diff options
Diffstat (limited to 'net/ipv4/udp_offload.c')
| -rw-r--r-- | net/ipv4/udp_offload.c | 556 |
1 files changed, 498 insertions, 58 deletions
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 64f9715173ac..19d0b5b09ffa 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -1,19 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * UDPv4 GSO support */ #include <linux/skbuff.h> +#include <net/gro.h> +#include <net/gso.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> +#include <net/udp_tunnel.h> + +#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) + +/* + * Dummy GRO tunnel callback, exists mainly to avoid dangling/NULL + * values for the udp tunnel static call. + */ +static struct sk_buff *dummy_gro_rcv(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->flush = 1; + return NULL; +} + +typedef struct sk_buff *(*udp_tunnel_gro_rcv_t)(struct sock *sk, + struct list_head *head, + struct sk_buff *skb); + +struct udp_tunnel_type_entry { + udp_tunnel_gro_rcv_t gro_receive; + refcount_t count; +}; + +#define UDP_MAX_TUNNEL_TYPES (IS_ENABLED(CONFIG_GENEVE) + \ + IS_ENABLED(CONFIG_VXLAN) * 2 + \ + IS_ENABLED(CONFIG_NET_FOU) * 2 + \ + IS_ENABLED(CONFIG_XFRM) * 2) + +DEFINE_STATIC_CALL(udp_tunnel_gro_rcv, dummy_gro_rcv); +static DEFINE_STATIC_KEY_FALSE(udp_tunnel_static_call); +static DEFINE_MUTEX(udp_tunnel_gro_type_lock); +static struct udp_tunnel_type_entry udp_tunnel_gro_types[UDP_MAX_TUNNEL_TYPES]; +static unsigned int udp_tunnel_gro_type_nr; +static DEFINE_SPINLOCK(udp_tunnel_gro_lock); + +void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add) +{ + bool is_ipv6 = sk->sk_family == AF_INET6; + struct udp_sock *tup, *up = udp_sk(sk); + struct udp_tunnel_gro *udp_tunnel_gro; + + spin_lock(&udp_tunnel_gro_lock); + udp_tunnel_gro = &net->ipv4.udp_tunnel_gro[is_ipv6]; + if (add) + hlist_add_head(&up->tunnel_list, &udp_tunnel_gro->list); + else if (up->tunnel_list.pprev) + hlist_del_init(&up->tunnel_list); + + if (udp_tunnel_gro->list.first && + !udp_tunnel_gro->list.first->next) { + tup = hlist_entry(udp_tunnel_gro->list.first, struct udp_sock, + tunnel_list); + + rcu_assign_pointer(udp_tunnel_gro->sk, (struct sock *)tup); + } else { + RCU_INIT_POINTER(udp_tunnel_gro->sk, NULL); + } + + spin_unlock(&udp_tunnel_gro_lock); +} +EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_lookup); + +void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) +{ + struct udp_tunnel_type_entry *cur = NULL; + struct udp_sock *up = udp_sk(sk); + int i, old_gro_type_nr; + + if (!UDP_MAX_TUNNEL_TYPES || !up->gro_receive) + return; + + mutex_lock(&udp_tunnel_gro_type_lock); + + /* Check if the static call is permanently disabled. */ + if (udp_tunnel_gro_type_nr > UDP_MAX_TUNNEL_TYPES) + goto out; + + for (i = 0; i < udp_tunnel_gro_type_nr; i++) + if (udp_tunnel_gro_types[i].gro_receive == up->gro_receive) + cur = &udp_tunnel_gro_types[i]; + + old_gro_type_nr = udp_tunnel_gro_type_nr; + if (add) { + /* + * Update the matching entry, if found, or add a new one + * if needed + */ + if (cur) { + refcount_inc(&cur->count); + goto out; + } + + if (unlikely(udp_tunnel_gro_type_nr == UDP_MAX_TUNNEL_TYPES)) { + pr_err_once("Too many UDP tunnel types, please increase UDP_MAX_TUNNEL_TYPES\n"); + /* Ensure static call will never be enabled */ + udp_tunnel_gro_type_nr = UDP_MAX_TUNNEL_TYPES + 1; + } else { + cur = &udp_tunnel_gro_types[udp_tunnel_gro_type_nr++]; + refcount_set(&cur->count, 1); + cur->gro_receive = up->gro_receive; + } + } else { + /* + * The stack cleanups only successfully added tunnel, the + * lookup on removal should never fail. + */ + if (WARN_ON_ONCE(!cur)) + goto out; + + if (!refcount_dec_and_test(&cur->count)) + goto out; + + /* Avoid gaps, so that the enable tunnel has always id 0 */ + *cur = udp_tunnel_gro_types[--udp_tunnel_gro_type_nr]; + } + + if (udp_tunnel_gro_type_nr == 1) { + static_call_update(udp_tunnel_gro_rcv, + udp_tunnel_gro_types[0].gro_receive); + static_branch_enable(&udp_tunnel_static_call); + } else if (old_gro_type_nr == 1) { + static_branch_disable(&udp_tunnel_static_call); + static_call_update(udp_tunnel_gro_rcv, dummy_gro_rcv); + } + +out: + mutex_unlock(&udp_tunnel_gro_type_lock); +} +EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_rcv); + +static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + if (static_branch_likely(&udp_tunnel_static_call)) { + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + return static_call(udp_tunnel_gro_rcv)(sk, head, skb); + } + return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); +} + +#else + +static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); +} + +#endif static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, @@ -53,6 +207,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; @@ -62,7 +217,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; - need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && @@ -71,6 +226,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; + if (need_csum) + features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and @@ -153,8 +310,8 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { + const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; - const struct net_offload **offloads; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, @@ -188,8 +345,140 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); +static void __udpv4_gso_segment_csum(struct sk_buff *seg, + __be32 *oldip, __be32 *newip, + __be16 *oldport, __be16 *newport) +{ + struct udphdr *uh; + struct iphdr *iph; + + if (*oldip == *newip && *oldport == *newport) + return; + + uh = udp_hdr(seg); + iph = ip_hdr(seg); + + if (uh->check) { + inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, + true); + inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, + false); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + *oldport = *newport; + + csum_replace4(&iph->check, *oldip, *newip); + *oldip = *newip; +} + +static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) +{ + struct sk_buff *seg; + struct udphdr *uh, *uh2; + struct iphdr *iph, *iph2; + + seg = segs; + uh = udp_hdr(seg); + iph = ip_hdr(seg); + + if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && + (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && + (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && + (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) + return segs; + + while ((seg = seg->next)) { + uh2 = udp_hdr(seg); + iph2 = ip_hdr(seg); + + __udpv4_gso_segment_csum(seg, + &iph2->saddr, &iph->saddr, + &uh2->source, &uh->source); + __udpv4_gso_segment_csum(seg, + &iph2->daddr, &iph->daddr, + &uh2->dest, &uh->dest); + } + + return segs; +} + +static void __udpv6_gso_segment_csum(struct sk_buff *seg, + struct in6_addr *oldip, + const struct in6_addr *newip, + __be16 *oldport, __be16 newport) +{ + struct udphdr *uh = udp_hdr(seg); + + if (ipv6_addr_equal(oldip, newip) && *oldport == newport) + return; + + if (uh->check) { + inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32, + newip->s6_addr32, true); + + inet_proto_csum_replace2(&uh->check, seg, *oldport, newport, + false); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + + *oldip = *newip; + *oldport = newport; +} + +static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs) +{ + const struct ipv6hdr *iph; + const struct udphdr *uh; + struct ipv6hdr *iph2; + struct sk_buff *seg; + struct udphdr *uh2; + + seg = segs; + uh = udp_hdr(seg); + iph = ipv6_hdr(seg); + uh2 = udp_hdr(seg->next); + iph2 = ipv6_hdr(seg->next); + + if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) && + ipv6_addr_equal(&iph->saddr, &iph2->saddr) && + ipv6_addr_equal(&iph->daddr, &iph2->daddr)) + return segs; + + while ((seg = seg->next)) { + uh2 = udp_hdr(seg); + iph2 = ipv6_hdr(seg); + + __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, + &uh2->source, uh->source); + __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, + &uh2->dest, uh->dest); + } + + return segs; +} + +static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, + netdev_features_t features, + bool is_ipv6) +{ + unsigned int mss = skb_shinfo(skb)->gso_size; + + skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); + if (IS_ERR(skb)) + return skb; + + udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); + + if (is_ipv6) + return __udpv6_gso_segment_list_csum(skb); + else + return __udpv4_gso_segment_list_csum(skb); +} + struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, - netdev_features_t features) + netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; @@ -199,22 +488,70 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, bool copy_dtor; __sum16 check; __be16 newlen; + int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) + return ERR_PTR(-EINVAL); + + /* We don't know if egress device can segment and checksum the packet + * when IPv6 extension headers are present. Fall back to software GSO. + */ + if (gso_skb->ip_summed != CHECKSUM_PARTIAL) + features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); + + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), + mss); + return