* [PATCH v4 01/16] vfio/pci: Register a file handler with Live Update Orchestrator
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 02/16] vfio/pci: Preserve vfio-pci device files across Live Update Vipin Sharma
` (14 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
Register a live update file handler for vfio-pci device files. Add stub
implementations of all required callbacks so that registration does not
fail (i.e. to avoid breaking git-bisect).
This file handler will be extended in subsequent commits to enable a
device bound to vfio-pci to run without interruption while the host is
going through a kexec Live Update.
Put this support behind a new Kconfig VFIO_PCI_LIVEUPDATE that is marked
experimental and default-disabled until more of the device preservation
support has landed in the kernel.
Co-developed-by: David Matlack <dmatlack@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
MAINTAINERS | 1 +
drivers/vfio/pci/Kconfig | 12 +++++
drivers/vfio/pci/Makefile | 1 +
drivers/vfio/pci/vfio_pci.c | 11 +++-
drivers/vfio/pci/vfio_pci_liveupdate.c | 70 ++++++++++++++++++++++++++
drivers/vfio/pci/vfio_pci_priv.h | 14 ++++++
include/linux/kho/abi/vfio_pci.h | 28 +++++++++++
7 files changed, 136 insertions(+), 1 deletion(-)
create mode 100644 drivers/vfio/pci/vfio_pci_liveupdate.c
create mode 100644 include/linux/kho/abi/vfio_pci.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 42dbac2c2ed3..b6c33c2bcc7c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -27980,6 +27980,7 @@ F: Documentation/ABI/testing/debugfs-vfio
F: Documentation/ABI/testing/sysfs-devices-vfio-dev
F: Documentation/driver-api/vfio.rst
F: drivers/vfio/
+F: include/linux/kho/abi/vfio_pci.h
F: include/linux/vfio.h
F: include/linux/vfio_pci_core.h
F: include/uapi/linux/vfio.h
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 296bf01e185e..c12d614fc6c4 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -42,6 +42,18 @@ config VFIO_PCI_IGD
and LPC bridge config space.
To enable Intel IGD assignment through vfio-pci, say Y.
+
+config VFIO_PCI_LIVEUPDATE
+ bool "VFIO PCI support for Live Update (EXPERIMENTAL)"
+ depends on PCI_LIVEUPDATE
+ help
+ Support for preserving devices bound to vfio-pci across a Live
+ Update. This option should only be enabled by developers working on
+ implementing this support. Once enough support has landed in the
+ kernel, this option will no longer be marked EXPERIMENTAL.
+
+ If you don't know what to do here, say N.
+
endif
config VFIO_PCI_ZDEV_KVM
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 6138f1bf241d..bf296ab1c967 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -7,6 +7,7 @@ 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-$(CONFIG_VFIO_PCI_LIVEUPDATE) += vfio_pci_liveupdate.o
obj-$(CONFIG_VFIO_PCI) += vfio-pci.o
obj-$(CONFIG_MLX5_VFIO_PCI) += mlx5/
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 0c771064c0b8..5038265f3af5 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -264,10 +264,14 @@ static int __init vfio_pci_init(void)
vfio_pci_core_set_params(nointxmask, is_disable_vga, disable_idle_d3);
+ ret = vfio_pci_liveupdate_init();
+ if (ret)
+ return ret;
+
/* Register and scan for devices */
ret = pci_register_driver(&vfio_pci_driver);
if (ret)
- return ret;
+ goto err_liveupdate_cleanup;
vfio_pci_fill_ids();
@@ -275,12 +279,17 @@ static int __init vfio_pci_init(void)
pr_warn("device denylist disabled.\n");
return 0;
+
+err_liveupdate_cleanup:
+ vfio_pci_liveupdate_cleanup();
+ return ret;
}
module_init(vfio_pci_init);
static void __exit vfio_pci_cleanup(void)
{
pci_unregister_driver(&vfio_pci_driver);
+ vfio_pci_liveupdate_cleanup();
}
module_exit(vfio_pci_cleanup);
diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c
new file mode 100644
index 000000000000..1c74854600ea
--- /dev/null
+++ b/drivers/vfio/pci/vfio_pci_liveupdate.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (c) 2026, Google LLC.
+ * Vipin Sharma <vipinsh@google.com>
+ * David Matlack <dmatlack@google.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/errno.h>
+#include <linux/kho/abi/vfio_pci.h>
+#include <linux/liveupdate.h>
+#include <linux/module.h>
+
+#include "vfio_pci_priv.h"
+
+static bool vfio_pci_liveupdate_can_preserve(struct liveupdate_file_handler *handler,
+ struct file *file)
+{
+ return false;
+}
+
+static int vfio_pci_liveupdate_preserve(struct liveupdate_file_op_args *args)
+{
+ return -EOPNOTSUPP;
+}
+
+static void vfio_pci_liveupdate_unpreserve(struct liveupdate_file_op_args *args)
+{
+}
+
+static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args)
+{
+ return -EOPNOTSUPP;
+}
+
+static void vfio_pci_liveupdate_finish(struct liveupdate_file_op_args *args)
+{
+}
+
+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,
+ .retrieve = vfio_pci_liveupdate_retrieve,
+ .finish = vfio_pci_liveupdate_finish,
+ .owner = THIS_MODULE,
+};
+
+static struct liveupdate_file_handler vfio_pci_liveupdate_fh = {
+ .ops = &vfio_pci_liveupdate_file_ops,
+ .compatible = VFIO_PCI_LUO_FH_COMPATIBLE,
+};
+
+int __init vfio_pci_liveupdate_init(void)
+{
+ int ret;
+
+ ret = liveupdate_register_file_handler(&vfio_pci_liveupdate_fh);
+ if (ret && ret != -EOPNOTSUPP)
+ return ret;
+
+ return 0;
+}
+
+void vfio_pci_liveupdate_cleanup(void)
+{
+ liveupdate_unregister_file_handler(&vfio_pci_liveupdate_fh);
+}
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index fca9d0dfac90..c130ac53c4f9 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -137,4 +137,18 @@ static inline void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev,
}
#endif
+#ifdef CONFIG_VFIO_PCI_LIVEUPDATE
+int __init vfio_pci_liveupdate_init(void);
+void vfio_pci_liveupdate_cleanup(void);
+#else
+static inline int vfio_pci_liveupdate_init(void)
+{
+ return 0;
+}
+
+static inline void vfio_pci_liveupdate_cleanup(void)
+{
+}
+#endif /* CONFIG_VFIO_PCI_LIVEUPDATE */
+
#endif
diff --git a/include/linux/kho/abi/vfio_pci.h b/include/linux/kho/abi/vfio_pci.h
new file mode 100644
index 000000000000..67e8199eec59
--- /dev/null
+++ b/include/linux/kho/abi/vfio_pci.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2026, Google LLC.
+ * Vipin Sharma <vipinsh@google.com>
+ * David Matlack <dmatlack@google.com>
+ */
+
+#ifndef _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H
+#define _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H
+
+/**
+ * DOC: VFIO PCI Live Update ABI
+ *
+ * VFIO uses the ABI defined below for preserving device files across a kexec
+ * reboot using LUO.
+ *
+ * Device metadata is serialized into memory which is then handed to the next
+ * kernel via KHO.
+ *
+ * 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 VFIO_PCI_LUO_FH_COMPATIBLE string.
+ */
+
+#define VFIO_PCI_LUO_FH_COMPATIBLE "vfio-pci-v1"
+
+#endif /* _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H */
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 02/16] vfio/pci: Preserve vfio-pci device files across Live Update
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 01/16] vfio/pci: Register a file handler with Live Update Orchestrator Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 03/16] vfio/pci: Retrieve preserved device files after " Vipin Sharma
` (13 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
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 until userspace has unpreserved the file using LUO.
Co-developed-by: David Matlack <dmatlack@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
drivers/vfio/pci/Kconfig | 6 +-
drivers/vfio/pci/vfio_pci.c | 2 +-
drivers/vfio/pci/vfio_pci_core.c | 60 +++++----
drivers/vfio/pci/vfio_pci_liveupdate.c | 178 ++++++++++++++++++++++++-
drivers/vfio/pci/vfio_pci_priv.h | 5 +
drivers/vfio/vfio_main.c | 3 +-
include/linux/kho/abi/vfio_pci.h | 15 +++
include/linux/vfio.h | 2 +
8 files changed, 242 insertions(+), 29 deletions(-)
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index c12d614fc6c4..019de053f116 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -45,13 +45,15 @@ config VFIO_PCI_IGD
config VFIO_PCI_LIVEUPDATE
bool "VFIO PCI support for Live Update (EXPERIMENTAL)"
- depends on PCI_LIVEUPDATE
+ depends on PCI_LIVEUPDATE && VFIO_DEVICE_CDEV
help
Support for preserving devices bound to vfio-pci across a Live
Update. This option should only be enabled by developers working on
implementing this support. Once enough support has landed in the
kernel, this option will no longer be marked EXPERIMENTAL.
