Mesa (master): winsys/amdgpu: report a rejected IB as a lost context

[Marek Olšák]

Module: Mesa
Branch: master
Commit: 18408008609df9007dc40512f00c5700167c5887
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=18408008609df9007dc40512f00c5700167c5887

Author: Marek Olšák <marek.olsak at amd.com>
Date:   Thu Jan 19 20:32:28 2017 +0100

winsys/amdgpu: report a rejected IB as a lost context

Reviewed-by: Nicolai Hähnle <nicolai.haehnle at amd.com>

---

 src/gallium/winsys/amdgpu/drm/amdgpu_cs.c     | 11 +++++++++++
 src/gallium/winsys/amdgpu/drm/amdgpu_cs.h     |  2 ++
 src/gallium/winsys/amdgpu/drm/amdgpu_winsys.h |  1 +
 3 files changed, 14 insertions(+)

diff --git a/src/gallium/winsys/amdgpu/drm/amdgpu_cs.c b/src/gallium/winsys/amdgpu/drm/amdgpu_cs.c
index 87246f7..d63ff36 100644
--- a/src/gallium/winsys/amdgpu/drm/amdgpu_cs.c
+++ b/src/gallium/winsys/amdgpu/drm/amdgpu_cs.c
@@ -178,6 +178,7 @@ static struct radeon_winsys_ctx *amdgpu_ctx_create(struct radeon_winsys *ws)
 
    ctx->ws = amdgpu_winsys(ws);
    ctx->refcount = 1;
+   ctx->initial_num_total_rejected_cs = ctx->ws->num_total_rejected_cs;
 
    r = amdgpu_cs_ctx_create(ctx->ws->dev, &ctx->ctx);
    if (r) {
@@ -227,6 +228,13 @@ amdgpu_ctx_query_reset_status(struct radeon_winsys_ctx *rwctx)
    uint32_t result, hangs;
    int r;
 
+   /* Return a failure due to a rejected command submission. */
+   if (ctx->ws->num_total_rejected_cs > ctx->initial_num_total_rejected_cs) {
+      return ctx->num_rejected_cs ? PIPE_GUILTY_CONTEXT_RESET :
+                                    PIPE_INNOCENT_CONTEXT_RESET;
+   }
+
+   /* Return a failure due to a GPU hang. */
    r = amdgpu_cs_query_reset_state(ctx->ctx, &result, &hangs);
    if (r) {
       fprintf(stderr, "amdgpu: amdgpu_cs_query_reset_state failed. (%i)\n", r);
@@ -1041,6 +1049,9 @@ void amdgpu_cs_submit_ib(void *job, int thread_index)
                  "see dmesg for more information (%i).\n", r);
 
       amdgpu_fence_signalled(cs->fence);
+
+      acs->ctx->num_rejected_cs++;
+      ws->num_total_rejected_cs++;
    } else {
       /* Success. */
       uint64_t *user_fence = NULL;
diff --git a/src/gallium/winsys/amdgpu/drm/amdgpu_cs.h b/src/gallium/winsys/amdgpu/drm/amdgpu_cs.h
index 5f181a5..90b9e83 100644
--- a/src/gallium/winsys/amdgpu/drm/amdgpu_cs.h
+++ b/src/gallium/winsys/amdgpu/drm/amdgpu_cs.h
@@ -41,6 +41,8 @@ struct amdgpu_ctx {
    amdgpu_bo_handle user_fence_bo;
    uint64_t *user_fence_cpu_address_base;
    int refcount;
+   unsigned initial_num_total_rejected_cs;
+   unsigned num_rejected_cs;
 };
 
 struct amdgpu_cs_buffer {
diff --git a/src/gallium/winsys/amdgpu/drm/amdgpu_winsys.h b/src/gallium/winsys/amdgpu/drm/amdgpu_winsys.h
index 2a7900a..c56c342 100644
--- a/src/gallium/winsys/amdgpu/drm/amdgpu_winsys.h
+++ b/src/gallium/winsys/amdgpu/drm/amdgpu_winsys.h
@@ -55,6 +55,7 @@ struct amdgpu_winsys {
    pipe_mutex bo_fence_lock;
 
    int num_cs; /* The number of command streams created. */
+   unsigned num_total_rejected_cs;
    uint32_t next_bo_unique_id;
    uint64_t allocated_vram;
    uint64_t allocated_gtt;