diff options
Diffstat (limited to 'net/ipv4/ip_output.c')
| -rw-r--r-- | net/ipv4/ip_output.c | 922 |
1 files changed, 487 insertions, 435 deletions
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c80188875f39..ff11d3a85a36 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket @@ -33,7 +34,7 @@ * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 - * and more readibility. + * and more readability. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. @@ -62,6 +63,7 @@ #include <linux/stat.h> #include <linux/init.h> +#include <net/flow.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> @@ -72,14 +74,17 @@ #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> +#include <net/gso.h> #include <net/inetpeer.h> #include <net/lwtunnel.h> +#include <net/inet_dscp.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> +#include <net/psp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, @@ -98,7 +103,9 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); - iph->tot_len = htons(skb->len); + IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); + + iph_set_totlen(iph, skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the @@ -111,7 +118,7 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, - net, sk, skb, NULL, skb_dst(skb)->dev, + net, sk, skb, NULL, skb_dst_dev(skb), dst_output); } @@ -127,9 +134,10 @@ int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ip_local_out); -static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) +static inline int ip_select_ttl(const struct inet_sock *inet, + const struct dst_entry *dst) { - int ttl = inet->uc_ttl; + int ttl = READ_ONCE(inet->uc_ttl); if (ttl < 0) ttl = ip4_dst_hoplimit(dst); @@ -141,9 +149,10 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, - __be32 saddr, __be32 daddr, struct ip_options_rcu *opt) + __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, + u8 tos) { - struct inet_sock *inet = inet_sk(sk); + const struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; @@ -154,27 +163,34 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; - iph->tos = inet->tos; + iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - if (ip_dont_fragment(sk, &rt->dst)) { + /* Do not bother generating IPID for small packets (eg SYNACK) */ + if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; - __ip_select_ident(net, iph, 1); + /* TCP packets here are SYNACK with fat IPv4/TCP options. + * Avoid using the hashed IP ident generator. + */ + if (sk->sk_protocol == IPPROTO_TCP) + iph->id = (__force __be16)get_random_u16(); + else + __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; - ip_options_build(skb, &opt->opt, daddr, rt, 0); + ip_options_build(skb, &opt->opt, daddr, rt); } - skb->priority = sk->sk_priority; + skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) - skb->mark = sk->sk_mark; + skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); @@ -184,66 +200,57 @@ EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct rtable *rt = (struct rtable *)dst; - struct net_device *dev = dst->dev; + struct rtable *rt = dst_rtable(dst); + struct net_device *dev = dst_dev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; - u32 nexthop; + bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); - /* Be paranoid, rather than too clever. */ - if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { - struct sk_buff *skb2; + /* OUTOCTETS should be counted after fragment */ + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); - skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev)); - if (!skb2) { - kfree_skb(skb); + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + skb = skb_expand_head(skb, hh_len); + if (!skb) return -ENOMEM; - } - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - consume_skb(skb); - skb = skb2; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } - rcu_read_lock_bh(); - nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr); - neigh = __ipv4_neigh_lookup_noref(dev, nexthop); - if (unlikely(!neigh)) - neigh = __neigh_create(&arp_tbl, &nexthop, dev, false); + rcu_read_lock(); + neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); - res = neigh_output(neigh, skb); - - rcu_read_unlock_bh(); + /* if crossing protocols, can not use the cached header */ + res = neigh_output(neigh, skb, is_v6gw); + rcu_read_unlock(); return res; } - rcu_read_unlock_bh(); + rcu_read_unlock(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); - kfree_skb(skb); - return -EINVAL; + kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); + return PTR_ERR(neigh); } static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { + struct sk_buff *segs, *nskb; netdev_features_t features; - struct sk_buff *segs; int ret = 0; /* common case: seglen is <= mtu @@ -262,10 +269,10 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an - * insufficent MTU. + * insufficient MTU. */ features = netif_skb_features(skb); - BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); @@ -274,8 +281,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, consume_skb(skb); - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); @@ -283,22 +289,14 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, if (err && ret == 0) ret = err; - segs = nskb; - } while (segs); + } return ret; } -static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) +static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; - int ret; - - ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); - if (ret) { - kfree_skb(skb); - return ret; - } #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ @@ -311,24 +309,60 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); - if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) + if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } +static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + int ret; + + ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); + switch (ret) { + case NET_XMIT_SUCCESS: + return __ip_finish_output(net, sk, skb); + case NET_XMIT_CN: + return __ip_finish_output(net, sk, skb) ? : ret; + default: + kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); + return ret; + } +} + static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - int ret; + struct rtable *new_rt; + bool do_cn = false; + int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); - if (ret) { - kfree_skb(skb); + switch (ret) { + case NET_XMIT_CN: + do_cn = true; + fallthrough; + case NET_XMIT_SUCCESS: + break; + default: + kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } - return dev_loopback_xmit(net, sk, skb); + /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting + * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, + * see ipv4_pktinfo_prepare(). + */ + new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); + if (new_rt) { + new_rt->rt_iif = 0; + skb_dst_drop(skb); + skb_dst_set(skb, &new_rt->dst); + } + + err = dev_loopback_xmit(net, sk, skb); + return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -339,8 +373,6 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) /* * If the indicated interface is up and running, send the packet. */ - IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); - skb->dev = dev; skb->protocol = htons(ETH_P_IP); @@ -395,18 +427,22 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev; - - IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); + struct net_device *dev, *indev = skb->dev; + int ret_val; + rcu_read_lock(); + dev = skb_dst_dev_rcu(skb); skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, NULL, dev, - ip_finish_output, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + ret_val = NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, skb, indev, dev, + ip_finish_output, + !(IPCB(skb)->flags & IPSKB_REROUTED)); + rcu_read_unlock(); + return ret_val; } +EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores @@ -418,8 +454,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); - memcpy(&iph->saddr, &fl4->saddr, - sizeof(fl4->saddr) + sizeof(fl4->daddr)); + + iph->saddr = fl4->saddr; + iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ @@ -445,26 +482,18 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, goto packet_routed; /* Make sure we can route this packet. */ - rt = (struct rtable *)__sk_dst_check(sk, 0); + rt = dst_rtable(__sk_dst_check(sk, 0)); if (!rt) { - __be32 daddr; + inet_sk_init_flowi4(inet, fl4); - /* Use correct destination address if we have options. */ - daddr = inet->inet_daddr; - if (inet_opt && inet_opt->opt.srr) - daddr = inet_opt->opt.faddr; + /* sctp_v4_xmit() uses its own DSCP value */ + fl4->flowi4_dscp = inet_dsfield_to_dscp(tos); /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ - rt = ip_route_output_ports(net, fl4, sk, - daddr, inet->inet_saddr, - inet->inet_dport, - inet->inet_sport, - sk->sk_protocol, - RT_CONN_FLAGS_TOS(sk, tos), - sk->sk_bound_dev_if); + rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); @@ -492,15 +521,15 @@ packet_routed: if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; - ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); + ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ - skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->priority = READ_ONCE(sk->sk_priority); + skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); @@ -509,16 +538,23 @@ packet_routed: no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_IP_OUTNOROUTES); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); +int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) +{ + return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos)); +} +EXPORT_SYMBOL(ip_queue_xmit); + static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; + to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; @@ -526,9 +562,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) skb_copy_hash(to, from); - /* Copy the flags to each fragment. */ - IPCB(to)->flags = IPCB(from)->flags; - #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif @@ -562,6 +595,162 @@ static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return ip_do_fragment(net, sk, skb, output); } +void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, + unsigned int hlen, struct ip_fraglist_iter *iter) +{ + unsigned int first_len = skb_pagelen(skb); + + iter->frag = skb_shinfo(skb)->frag_list; + skb_frag_list_init(skb); + + iter->offset = 0; + iter->iph = iph; + iter->hlen = hlen; + + skb->data_len = first_len - skb_headlen(skb); + skb->len = first_len; + iph->tot_len = htons(first_len); + iph->frag_off = htons(IP_MF); + ip_send_check(iph); +} +EXPORT_SYMBOL(ip_fraglist_init); + +void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) +{ + unsigned int hlen = iter->hlen; + struct iphdr *iph = iter->iph; + struct sk_buff *frag; + + frag = iter->frag; + frag->ip_summed = CHECKSUM_NONE; + skb_reset_transport_header(frag); + __skb_push(frag, hlen); + skb_reset_network_header(frag); + memcpy(skb_network_header(frag), iph, hlen); + iter->iph = ip_hdr(frag); + iph = iter->iph; + iph->tot_len = htons(frag->len); + ip_copy_metadata(frag, skb); + iter->offset += skb->len - hlen; + iph->frag_off = htons(iter->offset >> 3); + if (frag->next) + iph->frag_off |= htons(IP_MF); + /* Ready, complete checksum */ + ip_send_check(iph); +} +EXPORT_SYMBOL(ip_fraglist_prepare); + +void ip_frag_init(struct sk_buff *skb, unsigned int hlen, + unsigned int ll_rs, unsigned int mtu, bool DF, + struct ip_frag_state *state) +{ + struct iphdr *iph = ip_hdr(skb); + + state->DF = DF; + state->hlen = hlen; + state->ll_rs = ll_rs; + state->mtu = mtu; + + state->left = skb->len - hlen; /* Space per frame */ + state->ptr = hlen; /* Where to start from */ + + state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; + state->not_last_frag = iph->frag_off & htons(IP_MF); +} +EXPORT_SYMBOL(ip_frag_init); + +static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, + bool first_frag) +{ + /* Copy the flags to each fragment. */ + IPCB(to)->flags = IPCB(from)->flags; + + /* ANK: dirty, but effective trick. Upgrade options only if + * the segment to be fragmented was THE FIRST (otherwise, + * options are already fixed) and make it ONCE + * on the initial skb, so that all the following fragments + * will inherit fixed options. + */ + if (first_frag) + ip_options_fragment(from); +} + +struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) +{ + unsigned int len = state->left; + struct sk_buff *skb2; + struct iphdr *iph; + + /* IF: it doesn't fit, use 'mtu' - the data space left */ + if (len > state->mtu) + len = state->mtu; + /* IF: we are not sending up to and including the packet end + then align the next start on an eight byte boundary */ + if (len < state->left) { + len &= ~7; + } + + /* Allocate buffer */ + skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); + if (!skb2) + return ERR_PTR(-ENOMEM); + + /* + * Set up data on packet + */ + + ip_copy_metadata(skb2, skb); + skb_reserve(skb2, state->ll_rs); + skb_put(skb2, len + state->hlen); + skb_reset_network_header(skb2); + skb2->transport_header = skb2->network_header + state->hlen; + + /* + * Charge the memory for the fragment to any owner + * it might possess + */ + + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + + /* + * Copy the packet header into the new buffer. + */ + + skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); + + /* + * Copy a block of the IP datagram. + */ + if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) + BUG(); + state->left -= len; + + /* + * Fill in the new header fields. + */ + iph = ip_hdr(skb2); + iph->frag_off = htons((state->offset >> 3)); + if (state->DF) + iph->frag_off |= htons(IP_DF); + + /* + * Added AC : If we are fragmenting a fragment that's not the + * last fragment then keep MF on each bit + */ + if (state->left > 0 || state->not_last_frag) + iph->frag_off |= htons(IP_MF); + state->ptr += len; + state->offset += len; + + iph->tot_len = htons(len + state->hlen); + + ip_send_check(iph); + + return skb2; +} +EXPORT_SYMBOL(ip_frag_next); + /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus @@ -573,12 +762,13 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; - int ptr; struct sk_buff *skb2; - unsigned int mtu, hlen, left, len, ll_rs; - int offset; - __be16 