Add an API to enable the PCI subsystem to track all devices that are preserved across a Live Update, including both incoming devices (passed from the previous kernel) and outgoing devices (passed to the next kernel).

Use PCI segment number and BDF to keep track of devices across Live Update. This means the kernel must keep both identifiers constant across a Live Update for any preserved device. VFs are not supported for now, since that requires preserving SR-IOV state on the device to ensure the same number of VFs appear after kexec and with the same BDFs.

Drivers that preserve devices across Live Update can now register their struct liveupdate_file_handler with the PCI subsystem so that the PCI subsystem can allocate and manage File-Lifecycle-Bound (FLB) global data to track the list of incoming and outgoing preserved devices.

pci_liveupdate_register_fh(driver_fh) pci_liveupdate_unregister_fh(driver_fh)

Drivers can notify the PCI subsystem whenever a device is preserved and unpreserved with the following APIs:

pci_liveupdate_outgoing_preserve(pci_dev) pci_liveupdate_outgoing_unpreserve(pci_dev)

After a Live Update, the PCI subsystem can fetch its FLB global data from the previous kernel from the Live Update Orchestrator (LUO) to determine which devices are preserved. This API is also made available for drivers to use to check if a device was preserved before userspace retrieves the file for it.

pci_liveupdate_incoming_is_preserved(pci_dev)

Once a driver has finished restoring an incoming preserved device, it can notify the PCI subsystem with the following call:

pci_liveupdate_incoming_finish(pci_dev)

This will be used in subsequent commits by the vfio-pci driver to preserve VFIO devices across Live Update.

Signed-off-by: David Matlack dmatlack@google.com --- drivers/pci/Makefile | 1 + drivers/pci/liveupdate.c | 248 ++++++++++++++++++++++++++++++++++++ include/linux/kho/abi/pci.h | 53 ++++++++ include/linux/pci.h | 38 ++++++ 4 files changed, 340 insertions(+) create mode 100644 drivers/pci/liveupdate.c create mode 100644 include/linux/kho/abi/pci.h

diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 67647f1880fb..0cb43e10e71d 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSFS) += pci-sysfs.o slot.o obj-$(CONFIG_ACPI) += pci-acpi.o obj-$(CONFIG_GENERIC_PCI_IOMAP) += iomap.o +obj-$(CONFIG_LIVEUPDATE) += liveupdate.o endif

obj-$(CONFIG_OF) += of.o diff --git a/drivers/pci/liveupdate.c b/drivers/pci/liveupdate.c new file mode 100644 index 000000000000..f9bb97f3bada --- /dev/null +++ b/drivers/pci/liveupdate.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2025, Google LLC. + * David Matlack dmatlack@google.com + */ + +#include <linux/bsearch.h> +#include <linux/io.h> +#include <linux/kexec_handover.h> +#include <linux/kho/abi/pci.h> +#include <linux/liveupdate.h> +#include <linux/mutex.h> +#include <linux/mm.h> +#include <linux/pci.h> +#include <linux/sort.h> + +static DEFINE_MUTEX(pci_flb_outgoing_lock); +static DEFINE_MUTEX(pci_flb_incoming_lock); + +static int pci_flb_preserve(struct liveupdate_flb_op_args *args) +{ + struct pci_dev *dev = NULL; + struct folio *folio; + unsigned int order; + int nr_devices = 0; + int ret; + + /* + * Calculate the maximum number of devices based on what's present + * on the system currently (including VFs) to size the folio holding + * struct pci_ser. This is not perfect given devices could be + * hotplugged, but it's also unlikely that all devices in the system are + * going to be preserved anyway. + */ + for_each_pci_dev(dev) { + if (dev->is_virtfn) + continue; + + nr_devices += 1 + pci_sriov_get_totalvfs(dev); + } + + order = get_order(offsetof(struct pci_ser, devices[nr_devices + 1])); + + folio = folio_alloc(GFP_KERNEL | __GFP_ZERO, order); + if (!folio) + return -ENOMEM; + + ret = kho_preserve_folio(folio); + if (ret) { + folio_put(folio); + return ret; + } + + args->obj = folio_address(folio); + args->data = virt_to_phys(args->obj); + + return 0; +} + +static void pci_flb_unpreserve(struct liveupdate_flb_op_args *args) +{ + struct pci_ser *ser = args->obj; + struct folio *folio = virt_to_folio(ser); + + WARN_ON_ONCE(ser->nr_devices); + kho_unpreserve_folio(folio); + folio_put(folio); +} + +static int pci_flb_retrieve(struct liveupdate_flb_op_args *args) +{ + struct folio *folio; + + folio = kho_restore_folio(args->data); + if (!folio) + panic("Unable to restore preserved FLB data from KHO (0x%llx)\n", args->data); + + args->obj = folio_address(folio); + return 0; +} + +static void pci_flb_finish(struct liveupdate_flb_op_args *args) +{ + struct pci_ser *ser = args->obj; + + /* + * Sanity check that all devices have been finished via + * pci_liveupdate_incoming_finish(). + */ + WARN_ON_ONCE(ser->nr_devices); + folio_put(virt_to_folio(ser)); +} + +static struct liveupdate_flb_ops pci_liveupdate_flb_ops = { + .preserve = pci_flb_preserve, + .unpreserve = pci_flb_unpreserve, + .retrieve = pci_flb_retrieve, + .finish = pci_flb_finish, + .owner = THIS_MODULE, +}; + +static struct liveupdate_flb pci_liveupdate_flb = { + .ops = &pci_liveupdate_flb_ops, + .compatible = PCI_LUO_FLB_COMPATIBLE, +}; + +#define INIT_PCI_DEV_SER(_dev) { \ + .domain = pci_domain_nr((_dev)->bus), \ + .bdf = pci_dev_id(_dev), \ +} + +static int pci_dev_ser_cmp(const void *__a, const void *__b) +{ + const struct pci_dev_ser *a = __a, *b = __b; + + return cmp_int(a->domain << 16 | a->bdf, b->domain << 16 | b->bdf); +} + +static struct pci_dev_ser *pci_ser_find(struct pci_ser *ser, struct pci_dev *dev) +{ + const struct pci_dev_ser key = INIT_PCI_DEV_SER(dev); + + return bsearch(&key, ser->devices, ser->nr_devices, + sizeof(key), pci_dev_ser_cmp); +} + +static int pci_ser_delete(struct pci_ser *ser, struct pci_dev *dev) +{ + struct pci_dev_ser *dev_ser; + int i; + + dev_ser = pci_ser_find(ser, dev); + if (!dev_ser) + return -ENOENT; + + for (i = dev_ser - ser->devices; i < ser->nr_devices - 1; i++) + ser->devices[i] = ser->devices[i + 1]; + + ser->nr_devices--; + return 0; +} + +static int max_nr_devices(struct pci_ser *ser) +{ + u64 size; + + size = folio_size(virt_to_folio(ser)); + size -= offsetof(struct pci_ser, devices); + + return size / sizeof(struct pci_dev_ser); +} + +int pci_liveupdate_outgoing_preserve(struct pci_dev *dev) +{ + struct pci_dev_ser new = INIT_PCI_DEV_SER(dev); + struct pci_ser *ser; + int i, ret; + + /* VFs are not supported yet due to BDF instability across kexec */ + if (dev->is_virtfn) + return -EINVAL; + + guard(mutex)(&pci_flb_outgoing_lock); + + ret = liveupdate_flb_get_outgoing(&pci_liveupdate_flb, (void **)&ser); + if (ret) + return ret; + + if (ser->nr_devices == max_nr_devices(ser)) + return -E2BIG; + + for (i = ser->nr_devices; i > 0; i--) { + struct pci_dev_ser *prev = &ser->devices[i - 1]; + int cmp = pci_dev_ser_cmp(&new, prev); + + /* This device is already preserved. */ + if (cmp == 0) + return 0; + + if (cmp > 0) + break; + + ser->devices[i] = *prev; + } + + ser->devices[i] = new; + ser->nr_devices++; + return 0; +} +EXPORT_SYMBOL_GPL(pci_liveupdate_outgoing_preserve); + +void pci_liveupdate_outgoing_unpreserve(struct pci_dev *dev) +{ + struct pci_ser *ser; + int ret; + + guard(mutex)(&pci_flb_outgoing_lock); + + ret = liveupdate_flb_get_outgoing(&pci_liveupdate_flb, (void **)&ser); + if (WARN_ON_ONCE(ret)) + return; + + WARN_ON_ONCE(pci_ser_delete(ser, dev)); +} +EXPORT_SYMBOL_GPL(pci_liveupdate_outgoing_unpreserve); + +bool pci_liveupdate_incoming_is_preserved(struct pci_dev *dev) +{ + struct pci_ser *ser; + int ret; + + guard(mutex)(&pci_flb_incoming_lock); + + ret = liveupdate_flb_get_incoming(&pci_liveupdate_flb, (void **)&ser); + if (ret) + return false; + + return pci_ser_find(ser, dev); +} +EXPORT_SYMBOL_GPL(pci_liveupdate_incoming_is_preserved); + +void pci_liveupdate_incoming_finish(struct pci_dev *dev) +{ + struct pci_ser *ser; + int ret; + + guard(mutex)(&pci_flb_incoming_lock); + + ret = liveupdate_flb_get_incoming(&pci_liveupdate_flb, (void **)&ser); + if (WARN_ON_ONCE(ret)) + return; + + WARN_ON_ONCE(pci_ser_delete(ser, dev)); +} +EXPORT_SYMBOL_GPL(pci_liveupdate_incoming_finish); + +int pci_liveupdate_register_fh(struct liveupdate_file_handler *fh) +{ + return liveupdate_register_flb(fh, &pci_liveupdate_flb); +} +EXPORT_SYMBOL_GPL(pci_liveupdate_register_fh); + +int pci_liveupdate_unregister_fh(struct liveupdate_file_handler *fh) +{ + return liveupdate_unregister_flb(fh, &pci_liveupdate_flb); +} +EXPORT_SYMBOL_GPL(pci_liveupdate_unregister_fh); diff --git a/include/linux/kho/abi/pci.h b/include/linux/kho/abi/pci.h new file mode 100644 index 000000000000..53744b6f191a --- /dev/null +++ b/include/linux/kho/abi/pci.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2025, Google LLC. + * David Matlack dmatlack@google.com + */ + +#ifndef _LINUX_KHO_ABI_PCI_H +#define _LINUX_KHO_ABI_PCI_H + +#include <linux/compiler.h> +#include <linux/types.h> + +/** + * DOC: PCI File-Lifecycle Bound (FLB) Live Update ABI + * + * This header defines the ABI for preserving core PCI state across kexec using + * Live Update File-Lifecycle Bound (FLB) data. + * + * This interface is a contract. Any modification to any of the serialization + * structs defined here constitutes a breaking change. Such changes require + * incrementing the version number in the PCI_LUO_FLB_COMPATIBLE string. + */ + +#define PCI_LUO_FLB_COMPATIBLE "pci-v1" + +/** + * struct pci_dev_ser - Serialized state about a single PCI device. + * + * @domain: The device's PCI domain number (segment). + * @bdf: The device's PCI bus, device, and function number. + */ +struct pci_dev_ser { + u16 domain; + u16 bdf; +} __packed; + +/** + * struct pci_ser - PCI Subsystem Live Update State + * + * This struct tracks state about all devices that are being preserved across + * a Live Update for the next kernel. + * + * @nr_devices: The number of devices that were preserved. + * @devices: Flexible array of pci_dev_ser structs for each device. Guaranteed + * to be sorted ascending by domain and bdf. + */ +struct pci_ser { + u64 nr_devices; + struct pci_dev_ser devices[]; +} __packed; + +#endif /* _LINUX_KHO_ABI_PCI_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index d1fdf81fbe1e..6a3c2d7e5b82 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -40,6 +40,7 @@ #include <linux/resource_ext.h> #include <linux/msi_api.h> #include <uapi/linux/pci.h> +#include <linux/liveupdate.h>

