diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/Makefile | 2 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 8 | ||||
-rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 17 | ||||
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 7 | ||||
-rw-r--r-- | net/ipv4/inet_fragment.c | 14 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 19 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 12 | ||||
-rw-r--r-- | net/ipv4/ip_sockglue.c | 3 | ||||
-rw-r--r-- | net/ipv4/ip_tunnel.c | 32 | ||||
-rw-r--r-- | net/ipv4/ip_vti.c | 20 | ||||
-rw-r--r-- | net/ipv4/ipip.c | 2 | ||||
-rw-r--r-- | net/ipv4/ipmr.c | 12 | ||||
-rw-r--r-- | net/ipv4/metrics.c | 3 | ||||
-rw-r--r-- | net/ipv4/netfilter/nft_dup_ipv4.c | 3 | ||||
-rw-r--r-- | net/ipv4/netfilter/nft_fib_ipv4.c | 5 | ||||
-rw-r--r-- | net/ipv4/ping.c | 2 | ||||
-rw-r--r-- | net/ipv4/proc.c | 1 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 83 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 10 | ||||
-rw-r--r-- | net/ipv4/tcp_bpf.c | 19 | ||||
-rw-r--r-- | net/ipv4/tcp_dctcp.c | 23 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 67 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 105 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 61 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 41 | ||||
-rw-r--r-- | net/ipv4/tcp_plb.c | 109 | ||||
-rw-r--r-- | net/ipv4/udp.c | 217 | ||||
-rw-r--r-- | net/ipv4/udp_diag.c | 6 | ||||
-rw-r--r-- | net/ipv4/udp_offload.c | 8 | ||||
-rw-r--r-- | net/ipv4/udp_tunnel_nic.c | 2 |
30 files changed, 689 insertions, 224 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index bbdd9c44f14e..af7d2cf490fb 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -10,7 +10,7 @@ obj-y := route.o inetpeer.o protocol.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_ulp.o \ - tcp_offload.o datagram.o raw.o udp.o udplite.o \ + tcp_offload.o tcp_plb.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 \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0da679411330..ab4a06be489b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -522,9 +522,9 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { - if (sk->sk_prot->get_port(sk, snum)) { + err = sk->sk_prot->get_port(sk, snum); + if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; - err = -EADDRINUSE; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { @@ -1699,9 +1699,9 @@ u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { - start = u64_stats_fetch_begin_irq(syncp); + start = u64_stats_fetch_begin(syncp); v = *(((u64 *)bhptr) + offt); - } while (u64_stats_fetch_retry_irq(syncp, start)); + } while (u64_stats_fetch_retry(syncp, start)); return v; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 6da16ae6a962..4517d2bd186a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -61,7 +61,9 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; - if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + if (base_type(info->reg_type) == PTR_TO_BTF_ID && + !bpf_type_has_unsafe_modifiers(info->reg_type) && + info->btf_id == sock_id) /* promote it to tcp_sock */ info->btf_id = tcp_sock_id; @@ -69,18 +71,17 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { + const struct btf_type *t; size_t end; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + t = btf_type_by_id(reg->btf, reg->btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); return -EACCES; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 4e84ed21d16f..4a34bc7cb15e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -471,11 +471,11 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; + int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; - int ret = 1, port = snum, l3mdev; struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); @@ -1186,7 +1186,7 @@ int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - int err = -EADDRINUSE; + int err; reqsk_queue_alloc(&icsk->icsk_accept_queue); @@ -1202,7 +1202,8 @@ int inet_csk_listen_start(struct sock *sk) * after validation is complete. */ inet_sk_state_store(sk, TCP_LISTEN); - if (!sk->sk_prot->get_port(sk, inet->inet_num)) { + err = sk->sk_prot->get_port(sk, inet->inet_num); + if (!err) { inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9f9ac5013a7..7072fc0783ef 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -133,6 +133,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); + fq->flags |= INET_FRAG_DROP; if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; count++; @@ -260,7 +261,8 @@ 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) +unsigned int inet_frag_rbtree_purge(struct rb_root *root, + enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; @@ -274,7 +276,7 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root) struct sk_buff *next = FRAG_CB(skb)->next_frag; sum += skb->truesize; - kfree_skb(skb); + kfree_skb_reason(skb, reason); skb = next; } } @@ -284,17 +286,21 @@ EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { - struct fqdir *fqdir; unsigned int sum, sum_truesize = 0; + enum skb_drop_reason reason; struct inet_frags *f; + struct fqdir *fqdir; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); + reason = (q->flags & INET_FRAG_DROP) ? + SKB_DROP_REASON_FRAG_REASM_TIMEOUT : + SKB_CONSUMED; WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; f = fqdir->f; - sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments); + sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments, reason); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fb153569889e..69c00ffdcf3e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -153,6 +153,7 @@ static void ip_expire(struct timer_list *t) if (qp->q.flags & INET_FRAG_COMPLETE) goto out; + qp->q.flags |= INET_FRAG_DROP; ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); @@ -194,7 +195,7 @@ out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); - kfree_skb(head); + kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); ipq_put(qp); } @@ -254,7 +255,8 @@ static int ip_frag_reinit(struct ipq *qp) return -ETIMEDOUT; } - sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments); + sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, + SKB_DROP_REASON_FRAG_TOO_FAR); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; @@ -278,10 +280,14 