@@ -512,11 +512,13 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
* increase them as needed.
*/
if (vdev->nr_vectors < nr + 1) {
- vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX);
vdev->nr_vectors = nr + 1;
- ret = vfio_enable_vectors(vdev, true);
- if (ret) {
- error_report("vfio: failed to enable vectors, %d", ret);
+ if (!vdev->defer_kvm_irq_routing) {
+ vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX);
+ ret = vfio_enable_vectors(vdev, true);
+ if (ret) {
+ error_report("vfio: failed to enable vectors, %d", ret);
+ }
}
} else {
Error *err = NULL;
@@ -608,6 +610,9 @@ static void vfio_commit_kvm_msi_virq(VFIOPCIDevice *vdev)
static void vfio_msix_enable(VFIOPCIDevice *vdev)
{
+ PCIDevice *pdev = &vdev->pdev;
+ int ret;
+
vfio_disable_interrupts(vdev);
vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->msix->entries);
@@ -630,11 +635,22 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev)
vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL);
vfio_msix_vector_release(&vdev->pdev, 0);
- if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
- vfio_msix_vector_release, NULL)) {
+ vdev->defer_kvm_irq_routing = true;
+
+ ret = msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use,
+ vfio_msix_vector_release, NULL);
+ if (ret < 0) {
error_report("vfio: msix_set_vector_notifiers failed");
+ } else if (!pdev->msix_function_masked) {
+ vfio_commit_kvm_msi_virq(vdev);
+ vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX);
+ ret = vfio_enable_vectors(vdev, true);
+ if (ret) {
+ error_report("vfio: failed to enable vectors, %d", ret);
+ }
}
+ vdev->defer_kvm_irq_routing = false;
trace_vfio_msix_enable(vdev->vbasedev.name);
}
@@ -643,6 +659,7 @@ static void vfio_msi_enable(VFIOPCIDevice *vdev)
int ret, i;
vfio_disable_interrupts(vdev);
+ vdev->defer_kvm_irq_routing = true;
vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev);
retry:
@@ -669,6 +686,8 @@ retry:
vfio_add_kvm_msi_virq(vdev, vector, i, false);
}
+ vfio_commit_kvm_msi_virq(vdev);
+
/* Set interrupt type prior to possible interrupts */
vdev->interrupt = VFIO_INT_MSI;
@@ -695,9 +714,11 @@ retry:
*/
error_report("vfio: Error: Failed to enable MSI");
+ vdev->defer_kvm_irq_routing = false;
return;
}
+ vdev->defer_kvm_irq_routing = false;
trace_vfio_msi_enable(vdev->vbasedev.name, vdev->nr_vectors);
}
In migration resume phase, all unmasked msix vectors need to be setup when load the VF state. However, the setup operation would take longer if the VM has more VFs and each VF has more unmasked vectors. The hot spot is kvm_irqchip_commit_routes, it'll scan and update all irqfds that already assigned each invocation, so more vectors means need more time to process them. vfio_pci_load_config vfio_msix_enable msix_set_vector_notifiers for (vector = 0; vector < dev->msix_entries_nr; vector++) { vfio_msix_vector_do_use vfio_add_kvm_msi_virq kvm_irqchip_commit_routes <-- expensive } We can reduce the cost by only commit once outside the loop. The routes is cached in kvm_state, we commit them first and then bind irqfd for each vector. The test VM has 128 vcpus and 8 VF (each one has 65 vectors), we measure the cost of the vfio_msix_enable for each VF, and we can see 90+% costs can be reduce. VF Count of irqfds[*] Original With this patch 1st 65 8 2 2nd 130 15 2 3rd 195 22 2 4th 260 24 3 5th 325 36 2 6th 390 44 3 7th 455 51 3 8th 520 58 4 Total 258ms 21ms [*] Count of irqfds How many irqfds that already assigned and need to process in this round. The optimition can be applied to msi type too. Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com> --- hw/vfio/pci.c | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-)