#include <linux/pci_ids.h>

@@ -2795,4 +2796,41 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); WARN_ONCE(condition, "%s %s: " fmt, \ dev_driver_string(&(pdev)->dev), pci_name(pdev), ##arg)

+#ifdef CONFIG_LIVEUPDATE +int pci_liveupdate_outgoing_preserve(struct pci_dev *dev); +void pci_liveupdate_outgoing_unpreserve(struct pci_dev *dev); +bool pci_liveupdate_incoming_is_preserved(struct pci_dev *dev); +void pci_liveupdate_incoming_finish(struct pci_dev *dev); +int pci_liveupdate_register_fh(struct liveupdate_file_handler *fh); +int pci_liveupdate_unregister_fh(struct liveupdate_file_handler *fh); +#else /* !CONFIG_LIVEUPDATE */ +static inline int pci_liveupdate_outgoing_preserve(struct pci_dev *dev) +{ + return -EOPNOTSUPP; +} + +static inline void pci_liveupdate_outgoing_unpreserve(struct pci_dev *dev) +{ +} + +static inline bool pci_liveupdate_incoming_is_preserved(struct pci_dev *dev) +{ + return false; +} + +static inline void pci_liveupdate_incoming_finish(struct pci_dev *dev) +{ +} + +static inline int pci_liveupdate_register_fh(struct liveupdate_file_handler *fh) +{ + return -EOPNOTSUPP; +} + +static inline int pci_liveupdate_unregister_fh(struct liveupdate_file_handler *fh) +{ + return -EOPNOTSUPP; +} +#endif /* !CONFIG_LIVEUPDATE */ + #endif /* LINUX_PCI_H */

From: Vipin Sharma vipinsh@google.com

Implement the live update file handler callbacks to preserve a vfio-pci device across a Live Update. Subsequent commits will enable userspace to then retrieve this file after the Live Update.

Live Update support is scoped only to cdev files (i.e. not VFIO_GROUP_GET_DEVICE_FD files).

State about each device is serialized into a new ABI struct vfio_pci_core_device_ser. The contents of this struct are preserved across the Live Update to the next kernel using a combination of Kexec-Handover (KHO) to preserve the page(s) holding the struct and the Live Update Orchestrator (LUO) to preserve the physical address of the struct.

For now the only contents of struct vfio_pci_core_device_ser the device's PCI segment number and BDF, so that the device can be uniquely identified after the Live Update.

Require that userspace disables interrupts on the device prior to freeze() so that the device does not send any interrupts until new interrupt handlers have been set up by the next kernel.

Reset the device and restore its state in the freeze() callback. This ensures the device can be received by the next kernel in a consistent state. Eventually this will be dropped and the device can be preserved across in a running state, but that requires further work in VFIO and the core PCI layer.

Note that LUO holds a reference to this file when it is preserved. So VFIO is guaranteed that vfio_df_device_last_close() will not be called on this device no matter what userspace does.

Signed-off-by: Vipin Sharma vipinsh@google.com Co-Developed-by: David Matlack dmatlack@google.com Signed-off-by: David Matlack dmatlack@google.com --- drivers/vfio/pci/vfio_pci.c | 2 +- drivers/vfio/pci/vfio_pci_liveupdate.c | 100 ++++++++++++++++++++++++- drivers/vfio/pci/vfio_pci_priv.h | 2 + drivers/vfio/vfio.h | 13 ---- drivers/vfio/vfio_main.c | 9 --- include/linux/kho/abi/vfio_pci.h | 15 ++++ include/linux/vfio.h | 28 +++++++ 7 files changed, 144 insertions(+), 25 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index c2fe34a830d8..281c69c086d3 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -125,7 +125,7 @@ static int vfio_pci_open_device(struct vfio_device *core_vdev) return 0; }

-static const struct vfio_device_ops vfio_pci_ops = { +const struct vfio_device_ops vfio_pci_ops = { .name = "vfio-pci", .init = vfio_pci_core_init_dev, .release = vfio_pci_core_release_dev, diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c index b84e63c0357b..a0147dee8c0f 100644 --- a/drivers/vfio/pci/vfio_pci_liveupdate.c +++ b/drivers/vfio/pci/vfio_pci_liveupdate.c @@ -8,25 +8,120 @@

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

+#include <linux/kexec_handover.h> #include <linux/kho/abi/vfio_pci.h> #include <linux/liveupdate.h> #include <linux/errno.h> +#include <linux/vfio.h>

#include "vfio_pci_priv.h"

static bool vfio_pci_liveupdate_can_preserve(struct liveupdate_file_handler *handler, struct file *file) { - return false; + struct vfio_device_file *df = to_vfio_device_file(file); + + if (!df) + return false; + + /* Live Update support is limited to cdev files. */ + if (df->group) + return false; + + return df->device->ops == &vfio_pci_ops; }

static int vfio_pci_liveupdate_preserve(struct liveupdate_file_op_args *args) { - return -EOPNOTSUPP; + struct vfio_device *device = vfio_device_from_file(args->file); + struct vfio_pci_core_device_ser *ser; + struct vfio_pci_core_device *vdev; + struct pci_dev *pdev; + struct folio *folio; + int err; + + vdev = container_of(device, struct vfio_pci_core_device, vdev); + pdev = vdev->pdev; + + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + return -EINVAL; + + if (vfio_pci_is_intel_display(pdev)) + return -EINVAL; + + folio = folio_alloc(GFP_KERNEL | __GFP_ZERO, get_order(sizeof(*ser))); + if (!folio) + return -ENOMEM; + + ser = folio_address(folio); + + ser->bdf = pci_dev_id(pdev); + ser->domain = pci_domain_nr(pdev->bus); + + err = kho_preserve_folio(folio); + if (err) + goto error; + + args->serialized_data = virt_to_phys(ser); + return 0; + +error: + folio_put(folio); + return err; }

