diff options
Diffstat (limited to 'net/ipv4')
32 files changed, 693 insertions, 228 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 f22051219b50..b366ab9148f2 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/syncookies.c b/net/ipv4/syncookies.c index 942d2dfa1115..26fb97d1d4d9 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -288,12 +288,11 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct tcp_request_sock *treq; struct request_sock *req; -#ifdef CONFIG_MPTCP if (sk_is_mptcp(sk)) - ops = &mptcp_subflow_request_sock_ops; -#endif + req = mptcp_subflow_reqsk_alloc(ops, sk, false); + else + req = inet_reqsk_alloc(ops, sk, false); - req = inet_reqsk_alloc(ops, sk, false); if (!req) return NULL; 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 3f570b25c53d..c567d5e8053e 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; |