Cross-subsystem Changes:

- Add device specific vfio_pci driver variant for intel graphics (Michal Winiarski)
 
 Driver Changes:
 - Add scope-based cleanup helper for runtime PM (Matt Roper)
 - Additional xe driver prerequisites and exports (Michal Winiarski)
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRskUM7w1oG5rx2IZO4FpNVCsYGvwUCaS1ZrwAKCRC4FpNVCsYG
 v9iHAQCPfipm3pC3SykJCKe0Ve+gWfglHg4uuwaRLcvlO+fZsQD/T/enYeR+6omX
 S+owV2xgoVY0cEqYqPsEeOwp4Nj7BQs=
 =0Ouw
 -----END PGP SIGNATURE-----

Merge tag 'topic/xe-vfio-2025-12-01' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Cross-subsystem Changes:
- Add device specific vfio_pci driver variant for intel graphics (Michal Winiarski)

Driver Changes:
- Add scope-based cleanup helper for runtime PM (Matt Roper)
- Additional xe driver prerequisites and exports (Michal Winiarski)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patch.msgid.link/aS1bNpqeem6PIHrA@fedora

MAINTAINERS

@@ -27022,6 +27022,13 @@ L:	virtualization@lists.linux.dev
 S:	Maintained
 F:	drivers/vfio/pci/virtio
 
+VFIO XE PCI DRIVER
+M:	Michał Winiarski <michal.winiarski@intel.com>
+L:	kvm@vger.kernel.org
+L:	intel-xe@lists.freedesktop.org
+S:	Supported
+F:	drivers/vfio/pci/xe
+
 VGA_SWITCHEROO
 R:	Lukas Wunner <lukas@wunner.de>
 S:	Maintained

drivers/gpu/drm/xe/Makefile

@@ -184,6 +184,10 @@ xe-$(CONFIG_PCI_IOV) += \
 	xe_sriov_pf_sysfs.o \
 	xe_tile_sriov_pf_debugfs.o
 
+ifeq ($(CONFIG_PCI_IOV),y)
+	xe-$(CONFIG_XE_VFIO_PCI) += xe_sriov_vfio.o
+endif
+
 # include helpers for tests even when XE is built-in
 ifdef CONFIG_DRM_XE_KUNIT_TEST
 xe-y += tests/xe_kunit_helpers.o

drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c

@@ -17,6 +17,7 @@
 #include "xe_gt_sriov_pf_helpers.h"
 #include "xe_gt_sriov_pf_migration.h"
 #include "xe_gt_sriov_printk.h"
+#include "xe_guc.h"
 #include "xe_guc_buf.h"
 #include "xe_guc_ct.h"
 #include "xe_migrate.h"
@@ -1023,6 +1024,12 @@ static void action_ring_cleanup(void *arg)
 	ptr_ring_cleanup(r, destroy_pf_packet);
 }
 
+static void pf_gt_migration_check_support(struct xe_gt *gt)
+{
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) < MAKE_GUC_VER(70, 54, 0))
+		xe_sriov_pf_migration_disable(gt_to_xe(gt), "requires GuC version >= 70.54.0");
+}
+
 /**
  * xe_gt_sriov_pf_migration_init() - Initialize support for VF migration.
  * @gt: the &xe_gt
@@ -1039,6 +1046,8 @@ int xe_gt_sriov_pf_migration_init(struct xe_gt *gt)
 
 	xe_gt_assert(gt, IS_SRIOV_PF(xe));
 
+	pf_gt_migration_check_support(gt);
+
 	if (!pf_migration_supported(gt))
 		return 0;
 

drivers/gpu/drm/xe/xe_pci.c

@@ -1223,6 +1223,23 @@ static struct pci_driver xe_pci_driver = {
 #endif
 };
 
+/**
+ * xe_pci_to_pf_device() - Get PF &xe_device.
+ * @pdev: the VF &pci_dev device
+ *
+ * Return: pointer to PF &xe_device, NULL otherwise.
+ */
+struct xe_device *xe_pci_to_pf_device(struct pci_dev *pdev)
+{
+	struct drm_device *drm;
+
+	drm = pci_iov_get_pf_drvdata(pdev, &xe_pci_driver);
+	if (IS_ERR(drm))
+		return NULL;
+
+	return to_xe_device(drm);
+}
+
 int xe_register_pci_driver(void)
 {
 	return pci_register_driver(&xe_pci_driver);

drivers/gpu/drm/xe/xe_pci.h

@@ -6,7 +6,10 @@
 #ifndef _XE_PCI_H_
 #define _XE_PCI_H_
 
+struct pci_dev;
+
 int xe_register_pci_driver(void);
 void xe_unregister_pci_driver(void);
+struct xe_device *xe_pci_to_pf_device(struct pci_dev *pdev);
 
