Backmerge tag 'v5.14-rc3' into drm-next

Linux 5.14-rc3

Daniel said we should pull the nouveau fix from fixes in here, probably
a good plan.

Signed-off-by: Dave Airlie <airlied@redhat.com>

2 files changed, 17 insertions, 214 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 8e195fa7626a..989ff064cf3a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,10 +25,8 @@
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
-#include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
-#include "i915_memcpy.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -1456,6 +1454,10 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 		int err;
 		struct intel_engine_cs *engine = eb->engine;
 
+		/* If we need to copy for the cmdparser, we will stall anyway */
+		if (eb_use_cmdparser(eb))
+			return ERR_PTR(-EWOULDBLOCK);
+
 		if (!reloc_can_use_engine(engine)) {
 			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
 			if (!engine)
@@ -2372,217 +2374,6 @@ shadow_batch_pin(struct i915_execbuffer *eb,
 	return vma;
 }
 
-struct eb_parse_work {
-	struct dma_fence_work base;
-	struct intel_engine_cs *engine;
-	struct i915_vma *batch;
-	struct i915_vma *shadow;
-	struct i915_vma *trampoline;
-	unsigned long batch_offset;
-	unsigned long batch_length;
-	unsigned long *jump_whitelist;
-	const void *batch_map;
-	void *shadow_map;
-};
-
-static int __eb_parse(struct dma_fence_work *work)
-{
-	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-	int ret;
-	bool cookie;
-
-	cookie = dma_fence_begin_signalling();
-	ret = intel_engine_cmd_parser(pw->engine,
-				      pw->batch,
-				      pw->batch_offset,
-				      pw->batch_length,
-				      pw->shadow,
-				      pw->jump_whitelist,
-				      pw->shadow_map,
-				      pw->batch_map);
-	dma_fence_end_signalling(cookie);
-
-	return ret;
-}
-
-static void __eb_parse_release(struct dma_fence_work *work)
-{
-	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-
-	if (!IS_ERR_OR_NULL(pw->jump_whitelist))
-		kfree(pw->jump_whitelist);
-
-	if (pw->batch_map)
-		i915_gem_object_unpin_map(pw->batch->obj);
-	else
-		i915_gem_object_unpin_pages(pw->batch->obj);
-
-	i915_gem_object_unpin_map(pw->shadow->obj);
-
-	if (pw->trampoline)
-		i915_active_release(&pw->trampoline->active);
-	i915_active_release(&pw->shadow->active);
-	i915_active_release(&pw->batch->active);
-}
-
-static const struct dma_fence_work_ops eb_parse_ops = {
-	.name = "eb_parse",
-	.work = __eb_parse,
-	.release = __eb_parse_release,
-};
-
-static inline int
-__parser_mark_active(struct i915_vma *vma,
-		     struct intel_timeline *tl,
-		     struct dma_fence *fence)
-{
-	struct intel_gt_buffer_pool_node *node = vma->private;
-
-	return i915_active_ref(&node->active, tl->fence_context, fence);
-}
-
-static int
-parser_mark_active(struct eb_parse_work *pw, struct intel_timeline *tl)
-{
-	int err;
-
-	mutex_lock(&tl->mutex);
-
-	err = __parser_mark_active(pw->shadow, tl, &pw->base.dma);
-	if (err)
-		goto unlock;
-
-	if (pw->trampoline) {
-		err = __parser_mark_active(pw->trampoline, tl, &pw->base.dma);
-		if (err)
-			goto unlock;
-	}
-
-unlock:
-	mutex_unlock(&tl->mutex);
-	return err;
-}
-
-static int eb_parse_pipeline(struct i915_execbuffer *eb,
-			     struct i915_vma *shadow,
-			     struct i915_vma *trampoline)
-{
-	struct eb_parse_work *pw;
-	struct drm_i915_gem_object *batch = eb->batch->vma->obj;
-	bool needs_clflush;
-	int err;
-
-	GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset));
-	GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length));
-
-	pw = kzalloc(sizeof(*pw), GFP_KERNEL);
-	if (!pw)
-		return -ENOMEM;
-
