drm/amdgpu: add GFX RAS common function

The common function can help reduce redundant code.

v2: remove xcp operation, only need to do RAS operations for all
instances.
v3: remove check for GFX RAS support, will be checked in higher level.
    add amdgpu prefix for the function name.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 6098b8b..8883d5e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -884,6 +884,25 @@ int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev,
        return 0;
 }
 
+void amdgpu_gfx_ras_error_func(struct amdgpu_device *adev,
+               void *ras_error_status,
+               void (*func)(struct amdgpu_device *adev, void *ras_error_status,
+                               int xcc_id))
+{
+       int i;
+       int num_xcc = adev->gfx.xcc_mask ? NUM_XCC(adev->gfx.xcc_mask) : 1;
+       uint32_t xcc_mask = GENMASK(num_xcc - 1, 0);
+       struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+
+       if (err_data) {
+               err_data->ue_count = 0;
+               err_data->ce_count = 0;
+       }
+
+       for_each_inst(i, xcc_mask)
+               func(adev, ras_error_status, i);
+}
+
 uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 {
        signed long r, cnt = 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 3d11b7a..0df53fe 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -494,6 +494,10 @@ int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev,
 bool amdgpu_gfx_is_master_xcc(struct amdgpu_device *adev, int xcc_id);
 int amdgpu_gfx_sysfs_init(struct amdgpu_device *adev);
 void amdgpu_gfx_sysfs_fini(struct amdgpu_device *adev);
+void amdgpu_gfx_ras_error_func(struct amdgpu_device *adev,
+               void *ras_error_status,
+               void (*func)(struct amdgpu_device *adev, void *ras_error_status,
+                               int xcc_id));
 
 static inline const char *amdgpu_gfx_compute_mode_desc(int mode)
 {