#include "virtio.h"
#include "virtio-blk.h"
#include "virtio-net.h"
+#include "virtio-serial.h"
#include "pci.h"
#include "qemu-error.h"
#include "msix.h"
#include "loader.h"
#include "kvm.h"
#include "blockdev.h"
+#include "virtio-pci.h"
/* from Linux's linux/virtio_pci.h */
VIRTIO_PCI_CONFIG_MSI : \
VIRTIO_PCI_CONFIG_NOMSI)
-/* Virtio ABI version, if we increment this, we break the guest driver. */
-#define VIRTIO_PCI_ABI_VERSION 0
-
/* How many bits to shift physical queue address written to QUEUE_PFN.
* 12 is historical, and due to x86 page size. */
#define VIRTIO_PCI_QUEUE_ADDR_SHIFT 12
-/* We can catch some guest bugs inside here so we continue supporting older
- guests. */
-#define VIRTIO_PCI_BUG_BUS_MASTER (1 << 0)
+/* Flags track per-device state like workarounds for quirks in older guests. */
+#define VIRTIO_PCI_FLAG_BUS_MASTER_BUG (1 << 0)
+
+/* Performance improves when virtqueue kick processing is decoupled from the
+ * vcpu thread using ioeventfd for some devices. */
+#define VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT 1
+#define VIRTIO_PCI_FLAG_USE_IOEVENTFD (1 << VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT)
/* QEMU doesn't strictly need write barriers since everything runs in
* lock-step. We'll leave the calls to wmb() in though to make it obvious for
*/
#define wmb() do { } while (0)
-/* PCI bindings. */
-
-typedef struct {
- PCIDevice pci_dev;
- VirtIODevice *vdev;
- uint32_t bugs;
- uint32_t addr;
- uint32_t class_code;
- uint32_t nvectors;
- BlockConf block;
- NICConf nic;
- uint32_t host_features;
-#ifdef CONFIG_LINUX
- V9fsConf fsconf;
-#endif
- /* Max. number of ports we can have for a the virtio-serial device */
- uint32_t max_virtserial_ports;
- virtio_net_conf net;
-} VirtIOPCIProxy;
-
/* virtio device */
static void virtio_pci_notify(void *opaque, uint16_t vector)
if (proxy->vdev->config_vector != VIRTIO_NO_VECTOR) {
return msix_vector_use(&proxy->pci_dev, proxy->vdev->config_vector);
}
-
- /* Try to find out if the guest has bus master disabled, but is
- in ready state. Then we have a buggy guest OS. */
- if ((proxy->vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
- !(proxy->pci_dev.config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
- proxy->bugs |= VIRTIO_PCI_BUG_BUS_MASTER;
- }
return 0;
}
return 0;
}
+static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
+ int n, bool assign)
+{
+ VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
+ EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
+ int r;
+ if (assign) {
+ r = event_notifier_init(notifier, 1);
+ if (r < 0) {
+ error_report("%s: unable to init event notifier: %d",
+ __func__, r);
+ return r;
+ }
+ r = kvm_set_ioeventfd_pio_word(event_notifier_get_fd(notifier),
+ proxy->addr + VIRTIO_PCI_QUEUE_NOTIFY,
+ n, assign);
+ if (r < 0) {
+ error_report("%s: unable to map ioeventfd: %d",
+ __func__, r);
+ event_notifier_cleanup(notifier);
+ }
+ } else {
+ r = kvm_set_ioeventfd_pio_word(event_notifier_get_fd(notifier),
+ proxy->addr + VIRTIO_PCI_QUEUE_NOTIFY,
+ n, assign);
+ if (r < 0) {
+ error_report("%s: unable to unmap ioeventfd: %d",
+ __func__, r);
+ return r;
+ }
+
+ /* Handle the race condition where the guest kicked and we deassigned
+ * before we got around to handling the kick.
