diff options
Diffstat (limited to 'net/ipv4')
34 files changed, 709 insertions, 451 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index b54b3ca939db..4d265d4a0dbe 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -298,6 +298,7 @@ config SYN_COOKIES config NET_IPVTI tristate "Virtual (secure) IP: tunneling" + depends on IPV6 || IPV6=n select INET_TUNNEL select NET_IP_TUNNEL depends on INET_XFRM_MODE_TUNNEL diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 71bcab94c5c7..0a6f72763beb 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1738,6 +1738,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1749,7 +1750,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f915abff1350..d3eddfd13875 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -75,7 +75,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = jiffies; + inet->inet_id = prandom_u32(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f08f984ebc56..af3363f4543f 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -67,6 +67,11 @@ #include "fib_lookup.h" +#define IPV6ONLY_FLAGS \ + (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ + IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ + IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) + static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, @@ -453,6 +458,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; + /* Don't set IPv6 only flags to IPv4 addresses */ + ifa->ifa_flags &= ~IPV6ONLY_FLAGS; + for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; ifap = &ifa1->ifa_next) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && @@ -552,12 +560,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, return NULL; } -static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) +static int ip_mc_autojoin_config(struct net *net, bool join, + const struct in_ifaddr *ifa) { +#if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; + struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL(); @@ -570,6 +581,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) release_sock(sk); return ret; +#else + return -EOPNOTSUPP; +#endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) @@ -609,7 +623,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) continue; if (ipv4_is_multicast(ifa->ifa_address)) - ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa); + ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -865,8 +879,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { - int ret = ip_mc_config(net->ipv4.mc_autojoin_sk, - true, ifa); + int ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { inet_free_ifa(ifa); @@ -1378,11 +1391,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 90c654012510..6aec95e1fc13 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1358,8 +1358,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 36f0a8c581d0..a1a7ed6fc8dd 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2256,6 +2256,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) " %Zd bytes, size of tnode: %Zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); + rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; @@ -2275,7 +2276,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) trie_show_usage(seq, t->stats); #endif } + cond_resched_rcu(); } + rcu_read_unlock(); return 0; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 030d1531e897..17acc89f9dec 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -119,6 +119,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) struct guehdr *guehdr; void *data; u16 doffset = 0; + u8 proto_ctype; if (!fou) return 1; @@ -210,13 +211,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr); + proto_ctype = guehdr->proto_ctype; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); if (iptunnel_pull_offloads(skb)) goto drop; - return -guehdr->proto_ctype; + return -proto_ctype; drop: kfree_skb(skb); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index b798862b6be5..4a5e55e94a9e 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -60,7 +60,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -/* Fills in tpi and returns header length to be pulled. */ +/* Fills in tpi and returns header length to be pulled. + * Note that caller must use pskb_may_pull() before pulling GRE header. + */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { @@ -86,13 +88,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { + if (!skb_checksum_simple_validate(skb)) { + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + } else if (csum_err) { *csum_err = true; return -EINVAL; } - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); options++; } @@ -113,8 +116,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + u8 _val, *val; + + val = skb_header_pointer(skb, nhs + hdr_len, + sizeof(_val), &_val); + if (!val) + return -EINVAL; tpi->proto = proto; - if ((*(u8 *)options & 0xF0) != 0x40) + if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 172d3dfed0c4..cc5c8d598e5e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -256,10 +256,11 @@ bool icmp_global_allow(void) bool rc = false; /* Check if token bucket is empty and cannot be refilled - * without taking the spinlock. + * without taking the spinlock. The READ_ONCE() are paired + * with the following WRITE_ONCE() in this same function. */ - if (!icmp_global.credit) { - delta = min_t(u32, now - icmp_global.stamp, HZ); + if (!READ_ONCE(icmp_global.credit)) { + delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ); if (delta < HZ / 50) return false; } @@ -269,14 +270,14 @@ bool icmp_global_allow(void) if (delta >= HZ / 50) { incr = sysctl_icmp_msgs_per_sec * delta / HZ ; if (incr) - icmp_global.stamp = now; + WRITE_ONCE(icmp_global.stamp, now); } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { credit--; rc = true; } - icmp_global.credit = credit; + WRITE_ONCE(icmp_global.credit, credit); spin_unlock(&icmp_global.lock); return rc; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index f2e6e874e4ec..02c1736c0b89 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -190,6 +190,17 @@ static void ip_ma_put(struct ip_mc_list *im) pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) +static void ip_sf_list_clear_all(struct ip_sf_list *psf) +{ + struct ip_sf_list *next; + + while (psf) { + next = psf->sf_next; + kfree(psf); + psf = next; + } +} + #ifdef CONFIG_IP_MULTICAST /* @@ -635,6 +646,13 @@ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) } } +static void kfree_pmc(struct ip_mc_list *pmc) +{ + ip_sf_list_clear_all(pmc->sources); + ip_sf_list_clear_all(pmc->tomb); + kfree(pmc); +} + static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; @@ -671,7 +689,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); - kfree(pmc); + kfree_pmc(pmc); } else pmc_prev = pmc; } @@ -1194,13 +1212,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) im->interface = pmc->interface; im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; if (im->sfmode == MCAST_INCLUDE) { - im->tomb = pmc->tomb; - im->sources = pmc->sources; + swap(im->tomb, pmc->tomb); + swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = im->crcount; } in_dev_put(pmc->interface); - kfree(pmc); + kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } @@ -1221,21 +1239,18 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); - kfree(pmc); + kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { - struct ip_sf_list *psf, *psf_next; + struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); - for (; psf; psf = psf_next) { - psf_next = psf->sf_next; - kfree(psf); - } + ip_sf_list_clear_all(psf); } rcu_read_unlock(); } @@ -2099,7 +2114,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, static void ip_mc_clear_src(struct ip_mc_list *pmc) { - struct ip_sf_list *psf, *nextpsf, *tomb, *sources; + struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; @@ -2111,14 +2126,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); - for (psf = tomb; psf; psf = nextpsf) { - nextpsf = psf->sf_next; - kfree(psf); - } - for (psf = sources; psf; psf = nextpsf) { - nextpsf = psf->sf_next; - kfree(psf); - } + ip_sf_list_clear_all(tomb); + ip_sf_list_clear_all(sources); } /* Join a multicast group diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e4d16fc5bbb3..4273576e1475 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -868,12 +868,13 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock_bh(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 0fb49dedc9fb..2325cd3454a6 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,62 @@ #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> +#include <net/ip.h> +#include <net/ipv6.h> + +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + }; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void fragcb_clear(struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void fragrun_append_to_last(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + fragcb_clear(skb); + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + fragcb_clear(skb); + + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + q->fragments_tail = skb; + q->last_run_head = skb; +} /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. @@ -122,6 +178,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } +unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -223,3 +301,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) return fq; } EXPORT_SYMBOL(inet_frag_find); + +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end) +{ + struct sk_buff *last = q->fragments_tail; + + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * Duplicates, however, should be ignored (i.e. skb dropped, but the + * queue/fragments kept for later reassembly). + */ + if (!last) + fragrun_create(q, skb); /* First fragment. */ + else if (last->ip_defrag_offset + last->len < end) { + /* This is the common case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < last->ip_defrag_offset + last->len) + return IPFRAG_OVERLAP; + if (offset == last->ip_defrag_offset + last->len) + fragrun_append_to_last(q, skb); + else + fragrun_create(q, skb); + } else { + /* Binary search. Note that skb can become the first fragment, + * but not the last (covered above). + */ + struct rb_node **rbn, *parent; + + rbn = &q->rb_fragments.rb_node; + do { + struct sk_buff *curr; + int curr_run_end; + + parent = *rbn; + curr = rb_to_skb(parent); + curr_run_end = curr->ip_defrag_offset + + FRAG_CB(curr)->frag_run_len; + if (end <= curr->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= curr_run_end) + rbn = &parent->rb_right; + else if (offset >= curr->ip_defrag_offset && + end <= curr_run_end) + return IPFRAG_DUP; + else + return IPFRAG_OVERLAP; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. + */ + fragcb_clear(skb); + rb_link_node(&skb->rbnode, parent, rbn); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + } + + skb->ip_defrag_offset = offset; + + return IPFRAG_OK; +} +EXPORT_SYMBOL(inet_frag_queue_insert); + +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent) +{ + struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); + struct sk_buff **nextp; + int delta; + + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); + if (!fp) + return NULL; + FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; + if (RB_EMPTY_NODE(&skb->rbnode)) + FRAG_CB(parent)->next_frag = fp; + else + rb_replace_node(&skb->rbnode, &fp->rbnode, + &q->rb_fragments); + if (q->fragments_tail == skb) + q->fragments_tail = fp; + skb_morph(skb, head); + FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + consume_skb(head); + head = skb; + } + WARN_ON(head->ip_defrag_offset != 0); + + delta = -head->truesize; + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + return NULL; + + delta += head->truesize; + if (delta) + add_frag_mem_limit(q->net, delta); + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + return NULL; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->data_len = head->data_len - plen; + clone->len = clone->data_len; + head->truesize += clone->truesize; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + add_frag_mem_limit(q->net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; + } + + return nextp; +} +EXPORT_SYMBOL(inet_frag_reasm_prepare); + +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data) +{ + struct sk_buff **nextp = (struct sk_buff **)reasm_data; + struct rb_node *rbn; + struct sk_buff *fp; + + skb_push(head, head->data - skb_network_header(head)); + + /* Traverse the tree in order, to build frag_list. */ + fp = FRAG_CB(head)->next_frag; + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &q->rb_fragments); + while (rbn || fp) { + /* fp points to the next sk_buff in the current run; + * rbn