From bc3ed28caaef55e7e3a9316464256353c5f9b1df Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 3 Jun 2008 16:36:54 -0700 Subject: netlink: Improve returned error codes Make nlmsg_trim(), nlmsg_cancel(), genlmsg_cancel(), and nla_nest_cancel() void functions. Return -EMSGSIZE instead of -1 if the provided message buffer is not big enough. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/genetlink.h | 4 ++-- include/net/netlink.h | 20 +++++++++----------- 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index decdda54682..747c255d1df 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -162,9 +162,9 @@ static inline int genlmsg_end(struct sk_buff *skb, void *hdr) * @skb: socket buffer the message is stored in * @hdr: generic netlink message header */ -static inline int genlmsg_cancel(struct sk_buff *skb, void *hdr) +static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { - return nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); + nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** diff --git a/include/net/netlink.h b/include/net/netlink.h index 112dcdf7e34..dfc3701dfcc 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -556,14 +556,12 @@ static inline void *nlmsg_get_pos(struct sk_buff *skb) * @skb: socket buffer the message is stored in * @mark: mark to trim to * - * Trims the message to the provided mark. Returns -1. + * Trims the message to the provided mark. */ -static inline int nlmsg_trim(struct sk_buff *skb, const void *mark) +static inline void nlmsg_trim(struct sk_buff *skb, const void *mark) { if (mark) skb_trim(skb, (unsigned char *) mark - skb->data); - - return -1; } /** @@ -572,11 +570,11 @@ static inline int nlmsg_trim(struct sk_buff *skb, const void *mark) * @nlh: netlink message header * * Removes the complete netlink message including all - * attributes from the socket buffer again. Returns -1. + * attributes from the socket buffer again. */ -static inline int nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) +static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) { - return nlmsg_trim(skb, nlh); + nlmsg_trim(skb, nlh); } /** @@ -775,7 +773,7 @@ static inline int __nla_parse_nested_compat(struct nlattr *tb[], int maxtype, int nested_len = nla_len(nla) - NLA_ALIGN(len); if (nested_len < 0) - return -1; + return -EINVAL; if (nested_len >= nla_attr_size(0)) return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy); @@ -1080,11 +1078,11 @@ static inline int nla_nest_compat_end(struct sk_buff *skb, struct nlattr *start) * @start: container attribute * * Removes the container attribute and including all nested - * attributes. Returns -1. + * attributes. Returns -EMSGSIZE */ -static inline int nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) +static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) { - return nlmsg_trim(skb, start); + nlmsg_trim(skb, start); } /** -- cgit v1.2.3-70-g09d2 From e51171019bb0e1f9fb57c25bd2e38ce652eaea27 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 29 May 2008 19:55:05 +0900 Subject: [SCTP]: Fix NULL dereference of asoc. Commit 7cbca67c073263c179f605bdbbdc565ab29d801d ("[IPV6]: Support Source Address Selection API (RFC5014)") introduced NULL dereference of asoc to sctp_v6_get_saddr in net/sctp/ipv6.c. Pointed out by Johann Felix Soden . Signed-off-by: YOSHIFUJI Hideaki --- include/net/sctp/structs.h | 3 ++- net/sctp/ipv6.c | 5 +++-- net/sctp/protocol.c | 3 ++- net/sctp/transport.c | 2 +- 4 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0ce0443c5b7..917d425f054 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -548,7 +548,8 @@ struct sctp_af { struct dst_entry *(*get_dst) (struct sctp_association *asoc, union sctp_addr *daddr, union sctp_addr *saddr); - void (*get_saddr) (struct sctp_association *asoc, + void (*get_saddr) (struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e45e44c6063..e4aac3266fc 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -299,7 +299,8 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1, /* Fills in the source address(saddr) based on the destination address(daddr) * and asoc's bind address list. */ -static void sctp_v6_get_saddr(struct sctp_association *asoc, +static void sctp_v6_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -318,7 +319,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, if (!asoc) { ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, &daddr->v6.sin6_addr, - inet6_sk(asoc->base.sk)->srcprefs, + inet6_sk(&sk->inet.sk)->srcprefs, &saddr->v6.sin6_addr); SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 0ec234b762c..13ee7fa92e0 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -519,7 +519,8 @@ out: /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ -static void sctp_v4_get_saddr(struct sctp_association *asoc, +static void sctp_v4_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index f4938f6c5ab..62082e7b797 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -291,7 +291,7 @@ void sctp_transport_route(struct sctp_transport *transport, if (saddr) memcpy(&transport->saddr, saddr, sizeof(union sctp_addr)); else - af->get_saddr(asoc, dst, daddr, &transport->saddr); + af->get_saddr(opt, asoc, dst, daddr, &transport->saddr); transport->dst = dst; if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { -- cgit v1.2.3-70-g09d2 From 4bed72e4f5502ea3322f0a00794815fa58951abe Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 27 May 2008 17:37:49 +0900 Subject: [IPV6] ADDRCONF: Allow longer lifetime on 64bit archs. - Allow longer lifetimes (>= 0x7fffffff/HZ) on 64bit archs by using unsigned long. - Shadow this arithmetic overflow workaround by introducing helper functions: addrconf_timeout_fixup() and addrconf_finite_timeout(). Signed-off-by: YOSHIFUJI Hideaki --- include/net/addrconf.h | 22 ++++++++++++ net/ipv6/addrconf.c | 97 ++++++++++++++++++++++++++------------------------ net/ipv6/route.c | 12 ++----- 3 files changed, 75 insertions(+), 56 deletions(-) (limited to 'include/net') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 0a2f0372df3..bbd3d583c6e 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -94,6 +94,28 @@ extern void addrconf_join_solict(struct net_device *dev, extern void addrconf_leave_solict(struct inet6_dev *idev, struct in6_addr *addr); +static inline unsigned long addrconf_timeout_fixup(u32 timeout, + unsigned unit) +{ + if (timeout == 0xffffffff) + return ~0UL; + + /* + * Avoid arithmetic overflow. + * Assuming unit is constant and non-zero, this "if" statement + * will go away on 64bit archs. + */ + if (0xfffffffe > LONG_MAX / unit && timeout > LONG_MAX / unit) + return LONG_MAX / unit; + + return timeout; +} + +static inline int addrconf_finite_timeout(unsigned long timeout) +{ + return ~timeout; +} + /* * IPv6 Address Label subsystem (addrlabel.c) */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c3b20c5afa3..147588f4c7c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -731,8 +731,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) onlink = -1; spin_lock(&ifa->lock); - lifetime = min_t(unsigned long, - ifa->valid_lft, 0x7fffffffUL/HZ); + + lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); + /* + * Note: Because this address is + * not permanent, lifetime < + * LONG_MAX / HZ here. + */ if (time_before(expires, ifa->tstamp + lifetime * HZ)) expires = ifa->tstamp + lifetime * HZ; @@ -1722,7 +1727,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) __u32 valid_lft; __u32 prefered_lft; int addr_type; - unsigned long rt_expires; struct inet6_dev *in6_dev; pinfo = (struct prefix_info *) opt; @@ -1764,28 +1768,23 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) * 2) Configure prefixes with the auto flag set */ - if (valid_lft == INFINITY_LIFE_TIME) - rt_expires = ~0UL; - else if (valid_lft >= 0x7FFFFFFF/HZ) { + if (pinfo->onlink) { + struct rt6_info *rt; + unsigned long rt_expires; + /* Avoid arithmetic overflow. Really, we could * save rt_expires in seconds, likely valid_lft, * but it would require division in fib gc, that it * not good. */ - rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ); - } else - rt_expires = valid_lft * HZ; + if (HZ > USER_HZ) + rt_expires = addrconf_timeout_fixup(valid_lft, HZ); + else + rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); - /* - * We convert this (in jiffies) to clock_t later. - * Avoid arithmetic overflow there as well. - * Overflow can happen only if HZ < USER_HZ. - */ - if (HZ < USER_HZ && ~rt_expires && rt_expires > 0x7FFFFFFF / USER_HZ) - rt_expires = 0x7FFFFFFF / USER_HZ; + if (addrconf_finite_timeout(rt_expires)) + rt_expires *= HZ; - if (pinfo->onlink) { - struct rt6_info *rt; rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, dev->ifindex, 1); @@ -1794,7 +1793,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (valid_lft == 0) { ip6_del_rt(rt); rt = NULL; - } else if (~rt_expires) { + } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ rt->rt6i_expires = jiffies + rt_expires; rt->rt6i_flags |= RTF_EXPIRES; @@ -1803,9 +1802,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) rt->rt6i_expires = 0; } } else if (valid_lft) { - int flags = RTF_ADDRCONF | RTF_PREFIX_RT; clock_t expires = 0; - if (~rt_expires) { + int flags = RTF_ADDRCONF | RTF_PREFIX_RT; + if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ flags |= RTF_EXPIRES; expires = jiffies_to_clock_t(rt_expires); @@ -2036,6 +2035,7 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, int scope; u32 flags; clock_t expires; + unsigned long timeout; ASSERT_RTNL(); @@ -2055,22 +2055,23 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, scope = ipv6_addr_scope(pfx); - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; - flags = 0; - expires = 0; - } else { - if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; flags = RTF_EXPIRES; - expires = jiffies_to_clock_t(valid_lft * HZ); + } else { + expires = 0; + flags = 0; + ifa_flags |= IFA_F_PERMANENT; } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); @@ -3175,26 +3176,28 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, { u32 flags; clock_t expires; + unsigned long timeout; if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; - flags = 0; - expires = 0; - } else { - if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; flags = RTF_EXPIRES; - expires = jiffies_to_clock_t(valid_lft * HZ); + } else { + expires = 0; + flags = 0; + ifa_flags |= IFA_F_PERMANENT; } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } spin_lock_bh(&ifp->lock); ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 48534c6c073..220cffe9e63 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -446,7 +446,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; unsigned int pref; - u32 lifetime; + unsigned long lifetime; struct rt6_info *rt; if (len < sizeof(struct route_info)) { @@ -472,13 +472,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (pref == ICMPV6_ROUTER_PREF_INVALID) pref = ICMPV6_ROUTER_PREF_MEDIUM; - lifetime = ntohl(rinfo->lifetime); - if (lifetime == 0xffffffff) { - /* infinity */ - } else if (lifetime > 0x7fffffff/HZ - 1) { - /* Avoid arithmetic overflow */ - lifetime = 0x7fffffff/HZ - 1; - } + lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; @@ -506,7 +500,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (lifetime == 0xffffffff) { + if (!addrconf_finite_timeout(lifetime)) { rt->rt6i_flags &= ~RTF_EXPIRES; } else { rt->rt6i_expires = jiffies + HZ * lifetime; -- cgit v1.2.3-70-g09d2 From 91e1908f569dd96a25a3947de8771e6cc93999dd Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 4 Jun 2008 13:02:49 +0900 Subject: [IPV6] NETNS: Handle ancillary data in appropriate namespace. Signed-off-by: YOSHIFUJI Hideaki --- include/net/transp_v6.h | 3 ++- net/ipv6/datagram.c | 7 ++++--- net/ipv6/ip6_flowlabel.c | 2 +- net/ipv6/ipv6_sockglue.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index 27394e0447d..112934a3288 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -40,7 +40,8 @@ extern int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb); -extern int datagram_send_ctl(struct msghdr *msg, +extern int datagram_send_ctl(struct net *net, + struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, int *hlimit, int *tclass); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 53e3883f766..b9c2de84a8a 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -496,7 +496,8 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) return 0; } -int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, +int datagram_send_ctl(struct net *net, + struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, int *hlimit, int *tclass) { @@ -540,7 +541,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, addr_type = __ipv6_addr_type(&src_info->ipi6_addr); if (fl->oif) { - dev = dev_get_by_index(&init_net, fl->oif); + dev = dev_get_by_index(net, fl->oif); if (!dev) return -ENODEV; } else if (addr_type & IPV6_ADDR_LINKLOCAL) @@ -548,7 +549,7 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; - if (!ipv6_chk_addr(&init_net, &src_info->ipi6_addr, + if (!ipv6_chk_addr(net, &src_info->ipi6_addr, strict ? dev : NULL, 0)) err = -EINVAL; else diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index eb7a940310f..37a4e777e34 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -354,7 +354,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_control = (void*)(fl->opt+1); flowi.oif = 0; - err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk); + err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 9293b9f0ac2..3eef8e5b363 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -416,7 +416,7 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk); + retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk); if (retv) goto done; update: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 232e0dc45bf..603df76e052 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -813,7 +813,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 47123bf5eb0..1b35c472200 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -731,7 +731,7 