All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 06/11] drm/i915/gem: Lift GPU relocation allocation
Date: Thu, 28 May 2020 08:41:04 +0100	[thread overview]
Message-ID: <20200528074109.28235-6-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200528074109.28235-1-chris@chris-wilson.co.uk>

Since we have reduced the relocations paths to just use the async GPU,
we can lift the request allocation to the start of the relocations.
Knowing that we use one request for all relocations will simplify
tracking the relocation fence.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 98 ++++++++++---------
 .../i915/gem/selftests/i915_gem_execbuffer.c  |  5 +-
 2 files changed, 56 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index f50378699a19..d48f42567f75 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -900,8 +900,6 @@ eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
 
 static void eb_destroy(const struct i915_execbuffer *eb)
 {
-	GEM_BUG_ON(eb->reloc_cache.rq);
-
 	if (eb->array)
 		eb_vma_array_put(eb->array);
 
@@ -926,7 +924,6 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->has_fence = cache->gen < 4;
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
-	cache->rq = NULL;
 	cache->target = NULL;
 }
 
@@ -1026,13 +1023,9 @@ static unsigned int reloc_bb_flags(const struct reloc_cache *cache)
 
 static int reloc_gpu_flush(struct reloc_cache *cache)
 {
-	struct i915_request *rq;
+	struct i915_request *rq = cache->rq;
 	int err;
 
-	rq = fetch_and_zero(&cache->rq);
-	if (!rq)
-		return 0;
-
 	if (cache->rq_vma) {
 		struct drm_i915_gem_object *obj = cache->rq_vma->obj;
 
@@ -1081,9 +1074,8 @@ static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
 	return err;
 }
 
-static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
-			     struct intel_engine_cs *engine,
-			     unsigned int len)
+static int
+__reloc_gpu_alloc(struct i915_execbuffer *eb, struct intel_engine_cs *engine)
 {
 	struct reloc_cache *cache = &eb->reloc_cache;
 	struct intel_gt_buffer_pool_node *pool;
@@ -1173,33 +1165,14 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	return err;
 }
 
-static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
-{
-	return engine->class != VIDEO_DECODE_CLASS || !IS_GEN(engine->i915, 6);
-}
-
-static u32 *reloc_gpu(struct i915_execbuffer *eb,
-		      struct i915_vma *vma,
-		      unsigned int len)
+static u32 *reloc_batch_grow(struct i915_execbuffer *eb,
+			     struct i915_vma *vma,
+			     unsigned int len)
 {
 	struct reloc_cache *cache = &eb->reloc_cache;
 	u32 *cmd;
 	int err;
 
-	if (unlikely(!cache->rq)) {
-		struct intel_engine_cs *engine = eb->engine;
-
-		if (!reloc_can_use_engine(engine)) {
-			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
-			if (!engine)
-				return ERR_PTR(-ENODEV);
-		}
-
-		err = __reloc_gpu_alloc(eb, engine, len);
-		if (unlikely(err))
-			return ERR_PTR(err);
-	}
-
 	if (vma != cache->target) {
 		err = reloc_move_to_gpu(cache->rq, vma);
 		if (unlikely(err)) {
@@ -1257,7 +1230,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb,
 	else
 		len = 3;
 
-	batch = reloc_gpu(eb, vma, len);
+	batch = reloc_batch_grow(eb, vma, len);
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
@@ -1577,6 +1550,47 @@ static long eb_reloc_vma_validate(struct i915_execbuffer *eb, struct eb_vma *ev)
 	return required;
 }
 
+static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
+{
+	return engine->class != VIDEO_DECODE_CLASS || !IS_GEN(engine->i915, 6);
+}
+
+static int reloc_gpu_alloc(struct i915_execbuffer *eb)
+{
+	struct intel_engine_cs *engine = eb->engine;
+
+	if (!reloc_can_use_engine(engine)) {
+		engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
+		if (!engine)
+			return -ENODEV;
+	}
+
+	return __reloc_gpu_alloc(eb, engine);
+}
+
+static int reloc_gpu(struct i915_execbuffer *eb)
+{
+	struct eb_vma *ev;
+	int flush, err;
+
+	err = reloc_gpu_alloc(eb);
+	if (err)
+		return err;
+	GEM_BUG_ON(!eb->reloc_cache.rq);
+
+	list_for_each_entry(ev, &eb->relocs, reloc_link) {
+		err = eb_relocate_vma(eb, ev);
+		if (err)
+			goto out;
+	}
+
+out:
+	flush = reloc_gpu_flush(&eb->reloc_cache);
+	if (!err)
+		err = flush;
+	return err;
+}
+
 static int eb_relocate(struct i915_execbuffer *eb)
 {
 	int err;
@@ -1594,7 +1608,6 @@ static int eb_relocate(struct i915_execbuffer *eb)
 	/* The objects are in their final locations, apply the relocations. */
 	if (eb->args->flags & __EXEC_HAS_RELOC) {
 		struct eb_vma *ev, *en;
-		int flush;
 
 		list_for_each_entry_safe(ev, en, &eb->relocs, reloc_link) {
 			err = eb_reloc_vma_validate(eb, ev);
@@ -1605,18 +1618,14 @@ static int eb_relocate(struct i915_execbuffer *eb)
 				list_del_init(&ev->reloc_link);
 		}
 
-		list_for_each_entry(ev, &eb->relocs, reloc_link) {
-			err = eb_relocate_vma(eb, ev);
+		if (!list_empty(&eb->relocs)) {
+			err = reloc_gpu(eb);
 			if (err)
-				break;
+				return err;
 		}
-
-		flush = reloc_gpu_flush(&eb->reloc_cache);
-		if (!err)
-			err = flush;
 	}
 
-	return err;
+	return 0;
 }
 
 static int eb_move_to_gpu(struct i915_execbuffer *eb)
@@ -2576,9 +2585,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		batch = vma;
 	}
 
-	/* All GPU relocation batches must be submitted prior to the user rq */
-	GEM_BUG_ON(eb.reloc_cache.rq);
-
 	/* Allocate a request for this batch buffer nice and early. */
 	eb.request = i915_request_create(eb.context);
 	if (IS_ERR(eb.request)) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 57c14d3340cd..50fe22d87ae1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -36,6 +36,10 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 	if (err)
 		return err;
 
+	err = reloc_gpu_alloc(eb);
+	if (err)
+		goto unpin_vma;
+
 	/* 8-Byte aligned */
 	err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
 	if (err)
@@ -63,7 +67,6 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 	err = reloc_gpu_flush(&eb->reloc_cache);
 	if (err)
 		goto put_rq;
-	GEM_BUG_ON(eb->reloc_cache.rq);
 
 	err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, HZ / 2);
 	if (err) {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2020-05-28  7:41 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-28  7:40 [Intel-gfx] [PATCH 01/11] drm/i915/gt: Prevent timeslicing into unpreemptable requests Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 02/11] drm/i915/gt: Don't declare hangs if engine is stalled Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 03/11] drm/i915/gem: Async GPU relocations only Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 04/11] drm/i915: Add list_for_each_entry_safe_continue_reverse Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 05/11] drm/i915/gem: Separate reloc validation into an earlier step Chris Wilson
2020-05-28  7:41 ` Chris Wilson [this message]
2020-05-28  7:41 ` [Intel-gfx] [PATCH 07/11] drm/i915/gem: Add all GPU reloc awaits/signals en masse Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 08/11] drm/i915/gem: Build the reloc request first Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 09/11] dma-buf: Proxy fence, an unsignaled fence placeholder Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 10/11] drm/i915: Unpeel awaits on a proxy fence Chris Wilson
2020-05-28  7:41 ` [Intel-gfx] [PATCH 11/11] drm/i915/gem: Make relocations atomic within execbuf Chris Wilson
2020-05-28  7:54 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/11] drm/i915/gt: Prevent timeslicing into unpreemptable requests Patchwork
2020-05-28  7:55 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-05-28  8:16 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-05-28 10:38 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2020-05-28 21:15 [Intel-gfx] [PATCH 01/11] drm/i915/gt: Start timeslice on partial submission Chris Wilson
2020-05-28 21:15 ` [Intel-gfx] [PATCH 06/11] drm/i915/gem: Lift GPU relocation allocation Chris Wilson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200528074109.28235-6-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.