gallium/radeon: add RADEON_USAGE_SYNCHRONIZED

This is really the behavior we want most of the time, but having a
SYNCHRONIZED flag instead of an UNSYNCHRONIZED one has the advantage that
OR'ing different flags together always results in stronger guarantees.

The parent BOs of sub-allocated buffers will be added unsynchronized.

Reviewed-by: Marek Olšák <[email protected]>

4 files changed, 14 insertions, 5 deletions

diff --git a/src/gallium/drivers/radeon/r600_cs.h b/src/gallium/drivers/radeon/r600_cs.h
index 6c15df88807..28bdf15b8ad 100644
--- a/src/gallium/drivers/radeon/r600_cs.h
+++ b/src/gallium/drivers/radeon/r600_cs.h
@@ -73,8 +73,10 @@ static inline unsigned radeon_add_to_buffer_list(struct r600_common_context *rct
 						 enum radeon_bo_priority priority)
 {
 	assert(usage);
-	return rctx->ws->cs_add_buffer(ring->cs, rbo->buf, usage,
-				      rbo->domains, priority) * 4;
+	return rctx->ws->cs_add_buffer(
+		ring->cs, rbo->buf,
+		(enum radeon_bo_usage)(usage | RADEON_USAGE_SYNCHRONIZED),
+		rbo->domains, priority) * 4;
 }
 
 /**
diff --git a/src/gallium/drivers/radeon/radeon_uvd.c b/src/gallium/drivers/radeon/radeon_uvd.c
index d5d654ac4a3..3ae0eaa6e44 100644
--- a/src/gallium/drivers/radeon/radeon_uvd.c
+++ b/src/gallium/drivers/radeon/radeon_uvd.c
@@ -113,7 +113,8 @@ static void send_cmd(struct ruvd_decoder *dec, unsigned cmd,
 {
 	int reloc_idx;
 
-	reloc_idx = dec->ws->cs_add_buffer(dec->cs, buf, usage, domain,
+	reloc_idx = dec->ws->cs_add_buffer(dec->cs, buf, usage | RADEON_USAGE_SYNCHRONIZED,
+					   domain,
 					  RADEON_PRIO_UVD);
 	if (!dec->use_legacy) {
 		uint64_t addr;
diff --git a/src/gallium/drivers/radeon/radeon_vce.c b/src/gallium/drivers/radeon/radeon_vce.c
index 8504d93d9b8..10c5a78dd33 100644
--- a/src/gallium/drivers/radeon/radeon_vce.c
+++ b/src/gallium/drivers/radeon/radeon_vce.c
@@ -540,7 +540,8 @@ void rvce_add_buffer(struct rvce_encoder *enc, struct pb_buffer *buf,
 {
 	int reloc_idx;
 
-	reloc_idx = enc->ws->cs_add_buffer(enc->cs, buf, usage, domain, RADEON_PRIO_VCE);
+	reloc_idx = enc->ws->cs_add_buffer(enc->cs, buf, usage | RADEON_USAGE_SYNCHRONIZED,
+					   domain, RADEON_PRIO_VCE);
 	if (enc->use_vm) {
 		uint64_t addr;
 		addr = enc->ws->buffer_get_virtual_address(buf);
diff --git a/src/gallium/drivers/radeon/radeon_winsys.h b/src/gallium/drivers/radeon/radeon_winsys.h
index 91f6e898e07..809a2032f7d 100644
--- a/src/gallium/drivers/radeon/radeon_winsys.h
+++ b/src/gallium/drivers/radeon/radeon_winsys.h
@@ -57,7 +57,12 @@ enum radeon_bo_flag { /* bitfield */
 enum radeon_bo_usage { /* bitfield */
     RADEON_USAGE_READ = 2,
     RADEON_USAGE_WRITE = 4,
-    RADEON_USAGE_READWRITE = RADEON_USAGE_READ | RADEON_USAGE_WRITE
+    RADEON_USAGE_READWRITE = RADEON_USAGE_READ | RADEON_USAGE_WRITE,
+
+    /* The winsys ensures that the CS submission will be scheduled after
+     * previously flushed CSs referencing this BO in a conflicting way.
+     */
+    RADEON_USAGE_SYNCHRONIZED = 8
 };
 
 enum ring_type {