vhost: vhost net support

This adds vhost net device support in qemu. Will be tied to tap device
and virtio by following patches.  Raw backend is currently missing,
will be worked on/submitted separately.
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>

Makefile.target

@@ -166,6 +166,8 @@ obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o vl.o
 # need to fix this properly
 obj-y += virtio-blk.o virtio-balloon.o virtio-net.o virtio-pci.o virtio-serial-bus.o
 obj-y += event_notifier.o
+obj-y += vhost_net.o
+obj-$(CONFIG_VHOST_NET) += vhost.o
 obj-y += rwhandler.o
 obj-$(CONFIG_KVM) += kvm.o kvm-all.o
 LIBS+=-lz

configure

@@ -263,6 +263,7 @@ vnc_tls=""
 vnc_sasl=""
 xen=""
 linux_aio=""
+vhost_net=""
 
 gprof="no"
 debug_tcg="no"
@@ -653,6 +654,10 @@ for opt do
   ;;
   --enable-docs) docs="yes"
   ;;
+  --disable-vhost-net) vhost_net="no"
+  ;;
+  --enable-vhost-net) vhost_net="yes"
+  ;;
   *) echo "ERROR: unknown option $opt"; show_help="yes"
   ;;
   esac
@@ -811,6 +816,8 @@ echo "  --disable-blobs          disable installing provided firmware blobs"
 echo "  --kerneldir=PATH         look for kernel includes in PATH"
 echo "  --enable-docs            enable documentation build"
 echo "  --disable-docs           disable documentation build"
+echo "  --disable-vhost-net      disable vhost-net acceleration support"
+echo "  --enable-vhost-net       enable vhost-net acceleration support"
 echo ""
 echo "NOTE: The object files are built at the place where configure is launched"
 exit 1
@@ -1502,6 +1509,32 @@ EOF
   fi
 fi
 
+##########################################
+# test for vhost net
+
+if test "$vhost_net" != "no"; then
+    if test "$kvm" != "no"; then
+            cat > $TMPC <<EOF
+    #include <linux/vhost.h>
+    int main(void) { return 0; }
+EOF
+            if compile_prog "$kvm_cflags" "" ; then
+                vhost_net=yes
+            else
+                if test "$vhost_net" = "yes" ; then
+                    feature_not_found "vhost-net"
+                fi
+                vhost_net=no
+            fi
+    else
+            if test "$vhost_net" = "yes" ; then
+                echo -e "NOTE: vhost-net feature requires KVM (--enable-kvm)."
+                feature_not_found "vhost-net"
+            fi
+            vhost_net=no
+    fi
+fi
+
 ##########################################
 # pthread probe
 PTHREADLIBS_LIST="-lpthread -lpthreadGC2"
@@ -1988,6 +2021,7 @@ echo "fdt support       $fdt"
 echo "preadv support    $preadv"
 echo "fdatasync         $fdatasync"
 echo "uuid support      $uuid"
+echo "vhost-net support $vhost_net"
 
 if test $sdl_too_old = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -2522,6 +2556,9 @@ case "$target_arch2" in
       if test "$kvm_para" = "yes"; then
         echo "CONFIG_KVM_PARA=y" >> $config_target_mak
       fi
+      if test $vhost_net = "yes" ; then
+        echo "CONFIG_VHOST_NET=y" >> $config_target_mak
+      fi
     fi
 esac
 if test "$target_bigendian" = "yes" ; then

