diff options
Diffstat (limited to 'net/core/dev.c')
-rw-r--r-- | net/core/dev.c | 414 |
1 files changed, 355 insertions, 59 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index ae00b894e675..0ca95d5d7af0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -96,6 +96,7 @@ #include <linux/skbuff.h> #include <net/net_namespace.h> #include <net/sock.h> +#include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dst.h> @@ -137,6 +138,7 @@ #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_ingress.h> +#include <linux/sctp.h> #include "net-sysfs.h" @@ -182,8 +184,8 @@ EXPORT_SYMBOL(dev_base_lock); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); -static unsigned int napi_gen_id; -static DEFINE_HASHTABLE(napi_hash, 8); +static unsigned int napi_gen_id = NR_CPUS; +static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static seqcount_t devnet_rename_seq; @@ -1674,6 +1676,22 @@ void net_dec_ingress_queue(void) EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif +#ifdef CONFIG_NET_EGRESS +static struct static_key egress_needed __read_mostly; + +void net_inc_egress_queue(void) +{ + static_key_slow_inc(&egress_needed); +} +EXPORT_SYMBOL_GPL(net_inc_egress_queue); + +void net_dec_egress_queue(void) +{ + static_key_slow_dec(&egress_needed); +} +EXPORT_SYMBOL_GPL(net_dec_egress_queue); +#endif + static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL /* We are not allowed to call static_key_slow_dec() from irq context @@ -2470,6 +2488,141 @@ out: } EXPORT_SYMBOL(skb_checksum_help); +/* skb_csum_offload_check - Driver helper function to determine if a device + * with limited checksum offload capabilities is able to offload the checksum + * for a given packet. + * + * Arguments: + * skb - sk_buff for the packet in question + * spec - contains the description of what device can offload + * csum_encapped - returns true if the checksum being offloaded is + * encpasulated. That is it is checksum for the transport header + * in the inner headers. + * checksum_help - when set indicates that helper function should + * call skb_checksum_help if offload checks fail + * + * Returns: + * true: Packet has passed the checksum checks and should be offloadable to + * the device (a driver may still need to check for additional + * restrictions of its device) + * false: Checksum is not offloadable. If checksum_help was set then + * skb_checksum_help was called to resolve checksum for non-GSO + * packets and when IP protocol is not SCTP + */ +bool __skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help) +{ + struct iphdr *iph; + struct ipv6hdr *ipv6; + void *nhdr; + int protocol; + u8 ip_proto; + + if (skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) { + if (!spec->vlan_okay) + goto need_help; + } + + /* We check whether the checksum refers to a transport layer checksum in + * the outermost header or an encapsulated transport layer checksum that + * corresponds to the inner headers of the skb. If the checksum is for + * something else in the packet we need help. + */ + if (skb_checksum_start_offset(skb) == skb_transport_offset(skb)) { + /* Non-encapsulated checksum */ + protocol = eproto_to_ipproto(vlan_get_protocol(skb)); + nhdr = skb_network_header(skb); + *csum_encapped = false; + if (spec->no_not_encapped) + goto need_help; + } else if (skb->encapsulation && spec->encap_okay && + skb_checksum_start_offset(skb) == + skb_inner_transport_offset(skb)) { + /* Encapsulated checksum */ + *csum_encapped = true; + switch (skb->inner_protocol_type) { + case ENCAP_TYPE_ETHER: + protocol = eproto_to_ipproto(skb->inner_protocol); + break; + case ENCAP_TYPE_IPPROTO: + protocol = skb->inner_protocol; + break; + } + nhdr = skb_inner_network_header(skb); + } else { + goto need_help; + } + + switch (protocol) { + case IPPROTO_IP: + if (!spec->ipv4_okay) + goto need_help; + iph = nhdr; + ip_proto = iph->protocol; + if (iph->ihl != 5 && !spec->ip_options_okay) + goto need_help; + break; + case IPPROTO_IPV6: + if (!spec->ipv6_okay) + goto need_help; + if (spec->no_encapped_ipv6 && *csum_encapped) + goto need_help; + ipv6 = nhdr; + nhdr += sizeof(*ipv6); + ip_proto = ipv6->nexthdr; + break; + default: + goto need_help; + } + +ip_proto_again: + switch (ip_proto) { + case IPPROTO_TCP: + if (!spec->tcp_okay || + skb->csum_offset != offsetof(struct tcphdr, check)) + goto need_help; + break; + case IPPROTO_UDP: + if (!spec->udp_okay || + skb->csum_offset != offsetof(struct udphdr, check)) + goto need_help; + break; + case IPPROTO_SCTP: + if (!spec->sctp_okay || + skb->csum_offset != offsetof(struct sctphdr, checksum)) + goto cant_help; + break; + case NEXTHDR_HOP: + case NEXTHDR_ROUTING: + case NEXTHDR_DEST: { + u8 *opthdr = nhdr; + + if (protocol != IPPROTO_IPV6 || !spec->ext_hdrs_okay) + goto need_help; + + ip_proto = opthdr[0]; + nhdr += (opthdr[1] + 1) << 3; + + goto ip_proto_again; + } + default: + goto need_help; + } + + /* Passed the tests for offloading checksum */ + return true; + +need_help: + if (csum_help && !skb_shinfo(skb)->gso_size) + skb_checksum_help(skb); +cant_help: + return false; +} +EXPORT_SYMBOL(__skb_csum_offload_chk); + __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; @@ -2644,7 +2797,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { - features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_CSUM_MASK; } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } @@ -2791,7 +2944,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); - if (!(features & NETIF_F_ALL_CSUM) && + if (!(features & NETIF_F_CSUM_MASK) && skb_checksum_help(skb)) goto out_kfree_skb; } @@ -2870,7 +3023,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, bool contended; int rc; - qdisc_pkt_len_init(skb); qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a @@ -2928,7 +3080,8 @@ static void skb_update_prio(struct sk_buff *skb) struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); if (!skb->priority && skb->sk && map) { - unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + unsigned int prioidx = + sock_cgroup_prioidx(&skb->sk->sk_cgrp_data); if (prioidx < map->priomap_len) skb->priority = map->priomap[prioidx]; @@ -2962,6 +3115,49 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(dev_loopback_xmit); +#ifdef CONFIG_NET_EGRESS +static struct sk_buff * +sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) +{ + struct tcf_proto *cl = rcu_dereference_bh(dev->egress_cl_list); + struct tcf_result cl_res; + + if (!cl) + return skb; + + /* skb->tc_verd and qdisc_skb_cb(skb)->pkt_len were already set + * earlier by the caller. + */ + qdisc_bstats_cpu_update(cl->q, skb); + + switch (tc_classify(skb, cl, &cl_res, false)) { + case TC_ACT_OK: + case TC_ACT_RECLASSIFY: + skb->tc_index = TC_H_MIN(cl_res.classid); + break; + case TC_ACT_SHOT: + qdisc_qstats_cpu_drop(cl->q); + *ret = NET_XMIT_DROP; + goto drop; + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + *ret = NET_XMIT_SUCCESS; +drop: + kfree_skb(skb); + return NULL; + case TC_ACT_REDIRECT: + /* No need to push/pop skb's mac_header here on egress! */ + skb_do_redirect(skb); + *ret = NET_XMIT_SUCCESS; + return NULL; + default: + break; + } + + return skb; +} +#endif /* CONFIG_NET_EGRESS */ + static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -3021,7 +3217,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, int queue_index = 0; #ifdef CONFIG_XPS - if (skb->sender_cpu == 0) + u32 sender_cpu = skb->sender_cpu - 1; + + if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif @@ -3086,6 +3284,17 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) skb_update_prio(skb); + qdisc_pkt_len_init(skb); +#ifdef CONFIG_NET_CLS_ACT + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); +# ifdef CONFIG_NET_EGRESS + if (static_key_false(&egress_needed)) { + skb = sch_handle_egress(skb, &rc, dev); + if (!skb) + goto out; + } +# endif +#endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. */ @@ -3107,9 +3316,6 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) txq = netdev_pick_tx(dev, skb, accel_priv); q = rcu_dereference_bh(txq->qdisc); -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); -#endif trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); @@ -3666,9 +3872,9 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev, EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif -static inline struct sk_buff *handle_ing(struct sk_buff *skb, - struct packet_type **pt_prev, - int *ret, struct net_device *orig_dev) +static inline struct sk_buff * +sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, + struct net_device *orig_dev) { #ifdef CONFIG_NET_CLS_ACT struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list); @@ -3862,7 +4068,7 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS if (static_key_false(&ingress_needed)) { - skb = handle_ing(skb, &pt_prev, &ret, orig_dev); + skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); if (!skb) goto out; @@ -4353,6 +4559,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { + skb_mark_napi_id(skb, napi); trace_napi_gro_receive_entry(skb); skb_gro_reset_offset(skb); @@ -4386,7 +4593,10 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) if (!skb) { skb = napi_alloc_skb(napi, GRO_MAX_HEAD); - napi->skb = skb; + if (skb) { + napi->skb = skb; + skb_mark_napi_id(skb, napi); + } } return skb; } @@ -4661,7 +4871,7 @@ void napi_complete_done(struct napi_struct *n, int work_done) EXPORT_SYMBOL(napi_complete_done); /* must be called under rcu_read_lock(), as we dont take a reference */ -struct napi_struct *napi_by_id(unsigned int napi_id) +static struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; @@ -4672,43 +4882,101 @@ struct napi_struct *napi_by_id(unsigned int napi_id) return NULL; } -EXPORT_SYMBOL_GPL(napi_by_id); -void napi_hash_add(struct napi_struct *napi) +#if defined(CONFIG_NET_RX_BUSY_POLL) +#define BUSY_POLL_BUDGET 8 +bool sk_busy_loop(struct sock *sk, int nonblock) { - if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) { + unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0; + int (*busy_poll)(struct napi_struct *dev); + struct napi_struct *napi; + int rc = false; - spin_lock(&napi_hash_lock); + rcu_read_lock(); - /* 0 is not a valid id, we also skip an id that is taken - * we expect both events to be extremely rare - */ - napi->napi_id = 0; - while (!napi->napi_id) { - napi->napi_id = ++napi_gen_id; - if (napi_by_id(napi->napi_id)) - napi->napi_id = 0; + napi = napi_by_id(sk->sk_napi_id); + if (!napi) + goto out; + + /* Note: ndo_busy_poll method is optional in linux-4.5 */ + busy_poll = napi->dev->netdev_ops->ndo_busy_poll; + + do { + rc = 0; + local_bh_disable(); + if (busy_poll) { + rc = busy_poll(napi); + } else if (napi_schedule_prep(napi)) { + void *have = netpoll_poll_lock(napi); + + if (test_bit(NAPI_STATE_SCHED, &napi->state)) { + rc = napi->poll(napi, BUSY_POLL_BUDGET); + trace_napi_poll(napi); + if (rc == BUSY_POLL_BUDGET) { + napi_complete_done(napi, rc); + napi_schedule(napi); + } + } + netpoll_poll_unlock(have); } + if (rc > 0) + NET_ADD_STATS_BH(sock_net(sk), + LINUX_MIB_BUSYPOLLRXPACKETS, rc); + local_bh_enable(); - hlist_add_head_rcu(&napi->napi_hash_node, - &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + if (rc == LL_FLUSH_FAILED) + break; /* permanent failure */ - spin_unlock(&napi_hash_lock); - } + cpu_relax(); + } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) && + !need_resched() && !busy_loop_timeout(end_time)); + + rc = !skb_queue_empty(&sk->sk_receive_queue); +out: + rcu_read_unlock(); + return rc; +} +EXPORT_SYMBOL(sk_busy_loop); + +#endif /* CONFIG_NET_RX_BUSY_POLL */ + +void napi_hash_add(struct napi_struct *napi) +{ + if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) || + test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) + return; + + spin_lock(&napi_hash_lock); + + /* 0..NR_CPUS+1 range is reserved for sender_cpu use */ + do { + if (unlikely(++napi_gen_id < NR_CPUS + 1)) + napi_gen_id = NR_CPUS + 1; + } while (napi_by_id(napi_gen_id)); + napi->napi_id = napi_gen_id; + + hlist_add_head_rcu(&napi->napi_hash_node, + &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + + spin_unlock(&napi_hash_lock); } EXPORT_SYMBOL_GPL(napi_hash_add); /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ -void napi_hash_del(struct napi_struct *napi) +bool napi_hash_del(struct napi_struct *napi) { + bool rcu_sync_needed = false; + spin_lock(&napi_hash_lock); - if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) + if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) { + rcu_sync_needed = true; hlist_del_rcu(&napi->napi_hash_node); - + } spin_unlock(&napi_hash_lock); + return rcu_sync_needed; } EXPORT_SYMBOL_GPL(napi_hash_del); @@ -4744,6 +5012,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); + napi_hash_add(napi); } EXPORT_SYMBOL(netif_napi_add); @@ -4763,8 +5032,12 @@ void napi_disable(struct napi_struct *n) } EXPORT_SYMBOL(napi_disable); +/* Must be called in process context */ void netif_napi_del(struct napi_struct *napi) { + might_sleep(); + if (napi_hash_del(napi)) + synchronize_net(); list_del_init(&napi->dev_list); napi_free_frags(napi); @@ -5351,7 +5624,7 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, - void *private) + void *upper_priv, void *upper_info) { struct netdev_notifier_changeupper_info changeupper_info; struct netdev_adjacent *i, *j, *to_i, *to_j; @@ -5375,6 +5648,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, changeupper_info.upper_dev = upper_dev; changeupper_info.master = master; changeupper_info.linking = true; + changeupper_info.upper_info = upper_info; ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, &changeupper_info.info); @@ -5382,7 +5656,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) return ret; - ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv, master); if (ret) return ret; @@ -5420,8 +5694,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, goto rollback_lower_mesh; } - call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, - &changeupper_info.info); + ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, + &changeupper_info.info); + ret = notifier_to_errno(ret); + if (ret) + goto rollback_lower_mesh; + return 0; rollback_lower_mesh: @@ -5475,7 +5753,7 @@ rollback_mesh: int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev) { - return __netdev_upper_dev_link(dev, upper_dev, false, NULL); + return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -5483,6 +5761,8 @@ EXPORT_SYMBOL(netdev_upper_dev_link); * netdev_master_upper_dev_link - Add a master link to the upper device * @dev: device * @upper_dev: new upper device + * @upper_priv: upper device private + * @upper_info: upper info to be passed down via notifier * * Adds a link to device which is upper to this one. In this case, only * one master upper device can be linked, although other non-master devices @@ -5491,20 +5771,14 @@ EXPORT_SYMBOL(netdev_upper_dev_link); * counts are adjusted and the function returns zero. */ int netdev_master_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + void *upper_priv, void *upper_info) { - return __netdev_upper_dev_link(dev, upper_dev, true, NULL); + return __netdev_upper_dev_link(dev, upper_dev, true, + upper_priv, upper_info); } EXPORT_SYMBOL(netdev_master_upper_dev_link); -int netdev_master_upper_dev_link_private(struct net_device *dev, - struct net_device *upper_dev, - void *private) -{ - return __netdev_upper_dev_link(dev, upper_dev, true, private); -} -EXPORT_SYMBOL(netdev_master_upper_dev_link_private); - /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device @@ -5663,7 +5937,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private); int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(struct net_device *dev)) + bool (*type_check)(const struct net_device *dev)) { struct net_device *lower = NULL; struct list_head *iter; @@ -5685,6 +5959,26 @@ int dev_get_nest_level(struct net_device *dev, } EXPORT_SYMBOL(dev_get_nest_level); +/** + * netdev_lower_change - Dispatch event about lower device state change + * @lower_dev: device + * @lower_state_info: state to dispatch + * + * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. + * The caller must hold the RTNL lock. + */ +void netdev_lower_state_changed(struct net_device *lower_dev, + void *lower_state_info) +{ + struct netdev_notifier_changelowerstate_info changelowerstate_info; + + ASSERT_RTNL(); + changelowerstate_info.lower_state_info = lower_state_info; + call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev, + &changelowerstate_info.info); +} +EXPORT_SYMBOL(netdev_lower_state_changed); + static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -6375,9 +6669,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, /* UFO needs SG and checksumming */ if (features & NETIF_F_UFO) { /* maybe split UFO into V4 and V6? */ - if (!((features & NETIF_F_GEN_CSUM) || - (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) - == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + if (!(features & NETIF_F_HW_CSUM) && + ((features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) != + (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) { netdev_dbg(dev, "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; @@ -7164,11 +7458,13 @@ EXPORT_SYMBOL(alloc_netdev_mqs); * This function does the last stage of destroying an allocated device * interface. The reference to the device object is released. * If this is the last reference then it will be freed. + * Must be called in process context. */ void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; + might_sleep(); netif_free_tx_queues(dev); #ifdef CONFIG_SYSFS kvfree(dev->_rx); @@ -7477,16 +7773,16 @@ static int dev_cpu_callback(struct notifier_block *nfb, netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { - if (mask & NETIF_F_GEN_CSUM) - mask |= NETIF_F_ALL_CSUM; + if (mask & NETIF_F_HW_CSUM) + mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; - all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ - if (all & NETIF_F_GEN_CSUM) - all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + if (all & NETIF_F_HW_CSUM) + all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } |