From 7bc80a5462c37eab58a9ea386064307c0f447fd1 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 9 Nov 2021 11:08:18 +0100
Subject: dma-buf: add enum dma_resv_usage v4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

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
v4: some more kerneldoc suggestions by Daniel, fix missing cases lost in
    the rebase pointed out by Bas.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-2-christian.koenig@amd.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 6f57a2fd5fe3..a7f39f8ab7be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -768,8 +768,8 @@ 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;
 
-- 
cgit v1.2.3


From 73511edf8b196e6f1ccda0fdf294ff57aa2dc9db Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 9 Nov 2021 11:08:18 +0100
Subject: dma-buf: specify usage while adding fences to dma_resv obj v7
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of distingting between shared and exclusive fences specify
the fence usage while adding fences.

Rework all drivers to use this interface instead and deprecate the old one.

v2: some kerneldoc comments suggested by Daniel
v3: fix a missing case in radeon
v4: rebase on nouveau changes, fix lockdep and temporary disable warning
v5: more documentation updates
v6: separate internal dma_resv changes from this patch, avoids to
    disable warning temporary, rebase on upstream changes
v7: fix missed case in lima driver, minimize changes to i915_gem_busy_ioctl

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-3-christian.koenig@amd.com
---
 drivers/dma-buf/dma-resv.c                         |  48 +++++++---
 drivers/dma-buf/st-dma-resv.c                      | 101 ++++++---------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c   |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c             |   4 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c         |   6 +-
 drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c       |  10 +-
 drivers/gpu/drm/i915/gem/i915_gem_busy.c           |   6 +-
 drivers/gpu/drm/i915/gem/i915_gem_clflush.c        |   3 +-
 drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c       |   5 +-
 .../gpu/drm/i915/gem/selftests/i915_gem_migrate.c  |   4 +-
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |   3 +-
 drivers/gpu/drm/i915/i915_vma.c                    |   8 +-
 .../gpu/drm/i915/selftests/intel_memory_region.c   |   3 +-
 drivers/gpu/drm/lima/lima_gem.c                    |   7 +-
 drivers/gpu/drm/msm/msm_gem_submit.c               |   6 +-
 drivers/gpu/drm/nouveau/nouveau_bo.c               |   9 +-
 drivers/gpu/drm/nouveau/nouveau_fence.c            |   4 +-
 drivers/gpu/drm/panfrost/panfrost_job.c            |   2 +-
 drivers/gpu/drm/qxl/qxl_release.c                  |   3 +-
 drivers/gpu/drm/radeon/radeon_object.c             |   6 +-
 drivers/gpu/drm/ttm/ttm_bo.c                       |   2 +-
 drivers/gpu/drm/ttm/ttm_bo_util.c                  |   5 +-
 drivers/gpu/drm/ttm/ttm_execbuf_util.c             |   6 +-
 drivers/gpu/drm/v3d/v3d_gem.c                      |   4 +-
 drivers/gpu/drm/vc4/vc4_gem.c                      |   2 +-
 drivers/gpu/drm/vgem/vgem_fence.c                  |   9 +-
 drivers/gpu/drm/virtio/virtgpu_gem.c               |   3 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c                 |   3 +-
 include/linux/dma-buf.h                            |  16 ++--
 include/linux/dma-resv.h                           |  25 +++--
 30 files changed, 149 insertions(+), 166 deletions(-)

(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 17237e6ee30c..543dae6566d2 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -234,14 +234,14 @@ EXPORT_SYMBOL(dma_resv_reserve_fences);
 
 #ifdef CONFIG_DEBUG_MUTEXES
 /**
- * dma_resv_reset_shared_max - reset shared fences for debugging
+ * dma_resv_reset_max_fences - reset shared fences for debugging
  * @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_fences(). See also
  * &dma_resv_list.shared_max.
  */
-void dma_resv_reset_shared_max(struct dma_resv *obj)
+void dma_resv_reset_max_fences(struct dma_resv *obj)
 {
 	struct dma_resv_list *fences = dma_resv_shared_list(obj);
 
@@ -251,7 +251,7 @@ void dma_resv_reset_shared_max(struct dma_resv *obj)
 	if (fences)
 		fences->shared_max = fences->shared_count;
 }
-EXPORT_SYMBOL(dma_resv_reset_shared_max);
+EXPORT_SYMBOL(dma_resv_reset_max_fences);
 #endif
 
 /**
@@ -264,7 +264,8 @@ EXPORT_SYMBOL(dma_resv_reset_shared_max);
  *
  * See also &dma_resv.fence for a discussion of the semantics.
  */
-void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
+static void dma_resv_add_shared_fence(struct dma_resv *obj,
+				      struct dma_fence *fence)
 {
 	struct dma_resv_list *fobj;
 	struct dma_fence *old;
@@ -305,13 +306,13 @@ replace:
 	write_seqcount_end(&obj->seq);
 	dma_fence_put(old);
 }
-EXPORT_SYMBOL(dma_resv_add_shared_fence);
 
 /**
  * dma_resv_replace_fences - replace fences in the dma_resv obj
  * @obj: the reservation object
  * @context: the context of the fences to replace
  * @replacement: the new fence to use instead
+ * @usage: how the new fence is used, see enum dma_resv_usage
  *
  * Replace fences with a specified context with a new fence. Only valid if the
  * operation represented by the original fence has no longer access to the
@@ -321,12 +322,16 @@ EXPORT_SYMBOL(dma_resv_add_shared_fence);
  * update fence which makes the resource inaccessible.
  */
 void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context,
-			     struct dma_fence *replacement)
+			     struct dma_fence *replacement,
+			     enum dma_resv_usage usage)
 {
 	struct dma_resv_list *list;
 	struct dma_fence *old;
 	unsigned int i;
 
