i965: Use full-length PIPE_CONTROL packets for workaround writes.

I believe that PIPE_CONTROL uses the length field to decide whether to
do 32-bit or 64-bit writes.  A length of 4 would do a 32-bit write,
while a length of 5 would do a 64-bit write.  (I haven't verified this,
though.)

For workaround writes, we don't care what value gets written, or how
much data.  We're only writing something because hardware bugs mandate
that do so.  So using a 64-bit write should be fine.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/mesa/drivers/dri/i965/intel_batchbuffer.c b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
index 12c7eccae692e19aaee0395fdb993d3efaab75bf..f54ca9b30e4f778ad0b34d0919ac398b7bae5f8e 100644 (file)
--- a/src/mesa/drivers/dri/i965/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
@@ -493,12 +493,13 @@ gen7_emit_vs_workaround_flush(struct brw_context *brw)
 {
    assert(brw->gen == 7);
 
-   BEGIN_BATCH(4);
-   OUT_BATCH(_3DSTATE_PIPE_CONTROL | (4 - 2));
+   BEGIN_BATCH(5);
+   OUT_BATCH(_3DSTATE_PIPE_CONTROL | (5 - 2));
    OUT_BATCH(PIPE_CONTROL_DEPTH_STALL | PIPE_CONTROL_WRITE_IMMEDIATE);
    OUT_RELOC(brw->batch.workaround_bo,
             I915_GEM_DOMAIN_INSTRUCTION, I915_GEM_DOMAIN_INSTRUCTION, 0);
    OUT_BATCH(0); /* write data */
+   OUT_BATCH(0); /* write data */
    ADVANCE_BATCH();
 }
 
@@ -509,8 +510,8 @@ gen7_emit_vs_workaround_flush(struct brw_context *brw)
 void
 gen7_emit_cs_stall_flush(struct brw_context *brw)
 {
-   BEGIN_BATCH(4);
-   OUT_BATCH(_3DSTATE_PIPE_CONTROL | (4 - 2));
+   BEGIN_BATCH(5);
+   OUT_BATCH(_3DSTATE_PIPE_CONTROL | (5 - 2));
    /* From p61 of the Ivy Bridge PRM (1.10.4 PIPE_CONTROL Command: DW1[20]
     * CS Stall):
     *
@@ -528,6 +529,7 @@ gen7_emit_cs_stall_flush(struct brw_context *brw)
    OUT_RELOC(brw->batch.workaround_bo,
              I915_GEM_DOMAIN_INSTRUCTION, I915_GEM_DOMAIN_INSTRUCTION, 0);
    OUT_BATCH(0);
+   OUT_BATCH(0);
    ADVANCE_BATCH();
 }
 
@@ -579,12 +581,13 @@ intel_emit_post_sync_nonzero_flush(struct brw_context *brw)
                                PIPE_CONTROL_CS_STALL |
                                PIPE_CONTROL_STALL_AT_SCOREBOARD);
 
-   BEGIN_BATCH(4);
-   OUT_BATCH(_3DSTATE_PIPE_CONTROL | (4 - 2));
+   BEGIN_BATCH(5);
+   OUT_BATCH(_3DSTATE_PIPE_CONTROL | (5 - 2));
    OUT_BATCH(PIPE_CONTROL_WRITE_IMMEDIATE);
    OUT_RELOC(brw->batch.workaround_bo,
             I915_GEM_DOMAIN_INSTRUCTION, I915_GEM_DOMAIN_INSTRUCTION, 0);
    OUT_BATCH(0); /* write data */
+   OUT_BATCH(0); /* write data */
    ADVANCE_BATCH();
 
    brw->batch.need_workaround_flush = false;