NULL; + } + + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { + /* Detect modified geometry and pass those to skb_segment. */ + if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + + ret = __skb_linearize(gso_skb); + if (ret) + return ERR_PTR(ret); + + /* Setup csum, as fraglist skips this in udp4_gro_receive. */ + gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; + gso_skb->csum_offset = offsetof(struct udphdr, check); + gso_skb->ip_summed = CHECKSUM_PARTIAL; + + uh = udp_hdr(gso_skb); + if (is_ipv6) + uh->check = ~udp_v6_check(gso_skb->len, + &ipv6_hdr(gso_skb)->saddr, + &ipv6_hdr(gso_skb)->daddr, 0); + else + uh->check = ~udp_v4_check(gso_skb->len, + ip_hdr(gso_skb)->saddr, + ip_hdr(gso_skb)->daddr, 0); + } + skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; - if (copy_dtor) + if (copy_dtor) { gso_skb->destructor = NULL; + gso_skb->sk = NULL; + } segs = skb_segment(gso_skb, features); - if (unlikely(IS_ERR_OR_NULL(segs))) { - if (copy_dtor) + if (IS_ERR_OR_NULL(segs)) { + if (copy_dtor) { gso_skb->destructor = sock_wfree; + gso_skb->sk = sk; + } return segs; } @@ -228,6 +565,11 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, seg = segs; uh = udp_hdr(seg); + /* preserve TX timestamp flags and TS key for first segment */ + skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey; + skb_shinfo(seg)->tx_flags |= + (skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP); + /* compute checksum adjustment based on old length versus new */ newlen = htons(sizeof(*uh) + mss); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); @@ -268,6 +610,14 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; + /* On the TX path, CHECKSUM_NONE and CHECKSUM_UNNECESSARY have the same + * meaning. However, check for bad offloads in the GSO stack expects the + * latter, if the checksum was calculated in software. To vouch for the + * segment skbs we actually need to set it on the gso_skb. + */ + if (gso_skb->ip_summed == CHECKSUM_NONE) + gso_skb->ip_summed = CHECKSUM_UNNECESSARY; + /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; @@ -307,7 +657,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) - return __udp_gso_segment(skb, features); + return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) @@ -344,14 +694,18 @@ out: return segs; } + #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { - struct udphdr *uh = udp_hdr(skb); + struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; + unsigned int ulen; + int ret = 0; + int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -359,9 +713,14 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return NULL; } + /* Do not deal with padded or malicious packets, sorry ! */ + ulen = ntohs(uh->len); + if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); - skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) @@ -375,14 +734,44 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, continue; } + if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->flush = 1; + return p; + } + + flush = gro_receive_network_flush(uh, uh2, p); + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot - * leading to execessive truesize values + * leading to excessive truesize values. + * On len mismatch merge the first packet shorter than gso_size, + * otherwise complete the GRO packet. */ - if (!skb_gro_receive(p, skb) && - NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) + if (ulen > ntohs(uh2->len) || flush) { pp = p; - else if (uh->len != uh2->len) + } else { + if (NAPI_GRO_CB(skb)->is_flist) { + if (!pskb_may_pull(skb, skb_gro_offset(skb))) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + if ((skb->ip_summed != p->ip_summed) || + (skb->csum_level != p->csum_level)) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + skb_set_network_header(skb, skb_gro_receive_network_offset(skb)); + ret = skb_gro_receive_list(p, skb); + } else { + skb_gro_postpull_rcsum(skb, uh, + sizeof(struct udphdr)); + + ret = skb_gro_receive(p, skb); + } + } + + if (ret || ulen != ntohs(uh2->len) || + NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; return pp; @@ -392,36 +781,44 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return NULL; } -INDIRECT_CALLABLE_DECLARE(struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, - __be16 sport, __be16 dport)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup) + struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; - struct sock *sk; - rcu_read_lock(); - sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, - udp4_lib_lookup_skb, skb, uh->source, uh->dest); - if (!sk) - goto out_unlock; + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. + */ + NAPI_GRO_CB(skb)->is_flist = 0; + if (!sk || !udp_sk(sk)->gro_receive) { + /* If the packet was locally encapsulated in a UDP tunnel that + * wasn't detected above, do not GRO. + */ + if (skb->encapsulation) + goto out; - if (udp_sk(sk)->gro_enabled) { - pp = call_gro_receive(udp_gro_receive_segment, head, skb); - rcu_read_unlock(); - return pp; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) + NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; + + if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || + (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist) + return call_gro_receive(udp_gro_receive_segment, head, skb); + + /* no GRO, be sure flush the current packet */ + goto out; } if (NAPI_GRO_CB(skb)->encap_mark || - (skb->ip_summed != CHECKSUM_PARTIAL && + (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && - !NAPI_GRO_CB(skb)->csum_valid) || - !udp_sk(sk)->gro_receive) - goto out_unlock; + !NAPI_GRO_CB(skb)->csum_valid)) + goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; @@ -446,21 +843,41 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); - pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); + pp = udp_tunnel_gro_rcv(sk, head, skb); -out_unlock: - rcu_read_unlock(); +out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); +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_rcu(skb->dev); + struct sock *sk; + int iif, sdif; + + sk = udp_tunnel_sk(net, false); + if (sk && dport == htons(sk->sk_num)) + return sk; + + inet_get_iif_sdif(skb, &iif, &sdif); + + return __udp4_lib_lookup(net, iph->saddr, sport, + iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; + struct sk_buff *pp; - if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key)) + if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ @@ -471,11 +888,14 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) inet_gro_compute_pseudo)) goto flush; else if (uh->check) - skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: - NAPI_GRO_CB(skb)->is_ipv6 = 0; - return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb); + if (static_branch_unlikely(&udp_encap_needed_key)) + sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); + + pp = udp_gro_receive(head, skb, uh, sk); + return pp; flush: NAPI_GRO_CB(skb)->flush = 1; @@ -492,6 +912,10 @@ static int udp_gro_complete_segment(struct sk_buff *skb) skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; + return 0; } @@ -500,28 +924,31 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, { __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); - int err = -ENOSYS; struct sock *sk; + int err; uh->len = newlen; - rcu_read_lock(); sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); - if (sk && udp_sk(sk)->gro_enabled) { - err = udp_gro_complete_segment(skb); - } else if (sk && udp_sk(sk)->gro_complete) { + if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; + /* clear the encap mark, so that inner frag_list gro_complete + * can take place + */ + NAPI_GRO_CB(skb)->encap_mark = 0; + /* Set encapsulation before calling into inner gro_complete() * functions to make them set up the inner offsets. */ skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); + } else { + err = udp_gro_complete_segment(skb); } - rcu_read_unlock(); if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; @@ -532,9 +959,22 @@ EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); + /* do fraglist only if there is no outer UDP encap (or we already processed it) */ + if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { + uh->len = htons(skb->len - nhoff); + + skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + __skb_incr_checksum_unnecessary(skb); + + return 0; + } + if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); @@ -542,15 +982,15 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } -static const struct net_offload udpv4_offload = { - .callbacks = { - .gso_segment = udp4_ufo_fragment, - .gro_receive = udp4_gro_receive, - .gro_complete = udp4_gro_complete, - }, -}; - int __init udpv4_offload_init(void) { - return inet_add_offload(&udpv4_offload, IPPROTO_UDP); + net_hotdata.udpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp4_ufo_fragment, + .gro_receive = udp4_gro_receive, + .gro_complete = udp4_gro_complete, + }, + }; + + return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } |