Re: [PATCH] drm/amd/ras: Reduce stack usage in ras_umc_handle_bad_pages()

[Lazar, Lijo]

On 12/5/2025 5:45 PM, Srinivasan Shanmugam wrote:

ras_umc_handle_bad_pages() function used a large local array:
   struct eeprom_umc_record records[MAX_ECC_NUM_PER_RETIREMENT];

Move this array off the stack by allocating it with kcalloc()
and freeing it before return.

This reduces the stack frame size of ras_umc_handle_bad_pages()
and avoids the frame size warning.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/../ras/rascore/ras_umc.c:498:5: warning: stack frame 
size (1208) exceeds limit (1024) in 'ras_umc_handle_bad_pages' 
[-Wframe-larger-than]

Cc: Tao Zhou <tao.zh...@amd.com>
Cc: Hawking Zhang <hawking.zh...@amd.com>
Cc: Christian König <christian.koe...@amd.com>
Cc: Alex Deucher <alexander.deuc...@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmu...@amd.com>
---
  drivers/gpu/drm/amd/ras/rascore/ras_umc.c | 31 ++++++++++++++++++-----
  1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/ras/rascore/ras_umc.c 
b/drivers/gpu/drm/amd/ras/rascore/ras_umc.c
index 4dae64c424a2..6061776b894d 100644
--- a/drivers/gpu/drm/amd/ras/rascore/ras_umc.c
+++ b/drivers/gpu/drm/amd/ras/rascore/ras_umc.c
@@ -497,27 +497,44 @@ static int ras_umc_save_bad_pages(struct ras_core_context 
*ras_core)

int ras_umc_handle_bad_pages(struct ras_core_context *ras_core, void *data)

  {
-       struct eeprom_umc_record records[MAX_ECC_NUM_PER_RETIREMENT];
+       struct eeprom_umc_record *records;
        int count, ret;

+ records = kcalloc(MAX_ECC_NUM_PER_RETIREMENT,

+                         sizeof(*records), GFP_KERNEL);
+       if (!records)
+               return -ENOMEM;
+
+       count = ras_umc_get_new_records(ras_core, records,
+                                       MAX_ECC_NUM_PER_RETIREMENT);
+

This looks unintentional, same function called below.

        memset(records, 0, sizeof(records));

This is not required and can be skipped.

Thanks,
Lijo

-       count = ras_umc_get_new_records(ras_core, records, ARRAY_SIZE(records));
-       if (count <= 0)
-               return -ENODATA;
+       count = ras_umc_get_new_records(ras_core, records,
+                                       MAX_ECC_NUM_PER_RETIREMENT);
+       if (count <= 0) {
+               ret = -ENODATA;
+               goto out;
+       }

ret = ras_umc_add_bad_pages(ras_core, records, count, false);

        if (ret) {
                RAS_DEV_ERR(ras_core->dev, "Failed to add ras bad page!\n");
-               return -EINVAL;
+               ret = -EINVAL;
+               goto out;
        }

ret = ras_umc_save_bad_pages(ras_core);

        if (ret) {
                RAS_DEV_ERR(ras_core->dev, "Failed to save ras bad page\n");
-               return -EINVAL;
+               ret = -EINVAL;
+               goto out;
        }

- return 0;

+       ret = 0;
+
+out:
+       kfree(records);
+       return ret;
  }

int ras_umc_sw_init(struct ras_core_context *ras_core)