amdgpu: Wrap dev_err() calls on vm faults with printk_ratelimit()
It can be the case that upon GPU page faults we start trashing
the logs, and so let us ratelimit here to avoid that.
V2. Fix issue where calling dev_err_ratelimited separately for
each line means that some lines corresponding to a single
VM fault may or may not appear depending on the rate.
- Michel Dänzer.
Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Signed-off-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 3b6ad84..64d3c1e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -1036,13 +1036,15 @@ static int gmc_v6_0_process_interrupt(struct amdgpu_device *adev,
if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
gmc_v6_0_set_fault_enable_default(adev, false);
- dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
- entry->src_id, entry->src_data);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
- addr);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
- status);
- gmc_v6_0_vm_decode_fault(adev, status, addr, 0);
+ if (printk_ratelimit()) {
+ dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
+ entry->src_id, entry->src_data);
+ dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
+ addr);
+ dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+ status);
+ gmc_v6_0_vm_decode_fault(adev, status, addr, 0);
+ }
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 18a0612..fbe1d9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1198,13 +1198,15 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
gmc_v7_0_set_fault_enable_default(adev, false);
- dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
- entry->src_id, entry->src_data);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
- addr);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
- status);
- gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client);
+ if (printk_ratelimit()) {
+ dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
+ entry->src_id, entry->src_data);
+ dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
+ addr);
+ dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+ status);
+ gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client);
+ }
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index af2c6cc..12ea3404 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1242,13 +1242,15 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
gmc_v8_0_set_fault_enable_default(adev, false);
- dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
- entry->src_id, entry->src_data);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
- addr);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
- status);
- gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client);
+ if (printk_ratelimit()) {
+ dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
+ entry->src_id, entry->src_data);
+ dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
+ addr);
+ dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+ status);
+ gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client);
+ }
return 0;
}