drm/amdgpu: Fix error handling in amdgpu_ras_add_bad_pages

It ensures that appropriate error codes are returned when an error
condition is detected

Fixes the below;
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:2849 amdgpu_ras_add_bad_pages() warn: missing error code here? 'amdgpu_umc_pages_in_a_row()' failed.
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c:2884 amdgpu_ras_add_bad_pages() warn: missing error code here? 'amdgpu_ras_mca2pa()' failed.

v2: s/-EIO/-EINVAL, retained the use of -EINVAL from
    amdgpu_umc_pages_in_a_row & and amdgpu_ras_mca2pa_by_idx, when the
    RAS context is not initialized or the convert_ras_err_addr function is
    unavailable. (Thomas)

V3: Returning 0 as the absence of eh_data is acceptable. (Tao)

Fixes: a8d133e625ce ("drm/amdgpu: parse legacy RAS bad page mixed with new data in various NPS modes")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: YiPeng Chai <yipeng.chai@amd.com>
Cc: Tao Zhou <tao.zhou1@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 01c947066a2eb02d2e2848a3943c918147146b0e..f0924aa3f4e485ac60f05f5d71e7d65f5ed162c9 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2832,8 +2832,10 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 
        mutex_lock(&con->recovery_lock);
        data = con->eh_data;
-       if (!data)
+       if (!data) {
+               /* Returning 0 as the absence of eh_data is acceptable */
                goto free;
+       }
 
        for (i = 0; i < pages; i++) {
                if (from_rom &&
@@ -2845,26 +2847,34 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
                                                 * one row
                                                 */
                                                if (amdgpu_umc_pages_in_a_row(adev, &err_data,
-                                                               bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT))
+                                                                             bps[i].retired_page <<
+                                                                             AMDGPU_GPU_PAGE_SHIFT)) {
+                                                       ret = -EINVAL;
                                                        goto free;
-                                               else
+                                               } else {
                                                        find_pages_per_pa = true;
+                                               }
                                        } else {
                                                /* unsupported cases */
+                                               ret = -EOPNOTSUPP;
                                                goto free;
                                        }
                                }
                        } else {
                                if (amdgpu_umc_pages_in_a_row(adev, &err_data,
-                                               bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT))
+                                               bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT)) {
+                                       ret = -EINVAL;
                                        goto free;
+                               }
                        }
                } else {
                        if (from_rom && !find_pages_per_pa) {
                                if (bps[i].retired_page & UMC_CHANNEL_IDX_V2) {
                                        /* bad page in any NPS mode in eeprom */
-                                       if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data))
+                                       if (amdgpu_ras_mca2pa_by_idx(adev, &bps[i], &err_data)) {
+                                               ret = -EINVAL;
                                                goto free;
+                                       }
                                } else {
                                        /* legacy bad page in eeprom, generated only in
                                         * NPS1 mode
@@ -2881,6 +2891,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
                                                        /* non-nps1 mode, old RAS TA
                                                         * can't support it
                                                         */
+                                                       ret = -EOPNOTSUPP;
                                                        goto free;
                                                }
                                        }