From eb20ff9c91ddcb2d55c1849a87d3db85af5e88a9 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Wed, 13 Mar 2013 19:46:20 -0300 Subject: Bluetooth: Fix not closing SCO sockets in the BT_CONNECT2 state With deferred setup for SCO, it is possible that userspace closes the socket when it is in the BT_CONNECT2 state, after the Connect Request is received but before the Accept Synchonous Connection is sent. If this happens the following crash was observed, when the connection is terminated: [ +0.000003] hci_sync_conn_complete_evt: hci0 status 0x10 [ +0.000005] sco_connect_cfm: hcon ffff88003d1bd800 bdaddr 40:98:4e:32:d7:39 status 16 [ +0.000003] sco_conn_del: hcon ffff88003d1bd800 conn ffff88003cc8e300, err 110 [ +0.000015] BUG: unable to handle kernel NULL pointer dereference at 0000000000000199 [ +0.000906] IP: [] __lock_acquire+0xed/0xe82 [ +0.000000] PGD 3d21f067 PUD 3d291067 PMD 0 [ +0.000000] Oops: 0002 [#1] SMP [ +0.000000] Modules linked in: rfcomm bnep btusb bluetooth [ +0.000000] CPU 0 [ +0.000000] Pid: 1481, comm: kworker/u:2H Not tainted 3.9.0-rc1-25019-gad82cdd #1 Bochs Bochs [ +0.000000] RIP: 0010:[] [] __lock_acquire+0xed/0xe82 [ +0.000000] RSP: 0018:ffff88003c3c19d8 EFLAGS: 00010002 [ +0.000000] RAX: 0000000000000001 RBX: 0000000000000246 RCX: 0000000000000000 [ +0.000000] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88003d1be868 [ +0.000000] RBP: ffff88003c3c1a98 R08: 0000000000000002 R09: 0000000000000000 [ +0.000000] R10: ffff88003d1be868 R11: ffff88003e20b000 R12: 0000000000000002 [ +0.000000] R13: ffff88003aaa8000 R14: 000000000000006e R15: ffff88003d1be850 [ +0.000000] FS: 0000000000000000(0000) GS:ffff88003e200000(0000) knlGS:0000000000000000 [ +0.000000] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ +0.000000] CR2: 0000000000000199 CR3: 000000003c1cb000 CR4: 00000000000006b0 [ +0.000000] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ +0.000000] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ +0.000000] Process kworker/u:2H (pid: 1481, threadinfo ffff88003c3c0000, task ffff88003aaa8000) [ +0.000000] Stack: [ +0.000000] ffffffff81b16342 0000000000000000 0000000000000000 ffff88003d1be868 [ +0.000000] ffffffff00000000 00018c0c7863e367 000000003c3c1a28 ffffffff8101efbd [ +0.000000] 0000000000000000 ffff88003e3d2400 ffff88003c3c1a38 ffffffff81007c7a [ +0.000000] Call Trace: [ +0.000000] [] ? kvm_clock_read+0x34/0x3b [ +0.000000] [] ? paravirt_sched_clock+0x9/0xd [ +0.000000] [] ? sched_clock+0x9/0xb [ +0.000000] [] ? sched_clock_local+0x12/0x75 [ +0.000000] [] lock_acquire+0x93/0xb1 [ +0.000000] [] ? spin_lock+0x9/0xb [bluetooth] [ +0.000000] [] ? lock_release_holdtime.part.22+0x4e/0x55 [ +0.000000] [] _raw_spin_lock+0x40/0x74 [ +0.000000] [] ? spin_lock+0x9/0xb [bluetooth] [ +0.000000] [] ? _raw_spin_unlock+0x23/0x36 [ +0.000000] [] spin_lock+0x9/0xb [bluetooth] [ +0.000000] [] sco_conn_del+0x76/0xbb [bluetooth] [ +0.000000] [] sco_connect_cfm+0x2da/0x2e9 [bluetooth] [ +0.000000] [] hci_proto_connect_cfm+0x38/0x65 [bluetooth] [ +0.000000] [] hci_sync_conn_complete_evt.isra.79+0x11a/0x13e [bluetooth] [ +0.000000] [] hci_event_packet+0x153b/0x239d [bluetooth] [ +0.000000] [] ? _raw_spin_unlock_irqrestore+0x48/0x5c [ +0.000000] [] hci_rx_work+0xf3/0x2e3 [bluetooth] [ +0.000000] [] process_one_work+0x1dc/0x30b [ +0.000000] [] ? process_one_work+0x172/0x30b [ +0.000000] [] ? spin_lock_irq+0x9/0xb [ +0.000000] [] worker_thread+0x123/0x1d2 [ +0.000000] [] ? manage_workers+0x240/0x240 [ +0.000000] [] kthread+0x9d/0xa5 [ +0.000000] [] ? __kthread_parkme+0x60/0x60 [ +0.000000] [] ret_from_fork+0x7c/0xb0 [ +0.000000] [] ? __kthread_parkme+0x60/0x60 [ +0.000000] Code: d7 44 89 8d 50 ff ff ff 4c 89 95 58 ff ff ff e8 44 fc ff ff 44 8b 8d 50 ff ff ff 48 85 c0 4c 8b 95 58 ff ff ff 0f 84 7a 04 00 00 ff 80 98 01 00 00 83 3d 25 41 a7 00 00 45 8b b5 e8 05 00 00 [ +0.000000] RIP [] __lock_acquire+0xed/0xe82 [ +0.000000] RSP [ +0.000000] CR2: 0000000000000199 [ +0.000000] ---[ end trace e73cd3b52352dd34 ]--- Cc: stable@vger.kernel.org [3.8] Signed-off-by: Vinicius Costa Gomes Tested-by: Frederic Dalleau Signed-off-by: Gustavo Padovan --- net/bluetooth/sco.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 57f250c20e39..aaf1957bc4fe 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -361,6 +361,7 @@ static void __sco_sock_close(struct sock *sk) sco_chan_del(sk, ECONNRESET); break; + case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); -- cgit v1.2.1 From 0d98da5d845e0d0293055913ce65c9904b3b902a Mon Sep 17 00:00:00 2001 From: Gao feng Date: Thu, 7 Mar 2013 17:20:46 +0000 Subject: netfilter: nf_conntrack: register pernet subsystem before register L4 proto In (c296bb4 netfilter: nf_conntrack: refactor l4proto support for netns) the l4proto gre/dccp/udplite/sctp registration happened before the pernet subsystem, which is wrong. Register pernet subsystem before register L4proto since after register L4proto, init_conntrack may try to access the resources which allocated in register_pernet_subsys. Reported-by: Alexey Dobriyan Cc: Alexey Dobriyan Signed-off-by: Gao feng Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_dccp.c | 12 ++++++------ net/netfilter/nf_conntrack_proto_gre.c | 12 ++++++------ net/netfilter/nf_conntrack_proto_sctp.c | 12 ++++++------ net/netfilter/nf_conntrack_proto_udplite.c | 12 ++++++------ 4 files changed, 24 insertions(+), 24 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 432f95780003..ba65b2041eb4 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -969,6 +969,10 @@ static int __init nf_conntrack_proto_dccp_init(void) { int ret; + ret = register_pernet_subsys(&dccp_net_ops); + if (ret < 0) + goto out_pernet; + ret = nf_ct_l4proto_register(&dccp_proto4); if (ret < 0) goto out_dccp4; @@ -977,16 +981,12 @@ static int __init nf_conntrack_proto_dccp_init(void) if (ret < 0) goto out_dccp6; - ret = register_pernet_subsys(&dccp_net_ops); - if (ret < 0) - goto out_pernet; - return 0; -out_pernet: - nf_ct_l4proto_unregister(&dccp_proto6); out_dccp6: nf_ct_l4proto_unregister(&dccp_proto4); out_dccp4: + unregister_pernet_subsys(&dccp_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index bd7d01d9c7e7..155ce9f8a0db 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -420,18 +420,18 @@ static int __init nf_ct_proto_gre_init(void) { int ret; - ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); - if (ret < 0) - goto out_gre4; - ret = register_pernet_subsys(&proto_gre_net_ops); if (ret < 0) goto out_pernet; + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); + if (ret < 0) + goto out_gre4; + return 0; -out_pernet: - nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); out_gre4: + unregister_pernet_subsys(&proto_gre_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 480f616d5936..ec83536def9a 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -888,6 +888,10 @@ static int __init nf_conntrack_proto_sctp_init(void) { int ret; + ret = register_pernet_subsys(&sctp_net_ops); + if (ret < 0) + goto out_pernet; + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp4); if (ret < 0) goto out_sctp4; @@ -896,16 +900,12 @@ static int __init nf_conntrack_proto_sctp_init(void) if (ret < 0) goto out_sctp6; - ret = register_pernet_subsys(&sctp_net_ops); - if (ret < 0) - goto out_pernet; - return 0; -out_pernet: - nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); out_sctp6: nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); out_sctp4: + unregister_pernet_subsys(&sctp_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 157489581c31..ca969f6273f7 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -371,6 +371,10 @@ static int __init nf_conntrack_proto_udplite_init(void) { int ret; + ret = register_pernet_subsys(&udplite_net_ops); + if (ret < 0) + goto out_pernet; + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite4); if (ret < 0) goto out_udplite4; @@ -379,16 +383,12 @@ static int __init nf_conntrack_proto_udplite_init(void) if (ret < 0) goto out_udplite6; - ret = register_pernet_subsys(&udplite_net_ops); - if (ret < 0) - goto out_pernet; - return 0; -out_pernet: - nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); out_udplite6: nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); out_udplite4: + unregister_pernet_subsys(&udplite_net_ops); +out_pernet: return ret; } -- cgit v1.2.1 From bae99f7a1d372374aaf9ed8910f3b825da995b36 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 14 Mar 2013 06:03:18 +0000 Subject: netfilter: nfnetlink_queue: fix incorrect initialization of copy range field 2^16 = 0xffff, not 0xfffff (note the extra 'f'). Not dangerous since you adjust it to min_t(data_len, skb->len) just after on. Reported-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_queue_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 858fd52c1040..1cb48540f86a 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -112,7 +112,7 @@ instance_create(u_int16_t queue_num, int portid) inst->queue_num = queue_num; inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; - inst->copy_range = 0xfffff; + inst->copy_range = 0xffff; inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); -- cgit v1.2.1 From a82783c91d5dce680dbd290ebf301a520b0e72a5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Mar 2013 20:11:01 +0000 Subject: netfilter: ip6t_NPT: restrict to mangle table As the translation is stateless, using it in nat table doesn't work (only initial packet is translated). filter table OUTPUT works but won't re-route the packet after translation. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/ip6t_NPT.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index 83acc1405a18..33608c610276 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -114,6 +114,7 @@ ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) static struct xt_target ip6t_npt_target_reg[] __read_mostly = { { .name = "SNPT", + .table = "mangle", .target = ip6t_snpt_tg, .targetsize = sizeof(struct ip6t_npt_tginfo), .checkentry = ip6t_npt_checkentry, @@ -124,6 +125,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = { }, { .name = "DNPT", + .table = "mangle", .target = ip6t_dnpt_tg, .targetsize = sizeof(struct ip6t_npt_tginfo), .checkentry = ip6t_npt_checkentry, -- cgit v1.2.1 From 92f28d973cce45ef5823209aab3138eb45d8b349 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 15 Mar 2013 01:03:33 -0700 Subject: scm: Require CAP_SYS_ADMIN over the current pidns to spoof pids. Don't allow spoofing pids over unix domain sockets in the corner cases where a user has created a user namespace but has not yet created a pid namespace. Cc: stable@vger.kernel.org Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" --- net/core/scm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/scm.c b/net/core/scm.c index 905dcc6ad1e3..2dc6cdaaae8a 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -52,7 +53,8 @@ static __inline__ int scm_check_creds(struct ucred *creds) if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; - if ((creds->pid == task_tgid_vnr(current) || nsown_capable(CAP_SYS_ADMIN)) && + if ((creds->pid == task_tgid_vnr(current) || + ns_capable(current->nsproxy->pid_ns->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || -- cgit v1.2.1 From cf2e39429c245245db889fffdfbdf3f889a6cb22 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 9 Mar 2013 23:25:06 +0200 Subject: ipvs: fix sctp chunk length order Fix wrong but non-fatal access to chunk length. sch->length should be in network order, next chunk should be aligned to 4 bytes. Problem noticed in sparse output. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_proto_sctp.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index ae8ec6f27688..cd1d7298f7ba 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -906,7 +906,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, sctp_chunkhdr_t _sctpch, *sch; unsigned char chunk_type; int event, next_state; - int ihl; + int ihl, cofs; #ifdef CONFIG_IP_VS_IPV6 ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); @@ -914,8 +914,8 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ihl = ip_hdrlen(skb); #endif - sch = skb_header_pointer(skb, ihl + sizeof(sctp_sctphdr_t), - sizeof(_sctpch), &_sctpch); + cofs = ihl + sizeof(sctp_sctphdr_t); + sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; @@ -933,10 +933,12 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, */ if ((sch->type == SCTP_CID_COOKIE_ECHO) || (sch->type == SCTP_CID_COOKIE_ACK)) { - sch = skb_header_pointer(skb, (ihl + sizeof(sctp_sctphdr_t) + - sch->length), sizeof(_sctpch), &_sctpch); - if (sch) { - if (sch->type == SCTP_CID_ABORT) + int clen = ntohs(sch->length); + + if (clen >= sizeof(sctp_chunkhdr_t)) { + sch = skb_header_pointer(skb, cofs + ALIGN(clen, 4), + sizeof(_sctpch), &_sctpch); + if (sch && sch->type == SCTP_CID_ABORT) chunk_type = sch->type; } } -- cgit v1.2.1 From 0c12582fbcdea0cbb0dfd224e1c5f9a8428ffa18 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 9 Mar 2013 23:25:04 +0200 Subject: ipvs: add backup_only flag to avoid loops Dmitry Akindinov is reporting for a problem where SYNs are looping between the master and backup server when the backup server is used as real server in DR mode and has IPVS rules to function as director. Even when the backup function is enabled we continue to forward traffic and schedule new connections when the current master is using the backup server as real server. While this is not a problem for NAT, for DR and TUN method the backup server can not determine if a request comes from client or from director. To avoid such loops add new sysctl flag backup_only. It can be needed for DR/TUN setups that do not need backup and director function at the same time. When the backup function is enabled we stop any forwarding and pass the traffic to the local stack (real server mode). The flag disables the director function when the backup function is enabled. For setups that enable backup function for some virtual services and director function for other virtual services there should be another more complex solution to support DR/TUN mode, may be to assign per-virtual service syncid value, so that we can differentiate the requests. Reported-by: Dmitry Akindinov Tested-by: German Myzovsky Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 12 ++++++++---- net/netfilter/ipvs/ip_vs_ctl.c | 7 +++++++ 2 files changed, 15 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 47edf5a40a59..18b4bc55fa3d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1577,7 +1577,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, &iph); @@ -1654,7 +1655,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ @@ -1815,13 +1815,15 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct netns_ipvs *ipvs; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp(skb, &r, hooknum); @@ -1835,6 +1837,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct netns_ipvs *ipvs; struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr); @@ -1843,7 +1846,8 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c68198bf9128..9e2d1cccd1eb 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1808,6 +1808,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "backup_only", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -3741,6 +3747,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; ipvs->sysctl_pmtu_disc = 1; tbl[idx++].data = &ipvs->sysctl_pmtu_disc; + tbl[idx++].data = &ipvs->sysctl_backup_only; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); -- cgit v1.2.1 From bf93ad72cd8cfabe66a7b3d66236a1266d357189 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 9 Mar 2013 23:25:05 +0200 Subject: ipvs: remove extra rcu lock In 3.7 we added code that uses ipv4_update_pmtu but after commit c5ae7d4192 (ipv4: must use rcu protection while calling fib_lookup) the RCU lock is not needed. Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- net/netfilter/ipvs/ip_vs_core.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 18b4bc55fa3d..61f49d241712 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1394,10 +1394,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); - rcu_read_lock(); ipv4_update_pmtu(skb, dev_net(skb->dev), mtu, 0, 0, 0, 0); - rcu_read_unlock(); /* Client uses PMTUD? */ if (!(cih->frag_off & htons(IP_DF))) goto ignore_ipip; -- cgit v1.2.1 From 3dd6664fac7e6041bfc8756ae9e8c78f59108cd9 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Tue, 19 Mar 2013 13:09:59 +0000 Subject: netfilter: remove unused "config IP_NF_QUEUE" Kconfig symbol IP_NF_QUEUE is unused since commit d16cf20e2f2f13411eece7f7fb72c17d141c4a84 ("netfilter: remove ip_queue support"). Let's remove it too. Signed-off-by: Paul Bolle Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/Kconfig | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'net') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index ce2d43e1f09f..0d755c50994b 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -36,19 +36,6 @@ config NF_CONNTRACK_PROC_COMPAT If unsure, say Y. -config IP_NF_QUEUE - tristate "IP Userspace queueing via NETLINK (OBSOLETE)" - depends on NETFILTER_ADVANCED - help - Netfilter has the ability to queue packets to user space: the - netlink device can be used to access them using this driver. - - This option enables the old IPv4-only "ip_queue" implementation - which has been obsoleted by the new "nfnetlink_queue" code (see - CONFIG_NETFILTER_NETLINK_QUEUE). - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" default m if NETFILTER_ADVANCED=n -- cgit v1.2.1 From f1e79e208076ffe7bad97158275f1c572c04f5c7 Mon Sep 17 00:00:00 2001 From: Masatake YAMATO Date: Tue, 19 Mar 2013 01:47:27 +0000 Subject: genetlink: trigger BUG_ON if a group name is too long Trigger BUG_ON if a group name is longer than GENL_NAMSIZ. Signed-off-by: Masatake YAMATO Signed-off-by: David S. Miller --- net/netlink/genetlink.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index f2aabb6f4105..5a55be3f17a5 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -142,6 +142,7 @@ int genl_register_mc_group(struct genl_family *family, int err = 0; BUG_ON(grp->name[0] == '\0'); + BUG_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL); genl_lock(); -- cgit v1.2.1 From 44046a593eb770dbecdabf1c82bcd252f2a8337b Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:12 +0000 Subject: udp: add encap_destroy callback Users of udp encapsulation currently have an encap_rcv callback which they can use to hook into the udp receive path. In situations where a encapsulation user allocates resources associated with a udp encap socket, it may be convenient to be able to also hook the proto .destroy operation. For example, if an encap user holds a reference to the udp socket, the destroy hook might be used to relinquish this reference. This patch adds a socket destroy hook into udp, which is set and enabled in the same way as the existing encap_rcv hook. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/ipv4/udp.c | 7 +++++++ net/ipv6/udp.c | 8 ++++++++ 2 files changed, 15 insertions(+) (limited to 'net') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 265c42cf963c..0a073a263720 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1762,9 +1762,16 @@ int udp_rcv(struct sk_buff *skb) void udp_destroy_sock(struct sock *sk) { + struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); + if (static_key_false(&udp_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } } /* diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 599e1ba6d1ce..d8e5e852fc7a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1285,10 +1285,18 @@ do_confirm: void udpv6_destroy_sock(struct sock *sk) { + struct udp_sock *up = udp_sk(sk); lock_sock(sk); udp_v6_flush_pending_frames(sk); release_sock(sk); + if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } + inet6_destroy_sock(sk); } -- cgit v1.2.1 From 9980d001cec86c3c75f3a6008ddb73c397ea3b3e Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:13 +0000 Subject: l2tp: add udp encap socket destroy handler L2TP sessions hold a reference to the tunnel socket to prevent it going away while sessions are still active. However, since tunnel destruction is handled by the sock sk_destruct callback there is a catch-22: a tunnel with sessions cannot be deleted since each session holds a reference to the tunnel socket. If userspace closes a managed tunnel socket, or dies, the tunnel will persist and it will be neccessary to individually delete the sessions using netlink commands. This is ugly. To prevent this occuring, this patch leverages the udp encapsulation socket destroy callback to gain early notification when the tunnel socket is closed. This allows us to safely close the sessions running in the tunnel, dropping the tunnel socket references in the process. The tunnel socket is then destroyed as normal, and the tunnel resources deallocated in sk_destruct. While we're at it, ensure that l2tp_tunnel_closeall correctly drops session references to allow the sessions to be deleted rather than leaking. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index d36875f3427e..ee726a752292 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1282,6 +1282,7 @@ static void l2tp_tunnel_destruct(struct sock *sk) /* No longer an encapsulation socket. See net/ipv4/udp.c */ (udp_sk(sk))->encap_type = 0; (udp_sk(sk))->encap_rcv = NULL; + (udp_sk(sk))->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; @@ -1360,6 +1361,8 @@ again: if (session->deref != NULL) (*session->deref)(session); + l2tp_session_dec_refcount(session); + write_lock_bh(&tunnel->hlist_lock); /* Now restart from the beginning of this hash @@ -1373,6 +1376,16 @@ again: write_unlock_bh(&tunnel->hlist_lock); } +/* Tunnel socket destroy hook for UDP encapsulation */ +static void l2tp_udp_encap_destroy(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + if (tunnel) { + l2tp_tunnel_closeall(tunnel); + sock_put(sk); + } +} + /* Really kill the tunnel. * Come here only when all sessions have been cleared from the tunnel. */ @@ -1668,6 +1681,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ udp_sk(sk)->encap_type = UDP_ENCAP_L2TPINUDP; udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; + udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) udpv6_encap_enable(); -- cgit v1.2.1 From e34f4c7050e5471b6d4fb25380713937fc837514 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:14 +0000 Subject: l2tp: export l2tp_tunnel_closeall l2tp_core internally uses l2tp_tunnel_closeall to close all sessions in a tunnel when a UDP-encapsulation socket is destroyed. We need to do something similar for IP-encapsulation sockets. Export l2tp_tunnel_closeall as a GPL symbol to enable l2tp_ip and l2tp_ip6 to call it from their .destroy handlers. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 4 ++-- net/l2tp/l2tp_core.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ee726a752292..287e327342d1 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -114,7 +114,6 @@ struct l2tp_net { static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); -static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); static inline struct l2tp_net *l2tp_pernet(struct net *net) { @@ -1312,7 +1311,7 @@ end: /* When the tunnel is closed, all the attached sessions need to go too. */ -static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { int hash; struct hlist_node *walk; @@ -1375,6 +1374,7 @@ again: } write_unlock_bh(&tunnel->hlist_lock); } +EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 8eb8f1d47f3a..b0861f68a10b 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -240,6 +240,7 @@ extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id); extern struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth); extern int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); +extern void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); extern int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); extern int l2tp_session_delete(struct l2tp_session *session); -- cgit v1.2.1 From 936063175afd895913a5e9db77e1a0ef43ea44ea Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:15 +0000 Subject: l2tp: close sessions in ip socket destroy callback l2tp_core hooks UDP's .destroy handler to gain advance warning of a tunnel socket being closed from userspace. We need to do the same thing for IP-encapsulation sockets. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_ip.c | 6 ++++++ net/l2tp/l2tp_ip6.c | 7 +++++++ 2 files changed, 13 insertions(+) (limited to 'net') diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 7f41b7051269..571db8dd2292 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -228,10 +228,16 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { struct sk_buff *skb; + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); + if (tunnel) { + l2tp_tunnel_closeall(tunnel); + sock_put(sk); + } + sk_refcnt_debug_dec(sk); } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 41f2f8126ebc..c74f5a91ff6a 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -241,10 +241,17 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); + if (tunnel) { + l2tp_tunnel_closeall(tunnel); + sock_put(sk); + } + inet6_destroy_sock(sk); } -- cgit v1.2.1 From 2b551c6e7d5bca2c78c216b15ef675653d4f459a Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:16 +0000 Subject: l2tp: close sessions before initiating tunnel delete When a user deletes a tunnel using netlink, all the sessions in the tunnel should also be deleted. Since running sessions will pin the tunnel socket with the references they hold, have the l2tp_tunnel_delete close all sessions in a tunnel before finally closing the tunnel socket. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 287e327342d1..0dd50c079f29 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1737,6 +1737,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); */ int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { + l2tp_tunnel_closeall(tunnel); return (false == queue_work(l2tp_wq, &tunnel->del_work)); } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); -- cgit v1.2.1 From 8abbbe8ff572fd84d1b98eb9acf30611a97cf72e Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:17 +0000 Subject: l2tp: take a reference for kernel sockets in l2tp_tunnel_sock_lookup When looking up the tunnel socket in struct l2tp_tunnel, hold a reference whether the socket was created by the kernel or by userspace. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 0dd50c079f29..45373fee38c5 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -191,6 +191,7 @@ struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) } else { /* Socket is owned by kernelspace */ sk = tunnel->sock; + sock_hold(sk); } out: @@ -209,6 +210,7 @@ void l2tp_tunnel_sock_put(struct sock *sk) } sock_put(sk); } + sock_put(sk); } EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); -- cgit v1.2.1 From 02d13ed5f94af38c37d1abd53462fe48d78bcc9d Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:18 +0000 Subject: l2tp: don't BUG_ON sk_socket being NULL It is valid for an existing struct sock object to have a NULL sk_socket pointer, so don't BUG_ON in l2tp_tunnel_del_work if that should occur. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 45373fee38c5..e841ef2a68a5 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1412,19 +1412,21 @@ static void l2tp_tunnel_del_work(struct work_struct *work) return; sock = sk->sk_socket; - BUG_ON(!sock); - /* If the tunnel socket was created directly by the kernel, use the - * sk_* API to release the socket now. Otherwise go through the - * inet_* layer to shut the socket down, and let userspace close it. + /* If the tunnel socket was created by userspace, then go through the + * inet layer to shut the socket down, and let userspace close it. + * Otherwise, if we created the socket directly within the kernel, use + * the sk API to release it here. * In either case the tunnel resources are freed in the socket * destructor when the tunnel socket goes away. */ - if (sock->file == NULL) { - kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sk); + if (tunnel->fd >= 0) { + if (sock) + inet_shutdown(sock, 2); } else { - inet_shutdown(sock, 2); + if (sock) + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sk); } l2tp_tunnel_sock_put(sk); -- cgit v1.2.1 From 48f72f92b31431c40279b0fba6c5588e07e67d95 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:19 +0000 Subject: l2tp: add session reorder queue purge function to core If an l2tp session is deleted, it is necessary to delete skbs in-flight on the session's reorder queue before taking it down. Rather than having each pseudowire implementation reaching into the l2tp_session struct to handle this itself, provide a function in l2tp_core to purge the session queue. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 17 +++++++++++++++++ net/l2tp/l2tp_core.h | 1 + 2 files changed, 18 insertions(+) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index e841ef2a68a5..69c316dd02dc 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -829,6 +829,23 @@ discard: } EXPORT_SYMBOL(l2tp_recv_common); +/* Drop skbs from the session's reorder_q + */ +int l2tp_session_queue_purge(struct l2tp_session *session) +{ + struct sk_buff *skb = NULL; + BUG_ON(!session); + BUG_ON(session->magic != L2TP_SESSION_MAGIC); + while ((skb = skb_dequeue(&session->reorder_q))) { + atomic_long_inc(&session->stats.rx_errors); + kfree_skb(skb); + if (session->deref) + (*session->deref)(session); + } + return 0; +} +EXPORT_SYMBOL_GPL(l2tp_session_queue_purge); + /* Internal UDP receive frame. Do the real work of receiving an L2TP data frame * here. The skb is not on a list when we get here. * Returns 0 if the packet was a data packet and was successfully passed on. diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index b0861f68a10b..d40713d105fc 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -246,6 +246,7 @@ extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunne extern int l2tp_session_delete(struct l2tp_session *session); extern void l2tp_session_free(struct l2tp_session *session); extern void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length, int (*payload_hook)(struct sk_buff *skb)); +extern int l2tp_session_queue_purge(struct l2tp_session *session); extern int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); extern int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len); -- cgit v1.2.1 From 4c6e2fd35460208596fa099ee0750a4b0438aa5c Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:20 +0000 Subject: l2tp: purge session reorder queue on delete Add calls to l2tp_session_queue_purge as a part of l2tp_tunnel_closeall and l2tp_session_delete. Pseudowire implementations which are deleted only via. l2tp_core l2tp_session_delete calls can dispense with their own code for flushing the reorder queue. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 69c316dd02dc..c00f31b8cc04 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1373,6 +1373,8 @@ again: synchronize_rcu(); } + l2tp_session_queue_purge(session); + if (session->session_close != NULL) (*session->session_close)(session); @@ -1813,6 +1815,8 @@ EXPORT_SYMBOL_GPL(l2tp_session_free); */ int l2tp_session_delete(struct l2tp_session *session) { + l2tp_session_queue_purge(session); + if (session->session_close != NULL) (*session->session_close)(session); -- cgit v1.2.1 From cf2f5c886a209377daefd5d2ba0bcd49c3887813 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:21 +0000 Subject: l2tp: push all ppp pseudowire shutdown through .release handler If userspace deletes a ppp pseudowire using the netlink API, either by directly deleting the session or by deleting the tunnel that contains the session, we need to tear down the corresponding pppox channel. Rather than trying to manage two pppox unbind codepaths, switch the netlink and l2tp_core session_close handlers to close via. the l2tp_ppp socket .release handler. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_ppp.c | 53 ++++++++++------------------------------------------- 1 file changed, 10 insertions(+), 43 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 6a53371dba1f..7e3e16aefcb5 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include @@ -447,34 +448,16 @@ static void pppol2tp_session_close(struct l2tp_session *session) { struct pppol2tp_session *ps = l2tp_session_priv(session); struct sock *sk = ps->sock; - struct sk_buff *skb; + struct socket *sock = sk->sk_socket; BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (session->session_id == 0) - goto out; - - if (sk != NULL) { - lock_sock(sk); - - if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { - pppox_unbind_sock(sk); - sk->sk_state = PPPOX_DEAD; - sk->sk_state_change(sk); - } - - /* Purge any queued data */ - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - while ((skb = skb_dequeue(&session->reorder_q))) { - kfree_skb(skb); - sock_put(sk); - } - release_sock(sk); + if (sock) { + inet_shutdown(sock, 2); + /* Don't let the session go away before our socket does */ + l2tp_session_inc_refcount(session); } - -out: return; } @@ -525,16 +508,12 @@ static int pppol2tp_release(struct socket *sock) session = pppol2tp_sock_to_session(sk); /* Purge any queued data */ - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); if (session != NULL) { - struct sk_buff *skb; - while ((skb = skb_dequeue(&session->reorder_q))) { - kfree_skb(skb); - sock_put(sk); - } + l2tp_session_queue_purge(session); sock_put(sk); } + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); release_sock(sk); @@ -880,18 +859,6 @@ out: return error; } -/* Called when deleting sessions via the netlink interface. - */ -static int pppol2tp_session_delete(struct l2tp_session *session) -{ - struct pppol2tp_session *ps = l2tp_session_priv(session); - - if (ps->sock == NULL) - l2tp_session_dec_refcount(session); - - return 0; -} - #endif /* CONFIG_L2TP_V3 */ /* getname() support. @@ -1839,7 +1806,7 @@ static const struct pppox_proto pppol2tp_proto = { static const struct l2tp_nl_cmd_ops pppol2tp_nl_cmd_ops = { .session_create = pppol2tp_session_create, - .session_delete = pppol2tp_session_delete, + .session_delete = l2tp_session_delete, }; #endif /* CONFIG_L2TP_V3 */ -- cgit v1.2.1 From 7b7c0719cd7afee725b920d75ec6a500b76107e6 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:22 +0000 Subject: l2tp: avoid deadlock in l2tp stats update l2tp's u64_stats writers were incorrectly synchronised, making it possible to deadlock a 64bit machine running a 32bit kernel simply by sending the l2tp code netlink commands while passing data through l2tp sessions. Previous discussion on netdev determined that alternative solutions such as spinlock writer synchronisation or per-cpu data would bring unjustified overhead, given that most users interested in high volume traffic will likely be running 64bit kernels on 64bit hardware. As such, this patch replaces l2tp's use of u64_stats with atomic_long_t, thereby avoiding the deadlock. Ref: http://marc.info/?l=linux-netdev&m=134029167910731&w=2 http://marc.info/?l=linux-netdev&m=134079868111131&w=2 Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 75 +++++++++++++------------------------------------ net/l2tp/l2tp_core.h | 19 ++++++------- net/l2tp/l2tp_debugfs.c | 28 +++++++++--------- net/l2tp/l2tp_netlink.c | 72 ++++++++++++++++++----------------------------- net/l2tp/l2tp_ppp.c | 46 +++++++++++++++--------------- 5 files changed, 93 insertions(+), 147 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c00f31b8cc04..97d30ac67c88 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -374,10 +374,8 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; - struct l2tp_stats *sstats; spin_lock_bh(&session->reorder_q.lock); - sstats = &session->stats; skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); @@ -385,9 +383,7 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", session->name, ns, L2TP_SKB_CB(skbp)->ns, skb_queue_len(&session->reorder_q)); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_oos_packets++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_oos_packets); goto out; } } @@ -404,23 +400,16 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; - struct l2tp_stats *tstats, *sstats; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); - tstats = &tunnel->stats; - u64_stats_update_begin(&tstats->syncp); - sstats = &session->stats; - u64_stats_update_begin(&sstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += length; - sstats->rx_packets++; - sstats->rx_bytes += length; - u64_stats_update_end(&tstats->syncp); - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&tunnel->stats.rx_packets); + atomic_long_add(length, &tunnel->stats.rx_bytes); + atomic_long_inc(&session->stats.rx_packets); + atomic_long_add(length, &session->stats.rx_bytes); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ @@ -451,7 +440,6 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; - struct l2tp_stats *sstats; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other @@ -459,13 +447,10 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) */ start: spin_lock_bh(&session->reorder_q.lock); - sstats = &session->stats; skb_queue_walk_safe(&session->reorder_q, skb, tmp) { if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - sstats->rx_errors++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); + atomic_long_inc(&session->stats.rx_errors); l2tp_dbg(session, L2TP_MSG_SEQ, "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n", session->name, L2TP_SKB_CB(skb)->ns, @@ -624,7 +609,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, struct l2tp_tunnel *tunnel = session->tunnel; int offset; u32 ns, nr; - struct l2tp_stats *sstats = &session->stats; /* The ref count is increased since we now hold a pointer to * the session. Take care to decrement the refcnt when exiting @@ -641,9 +625,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, "%s: cookie mismatch (%u/%u). Discarding.