drm/xe: Move survivability back to xe

Commit d40f275d96e8 ("drm/xe: Move survivability entirely to xe_pci")
moved the survivability handling to be done entirely in the xe_pci
layer. However there are some issues with that approach:

1) Survivability mode needs at least the mmio initialized, otherwise it
   can't really read a register to decide if it should enter that state
2) SR-IOV mode should be initialized, otherwise it's not possible to
   check if it's VF

Besides, as pointed by Riana the check for
xe_survivability_mode_enable() was wrong in xe_pci_probe() since it's
not a bool return.

Fix that by moving the initialization to be entirely in the xe_device
layer, with the correct dependencies handled: only after mmio and sriov
initialization, and not triggering it on error from
wait_for_lmem_ready(). This restores the trigger behavior before that
commit. The xe_pci layer now only checks for "is it enabled?",
like it's doing in xe_pci_suspend()/xe_pci_remove(), etc.

Cc: Riana Tauro <riana.tauro@intel.com>
Fixes: d40f275d96e8 ("drm/xe: Move survivability entirely to xe_pci")
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250314-fix-survivability-v5-1-fdb3559ea965@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

4 files changed, 34 insertions, 19 deletions

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index b2f656b2a563..0e8805f93468 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -53,6 +53,7 @@
 #include "xe_pxp.h"
 #include "xe_query.h"
 #include "xe_shrinker.h"
+#include "xe_survivability_mode.h"
 #include "xe_sriov.h"
 #include "xe_tile.h"
 #include "xe_ttm_stolen_mgr.h"
@@ -711,8 +712,20 @@ int xe_device_probe_early(struct xe_device *xe)
 	sriov_update_device_info(xe);
 
 	err = xe_pcode_probe_early(xe);
-	if (err)
-		return err;
+	if (err) {
+		int save_err = err;
+
+		/*
+		 * Try to leave device in survivability mode if device is
+		 * possible, but still return the previous error for error
+		 * propagation
+		 */
+		err = xe_survivability_mode_enable(xe);
+		if (err)
+			return err;
+
+		return save_err;
+	}
 
 	err = wait_for_lmem_ready(xe);
 	if (err)
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index fc89d744978a..88138a3fcf50 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -807,16 +807,14 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return err;
 
 	err = xe_device_probe_early(xe);
-
-	/*
-	 * In Boot Survivability mode, no drm card is exposed and driver is
-	 * loaded with bare minimum to allow for firmware to be flashed through
-	 * mei. If early probe fails, check if survivability mode is flagged by
-	 * HW to be enabled. In that case enable it and return success.
-	 */
 	if (err) {
-		if (xe_survivability_mode_required(xe) &&
-		    xe_survivability_mode_enable(xe))
+		/*
+		 * In Boot Survivability mode, no drm card is exposed and driver
+		 * is loaded with bare minimum to allow for firmware to be
+		 * flashed through mei. If early probe failed, but it managed to
+		 * enable survivability mode, return success.
+		 */
+		if (xe_survivability_mode_is_enabled(xe))
 			return 0;
 
 		return err;
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index d939ce70e6fa..7b1ec643f0f0 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -178,15 +178,16 @@ bool xe_survivability_mode_is_enabled(struct xe_device *xe)
 	return xe->survivability.mode;
 }
 
-/**
- * xe_survivability_mode_required - checks if survivability mode is required
- * @xe: xe device instance
+/*
+ * survivability_mode_requested - check if it's possible to enable
+ * survivability mode and that was requested by firmware
  *
- * This function reads the boot status from Pcode
+ * This function reads the boot status from Pcode.
  *
- * Return: true if boot status indicates failure, false otherwise
+ * Return: true if platform support is available and boot status indicates
+ * failure, false otherwise.
  */
-bool xe_survivability_mode_required(struct xe_device *xe)
+static bool survivability_mode_requested(struct xe_device *xe)
 {
 	struct xe_survivability *survivability = &xe->survivability;
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
@@ -208,7 +209,8 @@ bool xe_survivability_mode_required(struct xe_device *xe)
  *
  * Initialize survivability information and enable survivability mode
  *
- * Return: 0 for success, negative error code otherwise.
+ * Return: 0 if survivability mode is enabled or not requested; negative error
+ * code otherwise.
  */
 int xe_survivability_mode_enable(struct xe_device *xe)
 {
@@ -216,6 +218,9 @@ int xe_survivability_mode_enable(struct xe_device *xe)
 	struct xe_survivability_info *info;
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 
+	if (!survivability_mode_requested(xe))
+		return 0;
+
 	survivability->size = MAX_SCRATCH_MMIO;
 
 	info = devm_kcalloc(xe->drm.dev, survivability->size, sizeof(*info),
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.h b/drivers/gpu/drm/xe/xe_survivability_mode.h
index f4df5f9025ce..d7e64885570d 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.h
@@ -12,6 +12,5 @@ struct xe_device;
 
 int xe_survivability_mode_enable(struct xe_device *xe);
 bool xe_survivability_mode_is_enabled(struct xe_device *xe);
-bool xe_survivability_mode_required(struct xe_device *xe);
 
 #endif /* _XE_SURVIVABILITY_MODE_H_ */