Mesa (staging/21.3): radv: re-emit prolog inputs when the nontrivial divisors state changed

[GitLab Mirror]

Module: Mesa
Branch: staging/21.3
Commit: 1b083586ce539e457c43905d4464319e40be72ec
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=1b083586ce539e457c43905d4464319e40be72ec

Author: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Date:   Fri Oct 15 14:27:38 2021 +0200

radv: re-emit prolog inputs when the nontrivial divisors state changed

If the application first uses nontrivial divisors, the driver emits
the vertex shader VA to the upload BO rather than directly via the
user SGPRs locations. But, if the vertex input dynamic state changes,
the driver might select a different VS prolog that no longer needs
nontrivial divisors.

In this case, the driver needs to re-emit the prolog inputs because
otherwise the VS prolog will jump to the PC that is emitted via the
user SGPR locations, and the previous one was somewhere in the
upload BO...

This fixes a GPU hang with Bioshock and Zink.

Fixes: d9c7a175424 ("radv: enable VK_EXT_vertex_input_dynamic_state")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02 at gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13377>
(cherry picked from commit b6a69dbb40d06963056b14158acd0521a91fc395)

---

 .pick_status.json                | 2 +-
 src/amd/vulkan/radv_cmd_buffer.c | 3 ++-
 src/amd/vulkan/radv_shader.c     | 3 +++
 src/amd/vulkan/radv_shader.h     | 1 +
 4 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/.pick_status.json b/.pick_status.json
index 68fe94a21bd..720ea320c75 100644
--- a/.pick_status.json
+++ b/.pick_status.json
@@ -103,7 +103,7 @@
         "description": "radv: re-emit prolog inputs when the nontrivial divisors state changed",
         "nominated": true,
         "nomination_type": 1,
-        "resolution": 0,
+        "resolution": 1,
         "main_sha": null,
         "because_sha": "d9c7a175424308b4da7673ea885fd8a8b3edf862"
     },
diff --git a/src/amd/vulkan/radv_cmd_buffer.c b/src/amd/vulkan/radv_cmd_buffer.c
index 44ae2bd9aa2..2c236b2bdd2 100644
--- a/src/amd/vulkan/radv_cmd_buffer.c
+++ b/src/amd/vulkan/radv_cmd_buffer.c
@@ -2909,7 +2909,8 @@ emit_prolog_inputs(struct radv_cmd_buffer *cmd_buffer, struct radv_shader_varian
                    uint32_t nontrivial_divisors, bool pipeline_is_dirty)
 {
    /* no need to re-emit anything in this case */
-   if (!nontrivial_divisors && !pipeline_is_dirty)
+   if (!nontrivial_divisors && !pipeline_is_dirty && cmd_buffer->state.emitted_vs_prolog &&
+       !cmd_buffer->state.emitted_vs_prolog->nontrivial_divisors)
       return;
 
    struct radv_vs_input_state *state = &cmd_buffer->state.dynamic_vs_input;
diff --git a/src/amd/vulkan/radv_shader.c b/src/amd/vulkan/radv_shader.c
index e610b92b0cf..0cb330df5b5 100644
--- a/src/amd/vulkan/radv_shader.c
+++ b/src/amd/vulkan/radv_shader.c
@@ -1975,6 +1975,9 @@ radv_create_vs_prolog(struct radv_device *device, const struct radv_vs_prolog_ke
    struct radv_prolog_binary *binary = NULL;
    aco_compile_vs_prolog(key, &binary, &args);
    struct radv_shader_prolog *prolog = upload_vs_prolog(device, binary, info.wave_size);
+   if (prolog) {
+      prolog->nontrivial_divisors = key->state->nontrivial_divisors;
+   }
    free(binary);
 
    return prolog;
diff --git a/src/amd/vulkan/radv_shader.h b/src/amd/vulkan/radv_shader.h
index 4204e5a5b30..9cabbfc21c1 100644
--- a/src/amd/vulkan/radv_shader.h
+++ b/src/amd/vulkan/radv_shader.h
@@ -479,6 +479,7 @@ struct radv_shader_prolog {
    union radv_shader_arena_block *alloc;
    uint32_t rsrc1;
    uint8_t num_preserved_sgprs;
+   bool nontrivial_divisors;
 };
 
 void radv_optimize_nir(const struct radv_device *device, struct nir_shader *shader,