#include "qemu/osdep.h"
#include "qapi/error.h"
#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-user.h"
#include "hw/virtio/vhost-backend.h"
+#include "hw/virtio/virtio.h"
#include "hw/virtio/virtio-net.h"
#include "chardev/char-fe.h"
#include "sysemu/kvm.h"
#include "sysemu/cryptodev.h"
#include "migration/migration.h"
#include "migration/postcopy-ram.h"
+#include "trace.h"
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <linux/vhost.h>
+#include <linux/userfaultfd.h>
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
+#define VHOST_USER_SLAVE_MAX_FDS 8
/*
* Maximum size of virtio device config space
VHOST_USER_PROTOCOL_F_CROSS_ENDIAN = 6,
VHOST_USER_PROTOCOL_F_CRYPTO_SESSION = 7,
VHOST_USER_PROTOCOL_F_PAGEFAULT = 8,
+ VHOST_USER_PROTOCOL_F_CONFIG = 9,
+ VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD = 10,
+ VHOST_USER_PROTOCOL_F_HOST_NOTIFIER = 11,
VHOST_USER_PROTOCOL_F_MAX
};
VHOST_USER_SET_CONFIG = 25,
VHOST_USER_CREATE_CRYPTO_SESSION = 26,
VHOST_USER_CLOSE_CRYPTO_SESSION = 27,
+ VHOST_USER_POSTCOPY_ADVISE = 28,
+ VHOST_USER_POSTCOPY_LISTEN = 29,
+ VHOST_USER_POSTCOPY_END = 30,
VHOST_USER_MAX
} VhostUserRequest;
VHOST_USER_SLAVE_NONE = 0,
VHOST_USER_SLAVE_IOTLB_MSG = 1,
VHOST_USER_SLAVE_CONFIG_CHANGE_MSG = 2,
+ VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG = 3,
VHOST_USER_SLAVE_MAX
} VhostUserSlaveRequest;
+ sizeof(c.size) \
+ sizeof(c.flags))
+typedef struct VhostUserVringArea {
+ uint64_t u64;
+ uint64_t size;
+ uint64_t offset;
+} VhostUserVringArea;
+
typedef struct {
VhostUserRequest request;
struct vhost_iotlb_msg iotlb;
VhostUserConfig config;
VhostUserCryptoSession session;
+ VhostUserVringArea area;
} VhostUserPayload;
typedef struct VhostUserMsg {
struct vhost_user {
struct vhost_dev *dev;
- CharBackend *chr;
+ /* Shared between vhost devs of the same virtio device */
+ VhostUserState *user;
int slave_fd;
NotifierWithReturn postcopy_notifier;
+ struct PostCopyFD postcopy_fd;
+ uint64_t postcopy_client_bases[VHOST_MEMORY_MAX_NREGIONS];
+ /* Length of the region_rb and region_rb_offset arrays */
+ size_t region_rb_len;
+ /* RAMBlock associated with a given region */
+ RAMBlock **region_rb;
+ /* The offset from the start of the RAMBlock to the start of the
+ * vhost region.
