net: Adding netmap network backend

This patch adds support for a network backend based on netmap.
netmap is a framework for high speed packet I/O. You can use it
to build extremely fast traffic generators, monitors, software
switches or network middleboxes. Its companion software switch
VALE lets you interconnect virtual machines.
netmap and VALE are implemented as a non-intrusive kernel module,
support NICs from multiple vendors, are part of standard FreeBSD
distributions and available in source format for Linux too.

To compile QEMU with netmap support, use the following configure
options:
    ./configure [...] --enable-netmap --extra-cflags=-I/path/to/netmap/sys
where "/path/to/netmap" contains the netmap source code, available at
    http://info.iet.unipi.it/~luigi/netmap/

The same webpage contains more information about the netmap project
(together with papers and presentations).

Signed-off-by: Vincenzo Maffione <v.maffione@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

4 files changed, 447 insertions, 0 deletions

diff --git a/net/Makefile.objs b/net/Makefile.objs
index 4854a14fe4..c25fe6920c 100644
--- a/net/Makefile.objs
+++ b/net/Makefile.objs
@@ -11,3 +11,4 @@ common-obj-$(CONFIG_AIX) += tap-aix.o
 common-obj-$(CONFIG_HAIKU) += tap-haiku.o
 common-obj-$(CONFIG_SLIRP) += slirp.o
 common-obj-$(CONFIG_VDE) += vde.o
+common-obj-$(CONFIG_NETMAP) += netmap.o
diff --git a/net/clients.h b/net/clients.h
index 77932942bd..7322ff5f33 100644
--- a/net/clients.h
+++ b/net/clients.h
@@ -52,4 +52,9 @@ int net_init_vde(const NetClientOptions *opts, const char *name,
                  NetClientState *peer);
 #endif
 