hw/vhost.c

+/*
+ * vhost support
+ *
+ * Copyright Red Hat, Inc. 2010
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/vhost.h>
+#include <sys/ioctl.h>
+#include <sys/eventfd.h>
+#include "vhost.h"
+#include "hw/hw.h"
+/* For range_get_last */
+#include "pci.h"
+
+static void vhost_dev_sync_region(struct vhost_dev *dev,
+                                  uint64_t mfirst, uint64_t mlast,
+                                  uint64_t rfirst, uint64_t rlast)
+{
+    uint64_t start = MAX(mfirst, rfirst);
+    uint64_t end = MIN(mlast, rlast);
+    vhost_log_chunk_t *from = dev->log + start / VHOST_LOG_CHUNK;
+    vhost_log_chunk_t *to = dev->log + end / VHOST_LOG_CHUNK + 1;
+    uint64_t addr = (start / VHOST_LOG_CHUNK) * VHOST_LOG_CHUNK;
+
+    assert(end / VHOST_LOG_CHUNK < dev->log_size);
+    assert(start / VHOST_LOG_CHUNK < dev->log_size);
+    if (end < start) {
+        return;
+    }
+    for (;from < to; ++from) {
+        vhost_log_chunk_t log;
+        int bit;
+        /* We first check with non-atomic: much cheaper,
+         * and we expect non-dirty to be the common case. */
+        if (!*from) {
+            continue;
+        }
+        /* Data must be read atomically. We don't really
+         * need the barrier semantics of __sync
+         * builtins, but it's easier to use them than
+         * roll our own. */
+        log = __sync_fetch_and_and(from, 0);
+        while ((bit = sizeof(log) > sizeof(int) ?
+                ffsll(log) : ffs(log))) {
+            bit -= 1;
+            cpu_physical_memory_set_dirty(addr + bit * VHOST_LOG_PAGE);
+            log &= ~(0x1ull << bit);
+        }
+        addr += VHOST_LOG_CHUNK;
+    }
+}
+
+static int vhost_client_sync_dirty_bitmap(CPUPhysMemoryClient *client,
+                                          target_phys_addr_t start_addr,
+                                          target_phys_addr_t end_addr)
+{
+    struct vhost_dev *dev = container_of(client, struct vhost_dev, client);
+    int i;
+    if (!dev->log_enabled || !dev->started) {
+        return 0;
+    }
+    for (i = 0; i < dev->mem->nregions; ++i) {
+        struct vhost_memory_region *reg = dev->mem->regions + i;
+        vhost_dev_sync_region(dev, start_addr, end_addr,
+                              reg->guest_phys_addr,
+                              range_get_last(reg->guest_phys_addr,
+                                             reg->memory_size));
+    }
+    for (i = 0; i < dev->nvqs; ++i) {
+        struct vhost_virtqueue *vq = dev->vqs + i;
+        vhost_dev_sync_region(dev, start_addr, end_addr, vq->used_phys,
+                              range_get_last(vq->used_phys, vq->used_size));
+    }
+    return 0;
+}
+
+/* Assign/unassign. Keep an unsorted array of non-overlapping
+ * memory regions in dev->mem. */
+static void vhost_dev_unassign_memory(struct vhost_dev *dev,
+                                      uint64_t start_addr,
+                                      uint64_t size)
+{
+    int from, to, n = dev->mem->nregions;
+    /* Track overlapping/split regions for sanity checking. */
+    int overlap_start = 0, overlap_end = 0, overlap_middle = 0, split = 0;
+
+    for (from = 0, to = 0; from < n; ++from, ++to) {
+        struct vhost_memory_region *reg = dev->mem->regions + to;
+        uint64_t reglast;
+        uint64_t memlast;
+        uint64_t change;
+
+        /* clone old region */
+        if (to != from) {
+            memcpy(reg, dev->mem->regions + from, sizeof *reg);
+        }
+
+        /* No overlap is simple */
+        if (!ranges_overlap(reg->guest_phys_addr, reg->memory_size,
+                            start_addr, size)) {
+            continue;
+        }
+
+        /* Split only happens if supplied region
+         * is in the middle of an existing one. Thus it can not
+         * overlap with any other existing region. */
+        assert(!split);
+
+        reglast = range_get_last(reg->guest_phys_addr, reg->memory_size);
+        memlast = range_get_last(start_addr, size);
+
+        /* Remove whole region */
+        if (start_addr <= reg->guest_phys_addr && memlast >= reglast) {
+            --dev->mem->nregions;
+            --to;
+            assert(to >= 0);
+            ++overlap_middle;
+            continue;
+        }
+
+        /* Shrink region */
+        if (memlast >= reglast) {
+            reg->memory_size = start_addr - reg->guest_phys_addr;
+            assert(reg->memory_size);
+            assert(!overlap_end);
+            ++overlap_end;
+            continue;
+        }
+
+        /* Shift region */
+        if (start_addr <= reg->guest_phys_addr) {