-	err = i915_active_acquire(&eb->batch->vma->active);
-	if (err)
-		goto err_free;
-
-	err = i915_active_acquire(&shadow->active);
-	if (err)
-		goto err_batch;
-
-	if (trampoline) {
-		err = i915_active_acquire(&trampoline->active);
-		if (err)
-			goto err_shadow;
-	}
-
-	pw->shadow_map = i915_gem_object_pin_map(shadow->obj, I915_MAP_WB);
-	if (IS_ERR(pw->shadow_map)) {
-		err = PTR_ERR(pw->shadow_map);
-		goto err_trampoline;
-	}
-
-	needs_clflush =
-		!(batch->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
-	pw->batch_map = ERR_PTR(-ENODEV);
-	if (needs_clflush && i915_has_memcpy_from_wc())
-		pw->batch_map = i915_gem_object_pin_map(batch, I915_MAP_WC);
-
-	if (IS_ERR(pw->batch_map)) {
-		err = i915_gem_object_pin_pages(batch);
-		if (err)
-			goto err_unmap_shadow;
-		pw->batch_map = NULL;
-	}
-
-	pw->jump_whitelist =
-		intel_engine_cmd_parser_alloc_jump_whitelist(eb->batch_len,
-							     trampoline);
-	if (IS_ERR(pw->jump_whitelist)) {
-		err = PTR_ERR(pw->jump_whitelist);
-		goto err_unmap_batch;
-	}
-
-	dma_fence_work_init(&pw->base, &eb_parse_ops);
-
-	pw->engine = eb->engine;
-	pw->batch = eb->batch->vma;
-	pw->batch_offset = eb->batch_start_offset;
-	pw->batch_length = eb->batch_len;
-	pw->shadow = shadow;
-	pw->trampoline = trampoline;
-
-	/* Mark active refs early for this worker, in case we get interrupted */
-	err = parser_mark_active(pw, eb->context->timeline);
-	if (err)
-		goto err_commit;
-
-	err = dma_resv_reserve_shared(pw->batch->resv, 1);
-	if (err)
-		goto err_commit;
-
-	err = dma_resv_reserve_shared(shadow->resv, 1);
-	if (err)
-		goto err_commit;
-
-	/* Wait for all writes (and relocs) into the batch to complete */
-	err = i915_sw_fence_await_reservation(&pw->base.chain,
-					      pw->batch->resv, NULL, false,
-					      0, I915_FENCE_GFP);
-	if (err < 0)
-		goto err_commit;
-
-	/* Keep the batch alive and unwritten as we parse */
-	dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
-
-	/* Force execution to wait for completion of the parser */
-	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
-
-	dma_fence_work_commit_imm(&pw->base);
-	return 0;
-
-err_commit:
-	i915_sw_fence_set_error_once(&pw->base.chain, err);
-	dma_fence_work_commit_imm(&pw->base);
-	return err;
-
-err_unmap_batch:
-	if (pw->batch_map)
-		i915_gem_object_unpin_map(batch);
-	else
-		i915_gem_object_unpin_pages(batch);
-err_unmap_shadow:
-	i915_gem_object_unpin_map(shadow->obj);
-err_trampoline:
-	if (trampoline)
-		i915_active_release(&trampoline->active);
-err_shadow:
-	i915_active_release(&shadow->active);
-err_batch:
-	i915_active_release(&eb->batch->vma->active);
-err_free:
-	kfree(pw);
-	return err;
-}
-
 static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma)
 {
 	/*
@@ -2672,7 +2463,15 @@ static int eb_parse(struct i915_execbuffer *eb)
 		goto err_trampoline;
 	}
 
-	err = eb_parse_pipeline(eb, shadow, trampoline);
+	err = dma_resv_reserve_shared(shadow->resv, 1);
+	if (err)
+		goto err_trampoline;
+
+	err = intel_engine_cmd_parser(eb->engine,
+				      eb->batch->vma,
+				      eb->batch_start_offset,
+				      eb->batch_len,
+				      shadow, trampoline);
 	if (err)
 		goto err_unpin_batch;
 
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 4df505e4c53a..16162fc2782d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -125,6 +125,10 @@ static int igt_gpu_reloc(void *arg)
 	intel_gt_pm_get(&eb.i915->gt);
 
 	for_each_uabi_engine(eb.engine, eb.i915) {
+		if (intel_engine_requires_cmd_parser(eb.engine) ||
+		    intel_engine_using_cmd_parser(eb.engine))
+			continue;
+
 		reloc_cache_init(&eb.reloc_cache, eb.i915);
 		memset(map, POISON_INUSE, 4096);