+ */
+ if (event_notifier_test_and_clear(notifier)) {
+ virtio_queue_notify_vq(vq);
+ }
+
+ event_notifier_cleanup(notifier);
+ }
+ return r;
+}
+
+static void virtio_pci_host_notifier_read(void *opaque)
+{
+ VirtQueue *vq = opaque;
+ EventNotifier *n = virtio_queue_get_host_notifier(vq);
+ if (event_notifier_test_and_clear(n)) {
+ virtio_queue_notify_vq(vq);
+ }
+}
+
+static void virtio_pci_set_host_notifier_fd_handler(VirtIOPCIProxy *proxy,
+ int n, bool assign)
+{
+ VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
+ EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
+ if (assign) {
+ qemu_set_fd_handler(event_notifier_get_fd(notifier),
+ virtio_pci_host_notifier_read, NULL, vq);
+ } else {
+ qemu_set_fd_handler(event_notifier_get_fd(notifier),
+ NULL, NULL, NULL);
+ }
+}
+
+static void virtio_pci_start_ioeventfd(VirtIOPCIProxy *proxy)
+{
+ int n, r;
+
+ if (!(proxy->flags & VIRTIO_PCI_FLAG_USE_IOEVENTFD) ||
+ proxy->ioeventfd_disabled ||
+ proxy->ioeventfd_started) {
+ return;
+ }
+
+ for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
+ if (!virtio_queue_get_num(proxy->vdev, n)) {
+ continue;
+ }
+
+ r = virtio_pci_set_host_notifier_internal(proxy, n, true);
+ if (r < 0) {
+ goto assign_error;
+ }
+
+ virtio_pci_set_host_notifier_fd_handler(proxy, n, true);
+ }
+ proxy->ioeventfd_started = true;
+ return;
+
+assign_error:
+ while (--n >= 0) {
+ if (!virtio_queue_get_num(proxy->vdev, n)) {
+ continue;
+ }
+
+ virtio_pci_set_host_notifier_fd_handler(proxy, n, false);
+ r = virtio_pci_set_host_notifier_internal(proxy, n, false);
+ assert(r >= 0);
+ }
+ proxy->ioeventfd_started = false;
+ error_report("%s: failed. Fallback to a userspace (slower).", __func__);
+}
+
+static void virtio_pci_stop_ioeventfd(VirtIOPCIProxy *proxy)
+{
+ int r;
+ int n;
+
+ if (!proxy->ioeventfd_started) {
+ return;
+ }
+
+ for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
+ if (!virtio_queue_get_num(proxy->vdev, n)) {
+ continue;
+ }
+
+ virtio_pci_set_host_notifier_fd_handler(proxy, n, false);
+ r = virtio_pci_set_host_notifier_internal(proxy, n, false);
+ assert(r >= 0);
+ }
+ proxy->ioeventfd_started = false;
+}
+
static void virtio_pci_reset(DeviceState *d)
{
VirtIOPCIProxy *proxy = container_of(d, VirtIOPCIProxy, pci_dev.qdev);
+ virtio_pci_stop_ioeventfd(proxy);
virtio_reset(proxy->vdev);
msix_reset(&proxy->pci_dev);
- proxy->bugs = 0;
+ proxy->flags &= ~VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
}
static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
case VIRTIO_PCI_QUEUE_PFN:
pa = (target_phys_addr_t)val << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
if (pa == 0) {
+ virtio_pci_stop_ioeventfd(proxy);
virtio_reset(proxy->vdev);
msix_unuse_all_vectors(&proxy->pci_dev);
}
vdev->queue_sel = val;
break;
case VIRTIO_PCI_QUEUE_NOTIFY:
- virtio_queue_notify(vdev, val);
+ if (val < VIRTIO_PCI_QUEUE_MAX) {
+ virtio_queue_notify(vdev, val);
+ }
break;
case VIRTIO_PCI_STATUS:
+ if (!(val & VIRTIO_CONFIG_S_DRIVER_OK)) {
+ virtio_pci_stop_ioeventfd(proxy);
+ }
+
virtio_set_status(vdev, val & 0xFF);
+
+ if (val & VIRTIO_CONFIG_S_DRIVER_OK) {
+ virtio_pci_start_ioeventfd(proxy);
+ }
+
if (vdev->status == 0) {
virtio_reset(proxy->vdev);
msix_unuse_all_vectors(&proxy->pci_dev);
some safety checks. */
if ((val & VIRTIO_CONFIG_S_DRIVER_OK) &&
!(proxy->pci_dev.config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
- proxy->bugs |= VIRTIO_PCI_BUG_BUS_MASTER;
+ proxy->flags |= VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
}
break;
case VIRTIO_MSI_CONFIG_VECTOR:
if (PCI_COMMAND == address) {
if (!(val & PCI_COMMAND_MASTER)) {
- if (!(proxy->bugs & VIRTIO_PCI_BUG_BUS_MASTER)) {
+ if (!(proxy->flags & VIRTIO_PCI_FLAG_BUS_MASTER_BUG)) {
+ virtio_pci_stop_ioeventfd(proxy);
virtio_set_status(proxy->vdev,
proxy->vdev->status & ~VIRTIO_CONFIG_S_DRIVER_OK);
}
return 0;
}
+static bool virtio_pci_query_guest_notifiers(void *opaque)
+{
+ VirtIOPCIProxy *proxy = opaque;
+ return msix_enabled(&proxy->pci_dev);
+}
+
static int virtio_pci_set_guest_notifiers(void *opaque, bool assign)
{
VirtIOPCIProxy *proxy = opaque;
static int virtio_pci_set_host_notifier(void *opaque, int n, bool assign)
{
VirtIOPCIProxy *proxy = opaque;
- VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
- EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
- int r;
+
+ /* Stop using ioeventfd for virtqueue kick if the device starts using host
+ * notifiers. This makes it easy to avoid stepping on each others' toes.