+	/* Only readers supported for now */
+	WARN_ON(usage != DMA_RESV_USAGE_READ);
+
 	dma_resv_assert_held(obj);
 
 	write_seqcount_begin(&obj->seq);
@@ -360,7 +365,8 @@ EXPORT_SYMBOL(dma_resv_replace_fences);
  * Add a fence to the exclusive slot. @obj must be locked with dma_resv_lock().
  * See also &dma_resv.fence_excl for a discussion of the semantics.
  */
-void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence)
+static void dma_resv_add_excl_fence(struct dma_resv *obj,
+				    struct dma_fence *fence)
 {
 	struct dma_fence *old_fence = dma_resv_excl_fence(obj);
 
@@ -375,7 +381,27 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence)
 
 	dma_fence_put(old_fence);
 }
-EXPORT_SYMBOL(dma_resv_add_excl_fence);
+
+/**
+ * dma_resv_add_fence - Add a fence to the dma_resv obj
+ * @obj: the reservation object
+ * @fence: the fence to add
+ * @usage: how the fence is used, see enum dma_resv_usage
+ *
+ * Add a fence to a slot, @obj must be locked with dma_resv_lock(), and
+ * dma_resv_reserve_fences() has been called.
+ *
+ * See also &dma_resv.fence for a discussion of the semantics.
+ */
+void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence,
+			enum dma_resv_usage usage)
+{
+	if (usage == DMA_RESV_USAGE_WRITE)
+		dma_resv_add_excl_fence(obj, fence);
+	else
+		dma_resv_add_shared_fence(obj, fence);
+}
+EXPORT_SYMBOL(dma_resv_add_fence);
 
 /* Restart the iterator by initializing all the necessary fields, but not the
  * relation to the dma_resv object. */
@@ -574,7 +600,7 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)
 		}
 
 		dma_fence_get(f);
-		if (dma_resv_iter_is_exclusive(&cursor))
+		if (dma_resv_iter_usage(&cursor) == DMA_RESV_USAGE_WRITE)
 			excl = f;
 		else
 			RCU_INIT_POINTER(list->shared[list->shared_count++], f);
@@ -771,13 +797,13 @@ EXPORT_SYMBOL_GPL(dma_resv_test_signaled);
  */
 void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq)
 {
+	static const char *usage[] = { "write", "read" };
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
 
 	dma_resv_for_each_fence(&cursor, obj, DMA_RESV_USAGE_READ, fence) {
 		seq_printf(seq, "\t%s fence:",
-			   dma_resv_iter_is_exclusive(&cursor) ?
-				"Exclusive" : "Shared");
+			   usage[dma_resv_iter_usage(&cursor)]);
 		dma_fence_describe(fence, seq);
 	}
 }
diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c
index d097981061b1..d0f7c2bfd4f0 100644
--- a/drivers/dma-buf/st-dma-resv.c
+++ b/drivers/dma-buf/st-dma-resv.c
@@ -58,8 +58,9 @@ static int sanitycheck(void *arg)
 	return r;
 }
 
-static int test_signaling(void *arg, enum dma_resv_usage usage)
+static int test_signaling(void *arg)
 {
+	enum dma_resv_usage usage = (unsigned long)arg;
 	struct dma_resv resv;
 	struct dma_fence *f;
 	int r;
@@ -81,11 +82,7 @@ static int test_signaling(void *arg, enum dma_resv_usage usage)
 		goto err_unlock;
 	}
 
-	if (usage >= DMA_RESV_USAGE_READ)
-		dma_resv_add_shared_fence(&resv, f);
-	else
-		dma_resv_add_excl_fence(&resv, f);
-
+	dma_resv_add_fence(&resv, f, usage);
 	if (dma_resv_test_signaled(&resv, usage)) {
 		pr_err("Resv unexpectedly signaled\n");
 		r = -EINVAL;
@@ -105,18 +102,9 @@ err_free:
 	return r;
 }
 
-static int test_excl_signaling(void *arg)
-{
-	return test_signaling(arg, DMA_RESV_USAGE_WRITE);
-}
-
-static int test_shared_signaling(void *arg)
-{
-	return test_signaling(arg, DMA_RESV_USAGE_READ);
-}
-
-static int test_for_each(void *arg, enum dma_resv_usage usage)
+static int test_for_each(void *arg)
 {
+	enum dma_resv_usage usage = (unsigned long)arg;
 	struct dma_resv_iter cursor;
 	struct dma_fence *f, *fence;
 	struct dma_resv resv;
@@ -139,10 +127,7 @@ static int test_for_each(void *arg, enum dma_resv_usage usage)
 		goto err_unlock;
 	}
 
-	if (usage >= DMA_RESV_USAGE_READ)
-		dma_resv_add_shared_fence(&resv, f);
-	else
-		dma_resv_add_excl_fence(&resv, f);
+	dma_resv_add_fence(&resv, f, usage);
 
 	r = -ENOENT;
 	dma_resv_for_each_fence(&cursor, &resv, usage, fence) {
@@ -156,8 +141,7 @@ static int test_for_each(void *arg, enum dma_resv_usage usage)
 			r = -EINVAL;
 			goto err_unlock;
 		}
-		if (dma_resv_iter_is_exclusive(&cursor) !=
-		    (usage >= DMA_RESV_USAGE_READ)) {
+		if (dma_resv_iter_usage(&cursor) != usage) {
 			pr_err("Unexpected fence usage\n");
 			r = -EINVAL;
 			goto err_unlock;
@@ -177,18 +161,9 @@ err_free:
 	return r;
 }
 
