RE: [PATCH V4 1/1] drm/amdgpu: update athub interrupt harvesting handle
[AMD Public Use]
Reviewed-by: Hawking Zhang
Regards,
Hawking
-Original Message-
From: Stanley.Yang
Sent: Monday, September 21, 2020 21:48
To: amd-gfx@lists.freedesktop.org
Cc: Zhang, Hawking ; Chen, Guchun ;
Clements, John ; Li, Dennis ; Zhou1,
Tao ; Yang, Stanley
Subject: [PATCH V4 1/1] drm/amdgpu: update athub interrupt harvesting handle
GCEA/MMHUB EA error should not result to DF freeze, this is fixed in next
generation, but for some reasons the GCEA/MMHUB EA error will result to DF
freeze in previous generation, diver should avoid to indicate GCEA/MMHUB EA
error as hw fatal error in kernel message by read GCEA/MMHUB err status
registers.
Changed from V1:
make query_ras_error_status function more general
make read mmhub er status register more friendly
Changed from V2:
move ras error status query function into do_recovery workqueue
Changed from V3:
remove useless code from V2, print GCEA error status
instance number
Signed-off-by: Stanley.Yang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 43 ++-
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c | 29 +
drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h | 2 +
drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 29 +
.../amd/include/asic_reg/gc/gc_9_4_1_offset.h | 4 +-
8 files changed, 108 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index a611e78dd4ba..258498cbf1eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -217,6 +217,7 @@ struct amdgpu_gfx_funcs {
int (*query_ras_error_count) (struct amdgpu_device *adev, void
*ras_error_status);
void (*reset_ras_error_count) (struct amdgpu_device *adev);
void (*init_spm_golden)(struct amdgpu_device *adev);
+ void (*query_ras_error_status) (struct amdgpu_device *adev);
};
struct sq_work {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
index 0c43d7fe893c..1ae9bdae7311 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
@@ -40,6 +40,7 @@ struct amdgpu_mmhub_funcs {
uint64_t page_table_base);
void (*update_power_gating)(struct amdgpu_device *adev,
bool enable);
+ void (*query_ras_error_status)(struct amdgpu_device *adev);
};
struct amdgpu_mmhub {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e5ea14774c0c..40614ac9a111 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1498,6 +1498,45 @@ static void amdgpu_ras_log_on_err_counter(struct
amdgpu_device *adev)
}
}
+/* Parse RdRspStatus and WrRspStatus */ void
+amdgpu_ras_error_status_query(struct amdgpu_device *adev,
+ struct ras_query_if *info)
+{
+ /*
+* Only two block need to query read/write
+* RspStatus at current state
+*/
+ switch (info->head.block) {
+ case AMDGPU_RAS_BLOCK__GFX:
+ if (adev->gfx.funcs->query_ras_error_status)
+ adev->gfx.funcs->query_ras_error_status(adev);
+ break;
+ case AMDGPU_RAS_BLOCK__MMHUB:
+ if (adev->mmhub.funcs->query_ras_error_status)
+ adev->mmhub.funcs->query_ras_error_status(adev);
+ break;
+ default:
+ break;
+ }
+}
+
+static void amdgpu_ras_query_err_status(struct amdgpu_device *adev) {
+ struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+ struct ras_manager *obj;
+
+ if (!con)
+ return;
+
+ list_for_each_entry(obj, >head, node) {
+ struct ras_query_if info = {
+ .head = obj->head,
+ };
+
+ amdgpu_ras_error_status_query(adev, );
+ }
+}
+
/* recovery begin */
/* return 0 on success.
@@ -1568,8 +1607,10 @@ static void amdgpu_ras_do_recovery(struct work_struct
*work)
}
list_for_each_entry(remote_adev,
- device_list_handle, gmc.xgmi.head)
+ device_list_handle, gmc.xgmi.head) {
+ amdgpu_ras_query_err_status(remote_adev);
amdgpu_ras_log_on_err_counter(remote_adev);
+ }
amdgpu_put_xgmi_hive(hive);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d898c9ff3526..adee0177654e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@
[PATCH V4 1/1] drm/amdgpu: update athub interrupt harvesting handle
GCEA/MMHUB EA error should not result to DF freeze, this is
fixed in next generation, but for some reasons the GCEA/MMHUB
EA error will result to DF freeze in previous generation,
diver should avoid to indicate GCEA/MMHUB EA error as hw fatal
error in kernel message by read GCEA/MMHUB err status registers.