+ */
+ proxy->ioeventfd_disabled = assign;
if (assign) {
- r = event_notifier_init(notifier, 1);
- if (r < 0) {
- return r;
- }
- r = kvm_set_ioeventfd_pio_word(event_notifier_get_fd(notifier),
- proxy->addr + VIRTIO_PCI_QUEUE_NOTIFY,
- n, assign);
- if (r < 0) {
- event_notifier_cleanup(notifier);
+ virtio_pci_stop_ioeventfd(proxy);
+ }
+ /* We don't need to start here: it's not needed because backend
+ * currently only stops on status change away from ok,
+ * reset, vmstop and such. If we do add code to start here,
+ * need to check vmstate, device state etc. */
+ return virtio_pci_set_host_notifier_internal(proxy, n, assign);
+}
+
+static void virtio_pci_vmstate_change(void *opaque, bool running)
+{
+ VirtIOPCIProxy *proxy = opaque;
+
+ if (running) {
+ /* Try to find out if the guest has bus master disabled, but is
+ in ready state. Then we have a buggy guest OS. */
+ if ((proxy->vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+ !(proxy->pci_dev.config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
+ proxy->flags |= VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
}
+ virtio_pci_start_ioeventfd(proxy);
} else {
- r = kvm_set_ioeventfd_pio_word(event_notifier_get_fd(notifier),
- proxy->addr + VIRTIO_PCI_QUEUE_NOTIFY,
- n, assign);
- if (r < 0) {
- return r;
- }
- event_notifier_cleanup(notifier);
+ virtio_pci_stop_ioeventfd(proxy);
}
- return r;
}
static const VirtIOBindings virtio_pci_bindings = {
.save_queue = virtio_pci_save_queue,
.load_queue = virtio_pci_load_queue,
.get_features = virtio_pci_get_features,
+ .query_guest_notifiers = virtio_pci_query_guest_notifiers,
.set_host_notifier = virtio_pci_set_host_notifier,
.set_guest_notifiers = virtio_pci_set_guest_notifiers,
+ .vmstate_change = virtio_pci_vmstate_change,
};
-static void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev,
- uint16_t vendor, uint16_t device,
- uint16_t class_code, uint8_t pif)
+void virtio_init_pci(VirtIOPCIProxy *proxy, VirtIODevice *vdev)
{
uint8_t *config;
uint32_t size;
proxy->vdev = vdev;
config = proxy->pci_dev.config;
- pci_config_set_vendor_id(config, vendor);
- pci_config_set_device_id(config, device);
-
- config[0x08] = VIRTIO_PCI_ABI_VERSION;
-
- config[0x09] = pif;
- pci_config_set_class(config, class_code);
-
- config[0x2c] = vendor & 0xFF;
- config[0x2d] = (vendor >> 8) & 0xFF;
- config[0x2e] = vdev->device_id & 0xFF;
- config[0x2f] = (vdev->device_id >> 8) & 0xFF;
+ if (proxy->class_code) {
+ pci_config_set_class(config, proxy->class_code);
+ }
+ pci_set_word(config + 0x2c, pci_get_word(config + PCI_VENDOR_ID));
+ pci_set_word(config + 0x2e, vdev->device_id);
config[0x3d] = 1;
if (vdev->nvectors && !msix_init(&proxy->pci_dev, vdev->nvectors, 1, 0)) {
pci_register_bar(&proxy->pci_dev, 0, size, PCI_BASE_ADDRESS_SPACE_IO,
virtio_map);
+ if (!kvm_has_many_ioeventfds()) {
+ proxy->flags &= ~VIRTIO_PCI_FLAG_USE_IOEVENTFD;
+ }
+
virtio_bind_device(vdev, &virtio_pci_bindings, proxy);
proxy->host_features |= 0x1 << VIRTIO_F_NOTIFY_ON_EMPTY;
proxy->host_features |= 0x1 << VIRTIO_F_BAD_FEATURE;
proxy->class_code != PCI_CLASS_STORAGE_OTHER)
proxy->class_code = PCI_CLASS_STORAGE_SCSI;
