From 407785d0e97abd0cc51a6e360089111973748e7c Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 18 Jul 2011 17:17:03 -0700 Subject: [PATCH] i965: Enable the PIPE_CONTROL workaround workaround out of paranoia. There's scary stuff going on in PIPE_CONTROL internals, and if the BSpec says to do this to make PIPE_CONTROL work, I'll go ahead and do it because we'll probably never be able to debug it after the fact. v2: Use stall at scoreboard instead of depth stall, as noted by Ken. --- .../drivers/dri/intel/intel_batchbuffer.c | 31 +++++++++++++++++-- src/mesa/drivers/dri/intel/intel_reg.h | 1 + 2 files changed, 29 insertions(+), 3 deletions(-) diff --git a/src/mesa/drivers/dri/intel/intel_batchbuffer.c b/src/mesa/drivers/dri/intel/intel_batchbuffer.c index 9c97ef22888..97cc219ce6d 100644 --- a/src/mesa/drivers/dri/intel/intel_batchbuffer.c +++ b/src/mesa/drivers/dri/intel/intel_batchbuffer.c @@ -308,12 +308,29 @@ emit: * [Dev-SNB{W/A}]: Before a PIPE_CONTROL with Write Cache Flush Enable * =1, a PIPE_CONTROL with any non-zero post-sync-op is required. * - * XXX: There is also a workaround that would appear to apply to this - * workaround, but it doesn't appear to be necessary so far: + * And the workaround for these two requires this workaround first: * - * Dev-SNB{W/A}]: Pipe-control with CS-stall bit set must be sent + * [Dev-SNB{W/A}]: Pipe-control with CS-stall bit set must be sent * BEFORE the pipe-control with a post-sync op and no write-cache * flushes. + * + * And this last workaround is tricky because of the requirements on + * that bit. From section 1.4.7.2.3 "Stall" of the Sandy Bridge PRM + * volume 2 part 1: + * + * "1 of the following must also be set: + * - Render Target Cache Flush Enable ([12] of DW1) + * - Depth Cache Flush Enable ([0] of DW1) + * - Stall at Pixel Scoreboard ([1] of DW1) + * - Depth Stall ([13] of DW1) + * - Post-Sync Operation ([13] of DW1) + * - Notify Enable ([8] of DW1)" + * + * The cache flushes require the workaround flush that triggered this + * one, so we can't use it. Depth stall would trigger the same. + * Post-sync nonzero is what triggered this second workaround, so we + * can't use that one either. Notify enable is IRQs, which aren't + * really our business. That leaves only stall at scoreboard. */ void intel_emit_post_sync_nonzero_flush(struct intel_context *intel) @@ -321,6 +338,14 @@ intel_emit_post_sync_nonzero_flush(struct intel_context *intel) if (!intel->batch.need_workaround_flush) return; + BEGIN_BATCH(4); + OUT_BATCH(_3DSTATE_PIPE_CONTROL); + OUT_BATCH(PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_STALL_AT_SCOREBOARD); + OUT_BATCH(0); /* address */ + OUT_BATCH(0); /* write data */ + ADVANCE_BATCH(); + BEGIN_BATCH(4); OUT_BATCH(_3DSTATE_PIPE_CONTROL); OUT_BATCH(PIPE_CONTROL_WRITE_IMMEDIATE); diff --git a/src/mesa/drivers/dri/intel/intel_reg.h b/src/mesa/drivers/dri/intel/intel_reg.h index 5aa629150cf..a98a669af21 100644 --- a/src/mesa/drivers/dri/intel/intel_reg.h +++ b/src/mesa/drivers/dri/intel/intel_reg.h @@ -75,6 +75,7 @@ #define PIPE_CONTROL_VF_CACHE_INVALIDATE (1 << 4) #define PIPE_CONTROL_CONST_CACHE_INVALIDATE (1 << 3) #define PIPE_CONTROL_STATE_CACHE_INVALIDATE (1 << 2) +#define PIPE_CONTROL_STALL_AT_SCOREBOARD (1 << 1) #define PIPE_CONTROL_DEPTH_CACHE_FLUSH (1 << 0) #define PIPE_CONTROL_PPGTT_WRITE (0 << 2) #define PIPE_CONTROL_GLOBAL_GTT_WRITE (1 << 2) -- 2.30.2