drm/amdgpu: handle the case of pci_channel_io_frozen only in amdgpu_pci_resume

In current code, when a PCI error state pci_channel_io_normal is detectd,
it will report PCI_ERS_RESULT_CAN_RECOVER status to PCI driver, and PCI
driver will continue the execution of PCI resume callback report_resume by
pci_walk_bridge, and the callback will go into amdgpu_pci_resume
finally, where write lock is releasd unconditionally without acquiring
such lock first. In this case, a deadlock will happen when other threads
start to acquire the read lock.

To fix this, add a member in amdgpu_device strucutre to cache
pci_channel_state, and only continue the execution in amdgpu_pci_resume
when it's pci_channel_io_frozen.

Fixes: c9a6b82f45e2 ("drm/amdgpu: Implement DPC recovery")
Suggested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index eb1c117e82b4545a57cd108db788caa228585138..d58e37fd01f47595616904e4c112523ec40fe30e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1092,6 +1092,7 @@ struct amdgpu_device {
 
        bool                            no_hw_access;
        struct pci_saved_state          *pci_state;
+       pci_channel_state_t             pci_channel_state;
 
        struct amdgpu_reset_control     *reset_cntl;
        uint32_t                        ip_versions[HW_ID_MAX][HWIP_MAX_INSTANCE];

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b5f72724d4492ab84254c63a2ce6c914bf8f1cff..cda04918fd55520318c5c38bc804489fad817bb1 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5371,6 +5371,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
                return PCI_ERS_RESULT_DISCONNECT;
        }
 
+       adev->pci_channel_state = state;
+
        switch (state) {
        case pci_channel_io_normal:
                return PCI_ERS_RESULT_CAN_RECOVER;
@@ -5513,6 +5515,10 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
        DRM_INFO("PCI error: resume callback!!\n");
 
+       /* Only continue execution for the case of pci_channel_io_frozen */
+       if (adev->pci_channel_state != pci_channel_io_frozen)
+               return;
+
        for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
                struct amdgpu_ring *ring = adev->rings[i];