drm/amdgpu: initialize ras structures for xgmi block (v2)

init ras common interface and fs node for xgmi block

v2: remove unnecessary physical node number check before
invoking amdgpu_xgmi_ras_late_init

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index d3be51ba634926bba2143b8053730c94de164de7..b36d4c686844ec0b0195a2171e6bbe60bc4db662 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -123,6 +123,7 @@ struct amdgpu_xgmi {
        /* gpu list in the same hive */
        struct list_head head;
        bool supported;
+       struct ras_common_if *ras_if;
 };
 
 struct amdgpu_gmc {

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 65aae75f80fd5ee4b62b7dc2bdf4cecb24b1b859..7f6f2e964ae3f5ff56662168701e4cf163ca4773 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -25,6 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_xgmi.h"
 #include "amdgpu_smu.h"
+#include "amdgpu_ras.h"
 #include "df/df_3_6_offset.h"
 
 static DEFINE_MUTEX(xgmi_mutex);
@@ -437,3 +438,38 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
                mutex_unlock(&hive->hive_lock);
        }
 }
+
+int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
+{
+       int r;
+       struct ras_ih_if ih_info = {
+               .cb = NULL,
+       };
+       struct ras_fs_if fs_info = {
+               .sysfs_name = "xgmi_wafl_err_count",
+               .debugfs_name = "xgmi_wafl_err_inject",
+       };
+
+       if (!adev->gmc.xgmi.supported ||
+           adev->gmc.xgmi.num_physical_nodes == 0)
+               return 0;
+
+       if (!adev->gmc.xgmi.ras_if) {
+               adev->gmc.xgmi.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+               if (!adev->gmc.xgmi.ras_if)
+                       return -ENOMEM;
+               adev->gmc.xgmi.ras_if->block = AMDGPU_RAS_BLOCK__XGMI_WAFL;
+               adev->gmc.xgmi.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+               adev->gmc.xgmi.ras_if->sub_block_index = 0;
+               strcpy(adev->gmc.xgmi.ras_if->name, "xgmi_wafl");
+       }
+       ih_info.head = fs_info.head = *adev->gmc.xgmi.ras_if;
+       r = amdgpu_ras_late_init(adev, adev->gmc.xgmi.ras_if,
+                                &fs_info, &ih_info);
+       if (r || !amdgpu_ras_is_supported(adev, adev->gmc.xgmi.ras_if->block)) {
+               kfree(adev->gmc.xgmi.ras_if);
+               adev->gmc.xgmi.ras_if = NULL;
+       }
+
+       return r;
+}

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index fbcee31788c4dc4e30b5fd29739b6232005306ec..9023789397c0a2a83960219fe00ab12eb98cf597 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -42,6 +42,7 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
 int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
                struct amdgpu_device *peer_adev);
+int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev);
 
 static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
                struct amdgpu_device *bo_adev)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 167e916e40be2c27112f3edd613505cab7cf7fc5..a991a6c4f468d770a325fa3f04867d3eb09a5166 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -55,6 +55,7 @@
 #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
 
 #include "amdgpu_ras.h"
+#include "amdgpu_xgmi.h"
 
 /* add these here since we already include dce12 headers and these are for DCN */
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION                                                          0x055d
@@ -808,7 +809,8 @@ static int gmc_v9_0_ecc_late_init(void *handle)
                if (r)
                        return r;
        }
-       return 0;
+
+       return amdgpu_xgmi_ras_late_init(adev);
 }
 
 static int gmc_v9_0_late_init(void *handle)