diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/core/dev.c | 4 | ||||
-rw-r--r-- | net/core/skbuff.c | 30 | ||||
-rw-r--r-- | net/core/sock.c | 19 | ||||
-rw-r--r-- | net/ipv4/ip_forward.c | 3 | ||||
-rw-r--r-- | net/ipv4/ping.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 66 | ||||
-rw-r--r-- | net/ipv6/ip6_output.c | 3 | ||||
-rw-r--r-- | net/ipv6/ndisc.c | 9 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 2 | ||||
-rw-r--r-- | net/netfilter/nf_conntrack_proto_generic.c | 26 | ||||
-rw-r--r-- | net/netlink/af_netlink.c | 6 |
13 files changed, 140 insertions, 38 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 60bb6cefcc2c..538d17131772 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2783,7 +2783,9 @@ static void skb_update_prio(struct sk_buff *skb) #define skb_update_prio(skb) #endif -static DEFINE_PER_CPU(int, xmit_recursion); +DEFINE_PER_CPU(int, xmit_recursion); +EXPORT_SYMBOL(xmit_recursion); + #define RECURSION_LIMIT 10 /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30a7639bb930..23c59e0b63fd 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -279,13 +279,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -296,7 +297,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -310,7 +311,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -327,6 +327,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { @@ -354,7 +371,8 @@ refill: gfp_t gfp = gfp_mask; if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN | + __GFP_NOMEMALLOC; nc->frag.page = alloc_pages(gfp, order); if (likely(nc->frag.page)) break; diff --git a/net/core/sock.c b/net/core/sock.c index 479a25a271d5..8d2b9d74e46a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -659,6 +659,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) sock_reset_flag(sk, bit); } +bool sk_mc_loop(struct sock *sk) +{ + if (dev_recursion_level()) + return false; + if (!sk) + return true; + switch (sk->sk_family) { + case AF_INET: + return inet_sk(sk)->mc_loop; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + return inet6_sk(sk)->mc_loop; +#endif + } + WARN_ON(1); + return true; +} +EXPORT_SYMBOL(sk_mc_loop); + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index ecb34b5ea42f..57075c4508f7 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -127,6 +127,9 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b94002ab8052..1e2e9bf62f1a 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -158,6 +158,7 @@ void ping_unhash(struct sock *sk) if (sk_hashed(sk)) { write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); + sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 22917918fa80..9fbd69efa999 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3064,10 +3064,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (seq_rtt < 0) { seq_rtt = ca_seq_rtt; } - if (!(sacked & TCPCB_SACKED_ACKED)) + if (!(sacked & TCPCB_SACKED_ACKED)) { reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; + } } if (sacked & TCPCB_SACKED_ACKED) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b7effad5a58c..e2f8bd0d35ed 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1875,7 +1875,7 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 96f64e59d70c..a68cd7100349 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2595,39 +2595,65 @@ begin_fwd: } } -/* Send a fin. The caller locks the socket for us. This cannot be - * allowed to fail queueing a FIN frame under any circumstances. +/* We allow to exceed memory limits for FIN packets to expedite + * connection tear down and (memory) recovery. + * Otherwise tcp_send_fin() could be tempted to either delay FIN + * or even be forced to close flow without any FIN. + */ +static void sk_forced_wmem_schedule(struct sock *sk, int size) +{ + int amt, status; + + if (size <= sk->sk_forward_alloc) + return; + amt = sk_mem_pages(size); + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk_memory_allocated_add(sk, amt, &status); +} + +/* Send a FIN. The caller locks the socket for us. + * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { + struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb = tcp_write_queue_tail(sk); - int mss_now; - /* Optimization, tack on the FIN if we have a queue of - * unsent frames. But be careful about outgoing SACKS - * and IP options. + /* Optimization, tack on the FIN if we have one skb in write queue and + * this skb was not yet sent, or we are under memory pressure. + * Note: in the latter case, FIN packet will be sent after a timeout, + * as TCP stack thinks it has already been transmitted. */ - mss_now = tcp_current_mss(sk); - - if (tcp_send_head(sk) != NULL) { - TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; - TCP_SKB_CB(skb)->end_seq++; + if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) { +coalesce: + TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; + TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; + if (!tcp_send_head(sk)) { + /* This means tskb was already sent. + * Pretend we included the FIN on previous transmit. + * We need to set tp->snd_nxt to the value it would have + * if FIN had been sent. This is because retransmit path + * does not change tp->snd_nxt. + */ + tp->snd_nxt++; + return; + } } else { - /* Socket is locked, keep trying until memory is available. */ - for (;;) { - skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation); - if (skb) - break; - yield(); + skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + if (unlikely(!skb)) { + if (tskb) + goto coalesce; + return; } + skb_reserve(skb, MAX_TCP_HEADER); + sk_forced_wmem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF); + __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to @@ -2796,6 +2822,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } #endif + /* Do not fool tcpdump (if any), clean our debris */ + skb->tstamp.tv64 = 0; return skb; } EXPORT_SYMBOL(tcp_make_synack); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d7907ecf0b75..066d0b03f2b8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -555,7 +555,8 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info*)skb_dst(skb); - struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 09a22f4f36c9..bcd65186b497 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1193,7 +1193,14 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + /* Only set hop_limit on the interface if it is higher than + * the current hop_limit. + */ + if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + } else { + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + } if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a4f890dd223a..9d4332dba8ea 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1633,7 +1633,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index d25f29377648..957c1db66652 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -14,6 +14,30 @@ static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ; +static bool nf_generic_should_process(u8 proto) +{ + switch (proto) { +#ifdef CONFIG_NF_CT_PROTO_SCTP_MODULE + case IPPROTO_SCTP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP_MODULE + case IPPROTO_DCCP: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE + case IPPROTO_GRE: + return false; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE_MODULE + case IPPROTO_UDPLITE: + return false; +#endif + default: + return true; + } +} + static inline struct nf_generic_net *generic_pernet(struct net *net) { return &net->ct.nf_ct_proto.generic; @@ -67,7 +91,7 @@ static int generic_packet(struct nf_conn *ct, static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned int *timeouts) { - return true; + return nf_generic_should_process(nf_ct_protonum(ct)); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 1d52506bda14..a0b0ea949192 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1624,13 +1624,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } |