drm/xe: Use fault injection infrastructure to find issues at probe time

The kernel fault injection infrastructure is used to test proper error
handling during probe. The return code of the functions using
ALLOW_ERROR_INJECTION() can be conditionnally modified at runtime by
tuning some debugfs entries. This requires CONFIG_FUNCTION_ERROR_INJECTION
(among others).

One way to use fault injection at probe time by making each of those
functions fail one at a time is:

FAILTYPE=fail_function
DEVICE="0000:00:08.0" # depends on the system
ERRNO=-12 # -ENOMEM, can depend on the function

echo N > /sys/kernel/debug/$FAILTYPE/task-filter
echo 100 > /sys/kernel/debug/$FAILTYPE/probability
echo 0 > /sys/kernel/debug/$FAILTYPE/interval
echo -1 > /sys/kernel/debug/$FAILTYPE/times
echo 0 > /sys/kernel/debug/$FAILTYPE/space
echo 1 > /sys/kernel/debug/$FAILTYPE/verbose

modprobe xe
echo $DEVICE > /sys/bus/pci/drivers/xe/unbind

grep -oP "^.* \[xe\]" /sys/kernel/debug/$FAILTYPE/injectable | \
cut -d ' ' -f 1 | while read -r FUNCTION ; do
echo "Injecting fault in $FUNCTION"
echo "" > /sys/kernel/debug/$FAILTYPE/inject
echo $FUNCTION > /sys/kernel/debug/$FAILTYPE/inject
printf %#x $ERRNO > /sys/kernel/debug/$FAILTYPE/$FUNCTION/retval
echo $DEVICE > /sys/bus/pci/drivers/xe/bind
done

rmmod xe

It will also be integrated into IGT for systematic execution by CI.

v2: Wrappers are not needed in the cases covered by this patch, so
remove them and use ALLOW_ERROR_INJECTION() directly.

v3: Document the use of fault injection at probe time in xe_pci_probe
and refer to it where ALLOW_ERROR_INJECTION() is used.

Signed-off-by: Francois Dugast <[e-mail]>
Cc: Lucas De Marchi <[e-mail]>
Cc: Matthew Brost <[e-mail]>
Cc: Rodrigo Vivi <[e-mail]>
Cc: Michal Wajdeczko <[e-mail]>
Cc: Jani Nikula <[e-mail]>
Reviewed-by: Rodrigo Vivi <[e-mail]>
Link: https://patchwork.freedesktop.org/patch/msgid/[e-mail]
Signed-off-by: Rodrigo Vivi <[e-mail]>

drivers/gpu/drm/xe/xe_device.c

···
 #include "xe_device.h"
 
 #include <linux/delay.h>
+#include <linux/fault-inject.h>
 #include <linux/units.h>
 
 #include <drm/drm_aperture.h>
···
 err:
 	return ERR_PTR(err);
 }
+ALLOW_ERROR_INJECTION(xe_device_create, ERRNO); /* See xe_pci_probe() */
 
 static bool xe_driver_flr_disabled(struct xe_device *xe)
 {
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(wait_for_lmem_ready, ERRNO); /* See xe_pci_probe() */
 
 static void update_device_info(struct xe_device *xe)
 {

drivers/gpu/drm/xe/xe_ggtt.c

···
 
 #include "xe_ggtt.h"
 
+#include <linux/fault-inject.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/sizes.h>
 
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_ggtt_init_early, ERRNO); /* See xe_pci_probe() */
 
 static void xe_ggtt_invalidate(struct xe_ggtt *ggtt);
 

drivers/gpu/drm/xe/xe_guc_ads.c

···
 
 #include "xe_guc_ads.h"
 
+#include <linux/fault-inject.h>
+
 #include <drm/drm_managed.h>
 
 #include <generated/xe_wa_oob.h>
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_guc_ads_init, ERRNO); /* See xe_pci_probe() */
 
 /**
  * xe_guc_ads_init_post_hwconfig - initialize ADS post hwconfig load

drivers/gpu/drm/xe/xe_guc_ct.c

···
 #include <linux/bitfield.h>
 #include <linux/circ_buf.h>
 #include <linux/delay.h>
+#include <linux/fault-inject.h>
 
 #include <kunit/static_stub.h>
 
···
 	ct->state = XE_GUC_CT_STATE_DISABLED;
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_guc_ct_init, ERRNO); /* See xe_pci_probe() */
 
 #define desc_read(xe_, guc_ctb__, field_)			\
 	xe_map_rd_field(xe_, &guc_ctb__->desc, 0,		\

drivers/gpu/drm/xe/xe_guc_log.c

···
 
 #include "xe_guc_log.h"
 