 #endif

drivers/gpu/drm/xe/xe_pm.c

@@ -726,6 +726,13 @@ static void xe_pm_runtime_lockdep_prime(void)
 /**
  * xe_pm_runtime_get - Get a runtime_pm reference and resume synchronously
  * @xe: xe device instance
+ *
+ * When possible, scope-based runtime PM (through guard(xe_pm_runtime)) is
+ * be preferred over direct usage of this function.  Manual get/put handling
+ * should only be used when the function contains goto-based logic which
+ * can break scope-based handling, or when the lifetime of the runtime PM
+ * reference does not match a specific scope (e.g., runtime PM obtained in one
+ * function and released in a different one).
  */
 void xe_pm_runtime_get(struct xe_device *xe)
 {
@@ -758,6 +765,13 @@ void xe_pm_runtime_put(struct xe_device *xe)
  * xe_pm_runtime_get_ioctl - Get a runtime_pm reference before ioctl
  * @xe: xe device instance
  *
+ * When possible, scope-based runtime PM (through
+ * ACQUIRE(xe_pm_runtime_ioctl, ...)) is be preferred over direct usage of this
+ * function.  Manual get/put handling should only be used when the function
+ * contains goto-based logic which can break scope-based handling, or when the
+ * lifetime of the runtime PM reference does not match a specific scope (e.g.,
+ * runtime PM obtained in one function and released in a different one).
+ *
  * Returns: Any number greater than or equal to 0 for success, negative error
  * code otherwise.
  */
@@ -827,6 +841,13 @@ static bool xe_pm_suspending_or_resuming(struct xe_device *xe)
  * It will warn if not protected.
  * The reference should be put back after this function regardless, since it
  * will always bump the usage counter, regardless.
+ *
+ * When possible, scope-based runtime PM (through guard(xe_pm_runtime_noresume))
+ * is be preferred over direct usage of this function.  Manual get/put handling
+ * should only be used when the function contains goto-based logic which can
+ * break scope-based handling, or when the lifetime of the runtime PM reference
+ * does not match a specific scope (e.g., runtime PM obtained in one function
+ * and released in a different one).
  */
 void xe_pm_runtime_get_noresume(struct xe_device *xe)
 {

drivers/gpu/drm/xe/xe_pm.h

@@ -6,6 +6,7 @@
 #ifndef _XE_PM_H_
 #define _XE_PM_H_
 
+#include <linux/cleanup.h>
 #include <linux/pm_runtime.h>
 
 #define DEFAULT_VRAM_THRESHOLD 300 /* in MB */
@@ -37,4 +38,20 @@ int xe_pm_block_on_suspend(struct xe_device *xe);
 void xe_pm_might_block_on_suspend(void);
 int xe_pm_module_init(void);
 
+static inline void __xe_pm_runtime_noop(struct xe_device *xe) {}
+
+DEFINE_GUARD(xe_pm_runtime, struct xe_device *,
+	     xe_pm_runtime_get(_T), xe_pm_runtime_put(_T))
+DEFINE_GUARD(xe_pm_runtime_noresume, struct xe_device *,
+	     xe_pm_runtime_get_noresume(_T), xe_pm_runtime_put(_T))
+DEFINE_GUARD_COND(xe_pm_runtime, _ioctl, xe_pm_runtime_get_ioctl(_T), _RET >= 0)
+
+/*
+ * Used when a function needs to release runtime PM in all possible cases
+ * and error paths, but the wakeref was already acquired by a different
+ * function (i.e., get() has already happened so only a put() is needed).
+ */
+DEFINE_GUARD(xe_pm_runtime_release_only, struct xe_device *,
+	     __xe_pm_runtime_noop(_T), xe_pm_runtime_put(_T));
+
 #endif

drivers/gpu/drm/xe/xe_sriov_pf_migration.c

@@ -46,13 +46,37 @@ bool xe_sriov_pf_migration_supported(struct xe_device *xe)
 {
 	xe_assert(xe, IS_SRIOV_PF(xe));
 
-	return xe->sriov.pf.migration.supported;
+	return IS_ENABLED(CONFIG_DRM_XE_DEBUG) || !xe->sriov.pf.migration.disabled;
 }
 