points to the next run. + */ + /* Go through the current run. */ + while (fp) { + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + fp = FRAG_CB(fp)->next_frag; + } + /* Move to the next run. */ + if (rbn) { + struct rb_node *rbnext = rb_next(rbn); + + fp = rb_to_skb(rbn); + rb_erase(rbn, &q->rb_fragments); + rbn = rbnext; + } + } + sub_frag_mem_limit(q->net, head->truesize); + + *nextp = NULL; + head->next = NULL; + head->prev = NULL; + head->tstamp = q->stamp; +} +EXPORT_SYMBOL(inet_frag_reasm_finish); + +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) +{ + struct sk_buff *head; + + if (q->fragments) { + head = q->fragments; + q->fragments = head->next; + } else { + struct sk_buff *skb; + + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == q->fragments_tail) + q->fragments_tail = NULL; + + sub_frag_mem_limit(q->net, head->truesize); + + return head; +} +EXPORT_SYMBOL(inet_frag_pull_head); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index b9bcf3db3af9..4bf542f4d980 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -218,9 +218,10 @@ struct sock *__inet_lookup_listener(struct net *net, int score, hiscore = 0, matches = 0, reuseport = 0; bool exact_dif = inet_exact_dif_match(net, skb); struct sock *sk, *result = NULL; + struct hlist_nulls_node *node; u32 phash = 0; - sk_for_each_rcu(sk, &ilb->head) { + sk_nulls_for_each_rcu(sk, node, &ilb->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, exact_dif); if (score > hiscore) { reuseport = sk->sk_reuseport; @@ -441,10 +442,11 @@ static int inet_reuseport_add_sock(struct sock *sk, bool match_wildcard)) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -482,9 +484,9 @@ int __inet_hash(struct sock *sk, struct sock *osk, } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); sock_set_flag(sk, SOCK_RCU_FREE); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); unlock: @@ -527,10 +529,7 @@ void inet_unhash(struct sock *sk) spin_lock_bh(lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - if (listener) - done = __sk_del_node_init(sk); - else - done = __sk_nulls_del_node_init_rcu(sk); + done = __sk_nulls_del_node_init_rcu(sk); if (done) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock_bh(lock); @@ -666,7 +665,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); } } EXPORT_SYMBOL_GPL(inet_hashinfo_init); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index c7334d1e392a..6e9ba9dfb5b2 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -56,57 +56,6 @@ */ static const char ip_frag_cache_name[] = "ip4-frags"; -/* Use skb->cb to track consecutive/adjacent fragments coming at - * the end of the queue. Nodes in the rb-tree queue will - * contain "runs" of one or more adjacent fragments. - * - * Invariants: - * - next_frag is NULL at the tail of a "run"; - * - the head of a "run" has the sum of all fragment lengths in frag_run_len. - */ -struct ipfrag_skb_cb { - struct inet_skb_parm h; - struct sk_buff *next_frag; - int frag_run_len; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - -static void ip4_frag_init_run(struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); - - FRAG_CB(skb)->next_frag = NULL; - FRAG_CB(skb)->frag_run_len = skb->len; -} - -/* Append skb to the last "run". */ -static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, - struct sk_buff *skb) -{ - RB_CLEAR_NODE(&skb->rbnode); - FRAG_CB(skb)->next_frag = NULL; - - FRAG_CB(q->last_run_head)->frag_run_len += skb->len; - FRAG_CB(q->fragments_tail)->next_frag = skb; - q->fragments_tail = skb; -} - -/* Create a new "run" with the skb. */ -static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) -{ - if (q->last_run_head) - rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, - &q->last_run_head->rbnode.rb_right); - else - rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); - rb_insert_color(&skb->rbnode, &q->rb_fragments); - - ip4_frag_init_run(skb); - q->fragments_tail = skb; - q->last_run_head = skb; -} - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -210,27 +159,9 @@ static void ip_expire(unsigned long arg) * pull the head out of the tree in order to be able to * deal with head->dev. */ - if (qp->q.fragments) { - head = qp->q.fragments; - qp->q.fragments = head->next; - } else { - head = skb_rb_first(&qp->q.rb_fragments); - if (!head) - goto out; - if (FRAG_CB(head)->next_frag) - rb_replace_node(&head->rbnode, - &FRAG_CB(head)->next_frag->rbnode, - &qp->q.rb_fragments); - else - rb_erase(&head->rbnode, &qp->q.rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } - if (head == qp->q.fragments_tail) - qp->q.fragments_tail = NULL; - - sub_frag_mem_limit(qp->q.net, head->truesize); - + head = inet_frag_pull_head(&qp->q); + if (!head) + goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -343,12 +274,10 @@ static int ip_frag_reinit(struct ipq *qp) static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct rb_node **rbn, *parent; - struct sk_buff *skb1, *prev_tail; - int ihl, end, skb1_run_end; + int ihl, end, flags, offset; + struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; - int flags, offset; int err = -ENOENT; u8 ecn; @@ -380,7 +309,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) - goto err; + goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { @@ -392,82 +321,33 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_qp; qp->q.len = end; } } if (end == offset) - goto err; + goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) - goto err; + goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) - goto err; + goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - * - * We do the same here for IPv4 (and increment an snmp counter) but - * we do not want to drop the whole queue in response to a duplicate - * fragment. - */ - - err = -EINVAL; - /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; - if (!prev_tail) - ip4_frag_create_run(&qp->q, skb); /* First fragment. */ - else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { - /* This is the common case: skb goes to the end. */ - /* Detect and discard overlaps. */ - if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto discard_qp; - if (offset == prev_tail->ip_defrag_offset + prev_tail->len) - ip4_frag_append_to_last_run(&qp->q, skb); - else - ip4_frag_create_run(&qp->q, skb); - } else { - /* Binary search. Note that skb can become the