drm/amdgpu: Modify mmhub block to fit for the unified ras block data and ops

1.Modify mmhub block to fit for the unified ras block data and ops.
2.Change amdgpu_mmhub_ras_funcs to amdgpu_mmhub_ras, and the corresponding variable name remove _funcs suffix.
3.Remove the const flag of mmhub ras variable so that mmhub 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 mmhub ras block into amdgpu device ras block link list. 5.Remove the redundant code about mmhub in amdgpu_ras.c after using the unified ras block.
5.Remove the redundant code about mmhub in amdgpu_ras.c after using the unified ras block.
6.Fill unified ras block .name .block .ras_late_init and .ras_fini for all of mmhub versions. If .ras_late_init and .ras_fini had been defined by the selected mmhub version, the defined functions will take effect; if not defined, default fill them with amdgpu_mmhub_ras_late_init and amdgpu_mmhub_ras_fini.
Signed-off-by: yipechai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3307,9 +3307,9 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 		if (adev->asic_reset_res)
 			goto fail;
 
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->reset_ras_error_count)
-			adev->mmhub.ras_funcs->reset_ras_error_count(adev);
+		if (adev->mmhub.ras && adev->mmhub.ras->ras_block.hw_ops &&
+		    adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count)
+			adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count(adev);
 	} else {
 
 		task_barrier_full(&hive->tb);
@@ -4656,9 +4656,9 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 
 	if (!r && amdgpu_ras_intr_triggered()) {
 		list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-			if (tmp_adev->mmhub.ras_funcs &&
-			    tmp_adev->mmhub.ras_funcs->reset_ras_error_count)
-				tmp_adev->mmhub.ras_funcs->reset_ras_error_count(tmp_adev);
+			if (tmp_adev->mmhub.ras && tmp_adev->mmhub.ras->ras_block.hw_ops &&
+			    tmp_adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count)
+				tmp_adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count(tmp_adev);
 		}
 
 		amdgpu_ras_intr_cleared();

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

@@ -447,9 +447,8 @@ int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev)
 			return r;
 	}
 
-	if (adev->mmhub.ras_funcs &&
-	    adev->mmhub.ras_funcs->ras_late_init) {
-		r = adev->mmhub.ras_funcs->ras_late_init(adev);
+	if (adev->mmhub.ras && adev->mmhub.ras->ras_block.ras_late_init) {
+		r = adev->mmhub.ras->ras_block.ras_late_init(adev, NULL);
 		if (r)
 			return r;
 	}
@@ -501,9 +500,8 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev)
 	    adev->umc.ras_funcs->ras_fini)
 		adev->umc.ras_funcs->ras_fini(adev);
 
-	if (adev->mmhub.ras_funcs &&
-	    adev->mmhub.ras_funcs->ras_fini)
-		adev->mmhub.ras_funcs->ras_fini(adev);
+	if (adev->mmhub.ras && adev->mmhub.ras->ras_block.ras_fini)
+		adev->mmhub.ras->ras_block.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);

drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c

@@ -24,7 +24,7 @@
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
 
-int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev)
+int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev, void *ras_info)
 {
 	int r;
 	struct ras_ih_if ih_info = {

drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h

@@ -21,14 +21,8 @@
 #ifndef __AMDGPU_MMHUB_H__
 #define __AMDGPU_MMHUB_H__
 
-struct amdgpu_mmhub_ras_funcs {
-	int (*ras_late_init)(struct amdgpu_device *adev);
-	void (*ras_fini)(struct amdgpu_device *adev);
-	void (*query_ras_error_count)(struct amdgpu_device *adev,
-				      void *ras_error_status);
-	void (*query_ras_error_status)(struct amdgpu_device *adev);
-	void (*reset_ras_error_count)(struct amdgpu_device *adev);
-	void (*reset_ras_error_status)(struct amdgpu_device *adev);
+struct amdgpu_mmhub_ras {
+	struct amdgpu_ras_block_object ras_block;
 };
 
 struct amdgpu_mmhub_funcs {
@@ -50,10 +44,10 @@ struct amdgpu_mmhub_funcs {
 struct amdgpu_mmhub {
 	struct ras_common_if *ras_if;
 	const struct amdgpu_mmhub_funcs *funcs;
-	const struct amdgpu_mmhub_ras_funcs *ras_funcs;
+	struct amdgpu_mmhub_ras  *ras;
 };
 
-int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev);
+int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev, void *ras_info);
 void amdgpu_mmhub_ras_fini(struct amdgpu_device *adev);
 #endif
 

drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c

@@ -986,6 +986,7 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 		}
 		break;
 	case AMDGPU_RAS_BLOCK__GFX:
+	case AMDGPU_RAS_BLOCK__MMHUB:
 		if (!block_obj || !block_obj->hw_ops)   {
 			dev_info(adev->dev, "%s doesn't config ras function \n",
 						get_ras_block_str(&info->head));
@@ -997,15 +998,6 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
 		if (block_obj->hw_ops->query_ras_error_status)
 			block_obj->hw_ops->query_ras_error_status(adev);
 		break;
-	case AMDGPU_RAS_BLOCK__MMHUB:
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->query_ras_error_count)
-			adev->mmhub.ras_funcs->query_ras_error_count(adev, &err_data);
-
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->query_ras_error_status)
-			adev->mmhub.ras_funcs->query_ras_error_status(adev);
-		break;
 	case AMDGPU_RAS_BLOCK__PCIE_BIF:
 		if (adev->nbio.ras_funcs &&
 		    adev->nbio.ras_funcs->query_ras_error_count)
@@ -1089,6 +1081,7 @@ int amdgpu_ras_reset_error_status(struct amdgpu_device *adev,
 
 	switch (block) {
 	case AMDGPU_RAS_BLOCK__GFX:
+	case AMDGPU_RAS_BLOCK__MMHUB:
 		if (!block_obj || !block_obj->hw_ops)   {
 			dev_info(adev->dev, "%s doesn't config ras function \n", ras_block_str(block));
 			return -EINVAL;
@@ -1100,15 +1093,6 @@ int amdgpu_ras_reset_error_status(struct amdgpu_device *adev,
 		if (block_obj->hw_ops->reset_ras_error_status)
 			block_obj->hw_ops->reset_ras_error_status(adev);
 		break;
-	case AMDGPU_RAS_BLOCK__MMHUB:
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->reset_ras_error_count)
-			adev->mmhub.ras_funcs->reset_ras_error_count(adev);
-
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->reset_ras_error_status)
-			adev->mmhub.ras_funcs->reset_ras_error_status(adev);
-		break;
 	case AMDGPU_RAS_BLOCK__SDMA:
 		if (adev->sdma.funcs->reset_ras_error_count)
 			adev->sdma.funcs->reset_ras_error_count(adev);
@@ -1825,24 +1809,19 @@ static void amdgpu_ras_error_status_query(struct amdgpu_device *adev,
 	 * Only two block need to query read/write
 	 * RspStatus at current state
 	 */
-	switch (info->head.block) {
-	case AMDGPU_RAS_BLOCK__GFX:
-		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 ;
-		}
+	if ((info->head.block != AMDGPU_RAS_BLOCK__GFX) &&
+		(info->head.block != AMDGPU_RAS_BLOCK__MMHUB))
+		return ;
 
-		if (block_obj->hw_ops->query_ras_error_status)
-			block_obj->hw_ops->query_ras_error_status(adev);
-		break;
-	case AMDGPU_RAS_BLOCK__MMHUB:
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->query_ras_error_status)
-			adev->mmhub.ras_funcs->query_ras_error_status(adev);
-		break;
-	default:
-		break;
+	block_obj = amdgpu_ras_get_ras_block(adev, info->head.block, info->head.sub_block_index);
+	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 ;
 	}
+
+	if (block_obj->hw_ops->query_ras_error_status)
+	block_obj->hw_ops->query_ras_error_status(adev);
+
 }
 
 static void amdgpu_ras_query_err_status(struct amdgpu_device *adev)

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -1248,18 +1248,33 @@ static void gmc_v9_0_set_mmhub_ras_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->ip_versions[MMHUB_HWIP][0]) {
 	case IP_VERSION(9, 4, 0):
-		adev->mmhub.ras_funcs = &mmhub_v1_0_ras_funcs;
+		adev->mmhub.ras = &mmhub_v1_0_ras;
 		break;
 	case IP_VERSION(9, 4, 1):
-		adev->mmhub.ras_funcs = &mmhub_v9_4_ras_funcs;
+		adev->mmhub.ras = &mmhub_v9_4_ras;
 		break;
 	case IP_VERSION(9, 4, 2):
-		adev->mmhub.ras_funcs = &mmhub_v1_7_ras_funcs;
+		adev->mmhub.ras = &mmhub_v1_7_ras;
 		break;
 	default:
 		/* mmhub ras is not available */
 		break;
 	}
+
+	if (adev->mmhub.ras) {
+		amdgpu_ras_register_ras_block(adev, &adev->mmhub.ras->ras_block);
+
+		strcpy(adev->mmhub.ras->ras_block.name,"mmhub");
+		adev->mmhub.ras->ras_block.block = AMDGPU_RAS_BLOCK__MMHUB;
+
+		/* If don't define special ras_late_init function, use default ras_late_init */
+		if (!adev->mmhub.ras->ras_block.ras_late_init)
+			adev->mmhub.ras->ras_block.ras_late_init = amdgpu_mmhub_ras_late_init;
+
+		/* If don't define special ras_fini function, use default ras_fini */
+		if (!adev->mmhub.ras->ras_block.ras_fini)
+			adev->mmhub.ras->ras_block.ras_fini = amdgpu_mmhub_ras_fini;
+	}
 }
 
 static void gmc_v9_0_set_gfxhub_funcs(struct amdgpu_device *adev)
@@ -1343,9 +1358,9 @@ static int gmc_v9_0_late_init(void *handle)
 	}
 
