[Mesa-dev] [PATCH] r600g: Use a fake reloc to sleep for fences

[Simon Farnsworth]

r300g is able to sleep until a fence completes rather than busywait because
it creates a special buffer object and relocation that stays busy until the
CS containing the fence is finished.

Copy the idea into r600g, and use it to sleep if the user asked for an
infinite wait, falling back to busywaiting if the user provided a timeout.

Signed-off-by: Simon Farnsworth <simon.farnsworth at onelan.co.uk>
---

v2: Address Michel's review comments.

The fake bo is now unconditional, and is unreferenced when the fence is
moved to the fence pool by fence_reference. This entailed shifting to
r600_resource, which cleaned the code up a little to boot.

 src/gallium/drivers/r600/r600.h            |    2 +-
 src/gallium/drivers/r600/r600_hw_context.c |    9 ++++++++-
 src/gallium/drivers/r600/r600_pipe.c       |    9 ++++++++-
 src/gallium/drivers/r600/r600_pipe.h       |    1 +
 4 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/src/gallium/drivers/r600/r600.h b/src/gallium/drivers/r600/r600.h
index baf09c1..c5813c2 100644
--- a/src/gallium/drivers/r600/r600.h
+++ b/src/gallium/drivers/r600/r600.h
@@ -284,7 +284,7 @@ void r600_context_queries_resume(struct r600_context *ctx);
 void r600_query_predication(struct r600_context *ctx, struct r600_query *query, int operation,
 			    int flag_wait);
 void r600_context_emit_fence(struct r600_context *ctx, struct r600_resource *fence,
-                             unsigned offset, unsigned value);
+                             unsigned offset, unsigned value, struct r600_resource **sleep_bo);
 void r600_context_flush_all(struct r600_context *ctx, unsigned flush_flags);
 void r600_context_flush_dest_caches(struct r600_context *ctx);
 
diff --git a/src/gallium/drivers/r600/r600_hw_context.c b/src/gallium/drivers/r600/r600_hw_context.c
index 8eb8e6d..acfa494 100644
--- a/src/gallium/drivers/r600/r600_hw_context.c
+++ b/src/gallium/drivers/r600/r600_hw_context.c
@@ -1603,7 +1603,7 @@ void r600_context_flush(struct r600_context *ctx, unsigned flags)
 	}
 }
 
-void r600_context_emit_fence(struct r600_context *ctx, struct r600_resource *fence_bo, unsigned offset, unsigned value)
+void r600_context_emit_fence(struct r600_context *ctx, struct r600_resource *fence_bo, unsigned offset, unsigned value, struct r600_resource **sleep_bo)
 {
 	uint64_t va;
 
@@ -1623,6 +1623,13 @@ void r600_context_emit_fence(struct r600_context *ctx, struct r600_resource *fen
 	ctx->pm4[ctx->pm4_cdwords++] = 0;                       /* DATA_HI */
 	ctx->pm4[ctx->pm4_cdwords++] = PKT3(PKT3_NOP, 0, 0);
 	ctx->pm4[ctx->pm4_cdwords++] = r600_context_bo_reloc(ctx, fence_bo, RADEON_USAGE_WRITE);
+
+	/* Create a dummy BO so that fence_finish without a timeout can sleep waiting for completion */
+	*sleep_bo = (struct r600_resource*)
+			pipe_buffer_create(&ctx->screen->screen, PIPE_BIND_CUSTOM,
+					   PIPE_USAGE_STAGING, 1);
+	/* Add the fence as a dummy relocation. */
+	r600_context_bo_reloc(ctx, *sleep_bo, RADEON_USAGE_READWRITE);
 }
 
 static unsigned r600_query_read_result(char *map, unsigned start_index, unsigned end_index,
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index c38fbc5..748869a 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -115,7 +115,7 @@ static struct r600_fence *r600_create_fence(struct r600_pipe_context *ctx)
 	pipe_reference_init(&fence->reference, 1);
 
 	rscreen->fences.data[fence->index] = 0;
-	r600_context_emit_fence(&ctx->ctx, rscreen->fences.bo, fence->index, 1);
+	r600_context_emit_fence(&ctx->ctx, rscreen->fences.bo, fence->index, 1, &fence->sleep_bo);
 out:
 	pipe_mutex_unlock(rscreen->fences.mutex);
 	return fence;
@@ -572,6 +572,7 @@ static void r600_fence_reference(struct pipe_screen *pscreen,
 	if (pipe_reference(&(*oldf)->reference, &newf->reference)) {
 		struct r600_screen *rscreen = (struct r600_screen *)pscreen;
 		pipe_mutex_lock(rscreen->fences.mutex);
+		pipe_resource_reference((struct pipe_resource**)&(*oldf)->sleep_bo, NULL);
 		LIST_ADDTAIL(&(*oldf)->head, &rscreen->fences.pool);
 		pipe_mutex_unlock(rscreen->fences.mutex);
 	}
@@ -605,6 +606,12 @@ static boolean r600_fence_finish(struct pipe_screen *pscreen,
 	}
 
 	while (rscreen->fences.data[rfence->index] == 0) {
+		/* Special-case infinite timeout */
+		if (timeout == PIPE_TIMEOUT_INFINITE) {
+			rscreen->ws->buffer_wait(rfence->sleep_bo->buf, RADEON_USAGE_READWRITE);
+			continue;
+		}
+
 		if (++spins % 256)
 			continue;
 #ifdef PIPE_OS_UNIX
diff --git a/src/gallium/drivers/r600/r600_pipe.h b/src/gallium/drivers/r600/r600_pipe.h
index 9ba60c8..df56560 100644
--- a/src/gallium/drivers/r600/r600_pipe.h
+++ b/src/gallium/drivers/r600/r600_pipe.h
@@ -170,6 +170,7 @@ struct r600_textures_info {
 struct r600_fence {
 	struct pipe_reference		reference;
 	unsigned			index; /* in the shared bo */
+	struct r600_resource            *sleep_bo;
 	struct list_head		head;
 };
 
-- 
1.7.6.4