64d4f95778c4 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -324,6 +324,24 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) } EXPORT_SYMBOL(dma_resv_add_excl_fence);
+/**
- dma_resv_prune_unlocked - try to remove signaled fences
- @obj: The dma_resv object to prune
- Try to lock the object, test if it is signaled and if yes then remove all the
- signaled fences.
- */
+void dma_resv_prune_unlocked(struct dma_resv *obj) +{
- if (!dma_resv_trylock(obj))
return;
- if (dma_resv_test_signaled(obj, true))
dma_resv_add_excl_fence(obj, NULL);
- dma_resv_unlock(obj);
+} +EXPORT_SYMBOL(dma_resv_prune_unlocked);
/**
- dma_resv_iter_restart_unlocked - restart the unlocked iterator
- @cursor: The dma_resv_iter object to restart
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 660bb03de6fc..5c1af130cb6d 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -60,7 +60,6 @@ i915-y += i915_drv.o \
# core library code i915-y += \
- dma_resv_utils.o \ i915_memcpy.o \ i915_mm.o \ i915_sw_fence.o \
diff --git a/drivers/gpu/drm/i915/dma_resv_utils.c b/drivers/gpu/drm/i915/dma_resv_utils.c deleted file mode 100644 index 7df91b7e4ca8..000000000000 --- a/drivers/gpu/drm/i915/dma_resv_utils.c +++ /dev/null @@ -1,17 +0,0 @@ -// SPDX-License-Identifier: MIT -/*
- Copyright © 2020 Intel Corporation
- */
-#include <linux/dma-resv.h>
-#include "dma_resv_utils.h"
-void dma_resv_prune(struct dma_resv *resv) -{
- if (dma_resv_trylock(resv)) {
if (dma_resv_test_signaled(resv, true))
dma_resv_add_excl_fence(resv, NULL);
dma_resv_unlock(resv);
- }
-} diff --git a/drivers/gpu/drm/i915/dma_resv_utils.h b/drivers/gpu/drm/i915/dma_resv_utils.h deleted file mode 100644 index b9d8fb5f8367..000000000000 --- a/drivers/gpu/drm/i915/dma_resv_utils.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/*
- Copyright © 2020 Intel Corporation
- */
-#ifndef DMA_RESV_UTILS_H -#define DMA_RESV_UTILS_H
-struct dma_resv;
-void dma_resv_prune(struct dma_resv *resv);
-#endif /* DMA_RESV_UTILS_H */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 5ab136ffdeb2..48029bbda682 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -15,7 +15,6 @@
#include "gt/intel_gt_requests.h"
-#include "dma_resv_utils.h" #include "i915_trace.h"
static bool swap_available(void) @@ -229,7 +228,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, i915_gem_object_unlock(obj); }
dma_resv_prune(obj->base.resv);
dma_resv_prune_unlocked(obj->base.resv); scanned += obj->base.size >> PAGE_SHIFT;
skip: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index 569658c7859c..1915d203a72d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -10,7 +10,6 @@
#include "gt/intel_engine.h"
-#include "dma_resv_utils.h" #include "i915_gem_ioctls.h" #include "i915_gem_object.h"
@@ -53,7 +52,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, * signaled. */ if (timeout > 0)
dma_resv_prune(resv);
dma_resv_prune_unlocked(resv);
return timeout;
} diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index eebf04325b34..e0558429a5ee 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -458,6 +458,7 @@ void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(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_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); +void dma_resv_prune_unlocked(struct dma_resv *obj); int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, unsigned *pshared_count, struct dma_fence ***pshared); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src);
I don't mind adding a dma_resv_prune for locked case, but I don't think unlocked would have benefits.
Furthermore, I'm trying to remove the unlocked versions from i915. Could this be a prereq patch instead?
https://patchwork.freedesktop.org/patch/460722/?series=96115&rev=1
~Maarten
~Maarten
Am 25.11.21 um 10:31 schrieb Maarten Lankhorst:
[SNIP]
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index eebf04325b34..e0558429a5ee 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -458,6 +458,7 @@ void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(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_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); +void dma_resv_prune_unlocked(struct dma_resv *obj); int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, unsigned *pshared_count, struct dma_fence ***pshared); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src);
I don't mind adding a dma_resv_prune for locked case, but I don't think unlocked would have benefits.
Furthermore, I'm trying to remove the unlocked versions from i915. Could this be a prereq patch instead?
https://patchwork.freedesktop.org/patch/460722/?series=96115&rev=1
Yeah, that works for me as well.
I was on the edge of dropping that from TTM as well since this is really just abusing the interface to save a few bytes of memory.
Feel free to add an Acked-by: Christian König christian.koenig@amd.com to the i915 patch if it helps to get that committed.
Regards, Christian.
~Maarten
~Maarten
dri-devel@lists.freedesktop.org