diff options
Diffstat (limited to 'net/ipv4')
61 files changed, 1783 insertions, 739 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f83de23a30e7..afcb435adfbe 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ - tcp_rate.o tcp_recovery.o \ + tcp_rate.o tcp_recovery.o tcp_ulp.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 58925b6597de..76c2077c3f5b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -150,7 +150,7 @@ void inet_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 22377c8ff14b..37db44f60718 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -1,5 +1,6 @@ #define pr_fmt(fmt) "IPsec: " fmt +#include <crypto/algapi.h> #include <crypto/hash.h> #include <linux/err.h> #include <linux/module.h> @@ -220,7 +221,9 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -277,7 +280,7 @@ static void ah_input_done(struct crypto_async_request *base, int err) auth_data = ah_tmp_auth(work_iph, ihl); icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out; @@ -393,7 +396,9 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); sg_init_table(sg, nfrags + sglists); - skb_to_sgvec_nomark(skb, sg, 0, skb->len); + err = skb_to_sgvec_nomark(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out_free; if (x->props.flags & XFRM_STATE_ESN) { /* Attach seqhi sg right after packet payload */ @@ -413,7 +418,7 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) goto out_free; } - err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + err = crypto_memneq(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG : 0; if (err) goto out_free; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index e9f3386a528b..8b52179ddc6e 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -539,7 +539,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, skb_reserve(skb, hlen); skb_reset_network_header(skb); - arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); + arp = skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); if (!src_hw) @@ -1113,13 +1113,17 @@ static int arp_invalidate(struct net_device *dev, __be32 ip) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; + struct neigh_table *tbl = &arp_tbl; if (neigh) { if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); } return err; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index ae206163c273..c4c6e1969ed0 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -265,7 +265,7 @@ static int cipso_v4_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - atomic_inc(&entry->lsm_data->refcount); + refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CIPSOV4; @@ -332,7 +332,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, } entry->key_len = cipso_ptr_len; entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len); - atomic_inc(&secattr->cache->refcount); + refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); @@ -375,7 +375,7 @@ static struct cipso_v4_doi *cipso_v4_doi_search(u32 doi) struct cipso_v4_doi *iter; list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list) - if (iter->doi == doi && atomic_read(&iter->refcount)) + if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } @@ -429,7 +429,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, } } - atomic_set(&doi_def->refcount, 1); + refcount_set(&doi_def->refcount, 1); spin_lock(&cipso_v4_doi_list_lock); if (cipso_v4_doi_search(doi_def->doi)) { @@ -533,7 +533,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!atomic_dec_and_test(&doi_def->refcount)) { + if (!refcount_dec_and_test(&doi_def->refcount)) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -EBUSY; goto doi_remove_return; @@ -576,7 +576,7 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) doi_def = cipso_v4_doi_search(doi); if (!doi_def) goto doi_getdef_return; - if (!atomic_inc_not_zero(&doi_def->refcount)) + if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: @@ -597,7 +597,7 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) if (!doi_def) return; - if (!atomic_dec_and_test(&doi_def->refcount)) + if (!refcount_dec_and_test(&doi_def->refcount)) return; spin_lock(&cipso_v4_doi_list_lock); list_del_rcu(&doi_def->list); @@ -630,7 +630,7 @@ int cipso_v4_doi_walk(u32 *skip_cnt, rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &cipso_v4_doi_list, list) - if (atomic_read(&iter_doi->refcount) > 0) { + if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index df14815a3b8c..38d9af9b917c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -176,6 +176,7 @@ EXPORT_SYMBOL(__ip_dev_find); static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); +static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy); #ifdef CONFIG_SYSCTL @@ -251,7 +252,7 @@ static struct in_device *inetdev_init(struct net_device *dev) /* Reference in_dev->dev */ dev_hold(dev); /* Account for reference dev->ip_ptr (below) */ - in_dev_hold(in_dev); + refcount_set(&in_dev->refcnt, 1); err = devinet_sysctl_register(in_dev); if (err) { @@ -441,6 +442,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; + struct in_validator_info ivi; + int ret; ASSERT_RTNL(); @@ -471,6 +474,23 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } } + /* Allow any devices that wish to register ifaddr validtors to weigh + * in now, before changes are committed. The rntl lock is serializing + * access here, so the state should not change between a validator call + * and a final notify on commit. This isn't invoked on promotion under + * the assumption that validators are checking the address itself, and + * not the flags. + */ + ivi.ivi_addr = ifa->ifa_address; + ivi.ivi_dev = ifa->ifa_dev; + ret = blocking_notifier_call_chain(&inetaddr_validator_chain, + NETDEV_UP, &ivi); + ret = notifier_to_errno(ret); + if (ret) { + inet_free_ifa(ifa); + return ret; + } + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; @@ -1356,6 +1376,19 @@ int unregister_inetaddr_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_inetaddr_notifier); +int register_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inetaddr_validator_notifier); + +int unregister_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&inetaddr_validator_chain, + nb); +} +EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); + /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 93322f895eab..0cbee0a666ff 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -307,7 +307,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->data_len += tailen; skb->truesize += tailen; if (sk) - atomic_add(tailen, &sk->sk_wmem_alloc); + refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } @@ -377,9 +377,11 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * esp->esph = esph; sg_init_table(sg, esp->nfrags); - skb_to_sgvec(skb, sg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, sg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; if (!esp->inplace) { int allocsize; @@ -403,9 +405,11 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * spin_unlock_bh(&x->lock); sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1); - skb_to_sgvec(skb, dsg, - (unsigned char *)esph - skb->data, - assoclen + ivlen + esp->clen + alen); + err = skb_to_sgvec(skb, dsg, + (unsigned char *)esph - skb->data, + assoclen + ivlen + esp->clen + alen); + if (unlikely(err < 0)) + goto error; } if ((x->props.flags & XFRM_STATE_ESN)) @@ -605,7 +609,7 @@ static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) * decryption. */ if ((x->props.flags & XFRM_STATE_ESN)) { - esph = (void *)skb_push(skb, 4); + esph = skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; @@ -690,7 +694,9 @@ skip_cow: esp_input_set_header(skb, seqhi); sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + err = skb_to_sgvec(skb, sg, 0, skb->len); + if (unlikely(err < 0)) + goto out; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 83e3ed258467..4e678fa892dd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -588,13 +588,15 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, + NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, + &cfg, NULL); else err = -ENOBUFS; } @@ -626,14 +628,15 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_config *cfg) + struct nlmsghdr *nlh, struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, - NULL); + extack); if (err < 0) goto errout; @@ -654,6 +657,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { + NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } @@ -681,7 +685,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), - nla_len(attr)); + nla_len(attr), + extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); @@ -698,7 +703,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, + extack); if (err < 0) goto errout; break; @@ -718,17 +724,18 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; tb = fib_get_table(net, cfg.fc_table); if (!tb) { + NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto errout; } - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } @@ -741,7 +748,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; @@ -751,7 +758,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, &cfg, extack); errout: return err; } @@ -845,9 +852,9 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - fib_table_insert(net, tb, &cfg); + fib_table_insert(net, tb, &cfg, NULL); else - fib_table_delete(net, tb, &cfg); + fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 9c02920725db..769ab87ebc4b 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -28,8 +28,10 @@ static inline void fib_alias_accessed(struct fib_alias *fa) /* Exported by fib_semantics.c */ void fib_release_info(struct fib_info *); -struct fib_info *fib_create_info(struct fib_config *cfg); -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack); +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ad9ad4aab5da..222100103808 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -32,6 +32,7 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/netlink.h> #include <net/arp.h> #include <net/ip.h> @@ -151,7 +152,8 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp) * free_fib_info_rcu() */ - dst_free(&rt->dst); + dst_dev_put(&rt->dst); + dst_release_immediate(&rt->dst); } static void free_nh_exceptions(struct fib_nh *nh) @@ -193,8 +195,10 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) struct rtable *rt; rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); - if (rt) - dst_free(&rt->dst); + if (rt) { + dst_dev_put(&rt->dst); + dst_release_immediate(&rt->dst); + } } free_percpu(rtp); } @@ -456,7 +460,8 @@ static int fib_detect_death(struct fib_info *fi, int order, #ifdef CONFIG_IP_ROUTE_MULTIPATH -static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) +static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, + struct netlink_ext_ack *extack) { int nhs = 0; @@ -466,22 +471,35 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) } /* leftover implies invalid nexthop configuration, discard it */ - return remaining > 0 ? 0 : nhs; + if (remaining > 0) { + NL_SET_ERR_MSG(extack, + "Invalid nexthop configuration - extra data after nexthops"); + nhs = 0; + } + + return nhs; } static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, - int remaining, struct fib_config *cfg) + int remaining, struct fib_config *cfg, + struct netlink_ext_ack *extack) { int ret; change_nexthops(fi) { int attrlen; - if (!rtnh_ok(rtnh, remaining)) + if (!rtnh_ok(rtnh, remaining)) { + NL_SET_ERR_MSG(extack, + "Invalid nexthop configuration - extra data after nexthop"); return -EINVAL; + } - if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) { + NL_SET_ERR_MSG(extack, + "Invalid flags for nexthop - can not contain DEAD or LINKDOWN"); return -EINVAL; + } nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; @@ -507,13 +525,17 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); - if (!nla_entype) + if (!nla_entype) { + NL_SET_BAD_ATTR(extack, nla); + NL_SET_ERR_MSG(extack, + "Encap type is missing"); goto err_inval; + } ret = lwtunnel_build_state(nla_get_u16( nla_entype), nla, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (ret) goto errout; nexthop_nh->nh_lwtstate = @@ -595,7 +617,8 @@ static inline void fib_add_weight(struct fib_info *fi, static int fib_encap_match(u16 encap_type, struct nlattr *encap, const struct fib_nh *nh, - const struct fib_config *cfg) + const struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct lwtunnel_state *lwtstate; int ret, result = 0; @@ -603,8 +626,8 @@ static int fib_encap_match(u16 encap_type, if (encap_type == LWTUNNEL_ENCAP_NONE) return 0; - ret = lwtunnel_build_state(encap_type, encap, - AF_INET, cfg, &lwtstate); + ret = lwtunnel_build_state(encap_type, encap, AF_INET, + cfg, &lwtstate, extack); if (!ret) { result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); lwtstate_free(lwtstate); @@ -613,7 +636,8 @@ static int fib_encap_match(u16 encap_type, return result; } -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack) { #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; @@ -625,9 +649,9 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) if (cfg->fc_oif || cfg->fc_gw) { if (cfg->fc_encap) { - if (fib_encap_match(cfg->fc_encap_type, - cfg->fc_encap, fi->fib_nh, cfg)) - return 1; + if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap, + fi->fib_nh, cfg, extack)) + return 1; } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) @@ -716,7 +740,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) * |-> {local prefix} (terminal node) */ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh) + struct fib_nh *nh, struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -729,16 +753,25 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, if (nh->nh_flags & RTNH_F_ONLINK) { unsigned int addr_type; - if (cfg->fc_scope >= RT_SCOPE_LINK) + if (cfg->fc_scope >= RT_SCOPE_LINK) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid scope"); return -EINVAL; + } dev = __dev_get_by_index(net, nh->nh_oif); if (!dev) return -ENODEV; - if (!(dev->flags & IFF_UP)) + if (!(dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, + "Nexthop device is not up"); return -ENETDOWN; + } addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw); - if (addr_type != RTN_UNICAST) + if (addr_type != RTN_UNICAST) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid gateway"); return -EINVAL; + } if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; nh->nh_dev = dev; @@ -778,18 +811,25 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } if (err) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid gateway"); rcu_read_unlock(); return err; } } err = -EINVAL; - if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) + if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) { + NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); goto out; + } nh->nh_scope = res.scope; nh->nh_oif = FIB_RES_OIF(res); nh->nh_dev = dev = FIB_RES_DEV(res); - if (!dev) + if (!dev) { + NL_SET_ERR_MSG(extack, + "No egress device for nexthop gateway"); goto out; + } dev_hold(dev); if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; @@ -797,17 +837,21 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } else { struct in_device *in_dev; - if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) + if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) { + NL_SET_ERR_MSG(extack, + "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set"); return -EINVAL; - + } rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); if (!in_dev) goto out; err = -ENETDOWN; - if (!(in_dev->dev->flags & IFF_UP)) + if (!(in_dev->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Device for nexthop is not up"); goto out; + } nh->nh_dev = in_dev->dev; dev_hold(nh->nh_dev); nh->nh_scope = RT_SCOPE_HOST; @@ -982,7 +1026,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) return 0; } -struct fib_info *fib_create_info(struct fib_config *cfg) +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack) { int err; struct fib_info *fi = NULL; @@ -994,15 +1039,20 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto err_inval; /* Fast check to catch the most weird cases */ - if (fib_props[cfg->fc_type].scope > cfg->fc_scope) + if (fib_props[cfg->fc_type].scope > cfg->fc_scope) { + NL_SET_ERR_MSG(extack, "Invalid scope"); goto err_inval; + } - if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) { + NL_SET_ERR_MSG(extack, + "Invalid rtm_flags - can not contain DEAD or LINKDOWN"); goto err_inval; + } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { - nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); + nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack); if (nhs == 0) goto err_inval; } @@ -1065,18 +1115,29 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg); + err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); if (err != 0) goto failure; - if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) + if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) { + NL_SET_ERR_MSG(extack, + "Nexthop device index does not match RTA_OIF"); goto err_inval; - if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) + } + if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) { + NL_SET_ERR_MSG(extack, + "Nexthop gateway does not match RTA_GATEWAY"); goto err_inval; + } #ifdef CONFIG_IP_ROUTE_CLASSID - if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) + if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) { + NL_SET_ERR_MSG(extack, + "Nexthop class id does not match RTA_FLOW"); goto err_inval; + } #endif #else + NL_SET_ERR_MSG(extack, + "Multipath support not enabled in kernel"); goto err_inval; #endif } else { @@ -1085,11 +1146,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (cfg->fc_encap) { struct lwtunnel_state *lwtstate; - if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) + if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) { + NL_SET_ERR_MSG(extack, + "LWT encap type not specified"); goto err_inval; + } err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto failure; @@ -1109,8 +1173,11 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } if (fib_props[cfg->fc_type].error) { - if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) + if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) { + NL_SET_ERR_MSG(extack, + "Gateway, device and multipath can not be specified for this route type"); goto err_inval; + } goto link_it; } else { switch (cfg->fc_type) { @@ -1121,19 +1188,30 @@ struct fib_info *fib_create_info(struct fib_config *cfg) case RTN_MULTICAST: break; default: + NL_SET_ERR_MSG(extack, "Invalid route type"); goto err_inval; } } - if (cfg->fc_scope > RT_SCOPE_HOST) + if (cfg->fc_scope > RT_SCOPE_HOST) { + NL_SET_ERR_MSG(extack, "Invalid scope"); goto err_inval; + } if (cfg->fc_scope == RT_SCOPE_HOST) { struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ - if (nhs != 1 || nh->nh_gw) + if (nhs != 1) { + NL_SET_ERR_MSG(extack, + "Route with host scope can not have multiple nexthops"); goto err_inval; + } + if (nh->nh_gw) { + NL_SET_ERR_MSG(extack, + "Route with host scope can not have a gateway"); + goto err_inval; + } nh->nh_scope = RT_SCOPE_NOWHERE; nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); err = -ENODEV; @@ -1143,7 +1221,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh); + err = fib_check_nh(cfg, fi, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) @@ -1153,8 +1231,10 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_flags |= RTNH_F_LINKDOWN; } - if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) + if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) { + NL_SET_ERR_MSG(extack, "Invalid prefsrc address"); goto err_inval; + } change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); @@ -1173,7 +1253,7 @@ link_it: } fi->fib_treeref++; - atomic_inc(&fi->fib_clntref); + refcount_set(&fi->fib_clntref, 1); spin_lock_bh(&fib_info_lock); hlist_add_head(&fi->fib_hash, &fib_info_hash[fib_info_hashfn(fi)]); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 51182ff2b441..64668c69dda6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1099,9 +1099,25 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } +static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) +{ + if (plen > KEYLENGTH) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + return false; + } + + if ((plen < KEYLENGTH) && (key << plen)) { + NL_SET_ERR_MSG(extack, + "Invalid prefix for given prefix length"); + return false; + } + + return true; +} + /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; @@ -1115,17 +1131,14 @@ int fib_table_insert(struct net *net, struct fib_table *tb, u32 key; int err; - if (plen > KEYLENGTH) - return -EINVAL; - key = ntohl(cfg->fc_dst); - pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); - - if ((plen < KEYLENGTH) && (key << plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; - fi = fib_create_info(cfg); + pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); + + fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; @@ -1450,8 +1463,9 @@ found: } if (!(fib_flags & FIB_LOOKUP_NOREF)) - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); + res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->type = fa->fa_type; @@ -1507,7 +1521,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; @@ -1517,12 +1531,9 @@ int fib_table_delete(struct net *net, struct fib_table *tb, u8 tos = cfg->fc_tos; u32 key; - if (plen > KEYLENGTH) - return -EINVAL; - key = ntohl(cfg->fc_dst); - if ((plen < KEYLENGTH) && (key << plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); @@ -1551,7 +1562,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && - fib_nh_match(cfg, fi) == 0) { + fib_nh_match(cfg, fi, extack) == 0) { fa_to_delete = fa; break; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 805f6607f8d9..8e0257d01200 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -8,6 +8,7 @@ #include <linux/kernel.h> #include <net/genetlink.h> #include <net/gue.h> +#include <net/fou.h> #include <net/ip.h> #include <net/protocol.h> #include <net/udp.h> @@ -859,25 +860,6 @@ size_t gue_encap_hlen(struct ip_tunnel_encap *e) } EXPORT_SYMBOL(gue_encap_hlen); -static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, - struct flowi4 *fl4, u8 *protocol, __be16 sport) -{ - struct udphdr *uh; - - skb_push(skb, sizeof(struct udphdr)); - skb_reset_transport_header(skb); - - uh = udp_hdr(skb); - - uh->dest = e->dport; - uh->source = sport; - uh->len = htons(skb->len); - udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, - fl4->saddr, fl4->daddr, skb->len); - - *protocol = IPPROTO_UDP; -} - int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { @@ -894,24 +876,6 @@ int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, } EXPORT_SYMBOL(__fou_build_header); -int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi4 *fl4) -{ - int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : - SKB_GSO_UDP_TUNNEL; - __be16 sport; - int err; - - err = __fou_build_header(skb, e, protocol, &sport, type); - if (err) - return err; - - fou_build_udp(skb, e, fl4, protocol, sport); - - return 0; -} -EXPORT_SYMBOL(fou_build_header); - int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { @@ -985,8 +949,46 @@ int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, } EXPORT_SYMBOL(__gue_build_header); -int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, - u8 *protocol, struct flowi4 *fl4) +#ifdef CONFIG_NET_FOU_IP_TUNNELS + +static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, + struct flowi4 *fl4, u8 *protocol, __be16 sport) +{ + struct udphdr *uh; + + skb_push(skb, sizeof(struct udphdr)); + skb_reset_transport_header(skb); + + uh = udp_hdr(skb); + + uh->dest = e->dport; + uh->source = sport; + uh->len = htons(skb->len); + udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, + fl4->saddr, fl4->daddr, skb->len); + + *protocol = IPPROTO_UDP; +} + +static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4) +{ + int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : + SKB_GSO_UDP_TUNNEL; + __be16 sport; + int err; + + err = __fou_build_header(skb, e, protocol, &sport, type); + if (err) + return err; + + fou_build_udp(skb, e, fl4, protocol, sport); + + return 0; +} + +static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, + u8 *protocol, struct flowi4 *fl4) { int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; @@ -1001,9 +1003,7 @@ int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, return 0; } -EXPORT_SYMBOL(gue_build_header); -#ifdef CONFIG_NET_FOU_IP_TUNNELS static const struct ip_tunnel_encap_ops fou_iptun_ops = { .encap_hlen = fou_encap_hlen, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 9144fa7df2ad..c2be26b98b5f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -489,7 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key_hash(net, fl4, skb_in); + rt = ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index ec9a396fa466..28f14afd0dd3 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -173,7 +173,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, static void ip_ma_put(struct ip_mc_list *im) { - if (atomic_dec_and_test(&im->refcnt)) { + if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } @@ -199,7 +199,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) - atomic_dec(&im->refcnt); + refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; @@ -213,7 +213,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) - atomic_inc(&im->refcnt); + refcount_inc(&im->refcnt); } static void igmp_gq_start_timer(struct in_device *in_dev) @@ -249,7 +249,7 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) spin_unlock_bh(&im->lock); return; } - atomic_dec(&im->refcnt); + refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); @@ -414,7 +414,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, skb = igmpv3_newpack(dev, dev->mtu); if (!skb) return NULL; - pgr = (struct igmpv3_grec *)skb_put(skb, sizeof(struct igmpv3_grec)); + pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; @@ -508,7 +508,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, } if (!skb) return NULL; - psrc = (__be32 *)skb_put(skb, sizeof(__be32)); + psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || @@ -742,7 +742,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; - ih = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); + ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; @@ -1374,7 +1374,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; im->sfcount[MCAST_EXCLUDE] = 1; - atomic_set(&im->refcnt, 1); + refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST setup_timer(&im->timer, igmp_timer_expire, (unsigned long)im); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 1054d330bf9d..4089c013cb03 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -25,6 +25,7 @@ #include <net/xfrm.h> #include <net/tcp.h> #include <net/sock_reuseport.h> +#include <net/addrconf.h> #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -755,7 +756,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, * are committed to memory and refcnt initialized. */ smp_wmb(); - atomic_set(&req->rsk_refcnt, 2 + 1); + refcount_set(&req->rsk_refcnt, 2 + 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, @@ -789,7 +790,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); - newsk->sk_write_space = sk_stream_write_space; /* listeners have SOCK_RCU_FREE, not the children */ sock_reset_flag(newsk, SOCK_RCU_FREE); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index b5e9317eaf9e..96e95e83cc61 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -276,11 +276,11 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) { if (del_timer(&fq->timer)) - atomic_dec(&fq->refcnt); + refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); - atomic_dec(&fq->refcnt); + refcount_dec(&fq->refcnt); } } EXPORT_SYMBOL(inet_frag_kill); @@ -329,7 +329,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, */ hlist_for_each_entry(qp, &hb->chain, list) { if (qp->net == nf && f->match(qp, arg)) { - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); spin_unlock(&hb->chain_lock); qp_in->flags |= INET_FRAG_COMPLETE; inet_frag_put(qp_in, f); @@ -339,9 +339,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, #endif qp = qp_in; if (!mod_timer(&qp->timer, jiffies + nf->timeout)) - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); spin_unlock(&hb->chain_lock); @@ -370,7 +370,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); - atomic_set(&q->refcnt, 1); + refcount_set(&q->refcnt, 1); return q; } @@ -405,7 +405,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, spin_lock(&hb->chain_lock); hlist_for_each_entry(q, &hb->chain, list) { if (q->net == nf && f->match(q, key)) { - atomic_inc(&q->refcnt); + refcount_inc(&q->refcnt); spin_unlock(&hb->chain_lock); return q; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e9a59d2d91d4..2e3389d614d1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -43,7 +43,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr, /* This function handles inet_sock, but also timewait and request sockets * for IPv4/IPv6. */ -u32 sk_ehashfn(const struct sock *sk) +static u32 sk_ehashfn(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6 && @@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(__inet_lookup_listener); /* All sockets share common refcount, but have different destructors */ void sock_gen_put(struct sock *sk) { - if (!atomic_dec_and_test(&sk->sk_refcnt)) + if (!refcount_dec_and_test(&sk->sk_refcnt)) return; if (sk->sk_state == TCP_TIME_WAIT) @@ -287,7 +287,7 @@ begin: continue; if (likely(INET_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index f8aff2c71cde..5b039159e67a 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -76,7 +76,7 @@ void inet_twsk_free(struct inet_timewait_sock *tw) void inet_twsk_put(struct inet_timewait_sock *tw) { - if (atomic_dec_and_test(&tw->tw_refcnt)) + if (refcount_dec_and_test(&tw->tw_refcnt)) inet_twsk_free(tw); } EXPORT_SYMBOL_GPL(inet_twsk_put); @@ -131,7 +131,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 4); + refcount_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -195,7 +195,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, * to a non null value before everything is setup for this * timewait socket. */ - atomic_set(&tw->tw_refcnt, 0); + refcount_set(&tw->tw_refcnt, 0); __module_get(tw->tw_prot->owner); } @@ -278,7 +278,7 @@ restart: atomic_read(&twsk_net(tw)->count)) continue; - if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) continue; if (unlikely((tw->tw_family != family) || diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 86fa45809540..c5a117cc6619 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -115,7 +115,7 @@ static void inetpeer_gc_worker(struct work_struct *work) n = list_entry(p->gc_list.next, struct inet_peer, gc_list); - if (!atomic_read(&p->refcnt)) { + if (refcount_read(&p->refcnt) == 1) { list_del(&p->gc_list); kmem_cache_free(peer_cachep, p); } @@ -202,10 +202,11 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int cmp = inetpeer_addr_cmp(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was - * deleted (refcnt=-1) + * deleted (refcnt=0) */ - if (!atomic_add_unless(&u->refcnt, 1, -1)) + if (!refcount_inc_not_zero(&u->refcnt)) { u = NULL; + } return u; } if (cmp == -1) @@ -382,11 +383,10 @@ static int inet_peer_gc(struct inet_peer_base *base, while (stackptr > stack) { stackptr--; p = rcu_deref_locked(**stackptr, base); - if (atomic_read(&p->refcnt) == 0) { + if (refcount_read(&p->refcnt) == 1) { smp_rmb(); delta = (__u32)jiffies - p->dtime; - if (delta >= ttl && - atomic_cmpxchg(&p->refcnt, 0, -1) == 0) { + if (delta >= ttl && refcount_dec_if_one(&p->refcnt)) { p->gc_next = gchead; gchead = p; } @@ -432,7 +432,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, relookup: p = lookup(daddr, stack, base); if (p != peer_avl_empty) { - atomic_inc(&p->refcnt); + refcount_inc(&p->refcnt); write_sequnlock_bh(&base->lock); return p; } @@ -444,7 +444,7 @@ relookup: p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { p->daddr = *daddr; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 2); atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -468,7 +468,7 @@ void inet_putpeer(struct inet_peer *p) { p->dtime = (__u32)jiffies; smp_mb__before_atomic(); - atomic_dec(&p->refcnt); + refcount_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b3cdeec85f1f..9a8cfac503dc 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -312,7 +312,7 @@ static int ip_frag_reinit(struct ipq *qp) unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { - atomic_inc(&qp->q.refcnt); + refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index e90c80a548ad..7a7829e839c2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -592,7 +592,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, struct iphdr *iph; struct gre_base_hdr *greh; - iph = (struct iphdr *)skb_push(skb, t->hlen + sizeof(*iph)); + iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); @@ -779,7 +779,8 @@ static struct pernet_operations ipgre_net_ops = { .size = sizeof(struct ip_tunnel_net), }; -static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be16 flags; @@ -802,7 +803,8 @@ static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be32 daddr; @@ -823,7 +825,7 @@ static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) } out: - return ipgre_tunnel_validate(tb, data); + return ipgre_tunnel_validate(tb, data, extack); } static int ipgre_netlink_parms(struct net_device *dev, @@ -957,7 +959,8 @@ static void ipgre_tap_setup(struct net_device *dev) } static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; @@ -979,7 +982,8 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; @@ -1155,7 +1159,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, t = netdev_priv(dev); t->collect_md = true; - err = ipgre_newlink(net, dev, tb, NULL); + err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 532b36e9ce2a..7eb252dcecee 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -173,7 +173,8 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, } skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + if (!skb->mark) + skb->mark = sk->sk_mark; /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -1037,7 +1038,7 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (atomic_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len + 15, 1, @@ -1145,7 +1146,7 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; @@ -1369,7 +1370,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, skb->len += len; skb->data_len += len; skb->truesize += len; - atomic_add(len, &sk->sk_wmem_alloc); + refcount_add(len, &sk->sk_wmem_alloc); offset += len; size -= len; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ec4fe3d4b5c9..ecc4b4a2413e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -934,14 +934,9 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -ENOBUFS; break; } - msf = kmalloc(optlen, GFP_KERNEL); - if (!msf) { - err = -ENOBUFS; - break; - } - err = -EFAULT; - if (copy_from_user(msf, optval, optlen)) { - kfree(msf); + msf = memdup_user(optval, optlen); + if (IS_ERR(msf)) { + err = PTR_ERR(msf); break; } /* numsrc >= (1G-4) overflow in 32 bits */ @@ -1090,14 +1085,11 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -ENOBUFS; break; } - gsf = kmalloc(optlen, GFP_KERNEL); - if (!gsf) { - err = -ENOBUFS; + gsf = memdup_user(optval, optlen); + if (IS_ERR(gsf)) { + err = PTR_ERR(gsf); break; } - err = -EFAULT; - if (copy_from_user(gsf, optval, optlen)) - goto mc_msf_out; /* numsrc >= (4G-140)/128 overflow in 32 bits */ if (gsf->gf_numsrc >= 0x1ffffff || diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index baf196eaf1d8..2f39479be92f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -134,10 +134,12 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, struct metadata_dst *res; struct ip_tunnel_info *dst, *src; - if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + if (!md || md->type != METADATA_IP_TUNNEL || + md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + return NULL; - res = metadata_dst_alloc(0, flags); + res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags); if (!res) return NULL; @@ -228,14 +230,16 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { static int ip_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; int err; - err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, NULL); + err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, + extack); if (err < 0) return err; @@ -325,7 +329,8 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { static int ip6_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; @@ -333,7 +338,7 @@ static int ip6_tun_build_state(struct nlattr *attr, int err; err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy, - NULL); + extack); if (err < 0) return err; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 4ec9affb2252..0192c255e508 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -465,7 +465,8 @@ static struct pernet_operations vti_net_ops = { .size = sizeof(struct ip_tunnel_net), }; -static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return 0; } @@ -503,7 +504,8 @@ static void vti_netlink_parms(struct nlattr *data[], } static int vti_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel_parm parms; __u32 fwmark = 0; @@ -513,7 +515,8 @@ static int vti_newlink(struct net *src_net, struct net_device *dev, } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index c3b12b1c7162..4c5dfe6bd34d 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -813,8 +813,7 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d if (!skb) return; skb_reserve(skb, hlen); - b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt)); - memset(b, 0, sizeof(struct bootp_pkt)); + b = skb_put_zero(skb, sizeof(struct bootp_pkt)); /* Construct IP header */ skb_reset_network_header(skb); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 1e441c6f2160..fb1ad22b5e29 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -375,7 +375,8 @@ static int ipip_tunnel_init(struct net_device *dev) return ip_tunnel_init(dev); } -static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; @@ -469,7 +470,8 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[], } static int ipip_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; @@ -488,7 +490,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8ae425cad818..bb909f1d7537 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -109,6 +109,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); +static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); static void mroute_clean_tables(struct mr_table *mrt, bool all); static void ipmr_expire_process(unsigned long arg); @@ -669,7 +670,8 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct iphdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); @@ -972,7 +974,8 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, /* Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { - struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); + struct nlmsghdr *nlh = skb_pull(skb, + sizeof(struct iphdr)); if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - @@ -993,8 +996,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, } } -/* Bounce a cache query up to mrouted. We could use netlink for this but mrouted - * expects the following bizarre scheme. +/* Bounce a cache query up to mrouted and netlink. * * Called under mrt_lock. */ @@ -1044,7 +1046,7 @@ static int ipmr_cache_report(struct mr_table *mrt, msg->im_vif = vifi; skb_dst_set(skb, dst_clone(skb_dst(pkt))); /* Add our header */ - igmp = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); + igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; msg->im_msgtype = assert; igmp->code = 0; @@ -1060,6 +1062,8 @@ static int ipmr_cache_report(struct mr_table *mrt, return -EINVAL; } + igmpmsg_netlink_event(mrt, skb); + /* Deliver to mrouted */ ret = sock_queue_rcv_skb(mroute_sk, skb); rcu_read_unlock(); @@ -2339,6 +2343,130 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } +static size_t igmpmsg_netlink_msgsize(size_t payloadlen) +{ + size_t len = + NLMSG_ALIGN(sizeof(struct rtgenmsg)) + + nla_total_size(1) /* IPMRA_CREPORT_MSGTYPE */ + + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + /* IPMRA_CREPORT_PKT */ + + nla_total_size(payloadlen) + ; + + return len; +} + +static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt) +{ + struct net *net = read_pnet(&mrt->net); + struct nlmsghdr *nlh; + struct rtgenmsg *rtgenm; + struct igmpmsg *msg; + struct sk_buff *skb; + struct nlattr *nla; + int payloadlen; + + payloadlen = pkt->len - sizeof(struct igmpmsg); + msg = (struct igmpmsg *)skb_network_header(pkt); + + skb = nlmsg_new(igmpmsg_netlink_msgsize(payloadlen), GFP_ATOMIC); + if (!skb) + goto errout; + + nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, + sizeof(struct rtgenmsg), 0); + if (!nlh) + goto errout; + rtgenm = nlmsg_data(nlh); + rtgenm->rtgen_family = RTNL_FAMILY_IPMR; + if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || + nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif) || + nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, + msg->im_src.s_addr) || + nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, + msg->im_dst.s_addr)) + goto nla_put_failure; + + nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); + if (!nla || skb_copy_bits(pkt, sizeof(struct igmpmsg), + nla_data(nla), payloadlen)) + goto nla_put_failure; + + nlmsg_end(skb, nlh); + + rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE_R, NULL, GFP_ATOMIC); + return; + +nla_put_failure: + nlmsg_cancel(skb, nlh); +errout: + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE_R, -ENOBUFS); +} + +static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[RTA_MAX + 1]; + struct sk_buff *skb = NULL; + struct mfc_cache *cache; + struct mr_table *mrt; + struct rtmsg *rtm; + __be32 src, grp; + u32 tableid; + int err; + + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv4_policy, extack); + if (err < 0) + goto errout; + + rtm = nlmsg_data(nlh); + + src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; + grp = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; + tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0; + + mrt = ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); + if (IS_ERR(mrt)) { + err = PTR_ERR(mrt); + goto errout_free; + } + + /* entries are added/deleted only under RTNL */ + rcu_read_lock(); + cache = ipmr_cache_find(mrt, src, grp); + rcu_read_unlock(); + if (!cache) { + err = -ENOENT; + goto errout_free; + } + + skb = nlmsg_new(mroute_msgsize(false, mrt->maxvif), GFP_KERNEL); + if (!skb) { + err = -ENOBUFS; + goto errout_free; + } + + err = ipmr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, cache, + RTM_NEWROUTE, 0); + if (err < 0) + goto errout_free; + + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + +errout: + return err; + +errout_free: + kfree_skb(skb); + goto errout; +} + static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2526,6 +2654,129 @@ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh, return ipmr_mfc_delete(tbl, &mfcc, parent); } +static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) +{ + u32 queue_len = atomic_read(&mrt->cache_resolve_queue_len); + + if (nla_put_u32(skb, IPMRA_TABLE_ID, mrt->id) || + nla_put_u32(skb, IPMRA_TABLE_CACHE_RES_QUEUE_LEN, queue_len) || + nla_put_s32(skb, IPMRA_TABLE_MROUTE_REG_VIF_NUM, + mrt->mroute_reg_vif_num) || + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, + mrt->mroute_do_assert) || + nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim)) + return false; + + return true; +} + +static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb) +{ + struct nlattr *vif_nest; + struct vif_device *vif; + + /* if the VIF doesn't exist just continue */ + if (!VIF_EXISTS(mrt, vifid)) + return true; + + vif = &mrt->vif_table[vifid]; + vif_nest = nla_nest_start(skb, IPMRA_VIF); + if (!vif_nest) + return false; + if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif->dev->ifindex) || + nla_put_u32(skb, IPMRA_VIFA_VIF_ID, vifid) || + nla_put_u16(skb, IPMRA_VIFA_FLAGS, vif->flags) || + nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, vif->bytes_in, + IPMRA_VIFA_PAD) || + nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, vif->bytes_out, + IPMRA_VIFA_PAD) || + nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, vif->pkt_in, + IPMRA_VIFA_PAD) || + nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, vif->pkt_out, + IPMRA_VIFA_PAD) || + nla_put_be32(skb, IPMRA_VIFA_LOCAL_ADDR, vif->local) || + nla_put_be32(skb, IPMRA_VIFA_REMOTE_ADDR, vif->remote)) { + nla_nest_cancel(skb, vif_nest); + return false; + } + nla_nest_end(skb, vif_nest); + + return true; +} + +static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct nlmsghdr *nlh = NULL; + unsigned int t = 0, s_t; + unsigned int e = 0, s_e; + struct mr_table *mrt; + + s_t = cb->args[0]; + s_e = cb->args[1]; + + ipmr_for_each_table(mrt, net) { + struct nlattr *vifs, *af; + struct ifinfomsg *hdr; + u32 i; + + if (t < s_t) + goto skip_table; + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWLINK, + sizeof(*hdr), NLM_F_MULTI); + if (!nlh) + break; + + hdr = nlmsg_data(nlh); + memset(hdr, 0, sizeof(*hdr)); + hdr->ifi_family = RTNL_FAMILY_IPMR; + + af = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af) { + nlmsg_cancel(skb, nlh); + goto out; + } + + if (!ipmr_fill_table(mrt, skb)) { + nlmsg_cancel(skb, nlh); + goto out; + } + + vifs = nla_nest_start(skb, IPMRA_TABLE_VIFS); + if (!vifs) { + nla_nest_end(skb, af); + nlmsg_end(skb, nlh); + goto out; + } + for (i = 0; i < mrt->maxvif; i++) { + if (e < s_e) + goto skip_entry; + if (!ipmr_fill_vif(mrt, i, skb)) { + nla_nest_end(skb, vifs); + nla_nest_end(skb, af); + nlmsg_end(skb, nlh); + goto out; + } +skip_entry: + e++; + } + s_e = 0; + e = 0; + nla_nest_end(skb, vifs); + nla_nest_end(skb, af); + nlmsg_end(skb, nlh); +skip_table: + t++; + } + +out: + cb->args[1] = e; + cb->args[0] = t; + + return skb->len; +} + #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif @@ -2863,11 +3114,14 @@ int __init ip_mr_init(void) } #endif rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, - NULL, ipmr_rtm_dumproute, NULL); + ipmr_rtm_getroute, ipmr_rtm_dumproute, NULL); rtnl_register(RTNL_FAMILY_IPMR, RTM_NEWROUTE, ipmr_rtm_route, NULL, NULL); rtnl_register(RTNL_FAMILY_IPMR, RTM_DELROUTE, ipmr_rtm_route, NULL, NULL); + + rtnl_register(RTNL_FAMILY_IPMR, RTM_GETLINK, + NULL, ipmr_rtm_dumplink, NULL); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 038f293c2376..7d72decb80f9 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -47,7 +47,7 @@ struct clusterip_config { __be32 clusterip; /* the IP address */ u_int8_t clustermac[ETH_ALEN]; /* the MAC address */ - struct net_device *dev; /* device */ + int ifindex; /* device ifindex */ u_int16_t num_total_nodes; /* total number of nodes */ unsigned long local_nodes; /* node number array */ @@ -57,6 +57,9 @@ struct clusterip_config { enum clusterip_hashmode hash_mode; /* which hashing mode */ u_int32_t hash_initval; /* hash initialization */ struct rcu_head rcu; + + char ifname[IFNAMSIZ]; /* device ifname */ + struct notifier_block notifier; /* refresh c->ifindex in it */ }; #ifdef CONFIG_PROC_FS @@ -98,9 +101,8 @@ clusterip_config_put(struct clusterip_config *c) * entry(rule) is removed, remove the config from lists, but don't free it * yet, since proc-files could still be holding references */ static inline void -clusterip_config_entry_put(struct clusterip_config *c) +clusterip_config_entry_put(struct net *net, struct clusterip_config *c) { - struct net *net = dev_net(c->dev); struct clusterip_net *cn = net_generic(net, clusterip_net_id); local_bh_disable(); @@ -109,8 +111,7 @@ clusterip_config_entry_put(struct clusterip_config *c) spin_unlock(&cn->lock); local_bh_enable(); - dev_mc_del(c->dev, c->clustermac); - dev_put(c->dev); + unregister_netdevice_notifier(&c->notifier); /* In case anyone still accesses the file, the open/close * functions are also incrementing the refcount on their own, @@ -170,19 +171,55 @@ clusterip_config_init_nodelist(struct clusterip_config *c, set_bit(i->local_nodes[n] - 1, &c->local_nodes); } -static struct clusterip_config * -clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, - struct net_device *dev) +static int +clusterip_netdev_event(struct notifier_block *this, unsigned long event, + void *ptr) { - struct net *net = dev_net(dev); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct clusterip_config *c; + + c = container_of(this, struct clusterip_config, notifier); + switch (event) { + case NETDEV_REGISTER: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } + break; + case NETDEV_UNREGISTER: + if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + case NETDEV_CHANGENAME: + if (!strcmp(dev->name, c->ifname)) { + c->ifindex = dev->ifindex; + dev_mc_add(dev, c->clustermac); + } else if (dev->ifindex == c->ifindex) { + dev_mc_del(dev, c->clustermac); + c->ifindex = -1; + } + break; + } + + return NOTIFY_DONE; +} + +static struct clusterip_config * +clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, + __be32 ip, const char *iniface) +{ struct clusterip_net *cn = net_generic(net, clusterip_net_id); + struct clusterip_config *c; + int err; c = kzalloc(sizeof(*c), GFP_ATOMIC); if (!c) return ERR_PTR(-ENOMEM); - c->dev = dev; + strcpy(c->ifname, iniface); + c->ifindex = -1; c->clusterip = ip; memcpy(&c->clustermac, &i->clustermac, ETH_ALEN); c->num_total_nodes = i->num_total_nodes; @@ -213,17 +250,27 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, cn->procdir, &clusterip_proc_fops, c); if (!c->pde) { - spin_lock_bh(&cn->lock); - list_del_rcu(&c->list); - spin_unlock_bh(&cn->lock); - kfree(c); - - return ERR_PTR(-ENOMEM); + err = -ENOMEM; + goto err; } } #endif - return c; + c->notifier.notifier_call = clusterip_netdev_event; + err = register_netdevice_notifier(&c->notifier); + if (!err) + return c; + +#ifdef CONFIG_PROC_FS + proc_remove(c->pde); +err: +#endif + spin_lock_bh(&cn->lock); + list_del_rcu(&c->list); + spin_unlock_bh(&cn->lock); + kfree(c); + + return ERR_PTR(err); } #ifdef CONFIG_PROC_FS @@ -425,14 +472,13 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) e->ip.iniface); return -ENOENT; } + dev_put(dev); - config = clusterip_config_init(cipinfo, - e->ip.dst.s_addr, dev); - if (IS_ERR(config)) { - dev_put(dev); + config = clusterip_config_init(par->net, cipinfo, + e->ip.dst.s_addr, + e->ip.iniface); + if (IS_ERR(config)) return PTR_ERR(config); - } - dev_mc_add(config->dev, config->clustermac); } } cipinfo->config = config; @@ -458,7 +504,7 @@ static void clusterip_tg_destroy(const struct xt_tgdtor_param *par) /* if no more entries are referencing the config, remove it * from the list and destroy the proc entry */ - clusterip_config_entry_put(cipinfo->config); + clusterip_config_entry_put(par->net, cipinfo->config); clusterip_config_put(cipinfo->config); @@ -558,10 +604,9 @@ arp_mangle(void *priv, * addresses on different interfacs. However, in the CLUSTERIP case * this wouldn't work, since we didn't subscribe the mcast group on * other interfaces */ - if (c->dev != state->out) { - pr_debug("not mangling arp reply on different " - "interface: cip'%s'-skb'%s'\n", - c->dev->name, state->out->name); + if (c->ifindex != state->out->ifindex) { + pr_debug("not mangling arp reply on different interface: cip'%d'-skb'%d'\n", + c->ifindex, state->out->ifindex); clusterip_config_put(c); return NF_ACCEPT; } @@ -743,14 +788,20 @@ static const struct file_operations clusterip_proc_fops = { static int clusterip_net_init(struct net *net) { struct clusterip_net *cn = net_generic(net, clusterip_net_id); + int ret; INIT_LIST_HEAD(&cn->configs); spin_lock_init(&cn->lock); + ret = nf_register_net_hook(net, &cip_arp_ops); + if (ret < 0) + return ret; + #ifdef CONFIG_PROC_FS cn->procdir = proc_mkdir("ipt_CLUSTERIP", net->proc_net); if (!cn->procdir) { + nf_unregister_net_hook(net, &cip_arp_ops); pr_err("Unable to proc dir entry\n"); return -ENOMEM; } @@ -765,6 +816,7 @@ static void clusterip_net_exit(struct net *net) struct clusterip_net *cn = net_generic(net, clusterip_net_id); proc_remove(cn->procdir); #endif + nf_unregister_net_hook(net, &cip_arp_ops); } static struct pernet_operations clusterip_net_ops = { @@ -786,17 +838,11 @@ static int __init clusterip_tg_init(void) if (ret < 0) goto cleanup_subsys; - ret = nf_register_hook(&cip_arp_ops); - if (ret < 0) - goto cleanup_target; - pr_info("ClusterIP Version %s loaded successfully\n", CLUSTERIP_VERSION); return 0; -cleanup_target: - xt_unregister_target(&clusterip_tg_reg); cleanup_subsys: unregister_pernet_subsys(&clusterip_net_ops); return ret; @@ -806,7 +852,6 @@ static void __exit clusterip_tg_exit(void) { pr_info("ClusterIP Version %s unloading\n", CLUSTERIP_VERSION); - nf_unregister_hook(&cip_arp_ops); xt_unregister_target(&clusterip_tg_reg); unregister_pernet_subsys(&clusterip_net_ops); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index af2b69b6895f..f1528f7175a8 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -24,7 +24,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, struct iphdr *iph; skb_reset_network_header(skb); - iph = (struct iphdr *)skb_put(skb, sizeof(*iph)); + iph = skb_put(skb, sizeof(*iph)); iph->version = 4; iph->ihl = sizeof(*iph) / 4; iph->tos = 0; @@ -91,7 +91,7 @@ synproxy_send_client_synack(struct net *net, niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(__cookie_v4_init_sequence(iph, th, &mss)); @@ -133,7 +133,7 @@ synproxy_send_server_syn(struct net *net, niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(recv_seq - 1); @@ -178,7 +178,7 @@ synproxy_send_server_ack(struct net *net, niph = synproxy_build_ip(net, nskb, iph->daddr, iph->saddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->dest; nth->dest = th->source; nth->seq = htonl(ntohl(th->ack_seq)); @@ -216,7 +216,7 @@ synproxy_send_client_ack(struct net *net, niph = synproxy_build_ip(net, nskb, iph->saddr, iph->daddr); skb_reset_transport_header(nskb); - nth = (struct tcphdr *)skb_put(nskb, tcp_hdr_size); + nth = skb_put(nskb, tcp_hdr_size); nth->source = th->source; nth->dest = th->dest; nth->seq = htonl(ntohl(th->seq) + 1); diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index dc1dea15c1b4..f39037fca923 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -98,8 +98,8 @@ static int masq_device_event(struct notifier_block *this, */ NF_CT_ASSERT(dev->ifindex != 0); - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); } return NOTIFY_DONE; diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 7cd8d0d918f8..eeacbdaf7cdf 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -51,7 +51,7 @@ struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, struct iphdr *niph, *oiph = ip_hdr(oldskb); skb_reset_network_header(nskb); - niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr)); + niph = skb_put(nskb, sizeof(struct iphdr)); niph->version = 4; niph->ihl = sizeof(struct iphdr) / 4; niph->tos = 0; @@ -76,8 +76,7 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, struct tcphdr *tcph; skb_reset_transport_header(nskb); - tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); - memset(tcph, 0, sizeof(*tcph)); + tcph = skb_put_zero(nskb, sizeof(struct tcphdr)); tcph->source = oth->dest; tcph->dest = oth->source; tcph->doff = sizeof(struct tcphdr) / 4; @@ -172,7 +171,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) struct iphdr *iph = ip_hdr(skb_in); u8 proto; - if (skb_in->csum_bad || iph->frag_off & htons(IP_OFFSET)) + if (iph->frag_off & htons(IP_OFFSET)) return; if (skb_csum_unnecessary(skb_in)) { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index ccfbce13a633..b8f0db54b197 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -290,7 +290,7 @@ void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", inet_sk(sk), inet_sk(sk)->inet_num); - pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter); + pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt)); sk_common_release(sk); } @@ -1127,7 +1127,7 @@ static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index fa44e752a9a3..43eb6567b3a0 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -250,6 +250,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPAbortOnLinger", LINUX_MIB_TCPABORTONLINGER), SNMP_MIB_ITEM("TCPAbortFailed", LINUX_MIB_TCPABORTFAILED), SNMP_MIB_ITEM("TCPMemoryPressures", LINUX_MIB_TCPMEMORYPRESSURES), + SNMP_MIB_ITEM("TCPMemoryPressuresChrono", LINUX_MIB_TCPMEMORYPRESSURESCHRONO), SNMP_MIB_ITEM("TCPSACKDiscard", LINUX_MIB_TCPSACKDISCARD), SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD), SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO), diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bdffad875691..b0bb5d0a30bd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1063,7 +1063,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } static int raw_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6883b3d4ba8f..c816cd53f7fc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -114,6 +114,8 @@ #include <net/ip_tunnels.h> #include <net/l3mdev.h> +#include "fib_lookup.h" + #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -587,11 +589,6 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, build_sk_flow_key(fl4, sk); } -static inline void rt_free(struct rtable *rt) -{ - call_rcu(&rt->dst.rcu_head, dst_rcu_free); -} - static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) @@ -601,12 +598,14 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe) rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); - rt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); - rt_free(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); } } @@ -1300,7 +1299,7 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, - __be32 daddr) + __be32 daddr, const bool do_cache) { bool ret = false; @@ -1329,10 +1328,13 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, if (!rt->rt_gateway) rt->rt_gateway = daddr; - if (!