From 4d7c5db0383a827c2803375c26864fc67bf933cc Mon Sep 17 00:00:00 2001
From: yipechai <YiPeng.Chai@amd.com>
Date: Wed, 5 Jan 2022 15:30:37 +0800
Subject: drm/amdgpu: Modify sdma block to fit for the unified ras block data
and ops
Git-commit: bdc4292bd3b4337985f716be789b08eef921f7a6
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
1.Modify sdma block to fit for the unified ras block data and ops.
2.Change amdgpu_sdma_ras_funcs to amdgpu_sdma_ras, and the corresponding variable name remove _funcs suffix.
3.Remove the const flag of sdma ras variable so that sdma 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 sdma ras block into amdgpu device ras block link list.
5.Remove the redundant code about sdma 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 sdma versions. If .ras_late_init and .ras_fini had been defined by the selected sdma version, the defined functions will take effect; if not defined, default fill them with amdgpu_sdma_ras_late_init and amdgpu_sdma_ras_fini.
v2: squash in warning fix (Alex)
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>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 ----
drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h | 12 ++---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 58 ++++++++++++++++++------
drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c | 25 ++++++++--
drivers/gpu/drm/amd/amdgpu/sdma_v4_4.h | 2 +-
5 files changed, 71 insertions(+), 36 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 61a4f36e7eaf..090903663efa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -967,7 +967,6 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
struct amdgpu_ras_block_object* block_obj = NULL;
struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
struct ras_err_data err_data = {0, 0, 0, NULL};
- int i;
if (!obj)
return -EINVAL;
@@ -979,12 +978,6 @@ int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
amdgpu_ras_get_ecc_info(adev, &err_data);
break;
case AMDGPU_RAS_BLOCK__SDMA:
- if (adev->sdma.funcs->query_ras_error_count) {
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->sdma.funcs->query_ras_error_count(adev, i,
- &err_data);
- }
- break;
case AMDGPU_RAS_BLOCK__GFX:
case AMDGPU_RAS_BLOCK__MMHUB:
if (!block_obj || !block_obj->hw_ops) {
@@ -1090,9 +1083,6 @@ int amdgpu_ras_reset_error_status(struct amdgpu_device *adev,
block_obj->hw_ops->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);
- break;
case AMDGPU_RAS_BLOCK__HDP:
if (!block_obj || !block_obj->hw_ops) {
dev_info(adev->dev, "%s doesn't config ras function \n", ras_block_str(block));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index f8fb755e3aa6..eaee12ab6518 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -23,6 +23,7 @@
#ifndef __AMDGPU_SDMA_H__
#define __AMDGPU_SDMA_H__
+#include "amdgpu_ras.h"
/* max number of IP instances */
#define AMDGPU_MAX_SDMA_INSTANCES 8
@@ -50,13 +51,8 @@ struct amdgpu_sdma_instance {
bool burst_nop;
};
-struct amdgpu_sdma_ras_funcs {
- int (*ras_late_init)(struct amdgpu_device *adev,
- void *ras_ih_info);
- void (*ras_fini)(struct amdgpu_device *adev);
- int (*query_ras_error_count)(struct amdgpu_device *adev,
- uint32_t instance, void *ras_error_status);
- void (*reset_ras_error_count)(struct amdgpu_device *adev);
+struct amdgpu_sdma_ras {
+ struct amdgpu_ras_block_object ras_block;
};
struct amdgpu_sdma {
@@ -73,7 +69,7 @@ struct amdgpu_sdma {
uint32_t srbm_soft_reset;
bool has_page_queue;
struct ras_common_if *ras_if;
- const struct amdgpu_sdma_ras_funcs *funcs;
+ struct amdgpu_sdma_ras *ras;
};
/*
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index f0638db57111..0ca0f6eb1878 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1892,13 +1892,13 @@ static int sdma_v4_0_late_init(void *handle)
sdma_v4_0_setup_ulv(adev);
if (!amdgpu_persistent_edc_harvesting_supported(adev)) {
- if (adev->sdma.funcs &&
- adev->sdma.funcs->reset_ras_error_count)
- adev->sdma.funcs->reset_ras_error_count(adev);
+ if (adev->sdma.ras && adev->sdma.ras->ras_block.hw_ops &&
+ adev->sdma.ras->ras_block.hw_ops->reset_ras_error_count)
+ adev->sdma.ras->ras_block.hw_ops->reset_ras_error_count(adev);
}
- if (adev->sdma.funcs && adev->sdma.funcs->ras_late_init)
- return adev->sdma.funcs->ras_late_init(adev, &ih_info);
+ if (adev->sdma.ras && adev->sdma.ras->ras_block.ras_late_init)
+ return adev->sdma.ras->ras_block.ras_late_init(adev, &ih_info);
else
return 0;
}
@@ -2001,8 +2001,9 @@ static int sdma_v4_0_sw_fini(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int i;
