*/
+#include "qemu/osdep.h"
#include <sys/ioctl.h>
#include <net/if.h>
-#include <sys/mman.h>
-#include <stdint.h>
-#include <stdio.h>
#define NETMAP_WITH_LIBS
#include <net/netmap.h>
#include <net/netmap_user.h>
#include "clients.h"
#include "sysemu/sysemu.h"
#include "qemu/error-report.h"
+#include "qapi/error.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;
+#include "qemu/cutils.h"
typedef struct NetmapState {
NetClientState nc;
- NetmapPriv me;
+ struct nm_desc *nmd;
+ char ifname[IFNAMSIZ];
+ struct netmap_ring *tx;
+ struct netmap_ring *rx;
bool read_poll;
bool write_poll;
struct iovec iov[IOV_MAX];
* 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)
+static struct nm_desc *netmap_open(const NetdevNetmapOptions *nm_opts,
+ Error **errp)
{
- int fd;
- int err;
- size_t l;
+ struct nm_desc *nmd;
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;
+ nmd = nm_open(nm_opts->ifname, &req, NETMAP_NO_TX_POLL,
+ NULL);
+ if (nmd == NULL) {
+ error_setg_errno(errp, errno, "Failed to nm_open() %s",
+ nm_opts->ifname);
+ return NULL;
+ }
- return qemu_can_send_packet(&s->nc);
+ return nmd;
}
static void netmap_send(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);
+ qemu_set_fd_handler(s->nmd->fd,
+ s->read_poll ? netmap_send : NULL,
+ s->write_poll ? netmap_writable : NULL,
+ s);
}
/* Update the read handler. */
NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
if (s->read_poll != enable || s->write_poll != enable) {
- s->read_poll = enable;
- s->read_poll = enable;
+ s->write_poll = enable;
+ s->read_poll = enable;
netmap_update_fd_handler(s);
}
}
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 (nm_ring_empty(ring)) {
- /* 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 = ring->head = nm_ring_next(ring, i);
- 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;
+ struct netmap_ring *ring = s->tx;
+ unsigned int tail = ring->tail;
+ ssize_t totlen = 0;
uint32_t last;
uint32_t idx;
uint8_t *dst;
int j;
uint32_t i;
- if (unlikely(!ring)) {
- /* Drop the packet. */
- return iov_size(iov, iovcnt);
- }
-
- last = i = ring->cur;
+ last = i = ring->head;
if (nm_ring_space(ring) < iovcnt) {
- /* Not enough netmap slots. */
+ /* Not enough netmap slots. Tell the kernel that we have seen the new
+ * available slots (so that it notifies us again when it has more
+ * ones), but without publishing any new slots to be processed
+ * (e.g., we don't advance ring->head). */
+ ring->cur = tail;
netmap_write_poll(s, true);
return 0;
}
int offset = 0;
int nm_frag_size;
+ totlen += iov_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(nm_ring_empty(ring))) {
- /* We run out of netmap slots while splitting the
+ if (unlikely(i == tail)) {
+ /* We ran out of netmap slots while splitting the
iovec fragments. */
+ ring->cur = tail;
netmap_write_poll(s, true);
return 0;
}
/* The last slot must not have NS_MOREFRAG set. */
ring->slot[last].flags &= ~NS_MOREFRAG;
- /* Now update ring->cur and ring->head. */
- ring->cur = ring->head = i;
+ /* Now update ring->head and ring->cur to publish the new slots and
+ * the new wakeup point. */
+ ring->head = ring->cur = i;
- ioctl(s->me.fd, NIOCTXSYNC, NULL);
+ ioctl(s->nmd->fd, NIOCTXSYNC, NULL);
- return iov_size(iov, iovcnt);
+ return totlen;
+}
+
+static ssize_t netmap_receive(NetClientState *nc,
+ const uint8_t *buf, size_t size)
+{
+ struct iovec iov;
+
+ iov.iov_base = (void *)buf;
+ iov.iov_len = size;
+
+ return netmap_receive_iov(nc, &iov, 1);
}
/* Complete a previous send (backend --> guest) and enable the
static void netmap_send(void *opaque)
{
NetmapState *s = opaque;
- struct netmap_ring *ring = s->me.rx;
+ struct netmap_ring *ring = s->rx;
+ unsigned int tail = ring->tail;
- /* Keep sending while there are available packets into the netmap
+ /* Keep sending while there are available slots in the netmap
RX ring and the forwarding path towards the peer is open. */
- while (!nm_ring_empty(ring) && qemu_can_send_packet(&s->nc)) {
- uint32_t i;
+ while (ring->head != tail) {
+ uint32_t i = ring->head;
uint32_t idx;
bool morefrag;
int iovcnt = 0;
int iovsize;
+ /* Get a (possibly multi-slot) packet. */
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_base = (void *)NETMAP_BUF(ring, idx);
s->iov[iovcnt].iov_len = ring->slot[i].len;
iovcnt++;
+ i = nm_ring_next(ring, i);
+ } while (i != tail && morefrag);
- ring->cur = ring->head = nm_ring_next(ring, i);
- } while (!nm_ring_empty(ring) && morefrag);
+ /* Advance ring->cur to tell the kernel that we have seen the slots. */
+ ring->cur = i;
- if (unlikely(nm_ring_empty(ring) && morefrag)) {
- RD(5, "[netmap_send] ran out of slots, with a pending"
- "incomplete packet\n");
+ if (unlikely(morefrag)) {
+ /* This is a truncated packet, so we can stop without releasing the
+ * incomplete slots by updating ring->head. We will hopefully
+ * re-read the complete packet the next time we are called. */
+ break;
}
iovsize = qemu_sendv_packet_async(&s->nc, s->iov, iovcnt,
netmap_send_completed);
+ /* Release the slots to the kernel. */
+ ring->head = i;
+
if (iovsize == 0) {
/* The peer does not receive anymore. Packet is queued, stop
- * reading from the backend until netmap_send_completed()
- */
+ * reading from the backend until netmap_send_completed(). */
netmap_read_poll(s, false);
break;
}
qemu_purge_queued_packets(nc);
netmap_poll(nc, false);
- munmap(s->me.mem, s->me.memsize);
- close(s->me.fd);
-
- s->me.fd = -1;
+ nm_close(s->nmd);
+ s->nmd = NULL;
}
/* Offloading manipulation support callbacks. */
-static bool netmap_has_ufo(NetClientState *nc)
+static int netmap_fd_set_vnet_hdr_len(NetmapState *s, int len)
{
- return true;
+ struct nmreq req;
+
+ /* Issue a NETMAP_BDG_VNET_HDR command to change the virtio-net header
+ * length for the netmap adapter associated to 's->ifname'.