-static int test_excl_for_each(void *arg)
-{
-	return test_for_each(arg, DMA_RESV_USAGE_WRITE);
-}
-
-static int test_shared_for_each(void *arg)
-{
-	return test_for_each(arg, DMA_RESV_USAGE_READ);
-}
-
-static int test_for_each_unlocked(void *arg, enum dma_resv_usage usage)
+static int test_for_each_unlocked(void *arg)
 {
+	enum dma_resv_usage usage = (unsigned long)arg;
 	struct dma_resv_iter cursor;
 	struct dma_fence *f, *fence;
 	struct dma_resv resv;
@@ -212,10 +187,7 @@ static int test_for_each_unlocked(void *arg, enum dma_resv_usage usage)
 		goto err_free;
 	}
 
-	if (usage >= DMA_RESV_USAGE_READ)
-		dma_resv_add_shared_fence(&resv, f);
-	else
-		dma_resv_add_excl_fence(&resv, f);
+	dma_resv_add_fence(&resv, f, usage);
 	dma_resv_unlock(&resv);
 
 	r = -ENOENT;
@@ -235,8 +207,7 @@ static int test_for_each_unlocked(void *arg, enum dma_resv_usage usage)
 			r = -EINVAL;
 			goto err_iter_end;
 		}
-		if (dma_resv_iter_is_exclusive(&cursor) !=
-		    (usage >= DMA_RESV_USAGE_READ)) {
+		if (dma_resv_iter_usage(&cursor) != usage) {
 			pr_err("Unexpected fence usage\n");
 			r = -EINVAL;
 			goto err_iter_end;
@@ -262,18 +233,9 @@ err_free:
 	return r;
 }
 
-static int test_excl_for_each_unlocked(void *arg)
-{
-	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, DMA_RESV_USAGE_READ);
-}
-
-static int test_get_fences(void *arg, enum dma_resv_usage usage)
+static int test_get_fences(void *arg)
 {
+	enum dma_resv_usage usage = (unsigned long)arg;
 	struct dma_fence *f, **fences = NULL;
 	struct dma_resv resv;
 	int r, i;
@@ -296,10 +258,7 @@ static int test_get_fences(void *arg, enum dma_resv_usage usage)
 		goto err_resv;
 	}
 
-	if (usage >= DMA_RESV_USAGE_READ)
-		dma_resv_add_shared_fence(&resv, f);
-	else
-		dma_resv_add_excl_fence(&resv, f);
+	dma_resv_add_fence(&resv, f, usage);
 	dma_resv_unlock(&resv);
 
 	r = dma_resv_get_fences(&resv, usage, &i, &fences);
@@ -324,30 +283,24 @@ err_resv:
 	return r;
 }
 
-static int test_excl_get_fences(void *arg)
-{
-	return test_get_fences(arg, DMA_RESV_USAGE_WRITE);
-}
-
-static int test_shared_get_fences(void *arg)
-{
-	return test_get_fences(arg, DMA_RESV_USAGE_READ);
-}
-
 int dma_resv(void)
 {
 	static const struct subtest tests[] = {
 		SUBTEST(sanitycheck),
-		SUBTEST(test_excl_signaling),
-		SUBTEST(test_shared_signaling),
-		SUBTEST(test_excl_for_each),
-		SUBTEST(test_shared_for_each),
-		SUBTEST(test_excl_for_each_unlocked),
-		SUBTEST(test_shared_for_each_unlocked),
-		SUBTEST(test_excl_get_fences),
-		SUBTEST(test_shared_get_fences),
+		SUBTEST(test_signaling),
+		SUBTEST(test_for_each),
+		SUBTEST(test_for_each_unlocked),
+		SUBTEST(test_get_fences),
 	};
+	enum dma_resv_usage usage;
+	int r;
 
 	spin_lock_init(&fence_lock);
-	return subtests(tests, NULL);
+	for (usage = DMA_RESV_USAGE_WRITE; usage <= DMA_RESV_USAGE_READ;
+	     ++usage) {
+		r = subtests(tests, (void *)(unsigned long)usage);
+		if (r)
+			return r;
+	}
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 98b1736bb221..5031e26e6716 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);
+				replacement, DMA_RESV_USAGE_READ);
 	dma_fence_put(replacement);
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 413f32c3fd63..76fd916424d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -55,8 +55,8 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 	bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
 	p->uf_entry.priority = 0;
 	p->uf_entry.tv.bo = &bo->tbo;
-	/* One for TTM and one for the CS job */
-	p->uf_entry.tv.num_shared = 2;
+	/* One for TTM and two for the CS job */
+	p->uf_entry.tv.num_shared = 3;
 
 	drm_gem_object_put(gobj);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index a7f39f8ab7be..a3cdf8a24377 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1397,10 +1397,8 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
 		return;
 	}
 
-	if (shared)
-		dma_resv_add_shared_fence(resv, fence);
-	else
-		dma_resv_add_excl_fence(resv, fence);
+	dma_resv_add_fence(resv, fence, shared ? DMA_RESV_USAGE_READ :
+			   DMA_RESV_USAGE_WRITE);
 }
 
 /**
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 53f7c78628a4..98bb5c9239de 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -202,14 +202,10 @@ static void submit_attach_object_fences(struct etnaviv_gem_submit *submit)
 
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
+		bool write = submit->bos[i].flags & ETNA_SUBMIT_BO_WRITE;
 
