Re: [PATCH v3 18/23] drm/xe: Report 'Survivability Mode' errors using SIGID

On 30-07-2026 08:51 pm, Michal Wajdeczko wrote:
> Report various 'Survivability Mode' errors using xe_log() helpers.
>
> Signed-off-by: Michal Wajdeczko<[email protected]>
> Cc: Rodrigo Vivi<[email protected]>
> Cc: Riana Tauro<[email protected]>
> Cc: Aravind Iddamsetty<[email protected]>
> Cc: Mallesh Koujalagi<[email protected]>
> ---
>   drivers/gpu/drm/xe/xe_survivability_mode.c | 24 +++++++++++++---------
>   1 file changed, 14 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
> index 4c506027fa94..788b7e8137a9 100644
> --- a/drivers/gpu/drm/xe/xe_survivability_mode.c
> +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
> @@ -14,9 +14,11 @@
>   #include "xe_device.h"
>   #include "xe_heci_gsc.h"
>   #include "xe_i2c.h"
> +#include "xe_log.h"
>   #include "xe_mmio.h"
>   #include "xe_nvm.h"
>   #include "xe_pcode_api.h"
> +#include "xe_printk.h"
>   #include "xe_vsec.h"
>   
>   /**
> @@ -179,11 +181,11 @@ static void log_survivability_info(struct pci_dev *pdev)
>   	u32 *info = survivability->info;
>   	int id;
>   
> -	dev_info(&pdev->dev, "Survivability Boot Status : Critical Failure (%d)\n",
> -		 survivability->boot_status);
> +	xe_log_info(xe, SURVIVABILITY, "Boot Status : Critical Failure (%d)\n",
> +		    survivability->boot_status);
>   	for (id = 0; id < MAX_SCRATCH_REG; id++) {
>   		if (info[id])
> -			dev_info(&pdev->dev, "%s: 0x%x\n", reg_map[id], info[id]);
> +			xe_log_info(xe, SURVIVABILITY, "%s: 0x%x\n", reg_map[id], info[id]);
>   	}
>   }
>   
> @@ -316,7 +318,6 @@ static int create_survivability_sysfs(struct pci_dev *pdev)
>   
>   static int enable_boot_survivability_mode(struct pci_dev *pdev)
>   {
> -	struct device *dev = &pdev->dev;
>   	struct xe_device *xe = pdev_to_xe_device(pdev);
>   	struct xe_survivability *survivability = &xe->survivability;
>   	int ret = 0;
> @@ -342,12 +343,12 @@ static int enable_boot_survivability_mode(struct pci_dev *pdev)
>   	if (ret)
>   		goto err;
>   
> -	dev_err(dev, "In Survivability Mode\n");
> -
> +	xe_log_emit(pdev, check_boot_failure(xe) ? CPER_SEV_FATAL : CPER_SEV_INFORMATIONAL,
> +		    XE_SIGID_SURVIVABILITY, 0, 0, 0, 0, "In Survivability Boot Mode\n");

Please make it cleaner and simpler.

if(check_boot_failure(xe))

     xe_log_err_fatal(xe, SURVIVABILITY, .. );

else

      xe_log_info(xe, SURVIVABILITY, .. );


OR

xe_log_emit(xe_any_to_pdev(xe),
             check_boot_failure(xe) ? CPER_SEV_FATAL : 
CPER_SEV_INFORMATIONAL,
             XE_SIGID_SURVIVABILITY, XE_LOG_COMPONENT_SURVIVABILITY,
             xe_log_location(xe),
             &survivability->boot_status, 
sizeof(survivability->boot_status),
             "In Survivability Boot Mode\n");

>   	return 0;
>   
>   err:
> -	dev_err(dev, "Failed to enable Survivability Mode\n");
> +	xe_log_err_fatal(xe, SURVIVABILITY, ret, "Failed to enable Survivability Mode\n");
>   	survivability->mode = false;
>   	return ret;
>   }
> @@ -412,7 +413,7 @@ void xe_survivability_mode_runtime_enable(struct xe_device *xe)
>   	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
>   
>   	if (!IS_DGFX(xe) || IS_SRIOV_VF(xe) || xe->info.platform < XE_BATTLEMAGE) {
> -		dev_err(&pdev->dev, "Runtime Survivability Mode not supported\n");
> +		xe_log_info(xe, SURVIVABILITY, "Runtime Mode not supported!\n");
We can add xe_log_err(xe, SURVIVABILITY, -EOPNOTSUPP, ...);
>   		return;
>   	}
>   
> @@ -422,11 +423,14 @@ void xe_survivability_mode_runtime_enable(struct xe_device *xe)
>   		dev_err(&pdev->dev, "Failed to create survivability sysfs\n");
need to use xe_log_err(xe, SURVIVABILITY. -EIO, ... );
>   
>   	survivability->type = XE_SURVIVABILITY_TYPE_RUNTIME;
> -	dev_err(&pdev->dev, "Runtime Survivability mode enabled\n");
> +	xe_log_err_fatal(xe, SURVIVABILITY, 0, "Runtime Mode enabled!\n");
hmm, Logging error as fatal, however passing err=0 (Success). is it 
right? or simply we can log as xe_log_err or xe_log_info ? any thoughts.
>   
>   	xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_VENDOR);
>   	xe_device_declare_wedged(xe);
> -	dev_err(&pdev->dev, "Firmware flash required, Please refer to the userspace documentation for more details!\n");
> +
> +	xe_log_err_fatal(xe, SURVIVABILITY, 0, "Firmware flash required!\n");
ditto
> +	xe_info(xe, "Please refer to the userspace documentation for more details how to flash the firmware on %s!\n",
> +		xe->info.platform_name);
>   }
>   
>   /**