+            change = memlast + 1 - reg->guest_phys_addr;
+            reg->memory_size -= change;
+            reg->guest_phys_addr += change;
+            reg->userspace_addr += change;
+            assert(reg->memory_size);
+            assert(!overlap_start);
+            ++overlap_start;
+            continue;
+        }
+
+        /* This only happens if supplied region
+         * is in the middle of an existing one. Thus it can not
+         * overlap with any other existing region. */
+        assert(!overlap_start);
+        assert(!overlap_end);
+        assert(!overlap_middle);
+        /* Split region: shrink first part, shift second part. */
+        memcpy(dev->mem->regions + n, reg, sizeof *reg);
+        reg->memory_size = start_addr - reg->guest_phys_addr;
+        assert(reg->memory_size);
+        change = memlast + 1 - reg->guest_phys_addr;
+        reg = dev->mem->regions + n;
+        reg->memory_size -= change;
+        assert(reg->memory_size);
+        reg->guest_phys_addr += change;
+        reg->userspace_addr += change;
+        /* Never add more than 1 region */
+        assert(dev->mem->nregions == n);
+        ++dev->mem->nregions;
+        ++split;
+    }
+}
+
+/* Called after unassign, so no regions overlap the given range. */
+static void vhost_dev_assign_memory(struct vhost_dev *dev,
+                                    uint64_t start_addr,
+                                    uint64_t size,
+                                    uint64_t uaddr)
+{
+    int from, to;
+    struct vhost_memory_region *merged = NULL;
+    for (from = 0, to = 0; from < dev->mem->nregions; ++from, ++to) {
+        struct vhost_memory_region *reg = dev->mem->regions + to;
+        uint64_t prlast, urlast;
+        uint64_t pmlast, umlast;
+        uint64_t s, e, u;
+
+        /* clone old region */
+        if (to != from) {
+            memcpy(reg, dev->mem->regions + from, sizeof *reg);
+        }
+        prlast = range_get_last(reg->guest_phys_addr, reg->memory_size);
+        pmlast = range_get_last(start_addr, size);
+        urlast = range_get_last(reg->userspace_addr, reg->memory_size);
+        umlast = range_get_last(uaddr, size);
+
+        /* check for overlapping regions: should never happen. */
+        assert(prlast < start_addr || pmlast < reg->guest_phys_addr);
+        /* Not an adjacent or overlapping region - do not merge. */
+        if ((prlast + 1 != start_addr || urlast + 1 != uaddr) &&
+            (pmlast + 1 != reg->guest_phys_addr ||
+             umlast + 1 != reg->userspace_addr)) {
+            continue;
+        }
+
+        if (merged) {
+            --to;
+            assert(to >= 0);
+        } else {
+            merged = reg;
+        }
+        u = MIN(uaddr, reg->userspace_addr);
+        s = MIN(start_addr, reg->guest_phys_addr);
+        e = MAX(pmlast, prlast);
+        uaddr = merged->userspace_addr = u;
+        start_addr = merged->guest_phys_addr = s;
+        size = merged->memory_size = e - s + 1;
+        assert(merged->memory_size);
+    }
+
+    if (!merged) {
+        struct vhost_memory_region *reg = dev->mem->regions + to;
+        memset(reg, 0, sizeof *reg);
+        reg->memory_size = size;
+        assert(reg->memory_size);
+        reg->guest_phys_addr = start_addr;
+        reg->userspace_addr = uaddr;
+        ++to;
+    }
+    assert(to <= dev->mem->nregions + 1);
+    dev->mem->nregions = to;
+}
+
+static uint64_t vhost_get_log_size(struct vhost_dev *dev)
+{
+    uint64_t log_size = 0;
+    int i;
+    for (i = 0; i < dev->mem->nregions; ++i) {
+        struct vhost_memory_region *reg = dev->mem->regions + i;
+        uint64_t last = range_get_last(reg->guest_phys_addr,
+                                       reg->memory_size);
+        log_size = MAX(log_size, last / VHOST_LOG_CHUNK + 1);
+    }
+    for (i = 0; i < dev->nvqs; ++i) {
+        struct vhost_virtqueue *vq = dev->vqs + i;
+        uint64_t last = vq->used_phys + vq->used_size - 1;
+        log_size = MAX(log_size, last / VHOST_LOG_CHUNK + 1);
+    }
+    return log_size;
+}
+
+static inline void vhost_dev_log_resize(struct vhost_dev* dev, uint64_t size)
+{
+    vhost_log_chunk_t *log;
+    uint64_t log_base;
+    int r;
+    if (size) {
+        log = qemu_mallocz(size * sizeof *log);
+    } else {
+        log = NULL;
+    }
+    log_base = (uint64_t)(unsigned long)log;
+    r = ioctl(dev->control, VHOST_SET_LOG_BASE, &log_base);
+    assert(r >= 0);
+    vhost_client_sync_dirty_bitmap(&dev->client, 0,
+                                   (target_phys_addr_t)~0x0ull);
+    if (dev->log) {
+        qemu_free(dev->log);
+    }
+    dev->log = log;
+    dev->log_size = size;
+}
+
+static int vhost_verify_ring_mappings(struct vhost_dev *dev,
+                                      uint64_t start_addr,
+                                      uint64_t size)
+{
+    int i;
+    for (i = 0; i < dev->nvqs; ++i) {
+        struct vhost_virtqueue *vq = dev->vqs + i;
+        target_phys_addr_t l;
+        void *p;
+
+        if (!ranges_overlap(start_addr, size, vq->ring_phys, vq->ring_size)) {
+            continue;
+        }
+        l = vq->ring_size;
+        p = cpu_physical_memory_map(vq->ring_phys, &l, 1);
+        if (!p || l != vq->ring_size) {
+            fprintf(stderr, "Unable to map ring buffer for ring %d\n", i);
+            return -ENOMEM;
+        }
+        if (p != vq->ring) {
+            fprintf(stderr, "Ring buffer relocated for ring %d\n", i);
+            return -EBUSY;
+        }
+        cpu_physical_memory_unmap(p, l, 0, 0);
+    }
+    return 0;
+}
+
+static void vhost_client_set_memory(CPUPhysMemoryClient *client,
+                                    target_phys_addr_t start_addr,
+                                    ram_addr_t size,
+                                    ram_addr_t phys_offset)
+{
+    struct vhost_dev *dev = container_of(client, struct vhost_dev, client);
+    ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
+    int s = offsetof(struct vhost_memory, regions) +
+        (dev->mem->nregions + 1) * sizeof dev->mem->regions[0];
+    uint64_t log_size;
+    int r;
+    dev->mem = qemu_realloc(dev->mem, s);
+
+    assert(size);
+
+    vhost_dev_unassign_memory(dev, start_addr, size);
+    if (flags == IO_MEM_RAM) {
+        /* Add given mapping, merging adjacent regions if any */
+        vhost_dev_assign_memory(dev, start_addr, size,
+                                (uintptr_t)qemu_get_ram_ptr(phys_offset));
+    } else {
+        /* Remove old mapping for this memory, if any. */
+        vhost_dev_unassign_memory(dev, start_addr, size);
+    }
+
+    if (!dev->started) {
+        return;
+    }
+
+    if (dev->started) {
+        r = vhost_verify_ring_mappings(dev, start_addr, size);
+        assert(r >= 0);
+    }
+
+    if (!dev->log_enabled) {
+        r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem);
+        assert(r >= 0);
+        return;
+    }
+    log_size = vhost_get_log_size(dev);
+    /* We allocate an extra 4K bytes to log,
+     * to reduce the * number of reallocations. */
+#define VHOST_LOG_BUFFER (0x1000 / sizeof *dev->log)
+    /* To log more, must increase log size before table update. */
+    if (dev->log_size < log_size) {
+        vhost_dev_log_resize(dev, log_size + VHOST_LOG_BUFFER);
+    }
+    r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem);
+    assert(r >= 0);
+    /* To log less, can only decrease log size after table update. */
+    if (dev->log_size > log_size + VHOST_LOG_BUFFER) {
+        vhost_dev_log_resize(dev, log_size);
+    }
+}
+
+static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
+                                    struct vhost_virtqueue *vq,
+                                    unsigned idx, bool enable_log)
+{
+    struct vhost_vring_addr addr = {
+        .index = idx,
+        .desc_user_addr = (u_int64_t)(unsigned long)vq->desc,
+        .avail_user_addr = (u_int64_t)(unsigned long)vq->avail,
+        .used_user_addr = (u_int64_t)(unsigned long)vq->used,
+        .log_guest_addr = vq->used_phys,
+        .flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0,
+    };
+    int r = ioctl(dev->control, VHOST_SET_VRING_ADDR, &addr);
+    if (r < 0) {
+        return -errno;
+    }
+    return 0;
+}
+
+static int vhost_dev_set_features(struct vhost_dev *dev, bool enable_log)
+{
+    uint64_t features = dev->acked_features;
+    int r;
+    if (enable_log) {
+        features |= 0x1 << VHOST_F_LOG_ALL;
+    }
+    r = ioctl(dev->control, VHOST_SET_FEATURES, &features);
+    return r < 0 ? -errno : 0;
+}
+
+static int vhost_dev_set_log(struct vhost_dev *dev, bool enable_log)
+{
+    int r, t, i;
+    r = vhost_dev_set_features(dev, enable_log);
+    if (r < 0) {
+        goto err_features;
+    }
+    for (i = 0; i < dev->nvqs; ++i) {
+        r = vhost_virtqueue_set_addr(dev, dev->vqs + i, i,
+                                     enable_log);
+        if (r < 0) {
+            goto err_vq;
+        }
+    }
+    return 0;
+err_vq:
+    for (; i >= 0; --i) {
+        t = vhost_virtqueue_set_addr(dev, dev->vqs + i, i,
+                                     dev->log_enabled);
+        assert(t >= 0);
+    }
+    t = vhost_dev_set_features(dev, dev->log_enabled);
+    assert(t >= 0);
+err_features:
+    return r;
+}