-static bool pf_check_migration_support(struct xe_device *xe)
+/**
+ * xe_sriov_pf_migration_disable() - Turn off SR-IOV VF migration support on PF.
+ * @xe: the &xe_device instance.
+ * @fmt: format string for the log message, to be combined with following VAs.
+ */
+void xe_sriov_pf_migration_disable(struct xe_device *xe, const char *fmt, ...)
 {
-	/* XXX: for now this is for feature enabling only */
+	struct va_format vaf;
-	return IS_ENABLED(CONFIG_DRM_XE_DEBUG);
+	va_list va_args;
+
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
+	va_start(va_args, fmt);
+	vaf.fmt = fmt;
+	vaf.va  = &va_args;
+	xe_sriov_notice(xe, "migration %s: %pV\n",
+			IS_ENABLED(CONFIG_DRM_XE_DEBUG) ?
+			"missing prerequisite" : "disabled",
+			&vaf);
+	va_end(va_args);
+
+	xe->sriov.pf.migration.disabled = true;
+}
+
+static void pf_migration_check_support(struct xe_device *xe)
+{
+	if (!xe_device_has_memirq(xe))
+		xe_sriov_pf_migration_disable(xe, "requires memory-based IRQ support");
 }
 
 static void pf_migration_cleanup(void *arg)
@@ -77,7 +101,8 @@ int xe_sriov_pf_migration_init(struct xe_device *xe)
 
 	xe_assert(xe, IS_SRIOV_PF(xe));
 
-	xe->sriov.pf.migration.supported = pf_check_migration_support(xe);
+	pf_migration_check_support(xe);
+
 	if (!xe_sriov_pf_migration_supported(xe))
 		return 0;
 

drivers/gpu/drm/xe/xe_sriov_pf_migration.h

@@ -14,6 +14,7 @@ struct xe_sriov_packet;
 
 int xe_sriov_pf_migration_init(struct xe_device *xe);
 bool xe_sriov_pf_migration_supported(struct xe_device *xe);
+void xe_sriov_pf_migration_disable(struct xe_device *xe, const char *fmt, ...);
 int xe_sriov_pf_migration_restore_produce(struct xe_device *xe, unsigned int vfid,
 					  struct xe_sriov_packet *data);
 struct xe_sriov_packet *

drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h

@@ -14,8 +14,8 @@
  * struct xe_sriov_pf_migration - Xe device level VF migration data
  */
 struct xe_sriov_pf_migration {
-	/** @supported: indicates whether VF migration feature is supported */
+	/** @disabled: indicates whether VF migration feature is disabled */
-	bool supported;
+	bool disabled;
 };
 
 /**

drivers/gpu/drm/xe/xe_sriov_vfio.c

@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include <drm/intel/xe_sriov_vfio.h>
+#include <linux/cleanup.h>
+
+#include "xe_pci.h"
+#include "xe_pm.h"
+#include "xe_sriov_pf_control.h"
+#include "xe_sriov_pf_helpers.h"
+#include "xe_sriov_pf_migration.h"
+
+struct xe_device *xe_sriov_vfio_get_pf(struct pci_dev *pdev)
+{
+	return xe_pci_to_pf_device(pdev);
+}
+EXPORT_SYMBOL_FOR_MODULES(xe_sriov_vfio_get_pf, "xe-vfio-pci");
+
+bool xe_sriov_vfio_migration_supported(struct xe_device *xe)
+{
+	if (!IS_SRIOV_PF(xe))
+		return -EPERM;
+
+	return xe_sriov_pf_migration_supported(xe);
+}
+EXPORT_SYMBOL_FOR_MODULES(xe_sriov_vfio_migration_supported, "xe-vfio-pci");
+
+#define DEFINE_XE_SRIOV_VFIO_FUNCTION(_type, _func, _impl)			\
+_type xe_sriov_vfio_##_func(struct xe_device *xe, unsigned int vfid)		\
+{										\
+	if (!IS_SRIOV_PF(xe))							\
+		return -EPERM;							\
+	if (vfid == PFID || vfid > xe_sriov_pf_num_vfs(xe))			\
+		return -EINVAL;							\
+										\
+	guard(xe_pm_runtime_noresume)(xe);					\
+										\
+	return xe_sriov_pf_##_impl(xe, vfid);					\
+}										\
+EXPORT_SYMBOL_FOR_MODULES(xe_sriov_vfio_##_func, "xe-vfio-pci")
+
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, wait_flr_done, control_wait_flr);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, suspend_device, control_pause_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, resume_device, control_resume_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, stop_copy_enter, control_trigger_save_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, stop_copy_exit, control_finish_save_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, resume_data_enter, control_trigger_restore_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, resume_data_exit, control_finish_restore_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(int, error, control_stop_vf);
+DEFINE_XE_SRIOV_VFIO_FUNCTION(ssize_t, stop_copy_size, migration_size);
+
+ssize_t xe_sriov_vfio_data_read(struct xe_device *xe, unsigned int vfid,
+				char __user *buf, size_t len)
+{
+	if (!IS_SRIOV_PF(xe))
+		return -EPERM;
+	if (vfid == PFID || vfid > xe_sriov_pf_num_vfs(xe))
+		return -EINVAL;
+
+	guard(xe_pm_runtime_noresume)(xe);
+
+	return xe_sriov_pf_migration_read(xe, vfid, buf, len);
+}
+EXPORT_SYMBOL_FOR_MODULES(xe_sriov_vfio_data_read, "xe-vfio-pci");
+
+ssize_t xe_sriov_vfio_data_write(struct xe_device *xe, unsigned int vfid,
+				 const char __user *buf, size_t len)
+{
+	if (!IS_SRIOV_PF(xe))
+		return -EPERM;
+	if (vfid == PFID || vfid > xe_sriov_pf_num_vfs(xe))
+		return -EINVAL;
+
+	guard(xe_pm_runtime_noresume)(xe);
+
+	return xe_sriov_pf_migration_write(xe, vfid, buf, len);
+}
+EXPORT_SYMBOL_FOR_MODULES(xe_sriov_vfio_data_write, "xe-vfio-pci");

