Finish cpr for vfio-pci MSI/MSI-X devices by preserving eventfd's and
vector state.
Signed-off-by: Steve Sistare <steven.sist...@oracle.com>
---
hw/vfio/pci.c | 103 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 102 insertions(+), 1 deletion(-)
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index acac8a7..abef9b2 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -49,17 +49,55 @@
static void vfio_disable_interrupts(VFIOPCIDevice *vdev);
static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
+#define EVENT_FD_NAME(vdev, name) \
+ g_strdup_printf("%s_%s", (vdev)->vbasedev.name, (name))
+
+static int save_event_fd(VFIOPCIDevice *vdev, const char *name, int nr,
+ EventNotifier *ev)
+{
+ int fd = event_notifier_get_fd(ev);
+
+ if (fd >= 0) {
+ g_autofree char *fdname = EVENT_FD_NAME(vdev, name);
+ int old_fd = cpr_find_fd(fdname, nr);
+ if (old_fd < 0) {
+ cpr_save_fd(fdname, nr, fd);
+ } else if (old_fd != fd) {
+ error_report("fd %s %d already saved with a different value %d",
+ name, fd, old_fd);
+ return 1;
+ }
+ }
+ return 0;
+}
+
+static int load_event_fd(VFIOPCIDevice *vdev, const char *name, int nr)
+{
+ g_autofree char *fdname = EVENT_FD_NAME(vdev, name);
+ int fd = cpr_find_fd(fdname, nr);
+ return fd;
+}
+
+static void delete_event_fd(VFIOPCIDevice *vdev, const char *name, int nr)
+{
+ g_autofree char *fdname = EVENT_FD_NAME(vdev, name);
+ cpr_delete_fd(fdname, nr);
+}
+
/* Create new or reuse existing eventfd */
static int vfio_notifier_init(VFIOPCIDevice *vdev, EventNotifier *e,
const char *name, int nr)
{
- int fd = -1; /* placeholder until a subsequent patch */
int ret = 0;
+ int fd = load_event_fd(vdev, name, nr);
if (fd >= 0) {
event_notifier_init_fd(e, fd);
} else {
ret = event_notifier_init(e, 0);
+ if (!ret) {
+ save_event_fd(vdev, name, nr, e);
+ }
}
return ret;
}
@@ -67,6 +105,7 @@ static int vfio_notifier_init(VFIOPCIDevice *vdev,
EventNotifier *e,
static void vfio_notifier_cleanup(VFIOPCIDevice *vdev, EventNotifier *e,
const char *name, int nr)
{
+ delete_event_fd(vdev, name, nr);
event_notifier_cleanup(e);
}
@@ -2736,6 +2775,11 @@ static void vfio_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 (vdev->pdev.reused) {
+ return;
+ }
+
if (vfio_set_irq_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);
@@ -2801,6 +2845,12 @@ static void vfio_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 (vdev->pdev.reused) {
+ vdev->req_enabled = true;
+ return;
+ }
+
if (vfio_set_irq_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);
@@ -3330,6 +3380,40 @@ static void vfio_merge_config(VFIOPCIDevice *vdev)
}
}
+static void vfio_claim_vectors(VFIOPCIDevice *vdev, int nr_vectors, bool msix)
+{
+ int i, fd;
+ bool pending = false;
+ PCIDevice *pdev = &vdev->pdev;
+
+ vdev->nr_vectors = nr_vectors;
+ vdev->msi_vectors = g_new0(VFIOMSIVector, nr_vectors);
+ vdev->interrupt = msix ? VFIO_INT_MSIX : VFIO_INT_MSI;
+
+ for (i = 0; i < nr_vectors; i++) {
+ VFIOMSIVector *vector = &vdev->msi_vectors[i];
+
+ fd = load_event_fd(vdev, "interrupt", i);
+ if (fd >= 0) {
+ vfio_vector_init(vdev, i);
+ qemu_set_fd_handler(fd, vfio_msi_interrupt, NULL, vector);
+ }
+
+ if (load_event_fd(vdev, "kvm_interrupt", i) >= 0) {
+ vfio_add_kvm_msi_virq(vdev, vector, i, msix);
+ }
+
+ if (msix && msix_is_pending(pdev, i) && msix_is_masked(pdev, i)) {
+ set_bit(i, vdev->msix->pending);
+ pending = true;
+ }
+ }
+
+ if (msix) {
+ memory_region_set_enabled(&pdev->msix_pba_mmio, pending);
+ }
+}
+
/*
* The kernel may change non-emulated config bits. Exclude them from the
* changed-bits check in get_pci_config_device.
@@ -3352,9 +3436,24 @@ static int vfio_pci_post_load(void *opaque, int
version_id)
{
VFIOPCIDevice *vdev = opaque;
PCIDevice *pdev = &vdev->pdev;
+ int nr_vectors;
vfio_merge_config(vdev);
+ if (msix_enabled(pdev)) {
+ nr_vectors = vdev->msix->entries;
+ vfio_claim_vectors(vdev, nr_vectors, true);
+ msix_init_vector_notifiers(pdev, vfio_msix_vector_use,
+ vfio_msix_vector_release, NULL);
+
+ } else if (msi_enabled(pdev)) {
+ nr_vectors = msi_nr_vectors_allocated(pdev);
+ 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 */
+ }
+
pdev->reused = false;
return 0;
@@ -3374,6 +3473,8 @@ static const VMStateDescription vfio_pci_vmstate = {
.post_load = vfio_pci_post_load,
.needed = vfio_pci_needed,
.fields = (VMStateField[]) {
+ VMSTATE_PCI_DEVICE(pdev, VFIOPCIDevice),
+ VMSTATE_MSIX_TEST(pdev, VFIOPCIDevice, vfio_msix_present),
VMSTATE_END_OF_LIST()
}
};
--
1.8.3.1