static void vfio_pci_liveupdate_unpreserve(struct liveupdate_file_op_args *args) { + struct vfio_pci_core_device_ser *ser = phys_to_virt(args->serialized_data); + struct folio *folio = virt_to_folio(ser); + + kho_unpreserve_folio(folio); + folio_put(folio); +} + +static int vfio_pci_liveupdate_freeze(struct liveupdate_file_op_args *args) +{ + struct vfio_device *device = vfio_device_from_file(args->file); + struct vfio_pci_core_device *vdev; + struct pci_dev *pdev; + int ret; + + vdev = container_of(device, struct vfio_pci_core_device, vdev); + pdev = vdev->pdev; + + guard(mutex)(&device->dev_set->lock); + + /* + * Userspace must disable interrupts on the device prior to freeze so + * that the device does not send any interrupts until new interrupt + * handlers have been established by the next kernel. + */ + if (vdev->irq_type != VFIO_PCI_NUM_IRQS) { + pci_err(pdev, "Freeze failed! Interrupts are still enabled.\n"); + return -EINVAL; + } + + pci_dev_lock(pdev); + + ret = pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state); + if (ret) + goto out; + + /* + * Reset the device and restore it back to its original state before + * handing it to the next kernel. + * + * Eventually both of these should be dropped and the device should be + * kept running with its current state across the Live Update. + */ + if (vdev->reset_works) + ret = __pci_reset_function_locked(pdev); + + pci_restore_state(pdev); + +out: + pci_dev_unlock(pdev); + return ret; }

static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args) @@ -42,6 +137,7 @@ static const struct liveupdate_file_ops vfio_pci_liveupdate_file_ops = { .can_preserve = vfio_pci_liveupdate_can_preserve, .preserve = vfio_pci_liveupdate_preserve, .unpreserve = vfio_pci_liveupdate_unpreserve, + .freeze = vfio_pci_liveupdate_freeze, .retrieve = vfio_pci_liveupdate_retrieve, .finish = vfio_pci_liveupdate_finish, .owner = THIS_MODULE, diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h index b9f7c4e2b4df..7f189e5e6c0a 100644 --- a/drivers/vfio/pci/vfio_pci_priv.h +++ b/drivers/vfio/pci/vfio_pci_priv.h @@ -11,6 +11,8 @@ /* Cap maximum number of ioeventfds per device (arbitrary) */ #define VFIO_PCI_IOEVENTFD_MAX 1000

+extern const struct vfio_device_ops vfio_pci_ops; + struct vfio_pci_ioeventfd { struct list_head next; struct vfio_pci_core_device *vdev; diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 50128da18bca..6b89edbbf174 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -16,17 +16,6 @@ struct iommufd_ctx; struct iommu_group; struct vfio_container;

-struct vfio_device_file { - struct vfio_device *device; - struct vfio_group *group; - - u8 access_granted; - u32 devid; /* only valid when iommufd is valid */ - spinlock_t kvm_ref_lock; /* protect kvm field */ - struct kvm *kvm; - struct iommufd_ctx *iommufd; /* protected by struct vfio_device_set::lock */ -}; - void vfio_device_put_registration(struct vfio_device *device); bool vfio_device_try_get_registration(struct vfio_device *device); int vfio_df_open(struct vfio_device_file *df); @@ -34,8 +23,6 @@ void vfio_df_close(struct vfio_device_file *df); struct vfio_device_file * vfio_allocate_device_file(struct vfio_device *device);

-extern const struct file_operations vfio_device_fops; - #ifdef CONFIG_VFIO_NOIOMMU extern bool vfio_noiommu __read_mostly; #else diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 38c8e9350a60..9182dc46d73f 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1386,15 +1386,6 @@ const struct file_operations vfio_device_fops = { #endif };

-static struct vfio_device *vfio_device_from_file(struct file *file) -{ - struct vfio_device_file *df = file->private_data; - - if (file->f_op != &vfio_device_fops) - return NULL; - return df->device; -} - /** * vfio_file_is_valid - True if the file is valid vfio file * @file: VFIO group file or VFIO device file diff --git a/include/linux/kho/abi/vfio_pci.h b/include/linux/kho/abi/vfio_pci.h index 37a845eed972..9bf58a2f3820 100644 --- a/include/linux/kho/abi/vfio_pci.h +++ b/include/linux/kho/abi/vfio_pci.h @@ -9,6 +9,9 @@ #ifndef _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H #define _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H

+#include <linux/compiler.h> +#include <linux/types.h> + /** * DOC: VFIO PCI Live Update ABI * @@ -25,4 +28,16 @@

#define VFIO_PCI_LUO_FH_COMPATIBLE "vfio-pci-v1"

+/** + * struct vfio_pci_core_device_ser - Serialized state of a single VFIO PCI + * device. + * + * @bdf: The device's PCI bus, device, and function number. + * @domain: The device's PCI domain number (segment). + */ +struct vfio_pci_core_device_ser { + u16 bdf; + u16 domain; +} __packed; + #endif /* _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index eb563f538dee..f09da3bdf786 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -80,6 +80,34 @@ struct vfio_device { #endif };

+struct vfio_device_file { + struct vfio_device *device; + struct vfio_group *group; + + u8 access_granted; + u32 devid; /* only valid when iommufd is valid */ + spinlock_t kvm_ref_lock; /* protect kvm field */ + struct kvm *kvm; + struct iommufd_ctx *iommufd; /* protected by struct vfio_device_set::lock */ +}; + +extern const struct file_operations vfio_device_fops; + +static inline struct vfio_device_file *to_vfio_device_file(struct file *file) +{ + if (file->f_op != &vfio_device_fops) + return NULL; + + return file->private_data; +} + +static inline struct vfio_device *vfio_device_from_file(struct file *file) +{ + struct vfio_device_file *df = to_vfio_device_file(file); + + return df ? df->device : NULL; +} + /** * struct vfio_device_ops - VFIO bus driver device callbacks *

From: Vipin Sharma vipinsh@google.com

Enable userspace to retrieve preserved VFIO device files from VFIO after a Live Update by implementing the retrieve() and finish() file handler callbacks.

Use an anonymous inode when creating the file, since the retrieved device file is not opened through any particular cdev inode, and the cdev inode does not matter in practice.

For now the retrieved file is functionally equivalent a opening the corresponding VFIO cdev file. Subsequent commits will leverage the preserved state associated with the retrieved file to preserve bits of the device across Live Update.

Signed-off-by: Vipin Sharma vipinsh@google.com Co-Developed-by: David Matlack dmatlack@google.com Signed-off-by: David Matlack dmatlack@google.com --- drivers/vfio/device_cdev.c | 21 +++++--- drivers/vfio/pci/vfio_pci_liveupdate.c | 75 +++++++++++++++++++++++++- drivers/vfio/vfio_main.c | 13 +++++ include/linux/vfio.h | 12 +++++ 4 files changed, 113 insertions(+), 8 deletions(-)

diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c index 480cac3a0c27..0a6e972f322b 100644 --- a/drivers/vfio/device_cdev.c +++ b/drivers/vfio/device_cdev.c @@ -16,14 +16,8 @@ void vfio_init_device_cdev(struct vfio_device *device) device->cdev.owner = THIS_MODULE; }

-/* - * device access via the fd opened by this function is blocked until - * .open_device() is called successfully during BIND_IOMMUFD. - */ -int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep) +int __vfio_device_fops_cdev_open(struct vfio_device *device, struct file *filep) { - struct vfio_device *device = container_of(inode->i_cdev, - struct vfio_device, cdev); struct vfio_device_file *df; int ret;

@@ -52,6 +46,19 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep) vfio_device_put_registration(device); return ret; } +EXPORT_SYMBOL_GPL(__vfio_device_fops_cdev_open); + +/* + * device access via the fd opened by this function is blocked until + * .open_device() is called successfully during BIND_IOMMUFD. + */ +int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep) +{ + struct vfio_device *device = container_of(inode->i_cdev, + struct vfio_device, cdev); + + return __vfio_device_fops_cdev_open(device, filep); +}

static void vfio_df_get_kvm_safe(struct vfio_device_file *df) { diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c index a0147dee8c0f..b7451007fca4 100644 --- a/drivers/vfio/pci/vfio_pci_liveupdate.c +++ b/drivers/vfio/pci/vfio_pci_liveupdate.c @@ -8,6 +8,8 @@

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

+#include <linux/anon_inodes.h> +#include <linux/file.h> #include <linux/kexec_handover.h> #include <linux/kho/abi/vfio_pci.h> #include <linux/liveupdate.h> @@ -124,13 +126,83 @@ static int vfio_pci_liveupdate_freeze(struct liveupdate_file_op_args *args) return ret; }