+#include <linux/fault-inject.h>
+
 #include <drm/drm_managed.h>
 
 #include "xe_bo.h"
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_guc_log_init, ERRNO); /* See xe_pci_probe() */

drivers/gpu/drm/xe/xe_guc_relay.c

···
 
 #include <linux/bitfield.h>
 #include <linux/delay.h>
+#include <linux/fault-inject.h>
 
 #include <drm/drm_managed.h>
 
···
 
 	return drmm_add_action_or_reset(&xe->drm, __fini_relay, relay);
 }
+ALLOW_ERROR_INJECTION(xe_guc_relay_init, ERRNO); /* See xe_pci_probe() */
 
 static u32 to_relay_error(int err)
 {

drivers/gpu/drm/xe/xe_pci.c

···
 	pci_set_drvdata(pdev, NULL);
 }
 
+/*
+ * Probe the PCI device, initialize various parts of the driver.
+ *
+ * Fault injection is used to test the error paths of some initialization
+ * functions called either directly from xe_pci_probe() or indirectly for
+ * example through xe_device_probe(). Those functions use the kernel fault
+ * injection capabilities infrastructure, see
+ * Documentation/fault-injection/fault-injection.rst for details. The macro
+ * ALLOW_ERROR_INJECTION() is used to conditionally skip function execution
+ * at runtime and use a provided return value. The first requirement for
+ * error injectable functions is proper handling of the error code by the
+ * caller for recovery, which is always the case here. The second
+ * requirement is that no state is changed before the first error return.
+ * It is not strictly fullfilled for all initialization functions using the
+ * ALLOW_ERROR_INJECTION() macro but this is acceptable because for those
+ * error cases at probe time, the error code is simply propagated up by the
+ * caller. Therefore there is no consequence on those specific callers when
+ * function error injection skips the whole function.
+ */
 static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	const struct xe_device_desc *desc = (const void *)ent->driver_data;

drivers/gpu/drm/xe/xe_pm.c

···
 
 #include "xe_pm.h"
 
+#include <linux/fault-inject.h>
 #include <linux/pm_runtime.h>
 
 #include <drm/drm_managed.h>
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_pm_init_early, ERRNO); /* See xe_pci_probe() */
 
 /**
  * xe_pm_init - Initialize Xe Power Management

drivers/gpu/drm/xe/xe_sriov.c

···
  * Copyright © 2023 Intel Corporation
  */
 
+#include <linux/fault-inject.h>
+
 #include <drm/drm_managed.h>
 
 #include "regs/xe_regs.h"
···
 
 	return drmm_add_action_or_reset(&xe->drm, fini_sriov, xe);
 }
+ALLOW_ERROR_INJECTION(xe_sriov_init, ERRNO); /* See xe_pci_probe() */
 
 /**
  * xe_sriov_print_info - Print basic SR-IOV information.

drivers/gpu/drm/xe/xe_tile.c

···
  * Copyright © 2023 Intel Corporation
  */
 
+#include <linux/fault-inject.h>
+
 #include <drm/drm_managed.h>
 
 #include "xe_device.h"
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_tile_init_early, ERRNO); /* See xe_pci_probe() */
 
 static int tile_ttm_mgr_init(struct xe_tile *tile)
 {

drivers/gpu/drm/xe/xe_uc_fw.c

···
  */
 
 #include <linux/bitfield.h>
+#include <linux/fault-inject.h>
 #include <linux/firmware.h>
 
 #include <drm/drm_managed.h>
···
 
 	return err;
 }
+ALLOW_ERROR_INJECTION(xe_uc_fw_init, ERRNO); /* See xe_pci_probe() */
 
 static u32 uc_fw_ggtt_offset(struct xe_uc_fw *uc_fw)
 {

drivers/gpu/drm/xe/xe_wa.c

···
 #include <drm/drm_managed.h>
 #include <kunit/visibility.h>
 #include <linux/compiler_types.h>
+#include <linux/fault-inject.h>
 
 #include <generated/xe_wa_oob.h>
 
···
 
 	return 0;
 }
+ALLOW_ERROR_INJECTION(xe_wa_init, ERRNO); /* See xe_pci_probe() */
 
 void xe_wa_dump(struct xe_gt *gt, struct drm_printer *p)
 {

drivers/gpu/drm/xe/xe_wopcm.c

···
 
 #include "xe_wopcm.h"
 
+#include <linux/fault-inject.h>
+
 #include "regs/xe_guc_regs.h"
 #include "xe_device.h"
 #include "xe_force_wake.h"
···
 
 	return ret;
 }
+ALLOW_ERROR_INJECTION(xe_wopcm_init, ERRNO); /* See xe_pci_probe() */