-		if (submit->bos[i].flags & ETNA_SUBMIT_BO_WRITE)
-			dma_resv_add_excl_fence(obj->resv,
-							  submit->out_fence);
-		else
-			dma_resv_add_shared_fence(obj->resv,
-							    submit->out_fence);
-
+		dma_resv_add_fence(obj->resv, submit->out_fence, write ?
+				   DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ);
 		submit_unlock_object(submit, i);
 	}
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
index 14a1c0ad8c3c..ddda468241ef 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
@@ -148,11 +148,11 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 		if (dma_resv_iter_is_restarted(&cursor))
 			args->busy = 0;
 
-		if (dma_resv_iter_is_exclusive(&cursor))
-			/* Translate the exclusive fence to the READ *and* WRITE engine */
+		if (dma_resv_iter_usage(&cursor) <= DMA_RESV_USAGE_WRITE)
+			/* Translate the write fences to the READ *and* WRITE engine */
 			args->busy |= busy_check_writer(fence);
 		else
-			/* Translate shared fences to READ set of engines */
+			/* Translate read fences to READ set of engines */
 			args->busy |= busy_check_reader(fence);
 	}
 	dma_resv_iter_end(&cursor);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 1fd0cc9ca213..f5f2b8b115ea 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -116,7 +116,8 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
 						obj->base.resv, NULL, true,
 						i915_fence_timeout(i915),
 						I915_FENCE_GFP);
-		dma_resv_add_excl_fence(obj->base.resv, &clflush->base.dma);
+		dma_resv_add_fence(obj->base.resv, &clflush->base.dma,
+				   DMA_RESV_USAGE_WRITE);
 		dma_fence_work_commit(&clflush->base);
 		/*
 		 * We must have successfully populated the pages(since we are
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 432ac74ff225..438b8a95b3d1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -637,9 +637,8 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
 	if (IS_ERR_OR_NULL(copy_fence))
 		return PTR_ERR_OR_ZERO(copy_fence);
 
-	dma_resv_add_excl_fence(dst_bo->base.resv, copy_fence);
-	dma_resv_add_shared_fence(src_bo->base.resv, copy_fence);
-
+	dma_resv_add_fence(dst_bo->base.resv, copy_fence, DMA_RESV_USAGE_WRITE);
+	dma_resv_add_fence(src_bo->base.resv, copy_fence, DMA_RESV_USAGE_READ);
 	dma_fence_put(copy_fence);
 
 	return 0;
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 0e52eb87cd55..4997ed18b6e4 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c
@@ -218,8 +218,8 @@ static int __igt_lmem_pages_migrate(struct intel_gt *gt,
 		if (rq) {
 			err = dma_resv_reserve_fences(obj->base.resv, 1);
 			if (!err)
-				dma_resv_add_excl_fence(obj->base.resv,
-							&rq->fence);
+				dma_resv_add_fence(obj->base.resv, &rq->fence,
+						   DMA_RESV_USAGE_WRITE);
 			i915_gem_object_set_moving_fence(obj, &rq->fence);
 			i915_request_put(rq);
 		}
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index a132e241c3ee..3a6e3f6d239f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -1220,7 +1220,8 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 					  expand32(POISON_INUSE), &rq);
 	i915_gem_object_unpin_pages(obj);
 	if (rq) {
-		dma_resv_add_excl_fence(obj->base.resv, &rq->fence);
+		dma_resv_add_fence(obj->base.resv, &rq->fence,
+				   DMA_RESV_USAGE_WRITE);
 		i915_gem_object_set_moving_fence(obj, &rq->fence);
 		i915_request_put(rq);
 	}
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index bae3423f58e8..524477d8939e 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1826,7 +1826,8 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 		}
 
 		if (fence) {
-			dma_resv_add_excl_fence(vma->obj->base.resv, fence);
+			dma_resv_add_fence(vma->obj->base.resv, fence,
+					   DMA_RESV_USAGE_WRITE);
 			obj->write_domain = I915_GEM_DOMAIN_RENDER;
 			obj->read_domains = 0;
 		}
@@ -1838,7 +1839,8 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 		}
 
 		if (fence) {
-			dma_resv_add_shared_fence(vma->obj->base.resv, fence);
+			dma_resv_add_fence(vma->obj->base.resv, fence,
+					   DMA_RESV_USAGE_READ);
 			obj->write_domain = 0;
 		}
 	}
@@ -2078,7 +2080,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm)
 		goto out_rpm;
 	}
 
-	dma_resv_add_shared_fence(obj->base.resv, fence);
+	dma_resv_add_fence(obj->base.resv, fence, DMA_RESV_USAGE_READ);
 	dma_fence_put(fence);
 
 out_rpm:
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 6114e013092b..73eb53edb8de 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -1056,7 +1056,8 @@ static int igt_lmem_write_cpu(void *arg)
 					  obj->mm.pages->sgl, I915_CACHE_NONE,
 					  true, 0xdeadbeaf, &rq);
 	if (rq) {
-		dma_resv_add_excl_fence(obj->base.resv, &rq->fence);
+		dma_resv_add_fence(obj->base.resv, &rq->fence,
+				   DMA_RESV_USAGE_WRITE);
 		i915_request_put(rq);
 	}
 
diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
index e0a11ee0e86d..0f1ca0b0db49 100644
--- a/drivers/gpu/drm/lima/lima_gem.c
+++ b/drivers/gpu/drm/lima/lima_gem.c
@@ -364,10 +364,9 @@ int lima_gem_submit(struct drm_file *file, struct lima_submit *submit)
 	fence = lima_sched_context_queue_task(submit->task);
 