+
+static int vhost_client_migration_log(CPUPhysMemoryClient *client,
+                                      int enable)
+{
+    struct vhost_dev *dev = container_of(client, struct vhost_dev, client);
+    int r;
+    if (!!enable == dev->log_enabled) {
+        return 0;
+    }
+    if (!dev->started) {
+        dev->log_enabled = enable;
+        return 0;
+    }
+    if (!enable) {
+        r = vhost_dev_set_log(dev, false);
+        if (r < 0) {
+            return r;
+        }
+        if (dev->log) {
+            qemu_free(dev->log);
+        }
+        dev->log = NULL;
+        dev->log_size = 0;
+    } else {
+        vhost_dev_log_resize(dev, vhost_get_log_size(dev));
+        r = vhost_dev_set_log(dev, true);
+        if (r < 0) {
+            return r;
+        }
+    }
+    dev->log_enabled = enable;
+    return 0;
+}
+
+static int vhost_virtqueue_init(struct vhost_dev *dev,
+                                struct VirtIODevice *vdev,
+                                struct vhost_virtqueue *vq,
+                                unsigned idx)
+{
+    target_phys_addr_t s, l, a;
+    int r;
+    struct vhost_vring_file file = {
+        .index = idx,
+    };
+    struct vhost_vring_state state = {
+        .index = idx,
+    };
+    struct VirtQueue *vvq = virtio_get_queue(vdev, idx);
+
+    if (!vdev->binding->set_guest_notifier) {
+        fprintf(stderr, "binding does not support guest notifiers\n");
+        return -ENOSYS;
+    }
+
+    if (!vdev->binding->set_host_notifier) {
+        fprintf(stderr, "binding does not support host notifiers\n");
+        return -ENOSYS;
+    }
+
+    vq->num = state.num = virtio_queue_get_num(vdev, idx);
+    r = ioctl(dev->control, VHOST_SET_VRING_NUM, &state);
+    if (r) {
+        return -errno;
+    }
+
+    state.num = virtio_queue_get_last_avail_idx(vdev, idx);
+    r = ioctl(dev->control, VHOST_SET_VRING_BASE, &state);
+    if (r) {
+        return -errno;
+    }
+
+    s = l = virtio_queue_get_desc_size(vdev, idx);
+    a = virtio_queue_get_desc_addr(vdev, idx);
+    vq->desc = cpu_physical_memory_map(a, &l, 0);
+    if (!vq->desc || l != s) {
+        r = -ENOMEM;
+        goto fail_alloc_desc;
+    }
+    s = l = virtio_queue_get_avail_size(vdev, idx);
+    a = virtio_queue_get_avail_addr(vdev, idx);
+    vq->avail = cpu_physical_memory_map(a, &l, 0);
+    if (!vq->avail || l != s) {
+        r = -ENOMEM;
+        goto fail_alloc_avail;
+    }
+    vq->used_size = s = l = virtio_queue_get_used_size(vdev, idx);
+    vq->used_phys = a = virtio_queue_get_used_addr(vdev, idx);
+    vq->used = cpu_physical_memory_map(a, &l, 1);
+    if (!vq->used || l != s) {
+        r = -ENOMEM;
+        goto fail_alloc_used;
+    }
+
+    vq->ring_size = s = l = virtio_queue_get_ring_size(vdev, idx);
+    vq->ring_phys = a = virtio_queue_get_ring_addr(vdev, idx);
+    vq->ring = cpu_physical_memory_map(a, &l, 1);
+    if (!vq->ring || l != s) {
+        r = -ENOMEM;
+        goto fail_alloc_ring;
+    }
+
+    r = vhost_virtqueue_set_addr(dev, vq, idx, dev->log_enabled);
+    if (r < 0) {
+        r = -errno;
+        goto fail_alloc;
+    }
+    r = vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, true);
+    if (r < 0) {
+        fprintf(stderr, "Error binding guest notifier: %d\n", -r);
+        goto fail_guest_notifier;
+    }
+
+    r = vdev->binding->set_host_notifier(vdev->binding_opaque, idx, true);
+    if (r < 0) {
+        fprintf(stderr, "Error binding host notifier: %d\n", -r);
+        goto fail_host_notifier;
+    }
+
+    file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq));
+    r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file);
+    if (r) {
+        goto fail_kick;
+    }
+
+    file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq));
+    r = ioctl(dev->control, VHOST_SET_VRING_CALL, &file);
+    if (r) {
+        goto fail_call;
+    }
+
+    return 0;
+
+fail_call:
+fail_kick:
+    vdev->binding->set_host_notifier(vdev->binding_opaque, idx, false);
+fail_host_notifier:
+    vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, false);
+fail_guest_notifier:
+fail_alloc:
+    cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx),
+                              0, 0);
+fail_alloc_ring:
+    cpu_physical_memory_unmap(vq->used, virtio_queue_get_used_size(vdev, idx),
+                              0, 0);
+fail_alloc_used:
+    cpu_physical_memory_unmap(vq->avail, virtio_queue_get_avail_size(vdev, idx),
+                              0, 0);
+fail_alloc_avail:
+    cpu_physical_memory_unmap(vq->desc, virtio_queue_get_desc_size(vdev, idx),
+                              0, 0);