\n", tunnel->name, tunnel->tunnel_id, session->session_id); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_cookie_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } ptr += session->peer_cookie_len; @@ -712,9 +694,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, l2tp_warn(session, L2TP_MSG_SEQ, "%s: recv data has no seq numbers when required. Discarding.\n", session->name); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -733,9 +713,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, l2tp_warn(session, L2TP_MSG_SEQ, "%s: recv data has no seq numbers when required. Discarding.\n", session->name); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } } @@ -789,9 +767,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * packets */ if (L2TP_SKB_CB(skb)->ns != session->nr) { - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); l2tp_dbg(session, L2TP_MSG_SEQ, "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n", session->name, L2TP_SKB_CB(skb)->ns, @@ -817,9 +793,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, return; discard: - u64_stats_update_begin(&sstats->syncp); - sstats->rx_errors++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); if (session->deref) @@ -861,7 +835,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, u32 tunnel_id, session_id; u16 version; int length; - struct l2tp_stats *tstats; if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb)) goto discard_bad_csum; @@ -950,10 +923,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, discard_bad_csum: LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name); UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0); - tstats = &tunnel->stats; - u64_stats_update_begin(&tstats->syncp); - tstats->rx_errors++; - u64_stats_update_end(&tstats->syncp); + atomic_long_inc(&tunnel->stats.rx_errors); kfree_skb(skb); return 0; @@ -1080,7 +1050,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, struct l2tp_tunnel *tunnel = session->tunnel; unsigned int len = skb->len; int error; - struct l2tp_stats *tstats, *sstats; /* Debug */ if (session->send_seq) @@ -1109,21 +1078,15 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, error = ip_queue_xmit(skb, fl); /* Update stats */ - tstats = &tunnel->stats; - u64_stats_update_begin(&tstats->syncp); - sstats = &session->stats; - u64_stats_update_begin(&sstats->syncp); if (error >= 0) { - tstats->tx_packets++; - tstats->tx_bytes += len; - sstats->tx_packets++; - sstats->tx_bytes += len; + atomic_long_inc(&tunnel->stats.tx_packets); + atomic_long_add(len, &tunnel->stats.tx_bytes); + atomic_long_inc(&session->stats.tx_packets); + atomic_long_add(len, &session->stats.tx_bytes); } else { - tstats->tx_errors++; - sstats->tx_errors++; + atomic_long_inc(&tunnel->stats.tx_errors); + atomic_long_inc(&session->stats.tx_errors); } - u64_stats_update_end(&tstats->syncp); - u64_stats_update_end(&sstats->syncp); return 0; } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index d40713d105fc..519b013f8b31 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -36,16 +36,15 @@ enum { struct sk_buff; struct l2tp_stats { - u64 tx_packets; - u64 tx_bytes; - u64 tx_errors; - u64 rx_packets; - u64 rx_bytes; - u64 rx_seq_discards; - u64 rx_oos_packets; - u64 rx_errors; - u64 rx_cookie_discards; - struct u64_stats_sync syncp; + atomic_long_t tx_packets; + atomic_long_t tx_bytes; + atomic_long_t tx_errors; + atomic_long_t rx_packets; + atomic_long_t rx_bytes; + atomic_long_t rx_seq_discards; + atomic_long_t rx_oos_packets; + atomic_long_t rx_errors; + atomic_long_t rx_cookie_discards; }; struct l2tp_tunnel; diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index c3813bc84552..072d7202e182 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -146,14 +146,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0, atomic_read(&tunnel->ref_count)); - seq_printf(m, " %08x rx %llu/%llu/%llu rx %llu/%llu/%llu\n", + seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", tunnel->debug, - (unsigned long long)tunnel->stats.tx_packets, - (unsigned long long)tunnel->stats.tx_bytes, - (unsigned long long)tunnel->stats.tx_errors, - (unsigned long long)tunnel->stats.rx_packets, - (unsigned long long)tunnel->stats.rx_bytes, - (unsigned long long)tunnel->stats.rx_errors); + atomic_long_read(&tunnel->stats.tx_packets), + atomic_long_read(&tunnel->stats.tx_bytes), + atomic_long_read(&tunnel->stats.tx_errors), + atomic_long_read(&tunnel->stats.rx_packets), + atomic_long_read(&tunnel->stats.rx_bytes), + atomic_long_read(&tunnel->stats.rx_errors)); if (tunnel->show != NULL) tunnel->show(m, tunnel); @@ -203,14 +203,14 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) seq_printf(m, "\n"); } - seq_printf(m, " %hu/%hu tx %llu/%llu/%llu rx %llu/%llu/%llu\n", + seq_printf(m, " %hu/%hu tx %ld/%ld/%ld rx %ld/%ld/%ld\n", session->nr, session->ns, - (unsigned long long)session->stats.tx_packets, - (unsigned long long)session->stats.tx_bytes, - (unsigned long long)session->stats.tx_errors, - (unsigned long long)session->stats.rx_packets, - (unsigned long long)session->stats.rx_bytes, - (unsigned long long)session->stats.rx_errors); + atomic_long_read(&session->stats.tx_packets), + atomic_long_read(&session->stats.tx_bytes), + atomic_long_read(&session->stats.tx_errors), + atomic_long_read(&session->stats.rx_packets), + atomic_long_read(&session->stats.rx_bytes), + atomic_long_read(&session->stats.rx_errors)); if (session->show != NULL) session->show(m, session); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index c1bab22db85e..0825ff26e113 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -246,8 +246,6 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np = NULL; #endif - struct l2tp_stats stats; - unsigned int start; hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, L2TP_CMD_TUNNEL_GET); @@ -265,28 +263,22 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nest == NULL) goto nla_put_failure; - do { - start = u64_stats_fetch_begin(&tunnel->stats.syncp); - stats.tx_packets = tunnel->stats.tx_packets; - stats.tx_bytes = tunnel->stats.tx_bytes; - stats.tx_errors = tunnel->stats.tx_errors; - stats.rx_packets = tunnel->stats.rx_packets; - stats.rx_bytes = tunnel->stats.rx_bytes; - stats.rx_errors = tunnel->stats.rx_errors; - stats.rx_seq_discards = tunnel->stats.rx_seq_discards; - stats.rx_oos_packets = tunnel->stats.rx_oos_packets; - } while (u64_stats_fetch_retry(&tunnel->stats.syncp, start)); - - if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) || - nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) || - nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) || - nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) || + if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, + atomic_long_read(&tunnel->stats.tx_packets)) || + nla_put_u64(skb, L2TP_ATTR_TX_BYTES, + atomic_long_read(&tunnel->stats.tx_bytes)) || + nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, + atomic_long_read(&tunnel->stats.tx_errors)) || + nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, + atomic_long_read(&tunnel->stats.rx_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_BYTES, + atomic_long_read(&tunnel->stats.rx_bytes)) || nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, - stats.rx_seq_discards) || + atomic_long_read(&tunnel->stats.rx_seq_discards)) || nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS, - stats.rx_oos_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors)) + atomic_long_read(&tunnel->stats.rx_oos_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, + atomic_long_read(&tunnel->stats.rx_errors))) goto nla_put_failure; nla_nest_end(skb, nest); @@ -612,8 +604,6 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl struct nlattr *nest; struct l2tp_tunnel *tunnel = session->tunnel; struct sock *sk = NULL; - struct l2tp_stats stats; - unsigned int start; sk = tunnel->sock; @@ -656,28 +646,22 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl if (nest == NULL) goto nla_put_failure; - do { - start = u64_stats_fetch_begin(&session->stats.syncp); - stats.tx_packets = session->stats.tx_packets; - stats.tx_bytes = session->stats.tx_bytes; - stats.tx_errors = session->stats.tx_errors; - stats.rx_packets = session->stats.rx_packets; - stats.rx_bytes = session->stats.rx_bytes; - stats.rx_errors = session->stats.rx_errors; - stats.rx_seq_discards = session->stats.rx_seq_discards; - stats.rx_oos_packets = session->stats.rx_oos_packets; - } while (u64_stats_fetch_retry(&session->stats.syncp, start)); - - if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) || - nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) || - nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) || - nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) || + if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, + atomic_long_read(&session->stats.tx_packets)) || + nla_put_u64(skb, L2TP_ATTR_TX_BYTES, + atomic_long_read(&session->stats.tx_bytes)) || + nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, + atomic_long_read(&session->stats.tx_errors)) || + nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, + atomic_long_read(&session->stats.rx_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_BYTES, + atomic_long_read(&session->stats.rx_bytes)) || nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, - stats.rx_seq_discards) || + atomic_long_read(&session->stats.rx_seq_discards)) || nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS, - stats.rx_oos_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors)) + atomic_long_read(&session->stats.rx_oos_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, + atomic_long_read(&session->stats.rx_errors))) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 7e3e16aefcb5..9d0eb8c13530 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -260,7 +260,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int session->name); /* Not bound. Nothing we can do, so discard. */ - session->stats.rx_errors++; + atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } @@ -992,14 +992,14 @@ end: static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest, struct l2tp_stats *stats) { - dest->tx_packets = stats->tx_packets; - dest->tx_bytes = stats->tx_bytes; - dest->tx_errors = stats->tx_errors; - dest->rx_packets = stats->rx_packets; - dest->rx_bytes = stats->rx_bytes; - dest->rx_seq_discards = stats->rx_seq_discards; - dest->rx_oos_packets = stats->rx_oos_packets; - dest->rx_errors = stats->rx_errors; + dest->tx_packets = atomic_long_read(&stats->tx_packets); + dest->tx_bytes = atomic_long_read(&stats->tx_bytes); + dest->tx_errors = atomic_long_read(&stats->tx_errors); + dest->rx_packets = atomic_long_read(&stats->rx_packets); + dest->rx_bytes = atomic_long_read(&stats->rx_bytes); + dest->rx_seq_discards = atomic_long_read(&stats->rx_seq_discards); + dest->rx_oos_packets = atomic_long_read(&stats->rx_oos_packets); + dest->rx_errors = atomic_long_read(&stats->rx_errors); } /* Session ioctl helper. @@ -1633,14 +1633,14 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) tunnel->name, (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', atomic_read(&tunnel->ref_count) - 1); - seq_printf(m, " %08x %llu/%llu/%llu %llu/%llu/%llu\n", + seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", tunnel->debug, - (unsigned long long)tunnel->stats.tx_packets, - (unsigned long long)tunnel->stats.tx_bytes, - (unsigned long long)tunnel->stats.tx_errors, - (unsigned long long)tunnel->stats.rx_packets, - (unsigned long long)tunnel->stats.rx_bytes, - (unsigned long long)tunnel->stats.rx_errors); + atomic_long_read(&tunnel->stats.tx_packets), + atomic_long_read(&tunnel->stats.tx_bytes), + atomic_long_read(&tunnel->stats.tx_errors), + atomic_long_read(&tunnel->stats.rx_packets), + atomic_long_read(&tunnel->stats.rx_bytes), + atomic_long_read(&tunnel->stats.rx_errors)); } static void pppol2tp_seq_session_show(struct seq_file *m, void *v) @@ -1675,14 +1675,14 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) session->lns_mode ? "LNS" : "LAC", session->debug, jiffies_to_msecs(session->reorder_timeout)); - seq_printf(m, " %hu/%hu %llu/%llu/%llu %llu/%llu/%llu\n", + seq_printf(m, " %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n", session->nr, session->ns, - (unsigned long long)session->stats.tx_packets, - (unsigned long long)session->stats.tx_bytes, - (unsigned long long)session->stats.tx_errors, - (unsigned long long)session->stats.rx_packets, - (unsigned long long)session->stats.rx_bytes, - (unsigned long long)session->stats.rx_errors); + atomic_long_read(&session->stats.tx_packets), + atomic_long_read(&session->stats.tx_bytes), + atomic_long_read(&session->stats.tx_errors), + atomic_long_read(&session->stats.rx_packets), + atomic_long_read(&session->stats.rx_bytes), + atomic_long_read(&session->stats.rx_errors)); if (po) seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan)); -- cgit v1.2.1 From f6e16b299bacaa71c6604a784f2d088a966f8c23 Mon Sep 17 00:00:00 2001 From: Tom Parkin Date: Tue, 19 Mar 2013 06:11:23 +0000 Subject: l2tp: unhash l2tp sessions on delete, not on free If we postpone unhashing of l2tp sessions until the structure is freed, we risk: 1. further packets arriving and getting queued while the pseudowire is being closed down 2. the recv path hitting "scheduling while atomic" errors in the case that recv drops the last reference to a session and calls l2tp_session_free while in atomic context As such, l2tp sessions should be unhashed from l2tp_core data structures early in the teardown process prior to calling pseudowire close. For pseudowires like l2tp_ppp which have multiple shutdown codepaths, provide an unhash hook. Signed-off-by: Tom Parkin Signed-off-by: James Chapman Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 75 ++++++++++++++++++++++++---------------------------- net/l2tp/l2tp_core.h | 1 + net/l2tp/l2tp_ppp.c | 12 +++------ 3 files changed, 38 insertions(+), 50 deletions(-) (limited to 'net') diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 97d30ac67c88..8aecf5df6656 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1316,26 +1316,12 @@ again: hlist_del_init(&session->hlist); - /* Since we should hold the sock lock while - * doing any unbinding, we need to release the - * lock we're holding before taking that lock. - * Hold a reference to the sock so it doesn't - * disappear as we're jumping between locks. - */ if (session->ref != NULL) (*session->ref)(session); write_unlock_bh(&tunnel->hlist_lock); - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); - synchronize_rcu(); - } - + __l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close != NULL) @@ -1732,64 +1718,71 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); */ void l2tp_session_free(struct l2tp_session *session) { - struct l2tp_tunnel *tunnel; + struct l2tp_tunnel *tunnel = session->tunnel; BUG_ON(atomic_read(&session->ref_count) != 0); - tunnel = session->tunnel; - if (tunnel != NULL) { + if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); + if (session->session_id != 0) + atomic_dec(&l2tp_session_count); + sock_put(tunnel->sock); + session->tunnel = NULL; + l2tp_tunnel_dec_refcount(tunnel); + } + + kfree(session); + + return; +} +EXPORT_SYMBOL_GPL(l2tp_session_free); + +/* Remove an l2tp session from l2tp_core's hash lists. + * Provides a tidyup interface for pseudowire code which can't just route all + * shutdown via. l2tp_session_delete and a pseudowire-specific session_close + * callback. + */ +void __l2tp_session_unhash(struct l2tp_session *session) +{ + struct l2tp_tunnel *tunnel = session->tunnel; - /* Delete the session from the hash */ + /* Remove the session from core hashes */ + if (tunnel) { + /* Remove from the per-tunnel hash */ write_lock_bh(&tunnel->hlist_lock); hlist_del_init(&session->hlist); write_unlock_bh(&tunnel->hlist_lock); - /* Unlink from the global hash if not L2TPv2 */ + /* For L2TPv3 we have a per-net hash: remove from there, too */ if (tunnel->version != L2TP_HDR_VER_2) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_session_hlist_lock); hlist_del_init_rcu(&session->global_hlist); spin_unlock_bh(&pn->l2tp_session_hlist_lock); synchronize_rcu(); } - - if (session->session_id != 0) - atomic_dec(&l2tp_session_count); - - sock_put(tunnel->sock); - - /* This will delete the tunnel context if this - * is the last session on the tunnel. - */ - session->tunnel = NULL; - l2tp_tunnel_dec_refcount(tunnel); } - - kfree(session); - - return; } -EXPORT_SYMBOL_GPL(l2tp_session_free); +EXPORT_SYMBOL_GPL(__l2tp_session_unhash); /* This function is used by the netlink SESSION_DELETE command and by pseudowire modules. */ int l2tp_session_delete(struct l2tp_session *session) { + if (session->ref) + (*session->ref)(session); + __l2tp_session_unhash(session); l2tp_session_queue_purge(session); - if (session->session_close != NULL) (*session->session_close)(session); - + if (session->deref) + (*session->ref)(session); l2tp_session_dec_refcount(session); - return 0; } EXPORT_SYMBOL_GPL(l2tp_session_delete); - /* We come here whenever a session's send_seq, cookie_len or * l2specific_len parameters are set. */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 519b013f8b31..485a490fd990 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -242,6 +242,7 @@ extern int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_i extern void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); extern int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); +extern void __l2tp_session_unhash(struct l2tp_session *session); extern int l2tp_session_delete(struct l2tp_session *session); extern void l2tp_session_free(struct l2tp_session *session); extern void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length, int (*payload_hook)(struct sk_buff *skb)); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 9d0eb8c13530..637a341c1e2d 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -466,19 +466,12 @@ static void pppol2tp_session_close(struct l2tp_session *session) */ static void pppol2tp_session_destruct(struct sock *sk) { - struct l2tp_session *session; - - if (sk->sk_user_data != NULL) { - session = sk->sk_user_data; - if (session == NULL) - goto out; - + struct l2tp_session *session = sk->sk_user_data; + if (session) { sk->sk_user_data = NULL; BUG_ON(session->magic != L2TP_SESSION_MAGIC); l2tp_session_dec_refcount(session); } - -out: return; } @@ -509,6 +502,7 @@ static int pppol2tp_release(struct socket *sock) /* Purge any queued data */ if (session != NULL) { + __l2tp_session_unhash(session); l2tp_session_queue_purge(session); sock_put(sk); } -- cgit v1.2.1 From 8ed781668dd49b608f1e67a22e3b445fd0c2cd6f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 Mar 2013 06:39:29 +0000 Subject: flow_keys: include thoff into flow_keys for later usage In skb_flow_dissect(), we perform a dissection of a skbuff. Since we're doing the work here anyway, also store thoff for a later usage, e.g. in the BPF filter. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 9d4c7201400d..e187bf06d673 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -140,6 +140,8 @@ ipv6: flow->ports = *ports; } + flow->thoff = (u16) nhoff; + return true; } EXPORT_SYMBOL(skb_flow_dissect); -- cgit v1.2.1 From 283951f95b067877ca5ea77afaa212bb1e0507b5 Mon Sep 17 00:00:00 2001 From: Martin Fuzzey Date: Tue, 19 Mar 2013 08:19:29 +0000 Subject: ipconfig: Fix newline handling in log message. When using ipconfig the logs currently look like: Single name server: [ 3.467270] IP-Config: Complete: [ 3.470613] device=eth0, hwaddr=ac:de:48:00:00:01, ipaddr=172.16.42.2, mask=255.255.255.0, gw=172.16.42.1 [ 3.480670] host=infigo-1, domain=, nis-domain=(none) [ 3.486166] bootserver=172.16.42.1, rootserver=172.16.42.1, rootpath= [ 3.492910] nameserver0=172.16.42.1[ 3.496853] ALSA device list: Three name servers: [ 3.496949] IP-Config: Complete: [ 3.500293] device=eth0, hwaddr=ac:de:48:00:00:01, ipaddr=172.16.42.2, mask=255.255.255.0, gw=172.16.42.1 [ 3.510367] host=infigo-1, domain=, nis-domain=(none) [ 3.515864] bootserver=172.16.42.1, rootserver=172.16.42.1, rootpath= [ 3.522635] nameserver0=172.16.42.1, nameserver1=172.16.42.100 [ 3.529149] , nameserver2=172.16.42.200 Fix newline handling for these cases Signed-off-by: Martin Fuzzey Signed-off-by: David S. Miller --- net/ipv4/ipconfig.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 98cbc6877019..bf6c5cf31aed 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1522,7 +1522,8 @@ static int __init ip_auto_config(void) } for (i++; i < CONF_NAMESERVERS_MAX; i++) if (ic_nameservers[i] != NONE) - pr_cont(", nameserver%u=%pI4\n", i, &ic_nameservers[i]); + pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]); + pr_cont("\n"); #endif /* !SILENT */ return 0; -- cgit v1.2.1 From 896ee0eee6261e30c3623be931c3f621428947df Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 20 Mar 2013 05:19:24 +0000 Subject: net/irda: add missing error path release_sock call This makes sure that release_sock is called for all error conditions in irda_getsockopt. Signed-off-by: Kees Cook Reported-by: Brad Spengler Cc: stable@vger.kernel.org Signed-off-by: David S. Miller --- net/irda/af_irda.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index d07e3a626446..d28e7f014cc6 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -2583,8 +2583,10 @@ bed: NULL, NULL, NULL); /* Check if the we got some results */ - if (!self->cachedaddr) - return -EAGAIN; /* Didn't find any devices */ + if (!self->cachedaddr) { + err = -EAGAIN; /* Didn't find any devices */ + goto out; + } daddr = self->cachedaddr; /* Cleanup */ self->cachedaddr = 0; -- cgit v1.2.1 From f4541d60a449afd40448b06496dcd510f505928e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Mar 2013 17:36:09 +0000 Subject: tcp: preserve ACK clocking in TSO A long standing problem with TSO is the fact that tcp_tso_should_defer() rearms the deferred timer, while it should not. Current code leads to following bad bursty behavior : 20:11:24.484333 IP A > B: . 297161:316921(19760) ack 1 win 119 20:11:24.484337 IP B > A: . ack 263721 win 1117 20:11:24.485086 IP B > A: . ack 265241 win 1117 20:11:24.485925 IP B > A: . ack 266761 win 1117 20:11:24.486759 IP B > A: . ack 268281 win 1117 20:11:24.487594 IP B > A: . ack 269801 win 1117 20:11:24.488430 IP B > A: . ack 271321 win 1117 20:11:24.489267 IP B > A: . ack 272841 win 1117 20:11:24.490104 IP B > A: . ack 274361 win 1117 20:11:24.490939 IP B > A: . ack 275881 win 1117 20:11:24.491775 IP B > A: . ack 277401 win 1117 20:11:24.491784 IP A > B: . 316921:332881(15960) ack 1 win 119 20:11:24.492620 IP B > A: . ack 278921 win 1117 20:11:24.493448 IP B > A: . ack 280441 win 1117 20:11:24.494286 IP B > A: . ack 281961 win 1117 20:11:24.495122 IP B > A: . ack 283481 win 1117 20:11:24.495958 IP B > A: . ack 285001 win 1117 20:11:24.496791 IP B > A: . ack 286521 win 1117 20:11:24.497628 IP B > A: . ack 288041 win 1117 20:11:24.498459 IP B > A: . ack 289561 win 1117 20:11:24.499296 IP B > A: . ack 291081 win 1117 20:11:24.500133 IP B > A: . ack 292601 win 1117 20:11:24.500970 IP B > A: . ack 294121 win 1117 20:11:24.501388 IP B > A: . ack 295641 win 1117 20:11:24.501398 IP A > B: . 332881:351881(19000) ack 1 win 119 While the expected behavior is more like : 20:19:49.259620 IP A > B: . 197601:202161(4560) ack 1 win 119 20:19:49.260446 IP B > A: . ack 154281 win 1212 20:19:49.261282 IP B > A: . ack 155801 win 1212 20:19:49.262125 IP B > A: . ack 157321 win 1212 20:19:49.262136 IP A > B: . 202161:206721(4560) ack 1 win 119 20:19:49.262958 IP B > A: . ack 158841 win 1212 20:19:49.263795 IP B > A: . ack 160361 win 1212 20:19:49.264628 IP B > A: . ack 161881 win 1212 20:19:49.264637 IP A > B: . 206721:211281(4560) ack 1 win 119 20:19:49.265465 IP B > A: . ack 163401 win 1212 20:19:49.265886 IP B > A: . ack 164921 win 1212 20:19:49.266722 IP B > A: . ack 166441 win 1212 20:19:49.266732 IP A > B: . 211281:215841(4560) ack 1 win 119 20:19:49.267559 IP B > A: . ack 167961 win 1212 20:19:49.268394 IP B > A: . ack 169481 win 1212 20:19:49.269232 IP B > A: . ack 171001 win 1212 20:19:49.269241 IP A > B: . 215841:221161(5320) ack 1 win 119 Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Van Jacobson Cc: Neal Cardwell Cc: Nandita Dukkipati Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 817fbb396bc8..5d0b4387cba6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1809,8 +1809,11 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) goto send_now; } - /* Ok, it looks like it is advisable to defer. */ - tp->tso_deferred = 1 | (jiffies << 1); + /* Ok, it looks like it is advisable to defer. + * Do not rearm the timer if already set to not break TCP ACK clocking. + */ + if (!tp->tso_deferred) + tp->tso_deferred = 1 | (jiffies << 1); return true; -- cgit v1.2.1 From 9979a55a833883242e3a29f3596676edd7199c46 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Mar 2013 14:38:28 +0000 Subject: net: remove a WARN_ON() in net_enable_timestamp() The WARN_ON(in_interrupt()) in net_enable_timestamp() can get false positive, in socket clone path, run from softirq context : [ 3641.624425] WARNING: at net/core/dev.c:1532 net_enable_timestamp+0x7b/0x80() [ 3641.668811] Call Trace: [ 3641.671254] [] warn_slowpath_common+0x87/0xc0 [ 3641.677871] [] warn_slowpath_null+0x1a/0x20 [ 3641.683683] [] net_enable_timestamp+0x7b/0x80 [ 3641.689668] [] sk_clone_lock+0x425/0x450 [ 3641.695222] [] inet_csk_clone_lock+0x16/0x170 [ 3641.701213] [] tcp_create_openreq_child+0x29/0x820 [ 3641.707663] [] ? ipt_do_table+0x222/0x670 [ 3641.713354] [] tcp_v4_syn_recv_sock+0xab/0x3d0 [ 3641.719425] [] tcp_check_req+0x3da/0x530 [ 3641.724979] [] ? inet_hashinfo_init+0x60/0x80 [ 3641.730964] [] ? tcp_v4_rcv+0x79f/0xbe0 [ 3641.736430] [] tcp_v4_do_rcv+0x38d/0x4f0 [ 3641.741985] [] tcp_v4_rcv+0xa7a/0xbe0 Its safe at this point because the parent socket owns a reference on the netstamp_needed, so we cant have a 0 -> 1 transition, which requires to lock a mutex. Instead of refining the check, lets remove it, as all known callers are safe. If it ever changes in the future, static_key_slow_inc() will complain anyway. Reported-by: Laurent Chavey Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net') diff --git a/net/core/dev.c b/net/core/dev.c index d540ced1f6c6..b13e5c766c11 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1545,7 +1545,6 @@ void net_enable_timestamp(void) return; } #endif - WARN_ON(in_interrupt()); static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); -- cgit v1.2.1 From 4a7df340ed1bac190c124c1601bfc10cde9fb4fb Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 22 Mar 2013 19:14:07 +0000 Subject: 8021q: fix a potential use-after-free vlan_vid_del() could possibly free ->vlan_info after a RCU grace period, however, we may still refer to the freed memory area by 'grp' pointer. Found by code inspection. This patch moves vlan_vid_del() as behind as possible. Cc: Patrick McHardy Cc: "David S. Miller" Signed-off-by: Cong Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a18714469bf7..85addcd9372b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -86,13 +86,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp = &vlan_info->grp; - /* Take it out of our own structures, but be sure to interlock