From: Jason Wang <jasowang@redhat.com> To: mst@redhat.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, davem@davemloft.net Cc: kvm@vger.kernel.org, virtualization@lists.linux-foundation.org, eric.dumazet@gmail.com, brouer@redhat.com, Jason Wang <jasowang@redhat.com> Subject: [PATCH net-next V3 6/6] tun: switch to use skb array for tx Date: Thu, 30 Jun 2016 11:52:59 +0800 [thread overview] Message-ID: <1467258779-3539-7-git-send-email-jasowang@redhat.com> (raw) In-Reply-To: <1467258779-3539-1-git-send-email-jasowang@redhat.com> We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - switch from sk_receive_queue to a skb_array, and resize it when tx_queue_len was changed. - introduce a new proto_ops peek_len which was used for peeking the skb length. - implement a tun version of peek_len for vhost_net to use and convert vhost_net to use peek_len if possible. Pktgen test shows about 15.3% improvement on guest receiving pps for small buffers: Before: ~1300000pps After : ~1500000pps Signed-off-by: Jason Wang <jasowang@redhat.com> --- drivers/net/tun.c | 138 +++++++++++++++++++++++++++++++++++++++++++++++++--- drivers/vhost/net.c | 16 +++++- include/linux/net.h | 1 + 3 files changed, 146 insertions(+), 9 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 4884802..3be69ea 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -71,6 +71,7 @@ #include <net/sock.h> #include <linux/seq_file.h> #include <linux/uio.h> +#include <linux/skb_array.h> #include <asm/uaccess.h> @@ -167,6 +168,7 @@ struct tun_file { }; struct list_head next; struct tun_struct *detached; + struct skb_array tx_array; }; struct tun_flow_entry { @@ -515,7 +517,11 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile) static void tun_queue_purge(struct tun_file *tfile) { - skb_queue_purge(&tfile->sk.sk_receive_queue); + struct sk_buff *skb; + + while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) + kfree_skb(skb); + skb_queue_purge(&tfile->sk.sk_error_queue); } @@ -560,6 +566,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } + if (tun) + skb_array_cleanup(&tfile->tx_array); sock_put(&tfile->sk); } } @@ -613,6 +621,7 @@ static void tun_detach_all(struct net_device *dev) static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) { struct tun_file *tfile = file->private_data; + struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); @@ -642,6 +651,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte if (!err) goto out; } + + if (!tfile->detached && + skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) { + err = -ENOMEM; + goto out; + } + tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; rcu_assign_pointer(tfile->tun, tun); @@ -891,8 +907,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); - /* Enqueue packet */ - skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb); + if (skb_array_produce(&tfile->tx_array, skb)) + goto drop; /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) @@ -1107,7 +1123,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) poll_wait(file, sk_sleep(sk), wait); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_array_empty(&tfile->tx_array)) mask |= POLLIN | POLLRDNORM; if (sock_writeable(sk) || @@ -1426,22 +1442,61 @@ done: return total; } +static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, + int *err) +{ + DECLARE_WAITQUEUE(wait, current); + struct sk_buff *skb = NULL; + + skb = skb_array_consume(&tfile->tx_array); + if (skb) + goto out; + if (noblock) { + *err = -EAGAIN; + goto out; + } + + add_wait_queue(&tfile->wq.wait, &wait); + current->state = TASK_INTERRUPTIBLE; + + while (1) { + skb = skb_array_consume(&tfile->tx_array); + if (skb) + break; + if (signal_pending(current)) { + *err = -ERESTARTSYS; + break; + } + if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { + *err = -EFAULT; + break; + } + + schedule(); + }; + + current->state = TASK_RUNNING; + remove_wait_queue(&tfile->wq.wait, &wait); + +out: + return skb; +} + static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock) { struct sk_buff *skb; ssize_t ret; - int peeked, err, off = 0; + int err; tun_debug(KERN_INFO, tun, "tun_do_read\n"); if (!iov_iter_count(to)) return 0; - /* Read frames from queue */ - skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0, - &peeked, &off, &err); + /* Read frames from ring */ + skb = tun_ring_recv(tfile, noblock, &err); if (!skb) return err; @@ -1574,8 +1629,25 @@ out: return ret; } +static int tun_peek_len(struct socket *sock) +{ + struct tun_file *tfile = container_of(sock, struct tun_file, socket); + struct tun_struct *tun; + int ret = 0; + + tun = __tun_get(tfile); + if (!tun) + return 0; + + ret = skb_array_peek_len(&tfile->tx_array); + tun_put(tun); + + return ret; +} + /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { + .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; @@ -2397,6 +2469,53 @@ static const struct ethtool_ops tun_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, }; +static int tun_queue_resize(struct tun_struct *tun) +{ + struct net_device *dev = tun->dev; + struct tun_file *tfile; + struct skb_array **arrays; + int n = tun->numqueues + tun->numdisabled; + int ret, i; + + arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL); + if (!arrays) + return -ENOMEM; + + for (i = 0; i < tun->numqueues; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + arrays[i] = &tfile->tx_array; + } + list_for_each_entry(tfile, &tun->disabled, next) + arrays[i++] = &tfile->tx_array; + + ret = skb_array_resize_multiple(arrays, n, + dev->tx_queue_len, GFP_KERNEL); + + kfree(arrays); + return ret; +} + +static int tun_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct tun_struct *tun = netdev_priv(dev); + + switch (event) { + case NETDEV_CHANGE_TX_QUEUE_LEN: + if (tun_queue_resize(tun)) + return NOTIFY_BAD; + break; + default: + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block tun_notifier_block __read_mostly = { + .notifier_call = tun_device_event, +}; static int __init tun_init(void) { @@ -2416,6 +2535,8 @@ static int __init tun_init(void) pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } + + register_netdevice_notifier(&tun_notifier_block); return 0; err_misc: rtnl_link_unregister(&tun_link_ops); @@ -2427,6 +2548,7 @@ static void tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); + unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 1d3e45f..e032ca3 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -481,10 +481,14 @@ out: static int peek_head_len(struct sock *sk) { + struct socket *sock = sk->sk_socket; struct sk_buff *head; int len = 0; unsigned long flags; + if (sock->ops->peek_len) + return sock->ops->peek_len(sock); + spin_lock_irqsave(&sk->sk_receive_queue.lock, flags); head = skb_peek(&sk->sk_receive_queue); if (likely(head)) { @@ -497,6 +501,16 @@ static int peek_head_len(struct sock *sk) return len; } +static int sk_has_rx_data(struct sock *sk) +{ + struct socket *sock = sk->sk_socket; + + if (sock->ops->peek_len) + return sock->ops->peek_len(sock); + + return skb_queue_empty(&sk->sk_receive_queue); +} + static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; @@ -513,7 +527,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk) endtime = busy_clock() + vq->busyloop_timeout; while (vhost_can_busy_poll(&net->dev, endtime) && - skb_queue_empty(&sk->sk_receive_queue) && + !sk_has_rx_data(sk) && vhost_vq_avail_empty(&net->dev, vq)) cpu_relax_lowlatency(); diff --git a/include/linux/net.h b/include/linux/net.h index 9aa49a0..b6b3843 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -185,6 +185,7 @@ struct proto_ops { ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); + int (*peek_len)(struct socket *sock); }; #define DECLARE_SOCKADDR(type, dst, src) \ -- 2.7.4
WARNING: multiple messages have this Message-ID (diff)
From: Jason Wang <jasowang@redhat.com> To: mst@redhat.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, davem@davemloft.net Cc: brouer@redhat.com, eric.dumazet@gmail.com, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org Subject: [PATCH net-next V3 6/6] tun: switch to use skb array for tx Date: Thu, 30 Jun 2016 11:52:59 +0800 [thread overview] Message-ID: <1467258779-3539-7-git-send-email-jasowang@redhat.com> (raw) In-Reply-To: <1467258779-3539-1-git-send-email-jasowang@redhat.com> We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - switch from sk_receive_queue to a skb_array, and resize it when tx_queue_len was changed. - introduce a new proto_ops peek_len which was used for peeking the skb length. - implement a tun version of peek_len for vhost_net to use and convert vhost_net to use peek_len if possible. Pktgen test shows about 15.3% improvement on guest receiving pps for small buffers: Before: ~1300000pps After : ~1500000pps Signed-off-by: Jason Wang <jasowang@redhat.com> --- drivers/net/tun.c | 138 +++++++++++++++++++++++++++++++++++++++++++++++++--- drivers/vhost/net.c | 16 +++++- include/linux/net.h | 1 + 3 files changed, 146 insertions(+), 9 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 4884802..3be69ea 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -71,6 +71,7 @@ #include <net/sock.h> #include <linux/seq_file.h> #include <linux/uio.h> +#include <linux/skb_array.h> #include <asm/uaccess.h> @@ -167,6 +168,7 @@ struct tun_file { }; struct list_head next; struct tun_struct *detached; + struct skb_array tx_array; }; struct tun_flow_entry { @@ -515,7 +517,11 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile) static void tun_queue_purge(struct tun_file *tfile) { - skb_queue_purge(&tfile->sk.sk_receive_queue); + struct sk_buff *skb; + + while ((skb = skb_array_consume(&tfile->tx_array)) != NULL) + kfree_skb(skb); + skb_queue_purge(&tfile->sk.sk_error_queue); } @@ -560,6 +566,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } + if (tun) + skb_array_cleanup(&tfile->tx_array); sock_put(&tfile->sk); } } @@ -613,6 +621,7 @@ static void tun_detach_all(struct net_device *dev) static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) { struct tun_file *tfile = file->private_data; + struct net_device *dev = tun->dev; int err; err = security_tun_dev_attach(tfile->socket.sk, tun->security); @@ -642,6 +651,13 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte if (!err) goto out; } + + if (!tfile->detached && + skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) { + err = -ENOMEM; + goto out; + } + tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; rcu_assign_pointer(tfile->tun, tun); @@ -891,8 +907,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); - /* Enqueue packet */ - skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb); + if (skb_array_produce(&tfile->tx_array, skb)) + goto drop; /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) @@ -1107,7 +1123,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) poll_wait(file, sk_sleep(sk), wait); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_array_empty(&tfile->tx_array)) mask |= POLLIN | POLLRDNORM; if (sock_writeable(sk) || @@ -1426,22 +1442,61 @@ done: return total; } +static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock, + int *err) +{ + DECLARE_WAITQUEUE(wait, current); + struct sk_buff *skb = NULL; + + skb = skb_array_consume(&tfile->tx_array); + if (skb) + goto out; + if (noblock) { + *err = -EAGAIN; + goto out; + } + + add_wait_queue(&tfile->wq.wait, &wait); + current->state = TASK_INTERRUPTIBLE; + + while (1) { + skb = skb_array_consume(&tfile->tx_array); + if (skb) + break; + if (signal_pending(current)) { + *err = -ERESTARTSYS; + break; + } + if (tfile->socket.sk->sk_shutdown & RCV_SHUTDOWN) { + *err = -EFAULT; + break; + } + + schedule(); + }; + + current->state = TASK_RUNNING; + remove_wait_queue(&tfile->wq.wait, &wait); + +out: + return skb; +} + static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *to, int noblock) { struct sk_buff *skb; ssize_t ret; - int peeked, err, off = 0; + int err; tun_debug(KERN_INFO, tun, "tun_do_read\n"); if (!iov_iter_count(to)) return 0; - /* Read frames from queue */ - skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0, - &peeked, &off, &err); + /* Read frames from ring */ + skb = tun_ring_recv(tfile, noblock, &err); if (!skb) return err; @@ -1574,8 +1629,25 @@ out: return ret; } +static int tun_peek_len(struct socket *sock) +{ + struct tun_file *tfile = container_of(sock, struct tun_file, socket); + struct tun_struct *tun; + int ret = 0; + + tun = __tun_get(tfile); + if (!tun) + return 0; + + ret = skb_array_peek_len(&tfile->tx_array); + tun_put(tun); + + return ret; +} + /* Ops structure to mimic raw sockets with tun */ static const struct proto_ops tun_socket_ops = { + .peek_len = tun_peek_len, .sendmsg = tun_sendmsg, .recvmsg = tun_recvmsg, }; @@ -2397,6 +2469,53 @@ static const struct ethtool_ops tun_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, }; +static int tun_queue_resize(struct tun_struct *tun) +{ + struct net_device *dev = tun->dev; + struct tun_file *tfile; + struct skb_array **arrays; + int n = tun->numqueues + tun->numdisabled; + int ret, i; + + arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL); + if (!arrays) + return -ENOMEM; + + for (i = 0; i < tun->numqueues; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + arrays[i] = &tfile->tx_array; + } + list_for_each_entry(tfile, &tun->disabled, next) + arrays[i++] = &tfile->tx_array; + + ret = skb_array_resize_multiple(arrays, n, + dev->tx_queue_len, GFP_KERNEL); + + kfree(arrays); + return ret; +} + +static int tun_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct tun_struct *tun = netdev_priv(dev); + + switch (event) { + case NETDEV_CHANGE_TX_QUEUE_LEN: + if (tun_queue_resize(tun)) + return NOTIFY_BAD; + break; + default: + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block tun_notifier_block __read_mostly = { + .notifier_call = tun_device_event, +}; static int __init tun_init(void) { @@ -2416,6 +2535,8 @@ static int __init tun_init(void) pr_err("Can't register misc device %d\n", TUN_MINOR); goto err_misc; } + + register_netdevice_notifier(&tun_notifier_block); return 0; err_misc: rtnl_link_unregister(&tun_link_ops); @@ -2427,6 +2548,7 @@ static void tun_cleanup(void) { misc_deregister(&tun_miscdev); rtnl_link_unregister(&tun_link_ops); + unregister_netdevice_notifier(&tun_notifier_block); } /* Get an underlying socket object from tun file. Returns error unless file is diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 1d3e45f..e032ca3 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -481,10 +481,14 @@ out: static int peek_head_len(struct sock *sk) { + struct socket *sock = sk->sk_socket; struct sk_buff *head; int len = 0; unsigned long flags; + if (sock->ops->peek_len) + return sock->ops->peek_len(sock); + spin_lock_irqsave(&sk->sk_receive_queue.lock, flags); head = skb_peek(&sk->sk_receive_queue); if (likely(head)) { @@ -497,6 +501,16 @@ static int peek_head_len(struct sock *sk) return len; } +static int sk_has_rx_data(struct sock *sk) +{ + struct socket *sock = sk->sk_socket; + + if (sock->ops->peek_len) + return sock->ops->peek_len(sock); + + return skb_queue_empty(&sk->sk_receive_queue); +} + static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; @@ -513,7 +527,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk) endtime = busy_clock() + vq->busyloop_timeout; while (vhost_can_busy_poll(&net->dev, endtime) && - skb_queue_empty(&sk->sk_receive_queue) && + !sk_has_rx_data(sk) && vhost_vq_avail_empty(&net->dev, vq)) cpu_relax_lowlatency(); diff --git a/include/linux/net.h b/include/linux/net.h index 9aa49a0..b6b3843 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -185,6 +185,7 @@ struct proto_ops { ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); + int (*peek_len)(struct socket *sock); }; #define DECLARE_SOCKADDR(type, dst, src) \ -- 2.7.4
next prev parent reply other threads:[~2016-06-30 3:54 UTC|newest] Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-06-30 3:52 [PATCH net-next V3 0/6] switch to use tx skb array in tun Jason Wang 2016-06-30 3:52 ` Jason Wang 2016-06-30 3:52 ` [PATCH net-next V3 1/6] ptr_ring: support zero length ring Jason Wang 2016-06-30 3:52 ` Jason Wang 2016-06-30 3:52 ` [PATCH net-next V3 2/6] skb_array: minor tweak Jason Wang 2016-06-30 3:52 ` Jason Wang 2016-06-30 3:52 ` [PATCH net-next V3 3/6] ptr_ring: support resizing multiple queues Jason Wang 2016-06-30 3:52 ` Jason Wang 2016-06-30 3:52 ` [PATCH net-next V3 4/6] skb_array: add wrappers for resizing Jason Wang 2016-06-30 3:52 ` Jason Wang 2016-06-30 3:52 ` [PATCH net-next V3 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN Jason Wang 2016-06-30 3:52 ` Jason Wang 2016-06-30 4:56 ` John Fastabend 2016-06-30 5:12 ` Jason Wang 2016-06-30 5:12 ` Jason Wang 2016-06-30 5:59 ` Jason Wang 2016-06-30 5:59 ` Jason Wang 2016-06-30 6:43 ` Jason Wang 2016-06-30 6:43 ` Jason Wang 2016-06-30 4:56 ` John Fastabend 2016-06-30 3:52 ` Jason Wang [this message] 2016-06-30 3:52 ` [PATCH net-next V3 6/6] tun: switch to use skb array for tx Jason Wang 2016-06-30 6:20 ` [PATCH] tun: fix semicolon.cocci warnings kbuild test robot 2016-06-30 6:20 ` kbuild test robot 2016-06-30 6:20 ` [PATCH net-next V3 6/6] tun: switch to use skb array for tx kbuild test robot 2016-06-30 6:20 ` kbuild test robot 2016-06-30 5:37 ` [PATCH net-next V3 0/6] switch to use tx skb array in tun Michael S. Tsirkin 2016-06-30 5:37 ` Michael S. Tsirkin
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1467258779-3539-7-git-send-email-jasowang@redhat.com \ --to=jasowang@redhat.com \ --cc=brouer@redhat.com \ --cc=davem@davemloft.net \ --cc=eric.dumazet@gmail.com \ --cc=kvm@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=mst@redhat.com \ --cc=netdev@vger.kernel.org \ --cc=virtualization@lists.linux-foundation.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.