+static int match_device(struct device *dev, const void *arg) +{ + struct vfio_device *device = container_of(dev, struct vfio_device, device); + const struct vfio_pci_core_device_ser *ser = arg; + struct vfio_pci_core_device *vdev; + struct pci_dev *pdev; + + vdev = container_of(device, struct vfio_pci_core_device, vdev); + pdev = vdev->pdev; + + return ser->bdf == pci_dev_id(pdev) && ser->domain == pci_domain_nr(pdev->bus); +} + static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args) { - return -EOPNOTSUPP; + struct vfio_pci_core_device_ser *ser; + struct vfio_device *device; + struct folio *folio; + struct file *file; + int ret; + + folio = kho_restore_folio(args->serialized_data); + if (!folio) + return -ENOENT; + + ser = folio_address(folio); + + device = vfio_find_device(ser, match_device); + if (!device) + return -ENODEV; + + /* + * During a Live Update userspace retrieves preserved VFIO cdev files by + * issuing an ioctl on /dev/liveupdate rather than by opening VFIO + * character devices. + * + * To handle that scenario, this routine simulates opening the VFIO + * character device for userspace with an anonymous inode. The returned + * file has the same properties as a cdev file (e.g. operations are + * blocked until BIND_IOMMUFD is called), aside from the inode + * association. + */ + file = anon_inode_getfile_fmode("[vfio-device-liveupdate]", + &vfio_device_fops, NULL, + O_RDWR, FMODE_PREAD | FMODE_PWRITE); + + if (IS_ERR(file)) { + ret = PTR_ERR(file); + goto out; + } + + ret = __vfio_device_fops_cdev_open(device, file); + if (ret) { + fput(file); + goto out; + } + + args->file = file; + +out: + /* Drop the reference from vfio_find_device() */ + put_device(&device->device); + + return ret; +} + +static bool vfio_pci_liveupdate_can_finish(struct liveupdate_file_op_args *args) +{ + return args->retrieved; }

static void vfio_pci_liveupdate_finish(struct liveupdate_file_op_args *args) { + struct folio *folio; + + folio = virt_to_folio(phys_to_virt(args->serialized_data)); + folio_put(folio); }

static const struct liveupdate_file_ops vfio_pci_liveupdate_file_ops = { @@ -139,6 +211,7 @@ static const struct liveupdate_file_ops vfio_pci_liveupdate_file_ops = { .unpreserve = vfio_pci_liveupdate_unpreserve, .freeze = vfio_pci_liveupdate_freeze, .retrieve = vfio_pci_liveupdate_retrieve, + .can_finish = vfio_pci_liveupdate_can_finish, .finish = vfio_pci_liveupdate_finish, .owner = THIS_MODULE, }; diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 9182dc46d73f..c5b5eb509474 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -13,6 +13,7 @@ #include <linux/cdev.h> #include <linux/compat.h> #include <linux/device.h> +#include <linux/device/class.h> #include <linux/fs.h> #include <linux/idr.h> #include <linux/iommu.h> @@ -1706,6 +1707,18 @@ int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data, } EXPORT_SYMBOL(vfio_dma_rw);

+struct vfio_device *vfio_find_device(const void *data, device_match_t match) +{ + struct device *device; + + device = class_find_device(vfio.device_class, NULL, data, match); + if (!device) + return NULL; + + return container_of(device, struct vfio_device, device); +} +EXPORT_SYMBOL_GPL(vfio_find_device); + /* * Module/class support */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f09da3bdf786..4e400a7219ea 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -413,4 +413,16 @@ int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void vfio_virqfd_disable(struct virqfd **pvirqfd); void vfio_virqfd_flush_thread(struct virqfd **pvirqfd);

+#if IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) +int __vfio_device_fops_cdev_open(struct vfio_device *device, struct file *filep); +#else +static inline int __vfio_device_fops_cdev_open(struct vfio_device *device, + struct file *filep) +{ + return -EOPNOTSUPP; +} +#endif /* IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) */ + +struct vfio_device *vfio_find_device(const void *data, device_match_t match); + #endif /* VFIO_H */

Stash a pointer to a device's Live Updated state in struct vfio_pci_core_device. This will enable subsequent commits to use the preserved state when enabling the device.

To enable VFIO to safely access this pointer during device enablement, require that the device is fully enabled before returning true from can_finish().

Signed-off-by: David Matlack dmatlack@google.com --- drivers/vfio/pci/vfio_pci_core.c | 1 + drivers/vfio/pci/vfio_pci_liveupdate.c | 20 +++++++++++++++++++- include/linux/vfio_pci_core.h | 6 ++++++ 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 7dcf5439dedc..b09fe0993e04 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -536,6 +536,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev)) vdev->has_vga = true;

+ vdev->liveupdate_state = NULL;

return 0;

diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c index 7669c65bde17..0fb29bd3ae3b 100644 --- a/drivers/vfio/pci/vfio_pci_liveupdate.c +++ b/drivers/vfio/pci/vfio_pci_liveupdate.c @@ -145,6 +145,7 @@ static int match_device(struct device *dev, const void *arg) static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args) { struct vfio_pci_core_device_ser *ser; + struct vfio_pci_core_device *vdev; struct vfio_device *device; struct folio *folio; struct file *file; @@ -186,6 +187,9 @@ static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args) goto out; }

+ vdev = container_of(device, struct vfio_pci_core_device, vdev); + vdev->liveupdate_state = ser; + args->file = file;

out: @@ -197,7 +201,21 @@ static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args)

static bool vfio_pci_liveupdate_can_finish(struct liveupdate_file_op_args *args) { - return args->retrieved; + struct vfio_pci_core_device *vdev; + struct vfio_device *device; + + if (!args->retrieved) + return false; + + device = vfio_device_from_file(args->file); + vdev = container_of(device, struct vfio_pci_core_device, vdev); + + /* + * Ensure VFIO is done using vdev->liveupdate_state, which means its + * safe for vfio_pci_liveupdate_finish() to free it. + */ + guard(mutex)(&device->dev_set->lock); + return !vdev->liveupdate_state; }

static void vfio_pci_liveupdate_finish(struct liveupdate_file_op_args *args) diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index f541044e42a2..56ff6452562d 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -94,6 +94,12 @@ struct vfio_pci_core_device { struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct rw_semaphore memory_lock; + + /* + * State passed by the previous kernel during a Live Update. Only + * safe to access when first opening the device. + */ + struct vfio_pci_core_device_ser *liveupdate_state; };

/* Will be exported for vfio pci drivers usage */

From: Vipin Sharma vipinsh@google.com

Use the given VFIO cdev FD to initialize vfio_pci_device in VFIO selftests. Add the assertion to make sure that passed cdev FD is not used with legacy VFIO APIs. If VFIO cdev FD is provided then do not open the device instead use the FD for any interaction with the device.

This API will allow to write selftests where VFIO device FD is preserved using liveupdate and retrieved later using liveupdate ioctl after kexec.

Signed-off-by: Vipin Sharma vipinsh@google.com Co-Developed-by: David Matlack dmatlack@google.com Signed-off-by: David Matlack dmatlack@google.com --- .../lib/include/libvfio/vfio_pci_device.h | 3 ++ .../selftests/vfio/lib/vfio_pci_device.c | 33 ++++++++++++++----- 2 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h b/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h index 2858885a89bb..896dfde88118 100644 --- a/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h +++ b/tools/testing/selftests/vfio/lib/include/libvfio/vfio_pci_device.h @@ -38,6 +38,9 @@ struct vfio_pci_device { #define dev_info(_dev, _fmt, ...) printf("%s: " _fmt, (_dev)->bdf, ##__VA_ARGS__) #define dev_err(_dev, _fmt, ...) fprintf(stderr, "%s: " _fmt, (_dev)->bdf, ##__VA_ARGS__)

+struct vfio_pci_device *__vfio_pci_device_init(const char *bdf, + struct iommu *iommu, + int device_fd); struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iommu); void vfio_pci_device_cleanup(struct vfio_pci_device *device);

diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 468ee1c61b0c..e9423dc3864a 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -319,19 +319,27 @@ static void vfio_device_attach_iommufd_pt(int device_fd, u32 pt_id) ioctl_assert(device_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &args); }

-static void vfio_pci_iommufd_setup(struct vfio_pci_device *device, const char *bdf) +static void vfio_pci_iommufd_setup(struct vfio_pci_device *device, + const char *bdf, int device_fd) { - const char *cdev_path = vfio_pci_get_cdev_path(bdf); + const char *cdev_path;

- device->fd = open(cdev_path, O_RDWR); - VFIO_ASSERT_GE(device->fd, 0); - free((void *)cdev_path); + if (device_fd >= 0) { + device->fd = device_fd; + } else { + cdev_path = vfio_pci_get_cdev_path(bdf); + device->fd = open(cdev_path, O_RDWR); + VFIO_ASSERT_GE(device->fd, 0); + free((void *)cdev_path); + }

vfio_device_bind_iommufd(device->fd, device->iommu->iommufd); vfio_device_attach_iommufd_pt(device->fd, device->iommu->ioas_id); }

-struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iommu) +struct vfio_pci_device *__vfio_pci_device_init(const char *bdf, + struct iommu *iommu, + int device_fd) { struct vfio_pci_device *device;

@@ -341,10 +349,12 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iomm device->bdf = bdf; device->iommu = iommu;

- if (device->iommu->mode->container_path) + if (device->iommu->mode->container_path) { + VFIO_ASSERT_EQ(device_fd, -1); vfio_pci_container_setup(device, bdf); - else - vfio_pci_iommufd_setup(device, bdf); + } else { + vfio_pci_iommufd_setup(device, bdf, device_fd); + }

vfio_pci_device_setup(device); vfio_pci_driver_probe(device); @@ -352,6 +362,11 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iomm return device; }

+struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iommu) +{ + return __vfio_pci_device_init(bdf, iommu, /*device_fd=*/-1); +} + void vfio_pci_device_cleanup(struct vfio_pci_device *device) { int i;

From: Vipin Sharma vipinsh@google.com

Do not reset the device when a Live Update preserved vfio-pci device is retrieved and first enabled. vfio_pci_liveupdate_freeze() guarantees the device is reset prior to Live Update, so there's no reason to reset it again after Live Update.

