i965: Drop INTEL_DEBUG=stats.

For whatever reason, we had an INTEL_DEBUG=stats option that enabled
various statistics counters on Gen4-5 systems.  It's been around
forever, though I can't think of a single time that it's been useful.

On Gen6+, we enable statistics all the time because they're necessary
to support various query object targets.  Turning them off would break
those queries.

Gen4-5 don't support those queries, so the statistics counters generally
aren't useful; we disabled them by default.  This patch disables them
altogether.

Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>

docs/envvars.html

@@ -195,7 +195,6 @@ See the <a href="xlibdriver.html">Xlib software driver page</a> for details.
    <li>spill_fs - force spilling of all registers in the scalar backend (useful to debug spilling code)</li>
    <li>spill_vec4 - force spilling of all registers in the vec4 backend (useful to debug spilling code)</li>
    <li>state - emit messages about state flag tracking</li>
-   <li>stats - enable statistics counters. you probably actually want perfmon or intel_gpu_top instead.</li>
    <li>sync - after sending each batch, emit a message and wait for that batch to finish rendering</li>
    <li>tcs - dump shader assembly for tessellation control shaders</li>
    <li>tes - dump shader assembly for tessellation evaluation shaders</li>

src/intel/common/gen_debug.c

@@ -57,7 +57,6 @@ static const struct debug_control debug_control[] = {
    { "vert",        DEBUG_VERTS },
    { "dri",         DEBUG_DRI },
    { "sf",          DEBUG_SF },
-   { "stats",       DEBUG_STATS },
    { "wm",          DEBUG_WM },
    { "urb",         DEBUG_URB },
    { "vs",          DEBUG_VS },

src/intel/common/gen_debug.h

@@ -57,7 +57,7 @@ extern uint64_t INTEL_DEBUG;
 #define DEBUG_VERTS               (1ull << 13)
 #define DEBUG_DRI                 (1ull << 14)
 #define DEBUG_SF                  (1ull << 15)
-#define DEBUG_STATS               (1ull << 16)
+/* Hole - feel free to reuse      (1ull << 16) */
 #define DEBUG_WM                  (1ull << 17)
 #define DEBUG_URB                 (1ull << 18)
 #define DEBUG_VS                  (1ull << 19)

src/mesa/drivers/dri/i965/brw_cc.c

@@ -226,7 +226,7 @@ static void upload_cc_unit(struct brw_context *brw)
       cc->cc2.depth_write_enable = brw_depth_writes_enabled(brw);
    }
 
-   if (brw->stats_wm || unlikely(INTEL_DEBUG & DEBUG_STATS))
+   if (brw->stats_wm)
       cc->cc5.statistics_enable = 1;
 
    /* BRW_NEW_CC_VP */

src/mesa/drivers/dri/i965/brw_clip_state.c

@@ -114,9 +114,6 @@ brw_upload_clip_unit(struct brw_context *brw)
       clip->thread4.max_threads = 1 - 1;
    }
 
-   if (unlikely(INTEL_DEBUG & DEBUG_STATS))
-      clip->thread4.stats_enable = 1;
-
    /* _NEW_TRANSFORM */
    if (brw->gen == 5 || brw->is_g4x)
       clip->clip5.userclip_enable_flags = ctx->Transform.ClipPlanesEnabled;

src/mesa/drivers/dri/i965/brw_gs_state.c

@@ -80,9 +80,6 @@ brw_upload_gs_unit(struct brw_context *brw)
    if (brw->gen == 5)
       gs->thread4.rendering_enable = 1;
 
-   if (unlikely(INTEL_DEBUG & DEBUG_STATS))
-      gs->thread4.stats_enable = 1;
-
    /* BRW_NEW_VIEWPORT_COUNT */
    gs->gs6.max_vp_index = brw->clip.viewport_count - 1;
 

src/mesa/drivers/dri/i965/brw_sf_state.c

@@ -174,9 +174,6 @@ static void upload_sf_unit( struct brw_context *brw )
    sf->thread4.max_threads = MIN2(chipset_max_threads,
 				  brw->urb.nr_sf_entries) - 1;
 
-   if (unlikely(INTEL_DEBUG & DEBUG_STATS))
-      sf->thread4.stats_enable = 1;
-
    /* BRW_NEW_SF_VP */
    sf->sf5.sf_viewport_state_offset = (brw->batch.bo->offset64 +
 				       brw->sf.vp_offset) >> 5; /* reloc */

src/mesa/drivers/dri/i965/brw_vs_state.c

@@ -146,10 +146,6 @@ brw_upload_vs_unit(struct brw_context *brw)
       vs->vs5.sampler_count = (stage_state->sampler_count + 3) / 4;
    }
 
-
-   if (unlikely(INTEL_DEBUG & DEBUG_STATS))
-      vs->thread4.stats_enable = 1;
-
    /* Vertex program always enabled:
     */
    vs->vs6.vs_enable = 1;

src/mesa/drivers/dri/i965/brw_wm_state.c

@@ -217,7 +217,7 @@ brw_upload_wm_unit(struct brw_context *brw)
    wm->wm5.line_stipple = ctx->Line.StippleFlag;
 
    /* BRW_NEW_STATS_WM */
-   if (unlikely(INTEL_DEBUG & DEBUG_STATS) || brw->stats_wm)
+   if (brw->stats_wm)
       wm->wm4.stats_enable = 1;
 
    /* Emit scratch space relocation */