+ */
+ ram_addr_t *region_rb_offset;
+
+ /* True once we've entered postcopy_listen */
+ bool postcopy_listen;
};
static bool ioeventfd_enabled(void)
static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
struct vhost_user *u = dev->opaque;
- CharBackend *chr = u->chr;
+ CharBackend *chr = u->user->chr;
uint8_t *p = (uint8_t *) msg;
int r, size = VHOST_USER_HDR_SIZE;
int *fds, int fd_num)
{
struct vhost_user *u = dev->opaque;
- CharBackend *chr = u->chr;
+ CharBackend *chr = u->user->chr;
int ret, size = VHOST_USER_HDR_SIZE + msg->hdr.size;
/*
return 0;
}
+static int vhost_user_set_mem_table_postcopy(struct vhost_dev *dev,
+ struct vhost_memory *mem)
+{
+ struct vhost_user *u = dev->opaque;
+ int fds[VHOST_MEMORY_MAX_NREGIONS];
+ int i, fd;
+ size_t fd_num = 0;
+ VhostUserMsg msg_reply;
+ int region_i, msg_i;
+
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_SET_MEM_TABLE,
+ .hdr.flags = VHOST_USER_VERSION,
+ };
+
+ if (u->region_rb_len < dev->mem->nregions) {
+ u->region_rb = g_renew(RAMBlock*, u->region_rb, dev->mem->nregions);
+ u->region_rb_offset = g_renew(ram_addr_t, u->region_rb_offset,
+ dev->mem->nregions);
+ memset(&(u->region_rb[u->region_rb_len]), '\0',
+ sizeof(RAMBlock *) * (dev->mem->nregions - u->region_rb_len));
+ memset(&(u->region_rb_offset[u->region_rb_len]), '\0',
+ sizeof(ram_addr_t) * (dev->mem->nregions - u->region_rb_len));
+ u->region_rb_len = dev->mem->nregions;
+ }
+
+ for (i = 0; i < dev->mem->nregions; ++i) {
+ struct vhost_memory_region *reg = dev->mem->regions + i;
+ ram_addr_t offset;
+ MemoryRegion *mr;
+
+ assert((uintptr_t)reg->userspace_addr == reg->userspace_addr);
+ mr = memory_region_from_host((void *)(uintptr_t)reg->userspace_addr,
+ &offset);
+ fd = memory_region_get_fd(mr);
+ if (fd > 0) {
+ trace_vhost_user_set_mem_table_withfd(fd_num, mr->name,
+ reg->memory_size,
+ reg->guest_phys_addr,
+ reg->userspace_addr, offset);
+ u->region_rb_offset[i] = offset;
+ u->region_rb[i] = mr->ram_block;
+ msg.payload.memory.regions[fd_num].userspace_addr =
+ reg->userspace_addr;
+ msg.payload.memory.regions[fd_num].memory_size = reg->memory_size;
+ msg.payload.memory.regions[fd_num].guest_phys_addr =
+ reg->guest_phys_addr;
+ msg.payload.memory.regions[fd_num].mmap_offset = offset;
+ assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
+ fds[fd_num++] = fd;
+ } else {
+ u->region_rb_offset[i] = 0;
+ u->region_rb[i] = NULL;
+ }
+ }
+
+ msg.payload.memory.nregions = fd_num;
+
+ if (!fd_num) {
+ error_report("Failed initializing vhost-user memory map, "
+ "consider using -object memory-backend-file share=on");
+ return -1;
+ }
+
+ msg.hdr.size = sizeof(msg.payload.memory.nregions);
+ msg.hdr.size += sizeof(msg.payload.memory.padding);
+ msg.hdr.size += fd_num * sizeof(VhostUserMemoryRegion);
+
+ if (vhost_user_write(dev, &msg, fds, fd_num) < 0) {
+ return -1;
+ }
+
+ if (vhost_user_read(dev, &msg_reply) < 0) {
+ return -1;
+ }
+
+ if (msg_reply.hdr.request != VHOST_USER_SET_MEM_TABLE) {
+ error_report("%s: Received unexpected msg type."
+ "Expected %d received %d", __func__,
+ VHOST_USER_SET_MEM_TABLE, msg_reply.hdr.request);
+ return -1;
+ }
+ /* We're using the same structure, just reusing one of the
+ * fields, so it should be the same size.