drivers/vfio/pci/Kconfig

@@ -67,4 +67,6 @@ source "drivers/vfio/pci/nvgrace-gpu/Kconfig"
 
 source "drivers/vfio/pci/qat/Kconfig"
 
+source "drivers/vfio/pci/xe/Kconfig"
+
 endmenu

drivers/vfio/pci/Makefile

@@ -19,3 +19,5 @@ obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/
 obj-$(CONFIG_NVGRACE_GPU_VFIO_PCI) += nvgrace-gpu/
 
 obj-$(CONFIG_QAT_VFIO_PCI) += qat/
+
+obj-$(CONFIG_XE_VFIO_PCI) += xe/

drivers/vfio/pci/xe/Kconfig

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config XE_VFIO_PCI
+	tristate "VFIO support for Intel Graphics"
+	depends on DRM_XE && PCI_IOV
+	select VFIO_PCI_CORE
+	help
+	  This option enables device specific VFIO driver variant for Intel Graphics.
+	  In addition to generic VFIO PCI functionality, it implements VFIO
+	  migration uAPI allowing userspace to enable migration for
+	  Intel Graphics SR-IOV Virtual Functions supported by the Xe driver.
+
+	  If you don't know what to do here, say N.

drivers/vfio/pci/xe/Makefile

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_XE_VFIO_PCI) += xe-vfio-pci.o
+xe-vfio-pci-y := main.o

