Merge tag 'pull-vfio-20250810' of https://github.com/legoater/qemu into staging

vfio queue:

* Add documentation for the use-legacy-x86-rom property
* Preserve pending VFIO interrupts during CPR

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmiYwgkACgkQUaNDx8/7
# 7KH5ew//ThaCgYlT2KwwJFfNUw290uQuvZAZUCB0vx+zhsQzQW5vzAx6KvFO+UQu
# k64BQLk8OV97tDpsEcnZEUoPfLo/05mxlcSKYfG3rTpp+ZxoCXUBhQ9f0ZR9t2gz
# WihHrA+g/r69VlcW9fCdar/n2svvysmY2OzybSAILplmJlk5CsJRB4cbpy09AR70
# t70bWGl+4+voENeVQjdYa35588bjwTdnzpOqy7fbFacs6L17NzaW30lJ8S8AWX8W
# a84nnuJgL2qkR73EvY1wL10EyqqR6gYCsbE39ARf4GoC8UE0cRp7tSXm/xkFd6U1
# I6Wv/7zx9FkKq51b8GB9n8NfW9U3XTTfJSS6QR6GYU77zcukUj06Fr5PNLEg9yOf
# 9dfrPt6pap1vx4xuoq9IqrwOVcKd9e9vi9hARLonlzcLMXZqJnKr3KcelcCcF8El
# Sf994H1izHjr1PqpKCDn7dDJ5Bp7CkvnR9RSCzRssovDzfRBmSI5iC75vpjcEd9z
# zMpKG1auyamlpjyFIBOw3rlMXSkv4vk0wmjv/P5aQxKTlu0Oyyp4dZMPl7C4Grut
# WmXJao6zrcUsxvxf2pi2aELGKzLow240Xh4oceD+dDyLQ6Z25J5aj/4MUWxXbbUT
# YffunKYQ00Bk5+x0gp7tiitNu9s4Z2ezshqebweBxNGHWMiJ5sI=
# =lM1W
# -----END PGP SIGNATURE-----
# gpg: Signature made Sun 10 Aug 2025 12:00:09 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-20250810' of https://github.com/legoater/qemu:
  vfio: Document 'use-legacy-x86-rom' property
  vfio/pci: preserve pending interrupts
  vfio/pci: augment set_handler

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

4 files changed, 117 insertions, 4 deletions

diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c
index 384b56c..a831243 100644
--- a/hw/vfio/cpr.c
+++ b/hw/vfio/cpr.c
@@ -70,7 +70,7 @@ static void vfio_cpr_claim_vectors(VFIOPCIDevice *vdev, int nr_vectors,
         fd = vfio_cpr_load_vector_fd(vdev, "interrupt", i);
         if (fd >= 0) {
             vfio_pci_vector_init(vdev, i);
-            vfio_pci_msi_set_handler(vdev, i);
+            vfio_pci_msi_set_handler(vdev, i, true);
         }
 
