vfio_cdx_set_msi_trigger() reads vdev->config_msi and operates on the
vdev->cdx_irqs array based on its value, but provides no serialization
against concurrent VFIO_DEVICE_SET_IRQS ioctls. Two callers can race
such that one observes config_msi as set while another clears it and
frees cdx_irqs via vfio_cdx_msi_disable(), resulting in a use-after-free
of the cdx_irqs array.
Add a cdx_irqs_lock mutex to struct vfio_cdx_device and acquire it in
vfio_cdx_set_msi_trigger(), which is the single chokepoint through
which all updates to config_msi, cdx_irqs, and msi_count flow, covering
both the ioctl path and the close-device cleanup path. This keeps the
test of config_msi atomic with the subsequent enable, disable, or
trigger operations.
Drop the pre-call !cdx_irqs test from vfio_cdx_irqs_cleanup() as part
of this change: the optimization it provided is redundant with the
!config_msi early-return inside vfio_cdx_msi_disable(), and leaving the
test in place would be an unsynchronized read of state the new lock is
meant to protect.
Fixes: 848e447e000c ("vfio/cdx: add interrupt support")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Alex Williamson <alex.williamson@nvidia.com>
Acked-by: Nikhil Agarwal <nikhil.agarwal@amd.com>
Link: https://lore.kernel.org/r/20260417202800.88287-3-alex.williamson@nvidia.com
Signed-off-by: Alex Williamson <alex@shazbot.org>
if (start + count > cdx_dev->num_msi)
return -EINVAL;
+ guard(mutex)(&vdev->cdx_irqs_lock);
+
if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
vfio_cdx_msi_disable(vdev);
return 0;
/* Free All IRQs for the given device */
void vfio_cdx_irqs_cleanup(struct vfio_cdx_device *vdev)
{
- /*
- * Device does not support any interrupt or the interrupts
- * were not configured
- */
- if (!vdev->cdx_irqs)
- return;
-
vfio_cdx_set_msi_trigger(vdev, 0, 0, 0, VFIO_IRQ_SET_DATA_NONE, NULL);
}
#include "private.h"
+static int vfio_cdx_init_dev(struct vfio_device *core_vdev)
+{
+ struct vfio_cdx_device *vdev =
+ container_of(core_vdev, struct vfio_cdx_device, vdev);
+
+ mutex_init(&vdev->cdx_irqs_lock);
+ return 0;
+}
+
+static void vfio_cdx_release_dev(struct vfio_device *core_vdev)
+{
+ struct vfio_cdx_device *vdev =
+ container_of(core_vdev, struct vfio_cdx_device, vdev);
+
+ mutex_destroy(&vdev->cdx_irqs_lock);
+}
+
static int vfio_cdx_open_device(struct vfio_device *core_vdev)
{
struct vfio_cdx_device *vdev =
static const struct vfio_device_ops vfio_cdx_ops = {
.name = "vfio-cdx",
+ .init = vfio_cdx_init_dev,
+ .release = vfio_cdx_release_dev,
.open_device = vfio_cdx_open_device,
.close_device = vfio_cdx_close_device,
.ioctl = vfio_cdx_ioctl,
#ifndef VFIO_CDX_PRIVATE_H
#define VFIO_CDX_PRIVATE_H
+#include <linux/mutex.h>
+
#define VFIO_CDX_OFFSET_SHIFT 40
static inline u64 vfio_cdx_index_to_offset(u32 index)
struct vfio_cdx_device {
struct vfio_device vdev;
struct vfio_cdx_region *regions;
+ struct mutex cdx_irqs_lock;
struct vfio_cdx_irq *cdx_irqs;
u32 flags;
#define BME_SUPPORT BIT(0)