drivers/vfio/pci/xe/main.c

@@ -0,0 +1,573 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include <linux/anon_inodes.h>
+#include <linux/delay.h>
+#include <linux/file.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/sizes.h>
+#include <linux/types.h>
+#include <linux/vfio.h>
+#include <linux/vfio_pci_core.h>
+
+#include <drm/intel/xe_sriov_vfio.h>
+#include <drm/intel/pciids.h>
+
+struct xe_vfio_pci_migration_file {
+	struct file *filp;
+	/* serializes accesses to migration data */
+	struct mutex lock;
+	struct xe_vfio_pci_core_device *xe_vdev;
+	u8 disabled:1;
+};
+
+struct xe_vfio_pci_core_device {
+	struct vfio_pci_core_device core_device;
+	struct xe_device *xe;
+	/* PF internal control uses vfid index starting from 1 */
+	unsigned int vfid;
+	u8 deferred_reset:1;
+	/* protects migration state */
+	struct mutex state_mutex;
+	enum vfio_device_mig_state mig_state;
+	/* protects the reset_done flow */
+	spinlock_t reset_lock;
+	struct xe_vfio_pci_migration_file *migf;
+};
+
+#define xe_vdev_to_dev(xe_vdev) (&(xe_vdev)->core_device.pdev->dev)
+
+static void xe_vfio_pci_disable_file(struct xe_vfio_pci_migration_file *migf)
+{
+	mutex_lock(&migf->lock);
+	migf->disabled = true;
+	mutex_unlock(&migf->lock);
+}
+
+static void xe_vfio_pci_put_file(struct xe_vfio_pci_core_device *xe_vdev)
+{
+	xe_vfio_pci_disable_file(xe_vdev->migf);
+	fput(xe_vdev->migf->filp);
+	xe_vdev->migf = NULL;
+}
+
+static void xe_vfio_pci_reset(struct xe_vfio_pci_core_device *xe_vdev)
+{
+	if (xe_vdev->migf)
+		xe_vfio_pci_put_file(xe_vdev);
+
+	xe_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+}
+
+static void xe_vfio_pci_state_mutex_lock(struct xe_vfio_pci_core_device *xe_vdev)
+{
+	mutex_lock(&xe_vdev->state_mutex);
+}
+
+/*
+ * This function is called in all state_mutex unlock cases to
+ * handle a 'deferred_reset' if exists.
+ */
+static void xe_vfio_pci_state_mutex_unlock(struct xe_vfio_pci_core_device *xe_vdev)
+{
+again:
+	spin_lock(&xe_vdev->reset_lock);
+	if (xe_vdev->deferred_reset) {
+		xe_vdev->deferred_reset = false;
+		spin_unlock(&xe_vdev->reset_lock);
+		xe_vfio_pci_reset(xe_vdev);
+		goto again;
+	}
+	mutex_unlock(&xe_vdev->state_mutex);
+	spin_unlock(&xe_vdev->reset_lock);
+}
+
+static void xe_vfio_pci_reset_done(struct pci_dev *pdev)
+{
+	struct xe_vfio_pci_core_device *xe_vdev = pci_get_drvdata(pdev);
+	int ret;
+
+	if (!pdev->is_virtfn)
+		return;
+
+	/*
+	 * VF FLR requires additional processing done by PF driver.
+	 * The processing is done after FLR is already finished from PCIe
+	 * perspective.
+	 * In order to avoid a scenario where VF is used while PF processing
+	 * is still in progress, additional synchronization point is needed.
+	 */
+	ret = xe_sriov_vfio_wait_flr_done(xe_vdev->xe, xe_vdev->vfid);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to wait for FLR: %d\n", ret);
+
+	if (!xe_vdev->vfid)
+		return;
+
+	/*
+	 * As the higher VFIO layers are holding locks across reset and using
+	 * those same locks with the mm_lock we need to prevent ABBA deadlock
+	 * with the state_mutex and mm_lock.
+	 * In case the state_mutex was taken already we defer the cleanup work
+	 * to the unlock flow of the other running context.
+	 */
+	spin_lock(&xe_vdev->reset_lock);
+	xe_vdev->deferred_reset = true;
+	if (!mutex_trylock(&xe_vdev->state_mutex)) {
+		spin_unlock(&xe_vdev->reset_lock);
+		return;
+	}
+	spin_unlock(&xe_vdev->reset_lock);
+	xe_vfio_pci_state_mutex_unlock(xe_vdev);
+
+	xe_vfio_pci_reset(xe_vdev);
+}
+
+static const struct pci_error_handlers xe_vfio_pci_err_handlers = {
+	.reset_done = xe_vfio_pci_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
+static int xe_vfio_pci_open_device(struct vfio_device *core_vdev)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+	struct vfio_pci_core_device *vdev = &xe_vdev->core_device;
+	int ret;
+
+	ret = vfio_pci_core_enable(vdev);
+	if (ret)
+		return ret;
+
+	xe_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+
+	vfio_pci_core_finish_enable(vdev);
+
+	return 0;
+}
+
+static void xe_vfio_pci_close_device(struct vfio_device *core_vdev)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+
+	xe_vfio_pci_state_mutex_lock(xe_vdev);
+	xe_vfio_pci_reset(xe_vdev);
+	xe_vfio_pci_state_mutex_unlock(xe_vdev);
+	vfio_pci_core_close_device(core_vdev);
+}
+
+static int xe_vfio_pci_release_file(struct inode *inode, struct file *filp)
+{
+	struct xe_vfio_pci_migration_file *migf = filp->private_data;
+
+	mutex_destroy(&migf->lock);
+	kfree(migf);
+
+	return 0;
+}
+
+static ssize_t xe_vfio_pci_save_read(struct file *filp, char __user *buf, size_t len, loff_t *pos)
+{
+	struct xe_vfio_pci_migration_file *migf = filp->private_data;
+	ssize_t ret;
+
+	if (pos)
+		return -ESPIPE;
+
+	mutex_lock(&migf->lock);
+	if (migf->disabled) {
+		mutex_unlock(&migf->lock);
+		return -ENODEV;
+	}
+
+	ret = xe_sriov_vfio_data_read(migf->xe_vdev->xe, migf->xe_vdev->vfid, buf, len);
+	mutex_unlock(&migf->lock);