 	for (i = 0; i < submit->nr_bos; i++) {
-		if (submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE)
-			dma_resv_add_excl_fence(lima_bo_resv(bos[i]), fence);
-		else
-			dma_resv_add_shared_fence(lima_bo_resv(bos[i]), fence);
+		dma_resv_add_fence(lima_bo_resv(bos[i]), fence,
+				   submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE ?
+				   DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ);
 	}
 
 	drm_gem_unlock_reservations((struct drm_gem_object **)bos,
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3164db8be893..8d1eef914ba8 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -395,9 +395,11 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit)
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
-			dma_resv_add_excl_fence(obj->resv, submit->user_fence);
+			dma_resv_add_fence(obj->resv, submit->user_fence,
+					   DMA_RESV_USAGE_WRITE);
 		else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ)
-			dma_resv_add_shared_fence(obj->resv, submit->user_fence);
+			dma_resv_add_fence(obj->resv, submit->user_fence,
+					   DMA_RESV_USAGE_READ);
 	}
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index c6bb4dbcd735..05076e530e7d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1308,10 +1308,11 @@ nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence, bool excl
 {
 	struct dma_resv *resv = nvbo->bo.base.resv;
 
-	if (exclusive)
-		dma_resv_add_excl_fence(resv, &fence->base);
-	else if (fence)
-		dma_resv_add_shared_fence(resv, &fence->base);
+	if (!fence)
+		return;
+
+	dma_resv_add_fence(resv, &fence->base, exclusive ?
+			   DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index d5e81ccee01c..7f01dcf81fab 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -360,9 +360,11 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan,
 		dma_resv_for_each_fence(&cursor, resv,
 					dma_resv_usage_rw(exclusive),
 					fence) {
+			enum dma_resv_usage usage;
 			struct nouveau_fence *f;
 
-			if (i == 0 && dma_resv_iter_is_exclusive(&cursor))
+			usage = dma_resv_iter_usage(&cursor);
+			if (i == 0 && usage == DMA_RESV_USAGE_WRITE)
 				continue;
 
 			f = nouveau_local_fence(fence, chan->drm);
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index c34114560e49..fda5871aebe3 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -268,7 +268,7 @@ static void panfrost_attach_object_fences(struct drm_gem_object **bos,
 	int i;
 
 	for (i = 0; i < bo_count; i++)
-		dma_resv_add_excl_fence(bos[i]->resv, fence);
+		dma_resv_add_fence(bos[i]->resv, fence, DMA_RESV_USAGE_WRITE);
 }
 
 int panfrost_job_push(struct panfrost_job *job)
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index cde1e8ddaeaa..368d26da0d6a 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -429,7 +429,8 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 	list_for_each_entry(entry, &release->bos, head) {
 		bo = entry->bo;
 
-		dma_resv_add_shared_fence(bo->base.resv, &release->base);
+		dma_resv_add_fence(bo->base.resv, &release->base,
+				   DMA_RESV_USAGE_READ);
 		ttm_bo_move_to_lru_tail_unlocked(bo);
 		dma_resv_unlock(bo->base.resv);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 7ffd2e90f325..cb5c4aa45cef 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -791,8 +791,6 @@ void radeon_bo_fence(struct radeon_bo *bo, struct radeon_fence *fence,
 		return;
 	}
 
-	if (shared)
-		dma_resv_add_shared_fence(resv, &fence->base);
-	else
-		dma_resv_add_excl_fence(resv, &fence->base);
+	dma_resv_add_fence(resv, &fence->base, shared ?
+			   DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index cff05b62f3f7..d74f9eea855e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -739,7 +739,7 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 		return ret;
 	}
 
-	dma_resv_add_shared_fence(bo->base.resv, fence);
+	dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_WRITE);
 
 	ret = dma_resv_reserve_fences(bo->base.resv, 1);
 	if (unlikely(ret)) {
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 1b96b91bf81b..7a96a1db13a7 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -507,7 +507,8 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo,
 	if (ret)
 		return ret;
 
-	dma_resv_add_excl_fence(&ghost_obj->base._resv, fence);
+	dma_resv_add_fence(&ghost_obj->base._resv, fence,
+			   DMA_RESV_USAGE_WRITE);
 
 	/**
 	 * If we're not moving to fixed memory, the TTM object
@@ -561,7 +562,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 	struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type);
 	int ret = 0;
 
-	dma_resv_add_excl_fence(bo->base.resv, fence);
+	dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_WRITE);
 	if (!evict)
 		ret = ttm_bo_move_to_ghost(bo, fence, man->use_tt);
 	else if (!from->use_tt && pipeline)
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 789c645f004e..0eb995d25df1 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -154,10 +154,8 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
 
-		if (entry->num_shared)
-			dma_resv_add_shared_fence(bo->base.resv, fence);
-		else
-			dma_resv_add_excl_fence(bo->base.resv, fence);
+		dma_resv_add_fence(bo->base.resv, fence, entry->num_shared ?
+				   DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE);
 		ttm_bo_move_to_lru_tail_unlocked(bo);
 		dma_resv_unlock(bo->base.resv);
 	}
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 961812d33827..2352e9640922 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -550,8 +550,8 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv,
 
 	for (i = 0; i < job->bo_count; i++) {
 		/* XXX: Use shared fences for read-only objects. */
-		dma_resv_add_excl_fence(job->bo[i]->resv,
-					job->done_fence);
+		dma_resv_add_fence(job->bo[i]->resv, job->done_fence,
+				   DMA_RESV_USAGE_WRITE);
 	}
 
 	drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 594bd6bb00d2..38550317e025 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -546,7 +546,7 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno)
 		bo = to_vc4_bo(&exec->bo[i]->base);
 		bo->seqno = seqno;
 
