[PATCH 5/7] drm/i915: Remove locking from i915_gem_object_prepare_read/write

Maarten Lankhorst maarten.lankhorst at linux.intel.com
Mon Jan 20 13:14:24 UTC 2020


Execbuffer submission will perform its own WW locking, and we
cannot rely on the implicit lock there.

This also makes it clear that the GVT code will get a lockdep splat when
multiple batchbuffer shadows need to be performed in the same instance,
fix that up.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_domain.c    | 20 ++++++-------------
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 13 ++++++++++--
 drivers/gpu/drm/i915/gem/i915_gem_object.h    |  1 -
 .../gpu/drm/i915/gem/selftests/huge_pages.c   |  5 ++++-
 .../i915/gem/selftests/i915_gem_coherency.c   | 14 +++++++++----
 .../drm/i915/gem/selftests/i915_gem_context.c | 12 ++++++++---
 drivers/gpu/drm/i915/gt/intel_renderstate.c   |  5 ++++-
 drivers/gpu/drm/i915/gvt/cmd_parser.c         |  9 ++++++++-
 drivers/gpu/drm/i915/i915_gem.c               |  8 +++++++-
 9 files changed, 59 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index f4602faa8db9..e9d3b587f562 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -581,19 +581,17 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_has_struct_page(obj))
 		return -ENODEV;
 
-	ret = i915_gem_object_lock_interruptible(obj, NULL);
-	if (ret)
-		return ret;
+	assert_object_held(obj);
 
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE,
 				   MAX_SCHEDULE_TIMEOUT);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	ret = i915_gem_object_pin_pages(obj);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ ||
 	    !static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -621,8 +619,6 @@ int i915_gem_object_prepare_read(struct drm_i915_gem_object *obj,
 
 err_unpin:
 	i915_gem_object_unpin_pages(obj);
-err_unlock:
-	i915_gem_object_unlock(obj);
 	return ret;
 }
 
@@ -635,20 +631,18 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_has_struct_page(obj))
 		return -ENODEV;
 
-	ret = i915_gem_object_lock_interruptible(obj, NULL);
-	if (ret)
-		return ret;
+	assert_object_held(obj);
 
 	ret = i915_gem_object_wait(obj,
 				   I915_WAIT_INTERRUPTIBLE |
 				   I915_WAIT_ALL,
 				   MAX_SCHEDULE_TIMEOUT);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	ret = i915_gem_object_pin_pages(obj);
 	if (ret)
-		goto err_unlock;
+		return ret;
 
 	if (obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE ||
 	    !static_cpu_has(X86_FEATURE_CLFLUSH)) {
@@ -685,7 +679,5 @@ int i915_gem_object_prepare_write(struct drm_i915_gem_object *obj,
 
 err_unpin:
 	i915_gem_object_unpin_pages(obj);
-err_unlock:
-	i915_gem_object_unlock(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 59d75d85f47f..207ba465aef3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -934,11 +934,14 @@ static void reloc_cache_reset(struct reloc_cache *cache)
 
 	vaddr = unmask_page(cache->vaddr);
 	if (cache->vaddr & KMAP) {
+		struct drm_i915_gem_object *obj =
+			(struct drm_i915_gem_object *)cache->node.mm;
 		if (cache->vaddr & CLFLUSH_AFTER)
 			mb();
 
 		kunmap_atomic(vaddr);
-		i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm);
+		i915_gem_object_finish_access(obj);
+		i915_gem_object_unlock(obj);
 	} else {
 		struct i915_ggtt *ggtt = cache_to_ggtt(cache);
 
@@ -973,10 +976,16 @@ static void *reloc_kmap(struct drm_i915_gem_object *obj,
 		unsigned int flushes;
 		int err;
 
-		err = i915_gem_object_prepare_write(obj, &flushes);
+		err = i915_gem_object_lock_interruptible(obj, NULL);
 		if (err)
 			return ERR_PTR(err);
 
+		err = i915_gem_object_prepare_write(obj, &flushes);
+		if (err) {
+			i915_gem_object_unlock(obj);
+			return ERR_PTR(err);
+		}
+
 		BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);
 		BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index f0a293c1fc82..c68b85775a9e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -428,7 +428,6 @@ static inline void
 i915_gem_object_finish_access(struct drm_i915_gem_object *obj)
 {
 	i915_gem_object_unpin_pages(obj);
-	i915_gem_object_unlock(obj);
 }
 
 static inline struct intel_engine_cs *
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index e5f98c14052d..8773b7e0834f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -991,9 +991,10 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	unsigned long n;
 	int err;
 
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_prepare_read(obj, &needs_flush);
 	if (err)
-		return err;
+		goto err_unlock;
 
 	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
 		u32 *ptr = kmap_atomic(i915_gem_object_get_page(obj, n));
@@ -1013,6 +1014,8 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	}
 
 	i915_gem_object_finish_access(obj);
+err_unlock:
+	i915_gem_object_unlock(obj);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index f5a0c7b1e113..99f8466a108a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -27,9 +27,10 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
 	u32 *cpu;
 	int err;
 
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_prepare_write(ctx->obj, &needs_clflush);
 	if (err)
-		return err;
+		goto out;
 
