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

10 files changed, 184 insertions, 7 deletions

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index e4b273b025d2..a1f86a59d687 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/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
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
index d5d918ddce4f..3174a8dee779 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_migration.c
+++ b/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;
 
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index bbe6f8e65844..0e39a0255b99 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/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);
diff --git a/drivers/gpu/drm/xe/xe_pci.h b/drivers/gpu/drm/xe/xe_pci.h
index 611c1209b14c..11bcc5fe2c5b 100644
--- a/drivers/gpu/drm/xe/xe_pci.h
+++ b/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
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index 44924512830f..766922530265 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/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)
 {
diff --git a/drivers/gpu/drm/xe/xe_pm.h b/drivers/gpu/drm/xe/xe_pm.h
index f7f89a18b6fc..6b27039e7b2d 100644
--- a/drivers/gpu/drm/xe/xe_pm.h
+++ b/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
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c b/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
index de06cc690fc8..6c4b16409cc9 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.c
+++ b/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, ...)
+{
+	struct va_format vaf;
+	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)
 {
-	/* XXX: for now this is for feature enabling only */
-	return IS_ENABLED(CONFIG_DRM_XE_DEBUG);
+	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;
 
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration.h b/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
index b806298a0bb6..f8f408df8481 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf_migration.h
+++ b/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 *
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h b/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h
index 363d673ee1dd..7d9a8a278d91 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf_migration_types.h
+++ b/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 */
-	bool supported;
+	/** @disabled: indicates whether VF migration feature is disabled */
+	bool disabled;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_sriov_vfio.c b/drivers/gpu/drm/xe/xe_sriov_vfio.c
new file mode 100644
index 000000000000..e9a7615bb5c5
--- /dev/null
+++ b/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");