[PATCH 4/6] drm/radeon: add explicit command submission sync

[Christian König]

From: Christian König <christian.koenig at amd.com>

The driver falls back to explicit synchronization as soon as
buffers move between clients or are moved by TTM.

Signed-off-by: Christian König <christian.koenig at amd.com>
---
 drivers/gpu/drm/radeon/radeon.h    |  1 +
 drivers/gpu/drm/radeon/radeon_cs.c | 24 +++++++++++++++++++++++-
 include/uapi/drm/radeon_drm.h      |  7 ++++---
 3 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b9fde1d..1529afb 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1101,6 +1101,7 @@ struct radeon_cs_parser {
 	struct radeon_cs_chunk  *chunk_relocs;
 	struct radeon_cs_chunk  *chunk_flags;
 	struct radeon_cs_chunk  *chunk_const_ib;
+	struct radeon_cs_chunk	*chunk_wait_for;
 	struct radeon_ib	ib;
 	struct radeon_ib	const_ib;
 	void			*track;
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index c0fc8d8..a73f9da 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -165,7 +165,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		}
 
 		p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
-		p->relocs[i].tv.shared = !r->write_domain;
+		p->relocs[i].tv.shared = !r->write_domain ||
+					 !!p->chunk_wait_for;
 
 		radeon_cs_buckets_add(&buckets, &p->relocs[i].tv.head,
 				      priority);
@@ -235,6 +236,23 @@ static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
 	struct radeon_bo_list *reloc;
 	int r;
 
+	if (p->chunk_wait_for) {
+		struct radeon_fpriv *fpriv = p->filp->driver_priv;
+		unsigned i;
+
+		for (i = 0; i < p->chunk_wait_for->length_dw; i += 2) {
+			struct radeon_fence *fence;
+			uint64_t *id;
+
+			id = (uint64_t *)&p->chunk_wait_for->kdata[i];
+
+			mutex_lock(&fpriv->seq_lock);
+			fence = radeon_seq_query(fpriv->seq, *id);
+			radeon_sync_fence(&p->ib.sync, fence);
+			mutex_unlock(&fpriv->seq_lock);
+		}
+	}
+
 	list_for_each_entry(reloc, &p->validated, tv.head) {
 		struct reservation_object *resv;
 		long owner = reloc->tv.shared ? (long)p->filp :
@@ -317,6 +335,10 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			if (p->chunks[i].length_dw == 0)
 				return -EINVAL;
 		}
+		if (user_chunk.chunk_id == RADEON_CHUNK_ID_WAIT_FOR) {
+			p->chunk_wait_for = &p->chunks[i];
+			/* zero length wait for list is actually useful */
+		}
 
 		size = p->chunks[i].length_dw;
 		cdata = (void __user *)(unsigned long)user_chunk.chunk_data;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 6b2b2e7..a34e3db 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -942,10 +942,11 @@ struct drm_radeon_gem_va {
 	uint64_t		offset;
 };
 
-#define RADEON_CHUNK_ID_RELOCS	0x01
-#define RADEON_CHUNK_ID_IB	0x02
-#define RADEON_CHUNK_ID_FLAGS	0x03
+#define RADEON_CHUNK_ID_RELOCS		0x01
+#define RADEON_CHUNK_ID_IB		0x02
+#define RADEON_CHUNK_ID_FLAGS		0x03
 #define RADEON_CHUNK_ID_CONST_IB	0x04
+#define RADEON_CHUNK_ID_WAIT_FOR	0x05
 
 /* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */
 #define RADEON_CS_KEEP_TILING_FLAGS 0x01
-- 
1.9.1