drm/xe/xe_survivability: Add support for Runtime survivability mode

Certain runtime firmware errors can cause the device to be in a unusable
state requiring a firmware flash to restore normal operation.
Runtime Survivability Mode indicates firmware flash is necessary by
wedging the device and exposing survivability mode sysfs.

The below sysfs is an indication that device is in survivability mode

/sys/bus/pci/devices/<device>/survivability_mode

v2: Fix kernel-doc (Umesh)
v3: Add user friendly dmesg (Frank)

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-7-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 4a2d1cff65d2b9651de66e73a33ff2e934bf9652..267d0e3fd85a6771ab922e9420a2e9fd9539d231 100644 (file)
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -138,7 +138,8 @@ static ssize_t survivability_mode_show(struct device *dev,
        struct xe_survivability_info *info = survivability->info;
        int index = 0, count = 0;
 
-       count += sysfs_emit_at(buff, count, "Survivability mode type: Boot\n");
+       count += sysfs_emit_at(buff, count, "Survivability mode type: %s\n",
+                              survivability->type ? "Runtime" : "Boot");
 
        if (!check_boot_failure(xe))
                return count;
@@ -291,6 +292,46 @@ bool xe_survivability_mode_is_requested(struct xe_device *xe)
        return check_boot_failure(xe);
 }
 
+/**
+ * xe_survivability_mode_runtime_enable - Initialize and enable runtime survivability mode
+ * @xe: xe device instance
+ *
+ * Initialize survivability information and enable runtime survivability mode.
+ * Runtime survivability mode is enabled when certain errors cause the device to be
+ * in non-recoverable state. The device is declared wedged with the appropriate
+ * recovery method and survivability mode sysfs exposed to userspace
+ *
+ * Return: 0 if runtime survivability mode is enabled, negative error code otherwise.
+ */
+int xe_survivability_mode_runtime_enable(struct xe_device *xe)
+{
+       struct xe_survivability *survivability = &xe->survivability;
+       struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+       int ret;
+
+       if (!IS_DGFX(xe) || IS_SRIOV_VF(xe) || xe->info.platform < XE_BATTLEMAGE) {
+               dev_err(&pdev->dev, "Runtime Survivability Mode not supported\n");
+               return -EINVAL;
+       }
+
+       ret = init_survivability_mode(xe);
+       if (ret)
+               return ret;
+
+       ret = create_survivability_sysfs(pdev);
+       if (ret)
+               dev_err(&pdev->dev, "Failed to create survivability mode sysfs\n");
+
+       survivability->type = XE_SURVIVABILITY_TYPE_RUNTIME;
+       dev_err(&pdev->dev, "Runtime Survivability mode enabled\n");
+
+       xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_VENDOR);
+       xe_device_declare_wedged(xe);
+       dev_err(&pdev->dev, "Firmware update required, Refer the userspace documentation for more details!\n");
+
+       return 0;
+}
+
 /**
  * xe_survivability_mode_boot_enable - Initialize and enable boot survivability mode
  * @xe: xe device instance

diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.h b/drivers/gpu/drm/xe/xe_survivability_mode.h
index f6ee283ea5e800f2c7fc7163d07dff19c59501eb..1cc94226aa82d666f8f5d16f328ae6a9b164948d 100644 (file)
--- a/drivers/gpu/drm/xe/xe_survivability_mode.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.h
@@ -11,6 +11,7 @@
 struct xe_device;
 
 int xe_survivability_mode_boot_enable(struct xe_device *xe);
+int xe_survivability_mode_runtime_enable(struct xe_device *xe);
 bool xe_survivability_mode_is_boot_enabled(struct xe_device *xe);
 bool xe_survivability_mode_is_requested(struct xe_device *xe);
 

diff --git a/drivers/gpu/drm/xe/xe_survivability_mode_types.h b/drivers/gpu/drm/xe/xe_survivability_mode_types.h
index 5dce393498da5d3f680d84b93aaea356a7b046aa..cd65a5d167c9c88b0985908c010d6bf7939227a6 100644 (file)
--- a/drivers/gpu/drm/xe/xe_survivability_mode_types.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode_types.h
@@ -11,6 +11,7 @@
 
 enum xe_survivability_type {
        XE_SURVIVABILITY_TYPE_BOOT,
+       XE_SURVIVABILITY_TYPE_RUNTIME,
 };
 
 struct xe_survivability_info {