radeon/winsys: pad IBs to a multiple of 8 DWs

This aligns the gfx, compute, and dma IBs to 8 DW boundries.
This aligns the the IB to the fetch size of the CP for optimal
performance. Additionally, r6xx hardware requires at least 4
DW alignment to avoid a hw bug.  This also aligns the DMA
IBs to 8 DW which is required for the DMA engine.  This
alignment is already handled in the gallium driver, but that
patch can be removed now that it's done in the winsys.

Reviewed-by: Marek Olšák <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
CC: "9.2" <[email protected]>
CC: "9.1" <[email protected]>

1 files changed, 30 insertions, 0 deletions

diff --git a/src/gallium/winsys/radeon/drm/radeon_drm_cs.c b/src/gallium/winsys/radeon/drm/radeon_drm_cs.c
index ea0c99df3fa..38a92095507 100644
--- a/src/gallium/winsys/radeon/drm/radeon_drm_cs.c
+++ b/src/gallium/winsys/radeon/drm/radeon_drm_cs.c
@@ -466,6 +466,36 @@ static void radeon_drm_cs_flush(struct radeon_winsys_cs *rcs, unsigned flags, ui
     struct radeon_drm_cs *cs = radeon_drm_cs(rcs);
     struct radeon_cs_context *tmp;
 
+    switch (cs->base.ring_type) {
+    case RING_DMA:
+	    /* pad DMA ring to 8 DWs */
+	    if (cs->ws->info.chip_class <= SI) {
+		    while (rcs->cdw & 7)
+			    OUT_CS(&cs->base, 0xf0000000); /* NOP packet */
+	    } else {
+		    while (rcs->cdw & 7)
+			    OUT_CS(&cs->base, 0x00000000); /* NOP packet */
+	    }
+	    break;
+    case RING_GFX:
+	    /* pad DMA ring to 8 DWs to meet CP fetch alignment requirements
+	     * r6xx, requires at least 4 dw alignment to avoid a hw bug.
+	     */
+            if (flags & RADEON_FLUSH_COMPUTE) {
+		    if (cs->ws->info.chip_class <= SI) {
+			    while (rcs->cdw & 7)
+				    OUT_CS(&cs->base, 0x80000000); /* type2 nop packet */
+		    } else {
+			    while (rcs->cdw & 7)
+				    OUT_CS(&cs->base, 0xffff1000); /* type3 nop packet */
+		    }
+	    } else {
+		    while (rcs->cdw & 7)
+			    OUT_CS(&cs->base, 0x80000000); /* type2 nop packet */
+	    }
+	    break;
+    }
+
     if (rcs->cdw > RADEON_MAX_CMDBUF_DWORDS) {
        fprintf(stderr, "radeon: command stream overflowed\n");
     }