anv/cmd_buffer: Re-emit MEDIA_CURBE_LOAD when CS push constants are dirty

This can happen even if the binding table isn't changed.  For instance, you
could have dynamic offsets with your descriptor set.  This fixes the new
stress.lots-of-surface-state.cs.dynamic cricible test.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Cc: "13.0" <mesa-stable@lists.freedesktop.org>
(cherry picked from commit 054e48ee0ead7e5a81d28220e3890c7dfc410188)

Conflicts:
	src/intel/vulkan/genX_cmd_buffer.c

Squashed with commit:

anv/cmd_buffer: Emit CS push constants after binding tables

Emitting binding tables can cause push constants to be dirtied if the
shader uses images so we need to handle push constants later.

(cherry picked from commit 7a2cfd4adb891fb93e84fd8aedfbe387a8a2c781)

1 files changed, 13 insertions, 10 deletions

diff --git a/src/intel/vulkan/genX_cmd_buffer.c b/src/intel/vulkan/genX_cmd_buffer.c
index f1b5387..4977c2e 100644
--- a/src/intel/vulkan/genX_cmd_buffer.c
+++ b/src/intel/vulkan/genX_cmd_buffer.c
@@ -1356,22 +1356,13 @@ flush_compute_descriptor_set(struct anv_cmd_buffer *cmd_buffer)
       result = emit_binding_table(cmd_buffer, MESA_SHADER_COMPUTE, &surfaces);
       assert(result == VK_SUCCESS);
    }
+
    result = emit_samplers(cmd_buffer, MESA_SHADER_COMPUTE, &samplers);
    assert(result == VK_SUCCESS);
 
-
-   struct anv_state push_state = anv_cmd_buffer_cs_push_constants(cmd_buffer);
-
    const struct brw_cs_prog_data *cs_prog_data = get_cs_prog_data(pipeline);
    const struct brw_stage_prog_data *prog_data = &cs_prog_data->base;
 
-   if (push_state.alloc_size) {
-      anv_batch_emit(&cmd_buffer->batch, GENX(MEDIA_CURBE_LOAD), curbe) {
-         curbe.CURBETotalDataLength    = push_state.alloc_size;
-         curbe.CURBEDataStartAddress   = push_state.offset;
-      }
-   }
-
    const uint32_t slm_size = encode_slm_size(GEN_GEN, prog_data->total_shared);
 
    struct anv_state state =
@@ -1441,6 +1432,18 @@ genX(cmd_buffer_flush_compute_state)(struct anv_cmd_buffer *cmd_buffer)
       cmd_buffer->state.descriptors_dirty &= ~VK_SHADER_STAGE_COMPUTE_BIT;
    }
 
+   if (cmd_buffer->state.push_constants_dirty & VK_SHADER_STAGE_COMPUTE_BIT) {
+      struct anv_state push_state =
+         anv_cmd_buffer_cs_push_constants(cmd_buffer);
+
+      if (push_state.alloc_size) {
+         anv_batch_emit(&cmd_buffer->batch, GENX(MEDIA_CURBE_LOAD), curbe) {
+            curbe.CURBETotalDataLength    = push_state.alloc_size;
+            curbe.CURBEDataStartAddress   = push_state.offset;
+         }
+      }
+   }
+
    cmd_buffer->state.compute_dirty = 0;
 
    genX(cmd_buffer_apply_pipe_flushes)(cmd_buffer);