+ */
+ if (msg_reply.hdr.size != msg.hdr.size) {
+ error_report("%s: Unexpected size for postcopy reply "
+ "%d vs %d", __func__, msg_reply.hdr.size, msg.hdr.size);
+ return -1;
+ }
+
+ memset(u->postcopy_client_bases, 0,
+ sizeof(uint64_t) * VHOST_MEMORY_MAX_NREGIONS);
+
+ /* They're in the same order as the regions that were sent
+ * but some of the regions were skipped (above) if they
+ * didn't have fd's
+ */
+ for (msg_i = 0, region_i = 0;
+ region_i < dev->mem->nregions;
+ region_i++) {
+ if (msg_i < fd_num &&
+ msg_reply.payload.memory.regions[msg_i].guest_phys_addr ==
+ dev->mem->regions[region_i].guest_phys_addr) {
+ u->postcopy_client_bases[region_i] =
+ msg_reply.payload.memory.regions[msg_i].userspace_addr;
+ trace_vhost_user_set_mem_table_postcopy(
+ msg_reply.payload.memory.regions[msg_i].userspace_addr,
+ msg.payload.memory.regions[msg_i].userspace_addr,
+ msg_i, region_i);
+ msg_i++;
+ }
+ }
+ if (msg_i != fd_num) {
+ error_report("%s: postcopy reply not fully consumed "
+ "%d vs %zd",
+ __func__, msg_i, fd_num);
+ return -1;
+ }
+ /* Now we've registered this with the postcopy code, we ack to the client,
+ * because now we're in the position to be able to deal with any faults
+ * it generates.
+ */
+ /* TODO: Use this for failure cases as well with a bad value */
+ msg.hdr.size = sizeof(msg.payload.u64);
+ msg.payload.u64 = 0; /* OK */
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ return -1;
+ }
+
+ return 0;
+}
+
static int vhost_user_set_mem_table(struct vhost_dev *dev,
struct vhost_memory *mem)
{
+ struct vhost_user *u = dev->opaque;
int fds[VHOST_MEMORY_MAX_NREGIONS];
int i, fd;
size_t fd_num = 0;
+ bool do_postcopy = u->postcopy_listen && u->postcopy_fd.handler;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
+ if (do_postcopy) {
+ /* Postcopy has enough differences that it's best done in it's own
+ * version
+ */
+ return vhost_user_set_mem_table_postcopy(dev, mem);
+ }
+
VhostUserMsg msg = {
.hdr.request = VHOST_USER_SET_MEM_TABLE,
.hdr.flags = VHOST_USER_VERSION,
error_report("Failed preparing vhost-user memory table msg");
return -1;
}
- msg.payload.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
+ msg.payload.memory.regions[fd_num].userspace_addr =
+ reg->userspace_addr;
msg.payload.memory.regions[fd_num].memory_size = reg->memory_size;
- msg.payload.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
+ msg.payload.memory.regions[fd_num].guest_phys_addr =
+ reg->guest_phys_addr;
msg.payload.memory.regions[fd_num].mmap_offset = offset;
fds[fd_num++] = fd;
}
return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring);
}
+static void vhost_user_host_notifier_restore(struct vhost_dev *dev,
+ int queue_idx)
+{
+ struct vhost_user *u = dev->opaque;
+ VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
+ VirtIODevice *vdev = dev->vdev;
+
+ if (n->addr && !n->set) {
+ virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true);
+ n->set = true;
+ }
+}
+
+static void vhost_user_host_notifier_remove(struct vhost_dev *dev,
+ int queue_idx)
+{
+ struct vhost_user *u = dev->opaque;
+ VhostUserHostNotifier *n = &u->user->notifier[queue_idx];
+ VirtIODevice *vdev = dev->vdev;
+
+ if (n->addr && n->set) {
+ virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
+ n->set = false;
+ }
+}
+
static int vhost_user_set_vring_base(struct vhost_dev *dev,
struct vhost_vring_state *ring)
{
+ vhost_user_host_notifier_restore(dev, ring->index);
+
return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring);
}
.hdr.size = sizeof(msg.payload.state),
};
+ vhost_user_host_notifier_remove(dev, ring->index);