+ */
+ memset(&req, 0, sizeof(req));
+ pstrcpy(req.nr_name, sizeof(req.nr_name), s->ifname);
+ req.nr_version = NETMAP_API;
+ req.nr_cmd = NETMAP_BDG_VNET_HDR;
+ req.nr_arg1 = len;
+
+ return ioctl(s->nmd->fd, NIOCREGIF, &req);
}
-static bool netmap_has_vnet_hdr(NetClientState *nc)
+static bool netmap_has_vnet_hdr_len(NetClientState *nc, int len)
{
+ NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
+ int prev_len = s->vnet_hdr_len;
+
+ /* Check that we can set the new length. */
+ if (netmap_fd_set_vnet_hdr_len(s, len)) {
+ return false;
+ }
+
+ /* Restore the previous length. */
+ if (netmap_fd_set_vnet_hdr_len(s, prev_len)) {
+ error_report("Failed to restore vnet-hdr length %d on %s: %s",
+ prev_len, s->ifname, strerror(errno));
+ abort();
+ }
+
return true;
}
-static bool netmap_has_vnet_hdr_len(NetClientState *nc, int len)
+/* A netmap interface that supports virtio-net headers always
+ * supports UFO, so we use this callback also for the has_ufo hook. */
+static bool netmap_has_vnet_hdr(NetClientState *nc)
{
- return len == 0 || len == sizeof(struct virtio_net_hdr) ||
- len == sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ return netmap_has_vnet_hdr_len(nc, sizeof(struct virtio_net_hdr));
}
static void netmap_using_vnet_hdr(NetClientState *nc, bool enable)
{
NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
int err;
- struct nmreq req;
- /* Issue a NETMAP_BDG_VNET_HDR command to change the virtio-net header
- * length for the netmap adapter associated to 'me->ifname'.
- */
- memset(&req, 0, sizeof(req));
- pstrcpy(req.nr_name, sizeof(req.nr_name), s->me.ifname);
- req.nr_version = NETMAP_API;
- req.nr_cmd = NETMAP_BDG_VNET_HDR;
- req.nr_arg1 = len;
- err = ioctl(s->me.fd, NIOCREGIF, &req);
+ err = netmap_fd_set_vnet_hdr_len(s, len);
if (err) {
- error_report("Unable to execute NETMAP_BDG_VNET_HDR on %s: %s",
- s->me.ifname, strerror(errno));
+ error_report("Unable to set vnet-hdr length %d on %s: %s",
+ len, s->ifname, strerror(errno));
} else {
/* Keep track of the current length. */
s->vnet_hdr_len = len;
NetmapState *s = DO_UPCAST(NetmapState, nc, nc);
/* Setting a virtio-net header length greater than zero automatically
- * enables the offloadings.
- */
+ * enables the offloadings. */
if (!s->vnet_hdr_len) {
netmap_set_vnet_hdr_len(nc, sizeof(struct virtio_net_hdr));
}
/* NetClientInfo methods */
static NetClientInfo net_netmap_info = {
- .type = NET_CLIENT_OPTIONS_KIND_NETMAP,
+ .type = NET_CLIENT_DRIVER_NETMAP,
.size = sizeof(NetmapState),
.receive = netmap_receive,
.receive_iov = netmap_receive_iov,
.poll = netmap_poll,
.cleanup = netmap_cleanup,
- .has_ufo = netmap_has_ufo,
+ .has_ufo = netmap_has_vnet_hdr,
.has_vnet_hdr = netmap_has_vnet_hdr,
.has_vnet_hdr_len = netmap_has_vnet_hdr_len,
.using_vnet_hdr = netmap_using_vnet_hdr,
*
* ... -net netmap,ifname="..."
*/
-int net_init_netmap(const NetClientOptions *opts,
- const char *name, NetClientState *peer)
+int net_init_netmap(const Netdev *netdev,
+ const char *name, NetClientState *peer, Error **errp)
{
- const NetdevNetmapOptions *netmap_opts = opts->netmap;
+ const NetdevNetmapOptions *netmap_opts = &netdev->u.netmap;
+ struct nm_desc *nmd;
NetClientState *nc;
- NetmapPriv me;
+ Error *err = NULL;
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)) {
+ nmd = netmap_open(netmap_opts, &err);
+ if (err) {
+ error_propagate(errp, err);
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;
+ s->nmd = nmd;
+ s->tx = NETMAP_TXRING(nmd->nifp, 0);
+ s->rx = NETMAP_RXRING(nmd->nifp, 0);
s->vnet_hdr_len = 0;
+ pstrcpy(s->ifname, sizeof(s->ifname), netmap_opts->ifname);
netmap_read_poll(s, true); /* Initially only poll for reads. */
return 0;
projects / mirror_qemu.git / blobdiff