On 02.07.25 19:10, vitaly.pros...@amd.com wrote:
> From: Vitaly Prosyak <vitaly.pros...@amd.com>
>
> This reverts commit 0203ef5eb3b2a3a10dd31bac8fc2fa3b439cbb09.
>
> The original patch moved `amdgpu_userq_mgr_fini()` to the driver's `postclose`
> callback, which is called after `drm_gem_release()` in the DRM file cleanup
> sequence. If a user application crashes or aborts without cleaning up its
> user queues,
> 'drm_gem_release()` may free GEM objects that are still referenced by active
> user queues, leading to use-after-free. By reverting, we ensure that user
> queues are
> disabled and cleaned up before any GEM objects are released, preventing this
> class of bug.
> However, this reintroduces a race during PCI hot-unplug, where device removal
> can
> race with per-file cleanup, leading to use-after-free in suspend/unplug paths.
> This will be fixed in the next patch.
>
> Cc: Alex Deucher <alexander.deuc...@amd.com>
> Cc: Christian Koenig <christian.koe...@amd.com>
> Signed-off-by Vitaly Prosyak <vitaly.pros...@amd.com>
Reviewed-by: Christian König <christian.koe...@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 +++++++++++++++-
> drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 3 ---
> 2 files changed, 15 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 4f8632737574..1c54b2e5a225 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -2911,6 +2911,20 @@ static int amdgpu_pmops_runtime_idle(struct device
> *dev)
> return ret;
> }
>
> +static int amdgpu_drm_release(struct inode *inode, struct file *filp)
> +{
> + struct drm_file *file_priv = filp->private_data;
> + struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
> +
> + if (fpriv) {
> + fpriv->evf_mgr.fd_closing = true;
> + amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
> + amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
> + }
> +
> + return drm_release(inode, filp);
> +}
> +
> long amdgpu_drm_ioctl(struct file *filp,
> unsigned int cmd, unsigned long arg)
> {
> @@ -2962,7 +2976,7 @@ static const struct file_operations
> amdgpu_driver_kms_fops = {
> .owner = THIS_MODULE,
> .open = drm_open,
> .flush = amdgpu_flush,
> - .release = drm_release,
> + .release = amdgpu_drm_release,
> .unlocked_ioctl = amdgpu_drm_ioctl,
> .mmap = drm_gem_mmap,
> .poll = drm_poll,
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> index 4aab5e394ce2..adba7d0ac147 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
> @@ -1521,9 +1521,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
> amdgpu_vm_bo_del(adev, fpriv->prt_va);
> amdgpu_bo_unreserve(pd);
> }
> - fpriv->evf_mgr.fd_closing = true;
> - amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
> - amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
>
> amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr);
> amdgpu_vm_fini(adev, &fpriv->vm);