first fragment, - * but not the last (covered above). - */ - rbn = &qp->q.rb_fragments.rb_node; - do { - parent = *rbn; - skb1 = rb_to_skb(parent); - skb1_run_end = skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len; - if (end <= skb1->ip_defrag_offset) - rbn = &parent->rb_left; - else if (offset >= skb1_run_end) - rbn = &parent->rb_right; - else if (offset >= skb1->ip_defrag_offset && - end <= skb1_run_end) - goto err; /* No new data, potential duplicate */ - else - goto discard_qp; /* Found an overlap */ - } while (*rbn); - /* Here we have parent properly set, and rbn pointing to - * one of its NULL left/right children. Insert skb. - */ - ip4_frag_init_run(skb); - rb_link_node(&skb->rbnode, parent, rbn); - rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - } + err = inet_frag_queue_insert(&qp->q, skb, offset, end); + if (err) + goto insert_error; if (dev) qp->iif = dev->ifindex; - skb->ip_defrag_offset = offset; qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; @@ -492,15 +372,24 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; + if (err) + inet_frag_kill(&qp->q); return err; } skb_dst_drop(skb); return -EINPROGRESS; +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); - __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -512,12 +401,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); - struct sk_buff **nextp; /* To build frag_list. */ - struct rb_node *rbn; - int len; - int ihlen; - int err; + void *reasm_data; + int len, err; u8 ecn; ipq_kill(qp); @@ -527,111 +412,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, err = -EINVAL; goto out_fail; } - /* Make the one we just received the head. */ - if (head != skb) { - fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - goto out_nomem; - FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; - if (RB_EMPTY_NODE(&skb->rbnode)) - FRAG_CB(prev_tail)->next_frag = fp; - else - rb_replace_node(&skb->rbnode, &fp->rbnode, - &qp->q.rb_fragments); - if (qp->q.fragments_tail == skb) - qp->q.fragments_tail = fp; - skb_morph(skb, head); - FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; - rb_replace_node(&head->rbnode, &skb->rbnode, - &qp->q.rb_fragments); - consume_skb(head); - head = skb; - } - - WARN_ON(head->ip_defrag_offset != 0); - /* Allocate a new buffer for the datagram. */ - ihlen = ip_hdrlen(head); - len = ihlen + qp->q.len; + /* Make the one we just received the head. */ + reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); + if (!reasm_data) + goto out_nomem; + len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_nomem; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->truesize += clone->truesize; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(qp->q.net, clone->truesize); - skb_shinfo(head)->frag_list = clone; - nextp = &clone->next; - } else { - nextp = &skb_shinfo(head)->frag_list; - } + inet_frag_reasm_finish(&qp->q, skb, reasm_data); - skb_push(head, head->data - skb_network_header(head)); + skb->dev = dev; + IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - /* Traverse the tree in order, to build frag_list. */ - fp = FRAG_CB(head)->next_frag; - rbn = rb_next(&head->rbnode); - rb_erase(&head->rbnode, &qp->q.rb_fragments); - while (rbn || fp) { - /* fp points to the next sk_buff in the current run; - * rbn points to the next run. - */ - /* Go through the current run. */ - while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; - } - /* Move to the next run. */ - if (rbn) { - struct rb_node *rbnext = rb_next(rbn); - - fp = rb_to_skb(rbn); - rb_erase(rbn, &qp->q.rb_fragments); - rbn = rbnext; - } - } - sub_frag_mem_limit(qp->q.net, head->truesize); - - *nextp = NULL; - head->next = NULL; - head->prev = NULL; - head->dev = dev; - head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - - iph = ip_hdr(head); + iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; @@ -644,7 +441,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { - IPCB(head)->flags |= IPSKB_FRAG_PMTU; + IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; @@ -742,28 +539,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_check_defrag); -unsigned int inet_frag_rbtree_purge(struct rb_root *root) -{ - struct rb_node *p = rb_first(root); - unsigned int sum = 0; - - while (p) { - struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - - p = rb_next(p); - rb_erase(&skb->rbnode, root); - while (skb) { - struct sk_buff *next = FRAG_CB(skb)->next_frag; - - sum += skb->truesize; - kfree_skb(skb); - skb = next; - } - } - return sum; -} -EXPORT_SYMBOL(inet_frag_rbtree_purge); - #ifdef CONFIG_SYSCTL static int dist_min; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 576f705d8180..9609ad71dd26 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -224,13 +224,10 @@ static void gre_err(struct sk_buff *skb, u32 info) const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; - bool csum_err = false; - if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), - iph->ihl * 4) < 0) { - if (!csum_err) /* ignore csum errors. */ - return; - } + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), + iph->ihl * 4) < 0) + return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index bcadca26523b..ce0ce1401f28 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -259,11 +259,10 @@ int ip_local_deliver(struct sk_buff *skb) ip_local_deliver_finish); } -static inline bool ip_rcv_options(struct sk_buff *skb) +static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt; const struct iphdr *iph; - struct net_device *dev = skb->dev; /* It looks as overkill, because not all IP options require packet mangling. @@ -299,7 +298,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb) } } - if (ip_options_rcv_srr(skb)) + if (ip_options_rcv_srr(skb, dev)) goto drop; } @@ -361,7 +360,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) } #endif - if (iph->ihl > 5 && ip_rcv_options(skb)) + if (iph->ihl > 5 && ip_rcv_options(skb, dev)) goto drop; rt = skb_rtable(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 4cd3b5ad9cee..570cdb547234 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -614,7 +614,7 @@ void ip_forward_options(struct sk_buff *skb) } } -int ip_options_rcv_srr(struct sk_buff *skb) +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; @@ -649,7 +649,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); - err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); + err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 100c86f1f547..4f3decbe6a3a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -492,6 +492,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; + to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; @@ -1158,13 +1159,17 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, rt = *rtp; if (unlikely(!rt)) return -EFAULT; - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; + cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index e6ee6acac80c..dd5db4cc7d06 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -155,11 +155,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, cand = t; } - if (flags & TUNNEL_NO_KEY) - goto skip_key_lookup; - hlist_for_each_entry_rcu(t, head, hash_node) { - if (t->parms.i_key != key || + if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) @@ -171,7 +168,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, cand = t; } -skip_key_lookup: if (cand) return cand; @@ -653,13 +649,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ + struct ip_tunnel_info *tun_info; if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } - if (skb->protocol == htons(ETH_P_IP)) { + tun_info = skb_tunnel_info(skb); + if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && + ip_tunnel_info_af(tun_info) == AF_INET && + tun_info->key.u.ipv4.dst) + dst = tun_info->key.u.ipv4.dst; + else if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } @@ -1178,10 +1180,8 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; - if (tunnel->collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (tunnel->collect_md) netif_keep_dst(dev); - } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 270e79f4d40e..58e0dab06f19 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -208,8 +208,39 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, int mtu; if (!dst) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; + switch (skb->protocol) { + case htons(ETH_P_IP): { + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst = &rt->dst; + skb_dst_set(skb, dst); + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + fl->u.ip6.flowi6_oif = dev->ifindex; + fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); + if (dst->error) { + dst_release(dst); + dst = NULL; + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + skb_dst_set(skb, dst); + break; +#endif + default: + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } } dst_hold(dst); @@ -678,9 +709,9 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); -xfrm_tunnel_failed: xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel_failed: + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: @@ -696,6 +727,7 @@ pernet_dev_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d35815e5967b..e02b86265194 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -403,10 +403,11 @@ next: ; return 1; } -static inline int check_target(struct arpt_entry *e, const char *name) +static int check_target(struct arpt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = arpt_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -418,8 +419,9 @@ static inline int check_target(struct arpt_entry *e, const char *name) return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); } -static inline int -find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, +static int +find_check_entry(struct arpt_entry *e, struct net *net, const char *name, + unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; @@ -438,7 +440,7 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; return 0; @@ -513,12 +515,13 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return 0; } -static inline void cleanup_entry(struct arpt_entry *e) +static void cleanup_entry(struct arpt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; t = arpt_get_target(e); + par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_ARP; @@ -531,7 +534,9 @@ static inline void cleanup_entry(struct arpt_entry *e) /* Checks and translates the user-supplied table segment (held in * newinfo). */ -static int translate_table(struct xt_table_info *newinfo, void *entry0, +static int translate_table(struct net *net, + struct xt_table_info *newinfo, + void *entry0, const struct arpt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; @@ -597,7 +602,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { - ret = find_check_entry(iter, repl->name, repl->size, + ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; @@ -608,7 +613,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; - cleanup_entry(iter); + cleanup_entry(iter, net); } return ret; } @@ -935,7 +940,7 @@ static int __do_replace(struct net *net, const char *name, /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries; xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, @@ -987,7 +992,7 @@ static int do_replace(struct net *net, const void __user *user, goto free_newinfo; } - ret = translate_table(newinfo, loc_cpu_entry, &tmp); + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -999,7 +1004,7 @@ static int do_replace(struct net *net, const void __user *user, free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1164,7 +1169,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, } } -static int translate_compat_table(struct xt_table_info **pinfo, +static int translate_compat_table(struct net *net, + struct xt_table_info **pinfo, void **pentry0, const struct compat_arpt_replace *compatr) { @@ -1230,7 +1236,7 @@ static int translate_compat_table(struct xt_table_info **pinfo, repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; - ret = translate_table(newinfo, entry1, &repl); + ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; @@ -1283,7 +1289,7 @@ static int compat_do_replace(struct net *net, void __user *user, goto free_newinfo; } - ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -1295,7 +1301,7 @@ static int compat_do_replace(struct net *net, void __user *user, free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1522,7 +1528,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -static void __arpt_unregister_table(struct xt_table *table) +static void __arpt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; @@ -1534,7 +1540,7 @@ static void __arpt_unregister_table(struct xt_table *table) /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter); + cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); @@ -1559,7 +1565,7 @@ int arpt_register_table(struct net *net, loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(newinfo, loc_cpu_entry, repl); + ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) goto out_free; @@ -1574,7 +1580,7 @@ int arpt_register_table(struct net *net, ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret != 0) { - __arpt_unregister_table(new_table); + __arpt_unregister_table(net, new_table); *res = NULL; } @@ -1589,7 +1595,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); - __arpt_unregister_table(table); + __arpt_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index ec48d8eafc7e..8b221398534b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -306,6 +306,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), + SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 59d8770055ed..ed53bf5d2b68 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -169,6 +169,7 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) */ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) { + int dif = inet_iif(skb); struct sock *sk; struct hlist_head *head; int delivered = 0; @@ -181,8 +182,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) net = dev_net(skb->dev); sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol, - iph->saddr, iph->daddr, - skb->dev->ifindex); + iph->saddr, iph->daddr, dif); while (sk) { delivered = 1; @@ -197,7 +197,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) } sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol, iph->saddr, iph->daddr, - skb->dev->ifindex); + dif); } out: read_unlock(&raw_v4_hashinfo.lock); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c42fb2330b45..8f5c6fa54ac0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -496,15 +496,17 @@ EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { - static u32 ip_idents_hashrnd __read_mostly; u32 hash, id; - net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); + /* Note the following code is not safe, but this is okay. */ + if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) + get_random_bytes(&net->ipv4.ip_id_key, + sizeof(net->ipv4.ip_id_key)); - hash = jhash_3words((__force u32)iph->daddr, + hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, - iph->protocol ^ net_hash_mix(net), - ip_idents_hashrnd); + iph->protocol, + &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } @@ -901,16 +903,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (peer->rate_tokens == 0 || time_after(jiffies, (peer->rate_last + - (ip_rt_redirect_load << peer->rate_tokens)))) { + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; - ++peer->rate_tokens; ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number) + peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); @@ -990,21 +991,22 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; if (ip_mtu_locked(dst)) return; - if (ipv4_mtu(dst) < mtu) + if (old_mtu < mtu) return; if (mtu < ip_rt_min_pmtu) { lock = true; - mtu = ip_rt_min_pmtu; + mtu = min(old_mtu, ip_rt_min_pmtu); } - if (rt->rt_pmtu == mtu && + if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) return; @@ -1168,11 +1170,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return dst; } +static void ipv4_send_dest_unreach(struct sk_buff *skb) +{ + struct ip_options opt; + int res; + + /* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. + */ + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) + return; + + memset(&opt, 0, sizeof(opt)); + if (ip_hdr(skb)->ihl > 5) { + if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) + return; + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); + + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) + return; + } + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); +} + static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) @@ -2192,7 +2222,7 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct fib_result res; struct rtable *rth; int orig_oif; - int err = -ENETUNREACH; + int err; res.tclassid = 0; res.fi = NULL; @@ -2207,11 +2237,14 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, rcu_read_lock(); if (fl4->saddr) { - rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || - ipv4_is_zeronet(fl4->saddr)) + ipv4_is_zeronet(fl4->saddr)) { + rth = ERR_PTR(-EINVAL); goto out; + } + + rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. It was wrong for two reasons: diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 024ab833557d..e202babb14d6 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -35,12 +35,15 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; +static int tcp_min_snd_mss_max = 65535; static int ip_ttl_min = 1; static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static int one_day_secs = 24 * 3600; /* Update system visible IP port range */ static void set_local_port_range(struct net *net, int range[2]) @@ -460,7 +463,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_day_secs }, { .procname = "tcp_low_latency", @@ -836,6 +841,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "tcp_min_snd_mss", + .data = &init_net.ipv4.sysctl_tcp_min_snd_mss, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_min_snd_mss_min, + .extra2 = &tcp_min_snd_mss_max, + }, + { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2ededb32b754..02918e0d635e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2298,9 +2298,11 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); + tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() @@ -2312,6 +2314,12 @@ int tcp_disconnect(struct sock *sk, int flags) dst_release(sk->sk_rx_dst); sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); + tp->segs_in = 0; + tp->segs_out = 0; + tp->bytes_acked = 0; + tp->bytes_received = 0; + tp->data_segs_in = 0; + tp->data_segs_out = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); @@ -3307,6 +3315,7 @@ void __init tcp_init(void) unsigned long limit; unsigned int i; + BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 7e44d23b0328..3bfab2d41574 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -649,8 +649,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ - bw = (u64)rs->delivered * BW_UNIT; - do_div(bw, rs->interval_us); + bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index