diff options
Diffstat (limited to 'net/packet/af_packet.c')
| -rw-r--r-- | net/packet/af_packet.c | 288 |
1 files changed, 199 insertions, 89 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9d70f134992..b85c67ccb79 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -88,7 +88,7 @@ #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> -#include <linux/reciprocal_div.h> +#include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif @@ -243,40 +243,41 @@ static int packet_direct_xmit(struct sk_buff *skb) const struct net_device_ops *ops = dev->netdev_ops; netdev_features_t features; struct netdev_queue *txq; + int ret = NETDEV_TX_BUSY; u16 queue_map; - int ret; if (unlikely(!netif_running(dev) || - !netif_carrier_ok(dev))) { - kfree_skb(skb); - return NET_XMIT_DROP; - } + !netif_carrier_ok(dev))) + goto drop; features = netif_skb_features(skb); if (skb_needs_linearize(skb, features) && - __skb_linearize(skb)) { - kfree_skb(skb); - return NET_XMIT_DROP; - } + __skb_linearize(skb)) + goto drop; queue_map = skb_get_queue_mapping(skb); txq = netdev_get_tx_queue(dev, queue_map); - __netif_tx_lock_bh(txq); - if (unlikely(netif_xmit_frozen_or_stopped(txq))) { - ret = NETDEV_TX_BUSY; - kfree_skb(skb); - goto out; + local_bh_disable(); + + HARD_TX_LOCK(dev, txq, smp_processor_id()); + if (!netif_xmit_frozen_or_drv_stopped(txq)) { + ret = ops->ndo_start_xmit(skb, dev); + if (ret == NETDEV_TX_OK) + txq_trans_update(txq); } + HARD_TX_UNLOCK(dev, txq); - ret = ops->ndo_start_xmit(skb, dev); - if (likely(dev_xmit_complete(ret))) - txq_trans_update(txq); - else + local_bh_enable(); + + if (!dev_xmit_complete(ret)) kfree_skb(skb); -out: - __netif_tx_unlock_bh(txq); + return ret; +drop: + atomic_long_inc(&dev->tx_dropped); + kfree_skb(skb); + return NET_XMIT_DROP; } static struct net_device *packet_cached_dev_get(struct packet_sock *po) @@ -308,9 +309,25 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) return po->xmit == packet_direct_xmit; } -static u16 packet_pick_tx_queue(struct net_device *dev) +static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) { - return (u16) smp_processor_id() % dev->real_num_tx_queues; + return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; +} + +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +{ + const struct net_device_ops *ops = dev->netdev_ops; + u16 queue_index; + + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb, NULL, + __packet_pick_tx_queue); + queue_index = netdev_cap_txqueue(dev, queue_index); + } else { + queue_index = __packet_pick_tx_queue(dev, skb); + } + + skb_set_queue_mapping(skb, queue_index); } /* register_prot_hook must be invoked with the po->bind_lock held, @@ -963,7 +980,7 @@ static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { - ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb); + ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, @@ -977,9 +994,11 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, { if (vlan_tx_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb); - ppd->tp_status = TP_STATUS_VLAN_VALID; + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; + ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } @@ -987,6 +1006,7 @@ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) @@ -1165,6 +1185,47 @@ static void packet_increment_head(struct packet_ring_buffer *buff) buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } +static void packet_inc_pending(struct packet_ring_buffer *rb) +{ + this_cpu_inc(*rb->pending_refcnt); +} + +static void packet_dec_pending(struct packet_ring_buffer *rb) +{ + this_cpu_dec(*rb->pending_refcnt); +} + +static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) +{ + unsigned int refcnt = 0; + int cpu; + + /* We don't use pending refcount in rx_ring. */ + if (rb->pending_refcnt == NULL) + return 0; + + for_each_possible_cpu(cpu) + refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); + + return refcnt; +} + +static int packet_alloc_pending(struct packet_sock *po) +{ + po->rx_ring.pending_refcnt = NULL; + + po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); + if (unlikely(po->tx_ring.pending_refcnt == NULL)) + return -ENOBUFS; + + return 0; +} + +static void packet_free_pending(struct packet_sock *po) +{ + free_percpu(po->tx_ring.pending_refcnt); +} + static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { struct sock *sk = &po->sk; @@ -1217,7 +1278,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_divide(skb->rxhash, num); + return reciprocal_scale(skb_get_hash(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, @@ -1244,7 +1305,7 @@ static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_divide(prandom_u32(), num); + return prandom_u32_max(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, @@ -1268,6 +1329,13 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f, return idx; } +static unsigned int fanout_demux_qm(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int num) +{ + return skb_get_queue_mapping(skb) % num; +} + static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); @@ -1295,7 +1363,6 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; } - skb_get_rxhash(skb); idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: @@ -1307,6 +1374,9 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; + case PACKET_FANOUT_QM: + idx = fanout_demux_qm(f, skb, num); + break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num); break; @@ -1353,9 +1423,9 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) spin_unlock(&f->lock); } -static bool match_fanout_group(struct packet_type *ptype, struct sock * sk) +static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { - if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout) + if (ptype->af_packet_priv == (void *)((struct packet_sock *)sk)->fanout) return true; return false; @@ -1377,6 +1447,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: + case PACKET_FANOUT_QM: break; default: return -EINVAL; @@ -1539,7 +1610,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; __be16 proto = 0; @@ -1777,7 +1848,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->dropcount = atomic_read(&sk->sk_drops); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return 0; drop_n_acct: @@ -1812,6 +1883,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct timespec ts; __u32 ts_status; + /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. + * We may add members to them until current aligned size without forcing + * userspace to call getsockopt(..., PACKET_HDRLEN, ...). + */ + BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); + BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); + if (skb->pkt_type == PACKET_LOOPBACK) goto drop; @@ -1918,11 +1996,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_nsec = ts.tv_nsec; if (vlan_tx_tag_present(skb)) { h.h2->tp_vlan_tci = vlan_tx_tag_get(skb); - status |= TP_STATUS_VLAN_VALID; + h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; + h.h2->tp_vlan_tpid = 0; } - h.h2->tp_padding = 0; + memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: @@ -1936,6 +2016,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; + memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: @@ -1954,25 +2035,26 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_ifindex = dev->ifindex; smp_mb(); + #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 - { + if (po->tp_version <= TPACKET_V2) { u8 *start, *end; - if (po->tp_version <= TPACKET_V2) { - end = (u8 *)PAGE_ALIGN((unsigned long)h.raw - + macoff + snaplen); - for (start = h.raw; start < end; start += PAGE_SIZE) - flush_dcache_page(pgv_to_page(start)); - } - smp_wmb(); + end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + + macoff + snaplen); + + for (start = h.raw; start < end; start += PAGE_SIZE) + flush_dcache_page(pgv_to_page(start)); } + smp_wmb(); #endif + if (po->tp_version <= TPACKET_V2) __packet_set_status(po, h.raw, status); else prb_clear_blk_fill_status(&po->rx_ring); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -1987,7 +2069,7 @@ ring_is_full: po->stats.stats1.tp_drops++; spin_unlock(&sk->sk_receive_queue.lock); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); kfree_skb(copy_skb); goto drop_n_restore; } @@ -1995,14 +2077,13 @@ ring_is_full: static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); - void *ph; if (likely(po->tx_ring.pg_vec)) { + void *ph; __u32 ts; ph = skb_shinfo(skb)->destructor_arg; - BUG_ON(atomic_read(&po->tx_ring.pending) == 0); - atomic_dec(&po->tx_ring.pending); + packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); @@ -2142,7 +2223,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) __be16 proto; int err, reserve = 0; void *ph; - struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); + bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int tp_len, size_max; unsigned char *addr; int len_sum = 0; @@ -2175,8 +2257,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - reserve = dev->hard_header_len; - + reserve = dev->hard_header_len + VLAN_HLEN; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2185,10 +2266,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) do { ph = packet_current_frame(po, &po->tx_ring, - TP_STATUS_SEND_REQUEST); - + TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { - schedule(); + if (need_wait && need_resched()) + schedule(); continue; } @@ -2203,8 +2284,19 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, - addr, hlen); + addr, hlen); + if (tp_len > dev->mtu + dev->hard_header_len) { + struct ethhdr *ehdr; + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) + tp_len = -EMSGSIZE; + } if (unlikely(tp_len < 0)) { if (po->tp_loss) { __packet_set_status(po, ph, @@ -2219,10 +2311,11 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } } - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + packet_pick_tx_queue(dev, skb); + skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); - atomic_inc(&po->tx_ring.pending); + packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); @@ -2243,9 +2336,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || - ((!