(rt->dst.flags & DST_NOCACHE)) { + if (do_cache) { + dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); - if (orig) - rt_free(orig); + if (orig) { + dst_dev_put(&orig->dst); + dst_release(&orig->dst); + } ret = true; } @@ -1355,12 +1357,20 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) } orig = *p; + /* hold dst before doing cmpxchg() to avoid race condition + * on this dst + */ + dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { - if (orig) - rt_free(orig); - } else + if (orig) { + dst_dev_put(&orig->dst); + dst_release(&orig->dst); + } + } else { + dst_release(&rt->dst); ret = false; + } return ret; } @@ -1431,7 +1441,8 @@ static bool rt_cache_valid(const struct rtable *rt) static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, - struct fib_info *fi, u16 type, u32 itag) + struct fib_info *fi, u16 type, u32 itag, + const bool do_cache) { bool cached = false; @@ -1452,8 +1463,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #endif rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) - cached = rt_bind_exception(rt, fnhe, daddr); - else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_bind_exception(rt, fnhe, daddr, do_cache); + else if (do_cache) cached = rt_cache_route(nh, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or @@ -1461,7 +1472,6 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ - rt->dst.flags |= DST_NOCACHE; if (!rt->rt_gateway) rt->rt_gateway = daddr; rt_add_uncached_list(rt); @@ -1484,7 +1494,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | + (will_cache ? 0 : DST_HOST) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); @@ -1728,7 +1738,8 @@ rt_cache: rth->dst.input = ip_forward; - rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, + do_cache); set_lwt_redirect(rth); skb_dst_set(skb, &rth->dst); out: @@ -1860,9 +1871,9 @@ static int ip_mkroute_input(struct sk_buff *skb, */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) + u8 tos, struct net_device *dev, + struct fib_result *res) { - struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); struct ip_tunnel_info *tun_info; struct flowi4 fl4; @@ -1892,8 +1903,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -1929,17 +1940,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); - err = fib_lookup(net, &fl4, &res, 0); + err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } - if (res.type == RTN_BROADCAST) + if (res->type == RTN_BROADCAST) goto brd_input; - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) @@ -1951,10 +1962,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = -EHOSTUNREACH; goto no_route; } - if (res.type != RTN_UNICAST) + if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, &res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); out: return err; brd_input: @@ -1968,14 +1979,14 @@ brd_input: goto martian_source; } flags |= RTCF_BROADCAST; - res.type = RTN_BROADCAST; + res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: do_cache = false; - if (res.fi) { + if (res->fi) { if (!itag) { - rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; @@ -1986,7 +1997,7 @@ local_input: } rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, - flags | RTCF_LOCAL, res.type, + flags | RTCF_LOCAL, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; @@ -1996,18 +2007,18 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res.table) - rth->rt_table_id = res.table->tb_id; + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); - if (res.type == RTN_UNREACHABLE) { + if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { - struct fib_nh *nh = &FIB_RES_NH(res); + struct fib_nh *nh = &FIB_RES_NH(*res); rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { @@ -2016,10 +2027,8 @@ local_input: rth->dst.input = lwtunnel_input; } - if (unlikely(!rt_cache_route(nh, rth))) { - rth->dst.flags |= DST_NOCACHE; + if (unlikely(!rt_cache_route(nh, rth))) rt_add_uncached_list(rth); - } } skb_dst_set(skb, &rth->dst); err = 0; @@ -2027,9 +2036,9 @@ local_input: no_route: RT_CACHE_STAT_INC(in_no_route); - res.type = RTN_UNREACHABLE; - res.fi = NULL; - res.table = NULL; + res->type = RTN_UNREACHABLE; + res->fi = NULL; + res->table = NULL; goto local_input; /* @@ -2059,11 +2068,22 @@ martian_source: int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { - int res; + struct fib_result res; + int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); + err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(ip_route_input_noref); + +/* called with rcu_read_lock held */ +int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, struct fib_result *res) +{ /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting @@ -2078,6 +2098,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; + int err = -EINVAL; if (in_dev) our = ip_check_mc_rcu(in_dev, daddr, saddr, @@ -2093,7 +2114,6 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, ip_hdr(skb)->protocol); } - res = -EINVAL; if (our #ifdef CONFIG_IP_MROUTE || @@ -2101,17 +2121,14 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, IN_DEV_MFORWARD(in_dev)) #endif ) { - res = ip_route_input_mc(skb, daddr, saddr, + err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } - rcu_read_unlock(); - return res; + return err; } - res = ip_route_input_slow(skb, daddr, saddr, tos, dev); - rcu_read_unlock(); - return res; + + return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } -EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, @@ -2207,10 +2224,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth = rcu_dereference(*prth); rt_cache: - if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); + if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; - } } add: @@ -2244,7 +2259,7 @@ add: #endif } - rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); set_lwt_redirect(rth); return rth; @@ -2254,29 +2269,40 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, - const struct sk_buff *skb) +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + const struct sk_buff *skb) { - struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); - unsigned int flags = 0; struct fib_result res; struct rtable *rth; - int orig_oif; - int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; res.table = NULL; - orig_oif = fl4->flowi4_oif; - fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); rcu_read_lock(); + rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); + rcu_read_unlock(); + + return rth; +} +EXPORT_SYMBOL_GPL(ip_route_output_key_hash); + +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, + struct fib_result *res, + const struct sk_buff *skb) +{ + struct net_device *dev_out = NULL; + int orig_oif = fl4->flowi4_oif; + unsigned int flags = 0; + struct rtable *rth; + int err = -ENETUNREACH; + if (fl4->saddr) { rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || @@ -2362,15 +2388,15 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; - res.type = RTN_LOCAL; + res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } - err = fib_lookup(net, fl4, &res, 0); + err = fib_lookup(net, fl4, res, 0); if (err) { - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !netif_index_is_l3_master(net, fl4->flowi4_oif))) { @@ -2395,43 +2421,41 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); - res.type = RTN_UNICAST; + res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { if (!fl4->saddr) { - if (res.fi->fib_prefsrc) - fl4->saddr = res.fi->fib_prefsrc; + if (res->fi->fib_prefsrc) + fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ - dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? : + dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } - fib_select_path(net, &res, fl4, skb); + fib_select_path(net, res, fl4, skb); - dev_out = FIB_RES_DEV(res); + dev_out = FIB_RES_DEV(*res); fl4->flowi4_oif = dev_out->ifindex; make_route: - rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags); + rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: - rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { @@ -2485,7 +2509,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->input = dst_discard; new->output = dst_discard_out; - new->dev = ort->dst.dev; + new->dev = net->loopback_dev; if (new->dev) dev_hold(new->dev); @@ -2500,7 +2524,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - dst_free(new); } dst_release(dst_orig); @@ -2525,9 +2548,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); +/* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, - u32 seq, int event) + u32 seq) { struct rtable *rt = skb_rtable(skb); struct rtmsg *r; @@ -2536,7 +2560,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, u32 error; u32 metrics[RTAX_MAX]; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), 0); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0); if (!nlh) return -EMSGSIZE; @@ -2644,6 +2668,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct net *net = sock_net(in_skb->sk); struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; + struct fib_result res = {}; struct rtable *rt = NULL; struct flowi4 fl4; __be32 dst = 0; @@ -2700,10 +2725,12 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; + rcu_read_lock(); + if (iif) { struct net_device *dev; - dev = __dev_get_by_index(net, iif); + dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_free; @@ -2712,14 +2739,14 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb->protocol = htons(ETH_P_IP); skb->dev = dev; skb->mark = mark; - err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev); + err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, + dev, &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { - rt = ip_route_output_key(net, &fl4); - + rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); @@ -2735,17 +2762,25 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = rt->rt_table_id; - err = rt_fill_info(net, dst, src, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - RTM_NEWROUTE); + if (rtm->rtm_flags & RTM_F_FIB_MATCH) + err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, RTM_NEWROUTE, table_id, + rt->rt_type, res.prefix, res.prefixlen, + fl4.flowi4_tos, res.fi, 0); + else + err = rt_fill_info(net, dst, src, table_id, &fl4, skb, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); if (err < 0) goto errout_free; + rcu_read_unlock(); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; errout_free: + rcu_read_unlock(); kfree_skb(skb); goto errout; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0257d965f111..0905cf04c2a4 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -66,10 +66,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, * Since subsequent timestamps use the normal tcp_time_stamp value, we * must make sure that the resulting initial timestamp is <= tcp_time_stamp. */ -__u32 cookie_init_timestamp(struct request_sock *req) +u64 cookie_init_timestamp(struct request_sock *req) { struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_time_stamp; + u32 ts, ts_now = tcp_time_stamp_raw(); u32 options = 0; ireq = inet_rsk(req); @@ -88,7 +88,7 @@ __u32 cookie_init_timestamp(struct request_sock *req) ts <<= TSBITS; ts |= options; } - return ts; + return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ); } @@ -213,7 +213,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, NULL, &own_req); if (child) { - atomic_set(&req->rsk_refcnt, 1); + refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); inet_csk_reqsk_queue_add(sk, req, child); @@ -232,7 +232,8 @@ EXPORT_SYMBOL(tcp_get_cookie_sock); * return false if we decode a tcp option that is disabled * on the host. */ -bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) +bool cookie_timestamp_decode(const struct net *net, + struct tcp_options_received *tcp_opt) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr; @@ -242,12 +243,12 @@ bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) return true; } - if (!sysctl_tcp_timestamps) + if (!net->ipv4.sysctl_tcp_timestamps) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; - if (tcp_opt->sack_ok && !sysctl_tcp_sack) + if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) @@ -256,7 +257,7 @@ bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; - return sysctl_tcp_window_scaling != 0; + return net->ipv4.sysctl_tcp_window_scaling != 0; } EXPORT_SYMBOL(cookie_timestamp_decode); @@ -312,14 +313,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + tsoff = secure_tcp_ts_off(sock_net(sk), + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr); tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(&tcp_opt)) + if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) goto out; ret = NULL; @@ -343,7 +346,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->tfo_listener = false; ireq->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 86957e9cd6c6..9bf809726066 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -360,32 +360,30 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) tcp_fastopen_active_timeout_reset(); + + return ret; +} + +static int proc_tcp_available_ulp(struct ctl_table *ctl, + int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, }; + int ret; + + tbl.data = kmalloc(tbl.maxlen, GFP_USER); + if (!tbl.data) + return -ENOMEM; + tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + kfree(tbl.data); + return ret; } static struct ctl_table ipv4_table[] = { { - .procname = "tcp_timestamps", - .data = &sysctl_tcp_timestamps, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_window_scaling", - .data = &sysctl_tcp_window_scaling, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "tcp_sack", - .data = &sysctl_tcp_sack, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_retrans_collapse", .data = &sysctl_tcp_retrans_collapse, .maxlen = sizeof(int), @@ -707,6 +705,12 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec_ms_jiffies, }, { + .procname = "tcp_available_ulp", + .maxlen = TCP_ULP_BUF_MAX, + .mode = 0444, + .proc_handler = proc_tcp_available_ulp, + }, + { .procname = "icmp_msgs_per_sec", .data = &sysctl_icmp_msgs_per_sec, .maxlen = sizeof(int), @@ -1116,6 +1120,27 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &one, }, #endif + { + .procname = "tcp_sack", + .data = &init_net.ipv4.sysctl_tcp_sack, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_window_scaling", + .data = &init_net.ipv4.sysctl_tcp_window_scaling, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "tcp_timestamps", + .data = &init_net.ipv4.sysctl_tcp_timestamps, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 40aca7803cf2..71ce33decd97 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -320,17 +320,36 @@ struct tcp_splice_state { * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ -int tcp_memory_pressure __read_mostly; -EXPORT_SYMBOL(tcp_memory_pressure); +unsigned long tcp_memory_pressure __read_mostly; +EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { - if (!tcp_memory_pressure) { + unsigned long val; + + if (tcp_memory_pressure) + return; + val = jiffies; + + if (!val) + val--; + if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); - tcp_memory_pressure = 1; - } } -EXPORT_SYMBOL(tcp_enter_memory_pressure); +EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); + +void tcp_leave_memory_pressure(struct sock *sk) +{ + unsigned long val; + + if (!tcp_memory_pressure) + return; + val = xchg(&tcp_memory_pressure, 0); + if (val) + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, + jiffies_to_msecs(jiffies - val)); +} +EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) @@ -386,7 +405,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - minmax_reset(&tp->rtt_min, tcp_time_stamp, ~0U); + minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -645,7 +664,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, return skb->len < size_goal && sysctl_tcp_autocorking && skb != tcp_write_queue_head(sk) && - atomic_read(&sk->sk_wmem_alloc) > skb->truesize; + refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } static void tcp_push(struct sock *sk, int flags, int mss_now, @@ -673,7 +692,7 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ - if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize) + if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } @@ -882,8 +901,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, + size_t size, int flags) { struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; @@ -1013,6 +1032,7 @@ out_err: } return sk_stream_error(sk, flags, err); } +EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) @@ -2186,7 +2206,7 @@ adjudge_to_death: /* Now socket is owned by kernel and we acquire BH lock - to finish close. No need to check for user refs. + * to finish close. No need to check for user refs. */ local_bh_disable(); bh_lock_sock(sk); @@ -2461,7 +2481,25 @@ static int do_tcp_setsockopt(struct sock *sk, int level, name[val] = 0; lock_sock(sk); - err = tcp_set_congestion_control(sk, name); + err = tcp_set_congestion_control(sk, name, true); + release_sock(sk); + return err; + } + case TCP_ULP: { + char name[TCP_ULP_NAME_MAX]; + + if (optlen < 1) + return -EINVAL; + + val = strncpy_from_user(name, optval, + min_t(long, TCP_ULP_NAME_MAX - 1, + optlen)); + if (val < 0) + return -EFAULT; + name[val] = 0; + + lock_sock(sk); + err = tcp_set_ulp(sk, name); release_sock(sk); return err; } @@ -2482,7 +2520,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_MAXSEG: /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet - * know which interface is going to be used */ + * know which interface is going to be used + */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; @@ -2677,8 +2716,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: + case TCP_MD5SIG_EXT: /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optval, optlen); + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -2717,7 +2757,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp; + tp->tsoffset = val - tcp_time_stamp_raw(); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -2768,7 +2808,7 @@ static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = tp->chrono_stat[i - 1]; if (i == tp->chrono_type) - stats[i] += tcp_time_stamp - tp->chrono_start; + stats[i] += tcp_jiffies32 - tp->chrono_start; stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } @@ -2852,7 +2892,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_retrans = tp->retrans_out; info->tcpi_fackets = tp->fackets_out; - now = tcp_time_stamp; + now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); @@ -3020,6 +3060,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; + case TCP_ULP: + if (get_user(len, optlen)) + return -EFAULT; + len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); + if (!icsk->icsk_ulp_ops) { + if (put_user(0, optlen)) + return -EFAULT; + return 0; + } + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len)) + return -EFAULT; + return 0; + case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; @@ -3083,7 +3138,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp + tp->tsoffset; + val = tcp_time_stamp_raw() + tp->tsoffset; break; case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index b89bce4c721e..dbcc9352a48f 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -52,10 +52,9 @@ * There is a public e-mail list for discussing BBR development and testing: * https://groups.google.com/forum/#!forum/bbr-dev * - * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, - * since pacing is integral to the BBR design and implementation. - * BBR without pacing would not function properly, and may incur unnecessary - * high packet loss rates. + * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled, + * otherwise TCP stack falls back to an internal pacing using one high + * resolution timer per TCP socket and may use more resources. */ #include <linux/module.h> #include <net/tcp.h> @@ -92,7 +91,7 @@ struct bbr { struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ u32 rtt_cnt; /* count of packet-timed rounds elapsed */ u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ - struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u64 cycle_mstamp; /* time of this cycle phase start */ u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ @@ -412,7 +411,7 @@ static bool bbr_is_next_cycle_phase(struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool is_full_length = - skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) > bbr->min_rtt_us; u32 inflight, bw; @@ -498,7 +497,7 @@ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC); bbr->lt_last_delivered = tp->delivered; bbr->lt_last_lost = tp->lost; bbr->lt_rtt_cnt = 0; @@ -552,7 +551,7 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) struct bbr *bbr = inet_csk_ca(sk); u32 lost, delivered; u64 bw; - s32 t; + u32 t; if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ if (bbr->mode == BBR_PROBE_BW && bbr->round_start && @@ -604,15 +603,15 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) return; /* Find average delivery rate in this sampling interval. */ - t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); - if (t < 1) - return; /* interval is less than one jiffy, so wait */ - t = jiffies_to_usecs(t); - /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ - if (t < 1) { + t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp; + if ((s32)t < 1) + return; /* interval is less than one ms, so wait */ + /* Check if can multiply without overflow */ + if (t >= ~0U / USEC_PER_MSEC) { bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ return; } + t *= USEC_PER_MSEC; bw = (u64)delivered * BW_UNIT; do_div(bw, t); bbr_lt_bw_interval_done(sk, bw); @@ -731,12 +730,12 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) bool filter_expired; /* Track min RTT seen in the min_rtt_win_sec filter window: */ - filter_expired = after(tcp_time_stamp, + filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && (rs->rtt_us <= bbr->min_rtt_us || filter_expired)) { bbr->min_rtt_us = rs->rtt_us; - bbr->min_rtt_stamp = tcp_time_stamp; + bbr->min_rtt_stamp = tcp_jiffies32; } if (bbr_probe_rtt_mode_ms > 0 && filter_expired && @@ -755,7 +754,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) /* Maintain min packets in flight for max(200 ms, 1 round). */ if (!bbr->probe_rtt_done_stamp && tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) { - bbr->probe_rtt_done_stamp = tcp_time_stamp + + bbr->probe_rtt_done_stamp = tcp_jiffies32 + msecs_to_jiffies(bbr_probe_rtt_mode_ms); bbr->probe_rtt_round_done = 0; bbr->next_rtt_delivered = tp->delivered; @@ -763,8 +762,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) if (bbr->round_start) bbr->probe_rtt_round_done = 1; if (bbr->probe_rtt_round_done && - after(tcp_time_stamp, bbr->probe_rtt_done_stamp)) { - bbr->min_rtt_stamp = tcp_time_stamp; + after(tcp_jiffies32, bbr->probe_rtt_done_stamp)) { + bbr->min_rtt_stamp = tcp_jiffies32; bbr->restore_cwnd = 1; /* snap to prior_cwnd */ bbr_reset_mode(sk); } @@ -811,7 +810,7 @@ static void bbr_init(struct sock *sk) bbr->probe_rtt_done_stamp = 0; bbr->probe_rtt_round_done = 0; bbr->min_rtt_us = tcp_min_rtt(tp); - bbr->min_rtt_stamp = tcp_time_stamp; + bbr->min_rtt_stamp = tcp_jiffies32; minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */ @@ -826,10 +825,12 @@ static void bbr_init(struct sock *sk) bbr->idle_restart = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; - bbr->cycle_mstamp.v64 = 0; + bbr->cycle_mstamp = 0; bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); + + cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } static u32 bbr_sndbuf_expand(struct sock *sk) diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 36087bca9f48..609965f0e298 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -84,14 +84,14 @@ static void bictcp_init(struct sock *sk) static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { if (ca->last_cwnd == cwnd && - (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32) + (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; ca->last_cwnd = cwnd; - ca->last_time = tcp_time_stamp; + ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) /* record the beginning of an epoch */ - ca->epoch_start = tcp_time_stamp; + ca->epoch_start = tcp_jiffies32; /* start off normal */ if (cwnd <= low_window) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 324c9bcc5456..fde983f6376b 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk) INET_ECN_dontxmit(sk); } -static void tcp_reinit_congestion_control(struct sock *sk, - const struct tcp_congestion_ops *ca) +void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -333,8 +333,12 @@ out: return ret; } -/* Change congestion control for socket */ -int tcp_set_congestion_control(struct sock *sk, const char *name) +/* Change congestion control for socket. If load is false, then it is the + * responsibility of the caller to call tcp_init_congestion_control or + * tcp_reinit_congestion_control (if the current congestion control was + * already initialized. + */ +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; @@ -344,21 +348,29 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) return -EPERM; rcu_read_lock(); - ca = __tcp_ca_find_autoload(name); + if (!load) + ca = tcp_ca_find(name); + else + ca = __tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } - if (!ca) + if (!ca) { err = -ENOENT; - else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || - ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) + } else if (!load) { + icsk->icsk_ca_ops = ca; + if (!try_module_get(ca->owner)) + err = -EBUSY; + } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) { err = -EPERM; - else if (!try_module_get(ca->owner)) + } else if (!try_module_get(ca->owner)) { err = -EBUSY; - else + } else { tcp_reinit_congestion_control(sk, ca); + } out: rcu_read_unlock(); return err; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0683ba447d77..57ae5b5ae643 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -155,7 +155,7 @@ static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; @@ -231,21 +231,21 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && - (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32) + (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; /* The CUBIC function can update ca->cnt at most once per jiffy. * On all cwnd reduction events, ca->epoch_start is set to 0, * which will force a recalculation of ca->cnt. */ - if (ca->epoch_start && tcp_time_stamp == ca->last_time) + if (ca->epoch_start && tcp_jiffies32 == ca->last_time) goto tcp_friendliness; ca->last_cwnd = cwnd; - ca->last_time = tcp_time_stamp; + ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) { - ca->epoch_start = tcp_time_stamp; /* record beginning */ + ca->epoch_start = tcp_jiffies32; /* record beginning */ ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ @@ -276,7 +276,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) * if the cwnd < 1 million packets !!! */ - t = (s32)(tcp_time_stamp - ca->epoch_start); + t = (s32)(tcp_jiffies32 - ca->epoch_start); t += msecs_to_jiffies(ca->delay_min >> 3); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; @@ -448,7 +448,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) return; /* Discard delay samples right after fast recovery */ - if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ) + if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; delay = (sample->rtt_us << 3) / USEC_PER_MSEC; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 4af82b914dd4..ce9c7fef200f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -214,13 +214,14 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); - atomic_set(&req->rsk_refcnt, 2); + refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ inet_csk(child)->icsk_af_ops->rebuild_header(child); tcp_init_congestion_control(child); tcp_mtup_init(child); tcp_init_metrics(child); + tcp_call_bpf(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tcp_init_buffer_space(child); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 4a4d8e76738f..3eb78cde6ff0 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -104,7 +104,7 @@ static void measure_achieved_throughput(struct sock *sk, const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct htcp *ca = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_jiffies32; if (icsk->icsk_ca_state == TCP_CA_Open) ca->pkts_acked = sample->pkts_acked; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 174d4376baa5..2920e0cb09f8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -76,9 +76,6 @@ #include <asm/unaligned.h> #include <linux/errqueue.h> -int sysctl_tcp_timestamps __read_mostly = 1; -int sysctl_tcp_window_scaling __read_mostly = 1; -int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly; int sysctl_tcp_max_reordering __read_mostly = 300; int sysctl_tcp_dsack __read_mostly = 1; @@ -112,6 +109,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ +#define FLAG_NO_CHALLENGE_ACK 0x8000 /* do not call tcp_send_challenge_ack() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -441,7 +439,7 @@ void tcp_init_buffer_space(struct sock *sk) tcp_sndbuf_expand(sk); tp->rcvq_space.space = tp->rcv_wnd; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -463,7 +461,7 @@ void tcp_init_buffer_space(struct sock *sk) tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } /* 5. Recalculate window clamp after socket hit its memory bounds. */ @@ -555,11 +553,11 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) { u32 delta_us; - if (tp->rcv_rtt_est.time.v64 == 0) + if (tp->rcv_rtt_est.time == 0) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - delta_us = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcv_rtt_est.time); + delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time); tcp_rcv_rtt_update(tp, delta_us, 1); new_measure: @@ -571,13 +569,15 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + if (tp->rx_opt.rcv_tsecr && (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) - tcp_rcv_rtt_update(tp, - jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr), - 0); + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + tcp_rcv_rtt_update(tp, delta_us, 0); + } } /* @@ -590,7 +590,7 @@ void tcp_rcv_space_adjust(struct sock *sk) int time; int copied; - time = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcvq_space.time); + time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) return; @@ -672,7 +672,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_rcv_rtt_measure(tp); - now = tcp_time_stamp; + now = tcp_jiffies32; if (!icsk->icsk_ack.ato) { /* The _first_ data packet received, initialize @@ -885,6 +885,9 @@ static void tcp_update_reordering(struct sock *sk, const int metric, struct tcp_sock *tp = tcp_sk(sk); int mib_idx; + if (WARN_ON_ONCE(metric < 0)) + return; + if (metric > tp->reordering) { tp->reordering = min(sysctl_tcp_max_reordering, metric); @@ -1134,8 +1137,8 @@ struct tcp_sacktag_state { * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal. */ - struct skb_mstamp first_sackt; - struct skb_mstamp last_sackt; + u64 first_sackt; + u64 last_sackt; struct rate_sample *rate; int flag; }; @@ -1200,7 +1203,7 @@ static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, int dup_sack, int pcount, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1242,9 +1245,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; - if (state->first_sackt.v64 == 0) - state->first_sackt = *xmit_time; - state->last_sackt = *xmit_time; + if (state->first_sackt == 0) + state->first_sackt = xmit_time; + state->last_sackt = xmit_time; } if (sacked & TCPCB_LOST) { @@ -1304,7 +1307,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) @@ -1356,8 +1359,8 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); - if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) - TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) + TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1587,7 +1590,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, @@ -1954,7 +1957,7 @@ void tcp_enter_loss(struct sock *sk) } tp->snd_cwnd = 1; tp->snd_cwnd_cnt = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->retrans_out = 0; tp->lost_out = 0; @@ -2383,7 +2386,7 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tcp_ecn_withdraw_cwr(tp); } } - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->undo_marker = 0; } @@ -2520,7 +2523,7 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { tp->snd_cwnd = tp->snd_ssthresh; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } @@ -2590,7 +2593,7 @@ static void tcp_mtup_probe_success(struct sock *sk) tcp_mss_to_mtu(sk, tp->mss_cache) / icsk->icsk_mtup.probe_size; tp->snd_cwnd_cnt = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_ssthresh = tcp_current_ssthresh(sk); icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; @@ -2911,13 +2914,13 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) struct tcp_sock *tp = tcp_sk(sk); u32 wlen = sysctl_tcp_min_rtt_wlen * HZ; - minmax_running_min(&tp->rtt_min, wlen, tcp_time_stamp, + minmax_running_min(&tp->rtt_min, wlen, tcp_jiffies32, rtt_us ? : jiffies_to_usecs(1)); } -static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - long seq_rtt_us, long sack_rtt_us, - long ca_rtt_us) +static bool tcp_ack_update_rtt(struct sock *sk, const int flag, + long seq_rtt_us, long sack_rtt_us, + long ca_rtt_us, struct rate_sample *rs) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2936,9 +2939,13 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * See draft-ietf-tcplw-high-performance-00, section 3.3. */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) - seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr); + flag & FLAG_ACKED) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + seq_rtt_us = ca_rtt_us = delta_us; + } + rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) return false; @@ -2958,16 +2965,13 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { + struct rate_sample rs; long rtt_us = -1L; - if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { - struct skb_mstamp now; + if (req && !req->num_retrans && tcp_rsk(req)->snt_synack) + rtt_us = tcp_stamp_us_delta(tcp_clock_us(), tcp_rsk(req)->snt_synack); - skb_mstamp_get(&now); - rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); - } - - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us, &rs); } @@ -2976,7 +2980,7 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) const struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ca_ops->cong_avoid(sk, ack, acked); - tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp; + tcp_sk(sk)->snd_cwnd_stamp = tcp_jiffies32; } /* Restart timer after forward progress on connection. @@ -3001,14 +3005,14 @@ void tcp_rearm_rto(struct sock *sk) if (icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { struct sk_buff *skb = tcp_write_queue_head(sk); - const u32 rto_time_stamp = - tcp_skb_timestamp(skb) + rto; - s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); - /* delta may not be positive if the socket is locked + u64 rto_time_stamp = skb->skb_mstamp + + jiffies_to_usecs(rto); + s64 delta_us = rto_time_stamp - tp->tcp_mstamp; + /* delta_us may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ - if (delta > 0) - rto = delta; + if (delta_us > 0) + rto = usecs_to_jiffies(delta_us); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); @@ -3060,9 +3064,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sacktag_state *sack) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt; + u64 first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); - struct skb_mstamp *now = &tp->tcp_mstamp; u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; bool fully_acked = true; @@ -3075,7 +3078,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, bool rtt_update; int flag = 0; - first_ackt.v64 = 0; + first_ackt = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3106,8 +3109,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_RETRANS_DATA_ACKED; } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; - WARN_ON_ONCE(last_ackt.v64 == 0); - if (!first_ackt.v64) + WARN_ON_ONCE(last_ackt == 0); + if (!first_ackt) first_ackt = last_ackt; last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; @@ -3122,7 +3125,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->delivered += acked_pcount; if (!tcp_skb_spurious_retrans(tp, skb)) tcp_rack_advance(tp, sacked, scb->end_seq, - &skb->skb_mstamp); + skb->skb_mstamp); } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3165,17 +3168,16 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); + if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) { + seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt); } - if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); + if (sack->first_sackt) { + sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->last_sackt); } - sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, - ca_rtt_us); + ca_rtt_us, sack->rate); if (flag & FLAG_ACKED) { tcp_rearm_rto(sk); @@ -3201,7 +3203,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { + sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3211,7 +3213,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (icsk->icsk_ca_ops->pkts_acked) { struct ack_sample sample = { .pkts_acked = pkts_acked, - .rtt_us = ca_rtt_us, + .rtt_us = sack->rate->rtt_us, .in_flight = last_in_flight }; icsk->icsk_ca_ops->pkts_acked(sk, &sample); @@ -3390,7 +3392,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { NET_INC_STATS(net, mib_idx); @@ -3398,7 +3400,7 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, } } - *last_oow_ack_time = tcp_time_stamp; + *last_oow_ack_time = tcp_jiffies32; return false; /* not rate-limited: go ahead, send dupack now! */ } @@ -3553,7 +3555,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ - sack_state.first_sackt.v64 = 0; + sack_state.first_sackt = 0; sack_state.rate = &rs; /* We very likely will need to access write queue head. */ @@ -3565,7 +3567,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (before(ack, prior_snd_una)) { /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ if (before(ack, prior_snd_una - tp->max_window)) { - tcp_send_challenge_ack(sk, skb); + if (!(flag & FLAG_NO_CHALLENGE_ACK)) + tcp_send_challenge_ack(sk, skb); return -1; } goto old_ack; @@ -3636,7 +3639,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) */ sk->sk_err_soft = 0; icsk->icsk_probes_out = 0; - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; if (!prior_packets) goto no_queue; @@ -3718,7 +3721,8 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, * But, this can also be called on packets in the established flow when * the fast version below fails. */ -void tcp_parse_options(const struct sk_buff *skb, +void tcp_parse_options(const struct net *net, + const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc) { @@ -3759,7 +3763,7 @@ void tcp_parse_options(const struct sk_buff *skb, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling) { + !estab && net->ipv4.sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > TCP_MAX_WSCALE) { @@ -3775,7 +3779,7 @@ void tcp_parse_options(const struct sk_buff *skb, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps))) { + (!estab && net->ipv4.sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -3783,7 +3787,7 @@ void tcp_parse_options(const struct sk_buff *skb, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack) { + !estab && net->ipv4.sysctl_tcp_sack) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } @@ -3852,7 +3856,8 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ -static bool tcp_fast_parse_options(const struct sk_buff *skb, +static bool tcp_fast_parse_options(const struct net *net, + const struct sk_buff *skb, const struct tcphdr *th, struct tcp_sock *tp) { /* In the spirit of fast parsing, compare doff directly to constant @@ -3867,7 +3872,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, return true; } - tcp_parse_options(skb, &tp->rx_opt, 1, NULL); + tcp_parse_options(net, skb, &tp->rx_opt, 1, NULL); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5019,7 +5024,7 @@ static void tcp_new_space(struct sock *sk) if (tcp_should_expand_sndbuf(sk)) { tcp_sndbuf_expand(sk); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } sk->sk_write_space(sk); @@ -5228,7 +5233,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, bool rst_seq_match = false; /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5356,7 +5362,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* @@ -5554,7 +5560,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; + icsk->icsk_ack.lrcvtime = tcp_jiffies32; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -5565,13 +5571,13 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) icsk->icsk_af_ops->rebuild_header(sk); tcp_init_metrics(sk); - + tcp_call_bpf(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_init_buffer_space(sk); @@ -5599,7 +5605,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, /* Get original SYNACK MSS value if user MSS sets mss_clamp */ tcp_clear_options(&opt); opt.user_mss = opt.mss_clamp = 0; - tcp_parse_options(synack, &opt, 0, NULL); + tcp_parse_options(sock_net(sk), synack, &opt, 0, NULL); mss = opt.mss_clamp; } @@ -5653,7 +5659,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; bool fastopen_fail; - tcp_parse_options(skb, &tp->rx_opt, 0, &foc); + tcp_parse_options(sock_net(sk), skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5672,7 +5678,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp)) { + tcp_time_stamp(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -5917,7 +5923,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_SYN_SENT: tp->rx_opt.saw_tstamp = 0; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; @@ -5929,7 +5935,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; } - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { @@ -5948,13 +5954,17 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) /* step 5: check the ACK field */ acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | - FLAG_UPDATE_TS_RECENT) > 0; + FLAG_UPDATE_TS_RECENT | + FLAG_NO_CHALLENGE_ACK) > 0; + if (!acceptable) { + if (sk->sk_state == TCP_SYN_RECV) + return 1; /* send one RST */ + tcp_send_challenge_ack(sk, skb); + goto discard; + } switch (sk->sk_state) { case TCP_SYN_RECV: - if (!acceptable) - return 1; - if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); @@ -5967,6 +5977,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } else { /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); + tcp_call_bpf(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tcp_init_congestion_control(sk); tcp_mtup_init(sk); @@ -6008,7 +6019,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); @@ -6023,14 +6034,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) * our SYNACK so stop the SYNACK timer. */ if (req) { - /* Return RST if ack_seq is invalid. - * Note that RFC793 only says to generate a - * DUPACK for it but for TCP Fast Open it seems - * better to treat this case like TCP_SYN_RECV - * above. - */ - if (!acceptable) - return 1; /* We no longer need the request sock. */ reqsk_fastopen_remove(sk, req, false); tcp_rearm_rto(sk); @@ -6188,7 +6191,8 @@ static void tcp_ecn_create_request(struct request_sock *req, ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || - (ecn_ok_dst & DST_FEATURE_ECN_CA)) + (ecn_ok_dst & DST_FEATURE_ECN_CA) || + tcp_bpf_ca_needs_ecn((struct sock *)req)) inet_rsk(req)->ecn_ok = 1; } @@ -6202,7 +6206,7 @@ static void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - skb_mstamp_get(&tcp_rsk(req)->snt_synack); + tcp_rsk(req)->snt_synack = tcp_clock_us(); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; @@ -6330,7 +6334,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); + tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, + want_cookie ? NULL : &foc); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -6348,7 +6353,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (tmp_opt.tstamp_ok) - tcp_rsk(req)->ts_off = af_ops->init_ts_off(skb); + tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); if (!want_cookie && !isn) { /* Kill the following clause, if you dislike this way. */ @@ -6403,7 +6408,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } else { tcp_rsk(req)->tfo_listener = false; if (!want_cookie) - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + inet_csk_reqsk_queue_hash_add(sk, req, + tcp_timeout_init((struct sock *)req)); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : TCP_SYNACK_COOKIE); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5ab2aac5ca19..a20e7f03d5f7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -80,6 +80,7 @@ #include <linux/stddef.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/inetdevice.h> #include <crypto/hash.h> #include <linux/scatterlist.h> @@ -102,10 +103,9 @@ static u32 tcp_v4_init_seq(const struct sk_buff *skb) tcp_hdr(skb)->source); } -static u32 tcp_v4_init_ts_off(const struct sk_buff *skb) +static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_ts_off(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -242,7 +242,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port); - tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr, + tp->tsoffset = secure_tcp_ts_off(sock_net(sk), + inet->inet_saddr, inet->inet_daddr); } @@ -376,8 +377,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) struct sock *sk; struct sk_buff *skb; struct request_sock *fastopen; - __u32 seq, snd_una; - __u32 remaining; + u32 seq, snd_una; + s32 remaining; + u32 delta_us; int err; struct net *net = dev_net(icmp_skb->dev); @@ -483,11 +485,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) skb = tcp_write_queue_head(sk); BUG_ON(!skb); + tcp_mstamp_refresh(tp); + delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp); remaining = icsk->icsk_rto - - min(icsk->icsk_rto, - tcp_time_stamp - tcp_skb_timestamp(skb)); + usecs_to_jiffies(delta_us); - if (remaining) { + if (remaining > 0) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); } else { @@ -811,7 +814,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -839,7 +842,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, @@ -904,6 +907,48 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; + const struct tcp_md5sig_info *md5sig; + __be32 mask; + struct tcp_md5sig_key *best_match = NULL; + bool match; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) + return NULL; + + hlist_for_each_entry_rcu(key, &md5sig->head, node) { + if (key->family != family) + continue; + + if (family == AF_INET) { + mask = inet_make_mask(key->prefixlen); + match = (key->addr.a4.s_addr & mask) == + (addr->a4.s_addr & mask); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, + key->prefixlen); +#endif + } else { + match = false; + } + + if (match && (!best_match || + key->prefixlen > best_match->prefixlen)) + best_match = key; + } + return best_match; +} +EXPORT_SYMBOL(tcp_md5_do_lookup); + +static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, + const union tcp_md5_addr *addr, + int family, u8 prefixlen) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; @@ -919,12 +964,12 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; - if (!memcmp(&key->addr, addr, size)) + if (!memcmp(&key->addr, addr, size) && + key->prefixlen == prefixlen) return key; } return NULL; } -EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) @@ -938,14 +983,15 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) + int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, + gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup(sk, addr, family); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { /* Pre-existing entry - just update that one. */ memcpy(key->key, newkey, newkeylen); @@ -976,6 +1022,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; + key->prefixlen = prefixlen; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); @@ -984,11 +1031,12 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } EXPORT_SYMBOL(tcp_md5_do_add); -int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, + u8 prefixlen) { struct tcp_md5sig_key *key; - key = tcp_md5_do_lookup(sk, addr, family); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (!key) return -ENOENT; hlist_del_rcu(&key->node); @@ -1014,11 +1062,12 @@ static void tcp_clear_md5_list(struct sock *sk) } } -static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, - int optlen) +static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, + char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; + u8 prefixlen = 32; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1029,15 +1078,22 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 32) + return -EINVAL; + } + if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET); + AF_INET, prefixlen); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, + AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } @@ -1340,7 +1396,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET, key->key, key->keylen, GFP_ATOMIC); + AF_INET, 32, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1673,6 +1729,8 @@ process: } if (nsk == sk) { reqsk_put(req); + } else if (tcp_filter(sk, skb)) { + goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; @@ -1858,6 +1916,8 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cleanup_congestion_control(sk); + tcp_cleanup_ulp(sk); + /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); @@ -2263,7 +2323,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), - atomic_read(&sk->sk_refcnt), sk, + refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, @@ -2289,7 +2349,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, - atomic_read(&tw->tw_refcnt), tw); + refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 @@ -2385,6 +2445,7 @@ struct proto tcp_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, @@ -2463,6 +2524,9 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); + net->ipv4.sysctl_tcp_sack = 1; + net->ipv4.sysctl_tcp_window_scaling = 1; + net->ipv4.sysctl_tcp_timestamps = 1; return 0; fail: diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index d6fb6c067af4..ae10ed64fe13 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -37,7 +37,7 @@ #include <net/tcp.h> /* resolution of owd */ -#define LP_RESOL 1000 +#define LP_RESOL TCP_TS_HZ /** * enum tcp_lp_state @@ -147,9 +147,9 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) tp->rx_opt.rcv_tsecr == lp->local_ref_time) goto out; - m = HZ * (tp->rx_opt.rcv_tsval - - lp->remote_ref_time) / (tp->rx_opt.rcv_tsecr - - lp->local_ref_time); + m = TCP_TS_HZ * + (tp->rx_opt.rcv_tsval - lp->remote_ref_time) / + (tp->rx_opt.rcv_tsecr - lp->local_ref_time); if (m < 0) m = -m; @@ -194,7 +194,7 @@ static u32 tcp_lp_owd_calculator(struct sock *sk) if (lp->flag & LP_VALID_RHZ) { owd = tp->rx_opt.rcv_tsval * (LP_RESOL / lp->remote_hz) - - tp->rx_opt.rcv_tsecr * (LP_RESOL / HZ); + tp->rx_opt.rcv_tsecr * (LP_RESOL / TCP_TS_HZ); if (owd < 0) owd = -owd; } @@ -264,18 +264,19 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); + u32 now = tcp_time_stamp(tp); u32 delta; if (sample->rtt_us > 0) tcp_lp_rtt_sample(sk, sample->rtt_us); /* calc inference */ - delta = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + delta = now - tp->rx_opt.rcv_tsecr; if ((s32)delta > 0) lp->inference = 3 * delta; /* test if within inference */ - if (lp->last_drop && (tcp_time_stamp - lp->last_drop < lp->inference)) + if (lp->last_drop && (now - lp->last_drop < lp->inference)) lp->flag |= LP_WITHIN_INF; else lp->flag &= ~LP_WITHIN_INF; @@ -312,7 +313,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) tp->snd_cwnd = max(tp->snd_cwnd >> 1U, 1U); /* record this drop time */ - lp->last_drop = tcp_time_stamp; + lp->last_drop = now; } static struct tcp_congestion_ops tcp_lp __read_mostly = { diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 653bbd67e3a3..102b2c90bb80 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -524,7 +524,7 @@ reset: tp->snd_cwnd = 1; else tp->snd_cwnd = tcp_init_cwnd(tp, dst); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 717be4de5324..0ff83c1637d8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -98,7 +98,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { if (tmp_opt.rcv_tsecr) @@ -351,6 +351,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, int full_space = tcp_full_space(sk_listener); u32 window_clamp; __u8 rcv_wscale; + u32 rcv_wnd; int mss; mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); @@ -363,6 +364,12 @@ void tcp_openreq_init_rwin(struct request_sock *req, (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) req->rsk_window_clamp = full_space; + rcv_wnd = tcp_rwnd_init_bpf((struct sock *)req); + if (rcv_wnd == 0) + rcv_wnd = dst_metric(dst, RTAX_INITRWND); + else if (full_space < rcv_wnd * mss) + full_space = rcv_wnd * mss; + /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), @@ -370,7 +377,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); + rcv_wnd); ireq->rcv_wscale = rcv_wscale; } EXPORT_SYMBOL(tcp_openreq_init_rwin); @@ -445,9 +452,9 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); - minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); + minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; - newicsk->icsk_ack.lrcvtime = tcp_time_stamp; + newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->packets_out = 0; newtp->retrans_out = 0; @@ -455,7 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; newtp->tlp_high_seq = 0; - newtp->lsndtime = treq->snt_synack.stamp_jiffies; + newtp->lsndtime = tcp_jiffies32; newsk->sk_txhash = treq->txhash; newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; @@ -526,7 +533,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; - newtp->rack.mstamp.v64 = 0; + newtp->rack.mstamp = 0; newtp->rack.advanced = 0; __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); @@ -559,7 +566,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 5de82a8d4d87..6d650ed3cb59 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -424,8 +424,8 @@ static void tcpnv_acked(struct sock *sk, const struct ack_sample *sample) } /* Extract info for Tcp socket info provided via netlink */ -size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, - union tcp_cc_info *info) +static size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, + union tcp_cc_info *info) { const struct tcpnv *ca = inet_csk_ca(sk); @@ -440,7 +440,6 @@ size_t tcpnv_get_info(struct sock *sk, u32 ext, int *attr, } return 0; } -EXPORT_SYMBOL_GPL(tcpnv_get_info); static struct tcp_congestion_ops tcpnv __read_mostly = { .init = tcpnv_init, diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index bc68da38ea86..11f69bbf9307 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -152,7 +152,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); sum_truesize += skb->truesize; - atomic_add(sum_truesize - gso_skb->truesize, + refcount_add(sum_truesize - gso_skb->truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4858e190f6ac..4e985dea1dd2 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -151,7 +151,7 @@ void tcp_cwnd_restart(struct sock *sk, s32 delta) while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tp->snd_cwnd = max(cwnd, restart_cwnd); - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_cwnd_used = 0; } @@ -160,7 +160,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - const u32 now = tcp_time_stamp; + const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); @@ -316,7 +316,8 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; - else if (tcp_ca_needs_ecn(sk)) + else if (tcp_ca_needs_ecn(sk) || + tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } @@ -324,8 +325,9 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || - tcp_ca_needs_ecn(sk); + tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); @@ -339,7 +341,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; - if (tcp_ca_needs_ecn(sk)) + if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } @@ -569,18 +571,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && !*md5)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -861,12 +863,11 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; - int wmem; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ - wmem = atomic_sub_return(skb->truesize - 1, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. @@ -875,7 +876,7 @@ void tcp_wfree(struct sk_buff *skb) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ - if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) + if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { @@ -904,6 +905,72 @@ out: sk_free(sk); } +/* Note: Called under hard irq. + * We can not call TCP stack right away. + */ +enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) +{ + struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); + struct sock *sk = (struct sock *)tp; + unsigned long nval, oval; + + for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { + struct tsq_tasklet *tsq; + bool empty; + + if (oval & TSQF_QUEUED) + break; + + nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; + nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); + if (nval != oval) + continue; + + if (!refcount_inc_not_zero(&sk->sk_wmem_alloc)) + break; + /* queue this socket to tasklet queue */ + tsq = this_cpu_ptr(&tsq_tasklet); + empty = list_empty(&tsq->head); + list_add(&tp->tsq_node, &tsq->head); + if (empty) + tasklet_schedule(&tsq->tasklet); + break; + } + return HRTIMER_NORESTART; +} + +/* BBR congestion control needs pacing. + * Same remark for SO_MAX_PACING_RATE. + * sch_fq packet scheduler is efficiently handling pacing, + * but is not always installed/used. + * Return true if TCP stack should pace packets itself. + */ +static bool tcp_needs_internal_pacing(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; +} + +static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) +{ + u64 len_ns; + u32 rate; + + if (!tcp_needs_internal_pacing(sk)) + return; + rate = sk->sk_pacing_rate; + if (!rate || rate == ~0U) + return; + + /* Should account for header sizes as sch_fq does, + * but lets make things simple. + */ + len_ns = (u64)skb->len * NSEC_PER_SEC; + do_div(len_ns, rate); + hrtimer_start(&tcp_sk(sk)->pacing_timer, + ktime_add_ns(ktime_get(), len_ns), + HRTIMER_MODE_ABS_PINNED); +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -931,8 +998,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); + skb->skb_mstamp = tp->tcp_mstamp; if (clone_it) { - skb_mstamp_get(&skb->skb_mstamp); TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; tcp_rate_skb_sent(sk, skb); @@ -979,7 +1046,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; skb_set_hash_from_sk(skb, sk); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); @@ -1034,6 +1101,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); + tcp_internal_pacing(sk, skb); } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) @@ -1261,9 +1329,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, return 0; } -/* This is similar to __pskb_pull_head() (it will go to core/skbuff.c - * eventually). The difference is that pulled data not copied, but - * immediately discarded. +/* This is similar to __pskb_pull_tail(). The difference is that pulled + * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { @@ -1298,7 +1365,6 @@ static int __pskb_trim_head(struct sk_buff *skb, int len) } shinfo->nr_frags = k; - skb_reset_tail_pointer(skb); skb->data_len -= len; skb->len = skb->data_len; return len; @@ -1408,7 +1474,7 @@ void tcp_mtup_init(struct sock *sk) icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) - icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } EXPORT_SYMBOL(tcp_mtup_init); @@ -1509,7 +1575,7 @@ static void tcp_cwnd_application_limited(struct sock *sk) } tp->snd_cwnd_used = 0; } - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) @@ -1530,14 +1596,14 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; + tp->snd_cwnd_stamp = tcp_jiffies32; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (sysctl_tcp_slow_start_after_idle && - (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && + (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -1839,7 +1905,6 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, const struct inet_connection_sock *icsk = inet_csk(sk); u32 age, send_win, cong_win, limit, in_flight; struct tcp_sock *tp = tcp_sk(sk); - struct skb_mstamp now; struct sk_buff *head; int win_divisor; @@ -1852,7 +1917,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, /* Avoid bursty behavior by allowing defer * only if the last write was recent. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 0) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); @@ -1895,8 +1960,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, } head = tcp_write_queue_head(sk); - skb_mstamp_get(&now); - age = skb_mstamp_us_delta(&now, &head->skb_mstamp); + + age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) goto send_now; @@ -1921,7 +1986,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) s32 delta; interval = net->ipv4.sysctl_tcp_probe_interval; - delta = tcp_time_stamp - icsk->icsk_mtup.probe_timestamp; + delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); @@ -1933,7 +1998,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); /* Update probe time stamp */ - icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } } @@ -2086,6 +2151,12 @@ static int tcp_mtu_probe(struct sock *sk) return -1; } +static bool tcp_pacing_check(const struct sock *sk) +{ + return tcp_needs_internal_pacing(sk) && + hrtimer_active(&tcp_sk(sk)->pacing_timer); +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2106,7 +2177,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); limit <<= factor; - if (atomic_read(&sk->sk_wmem_alloc) > limit) { + if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send the 1st or 2nd skb in write queue. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. @@ -2122,7 +2193,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, * test again the condition. */ smp_mb__after_atomic(); - if (atomic_read(&sk->sk_wmem_alloc) > limit) + if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; @@ -2130,7 +2201,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { - const u32 now = tcp_time_stamp; + const u32 now = tcp_jiffies32; if (tp->chrono_type > TCP_CHRONO_UNSPEC) tp->chrono_stat[tp->chrono_type - 1] += now - tp->chrono_start; @@ -2207,15 +2278,19 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } max_segs = tcp_tso_segs(sk, mss_now); + tcp_mstamp_refresh(tp); while ((skb = tcp_send_head(sk))) { unsigned int limit; + if (tcp_pacing_check(sk)) + break; + tso_segs = tcp_init_tso_segs(skb, mss_now); BUG_ON(!tso_segs); if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tp->tcp_mstamp; goto repair; /* Skip network transmission */ } @@ -2342,10 +2417,10 @@ bool tcp_schedule_loss_probe(struct sock *sk) timeout = max_t(u32, timeout, msecs_to_jiffies(10)); /* If RTO is shorter, just schedule TLP in its place. */ - tlp_time_stamp = tcp_time_stamp + timeout; + tlp_time_stamp = tcp_jiffies32 + timeout; rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { - s32 delta = rto_time_stamp - tcp_time_stamp; + s32 delta = rto_time_stamp - tcp_jiffies32; if (delta > 0) timeout = delta; } @@ -2738,7 +2813,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ - if (atomic_read(&sk->sk_wmem_alloc) > + if (refcount_read(&sk->sk_wmem_alloc) > min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; @@ -2803,7 +2878,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tp->tcp_mstamp; nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; @@ -2878,6 +2953,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (skb == tcp_send_head(sk)) break; + + if (tcp_pacing_check(sk)) + break; + /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; @@ -3015,7 +3094,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); - skb_mstamp_get(&skb->skb_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); @@ -3111,10 +3190,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req); + skb->skb_mstamp = cookie_init_timestamp(req); else #endif - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tcp_clock_us(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); @@ -3134,6 +3213,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; + skb->mark = ireq->ir_mark; /* Setting of flags are superfluous here for callers (and ECE is * not even correctly set) */ @@ -3189,12 +3269,14 @@ static void tcp_connect_init(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; + u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ - tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); + tp->tcp_header_len = sizeof(struct tcphdr); + if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) + tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk)) @@ -3221,13 +3303,17 @@ static void tcp_connect_init(struct sock *sk) (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) tp->window_clamp = tcp_full_space(sk); + rcv_wnd = tcp_rwnd_init_bpf(sk); + if (rcv_wnd == 0) + rcv_wnd = dst_metric(dst, RTAX_INITRWND); + tcp_select_initial_window(tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sysctl_tcp_window_scaling, + sock_net(sk)->ipv4.sysctl_tcp_window_scaling, &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); + rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; @@ -3244,11 +3330,11 @@ static void tcp_connect_init(struct sock *sk) if (likely(!tp->repair)) tp->rcv_nxt = 0; else - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; + inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } @@ -3361,6 +3447,7 @@ int tcp_connect(struct sock *sk) struct sk_buff *buff; int err; + tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); tcp_connect_init(sk); if (unlikely(tp->repair)) { @@ -3373,7 +3460,8 @@ int tcp_connect(struct sock *sk) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); - tp->retrans_stamp = tcp_time_stamp; + tcp_mstamp_refresh(tp); + tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); @@ -3492,7 +3580,6 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - skb_mstamp_get(&buff->skb_mstamp); tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); } EXPORT_SYMBOL_GPL(tcp_send_ack); @@ -3526,15 +3613,16 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); - skb_mstamp_get(&skb->skb_mstamp); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } +/* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; + tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index c6a9fa894646..3330a370d306 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -78,7 +78,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - if (!scb->tx.delivered_mstamp.v64) + if (!scb->tx.delivered_mstamp) return; if (!rs->prior_delivered || @@ -89,9 +89,9 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, rs->is_retrans = scb->sacked & TCPCB_RETRANS; /* Find the duration of the "send phase" of this window: */ - rs->interval_us = skb_mstamp_us_delta( - &skb->skb_mstamp, - &scb->tx.first_tx_mstamp); + rs->interval_us = tcp_stamp_us_delta( + skb->skb_mstamp, + scb->tx.first_tx_mstamp); /* Record send time of most recently ACKed packet: */ tp->first_tx_mstamp = skb->skb_mstamp; @@ -101,7 +101,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, * we don't need to reset since it'll be freed soon. */ if (scb->sacked & TCPCB_SACKED_ACKED) - scb->tx.delivered_mstamp.v64 = 0; + scb->tx.delivered_mstamp = 0; } /* Update the connection delivery information and generate a rate sample. */ @@ -125,7 +125,7 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ rs->losses = lost; /* freshly marked lost */ /* Return an invalid sample if no timing information is available. */ - if (!rs->prior_mstamp.v64) { + if (!rs->prior_mstamp) { rs->delivered = -1; rs->interval_us = -1; return; @@ -138,8 +138,8 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, * longer phase. */ snd_us = rs->interval_us; /* send phase */ - ack_us = skb_mstamp_us_delta(&tp->tcp_mstamp, - &rs->prior_mstamp); /* ack phase */ + ack_us = tcp_stamp_us_delta(tp->tcp_mstamp, + rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); /* Normally we expect interval_us >= min-rtt. @@ -185,3 +185,4 @@ void tcp_rate_check_app_limited(struct sock *sk) tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; } +EXPORT_SYMBOL_GPL(tcp_rate_check_app_limited); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 362b8c75bfab..fe9a493d0208 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -17,12 +17,9 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -static bool tcp_rack_sent_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t2, - u32 seq1, u32 seq2) +static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { - return skb_mstamp_after(t1, t2) || - (t1->v64 == t2->v64 && after(seq1, seq2)); + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): @@ -72,14 +69,14 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) scb->sacked & TCPCB_SACKED_ACKED) continue; - if (tcp_rack_sent_after(&tp->rack.mstamp, &skb->skb_mstamp, + if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, tp->rack.end_seq, scb->end_seq)) { /* Step 3 in draft-cheng-tcpm-rack-00.txt: * A packet is lost if its elapsed time is beyond * the recent RTT plus the reordering window. */ - u32 elapsed = skb_mstamp_us_delta(&tp->tcp_mstamp, - &skb->skb_mstamp); + u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, + skb->skb_mstamp); s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; if (remaining < 0) { @@ -127,16 +124,16 @@ void tcp_rack_mark_lost(struct sock *sk) * draft-cheng-tcpm-rack-00.txt */ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { u32 rtt_us; - if (tp->rack.mstamp.v64 && - !tcp_rack_sent_after(xmit_time, &tp->rack.mstamp, + if (tp->rack.mstamp && + !tcp_rack_sent_after(xmit_time, tp->rack.mstamp, end_seq, tp->rack.end_seq)) return; - rtt_us = skb_mstamp_us_delta(&tp->tcp_mstamp, xmit_time); + rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time); if (sacked & TCPCB_RETRANS) { /* If the sacked packet was retransmitted, it's ambiguous * whether the retransmission or the original (or the prior @@ -152,7 +149,7 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, return; } tp->rack.rtt_us = rtt_us; - tp->rack.mstamp = *xmit_time; + tp->rack.mstamp = xmit_time; tp->rack.end_seq = end_seq; tp->rack.advanced = 1; } @@ -166,7 +163,6 @@ void tcp_rack_reo_timeout(struct sock *sk) u32 timeout, prior_inflight; prior_inflight = tcp_packets_in_flight(tp); - skb_mstamp_get(&tp->tcp_mstamp); tcp_rack_detect_loss(sk, &timeout); if (prior_inflight != tcp_packets_in_flight(tp)) { if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 14672543cf0b..c0feeeef962a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -63,7 +63,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ @@ -73,7 +73,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || + if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; @@ -115,7 +115,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) if (net->ipv4.sysctl_tcp_mtu_probing) { if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; - icsk->icsk_mtup.probe_timestamp = tcp_time_stamp; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } else { struct net *net = sock_net(sk); @@ -139,22 +139,18 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) * @timeout: A custom timeout value. * If set to 0 the default timeout is calculated and used. * Using TCP_RTO_MIN and the number of unsuccessful retransmits. - * @syn_set: true if the SYN Bit was set. * * The default "timeout" value this function can calculate and use * is equivalent to the timeout of a TCP Connection * after "boundary" unsuccessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if - * syn_set flag is set. - * + * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, - unsigned int timeout, - bool syn_set) + unsigned int timeout) { + const unsigned int rto_base = TCP_RTO_MIN; unsigned int linear_backoff_thresh, start_ts; - unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -172,7 +168,7 @@ static bool retransmits_timed_out(struct sock *sk, timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; } - return (tcp_time_stamp - start_ts) >= timeout; + return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= jiffies_to_msecs(timeout); } /* A write timeout has occurred. Process the after effects. */ @@ -181,8 +177,8 @@ static int tcp_write_timeout(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); + bool expired, do_reset; int retry_until; - bool do_reset, syn_set = false; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) { @@ -196,9 +192,9 @@ static int tcp_write_timeout(struct sock *sk) sk_rethink_txhash(sk); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; - syn_set = true; + expired = icsk->icsk_retransmits >= retry_until; } else { - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) { + if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { /* Some middle-boxes may black-hole Fast Open _after_ * the handshake. Therefore we conservatively disable * Fast Open on this path on recurring timeouts after @@ -224,15 +220,15 @@ static int tcp_write_timeout(struct sock *sk) retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || - !retransmits_timed_out(sk, retry_until, 0, 0); + !