[Intel-gfx] [PATCH 4/5] drm/i915/gem: Build the reloc request first

[Chris Wilson]

If we get interrupted in the middle of chaining up the relocation
entries, we will fail to submit the relocation batch. However, we will
report having already completed some of the relocations, and so the
reloc.presumed_offset will no longer match the batch contents, causing
confusion and invalid future batches. If we build the relocation request
packet first, we can always emit as far as we get up in the relocation
chain.

Fixes: 0e97fbb08055 ("drm/i915/gem: Use a single chained reloc batches for a single execbuf")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 51 ++++++++++---------
 .../i915/gem/selftests/i915_gem_execbuffer.c  |  8 +--
 2 files changed, 31 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 59e1856c99fc..489960ebe608 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1021,11 +1021,27 @@ static unsigned int reloc_bb_flags(const struct reloc_cache *cache)
 	return cache->gen > 5 ? 0 : I915_DISPATCH_SECURE;
 }
 
-static int reloc_gpu_flush(struct reloc_cache *cache)
+static int reloc_gpu_emit(struct reloc_cache *cache)
 {
 	struct i915_request *rq = cache->rq;
 	int err;
 
+	err = 0;
+	if (rq->engine->emit_init_breadcrumb)
+		err = rq->engine->emit_init_breadcrumb(rq);
+	if (!err)
+		err = rq->engine->emit_bb_start(rq,
+						rq->batch->node.start,
+						PAGE_SIZE,
+						reloc_bb_flags(cache));
+
+	return err;
+}
+
+static void reloc_gpu_flush(struct reloc_cache *cache)
+{
+	struct i915_request *rq = cache->rq;
+
 	if (cache->rq_vma) {
 		struct drm_i915_gem_object *obj = cache->rq_vma->obj;
 
@@ -1037,21 +1053,8 @@ static int reloc_gpu_flush(struct reloc_cache *cache)
 		i915_gem_object_unpin_map(obj);
 	}
 
-	err = 0;
-	if (rq->engine->emit_init_breadcrumb)
-		err = rq->engine->emit_init_breadcrumb(rq);
-	if (!err)
-		err = rq->engine->emit_bb_start(rq,
-						rq->batch->node.start,
-						PAGE_SIZE,
-						reloc_bb_flags(cache));
-	if (err)
-		i915_request_set_error_once(rq, err);
-
 	intel_gt_chipset_flush(rq->engine->gt);
 	i915_request_add(rq);
-
-	return err;
 }
 
 static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
@@ -1139,7 +1142,7 @@ __reloc_gpu_alloc(struct i915_execbuffer *eb, struct intel_engine_cs *engine)
 		err = i915_vma_move_to_active(batch, rq, 0);
 	i915_vma_unlock(batch);
 	if (err)
-		goto skip_request;
+		goto err_request;
 
 	rq->batch = batch;
 	i915_vma_unpin(batch);
@@ -1152,8 +1155,6 @@ __reloc_gpu_alloc(struct i915_execbuffer *eb, struct intel_engine_cs *engine)
 	/* Return with batch mapping (cmd) still pinned */
 	goto out_pool;
 
-skip_request:
-	i915_request_set_error_once(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
@@ -1186,10 +1187,8 @@ static u32 *reloc_batch_grow(struct i915_execbuffer *eb,
 	if (unlikely(cache->rq_size + len >
 		     PAGE_SIZE / sizeof(u32) - RELOC_TAIL)) {
 		err = reloc_gpu_chain(cache);
-		if (unlikely(err)) {
-			i915_request_set_error_once(cache->rq, err);
+		if (unlikely(err))
 			return ERR_PTR(err);
-		}
 	}
 
 	GEM_BUG_ON(cache->rq_size + len >= PAGE_SIZE  / sizeof(u32));
@@ -1571,23 +1570,25 @@ static int reloc_gpu_alloc(struct i915_execbuffer *eb)
 static int reloc_gpu(struct i915_execbuffer *eb)
 {
 	struct eb_vma *ev;
-	int flush, err;
+	int err;
 
 	err = reloc_gpu_alloc(eb);
 	if (err)
 		return err;
 	GEM_BUG_ON(!eb->reloc_cache.rq);
 
+	err = reloc_gpu_emit(&eb->reloc_cache);
+	if (err)
+		goto out;
+
 	list_for_each_entry(ev, &eb->relocs, reloc_link) {
 		err = eb_relocate_vma(eb, ev);
 		if (err)
-			goto out;
+			break;
 	}
 
 out:
-	flush = reloc_gpu_flush(&eb->reloc_cache);
-	if (!err)
-		err = flush;
+	reloc_gpu_flush(&eb->reloc_cache);
 	return err;
 }
 
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 50fe22d87ae1..faed6480a792 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -40,6 +40,10 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 	if (err)
 		goto unpin_vma;
 
+	err = reloc_gpu_emit(&eb->reloc_cache);
+	if (err)
+		goto unpin_vma;
+
 	/* 8-Byte aligned */
 	err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0);
 	if (err)
@@ -64,9 +68,7 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb,
 
 	GEM_BUG_ON(!eb->reloc_cache.rq);
 	rq = i915_request_get(eb->reloc_cache.rq);
-	err = reloc_gpu_flush(&eb->reloc_cache);
-	if (err)
-		goto put_rq;
+	reloc_gpu_flush(&eb->reloc_cache);
 
 	err = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, HZ / 2);
 	if (err) {
-- 
2.20.1