drm/amdgpu: SRIOV flr_work should take write_lock

[Why]
If flr_work takes read_lock, then other threads who takes
read_lock can access hardware when host is doing vf flr.

[How]
flr_work should take write_lock to avoid this case.

Signed-off-by: Jingwen Chen <Jingwen.Chen2@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 3ee481557fc9741b480284c8330e48723e0b0d5b..ff2307d7ee0fa72dd1064192dc71bc16b1310146 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -252,7 +252,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
         * otherwise the mailbox msg will be ruined/reseted by
         * the VF FLR.
         */
-       if (!down_read_trylock(&adev->reset_sem))
+       if (!down_write_trylock(&adev->reset_sem))
                return;
 
        amdgpu_virt_fini_data_exchange(adev);
@@ -268,7 +268,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
        atomic_set(&adev->in_gpu_reset, 0);
-       up_read(&adev->reset_sem);
+       up_write(&adev->reset_sem);
 
        /* Trigger recovery for world switch failure if no TDR */
        if (amdgpu_device_should_recover_gpu(adev)

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 48e588d3c4098c84dcd5900426c235463eb962f9..9f7aac435d695e93b871c7c8c32e1326c33aee4f 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -273,7 +273,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
         * otherwise the mailbox msg will be ruined/reseted by
         * the VF FLR.
         */
-       if (!down_read_trylock(&adev->reset_sem))
+       if (!down_write_trylock(&adev->reset_sem))
                return;
 
        amdgpu_virt_fini_data_exchange(adev);
@@ -289,7 +289,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
        atomic_set(&adev->in_gpu_reset, 0);
-       up_read(&adev->reset_sem);
+       up_write(&adev->reset_sem);
 
        /* Trigger recovery for world switch failure if no TDR */
        if (amdgpu_device_should_recover_gpu(adev)