1 files changed, 282 insertions, 85 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..02b1630f513e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -26,6 +26,7 @@
 #include "i915_gem_ioctls.h"
 #include "i915_sw_fence_work.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -222,6 +223,13 @@ struct eb_vma_array {
  * the batchbuffer in trusted mode, otherwise the ioctl is rejected.
  */
 
+struct eb_fence {
+	struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	struct dma_fence *dma_fence;
+	u64 value;
+	struct dma_fence_chain *chain_fence;
+};
+
 struct i915_execbuffer {
 	struct drm_i915_private *i915; /** i915 backpointer */
 	struct drm_file *file; /** per-file lookup tables and limits */
@@ -281,6 +289,9 @@ struct i915_execbuffer {
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
 	struct eb_vma_array *array;
+
+	struct eb_fence *fences;
+	unsigned long num_fences;
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -1622,7 +1633,8 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
-	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
+	if (!(exec->flags & (I915_EXEC_FENCE_ARRAY |
+			     I915_EXEC_USE_EXTENSIONS))) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
 			return -EINVAL;
 	}
@@ -2201,107 +2213,241 @@ eb_pin_engine(struct i915_execbuffer *eb,
 }
 
 static void
-__free_fence_array(struct drm_syncobj **fences, unsigned int n)
+__free_fence_array(struct eb_fence *fences, unsigned int n)
 {
-	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+	while (n--) {
+		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
+		dma_fence_put(fences[n].dma_fence);
+		kfree(fences[n].chain_fence);
+	}
 	kvfree(fences);
 }
 
-static struct drm_syncobj **
-get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_file *file)
+static int
+add_timeline_fence_array(struct i915_execbuffer *eb,
+			 const struct drm_i915_gem_execbuffer_ext_timeline_fences *timeline_fences)
 {
-	const unsigned long nfences = args->num_cliprects;
-	struct drm_i915_gem_exec_fence __user *user;
-	struct drm_syncobj **fences;
-	unsigned long n;
-	int err;
+	struct drm_i915_gem_exec_fence __user *user_fences;
+	u64 __user *user_values;
+	struct eb_fence *f;
+	u64 nfences;
+	int err = 0;
 
-	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
-		return NULL;
+	nfences = timeline_fences->fence_count;
+	if (!nfences)
+		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
-			    ULONG_MAX / sizeof(*user),
-			    SIZE_MAX / sizeof(*fences)))
-		return ERR_PTR(-EINVAL);
+			    ULONG_MAX / sizeof(*user_fences),
+			    SIZE_MAX / sizeof(*f)) - eb->num_fences)
+		return -EINVAL;
 
-	user = u64_to_user_ptr(args->cliprects_ptr);
-	if (!access_ok(user, nfences * sizeof(*user)))
-		return ERR_PTR(-EFAULT);
+	user_fences = u64_to_user_ptr(timeline_fences->handles_ptr);
+	if (!access_ok(user_fences, nfences * sizeof(*user_fences)))
+		return -EFAULT;
+
+	user_values = u64_to_user_ptr(timeline_fences->values_ptr);
+	if (!access_ok(user_values, nfences * sizeof(*user_values)))
+		return -EFAULT;
 
-	fences = kvmalloc_array(nfences, sizeof(*fences),
-				__GFP_NOWARN | GFP_KERNEL);
-	if (!fences)
-		return ERR_PTR(-ENOMEM);
+	f = krealloc(eb->fences,
+		     (eb->num_fences + nfences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
 
-	for (n = 0; n < nfences; n++) {
-		struct drm_i915_gem_exec_fence fence;
+	BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
+		     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
+
+	while (nfences--) {
+		struct drm_i915_gem_exec_fence user_fence;
 		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+		u64 point;
+
+		if (__copy_from_user(&user_fence,
+				     user_fences++,
+				     sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		if (__get_user(point, user_values++))
+			return -EFAULT;
 
-		if (__copy_from_user(&fence, user++, sizeof(fence))) {
-			err = -EFAULT;
-			goto err;
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
+		if (!syncobj) {
+			DRM_DEBUG("Invalid syncobj handle provided\n");
+			return -ENOENT;
 		}
 
-		if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) {
-			err = -EINVAL;
-			goto err;
+		fence = drm_syncobj_fence_get(syncobj);
+
+		if (!fence && user_fence.flags &&
+		    !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle has no fence\n");
+			drm_syncobj_put(syncobj);
+			return -EINVAL;
 		}
 
