Merge tag 'pull-vfio-20250611' of https://github.com/legoater/qemu into stagingHEADmaster

vfio queue:

* Fixed newly added potential issues in vfio-pci
* Added support to report vfio-ap configuration changes
* Added prerequisite support for vfio-user
* Added first part for VFIO live update support

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmhJm00ACgkQUaNDx8/7
# 7KHBehAAlbSt+QCPwdNJ/5QPGGPWIQ86acIHaI/sE/lpcJx9FideQhtKTtt0gTOE
# ZNGbzfeCnewCM+VLMgkrYZC9DWd9OpEO68tDy6ev577F6ijSR8wzXRtDl2j5Revm
# R9gBuOm/cQ6Mafiv8SNPNSGW2tQ0M9Bd4GJRa5K3VBf8kFwPpWEZC/yDWbvSVvwc
# 99TFXziIbWJEYGRzG4h7hoEEd/GapZOwTRIPRoRGHznbOPMsxShjIhExn8ZGTlU9
# woaNBPZXS5xjjy5tKyURexu+eyxbR6WsZFyeAA03+HzWEfRzhFc/rhAC6mBbpq7v
# 03a/4ewkKZ0fYUf9G2H5YpXTXl6io+qk+irKi99/4GT0oSBMrm+/NcY7u9Hv2MwA
# 50h3iXUhLQYzL2G2bSSoBTKOGxV84Xtto9j7dM7fy8e0nYv9rucvKl+V3Ox1Qwv4
# 8+bQsxP5tjmHlXE/n6ckfcrWtSHuWmb3JJ8yxdBttdo3Cz/+KxJ3UjtP9U81RXxY
# gepxCRXZmcTfnv1dV6FyjOE6QOhB3WIT5rHmgoQIvHGhtBsLpT2mDlSsMVEQIXvm
# ixQnRguwQv9fgEZeYB/ck/ezluOxewBlOv5Q3CPpHQBd2Ykh4N/8xsWpXlKI1KWr
# Tj7Nh/2ObqNXbKdmb9nNiuo6eQDkPOm4mr1cs2ncMr7/cRGeKeA=
# =KOf3
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 11 Jun 2025 11:05:49 EDT
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@redhat.com>" [full]
# gpg:                 aka "Cédric Le Goater <clg@kaod.org>" [full]
# Primary key fingerprint: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-vfio-20250611' of https://github.com/legoater/qemu: (27 commits)
  vfio: improve VFIODeviceIOOps docs
  vfio/pci: export MSI functions
  vfio/pci: vfio_notifier_cleanup
  vfio/pci: vfio_notifier_init cpr parameters
  vfio/pci: pass vector to virq functions
  vfio/pci: vfio_notifier_init
  vfio/pci: vfio_pci_vector_init
  vfio-pci: skip reset during cpr
  pci: skip reset during cpr
  pci: export msix_is_pending
  vfio/container: recover from unmap-all-vaddr failure
  vfio/container: mdev cpr blocker
  vfio/container: restore DMA vaddr
  vfio/container: discard old DMA vaddr
  vfio/container: preserve descriptors
  vfio/container: register container for cpr
  migration: lower handler priority
  migration: cpr helpers
  vfio: mark posted writes in region write callbacks
  vfio: add per-region fd support
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 287 insertions, 0 deletions

diff --git a/hw/vfio/cpr-legacy.c b/hw/vfio/cpr-legacy.c
new file mode 100644
index 0000000..a84c324
--- /dev/null
+++ b/hw/vfio/cpr-legacy.c
@@ -0,0 +1,287 @@
+/*
+ * Copyright (c) 2021-2025 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include <sys/ioctl.h>
+#include <linux/vfio.h>
+#include "qemu/osdep.h"
+#include "hw/vfio/vfio-container.h"
+#include "hw/vfio/vfio-device.h"
+#include "hw/vfio/vfio-listener.h"
+#include "migration/blocker.h"
+#include "migration/cpr.h"
+#include "migration/migration.h"
+#include "migration/vmstate.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+
+static bool vfio_dma_unmap_vaddr_all(VFIOContainer *container, Error **errp)
+{
+    struct vfio_iommu_type1_dma_unmap unmap = {
+        .argsz = sizeof(unmap),
+        .flags = VFIO_DMA_UNMAP_FLAG_VADDR | VFIO_DMA_UNMAP_FLAG_ALL,
+        .iova = 0,
+        .size = 0,
+    };
+    if (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
+        error_setg_errno(errp, errno, "vfio_dma_unmap_vaddr_all");
+        return false;
+    }
+    container->cpr.vaddr_unmapped = true;
+    return true;
+}
+
+/*
+ * Set the new @vaddr for any mappings registered during cpr load.