+ Enabling this will disable support for VFIO PCI DMA buffer.
+
If you don't know what to do here, say N.
endif
@@ -68,7 +70,7 @@ config VFIO_PCI_ZDEV_KVM
To enable s390x KVM vfio-pci extensions, say Y.
config VFIO_PCI_DMABUF
- def_bool y if VFIO_PCI_CORE && PCI_P2PDMA && DMA_SHARED_BUFFER
+ def_bool y if VFIO_PCI_CORE && PCI_P2PDMA && DMA_SHARED_BUFFER && !VFIO_PCI_LIVEUPDATE
source "drivers/vfio/pci/mlx5/Kconfig"
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 5038265f3af5..439d14d79d8f 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_core.c b/drivers/vfio/pci/vfio_pci_core.c
index ad52abc46c04..1726d4d41b57 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -585,9 +585,42 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
}
EXPORT_SYMBOL_GPL(vfio_pci_core_enable);
+void vfio_pci_core_try_reset(struct vfio_pci_core_device *vdev)
+{
+ struct pci_dev *pdev = vdev->pdev;
+ struct pci_dev *bridge = pci_upstream_bridge(pdev);
+
+ lockdep_assert_held(&vdev->vdev.dev_set->lock);
+
+ if (!vdev->reset_works)
+ return;
+
+ /*
+ * Try to get the locks ourselves to prevent a deadlock. The
+ * success of this is dependent on being able to lock the device,
+ * which is not always possible.
+ *
+ * We cannot use the "try" reset interface here, since that will
+ * overwrite the previously restored configuration information.
+ */
+ if (bridge && !pci_dev_trylock(bridge))
+ return;
+
+ if (!pci_dev_trylock(pdev))
+ goto out;
+
+ if (!__pci_reset_function_locked(pdev))
+ vdev->needs_reset = false;
+
+ pci_dev_unlock(pdev);
+out:
+ if (bridge)
+ pci_dev_unlock(bridge);
+}
+EXPORT_SYMBOL_GPL(vfio_pci_core_try_reset);
+
void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
{
- struct pci_dev *bridge;
struct pci_dev *pdev = vdev->pdev;
struct vfio_pci_dummy_resource *dummy_res, *tmp;
struct vfio_pci_ioeventfd *ioeventfd, *ioeventfd_tmp;
@@ -687,27 +720,7 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
*/
pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
- /*
- * Try to get the locks ourselves to prevent a deadlock. The
- * success of this is dependent on being able to lock the device,
- * which is not always possible.
- * We can not use the "try" reset interface here, which will
- * overwrite the previously restored configuration information.
- */
- if (vdev->reset_works) {
- bridge = pci_upstream_bridge(pdev);
- if (bridge && !pci_dev_trylock(bridge))
- goto out_restore_state;
- if (pci_dev_trylock(pdev)) {
- if (!__pci_reset_function_locked(pdev))
- vdev->needs_reset = false;
- pci_dev_unlock(pdev);
- }
- if (bridge)
- pci_dev_unlock(bridge);
- }
-
-out_restore_state:
+ vfio_pci_core_try_reset(vdev);
pci_restore_state(pdev);
out:
pci_disable_device(pdev);
@@ -1613,7 +1626,7 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu
}
EXPORT_SYMBOL_GPL(vfio_pci_core_write);
-static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev)
+void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev)
{
struct vfio_device *core_vdev = &vdev->vdev;
loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX);
@@ -1622,6 +1635,7 @@ static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev)
unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true);
}
+EXPORT_SYMBOL_GPL(vfio_pci_zap_bars);
void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev)
{
diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c
index 1c74854600ea..5cc57bf39dbe 100644
--- a/drivers/vfio/pci/vfio_pci_liveupdate.c
+++ b/drivers/vfio/pci/vfio_pci_liveupdate.c
@@ -6,28 +6,201 @@
* David Matlack <dmatlack@google.com>
*/
+/**
+ * DOC: VFIO PCI Preservation via LUO
+ *
+ * VFIO PCI devices can be preserved over a kexec using the Live Update
+ * Orchestrator (LUO) file preservation. This allows userspace (such as a VMM)
+ * to transfer an in-use device to the next kernel.
+ *
+ * .. note::
+ * The support for preserving VFIO PCI devices is currently *partial* and
+ * should be considered *experimental*. It should only be used by developers
+ * working on expanding the support for the time being.
+ *
+ * To avoid accidental usage while the support is still experimental, this
+ * support is hidden behind a default-disable config option
+ * ``CONFIG_VFIO_PCI_LIVEUPDATE``. Once the kernel support has stabilized and
+ * become complete, this option will be enabled by default when
+ * ``CONFIG_VFIO_PCI`` and ``CONFIG_LIVEUPDATE`` are enabled.
+ *
+ * Usage Example
+ * =============
+ *
+ * VFIO PCI devices can be preserved across a kexec by preserving the file
+ * associated with the device in a LUO session::
+ *
+ * device_fd = open("/dev/vfio/devices/vfioX");
+ * ...
+ * ioctl(session_fd, LIVEUPDATE_SESSION_PRESERVE_FD, { ..., device_fd, ...});
+ *
+ * .. note::
+ * LUO will hold an extra reference to the device file for as long as it is
+ * preserved, so there is no way for the file to be destroyed or the device
+ * to be unbound from the vfio-pci driver while it is preserved.
+ *
+ * Retrieving the file after kexec is not yet supported.
+ *
+ * Restrictions
+ * ============
+ *
+ * The kernel imposes the following restrictions when preserving VFIO devices:
+ *
+ * * The device must be bound to the ``vfio-pci`` driver.
+ *
+ * * ``CONFIG_VFIO_PCI_ZDEV_KVM`` must not be enabled. This may be relaxed in
+ * the future.
+ *
+ * * The device must not be an Intel display device. This may be relaxed in
+ * the future.
+ *
+ * * No support for VFIO PCI DMA buffer. This is to keep code simpler, it will
+ * be removed in future.
+ *
+ * * The device file descriptor must be obtained by opening the VFIO character
+ * device (``/dev/vfio/devices/vfioX``) and not via
+ * ``VFIO_GROUP_GET_DEVICE_FD``.
+ *
+ * * The device must have interrupt disable prior to kexec. Failure to disable
+ * interrupts on the device will cause the ``reboot(LINUX_REBOOT_CMD_KEXEC)``
+ * syscall (to initiate the kexec) to fail.
+ *
+ * Preservation Behavior
+ * =====================
+ *
+ * The eventual goal of this support is to avoid disrupting the workload, state,
+ * or configuration of each preserved device during a Live Update. This would
+ * include allowing the device to perform DMA to preserved memory buffers and
+ * perform P2P DMA to other preserved devices. However, there are many pieces
+ * that still need to land in the kernel.
+ *
+ * For now, VFIO only preserves the following state for for devices:
+ *
+ * * The PCI Segment, Bus, Device, and Function numbers of the device. The
+ * kernel guarantees the these will not change across a kexec when a device
+ * is preserved.
+ *
+ * Since the kernel is not yet prepared to preserve all parts of the device and
+ * its dependencies (such as DMA mappings), VFIO currently resets and restores
+ * preserved devices back into an idle state during kexec, before handing off
+ * control to the next kernel. This will be relaxed in future versions of the
+ * kernel once it is safe to allow the device to keep running across kexec.
+ */
+
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/errno.h>
+#include <linux/kexec_handover.h>
#include <linux/kho/abi/vfio_pci.h>
#include <linux/liveupdate.h>
#include <linux/module.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 *device = vfio_device_from_file(file);
+ struct vfio_pci_core_device *vdev;
+ struct pci_dev *pdev;
+
+ if (!device)
+ return false;
+
+ /* Live Update support is limited to cdev files. */
+ if (!vfio_device_cdev_opened(device))
+ return false;
+
+ if (device->ops != &vfio_pci_ops)
+ return false;
+
+ vdev = container_of(device, struct vfio_pci_core_device, vdev);
+ pdev = vdev->pdev;
+
+ /*
+ * Don't support specialized vfio-pci devices for now since they haven't
+ * been tested.