-		syncobj = drm_syncobj_find(file, fence.handle);
+		if (fence)
+			err = dma_fence_chain_find_seqno(&fence, point);
+
+		if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle missing requested point %llu\n", point);
+			drm_syncobj_put(syncobj);
+			return err;
+		}
+
+		/*
+		 * A point might have been signaled already and
+		 * garbage collected from the timeline. In this case
+		 * just ignore the point and carry on.
+		 */
+		if (!fence && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			drm_syncobj_put(syncobj);
+			continue;
+		}
+
+		/*
+		 * For timeline syncobjs we need to preallocate chains for
+		 * later signaling.
+		 */
+		if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) {
+			/*
+			 * Waiting and signaling the same point (when point !=
+			 * 0) would break the timeline.
+			 */
+			if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+				DRM_DEBUG("Trying to wait & signal the same timeline point.\n");
+				dma_fence_put(fence);
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
+
+			f->chain_fence =
+				kmalloc(sizeof(*f->chain_fence),
+					GFP_KERNEL);
+			if (!f->chain_fence) {
+				drm_syncobj_put(syncobj);
+				dma_fence_put(fence);
+				return -ENOMEM;
+			}
+		} else {
+			f->chain_fence = NULL;
+		}
+
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = point;
+		f++;
+		eb->num_fences++;
+	}
+
+	return 0;
+}
+
+static int add_fence_array(struct i915_execbuffer *eb)
+{
+	struct drm_i915_gem_execbuffer2 *args = eb->args;
+	struct drm_i915_gem_exec_fence __user *user;
+	unsigned long num_fences = args->num_cliprects;
+	struct eb_fence *f;
+
+	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+		return 0;
+
+	if (!num_fences)
+		return 0;
+
+	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
+	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
+	if (num_fences > min_t(unsigned long,
+			       ULONG_MAX / sizeof(*user),
+			       SIZE_MAX / sizeof(*f) - eb->num_fences))
+		return -EINVAL;
+
+	user = u64_to_user_ptr(args->cliprects_ptr);
+	if (!access_ok(user, num_fences * sizeof(*user)))
+		return -EFAULT;
+
+	f = krealloc(eb->fences,
+		     (eb->num_fences + num_fences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
+	while (num_fences--) {
+		struct drm_i915_gem_exec_fence user_fence;
+		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+
+		if (__copy_from_user(&user_fence, user++, sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
-			err = -ENOENT;
-			goto err;
+			return -ENOENT;
+		}
+
+		if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+			fence = drm_syncobj_fence_get(syncobj);
+			if (!fence) {
+				DRM_DEBUG("Syncobj handle has no fence\n");
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
 		}
 
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = 0;
+		f->chain_fence = NULL;
+		f++;
+		eb->num_fences++;
 	}
 
-	return fences;
-
-err:
-	__free_fence_array(fences, n);
-	return ERR_PTR(err);
+	return 0;
 }
 
-static void
-put_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_syncobj **fences)
+static void put_fence_array(struct eb_fence *fences, int num_fences)
 {
 	if (fences)
-		__free_fence_array(fences, args->num_cliprects);
+		__free_fence_array(fences, num_fences);
 }
 
 static int
-await_fence_array(struct i915_execbuffer *eb,
-		  struct drm_syncobj **fences)
+await_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
-		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
-		if (!(flags & I915_EXEC_FENCE_WAIT))
-			continue;
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 
-		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!eb->fences[n].dma_fence)
+			continue;
 
-		err = i915_request_await_dma_fence(eb->request, fence);
-		dma_fence_put(fence);
+		err = i915_request_await_dma_fence(eb->request,
+						   eb->fences[n].dma_fence);
 		if (err < 0)
 			return err;
 	}
@@ -2309,26 +2455,47 @@ await_fence_array(struct i915_execbuffer *eb,
 	return 0;
 }
 
-static void
-signal_fence_array(struct i915_execbuffer *eb,
-		   struct drm_syncobj **fences)
+static void signal_fence_array(const struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
-		drm_syncobj_replace_fence(syncobj, fence);
+		if (eb->fences[n].chain_fence) {
+			drm_syncobj_add_point(syncobj,
+					      eb->fences[n].chain_fence,
+					      fence,
+					      eb->fences[n].value);
+			/*
+			 * The chain's ownership is transferred to the
+			 * timeline.
+			 */
+			eb->fences[n].chain_fence = NULL;
+		} else {
+			drm_syncobj_replace_fence(syncobj, fence);
+		}
 	}
 }
 
+static int
+parse_timeline_fences(struct i915_user_extension __user *ext, void *data)
+{
+	struct i915_execbuffer *eb = data;
+	struct drm_i915_gem_execbuffer_ext_timeline_fences timeline_fences;
+
+	if (copy_from_user(&timeline_fences, ext, sizeof(timeline_fences)))
+		return -EFAULT;
+
+	return add_timeline_fence_array(eb, &timeline_fences);
+}
+
 static void retire_requests(struct intel_timeline *tl, struct i915_request *end)
 {
 	struct i915_request *rq, *rn;
@@ -2370,12 +2537,37 @@ static void eb_request_add(struct i915_execbuffer *eb)
 	mutex_unlock(&tl->mutex);
 }
 
+static const i915_user_extension_fn execbuf_extensions[] = {
+	[DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences,
+};
+
+static int
+parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
+			  struct i915_execbuffer *eb)
+{
+	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
+		return 0;
+
+	/* The execbuf2 extension mechanism reuses cliprects_ptr. So we cannot
+	 * have another flag also using it at the same time.
+	 */
+	if (eb->args->flags & I915_EXEC_FENCE_ARRAY)
+		return -EINVAL;
+
+	if (args->num_cliprects != 0)
+		return -EINVAL;
+
+	return i915_user_extensions(u64_to_user_ptr(args->cliprects_ptr),
+				    execbuf_extensions,
+				    ARRAY_SIZE(execbuf_extensions),
+				    eb);
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec,
-		       struct drm_syncobj **fences)
+		       struct drm_i915_gem_exec_object2 *exec)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
@@ -2405,6 +2597,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.batch_len = args->batch_len;
 	eb.trampoline = NULL;
 
+	eb.fences = NULL;
+	eb.num_fences = 0;
+
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
 		if (INTEL_GEN(i915) >= 11)
@@ -2422,14 +2617,24 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
+	err = parse_execbuf2_extensions(args, &eb);
+	if (err)
+		goto err_ext;
+
+	err = add_fence_array(&eb);
+	if (err)
+		goto err_ext;
+
 #define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
 	if (args->flags & IN_FENCES) {
 		if ((args->flags & IN_FENCES) == IN_FENCES)
 			return -EINVAL;
 
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!in_fence)
-			return -EINVAL;
+		if (!in_fence) {
+			err = -EINVAL;
+			goto err_ext;
+		}
 	}
 #undef IN_FENCES
 
@@ -2539,8 +2744,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (fences) {
-		err = await_fence_array(&eb, fences);
+	if (eb.fences) {
+		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
 	}
@@ -2571,8 +2776,8 @@ err_request:
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (fences)
-		signal_fence_array(&eb, fences);
+	if (eb.fences)
+		signal_fence_array(&eb);
 
 	if (out_fence) {
 		if (err == 0) {
@@ -2605,6 +2810,8 @@ err_out_fence:
 		put_unused_fd(out_fence_fd);
 err_in_fence:
 	dma_fence_put(in_fence);
+err_ext:
+	put_fence_array(eb.fences, eb.num_fences);
 	return err;
 }
 
@@ -2699,7 +2906,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 			exec2_list[i].flags = 0;
 	}
 
-	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL);
+	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list);
 	if (exec2.flags & __EXEC_HAS_RELOC) {
 		struct drm_i915_gem_exec_object __user *user_exec_list =
 			u64_to_user_ptr(args->buffers_ptr);
@@ -2731,7 +2938,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list;
-	struct drm_syncobj **fences = NULL;
 	const size_t count = args->buffer_count;
 	int err;
 
@@ -2759,15 +2965,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	if (args->flags & I915_EXEC_FENCE_ARRAY) {
-		fences = get_fence_array(args, file);
-		if (IS_ERR(fences)) {
-			kvfree(exec2_list);
-			return PTR_ERR(fences);
-		}
-	}
-
-	err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences);
+	err = i915_gem_do_execbuffer(dev, file, args, exec2_list);
 
 	/*
 	 * Now that we have begun execution of the batchbuffer, we ignore
@@ -2808,7 +3006,6 @@ end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
-	put_fence_array(args, fences);
 	kvfree(exec2_list);
 	return err;
 }