r600g: fix cache flushes on r6xx

r6xx asics have some problems with the surface
sync logic for the CB and DB.  It's recommended
to use the event write interface for flushing
the DB/CB caches rather than the sync packets.
A single event write flush flushes all dst
caches, so we only need one for all CBs and DB.

Should fix:
https://bugs.freedesktop.org/show_bug.cgi?id=35312

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

diff --git a/src/gallium/drivers/r600/r600.h b/src/gallium/drivers/r600/r600.h
index 0b0df9d019b4107b6feead87c31789cc28ad5cec..33aa45088a8f814a3cbd3fa76f6543897b353691 100644 (file)
--- a/src/gallium/drivers/r600/r600.h
+++ b/src/gallium/drivers/r600/r600.h
@@ -235,6 +235,7 @@ struct r600_query {
 
 #define R600_CONTEXT_DRAW_PENDING      (1 << 0)
 #define R600_CONTEXT_DST_CACHES_DIRTY  (1 << 1)
+#define R600_CONTEXT_CHECK_EVENT_FLUSH (1 << 2)
 
 struct r600_context {
        struct radeon           *radeon;

diff --git a/src/gallium/winsys/r600/drm/r600_hw_context.c b/src/gallium/winsys/r600/drm/r600_hw_context.c
index 150485d3fe1461a03a3cdf72dff9f6098d1467f3..b8a8108fb1228c171b41d93b2c53f31a141f140e 100644 (file)
--- a/src/gallium/winsys/r600/drm/r600_hw_context.c
+++ b/src/gallium/winsys/r600/drm/r600_hw_context.c
@@ -797,19 +797,33 @@ void r600_context_bo_flush(struct r600_context *ctx, unsigned flush_flags,
                                unsigned flush_mask, struct r600_bo *rbo)
 {
        struct radeon_bo *bo;
+       boolean use_event_flush = FALSE;
+
        bo = rbo->bo;
        /* if bo has already been flushed */
        if (!(~bo->last_flush & flush_flags)) {
                bo->last_flush &= flush_mask;
                return;
        }
-       ctx->pm4[ctx->pm4_cdwords++] = PKT3(PKT3_SURFACE_SYNC, 3, ctx->predicate_drawing);
-       ctx->pm4[ctx->pm4_cdwords++] = flush_flags;
-       ctx->pm4[ctx->pm4_cdwords++] = (bo->size + 255) >> 8;
-       ctx->pm4[ctx->pm4_cdwords++] = 0x00000000;
-       ctx->pm4[ctx->pm4_cdwords++] = 0x0000000A;
-       ctx->pm4[ctx->pm4_cdwords++] = PKT3(PKT3_NOP, 0, ctx->predicate_drawing);
-       ctx->pm4[ctx->pm4_cdwords++] = bo->reloc_id;
+
+       if ((ctx->radeon->family < CHIP_RV770) &&
+           (G_0085F0_CB_ACTION_ENA(flush_flags) ||
+            G_0085F0_DB_ACTION_ENA(flush_flags)))
+               use_event_flush = TRUE;
+
+       if (use_event_flush && (ctx->flags & R600_CONTEXT_CHECK_EVENT_FLUSH)) {
+               ctx->pm4[ctx->pm4_cdwords++] = PKT3(PKT3_EVENT_WRITE, 0, ctx->predicate_drawing);
+               ctx->pm4[ctx->pm4_cdwords++] = EVENT_TYPE(EVENT_TYPE_CACHE_FLUSH_AND_INV_EVENT) | EVENT_INDEX(0);
+               ctx->flags &= ~R600_CONTEXT_CHECK_EVENT_FLUSH;
+       } else {
+               ctx->pm4[ctx->pm4_cdwords++] = PKT3(PKT3_SURFACE_SYNC, 3, ctx->predicate_drawing);
+               ctx->pm4[ctx->pm4_cdwords++] = flush_flags;
+               ctx->pm4[ctx->pm4_cdwords++] = (bo->size + 255) >> 8;
+               ctx->pm4[ctx->pm4_cdwords++] = 0x00000000;
+               ctx->pm4[ctx->pm4_cdwords++] = 0x0000000A;
+               ctx->pm4[ctx->pm4_cdwords++] = PKT3(PKT3_NOP, 0, ctx->predicate_drawing);
+               ctx->pm4[ctx->pm4_cdwords++] = bo->reloc_id;
+       }
        bo->last_flush = (bo->last_flush | flush_flags) & flush_mask;
 }
 
@@ -1119,6 +1133,7 @@ void r600_context_block_emit_dirty(struct r600_context *ctx, struct r600_block *
                goto out;
        }
 
+       ctx->flags |= R600_CONTEXT_CHECK_EVENT_FLUSH;
        for (int j = 0; j < block->nreg; j++) {
                if (block->pm4_bo_index[j]) {
                        /* find relocation */
@@ -1132,6 +1147,7 @@ void r600_context_block_emit_dirty(struct r600_context *ctx, struct r600_block *
                                        block->reloc[id].bo);
                }
        }
+       ctx->flags &= ~R600_CONTEXT_CHECK_EVENT_FLUSH;
        memcpy(&ctx->pm4[ctx->pm4_cdwords], block->pm4, block->pm4_ndwords * 4);
        ctx->pm4_cdwords += block->pm4_ndwords;
 
@@ -1155,6 +1171,7 @@ void r600_context_flush_dest_caches(struct r600_context *ctx)
 {
        struct r600_bo *cb[8];
        struct r600_bo *db;
+       int i;
 
        if (!(ctx->flags & R600_CONTEXT_DST_CACHES_DIRTY))
                return;
@@ -1169,8 +1186,9 @@ void r600_context_flush_dest_caches(struct r600_context *ctx)
        cb[6] = r600_context_reg_bo(ctx, R_028058_CB_COLOR6_BASE);
        cb[7] = r600_context_reg_bo(ctx, R_02805C_CB_COLOR7_BASE);
 
+       ctx->flags |= R600_CONTEXT_CHECK_EVENT_FLUSH;
        /* flush the color buffers */
-       for (int i = 0; i < 8; i++) {
+       for (i = 0; i < 8; i++) {
                if (!cb[i])
                        continue;
 
@@ -1182,7 +1200,7 @@ void r600_context_flush_dest_caches(struct r600_context *ctx)
        if (db) {
                r600_context_bo_flush(ctx, S_0085F0_DB_ACTION_ENA(1), 0, db);
        }
-
+       ctx->flags &= ~R600_CONTEXT_CHECK_EVENT_FLUSH;
        ctx->flags &= ~R600_CONTEXT_DST_CACHES_DIRTY;
 }