+ */
+ if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || vfio_pci_is_intel_display(pdev))
+ return false;
+
+ return true;
}
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;
+
+ vdev = container_of(device, struct vfio_pci_core_device, vdev);
+ pdev = vdev->pdev;
+
+ ser = kho_alloc_preserve(sizeof(*ser));
+ if (IS_ERR(ser))
+ return PTR_ERR(ser);
+
+ ser->bdf = pci_dev_id(pdev);
+ ser->domain = pci_domain_nr(pdev->bus);
+
+ args->serialized_data = virt_to_phys(ser);
+ return 0;
}
static void vfio_pci_liveupdate_unpreserve(struct liveupdate_file_op_args *args)
{
+ kho_unpreserve_free(phys_to_virt(args->serialized_data));
+}
+
+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;
+ }
+
+ guard(rwsem_write)(&vdev->memory_lock);
+
+ /*
+ * Userspace must make sure device is not in the lower power state for
+ * live update. We may relax this in future.
+ */
+ if (pdev->current_state != PCI_D0) {
+ pci_err(pdev, "Freeze failed! Device not in D0 state.\n");
+ return -EINVAL;
+ }
+
+ /*
+ * Reset is a temporary measure to provide kernel after kexec a clean
+ * device while VFIO live update work is under development and not
+ * fully supported. It will go away once continuous DMA support is
+ * added to device preservation.
+ */
+ vfio_pci_zap_bars(vdev);
+ ret = pci_load_saved_state(pdev, vdev->pci_saved_state);
+ if (ret)
+ return ret;
+ pci_clear_master(pdev);
+ vfio_pci_core_try_reset(vdev);
+ pci_restore_state(pdev);
+ return 0;
}
static int vfio_pci_liveupdate_retrieve(struct liveupdate_file_op_args *args)
@@ -43,6 +216,7 @@ 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 c130ac53c4f9..20d942a7d9b7 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -11,6 +11,10 @@
/* Cap maximum number of ioeventfds per device (arbitrary) */
#define VFIO_PCI_IOEVENTFD_MAX 1000
+extern const struct vfio_device_ops vfio_pci_ops;
+
+void vfio_pci_core_try_reset(struct vfio_pci_core_device *vdev);
+
struct vfio_pci_ioeventfd {
struct list_head next;
struct vfio_pci_core_device *vdev;
@@ -72,6 +76,7 @@ void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev);
u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev);
void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev,
u16 cmd);
+void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev);
#ifdef CONFIG_VFIO_PCI_IGD
bool vfio_pci_is_intel_display(struct pci_dev *pdev);
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 8666f35fb3f0..2148b00491e4 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -1457,7 +1457,7 @@ const struct file_operations vfio_device_fops = {
#endif
};
-static struct vfio_device *vfio_device_from_file(struct file *file)
+struct vfio_device *vfio_device_from_file(struct file *file)
{
struct vfio_device_file *df = file->private_data;
@@ -1465,6 +1465,7 @@ static struct vfio_device *vfio_device_from_file(struct file *file)
return NULL;
return df->device;
}
+EXPORT_SYMBOL_GPL(vfio_device_from_file);
/**
* vfio_file_is_valid - True if the file is valid vfio file
diff --git a/include/linux/kho/abi/vfio_pci.h b/include/linux/kho/abi/vfio_pci.h
index 67e8199eec59..229a13ac1e52 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.
+ *
+ * @domain: The device's PCI domain number (segment).
+ * @bdf: The device's PCI bus, device, and function number.
+ */
+struct vfio_pci_core_device_ser {
+ u32 domain;
+ u16 bdf;
+} __packed;
+
#endif /* _LINUX_LIVEUPDATE_ABI_VFIO_PCI_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 31b826efba00..f5f7ece51f8f 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -81,6 +81,8 @@ struct vfio_device {
struct dentry *debug_root;
};
+struct vfio_device *vfio_device_from_file(struct file *file);
+
/**
* struct vfio_device_ops - VFIO bus driver device callbacks
*
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 03/16] vfio/pci: Retrieve preserved device files after Live Update
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 01/16] vfio/pci: Register a file handler with Live Update Orchestrator Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 02/16] vfio/pci: Preserve vfio-pci device files across Live Update Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 04/16] vfio/pci: Notify PCI subsystem about devices preserved across " Vipin Sharma
` (12 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
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.
Co-developed-by: David Matlack <dmatlack@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
drivers/vfio/device_cdev.c | 59 ++++++++++++++++++++++----
drivers/vfio/pci/vfio_pci_liveupdate.c | 52 ++++++++++++++++++++++-
drivers/vfio/vfio_main.c | 13 ++++++
include/linux/vfio.h | 11 +++++
4 files changed, 124 insertions(+), 11 deletions(-)
diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
index 8ceca24ac136..1ab07ccaf3ab 100644
--- a/drivers/vfio/device_cdev.c
+++ b/drivers/vfio/device_cdev.c
@@ -2,6 +2,7 @@
/*
* Copyright (c) 2023 Intel Corporation.
*/
+#include <linux/anon_inodes.h>
#include <linux/vfio.h>
#include <linux/iommufd.h>
@@ -16,15 +17,10 @@ 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)
+static int vfio_device_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;
+ struct file *file = *filep;
int ret;
/* Paired with the put in vfio_device_fops_release() */
@@ -37,22 +33,67 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep)
goto err_put_registration;
}
- filep->private_data = df;
+ /*
+ * Simulate opening the character device using an anonymous inode. The
+ * returned file has the same properties as a cdev file (e.g. operations
+ * are blocked until BIND_IOMMUFD is called).
+ */
+ if (!file) {
+ 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 err_free_device_file;
+ }
+
+ *filep = file;
+ }
+
+ file->private_data = df;
/*
* Use the pseudo fs inode on the device to link all mmaps
* to the same address space, allowing us to unmap all vmas
* associated to this device using unmap_mapping_range().
*/
- filep->f_mapping = device->inode->i_mapping;
+ file->f_mapping = device->inode->i_mapping;
return 0;
+err_free_device_file:
+ kfree(df);
err_put_registration:
vfio_device_put_registration(device);
return ret;
}
+struct file *vfio_device_liveupdate_cdev_open(struct vfio_device *device)
+{
+ struct file *file = NULL;
+ int ret;
+
+ ret = vfio_device_cdev_open(device, &file);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return file;
+}
+EXPORT_SYMBOL_GPL(vfio_device_liveupdate_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 *file)
+{
+ struct vfio_device *device = container_of(inode->i_cdev,
+ struct vfio_device, cdev);
+
+ return vfio_device_cdev_open(device, &file);
+}
+
static void vfio_df_get_kvm_safe(struct vfio_device_file *df)
{
spin_lock(&df->kvm_ref_lock);
diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c
index 5cc57bf39dbe..9142aaea94f2 100644
--- a/drivers/vfio/pci/vfio_pci_liveupdate.c
+++ b/drivers/vfio/pci/vfio_pci_liveupdate.c
@@ -39,7 +39,13 @@
* preserved, so there is no way for the file to be destroyed or the device
* to be unbound from the vfio-pci driver while it is preserved.
*
- * Retrieving the file after kexec is not yet supported.
+ * After kexec, the preserved VFIO device file can be retrieved from the session
+ * just like any other preserved file::
+ *
+ * ioctl(session_fd, LIVEUPDATE_SESSION_RETRIEVE_FD, &arg);
+ * device_fd = arg.fd;
+ * ...
