[PATCH v2] drm/amdgpu: replace VM fault error by info logs
Alex Sierra
alex.sierra at amd.com
Sat Apr 23 02:24:45 UTC 2022
This is not a kernel error. These logs are caused by VM faults that
could not be handled. Typically, generated by user mode applications.
Signed-off-by: Alex Sierra <alex.sierra at amd.com>
---
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c | 14 +++++++-------
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c | 14 +++++++-------
drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 4 ++--
drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 8 ++++----
drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 8 ++++----
drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 8 ++++----
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 20 ++++++++++----------
drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 14 +++++++-------
drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c | 14 +++++++-------
9 files changed, 52 insertions(+), 52 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 6e0ace2fbfab..c226a4803086 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -79,25 +79,25 @@ gfxhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
u32 cid = REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, CID);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"GCVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
status);
- dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+ dev_info(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
cid >= ARRAY_SIZE(gfxhub_client_ids) ? "unknown" : gfxhub_client_ids[cid],
cid);
- dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
- dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
- dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
- dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
- dev_err(adev->dev, "\t RW: 0x%lx\n",
+ dev_info(adev->dev, "\t RW: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, RW));
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index ff738e9725ee..fdcca1477592 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -82,25 +82,25 @@ gfxhub_v2_1_print_l2_protection_fault_status(struct amdgpu_device *adev,
u32 cid = REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, CID);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"GCVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
status);
- dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+ dev_info(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
cid >= ARRAY_SIZE(gfxhub_client_ids) ? "unknown" : gfxhub_client_ids[cid],
cid);
- dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
- dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
- dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
- dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
- dev_err(adev->dev, "\t RW: 0x%lx\n",
+ dev_info(adev->dev, "\t RW: 0x%lx\n",
REG_GET_FIELD(status,
GCVM_L2_PROTECTION_FAULT_STATUS, RW));
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index a455e59f41f4..864fcc0edb90 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -148,14 +148,14 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
memset(&task_info, 0, sizeof(struct amdgpu_task_info));
amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u, "
"for process %s pid %d thread %s pid %d)\n",
entry->vmid_src ? "mmhub" : "gfxhub",
entry->src_id, entry->ring_id, entry->vmid,
entry->pasid, task_info.process_name, task_info.tgid,
task_info.task_name, task_info.pid);
- dev_err(adev->dev, " in page starting at address 0x%016llx from client 0x%x (%s)\n",
+ dev_info(adev->dev, " in page starting at address 0x%016llx from client 0x%x (%s)\n",
addr, entry->client_id,
soc15_ih_clientid_name[entry->client_id]);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index ec291d28edff..3d830fd7706b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -620,7 +620,7 @@ static void gmc_v6_0_vm_decode_fault(struct amdgpu_device *adev,
mc_id = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
MEMORY_CLIENT_ID);
- dev_err(adev->dev, "VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
+ dev_info(adev->dev, "VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
protections, vmid, addr,
REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
MEMORY_CLIENT_RW) ?
@@ -1083,11 +1083,11 @@ static int gmc_v6_0_process_interrupt(struct amdgpu_device *adev,
gmc_v6_0_set_fault_enable_default(adev, false);
if (printk_ratelimit()) {
- dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
+ dev_info(adev->dev, "GPU fault detected: %d 0x%08x\n",
entry->src_id, entry->src_data[0]);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
+ dev_info(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
addr);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+ dev_info(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v6_0_vm_decode_fault(adev, status, addr, 0);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 979da6f510e8..1f3ceb03b47b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -781,7 +781,7 @@ static void gmc_v7_0_vm_decode_fault(struct amdgpu_device *adev, u32 status,
mc_id = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
MEMORY_CLIENT_ID);
- dev_err(adev->dev, "VM fault (0x%02x, vmid %d, pasid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
+ dev_info(adev->dev, "VM fault (0x%02x, vmid %d, pasid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
protections, vmid, pasid, addr,
REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
MEMORY_CLIENT_RW) ?
