Re: [RFC] drm/xe/ras: Report one SIGID per device memory error

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Mon, Nov 09, 2026 at 11:17:34AM -0500, Rodrigo Vivi wrote:
> handle_page_offline() logged each step as SIGID 202 RECOVERABLE, so a
> single double-bit ECC error produced several 202 lines whose severity
> disagreed with the CPER record emitted by handle_device_memory_errors().
> 
> Log those steps without a SIGID and leave the caller's 202 with CPER as
> the only report. Firmware failures keep SIGID 105.
> 
> Cc: Riana Tauro <riana.tauro@intel.com>
> Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
> Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> Cc: Badal Nilawar <badal.nilawar@intel.com>
> Cc: Raag Jadav <raag.jadav@intel.com>
> Cc: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
> ---
> 
> AI generated and untested.
> 
> Aiming to solve the discussion:
> https://lore.kernel.org/intel-xe/520a56ea-40a6-47bd-84a0-be5cf604e5e7@intel.com/#r
> 
> I agree with Badal that we should reduce the noise in the mempage-offline
> that is only bringing multiple entries of the same and then emmit only a single
> SIGID and a single CPER for it.

Please ignore this and let's focus on a real one that has the same goal:
https://lore.kernel.org/intel-xe/20261104090701.1748619-2-riana.tauro@intel.com

Sorry for the duplication and the noise. I just noticed this other one just
now in my inbox.

> 
>  drivers/gpu/drm/xe/xe_ras.c | 32 +++++++++++++-------------------
>  1 file changed, 13 insertions(+), 19 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
> index 2c01c183d02b..5b13daf972ba 100644
> --- a/drivers/gpu/drm/xe/xe_ras.c
> +++ b/drivers/gpu/drm/xe/xe_ras.c
> @@ -269,11 +269,9 @@ static int send_page_offline_cmd(struct xe_device *xe, u64 page_address,
>  	request.action = action;
>  
>  	if (action == XE_RAS_PAGE_ACTION_OFFLINE)
> -		xe_log_err(xe, DEVICE_MEMORY, 0, "Requesting firmware to offline page 0x%llx\n",
> -			   page_address);
> +		xe_dbg(xe, "Requesting firmware to offline page 0x%llx\n", page_address);
>  	else
> -		xe_log_err(xe, DEVICE_MEMORY, 0, "Requesting firmware to remove page 0x%llx from queue\n",
> -			   page_address);
> +		xe_dbg(xe, "Requesting firmware to remove page 0x%llx from queue\n", page_address);
>  
>  	xe_sysctrl_create_command(&command, XE_SYSCTRL_GROUP_GFSP, XE_SYSCTRL_CMD_PAGE_OFFLINE,
>  				  &request, sizeof(request), &response, sizeof(response));
> @@ -326,7 +324,7 @@ static int handle_page_offline(struct xe_device *xe, u64 page_address, bool noti
>  	/* User policy set to disable page offlining */
>  	if (xe_ras_get_disable_vram_page_offline(xe)) {
>  		action = XE_RAS_PAGE_ACTION_REMOVE;
> -		xe_log_err(xe, DEVICE_MEMORY, -EOPNOTSUPP, "User policy set to disable page offlining\n");
> +		xe_info(xe, "User policy set to disable page offlining\n");
>  		goto notify;
>  	}
>  
> @@ -346,14 +344,12 @@ static int handle_page_offline(struct xe_device *xe, u64 page_address, bool noti
>  	switch (ret) {
>  	case 0:
>  		action = XE_RAS_PAGE_ACTION_REMOVE;
> -		xe_log_err(xe, DEVICE_MEMORY, ret,
> -			   "Poison detected at physical address 0x%llx, page soft-offlined\n",
> -			   page_address);
> +		xe_info(xe, "Poison detected at physical address 0x%llx, page soft-offlined\n",
> +			page_address);
>  		break;
>  	case -EIO:
> -		xe_log_err(xe, DEVICE_MEMORY, ret,
> -			   "Poison detected at physical address 0x%llx, page belongs to critical BO and cannot be soft-offlined\n",
> -			   page_address);
> +		xe_err(xe, "Poison detected at physical address 0x%llx, page belongs to critical BO and cannot be soft-offlined\n",
> +		       page_address);
>  		return ret;
>  	case -EEXIST:
>  		if (xa_load(&state->offlined_pages, page_address >> XE_PTE_SHIFT))
> @@ -361,18 +357,16 @@ static int handle_page_offline(struct xe_device *xe, u64 page_address, bool noti
>  		else
>  			action = XE_RAS_PAGE_ACTION_OFFLINE;
>  
> -		xe_log_err(xe, DEVICE_MEMORY, ret,
> -			   "Double-bit ECC error detected at physical address 0x%llx, page soft-offlined\n",
> -			   page_address);
> +		xe_info(xe, "Double-bit ECC error detected at physical address 0x%llx, page soft-offlined\n",
> +			page_address);
>  		break;
>  	case -ENOMEM:
> -		xe_log_err(xe, DEVICE_MEMORY, ret,
> -			   "Poison detected at physical address 0x%llx, failed to soft-offline\n",
> -			   page_address);
> +		xe_err(xe, "Poison detected at physical address 0x%llx, failed to soft-offline\n",
> +		       page_address);
>  		return ret;
>  	default:
> -		xe_log_err(xe, DEVICE_MEMORY, ret, "Failed to handle address fault at physical address 0x%llx\n",
> -			   page_address);
> +		xe_err(xe, "Failed to handle address fault at physical address 0x%llx: %d\n",
> +		       page_address, ret);
>  		return 0;
>  	}
>  
> -- 
> 2.55.0
>