summaryrefslogtreecommitdiff
path: root/drivers/vhost/net.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-05-02 01:08:52 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2013-05-02 01:08:52 +0400
commit73287a43cc79ca06629a88d1a199cd283f42456a (patch)
treeacf4456e260115bea77ee31a29f10ce17f0db45c /drivers/vhost/net.c
parent251df49db3327c64bf917bfdba94491fde2b4ee0 (diff)
parent20074f357da4a637430aec2879c9d864c5d2c23c (diff)
downloadlinux-73287a43cc79ca06629a88d1a199cd283f42456a.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: "Highlights (1721 non-merge commits, this has to be a record of some sort): 1) Add 'random' mode to team driver, from Jiri Pirko and Eric Dumazet. 2) Make it so that any driver that supports configuration of multiple MAC addresses can provide the forwarding database add and del calls by providing a default implementation and hooking that up if the driver doesn't have an explicit set of handlers. From Vlad Yasevich. 3) Support GSO segmentation over tunnels and other encapsulating devices such as VXLAN, from Pravin B Shelar. 4) Support L2 GRE tunnels in the flow dissector, from Michael Dalton. 5) Implement Tail Loss Probe (TLP) detection in TCP, from Nandita Dukkipati. 6) In the PHY layer, allow supporting wake-on-lan in situations where the PHY registers have to be written for it to be configured. Use it to support wake-on-lan in mv643xx_eth. From Michael Stapelberg. 7) Significantly improve firewire IPV6 support, from YOSHIFUJI Hideaki. 8) Allow multiple packets to be sent in a single transmission using network coding in batman-adv, from Martin Hundebøll. 9) Add support for T5 cxgb4 chips, from Santosh Rastapur. 10) Generalize the VXLAN forwarding tables so that there is more flexibility in configurating various aspects of the endpoints. From David Stevens. 11) Support RSS and TSO in hardware over GRE tunnels in bxn2x driver, from Dmitry Kravkov. 12) Zero copy support in nfnelink_queue, from Eric Dumazet and Pablo Neira Ayuso. 13) Start adding networking selftests. 14) In situations of overload on the same AF_PACKET fanout socket, or per-cpu packet receive queue, minimize drop by distributing the load to other cpus/fanouts. From Willem de Bruijn and Eric Dumazet. 15) Add support for new payload offset BPF instruction, from Daniel Borkmann. 16) Convert several drivers over to mdoule_platform_driver(), from Sachin Kamat. 17) Provide a minimal BPF JIT image disassembler userspace tool, from Daniel Borkmann. 18) Rewrite F-RTO implementation in TCP to match the final specification of it in RFC4138 and RFC5682. From Yuchung Cheng. 19) Provide netlink socket diag of netlink sockets ("Yo dawg, I hear you like netlink, so I implemented netlink dumping of netlink sockets.") From Andrey Vagin. 20) Remove ugly passing of rtnetlink attributes into rtnl_doit functions, from Thomas Graf. 21) Allow userspace to be able to see if a configuration change occurs in the middle of an address or device list dump, from Nicolas Dichtel. 22) Support RFC3168 ECN protection for ipv6 fragments, from Hannes Frederic Sowa. 23) Increase accuracy of packet length used by packet scheduler, from Jason Wang. 24) Beginning set of changes to make ipv4/ipv6 fragment handling more scalable and less susceptible to overload and locking contention, from Jesper Dangaard Brouer. 25) Get rid of using non-type-safe NLMSG_* macros and use nlmsg_*() instead. From Hong Zhiguo. 26) Optimize route usage in IPVS by avoiding reference counting where possible, from Julian Anastasov. 27) Convert IPVS schedulers to RCU, also from Julian Anastasov. 28) Support cpu fanouts in xt_NFQUEUE netfilter target, from Holger Eitzenberger. 29) Network namespace support for nf_log, ebt_log, xt_LOG, ipt_ULOG, nfnetlink_log, and nfnetlink_queue. From Gao feng. 30) Implement RFC3168 ECN protection, from Hannes Frederic Sowa. 31) Support several new r8169 chips, from Hayes Wang. 32) Support tokenized interface identifiers in ipv6, from Daniel Borkmann. 33) Use usbnet_link_change() helper in USB net driver, from Ming Lei. 34) Add 802.1ad vlan offload support, from Patrick McHardy. 35) Support mmap() based netlink communication, also from Patrick McHardy. 36) Support HW timestamping in mlx4 driver, from Amir Vadai. 37) Rationalize AF_PACKET packet timestamping when transmitting, from Willem de Bruijn and Daniel Borkmann. 38) Bring parity to what's provided by /proc/net/packet socket dumping and the info provided by netlink socket dumping of AF_PACKET sockets. From Nicolas Dichtel. 39) Fix peeking beyond zero sized SKBs in AF_UNIX, from Benjamin Poirier" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits) filter: fix va_list build error af_unix: fix a fatal race with bit fields bnx2x: Prevent memory leak when cnic is absent bnx2x: correct reading of speed capabilities net: sctp: attribute printl with __printf for gcc fmt checks netlink: kconfig: move mmap i/o into netlink kconfig netpoll: convert mutex into a semaphore netlink: Fix skb ref counting. net_sched: act_ipt forward compat with xtables mlx4_en: fix a build error on 32bit arches Revert "bnx2x: allow nvram test to run when device is down" bridge: avoid OOPS if root port not found drivers: net: cpsw: fix kernel warn on cpsw irq enable sh_eth: use random MAC address if no valid one supplied 3c509.c: call SET_NETDEV_DEV for all device types (ISA/ISAPnP/EISA) tg3: fix to append hardware time stamping flags unix/stream: fix peeking with an offset larger than data in queue unix/dgram: fix peeking with an offset larger than data in queue unix/dgram: peek beyond 0-sized skbs openvswitch: Remove unneeded ovs_netdev_get_ifindex() ...