+
if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
return -1;
}
return ret;
}
+static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev,
+ VhostUserVringArea *area,
+ int fd)
+{
+ int queue_idx = area->u64 & VHOST_USER_VRING_IDX_MASK;
+ size_t page_size = qemu_real_host_page_size;
+ struct vhost_user *u = dev->opaque;
+ VhostUserState *user = u->user;
+ VirtIODevice *vdev = dev->vdev;
+ VhostUserHostNotifier *n;
+ void *addr;
+ char *name;
+
+ if (!virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_HOST_NOTIFIER) ||
+ vdev == NULL || queue_idx >= virtio_get_num_queues(vdev)) {
+ return -1;
+ }
+
+ n = &user->notifier[queue_idx];
+
+ if (n->addr) {
+ virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false);
+ object_unparent(OBJECT(&n->mr));
+ munmap(n->addr, page_size);
+ n->addr = NULL;
+ }
+
+ if (area->u64 & VHOST_USER_VRING_NOFD_MASK) {
+ return 0;
+ }
+
+ /* Sanity check. */
+ if (area->size != page_size) {
+ return -1;
+ }
+
+ addr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+ fd, area->offset);
+ if (addr == MAP_FAILED) {
+ return -1;
+ }
+
+ name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]",
+ user, queue_idx);
+ memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name,
+ page_size, addr);
+ g_free(name);
+
+ if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) {
+ munmap(addr, page_size);
+ return -1;
+ }
+
+ n->addr = addr;
+ n->set = true;
+
+ return 0;
+}
+
static void slave_read(void *opaque)
{
struct vhost_dev *dev = opaque;
VhostUserHeader hdr = { 0, };
VhostUserPayload payload = { 0, };
int size, ret = 0;
+ struct iovec iov;
+ struct msghdr msgh;
+ int fd[VHOST_USER_SLAVE_MAX_FDS];
+ char control[CMSG_SPACE(sizeof(fd))];
+ struct cmsghdr *cmsg;
+ int i, fdsize = 0;
+
+ memset(&msgh, 0, sizeof(msgh));
+ msgh.msg_iov = &iov;
+ msgh.msg_iovlen = 1;
+ msgh.msg_control = control;
+ msgh.msg_controllen = sizeof(control);
+
+ memset(fd, -1, sizeof(fd));
/* Read header */
- size = read(u->slave_fd, &hdr, VHOST_USER_HDR_SIZE);
+ iov.iov_base = &hdr;
+ iov.iov_len = VHOST_USER_HDR_SIZE;
+
+ size = recvmsg(u->slave_fd, &msgh, 0);
if (size != VHOST_USER_HDR_SIZE) {
error_report("Failed to read from slave.");
goto err;
}
+ if (msgh.msg_flags & MSG_CTRUNC) {
+ error_report("Truncated message.");
+ goto err;
+ }
+
+ for (cmsg = CMSG_FIRSTHDR(&msgh); cmsg != NULL;
+ cmsg = CMSG_NXTHDR(&msgh, cmsg)) {
+ if (cmsg->cmsg_level == SOL_SOCKET &&
+ cmsg->cmsg_type == SCM_RIGHTS) {
+ fdsize = cmsg->cmsg_len - CMSG_LEN(0);
+ memcpy(fd, CMSG_DATA(cmsg), fdsize);
+ break;
+ }
+ }
+
if (hdr.size > VHOST_USER_PAYLOAD_SIZE) {
error_report("Failed to read msg header."
" Size %d exceeds the maximum %zu.", hdr.size,
case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG :
ret = vhost_user_slave_handle_config_change(dev);
break;
+ case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG:
+ ret = vhost_user_slave_handle_vring_host_notifier(dev, &payload.area,
+ fd[0]);
+ break;
default:
error_report("Received unexpected msg type.");
ret = -EINVAL;
}
+ /* Close the remaining file descriptors. */
+ for (i = 0; i < fdsize; i++) {
+ if (fd[i] != -1) {
+ close(fd[i]);
+ }
+ }
+
/*
* REPLY_ACK feature handling. Other reply types has to be managed
* directly in their request handlers.
qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
close(u->slave_fd);
u->slave_fd = -1;
+ for (i = 0; i < fdsize; i++) {
+ if (fd[i] != -1) {
+ close(fd[i]);
+ }
+ }
return;
}
return ret;
}
+/*
+ * Called back from the postcopy fault thread when a fault is received on our
+ * ufd.
