Pass-through devices of a VM are not necessarily in the same group and
all groups/address_spaces need to be scanned when the machine is
reset. Commit f16f39c3fc97 ("Implement PCI hot reset") introduced a VM
reset handler for this purpose. Move it under device.cAlso reintroduce the comment which explained the context and was lost along the way. Reviewed-by: Zhenzhong Duan <zhenzhong.d...@intel.com> Reviewed-by: John Levon <john.le...@nutanix.com> Link: https://lore.kernel.org/qemu-devel/20250326075122.1299361-26-...@redhat.com Signed-off-by: Cédric Le Goater <c...@redhat.com> --- hw/vfio/common.c | 18 ------------------ hw/vfio/device.c | 35 +++++++++++++++++++++++++++++++++++ hw/vfio/trace-events | 2 +- 3 files changed, 36 insertions(+), 19 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index a85ed364090f6676cbbc9b513f6afbf26b5a894b..45ac8b7d8bdda391b1f8e04704908f2c0ef47aa8 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1300,21 +1300,3 @@ const MemoryListener vfio_memory_listener = { .log_global_stop = vfio_listener_log_global_stop, .log_sync = vfio_listener_log_sync, }; - -void vfio_reset_handler(void *opaque) -{ - VFIODevice *vbasedev; - - trace_vfio_reset_handler(); - QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) { - if (vbasedev->dev->realized) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); - } - } - - QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) { - if (vbasedev->dev->realized && vbasedev->needs_reset) { - vbasedev->ops->vfio_hot_reset_multi(vbasedev); - } - } -} diff --git a/hw/vfio/device.c b/hw/vfio/device.c index 179c9fb8decc42dcd8d1b4fe10e7acaa2a6f2c7c..e122c797c206c285ef26c3a56d841d8c3be8b58b 100644 --- a/hw/vfio/device.c +++ b/hw/vfio/device.c @@ -34,6 +34,41 @@ VFIODeviceList vfio_device_list = QLIST_HEAD_INITIALIZER(vfio_device_list); +/* + * We want to differentiate hot reset of multiple in-use devices vs + * hot reset of a single in-use device. VFIO_DEVICE_RESET will already + * handle the case of doing hot resets when there is only a single + * device per bus. The in-use here refers to how many VFIODevices are + * affected. A hot reset that affects multiple devices, but only a + * single in-use device, means that we can call it from our bus + * ->reset() callback since the extent is effectively a single + * device. This allows us to make use of it in the hotplug path. When + * there are multiple in-use devices, we can only trigger the hot + * reset during a system reset and thus from our reset handler. We + * separate _one vs _multi here so that we don't overlap and do a + * double reset on the system reset path where both our reset handler + * and ->reset() callback are used. Calling _one() will only do a hot + * reset for the one in-use devices case, calling _multi() will do + * nothing if a _one() would have been sufficient. + */ +void vfio_reset_handler(void *opaque) +{ + VFIODevice *vbasedev; + + trace_vfio_reset_handler(); + QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) { + if (vbasedev->dev->realized) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); + } + } + + QLIST_FOREACH(vbasedev, &vfio_device_list, global_next) { + if (vbasedev->dev->realized && vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); + } + } +} + /* * Common VFIO interrupt disable */ diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 590d9674cf7bc47171516082abaf398dda72b86d..9fee7df8764978723f79dc60d3dc796777278858 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -108,7 +108,6 @@ vfio_put_base_device(int fd) "close vdev->fd=%d" vfio_legacy_dma_unmap_overflow_workaround(void) "" vfio_get_dirty_bitmap(uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start, uint64_t dirty_pages) "iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64" dirty_pages=%"PRIu64 vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64 -vfio_reset_handler(void) "" # region.c vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" @@ -196,3 +195,4 @@ iommufd_cdev_pci_hot_reset_dep_devices(int domain, int bus, int slot, int functi # device.c vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%08x" +vfio_reset_handler(void) "" -- 2.49.0
