[PATCH V3 04/12] drm/amdgpu: Modify xgmi block to fit for the unified ras block data and ops

yipechai YiPeng.Chai at amd.com
Wed Dec 29 06:32:03 UTC 2021


1.Modify gmc block to fit for the unified ras block data and ops.
2.Change amdgpu_xgmi_ras_funcs to amdgpu_xgmi_ras, and the corresponding variable name remove _funcs suffix.
3.Remove the const flag of gmc ras variable so that gmc ras block can be able to be inserted into amdgpu device ras block link list.
4.Invoke amdgpu_ras_register_ras_block function to register gmc ras block into amdgpu device ras block link list.
5.Remove the redundant code about gmc in amdgpu_ras.c after using the unified ras block.

Signed-off-by: yipechai <YiPeng.Chai at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c  | 16 +++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h  | 11 ++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c  | 10 ++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 26 +++++++++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h |  4 ++--
 5 files changed, 37 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 83f26bca7dac..af65ec46f783 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -448,12 +448,13 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev)
 			return r;
 	}
 
-	if (!adev->gmc.xgmi.connected_to_cpu)
-		adev->gmc.xgmi.ras_funcs = &xgmi_ras_funcs;
+	if (!adev->gmc.xgmi.connected_to_cpu) {
+		adev->gmc.xgmi.ras = &xgmi_ras;
+		amdgpu_ras_register_ras_block(adev, &adev->gmc.xgmi.ras->ras_block);
+	}
 
-	if (adev->gmc.xgmi.ras_funcs &&
-	    adev->gmc.xgmi.ras_funcs->ras_late_init) {
-		r = adev->gmc.xgmi.ras_funcs->ras_late_init(adev);
+	if (adev->gmc.xgmi.ras && adev->gmc.xgmi.ras->ras_block.ras_late_init) {
+		r = adev->gmc.xgmi.ras->ras_block.ras_late_init(adev, NULL);
 		if (r)
 			return r;
 	}
@@ -499,9 +500,8 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev)
 	    adev->mmhub.ras_funcs->ras_fini)
 		adev->mmhub.ras_funcs->ras_fini(adev);
 
-	if (adev->gmc.xgmi.ras_funcs &&
-	    adev->gmc.xgmi.ras_funcs->ras_fini)
-		adev->gmc.xgmi.ras_funcs->ras_fini(adev);
+	if (adev->gmc.xgmi.ras && adev->gmc.xgmi.ras->ras_block.ras_fini)
+		adev->gmc.xgmi.ras->ras_block.ras_fini(adev);
 
 	if (adev->hdp.ras_funcs &&
 	    adev->hdp.ras_funcs->ras_fini)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index e55201134a01..923db5ff5859 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -29,6 +29,7 @@
 #include <linux/types.h>
 
 #include "amdgpu_irq.h"
+#include "amdgpu_ras.h"
 
 /* VA hole for 48bit addresses on Vega10 */
 #define AMDGPU_GMC_HOLE_START	0x0000800000000000ULL
@@ -135,12 +136,8 @@ struct amdgpu_gmc_funcs {
 	unsigned int (*get_vbios_fb_size)(struct amdgpu_device *adev);
 };
 
-struct amdgpu_xgmi_ras_funcs {
-	int (*ras_late_init)(struct amdgpu_device *adev);
-	void (*ras_fini)(struct amdgpu_device *adev);
-	int (*query_ras_error_count)(struct amdgpu_device *adev,
-				     void *ras_error_status);
-	void (*reset_ras_error_count)(struct amdgpu_device *adev);
+struct amdgpu_xgmi_ras {
+	struct amdgpu_ras_block_object ras_block;
 };
 
 struct amdgpu_xgmi {
@@ -159,7 +156,7 @@ struct amdgpu_xgmi {
 	struct ras_common_if *ras_if;
 	bool connected_to_cpu;
 	bool pending_reset;
-	const struct amdgpu_xgmi_ras_funcs *ras_funcs;
+	struct amdgpu_xgmi_ras *ras;
 };
 