a08cedf9d286..910ef01759e7 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -66,11 +66,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; module_param(dctcp_alpha_on_init, uint, 0644); MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value"); -static unsigned int dctcp_clamp_alpha_on_loss __read_mostly; -module_param(dctcp_clamp_alpha_on_loss, uint, 0644); -MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss, - "parameter for clamping alpha on loss"); - static struct tcp_congestion_ops dctcp_reno; static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) @@ -211,21 +206,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) } } -static void dctcp_state(struct sock *sk, u8 new_state) +static void dctcp_react_to_loss(struct sock *sk) { - if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) { - struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); - /* If this extension is enabled, we clamp dctcp_alpha to - * max on packet loss; the motivation is that dctcp_alpha - * is an indicator to the extend of congestion and packet - * loss is an indicator of extreme congestion; setting - * this in practice turned out to be beneficial, and - * effectively assumes total congestion which reduces the - * window by half. - */ - ca->dctcp_alpha = DCTCP_MAX_ALPHA; - } + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +static void dctcp_state(struct sock *sk, u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != inet_csk(sk)->icsk_ca_state) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ } static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) @@ -237,6 +234,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ce_state_1_to_0(sk); break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cd4f13dda49e..52014c5312b9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -129,7 +129,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ -static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) +static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, + unsigned int len) { static bool __once __read_mostly; @@ -140,8 +141,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); - pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", - dev ? dev->name : "Unknown driver"); + if (!dev || len >= dev->mtu) + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); rcu_read_unlock(); } } @@ -164,8 +166,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (len >= icsk->icsk_ack.rcv_mss) { icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); - if (unlikely(icsk->icsk_ack.rcv_mss != len)) - tcp_gro_dev_warn(sk, skb); + /* Account for possibly-removed options */ + if (unlikely(len > icsk->icsk_ack.rcv_mss + + MAX_TCP_OPTION_SPACE)) + tcp_gro_dev_warn(sk, skb, len); } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. @@ -247,7 +251,7 @@ static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) { - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; } static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) @@ -389,11 +393,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + int room; + + room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh; /* Check #1 */ - if (tp->rcv_ssthresh < tp->window_clamp && - (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_under_memory_pressure(sk)) { + if (room > 0 && !tcp_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -406,8 +411,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) if (incr) { incr = max_t(int, incr, 2 * skb->len); - tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, - tp->window_clamp); + tp->rcv_ssthresh += min(room, incr); inet_csk(sk)->icsk_ack.quick |= 1; } } @@ -919,9 +923,10 @@ static void tcp_update_reordering(struct sock *sk, const int metric, /* This must be called before lost_out is incremented */ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) { - if (!tp->retransmit_skb_hint || - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->retransmit_skb_hint)->seq)) + if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) || + (tp->retransmit_skb_hint && + before(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(tp->retransmit_skb_hint)->seq))) tp->retransmit_skb_hint = skb; if (!tp->lost_out || @@ -1320,7 +1325,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, TCP_SKB_CB(skb)->seq += shifted; tcp_skb_pcount_add(prev, pcount); - BUG_ON(tcp_skb_pcount(skb) < pcount); + WARN_ON_ONCE(tcp_skb_pcount(skb) < pcount); tcp_skb_pcount_add(skb, -pcount); /* When we're adding to gso_segs == 1, gso_size will be zero, @@ -1387,6 +1392,21 @@ static int skb_can_shift(const struct sk_buff *skb) return !skb_headlen(skb) && skb_is_nonlinear(skb); } +int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, + int pcount, int shiftlen) +{ + /* TCP min gso_size is 8 bytes (TCP_MIN_GSO_SIZE) + * Since TCP_SKB_CB(skb)->tcp_gso_segs is 16 bits, we need + * to make sure not storing more than 65535 * 8 bytes per skb, + * even if current MSS is bigger. + */ + if (unlikely(to->len + shiftlen >= 65535 * TCP_MIN_GSO_SIZE)) + return 0; + if (unlikely(tcp_skb_pcount(to) + pcount > 65535)) + return 0; + return skb_shift(to, from, shiftlen); +} + /* Try collapsing SACK blocks spanning across multiple skbs to a single * skb. */ @@ -1398,6 +1418,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev; int mss; + int next_pcount; int pcount = 0; int len; int in_sack; @@ -1495,7 +1516,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una)) goto fallback; - if (!skb_shift(prev, skb, len)) + if (!tcp_skb_shift(prev, skb, pcount, len)) goto fallback; if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) goto out; @@ -1514,11 +1535,11 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, goto out; len = skb->len; - if (skb_shift(prev, skb, len)) { - pcount += tcp_skb_pcount(skb); - tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0); + next_pcount = tcp_skb_pcount(skb); + if (tcp_skb_shift(prev, skb, next_pcount, len)) { + pcount += next_pcount; + tcp_shifted_skb(sk, skb, state, next_pcount, len, mss, 0); } - out: state->fack_count += pcount; return prev; @@ -1725,8 +1746,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } /* Ignore very old stuff early */ - if (!after(sp[used_sacks].end_seq, prior_snd_una)) + if (!after(sp[used_sacks].end_seq, prior_snd_una)) { + if (i == 0) + first_sack_index = -1; continue; + } used_sacks++; } @@ -2837,9 +2861,9 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - if (WARN_ON(!tp->packets_out && tp->sacked_out)) + if (!tp->packets_out && tp->sacked_out) tp->sacked_out = 0; - if (WARN_ON(!tp->sacked_out && tp->fackets_out)) + if (!tp->sacked_out && tp->fackets_out) tp->fackets_out = 0; /* Now state machine starts. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 82c1064ff4aa..e1cf810140b0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -239,7 +239,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_sport, usin->sin_port); - inet->inet_id = tp->write_seq ^ jiffies; + inet->inet_id = prandom_u32(); err = tcp_connect(sk); @@ -1307,7 +1307,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = newtp->write_seq ^ jiffies; + newinet->inet_id = prandom_u32(); if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); @@ -1917,13 +1917,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock_bh(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -1931,9 +1932,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == st->family) @@ -2456,6 +2457,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_ecn_fallback = 1; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; + net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6f35cdd5f2f0..ea7e9308c555 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -707,8 +707,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + if (likely(opts->num_sack_blocks)) + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -1175,6 +1176,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; + long limit; int nlen; u8 flags; @@ -1185,6 +1187,19 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; + /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. + * We need some allowance to not penalize applications setting small + * SO_SNDBUF values. + * Also allow first and last skb in retransmit queue to be split. + */ + limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); + if (unlikely((sk->sk_wmem_queued >> 1) > limit && + skb != tcp_rtx_queue_head(sk) && + skb != tcp_rtx_queue_tail(sk))) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); + return -ENOMEM; + } + if (skb_unclone(skb, gfp)) return -ENOMEM; @@ -1355,8 +1370,7 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ - if (mss_now < 48) - mss_now = 48; + mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss); return mss_now; } @@ -1930,7 +1944,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; @@ -2053,6 +2067,7 @@ static int tcp_mtu_probe(struct sock *sk) * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; + tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { @@ -2218,6 +2233,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 69523389f067..761a198ed5f3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -140,6 +140,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(net->ipv4.sysctl_tcp_base_mss, mss); mss = max(mss, 68 - tp->tcp_header_len); + mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } @@ -371,7 +372,7 @@ static void tcp_probe_timer(struct sock *sk) return; } - if (icsk->icsk_probes_out > max_probes) { + if (icsk->icsk_probes_out >= max_probes) { abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ @@ -477,11 +478,12 @@ void tcp_retransmit_timer(struct sock *sk) goto out_reset_timer; } + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { - int mib_idx; + int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) @@ -496,10 +498,9 @@ void tcp_retransmit_timer(struct sock *sk) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; - } else { - mib_idx = LINUX_MIB_TCPTIMEOUTS; } - __NET_INC_STATS(sock_net(sk), mib_idx); + if (mib_idx) + __NET_INC_STATS(sock_net(sk), mib_idx); } tcp_enter_loss(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5d4b5e0f6b5e..1bb1e27d3d13 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -569,7 +569,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { - return __udp4_lib_lookup_skb(skb, sport, dport, &udp_table); + const struct iphdr *iph = ip_hdr(skb); + + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 622e158a6fc4..1805413cd225 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -108,7 +108,8 @@ static void _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) { const struct iphdr *iph = ip_hdr(skb); - u8 *xprth = skb_network_header(skb) + iph->ihl * 4; + int ihl = iph->ihl; + u8 *xprth = skb_network_header(skb) + ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; @@ -119,6 +120,11 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) fl4->flowi4_mark = skb->mark; fl4->flowi4_oif = reverse ? skb->skb_iif : oif; + fl4->flowi4_proto = iph->protocol; + fl4->daddr = reverse ? iph->saddr : iph->daddr; + fl4->saddr = reverse ? iph->daddr : iph->saddr; + fl4->flowi4_tos = iph->tos; + if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: @@ -130,7 +136,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ports = (__be16 *)xprth; fl4->fl4_sport = ports[!!reverse]; @@ -143,7 +149,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 2 - skb->data)) { u8 *icmp; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; icmp = xprth; fl4->fl4_icmp_type = icmp[0]; @@ -156,7 +162,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be32 *ehdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ehdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ehdr[0]; @@ -168,7 +174,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 8 - skb->data)) { __be32 *ah_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ah_hdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ah_hdr[1]; @@ -180,7 +186,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ipcomp_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ipcomp_hdr = (__be16 *)xprth; fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1])); @@ -193,7 +199,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) __be16 *greflags; __be32 *gre_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; greflags = (__be16 *)xprth; gre_hdr = (__be32 *)xprth; @@ -210,10 +216,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) break; } } - fl4->flowi4_proto = iph->protocol; - fl4->daddr = reverse ? iph->saddr : iph->daddr; - fl4->saddr = reverse ? iph->daddr : iph->saddr; - fl4->flowi4_tos = iph->tos; } static inline int xfrm4_garbage_collect(struct dst_ops *ops) |