Since VFIO normally uses the initial reset to detect if the device supports function resets, pass that from the previous kernel via struct vfio_pci_core_dev_ser.

Signed-off-by: Vipin Sharma vipinsh@google.com Signed-off-by: David Matlack dmatlack@google.com --- drivers/vfio/pci/vfio_pci_core.c | 22 +++++++++++++++++----- drivers/vfio/pci/vfio_pci_liveupdate.c | 1 + include/linux/kho/abi/vfio_pci.h | 2 ++ include/linux/vfio_pci_core.h | 1 + 4 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index b09fe0993e04..c3b30f08a788 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -482,12 +482,24 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) if (ret) goto out_power;

- /* If reset fails because of the device lock, fail this path entirely */ - ret = pci_try_reset_function(pdev); - if (ret == -EAGAIN) - goto out_disable_device; + if (vdev->liveupdate_state) { + /* + * This device was handed off by vfio-pci from a previous kernel + * via Live Update, so it does not need to be reset. + */ + vdev->reset_works = vdev->liveupdate_state->reset_works; + } else { + /* + * If reset fails because of the device lock, fail this path + * entirely. + */ + ret = pci_try_reset_function(pdev); + if (ret == -EAGAIN) + goto out_disable_device; + + vdev->reset_works = !ret; + }

- vdev->reset_works = !ret; pci_save_state(pdev); vdev->pci_saved_state = pci_store_saved_state(pdev); if (!vdev->pci_saved_state) diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c index 0fb29bd3ae3b..bcaf9de8a823 100644 --- a/drivers/vfio/pci/vfio_pci_liveupdate.c +++ b/drivers/vfio/pci/vfio_pci_liveupdate.c @@ -59,6 +59,7 @@ static int vfio_pci_liveupdate_preserve(struct liveupdate_file_op_args *args)

ser->bdf = pci_dev_id(pdev); ser->domain = pci_domain_nr(pdev->bus); + ser->reset_works = vdev->reset_works;

err = kho_preserve_folio(folio); if (err) diff --git a/include/linux/kho/abi/vfio_pci.h b/include/linux/kho/abi/vfio_pci.h index 9bf58a2f3820..6c3d3c6dfc09 100644 --- a/include/linux/kho/abi/vfio_pci.h +++ b/include/linux/kho/abi/vfio_pci.h @@ -34,10 +34,12 @@ * * @bdf: The device's PCI bus, device, and function number. * @domain: The device's PCI domain number (segment). + * @reset_works: Non-zero if the device supports function resets. */ struct vfio_pci_core_device_ser { u16 bdf; u16 domain; + u8 reset_works; } __packed;

#endif /* _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 56ff6452562d..3421721a1615 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -15,6 +15,7 @@ #include <linux/types.h> #include <linux/uuid.h> #include <linux/notifier.h> +#include <linux/kho/abi/vfio_pci.h>

#ifndef VFIO_PCI_CORE_H #define VFIO_PCI_CORE_H

From: Vipin Sharma vipinsh@google.com

Move luo_test_utils.[ch] into a lib/ directory and pull the rules to build them out into a separate make script. This will enable these utilities to be also built by and used within other selftests (such as VFIO) in subsequent commits.

No functional change intended.

Signed-off-by: Vipin Sharma vipinsh@google.com Co-Developed-by: David Matlack dmatlack@google.com Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/liveupdate/.gitignore | 1 + tools/testing/selftests/liveupdate/Makefile | 14 ++++--------- .../include/libliveupdate.h} | 8 ++++---- .../selftests/liveupdate/lib/libliveupdate.mk | 20 +++++++++++++++++++ .../{luo_test_utils.c => lib/liveupdate.c} | 2 +- .../selftests/liveupdate/luo_kexec_simple.c | 2 +- .../selftests/liveupdate/luo_multi_session.c | 2 +- 7 files changed, 32 insertions(+), 17 deletions(-) rename tools/testing/selftests/liveupdate/{luo_test_utils.h => lib/include/libliveupdate.h} (87%) create mode 100644 tools/testing/selftests/liveupdate/lib/libliveupdate.mk rename tools/testing/selftests/liveupdate/{luo_test_utils.c => lib/liveupdate.c} (99%)

diff --git a/tools/testing/selftests/liveupdate/.gitignore b/tools/testing/selftests/liveupdate/.gitignore index 661827083ab6..18a0c7036cf3 100644 --- a/tools/testing/selftests/liveupdate/.gitignore +++ b/tools/testing/selftests/liveupdate/.gitignore @@ -3,6 +3,7 @@ !/**/ !*.c !*.h +!*.mk !*.sh !.gitignore !config diff --git a/tools/testing/selftests/liveupdate/Makefile b/tools/testing/selftests/liveupdate/Makefile index 080754787ede..a060cc21f27f 100644 --- a/tools/testing/selftests/liveupdate/Makefile +++ b/tools/testing/selftests/liveupdate/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only

-LIB_C += luo_test_utils.c - TEST_GEN_PROGS += liveupdate

TEST_GEN_PROGS_EXTENDED += luo_kexec_simple @@ -10,25 +8,21 @@ TEST_GEN_PROGS_EXTENDED += luo_multi_session TEST_FILES += do_kexec.sh

include ../lib.mk +include lib/libliveupdate.mk

CFLAGS += $(KHDR_INCLUDES) CFLAGS += -Wall -O2 -Wno-unused-function CFLAGS += -MD

-LIB_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIB_C)) TEST_O := $(patsubst %, %.o, $(TEST_GEN_PROGS)) TEST_O += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))

-TEST_DEP_FILES := $(patsubst %.o, %.d, $(LIB_O)) +TEST_DEP_FILES := $(patsubst %.o, %.d, $(LIBLIVEUPDATE_O)) TEST_DEP_FILES += $(patsubst %.o, %.d, $(TEST_O)) -include $(TEST_DEP_FILES)

-$(LIB_O): $(OUTPUT)/%.o: %.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/%: %.o $(LIB_O) - $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIB_O) $(LDLIBS) -o $@ +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/%: %.o $(LIBLIVEUPDATE_O) + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBLIVEUPDATE_O) $(LDLIBS) -o $@

-EXTRA_CLEAN += $(LIB_O) EXTRA_CLEAN += $(TEST_O) EXTRA_CLEAN += $(TEST_DEP_FILES) diff --git a/tools/testing/selftests/liveupdate/luo_test_utils.h b/tools/testing/selftests/liveupdate/lib/include/libliveupdate.h similarity index 87% rename from tools/testing/selftests/liveupdate/luo_test_utils.h rename to tools/testing/selftests/liveupdate/lib/include/libliveupdate.h index 90099bf49577..4390a2737930 100644 --- a/tools/testing/selftests/liveupdate/luo_test_utils.h +++ b/tools/testing/selftests/liveupdate/lib/include/libliveupdate.h @@ -7,13 +7,13 @@ * Utility functions for LUO kselftests. */

-#ifndef LUO_TEST_UTILS_H -#define LUO_TEST_UTILS_H +#ifndef SELFTESTS_LIVEUPDATE_LIB_LIVEUPDATE_H +#define SELFTESTS_LIVEUPDATE_LIB_LIVEUPDATE_H

#include <errno.h> #include <string.h> #include <linux/liveupdate.h> -#include "../kselftest.h" +#include "../../../kselftest.h"

#define LUO_DEVICE "/dev/liveupdate"

@@ -41,4 +41,4 @@ typedef void (*luo_test_stage2_fn)(int luo_fd, int state_session_fd); int luo_test(int argc, char *argv[], const char *state_session_name, luo_test_stage1_fn stage1, luo_test_stage2_fn stage2);

