Right now it's possible to trigger fence_drv.fences[] dereference after
the array has been freed. While the real problem is elsewhere, this still
results in confusing errors that depend on how the freed memory was
reused (I've seen "kernel tried to execute NX-protected page"), it's
better to clear them and get NULL dereference so that it's obvious what's
going wrong.
Signed-off-by: Grazvydas Ignotas <nota...@gmail.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 1 +
2 files changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 17e1362..e203e55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -60,6 +60,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, struct
amdgpu_ctx *ctx)
amd_sched_entity_fini(&adev->rings[j]->sched,
&ctx->rings[j].entity);
kfree(ctx->fences);
+ ctx->fences = NULL;
return r;
}
return 0;
@@ -77,6 +78,7 @@ static void amdgpu_ctx_fini(struct amdgpu_ctx *ctx)
for (j = 0; j < amdgpu_sched_jobs; ++j)
fence_put(ctx->rings[i].fences[j]);
kfree(ctx->fences);
+ ctx->fences = NULL;
for (i = 0; i < adev->num_rings; i++)
amd_sched_entity_fini(&adev->rings[i]->sched,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 0b109ae..3a2e42f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -454,6 +454,7 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
fence_put(ring->fence_drv.fences[j]);
kfree(ring->fence_drv.fences);
+ ring->fence_drv.fences = NULL;
ring->fence_drv.initialized = false;
}
}
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