+ * ioctl(session_fd, LIVEUPDATE_SESSION_FINISH, ...);
*
* Restrictions
* ============
@@ -90,6 +96,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/errno.h>
+#include <linux/file.h>
#include <linux/kexec_handover.h>
#include <linux/kho/abi/vfio_pci.h>
#include <linux/liveupdate.h>
@@ -203,13 +210,53 @@ static int vfio_pci_liveupdate_freeze(struct liveupdate_file_op_args *args)
return 0;
}
+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 pci_dev *pdev;
+
+ pdev = dev_is_pci(device->dev) ? to_pci_dev(device->dev) : NULL;
+ if (!pdev)
+ return false;
+
+ 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 file *file;
+ int ret = 0;
+
+ ser = phys_to_virt(args->serialized_data);
+
+ device = vfio_find_device(ser, match_device);
+ if (!device)
+ return -ENODEV;
+
+ file = vfio_device_liveupdate_cdev_open(device);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(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->retrieve_status > 0;
}
static void vfio_pci_liveupdate_finish(struct liveupdate_file_op_args *args)
{
+ kho_restore_free(phys_to_virt(args->serialized_data));
}
static const struct liveupdate_file_ops vfio_pci_liveupdate_file_ops = {
@@ -218,6 +265,7 @@ 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 2148b00491e4..33e082af9a08 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>
@@ -1787,6 +1788,18 @@ 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 f5f7ece51f8f..0b61aeff8216 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -431,4 +431,15 @@ 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)
+struct file *vfio_device_liveupdate_cdev_open(struct vfio_device *device);
+#else
+static inline struct file *vfio_device_liveupdate_cdev_open(struct vfio_device *device)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+#endif /* IS_ENABLED(CONFIG_VFIO_DEVICE_CDEV) */
+
+struct vfio_device *vfio_find_device(const void *data, device_match_t match);
+
#endif /* VFIO_H */
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 04/16] vfio/pci: Notify PCI subsystem about devices preserved across Live Update
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (2 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 03/16] vfio/pci: Retrieve preserved device files after " Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 05/16] vfio: Enforce preserved devices are retrieved via LIVEUPDATE_SESSION_RETRIEVE_FD Vipin Sharma
` (11 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Notify the PCI subsystem about devices vfio-pci is preserving across
Live Update by registering the vfio-pci liveupdate file handler with the
PCI subsystem's FLB handler.
Notably this will ensure that devices preserved through vfio-pci will
have their PCI bus numbers preserved across Live Update, allowing VFIO
to use BDF as a key to identify the device across the Live Update and
(in the future) allow the device to continue DMA operations across
the Live Update.
This also enables VFIO to detect that a device was preserved before
userspace first retrieves the file from it, which will be used in
subsequent commits.
Signed-off-by: David Matlack <dmatlack@google.com>
Co-developed-by: Vipin Sharma <vipinsh@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
drivers/vfio/pci/vfio_pci_liveupdate.c | 44 +++++++++++++++++++++++---
1 file changed, 40 insertions(+), 4 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c
index 9142aaea94f2..11c3bc8a8dcd 100644
--- a/drivers/vfio/pci/vfio_pci_liveupdate.c
+++ b/drivers/vfio/pci/vfio_pci_liveupdate.c
@@ -71,6 +71,9 @@
* interrupts on the device will cause the ``reboot(LINUX_REBOOT_CMD_KEXEC)``
* syscall (to initiate the kexec) to fail.
*
+ * In addition, the device must meet all of the restrictions imposed by the
+ * core PCI layer documented at :doc:`/PCI/liveupdate`.
+ *
* Preservation Behavior
* =====================
*
@@ -141,23 +144,37 @@ static int vfio_pci_liveupdate_preserve(struct liveupdate_file_op_args *args)
struct vfio_pci_core_device_ser *ser;
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;
+ ret = pci_liveupdate_preserve(pdev);
+ if (ret)
+ return ret;
+
ser = kho_alloc_preserve(sizeof(*ser));
- if (IS_ERR(ser))
- return PTR_ERR(ser);
+ if (IS_ERR(ser)) {
+ ret = PTR_ERR(ser);
+ goto err_unpreserve;
+ }
ser->bdf = pci_dev_id(pdev);
ser->domain = pci_domain_nr(pdev->bus);
args->serialized_data = virt_to_phys(ser);
return 0;
+
+err_unpreserve:
+ pci_liveupdate_unpreserve(pdev);
+ return ret;
}
static void vfio_pci_liveupdate_unpreserve(struct liveupdate_file_op_args *args)
{
+ struct vfio_device *device = vfio_device_from_file(args->file);
+
+ pci_liveupdate_unpreserve(to_pci_dev(device->dev));
kho_unpreserve_free(phys_to_virt(args->serialized_data));
}
@@ -256,6 +273,15 @@ static bool vfio_pci_liveupdate_can_finish(struct liveupdate_file_op_args *args)
static void vfio_pci_liveupdate_finish(struct liveupdate_file_op_args *args)
{
+ struct vfio_device *device;
+
+ if (!args->file) {
+ pr_err("Finish called on an unretrieved file.\n");
+ return;
+ }
+
+ device = vfio_device_from_file(args->file);
+ pci_liveupdate_finish(to_pci_dev(device->dev));
kho_restore_free(phys_to_virt(args->serialized_data));
}
@@ -280,13 +306,23 @@ int __init vfio_pci_liveupdate_init(void)
int ret;
ret = liveupdate_register_file_handler(&vfio_pci_liveupdate_fh);
- if (ret && ret != -EOPNOTSUPP)
- return ret;
+ if (ret)
+ goto err_return;
+
+ ret = pci_liveupdate_register_flb(&vfio_pci_liveupdate_fh);
+ if (ret)
+ goto err_unregister;
return 0;
+
+err_unregister:
+ liveupdate_unregister_file_handler(&vfio_pci_liveupdate_fh);
+err_return:
+ return (ret == -EOPNOTSUPP) ? 0 : ret;
}
void vfio_pci_liveupdate_cleanup(void)
{
+ pci_liveupdate_unregister_flb(&vfio_pci_liveupdate_fh);
liveupdate_unregister_file_handler(&vfio_pci_liveupdate_fh);
}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 05/16] vfio: Enforce preserved devices are retrieved via LIVEUPDATE_SESSION_RETRIEVE_FD
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (3 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 04/16] vfio/pci: Notify PCI subsystem about devices preserved across " Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 06/16] vfio/pci: Store incoming Live Update state in struct vfio_pci_core_device Vipin Sharma
` (10 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Enforce that files for incoming (preserved by previous kernel) VFIO
devices are retrieved via LIVEUPDATE_SESSION_RETRIEVE_FD rather than by
opening the corresponding VFIO character device or via
VFIO_GROUP_GET_DEVICE_FD.
Both of these methods would result in VFIO initializing the device
without access to the preserved state of the device passed by the
previous kernel.
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Co-developed-by: Vipin Sharma <vipinsh@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
drivers/vfio/device_cdev.c | 8 ++++++++
drivers/vfio/group.c | 9 +++++++++
drivers/vfio/pci/vfio_pci_liveupdate.c | 6 ++++++
drivers/vfio/vfio.h | 18 ++++++++++++++++++
4 files changed, 41 insertions(+)
diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
index 1ab07ccaf3ab..4df0495941c6 100644
--- a/drivers/vfio/device_cdev.c
+++ b/drivers/vfio/device_cdev.c
@@ -49,6 +49,14 @@ static int vfio_device_cdev_open(struct vfio_device *device, struct file **filep
}
*filep = file;
+ } else if (vfio_liveupdate_incoming_is_preserved(device)) {
+ /*
+ * Since it is live update preserved device, it must be
+ * retrieved via LIVEUPDATE_SESSION_RETRIEVE_FD instead of
+ * opening /dev/vfio/devices/vfioX.
+ */
+ ret = -EBUSY;
+ goto err_free_device_file;
}
file->private_data = df;
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index b2299e5bc6df..62b4eaabc829 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -316,6 +316,15 @@ static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
if (IS_ERR(device))
return PTR_ERR(device);
+ /*
+ * This device was preserved across a Live Update. Accessing it via
+ * VFIO_GROUP_GET_DEVICE_FD is not allowed.
+ */
+ if (vfio_liveupdate_incoming_is_preserved(device)) {
+ vfio_device_put_registration(device);
+ return -EBUSY;
+ }
+
fd = FD_ADD(O_CLOEXEC, vfio_device_open_file(device));
if (fd < 0)
vfio_device_put_registration(device);
diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c
index 11c3bc8a8dcd..731a3e34085f 100644
--- a/drivers/vfio/pci/vfio_pci_liveupdate.c
+++ b/drivers/vfio/pci/vfio_pci_liveupdate.c
@@ -47,6 +47,12 @@
* ...