with - * HW accelerating devices or SW vlan input packet processing if - * VLAN is not 0 (leave it there for 802.1p). - */ - if (vlan_id) - vlan_vid_del(real_dev, vlan_id); - grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) @@ -114,6 +107,13 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) vlan_gvrp_uninit_applicant(real_dev); } + /* Take it out of our own structures, but be sure to interlock with + * HW accelerating devices or SW vlan input packet processing if + * VLAN is not 0 (leave it there for 802.1p). + */ + if (vlan_id) + vlan_vid_del(real_dev, vlan_id); + /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); } -- cgit v1.2.1 From 9b46922e15f4d9d2aedcd320c3b7f7f54d956da7 Mon Sep 17 00:00:00 2001 From: Hong zhi guo Date: Sat, 23 Mar 2013 02:27:50 +0000 Subject: bridge: fix crash when set mac address of br interface When I tried to set mac address of a bridge interface to a mac address which already learned on this bridge, I got system hang. The cause is straight forward: function br_fdb_change_mac_address calls fdb_insert with NULL source nbp. Then an fdb lookup is performed. If an fdb entry is found and it's local, it's OK. But if it's not local, source is dereferenced for printk without NULL check. Signed-off-by: Hong Zhiguo Signed-off-by: David S. Miller --- net/bridge/br_fdb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index b0812c91c0f0..bab338e6270d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -423,7 +423,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return 0; br_warn(br, "adding interface %s with same address " "as a received packet\n", - source->dev->name); + source ? source->dev->name : br->dev->name); fdb_delete(br, fdb); } -- cgit v1.2.1 From 7ebe183c6d444ef5587d803b64a1f4734b18c564 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Sun, 24 Mar 2013 10:42:25 +0000 Subject: tcp: undo spurious timeout after SACK reneging On SACK reneging the sender immediately retransmits and forces a timeout but disables Eifel (undo). If the (buggy) receiver does not drop any packet this can trigger a false slow-start retransmit storm driven by the ACKs of the original packets. This can be detected with undo and TCP timestamps. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0d9bdacce99f..3bd55bad230a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2059,11 +2059,8 @@ void tcp_enter_loss(struct sock *sk, int how) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - if (!how) { - /* Push undo marker, if it was plain RTO and nothing - * was retransmitted. */ - tp->undo_marker = tp->snd_una; - } else { + tp->undo_marker = tp->snd_una; + if (how) { tp->sacked_out = 0; tp->fackets_out = 0; } -- cgit v1.2.1 From 1166fde6a923c30f4351515b6a9a1efc513e7d00 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 25 Mar 2013 11:23:40 -0400 Subject: SUNRPC: Add barriers to ensure read ordering in rpc_wake_up_task_queue_locked We need to be careful when testing task->tk_waitqueue in rpc_wake_up_task_queue_locked, because it can be changed while we are holding the queue->lock. By adding appropriate memory barriers, we can ensure that it is safe to test task->tk_waitqueue for equality if the RPC_TASK_QUEUED bit is set. Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org --- net/sunrpc/sched.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index fb20f25ddec9..f8529fc8e542 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -180,6 +180,8 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]); task->tk_waitqueue = queue; queue->qlen++; + /* barrier matches the read in rpc_wake_up_task_queue_locked() */ + smp_wmb(); rpc_set_queued(task); dprintk("RPC: %5u added to queue %p \"%s\"\n", @@ -430,8 +432,11 @@ static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task */ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task) { - if (RPC_IS_QUEUED(task) && task->tk_waitqueue == queue) - __rpc_do_wake_up_task(queue, task); + if (RPC_IS_QUEUED(task)) { + smp_rmb(); + if (task->tk_waitqueue == queue) + __rpc_do_wake_up_task(queue, task); + } } /* -- cgit v1.2.1 From ded34e0fe8fe8c2d595bfa30626654e4b87621e0 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Mon, 25 Mar 2013 03:18:33 +0000 Subject: unix: fix a race condition in unix_release() As reported by Jan, and others over the past few years, there is a race condition caused by unix_release setting the sock->sk pointer to NULL before properly marking the socket as dead/orphaned. This can cause a problem with the LSM hook security_unix_may_send() if there is another socket attempting to write to this partially released socket in between when sock->sk is set to NULL and it is marked as dead/orphaned. This patch fixes this by only setting sock->sk to NULL after the socket has been marked as dead; I also take the opportunity to make unix_release_sock() a void function as it only ever returned 0/success. Dave, I think this one should go on the -stable pile. Special thanks to Jan for coming up with a reproducer for this problem. Reported-by: Jan Stancek Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- net/unix/af_unix.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 51be64f163ec..f153a8d6e339 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -382,7 +382,7 @@ static void unix_sock_destructor(struct sock *sk) #endif } -static int unix_release_sock(struct sock *sk, int embrion) +static void unix_release_sock(struct sock *sk, int embrion) { struct unix_sock *u = unix_sk(sk); struct path path; @@ -451,8 +451,6 @@ static int unix_release_sock(struct sock *sk, int embrion) if (unix_tot_inflight) unix_gc(); /* Garbage collect fds */ - - return 0; } static void init_peercred(struct sock *sk) @@ -699,9 +697,10 @@ static int unix_release(struct socket *sock) if (!sk) return 0; + unix_release_sock(sk, 0); sock->sk = NULL; - return unix_release_sock(sk, 0); + return 0; } static int unix_autobind(struct socket *sock) -- cgit v1.2.1 From a79ca223e029aa4f09abb337accf1812c900a800 Mon Sep 17 00:00:00 2001 From: Hong Zhiguo Date: Tue, 26 Mar 2013 01:52:45 +0800 Subject: ipv6: fix bad free of addrconf_init_net Signed-off-by: Hong Zhiguo Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'net') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f2c7e615f902..26512250e095 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4784,26 +4784,20 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev) static int __net_init addrconf_init_net(struct net *net) { - int err; + int err = -ENOMEM; struct ipv6_devconf *all, *dflt; - err = -ENOMEM; - all = &ipv6_devconf; - dflt = &ipv6_devconf_dflt; + all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); + if (all == NULL) + goto err_alloc_all; - if (!net_eq(net, &init_net)) { - all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); - if (all == NULL) - goto err_alloc_all; + dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); + if (dflt == NULL) + goto err_alloc_dflt; - dflt = kmemdup(dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) - goto err_alloc_dflt; - } else { - /* these will be inherited by all namespaces */ - dflt->autoconf = ipv6_defaults.autoconf; - dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; - } + /* these will be inherited by all namespaces */ + dflt->autoconf = ipv6_defaults.autoconf; + dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; -- cgit v1.2.1 From 14134f6584212d585b310ce95428014b653dfaf6 Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Mon, 25 Mar 2013 17:02:04 +0000 Subject: af_unix: dont send SCM_CREDENTIAL when dest socket is NULL SCM_SCREDENTIALS should apply to write() syscalls only either source or destination socket asserted SOCK_PASSCRED. The original implememtation in maybe_add_creds is wrong, and breaks several LSB testcases ( i.e. /tset/LSB.os/netowkr/recvfrom/T.recvfrom). Origionally-authored-by: Karel Srot Signed-off-by: Ding Tianhong Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f153a8d6e339..971282b6f6a3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1412,8 +1412,8 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, if (UNIXCB(skb).cred) return; if (test_bit(SOCK_PASSCRED, &sock->flags) || - !other->sk_socket || - test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) { + (other->sk_socket && + test_bit(SOCK_PASSCRED, &other->sk_socket->flags))) { UNIXCB(skb).pid = get_pid(task_tgid(current)); UNIXCB(skb).cred = get_current_cred(); } -- cgit v1.2.1 From 330305cc4a6b0cb75c22fc01b8826f0ad755550f Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sun, 24 Mar 2013 17:36:29 +0000 Subject: ipv4: Fix ip-header identification for gso packets. ip-header id needs to be incremented even if IP_DF flag is set. This behaviour was changed in commit 490ab08127cebc25e3a26 (IP_GRE: Fix IP-Identification). Following patch fixes it so that identification is always incremented. Reported-by: Cong Wang Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 68f6a94f7661..c929d9c1c4b6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1333,8 +1333,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, iph->frag_off |= htons(IP_MF); offset += (skb->len - skb->mac_len - iph->ihl * 4); } else { - if (!(iph->frag_off & htons(IP_DF))) - iph->id = htons(id++); + iph->id = htons(id++); } iph->tot_len = htons(skb->len - skb->mac_len); iph->check = 0; -- cgit v1.2.1