+fail_alloc_desc:
+    return r;
+}
+
+static void vhost_virtqueue_cleanup(struct vhost_dev *dev,
+                                    struct VirtIODevice *vdev,
+                                    struct vhost_virtqueue *vq,
+                                    unsigned idx)
+{
+    struct vhost_vring_state state = {
+        .index = idx,
+    };
+    int r;
+    r = vdev->binding->set_guest_notifier(vdev->binding_opaque, idx, false);
+    if (r < 0) {
+        fprintf(stderr, "vhost VQ %d guest cleanup failed: %d\n", idx, r);
+        fflush(stderr);
+    }
+    assert (r >= 0);
+
+    r = vdev->binding->set_host_notifier(vdev->binding_opaque, idx, false);
+    if (r < 0) {
+        fprintf(stderr, "vhost VQ %d host cleanup failed: %d\n", idx, r);
+        fflush(stderr);
+    }
+    assert (r >= 0);
+    r = ioctl(dev->control, VHOST_GET_VRING_BASE, &state);
+    if (r < 0) {
+        fprintf(stderr, "vhost VQ %d ring restore failed: %d\n", idx, r);
+        fflush(stderr);
+    }
+    virtio_queue_set_last_avail_idx(vdev, idx, state.num);
+    assert (r >= 0);
+    cpu_physical_memory_unmap(vq->ring, virtio_queue_get_ring_size(vdev, idx),
+                              0, virtio_queue_get_ring_size(vdev, idx));
+    cpu_physical_memory_unmap(vq->used, virtio_queue_get_used_size(vdev, idx),
+                              1, virtio_queue_get_used_size(vdev, idx));
+    cpu_physical_memory_unmap(vq->avail, virtio_queue_get_avail_size(vdev, idx),
+                              0, virtio_queue_get_avail_size(vdev, idx));
+    cpu_physical_memory_unmap(vq->desc, virtio_queue_get_desc_size(vdev, idx),
+                              0, virtio_queue_get_desc_size(vdev, idx));
+}
+
+int vhost_dev_init(struct vhost_dev *hdev, int devfd)
+{
+    uint64_t features;
+    int r;
+    if (devfd >= 0) {
+        hdev->control = devfd;
+    } else {
+        hdev->control = open("/dev/vhost-net", O_RDWR);
+        if (hdev->control < 0) {
+            return -errno;
+        }
+    }
+    r = ioctl(hdev->control, VHOST_SET_OWNER, NULL);
+    if (r < 0) {
+        goto fail;
+    }
+
+    r = ioctl(hdev->control, VHOST_GET_FEATURES, &features);
+    if (r < 0) {
+        goto fail;
+    }
+    hdev->features = features;
+
+    hdev->client.set_memory = vhost_client_set_memory;
+    hdev->client.sync_dirty_bitmap = vhost_client_sync_dirty_bitmap;
+    hdev->client.migration_log = vhost_client_migration_log;
+    hdev->mem = qemu_mallocz(offsetof(struct vhost_memory, regions));
+    hdev->log = NULL;
+    hdev->log_size = 0;
+    hdev->log_enabled = false;
+    hdev->started = false;
+    cpu_register_phys_memory_client(&hdev->client);
+    return 0;
+fail:
+    r = -errno;
+    close(hdev->control);
+    return r;
+}
+
+void vhost_dev_cleanup(struct vhost_dev *hdev)
+{
+    cpu_unregister_phys_memory_client(&hdev->client);
+    qemu_free(hdev->mem);
+    close(hdev->control);
+}
+
+int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
+{
+    int i, r;
+
+    r = vhost_dev_set_features(hdev, hdev->log_enabled);
+    if (r < 0) {
+        goto fail;
+    }
+    r = ioctl(hdev->control, VHOST_SET_MEM_TABLE, hdev->mem);
+    if (r < 0) {
+        r = -errno;
+        goto fail;
+    }
+    if (hdev->log_enabled) {
+        hdev->log_size = vhost_get_log_size(hdev);
+        hdev->log = hdev->log_size ?
+            qemu_mallocz(hdev->log_size * sizeof *hdev->log) : NULL;
+        r = ioctl(hdev->control, VHOST_SET_LOG_BASE,
+                  (uint64_t)(unsigned long)hdev->log);
+        if (r < 0) {
+            r = -errno;
+            goto fail;
+        }
+    }
+
+    for (i = 0; i < hdev->nvqs; ++i) {
+        r = vhost_virtqueue_init(hdev,
+                                 vdev,
+                                 hdev->vqs + i,
+                                 i);
+        if (r < 0) {
+            goto fail_vq;
+        }
+    }
+    hdev->started = true;
+
+    return 0;
+fail_vq:
+    while (--i >= 0) {
+        vhost_virtqueue_cleanup(hdev,
+                                vdev,
+                                hdev->vqs + i,
+                                i);
+    }
+fail:
+    return r;
+}
+
+void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
+{
+    int i;
+    for (i = 0; i < hdev->nvqs; ++i) {
+        vhost_virtqueue_cleanup(hdev,
+                                vdev,
+                                hdev->vqs + i,
+                                i);
+    }
+    vhost_client_sync_dirty_bitmap(&hdev->client, 0,
+                                   (target_phys_addr_t)~0x0ull);
+    hdev->started = false;
+    qemu_free(hdev->log);
+    hdev->log_size = 0;
+}