+
+	return ret;
+}
+
+static const struct file_operations xe_vfio_pci_save_fops = {
+	.owner = THIS_MODULE,
+	.read = xe_vfio_pci_save_read,
+	.release = xe_vfio_pci_release_file,
+	.llseek = noop_llseek,
+};
+
+static ssize_t xe_vfio_pci_resume_write(struct file *filp, const char __user *buf,
+					size_t len, loff_t *pos)
+{
+	struct xe_vfio_pci_migration_file *migf = filp->private_data;
+	ssize_t ret;
+
+	if (pos)
+		return -ESPIPE;
+
+	mutex_lock(&migf->lock);
+	if (migf->disabled) {
+		mutex_unlock(&migf->lock);
+		return -ENODEV;
+	}
+
+	ret = xe_sriov_vfio_data_write(migf->xe_vdev->xe, migf->xe_vdev->vfid, buf, len);
+	mutex_unlock(&migf->lock);
+
+	return ret;
+}
+
+static const struct file_operations xe_vfio_pci_resume_fops = {
+	.owner = THIS_MODULE,
+	.write = xe_vfio_pci_resume_write,
+	.release = xe_vfio_pci_release_file,
+	.llseek = noop_llseek,
+};
+
+static const char *vfio_dev_state_str(u32 state)
+{
+	switch (state) {
+	case VFIO_DEVICE_STATE_RUNNING: return "running";
+	case VFIO_DEVICE_STATE_RUNNING_P2P: return "running_p2p";
+	case VFIO_DEVICE_STATE_STOP_COPY: return "stopcopy";
+	case VFIO_DEVICE_STATE_STOP: return "stop";
+	case VFIO_DEVICE_STATE_RESUMING: return "resuming";
+	case VFIO_DEVICE_STATE_ERROR: return "error";
+	default: return "";
+	}
+}
+
+enum xe_vfio_pci_file_type {
+	XE_VFIO_FILE_SAVE = 0,
+	XE_VFIO_FILE_RESUME,
+};
+
+static struct xe_vfio_pci_migration_file *
+xe_vfio_pci_alloc_file(struct xe_vfio_pci_core_device *xe_vdev,
+		       enum xe_vfio_pci_file_type type)
+{
+	struct xe_vfio_pci_migration_file *migf;
+	const struct file_operations *fops;
+	int flags;
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	fops = type == XE_VFIO_FILE_SAVE ? &xe_vfio_pci_save_fops : &xe_vfio_pci_resume_fops;
+	flags = type == XE_VFIO_FILE_SAVE ? O_RDONLY : O_WRONLY;
+	migf->filp = anon_inode_getfile("xe_vfio_mig", fops, migf, flags);
+	if (IS_ERR(migf->filp)) {
+		kfree(migf);
+		return ERR_CAST(migf->filp);
+	}
+
+	mutex_init(&migf->lock);
+	migf->xe_vdev = xe_vdev;
+	xe_vdev->migf = migf;
+
+	stream_open(migf->filp->f_inode, migf->filp);
+
+	return migf;
+}
+
+static struct file *
+xe_vfio_set_state(struct xe_vfio_pci_core_device *xe_vdev, u32 new)
+{
+	u32 cur = xe_vdev->mig_state;
+	int ret;
+
+	dev_dbg(xe_vdev_to_dev(xe_vdev),
+		"state: %s->%s\n", vfio_dev_state_str(cur), vfio_dev_state_str(new));
+
+	/*
+	 * "STOP" handling is reused for "RUNNING_P2P", as the device doesn't
+	 * have the capability to selectively block outgoing p2p DMA transfers.
+	 * While the device is allowing BAR accesses when the VF is stopped, it
+	 * is not processing any new workload requests, effectively stopping
+	 * any outgoing DMA transfers (not just p2p).
+	 * Any VRAM / MMIO accesses occurring during "RUNNING_P2P" are kept and
+	 * will be migrated to target VF during stop-copy.
+	 */
+	if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+		ret = xe_sriov_vfio_suspend_device(xe_vdev->xe, xe_vdev->vfid);
+		if (ret)
+			goto err;
+
+		return NULL;
+	}
+
+	if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_STOP) ||
+	    (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING_P2P))
+		return NULL;
+
+	if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
+		ret = xe_sriov_vfio_resume_device(xe_vdev->xe, xe_vdev->vfid);
+		if (ret)
+			goto err;
+
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
+		struct xe_vfio_pci_migration_file *migf;
+
+		migf = xe_vfio_pci_alloc_file(xe_vdev, XE_VFIO_FILE_SAVE);
+		if (IS_ERR(migf)) {
+			ret = PTR_ERR(migf);
+			goto err;
+		}
+		get_file(migf->filp);
+
+		ret = xe_sriov_vfio_stop_copy_enter(xe_vdev->xe, xe_vdev->vfid);
+		if (ret) {
+			fput(migf->filp);
+			goto err;
+		}
+
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) {
+		if (xe_vdev->migf)
+			xe_vfio_pci_put_file(xe_vdev);
+
+		ret = xe_sriov_vfio_stop_copy_exit(xe_vdev->xe, xe_vdev->vfid);
+		if (ret)
+			goto err;
+
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RESUMING) {
+		struct xe_vfio_pci_migration_file *migf;
+
+		migf = xe_vfio_pci_alloc_file(xe_vdev, XE_VFIO_FILE_RESUME);
+		if (IS_ERR(migf)) {
+			ret = PTR_ERR(migf);
+			goto err;
+		}
+		get_file(migf->filp);
+
+		ret = xe_sriov_vfio_resume_data_enter(xe_vdev->xe, xe_vdev->vfid);
+		if (ret) {
+			fput(migf->filp);
+			goto err;
+		}
+
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
+		if (xe_vdev->migf)
+			xe_vfio_pci_put_file(xe_vdev);
+
+		ret = xe_sriov_vfio_resume_data_exit(xe_vdev->xe, xe_vdev->vfid);
+		if (ret)
+			goto err;
+
+		return NULL;
+	}
+
+	WARN(true, "Unknown state transition %d->%d", cur, new);
+	return ERR_PTR(-EINVAL);
+
+err:
+	dev_dbg(xe_vdev_to_dev(xe_vdev),
+		"Failed to transition state: %s->%s err=%d\n",
+		vfio_dev_state_str(cur), vfio_dev_state_str(new), ret);
+	return ERR_PTR(ret);
+}
+
+static struct file *
+xe_vfio_pci_set_device_state(struct vfio_device *core_vdev,