-#endif /* LUO_TEST_UTILS_H */ +#endif /* SELFTESTS_LIVEUPDATE_LIB_LIVEUPDATE_H */ diff --git a/tools/testing/selftests/liveupdate/lib/libliveupdate.mk b/tools/testing/selftests/liveupdate/lib/libliveupdate.mk new file mode 100644 index 000000000000..fffd95b085b6 --- /dev/null +++ b/tools/testing/selftests/liveupdate/lib/libliveupdate.mk @@ -0,0 +1,20 @@ +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + +LIBLIVEUPDATE_SRCDIR := $(selfdir)/liveupdate/lib + +LIBLIVEUPDATE_C := liveupdate.c + +LIBLIVEUPDATE_OUTPUT := $(OUTPUT)/libliveupdate + +LIBLIVEUPDATE_O := $(patsubst %.c, $(LIBLIVEUPDATE_OUTPUT)/%.o, $(LIBLIVEUPDATE_C)) + +LIBLIVEUPDATE_O_DIRS := $(shell dirname $(LIBLIVEUPDATE_O) | uniq) +$(shell mkdir -p $(LIBLIVEUPDATE_O_DIRS)) + +CFLAGS += -I$(LIBLIVEUPDATE_SRCDIR)/include + +$(LIBLIVEUPDATE_O): $(LIBLIVEUPDATE_OUTPUT)/%.o : $(LIBLIVEUPDATE_SRCDIR)/%.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +EXTRA_CLEAN += $(LIBLIVEUPDATE_OUTPUT) diff --git a/tools/testing/selftests/liveupdate/luo_test_utils.c b/tools/testing/selftests/liveupdate/lib/liveupdate.c similarity index 99% rename from tools/testing/selftests/liveupdate/luo_test_utils.c rename to tools/testing/selftests/liveupdate/lib/liveupdate.c index 3c8721c505df..60121873f685 100644 --- a/tools/testing/selftests/liveupdate/luo_test_utils.c +++ b/tools/testing/selftests/liveupdate/lib/liveupdate.c @@ -21,7 +21,7 @@ #include <errno.h> #include <stdarg.h>

-#include "luo_test_utils.h" +#include <libliveupdate.h>

int luo_open_device(void) { diff --git a/tools/testing/selftests/liveupdate/luo_kexec_simple.c b/tools/testing/selftests/liveupdate/luo_kexec_simple.c index d7ac1f3dc4cb..786ac93b9ae3 100644 --- a/tools/testing/selftests/liveupdate/luo_kexec_simple.c +++ b/tools/testing/selftests/liveupdate/luo_kexec_simple.c @@ -8,7 +8,7 @@ * across a single kexec reboot. */

-#include "luo_test_utils.h" +#include <libliveupdate.h>

#define TEST_SESSION_NAME "test-session" #define TEST_MEMFD_TOKEN 0x1A diff --git a/tools/testing/selftests/liveupdate/luo_multi_session.c b/tools/testing/selftests/liveupdate/luo_multi_session.c index 0ee2d795beef..aac24a5f5ce3 100644 --- a/tools/testing/selftests/liveupdate/luo_multi_session.c +++ b/tools/testing/selftests/liveupdate/luo_multi_session.c @@ -9,7 +9,7 @@ * files. */

-#include "luo_test_utils.h" +#include <libliveupdate.h>

#define SESSION_EMPTY_1 "multi-test-empty-1" #define SESSION_EMPTY_2 "multi-test-empty-2"

From: Vipin Sharma vipinsh@google.com

Add helper functions to preserve and retrieve file descriptors from an LUO session. These will be used be used in subsequent commits to preserve FDs other than memfd.

No functional change intended.

Signed-off-by: Vipin Sharma vipinsh@google.com Co-Developed-by: David Matlack dmatlack@google.com Signed-off-by: David Matlack dmatlack@google.com --- .../liveupdate/lib/include/libliveupdate.h | 3 ++ .../selftests/liveupdate/lib/liveupdate.c | 41 +++++++++++++++---- 2 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/liveupdate/lib/include/libliveupdate.h b/tools/testing/selftests/liveupdate/lib/include/libliveupdate.h index 4390a2737930..4c93d043d2b3 100644 --- a/tools/testing/selftests/liveupdate/lib/include/libliveupdate.h +++ b/tools/testing/selftests/liveupdate/lib/include/libliveupdate.h @@ -26,6 +26,9 @@ int luo_create_session(int luo_fd, const char *name); int luo_retrieve_session(int luo_fd, const char *name); int luo_session_finish(int session_fd);

+int luo_session_preserve_fd(int session_fd, int fd, int token); +int luo_session_retrieve_fd(int session_fd, int token); + int create_and_preserve_memfd(int session_fd, int token, const char *data); int restore_and_verify_memfd(int session_fd, int token, const char *expected_data);

diff --git a/tools/testing/selftests/liveupdate/lib/liveupdate.c b/tools/testing/selftests/liveupdate/lib/liveupdate.c index 60121873f685..9bf4f16ca0a4 100644 --- a/tools/testing/selftests/liveupdate/lib/liveupdate.c +++ b/tools/testing/selftests/liveupdate/lib/liveupdate.c @@ -54,9 +54,35 @@ int luo_retrieve_session(int luo_fd, const char *name) return arg.fd; }

+int luo_session_preserve_fd(int session_fd, int fd, int token) +{ + struct liveupdate_session_preserve_fd arg = { + .size = sizeof(arg), + .fd = fd, + .token = token, + }; + + if (ioctl(session_fd, LIVEUPDATE_SESSION_PRESERVE_FD, &arg)) + return -errno; + + return 0; +} + +int luo_session_retrieve_fd(int session_fd, int token) +{ + struct liveupdate_session_retrieve_fd arg = { + .size = sizeof(arg), + .token = token, + }; + + if (ioctl(session_fd, LIVEUPDATE_SESSION_RETRIEVE_FD, &arg)) + return -errno; + + return arg.fd; +} + int create_and_preserve_memfd(int session_fd, int token, const char *data) { - struct liveupdate_session_preserve_fd arg = { .size = sizeof(arg) }; long page_size = sysconf(_SC_PAGE_SIZE); void *map = MAP_FAILED; int mfd = -1, ret = -1; @@ -75,9 +101,8 @@ int create_and_preserve_memfd(int session_fd, int token, const char *data) snprintf(map, page_size, "%s", data); munmap(map, page_size);

- arg.fd = mfd; - arg.token = token; - if (ioctl(session_fd, LIVEUPDATE_SESSION_PRESERVE_FD, &arg) < 0) + ret = luo_session_preserve_fd(session_fd, mfd, token); + if (ret) goto out;

ret = 0; @@ -92,15 +117,13 @@ int create_and_preserve_memfd(int session_fd, int token, const char *data) int restore_and_verify_memfd(int session_fd, int token, const char *expected_data) { - struct liveupdate_session_retrieve_fd arg = { .size = sizeof(arg) }; long page_size = sysconf(_SC_PAGE_SIZE); void *map = MAP_FAILED; int mfd = -1, ret = -1;

- arg.token = token; - if (ioctl(session_fd, LIVEUPDATE_SESSION_RETRIEVE_FD, &arg) < 0) - return -errno; - mfd = arg.fd; + mfd = luo_session_retrieve_fd(session_fd, token); + if (mfd < 0) + return mfd;

map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, mfd, 0); if (map == MAP_FAILED)

Add a selftest to exercise preserving a various VFIO files through /dev/liveupdate. Ensure that VFIO cdev device files can be preserved and everything else (group-based device files, group files, and container files) all fail.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/Makefile | 1 + .../vfio/vfio_pci_liveupdate_uapi_test.c | 93 +++++++++++++++++++ 2 files changed, 94 insertions(+) create mode 100644 tools/testing/selftests/vfio/vfio_pci_liveupdate_uapi_test.c

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile index 424649049d94..9b2a4f10c558 100644 --- a/tools/testing/selftests/vfio/Makefile +++ b/tools/testing/selftests/vfio/Makefile @@ -4,6 +4,7 @@ TEST_GEN_PROGS += vfio_iommufd_setup_test TEST_GEN_PROGS += vfio_pci_device_test TEST_GEN_PROGS += vfio_pci_device_init_perf_test TEST_GEN_PROGS += vfio_pci_driver_test +TEST_GEN_PROGS += vfio_pci_liveupdate_uapi_test

TEST_PROGS_EXTENDED := scripts/cleanup.sh TEST_PROGS_EXTENDED := scripts/lib.sh diff --git a/tools/testing/selftests/vfio/vfio_pci_liveupdate_uapi_test.c b/tools/testing/selftests/vfio/vfio_pci_liveupdate_uapi_test.c new file mode 100644 index 000000000000..3b4276b2532c --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_pci_liveupdate_uapi_test.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <libliveupdate.h> +#include <libvfio.h> +#include <kselftest_harness.h> + +static const char *device_bdf; + +FIXTURE(vfio_pci_liveupdate_uapi_test) { + int luo_fd; + int session_fd; + struct iommu *iommu; + struct vfio_pci_device *device; +}; + +FIXTURE_VARIANT(vfio_pci_liveupdate_uapi_test) { + const char *iommu_mode; +}; + +#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode) \ +FIXTURE_VARIANT_ADD(vfio_pci_liveupdate_uapi_test, _iommu_mode) { \ + .iommu_mode = #_iommu_mode, \ +} + +FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(); +#undef FIXTURE_VARIANT_ADD_IOMMU_MODE + +FIXTURE_SETUP(vfio_pci_liveupdate_uapi_test) +{ + self->luo_fd = luo_open_device(); + ASSERT_GE(self->luo_fd, 0); + + self->session_fd = luo_create_session(self->luo_fd, "session"); + ASSERT_GE(self->session_fd, 0); + + self->iommu = iommu_init(variant->iommu_mode); + self->device = vfio_pci_device_init(device_bdf, self->iommu); +} + +FIXTURE_TEARDOWN(vfio_pci_liveupdate_uapi_test) +{ + vfio_pci_device_cleanup(self->device); + iommu_cleanup(self->iommu); + close(self->session_fd); + close(self->luo_fd); +} + +TEST_F(vfio_pci_liveupdate_uapi_test, preserve_device) +{ + int ret; + + ret = luo_session_preserve_fd(self->session_fd, self->device->fd, 0); + + /* Preservation should only be supported for VFIO cdev files. */ + ASSERT_EQ(ret, self->iommu->iommufd ? 0 : -ENOENT); +} + +TEST_F(vfio_pci_liveupdate_uapi_test, preserve_group_fails) +{ + int ret; + + if (self->iommu->iommufd) + return; + + ret = luo_session_preserve_fd(self->session_fd, self->device->group_fd, 0); + ASSERT_EQ(ret, -ENOENT); +} + +TEST_F(vfio_pci_liveupdate_uapi_test, preserve_container_fails) +{ + int ret; + + if (self->iommu->iommufd) + return; + + ret = luo_session_preserve_fd(self->session_fd, self->iommu->container_fd, 0); + ASSERT_EQ(ret, -ENOENT); +} + +int main(int argc, char *argv[]) +{ + int fd; + + fd = luo_open_device(); + if (fd < 0) { + printf("open(%s) failed: %s, skipping\n", LUO_DEVICE, strerror(errno)); + return KSFT_SKIP; + } + close(fd); + + device_bdf = vfio_selftests_get_bdf(&argc, argv); + return test_harness_run(argc, argv); +}

Verify that opening a VFIO device through its cdev file and via VFIO_GROUP_GET_DEVICE_FD both fail with -EBUSY if the device was preserved across a Live Update. When a device file is preserve across a Live Update, the file must be retrieved from /dev/liveupdate, not from VFIO directly.

Signed-off-by: David Matlack dmatlack@google.com --- .../vfio/vfio_pci_liveupdate_kexec_test.c | 38 +++++++++++++++++++ 1 file changed, 38 insertions(+)

diff --git a/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c b/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c index 95644c3bd2d3..925c5fc30d56 100644 --- a/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c @@ -36,6 +36,42 @@ static void before_kexec(int luo_fd) daemonize_and_wait(); }

+static void check_open_vfio_device_fails(void) +{ + const char *cdev_path = vfio_pci_get_cdev_path(device_bdf); + struct vfio_pci_device *device; + struct iommu *iommu; + int ret, i; + + printf("Checking open(%s) fails\n", cdev_path); + ret = open(cdev_path, O_RDWR); + VFIO_ASSERT_EQ(ret, -1); + VFIO_ASSERT_EQ(errno, EBUSY); + free((void *)cdev_path); + + for (i = 0; i < nr_iommu_modes; i++) { + if (!iommu_modes[i].container_path) + continue; + + iommu = iommu_init(iommu_modes[i].name); + + device = vfio_pci_device_alloc(device_bdf, iommu); + vfio_pci_group_setup(device); + vfio_pci_iommu_setup(device); + + printf("Checking ioctl(group_fd, VFIO_GROUP_GET_DEVICE_FD, "%s") fails (%s)\n", + device_bdf, iommu_modes[i].name); + + ret = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, device->bdf); + VFIO_ASSERT_EQ(ret, -1); + VFIO_ASSERT_EQ(errno, EBUSY); + + close(device->group_fd); + free(device); + iommu_cleanup(iommu); + } +} + static void after_kexec(int luo_fd, int state_session_fd) { struct vfio_pci_device *device; @@ -44,6 +80,8 @@ static void after_kexec(int luo_fd, int state_session_fd) int device_fd; int stage;

+ check_open_vfio_device_fails(); + restore_and_read_stage(state_session_fd, STATE_TOKEN, &stage); VFIO_ASSERT_EQ(stage, 2);

On 2025-12-01 05:32 PM, David Matlack wrote:

On 2025-12-01 09:16 AM, Zhu Yanjun wrote:

...

在 2025/12/1 9:10, David Matlack 写道:

...

On Mon, Dec 1, 2025 at 7:49 AM Zhu Yanjun yanjun.zhu@linux.dev wrote:

...

在 2025/11/27 20:56, Zhu Yanjun 写道:

...

Hi, David

ERROR: modpost: "liveupdate_register_file_handler" [drivers/vfio/pci/ vfio-pci-core.ko] undefined!

ERROR: modpost: "vfio_pci_ops" [drivers/vfio/pci/vfio-pci-core.ko] undefined! ERROR: modpost: "liveupdate_enabled" [drivers/vfio/pci/vfio-pci-core.ko] undefined! ERROR: modpost: "liveupdate_unregister_file_handler" [drivers/vfio/pci/ vfio-pci-core.ko] undefined! ERROR: modpost: "vfio_device_fops" [drivers/vfio/pci/vfio-pci-core.ko] undefined! ERROR: modpost: "vfio_pci_is_intel_display" [drivers/vfio/pci/vfio-pci- core.ko] undefined! ERROR: modpost: "vfio_pci_liveupdate_init" [drivers/vfio/pci/vfio- pci.ko] undefined! ERROR: modpost: "vfio_pci_liveupdate_cleanup" [drivers/vfio/pci/vfio- pci.ko] undefined! make[4]: *** [scripts/Makefile.modpost:147: Module.symvers] Error 1 make[3]: *** [Makefile:1960: modpost] Error 2

After I git clone the source code from the link https://github.com/ dmatlack/linux/tree/liveupdate/vfio/cdev/v1,

I found the above errors when I built the source code.

Perhaps the above errors can be solved by EXPORT_SYMBOL.

But I am not sure if a better solution can solve the above problems or not.

I reviewed this patch series in detail. If I’m understanding it correctly, there appears to be a cyclic dependency issue. Specifically, some functions in kernel module A depend on kernel module B, while at the same time certain functions in module B depend on module A.

I’m not entirely sure whether this constitutes a real problem or if it’s intentional design.

Thanks for your report. Can you share the .config file you used to generate these errors?

IIRC, I used FC 42 default config. Perhaps you can make tests with it. If this problem can not be reproduced, I will share my config with you.

What does "FC 42 default config" mean?

Either way I was able to reproduce the errors you posted above by changing CONFIG_VFIO_PCI{_CORE} from "y" to "m".

To unblock building and testing this series you can change these configs from "m" to "y", or the following patch (which fixed things for me):

Oops, sorry, something went wrong when I posted that diff. Here's the correct diff:

diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 929df22c079b..c2cca16e99a8 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -2,11 +2,11 @@

vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o -vfio-pci-core-$(CONFIG_LIVEUPDATE) += vfio_pci_liveupdate.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o

vfio-pci-y := vfio_pci.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o +vfio-pci-$(CONFIG_LIVEUPDATE) += vfio_pci_liveupdate.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o

obj-$(CONFIG_MLX5_VFIO_PCI) += mlx5/ diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index c5b5eb509474..b9805861763a 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1386,6 +1386,7 @@ const struct file_operations vfio_device_fops = { .show_fdinfo = vfio_device_show_fdinfo, #endif }; +EXPORT_SYMBOL_GPL(vfio_device_fops);

/** * vfio_file_is_valid - True if the file is valid vfio file diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c index 69298d82f404..c7a0c9c3b6a8 100644 --- a/kernel/liveupdate/luo_core.c +++ b/kernel/liveupdate/luo_core.c @@ -256,6 +256,7 @@ bool liveupdate_enabled(void) { return luo_global.enabled; } +EXPORT_SYMBOL_GPL(liveupdate_enabled);

/** * DOC: LUO ioctl Interface diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index fca3806dae28..9baa88966f04 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -868,6 +868,7 @@ int liveupdate_register_file_handler(struct liveupdate_file_handler *fh) luo_session_resume(); return err; } +EXPORT_SYMBOL_GPL(liveupdate_register_file_handler);

/** * liveupdate_unregister_file_handler - Unregister a liveupdate file handler @@ -913,3 +914,4 @@ int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh) liveupdate_test_register(fh); return err; } +EXPORT_SYMBOL_GPL(liveupdate_unregister_file_handler);

On Mon, Dec 1, 2025 at 1:46 PM Yanjun.Zhu yanjun.zhu@linux.dev wrote:

On 12/1/25 9:44 AM, Pasha Tatashin wrote:

...

On Mon, Dec 1, 2025 at 12:36 PM David Matlack dmatlack@google.com wrote:

...

On 2025-12-01 05:32 PM, David Matlack wrote:

...

On 2025-12-01 09:16 AM, Zhu Yanjun wrote:

...

在 2025/12/1 9:10, David Matlack 写道:

...

