Register a notifier and attempt to unplug when a request for the device is received. Signed-off-by: Alex Williamson <alex.williamson@xxxxxxxxxx> --- This is the matching QEMU support for the proposed vfio device request interface (https://lkml.org/lkml/2015/2/4/425). By default QEMU would be cooperative, registering for and attempting to unplug a device when requested. That of course doesn't mean that the guest is necessarily cooperative by way of supporting device hot-unplug. The vfio kernel is expected to make repeated attempts to request the device, so we don't do any sort of tracking ourselves. This conveniently allows for guests that may not handle a hotplug while the device is in use or may not be in a state to acknowledge the request. hw/vfio/pci.c | 100 ++++++++++++++++++++++++++++++++++++++++++++ linux-headers/linux/vfio.h | 1 2 files changed, 101 insertions(+) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 29caabc..1eb4795 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -153,13 +153,17 @@ typedef struct VFIOPCIDevice { VFIOVGA vga; /* 0xa0000, 0x3b0, 0x3c0 */ PCIHostDeviceAddress host; EventNotifier err_notifier; + EventNotifier req_notifier; uint32_t features; #define VFIO_FEATURE_ENABLE_VGA_BIT 0 #define VFIO_FEATURE_ENABLE_VGA (1 << VFIO_FEATURE_ENABLE_VGA_BIT) +#define VFIO_FEATURE_ENABLE_REQ_BIT 1 +#define VFIO_FEATURE_ENABLE_REQ (1 << VFIO_FEATURE_ENABLE_REQ_BIT) int32_t bootindex; uint8_t pm_cap; bool has_vga; bool pci_aer; + bool req_enabled; bool has_flr; bool has_pm_reset; bool rom_read_failed; @@ -3042,6 +3046,7 @@ static int vfio_populate_device(VFIODevice *vbasedev) vdev->has_vga = true; } + irq_info.index = VFIO_PCI_ERR_IRQ_INDEX; ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info); @@ -3177,6 +3182,97 @@ static void vfio_unregister_err_notifier(VFIOPCIDevice *vdev) event_notifier_cleanup(&vdev->err_notifier); } +static void vfio_req_notifier_handler(void *opaque) +{ + VFIOPCIDevice *vdev = opaque; + + if (!event_notifier_test_and_clear(&vdev->req_notifier)) { + return; + } + + qdev_unplug(&vdev->pdev.qdev, NULL); +} + +static void vfio_register_req_notifier(VFIOPCIDevice *vdev) +{ + struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info), + .index = VFIO_PCI_REQ_IRQ_INDEX }; + int argsz; + struct vfio_irq_set *irq_set; + int32_t *pfd; + + if (!(vdev->features & VFIO_FEATURE_ENABLE_REQ)) { + return; + } + + if (ioctl(vdev->vbasedev.fd, + VFIO_DEVICE_GET_IRQ_INFO, &irq_info) < 0 || irq_info.count < 1) { + return; + } + + if (event_notifier_init(&vdev->req_notifier, 0)) { + error_report("vfio: Unable to init event notifier for device request"); + return; + } + + argsz = sizeof(*irq_set) + sizeof(*pfd); + + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_PCI_REQ_IRQ_INDEX; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + + *pfd = event_notifier_get_fd(&vdev->req_notifier); + qemu_set_fd_handler(*pfd, vfio_req_notifier_handler, NULL, vdev); + + if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + error_report("vfio: Failed to set up device request notification"); + qemu_set_fd_handler(*pfd, NULL, NULL, vdev); + event_notifier_cleanup(&vdev->req_notifier); + } else { + vdev->req_enabled = true; + } + + g_free(irq_set); +} + +static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev) +{ + int argsz; + struct vfio_irq_set *irq_set; + int32_t *pfd; + + if (!vdev->req_enabled) { + return; + } + + argsz = sizeof(*irq_set) + sizeof(*pfd); + + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_PCI_REQ_IRQ_INDEX; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + *pfd = -1; + + if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + error_report("vfio: Failed to de-assign device request fd: %m"); + } + g_free(irq_set); + qemu_set_fd_handler(event_notifier_get_fd(&vdev->req_notifier), + NULL, NULL, vdev); + event_notifier_cleanup(&vdev->req_notifier); + + vdev->req_enabled = false; +} + static int vfio_initfn(PCIDevice *pdev) { VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); @@ -3319,6 +3415,7 @@ static int vfio_initfn(PCIDevice *pdev) } vfio_register_err_notifier(vdev); + vfio_register_req_notifier(vdev); return 0; @@ -3338,6 +3435,7 @@ static void vfio_exitfn(PCIDevice *pdev) VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev); VFIOGroup *group = vdev->vbasedev.group; + vfio_unregister_req_notifier(vdev); vfio_unregister_err_notifier(vdev); pci_device_set_intx_routing_notifier(&vdev->pdev, NULL); vfio_disable_interrupts(vdev); @@ -3400,6 +3498,8 @@ static Property vfio_pci_dev_properties[] = { intx.mmap_timeout, 1100), DEFINE_PROP_BIT("x-vga", VFIOPCIDevice, features, VFIO_FEATURE_ENABLE_VGA_BIT, false), + DEFINE_PROP_BIT("x-req", VFIOPCIDevice, features, + VFIO_FEATURE_ENABLE_REQ_BIT, true), DEFINE_PROP_INT32("bootindex", VFIOPCIDevice, bootindex, -1), /* * TODO - support passed fds... is this necessary? diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index 0f21aa6..95ba870 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -333,6 +333,7 @@ enum { VFIO_PCI_MSI_IRQ_INDEX, VFIO_PCI_MSIX_IRQ_INDEX, VFIO_PCI_ERR_IRQ_INDEX, + VFIO_PCI_REQ_IRQ_INDEX, VFIO_PCI_NUM_IRQS }; -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