(msg->msg_flags & MSG_DONTWAIT)) && - (atomic_read(&po->tx_ring.pending)))) - ); + /* Note: packet_read_pending() might be slow if we have + * to call it as it's per_cpu variable, but in fast-path + * we already short-circuit the loop with the first + * condition, and luckily don't have to go that path + * anyway. + */ + (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; @@ -2287,7 +2384,7 @@ static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; @@ -2429,7 +2526,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + + packet_pick_tx_queue(dev, skb); if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { @@ -2544,6 +2642,7 @@ static int packet_release(struct socket *sock) /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); + packet_free_pending(po); sk_refcnt_debug_release(sk); sock_put(sk); @@ -2554,9 +2653,12 @@ static int packet_release(struct socket *sock) * Attach a packet hook. */ -static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol) +static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto) { struct packet_sock *po = pkt_sk(sk); + const struct net_device *dev_curr; + __be16 proto_curr; + bool need_rehook; if (po->fanout) { if (dev) @@ -2566,21 +2668,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc } lock_sock(sk); - spin_lock(&po->bind_lock); - unregister_prot_hook(sk, true); - po->num = protocol; - po->prot_hook.type = protocol; - if (po->prot_hook.dev) - dev_put(po->prot_hook.dev); + proto_curr = po->prot_hook.type; + dev_curr = po->prot_hook.dev; - po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + need_rehook = proto_curr != proto || dev_curr != dev; + + if (need_rehook) { + unregister_prot_hook(sk, true); + + po->num = proto; + po->prot_hook.type = proto; - packet_cached_dev_assign(po, dev); + if (po->prot_hook.dev) + dev_put(po->prot_hook.dev); - if (protocol == 0) + po->prot_hook.dev = dev; + + po->ifindex = dev ? dev->ifindex : 0; + packet_cached_dev_assign(po, dev); + } + + if (proto == 0 || !need_rehook) goto out_unlock; if (!dev || (dev->flags & IFF_UP)) { @@ -2694,6 +2804,10 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po->num = proto; po->xmit = dev_queue_xmit; + err = packet_alloc_pending(po); + if (err) + goto out2; + packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; @@ -2726,6 +2840,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, preempt_enable(); return 0; +out2: + sk_free(sk); out: return err; } @@ -2845,6 +2961,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { + __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; @@ -2867,11 +2984,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, aux.tp_net = skb_network_offset(skb); if (vlan_tx_tag_present(skb)) { aux.tp_vlan_tci = vlan_tx_tag_get(skb); - aux.tp_status |= TP_STATUS_VLAN_VALID; + aux.tp_vlan_tpid = ntohs(skb->vlan_proto); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; } - aux.tp_padding = 0; put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } @@ -3570,34 +3688,26 @@ static void free_pg_vec(struct pgv *pg_vec, unsigned int order, static char *alloc_one_pg_vec_page(unsigned long order) { - char *buffer = NULL; + char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); - if (buffer) return buffer; - /* - * __get_free_pages failed, fall back to vmalloc - */ + /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc((1 << order) * PAGE_SIZE); - if (buffer) return buffer; - /* - * vmalloc failed, lets dig into swap here - */ + /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; - buffer = (char *)__get_free_pages(gfp_flags, order); + buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; - /* - * complete and utter failure - */ + /* complete and utter failure */ return NULL; } @@ -3652,7 +3762,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (!closing) { if (atomic_read(&po->mapped)) goto out; - if (atomic_read(&rb->pending)) + if (packet_read_pending(rb)) goto out; } @@ -3704,7 +3814,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, */ if (!tx_ring) init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring); - break; + break; default: break; } |