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } + expired = retransmits_timed_out(sk, retry_until, + icsk->icsk_user_timeout); } - - if (retransmits_timed_out(sk, retry_until, - syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) { + if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; @@ -339,9 +335,10 @@ static void tcp_probe_timer(struct sock *sk) */ start_ts = tcp_skb_timestamp(tcp_send_head(sk)); if (!start_ts) - skb_mstamp_get(&tcp_send_head(sk)->skb_mstamp); + tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && - (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + (s32)(tcp_time_stamp(tp) - start_ts) > + jiffies_to_msecs(icsk->icsk_user_timeout)) goto abort; max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; @@ -451,7 +448,7 @@ void tcp_retransmit_timer(struct sock *sk) tp->snd_una, tp->snd_nxt); } #endif - if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { tcp_write_err(sk); goto out; } @@ -539,7 +536,7 @@ out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0)) + if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0)) __sk_dst_reset(sk); out:; @@ -561,6 +558,7 @@ void tcp_write_timer_handler(struct sock *sk) goto out; } + tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { @@ -710,4 +708,7 @@ void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); + hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED); + tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; } diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c new file mode 100644 index 000000000000..2417f55374c5 --- /dev/null +++ b/net/ipv4/tcp_ulp.c @@ -0,0 +1,135 @@ +/* + * Pluggable TCP upper layer protocol support. + * + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. + * + */ + +#include<linux/module.h> +#include <linux/mm.h> +#include <linux/types.h> +#include <linux/list.h> +#include <linux/gfp.h> +#include <net/tcp.h> + +static DEFINE_SPINLOCK(tcp_ulp_list_lock); +static LIST_HEAD(tcp_ulp_list); + +/* Simple linear search, don't expect many entries! */ +static struct tcp_ulp_ops *tcp_ulp_find(const char *name) +{ + struct tcp_ulp_ops *e; + + list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + if (strcmp(e->name, name) == 0) + return e; + } + + return NULL; +} + +static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name) +{ + const struct tcp_ulp_ops *ulp = NULL; + + rcu_read_lock(); + ulp = tcp_ulp_find(name); + +#ifdef CONFIG_MODULES + if (!ulp && capable(CAP_NET_ADMIN)) { + rcu_read_unlock(); + request_module("%s", name); + rcu_read_lock(); + ulp = tcp_ulp_find(name); + } +#endif + if (!ulp || !try_module_get(ulp->owner)) + ulp = NULL; + + rcu_read_unlock(); + return ulp; +} + +/* Attach new upper layer protocol to the list + * of available protocols. + */ +int tcp_register_ulp(struct tcp_ulp_ops *ulp) +{ + int ret = 0; + + spin_lock(&tcp_ulp_list_lock); + if (tcp_ulp_find(ulp->name)) { + pr_notice("%s already registered or non-unique name\n", + ulp->name); + ret = -EEXIST; + } else { + list_add_tail_rcu(&ulp->list, &tcp_ulp_list); + } + spin_unlock(&tcp_ulp_list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tcp_register_ulp); + +void tcp_unregister_ulp(struct tcp_ulp_ops *ulp) +{ + spin_lock(&tcp_ulp_list_lock); + list_del_rcu(&ulp->list); + spin_unlock(&tcp_ulp_list_lock); + + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(tcp_unregister_ulp); + +/* Build string with list of available upper layer protocl values */ +void tcp_get_available_ulp(char *buf, size_t maxlen) +{ + struct tcp_ulp_ops *ulp_ops; + size_t offs = 0; + + *buf = '\0'; + rcu_read_lock(); + list_for_each_entry_rcu(ulp_ops, &tcp_ulp_list, list) { + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", ulp_ops->name); + } + rcu_read_unlock(); +} + +void tcp_cleanup_ulp(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) + return; + + if (icsk->icsk_ulp_ops->release) + icsk->icsk_ulp_ops->release(sk); + module_put(icsk->icsk_ulp_ops->owner); +} + +/* Change upper layer protocol for socket */ +int tcp_set_ulp(struct sock *sk, const char *name) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_ulp_ops *ulp_ops; + int err = 0; + + if (icsk->icsk_ulp_ops) + return -EEXIST; + + ulp_ops = __tcp_ulp_find_autoload(name); + if (!ulp_ops) + err = -ENOENT; + else + err = ulp_ops->init(sk); + + if (err) + goto out; + + icsk->icsk_ulp_ops = ulp_ops; + out: + return err; +} diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 9775453b8d17..bec9cafbe3f9 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -68,7 +68,7 @@ static void tcp_westwood_init(struct sock *sk) w->cumul_ack = 0; w->reset_rtt_min = 1; w->rtt_min = w->rtt = TCP_WESTWOOD_INIT_RTT; - w->rtt_win_sx = tcp_time_stamp; + w->rtt_win_sx = tcp_jiffies32; w->snd_una = tcp_sk(sk)->snd_una; w->first_ack = 1; } @@ -116,7 +116,7 @@ static void tcp_westwood_pkts_acked(struct sock *sk, static void westwood_update_window(struct sock *sk) { struct westwood *w = inet_csk_ca(sk); - s32 delta = tcp_time_stamp - w->rtt_win_sx; + s32 delta = tcp_jiffies32 - w->rtt_win_sx; /* Initialize w->snd_una with the first acked sequence number in order * to fix mismatch between tp->snd_una and w->snd_una for the first @@ -140,7 +140,7 @@ static void westwood_update_window(struct sock *sk) westwood_filter(w, delta); w->bk = 0; - w->rtt_win_sx = tcp_time_stamp; + w->rtt_win_sx = tcp_jiffies32; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1d6219bf2d6b..25294d43e147 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -577,7 +577,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } @@ -1163,23 +1163,62 @@ out: return ret; } +#if BITS_PER_LONG == 64 +static void udp_set_dev_scratch(struct sk_buff *skb) +{ + struct udp_dev_scratch *scratch; + + BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long)); + scratch = (struct udp_dev_scratch *)&skb->dev_scratch; + scratch->truesize = skb->truesize; + scratch->len = skb->len; + scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); + scratch->is_linear = !skb_is_nonlinear(skb); +} + +static int udp_skb_truesize(struct sk_buff *skb) +{ + return ((struct udp_dev_scratch *)&skb->dev_scratch)->truesize; +} +#else +static void udp_set_dev_scratch(struct sk_buff *skb) +{ + skb->dev_scratch = skb->truesize; +} + +static int udp_skb_truesize(struct sk_buff *skb) +{ + return skb->dev_scratch; +} +#endif + /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial) +static void udp_rmem_release(struct sock *sk, int size, int partial, + bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); + struct sk_buff_head *sk_queue; int amt; if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; if (size < (sk->sk_rcvbuf >> 2) && - !skb_queue_empty(&sk->sk_receive_queue)) + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; } up->forward_deficit = 0; + /* acquire the sk_receive_queue for fwd allocated memory scheduling, + * if the called don't held it already + */ + sk_queue = &sk->sk_receive_queue; + if (!rx_queue_lock_held) + spin_lock(&sk_queue->lock); + + sk->sk_forward_alloc += size; amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); sk->sk_forward_alloc -= amt; @@ -1188,19 +1227,33 @@ static void udp_rmem_release(struct sock *sk, int size, int partial) __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); + + /* this can save us from acquiring the rx queue lock on next receive */ + skb_queue_splice_tail_init(sk_queue, &up->reader_queue); + + if (!rx_queue_lock_held) + spin_unlock(&sk_queue->lock); } -/* Note: called with sk_receive_queue.lock held. +/* Note: called with reader_queue.lock held. * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch * This avoids a cache line miss while receive_queue lock is held. * Look at __udp_enqueue_schedule_skb() to find where this copy is done. */ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) { - udp_rmem_release(sk, skb->dev_scratch, 1); + prefetch(&skb->data); + udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); } EXPORT_SYMBOL(udp_skb_destructor); +/* as above, but the caller held the rx queue lock, too */ +static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) +{ + prefetch(&skb->data); + udp_rmem_release(sk, udp_skb_truesize(skb), 1, true); +} + /* Idea of busylocks is to let producers grab an extra spinlock * to relieve pressure on the receive_queue spinlock shared by consumer. * Under flood, this means that only one producer can be in line @@ -1252,10 +1305,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) busy = busylock_acquire(sk); } size = skb->truesize; - /* Copy skb->truesize into skb->dev_scratch to avoid a cache line miss - * in udp_skb_destructor() - */ - skb->dev_scratch = size; + udp_set_dev_scratch(skb); /* we drop only if the receive buf is full and the receive * queue contains some other skb @@ -1306,14 +1356,16 @@ EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); void udp_destruct_sock(struct sock *sk) { /* reclaim completely the forward allocated memory */ + struct udp_sock *up = udp_sk(sk); unsigned int total = 0; struct sk_buff *skb; - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { + skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue); + while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) { total += skb->truesize; kfree_skb(skb); } - udp_rmem_release(sk, total, 0); + udp_rmem_release(sk, total, 0, true); inet_sock_destruct(sk); } @@ -1321,6 +1373,7 @@ EXPORT_SYMBOL_GPL(udp_destruct_sock); int udp_init_sock(struct sock *sk) { + skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; return 0; } @@ -1334,10 +1387,38 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) sk_peek_offset_bwd(sk, len); unlock_sock_fast(sk, slow); } - consume_skb(skb); + + consume_stateless_skb(skb); } EXPORT_SYMBOL_GPL(skb_consume_udp); +static struct sk_buff *__first_packet_length(struct sock *sk, + struct sk_buff_head *rcvq, + int *total) +{ + struct sk_buff *skb; + + while ((skb = skb_peek(rcvq)) != NULL) { + if (udp_lib_checksum_complete(skb)) { + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); + __skb_unlink(skb, rcvq); + *total += skb->truesize; + kfree_skb(skb); + } else { + /* the csum related bits could be changed, refresh + * the scratch area + */ + udp_set_dev_scratch(skb); + break; + } + } + return skb; +} + /** * first_packet_length - return length of first packet in receive queue * @sk: socket @@ -1347,26 +1428,24 @@ EXPORT_SYMBOL_GPL(skb_consume_udp); */ static int first_packet_length(struct sock *sk) { - struct sk_buff_head *rcvq = &sk->sk_receive_queue; + struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff *skb; int total = 0; int res; spin_lock_bh(&rcvq->lock); - while ((skb = skb_peek(rcvq)) != NULL && - udp_lib_checksum_complete(skb)) { - __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, - IS_UDPLITE(sk)); - __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - atomic_inc(&sk->sk_drops); - __skb_unlink(skb, rcvq); - total += skb->truesize; - kfree_skb(skb); + skb = __first_packet_length(sk, rcvq, &total); + if (!skb && !skb_queue_empty(sk_queue)) { + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, rcvq); + spin_unlock(&sk_queue->lock); + + skb = __first_packet_length(sk, rcvq, &total); } res = skb ? skb->len : -1; if (total) - udp_rmem_release(sk, total, 1); + udp_rmem_release(sk, total, 1, false); spin_unlock_bh(&rcvq->lock); return res; } @@ -1400,6 +1479,77 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) } EXPORT_SYMBOL(udp_ioctl); +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, + int noblock, int *peeked, int *off, int *err) +{ + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + struct sk_buff_head *queue; + struct sk_buff *last; + long timeo; + int error; + + queue = &udp_sk(sk)->reader_queue; + flags |= noblock ? MSG_DONTWAIT : 0; + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + do { + struct sk_buff *skb; + + error = sock_error(sk); + if (error) + break; + + error = -EAGAIN; + *peeked = 0; + do { + spin_lock_bh(&queue->lock); + skb = __skb_try_recv_from_queue(sk, queue, flags, + udp_skb_destructor, + peeked, off, err, + &last); + if (skb) { + spin_unlock_bh(&queue->lock); + return skb; + } + + if (skb_queue_empty(sk_queue)) { + spin_unlock_bh(&queue->lock); + goto busy_check; + } + + /* refill the reader queue and walk it again + * keep both queues locked to avoid re-acquiring + * the sk_receive_queue lock if fwd memory scheduling + * is needed. + */ + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, queue); + + skb = __skb_try_recv_from_queue(sk, queue, flags, + udp_skb_dtor_locked, + peeked, off, err, + &last); + spin_unlock(&sk_queue->lock); + spin_unlock_bh(&queue->lock); + if (skb) + return skb; + +busy_check: + if (!sk_can_busy_loop(sk)) + break; + + sk_busy_loop(sk, flags & MSG_DONTWAIT); + } while (!skb_queue_empty(sk_queue)); + + /* sk_queue is empty, reader_queue may contain peeked packets */ + } while (timeo && + !__skb_wait_for_more_packets(sk, &error, &timeo, + (struct sk_buff *)sk_queue)); + + *err = error; + return NULL; +} +EXPORT_SYMBOL_GPL(__skb_recv_udp); + /* * This should be easy, if there is something there we * return it, otherwise we block. @@ -1426,7 +1576,7 @@ try_again: if (!skb) return err; - ulen = skb->len; + ulen = udp_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; @@ -1441,14 +1591,18 @@ try_again: if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { - checksum_valid = !udp_lib_checksum_complete(skb); + checksum_valid = udp_skb_csum_unnecessary(skb) || + !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } - if (checksum_valid || skb_csum_unnecessary(skb)) - err = skb_copy_datagram_msg(skb, off, msg, copied); - else { + if (checksum_valid || udp_skb_csum_unnecessary(skb)) { + if (udp_skb_is_linear(skb)) + err = copy_linear_skb(skb, copied, off, &msg->msg_iter); + else + err = skb_copy_datagram_msg(skb, off, msg, copied); + } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) @@ -1490,7 +1644,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } @@ -1624,6 +1779,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id_once(sk, skb); } + /* clear all pending head states while they are hot in the cache */ + skb_release_head_state(skb); + rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1738,6 +1896,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } + prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; @@ -1766,9 +1925,10 @@ static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; - dst_hold(dst); - old = xchg(&sk->sk_rx_dst, dst); - dst_release(old); + if (dst_hold_safe(dst)) { + old = xchg(&sk->sk_rx_dst, dst); + dst_release(old); + } } /* @@ -2082,7 +2242,7 @@ void udp_v4_early_demux(struct sk_buff *skb) uh->source, iph->saddr, dif); } - if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; @@ -2092,13 +2252,11 @@ void udp_v4_early_demux(struct sk_buff *skb) if (dst) dst = dst_check(dst, 0); if (dst) { - /* DST_NOCACHE can not be used without taking a reference */ - if (dst->flags & DST_NOCACHE) { - if (likely(atomic_inc_not_zero(&dst->__refcnt))) - skb_dst_set(skb, dst); - } else { - skb_dst_set_noref(skb, dst); - } + /* set noref for now. + * any place which wants to hold dst has to call + * dst_hold_safe() + */ + skb_dst_set_noref(skb, dst); } } @@ -2325,6 +2483,9 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; + if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + mask |= POLLIN | POLLRDNORM; + sock_rps_record_flow(sk); /* Check for false positives due to checksum errors */ @@ -2530,7 +2691,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 9a89c10a55f0..4515836d2a3a 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -55,7 +55,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_dport, req->id.idiag_if, tbl, NULL); #endif - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); err = -ENOENT; @@ -206,7 +206,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, return -EINVAL; } - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 71acd0014f2d..856d2dfdb44b 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -57,8 +57,7 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb) xfrm4_beet_make_header(skb); - ph = (struct ip_beet_phdr *) - __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); + ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen); top_iph = ip_hdr(skb); |