not_last_frag; + u8 tstamp_type = skb->tstamp_type; struct rtable *rt = skb_rtable(skb); + unsigned int mtu, hlen, ll_rs; + struct ip_fraglist_iter iter; + ktime_t tstamp = skb->tstamp; + struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ @@ -643,49 +833,37 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, } /* Everything is OK. Generate! */ - - err = 0; - offset = 0; - frag = skb_shinfo(skb)->frag_list; - skb_frag_list_init(skb); - skb->data_len = first_len - skb_headlen(skb); - skb->len = first_len; - iph->tot_len = htons(first_len); - iph->frag_off = htons(IP_MF); - ip_send_check(iph); + ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ - if (frag) { - frag->ip_summed = CHECKSUM_NONE; - skb_reset_transport_header(frag); - __skb_push(frag, hlen); - skb_reset_network_header(frag); - memcpy(skb_network_header(frag), iph, hlen); - iph = ip_hdr(frag); - iph->tot_len = htons(frag->len); - ip_copy_metadata(frag, skb); - if (offset == 0) - ip_options_fragment(frag); - offset += skb->len - hlen; - iph->frag_off = htons(offset>>3); - if (frag->next) - iph->frag_off |= htons(IP_MF); - /* Ready, complete checksum */ - ip_send_check(iph); + if (iter.frag) { + bool first_frag = (iter.offset == 0); + + IPCB(iter.frag)->flags = IPCB(skb)->flags; + ip_fraglist_prepare(skb, &iter); + if (first_frag && IPCB(skb)->opt.optlen) { + /* ipcb->opt is not populated for frags + * coming from __ip_make_skb(), + * ip_options_fragment() needs optlen + */ + IPCB(iter.frag)->opt.optlen = + IPCB(skb)->opt.optlen; + ip_options_fragment(iter.frag); + ip_send_check(iter.iph); + } } + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); - if (err || !frag) + if (err || !iter.frag) break; - skb = frag; - frag = skb->next; - skb_mark_not_on_list(skb); + skb = ip_fraglist_next(&iter); } if (err == 0) { @@ -693,11 +871,8 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, return 0; } - while (frag) { - skb = frag->next; - kfree_skb(frag); - frag = skb; - } + kfree_skb_list(iter.frag); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; @@ -712,105 +887,31 @@ slow_path_clean: } slow_path: - iph = ip_hdr(skb); - - left = skb->len - hlen; /* Space per frame */ - ptr = hlen; /* Where to start from */ - /* * Fragment the datagram. */ - offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; - not_last_frag = iph->frag_off & htons(IP_MF); + ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, + &state); /* * Keep copying data until we run out. */ - while (left > 0) { - len = left; - /* IF: it doesn't fit, use 'mtu' - the data space left */ - if (len > mtu) - len = mtu; - /* IF: we are not sending up to and including the packet end - then align the next start on an eight byte boundary */ - if (len < left) { - len &= ~7; - } + while (state.left > 0) { + bool first_frag = (state.offset == 0); - /* Allocate buffer */ - skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC); - if (!skb2) { - err = -ENOMEM; + skb2 = ip_frag_next(skb, &state); + if (IS_ERR(skb2)) { + err = PTR_ERR(skb2); goto fail; } - - /* - * Set up data on packet - */ - - ip_copy_metadata(skb2, skb); - skb_reserve(skb2, ll_rs); - skb_put(skb2, len + hlen); - skb_reset_network_header(skb2); - skb2->transport_header = skb2->network_header + hlen; - - /* - * Charge the memory for the fragment to any owner - * it might possess - */ - - if (skb->sk) - skb_set_owner_w(skb2, skb->sk); - - /* - * Copy the packet header into the new buffer. - */ - - skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen); - - /* - * Copy a block of the IP datagram. - */ - if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len)) - BUG(); - left -= len; - - /* - * Fill in the new header fields. - */ - iph = ip_hdr(skb2); - iph->frag_off = htons((offset >> 3)); - - if (IPCB(skb)->flags & IPSKB_FRAG_PMTU) - iph->frag_off |= htons(IP_DF); - - /* ANK: dirty, but effective trick. Upgrade options only if - * the segment to be fragmented was THE FIRST (otherwise, - * options are already fixed) and make it ONCE - * on the initial skb, so that all the following fragments - * will inherit fixed options. - */ - if (offset == 0) - ip_options_fragment(skb); - - /* - * Added AC : If we are fragmenting a fragment that's not the - * last fragment then keep MF on each bit - */ - if (left > 0 || not_last_frag) - iph->frag_off |= htons(IP_MF); - ptr += len; - offset += len; + ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. */ - iph->tot_len = htons(len + hlen); - - ip_send_check(iph); - + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, skb2); if (err) goto fail; @@ -846,17 +947,6 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk } EXPORT_SYMBOL(ip_generic_getfrag); -static inline __wsum -csum_page(struct page *page, int offset, int copy) -{ - char *kaddr; - __wsum csum; - kaddr = kmap(page); - csum = csum_partial(kaddr + offset, copy, 0); - kunmap(page); - return csum; -} - static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, @@ -870,7 +960,6 @@ static int __ip_append_data(struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; - struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; @@ -878,11 +967,12 @@ static int __ip_append_data(struct sock *sk, int copy; int err; int offset = 0; + bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; - struct rtable *rt = (struct rtable *)cork->dst; + struct rtable *rt = dst_rtable(cork->dst); + bool paged, hold_tskey = false, extra_uref = false; unsigned int wmem_alloc_delta = 0; - bool paged, extra_uref; u32 tskey = 0; skb = skb_peek_tail(queue); @@ -891,15 +981,11 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) - tskey = sk->sk_tskey++; - hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; + maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -918,22 +1004,60 @@ static int __ip_append_data(struct sock *sk, (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; - if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb)); - if (!uarg) - return -ENOBUFS; - extra_uref = true; + if ((flags & MSG_ZEROCOPY) && length) { + struct msghdr *msg = from; + + if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { + if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) + return -EINVAL; + + /* Leave uarg NULL if can't zerocopy, callers should + * be able to handle it. + */ + if ((rt->dst.dev->features & NETIF_F_SG) && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + uarg = msg->msg_ubuf; + } + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb), + false); + if (!uarg) + return -ENOBUFS; + extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ + if (rt->dst.dev->features & NETIF_F_SG && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + } else { + uarg_to_msgzc(uarg)->zerocopy = 0; + skb_zcopy_set(skb, uarg, &extra_uref); + } + } + } else if ((flags & MSG_SPLICE_PAGES) && length) { + if (inet_test_bit(HDRINCL, sk)) + return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && - csummode == CHECKSUM_PARTIAL) { + getfrag == ip_generic_getfrag) + /* We need an empty buffer to attach stuff to */ paged = true; - } else { - uarg->zerocopy = 0; - skb_zcopy_set(skb, uarg, &extra_uref); - } + else + flags &= ~MSG_SPLICE_PAGES; } cork->length += length; + if (cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { + if (cork->flags & IPCORK_TS_OPT_ID) { + tskey = cork->ts_opt_id; + } else { + tskey = atomic_inc_return(&sk->sk_tskey) - 1; + hold_tskey = true; + } + } + /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, @@ -954,7 +1078,7 @@ static int __ip_append_data(struct sock *sk, unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: @@ -974,17 +1098,8 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; - if ((flags & MSG_MORE) && - !(rt->dst.dev->features&NETIF_F_SG)) - alloclen = mtu; - else if (!paged) - alloclen = fraglen; - else { - alloclen = min_t(int, fraglen, MAX_HEADER); - pagedlen = fraglen - alloclen; - } - - alloclen += exthdrlen; + alloc_extra = hh_len + 15; + alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, @@ -992,17 +1107,30 @@ alloc_new_skb: * the last. */ if (datalen == length + fraggap) - alloclen += rt->dst.trailer_len; + alloc_extra += rt->dst.trailer_len; + + if ((flags & MSG_MORE) && + !(rt->dst.dev->features&NETIF_F_SG)) + alloclen = mtu; + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) + alloclen = fraglen; + else { + alloclen = fragheaderlen + transhdrlen; + pagedlen = datalen - transhdrlen; + } + + alloclen += alloc_extra; if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len + 15, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len + 15, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; @@ -1029,7 +1157,7 @@ alloc_new_skb: if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, - data + transhdrlen, fraggap, 0); + data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; @@ -1037,10 +1165,18 @@ alloc_new_skb: } copy = datalen - transhdrlen - fraggap - pagedlen; - if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { + /* [!] NOTE: copy will be negative if pagedlen>0 + * because then the equation reduces to -fraggap. + */ + if (copy > 0 && + INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, data + transhdrlen, offset, + copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; + } else if (flags & MSG_SPLICE_PAGES) { + copy = 0; } offset += copy; @@ -1079,19 +1215,33 @@ alloc_new_skb: unsigned int off; off = skb->len; - if (getfrag(from, skb_put(skb, copy), - offset, copy, off, skb) < 0) { + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, skb_put(skb, copy), + offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } - } else if (!uarg || !uarg->zerocopy) { + } else if (flags & MSG_SPLICE_PAGES) { + struct msghdr *msg = from; + + err = -EIO; + if (WARN_ON_ONCE(copy > msg->msg_iter.count)) + goto error; + + err = skb_splice_from_iter(skb, &msg->msg_iter, copy); + if (err < 0) + goto error; + copy = err; + wmem_alloc_delta += copy; + } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; + skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; @@ -1104,16 +1254,15 @@ alloc_new_skb: get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); - if (getfrag(from, + if (INDIRECT_CALL_1(getfrag, ip_generic_getfrag, + from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; + skb_len_add(skb, copy); wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); @@ -1131,11 +1280,12 @@ alloc_new_skb: error_efault: err = -EFAULT; error: - if (uarg) - sock_zerocopy_put_abort(uarg, extra_uref); + net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); + if (hold_tskey) + atomic_dec(&sk->sk_tskey); return err; } @@ -1149,6 +1299,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(!rt)) return -EFAULT; + cork->fragsize = ip_sk_use_pmtu(sk) ? + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + /* * setup for corking. */ @@ -1165,31 +1321,33 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; - cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; - cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; - cork->priority = ipc->priority; + cork->mark = ipc->sockc.mark; + cork->priority = ipc->sockc.priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; - sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); + sock_tx_timestamp(sk, &ipc->sockc, &cork->tx_flags); + if (ipc->sockc.tsflags & SOCKCM_FLAG_TS_OPT_ID) { + cork->flags |= IPCORK_TS_OPT_ID; + cork->ts_opt_id = ipc->sockc.ts_opt_id; + } return 0; } /* - * ip_append_data() and ip_append_page() can make one large IP datagram - * from many pieces of data. Each pieces will be holded on the socket - * until ip_push_pending_frames() is called. Each piece can be a page - * or non-page data. + * ip_append_data() can make one large IP datagram from many pieces of + * data. Each piece will be held on the socket until + * ip_push_pending_frames() is called. Each piece can be a page or + * non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. @@ -1222,136 +1380,6 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4, from, length, transhdrlen, flags); } -ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, - int offset, size_t size, int flags) -{ - struct inet_sock *inet = inet_sk(sk); - struct sk_buff *skb; - struct rtable *rt; - struct ip_options *opt = NULL; - struct inet_cork *cork; - int hh_len; - int mtu; - int len; - int err; - unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize; - - if (inet->hdrincl) - return -EPERM; - - if (flags&MSG_PROBE) - return 0; - - if (skb_queue_empty(&sk->sk_write_queue)) - return -EINVAL; - - cork = &inet->cork.base; - rt = (struct rtable *)cork->dst; - if (cork->flags & IPCORK_OPT) - opt = cork->opt; - - if (!(rt->dst.dev->features&NETIF_F_SG)) - return -EOPNOTSUPP; - - hh_len = LL_RESERVED_SPACE(rt->dst.dev); - mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; - - fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; - - if (cork->length + size > maxnonfragsize - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, - mtu - (opt ? opt->optlen : 0)); - return -EMSGSIZE; - } - - skb = skb_peek_tail(&sk->sk_write_queue); - if (!skb) - return -EINVAL; - - cork->length += size; - - while (size > 0) { - /* Check if the remaining data fits into current packet. */ - len = mtu - skb->len; - if (len < size) - len = maxfraglen - skb->len; - - if (len <= 0) { - struct sk_buff *skb_prev; - int alloclen; - - skb_prev = skb; - fraggap = skb_prev->len - maxfraglen; - - alloclen = fragheaderlen + hh_len + fraggap + 15; - skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation); - if (unlikely(!skb)) { - err = -ENOBUFS; - goto error; - } - - /* - * Fill in the control structures - */ - skb->ip_summed = CHECKSUM_NONE; - skb->csum = 0; - skb_reserve(skb, hh_len); - - /* - * Find where to start putting bytes. - */ - skb_put(skb, fragheaderlen + fraggap); - skb_reset_network_header(skb); - skb->transport_header = (skb->network_header + - fragheaderlen); - if (fraggap) { - skb->csum = skb_copy_and_csum_bits(skb_prev, - maxfraglen, - skb_transport_header(skb), - fraggap, 0); - skb_prev->csum = csum_sub(skb_prev->csum, - skb->csum); - pskb_trim_unique(skb_prev, maxfraglen); - } - - /* - * Put the packet on the pending queue. - */ - __skb_queue_tail(&sk->sk_write_queue, skb); - continue; - } - - if (len > size) - len = size; - - if (skb_append_pagefrags(skb, page, offset, len)) { - err = -EMSGSIZE; - goto error; - } - - if (skb->ip_summed == CHECKSUM_NONE) { - __wsum csum; - csum = csum_page(page, offset, len); - skb->csum = csum_block_add(skb->csum, csum, skb->len); - } - - skb->len += len; - skb->data_len += len; - skb->truesize += len; - refcount_add(len, &sk->sk_wmem_alloc); - offset += len; - size -= len; - } - return 0; - -error: - cork->length -= size; - IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); - return err; -} - static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; @@ -1375,10 +1403,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; - struct rtable *rt = (struct rtable *)cork->dst; + struct rtable *rt = dst_rtable(cork->dst); struct iphdr *iph; + u8 pmtudisc, ttl; __be16 df = 0; - __u8 ttl; skb = __skb_dequeue(queue); if (!skb) @@ -1408,8 +1436,9 @@ struct sk_buff *__ip_make_skb(struct sock *sk, /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ - if (inet->pmtudisc == IP_PMTUDISC_DO || - inet->pmtudisc == IP_PMTUDISC_PROBE || + pmtudisc = READ_ONCE(inet->pmtudisc); + if (pmtudisc == IP_PMTUDISC_DO || + pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); @@ -1420,14 +1449,14 @@ struct sk_buff *__ip_make_skb(struct sock *sk, if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) - ttl = inet->mc_ttl; + ttl = READ_ONCE(inet->mc_ttl); else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; - iph->tos = (cork->tos != -1) ? cork->tos : inet->tos; + iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos); iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; @@ -1435,13 +1464,16 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_select_ident(net, skb, sk); if (opt) { - iph->ihl += opt->optlen>>2; - ip_options_build(skb, opt, cork->addr, rt, 0); + iph->ihl += opt->optlen >> 2; + ip_options_build(skb, opt, cork->addr, rt); } - skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; - skb->mark = sk->sk_mark; - skb->tstamp = cork->transmit_time; + skb->priority = cork->priority; + skb->mark = cork->mark; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid); /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount @@ -1449,9 +1481,20 @@ struct sk_buff *__ip_make_skb(struct sock *sk, cork->dst = NULL; skb_dst_set(skb, &rt->dst); - if (iph->protocol == IPPROTO_ICMP) - icmp_out_count(net, ((struct icmphdr *) - skb_transport_header(skb))->type); + if (iph->protocol == IPPROTO_ICMP) { + u8 icmp_type; + + /* For such sockets, transhdrlen is zero when do ip_append_data(), + * so icmphdr does not in skb linear region and can not get icmp_type + * by icmp_hdr(skb)->type. + */ + if (sk->sk_type == SOCK_RAW && + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) + icmp_type = fl4->fl4_icmp_type; + else + icmp_type = icmp_hdr(skb)->type; + icmp_out_count(net, icmp_type); + } ip_cork_release(cork); out: @@ -1547,7 +1590,7 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, { __wsum csum; - csum = csum_partial_copy_nocheck(dptr+offset, to, len, 0); + csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } @@ -1556,11 +1599,12 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset, * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ -void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, +void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk, + struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len) + unsigned int len, u64 transmit_time, u32 txhash) { struct ip_options_data replyopts; struct ipcm_cookie ipc; @@ -1576,6 +1620,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, ipcm_init(&ipc); ipc.addr = daddr; + ipc.sockc.transmit_time = transmit_time; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; @@ -1590,24 +1635,23 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, - RT_TOS(arg->tos), + arg->tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); - security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); - rt = ip_route_output_key(net, &fl4); + security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); + rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; inet_sk(sk)->tos = arg->tos; - sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; - sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_mark = fl4.flowi4_mark; + sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); + ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { @@ -1622,6 +1666,14 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; + if (orig_sk) { + skb_set_owner_edemux(nskb, (struct sock *)orig_sk); + psp_reply_set_decrypted(orig_sk, nskb); + } + if (transmit_time) + nskb->tstamp_type = SKB_CLOCK_MONOTONIC; + if (txhash) + skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); } out: |