[PATCH V6 21/27] vfio-pci: cpr part 3 (intx)

[Steve Sistare <steven.sistare@oracle.com>]

Preserve vfio INTX state across cpr restart.  Preserve VFIOINTx fields as
follows:
  pin : Recover this from the vfio config in kernel space
  interrupt : Preserve its eventfd descriptor across exec.
  unmask : Ditto
  route.irq : This could perhaps be recovered in vfio_pci_post_load by
    calling pci_device_route_intx_to_irq(pin), whose implementation reads
    config space for a bridge device such as ich9.  However, there is no
    guarantee that the bridge vmstate is read before vfio vmstate.  Rather
    than fiddling with MigrationPriority for vmstate handlers, explicitly
    save route.irq in vfio vmstate.
  pending : save in vfio vmstate.
  mmap_timeout, mmap_timer : Re-initialize
  bool kvm_accel : Re-initialize

In vfio_realize, defer calling vfio_intx_enable until the vmstate
is available, in vfio_pci_post_load.  Modify vfio_intx_enable and
vfio_intx_kvm_enable to skip vfio initialization, but still perform
kvm initialization.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 hw/vfio/pci.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 83 insertions(+), 11 deletions(-)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 1cee52a..7e59f4f 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -145,14 +145,45 @@ static void vfio_intx_eoi(VFIODevice *vbasedev)
     vfio_unmask_single_irqindex(vbasedev, VFIO_PCI_INTX_IRQ_INDEX);
 }
 
+#ifdef CONFIG_KVM
+static bool vfio_no_kvm_intx(VFIOPCIDevice *vdev)
+{
+    return vdev->no_kvm_intx || !kvm_irqfds_enabled() ||
+           vdev->intx.route.mode != PCI_INTX_ENABLED ||
+           !kvm_resamplefds_enabled();
+}
+#endif
+
+static void vfio_intx_reenable_kvm(VFIOPCIDevice *vdev, Error **errp)
+{
+#ifdef CONFIG_KVM
+    if (vfio_no_kvm_intx(vdev)) {
+        return;
+    }
+
+    if (vfio_named_notifier_init(vdev, &vdev->intx.unmask, "intx-unmask", 0)) {
+        error_setg(errp, "vfio_named_notifier_init failed");
+        return;
+    }
+
+    if (kvm_irqchip_add_irqfd_notifier_gsi(kvm_state,
+                                           &vdev->intx.interrupt,
+                                           &vdev->intx.unmask,
+                                           vdev->intx.route.irq)) {
+        error_setg_errno(errp, errno, "failed to setup resample irqfd");
+        return;
+    }
+
+    vdev->intx.kvm_accel = true;
+#endif
+}
+
 static void vfio_intx_enable_kvm(VFIOPCIDevice *vdev, Error **errp)
 {
 #ifdef CONFIG_KVM
     int irq_fd = event_notifier_get_fd(&vdev->intx.interrupt);
 
-    if (vdev->no_kvm_intx || !kvm_irqfds_enabled() ||
-        vdev->intx.route.mode != PCI_INTX_ENABLED ||
-        !kvm_resamplefds_enabled()) {
+    if (vfio_no_kvm_intx(vdev)) {
         return;
     }
 
@@ -300,7 +331,9 @@ static int vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp)
         return 0;
     }
 
-    vfio_disable_interrupts(vdev);
+    if (!vdev->pdev.reused) {
+        vfio_disable_interrupts(vdev);
+    }
 
     vdev->intx.pin = pin - 1; /* Pin A (1) -> irq[0] */
     pci_config_set_interrupt_pin(vdev->pdev.config, pin);
@@ -316,7 +349,8 @@ static int vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp)
     }
 #endif
 
-    ret = event_notifier_init(&vdev->intx.interrupt, 0);
+    ret = vfio_named_notifier_init(vdev, &vdev->intx.interrupt,
+                                   "intx-interrupt", 0);
     if (ret) {
         error_setg_errno(errp, -ret, "event_notifier_init failed");
         return ret;
@@ -324,6 +358,11 @@ static int vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp)
     fd = event_notifier_get_fd(&vdev->intx.interrupt);
     qemu_set_fd_handler(fd, vfio_intx_interrupt, NULL, vdev);
 