hw/vhost.h

+#ifndef VHOST_H
+#define VHOST_H
+
+#include "hw/hw.h"
+#include "hw/virtio.h"
+
+/* Generic structures common for any vhost based device. */
+struct vhost_virtqueue {
+    int kick;
+    int call;
+    void *desc;
+    void *avail;
+    void *used;
+    int num;
+    unsigned long long used_phys;
+    unsigned used_size;
+    void *ring;
+    unsigned long long ring_phys;
+    unsigned ring_size;
+};
+
+typedef unsigned long vhost_log_chunk_t;
+#define VHOST_LOG_PAGE 0x1000
+#define VHOST_LOG_BITS (8 * sizeof(vhost_log_chunk_t))
+#define VHOST_LOG_CHUNK (VHOST_LOG_PAGE * VHOST_LOG_BITS)
+
+struct vhost_memory;
+struct vhost_dev {
+    CPUPhysMemoryClient client;
+    int control;
+    struct vhost_memory *mem;
+    struct vhost_virtqueue *vqs;
+    int nvqs;
+    unsigned long long features;
+    unsigned long long acked_features;
+    unsigned long long backend_features;
+    bool started;
+    bool log_enabled;
+    vhost_log_chunk_t *log;
+    unsigned long long log_size;
+};
+
+int vhost_dev_init(struct vhost_dev *hdev, int devfd);
+void vhost_dev_cleanup(struct vhost_dev *hdev);
+int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev);
+void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev);
+
+#endif

