From 64e46749224aa658d8fc0d37ea83ab20b1d7955d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 29 Oct 2010 16:28:07 +0200 Subject: netfilter: nf_nat: fix compiler warning with CONFIG_NF_CT_NETLINK=n net/ipv4/netfilter/nf_nat_core.c:52: warning: 'nf_nat_proto_find_get' defined but not used net/ipv4/netfilter/nf_nat_core.c:66: warning: 'nf_nat_proto_put' defined but not used Reported-by: Geert Uytterhoeven Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/nf_nat_core.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 295c97431e43..c04787ce1a71 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -47,26 +47,6 @@ __nf_nat_proto_find(u_int8_t protonum) return rcu_dereference(nf_nat_protos[protonum]); } -static const struct nf_nat_protocol * -nf_nat_proto_find_get(u_int8_t protonum) -{ - const struct nf_nat_protocol *p; - - rcu_read_lock(); - p = __nf_nat_proto_find(protonum); - if (!try_module_get(p->me)) - p = &nf_nat_unknown_protocol; - rcu_read_unlock(); - - return p; -} - -static void -nf_nat_proto_put(const struct nf_nat_protocol *p) -{ - module_put(p->me); -} - /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int hash_by_src(const struct net *net, u16 zone, @@ -588,6 +568,26 @@ static struct nf_ct_ext_type nat_extend __read_mostly = { #include #include +static const struct nf_nat_protocol * +nf_nat_proto_find_get(u_int8_t protonum) +{ + const struct nf_nat_protocol *p; + + rcu_read_lock(); + p = __nf_nat_proto_find(protonum); + if (!try_module_get(p->me)) + p = &nf_nat_unknown_protocol; + rcu_read_unlock(); + + return p; +} + +static void +nf_nat_proto_put(const struct nf_nat_protocol *p) +{ + module_put(p->me); +} + static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, -- cgit v1.2.1 From 1a8b7a67224eb0c9dbd883b9bfc4938278bad370 Mon Sep 17 00:00:00 2001 From: Vasiliy Kulikov Date: Wed, 3 Nov 2010 08:44:12 +0100 Subject: ipv4: netfilter: arp_tables: fix information leak to userland Structure arpt_getinfo is copied to userland with the field "name" that has the last elements unitialized. It leads to leaking of contents of kernel stack memory. Signed-off-by: Vasiliy Kulikov Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/arp_tables.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3cad2591ace0..3fac340a28d5 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -927,6 +927,7 @@ static int get_info(struct net *net, void __user *user, private = &tmp; } #endif + memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); -- cgit v1.2.1 From b5f15ac4f89f84853544c934fc7a744289e95e34 Mon Sep 17 00:00:00 2001 From: Vasiliy Kulikov Date: Wed, 3 Nov 2010 08:45:06 +0100 Subject: ipv4: netfilter: ip_tables: fix information leak to userland Structure ipt_getinfo is copied to userland with the field "name" that has the last elements unitialized. It leads to leaking of contents of kernel stack memory. Signed-off-by: Vasiliy Kulikov Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/ip_tables.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d31b007a6d80..a846d633b3b6 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1124,6 +1124,7 @@ static int get_info(struct net *net, void __user *user, private = &tmp; } #endif + memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); -- cgit v1.2.1 From 1f1b9c9990205759aae31b7734b0ede41a867f32 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 4 Nov 2010 01:21:39 +0000 Subject: fib: fib_result_assign() should not change fib refcounts After commit ebc0ffae5 (RCU conversion of fib_lookup()), fib_result_assign() should not change fib refcounts anymore. Thanks to Michael who did the bisection and bug report. Reported-by: Michael Ellerman Tested-by: Michael Ellerman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/fib_lookup.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index a29edf2219c8..c079cc0ec651 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -47,11 +47,8 @@ extern int fib_detect_death(struct fib_info *fi, int order, static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) { - if (res->fi != NULL) - fib_info_put(res->fi); + /* we used to play games with refcounts, but we now use RCU */ res->fi = fi; - if (fi != NULL) - atomic_inc(&fi->fib_clntref); } #endif /* _FIB_LOOKUP_H */ -- cgit v1.2.1 From 22e76c849d505d87c5ecf3d3e6742a65f0ff4860 Mon Sep 17 00:00:00 2001 From: Nelson Elhage Date: Wed, 3 Nov 2010 16:35:41 +0000 Subject: inet_diag: Make sure we actually run the same bytecode we audited. We were using nlmsg_find_attr() to look up the bytecode by attribute when auditing, but then just using the first attribute when actually running bytecode. So, if we received a message with two attribute elements, where only the second had type INET_DIAG_REQ_BYTECODE, we would validate and run different bytecode strings. Fix this by consistently using nlmsg_find_attr everywhere. Signed-off-by: Nelson Elhage Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/ipv4/inet_diag.