+			     enum vfio_device_mig_state new_state)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+	enum vfio_device_mig_state next_state;
+	struct file *f = NULL;
+	int ret;
+
+	xe_vfio_pci_state_mutex_lock(xe_vdev);
+	while (new_state != xe_vdev->mig_state) {
+		ret = vfio_mig_get_next_state(core_vdev, xe_vdev->mig_state,
+					      new_state, &next_state);
+		if (ret) {
+			xe_sriov_vfio_error(xe_vdev->xe, xe_vdev->vfid);
+			f = ERR_PTR(ret);
+			break;
+		}
+		f = xe_vfio_set_state(xe_vdev, next_state);
+		if (IS_ERR(f))
+			break;
+
+		xe_vdev->mig_state = next_state;
+
+		/* Multiple state transitions with non-NULL file in the middle */
+		if (f && new_state != xe_vdev->mig_state) {
+			fput(f);
+			f = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	xe_vfio_pci_state_mutex_unlock(xe_vdev);
+
+	return f;
+}
+
+static int xe_vfio_pci_get_device_state(struct vfio_device *core_vdev,
+					enum vfio_device_mig_state *curr_state)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+
+	xe_vfio_pci_state_mutex_lock(xe_vdev);
+	*curr_state = xe_vdev->mig_state;
+	xe_vfio_pci_state_mutex_unlock(xe_vdev);
+
+	return 0;
+}
+
+static int xe_vfio_pci_get_data_size(struct vfio_device *vdev,
+				     unsigned long *stop_copy_length)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+
+	xe_vfio_pci_state_mutex_lock(xe_vdev);
+	*stop_copy_length = xe_sriov_vfio_stop_copy_size(xe_vdev->xe, xe_vdev->vfid);
+	xe_vfio_pci_state_mutex_unlock(xe_vdev);
+
+	return 0;
+}
+
+static const struct vfio_migration_ops xe_vfio_pci_migration_ops = {
+	.migration_set_state = xe_vfio_pci_set_device_state,
+	.migration_get_state = xe_vfio_pci_get_device_state,
+	.migration_get_data_size = xe_vfio_pci_get_data_size,
+};
+
+static void xe_vfio_pci_migration_init(struct xe_vfio_pci_core_device *xe_vdev)
+{
+	struct vfio_device *core_vdev = &xe_vdev->core_device.vdev;
+	struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
+	struct xe_device *xe = xe_sriov_vfio_get_pf(pdev);
+
+	if (!xe)
+		return;
+	if (!xe_sriov_vfio_migration_supported(xe))
+		return;
+
+	mutex_init(&xe_vdev->state_mutex);
+	spin_lock_init(&xe_vdev->reset_lock);
+
+	/* PF internal control uses vfid index starting from 1 */
+	xe_vdev->vfid = pci_iov_vf_id(pdev) + 1;
+	xe_vdev->xe = xe;
+
+	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
+	core_vdev->mig_ops = &xe_vfio_pci_migration_ops;
+}
+
+static void xe_vfio_pci_migration_fini(struct xe_vfio_pci_core_device *xe_vdev)
+{
+	if (!xe_vdev->vfid)
+		return;
+
+	mutex_destroy(&xe_vdev->state_mutex);
+}
+
+static int xe_vfio_pci_init_dev(struct vfio_device *core_vdev)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+
+	xe_vfio_pci_migration_init(xe_vdev);
+
+	return vfio_pci_core_init_dev(core_vdev);
+}
+
+static void xe_vfio_pci_release_dev(struct vfio_device *core_vdev)
+{
+	struct xe_vfio_pci_core_device *xe_vdev =
+		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+
+	xe_vfio_pci_migration_fini(xe_vdev);
+}
+
+static const struct vfio_device_ops xe_vfio_pci_ops = {
+	.name = "xe-vfio-pci",
+	.init = xe_vfio_pci_init_dev,
+	.release = xe_vfio_pci_release_dev,
+	.open_device = xe_vfio_pci_open_device,
+	.close_device = xe_vfio_pci_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.device_feature = vfio_pci_core_ioctl_feature,
+	.read = vfio_pci_core_read,
+	.write = vfio_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static int xe_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct xe_vfio_pci_core_device *xe_vdev;
+	int ret;
+
+	xe_vdev = vfio_alloc_device(xe_vfio_pci_core_device, core_device.vdev, &pdev->dev,
+				    &xe_vfio_pci_ops);
+	if (IS_ERR(xe_vdev))
+		return PTR_ERR(xe_vdev);
+
+	dev_set_drvdata(&pdev->dev, &xe_vdev->core_device);
+
+	ret = vfio_pci_core_register_device(&xe_vdev->core_device);
+	if (ret) {
+		vfio_put_device(&xe_vdev->core_device.vdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void xe_vfio_pci_remove(struct pci_dev *pdev)
+{
+	struct xe_vfio_pci_core_device *xe_vdev = pci_get_drvdata(pdev);
+
+	vfio_pci_core_unregister_device(&xe_vdev->core_device);
+	vfio_put_device(&xe_vdev->core_device.vdev);
+}
+
+#define INTEL_PCI_VFIO_DEVICE(_id) { \
+	PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, (_id)) \
+}
+
+static const struct pci_device_id xe_vfio_pci_table[] = {
+	INTEL_PTL_IDS(INTEL_PCI_VFIO_DEVICE),
+	INTEL_WCL_IDS(INTEL_PCI_VFIO_DEVICE),
+	INTEL_BMG_IDS(INTEL_PCI_VFIO_DEVICE),
+	{}
+};
+MODULE_DEVICE_TABLE(pci, xe_vfio_pci_table);
+
+static struct pci_driver xe_vfio_pci_driver = {
+	.name = "xe-vfio-pci",
+	.id_table = xe_vfio_pci_table,
+	.probe = xe_vfio_pci_probe,
+	.remove = xe_vfio_pci_remove,
+	.err_handler = &xe_vfio_pci_err_handlers,
+	.driver_managed_dma = true,
+};
+module_pci_driver(xe_vfio_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Michał Winiarski <michal.winiarski@intel.com>");
+MODULE_DESCRIPTION("VFIO PCI driver with migration support for Intel Graphics");