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; -- cgit v1.2.3-70-g09d2 From 36d926b94a9908937593e5669162305a071b9cc3 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Wed, 4 Jun 2008 15:49:07 +0400 Subject: [IPV6]: inet_sk(sk)->cork.opt leak IPv6 UDP sockets wth IPv4 mapped address use udp_sendmsg to send the data actually. In this case ip_flush_pending_frames should be called instead of ip6_flush_pending_frames. Signed-off-by: Denis V. Lunev Signed-off-by: YOSHIFUJI Hideaki --- include/net/udp.h | 1 + net/ipv4/udp.c | 3 ++- net/ipv6/udp.c | 4 +++- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/udp.h b/include/net/udp.h index 3e55a99b0ba..ccce8370704 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -135,6 +135,7 @@ extern void udp_err(struct sk_buff *, u32); extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); +extern void udp_flush_pending_frames(struct sock *sk); extern int udp_rcv(struct sk_buff *skb); extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db1cb7c96d6..56fcda3694b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -420,7 +420,7 @@ void udp_err(struct sk_buff *skb, u32 info) /* * Throw away all pending data and cancel the corking. Socket is locked. */ -static void udp_flush_pending_frames(struct sock *sk) +void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -430,6 +430,7 @@ static void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } +EXPORT_SYMBOL(udp_flush_pending_frames); /** * udp4_hwcsum_outgoing - handle outgoing HW checksumming diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1b35c472200..dd309626ae9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -534,7 +534,9 @@ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); - if (up->pending) { + if (up->pending == AF_INET) + udp_flush_pending_frames(sk); + else if (up->pending) { up->len = 0; up->pending = 0; ip6_flush_pending_frames(sk); -- cgit v1.2.3-70-g09d2 From a6465234814efda9ed1dccdba852953f7508e827 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 4 Jun 2008 12:38:43 -0700 Subject: sctp: Correctly implement Fast Recovery cwnd manipulations. Correctly keep track of Fast Recovery state and do not reduce congestion window multiple times during sucht state. Signed-off-by: Vlad Yasevich Tested-by: Wei Yongjun Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 8 +++++++- net/sctp/transport.c | 44 ++++++++++++++++++++++++++++++++------------ 2 files changed, 39 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 917d425f054..67592072a32 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -902,7 +902,10 @@ struct sctp_transport { * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ - int rto_pending; + __u8 rto_pending; + + /* Flag to track the current fast recovery state */ + __u8 fast_recovery; /* * These are the congestion stats. @@ -921,6 +924,9 @@ struct sctp_transport { /* Data that has been sent, but not acknowledged. */ __u32 flight_size; + /* TSN marking the fast recovery exit point */ + __u32 fast_recovery_exit; + /* Destination */ struct dst_entry *dst; /* Source address. */ diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 62082e7b797..9647fb27722 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -79,6 +79,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; + peer->fast_recovery = 0; peer->last_time_heard = jiffies; peer->last_time_used = jiffies; @@ -403,11 +404,16 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, cwnd = transport->cwnd; flight_size = transport->flight_size; + /* See if we need to exit Fast Recovery first */ + if (transport->fast_recovery && + TSN_lte(transport->fast_recovery_exit, sack_ctsn)) + transport->fast_recovery = 0; + /* The appropriate cwnd increase algorithm is performed if, and only - * if the cumulative TSN has advanced and the congestion window is + * if the cumulative TSN whould advanced and the congestion window is * being fully utilized. */ - if ((transport->asoc->ctsn_ack_point >= sack_ctsn) || + if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) || (flight_size < cwnd)) return; @@ -416,17 +422,23 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, pmtu = transport->asoc->pathmtu; if (cwnd <= ssthresh) { - /* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less - * than or equal to ssthresh an SCTP endpoint MUST use the - * slow start algorithm to increase cwnd only if the current - * congestion window is being fully utilized and an incoming - * SACK advances the Cumulative TSN Ack Point. Only when these - * two conditions are met can the cwnd be increased otherwise - * the cwnd MUST not be increased. If these conditions are met - * then cwnd MUST be increased by at most the lesser of - * 1) the total size of the previously outstanding DATA - * chunk(s) acknowledged, and 2) the destination's path MTU. + /* RFC 4960 7.2.1 + * o When cwnd is less than or equal to ssthresh, an SCTP + * endpoint MUST use the slow-start algorithm to increase + * cwnd only if the current congestion window is being fully + * utilized, an incoming SACK advances the Cumulative TSN + * Ack Point, and the data sender is not in Fast Recovery. + * Only when these three conditions are met can the cwnd be + * increased; otherwise, the cwnd MUST not be increased. + * If these conditions are met, then cwnd MUST be increased + * by, at most, the lesser of 1) the total size of the + * previously outstanding DATA chunk(s) acknowledged, and + * 2) the destination's path MTU. This upper bound protects + * against the ACK-Splitting attack outlined in [SAVAGE99]. */ + if (transport->fast_recovery) + return; + if (bytes_acked > pmtu) cwnd += pmtu; else @@ -502,6 +514,13 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * cwnd = ssthresh * partial_bytes_acked = 0 */ + if (transport->fast_recovery) + return; + + /* Mark Fast recovery */ + transport->fast_recovery = 1; + transport->fast_recovery_exit = transport->asoc->next_tsn - 1; + transport->ssthresh = max(transport->cwnd/2, 4*transport->asoc->pathmtu); transport->cwnd = transport->ssthresh; @@ -586,6 +605,7 @@ void sctp_transport_reset(struct sctp_transport *t) t->flight_size = 0; t->error_count = 0; t->rto_pending = 0; + t->fast_recovery = 0; /* Initialize the state information for SFR-CACC */ t->cacc.changeover_active = 0; -- cgit v1.2.3-70-g09d2 From 62aeaff5ccd96462b7077046357a6d7886175a57 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 4 Jun 2008 12:39:11 -0700 Subject: sctp: Start T3-RTX timer when fast retransmitting lowest TSN When we are trying to fast retransmit the lowest outstanding TSN, we need to restart the T3-RTX timer, so that subsequent timeouts will correctly tag all the packets necessary for retransmissions. Signed-off-by: Vlad Yasevich Tested-by: Wei Yongjun Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 5 ++++- net/sctp/outqueue.c | 42 +++++++++++++++++++++++++++++++----------- net/sctp/transport.c | 4 ++-- 3 files changed, 37 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 67592072a32..714dc43c034 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1051,7 +1051,7 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, struct sctp_sock *); void sctp_transport_pmtu(struct sctp_transport *); void sctp_transport_free(struct sctp_transport *); -void sctp_transport_reset_timers(struct sctp_transport *); +void sctp_transport_reset_timers(struct sctp_transport *, int); void sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); @@ -1141,6 +1141,9 @@ struct sctp_outq { /* How many unackd bytes do we have in-flight? */ __u32 outstanding_bytes; + /* Are we doing fast-rtx on this queue */ + char fast_rtx; + /* Corked? */ char cork; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 59edfd25a19..5d3c441e84d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -208,6 +208,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + q->fast_rtx = 0; q->outstanding_bytes = 0; q->empty = 1; q->cork = 0; @@ -500,6 +501,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); + q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); @@ -543,10 +545,13 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, sctp_xmit_t status; struct sctp_chunk *chunk, *chunk1; struct sctp_association *asoc; + int fast_rtx; int error = 0; + int timer = 0; asoc = q->asoc; lqueue = &q->retransmit; + fast_rtx = q->fast_rtx; /* RFC 2960 6.3.3 Handle T3-rtx Expiration * @@ -587,13 +592,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, switch (status) { case SCTP_XMIT_PMTU_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* If we are retransmitting, we should only * send a single packet. */ - if (rtx_timeout) { + if (rtx_timeout || fast_rtx) { list_add(lchunk, lqueue); lchunk = NULL; } @@ -603,8 +607,7 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, case SCTP_XMIT_RWND_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA as there is no more room * at the receiver. @@ -615,8 +618,7 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, case SCTP_XMIT_NAGLE_DELAY: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA because of nagle delay. */ list_add(lchunk, lqueue); @@ -635,7 +637,14 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->fast_retransmit > 0) chunk->fast_retransmit = -1; - *start_timer = 1; + /* Force start T3-rtx timer when fast retransmitting + * the earliest outstanding TSN + */ + if (!timer && fast_rtx && + ntohl(chunk->subh.data_hdr->tsn) == + asoc->ctsn_ack_point + 1) + timer = 2; + q->empty = 0; /* Retrieve a new chunk to bundle. */ @@ -643,12 +652,16 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, break; } + /* Set the timer if there were no errors */ + if (!error && !timer) + timer = 1; + /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. */ - if (rtx_timeout && !lchunk) { + if (rtx_timeout && fast_rtx) { list_for_each_entry(chunk1, lqueue, transmitted_list) { if (chunk1->fast_retransmit > 0) chunk1->fast_retransmit = -1; @@ -656,6 +669,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, } } + *start_timer = timer; + + /* Clear fast retransmit hint */ + if (fast_rtx) + q->fast_rtx = 0; + return error; } @@ -862,7 +881,8 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) rtx_timeout, &start_timer); if (start_timer) - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, + start_timer-1); /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. @@ -977,7 +997,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) list_add_tail(&chunk->transmitted_list, &transport->transmitted); - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, start_timer-1); q->empty = 0; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 9647fb27722..3f34f61221e 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -191,7 +191,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport) /* Start T3_rtx timer if it is not already running and update the heartbeat * timer. This routine is called every time a DATA chunk is sent. */ -void sctp_transport_reset_timers(struct sctp_transport *transport) +void sctp_transport_reset_timers(struct sctp_transport *transport, int force) { /* RFC 2960 6.3.2 Retransmission Timer Rules * @@ -201,7 +201,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport) * address. */ - if (!timer_pending(&transport->T3_rtx_timer)) + if (force || !timer_pending(&transport->T3_rtx_timer)) if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); -- cgit v1.2.3-70-g09d2 From b9031d9d87b24e24cd32ea15b5f4220a1e8da909 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Wed, 4 Jun 2008 12:40:15 -0700 Subject: sctp: Fix ECN markings for IPv6 Commit e9df2e8fd8fbc95c57dbd1d33dada66c4627b44c ("[IPV6]: Use appropriate sock tclass setting for routing lookup.") also changed the way that ECN capable transports mark this capability in IPv6. As a result, SCTP was not marking ECN capablity because the traffic class was never set. This patch brings back the markings for IPv6 traffic. Signed-off-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + net/sctp/ipv6.c | 6 ++++++ net/sctp/output.c | 2 +- net/sctp/protocol.c | 6 ++++++ 4 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 714dc43c034..7f25195f985 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -588,6 +588,7 @@ struct sctp_af { int (*is_ce) (const struct sk_buff *sk); void (*seq_dump_addr)(struct seq_file *seq, union sctp_addr *addr); + void (*ecn_capable)(struct sock *sk); __u16 net_header_len; int sockaddr_len; sa_family_t sa_family; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e4aac3266fc..a2f4d4d5159 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -727,6 +727,11 @@ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr)); } +static void sctp_v6_ecn_capable(struct sock *sk) +{ + inet6_sk(sk)->tclass |= INET_ECN_ECT_0; +} + /* Initialize a PF_INET6 socket msg_name. */ static void sctp_inet6_msgname(char *msgname, int *addr_len) { @@ -997,6 +1002,7 @@ static struct sctp_af sctp_af_inet6 = { .skb_iif = sctp_v6_skb_iif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, + .ecn_capable = sctp_v6_ecn_capable, .net_header_len = sizeof(struct ipv6hdr), .sockaddr_len = sizeof(struct sockaddr_in6), #ifdef CONFIG_COMPAT diff --git a/net/sctp/output.c b/net/sctp/output.c index cf4f9fb6819..6d45bae93b4 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -548,7 +548,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - INET_ECN_xmit(nskb->sk); + (*tp->af_specific->ecn_capable)(nskb->sk); /* Set up the IP options. */ /* BUG: not implemented diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 56bdaf7fc42..b435a193c5d 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -617,6 +617,11 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr)); } +static void sctp_v4_ecn_capable(struct sock *sk) +{ + INET_ECN_xmit(sk); +} + /* Event handler for inet address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same @@ -935,6 +940,7 @@ static struct sctp_af sctp_af_inet = { .skb_iif = sctp_v4_skb_iif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, + .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), #ifdef CONFIG_COMPAT -- cgit v1.2.3-70-g09d2