- if (adev->sdma.funcs && adev->sdma.funcs->ras_fini)
- adev->sdma.funcs->ras_fini(adev);
+ if (adev->sdma.ras && adev->sdma.ras->ras_block.hw_ops &&
+ adev->sdma.ras->ras_block.ras_fini)
+ adev->sdma.ras->ras_block.ras_fini(adev);
for (i = 0; i < adev->sdma.num_instances; i++) {
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
@@ -2748,7 +2749,7 @@ static void sdma_v4_0_get_ras_error_count(uint32_t value,
}
}
-static int sdma_v4_0_query_ras_error_count(struct amdgpu_device *adev,
+static int sdma_v4_0_query_ras_error_count_by_instance(struct amdgpu_device *adev,
uint32_t instance, void *ras_error_status)
{
struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
@@ -2770,6 +2771,18 @@ static int sdma_v4_0_query_ras_error_count(struct amdgpu_device *adev,
return 0;
};
+static void sdma_v4_0_query_ras_error_count(struct amdgpu_device *adev, void *ras_error_status)
+{
+ int i = 0;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ if (sdma_v4_0_query_ras_error_count_by_instance(adev, i, ras_error_status))
+ {
+ dev_err(adev->dev, "Query ras error count failed in SDMA%d \n", i);
+ return;
+ }
+ }
+}
+
static void sdma_v4_0_reset_ras_error_count(struct amdgpu_device *adev)
{
int i;
@@ -2781,26 +2794,45 @@ static void sdma_v4_0_reset_ras_error_count(struct amdgpu_device *adev)
}
}
-static const struct amdgpu_sdma_ras_funcs sdma_v4_0_ras_funcs = {
- .ras_late_init = amdgpu_sdma_ras_late_init,
- .ras_fini = amdgpu_sdma_ras_fini,
+const struct amdgpu_ras_block_hw_ops sdma_v4_0_ras_hw_ops = {
.query_ras_error_count = sdma_v4_0_query_ras_error_count,
.reset_ras_error_count = sdma_v4_0_reset_ras_error_count,
};
+static struct amdgpu_sdma_ras sdma_v4_0_ras = {
+ .ras_block = {
+ .hw_ops = &sdma_v4_0_ras_hw_ops,
+ },
+};
+
static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev)
{
switch (adev->ip_versions[SDMA0_HWIP][0]) {
case IP_VERSION(4, 2, 0):
case IP_VERSION(4, 2, 2):
- adev->sdma.funcs = &sdma_v4_0_ras_funcs;
+ adev->sdma.ras = &sdma_v4_0_ras;
break;
case IP_VERSION(4, 4, 0):
- adev->sdma.funcs = &sdma_v4_4_ras_funcs;
+ adev->sdma.ras = &sdma_v4_4_ras;
break;
default:
break;
}
+
+ if (adev->sdma.ras) {
+ amdgpu_ras_register_ras_block(adev, &adev->sdma.ras->ras_block);
+
+ strcpy(adev->sdma.ras->ras_block.name,"sdma");
+ adev->sdma.ras->ras_block.block = AMDGPU_RAS_BLOCK__SDMA;
+
+ /* If don't define special ras_late_init function, use default ras_late_init */
+ if (!adev->sdma.ras->ras_block.ras_late_init)
+ adev->sdma.ras->ras_block.ras_late_init = amdgpu_sdma_ras_late_init;
+
+ /* If don't define special ras_fini function, use default ras_fini */
+ if (!adev->sdma.ras->ras_block.ras_fini)
+ adev->sdma.ras->ras_block.ras_fini = amdgpu_sdma_ras_fini;
+ }
}
const struct amdgpu_ip_block_version sdma_v4_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c
index bf95007f0843..5c1ba1116e5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.c
@@ -188,7 +188,7 @@ static void sdma_v4_4_get_ras_error_count(struct amdgpu_device *adev,
}
}
-static int sdma_v4_4_query_ras_error_count(struct amdgpu_device *adev,
+static int sdma_v4_4_query_ras_error_count_by_instance(struct amdgpu_device *adev,
uint32_t instance,
void *ras_error_status)
{
@@ -245,9 +245,26 @@ static void sdma_v4_4_reset_ras_error_count(struct amdgpu_device *adev)
}
}
-const struct amdgpu_sdma_ras_funcs sdma_v4_4_ras_funcs = {
- .ras_late_init = amdgpu_sdma_ras_late_init,
- .ras_fini = amdgpu_sdma_ras_fini,
+static void sdma_v4_4_query_ras_error_count(struct amdgpu_device *adev, void *ras_error_status)
+{
+ int i = 0;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ if (sdma_v4_4_query_ras_error_count_by_instance(adev, i, ras_error_status))
+ {
+ dev_err(adev->dev, "Query ras error count failed in SDMA%d \n", i);
+ return;
+ }
+ }
+
+}
+
+const struct amdgpu_ras_block_hw_ops sdma_v4_4_ras_hw_ops = {
.query_ras_error_count = sdma_v4_4_query_ras_error_count,
.reset_ras_error_count = sdma_v4_4_reset_ras_error_count,
};
+
+struct amdgpu_sdma_ras sdma_v4_4_ras = {
+ .ras_block = {
+ .hw_ops = &sdma_v4_4_ras_hw_ops,
+ },
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.h b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.h
index 74a6e5b5e949..a9f0c68359e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.h
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4.h
@@ -23,6 +23,6 @@
#ifndef __SDMA_V4_4_H__
#define __SDMA_V4_4_H__
-extern const struct amdgpu_sdma_ras_funcs sdma_v4_4_ras_funcs;
+extern struct amdgpu_sdma_ras sdma_v4_4_ras;
#endif
--
2.38.1