+    if (vdev->pdev.reused) {
+        vfio_intx_reenable_kvm(vdev, &err);
+        goto finish;
+    }
+
     if (vfio_set_irq_signaling(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX, 0,
                                VFIO_IRQ_SET_ACTION_TRIGGER, fd, errp)) {
         qemu_set_fd_handler(fd, NULL, NULL, vdev);
@@ -336,6 +375,7 @@ static int vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp)
         warn_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name);
     }
 
+finish:
     vdev->interrupt = VFIO_INT_INTx;
 
     trace_vfio_intx_enable(vdev->vbasedev.name);
@@ -3092,9 +3132,13 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
                                              vfio_intx_routing_notifier);
         vdev->irqchip_change_notifier.notify = vfio_irqchip_change;
         kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier);
-        ret = vfio_intx_enable(vdev, errp);
-        if (ret) {
-            goto out_deregister;
+
+        /* Wait until cpr-load reads intx routing data to enable */
+        if (!pdev->reused) {
+            ret = vfio_intx_enable(vdev, errp);
+            if (ret) {
+                goto out_deregister;
+            }
         }
     }
 
@@ -3338,7 +3382,8 @@ static int vfio_pci_pre_save(void *opaque)
     int i;
 
     if (vfio_pci_read_config(pdev, PCI_INTERRUPT_PIN, 1)) {
-        assert(0);      /* completed in a subsequent patch */
+        save_event_fd(vdev, "intx-interrupt", 0, &vdev->intx.interrupt);
+        save_event_fd(vdev, "intx-unmask", 0, &vdev->intx.unmask);
     }
 
     for (i = 0; i < vdev->nr_vectors; i++) {
@@ -3395,6 +3440,7 @@ static int vfio_pci_post_load(void *opaque, int version_id)
     VFIOPCIDevice *vdev = opaque;
     PCIDevice *pdev = &vdev->pdev;
     int nr_vectors;
+    int ret = 0;
 
     vfio_merge_config(vdev);
 
@@ -3409,12 +3455,37 @@ static int vfio_pci_post_load(void *opaque, int version_id)
         vfio_claim_vectors(vdev, nr_vectors, false);
 
     } else if (vfio_pci_read_config(pdev, PCI_INTERRUPT_PIN, 1)) {
-        assert(0);      /* completed in a subsequent patch */
+        Error *err = 0;
+        ret = vfio_intx_enable(vdev, &err);
+        if (ret) {
+            error_report_err(err);
+        }
     }
 
     pdev->reused = false;
 
-    return 0;
+    return ret;
+}
+
+static const VMStateDescription vfio_intx_vmstate = {
+    .name = "vfio-intx",
+    .unmigratable = 1,
+    .version_id = 0,
+    .minimum_version_id = 0,
+    .fields = (VMStateField[]) {
+        VMSTATE_BOOL(pending, VFIOINTx),
+        VMSTATE_UINT32(route.mode, VFIOINTx),
+        VMSTATE_INT32(route.irq, VFIOINTx),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+#define VMSTATE_VFIO_INTX(_field, _state) {                         \
+    .name       = (stringify(_field)),                              \
+    .size       = sizeof(VFIOINTx),                                 \
+    .vmsd       = &vfio_intx_vmstate,                               \
+    .flags      = VMS_STRUCT,                                       \
+    .offset     = vmstate_offset_value(_state, _field, VFIOINTx),   \
 }
 
 static bool vfio_pci_needed(void *opaque)
@@ -3433,6 +3504,7 @@ static const VMStateDescription vfio_pci_vmstate = {
     .fields = (VMStateField[]) {
         VMSTATE_PCI_DEVICE(pdev, VFIOPCIDevice),
         VMSTATE_MSIX_TEST(pdev, VFIOPCIDevice, vfio_msix_present),
+        VMSTATE_VFIO_INTX(intx, VFIOPCIDevice),
         VMSTATE_END_OF_LIST()
     }
 };
-- 
1.8.3.1