drm/xe: Enable Boot Survivability mode

Enable boot survivability mode if pcode initialization fails and
if boot status indicates a failure. In this mode, drm card is not
exposed and driver probe returns success after loading the bare minimum
to allow firmware to be flashed via mei.

v2: abstract survivability mode variable
    add BMG check inside function (Jani, Rodrigo)

v3: return -EBUSY during system suspend (Anshuman)
    check survivability mode in pci probe only
    on error

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250128095632.1294722-3-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_device.c

@@ -52,6 +52,7 @@
 #include "xe_pmu.h"
 #include "xe_query.h"
 #include "xe_sriov.h"
+#include "xe_survivability_mode.h"
 #include "xe_tile.h"
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_ttm_sys_mgr.h"
@@ -694,8 +695,12 @@ int xe_device_probe_early(struct xe_device *xe)
 	update_device_info(xe);
 
 	err = xe_pcode_probe_early(xe);
-	if (err)
+	if (err) {
+		if (xe_survivability_mode_required(xe))
+			xe_survivability_mode_init(xe);
+
 		return err;
+	}
 
 	err = wait_for_lmem_ready(xe);
 	if (err)

drivers/gpu/drm/xe/xe_pci.c

@@ -30,6 +30,7 @@
 #include "xe_pm.h"
 #include "xe_sriov.h"
 #include "xe_step.h"
+#include "xe_survivability_mode.h"
 #include "xe_tile.h"
 
 enum toggle_d3cold {
@@ -761,6 +762,9 @@ static void xe_pci_remove(struct pci_dev *pdev)
 	if (IS_SRIOV_PF(xe))
 		xe_pci_sriov_configure(pdev, 0);
 
+	if (xe_survivability_mode_enabled(xe))
+		return xe_survivability_mode_remove(xe);
+
 	xe_device_remove(xe);
 	xe_pm_runtime_fini(xe);
 	pci_set_drvdata(pdev, NULL);
@@ -833,8 +837,19 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return err;
 
 	err = xe_device_probe_early(xe);
-	if (err)
+
+	/*
+	 * 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. Return
+	 * success if survivability mode is enabled.
+	 */
+	if (err) {
+		if (xe_survivability_mode_enabled(xe))
+			return 0;
+
 		return err;
+	}
 
 	err = xe_info_init(xe, desc->graphics, desc->media);
 	if (err)
@@ -921,9 +936,13 @@ static void d3cold_toggle(struct pci_dev *pdev, enum toggle_d3cold toggle)
 static int xe_pci_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
+	struct xe_device *xe = pdev_to_xe_device(pdev);
 	int err;
 
-	err = xe_pm_suspend(pdev_to_xe_device(pdev));
+	if (xe_survivability_mode_enabled(xe))
+		return -EBUSY;
+
+	err = xe_pm_suspend(xe);
 	if (err)
 		return err;
 

drivers/gpu/drm/xe/xe_survivability_mode.c

@@ -144,6 +144,19 @@ static void enable_survivability_mode(struct pci_dev *pdev)
 	}
 }
 
+/**
+ * xe_survivability_mode_enabled - check if survivability mode is enabled
+ * @xe: xe device instance
+ *
+ * Returns true if in survivability mode, false otherwise
+ */
+bool xe_survivability_mode_enabled(struct xe_device *xe)
+{
+	struct xe_survivability *survivability = &xe->survivability;
+
+	return survivability->mode;
+}
+
 /**
  * xe_survivability_mode_required - checks if survivability mode is required
  * @xe: xe device instance
@@ -158,6 +171,9 @@ bool xe_survivability_mode_required(struct xe_device *xe)
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 	u32 data;
 
+	if (!IS_DGFX(xe) || xe->info.platform < XE_BATTLEMAGE)
+		return false;
+
 	data = xe_mmio_read32(mmio, PCODE_SCRATCH(0));
 	survivability->boot_status = REG_FIELD_GET(BOOT_STATUS, data);
 

drivers/gpu/drm/xe/xe_survivability_mode.h

@@ -12,6 +12,7 @@ struct xe_device;
 
 void xe_survivability_mode_init(struct xe_device *xe);
 void xe_survivability_mode_remove(struct xe_device *xe);
+bool xe_survivability_mode_enabled(struct xe_device *xe);
 bool xe_survivability_mode_required(struct xe_device *xe);
 
 #endif /* _XE_SURVIVABILITY_MODE_H_ */