include/drm/intel/xe_sriov_vfio.h

@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_SRIOV_VFIO_H_
+#define _XE_SRIOV_VFIO_H_
+
+#include <linux/types.h>
+
+struct pci_dev;
+struct xe_device;
+
+/**
+ * xe_sriov_vfio_get_pf() - Get PF &xe_device.
+ * @pdev: the VF &pci_dev device
+ *
+ * Return: pointer to PF &xe_device, NULL otherwise.
+ */
+struct xe_device *xe_sriov_vfio_get_pf(struct pci_dev *pdev);
+
+/**
+ * xe_sriov_vfio_migration_supported() - Check if migration is supported.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ *
+ * Return: true if migration is supported, false otherwise.
+ */
+bool xe_sriov_vfio_migration_supported(struct xe_device *xe);
+
+/**
+ * xe_sriov_vfio_wait_flr_done() - Wait for VF FLR completion.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * This function will wait until VF FLR is processed by PF on all tiles (or
+ * until timeout occurs).
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_wait_flr_done(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_suspend_device() - Suspend VF.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * This function will pause VF on all tiles/GTs.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_suspend_device(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_resume_device() - Resume VF.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * This function will resume VF on all tiles.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_resume_device(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_stop_copy_enter() - Initiate a VF device migration data save.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_stop_copy_enter(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_stop_copy_exit() - Finish a VF device migration data save.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_stop_copy_exit(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_resume_data_enter() - Initiate a VF device migration data restore.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_resume_data_enter(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_resume_data_exit() - Finish a VF device migration data restore.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_resume_data_exit(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_error() - Move VF device to error state.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * Reset is needed to move it out of error state.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_vfio_error(struct xe_device *xe, unsigned int vfid);
+
+/**
+ * xe_sriov_vfio_data_read() - Read migration data from the VF device.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ * @buf: start address of userspace buffer
+ * @len: requested read size from userspace
+ *
+ * Return: number of bytes that has been successfully read,
+ *	   0 if no more migration data is available, -errno on failure.
+ */
+ssize_t xe_sriov_vfio_data_read(struct xe_device *xe, unsigned int vfid,
+				char __user *buf, size_t len);
+/**
+ * xe_sriov_vfio_data_write() - Write migration data to the VF device.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ * @buf: start address of userspace buffer
+ * @len: requested write size from userspace
+ *
+ * Return: number of bytes that has been successfully written, -errno on failure.
+ */
+ssize_t xe_sriov_vfio_data_write(struct xe_device *xe, unsigned int vfid,
+				 const char __user *buf, size_t len);
+/**
+ * xe_sriov_vfio_stop_copy_size() - Get a size estimate of VF device migration data.
+ * @xe: the PF &xe_device obtained by calling xe_sriov_vfio_get_pf()
+ * @vfid: the VF identifier (can't be 0)
+ *
+ * Return: migration data size in bytes or a negative error code on failure.
+ */
+ssize_t xe_sriov_vfio_stop_copy_size(struct xe_device *xe, unsigned int vfid);
+
+#endif