* ioctl(session_fd, LIVEUPDATE_SESSION_FINISH, ...);
*
+ * .. note::
+ * After kexec, if a device was preserved by the previous kernel, attempting
+ * to open a new file for the device via its character device
+ * (``/dev/vfio/devices/X``) or via ``VFIO_GROUP_GET_DEVICE_FD`` will fail
+ * with ``-EBUSY``.
+ *
* Restrictions
* ============
*
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 0854f3fa1a22..5269fe021ee3 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -11,6 +11,7 @@
#include <linux/cdev.h>
#include <linux/module.h>
#include <linux/vfio.h>
+#include <linux/pci.h>
struct iommufd_ctx;
struct iommu_group;
@@ -461,4 +462,21 @@ static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
#endif /* CONFIG_VFIO_DEBUGFS */
+#ifdef CONFIG_PCI_LIVEUPDATE
+static inline bool vfio_liveupdate_incoming_is_preserved(struct vfio_device *device)
+{
+ struct device *d = device->dev;
+
+ if (dev_is_pci(d))
+ return to_pci_dev(d)->liveupdate_incoming;
+
+ return false;
+}
+#else
+static inline bool vfio_liveupdate_incoming_is_preserved(struct vfio_device *device)
+{
+ return false;
+}
+#endif /* CONFIG_PCI_LIVEUPDATE */
+
#endif
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 06/16] vfio/pci: Store incoming Live Update state in struct vfio_pci_core_device
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (4 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 05/16] vfio: Enforce preserved devices are retrieved via LIVEUPDATE_SESSION_RETRIEVE_FD Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 07/16] docs: liveupdate: Add documentation for VFIO PCI Vipin Sharma
` (9 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Stash a pointer to a device's incoming Live Updated state in struct
vfio_pci_core_device. This will enable subsequent commits to use the
preserved state when initializing 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(). This is synchronized by vfio_pci_core.c setting
vdev->liveupdate_incoming_state to NULL under dev_set lock once it's
done using it.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
drivers/vfio/pci/vfio_pci_core.c | 2 +-
drivers/vfio/pci/vfio_pci_liveupdate.c | 17 ++++++++++++++++-
include/linux/vfio_pci_core.h | 2 ++
3 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 1726d4d41b57..da013b4b1e94 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -568,7 +568,7 @@ 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_incoming_state = NULL;
return 0;
out_free_zdev:
diff --git a/drivers/vfio/pci/vfio_pci_liveupdate.c b/drivers/vfio/pci/vfio_pci_liveupdate.c
index 731a3e34085f..7b841a1e7fcc 100644
--- a/drivers/vfio/pci/vfio_pci_liveupdate.c
+++ b/drivers/vfio/pci/vfio_pci_liveupdate.c
@@ -249,6 +249,7 @@ 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 file *file;
int ret = 0;
@@ -265,6 +266,9 @@ 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_incoming_state = ser;
+
args->file = file;
out:
/* Drop the reference from vfio_find_device() */
@@ -274,7 +278,18 @@ 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->retrieve_status > 0;
+ struct vfio_pci_core_device *vdev;
+ struct vfio_device *device;
+
+ if (args->retrieve_status <= 0)
+ return false;
+
+ device = vfio_device_from_file(args->file);
+ vdev = container_of(device, struct vfio_pci_core_device, vdev);
+
+ /* Check that vdev->liveupdate_incoming_state is no longer in use. */
+ guard(mutex)(&device->dev_set->lock);
+ return !vdev->liveupdate_incoming_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 2ebba746c18f..0c508dd8d1ac 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -26,6 +26,7 @@
#define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1)
struct vfio_pci_core_device;
+struct vfio_pci_core_device_ser;
struct vfio_pci_region;
struct p2pdma_provider;
struct dma_buf_attachment;
@@ -142,6 +143,7 @@ struct vfio_pci_core_device {
struct notifier_block nb;
struct rw_semaphore memory_lock;
struct list_head dmabufs;
+ struct vfio_pci_core_device_ser *liveupdate_incoming_state;
};
enum vfio_pci_io_width {
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 07/16] docs: liveupdate: Add documentation for VFIO PCI
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (5 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 06/16] vfio/pci: Store incoming Live Update state in struct vfio_pci_core_device Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 08/16] vfio: selftests: Build liveupdate library in VFIO selftests Vipin Sharma
` (8 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Add documentation for preserving VFIO device files across a Live Update,
generated from the kernel-doc comments in the code.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
Documentation/core-api/liveupdate.rst | 1 +
.../driver-api/vfio_pci_liveupdate.rst | 23 +++++++++++++++++++
MAINTAINERS | 1 +
3 files changed, 25 insertions(+)
create mode 100644 Documentation/driver-api/vfio_pci_liveupdate.rst
diff --git a/Documentation/core-api/liveupdate.rst b/Documentation/core-api/liveupdate.rst
index d56a7760978a..c55d0d9d1d3b 100644
--- a/Documentation/core-api/liveupdate.rst
+++ b/Documentation/core-api/liveupdate.rst
@@ -34,6 +34,7 @@ The following types of file descriptors can be preserved
:maxdepth: 1
../mm/memfd_preservation
+ ../driver-api/vfio_pci_liveupdate
Public API
==========
diff --git a/Documentation/driver-api/vfio_pci_liveupdate.rst b/Documentation/driver-api/vfio_pci_liveupdate.rst
new file mode 100644
index 000000000000..1098b84e5ecd
--- /dev/null
+++ b/Documentation/driver-api/vfio_pci_liveupdate.rst
@@ -0,0 +1,23 @@
+.. SPDX-License-Identifier: GPL-2.0-or-later
+
+====================================
+VFIO PCI Device Preservation via LUO
+====================================
+
+.. kernel-doc:: drivers/vfio/pci/vfio_pci_liveupdate.c
+ :doc: VFIO PCI Preservation via LUO
+
+VFIO PCI Preservation ABI
+=========================
+
+.. kernel-doc:: include/linux/kho/abi/vfio_pci.h
+ :doc: VFIO PCI Live Update ABI
+
+.. kernel-doc:: include/linux/kho/abi/vfio_pci.h
+ :internal:
+
+See Also
+========
+
+- :doc:`/core-api/liveupdate`
+- :doc:`/core-api/kho/index`
diff --git a/MAINTAINERS b/MAINTAINERS
index b6c33c2bcc7c..737c5ed1ce38 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -27979,6 +27979,7 @@ T: git https://github.com/awilliam/linux-vfio.git
F: Documentation/ABI/testing/debugfs-vfio
F: Documentation/ABI/testing/sysfs-devices-vfio-dev
F: Documentation/driver-api/vfio.rst
+F: Documentation/driver-api/vfio_pci_liveupdate.rst
F: drivers/vfio/
F: include/linux/kho/abi/vfio_pci.h
F: include/linux/vfio.h
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 08/16] vfio: selftests: Build liveupdate library in VFIO selftests
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (6 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 07/16] docs: liveupdate: Add documentation for VFIO PCI Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 09/16] vfio: selftests: Add vfio_pci_liveupdate_uapi_test Vipin Sharma
` (7 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
Import and build liveupdate selftest library in VFIO selftests.