+ * TODO: This is Linux specific
+ */
+static int vhost_user_postcopy_fault_handler(struct PostCopyFD *pcfd,
+ void *ufd)
+{
+ struct vhost_dev *dev = pcfd->data;
+ struct vhost_user *u = dev->opaque;
+ struct uffd_msg *msg = ufd;
+ uint64_t faultaddr = msg->arg.pagefault.address;
+ RAMBlock *rb = NULL;
+ uint64_t rb_offset;
+ int i;
+
+ trace_vhost_user_postcopy_fault_handler(pcfd->idstr, faultaddr,
+ dev->mem->nregions);
+ for (i = 0; i < MIN(dev->mem->nregions, u->region_rb_len); i++) {
+ trace_vhost_user_postcopy_fault_handler_loop(i,
+ u->postcopy_client_bases[i], dev->mem->regions[i].memory_size);
+ if (faultaddr >= u->postcopy_client_bases[i]) {
+ /* Ofset of the fault address in the vhost region */
+ uint64_t region_offset = faultaddr - u->postcopy_client_bases[i];
+ if (region_offset < dev->mem->regions[i].memory_size) {
+ rb_offset = region_offset + u->region_rb_offset[i];
+ trace_vhost_user_postcopy_fault_handler_found(i,
+ region_offset, rb_offset);
+ rb = u->region_rb[i];
+ return postcopy_request_shared_page(pcfd, rb, faultaddr,
+ rb_offset);
+ }
+ }
+ }
+ error_report("%s: Failed to find region for fault %" PRIx64,
+ __func__, faultaddr);
+ return -1;
+}
+
+static int vhost_user_postcopy_waker(struct PostCopyFD *pcfd, RAMBlock *rb,
+ uint64_t offset)
+{
+ struct vhost_dev *dev = pcfd->data;
+ struct vhost_user *u = dev->opaque;
+ int i;
+
+ trace_vhost_user_postcopy_waker(qemu_ram_get_idstr(rb), offset);
+
+ if (!u) {
+ return 0;
+ }
+ /* Translate the offset into an address in the clients address space */
+ for (i = 0; i < MIN(dev->mem->nregions, u->region_rb_len); i++) {
+ if (u->region_rb[i] == rb &&
+ offset >= u->region_rb_offset[i] &&
+ offset < (u->region_rb_offset[i] +
+ dev->mem->regions[i].memory_size)) {
+ uint64_t client_addr = (offset - u->region_rb_offset[i]) +
+ u->postcopy_client_bases[i];
+ trace_vhost_user_postcopy_waker_found(client_addr);
+ return postcopy_wake_shared(pcfd, client_addr, rb);
+ }
+ }
+
+ trace_vhost_user_postcopy_waker_nomatch(qemu_ram_get_idstr(rb), offset);
+ return 0;
+}
+
+/*
+ * Called at the start of an inbound postcopy on reception of the
+ * 'advise' command.
+ */
+static int vhost_user_postcopy_advise(struct vhost_dev *dev, Error **errp)
+{
+ struct vhost_user *u = dev->opaque;
+ CharBackend *chr = u->user->chr;
+ int ufd;
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_POSTCOPY_ADVISE,
+ .hdr.flags = VHOST_USER_VERSION,
+ };
+
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ error_setg(errp, "Failed to send postcopy_advise to vhost");
+ return -1;
+ }
+
+ if (vhost_user_read(dev, &msg) < 0) {
+ error_setg(errp, "Failed to get postcopy_advise reply from vhost");
+ return -1;
+ }
+
+ if (msg.hdr.request != VHOST_USER_POSTCOPY_ADVISE) {
+ error_setg(errp, "Unexpected msg type. Expected %d received %d",
+ VHOST_USER_POSTCOPY_ADVISE, msg.hdr.request);
+ return -1;
+ }
+
+ if (msg.hdr.size) {
+ error_setg(errp, "Received bad msg size.");
+ return -1;
+ }
+ ufd = qemu_chr_fe_get_msgfd(chr);
+ if (ufd < 0) {
+ error_setg(errp, "%s: Failed to get ufd", __func__);
+ return -1;
+ }
+ qemu_set_nonblock(ufd);
+
+ /* register ufd with userfault thread */
+ u->postcopy_fd.fd = ufd;
+ u->postcopy_fd.data = dev;
+ u->postcopy_fd.handler = vhost_user_postcopy_fault_handler;
+ u->postcopy_fd.waker = vhost_user_postcopy_waker;
+ u->postcopy_fd.idstr = "vhost-user"; /* Need to find unique name */
+ postcopy_register_shared_ufd(&u->postcopy_fd);
+ return 0;
+}
+
+/*
+ * Called at the switch to postcopy on reception of the 'listen' command.
+ */
+static int vhost_user_postcopy_listen(struct vhost_dev *dev, Error **errp)
+{
+ struct vhost_user *u = dev->opaque;
+ int ret;
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_POSTCOPY_LISTEN,
+ .hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
+ };
+ u->postcopy_listen = true;
+ trace_vhost_user_postcopy_listen();
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ error_setg(errp, "Failed to send postcopy_listen to vhost");
+ return -1;
+ }
+
+ ret = process_message_reply(dev, &msg);
+ if (ret) {
+ error_setg(errp, "Failed to receive reply to postcopy_listen");
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * Called at the end of postcopy
+ */
+static int vhost_user_postcopy_end(struct vhost_dev *dev, Error **errp)
+{
+ VhostUserMsg msg = {
+ .hdr.request = VHOST_USER_POSTCOPY_END,
+ .hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
+ };
+ int ret;
+ struct vhost_user *u = dev->opaque;
+
+ trace_vhost_user_postcopy_end_entry();
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ error_setg(errp, "Failed to send postcopy_end to vhost");
+ return -1;
+ }
+
+ ret = process_message_reply(dev, &msg);
+ if (ret) {
+ error_setg(errp, "Failed to receive reply to postcopy_end");
+ return ret;
+ }
+ postcopy_unregister_shared_ufd(&u->postcopy_fd);
+ close(u->postcopy_fd.fd);
+ u->postcopy_fd.handler = NULL;
+
+ trace_vhost_user_postcopy_end_exit();
+
+ return 0;
+}
+
static int vhost_user_postcopy_notifier(NotifierWithReturn *notifier,
void *opaque)
{
}
break;
+ case POSTCOPY_NOTIFY_INBOUND_ADVISE:
+ return vhost_user_postcopy_advise(dev, pnd->errp);
+
+ case POSTCOPY_NOTIFY_INBOUND_LISTEN:
+ return vhost_user_postcopy_listen(dev, pnd->errp);
+
+ case POSTCOPY_NOTIFY_INBOUND_END:
+ return vhost_user_postcopy_end(dev, pnd->errp);
+
default:
/* We ignore notifications we don't know */
break;
return 0;
}
-static int vhost_user_init(struct vhost_dev *dev, void *opaque)
+static int vhost_user_backend_init(struct vhost_dev *dev, void *opaque)
