diff options
Diffstat (limited to 'hw/vfio/pci.c')
| -rw-r--r-- | hw/vfio/pci.c | 182 |
1 files changed, 171 insertions, 11 deletions
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index fa25bde..4fa692c 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" @@ -48,8 +49,6 @@ #include "vfio-migration-internal.h" #include "vfio-helpers.h" -#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" - /* Protected by BQL */ static KVMRouteChange vfio_route_change; @@ -57,20 +56,33 @@ 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); } @@ -196,6 +208,36 @@ fail: #endif } +static bool vfio_cpr_intx_enable_kvm(VFIOPCIDevice *vdev, Error **errp) +{ +#ifdef CONFIG_KVM + if (vdev->no_kvm_intx || !kvm_irqfds_enabled() || + vdev->intx.route.mode != PCI_INTX_ENABLED || + !kvm_resamplefds_enabled()) { + return true; + } + + if (!vfio_notifier_init(vdev, &vdev->intx.unmask, "intx-unmask", 0, errp)) { + return false; + } + + 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"); + vfio_notifier_cleanup(vdev, &vdev->intx.unmask, "intx-unmask", 0); + return false; + } + + vdev->intx.kvm_accel = true; + trace_vfio_intx_enable_kvm(vdev->vbasedev.name); + return true; +#else + return true; +#endif +} + static void vfio_intx_disable_kvm(VFIOPCIDevice *vdev) { #ifdef CONFIG_KVM @@ -291,7 +333,13 @@ static bool vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp) return true; } - vfio_disable_interrupts(vdev); + /* + * Do not alter interrupt state during vfio_realize and cpr load. + * The incoming state is cleared thereafter. + */ + if (!cpr_is_incoming()) { + vfio_disable_interrupts(vdev); + } vdev->intx.pin = pin - 1; /* Pin A (1) -> irq[0] */ pci_config_set_interrupt_pin(vdev->pdev.config, pin); @@ -314,6 +362,14 @@ static bool 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 (cpr_is_incoming()) { + if (!vfio_cpr_intx_enable_kvm(vdev, &err)) { + warn_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); + } + goto skip_signaling; + } + if (!vfio_device_irq_set_signaling(&vdev->vbasedev, VFIO_PCI_INTX_IRQ_INDEX, 0, VFIO_IRQ_SET_ACTION_TRIGGER, fd, errp)) { qemu_set_fd_handler(fd, NULL, NULL, vdev); @@ -325,6 +381,7 @@ static bool vfio_intx_enable(VFIOPCIDevice *vdev, Error **errp) warn_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); } +skip_signaling: vdev->interrupt = VFIO_INT_INTx; trace_vfio_intx_enable(vdev->vbasedev.name); @@ -394,6 +451,14 @@ 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 +721,15 @@ 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 +760,12 @@ 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); @@ -2744,6 +2824,20 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) return ret; } +void vfio_sub_page_bar_update_mappings(VFIOPCIDevice *vdev) +{ + PCIDevice *pdev = &vdev->pdev; + int page_size = qemu_real_host_page_size(); + int bar; + + for (bar = 0; bar < PCI_ROM_SLOT; bar++) { + PCIIORegion *r = &pdev->io_regions[bar]; + if (r->addr != PCI_BAR_UNMAPPED && r->size > 0 && r->size < page_size) { + vfio_sub_page_bar_update_mapping(pdev, bar); + } + } +} + static VFIODeviceOps vfio_pci_ops = { .vfio_compute_needs_reset = vfio_pci_compute_needs_reset, .vfio_hot_reset_multi = vfio_pci_hot_reset_multi, @@ -2811,10 +2905,6 @@ bool vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp) "vfio-vga-io@0x3c0", QEMU_PCI_VGA_IO_HI_SIZE); - pci_register_vga(&vdev->pdev, &vdev->vga->region[QEMU_PCI_VGA_MEM].mem, - &vdev->vga->region[QEMU_PCI_VGA_IO_LO].mem, - &vdev->vga->region[QEMU_PCI_VGA_IO_HI].mem); - return true; } @@ -2914,7 +3004,7 @@ void vfio_pci_put_device(VFIOPCIDevice *vdev) vfio_device_detach(&vdev->vbasedev); - g_free(vdev->vbasedev.name); + vfio_device_free_name(&vdev->vbasedev); g_free(vdev->msix); } @@ -2965,6 +3055,11 @@ 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 +3127,12 @@ 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); @@ -3061,6 +3162,15 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev) vdev->req_enabled = false; } +void vfio_pci_config_register_vga(VFIOPCIDevice *vdev) +{ + assert(vdev->vga != NULL); + + pci_register_vga(&vdev->pdev, &vdev->vga->region[QEMU_PCI_VGA_MEM].mem, + &vdev->vga->region[QEMU_PCI_VGA_IO_LO].mem, + &vdev->vga->region[QEMU_PCI_VGA_IO_HI].mem); +} + bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp) { PCIDevice *pdev = &vdev->pdev; @@ -3135,6 +3245,23 @@ bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp) vdev->sub_device_id); } + /* + * Class code is a 24-bit value at config space 0x09. Allow overriding it + * with any 24-bit value. + */ + if (vdev->class_code != PCI_ANY_ID) { + if (vdev->class_code > 0xffffff) { + error_setg(errp, "invalid PCI class code provided"); + return false; + } + /* Higher 24 bits of PCI_CLASS_REVISION are class code */ + vfio_add_emulated_long(vdev, PCI_CLASS_REVISION, + vdev->class_code << 8, ~0xff); + trace_vfio_pci_emulated_class_code(vbasedev->name, vdev->class_code); + } else { + vdev->class_code = pci_get_long(pdev->config + PCI_CLASS_REVISION) >> 8; + } + /* QEMU can change multi-function devices to single function, or reverse */ vdev->emulated_config_bits[PCI_HEADER_TYPE] = PCI_HEADER_TYPE_MULTI_FUNCTION; @@ -3164,6 +3291,10 @@ bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp) vfio_bars_register(vdev); + if (vdev->vga && vfio_is_vga(vdev)) { + vfio_pci_config_register_vga(vdev); + } + return true; } @@ -3189,7 +3320,13 @@ bool vfio_pci_interrupt_setup(VFIOPCIDevice *vdev, Error **errp) vfio_intx_routing_notifier); vdev->irqchip_change_notifier.notify = vfio_irqchip_change; kvm_irqchip_add_change_notifier(&vdev->irqchip_change_notifier); - if (!vfio_intx_enable(vdev, errp)) { + + /* + * During CPR, do not call vfio_intx_enable at this time. Instead, + * call it from vfio_pci_post_load after the intx routing data has + * been loaded from vmstate. + */ + if (!cpr_is_incoming() && !vfio_intx_enable(vdev, errp)) { timer_free(vdev->intx.mmap_timer); pci_device_set_intx_routing_notifier(&vdev->pdev, NULL); kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier); @@ -3524,6 +3661,11 @@ static const Property vfio_pci_dev_properties[] = { vbasedev.migration_multifd_transfer, vfio_pci_migration_multifd_transfer_prop, OnOffAuto, .set_default = true, .defval.i = ON_OFF_AUTO_AUTO), + DEFINE_PROP_ON_OFF_AUTO("x-migration-load-config-after-iter", VFIOPCIDevice, + vbasedev.migration_load_config_after_iter, + ON_OFF_AUTO_AUTO), + DEFINE_PROP_SIZE("x-migration-max-queued-buffers-size", VFIOPCIDevice, + vbasedev.migration_max_queued_buffers_size, UINT64_MAX), DEFINE_PROP_BOOL("migration-events", VFIOPCIDevice, vbasedev.migration_events, false), DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false), @@ -3544,6 +3686,8 @@ static const Property vfio_pci_dev_properties[] = { sub_vendor_id, PCI_ANY_ID), DEFINE_PROP_UINT32("x-pci-sub-device-id", VFIOPCIDevice, sub_device_id, PCI_ANY_ID), + DEFINE_PROP_UINT32("x-pci-class-code", VFIOPCIDevice, + class_code, PCI_ANY_ID), DEFINE_PROP_UINT32("x-igd-gms", VFIOPCIDevice, igd_gms, 0), DEFINE_PROP_UNSIGNED_NODEFAULT("x-nv-gpudirect-clique", VFIOPCIDevice, nv_gpudirect_clique, @@ -3698,6 +3842,20 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, const void *data) "x-migration-multifd-transfer", "Transfer this device state via " "multifd channels when live migrating it"); + object_class_property_set_description(klass, /* 10.1 */ + "x-migration-load-config-after-iter", + "Start the config load only after " + "all iterables were loaded (during " + "non-iterables loading phase) when " + "doing live migration of device state " + "via multifd channels"); + object_class_property_set_description(klass, /* 10.1 */ + "x-migration-max-queued-buffers-size", + "Maximum size of in-flight VFIO " + "device state buffers queued at the " + "destination when doing live " + "migration of device state via " + "multifd channels"); } static const TypeInfo vfio_pci_dev_info = { @@ -3710,6 +3868,8 @@ static const TypeInfo vfio_pci_dev_info = { static const Property vfio_pci_dev_nohotplug_properties[] = { DEFINE_PROP_BOOL("ramfb", VFIOPCIDevice, enable_ramfb, false), + DEFINE_PROP_BOOL("use-legacy-x86-rom", VFIOPCIDevice, + use_legacy_x86_rom, false), DEFINE_PROP_ON_OFF_AUTO("x-ramfb-migrate", VFIOPCIDevice, ramfb_migrate, ON_OFF_AUTO_AUTO), }; |