It allows to use liveupdate ioctls in VFIO selftests
Co-developed-by: David Matlack <dmatlack@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
tools/testing/selftests/vfio/Makefile | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index 0684932d91bf..7865b2aa011c 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -20,6 +20,7 @@ TEST_FILES += scripts/setup.sh
include ../lib.mk
include lib/libvfio.mk
+include ../liveupdate/lib/libliveupdate.mk
CFLAGS += -I$(top_srcdir)/tools/include
CFLAGS += -MD
@@ -27,11 +28,15 @@ CFLAGS += $(EXTRA_CFLAGS)
LDFLAGS += -pthread
-$(TEST_GEN_PROGS): %: %.o $(LIBVFIO_O)
- $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $< $(LIBVFIO_O) $(LDLIBS) -o $@
+LIBS_O := $(LIBVFIO_O)
+LIBS_O += $(LIBLIVEUPDATE_O)
+
+$(TEST_GEN_PROGS): %: %.o $(LIBS_O)
+ $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBS_O) $(LDLIBS) -o $@
TEST_GEN_PROGS_O = $(patsubst %, %.o, $(TEST_GEN_PROGS))
-TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_PROGS_O) $(LIBVFIO_O))
+TEST_DEP_FILES := $(patsubst %.o, %.d, $(TEST_GEN_PROGS_O))
+TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBS_O))
-include $(TEST_DEP_FILES)
EXTRA_CLEAN += $(TEST_GEN_PROGS_O) $(TEST_DEP_FILES)
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 09/16] vfio: selftests: Add vfio_pci_liveupdate_uapi_test
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (7 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 08/16] vfio: selftests: Build liveupdate library in VFIO selftests Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 10/16] vfio: selftests: Initialize vfio_pci_device using a VFIO cdev FD Vipin Sharma
` (6 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
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>
Signed-off-by: Vipin Sharma <vipinsh@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 7865b2aa011c..df3e44660bd0 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -12,6 +12,7 @@ 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_FILES += scripts/cleanup.sh
TEST_FILES += 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..1d89b08ab0a4
--- /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)
+ SKIP(return, "iommufd-mode does not have group files");
+
+ 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)
+ SKIP(return, "iommufd-mode does not have container files");
+
+ 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)
+ ksft_exit_skip("open(%s) failed: %s, skipping\n",
+ LUO_DEVICE, strerror(errno));
+
+ close(fd);
+
+ device_bdf = vfio_selftests_get_bdf(&argc, argv);
+ return test_harness_run(argc, argv);
+}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 10/16] vfio: selftests: Initialize vfio_pci_device using a VFIO cdev FD
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (8 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 09/16] vfio: selftests: Add vfio_pci_liveupdate_uapi_test Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 11/16] vfio: selftests: Add Makefile support for TEST_GEN_PROGS_EXTENDED Vipin Sharma
` (5 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
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.
Co-developed-by: David Matlack <dmatlack@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@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 fc75e04ef010..7a81edb3245e 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
@@ -342,19 +342,27 @@ 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;
@@ -365,10 +373,12 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, struct iommu *iomm
device->iommu = iommu;
device->bdf = bdf;
- if (iommu->mode->container_path)
+ if (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);
@@ -376,6 +386,11 @@ 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;
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 11/16] vfio: selftests: Add Makefile support for TEST_GEN_PROGS_EXTENDED
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (9 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 10/16] vfio: selftests: Initialize vfio_pci_device using a VFIO cdev FD Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 12/16] vfio: selftests: Add vfio_pci_liveupdate_kexec_test Vipin Sharma
` (4 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Add Makefile support for TEST_GEN_PROGS_EXTENDED targets. These tests
are not run by default.
TEST_GEN_PROGS_EXTENDED will be used for Live Update selftests in
subsequent commits. These selftests must be run manually because they
require the user/runner to perform additional actions, such as kexec,
during the test.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
tools/testing/selftests/vfio/Makefile | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index df3e44660bd0..ad081ec31fb2 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -32,14 +32,17 @@ LDFLAGS += -pthread
LIBS_O := $(LIBVFIO_O)
LIBS_O += $(LIBLIVEUPDATE_O)
-$(TEST_GEN_PROGS): %: %.o $(LIBS_O)
+$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o $(LIBS_O)
$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBS_O) $(LDLIBS) -o $@
-TEST_GEN_PROGS_O = $(patsubst %, %.o, $(TEST_GEN_PROGS))
-TEST_DEP_FILES := $(patsubst %.o, %.d, $(TEST_GEN_PROGS_O))
+TESTS_O := $(patsubst %, %.o, $(TEST_GEN_PROGS))
+TESTS_O += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))
+
+TEST_DEP_FILES := $(patsubst %.o, %.d, $(TESTS_O))
TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBS_O))
-include $(TEST_DEP_FILES)
-EXTRA_CLEAN += $(TEST_GEN_PROGS_O) $(TEST_DEP_FILES)
+EXTRA_CLEAN += $(TESTS_O)
+EXTRA_CLEAN += $(TEST_DEP_FILES)
endif
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 12/16] vfio: selftests: Add vfio_pci_liveupdate_kexec_test
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (10 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 11/16] vfio: selftests: Add Makefile support for TEST_GEN_PROGS_EXTENDED Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:47 ` [PATCH v4 13/16] vfio: selftests: Expose iommu_modes to tests Vipin Sharma
` (3 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
Add a selftest to exercise preserving a vfio-pci device across a Live
Update. For now the test is extremely simple and just verifies that the
device file can be preserved and retrieved. In the future this test will
be extended to verify more parts about device preservation as they are
implemented.
This test is added to TEST_GEN_PROGS_EXTENDED since it must be run
manually along with a kexec.
To run this test manually:
$ tools/testing/selftests/vfio/scripts/setup.sh 0000:00:04.0
$ tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test --stage 1 0000:00:04.0
$ kexec ... # NOTE: Exact method will be distro-dependent
$ tools/testing/selftests/vfio/scripts/setup.sh 0000:00:04.0
$ tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test --stage 2 0000:00:04.0
The second call to setup.sh is necessary because preserved devices are
not bound to a driver after Live Update. Such devices must be manually
bound by userspace after Live Update via driver_override.
This test is considered passing if all commands exit with 0.
Co-developed-by: David Matlack <dmatlack@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
tools/testing/selftests/vfio/Makefile | 4 +
.../vfio/vfio_pci_liveupdate_kexec_test.c | 89 +++++++++++++++++++
2 files changed, 93 insertions(+)
create mode 100644 tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c
diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index ad081ec31fb2..17082a57aa9f 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -14,6 +14,10 @@ TEST_GEN_PROGS += vfio_pci_device_init_perf_test
TEST_GEN_PROGS += vfio_pci_driver_test
TEST_GEN_PROGS += vfio_pci_liveupdate_uapi_test
+# This test must be run manually since it requires the user/automation to
+# perform a kexec during the test.
+TEST_GEN_PROGS_EXTENDED += vfio_pci_liveupdate_kexec_test
+
TEST_FILES += scripts/cleanup.sh
TEST_FILES += scripts/lib.sh
TEST_FILES += scripts/run.sh
diff --git a/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c b/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c
new file mode 100644
index 000000000000..15b3e3af91d1
--- /dev/null
+++ b/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <libliveupdate.h>
+#include <libvfio.h>
+
+static const char *device_bdf;
+
+static char state_session[LIVEUPDATE_SESSION_NAME_LENGTH];
+static char device_session[LIVEUPDATE_SESSION_NAME_LENGTH];
+
+enum {
+ STATE_TOKEN,
+ DEVICE_TOKEN,
+};
+
+static void before_kexec(int luo_fd)
+{
+ struct vfio_pci_device *device;
+ struct iommu *iommu;
+ int session_fd;
+ int ret;
+
+ iommu = iommu_init("iommufd");
+ device = vfio_pci_device_init(device_bdf, iommu);
+
+ create_state_file(luo_fd, state_session, STATE_TOKEN, /*next_stage=*/2);
+
+ session_fd = luo_create_session(luo_fd, device_session);
+ VFIO_ASSERT_GE(session_fd, 0);
+
+ printf("Preserving device in session\n");
+ ret = luo_session_preserve_fd(session_fd, device->fd, DEVICE_TOKEN);
+ VFIO_ASSERT_EQ(ret, 0);
+
+ close(luo_fd);
+ daemonize_and_wait();
+}
+
+static void after_kexec(int luo_fd, int state_session_fd)
+{
+ struct vfio_pci_device *device;
+ struct iommu *iommu;
+ int session_fd;
+ int device_fd;
+ int stage;
+
+ restore_and_read_stage(state_session_fd, STATE_TOKEN, &stage);
+ VFIO_ASSERT_EQ(stage, 2);
+
+ session_fd = luo_retrieve_session(luo_fd, device_session);
+ VFIO_ASSERT_GE(session_fd, 0);
+
+ printf("Finishing the session before retrieving the device (should fail)\n");
+ VFIO_ASSERT_NE(luo_session_finish(session_fd), 0);
+
+ printf("Retrieving the device FD from LUO\n");
+ device_fd = luo_session_retrieve_fd(session_fd, DEVICE_TOKEN);
+ VFIO_ASSERT_GE(device_fd, 0);
+
+ printf("Finishing the session before binding to iommufd (should fail)\n");
+ VFIO_ASSERT_NE(luo_session_finish(session_fd), 0);
+
+ printf("Binding the device to an iommufd and setting it up\n");
+ iommu = iommu_init("iommufd");
+
+ /*
+ * This will invoke various ioctls on device_fd such as
+ * VFIO_DEVICE_GET_INFO. So this is a decent sanity test
+ * that LUO actually handed us back a valid VFIO device
+ * file and not something else.
+ */
+ device = __vfio_pci_device_init(device_bdf, iommu, device_fd);
+
+ printf("Finishing the session\n");
+ VFIO_ASSERT_EQ(luo_session_finish(session_fd), 0);
+
+ vfio_pci_device_cleanup(device);
+ iommu_cleanup(iommu);
+}
+
+int main(int argc, char *argv[])
+{
+ device_bdf = vfio_selftests_get_bdf(&argc, argv);
+
+ sprintf(device_session, "device-%s", device_bdf);
+ sprintf(state_session, "state-%s", device_bdf);
+
+ return luo_test(argc, argv, state_session, before_kexec, after_kexec);
+}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 13/16] vfio: selftests: Expose iommu_modes to tests
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (11 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 12/16] vfio: selftests: Add vfio_pci_liveupdate_kexec_test Vipin Sharma
@ 2026-05-11 23:47 ` Vipin Sharma
2026-05-11 23:48 ` [PATCH v4 14/16] vfio: selftests: Expose low-level helper routines for setting up struct vfio_pci_device Vipin Sharma
` (2 subsequent siblings)
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:47 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Expose the list of iommu_modes to enable tests that want to iterate
through all possible iommu modes.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
tools/testing/selftests/vfio/lib/include/libvfio/iommu.h | 2 ++
tools/testing/selftests/vfio/lib/iommu.c | 4 +++-
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h
index e9a3386a4719..4b9cbe262159 100644
--- a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h
+++ b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h
@@ -15,6 +15,8 @@ struct iommu_mode {
unsigned long iommu_type;
};
+extern const struct iommu_mode iommu_modes[];
+extern const int nr_iommu_modes;
extern const char *default_iommu_mode;
struct dma_region {
diff --git a/tools/testing/selftests/vfio/lib/iommu.c b/tools/testing/selftests/vfio/lib/iommu.c
index 035dac069d60..95a494f829d2 100644
--- a/tools/testing/selftests/vfio/lib/iommu.c
+++ b/tools/testing/selftests/vfio/lib/iommu.c
@@ -23,7 +23,7 @@
const char *default_iommu_mode = MODE_IOMMUFD;
/* Reminder: Keep in sync with FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(). */
-static const struct iommu_mode iommu_modes[] = {
+const struct iommu_mode iommu_modes[] = {
{
.name = MODE_VFIO_TYPE1_IOMMU,
.container_path = "/dev/vfio/vfio",
@@ -49,6 +49,8 @@ static const struct iommu_mode iommu_modes[] = {
},
};
+const int nr_iommu_modes = ARRAY_SIZE(iommu_modes);
+
static const struct iommu_mode *lookup_iommu_mode(const char *iommu_mode)
{
int i;
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 14/16] vfio: selftests: Expose low-level helper routines for setting up struct vfio_pci_device
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (12 preceding siblings ...)
2026-05-11 23:47 ` [PATCH v4 13/16] vfio: selftests: Expose iommu_modes to tests Vipin Sharma
@ 2026-05-11 23:48 ` Vipin Sharma
2026-05-11 23:48 ` [PATCH v4 15/16] vfio: selftests: Verify that opening VFIO device fails during Live Update Vipin Sharma
2026-05-11 23:48 ` [PATCH v4 16/16] vfio: selftests: Add continuous DMA to vfio_pci_liveupdate_kexec_test Vipin Sharma
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:48 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Expose a few low-level helper routings for setting up vfio_pci_device
structs. These routines will be used in a subsequent commit to assert
that VFIO_GROUP_GET_DEVICE_FD fails under certain conditions.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
.../lib/include/libvfio/vfio_pci_device.h | 5 +++
.../selftests/vfio/lib/vfio_pci_device.c | 33 +++++++++++++------
2 files changed, 28 insertions(+), 10 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 896dfde88118..2389c7698335 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
@@ -125,4 +125,9 @@ static inline bool vfio_pci_device_match(struct vfio_pci_device *device,
const char *vfio_pci_get_cdev_path(const char *bdf);
+/* Low-level routines for setting up a struct vfio_pci_device */
+struct vfio_pci_device *vfio_pci_device_alloc(const char *bdf, struct iommu *iommu);
+void vfio_pci_group_setup(struct vfio_pci_device *device);
+void vfio_pci_iommu_setup(struct vfio_pci_device *device);
+
#endif /* SELFTESTS_VFIO_LIB_INCLUDE_LIBVFIO_VFIO_PCI_DEVICE_H */
diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
index 7a81edb3245e..3152196261a2 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c
@@ -222,7 +222,7 @@ static unsigned int vfio_pci_get_group_from_dev(const char *bdf)
return group;
}
-static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf)
+void vfio_pci_group_setup(struct vfio_pci_device *device)
{
struct vfio_group_status group_status = {
.argsz = sizeof(group_status),
@@ -230,7 +230,7 @@ static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf
char group_path[32];
int group;
- group = vfio_pci_get_group_from_dev(bdf);
+ group = vfio_pci_get_group_from_dev(device->bdf);
snprintf(group_path, sizeof(group_path), "/dev/vfio/%d", group);
device->group_fd = open(group_path, O_RDWR);
@@ -242,14 +242,12 @@ static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf
ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->iommu->container_fd);
}
-static void vfio_pci_container_setup(struct vfio_pci_device *device, const char *bdf)
+void vfio_pci_iommu_setup(struct vfio_pci_device *device)
{
struct iommu *iommu = device->iommu;
unsigned long iommu_type = iommu->mode->iommu_type;
int ret;
- vfio_pci_group_setup(device, bdf);
-
ret = ioctl(iommu->container_fd, VFIO_CHECK_EXTENSION, iommu_type);
VFIO_ASSERT_GT(ret, 0, "VFIO IOMMU type %lu not supported\n", iommu_type);
@@ -259,8 +257,14 @@ static void vfio_pci_container_setup(struct vfio_pci_device *device, const char
* because the IOMMU type is already set.
*/
(void)ioctl(iommu->container_fd, VFIO_SET_IOMMU, (void *)iommu_type);
+}
- device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, bdf);
+static void vfio_pci_container_setup(struct vfio_pci_device *device)
+{
+ vfio_pci_group_setup(device);
+ vfio_pci_iommu_setup(device);
+
+ device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, device->bdf);
VFIO_ASSERT_GE(device->fd, 0);
}
@@ -360,9 +364,7 @@ static void vfio_pci_iommufd_setup(struct vfio_pci_device *device,
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,
- int device_fd)
+struct vfio_pci_device *vfio_pci_device_alloc(const char *bdf, struct iommu *iommu)
{
struct vfio_pci_device *device;
@@ -373,9 +375,20 @@ struct vfio_pci_device *__vfio_pci_device_init(const char *bdf,
device->iommu = iommu;
device->bdf = bdf;
+ return device;
+}
+
+struct vfio_pci_device *__vfio_pci_device_init(const char *bdf,
+ struct iommu *iommu,
+ int device_fd)
+{
+ struct vfio_pci_device *device;
+
+ device = vfio_pci_device_alloc(bdf, iommu);
+
if (iommu->mode->container_path) {
VFIO_ASSERT_EQ(device_fd, -1);
- vfio_pci_container_setup(device, bdf);
+ vfio_pci_container_setup(device);
} else {
vfio_pci_iommufd_setup(device, bdf, device_fd);
}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 15/16] vfio: selftests: Verify that opening VFIO device fails during Live Update
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (13 preceding siblings ...)
2026-05-11 23:48 ` [PATCH v4 14/16] vfio: selftests: Expose low-level helper routines for setting up struct vfio_pci_device Vipin Sharma
@ 2026-05-11 23:48 ` Vipin Sharma
2026-05-11 23:48 ` [PATCH v4 16/16] vfio: selftests: Add continuous DMA to vfio_pci_liveupdate_kexec_test Vipin Sharma
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:48 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
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>
Signed-off-by: Vipin Sharma <vipinsh@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 15b3e3af91d1..65c48196e44e 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);
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread* [PATCH v4 16/16] vfio: selftests: Add continuous DMA to vfio_pci_liveupdate_kexec_test
2026-05-11 23:47 [PATCH v4 00/16] vfio/pci: Base Live Update support for VFIO Vipin Sharma
` (14 preceding siblings ...)
