[PATCH 2/4] drm/xe: Add fault injection for rebind worker -ENOSPC

[Thomas Hellström]

Add fault injection support using the kernel fault injection
infrastructure to inject -ENOSPC early in the success path of
preempt_rebind_work_func(), before xe_svm_notifier_lock() is taken,
testing the error handling paths without interference from real
resource exhaustion.

Injection is restricted to restartable VMs. When triggered, the
worker deactivates the VM (rebind_deactivated).
Upcoming patches will then also post an error event to userspace.

Enable via debugfs:

  echo 1 > /sys/kernel/debug/dri/0/fail_rebind/times
  echo 100 > /sys/kernel/debug/dri/0/fail_rebind/probability

Assisted-by: GitHub_Copilot:claude-sonnet-4.6
Signed-off-by: Thomas Hellström <thomas.hellstrom@xxxxxxxxxxxxxxx>
---
 drivers/gpu/drm/xe/xe_debugfs.c |  4 +++-
 drivers/gpu/drm/xe/xe_vm.c      | 32 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.h      |  5 +++++
 3 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 22b471303984..1a92c52ccd83 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -35,8 +35,8 @@
 #ifdef CONFIG_DRM_XE_DEBUG
 #include "xe_bo_evict.h"
 #include "xe_migrate.h"
-#include "xe_vm.h"
 #endif
+#include "xe_vm.h"
 
 DECLARE_FAULT_ATTR(gt_reset_failure);
 DECLARE_FAULT_ATTR(inject_csc_hw_error);
@@ -612,6 +612,8 @@ void xe_debugfs_register(struct xe_device *xe)
 
 	fault_create_debugfs_attr("fail_gt_reset", root, &gt_reset_failure);
 
+	xe_vm_debugfs_register(root);
+
 	if (IS_SRIOV_PF(xe))
 		xe_sriov_pf_debugfs_register(xe, root);
 	else if (IS_SRIOV_VF(xe))
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 86ed8f31a219..b69a2e5bd9c9 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -18,6 +18,9 @@
 #include <linux/kthread.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+#endif
 
 #include <generated/xe_wa_oob.h>
 
@@ -43,6 +46,17 @@
 #include "xe_vm_madvise.h"
 #include "xe_wa.h"
 
+#ifdef CONFIG_FAULT_INJECTION
+static DECLARE_FAULT_ATTR(rebind_enospc);
+
+static void xe_vm_register_fault_attrs(struct dentry *root)
+{
+	fault_create_debugfs_attr("fail_rebind", root, &rebind_enospc);
+}
+#else
+static inline void xe_vm_register_fault_attrs(struct dentry *root) {}
+#endif
+
 static struct drm_gem_object *xe_vm_obj(struct xe_vm *vm)
 {
 	return vm->gpuvm.r_obj;
@@ -529,6 +543,13 @@ static void preempt_rebind_work_func(struct work_struct *w)
 		goto out_unlock;
 	}
 
+#ifdef CONFIG_FAULT_INJECTION
+	if (xe_vm_is_restartable(vm) && should_fail(&rebind_enospc, 1)) {
+		err = -ENOSPC;
+		goto out_unlock;
+	}
+#endif
+
 #define retry_required(__tries, __vm) \
 	(IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT) ? \
 	(!(__tries)++ || __xe_vm_userptr_needs_repin(__vm)) : \
@@ -5042,3 +5063,14 @@ void xe_vm_remove_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 	}
 	up_write(&vm->exec_queues.lock);
 }
+
+#ifdef CONFIG_DEBUG_FS
+/**
+ * xe_vm_debugfs_register() - Register xe_vm debugfs entries
+ * @root: debugfs root dentry for this device
+ */
+void xe_vm_debugfs_register(struct dentry *root)
+{
+	xe_vm_register_fault_attrs(root);
+}
+#endif
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 9ee44599cacd..0f9a38d97bf6 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -216,6 +216,11 @@ int xe_vm_restart_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
 void xe_vm_close_and_put(struct xe_vm *vm);
 
+#ifdef CONFIG_DEBUG_FS
+struct dentry;
+void xe_vm_debugfs_register(struct dentry *root);
+#endif
+
 static inline bool xe_vm_in_fault_mode(struct xe_vm *vm)
 {
 	return vm->flags & XE_VM_FLAG_FAULT_MODE;
-- 
2.54.0