 	if (!amdgpu_persistent_edc_harvesting_supported(adev)) {
-		if (adev->mmhub.ras_funcs &&
-		    adev->mmhub.ras_funcs->reset_ras_error_count)
-			adev->mmhub.ras_funcs->reset_ras_error_count(adev);
+		if (adev->mmhub.ras && adev->mmhub.ras->ras_block.hw_ops &&
+		    adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count)
+			adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count(adev);
 
 		if (adev->hdp.ras && adev->hdp.ras->ras_block.hw_ops &&
 		    adev->hdp.ras->ras_block.hw_ops->reset_ras_error_count)

drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c

@@ -774,13 +774,17 @@ static void mmhub_v1_0_reset_ras_error_count(struct amdgpu_device *adev)
 	}
 }
 
-const struct amdgpu_mmhub_ras_funcs mmhub_v1_0_ras_funcs = {
-	.ras_late_init = amdgpu_mmhub_ras_late_init,
-	.ras_fini = amdgpu_mmhub_ras_fini,
+struct amdgpu_ras_block_hw_ops mmhub_v1_0_ras_hw_ops = {
 	.query_ras_error_count = mmhub_v1_0_query_ras_error_count,
 	.reset_ras_error_count = mmhub_v1_0_reset_ras_error_count,
 };
 
+struct amdgpu_mmhub_ras mmhub_v1_0_ras = {
+	.ras_block = {
+		.hw_ops = &mmhub_v1_0_ras_hw_ops,
+	},
+};
+
 const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = {
 	.get_fb_location = mmhub_v1_0_get_fb_location,
 	.init = mmhub_v1_0_init,

drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.h

@@ -24,6 +24,6 @@
 #define __MMHUB_V1_0_H__
 
 extern const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs;
-extern const struct amdgpu_mmhub_ras_funcs mmhub_v1_0_ras_funcs;
+extern struct amdgpu_mmhub_ras mmhub_v1_0_ras;
 
 #endif

drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c

@@ -1321,15 +1321,19 @@ static void mmhub_v1_7_reset_ras_error_status(struct amdgpu_device *adev)
 	}
 }
 
-const struct amdgpu_mmhub_ras_funcs mmhub_v1_7_ras_funcs = {
-	.ras_late_init = amdgpu_mmhub_ras_late_init,
-	.ras_fini = amdgpu_mmhub_ras_fini,
+struct amdgpu_ras_block_hw_ops mmhub_v1_7_ras_hw_ops = {
 	.query_ras_error_count = mmhub_v1_7_query_ras_error_count,
 	.reset_ras_error_count = mmhub_v1_7_reset_ras_error_count,
 	.query_ras_error_status = mmhub_v1_7_query_ras_error_status,
 	.reset_ras_error_status = mmhub_v1_7_reset_ras_error_status,
 };
 
+struct amdgpu_mmhub_ras mmhub_v1_7_ras = {
+	.ras_block = {
+		.hw_ops = &mmhub_v1_7_ras_hw_ops,
+	},
+};
+
 const struct amdgpu_mmhub_funcs mmhub_v1_7_funcs = {
 	.get_fb_location = mmhub_v1_7_get_fb_location,
 	.init = mmhub_v1_7_init,

drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.h

@@ -24,6 +24,6 @@
 #define __MMHUB_V1_7_H__
 
 extern const struct amdgpu_mmhub_funcs mmhub_v1_7_funcs;
-extern const struct amdgpu_mmhub_ras_funcs mmhub_v1_7_ras_funcs;
+extern struct amdgpu_mmhub_ras mmhub_v1_7_ras;
 
 #endif

drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c

@@ -1655,14 +1655,18 @@ static void mmhub_v9_4_query_ras_error_status(struct amdgpu_device *adev)
 	}
 }
 
-const struct amdgpu_mmhub_ras_funcs mmhub_v9_4_ras_funcs = {
-	.ras_late_init = amdgpu_mmhub_ras_late_init,
-	.ras_fini = amdgpu_mmhub_ras_fini,
+const struct amdgpu_ras_block_hw_ops mmhub_v9_4_ras_hw_ops = {
 	.query_ras_error_count = mmhub_v9_4_query_ras_error_count,
 	.reset_ras_error_count = mmhub_v9_4_reset_ras_error_count,
 	.query_ras_error_status = mmhub_v9_4_query_ras_error_status,
 };
 
+struct amdgpu_mmhub_ras mmhub_v9_4_ras = {
+	.ras_block = {
+		.hw_ops = &mmhub_v9_4_ras_hw_ops,
+	},
+};
+
 const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = {
 	.get_fb_location = mmhub_v9_4_get_fb_location,
 	.init = mmhub_v9_4_init,

drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h

@@ -24,6 +24,6 @@
 #define __MMHUB_V9_4_H__
 
 extern const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs;
-extern const struct amdgpu_mmhub_ras_funcs mmhub_v9_4_ras_funcs;
+extern struct amdgpu_mmhub_ras mmhub_v9_4_ras;
 
 #endif