+ * The incoming state is cleared thereafter.
+ */
+static int vfio_legacy_cpr_dma_map(const VFIOContainerBase *bcontainer,
+                                   hwaddr iova, ram_addr_t size, void *vaddr,
+                                   bool readonly, MemoryRegion *mr)
+{
+    const VFIOContainer *container = container_of(bcontainer, VFIOContainer,
+                                                  bcontainer);
+    struct vfio_iommu_type1_dma_map map = {
+        .argsz = sizeof(map),
+        .flags = VFIO_DMA_MAP_FLAG_VADDR,
+        .vaddr = (__u64)(uintptr_t)vaddr,
+        .iova = iova,
+        .size = size,
+    };
+
+    g_assert(cpr_is_incoming());
+
+    if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map)) {
+        return -errno;
+    }
+
+    return 0;
+}
+
+static void vfio_region_remap(MemoryListener *listener,
+                              MemoryRegionSection *section)
+{
+    VFIOContainer *container = container_of(listener, VFIOContainer,
+                                            cpr.remap_listener);
+    vfio_container_region_add(&container->bcontainer, section, true);
+}
+
+static bool vfio_cpr_supported(VFIOContainer *container, Error **errp)
+{
+    if (!ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UPDATE_VADDR)) {
+        error_setg(errp, "VFIO container does not support VFIO_UPDATE_VADDR");
+        return false;
+
+    } else if (!ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UNMAP_ALL)) {
+        error_setg(errp, "VFIO container does not support VFIO_UNMAP_ALL");
+        return false;
+
+    } else {
+        return true;
+    }
+}
+
+static int vfio_container_pre_save(void *opaque)
+{
+    VFIOContainer *container = opaque;
+    Error *local_err = NULL;
+
+    if (!vfio_dma_unmap_vaddr_all(container, &local_err)) {
+        error_report_err(local_err);
+        return -1;
+    }
+    return 0;
+}
+
+static int vfio_container_post_load(void *opaque, int version_id)
+{
+    VFIOContainer *container = opaque;
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+    VFIOGroup *group;
+    Error *local_err = NULL;
+
+    if (!vfio_listener_register(bcontainer, &local_err)) {
+        error_report_err(local_err);
+        return -1;
+    }
+
+    QLIST_FOREACH(group, &container->group_list, container_next) {
+        VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+
+        /* Restore original dma_map function */
+        vioc->dma_map = container->cpr.saved_dma_map;
+    }
+    return 0;
+}
+
+static const VMStateDescription vfio_container_vmstate = {
+    .name = "vfio-container",
+    .version_id = 0,
+    .minimum_version_id = 0,
+    .priority = MIG_PRI_LOW,  /* Must happen after devices and groups */
+    .pre_save = vfio_container_pre_save,
+    .post_load = vfio_container_post_load,
+    .needed = cpr_incoming_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static int vfio_cpr_fail_notifier(NotifierWithReturn *notifier,
+                                  MigrationEvent *e, Error **errp)
+{
+    VFIOContainer *container =
+        container_of(notifier, VFIOContainer, cpr.transfer_notifier);
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+
+    if (e->type != MIG_EVENT_PRECOPY_FAILED) {
+        return 0;
+    }
+
+    if (container->cpr.vaddr_unmapped) {
+        /*
+         * Force a call to vfio_region_remap for each mapped section by
+         * temporarily registering a listener, and temporarily diverting
+         * dma_map to vfio_legacy_cpr_dma_map.  The latter restores vaddr.