-		dma_resv_add_shared_fence(bo->base.base.resv, exec->fence);
+		dma_resv_add_fence(bo->base.base.resv, exec->fence);
 	}
 
 	list_for_each_entry(bo, &exec->unref_list, unref_head) {
diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c
index 91fc4940c65a..c2a879734d40 100644
--- a/drivers/gpu/drm/vgem/vgem_fence.c
+++ b/drivers/gpu/drm/vgem/vgem_fence.c
@@ -161,12 +161,9 @@ int vgem_fence_attach_ioctl(struct drm_device *dev,
 	/* Expose the fence via the dma-buf */
 	dma_resv_lock(resv, NULL);
 	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);
-	}
+	if (!ret)
+		dma_resv_add_fence(resv, fence, arg->flags & VGEM_FENCE_WRITE ?
+				   DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ);
 	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 1820ca6cf673..580a78809836 100644
--- a/drivers/gpu/drm/virtio/virtgpu_gem.c
+++ b/drivers/gpu/drm/virtio/virtgpu_gem.c
@@ -250,7 +250,8 @@ void virtio_gpu_array_add_fence(struct virtio_gpu_object_array *objs,
 	int i;
 
 	for (i = 0; i < objs->nents; i++)
-		dma_resv_add_excl_fence(objs->objs[i]->resv, fence);
+		dma_resv_add_fence(objs->objs[i]->resv, fence,
+				   DMA_RESV_USAGE_WRITE);
 }
 
 void virtio_gpu_array_put_free(struct virtio_gpu_object_array *objs)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index b96884f7d03d..bec50223efe5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -758,7 +758,8 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo,
 
 	ret = dma_resv_reserve_fences(bo->base.resv, 1);
 	if (!ret)
-		dma_resv_add_excl_fence(bo->base.resv, &fence->base);
+		dma_resv_add_fence(bo->base.resv, &fence->base,
+				   DMA_RESV_USAGE_WRITE);
 	else
 		/* Last resort fallback when we are OOM */
 		dma_fence_wait(&fence->base, false);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index a297397743a2..71731796c8c3 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -393,15 +393,15 @@ struct dma_buf {
 	 * e.g. exposed in `Implicit Fence Poll Support`_ must follow the
 	 * below rules.
 	 *
-	 * - Drivers must add a shared fence through dma_resv_add_shared_fence()
-	 *   for anything the userspace API considers a read access. This highly
-	 *   depends upon the API and window system.
+	 * - Drivers must add a read fence through dma_resv_add_fence() with the
+	 *   DMA_RESV_USAGE_READ flag for anything the userspace API considers a
+	 *   read access. This highly depends upon the API and window system.
 	 *
-	 * - Similarly drivers must set the exclusive fence through
-	 *   dma_resv_add_excl_fence() for anything the userspace API considers
-	 *   write access.
+	 * - Similarly drivers must add a write fence through
+	 *   dma_resv_add_fence() with the DMA_RESV_USAGE_WRITE flag for
+	 *   anything the userspace API considers write access.
 	 *
-	 * - Drivers may just always set the exclusive fence, since that only
+	 * - Drivers may just always add a write fence, since that only
 	 *   causes unecessarily synchronization, but no correctness issues.
 	 *
 	 * - Some drivers only expose a synchronous userspace API with no
@@ -416,7 +416,7 @@ struct dma_buf {
 	 * Dynamic importers, see dma_buf_attachment_is_dynamic(), have
 	 * additional constraints on how they set up fences:
 	 *
-	 * - Dynamic importers must obey the exclusive fence and wait for it to
+	 * - Dynamic importers must obey the write fences and wait for them to
 	 *   signal before allowing access to the buffer's underlying storage
 	 *   through the device.
 	 *
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index 92cd8023980f..98dc5234b487 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -195,6 +195,9 @@ struct dma_resv_iter {
 	/** @fence: the currently handled fence */
 	struct dma_fence *fence;
 
+	/** @fence_usage: the usage of the current fence */
+	enum dma_resv_usage fence_usage;
+
 	/** @seq: sequence number to check for modifications */
 	unsigned int seq;
 
@@ -244,14 +247,15 @@ static inline void dma_resv_iter_end(struct dma_resv_iter *cursor)
 }
 
 /**
- * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one
+ * dma_resv_iter_usage - Return the usage of the current fence
  * @cursor: the cursor of the current position
  *
- * Returns true if the currently returned fence is the exclusive one.
+ * Returns the usage of the currently processed fence.
  */
-static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor)
+static inline enum dma_resv_usage
+dma_resv_iter_usage(struct dma_resv_iter *cursor)
 {
-	return cursor->index == 0;
+	return cursor->fence_usage;
 }
 
 /**
@@ -306,9 +310,9 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor)
 #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base)
 
 #ifdef CONFIG_DEBUG_MUTEXES
-void dma_resv_reset_shared_max(struct dma_resv *obj);
+void dma_resv_reset_max_fences(struct dma_resv *obj);
 #else
-static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {}
+static inline void dma_resv_reset_max_fences(struct dma_resv *obj) {}
 #endif
 
 /**
@@ -454,17 +458,18 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj)
  */
 static inline void dma_resv_unlock(struct dma_resv *obj)
 {
-	dma_resv_reset_shared_max(obj);
+	dma_resv_reset_max_fences(obj);
 	ww_mutex_unlock(&obj->lock);
 }
 
 void dma_resv_init(struct dma_resv *obj);
 void dma_resv_fini(struct dma_resv *obj);
 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_add_fence(struct dma_resv *obj, struct dma_fence *fence,
+			enum dma_resv_usage usage);
 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);
+			     struct dma_fence *fence,
+			     enum dma_resv_usage usage);
 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, enum dma_resv_usage usage,
-- 
cgit v1.2.3


From c35fcfa344c7544c899610dd5e512f7d630a152c Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 4 Apr 2022 12:57:30 +0200
Subject: drm/amdgpu: use DMA_RESV_USAGE_KERNEL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Wait only for kernel fences before kmap or UVD direct submission.

