From dc580d51f7dd3e02134957be2b771636ac59e868 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Sat, 26 Mar 2022 14:02:26 +0800 Subject: [PATCH] vfio: defer to commit kvm irq routing when enable msi/msix In migration resume phase, all unmasked msix vectors need to be setup when loading 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 are 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 committing once outside the loop. The routes are 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 optimization can be applied to msi type too. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20220326060226.1892-6-longpeng2@huawei.com Signed-off-by: Alex Williamson --- hw/vfio/pci.c | 130 +++++++++++++++++++++++++++++++++++++------------- hw/vfio/pci.h | 2 + 2 files changed, 99 insertions(+), 33 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 8bc36f081a..ef9d7bf326 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -45,6 +45,9 @@ #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" +/* Protected by BQL */ +static KVMRouteChange vfio_route_change; + 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); @@ -413,33 +416,36 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) static void vfio_add_kvm_msi_virq(VFIOPCIDevice *vdev, VFIOMSIVector *vector, int vector_n, bool msix) { - KVMRouteChange c; - int virq; - if ((msix && vdev->no_kvm_msix) || (!msix && vdev->no_kvm_msi)) { return; } - if (event_notifier_init(&vector->kvm_interrupt, 0)) { + vector->virq = kvm_irqchip_add_msi_route(&vfio_route_change, + vector_n, &vdev->pdev); +} + +static void vfio_connect_kvm_msi_virq(VFIOMSIVector *vector) +{ + if (vector->virq < 0) { return; } - c = kvm_irqchip_begin_route_changes(kvm_state); - virq = kvm_irqchip_add_msi_route(&c, vector_n, &vdev->pdev); - if (virq < 0) { - event_notifier_cleanup(&vector->kvm_interrupt); - return; + if (event_notifier_init(&vector->kvm_interrupt, 0)) { + goto fail_notifier; } - kvm_irqchip_commit_route_changes(&c); if (kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &vector->kvm_interrupt, - NULL, virq) < 0) { - kvm_irqchip_release_virq(kvm_state, virq); - event_notifier_cleanup(&vector->kvm_interrupt); - return; + NULL, vector->virq) < 0) { + goto fail_kvm; } - vector->virq = virq; + return; + +fail_kvm: + event_notifier_cleanup(&vector->kvm_interrupt); +fail_notifier: + kvm_irqchip_release_virq(kvm_state, vector->virq); + vector->virq = -1; } static void vfio_remove_kvm_msi_virq(VFIOMSIVector *vector) @@ -494,7 +500,14 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, } } else { if (msg) { - vfio_add_kvm_msi_virq(vdev, vector, nr, true); + if (vdev->defer_kvm_irq_routing) { + vfio_add_kvm_msi_virq(vdev, vector, nr, true); + } else { + vfio_route_change = kvm_irqchip_begin_route_changes(kvm_state); + vfio_add_kvm_msi_virq(vdev, vector, nr, true); + kvm_irqchip_commit_route_changes(&vfio_route_change); + vfio_connect_kvm_msi_virq(vector); + } } } @@ -504,11 +517,13 @@ 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; @@ -570,6 +585,27 @@ static void vfio_msix_vector_release(PCIDevice *pdev, unsigned int nr) } } +static void vfio_prepare_kvm_msi_virq_batch(VFIOPCIDevice *vdev) +{ + assert(!vdev->defer_kvm_irq_routing); + vdev->defer_kvm_irq_routing = true; + vfio_route_change = kvm_irqchip_begin_route_changes(kvm_state); +} + +static void vfio_commit_kvm_msi_virq_batch(VFIOPCIDevice *vdev) +{ + int i; + + assert(vdev->defer_kvm_irq_routing); + vdev->defer_kvm_irq_routing = false; + + kvm_irqchip_commit_route_changes(&vfio_route_change); + + for (i = 0; i < vdev->nr_vectors; i++) { + vfio_connect_kvm_msi_virq(&vdev->msi_vectors[i]); + } +} + static void vfio_msix_enable(VFIOPCIDevice *vdev) { vfio_disable_interrupts(vdev); @@ -579,26 +615,45 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev) vdev->interrupt = VFIO_INT_MSIX; /* - * Some communication channels between VF & PF or PF & fw rely on the - * physical state of the device and expect that enabling MSI-X from the - * guest enables the same on the host. When our guest is Linux, the - * guest driver call to pci_enable_msix() sets the enabling bit in the - * MSI-X capability, but leaves the vector table masked. We therefore - * can't rely on a vector_use callback (from request_irq() in the guest) - * to switch the physical device into MSI-X mode because that may come a - * long time after pci_enable_msix(). This code enables vector 0 with - * triggering to userspace, then immediately release the vector, leaving - * the physical device with no vectors enabled, but MSI-X enabled, just - * like the guest view. + * Setting vector notifiers triggers synchronous vector-use + * callbacks for each active vector. Deferring to commit the KVM + * routes once rather than per vector provides a substantial + * performance improvement. */ - vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL); - vfio_msix_vector_release(&vdev->pdev, 0); + vfio_prepare_kvm_msi_virq_batch(vdev); if (msix_set_vector_notifiers(&vdev->pdev, vfio_msix_vector_use, vfio_msix_vector_release, NULL)) { error_report("vfio: msix_set_vector_notifiers failed"); } + vfio_commit_kvm_msi_virq_batch(vdev); + + if (vdev->nr_vectors) { + int ret; + + ret = vfio_enable_vectors(vdev, true); + if (ret) { + error_report("vfio: failed to enable vectors, %d", ret); + } + } else { + /* + * Some communication channels between VF & PF or PF & fw rely on the + * physical state of the device and expect that enabling MSI-X from the + * guest enables the same on the host. When our guest is Linux, the + * guest driver call to pci_enable_msix() sets the enabling bit in the + * MSI-X capability, but leaves the vector table masked. We therefore + * can't rely on a vector_use callback (from request_irq() in the guest) + * to switch the physical device into MSI-X mode because that may come a + * long time after pci_enable_msix(). This code enables vector 0 with + * triggering to userspace, then immediately release the vector, leaving + * the physical device with no vectors enabled, but MSI-X enabled, just + * like the guest view. + */ + vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL); + vfio_msix_vector_release(&vdev->pdev, 0); + } + trace_vfio_msix_enable(vdev->vbasedev.name); } @@ -608,6 +663,13 @@ static void vfio_msi_enable(VFIOPCIDevice *vdev) vfio_disable_interrupts(vdev); + /* + * Setting vector notifiers needs to enable route for each vector. + * Deferring to commit the KVM routes once rather than per vector + * provides a substantial performance improvement. + */ + vfio_prepare_kvm_msi_virq_batch(vdev); + vdev->nr_vectors = msi_nr_vectors_allocated(&vdev->pdev); retry: vdev->msi_vectors = g_new0(VFIOMSIVector, vdev->nr_vectors); @@ -633,6 +695,8 @@ retry: vfio_add_kvm_msi_virq(vdev, vector, i, false); } + vfio_commit_kvm_msi_virq_batch(vdev); + /* Set interrupt type prior to possible interrupts */ vdev->interrupt = VFIO_INT_MSI; diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index 64777516d1..7c236a52f4 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -19,6 +19,7 @@ #include "qemu/queue.h" #include "qemu/timer.h" #include "qom/object.h" +#include "sysemu/kvm.h" #define PCI_ANY_ID (~0) @@ -171,6 +172,7 @@ struct VFIOPCIDevice { bool no_kvm_ioeventfd; bool no_vfio_ioeventfd; bool enable_ramfb; + bool defer_kvm_irq_routing; VFIODisplay *dpy; Notifier irqchip_change_notifier; };