- vdev = virtio_blk_init(&pci_dev->qdev, &proxy->block);
+ vdev = virtio_blk_init(&pci_dev->qdev, &proxy->block,
+ &proxy->block_serial);
if (!vdev) {
return -1;
}
vdev->nvectors = proxy->nvectors;
- virtio_init_pci(proxy, vdev,
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- PCI_DEVICE_ID_VIRTIO_BLOCK,
- proxy->class_code, 0x00);
+ virtio_init_pci(proxy, vdev);
/* make the actual value visible */
proxy->nvectors = vdev->nvectors;
return 0;
{
VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
+ virtio_pci_stop_ioeventfd(proxy);
virtio_blk_exit(proxy->vdev);
blockdev_mark_auto_del(proxy->block.bs);
return virtio_exit_pci(pci_dev);
proxy->class_code != PCI_CLASS_OTHERS) /* qemu-kvm */
proxy->class_code = PCI_CLASS_COMMUNICATION_OTHER;
- vdev = virtio_serial_init(&pci_dev->qdev, proxy->max_virtserial_ports);
+ vdev = virtio_serial_init(&pci_dev->qdev, &proxy->serial);
if (!vdev) {
return -1;
}
vdev->nvectors = proxy->nvectors == DEV_NVECTORS_UNSPECIFIED
- ? proxy->max_virtserial_ports + 1
+ ? proxy->serial.max_virtserial_ports + 1
: proxy->nvectors;
- virtio_init_pci(proxy, vdev,
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- PCI_DEVICE_ID_VIRTIO_CONSOLE,
- proxy->class_code, 0x00);
+ virtio_init_pci(proxy, vdev);
proxy->nvectors = vdev->nvectors;
return 0;
}
{
VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
+ virtio_pci_stop_ioeventfd(proxy);
virtio_serial_exit(proxy->vdev);
return virtio_exit_pci(pci_dev);
}
vdev = virtio_net_init(&pci_dev->qdev, &proxy->nic, &proxy->net);
vdev->nvectors = proxy->nvectors;
- virtio_init_pci(proxy, vdev,
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- PCI_DEVICE_ID_VIRTIO_NET,
- PCI_CLASS_NETWORK_ETHERNET,
- 0x00);
+ virtio_init_pci(proxy, vdev);
/* make the actual value visible */
proxy->nvectors = vdev->nvectors;
{
VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
+ virtio_pci_stop_ioeventfd(proxy);
virtio_net_exit(proxy->vdev);
return virtio_exit_pci(pci_dev);
}
VirtIODevice *vdev;
vdev = virtio_balloon_init(&pci_dev->qdev);
- virtio_init_pci(proxy, vdev,
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- PCI_DEVICE_ID_VIRTIO_BALLOON,
- PCI_CLASS_MEMORY_RAM,
- 0x00);
+ if (!vdev) {
+ return -1;
+ }
+ virtio_init_pci(proxy, vdev);
return 0;
}
-#ifdef CONFIG_VIRTFS
-static int virtio_9p_init_pci(PCIDevice *pci_dev)
+static int virtio_balloon_exit_pci(PCIDevice *pci_dev)
{
VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
- VirtIODevice *vdev;
- vdev = virtio_9p_init(&pci_dev->qdev, &proxy->fsconf);
- vdev->nvectors = proxy->nvectors;
- virtio_init_pci(proxy, vdev,
- PCI_VENDOR_ID_REDHAT_QUMRANET,
- 0x1009,
- 0x2,
- 0x00);
- /* make the actual value visible */
- proxy->nvectors = vdev->nvectors;
- return 0;
+ virtio_pci_stop_ioeventfd(proxy);
+ virtio_balloon_exit(proxy->vdev);
+ return virtio_exit_pci(pci_dev);
}
-#endif
static PCIDeviceInfo virtio_info[] = {
{
.qdev.size = sizeof(VirtIOPCIProxy),
.init = virtio_blk_init_pci,
.exit = virtio_blk_exit_pci,
+ .vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET,
+ .device_id = PCI_DEVICE_ID_VIRTIO_BLOCK,
+ .revision = VIRTIO_PCI_ABI_VERSION,