+#ifdef CONFIG_NETMAP
+int net_init_netmap(const NetClientOptions *opts, const char *name,
+                    NetClientState *peer);
+#endif
+
 #endif /* QEMU_NET_CLIENTS_H */
diff --git a/net/net.c b/net/net.c
index 0a88e68253..ae8e5e5c35 100644
--- a/net/net.c
+++ b/net/net.c
@@ -726,6 +726,9 @@ static int (* const net_client_init_fun[NET_CLIENT_OPTIONS_KIND_MAX])(
 #ifdef CONFIG_VDE
         [NET_CLIENT_OPTIONS_KIND_VDE]       = net_init_vde,
 #endif
+#ifdef CONFIG_NETMAP
+        [NET_CLIENT_OPTIONS_KIND_NETMAP]    = net_init_netmap,
+#endif
         [NET_CLIENT_OPTIONS_KIND_DUMP]      = net_init_dump,
 #ifdef CONFIG_NET_BRIDGE
         [NET_CLIENT_OPTIONS_KIND_BRIDGE]    = net_init_bridge,
@@ -757,6 +760,9 @@ static int net_client_init1(const void *object, int is_netdev, Error **errp)
 #ifdef CONFIG_VDE
         case NET_CLIENT_OPTIONS_KIND_VDE:
 #endif
+#ifdef CONFIG_NETMAP
+        case NET_CLIENT_OPTIONS_KIND_NETMAP:
+#endif
 #ifdef CONFIG_NET_BRIDGE
         case NET_CLIENT_OPTIONS_KIND_BRIDGE:
 #endif
diff --git a/net/netmap.c b/net/netmap.c
new file mode 100644
index 0000000000..0ccc4976b5
--- /dev/null
+++ b/net/netmap.c
@@ -0,0 +1,435 @@
+/*
+ * netmap access for qemu
+ *
+ * Copyright (c) 2012-2013 Luigi Rizzo
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+
+#include <sys/ioctl.h>
+#include <net/if.h>
+#include <sys/mman.h>
+#include <stdint.h>
+#include <net/netmap.h>
+#include <net/netmap_user.h>
+
+#include "net/net.h"
+#include "clients.h"
+#include "sysemu/sysemu.h"
+#include "qemu/error-report.h"
+#include "qemu/iov.h"
+
+/* Private netmap device info. */
+typedef struct NetmapPriv {
+    int                 fd;
+    size_t              memsize;
+    void                *mem;
+    struct netmap_if    *nifp;
+    struct netmap_ring  *rx;
+    struct netmap_ring  *tx;
+    char                fdname[PATH_MAX];        /* Normally "/dev/netmap". */
+    char                ifname[IFNAMSIZ];
+} NetmapPriv;
+
+typedef struct NetmapState {
+    NetClientState      nc;
+    NetmapPriv          me;
+    bool                read_poll;
+    bool                write_poll;
+    struct iovec        iov[IOV_MAX];
+} NetmapState;
+
+#define D(format, ...)                                          \
+    do {                                                        \
+        struct timeval __xxts;                                  \
+        gettimeofday(&__xxts, NULL);                            \
+        printf("%03d.%06d %s [%d] " format "\n",                \
+                (int)__xxts.tv_sec % 1000, (int)__xxts.tv_usec, \
+                __func__, __LINE__, ##__VA_ARGS__);         \
+    } while (0)
+
+/* Rate limited version of "D", lps indicates how many per second */
+#define RD(lps, format, ...)                                    \
+    do {                                                        \
+        static int t0, __cnt;                                   \
+        struct timeval __xxts;                                  \
+        gettimeofday(&__xxts, NULL);                            \
+        if (t0 != __xxts.tv_sec) {                              \
+            t0 = __xxts.tv_sec;                                 \
+            __cnt = 0;                                          \
+        }                                                       \
+        if (__cnt++ < lps) {                                    \
+            D(format, ##__VA_ARGS__);                           \
+        }                                                       \
+    } while (0)
+
+
+#ifndef __FreeBSD__
+#define pkt_copy bcopy
+#else
+/* A fast copy routine only for multiples of 64 bytes, non overlapped. */
+static inline void
+pkt_copy(const void *_src, void *_dst, int l)
+{
+    const uint64_t *src = _src;
+    uint64_t *dst = _dst;
+    if (unlikely(l >= 1024)) {
+        bcopy(src, dst, l);
+        return;
+    }
+    for (; l > 0; l -= 64) {
+        *dst++ = *src++;
+        *dst++ = *src++;
+        *dst++ = *src++;
+        *dst++ = *src++;
+        *dst++ = *src++;
+        *dst++ = *src++;
+        *dst++ = *src++;
+        *dst++ = *src++;
+    }
+}
+#endif /* __FreeBSD__ */
+
+/*
+ * Open a netmap device. We assume there is only one queue
+ * (which is the case for the VALE bridge).
+ */
+static int netmap_open(NetmapPriv *me)
+{
+    int fd;
+    int err;
+    size_t l;
+    struct nmreq req;
+