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index ba8042665849..2ada17129fce 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -490,9 +490,11 @@ static int inet_csk_diag_dump(struct sock *sk, { struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { + if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { struct inet_diag_entry entry; - struct rtattr *bc = (struct rtattr *)(r + 1); + const struct nlattr *bc = nlmsg_find_attr(cb->nlh, + sizeof(*r), + INET_DIAG_REQ_BYTECODE); struct inet_sock *inet = inet_sk(sk); entry.family = sk->sk_family; @@ -512,7 +514,7 @@ static int inet_csk_diag_dump(struct sock *sk, entry.dport = ntohs(inet->inet_dport); entry.userlocks = sk->sk_userlocks; - if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) + if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry)) return 0; } @@ -527,9 +529,11 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, { struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { + if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { struct inet_diag_entry entry; - struct rtattr *bc = (struct rtattr *)(r + 1); + const struct nlattr *bc = nlmsg_find_attr(cb->nlh, + sizeof(*r), + INET_DIAG_REQ_BYTECODE); entry.family = tw->tw_family; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) @@ -548,7 +552,7 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, entry.dport = ntohs(tw->tw_dport); entry.userlocks = 0; - if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) + if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry)) return 0; } @@ -618,7 +622,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, struct inet_diag_req *r = NLMSG_DATA(cb->nlh); struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt; - struct rtattr *bc = NULL; + const struct nlattr *bc = NULL; struct inet_sock *inet = inet_sk(sk); int j, s_j; int reqnum, s_reqnum; @@ -638,8 +642,9 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (!lopt || !lopt->qlen) goto out; - if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { - bc = (struct rtattr *)(r + 1); + if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { + bc = nlmsg_find_attr(cb->nlh, sizeof(*r), + INET_DIAG_REQ_BYTECODE); entry.sport = inet->inet_num; entry.userlocks = sk->sk_userlocks; } @@ -672,8 +677,8 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, &ireq->rmt_addr; entry.dport = ntohs(ireq->rmt_port); - if (!inet_diag_bc_run(RTA_DATA(bc), - RTA_PAYLOAD(bc), &entry)) + if (!inet_diag_bc_run(nla_data(bc), + nla_len(bc), &entry)) continue; } -- cgit v1.2.1 From 18943d292facbc70e6a36fc62399ae833f64671b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 8 Nov 2010 11:15:54 +0000 Subject: inet: fix ip_mc_drop_socket() commit 8723e1b4ad9be4444 (inet: RCU changes in inetdev_by_index()) forgot one call site in ip_mc_drop_socket() We should not decrease idev refcount after inetdev_by_index() call, since refcount is not increased anymore. Reported-by: Markus Trippelsdorf Reported-by: Miles Lane Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c8877c6c7216..3c53c2d89e3b 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2306,10 +2306,8 @@ void ip_mc_drop_socket(struct sock *sk) in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); - if (in_dev != NULL) { + if (in_dev != NULL) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); - in_dev_put(in_dev); - } /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); call_rcu(&iml->rcu, ip_mc_socklist_reclaim); -- cgit v1.2.1 From 8d987e5c75107ca7515fa19e857cfa24aab6ec8f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 Nov 2010 23:24:26 +0000 Subject: net: avoid limits overflow Robin Holt tried to boot a 16TB machine and found some limits were reached : sysctl_tcp_mem[2], sysctl_udp_mem[2] We can switch infrastructure to use long "instead" of "int", now atomic_long_t primitives are available for free. Signed-off-by: Eric Dumazet Reported-by: Robin Holt Reviewed-by: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: David S. Miller --- net/ipv4/proc.c | 8 ++++---- net/ipv4/sysctl_net_ipv4.c | 5 ++--- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 11 +++++++---- net/ipv4/udp.c | 4 ++-- 5 files changed, 17 insertions(+), 15 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4ae1f203f7cb..1b48eb1ed453 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,13 +59,13 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) local_bh_enable(); socket_seq_show(seq); - seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", + seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, tcp_death_row.tw_count, sockets, - atomic_read(&tcp_memory_allocated)); - seq_printf(seq, "UDP: inuse %d mem %d\n", + atomic_long_read(&tcp_memory_allocated)); + seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), - atomic_read(&udp_memory_allocated)); + atomic_long_read(&udp_memory_allocated)); seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d96c1da4b17c..e91911d7aae2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -398,7 +398,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_mem, .maxlen = sizeof(sysctl_tcp_mem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_doulongvec_minmax }, { .procname = "tcp_wmem", @@ -602,8 +602,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .proc_handler = proc_doulongvec_minmax, }, { .procname = "udp_rmem_min", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1664a0590bb8..245603c4ad48 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,7 +282,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); -int sysctl_tcp_mem[3] __read_mostly; +long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; @@ -290,7 +290,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); -atomic_t tcp_memory_allocated; /* Current allocated memory. */ +atomic_long_t tcp_memory_allocated; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); /* diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3357f69e353d..6d8ab1c4efc3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -259,8 +259,11 @@ static void tcp_fixup_sndbuf(struct sock *sk) int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff); - if (sk->sk_sndbuf < 3 * sndmem) - sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]); + if (sk->sk_sndbuf < 3 * sndmem) { + sk->sk_sndbuf = 3 * sndmem; + if (sk->sk_sndbuf > sysctl_tcp_wmem[2]) + sk->sk_sndbuf = sysctl_tcp_wmem[2]; + } } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -396,7 +399,7 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_memory_pressure && - atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { + atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } @@ -4861,7 +4864,7 @@ static int tcp_should_expand_sndbuf(struct sock *sk) return 0; /* If we are under soft global TCP memory pressure, do not expand. */ - if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) return 0; /* If we filled the congestion window, do not expand. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 28cb2d733a3c..5e0a3a582a59 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -110,7 +110,7 @@ struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); -int sysctl_udp_mem[3] __read_mostly; +long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); int sysctl_udp_rmem_min __read_mostly; @@ -119,7 +119,7 @@ EXPORT_SYMBOL(sysctl_udp_rmem_min); int sysctl_udp_wmem_min __read_mostly; EXPORT_SYMBOL(sysctl_udp_wmem_min); -atomic_t udp_memory_allocated; +atomic_long_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); #define MAX_UDP_PORTS 65536 -- cgit v1.2.1 From 7a1abd08d52fdeddb3e9a5a33f2f15cc6a5674d2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 10 Nov 2010 21:35:37 -0800 Subject: tcp: Increase TCP_MAXSEG socket option minimum. As noted by Steve Chen, since commit f5fff5dc8a7a3f395b0525c02ba92c95d42b7390 ("tcp: advertise MSS requested by user") we can end up with a situation where tcp_select_initial_window() does a divide by a zero (or even negative) mss value. The problem is that sometimes we effectively subtract TCPOLEN_TSTAMP_ALIGNED and/or TCPOLEN_MD5SIG_ALIGNED from the mss. Fix this by increasing the minimum from 8 to 64. Reported-by: Steve Chen Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 245603c4ad48..081419969485 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2246,7 +2246,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < 8 || val > MAX_TCP_WINDOW) { + if (val < 64 || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } -- cgit v1.2.1 From 8f49c2703b33519aaaccc63f571b465b9d2b3a2d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 12 Nov 2010 13:35:00 -0800 Subject: tcp: Don't change unlocked socket state in tcp_v4_err(). Alexey Kuznetsov noticed a regression introduced by commit f1ecd5d9e7366609d640ff4040304ea197fbc618 ("Revert Backoff [v3]: Revert RTO on ICMP destination unreachable") The RTO and timer modification code added to tcp_v4_err() doesn't check sock_owned_by_user(), which if true means we don't have exclusive access to the socket and therefore cannot modify it's critical state. Just skip this new code block if sock_owned_by_user() is true and eliminate the now superfluous sock_owned_by_user() code block contained within. Reported-by: Alexey Kuznetsov Signed-off-by: David S. Miller CC: Damian Lukowski Acked-by: Eric Dumazet --- net/ipv4/tcp_ipv4.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8f8527d41682..69ccbc1dde9c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -415,6 +415,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) !icsk->icsk_backoff) break; + if (sock_owned_by_user(sk)) + break; + icsk->icsk_backoff--; inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) << icsk->icsk_backoff; @@ -429,11 +432,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (remaining) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); - } else if (sock_owned_by_user(sk)) { - /* RTO revert clocked out retransmission, - * but socket is locked. Will defer. */ - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - HZ/20, TCP_RTO_MAX); } else { /* RTO revert clocked out retransmission. * Will retransmit now */ -- cgit v1.2.1 From 7d98ffd8c2d1da6cec5d84eba42c4aa836a93f85 Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Fri, 5 Nov 2010 01:39:12 +0000 Subject: xfrm: update flowi saddr in icmp_send if unset otherwise xfrm_lookup will fail to find correct policy Signed-off-by: Ulrich Weber Signed-off-by: David S. Miller --- net/ipv4/icmp.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 96bc7f9475a3..e5d1a44bcbdf 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -569,6 +569,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) /* No need to clone since we're just using its address. */ rt2 = rt; + if (!fl.nl_u.ip4_u.saddr) + fl.nl_u.ip4_u.saddr = rt->rt_src; + err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0); switch (err) { case 0: -- cgit v1.2.1 From 7a1c8e5ab120a5f352e78bbc1fa5bb64e6f23639 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 20 Nov 2010 07:46:35 +0000 Subject: net: allow GFP_HIGHMEM in __vmalloc() We forgot to use __GFP_HIGHMEM in several __vmalloc() calls. In ceph, add the missing flag. In fib_trie.c, xfrm_hash.c and request_sock.c, using vzalloc() is cleaner and allows using HIGHMEM pages as well. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 200eb538fbb3..0f280348e0fd 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -365,7 +365,7 @@ static struct tnode *tnode_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else - return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); + return vzalloc(size); } static void __tnode_vfree(struct work_struct *arg) -- cgit v1.2.1