Diffstat (limited to 'drivers/vhost/net.c')
-rw-r--r--drivers/vhost/net.c74
1 files changed, 6 insertions, 68 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index ec6fb3fa59bb..87c216c1e54e 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -64,20 +64,10 @@ enum {
VHOST_NET_VQ_MAX = 2,
};
-enum vhost_net_poll_state {
- VHOST_NET_POLL_DISABLED = 0,
- VHOST_NET_POLL_STARTED = 1,
- VHOST_NET_POLL_STOPPED = 2,
-};
-
struct vhost_net {
struct vhost_dev dev;
struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
struct vhost_poll poll[VHOST_NET_VQ_MAX];
- /* Tells us whether we are polling a socket for TX.
- * We only do this when socket buffer fills up.
- * Protected by tx vq lock. */
- enum vhost_net_poll_state tx_poll_state;
/* Number of TX recently submitted.
* Protected by tx vq lock. */
unsigned tx_packets;
@@ -155,28 +145,6 @@ static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
}
}
-/* Caller must have TX VQ lock */
-static void tx_poll_stop(struct vhost_net *net)
-{
- if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
- return;
- vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
- net->tx_poll_state = VHOST_NET_POLL_STOPPED;
-}
-
-/* Caller must have TX VQ lock */
-static int tx_poll_start(struct vhost_net *net, struct socket *sock)
-{
- int ret;
-
- if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
- return 0;
- ret = vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
- if (!ret)
- net->tx_poll_state = VHOST_NET_POLL_STARTED;
- return ret;
-}
-
/* In case of DMA done not in order in lower device driver for some reason.
* upend_idx is used to track end of used idx, done_idx is used to track head
* of used idx. Once lower device DMA done contiguously, we will signal KVM
@@ -242,7 +210,7 @@ static void handle_tx(struct vhost_net *net)
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
- int err, wmem;
+ int err;
size_t hdr_size;
struct socket *sock;
struct vhost_ubuf_ref *uninitialized_var(ubufs);
@@ -253,19 +221,9 @@ static void handle_tx(struct vhost_net *net)
if (!sock)
return;
- wmem = atomic_read(&sock->sk->sk_wmem_alloc);
- if (wmem >= sock->sk->sk_sndbuf) {
- mutex_lock(&vq->mutex);
- tx_poll_start(net, sock);
- mutex_unlock(&vq->mutex);
- return;
- }
-
mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
- if (wmem < sock->sk->sk_sndbuf / 2)
- tx_poll_stop(net);
hdr_size = vq->vhost_hlen;
zcopy = vq->ubufs;
@@ -285,23 +243,14 @@ static void handle_tx(struct vhost_net *net)
if (head == vq->num) {
int num_pends;
- wmem = atomic_read(&sock->sk->sk_wmem_alloc);
- if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
- tx_poll_start(net, sock);
- set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
- break;
- }
/* If more outstanding DMAs, queue the work.
* Handle upend_idx wrap around
*/
num_pends = likely(vq->upend_idx >= vq->done_idx) ?
(vq->upend_idx - vq->done_idx) :
(vq->upend_idx + UIO_MAXIOV - vq->done_idx);
- if (unlikely(num_pends > VHOST_MAX_PEND)) {
- tx_poll_start(net, sock);
- set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+ if (unlikely(num_pends > VHOST_MAX_PEND))
break;
- }
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
@@ -364,8 +313,6 @@ static void handle_tx(struct vhost_net *net)
UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
- if (err == -EAGAIN || err == -ENOBUFS)
- tx_poll_start(net, sock);
break;
}
if (err != len)
@@ -628,7 +575,6 @@ static int vhost_net_open(struct inode *inode, struct file *f)
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
- n->tx_poll_state = VHOST_NET_POLL_DISABLED;
f->private_data = n;
@@ -638,32 +584,24 @@ static int vhost_net_open(struct inode *inode, struct file *f)
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
+ struct vhost_poll *poll = n->poll + (vq - n->vqs);
if (!vq->private_data)
return;
- if (vq == n->vqs + VHOST_NET_VQ_TX) {
- tx_poll_stop(n);
- n->tx_poll_state = VHOST_NET_POLL_DISABLED;
- } else
- vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
+ vhost_poll_stop(poll);
}
static int vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
+ struct vhost_poll *poll = n->poll + (vq - n->vqs);
struct socket *sock;
- int ret;
sock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (!sock)
return 0;
- if (vq == n->vqs + VHOST_NET_VQ_TX) {
- n->tx_poll_state = VHOST_NET_POLL_STOPPED;
- ret = tx_poll_start(n, sock);
- } else
- ret = vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
- return ret;
+ return vhost_poll_start(poll, sock->file);
}
static struct socket *vhost_net_stop_vq(struct vhost_net *n,