 struct amdgpu_gmc {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 8ca1f294c202..8b0d11bb8186 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -982,9 +982,13 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 			adev->nbio.ras_funcs->query_ras_error_count(adev, &err_data);
 		break;
 	case AMDGPU_RAS_BLOCK__XGMI_WAFL:
-		if (adev->gmc.xgmi.ras_funcs &&
-		    adev->gmc.xgmi.ras_funcs->query_ras_error_count)
-			adev->gmc.xgmi.ras_funcs->query_ras_error_count(adev, &err_data);
+		if (!block_obj || !block_obj->hw_ops)	{
+			dev_info(adev->dev, "%s doesn't config ras function \n",
+				get_ras_block_str(&info->head));
+			return -EINVAL;
+		}
+		if (block_obj->hw_ops->query_ras_error_count)
+			block_obj->hw_ops->query_ras_error_count(adev, &err_data);
 		break;
 	case AMDGPU_RAS_BLOCK__HDP:
 		if (adev->hdp.ras_funcs &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 0d149f5f000e..e3c6898c5d13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -725,7 +725,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 	return psp_xgmi_terminate(&adev->psp);
 }
 
-static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
+static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, void *ras_info)
 {
 	int r;
 	struct ras_ih_if ih_info = {
@@ -739,7 +739,7 @@ static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
 	    adev->gmc.xgmi.num_physical_nodes == 0)
 		return 0;
 
-	adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev);
+	adev->gmc.xgmi.ras->ras_block.hw_ops->reset_ras_error_count(adev);
 
 	if (!adev->gmc.xgmi.ras_if) {
 		adev->gmc.xgmi.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
@@ -859,7 +859,7 @@ static int amdgpu_xgmi_query_pcs_error_status(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
+static void amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 					     void *ras_error_status)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
@@ -868,7 +868,7 @@ static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 	uint32_t ue_cnt = 0, ce_cnt = 0;
 
 	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL))
-		return -EINVAL;
+		return ;
 
 	err_data->ue_count = 0;
 	err_data->ce_count = 0;
@@ -934,17 +934,23 @@ static int amdgpu_xgmi_query_ras_error_count(struct amdgpu_device *adev,
 		break;
 	}
 
-	adev->gmc.xgmi.ras_funcs->reset_ras_error_count(adev);
+	adev->gmc.xgmi.ras->ras_block.hw_ops->reset_ras_error_count(adev);
 
 	err_data->ue_count += ue_cnt;
 	err_data->ce_count += ce_cnt;
-
-	return 0;
 }
 
-const struct amdgpu_xgmi_ras_funcs xgmi_ras_funcs = {
-	.ras_late_init = amdgpu_xgmi_ras_late_init,
-	.ras_fini = amdgpu_xgmi_ras_fini,
+struct amdgpu_ras_block_hw_ops  xgmi_ras_hw_ops = {
 	.query_ras_error_count = amdgpu_xgmi_query_ras_error_count,
 	.reset_ras_error_count = amdgpu_xgmi_reset_ras_error_count,
 };
+
+struct amdgpu_xgmi_ras xgmi_ras = {
+	.ras_block = {
+		.name = "xgmi",
+		.block = AMDGPU_RAS_BLOCK__XGMI_WAFL,
+		.hw_ops = &xgmi_ras_hw_ops,
+		.ras_late_init = amdgpu_xgmi_ras_late_init,
+		.ras_fini = amdgpu_xgmi_ras_fini,
+	},
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index d2189bf7d428..0afca51c3c0c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -24,7 +24,7 @@
 
 #include <drm/task_barrier.h>
 #include "amdgpu_psp.h"
-
+#include "amdgpu_ras.h"
 
 struct amdgpu_hive_info {
 	struct kobject kobj;
@@ -50,7 +50,7 @@ struct amdgpu_pcs_ras_field {
 	uint32_t pcs_err_shift;
 };
 
-extern const struct amdgpu_xgmi_ras_funcs xgmi_ras_funcs;
+extern struct amdgpu_xgmi_ras  xgmi_ras;
 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev);
 void amdgpu_put_xgmi_hive(struct amdgpu_hive_info *hive);
 int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_device *adev);
-- 
2.25.1



More information about the amd-gfx mailing list