         if (vfio_cpr_load_vector_fd(vdev, "kvm_interrupt", i) >= 0) {
@@ -200,3 +200,94 @@ void vfio_cpr_add_kvm_notifier(void)
                                     MIG_MODE_CPR_TRANSFER);
     }
 }
+
+static int set_irqfd_notifier_gsi(KVMState *s, EventNotifier *n,
+                                  EventNotifier *rn, int virq, bool enable)
+{
+    if (enable) {
+        return kvm_irqchip_add_irqfd_notifier_gsi(s, n, rn, virq);
+    } else {
+        return kvm_irqchip_remove_irqfd_notifier_gsi(s, n, virq);
+    }
+}
+
+static int vfio_cpr_set_msi_virq(VFIOPCIDevice *vdev, Error **errp, bool enable)
+{
+    const char *op = (enable ? "enable" : "disable");
+    PCIDevice *pdev = &vdev->pdev;
+    int i, nr_vectors, ret = 0;
+
+    if (msix_enabled(pdev)) {
+        nr_vectors = vdev->msix->entries;
+
+    } else if (msi_enabled(pdev)) {
+        nr_vectors = msi_nr_vectors_allocated(pdev);
+
+    } else if (vfio_pci_read_config(pdev, PCI_INTERRUPT_PIN, 1)) {
+        ret = set_irqfd_notifier_gsi(kvm_state, &vdev->intx.interrupt,
+                                     &vdev->intx.unmask, vdev->intx.route.irq,
+                                     enable);
+        if (ret) {
+            error_setg_errno(errp, -ret, "failed to %s INTx irq %d",
+                             op, vdev->intx.route.irq);
+            return ret;
+        }
+        vfio_pci_intx_set_handler(vdev, enable);
+        return ret;
+
+    } else {
+        return 0;
+    }
+
+    for (i = 0; i < nr_vectors; i++) {
+        VFIOMSIVector *vector = &vdev->msi_vectors[i];
+        if (vector->use) {
+            ret = set_irqfd_notifier_gsi(kvm_state, &vector->kvm_interrupt,
+                                         NULL, vector->virq, enable);
+            if (ret) {
+                error_setg_errno(errp, -ret,
+                                 "failed to %s msi vector %d virq %d",
+                                 op, i, vector->virq);
+                return ret;
+            }
+            vfio_pci_msi_set_handler(vdev, i, enable);
+        }
+    }
+
+    return ret;
+}
+
+/*
+ * When CPR starts, detach IRQs from the VFIO device so future interrupts
+ * are posted to kvm_interrupt, which is preserved in new QEMU.  Interrupts
+ * that were already posted to the old KVM instance, but not delivered to the
+ * VCPU, are recovered via KVM_GET_LAPIC and pushed to the new KVM instance
+ * in new QEMU.
+ *
+ * If CPR fails, reattach the IRQs.
+ */
+static int vfio_cpr_pci_notifier(NotifierWithReturn *notifier,
+                                 MigrationEvent *e, Error **errp)
+{
+    VFIOPCIDevice *vdev =
+        container_of(notifier, VFIOPCIDevice, cpr.transfer_notifier);
+
+    if (e->type == MIG_EVENT_PRECOPY_SETUP) {
+        return vfio_cpr_set_msi_virq(vdev, errp, false);
+    } else if (e->type == MIG_EVENT_PRECOPY_FAILED) {
+        return vfio_cpr_set_msi_virq(vdev, errp, true);
+    }
+    return 0;
+}
+
+void vfio_cpr_pci_register_device(VFIOPCIDevice *vdev)
+{
+    migration_add_notifier_mode(&vdev->cpr.transfer_notifier,
+                                vfio_cpr_pci_notifier,
+                                MIG_MODE_CPR_TRANSFER);
+}
+
+void vfio_cpr_pci_unregister_device(VFIOPCIDevice *vdev)
+{
+    migration_remove_notifier(&vdev->cpr.transfer_notifier);
+}
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 4fa692c..07257d0 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -413,6 +413,14 @@ bool vfio_pci_intx_enable(VFIOPCIDevice *vdev, Error **errp)
     return vfio_intx_enable(vdev, errp);
 }
 
+void vfio_pci_intx_set_handler(VFIOPCIDevice *vdev, bool enable)
+{
+    int fd = event_notifier_get_fd(&vdev->intx.interrupt);
+    IOHandler *handler = (enable ? vfio_intx_interrupt : NULL);
+
+    qemu_set_fd_handler(fd, handler, NULL, vdev);
+}
+
 /*
  * MSI/X
  */
@@ -451,12 +459,13 @@ static void vfio_msi_interrupt(void *opaque)
     notify(&vdev->pdev, nr);
 }
 
-void vfio_pci_msi_set_handler(VFIOPCIDevice *vdev, int nr)
+void vfio_pci_msi_set_handler(VFIOPCIDevice *vdev, int nr, bool enable)
 {
     VFIOMSIVector *vector = &vdev->msi_vectors[nr];
     int fd = event_notifier_get_fd(&vector->interrupt);
+    IOHandler *handler = (enable ? vfio_msi_interrupt : NULL);
 