+ .class_id = PCI_CLASS_STORAGE_SCSI,
.qdev.props = (Property[]) {
DEFINE_PROP_HEX32("class", VirtIOPCIProxy, class_code, 0),
DEFINE_BLOCK_PROPERTIES(VirtIOPCIProxy, block),
+ DEFINE_PROP_STRING("serial", VirtIOPCIProxy, block_serial),
+ DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags,
+ VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true),
DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2),
DEFINE_VIRTIO_BLK_FEATURES(VirtIOPCIProxy, host_features),
DEFINE_PROP_END_OF_LIST(),
.qdev.reset = virtio_pci_reset,
},{
.qdev.name = "virtio-net-pci",
+ .qdev.alias = "virtio-net",
.qdev.size = sizeof(VirtIOPCIProxy),
.init = virtio_net_init_pci,
.exit = virtio_net_exit_pci,
- .romfile = "pxe-virtio.bin",
+ .romfile = "pxe-virtio.rom",
+ .vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET,
+ .device_id = PCI_DEVICE_ID_VIRTIO_NET,
+ .revision = VIRTIO_PCI_ABI_VERSION,
+ .class_id = PCI_CLASS_NETWORK_ETHERNET,
.qdev.props = (Property[]) {
+ DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags,
+ VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, false),
DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 3),
DEFINE_VIRTIO_NET_FEATURES(VirtIOPCIProxy, host_features),
DEFINE_NIC_PROPERTIES(VirtIOPCIProxy, nic),
.qdev.size = sizeof(VirtIOPCIProxy),
.init = virtio_serial_init_pci,
.exit = virtio_serial_exit_pci,
+ .vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET,
+ .device_id = PCI_DEVICE_ID_VIRTIO_CONSOLE,
+ .revision = VIRTIO_PCI_ABI_VERSION,
+ .class_id = PCI_CLASS_COMMUNICATION_OTHER,
.qdev.props = (Property[]) {
+ DEFINE_PROP_BIT("ioeventfd", VirtIOPCIProxy, flags,
+ VIRTIO_PCI_FLAG_USE_IOEVENTFD_BIT, true),
DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors,
DEV_NVECTORS_UNSPECIFIED),
DEFINE_PROP_HEX32("class", VirtIOPCIProxy, class_code, 0),
DEFINE_VIRTIO_COMMON_FEATURES(VirtIOPCIProxy, host_features),
- DEFINE_PROP_UINT32("max_ports", VirtIOPCIProxy, max_virtserial_ports,
- 31),
+ DEFINE_PROP_UINT32("max_ports", VirtIOPCIProxy,
+ serial.max_virtserial_ports, 31),
DEFINE_PROP_END_OF_LIST(),
},
.qdev.reset = virtio_pci_reset,
},{
.qdev.name = "virtio-balloon-pci",
+ .qdev.alias = "virtio-balloon",
.qdev.size = sizeof(VirtIOPCIProxy),
.init = virtio_balloon_init_pci,
- .exit = virtio_exit_pci,
+ .exit = virtio_balloon_exit_pci,
+ .vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET,
+ .device_id = PCI_DEVICE_ID_VIRTIO_BALLOON,
+ .revision = VIRTIO_PCI_ABI_VERSION,
+ .class_id = PCI_CLASS_MEMORY_RAM,
.qdev.props = (Property[]) {
DEFINE_VIRTIO_COMMON_FEATURES(VirtIOPCIProxy, host_features),
DEFINE_PROP_END_OF_LIST(),
},
.qdev.reset = virtio_pci_reset,
},{
-#ifdef CONFIG_VIRTFS
- .qdev.name = "virtio-9p-pci",
- .qdev.size = sizeof(VirtIOPCIProxy),
- .init = virtio_9p_init_pci,
- .qdev.props = (Property[]) {
- DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2),
- DEFINE_VIRTIO_COMMON_FEATURES(VirtIOPCIProxy, host_features),
- DEFINE_PROP_STRING("mount_tag", VirtIOPCIProxy, fsconf.tag),
- DEFINE_PROP_STRING("fsdev", VirtIOPCIProxy, fsconf.fsdev_id),
- DEFINE_PROP_END_OF_LIST(),
- },
- }, {
-#endif
/* end of list */
}
};