Changed from V1:
make query_ras_error_status function more general
make read mmhub er status register more friendly
Changed from V2:
move ras error status query function into do_recovery workqueue
Changed from V3:
remove useless code from V2, print GCEA error status
instance number
Signed-off-by: Stanley.Yang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 43 ++-
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 1 +
drivers/gpu/drm/amd/amdgpu/gfx_v9_4.c | 29 +
drivers/gpu/drm/amd/amdgpu/gfx_v9_4.h | 2 +
drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 29 +
.../amd/include/asic_reg/gc/gc_9_4_1_offset.h | 4 +-
8 files changed, 108 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index a611e78dd4ba..258498cbf1eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -217,6 +217,7 @@ struct amdgpu_gfx_funcs {
int (*query_ras_error_count) (struct amdgpu_device *adev, void
*ras_error_status);
void (*reset_ras_error_count) (struct amdgpu_device *adev);
void (*init_spm_golden)(struct amdgpu_device *adev);
+ void (*query_ras_error_status) (struct amdgpu_device *adev);
};
struct sq_work {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
index 0c43d7fe893c..1ae9bdae7311 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
@@ -40,6 +40,7 @@ struct amdgpu_mmhub_funcs {
uint64_t page_table_base);
void (*update_power_gating)(struct amdgpu_device *adev,
bool enable);
+ void (*query_ras_error_status)(struct amdgpu_device *adev);
};
struct amdgpu_mmhub {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e5ea14774c0c..40614ac9a111 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1498,6 +1498,45 @@ static void amdgpu_ras_log_on_err_counter(struct
amdgpu_device *adev)
}
}
+/* Parse RdRspStatus and WrRspStatus */
+void amdgpu_ras_error_status_query(struct amdgpu_device *adev,
+ struct ras_query_if *info)
+{
+ /*
+* Only two block need to query read/write
+* RspStatus at current state
+*/
+ switch (info->head.block) {
+ case AMDGPU_RAS_BLOCK__GFX:
+ if (adev->gfx.funcs->query_ras_error_status)
+ adev->gfx.funcs->query_ras_error_status(adev);
+ break;
+ case AMDGPU_RAS_BLOCK__MMHUB:
+ if (adev->mmhub.funcs->query_ras_error_status)
+ adev->mmhub.funcs->query_ras_error_status(adev);
+ break;
+ default:
+ break;
+ }
+}
+
+static void amdgpu_ras_query_err_status(struct amdgpu_device *adev)
+{
+ struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+ struct ras_manager *obj;
+
+ if (!con)
+ return;
+
+ list_for_each_entry(obj, >head, node) {
+ struct ras_query_if info = {
+ .head = obj->head,
+ };
+
+ amdgpu_ras_error_status_query(adev, );
+ }
+}
+
/* recovery begin */
/* return 0 on success.
@@ -1568,8 +1607,10 @@ static void amdgpu_ras_do_recovery(struct work_struct
*work)
}
list_for_each_entry(remote_adev,
- device_list_handle, gmc.xgmi.head)
+ device_list_handle, gmc.xgmi.head) {
+ amdgpu_ras_query_err_status(remote_adev);
amdgpu_ras_log_on_err_counter(remote_adev);
+ }
amdgpu_put_xgmi_hive(hive);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d898c9ff3526..adee0177654e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2075,6 +2075,7 @@ static const struct amdgpu_gfx_funcs gfx_v9_4_gfx_funcs =
{
.ras_error_inject = _v9_4_ras_error_inject,
.query_ras_error_count = _v9_4_query_ras_error_count,
.reset_ras_error_count = _v9_4_reset_ras_error_count,
+ .query_ras_error_status = _v9_4_query_ras_error_status,
};
static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
diff