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) struct net_device *dev; unsigned int fragsize; int err = -ENOENT; + SKB_DR(reason); u8 ecn; - if (qp->q.flags & INET_FRAG_COMPLETE) + /* If reassembly is already done, @skb must be a duplicate frag. */ + if (qp->q.flags & INET_FRAG_COMPLETE) { + SKB_DR_SET(reason, DUP_FRAG); goto err; + } if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && @@ -382,8 +388,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) insert_error: if (err == IPFRAG_DUP) { - kfree_skb(skb); - return -EINVAL; + SKB_DR_SET(reason, DUP_FRAG); + err = -EINVAL; + goto err; } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); @@ -391,7 +398,7 @@ discard_qp: inet_frag_kill(&qp->q); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return err; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index cae9f1a4e059..ffff46cdcb58 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -510,7 +510,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, err_free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) @@ -592,7 +592,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) err_free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) @@ -663,7 +663,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -717,7 +717,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -745,7 +745,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -1675,7 +1675,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, if (err) goto out; - err = rtnl_configure_link(dev, NULL); + err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6e19cad154f5..9f92ae35bb01 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -267,7 +267,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, } #endif if (cmsg->cmsg_level == SOL_SOCKET) { - err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc); + err = __sock_cmsg_send(sk, cmsg, &ipc->sockc); if (err) return err; continue; @@ -433,6 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, } kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 019f3b0839c5..de90b09dfe78 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -368,23 +368,23 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { - tunnel->dev->stats.multicast++; + DEV_STATS_INC(tunnel->dev, multicast); skb->pkt_type = PACKET_BROADCAST; } #endif if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { - tunnel->dev->stats.rx_crc_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_crc_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (tunnel->parms.i_flags&TUNNEL_SEQ) { if (!(tpi->flags&TUNNEL_SEQ) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { - tunnel->dev->stats.rx_fifo_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_fifo_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; @@ -398,8 +398,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { - ++tunnel->dev->stats.rx_frame_errors; - ++tunnel->dev->stats.rx_errors; + DEV_STATS_INC(tunnel->dev, rx_frame_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } @@ -581,7 +581,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) @@ -590,7 +590,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } if (rt->dst.dev == dev) { ip_rt_put(rt); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -625,10 +625,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, df, !net_eq(tunnel->net, dev_net(dev))); return; tx_error: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); goto kfree; tx_dropped: - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); kfree: kfree_skb(skb); } @@ -662,7 +662,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, /* NBMA tunnel */ if (!skb_dst(skb)) { - dev->stats.tx_fifo_errors++; + DEV_STATS_INC(dev, tx_fifo_errors); goto tx_error; } @@ -749,7 +749,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) @@ -762,7 +762,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (rt->dst.dev == dev) { ip_rt_put(rt); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -805,7 +805,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (skb_cow_head(skb, dev->needed_headroom)) { ip_rt_put(rt); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return; } @@ -819,7 +819,7 @@ tx_error_icmp: dst_link_failure(skb); #endif tx_error: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 8c2bd1d9ddce..53bfd8af6920 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -107,8 +107,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) dev = tunnel->dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -183,7 +183,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, 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++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst = &rt->dst; @@ -198,14 +198,14 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (dst->error) { dst_release(dst); dst = NULL; - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } skb_dst_set(skb, dst); break; #endif default: - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } } @@ -213,7 +213,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, dst_hold(dst); dst = xfrm_lookup_route(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } @@ -221,7 +221,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_release(dst); goto tx_error_icmp; } @@ -230,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (tdev == dev) { dst_release(dst); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -267,7 +267,7 @@ xmit: tx_error_icmp: dst_link_failure(skb); tx_error: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } @@ -304,7 +304,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) return vti_xmit(skb, dev, &fl); tx_err: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 180f9daf5bec..abea77759b7e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -310,7 +310,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, tx_error: kfree_skb(skb); - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e04544ac4b45..b58df3c1bf7d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -506,8 +506,8 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) return err; } - dev->stats.tx_bytes += skb->len; - dev->stats.tx_packets++; + DEV_STATS_ADD(dev, tx_bytes, skb->len); + DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ @@ -1839,8 +1839,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); - vif_dev->stats.tx_bytes += skb->len; - vif_dev->stats.tx_packets++; + DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); + DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } @@ -1898,8 +1898,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (vif->flags & VIFF_TUNNEL) { ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ - vif_dev->stats.tx_packets++; - vif_dev->stats.tx_bytes += skb->len; + DEV_STATS_INC(vif_dev, tx_packets); + DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } IPCB(skb)->flags |= IPSKB_FORWARDED; diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 25ea6ac44db9..7fcfdfd8f9de 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -14,9 +14,6 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, struct nlattr *nla; int remaining; - if (!fc_mx) - return 0; - nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) { int type = nla_type(nla); u32 val; diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index 0bcd6aee6000..a522c3a3be52 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -52,7 +52,8 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, return err; } -static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_ipv4_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index fc65d69f23e1..9eee535c64dd 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -138,12 +138,11 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, break; } - if (!oif) { - found = FIB_RES_DEV(res); + if (!oif) { + found = FIB_RES_DEV(res); } else { if (!fib_info_nh_uses_dev(res.fi, oif)) return; - found = oif; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 04b4ec07bb06..409ec2a1f95b 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -143,7 +143,7 @@ next_port: fail: spin_unlock(&ping_table.lock); - return 1; + return -EADDRINUSE; } EXPORT_SYMBOL_GPL(ping_get_port); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5386f460bd20..f88daace9de3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), + SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 9b8a6db7a66b..0d0cc4ef2b85 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -40,6 +40,9 @@ static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; +static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; +static int tcp_plb_max_rounds = 31; +static int tcp_plb_max_cong_thresh = 256; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -400,12 +403,36 @@ static int proc_tcp_ehash_entries(struct ctl_table *table, int write, if (!net_eq(net, &init_net) && !hinfo->pernet) tcp_ehash_entries *= -1; + memset(&tbl, 0, sizeof(tbl)); tbl.data = &tcp_ehash_entries; tbl.maxlen = sizeof(int); return proc_dointvec(&tbl, write, buffer, lenp, ppos); } +static int proc_udp_hash_entries(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_udp_child_hash_entries); + int udp_hash_entries; + struct ctl_table tbl; + + udp_hash_entries = net->ipv4.udp_table->mask + 1; + + /* A negative number indicates that the child netns + * shares the global udp_table. + */ + if (!net_eq(net, &init_net) && net->ipv4.udp_table == &udp_table) + udp_hash_entries *= -1; + + memset(&tbl, 0, sizeof(tbl)); + tbl.data = &udp_hash_entries; + tbl.maxlen = sizeof(int); + + return proc_dointvec(&tbl, write, buffer, lenp, ppos); +} + #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, @@ -1360,6 +1387,21 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_child_ehash_entries_max, }, { + .procname = "udp_hash_entries", + .data = &init_net.ipv4.sysctl_udp_child_hash_entries, + .mode = 0444, + .proc_handler = proc_udp_hash_entries, + }, + { + .procname = "udp_child_hash_entries", + .data = &init_net.ipv4.sysctl_udp_child_hash_entries, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_child_hash_entries_max, + }, + { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), @@ -1384,6 +1426,47 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, + { + .procname = "tcp_plb_enabled", + .data = &init_net.ipv4.sysctl_tcp_plb_enabled, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "tcp_plb_idle_rehash_rounds", + .data = &init_net.ipv4.sysctl_tcp_plb_idle_rehash_rounds, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra2 = &tcp_plb_max_rounds, + }, + { + .procname = "tcp_plb_rehash_rounds", + .data = &init_net.ipv4.sysctl_tcp_plb_rehash_rounds, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra2 = &tcp_plb_max_rounds, + }, + { + .procname = "tcp_plb_suspend_rto_sec", + .data = &init_net.ipv4.sysctl_tcp_plb_suspend_rto_sec, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, + { + .procname = "tcp_plb_cong_thresh", + .data = &init_net.ipv4.sysctl_tcp_plb_cong_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_plb_max_cong_thresh, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4f2205756cfe..001947136b0a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3175,6 +3175,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; + tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rack.mstamp = 0; @@ -3938,6 +3939,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_rcv_wnd = tp->rcv_wnd; + info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } @@ -3972,6 +3975,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } @@ -4048,6 +4052,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); + nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } @@ -4459,11 +4464,8 @@ bool tcp_alloc_md5sig_pool(void) if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { mutex_lock(&tcp_md5sig_mutex); - if (!tcp_md5sig_pool_populated) { + if (!tcp_md5sig_pool_populated) __tcp_alloc_md5sig_pool(); - if (tcp_md5sig_pool_populated) - static_branch_inc(&tcp_md5_needed); - } mutex_unlock(&tcp_md5sig_mutex); } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index cf9c3e8f7ccb..94aad3870c5f 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -45,8 +45,11 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, tmp->sg.end = i; if (apply) { apply_bytes -= size; - if (!apply_bytes) + if (!apply_bytes) { + if (sge->length) + sk_msg_iter_var_prev(i); break; + } } } while (i != msg->sg.end); @@ -131,10 +134,9 @@ static int tcp_bpf_push_locked(struct sock *sk, struct sk_msg *msg, return ret; } -int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, - u32 bytes, int flags) +int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, + struct sk_msg *msg, u32 bytes, int