-    qemu_set_fd_handler(fd, vfio_msi_interrupt, NULL, vector);
+    qemu_set_fd_handler(fd, handler, NULL, vector);
 }
 
 /*
@@ -2992,6 +3001,7 @@ void vfio_pci_put_device(VFIOPCIDevice *vdev)
 {
     vfio_display_finalize(vdev);
     vfio_bars_finalize(vdev);
+    vfio_cpr_pci_unregister_device(vdev);
     g_free(vdev->emulated_config_bits);
     g_free(vdev->rom);
     /*
@@ -3471,6 +3481,7 @@ static void vfio_pci_realize(PCIDevice *pdev, Error **errp)
     vfio_pci_register_err_notifier(vdev);
     vfio_pci_register_req_notifier(vdev);
     vfio_setup_resetfn_quirk(vdev);
+    vfio_cpr_pci_register_device(vdev);
 
     return;
 
@@ -3890,6 +3901,9 @@ static void vfio_pci_nohotplug_dev_class_init(ObjectClass *klass,
                                           "x-ramfb-migrate",
                                           "Override default migration support for ramfb support "
                                           "(DEBUG)");
+    object_class_property_set_description(klass, /* 10.1 */
+                                          "use-legacy-x86-rom",
+                                          "Controls loading of a legacy VGA BIOS ROM");
 }
 
 static const TypeInfo vfio_pci_nohotplug_dev_info = {
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 81465a8..810a842 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -188,6 +188,7 @@ struct VFIOPCIDevice {
     bool skip_vsc_check;
     VFIODisplay *dpy;
     Notifier irqchip_change_notifier;
+    VFIOPCICPR cpr;
 };
 
 /* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
@@ -209,8 +210,9 @@ void vfio_pci_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector,
 void vfio_pci_prepare_kvm_msi_virq_batch(VFIOPCIDevice *vdev);
 void vfio_pci_commit_kvm_msi_virq_batch(VFIOPCIDevice *vdev);
 bool vfio_pci_intx_enable(VFIOPCIDevice *vdev, Error **errp);
+void vfio_pci_intx_set_handler(VFIOPCIDevice *vdev, bool enable);
 void vfio_pci_msix_set_notifiers(VFIOPCIDevice *vdev);
-void vfio_pci_msi_set_handler(VFIOPCIDevice *vdev, int nr);
+void vfio_pci_msi_set_handler(VFIOPCIDevice *vdev, int nr, bool enable);
 
 uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
 void vfio_pci_write_config(PCIDevice *pdev,
diff --git a/include/hw/vfio/vfio-cpr.h b/include/hw/vfio/vfio-cpr.h
index 80ad20d..d37daff 100644
--- a/include/hw/vfio/vfio-cpr.h
+++ b/include/hw/vfio/vfio-cpr.h
@@ -38,6 +38,10 @@ typedef struct VFIODeviceCPR {
     uint32_t ioas_id;
 } VFIODeviceCPR;
 
+typedef struct VFIOPCICPR {
+    NotifierWithReturn transfer_notifier;
+} VFIOPCICPR;
+
 bool vfio_legacy_cpr_register_container(struct VFIOContainer *container,
                                         Error **errp);
 void vfio_legacy_cpr_unregister_container(struct VFIOContainer *container);
@@ -77,5 +81,7 @@ extern const VMStateDescription vfio_cpr_pci_vmstate;
 extern const VMStateDescription vmstate_cpr_vfio_devices;
 
 void vfio_cpr_add_kvm_notifier(void);
+void vfio_cpr_pci_register_device(struct VFIOPCIDevice *vdev);
+void vfio_cpr_pci_unregister_device(struct VFIOPCIDevice *vdev);
 
 #endif /* HW_VFIO_VFIO_CPR_H */