drm/amdgpu:make ctx_add_fence interruptible(v2)

otherwise a gpu hang will make application couldn't be killed
under timedout=0 mode

v2:
Fix memoryleak job/job->s_fence issue
unlock mn
remove the ERROR msg after waiting being interrupted

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 7 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index a11e44340b23..75c933b1a432 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -246,8 +246,8 @@ int amdgpu_ctx_put(struct amdgpu_ctx *ctx)
         return 0;
 }
 
-uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
-                              struct dma_fence *fence)
+int amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
+                              struct dma_fence *fence, uint64_t* handler)
 {
         struct amdgpu_ctx_ring *cring = & ctx->rings[ring->idx];
         uint64_t seq = cring->sequence;
@@ -258,9 +258,9 @@ uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
         other = cring->fences[idx];
         if (other) {
                 signed long r;
-                r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT);
+                r = dma_fence_wait_timeout(other, true, MAX_SCHEDULE_TIMEOUT);
                 if (r < 0)
-                        DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+                        return r;
         }
 
         dma_fence_get(fence);
@@ -271,8 +271,10 @@ uint64_t amdgpu_ctx_add_fence(struct amdgpu_ctx *ctx, struct amdgpu_ring *ring,
         spin_unlock(&ctx->ring_lock);
 
         dma_fence_put(other);
+        if (handler)
+                *handler = seq;
 
-        return seq;
+        return 0;
 }
 
 struct dma_fence *amdgpu_ctx_get_fence(struct amdgpu_ctx *ctx,