From 248b061689a40f4fed05252ee2c89f87cf26d7d8 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Fri, 1 Oct 2021 09:48:50 +0800 Subject: [PATCH] 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 Signed-off-by: Guchun Chen Reviewed-by: Andrey Grodzovsky Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d356e329e6f8..269437b01328 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1087,6 +1087,7 @@ 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; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 53f3e07f6bd4..af9bdf16eefd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5399,6 +5399,8 @@ 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; @@ -5541,6 +5543,10 @@ 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]; -- 2.11.0