From 493c6be3fedfe24aa676949b237b9b104d911abf Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala <sri@us.ibm.com> Date: Thu, 9 Jul 2009 08:09:54 +0000 Subject: udpv6: Fix HW checksum support for outgoing UFO packets - add HW checksum support for outgoing large UDP/IPv6 packets destined for a UFO enabled device. Signed-off-by: Sridhar Samudrala <sri@us.ibm.com> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> --- net/ipv6/udp.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) (limited to 'net/ipv6/udp.c') diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 33b59bd92c4..f31b1b9b0e0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -638,6 +638,47 @@ static void udp_v6_flush_pending_frames(struct sock *sk) } } +/** + * udp6_hwcsum_outgoing - handle outgoing HW checksumming + * @sk: socket we are sending on + * @skb: sk_buff containing the filled-in UDP header + * (checksum field must be zeroed out) + */ +static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, int len) +{ + unsigned int offset; + struct udphdr *uh = udp_hdr(skb); + __wsum csum = 0; + + if (skb_queue_len(&sk->sk_write_queue) == 1) { + /* Only one fragment on the socket. */ + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0); + } else { + /* + * HW-checksum won't work as there are two or more + * fragments on the socket so that all csums of sk_buffs + * should be together + */ + offset = skb_transport_offset(skb); + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + + skb->ip_summed = CHECKSUM_NONE; + + skb_queue_walk(&sk->sk_write_queue, skb) { + csum = csum_add(csum, skb->csum); + } + + uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, + csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } +} + /* * Sending */ @@ -668,7 +709,11 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (is_udplite) csum = udplite_csum_outgoing(sk, skb); - else + else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ + udp6_hwcsum_outgoing(sk, skb, &fl->fl6_src, &fl->fl6_dst, + up->len); + goto send; + } else csum = udp_csum_outgoing(sk, skb); /* add protocol-dependent pseudo-header */ @@ -677,6 +722,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (uh->check == 0) uh->check = CSUM_MANGLED_0; +send: err = ip6_push_pending_frames(sk); out: up->len = 0; -- cgit v1.2.3-70-g09d2 From ba73542585a4a3c8a708f502e62e6e63dd74b66c Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala <sri@us.ibm.com> Date: Thu, 9 Jul 2009 08:10:04 +0000 Subject: udpv6: Handle large incoming UDP/IPv6 packets and support software UFO - validate and forward GSO UDP/IPv6 packets from untrusted sources. - do software UFO if the outgoing device doesn't support UFO. Signed-off-by: Sridhar Samudrala <sri@us.ibm.com> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> --- net/ipv6/af_inet6.c | 20 ++++++++++-- net/ipv6/udp.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 110 insertions(+), 3 deletions(-) (limited to 'net/ipv6/udp.c') diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index caa0278d30a..bf85d5f9703 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -772,6 +772,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; struct inet6_protocol *ops; + int proto; + struct frag_hdr *fptr; + unsigned int unfrag_ip6hlen; + u8 *prevhdr; + int offset = 0; if (!(features & NETIF_F_V6_CSUM)) features &= ~NETIF_F_SG; @@ -791,10 +796,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) __skb_pull(skb, sizeof(*ipv6h)); segs = ERR_PTR(-EPROTONOSUPPORT); + proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); rcu_read_lock(); - ops = rcu_dereference(inet6_protos[ - ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr)]); - + ops = rcu_dereference(inet6_protos[proto]); if (likely(ops && ops->gso_segment)) { skb_reset_transport_header(skb); segs = ops->gso_segment(skb, features); @@ -808,6 +812,16 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) ipv6h = ipv6_hdr(skb); ipv6h->payload_len = htons(skb->len - skb->mac_len - sizeof(*ipv6h)); + if (proto == IPPROTO_UDP) { + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + fptr = (struct frag_hdr *)(skb_network_header(skb) + + unfrag_ip6hlen); + fptr->frag_off = htons(offset); + if (skb->next != NULL) + fptr->frag_off |= htons(IP6_MF); + offset += (ntohs(ipv6h->payload_len) - + sizeof(struct frag_hdr)); + } } out: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f31b1b9b0e0..d79fa672445 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1078,9 +1078,102 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif +static int udp6_ufo_send_check(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h; + struct udphdr *uh; + + if (!pskb_may_pull(skb, sizeof(*uh))) + return -EINVAL; + + ipv6h = ipv6_hdr(skb); + uh = udp_hdr(skb); + + uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len, + IPPROTO_UDP, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + return 0; +} + +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int mss; + unsigned int unfrag_ip6hlen, unfrag_len; + struct frag_hdr *fptr; + u8 *mac_start, *prevhdr; + u8 nexthdr; + u8 frag_hdr_sz = sizeof(struct frag_hdr); + int offset; + __wsum csum; + + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + int type = skb_shinfo(skb)->gso_type; + + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + !(type & (SKB_GSO_UDP)))) + goto out; + + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); + + segs = NULL; + goto out; + } + + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot + * do checksum of UDP packets sent as multiple IP fragments. + */ + offset = skb->csum_start - skb_headroom(skb); + csum = skb_checksum(skb, offset, skb->len- offset, 0); + offset += skb->csum_offset; + *(__sum16 *)(skb->data + offset) = csum_fold(csum); + skb->ip_summed = CHECKSUM_NONE; + + /* Check if there is enough headroom to insert fragment header. */ + if ((skb_headroom(skb) < frag_hdr_sz) && + pskb_expand_head(skb, frag_hdr_sz, 0, GFP_ATOMIC)) + goto out; + + /* Find the unfragmentable header and shift it left by frag_hdr_sz + * bytes to insert fragment header. + */ + unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); + nexthdr = *prevhdr; + *prevhdr = NEXTHDR_FRAGMENT; + unfrag_len = skb_network_header(skb) - skb_mac_header(skb) + + unfrag_ip6hlen; + mac_start = skb_mac_header(skb); + memmove(mac_start-frag_hdr_sz, mac_start, unfrag_len); + + skb->mac_header -= frag_hdr_sz; + skb->network_header -= frag_hdr_sz; + + fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); + fptr->nexthdr = nexthdr; + fptr->reserved = 0; + ipv6_select_ident(fptr); + + /* Fragment the skb. ipv6 header and the remaining fields of the + * fragment header are updated in ipv6_gso_segment() + */ + segs = skb_segment(skb, features); + +out: + return segs; +} + static struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, + .gso_send_check = udp6_ufo_send_check, + .gso_segment = udp6_ufo_fragment, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; -- cgit v1.2.3-70-g09d2 From e651f03afe833326faa0abe55948c1c6cfd0b8ac Mon Sep 17 00:00:00 2001 From: Gerrit Renker <gerrit@erg.abdn.ac.uk> Date: Sun, 9 Aug 2009 08:12:48 +0000 Subject: inet6: Conversion from u8 to int This replaces assignments of the type "int on LHS" = "u8 on RHS" with simpler code. The LHS can express all of the unsigned right hand side values, hence the assigned value can not be negative. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net> --- net/ipv6/icmp.c | 17 ++++------------- net/ipv6/ip6_output.c | 15 +++++---------- net/ipv6/ipv6_sockglue.c | 2 -- net/ipv6/raw.c | 5 +---- net/ipv6/udp.c | 5 +---- 5 files changed, 11 insertions(+), 33 deletions(-) (limited to 'net/ipv6/udp.c') diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index eab62a7a8f0..e2325f6a05f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -323,7 +323,7 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - int hlimit, tclass; + int hlimit; int err = 0; if ((u8 *)hdr < skb->head || @@ -469,10 +469,6 @@ route_done: if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - msg.skb = skb; msg.offset = skb_network_offset(skb); msg.type = type; @@ -488,8 +484,8 @@ route_done: err = ip6_append_data(sk, icmpv6_getfrag, &msg, len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), - hlimit, tclass, NULL, &fl, (struct rt6_info*)dst, + sizeof(struct icmp6hdr), hlimit, + np->tclass, NULL, &fl, (struct rt6_info*)dst, MSG_DONTWAIT); if (err) { ip6_flush_pending_frames(sk); @@ -522,7 +518,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct dst_entry *dst; int err = 0; int hlimit; - int tclass; saddr = &ipv6_hdr(skb)->daddr; @@ -562,10 +557,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - idev = in6_dev_get(skb->dev); msg.skb = skb; @@ -573,7 +564,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.type = ICMPV6_ECHO_REPLY; err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), - sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl, + sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, (struct rt6_info*)dst, MSG_DONTWAIT); if (err) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 93beee94465..6ad5aadf81a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -194,7 +194,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct ipv6hdr *hdr; u8 proto = fl->proto; int seg_len = skb->len; - int hlimit, tclass; + int hlimit = -1; + int tclass = 0; u32 mtu; if (opt) { @@ -237,19 +238,13 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, /* * Fill in the IPv6 header */ - - hlimit = -1; - if (np) + if (np) { + tclass = np->tclass; hlimit = np->hop_limit; + } if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - tclass = -1; - if (np) - tclass = np->tclass; - if (tclass < 0) - tclass = 0; - *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel; hdr->payload_len = htons(seg_len); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a7fdf9a27f1..c390b1eafb0 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1037,8 +1037,6 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_TCLASS: val = np->tclass; - if (val < 0) - val = 0; break; case IPV6_RECVTCLASS: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d6c3c1c34b2..506841030fb 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -877,11 +877,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, hlimit = ip6_dst_hoplimit(dst); } - if (tclass < 0) { + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d79fa672445..20d2ffc15f0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -946,11 +946,8 @@ do_udp_sendmsg: hlimit = ip6_dst_hoplimit(dst); } - if (tclass < 0) { + if (tclass < 0) tclass = np->tclass; - if (tclass < 0) - tclass = 0; - } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; -- cgit v1.2.3-70-g09d2 From 6ce9e7b5fe3195d1ae6e3a0753d4ddcac5cd699e Mon Sep 17 00:00:00 2001 From: Eric Dumazet <eric.dumazet@gmail.com> Date: Wed, 2 Sep 2009 18:05:33 -0700 Subject: ip: Report qdisc packet drops Christoph Lameter pointed out that packet drops at qdisc level where not accounted in SNMP counters. Only if application sets IP_RECVERR, drops are reported to user (-ENOBUFS errors) and SNMP counters updated. IP_RECVERR is used to enable extended reliable error message passing, but these are not needed to update system wide SNMP stats. This patch changes things a bit to allow SNMP counters to be updated, regardless of IP_RECVERR being set or not on the socket. Example after an UDP tx flood # netstat -s ... IP: 1487048 outgoing packets dropped ... Udp: ... SndbufErrors: 1487048 send() syscalls, do however still return an OK status, to not break applications. Note : send() manual page explicitly says for -ENOBUFS error : "The output queue for a network interface was full. This generally indicates that the interface has stopped sending, but may be caused by transient congestion. (Normally, this does not occur in Linux. Packets are just silently dropped when a device queue overflows.) " This is not true for IP_RECVERR enabled sockets : a send() syscall that hit a qdisc drop returns an ENOBUFS error. Many thanks to Christoph, David, and last but not least, Alexey ! Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> --- net/ipv4/ip_output.c | 2 +- net/ipv4/raw.c | 9 +++++++-- net/ipv4/udp.c | 12 +++++++++--- net/ipv6/ip6_output.c | 2 +- net/ipv6/raw.c | 4 +++- net/ipv6/udp.c | 12 +++++++++--- 6 files changed, 30 insertions(+), 11 deletions(-) (limited to 'net/ipv6/udp.c') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 7d082105472..afae0cbabbf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1302,7 +1302,7 @@ int ip_push_pending_frames(struct sock *sk) err = ip_local_out(skb); if (err) { if (err > 0) - err = inet->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 2979f14bb18..ebb1e5848bc 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -375,7 +375,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) - err = inet->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; out: @@ -386,6 +386,8 @@ error_fault: kfree_skb(skb); error: IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !inet->recverr) + err = 0; return err; } @@ -576,8 +578,11 @@ back_from_confirm: &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); - else if (!(msg->msg_flags & MSG_MORE)) + else if (!(msg->msg_flags & MSG_MORE)) { err = ip_push_pending_frames(sk); + if (err == -ENOBUFS && !inet->recverr) + err = 0; + } release_sock(sk); } done: diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 29ebb0d27a1..ebaaa7f973d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -561,12 +561,18 @@ static int udp_push_pending_frames(struct sock *sk) send: err = ip_push_pending_frames(sk); + if (err) { + if (err == -ENOBUFS && !inet->recverr) { + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); out: up->len = 0; up->pending = 0; - if (!err) - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a931229856b..cd48801a8d6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1511,7 +1511,7 @@ int ip6_push_pending_frames(struct sock *sk) err = ip6_local_out(skb); if (err) { if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 506841030fb..7d675b8d82d 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -642,7 +642,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output); if (err > 0) - err = np->recverr ? net_xmit_errno(err) : 0; + err = net_xmit_errno(err); if (err) goto error; out: @@ -653,6 +653,8 @@ error_fault: kfree_skb(skb); error: IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + if (err == -ENOBUFS && !np->recverr) + err = 0; return err; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 20d2ffc15f0..164040613c2 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -724,12 +724,18 @@ static int udp_v6_push_pending_frames(struct sock *sk) send: err = ip6_push_pending_frames(sk); + if (err) { + if (err == -ENOBUFS && !inet6_sk(sk)->recverr) { + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); out: up->len = 0; up->pending = 0; - if (!err) - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } -- cgit v1.2.3-70-g09d2