vfio-pci: preserve MSI

Save the MSI message area as part of vfio-pci vmstate, and preserve the
interrupt and notifier eventfd's.  migrate_incoming loads the MSI data,
then the vfio-pci post_load handler finds the eventfds in CPR state,
rebuilds vector data structures, and attaches the interrupts to the new
KVM instance.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1751493538-202042-2-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>

1 files changed, 50 insertions, 2 deletions

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index fa25bded25..5f9f2640e5 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -29,6 +29,7 @@
 #include "hw/pci/pci_bridge.h"
 #include "hw/qdev-properties.h"
 #include "hw/qdev-properties-system.h"
+#include "hw/vfio/vfio-cpr.h"
 #include "migration/vmstate.h"
 #include "migration/cpr.h"
 #include "qobject/qdict.h"
@@ -57,20 +58,33 @@ static void vfio_disable_interrupts(VFIOPCIDevice *vdev);
 static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
 static void vfio_msi_disable_common(VFIOPCIDevice *vdev);
 
+/* Create new or reuse existing eventfd */
 static bool vfio_notifier_init(VFIOPCIDevice *vdev, EventNotifier *e,
                                const char *name, int nr, Error **errp)
 {
-    int ret = event_notifier_init(e, 0);
+    int fd, ret;
 
+    fd = vfio_cpr_load_vector_fd(vdev, name, nr);
+    if (fd >= 0) {
+        event_notifier_init_fd(e, fd);
+        return true;
+    }
+
+    ret = event_notifier_init(e, 0);
     if (ret) {
         error_setg_errno(errp, -ret, "vfio_notifier_init %s failed", name);
+        return false;
     }
-    return !ret;
+
+    fd = event_notifier_get_fd(e);
+    vfio_cpr_save_vector_fd(vdev, name, nr, fd);
+    return true;
 }
 
 static void vfio_notifier_cleanup(VFIOPCIDevice *vdev, EventNotifier *e,
                                   const char *name, int nr)
 {
+    vfio_cpr_delete_vector_fd(vdev, name, nr);
     event_notifier_cleanup(e);
 }
 
@@ -394,6 +408,14 @@ static void vfio_msi_interrupt(void *opaque)
     notify(&vdev->pdev, nr);
 }
 
+void vfio_pci_msi_set_handler(VFIOPCIDevice *vdev, int nr)
+{
+    VFIOMSIVector *vector = &vdev->msi_vectors[nr];
+    int fd = event_notifier_get_fd(&vector->interrupt);
+
+    qemu_set_fd_handler(fd, vfio_msi_interrupt, NULL, vector);
+}
+
 /*
  * Get MSI-X enabled, but no vector enabled, by setting vector 0 with an invalid
  * fd to kernel.
@@ -656,6 +678,15 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
 static int vfio_msix_vector_use(PCIDevice *pdev,
                                 unsigned int nr, MSIMessage msg)
 {
+    /*
+     * Ignore the callback from msix_set_vector_notifiers during resume.
+     * The necessary subset of these actions is called from
+     * vfio_cpr_claim_vectors during post load.
+     */
+    if (cpr_is_incoming()) {
+        return 0;
+    }
+
     return vfio_msix_vector_do_use(pdev, nr, &msg, vfio_msi_interrupt);
 }
 
@@ -686,6 +717,12 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr)
     }
 }
 
+void vfio_pci_msix_set_notifiers(VFIOPCIDevice *vdev)
+{
+    msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
+                              vfio_msix_vector_release, NULL);
+}
+
 void vfio_pci_prepare_kvm_msi_virq_batch(VFIOPCIDevice *vdev)
 {
     assert(!vdev->defer_kvm_irq_routing);
@@ -2965,6 +3002,11 @@ void vfio_pci_register_err_notifier(VFIOPCIDevice *vdev)
     fd = event_notifier_get_fd(&vdev->err_notifier);
     qemu_set_fd_handler(fd, vfio_err_notifier_handler, NULL, vdev);
 
+    /* Do not alter irq_signaling during vfio_realize for cpr */
+    if (cpr_is_incoming()) {
+        return;
+    }
+
     if (!vfio_device_irq_set_signaling(&vdev->vbasedev, VFIO_PCI_ERR_IRQ_INDEX, 0,
                                        VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err)) {
         error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
@@ -3032,6 +3074,12 @@ void vfio_pci_register_req_notifier(VFIOPCIDevice *vdev)
     fd = event_notifier_get_fd(&vdev->req_notifier);
     qemu_set_fd_handler(fd, vfio_req_notifier_handler, NULL, vdev);
 
+    /* Do not alter irq_signaling during vfio_realize for cpr */
+    if (cpr_is_incoming()) {
+        vdev->req_enabled = true;
+        return;
+    }
+
     if (!vfio_device_irq_set_signaling(&vdev->vbasedev, VFIO_PCI_REQ_IRQ_INDEX, 0,
                                        VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err)) {
         error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);