On Mon, Dec 1, 2025 at 7:49 AM Zhu Yanjun yanjun.zhu@linux.dev wrote: > 在 2025/11/27 20:56, Zhu Yanjun 写道: >> Hi, David >> >> ERROR: modpost: "liveupdate_register_file_handler" [drivers/vfio/pci/ >> vfio-pci-core.ko] undefined! >> >> ERROR: modpost: "vfio_pci_ops" [drivers/vfio/pci/vfio-pci-core.ko] >> undefined! >> ERROR: modpost: "liveupdate_enabled" [drivers/vfio/pci/vfio-pci-core.ko] >> undefined! >> ERROR: modpost: "liveupdate_unregister_file_handler" [drivers/vfio/pci/ >> vfio-pci-core.ko] undefined! >> ERROR: modpost: "vfio_device_fops" [drivers/vfio/pci/vfio-pci-core.ko] >> undefined! >> ERROR: modpost: "vfio_pci_is_intel_display" [drivers/vfio/pci/vfio-pci- >> core.ko] undefined! >> ERROR: modpost: "vfio_pci_liveupdate_init" [drivers/vfio/pci/vfio- >> pci.ko] undefined! >> ERROR: modpost: "vfio_pci_liveupdate_cleanup" [drivers/vfio/pci/vfio- >> pci.ko] undefined! >> make[4]: *** [scripts/Makefile.modpost:147: Module.symvers] Error 1 >> make[3]: *** [Makefile:1960: modpost] Error 2 >> >> After I git clone the source code from the link https://github.com/ >> dmatlack/linux/tree/liveupdate/vfio/cdev/v1, >> >> I found the above errors when I built the source code. >> >> Perhaps the above errors can be solved by EXPORT_SYMBOL. >> >> But I am not sure if a better solution can solve the above problems or not. > I reviewed this patch series in detail. If I’m understanding it > correctly, there appears to be a cyclic dependency issue. Specifically, > some functions in kernel module A depend on kernel module B, while at > the same time certain functions in module B depend on module A. > > I’m not entirely sure whether this constitutes a real problem or if it’s > intentional design. Thanks for your report. Can you share the .config file you used to generate these errors?

IIRC, I used FC 42 default config. Perhaps you can make tests with it. If this problem can not be reproduced, I will share my config with you.

What does "FC 42 default config" mean?

Either way I was able to reproduce the errors you posted above by changing CONFIG_VFIO_PCI{_CORE} from "y" to "m".

To unblock building and testing this series you can change these configs from "m" to "y", or the following patch (which fixed things for me):

Oops, sorry, something went wrong when I posted that diff. Here's the correct diff:

diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 929df22c079b..c2cca16e99a8 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -2,11 +2,11 @@

vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o -vfio-pci-core-$(CONFIG_LIVEUPDATE) += vfio_pci_liveupdate.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o

vfio-pci-y := vfio_pci.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o +vfio-pci-$(CONFIG_LIVEUPDATE) += vfio_pci_liveupdate.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o

obj-$(CONFIG_MLX5_VFIO_PCI) += mlx5/ diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index c5b5eb509474..b9805861763a 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1386,6 +1386,7 @@ const struct file_operations vfio_device_fops = { .show_fdinfo = vfio_device_show_fdinfo, #endif }; +EXPORT_SYMBOL_GPL(vfio_device_fops);

/**

• vfio_file_is_valid - True if the file is valid vfio file

diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c index 69298d82f404..c7a0c9c3b6a8 100644 --- a/kernel/liveupdate/luo_core.c +++ b/kernel/liveupdate/luo_core.c @@ -256,6 +256,7 @@ bool liveupdate_enabled(void) { return luo_global.enabled; } +EXPORT_SYMBOL_GPL(liveupdate_enabled);

/**

• DOC: LUO ioctl Interface

diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index fca3806dae28..9baa88966f04 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -868,6 +868,7 @@ int liveupdate_register_file_handler(struct liveupdate_file_handler *fh) luo_session_resume(); return err; } +EXPORT_SYMBOL_GPL(liveupdate_register_file_handler);

/**

• liveupdate_unregister_file_handler - Unregister a liveupdate file handler

@@ -913,3 +914,4 @@ int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh) liveupdate_test_register(fh); return err; } +EXPORT_SYMBOL_GPL(liveupdate_unregister_file_handler);

Sure. Exactly. The above is the same with my solution. But after that EXPORT_SYMBOL_GPL, a cyclic dependency issue will occur.

Did see the change to drivers/vfio/pci/Makefile? That fixes the circular dependency between vfio-pci and vfio-pci-core that I created in this series.

在 2025/12/1 9:36, David Matlack 写道:

On 2025-12-01 05:32 PM, David Matlack wrote:

...

On 2025-12-01 09:16 AM, Zhu Yanjun wrote:

...

在 2025/12/1 9:10, David Matlack 写道:

...

On Mon, Dec 1, 2025 at 7:49 AM Zhu Yanjun yanjun.zhu@linux.dev wrote:

...

在 2025/11/27 20:56, Zhu Yanjun 写道:

...

Hi, David

ERROR: modpost: "liveupdate_register_file_handler" [drivers/vfio/pci/ vfio-pci-core.ko] undefined!

ERROR: modpost: "vfio_pci_ops" [drivers/vfio/pci/vfio-pci-core.ko] undefined! ERROR: modpost: "liveupdate_enabled" [drivers/vfio/pci/vfio-pci-core.ko] undefined! ERROR: modpost: "liveupdate_unregister_file_handler" [drivers/vfio/pci/ vfio-pci-core.ko] undefined! ERROR: modpost: "vfio_device_fops" [drivers/vfio/pci/vfio-pci-core.ko] undefined! ERROR: modpost: "vfio_pci_is_intel_display" [drivers/vfio/pci/vfio-pci- core.ko] undefined! ERROR: modpost: "vfio_pci_liveupdate_init" [drivers/vfio/pci/vfio- pci.ko] undefined! ERROR: modpost: "vfio_pci_liveupdate_cleanup" [drivers/vfio/pci/vfio- pci.ko] undefined! make[4]: *** [scripts/Makefile.modpost:147: Module.symvers] Error 1 make[3]: *** [Makefile:1960: modpost] Error 2

After I git clone the source code from the link https://github.com/ dmatlack/linux/tree/liveupdate/vfio/cdev/v1,

I found the above errors when I built the source code.

Perhaps the above errors can be solved by EXPORT_SYMBOL.

But I am not sure if a better solution can solve the above problems or not.

I reviewed this patch series in detail. If I’m understanding it correctly, there appears to be a cyclic dependency issue. Specifically, some functions in kernel module A depend on kernel module B, while at the same time certain functions in module B depend on module A.

I’m not entirely sure whether this constitutes a real problem or if it’s intentional design.

Thanks for your report. Can you share the .config file you used to generate these errors?

IIRC, I used FC 42 default config. Perhaps you can make tests with it. If this problem can not be reproduced, I will share my config with you.

What does "FC 42 default config" mean?

Either way I was able to reproduce the errors you posted above by changing CONFIG_VFIO_PCI{_CORE} from "y" to "m".

To unblock building and testing this series you can change these configs from "m" to "y", or the following patch (which fixed things for me):

Oops, sorry, something went wrong when I posted that diff. Here's the correct diff:

diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 929df22c079b..c2cca16e99a8 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -2,11 +2,11 @@

vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o -vfio-pci-core-$(CONFIG_LIVEUPDATE) += vfio_pci_liveupdate.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o

vfio-pci-y := vfio_pci.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o +vfio-pci-$(CONFIG_LIVEUPDATE) += vfio_pci_liveupdate.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o

obj-$(CONFIG_MLX5_VFIO_PCI) += mlx5/ diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index c5b5eb509474..b9805861763a 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1386,6 +1386,7 @@ const struct file_operations vfio_device_fops = { .show_fdinfo = vfio_device_show_fdinfo, #endif }; +EXPORT_SYMBOL_GPL(vfio_device_fops);

/**

• vfio_file_is_valid - True if the file is valid vfio file

diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c index 69298d82f404..c7a0c9c3b6a8 100644 --- a/kernel/liveupdate/luo_core.c +++ b/kernel/liveupdate/luo_core.c @@ -256,6 +256,7 @@ bool liveupdate_enabled(void) { return luo_global.enabled; } +EXPORT_SYMBOL_GPL(liveupdate_enabled);

/**

• DOC: LUO ioctl Interface

diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index fca3806dae28..9baa88966f04 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -868,6 +868,7 @@ int liveupdate_register_file_handler(struct liveupdate_file_handler *fh) luo_session_resume(); return err; } +EXPORT_SYMBOL_GPL(liveupdate_register_file_handler);

/**

• liveupdate_unregister_file_handler - Unregister a liveupdate file handler

@@ -913,3 +914,4 @@ int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh) liveupdate_test_register(fh); return err; } +EXPORT_SYMBOL_GPL(liveupdate_unregister_file_handler);

Hi, David

Thanks. The above changes resolve the EXPORT_SYMBOL_GPL issue as well as the cyclic dependency problem.

I recommend submitting this as a new commit, as it effectively addresses the issues present in the patch series.

Yanjun.Zhu