{
uint64_t features, protocol_features;
struct vhost_user *u;
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
u = g_new0(struct vhost_user, 1);
- u->chr = opaque;
+ u->user = opaque;
u->slave_fd = -1;
u->dev = dev;
dev->opaque = u;
dev->protocol_features =
protocol_features & VHOST_USER_PROTOCOL_FEATURE_MASK;
+
+ if (!dev->config_ops || !dev->config_ops->vhost_dev_config_notifier) {
+ /* Don't acknowledge CONFIG feature if device doesn't support it */
+ dev->protocol_features &= ~(1ULL << VHOST_USER_PROTOCOL_F_CONFIG);
+ } else if (!(protocol_features &
+ (1ULL << VHOST_USER_PROTOCOL_F_CONFIG))) {
+ error_report("Device expects VHOST_USER_PROTOCOL_F_CONFIG "
+ "but backend does not support it.");
+ return -1;
+ }
+
err = vhost_user_set_protocol_features(dev, dev->protocol_features);
if (err < 0) {
return err;
return 0;
}
-static int vhost_user_cleanup(struct vhost_dev *dev)
+static int vhost_user_backend_cleanup(struct vhost_dev *dev)
{
struct vhost_user *u;
postcopy_remove_notifier(&u->postcopy_notifier);
u->postcopy_notifier.notify = NULL;
}
+ u->postcopy_listen = false;
+ if (u->postcopy_fd.handler) {
+ postcopy_unregister_shared_ufd(&u->postcopy_fd);
+ close(u->postcopy_fd.fd);
+ u->postcopy_fd.handler = NULL;
+ }
if (u->slave_fd >= 0) {
qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
close(u->slave_fd);
u->slave_fd = -1;
}
+ g_free(u->region_rb);
+ u->region_rb = NULL;
+ g_free(u->region_rb_offset);
+ u->region_rb_offset = NULL;
+ u->region_rb_len = 0;
g_free(u);
dev->opaque = 0;
static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr)
{
- VhostUserMsg msg = { 0 };
+ VhostUserMsg msg = { };
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
.hdr.size = VHOST_USER_CONFIG_HDR_SIZE + config_len,
};
+ if (!virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_CONFIG)) {
+ return -1;
+ }
+
if (config_len > VHOST_USER_MAX_CONFIG_SIZE) {
return -1;
}
.hdr.size = VHOST_USER_CONFIG_HDR_SIZE + size,
};
+ if (!virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_CONFIG)) {
+ return -1;
+ }
+
if (reply_supported) {
msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
}
return 0;
}
+static bool vhost_user_mem_section_filter(struct vhost_dev *dev,
+ MemoryRegionSection *section)
+{
+ bool result;
+
+ result = memory_region_get_fd(section->mr) >= 0;
+
+ return result;
+}
+
+VhostUserState *vhost_user_init(void)
+{
+ VhostUserState *user = g_new0(struct VhostUserState, 1);
+
+ return user;
+}
+
+void vhost_user_cleanup(VhostUserState *user)
+{
+ int i;
+
+ for (i = 0; i < VIRTIO_QUEUE_MAX; i++) {
+ if (user->notifier[i].addr) {
+ object_unparent(OBJECT(&user->notifier[i].mr));
+ munmap(user->notifier[i].addr, qemu_real_host_page_size);
+ user->notifier[i].addr = NULL;
+ }
+ }
+}
+
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
- .vhost_backend_init = vhost_user_init,
- .vhost_backend_cleanup = vhost_user_cleanup,
+ .vhost_backend_init = vhost_user_backend_init,
+ .vhost_backend_cleanup = vhost_user_backend_cleanup,
.vhost_backend_memslots_limit = vhost_user_memslots_limit,
.vhost_set_log_base = vhost_user_set_log_base,
.vhost_set_mem_table = vhost_user_set_mem_table,
.vhost_set_config = vhost_user_set_config,
.vhost_crypto_create_session = vhost_user_crypto_create_session,
.vhost_crypto_close_session = vhost_user_crypto_close_session,
+ .vhost_backend_mem_section_filter = vhost_user_mem_section_filter,
};