hw/vhost_net.c

+/*
+ * vhost-net support
+ *
+ * Copyright Red Hat, Inc. 2010
+ *
+ * Authors:
+ *  Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include "net.h"
+#include "net/tap.h"
+
+#include "virtio-net.h"
+#include "vhost_net.h"
+
+#include "config.h"
+
+#ifdef CONFIG_VHOST_NET
+#include <linux/vhost.h>
+#include <sys/eventfd.h>
+#include <sys/socket.h>
+#include <linux/kvm.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <linux/virtio_ring.h>
+#include <netpacket/packet.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+
+#include <stdio.h>
+
+#include "vhost.h"
+
+struct vhost_net {
+    struct vhost_dev dev;
+    struct vhost_virtqueue vqs[2];
+    int backend;
+    VLANClientState *vc;
+};
+
+unsigned vhost_net_get_features(struct vhost_net *net, unsigned features)
+{
+    /* Clear features not supported by host kernel. */
+    if (!(net->dev.features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY))) {
+        features &= ~(1 << VIRTIO_F_NOTIFY_ON_EMPTY);
+    }
+    if (!(net->dev.features & (1 << VIRTIO_RING_F_INDIRECT_DESC))) {
+        features &= ~(1 << VIRTIO_RING_F_INDIRECT_DESC);
+    }
+    return features;
+}
+
+void vhost_net_ack_features(struct vhost_net *net, unsigned features)
+{
+    net->dev.acked_features = net->dev.backend_features;
+    if (features & (1 << VIRTIO_F_NOTIFY_ON_EMPTY)) {
+        net->dev.acked_features |= (1 << VIRTIO_F_NOTIFY_ON_EMPTY);
+    }
+    if (features & (1 << VIRTIO_RING_F_INDIRECT_DESC)) {
+        net->dev.acked_features |= (1 << VIRTIO_RING_F_INDIRECT_DESC);
+    }
+}
+
+static int vhost_net_get_fd(VLANClientState *backend)
+{
+    switch (backend->info->type) {
+    case NET_CLIENT_TYPE_TAP:
+        return tap_get_fd(backend);
+    default:
+        fprintf(stderr, "vhost-net requires tap backend\n");
+        return -EBADFD;
+    }
+}
+
+struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd)
+{
+    int r;
+    struct vhost_net *net = qemu_malloc(sizeof *net);
+    if (!backend) {
+        fprintf(stderr, "vhost-net requires backend to be setup\n");
+        goto fail;
+    }
+    r = vhost_net_get_fd(backend);
+    if (r < 0) {
+        goto fail;
+    }
+    net->vc = backend;
+    net->dev.backend_features = tap_has_vnet_hdr(backend) ? 0 :
+        (1 << VHOST_NET_F_VIRTIO_NET_HDR);
+    net->backend = r;
+
+    r = vhost_dev_init(&net->dev, devfd);
+    if (r < 0) {
+        goto fail;
+    }
+    if (~net->dev.features & net->dev.backend_features) {
+        fprintf(stderr, "vhost lacks feature mask %llu for backend\n",
+                ~net->dev.features & net->dev.backend_features);
+        vhost_dev_cleanup(&net->dev);
+        goto fail;
+    }
+
+    /* Set sane init value. Override when guest acks. */
+    vhost_net_ack_features(net, 0);
+    return net;
+fail:
+    qemu_free(net);
+    return NULL;
+}
+
+int vhost_net_start(struct vhost_net *net,
+                    VirtIODevice *dev)
+{
+    struct vhost_vring_file file = { };
+    int r;
+
+    net->dev.nvqs = 2;
+    net->dev.vqs = net->vqs;
+    r = vhost_dev_start(&net->dev, dev);
+    if (r < 0) {
+        return r;
+    }
+
+    net->vc->info->poll(net->vc, false);
+    qemu_set_fd_handler(net->backend, NULL, NULL, NULL);
+    file.fd = net->backend;
+    for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
+        r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
+        if (r < 0) {
+            r = -errno;
+            goto fail;
+        }
+    }
+    return 0;
+fail:
+    file.fd = -1;
+    while (--file.index >= 0) {
+        int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
+        assert(r >= 0);
+    }
+    net->vc->info->poll(net->vc, true);
+    vhost_dev_stop(&net->dev, dev);
+    return r;
+}
+
+void vhost_net_stop(struct vhost_net *net,
+                    VirtIODevice *dev)
+{
+    struct vhost_vring_file file = { .fd = -1 };
+
+    for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
+        int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
+        assert(r >= 0);
+    }
+    net->vc->info->poll(net->vc, true);
+    vhost_dev_stop(&net->dev, dev);
+}
+
+void vhost_net_cleanup(struct vhost_net *net)
+{
+    vhost_dev_cleanup(&net->dev);
+    qemu_free(net);
+}
+#else
+struct vhost_net *vhost_net_init(VLANClientState *backend, int devfd)
+{
+	return NULL;
+}
+
+int vhost_net_start(struct vhost_net *net,
+		    VirtIODevice *dev)
+{
+	return -ENOSYS;
+}
+void vhost_net_stop(struct vhost_net *net,
+		    VirtIODevice *dev)
+{
+}
+
+void vhost_net_cleanup(struct vhost_net *net)
+{
+}
+
+unsigned vhost_net_get_features(struct vhost_net *net, unsigned features)
+{
+	return features;
+}
+void vhost_net_ack_features(struct vhost_net *net, unsigned features)
+{
+}
+#endif

hw/vhost_net.h

+#ifndef VHOST_NET_H
+#define VHOST_NET_H
+
+#include "net.h"
+
+struct vhost_net;
+typedef struct vhost_net VHostNetState;
+
+VHostNetState *vhost_net_init(VLANClientState *backend, int devfd);
+
+int vhost_net_start(VHostNetState *net, VirtIODevice *dev);
+void vhost_net_stop(VHostNetState *net, VirtIODevice *dev);
+
+void vhost_net_cleanup(VHostNetState *net);
+
+unsigned vhost_net_get_features(VHostNetState *net, unsigned features);
+void vhost_net_ack_features(VHostNetState *net, unsigned features);
+
+#endif