+    me->fd = fd = open(me->fdname, O_RDWR);
+    if (fd < 0) {
+        error_report("Unable to open netmap device '%s' (%s)",
+                        me->fdname, strerror(errno));
+        return -1;
+    }
+    memset(&req, 0, sizeof(req));
+    pstrcpy(req.nr_name, sizeof(req.nr_name), me->ifname);
+    req.nr_ringid = NETMAP_NO_TX_POLL;
+    req.nr_version = NETMAP_API;
+    err = ioctl(fd, NIOCREGIF, &req);
+    if (err) {
+        error_report("Unable to register %s: %s", me->ifname, strerror(errno));
+        goto error;
+    }
+    l = me->memsize = req.nr_memsize;
+
+    me->mem = mmap(0, l, PROT_WRITE | PROT_READ, MAP_SHARED, fd, 0);
+    if (me->mem == MAP_FAILED) {
+        error_report("Unable to mmap netmap shared memory: %s",
+                        strerror(errno));
+        me->mem = NULL;
+        goto error;
+    }
+
+    me->nifp = NETMAP_IF(me->mem, req.nr_offset);
+    me->tx = NETMAP_TXRING(me->nifp, 0);
+    me->rx = NETMAP_RXRING(me->nifp, 0);
+    return 0;
+
+error:
+    close(me->fd);
+    return -1;
+}
+
+/* Tell the event-loop if the netmap backend can send packets
+   to the frontend. */
+static int netmap_can_send(void *opaque)
+{
+    NetmapState *s = opaque;
+
+    return qemu_can_send_packet(&s->nc);
+}
+
+static void netmap_send(void *opaque);
+static void netmap_writable(void *opaque);
+
+/* Set the event-loop handlers for the netmap backend. */
+static void netmap_update_fd_handler(NetmapState *s)
+{
+    qemu_set_fd_handler2(s->me.fd,
+                         s->read_poll  ? netmap_can_send : NULL,
+                         s->read_poll  ? netmap_send     : NULL,
+                         s->write_poll ? netmap_writable : NULL,
+                         s);
+}
+
+/* Update the read handler. */
+static void netmap_read_poll(NetmapState *s, bool enable)
+{
+    if (s->read_poll != enable) { /* Do nothing if not changed. */
+        s->read_poll = enable;
+        netmap_update_fd_handler(s);
+    }
+}
+
+/* Update the write handler. */
+static void netmap_write_poll(NetmapState *s, bool enable)
+{
+    if (s->write_poll != enable) {
+        s->write_poll = enable;
+        netmap_update_fd_handler(s);
+    }
+}
+
+static void netmap_poll(NetClientState *nc, bool enable)
+{
+    NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
+
+    if (s->read_poll != enable || s->write_poll != enable) {
+        s->read_poll = enable;
+        s->read_poll = enable;
+        netmap_update_fd_handler(s);
+    }
+}
+
+/*
+ * The fd_write() callback, invoked if the fd is marked as
+ * writable after a poll. Unregister the handler and flush any
+ * buffered packets.
+ */
+static void netmap_writable(void *opaque)
+{
+    NetmapState *s = opaque;
+
+    netmap_write_poll(s, false);
+    qemu_flush_queued_packets(&s->nc);
+}
+
+static ssize_t netmap_receive(NetClientState *nc,
+      const uint8_t *buf, size_t size)
+{
+    NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
+    struct netmap_ring *ring = s->me.tx;
+    uint32_t i;
+    uint32_t idx;
+    uint8_t *dst;
+
+    if (unlikely(!ring)) {
+        /* Drop. */
+        return size;
+    }
+
+    if (unlikely(size > ring->nr_buf_size)) {
+        RD(5, "[netmap_receive] drop packet of size %d > %d\n",
+                                    (int)size, ring->nr_buf_size);
+        return size;
+    }
+
+    if (ring->avail == 0) {
+        /* No available slots in the netmap TX ring. */
+        netmap_write_poll(s, true);
+        return 0;
+    }
+
+    i = ring->cur;
+    idx = ring->slot[i].buf_idx;
+    dst = (uint8_t *)NETMAP_BUF(ring, idx);
+
+    ring->slot[i].len = size;
+    ring->slot[i].flags = 0;
+    pkt_copy(buf, dst, size);
+    ring->cur = NETMAP_RING_NEXT(ring, i);
+    ring->avail--;
+    ioctl(s->me.fd, NIOCTXSYNC, NULL);
+
+    return size;
+}
+
+static ssize_t netmap_receive_iov(NetClientState *nc,
+                    const struct iovec *iov, int iovcnt)
+{
+    NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
+    struct netmap_ring *ring = s->me.tx;
+    uint32_t last;
+    uint32_t idx;
+    uint8_t *dst;
+    int j;
+    uint32_t i;
+    uint32_t avail;
+
+    if (unlikely(!ring)) {
+        /* Drop the packet. */
+        return iov_size(iov, iovcnt);
+    }
+
+    i = ring->cur;
+    avail = ring->avail;
+
+    if (avail < iovcnt) {
+        /* Not enough netmap slots. */
+        netmap_write_poll(s, true);
+        return 0;
+    }
+