flags) { - bool ingress = sk_msg_to_ingress(msg); struct sk_psock *psock = sk_psock_get(sk); int ret; @@ -276,10 +278,10 @@ msg_bytes_ready: static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = sk_msg_full(msg); + bool cork = false, enospc = sk_msg_full(msg), redir_ingress; struct sock *sk_redir; u32 tosend, origsize, sent, delta = 0; - u32 eval = __SK_NONE; + u32 eval; int ret; more_data: @@ -310,6 +312,7 @@ more_data: tosend = msg->sg.size; if (psock->apply_bytes && psock->apply_bytes < tosend) tosend = psock->apply_bytes; + eval = __SK_NONE; switch (psock->eval) { case __SK_PASS: @@ -321,6 +324,7 @@ more_data: sk_msg_apply_bytes(psock, tosend); break; case __SK_REDIRECT: + redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); if (!psock->apply_bytes) { @@ -337,7 +341,8 @@ more_data: release_sock(sk); origsize = msg->sg.size; - ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + ret = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress, + msg, tosend, flags); sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 2a6c0dd665a4..e0a2ca7456ff 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -54,6 +54,7 @@ struct dctcp { u32 next_seq; u32 ce_state; u32 loss_cwnd; + struct tcp_plb_state plb; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ @@ -91,6 +92,8 @@ static void dctcp_init(struct sock *sk) ca->ce_state = 0; dctcp_reset(tp, ca); + tcp_plb_init(sk, &ca->plb); + return; } @@ -117,14 +120,28 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) /* Expired RTT */ if (!before(tp->snd_una, ca->next_seq)) { + u32 delivered = tp->delivered - ca->old_delivered; u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; u32 alpha = ca->dctcp_alpha; + u32 ce_ratio = 0; + + if (delivered > 0) { + /* dctcp_alpha keeps EWMA of fraction of ECN marked + * packets. Because of EWMA smoothing, PLB reaction can + * be slow so we use ce_ratio which is an instantaneous + * measure of congestion. ce_ratio is the fraction of + * ECN marked packets in the previous RTT. + */ + if (delivered_ce > 0) + ce_ratio = (delivered_ce << TCP_PLB_SCALE) / delivered; + tcp_plb_update_state(sk, &ca->plb, (int)ce_ratio); + tcp_plb_check_rehash(sk, &ca->plb); + } /* alpha = (1 - g) * alpha + g * F */ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); if (delivered_ce) { - u32 delivered = tp->delivered - ca->old_delivered; /* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 M packets. @@ -172,8 +189,12 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); break; case CA_EVENT_LOSS: + tcp_plb_update_state_upon_rto(sk, &ca->plb); dctcp_react_to_loss(sk); break; + case CA_EVENT_TX_START: + tcp_plb_check_rehash(sk, &ca->plb); /* Maybe rehash when inflight is 0 */ + break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0640453fce54..1efacbe948da 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4764,8 +4764,8 @@ static void tcp_ofo_queue(struct sock *sk) } } -static bool tcp_prune_ofo_queue(struct sock *sk); -static int tcp_prune_queue(struct sock *sk); +static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); +static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size) @@ -4773,11 +4773,11 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, size)) { - if (tcp_prune_queue(sk) < 0) + if (tcp_prune_queue(sk, skb) < 0) return -1; while (!sk_rmem_schedule(sk, skb, size)) { - if (!tcp_prune_ofo_queue(sk)) + if (!tcp_prune_ofo_queue(sk, skb)) return -1; } } @@ -5329,6 +5329,8 @@ new_range: * Clean the out-of-order queue to make room. * We drop high sequences packets to : * 1) Let a chance for holes to be filled. + * This means we do not drop packets from ooo queue if their sequence + * is before incoming packet sequence. * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) @@ -5336,24 +5338,31 @@ new_range: * * Return true if queue has shrunk. */ -static bool tcp_prune_ofo_queue(struct sock *sk) +static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + bool pruned = false; int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; - NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; + do { + struct sk_buff *skb = rb_to_skb(node); + + /* If incoming skb would land last in ofo queue, stop pruning. */ + if (after(TCP_SKB_CB(in_skb)->seq, TCP_SKB_CB(skb)->seq)) + break; + pruned = true; prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); - goal -= rb_to_skb(node)->truesize; - tcp_drop_reason(sk, rb_to_skb(node), - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); + goal -= skb->truesize; + tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); + tp->ooo_last_skb = rb_to_skb(prev); if (!prev || goal <= 0) { if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) @@ -5362,16 +5371,18 @@ static bool tcp_prune_ofo_queue(struct sock *sk) } node = prev; } while (node); - tp->ooo_last_skb = rb_to_skb(prev); - /* Reset SACK state. A conforming SACK implementation will - * do the same at a timeout based retransmit. When a connection - * is in a sad state like this, we care only about integrity - * of the connection not performance. - */ - if (tp->rx_opt.sack_ok) - tcp_sack_reset(&tp->rx_opt); - return true; + if (pruned) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + /* Reset SACK state. A conforming SACK implementation will + * do the same at a timeout based retransmit. When a connection + * is in a sad state like this, we care only about integrity + * of the connection not performance. + */ + if (tp->rx_opt.sack_ok) + tcp_sack_reset(&tp->rx_opt); + } + return pruned; } /* Reduce allocated memory if we can, trying to get @@ -5381,7 +5392,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk) * until the socket owning process reads some of the data * to stabilize the situation. */ -static int tcp_prune_queue(struct sock *sk) +static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -5408,7 +5419,7 @@ static int tcp_prune_queue(struct sock *sk) /* Collapsing did not help, destructive actions follow. * This must not ever occur. */ - tcp_prune_ofo_queue(sk); + tcp_prune_ofo_queue(sk, in_skb); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) return 0; @@ -6830,10 +6841,18 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (!queue->synflood_warned && syncookies != 2 && - xchg(&queue->synflood_warned, 1) == 0) - net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, sk->sk_num, msg); + if (!READ_ONCE(queue->synflood_warned) && syncookies != 2 && + xchg(&queue->synflood_warned, 1) == 0) { + if (IS_ENABLED(CONFIG_IPV6) && sk->sk_family == AF_INET6) { + net_info_ratelimited("%s: Possible SYN flooding on port [%pI6c]:%u. %s.