 	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
@@ -46,7 +47,9 @@ static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
 	kunmap_atomic(map);
 	i915_gem_object_finish_access(ctx->obj);
 
-	return 0;
+out:
+	i915_gem_object_unlock(ctx->obj);
+	return err;
 }
 
 static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
@@ -57,9 +60,10 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
 	u32 *cpu;
 	int err;
 
+	i915_gem_object_lock(ctx->obj, NULL);
 	err = i915_gem_object_prepare_read(ctx->obj, &needs_clflush);
 	if (err)
-		return err;
+		goto out;
 
 	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
@@ -73,7 +77,9 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
 	kunmap_atomic(map);
 	i915_gem_object_finish_access(ctx->obj);
 
-	return 0;
+out:
+	i915_gem_object_unlock(ctx->obj);
+	return err;
 }
 
 static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 67426c20ffb1..b56ebf1b0aed 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -461,9 +461,10 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
 	unsigned int n, m, need_flush;
 	int err;
 
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_prepare_write(obj, &need_flush);
 	if (err)
-		return err;
+		goto out;
 
 	for (n = 0; n < real_page_count(obj); n++) {
 		u32 *map;
@@ -479,7 +480,9 @@ static int cpu_fill(struct drm_i915_gem_object *obj, u32 value)
 	i915_gem_object_finish_access(obj);
 	obj->read_domains = I915_GEM_DOMAIN_GTT | I915_GEM_DOMAIN_CPU;
 	obj->write_domain = 0;
-	return 0;
+out:
+	i915_gem_object_unlock(obj);
+	return err;
 }
 
 static noinline int cpu_check(struct drm_i915_gem_object *obj,
@@ -488,9 +491,10 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj,
 	unsigned int n, m, needs_flush;
 	int err;
 
+	i915_gem_object_lock(obj, NULL);
 	err = i915_gem_object_prepare_read(obj, &needs_flush);
 	if (err)
-		return err;
+		goto out_unlock;
 
 	for (n = 0; n < real_page_count(obj); n++) {
 		u32 *map;
@@ -527,6 +531,8 @@ static noinline int cpu_check(struct drm_i915_gem_object *obj,
 	}
 
 	i915_gem_object_finish_access(obj);
+out_unlock:
+	i915_gem_object_unlock(obj);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index 5954ecc3207f..fff61e86cfbf 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -74,9 +74,10 @@ static int render_state_setup(struct intel_renderstate *so,
 	u32 *d;
 	int ret;
 
+	i915_gem_object_lock(so->vma->obj, NULL);
 	ret = i915_gem_object_prepare_write(so->vma->obj, &needs_clflush);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	d = kmap_atomic(i915_gem_object_get_dirty_page(so->vma->obj, 0));
 
@@ -157,6 +158,8 @@ static int render_state_setup(struct intel_renderstate *so,
 	ret = 0;
 out:
 	i915_gem_object_finish_access(so->vma->obj);
+out_unlock:
+	i915_gem_object_unlock(so->vma->obj);
 	return ret;
 
 err:
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index a54d96a144be..5d17ee2bdb9b 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1865,10 +1865,14 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 		goto err_free_bb;
 	}
 
-	ret = i915_gem_object_prepare_write(bb->obj, &bb->clflush);
+	ret = i915_gem_object_lock_interruptible(bb->obj, NULL);
 	if (ret)
 		goto err_free_obj;
 
+	ret = i915_gem_object_prepare_write(bb->obj, &bb->clflush);
+	if (ret)
+		goto err_unlock;
+
 	bb->va = i915_gem_object_pin_map(bb->obj, I915_MAP_WB);
 	if (IS_ERR(bb->va)) {
 		ret = PTR_ERR(bb->va);
@@ -1893,6 +1897,7 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	if (ret)
 		goto err_unmap;
 
+	i915_gem_object_unlock(bb->obj);
 	INIT_LIST_HEAD(&bb->list);
 	list_add(&bb->list, &s->workload->shadow_bb);
 
@@ -1919,6 +1924,8 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	i915_gem_object_unpin_map(bb->obj);
 err_finish_shmem_access:
 	i915_gem_object_finish_access(bb->obj);
+err_unlock:
+	i915_gem_object_unlock(bb->obj);
 err_free_obj:
 	i915_gem_object_put(bb->obj);
 err_free_bb:
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1e93be8b6ae6..4173db8361c9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -518,15 +518,21 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto out;
 
-	ret = i915_gem_object_pin_pages(obj);
+	ret = i915_gem_object_lock_interruptible(obj, NULL);
 	if (ret)
 		goto out;
 
+	ret = i915_gem_object_pin_pages(obj);
+	if (ret)
+		goto out_unlock;
+
 	ret = i915_gem_shmem_pread(obj, args);
 	if (ret == -EFAULT || ret == -ENODEV)
 		ret = i915_gem_gtt_pread(obj, args);
 
 	i915_gem_object_unpin_pages(obj);
+out_unlock:
+	i915_gem_object_unlock(obj);
 out:
 	i915_gem_object_put(obj);
 	return ret;
-- 
2.24.1



More information about the Intel-gfx-trybot mailing list