This also makes sure that we always wait in amdgpu_bo_kmap() even when
returning a cached pointer.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-6-christian.koenig@amd.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 10 +++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c    |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index a3cdf8a24377..5832c05ab10d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -761,6 +761,11 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 	if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
 		return -EPERM;
 
+	r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_KERNEL,
+				  false, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0)
+		return r;
+
 	kptr = amdgpu_bo_kptr(bo);
 	if (kptr) {
 		if (ptr)
@@ -768,11 +773,6 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 		return 0;
 	}
 
-	r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_WRITE,
-				  false, MAX_SCHEDULE_TIMEOUT);
-	if (r < 0)
-		return r;
-
 	r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 3654326219e0..6eac649499d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1164,7 +1164,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 
 	if (direct) {
 		r = dma_resv_wait_timeout(bo->tbo.base.resv,
-					  DMA_RESV_USAGE_WRITE, false,
+					  DMA_RESV_USAGE_KERNEL, false,
 					  msecs_to_jiffies(10));
 		if (r == 0)
 			r = -ETIMEDOUT;
-- 
cgit v1.2.3


From 8bb31587820a6e04cb613b49238b1800d1a97223 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 23 Nov 2021 11:30:35 +0100
Subject: drm/ttm: remove bo->moving
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is now handled by the DMA-buf framework in the dma_resv obj.

Also remove the workaround inside VMWGFX to update the moving fence.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-14-christian.koenig@amd.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 13 ++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c       |  5 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c       | 11 ++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c      | 11 +++++---
 drivers/gpu/drm/ttm/ttm_bo.c                     | 10 ++-----
 drivers/gpu/drm/ttm/ttm_bo_util.c                |  7 -----
 drivers/gpu/drm/ttm/ttm_bo_vm.c                  | 34 +++++++++---------------
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c         |  6 -----
 include/drm/ttm/ttm_bo_api.h                     |  2 --
 9 files changed, 39 insertions(+), 60 deletions(-)

(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 5031e26e6716..3dc5ab2764ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2447,6 +2447,8 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 		struct amdgpu_bo *bo = mem->bo;
 		uint32_t domain = mem->domain;
 		struct kfd_mem_attachment *attachment;
+		struct dma_resv_iter cursor;
+		struct dma_fence *fence;
 
 		total_size += amdgpu_bo_size(bo);
 
@@ -2461,10 +2463,13 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 				goto validate_map_fail;
 			}
 		}
-		ret = amdgpu_sync_fence(&sync_obj, bo->tbo.moving);
-		if (ret) {
-			pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
-			goto validate_map_fail;
+		dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
+					DMA_RESV_USAGE_KERNEL, fence) {
+			ret = amdgpu_sync_fence(&sync_obj, fence);
+			if (ret) {
+				pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
+				goto validate_map_fail;
+			}
 		}
 		list_for_each_entry(attachment, &mem->attachments, list) {
 			if (!attachment->is_mapped)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 5832c05ab10d..ef93abec13b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -612,9 +612,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 		if (unlikely(r))
 			goto fail_unreserve;
 
-		amdgpu_bo_fence(bo, fence, false);
-		dma_fence_put(bo->tbo.moving);
-		bo->tbo.moving = dma_fence_get(fence);
+		dma_resv_add_fence(bo->tbo.base.resv, fence,
+				   DMA_RESV_USAGE_KERNEL);
 		dma_fence_put(fence);
 	}
 	if (!bp->resv)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
index e3fbf0f10add..31913ae86de6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
@@ -74,13 +74,12 @@ static int amdgpu_vm_cpu_update(struct amdgpu_vm_update_params *p,
 {
 	unsigned int i;
 	uint64_t value;
-	int r;
+	long r;
 
-	if (vmbo->bo.tbo.moving) {
-		r = dma_fence_wait(vmbo->bo.tbo.moving, true);
-		if (r)
-			return r;
-	}
+	r = dma_resv_wait_timeout(vmbo->bo.tbo.base.resv, DMA_RESV_USAGE_KERNEL,
+				  true, MAX_SCHEDULE_TIMEOUT);
+	if (r < 0)
+		return r;
 
 	pe += (unsigned long)amdgpu_bo_kptr(&vmbo->bo);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index dbb551762805..bdb44cee19d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -204,14 +204,19 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p,
 	struct amdgpu_bo *bo = &vmbo->bo;
 	enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE
 		: AMDGPU_IB_POOL_DELAYED;
+	struct dma_resv_iter cursor;
 	unsigned int i, ndw, nptes;
+	struct dma_fence *fence;
 	uint64_t *pte;
 	int r;
 