\n", + proto, inet6_rcv_saddr(sk), + sk->sk_num, msg); + } else { + net_info_ratelimited("%s: Possible SYN flooding on port %pI4:%u. %s.\n", + proto, &sk->sk_rcv_saddr, + sk->sk_num, msg); + } + } return want_cookie; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index da46357f501b..8320d0ecb13a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1053,7 +1053,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) * We need to maintain these in the sk structure. */ -DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); +DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); EXPORT_SYMBOL(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) @@ -1161,10 +1161,25 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, } EXPORT_SYMBOL(tcp_v4_md5_lookup); +static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_info *md5sig; + + md5sig = kmalloc(sizeof(*md5sig), gfp); + if (!md5sig) + return -ENOMEM; + + sk_gso_disable(sk); + INIT_HLIST_HEAD(&md5sig->head); + rcu_assign_pointer(tp->md5sig_info, md5sig); + return 0; +} + /* 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, u8 prefixlen, int l3index, u8 flags, - const u8 *newkey, u8 newkeylen, gfp_t gfp) +static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; @@ -1193,15 +1208,6 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); - if (!md5sig) { - md5sig = kmalloc(sizeof(*md5sig), gfp); - if (!md5sig) - return -ENOMEM; - - sk_gso_disable(sk); - INIT_HLIST_HEAD(&md5sig->head); - rcu_assign_pointer(tp->md5sig_info, md5sig); - } key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) @@ -1223,8 +1229,59 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } + +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { + if (tcp_md5sig_info_add(sk, GFP_KERNEL)) + return -ENOMEM; + + if (!static_branch_inc(&tcp_md5_needed.key)) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); + rcu_assign_pointer(tp->md5sig_info, NULL); + kfree_rcu(md5sig, rcu); + return -EUSERS; + } + } + + return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, + newkey, newkeylen, GFP_KERNEL); +} EXPORT_SYMBOL(tcp_md5_do_add); +int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, + struct tcp_md5sig_key *key) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { + if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) + return -ENOMEM; + + if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); + net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); + rcu_assign_pointer(tp->md5sig_info, NULL); + kfree_rcu(md5sig, rcu); + return -EUSERS; + } + } + + return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, + key->flags, key->key, key->keylen, + sk_gfp_mask(sk, GFP_ATOMIC)); +} +EXPORT_SYMBOL(tcp_md5_key_copy); + int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { @@ -1311,7 +1368,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1562,14 +1619,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, addr = (union tcp_md5_addr *)&newinet->inet_daddr; key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key) { - /* - * We're using one, so create a matching key - * on the newsk structure. If we fail to get - * memory, then we end up not copying the key - * across. Shucks. - */ - tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags, - key->key, key->keylen, GFP_ATOMIC); + if (tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key)) + goto put_and_exit; sk_gso_disable(newsk); } #endif @@ -2261,6 +2312,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_clear_md5_list(sk); kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); tp->md5sig_info = NULL; + static_branch_slow_dec_deferred(&tcp_md5_needed); } #endif @@ -2469,7 +2521,6 @@ static void *tcp_seek_last_pos(struct seq_file *seq) case TCP_SEQ_STATE_LISTENING: if (st->bucket > hinfo->lhash2_mask) break; - st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); @@ -3207,6 +3258,14 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); + /* Set default values for PLB */ + net->ipv4.sysctl_tcp_plb_enabled = 0; /* Disabled by default */ + net->ipv4.sysctl_tcp_plb_idle_rehash_rounds = 3; + net->ipv4.sysctl_tcp_plb_rehash_rounds = 12; + net->ipv4.sysctl_tcp_plb_suspend_rto_sec = 60; + /* Default congestion threshold for PLB to mark a round is 50% */ + net->ipv4.sysctl_tcp_plb_cong_thresh = (1 << TCP_PLB_SCALE) / 2; + /* Reno is always built in */ if (!net_eq(net, &init_net) && bpf_try_module_get(init_net.ipv4.tcp_congestion_control, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index c375f603a16c..e002f2e1d4f2 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -240,6 +240,40 @@ kill: } EXPORT_SYMBOL(tcp_timewait_state_process); +static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) +{ +#ifdef CONFIG_TCP_MD5SIG + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + + /* + * The timewait bucket does not have the key DB from the + * sock structure. We just make a quick copy of the + * md5 key being used (if indeed we are using one) + * so the timewait ack generating code has the key. + */ + tcptw->tw_md5_key = NULL; + if (!static_branch_unlikely(&tcp_md5_needed.key)) + return; + + key = tp->af_specific->md5_lookup(sk, sk); + if (key) { + tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); + if (!tcptw->tw_md5_key) + return; + if (!tcp_alloc_md5sig_pool()) + goto out_free; + if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) + goto out_free; + } + return; +out_free: + WARN_ON_ONCE(1); + kfree(tcptw->tw_md5_key); + tcptw->tw_md5_key = NULL; +#endif +} + /* * Move a socket to time-wait or dead fin-wait-2 state. */ @@ -282,26 +316,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } #endif -#ifdef CONFIG_TCP_MD5SIG - /* - * The timewait bucket does not have the key DB from the - * sock structure. We just make a quick copy of the - * md5 key being used (if indeed we are using one) - * so the timewait ack generating code has the key. - */ - do { - tcptw->tw_md5_key = NULL; - if (static_branch_unlikely(&tcp_md5_needed)) { - struct tcp_md5sig_key *key; - - key = tp->af_specific->md5_lookup(sk, sk); - if (key) { - tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); - BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); - } - } - } while (0); -#endif + tcp_time_wait_init(sk, tcptw); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -337,11 +352,13 @@ EXPORT_SYMBOL(tcp_time_wait); void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed)) { + if (static_branch_unlikely(&tcp_md5_needed.key)) { struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) + if (twsk->tw_md5_key) { kfree_rcu(twsk->tw_md5_key, rcu); + static_branch_slow_dec_deferred(&tcp_md5_needed); + } } #endif } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c69f4d966024..71d01cf3c13e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -766,7 +766,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { @@ -922,7 +922,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { @@ -1077,15 +1077,15 @@ static void tcp_tasklet_func(struct tasklet_struct *t) */ void tcp_release_cb(struct sock *sk) { - unsigned long flags, nflags; + unsigned long flags = smp_load_acquire(&sk->sk_tsq_flags); + unsigned long nflags; /* perform an atomic operation only if at least one flag is set */ do { - flags = sk->sk_tsq_flags; if (!(flags & TCP_DEFERRED_ALL)) return; nflags = flags & ~TCP_DEFERRED_ALL; - } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); + } while (!try_cmpxchg(&sk->sk_tsq_flags, &flags, nflags)); if (flags & TCPF_TSQ_DEFERRED) { tcp_tsq_write(sk); @@ -1139,6 +1139,8 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; + struct tsq_tasklet *tsq; + bool empty; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() @@ -1155,28 +1157,23 @@ void tcp_wfree(struct sk_buff *skb) 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) { - struct tsq_tasklet *tsq; - bool empty; - + oval = smp_load_acquire(&sk->sk_tsq_flags); + do { if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; - nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); - if (nval != oval) - continue; + } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); - /* queue this socket to tasklet queue */ - local_irq_save(flags); - tsq = this_cpu_ptr(&tsq_tasklet); - empty = list_empty(&tsq->head); - list_add(&tp->tsq_node, &tsq->head); - if (empty) - tasklet_schedule(&tsq->tasklet); - local_irq_restore(flags); - return; - } + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = this_cpu_ptr(&tsq_tasklet); + empty = list_empty(&tsq->head); + list_add(&tp->tsq_node, &tsq->head); + if (empty) + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + return; out: sk_free(sk); } diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c new file mode 100644 index 000000000000..bb1a08fda113 --- /dev/null +++ b/net/ipv4/tcp_plb.c @@ -0,0 +1,109 @@ +/* Protective Load Balancing (PLB) + * + * PLB was designed to reduce link load imbalance across datacenter + * switches. PLB is a host-based optimization; it leverages congestion + * signals from the transport layer to randomly change the path of the + * connection experiencing sustained congestion. PLB prefers to repath + * after idle periods to minimize packet reordering. It repaths by + * changing the IPv6 Flow Label on the packets of a connection, which + * datacenter switches include as part of ECMP/WCMP hashing. + * + * PLB is described in detail in: + * + * Mubashir Adnan Qureshi, Yuchung Cheng, Qianwen Yin, Qiaobin Fu, + * Gautam Kumar, Masoud Moshref, Junhua Yan, Van Jacobson, + * David Wetherall,Abdul Kabbani: + * "PLB: Congestion Signals are Simple and Effective for + * Network Load Balancing" + * In ACM SIGCOMM 2022, Amsterdam Netherlands. + * + */ + +#include <net/tcp.h> + +/* Called once per round-trip to update PLB state for a connection. */ +void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, + const int cong_ratio) +{ + struct net *net = sock_net(sk); + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + if (cong_ratio >= 0) { + if (cong_ratio < READ_ONCE(net->ipv4.sysctl_tcp_plb_cong_thresh)) + plb->consec_cong_rounds = 0; + else if (plb->consec_cong_rounds < + READ_ONCE(net->ipv4.sysctl_tcp_plb_rehash_rounds)) + plb->consec_cong_rounds++; + } +} +EXPORT_SYMBOL_GPL(tcp_plb_update_state); + +/* Check whether recent congestion has been persistent enough to warrant + * a load balancing decision that switches the connection to another path. + */ +void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb) +{ + struct net *net = sock_net(sk); + u32 max_suspend; + bool forced_rehash = false, idle_rehash = false; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + forced_rehash = plb->consec_cong_rounds >= + READ_ONCE(net->ipv4.sysctl_tcp_plb_rehash_rounds); + /* If sender goes idle then we check whether to rehash. */ + idle_rehash = READ_ONCE(net->ipv4.sysctl_tcp_plb_idle_rehash_rounds) && + !tcp_sk(sk)->packets_out && + plb->consec_cong_rounds >= + READ_ONCE(net->ipv4.sysctl_tcp_plb_idle_rehash_rounds); + + if (!forced_rehash && !idle_rehash) + return; + + /* Note that tcp_jiffies32 can wrap; we detect wraps by checking for + * cases where the max suspension end is before the actual suspension + * end. We clear pause_until to 0 to indicate there is no recent + * RTO event that constrains PLB rehashing. + */ + max_suspend = 2 * READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; + if (plb->pause_until && + (!before(tcp_jiffies32, plb->pause_until) || + before(tcp_jiffies32 + max_suspend, plb->pause_until))) + plb->pause_until = 0; + + if (plb->pause_until) + return; + + sk_rethink_txhash(sk); + plb->consec_cong_rounds = 0; + tcp_sk(sk)->plb_rehash++; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH); +} +EXPORT_SYMBOL_GPL(tcp_plb_check_rehash); + +/* Upon RTO, disallow load balancing for a while, to avoid having load + * balancing decisions switch traffic to a black-holed path that was + * previously avoided with a sk_rethink_txhash() call at RTO time. + */ +void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb) +{ + struct net *net = sock_net(sk); + u32 pause; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + pause = READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; + pause += prandom_u32_max(pause); + plb->pause_until = tcp_jiffies32 + pause; + + /* Reset PLB state upon