From: Iago Toral Quiroga <itoral@igalia.com>
Date: Fri, 18 Dec 2015 09:18:00 +0000 (+0100)
Subject: i965: Ensure FS execution in presence of atomic buffers
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=9bbdd0eda47677d27b339095913b7c1ee64b5f07;p=mesa.git

i965: Ensure FS execution in presence of atomic buffers

On Haswell we need to set the UAV_ONLY WM state bit when there are no colour
or depth buffer writes and on all hardware we should set the early
depth/stencil control field to PSEXEC unless early fragment tests are enabled
to make sure that the fragment shader is executed regardless of whether
per-fragment tests pass or not as the spec requires.

So far we have been doing this for images only, but we should apply the same
treatment to all side effectful scenarios. Suggested by Curro.

This is not strictly required for compliance with the original
ARB_shader_atomic_counters extension, it's only necessary to get the execution
semantics specified in GL4.2+ right.

v2:
- Mark active_fs_has_side_effects as constant. (Curro)
- Mention that this is only only necessary to get the execution semantics
specified in GL4.2+ right. (Curro)

Reviewed-by: Francisco Jerez <currojerez@riseup.net>
---

diff --git a/src/mesa/drivers/dri/i965/gen7_wm_state.c b/src/mesa/drivers/dri/i965/gen7_wm_state.c
index a6d1028dca1..7def5f5ad3c 100644
--- a/src/mesa/drivers/dri/i965/gen7_wm_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_wm_state.c
@@ -78,9 +78,10 @@ upload_wm_state(struct brw_context *brw)
    }
 
    /* _NEW_BUFFERS | _NEW_COLOR */
+   const bool active_fs_has_side_effects =
+      _mesa_active_fragment_shader_has_side_effects(&brw->ctx);
    if (brw_color_buffer_write_enabled(brw) || writes_depth ||
-       _mesa_active_fragment_shader_has_side_effects(&brw->ctx) ||
-       dw1 & GEN7_WM_KILL_ENABLE) {
+       active_fs_has_side_effects || dw1 & GEN7_WM_KILL_ENABLE) {
       dw1 |= GEN7_WM_DISPATCH_ENABLE;
    }
    if (multisampled_fbo) {
@@ -106,7 +107,7 @@ upload_wm_state(struct brw_context *brw)
    /* BRW_NEW_FS_PROG_DATA */
    if (prog_data->early_fragment_tests)
       dw1 |= GEN7_WM_EARLY_DS_CONTROL_PREPS;
-   else if (prog_data->base.nr_image_params)
+   else if (active_fs_has_side_effects)
       dw1 |= GEN7_WM_EARLY_DS_CONTROL_PSEXEC;
 
    /* The "UAV access enable" bits are unnecessary on HSW because they only
@@ -119,7 +120,7 @@ upload_wm_state(struct brw_context *brw)
     */
    if (brw->is_haswell &&
        !(brw_color_buffer_write_enabled(brw) || writes_depth) &&
-       prog_data->base.nr_image_params)
+       active_fs_has_side_effects)
       dw2 |= HSW_WM_UAV_ONLY;
 
    BEGIN_BATCH(3);
diff --git a/src/mesa/drivers/dri/i965/gen8_ps_state.c b/src/mesa/drivers/dri/i965/gen8_ps_state.c
index 3cc8c68e132..74cdcef015d 100644
--- a/src/mesa/drivers/dri/i965/gen8_ps_state.c
+++ b/src/mesa/drivers/dri/i965/gen8_ps_state.c
@@ -156,7 +156,7 @@ upload_wm_state(struct brw_context *brw)
    /* BRW_NEW_FS_PROG_DATA */
    if (brw->wm.prog_data->early_fragment_tests)
       dw1 |= GEN7_WM_EARLY_DS_CONTROL_PREPS;
-   else if (brw->wm.prog_data->base.nr_image_params)
+   else if (_mesa_active_fragment_shader_has_side_effects(&brw->ctx))
       dw1 |= GEN7_WM_EARLY_DS_CONTROL_PSEXEC;
 
    BEGIN_BATCH(2);