@@ -1286,11 +1286,11 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
gmc_v7_0_set_fault_enable_default(adev, false);
if (printk_ratelimit()) {
- dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
+ dev_info(adev->dev, "GPU fault detected: %d 0x%08x\n",
entry->src_id, entry->src_data[0]);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
+ dev_info(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
addr);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+ dev_info(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v7_0_vm_decode_fault(adev, status, addr, mc_client,
entry->pasid);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 382dde1ce74c..5be3f4f77c49 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1021,7 +1021,7 @@ static void gmc_v8_0_vm_decode_fault(struct amdgpu_device *adev, u32 status,
mc_id = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
MEMORY_CLIENT_ID);
- dev_err(adev->dev, "VM fault (0x%02x, vmid %d, pasid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
+ dev_info(adev->dev, "VM fault (0x%02x, vmid %d, pasid %d) at page %u, %s from '%s' (0x%08x) (%d)\n",
protections, vmid, pasid, addr,
REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
MEMORY_CLIENT_RW) ?
@@ -1466,12 +1466,12 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
memset(&task_info, 0, sizeof(struct amdgpu_task_info));
amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
- dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
+ dev_info(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
entry->src_id, entry->src_data[0], task_info.process_name,
task_info.tgid, task_info.task_name, task_info.pid);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
+ dev_info(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n",
addr);
- dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
+ dev_info(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
status);
gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client,
entry->pasid);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 22761a3bb818..98c8de7307be 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -582,14 +582,14 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
memset(&task_info, 0, sizeof(struct amdgpu_task_info));
amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"[%s] %s page fault (src_id:%u ring:%u vmid:%u "
"pasid:%u, for process %s pid %d thread %s pid %d)\n",
hub_name, retry_fault ? "retry" : "no-retry",
entry->src_id, entry->ring_id, entry->vmid,
entry->pasid, task_info.process_name, task_info.tgid,
task_info.task_name, task_info.pid);
- dev_err(adev->dev, " in page starting at address 0x%016llx from IH client 0x%x (%s)\n",
+ dev_info(adev->dev, " in page starting at address 0x%016llx from IH client 0x%x (%s)\n",
addr, entry->client_id,
soc15_ih_clientid_name[entry->client_id]);
@@ -611,11 +611,11 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
status);
if (hub == &adev->vmhub[AMDGPU_GFXHUB_0]) {
- dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+ dev_info(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
cid >= ARRAY_SIZE(gfxhub_client_ids) ? "unknown" :
gfxhub_client_ids[cid],
cid);
@@ -648,22 +648,22 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
mmhub_cid = NULL;
break;
}
- dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+ dev_info(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
mmhub_cid ? mmhub_cid : "unknown", cid);
}
- dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
VM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
- dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
VM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
- dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
VM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
- dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
VM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
- dev_err(adev->dev, "\t RW: 0x%x\n", rw);
+ dev_info(adev->dev, "\t RW: 0x%x\n", rw);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 636abd855686..ec8c8b2cab36 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -150,7 +150,7 @@ mmhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
rw = REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, RW);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"MMVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
status);
switch (adev->ip_versions[MMHUB_HWIP][0]) {
@@ -169,21 +169,21 @@ mmhub_v2_0_print_l2_protection_fault_status(struct amdgpu_device *adev,
mmhub_cid = NULL;
break;
}
- dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+ dev_info(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
mmhub_cid ? mmhub_cid : "unknown", cid);
- dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
- dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
- dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
- dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
- dev_err(adev->dev, "\t RW: 0x%x\n", rw);
+ dev_info(adev->dev, "\t RW: 0x%x\n", rw);
}
static void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index ff44c5364a8c..72dda850e7d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -87,7 +87,7 @@ mmhub_v2_3_print_l2_protection_fault_status(struct amdgpu_device *adev,
rw = REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, RW);
- dev_err(adev->dev,
+ dev_info(adev->dev,
"MMVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
status);
switch (adev->ip_versions[MMHUB_HWIP][0]) {
@@ -100,21 +100,21 @@ mmhub_v2_3_print_l2_protection_fault_status(struct amdgpu_device *adev,
mmhub_cid = NULL;
break;
}
- dev_err(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
+ dev_info(adev->dev, "\t Faulty UTCL2 client ID: %s (0x%x)\n",
mmhub_cid ? mmhub_cid : "unknown", cid);
- dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
- dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
- dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
+ dev_info(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
- dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
+ dev_info(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
REG_GET_FIELD(status,
MMVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
- dev_err(adev->dev, "\t RW: 0x%x\n", rw);
+ dev_info(adev->dev, "\t RW: 0x%x\n", rw);
}
static void mmhub_v2_3_setup_vm_pt_regs(struct amdgpu_device *adev,
--
2.32.0
More information about the amd-gfx
mailing list