 	/* Wait for PD/PT moves to be completed */
-	r = amdgpu_sync_fence(&p->job->sync, bo->tbo.moving);
-	if (r)
-		return r;
+	dma_resv_for_each_fence(&cursor, bo->tbo.base.resv,
+				DMA_RESV_USAGE_KERNEL, fence) {
+		r = amdgpu_sync_fence(&p->job->sync, fence);
+		if (r)
+			return r;
+	}
 
 	do {
 		ndw = p->num_dw_left;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 360f980c7e10..015a94f766de 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -418,7 +418,6 @@ static void ttm_bo_release(struct kref *kref)
 	dma_resv_unlock(bo->base.resv);
 
 	atomic_dec(&ttm_glob.bo_count);
-	dma_fence_put(bo->moving);
 	bo->destroy(bo);
 }
 
@@ -714,9 +713,8 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo)
 EXPORT_SYMBOL(ttm_bo_unpin);
 
 /*
- * Add the last move fence to the BO and reserve a new shared slot. We only use
- * a shared slot to avoid unecessary sync and rely on the subsequent bo move to
- * either stall or use an exclusive fence respectively set bo->moving.
+ * Add the last move fence to the BO as kernel dependency and reserve a new
+ * fence slot.
  */
 static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 				 struct ttm_resource_manager *man,
@@ -746,9 +744,6 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 		dma_fence_put(fence);
 		return ret;
 	}
-
-	dma_fence_put(bo->moving);
-	bo->moving = fence;
 	return 0;
 }
 
@@ -951,7 +946,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev,
 	bo->bdev = bdev;
 	bo->type = type;
 	bo->page_alignment = page_alignment;
-	bo->moving = NULL;
 	bo->pin_count = 0;
 	bo->sg = sg;
 	bo->bulk_move = NULL;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 99deb45894f4..bc5190340b9c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -228,7 +228,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 
 	atomic_inc(&ttm_glob.bo_count);
 	INIT_LIST_HEAD(&fbo->base.ddestroy);
-	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
 
 	kref_init(&fbo->base.kref);
@@ -500,9 +499,6 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo,
 	 * operation has completed.
 	 */
 
-	dma_fence_put(bo->moving);
-	bo->moving = dma_fence_get(fence);
-
 	ret = ttm_buffer_object_transfer(bo, &ghost_obj);
 	if (ret)
 		return ret;
@@ -546,9 +542,6 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo,
 	spin_unlock(&from->move_lock);
 
 	ttm_resource_free(bo, &bo->resource);
-
-	dma_fence_put(bo->moving);
-	bo->moving = dma_fence_get(fence);
 }
 
 int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 08ba083a80d2..5b324f245265 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -46,17 +46,13 @@
 static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_fault *vmf)
 {
-	vm_fault_t ret = 0;
-	int err = 0;
-
-	if (likely(!bo->moving))
-		goto out_unlock;
+	long err = 0;
 
 	/*
 	 * Quick non-stalling check for idle.
 	 */
-	if (dma_fence_is_signaled(bo->moving))
-		goto out_clear;
+	if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_KERNEL))
+		return 0;
 
 	/*
 	 * If possible, avoid waiting for GPU with mmap_lock
@@ -64,34 +60,30 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 	 * is the first attempt.
 	 */
 	if (fault_flag_allow_retry_first(vmf->flags)) {
-		ret = VM_FAULT_RETRY;
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
-			goto out_unlock;
+			return VM_FAULT_RETRY;
 
 		ttm_bo_get(bo);
 		mmap_read_unlock(vmf->vma->vm_mm);
-		(void) dma_fence_wait(bo->moving, true);
+		(void)dma_resv_wait_timeout(bo->base.resv,
+					    DMA_RESV_USAGE_KERNEL, true,
+					    MAX_SCHEDULE_TIMEOUT);
 		dma_resv_unlock(bo->base.resv);
 		ttm_bo_put(bo);
-		goto out_unlock;
+		return VM_FAULT_RETRY;
 	}
 
 	/*
 	 * Ordinary wait.
 	 */
-	err = dma_fence_wait(bo->moving, true);
-	if (unlikely(err != 0)) {
-		ret = (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
+	err = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_KERNEL, true,
+				    MAX_SCHEDULE_TIMEOUT);
+	if (unlikely(err < 0)) {
+		return (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
 			VM_FAULT_NOPAGE;
-		goto out_unlock;
 	}
 
-out_clear:
-	dma_fence_put(bo->moving);
-	bo->moving = NULL;
-
-out_unlock:
-	return ret;
+	return 0;
 }
 
 static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index a84d1d5628d0..a7d62a4eb47b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1161,12 +1161,6 @@ int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start,
 		*num_prefault = __KERNEL_DIV_ROUND_UP(last_cleaned - res_start,
 						      PAGE_SIZE);
 		vmw_bo_fence_single(bo, NULL);
-		if (bo->moving)
-			dma_fence_put(bo->moving);
-
-		return dma_resv_get_singleton(bo->base.resv,
-					      DMA_RESV_USAGE_WRITE,
-					      &bo->moving);
 	}
 
 	return 0;
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index c76932b68a33..2d524f8b0802 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -94,7 +94,6 @@ struct ttm_tt;
  * @deleted: True if the object is only a zombie and already deleted.
  * @ddestroy: List head for the delayed destroy list.
  * @swap: List head for swap LRU list.
- * @moving: Fence set when BO is moving
  * @offset: The current GPU offset, which can have different meanings
  * depending on the memory type. For SYSTEM type memory, it should be 0.
  * @cur_placement: Hint of current placement.
@@ -147,7 +146,6 @@ struct ttm_buffer_object {
 	 * Members protected by a bo reservation.
 	 */
 
-	struct dma_fence *moving;
 	unsigned priority;
 	unsigned pin_count;
 
-- 
cgit v1.2.3