+    for (j = 0; j < iovcnt; j++) {
+        int iov_frag_size = iov[j].iov_len;
+        int offset = 0;
+        int nm_frag_size;
+
+        /* Split each iovec fragment over more netmap slots, if
+           necessary. */
+        while (iov_frag_size) {
+            nm_frag_size = MIN(iov_frag_size, ring->nr_buf_size);
+
+            if (unlikely(avail == 0)) {
+                /* We run out of netmap slots while splitting the
+                   iovec fragments. */
+                netmap_write_poll(s, true);
+                return 0;
+            }
+
+            idx = ring->slot[i].buf_idx;
+            dst = (uint8_t *)NETMAP_BUF(ring, idx);
+
+            ring->slot[i].len = nm_frag_size;
+            ring->slot[i].flags = NS_MOREFRAG;
+            pkt_copy(iov[j].iov_base + offset, dst, nm_frag_size);
+
+            last = i;
+            i = NETMAP_RING_NEXT(ring, i);
+            avail--;
+
+            offset += nm_frag_size;
+            iov_frag_size -= nm_frag_size;
+        }
+    }
+    /* The last slot must not have NS_MOREFRAG set. */
+    ring->slot[last].flags &= ~NS_MOREFRAG;
+
+    /* Now update ring->cur and ring->avail. */
+    ring->cur = i;
+    ring->avail = avail;
+
+    ioctl(s->me.fd, NIOCTXSYNC, NULL);
+
+    return iov_size(iov, iovcnt);
+}
+
+/* Complete a previous send (backend --> guest) and enable the
+   fd_read callback. */
+static void netmap_send_completed(NetClientState *nc, ssize_t len)
+{
+    NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
+
+    netmap_read_poll(s, true);
+}
+
+static void netmap_send(void *opaque)
+{
+    NetmapState *s = opaque;
+    struct netmap_ring *ring = s->me.rx;
+
+    /* Keep sending while there are available packets into the netmap
+       RX ring and the forwarding path towards the peer is open. */
+    while (ring->avail > 0 && qemu_can_send_packet(&s->nc)) {
+        uint32_t i;
+        uint32_t idx;
+        bool morefrag;
+        int iovcnt = 0;
+        int iovsize;
+
+        do {
+            i = ring->cur;
+            idx = ring->slot[i].buf_idx;
+            morefrag = (ring->slot[i].flags & NS_MOREFRAG);
+            s->iov[iovcnt].iov_base = (u_char *)NETMAP_BUF(ring, idx);
+            s->iov[iovcnt].iov_len = ring->slot[i].len;
+            iovcnt++;
+
+            ring->cur = NETMAP_RING_NEXT(ring, i);
+            ring->avail--;
+        } while (ring->avail && morefrag);
+
+        if (unlikely(!ring->avail && morefrag)) {
+            RD(5, "[netmap_send] ran out of slots, with a pending"
+                   "incomplete packet\n");
+        }
+
+        iovsize = qemu_sendv_packet_async(&s->nc, s->iov, iovcnt,
+                                            netmap_send_completed);
+
+        if (iovsize == 0) {
+            /* The peer does not receive anymore. Packet is queued, stop
+             * reading from the backend until netmap_send_completed()
+             */
+            netmap_read_poll(s, false);
+            break;
+        }
+    }
+}
+
+/* Flush and close. */
+static void netmap_cleanup(NetClientState *nc)
+{
+    NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
+
+    qemu_purge_queued_packets(nc);
+
+    netmap_poll(nc, false);
+    munmap(s->me.mem, s->me.memsize);
+    close(s->me.fd);
+
+    s->me.fd = -1;
+}
+
+
+/* NetClientInfo methods */
+static NetClientInfo net_netmap_info = {
+    .type = NET_CLIENT_OPTIONS_KIND_NETMAP,
+    .size = sizeof(NetmapState),
+    .receive = netmap_receive,
+    .receive_iov = netmap_receive_iov,
+    .poll = netmap_poll,
+    .cleanup = netmap_cleanup,
+};
+
+/* The exported init function
+ *
+ * ... -net netmap,ifname="..."
+ */
+int net_init_netmap(const NetClientOptions *opts,
+        const char *name, NetClientState *peer)
+{
+    const NetdevNetmapOptions *netmap_opts = opts->netmap;
+    NetClientState *nc;
+    NetmapPriv me;
+    NetmapState *s;
+
+    pstrcpy(me.fdname, sizeof(me.fdname),
+        netmap_opts->has_devname ? netmap_opts->devname : "/dev/netmap");
+    /* Set default name for the port if not supplied. */
+    pstrcpy(me.ifname, sizeof(me.ifname), netmap_opts->ifname);
+    if (netmap_open(&me)) {
+        return -1;
+    }
+    /* Create the object. */
+    nc = qemu_new_net_client(&net_netmap_info, peer, "netmap", name);
+    s = DO_UPCAST(NetmapState, nc, nc);
+    s->me = me;
+    netmap_read_poll(s, true); /* Initially only poll for reads. */
+
+    return 0;
+}
+