2026-05-11 23:48 ` [PATCH v4 15/16] vfio: selftests: Verify that opening VFIO device fails during Live Update Vipin Sharma
@ 2026-05-11 23:48 ` Vipin Sharma
15 siblings, 0 replies; 17+ messages in thread
From: Vipin Sharma @ 2026-05-11 23:48 UTC (permalink / raw)
To: kvm, linux-doc, linux-kernel, linux-kselftest, linux-pci
Cc: ajayachandra, alex, amastro, ankita, apopple, chrisl, corbet,
dmatlack, graf, jacob.pan, jgg, jgg, jrhilke, julianr, kevin.tian,
leon, leonro, lukas, michal.winiarski, parav, pasha.tatashin,
praan, pratyush, rananta, rientjes, rodrigo.vivi, rppt, saeedm,
skhan, skhawaja, vipinsh, vivek.kasireddy, witu, yanjun.zhu,
yi.l.liu
From: David Matlack <dmatlack@google.com>
Add a long-running DMA memcpy operation to
vfio_pci_liveupdate_kexec_test so that the device attempts to perform
DMAs continuously during the Live Update.
At this point iommufd preservation is not supported and bus mastering is
not kept enabled on the device during across the kexec, so most of these
DMAs will be dropped. However this test ensures that the current device
preservation support does not lead to system instability or crashes if
the device is active. And once iommufd and bus mastering are preserved,
this test can be relaxed to check that the DMA operations completed
successfully.
Signed-off-by: David Matlack <dmatlack@google.com>
Signed-off-by: Vipin Sharma <vipinsh@google.com>
---
.../vfio/vfio_pci_liveupdate_kexec_test.c | 129 ++++++++++++++++++
1 file changed, 129 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 65c48196e44e..36bddfbb88ed 100644
--- a/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c
+++ b/tools/testing/selftests/vfio/vfio_pci_liveupdate_kexec_test.c
@@ -1,8 +1,16 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/sizes.h>
+#include <sys/mman.h>
+
#include <libliveupdate.h>
#include <libvfio.h>
+#define MEMCPY_SIZE SZ_1G
+#define DRIVER_SIZE SZ_1M
+#define MEMFD_SIZE (MEMCPY_SIZE + DRIVER_SIZE)
+
+static struct dma_region memcpy_region;
static const char *device_bdf;
static char state_session[LIVEUPDATE_SESSION_NAME_LENGTH];
@@ -11,8 +19,89 @@ static char device_session[LIVEUPDATE_SESSION_NAME_LENGTH];
enum {
STATE_TOKEN,
DEVICE_TOKEN,
+ MEMFD_TOKEN,
};
+static void dma_memcpy_one(struct vfio_pci_device *device)
+{
+ void *src = memcpy_region.vaddr, *dst;
+ u64 size;
+
+ size = min_t(u64, memcpy_region.size / 2, device->driver.max_memcpy_size);
+ dst = src + size;
+
+ memset(src, 1, size);
+ memset(dst, 0, size);
+
+ printf("Kicking off 1 DMA memcpy operations of size 0x%lx...\n", size);
+ vfio_pci_driver_memcpy(device,
+ to_iova(device, src),
+ to_iova(device, dst),
+ size);
+
+ VFIO_ASSERT_EQ(memcmp(src, dst, size), 0);
+}
+
+static void dma_memcpy_start(struct vfio_pci_device *device)
+{
+ void *src = memcpy_region.vaddr, *dst;
+ u64 count, size;
+
+ size = min_t(u64, memcpy_region.size / 2, device->driver.max_memcpy_size);
+ dst = src + size;
+
+ /*
+ * Rough Math: If we assume the device will perform memcpy at a rate of
+ * 30GB/s then 7200GB of transfers will run for about 4 minutes.
+ */
+ count = (u64)7200 * SZ_1G / size;
+ count = min_t(u64, count, device->driver.max_memcpy_count);
+
+ memset(src, 1, size / 2);
+ memset(dst, 0, size / 2);
+
+ printf("Kicking off %lu DMA memcpy operations of size 0x%lx...\n", count, size);
+ vfio_pci_driver_memcpy_start(device,
+ to_iova(device, src),
+ to_iova(device, dst),
+ size, count);
+}
+
+static void dma_memfd_map(struct vfio_pci_device *device, int fd)
+{
+ void *vaddr;
+
+ vaddr = mmap(NULL, MEMFD_SIZE, PROT_WRITE, MAP_SHARED, fd, 0);
+ VFIO_ASSERT_NE(vaddr, MAP_FAILED);
+
+ memcpy_region.iova = SZ_4G;
+ memcpy_region.size = MEMCPY_SIZE;
+ memcpy_region.vaddr = vaddr;
+ iommu_map(device->iommu, &memcpy_region);
+
+ device->driver.region.iova = memcpy_region.iova + memcpy_region.size;
+ device->driver.region.size = DRIVER_SIZE;
+ device->driver.region.vaddr = vaddr + memcpy_region.size;
+ iommu_map(device->iommu, &device->driver.region);
+}
+
+static void dma_memfd_setup(struct vfio_pci_device *device, int session_fd)
+{
+ int fd, ret;
+
+ fd = memfd_create("dma-buffer", 0);
+ VFIO_ASSERT_GE(fd, 0);
+
+ ret = fallocate(fd, 0, 0, MEMFD_SIZE);
+ VFIO_ASSERT_EQ(ret, 0);
+
+ printf("Preserving memfd of size 0x%x in session\n", MEMFD_SIZE);
+ ret = luo_session_preserve_fd(session_fd, fd, MEMFD_TOKEN);
+ VFIO_ASSERT_EQ(ret, 0);
+
+ dma_memfd_map(device, fd);
+}
+
static void before_kexec(int luo_fd)
{
struct vfio_pci_device *device;
@@ -32,6 +121,27 @@ static void before_kexec(int luo_fd)
ret = luo_session_preserve_fd(session_fd, device->fd, DEVICE_TOKEN);
VFIO_ASSERT_EQ(ret, 0);
+ dma_memfd_setup(device, session_fd);
+
+ /*
+ * If the device has a selftests driver, kick off a long-running DMA
+ * operation to exercise the device trying to DMA during a Live Update.
+ * Since iommufd preservation is not supported yet, these DMAs should be
+ * dropped. So this is just looking to verify that the system does not
+ * fall over and crash as a result of a busy device being preserved.
+ */
+ if (device->driver.ops) {
+ vfio_pci_driver_init(device);
+ dma_memcpy_start(device);
+
+ /*
+ * Disable interrupts on the device or freeze() will fail.
+ * Unfortunately there isn't a way to easily have a test for
+ * that here since the check happens during shutdown.
+ */
+ vfio_pci_msix_disable(device);
+ }
+
close(luo_fd);
daemonize_and_wait();
}
@@ -78,6 +188,7 @@ static void after_kexec(int luo_fd, int state_session_fd)
struct iommu *iommu;
int session_fd;
int device_fd;
+ int memfd;
int stage;
check_open_vfio_device_fails();
@@ -88,6 +199,10 @@ static void after_kexec(int luo_fd, int state_session_fd)
session_fd = luo_retrieve_session(luo_fd, device_session);
VFIO_ASSERT_GE(session_fd, 0);
+ printf("Retrieving memfd from LUO\n");
+ memfd = luo_session_retrieve_fd(session_fd, MEMFD_TOKEN);
+ VFIO_ASSERT_GE(memfd, 0);
+
printf("Finishing the session before retrieving the device (should fail)\n");
VFIO_ASSERT_NE(luo_session_finish(session_fd), 0);
@@ -109,9 +224,23 @@ static void after_kexec(int luo_fd, int state_session_fd)
*/
device = __vfio_pci_device_init(device_bdf, iommu, device_fd);
+ dma_memfd_map(device, memfd);
+
printf("Finishing the session\n");
VFIO_ASSERT_EQ(luo_session_finish(session_fd), 0);
+ /*
+ * Once iommufd preservation is supported and the device is kept fully
+ * running across the Live Update, this should wait for the long-
+ * running DMA memcpy operation kicked off in before_kexec() to
+ * complete. But for now we expect the device to be reset so just
+ * trigger a single memcpy to make sure it's still functional.
+ */
+ if (device->driver.ops) {
+ vfio_pci_driver_init(device);
+ dma_memcpy_one(device);
+ }
+
vfio_pci_device_cleanup(device);
iommu_cleanup(iommu);
}
--
2.54.0.563.g4f69b47b94-goog
^ permalink raw reply related [flat|nested] 17+ messages in thread