+         */
+
+        VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+        vioc->dma_map = vfio_legacy_cpr_dma_map;
+
+        container->cpr.remap_listener = (MemoryListener) {
+            .name = "vfio cpr recover",
+            .region_add = vfio_region_remap
+        };
+        memory_listener_register(&container->cpr.remap_listener,
+                                 bcontainer->space->as);
+        memory_listener_unregister(&container->cpr.remap_listener);
+        container->cpr.vaddr_unmapped = false;
+        vioc->dma_map = container->cpr.saved_dma_map;
+    }
+    return 0;
+}
+
+bool vfio_legacy_cpr_register_container(VFIOContainer *container, Error **errp)
+{
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+    Error **cpr_blocker = &container->cpr.blocker;
+
+    migration_add_notifier_mode(&bcontainer->cpr_reboot_notifier,
+                                vfio_cpr_reboot_notifier,
+                                MIG_MODE_CPR_REBOOT);
+
+    if (!vfio_cpr_supported(container, cpr_blocker)) {
+        return migrate_add_blocker_modes(cpr_blocker, errp,
+                                         MIG_MODE_CPR_TRANSFER, -1) == 0;
+    }
+
+    vmstate_register(NULL, -1, &vfio_container_vmstate, container);
+
+    /* During incoming CPR, divert calls to dma_map. */
+    if (cpr_is_incoming()) {
+        VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer);
+        container->cpr.saved_dma_map = vioc->dma_map;
+        vioc->dma_map = vfio_legacy_cpr_dma_map;
+    }
+
+    migration_add_notifier_mode(&container->cpr.transfer_notifier,
+                                vfio_cpr_fail_notifier,
+                                MIG_MODE_CPR_TRANSFER);
+    return true;
+}
+
+void vfio_legacy_cpr_unregister_container(VFIOContainer *container)
+{
+    VFIOContainerBase *bcontainer = &container->bcontainer;
+
+    migration_remove_notifier(&bcontainer->cpr_reboot_notifier);
+    migrate_del_blocker(&container->cpr.blocker);
+    vmstate_unregister(NULL, &vfio_container_vmstate, container);
+    migration_remove_notifier(&container->cpr.transfer_notifier);
+}
+
+/*
+ * In old QEMU, VFIO_DMA_UNMAP_FLAG_VADDR may fail on some mapping after
+ * succeeding for others, so the latter have lost their vaddr.  Call this
+ * to restore vaddr for a section with a giommu.
+ *
+ * The giommu already exists.  Find it and replay it, which calls
+ * vfio_legacy_cpr_dma_map further down the stack.
+ */
+void vfio_cpr_giommu_remap(VFIOContainerBase *bcontainer,
+                           MemoryRegionSection *section)
+{
+    VFIOGuestIOMMU *giommu = NULL;
+    hwaddr as_offset = section->offset_within_address_space;
+    hwaddr iommu_offset = as_offset - section->offset_within_region;
+
+    QLIST_FOREACH(giommu, &bcontainer->giommu_list, giommu_next) {
+        if (giommu->iommu_mr == IOMMU_MEMORY_REGION(section->mr) &&
+            giommu->iommu_offset == iommu_offset) {
+            break;
+        }
+    }
+    g_assert(giommu);
+    memory_region_iommu_replay(giommu->iommu_mr, &giommu->n);
+}
+
+/*
+ * In old QEMU, VFIO_DMA_UNMAP_FLAG_VADDR may fail on some mapping after
+ * succeeding for others, so the latter have lost their vaddr.  Call this
+ * to restore vaddr for a section with a RamDiscardManager.
+ *
+ * The ram discard listener already exists.  Call its populate function
+ * directly, which calls vfio_legacy_cpr_dma_map.
+ */
+bool vfio_cpr_ram_discard_register_listener(VFIOContainerBase *bcontainer,
+                                            MemoryRegionSection *section)
+{
+    VFIORamDiscardListener *vrdl =
+        vfio_find_ram_discard_listener(bcontainer, section);
+
+    g_assert(vrdl);
+    return vrdl->listener.notify_populate(&vrdl->listener, section) == 0;
+}
+
+int vfio_cpr_group_get_device_fd(int d, const char *name)
+{
+    const int id = 0;
+    int fd = cpr_find_fd(name, id);
+
+    if (fd < 0) {
+        fd = ioctl(d, VFIO_GROUP_GET_DEVICE_FD, name);
+        if (fd >= 0) {
+            cpr_save_fd(name, id, fd);
+        }
+    }
+    return fd;
+}
+
+static bool same_device(int fd1, int fd2)
+{
+    struct stat st1, st2;
+
+    return !fstat(fd1, &st1) && !fstat(fd2, &st2) && st1.st_dev == st2.st_dev;
+}
+
+bool vfio_cpr_container_match(VFIOContainer *container, VFIOGroup *group,
+                              int fd)
+{
+    if (container->fd == fd) {
+        return true;
+    }
+    if (!same_device(container->fd, fd)) {
+        return false;
+    }
+    /*
+     * Same device, different fd.  This occurs when the container fd is
+     * cpr_save'd multiple times, once for each groupid, so SCM_RIGHTS
+     * produces duplicates.  De-dup it.
+     */
+    cpr_delete_fd("vfio_container_for_group", group->groupid);
+    close(fd);
+    cpr_save_fd("vfio_container_for_group", group->groupid, container->fd);
+    return true;
+}