RTO, since an RTO causes a sk_rethink_txhash() call + * that may switch this connection to a path with completely different + * congestion characteristics. + */ + plb->consec_cong_rounds = 0; +} +EXPORT_SYMBOL_GPL(tcp_plb_update_state_upon_rto); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6a320a614e54..9592fe3e444a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -129,7 +129,12 @@ DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 -#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN_PERNET) + +static struct udp_table *udp_get_table_prot(struct sock *sk) +{ + return sk->sk_prot->h.udp_table ? : sock_net(sk)->ipv4.udp_table; +} static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, @@ -232,16 +237,16 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr) { + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; - struct udp_table *udptable = sk->sk_prot->h.udp_table; - int error = 1; struct net *net = sock_net(sk); + int error = -EADDRINUSE; if (!snum) { + DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); + unsigned short first, last; int low, high, remaining; unsigned int rand; - unsigned short first, last; - DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; @@ -467,7 +472,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, struct sock *sk, *reuse_sk; bool no_reuseport; - if (udptable != &udp_table) + if (udptable != net->ipv4.udp_table) return NULL; /* only UDP is supported */ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, @@ -548,10 +553,11 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); - return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), &udp_table, NULL); + inet_sdif(skb), net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). @@ -564,7 +570,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, struct sock *sk; sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, - dif, 0, &udp_table, NULL); + dif, 0, net->ipv4.udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -784,7 +790,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info, + (u8 *)(uh+1)); goto out; } if (!inet->recverr) { @@ -801,7 +808,7 @@ out: int udp_err(struct sk_buff *skb, u32 info) { - return __udp4_lib_err(skb, info, &udp_table); + return __udp4_lib_err(skb, info, dev_net(skb->dev)->ipv4.udp_table); } /* @@ -1448,7 +1455,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2) && + if (size < READ_ONCE(up->forward_threshold) && !skb_queue_empty(&up->reader_queue)) return; } else { @@ -1622,7 +1629,7 @@ static void udp_destruct_sock(struct sock *sk) int udp_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udp_destruct_sock; set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; @@ -1998,7 +2005,7 @@ EXPORT_SYMBOL(udp_disconnect); void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; hslot = udp_hashslot(udptable, sock_net(sk), @@ -2029,7 +2036,7 @@ EXPORT_SYMBOL(udp_lib_unhash); void udp_lib_rehash(struct sock *sk, u16 newhash) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); @@ -2518,10 +2525,14 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { - struct sock *sk, *result; + struct udp_table *udptable = net->ipv4.udp_table; unsigned short hnum = ntohs(loc_port); - unsigned int slot = udp_hashfn(net, hnum, udp_table.mask); - struct udp_hslot *hslot = &udp_table.hash[slot]; + struct sock *sk, *result; + struct udp_hslot *hslot; + unsigned int slot; + + slot = udp_hashfn(net, hnum, udptable->mask); + hslot = &udptable->hash[slot]; /* Do not bother scanning a too big list */ if (hslot->count > 10) @@ -2549,14 +2560,19 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { - unsigned short hnum = ntohs(loc_port); - unsigned int hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); - unsigned int slot2 = hash2 & udp_table.mask; - struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; + struct udp_table *udptable = net->ipv4.udp_table; INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); - const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); + unsigned short hnum = ntohs(loc_port); + unsigned int hash2, slot2; + struct udp_hslot *hslot2; + __portpair ports; struct sock *sk; + hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + ports = INET_COMBINED_PORTS(rmt_port, hnum); + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (inet_match(net, sk, acookie, ports, dif, sdif)) return sk; @@ -2636,7 +2652,7 @@ int udp_v4_early_demux(struct sk_buff *skb) int udp_rcv(struct sk_buff *skb) { - return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); + return __udp4_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP); } void udp_destroy_sock(struct sock *sk) @@ -2672,6 +2688,18 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int err = 0; int is_udplite = IS_UDPLITE(sk); + if (level == SOL_SOCKET) { + err = sk_setsockopt(sk, level, optname, optval, optlen); + + if (optname == SO_RCVBUF || optname == SO_RCVBUFFORCE) { + sockopt_lock_sock(sk); + /* paired with READ_ONCE in udp_rmem_release() */ + WRITE_ONCE(up->forward_threshold, sk->sk_rcvbuf >> 2); + sockopt_release_sock(sk); + } + return err; + } + if (optlen < sizeof(int)) return -EINVAL; @@ -2785,7 +2813,7 @@ EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_push_pending_frames); @@ -2947,7 +2975,7 @@ struct proto udp_prot = { .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), - .h.udp_table = &udp_table, + .h.udp_table = NULL, .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); @@ -2955,21 +2983,30 @@ EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS +static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo, + struct net *net) +{ + return afinfo->udp_table ? : net->ipv4.udp_table; +} + static struct sock *udp_get_first(struct seq_file *seq, int start) { - struct sock *sk; - struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct udp_seq_afinfo *afinfo; + struct udp_table *udptable; + struct sock *sk; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); - for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; + udptable = udp_get_table_afinfo(afinfo, net); + + for (state->bucket = start; state->bucket <= udptable->mask; ++state->bucket) { - struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; + struct udp_hslot *hslot = &udptable->hash[state->bucket]; if (hlist_empty(&hslot->head)) continue; @@ -2991,9 +3028,10 @@ found: static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { - struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct udp_seq_afinfo *afinfo; + struct udp_table *udptable; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; @@ -3007,8 +3045,11 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) sk->sk_family != afinfo->family))); if (!sk) { - if (state->bucket <= afinfo->udp_table->mask) - spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); + udptable = udp_get_table_afinfo(afinfo, net); + + if (state->bucket <= udptable->mask) + spin_unlock_bh(&udptable->hash[state->bucket].lock); + return udp_get_first(seq, state->bucket + 1); } return sk; @@ -3049,16 +3090,19 @@ EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { - struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; + struct udp_seq_afinfo *afinfo; + struct udp_table *udptable; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); - if (state->bucket <= afinfo->udp_table->mask) - spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); + udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq)); + + if (state->bucket <= udptable->mask) + spin_unlock_bh(&udptable->hash[state->bucket].lock); } EXPORT_SYMBOL(udp_seq_stop); @@ -3171,7 +3215,7 @@ EXPORT_SYMBOL(udp_seq_ops); static struct udp_seq_afinfo udp4_seq_afinfo = { .family = AF_INET, - .udp_table = &udp_table, + .udp_table = NULL, }; static int __net_init udp4_proc_init_net(struct net *net) @@ -3233,7 +3277,7 @@ void __init udp_table_init(struct udp_table *table, const char *name) &table->log, &table->mask, UDP_HTABLE_SIZE_MIN, - 64 * 1024); + UDP_HTABLE_SIZE_MAX); table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { @@ -3258,7 +3302,7 @@ u32 udp_flow_hashrnd(void) } EXPORT_SYMBOL(udp_flow_hashrnd); -static int __net_init udp_sysctl_init(struct net *net) +static void __net_init udp_sysctl_init(struct net *net) { net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; @@ -3266,12 +3310,103 @@ static int __net_init udp_sysctl_init(struct net *net) #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; #endif +} + +static struct udp_table __net_init *udp_pernet_table_alloc(unsigned int hash_entries) +{ + struct udp_table *udptable; + int i; + + udptable = kmalloc(sizeof(*udptable), GFP_KERNEL); + if (!udptable) + goto out; + + udptable->hash = vmalloc_huge(hash_entries * 2 * sizeof(struct udp_hslot), + GFP_KERNEL_ACCOUNT); + if (!udptable->hash) + goto free_table; + + udptable->hash2 = udptable->hash + hash_entries; + udptable->mask = hash_entries - 1; + udptable->log = ilog2(hash_entries); + + for (i = 0; i < hash_entries; i++) { + INIT_HLIST_HEAD(&udptable->hash[i].head); + udptable->hash[i].count = 0; + spin_lock_init(&udptable->hash[i].lock); + + INIT_HLIST_HEAD(&udptable->hash2[i].head); + udptable->hash2[i].count = 0; + spin_lock_init(&udptable->hash2[i].lock); + } + + return udptable; + +free_table: + kfree(udptable); +out: + return NULL; +} + +static void __net_exit udp_pernet_table_free(struct net *net) +{ + struct udp_table *udptable = net->ipv4.udp_table; + + if (udptable == &udp_table) + return; + + kvfree(udptable->hash); + kfree(udptable); +} + +static void __net_init udp_set_table(struct net *net) +{ + struct udp_table *udptable; + unsigned int hash_entries; + struct net *old_net; + + if (net_eq(net, &init_net)) + goto fallback; + + old_net = current->nsproxy->net_ns; + hash_entries = READ_ONCE(old_net->ipv4.sysctl_udp_child_hash_entries); + if (!hash_entries) + goto fallback; + + /* Set min to keep the bitmap on stack in udp_lib_get_port() */ + if (hash_entries < UDP_HTABLE_SIZE_MIN_PERNET) + hash_entries = UDP_HTABLE_SIZE_MIN_PERNET; + else + hash_entries = roundup_pow_of_two(hash_entries); + + udptable = udp_pernet_table_alloc(hash_entries); + if (udptable) { + net->ipv4.udp_table = udptable; + } else { + pr_warn("Failed to allocate UDP hash table (entries: %u) " + "for a netns, fallback to the global one\n", + hash_entries); +fallback: + net->ipv4.udp_table = &udp_table; + } +} + +static int __net_init udp_pernet_init(struct net *net) +{ + udp_sysctl_init(net); + udp_set_table(net); return 0; } +static void __net_exit udp_pernet_exit(struct net *net) +{ + udp_pernet_table_free(net); +} + static struct pernet_operations __net_initdata udp_sysctl_ops = { - .init = udp_sysctl_init, + .init = udp_pernet_init, + .exit = udp_pernet_exit, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) @@ -3289,7 +3424,7 @@ static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) return -ENOMEM; afinfo->family = AF_UNSPEC; - afinfo->udp_table = &udp_table; + afinfo->udp_table = NULL; st->bpf_seq_afinfo = afinfo; ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 1ed8c4d78e5c..de3f2d31f510 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -147,13 +147,13 @@ done: static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { - udp_dump(&udp_table, skb, cb, r); + udp_dump(sock_net(cb->skb->sk)->ipv4.udp_table, skb, cb, r); } static int udp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return udp_dump_one(&udp_table, cb, req); + return udp_dump_one(sock_net(cb->skb->sk)->ipv4.udp_table, cb, req); } static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, @@ -225,7 +225,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, static int udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { - return __udp_diag_destroy(in_skb, req, &udp_table); + return __udp_diag_destroy(in_skb, req, sock_net(in_skb->sk)->ipv4.udp_table); } static int udplite_diag_destroy(struct sk_buff *in_skb, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6d1a4bec2614..1f01e15ca24f 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -387,7 +387,8 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; @@ -600,10 +601,11 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); + struct net *net = dev_net(skb->dev); - return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), &udp_table, NULL); + inet_sdif(skb), net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index bc3a043a5d5c..029219749785 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -624,6 +624,8 @@ __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); + if (!nest) + return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || |