From 98d9ae841ad620045d653fb05764e4a899f42dbd Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 30 Sep 2011 16:38:29 +0200 Subject: netfilter: nf_conntrack: fix event flooding in GRE protocol tracker GRE connections cause ctnetlink event flood because the ASSURED event is set for every packet received. Reported-by: Denys Fedoryshchenko Tested-by: Denys Fedoryshchenko Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_proto_gre.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index cf616e55ca4..d69facdd9a7 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -241,8 +241,8 @@ static int gre_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.stream_timeout); /* Also, more likely to be important, and not a probe. */ - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); + if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.timeout); -- cgit v1.2.3-70-g09d2 From ae1d48b23d5e79efbcf0cef4f0ebb9742361af59 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Tue, 11 Oct 2011 10:54:35 +0900 Subject: IPVS netns shutdown/startup dead-lock ip_vs_mutext is used by both netns shutdown code and startup and both implicit uses sk_lock-AF_INET mutex. cleanup CPU-1 startup CPU-2 ip_vs_dst_event() ip_vs_genl_set_cmd() sk_lock-AF_INET __ip_vs_mutex sk_lock-AF_INET __ip_vs_mutex * DEAD LOCK * A new mutex placed in ip_vs netns struct called sync_mutex is added. Comments from Julian and Simon added. This patch has been running for more than 3 month now and it seems to work. Ver. 3 IP_VS_SO_GET_DAEMON in do_ip_vs_get_ctl protected by sync_mutex instead of __ip_vs_mutex as sugested by Julian. Signed-off-by: Hans Schillstrom Acked-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 1 + net/netfilter/ipvs/ip_vs_ctl.c | 131 ++++++++++++++++++++++++---------------- net/netfilter/ipvs/ip_vs_sync.c | 6 ++ 3 files changed, 87 insertions(+), 51 deletions(-) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 1aaf915656f..8fa4430f99c 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -900,6 +900,7 @@ struct netns_ipvs { volatile int sync_state; volatile int master_syncid; volatile int backup_syncid; + struct mutex sync_mutex; /* multicast interface name */ char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 2b771dc708a..3e5e08b78bf 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2283,6 +2283,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) struct ip_vs_service *svc; struct ip_vs_dest_user *udest_compat; struct ip_vs_dest_user_kern udest; + struct netns_ipvs *ipvs = net_ipvs(net); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -2303,6 +2304,24 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* increase the module use count */ ip_vs_use_count_inc(); + /* Handle daemons since they have another lock */ + if (cmd == IP_VS_SO_SET_STARTDAEMON || + cmd == IP_VS_SO_SET_STOPDAEMON) { + struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; + + if (mutex_lock_interruptible(&ipvs->sync_mutex)) { + ret = -ERESTARTSYS; + goto out_dec; + } + if (cmd == IP_VS_SO_SET_STARTDAEMON) + ret = start_sync_thread(net, dm->state, dm->mcast_ifn, + dm->syncid); + else + ret = stop_sync_thread(net, dm->state); + mutex_unlock(&ipvs->sync_mutex); + goto out_dec; + } + if (mutex_lock_interruptible(&__ip_vs_mutex)) { ret = -ERESTARTSYS; goto out_dec; @@ -2316,15 +2335,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg); goto out_unlock; - } else if (cmd == IP_VS_SO_SET_STARTDAEMON) { - struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = start_sync_thread(net, dm->state, dm->mcast_ifn, - dm->syncid); - goto out_unlock; - } else if (cmd == IP_VS_SO_SET_STOPDAEMON) { - struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = stop_sync_thread(net, dm->state); - goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2584,6 +2594,33 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) if (copy_from_user(arg, user, copylen) != 0) return -EFAULT; + /* + * Handle daemons first since it has its own locking + */ + if (cmd == IP_VS_SO_GET_DAEMON) { + struct ip_vs_daemon_user d[2]; + + memset(&d, 0, sizeof(d)); + if (mutex_lock_interruptible(&ipvs->sync_mutex)) + return -ERESTARTSYS; + + if (ipvs->sync_state & IP_VS_STATE_MASTER) { + d[0].state = IP_VS_STATE_MASTER; + strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, + sizeof(d[0].mcast_ifn)); + d[0].syncid = ipvs->master_syncid; + } + if (ipvs->sync_state & IP_VS_STATE_BACKUP) { + d[1].state = IP_VS_STATE_BACKUP; + strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, + sizeof(d[1].mcast_ifn)); + d[1].syncid = ipvs->backup_syncid; + } + if (copy_to_user(user, &d, sizeof(d)) != 0) + ret = -EFAULT; + mutex_unlock(&ipvs->sync_mutex); + return ret; + } if (mutex_lock_interruptible(&__ip_vs_mutex)) return -ERESTARTSYS; @@ -2681,28 +2718,6 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } break; - case IP_VS_SO_GET_DAEMON: - { - struct ip_vs_daemon_user d[2]; - - memset(&d, 0, sizeof(d)); - if (ipvs->sync_state & IP_VS_STATE_MASTER) { - d[0].state = IP_VS_STATE_MASTER; - strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, - sizeof(d[0].mcast_ifn)); - d[0].syncid = ipvs->master_syncid; - } - if (ipvs->sync_state & IP_VS_STATE_BACKUP) { - d[1].state = IP_VS_STATE_BACKUP; - strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, - sizeof(d[1].mcast_ifn)); - d[1].syncid = ipvs->backup_syncid; - } - if (copy_to_user(user, &d, sizeof(d)) != 0) - ret = -EFAULT; - } - break; - default: ret = -EINVAL; } @@ -3205,7 +3220,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct net *net = skb_sknet(skb); struct netns_ipvs *ipvs = net_ipvs(net); - mutex_lock(&__ip_vs_mutex); + mutex_lock(&ipvs->sync_mutex); if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, ipvs->master_mcast_ifn, @@ -3225,7 +3240,7 @@ static int ip_vs_genl_dump_daemons(struct sk_buff *skb, } nla_put_failure: - mutex_unlock(&__ip_vs_mutex); + mutex_unlock(&ipvs->sync_mutex); return skb->len; } @@ -3271,13 +3286,9 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) return ip_vs_set_timeout(net, &t); } -static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { - struct ip_vs_service *svc = NULL; - struct ip_vs_service_user_kern usvc; - struct ip_vs_dest_user_kern udest; int ret = 0, cmd; - int need_full_svc = 0, need_full_dest = 0; struct net *net; struct netns_ipvs *ipvs; @@ -3285,19 +3296,10 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; - mutex_lock(&__ip_vs_mutex); - - if (cmd == IPVS_CMD_FLUSH) { - ret = ip_vs_flush(net); - goto out; - } else if (cmd == IPVS_CMD_SET_CONFIG) { - ret = ip_vs_genl_set_config(net, info->attrs); - goto out; - } else if (cmd == IPVS_CMD_NEW_DAEMON || - cmd == IPVS_CMD_DEL_DAEMON) { - + if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1]; + mutex_lock(&ipvs->sync_mutex); if (!info->attrs[IPVS_CMD_ATTR_DAEMON] || nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX, info->attrs[IPVS_CMD_ATTR_DAEMON], @@ -3310,6 +3312,33 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) ret = ip_vs_genl_new_daemon(net, daemon_attrs); else ret = ip_vs_genl_del_daemon(net, daemon_attrs); +out: + mutex_unlock(&ipvs->sync_mutex); + } + return ret; +} + +static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct ip_vs_service *svc = NULL; + struct ip_vs_service_user_kern usvc; + struct ip_vs_dest_user_kern udest; + int ret = 0, cmd; + int need_full_svc = 0, need_full_dest = 0; + struct net *net; + struct netns_ipvs *ipvs; + + net = skb_sknet(skb); + ipvs = net_ipvs(net); + cmd = info->genlhdr->cmd; + + mutex_lock(&__ip_vs_mutex); + + if (cmd == IPVS_CMD_FLUSH) { + ret = ip_vs_flush(net); + goto out; + } else if (cmd == IPVS_CMD_SET_CONFIG) { + ret = ip_vs_genl_set_config(net, info->attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { @@ -3536,13 +3565,13 @@ static struct genl_ops ip_vs_genl_ops[] __read_mostly = { .cmd = IPVS_CMD_NEW_DAEMON, .flags = GENL_ADMIN_PERM, .policy = ip_vs_cmd_policy, - .doit = ip_vs_genl_set_cmd, + .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_DEL_DAEMON, .flags = GENL_ADMIN_PERM, .policy = ip_vs_cmd_policy, - .doit = ip_vs_genl_set_cmd, + .doit = ip_vs_genl_set_daemon, }, { .cmd = IPVS_CMD_GET_DAEMON, diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 7ee7215b8ba..3cdd479f9b5 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -61,6 +61,7 @@ #define SYNC_PROTO_VER 1 /* Protocol version in header */ +static struct lock_class_key __ipvs_sync_key; /* * IPVS sync connection entry * Version 0, i.e. original version. @@ -1545,6 +1546,7 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + if (state == IP_VS_STATE_MASTER) { if (ipvs->master_thread) return -EEXIST; @@ -1667,6 +1669,7 @@ int __net_init ip_vs_sync_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); + __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); INIT_LIST_HEAD(&ipvs->sync_queue); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); @@ -1680,7 +1683,9 @@ int __net_init ip_vs_sync_net_init(struct net *net) void ip_vs_sync_net_cleanup(struct net *net) { int retc; + struct netns_ipvs *ipvs = net_ipvs(net); + mutex_lock(&ipvs->sync_mutex); retc = stop_sync_thread(net, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); @@ -1688,4 +1693,5 @@ void ip_vs_sync_net_cleanup(struct net *net) retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); + mutex_unlock(&ipvs->sync_mutex); } -- cgit v1.2.3-70-g09d2 From f36c23bb9f822904dacf83a329518d0a5fde7968 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 17 Oct 2011 19:07:30 -0400 Subject: udplite: fast-path computation of checksum coverage Commit 903ab86d195cca295379699299c5fc10beba31c7 of 1 March this year ("udp: Add lockless transmit path") introduced a new fast TX path that broke the checksum coverage computation of UDP-lite, which so far depended on up->len (only set if the socket is locked and 0 in the fast path). Fixed by providing both fast- and slow-path computation of checksum coverage. The latter can be removed when UDP(-lite)v6 also uses a lockless transmit path. Reported-by: Thomas Volkert Signed-off-by: Gerrit Renker Signed-off-by: David S. Miller --- include/net/udplite.h | 63 +++++++++++++++++++++++++-------------------------- 1 file changed, 31 insertions(+), 32 deletions(-) diff --git a/include/net/udplite.h b/include/net/udplite.h index 673a024c6b2..5f097ca7d5c 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -66,40 +66,34 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) return 0; } -static inline int udplite_sender_cscov(struct udp_sock *up, struct udphdr *uh) +/* Slow-path computation of checksum. Socket is locked. */ +static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) { + const struct udp_sock *up = udp_sk(skb->sk); int cscov = up->len; + __wsum csum = 0; - /* - * Sender has set `partial coverage' option on UDP-Lite socket - */ - if (up->pcflag & UDPLITE_SEND_CC) { + if (up->pcflag & UDPLITE_SEND_CC) { + /* + * Sender has set `partial coverage' option on UDP-Lite socket. + * The special case "up->pcslen == 0" signifies full coverage. + */ if (up->pcslen < up->len) { - /* up->pcslen == 0 means that full coverage is required, - * partial coverage only if 0 < up->pcslen < up->len */ - if (0 < up->pcslen) { - cscov = up->pcslen; - } - uh->len = htons(up->pcslen); + if (0 < up->pcslen) + cscov = up->pcslen; + udp_hdr(skb)->len = htons(up->pcslen); } - /* - * NOTE: Causes for the error case `up->pcslen > up->len': - * (i) Application error (will not be penalized). - * (ii) Payload too big for send buffer: data is split - * into several packets, each with its own header. - * In this case (e.g. last segment), coverage may - * exceed packet length. - * Since packets with coverage length > packet length are - * illegal, we fall back to the defaults here. - */ + /* + * NOTE: Causes for the error case `up->pcslen > up->len': + * (i) Application error (will not be penalized). + * (ii) Payload too big for send buffer: data is split + * into several packets, each with its own header. + * In this case (e.g. last segment), coverage may + * exceed packet length. + * Since packets with coverage length > packet length are + * illegal, we fall back to the defaults here. + */ } - return cscov; -} - -static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) -{ - int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); - __wsum csum = 0; skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ @@ -115,16 +109,21 @@ static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) return csum; } +/* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { - struct sock *sk = skb->sk; - int cscov = udplite_sender_cscov(udp_sk(sk), udp_hdr(skb)); + const struct udp_sock *up = udp_sk(skb->sk); const int off = skb_transport_offset(skb); - const int len = skb->len - off; + int len = skb->len - off; + if ((up->pcflag & UDPLITE_SEND_CC) && up->pcslen < len) { + if (0 < up->pcslen) + len = up->pcslen; + udp_hdr(skb)->len = htons(up->pcslen); + } skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ - return skb_checksum(skb, off, min(cscov, len), 0); + return skb_checksum(skb, off, len, 0); } extern void udplite4_register(void); -- cgit v1.2.3-70-g09d2 From c7fd0d48bde943e228e9c28ce971a22d6a1744c4 Mon Sep 17 00:00:00 2001 From: Matthew Daley Date: Fri, 14 Oct 2011 18:45:03 +0000 Subject: x25: Validate incoming call user data lengths X.25 call user data is being copied in its entirety from incoming messages without consideration to the size of the destination buffers, leading to possible buffer overflows. Validate incoming call user data lengths before these copies are performed. It appears this issue was noticed some time ago, however nothing seemed to come of it: see http://www.spinics.net/lists/linux-x25/msg00043.html and commit 8db09f26f912f7c90c764806e804b558da520d4f. Signed-off-by: Matthew Daley Acked-by: Eric Dumazet Tested-by: Andrew Hendry Cc: stable Signed-off-by: David S. Miller --- net/x25/af_x25.c | 6 ++++++ net/x25/x25_in.c | 3 +++ 2 files changed, 9 insertions(+) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d30615419b4..a4bd1720e39 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -958,6 +958,12 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, goto out_clear_request; skb_pull(skb,len); + /* + * Ensure that the amount of call user data is valid. + */ + if (skb->len > X25_MAX_CUD_LEN) + goto out_clear_request; + /* * Find a listener for the particular address/cud pair. */ diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 0b073b51b18..63488fd4885 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -127,6 +127,9 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp * Copy any Call User Data. */ if (skb->len > 0) { + if (skb->len > X25_MAX_CUD_LEN) + goto out_clear; + skb_copy_from_linear_data(skb, x25->calluserdata.cuddata, skb->len); -- cgit v1.2.3-70-g09d2 From cb101ed2c3c7c0224d16953fe77bfb9d6c2cb9df Mon Sep 17 00:00:00 2001 From: Matthew Daley Date: Fri, 14 Oct 2011 18:45:04 +0000 Subject: x25: Handle undersized/fragmented skbs There are multiple locations in the X.25 packet layer where a skb is assumed to be of at least a certain size and that all its data is currently available at skb->data. These assumptions are not checked, hence buffer overreads may occur. Use pskb_may_pull to check these minimal size assumptions and ensure that data is available at skb->data when necessary, as well as use skb_copy_bits where needed. Signed-off-by: Matthew Daley Cc: Eric Dumazet Cc: Andrew Hendry Cc: stable Acked-by: Andrew Hendry Signed-off-by: David S. Miller --- net/x25/af_x25.c | 31 ++++++++++++++++++++++++------- net/x25/x25_dev.c | 6 ++++++ net/x25/x25_facilities.c | 10 ++++++---- net/x25/x25_in.c | 40 +++++++++++++++++++++++++++++++++++----- net/x25/x25_link.c | 3 +++ net/x25/x25_subr.c | 14 +++++++++++++- 6 files changed, 87 insertions(+), 17 deletions(-) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a4bd1720e39..aa567b09ea9 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -91,7 +91,7 @@ int x25_parse_address_block(struct sk_buff *skb, int needed; int rc; - if (skb->len < 1) { + if (!pskb_may_pull(skb, 1)) { /* packet has no address block */ rc = 0; goto empty; @@ -100,7 +100,7 @@ int x25_parse_address_block(struct sk_buff *skb, len = *skb->data; needed = 1 + (len >> 4) + (len & 0x0f); - if (skb->len < needed) { + if (!pskb_may_pull(skb, needed)) { /* packet is too short to hold the addresses it claims to hold */ rc = -1; @@ -951,10 +951,10 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, * * Facilities length is mandatory in call request packets */ - if (skb->len < 1) + if (!pskb_may_pull(skb, 1)) goto out_clear_request; len = skb->data[0] + 1; - if (skb->len < len) + if (!pskb_may_pull(skb, len)) goto out_clear_request; skb_pull(skb,len); @@ -964,6 +964,13 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, if (skb->len > X25_MAX_CUD_LEN) goto out_clear_request; + /* + * Get all the call user data so it can be used in + * x25_find_listener and skb_copy_from_linear_data up ahead. + */ + if (!pskb_may_pull(skb, skb->len)) + goto out_clear_request; + /* * Find a listener for the particular address/cud pair. */ @@ -1172,6 +1179,9 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, * byte of the user data is the logical value of the Q Bit. */ if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { + if (!pskb_may_pull(skb, 1)) + goto out_kfree_skb; + qbit = skb->data[0]; skb_pull(skb, 1); } @@ -1250,7 +1260,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, struct x25_sock *x25 = x25_sk(sk); struct sockaddr_x25 *sx25 = (struct sockaddr_x25 *)msg->msg_name; size_t copied; - int qbit; + int qbit, header_len = x25->neighbour->extended ? + X25_EXT_MIN_LEN : X25_STD_MIN_LEN; + struct sk_buff *skb; unsigned char *asmptr; int rc = -ENOTCONN; @@ -1271,6 +1283,9 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, skb = skb_dequeue(&x25->interrupt_in_queue); + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + goto out_free_dgram; + skb_pull(skb, X25_STD_MIN_LEN); /* @@ -1291,10 +1306,12 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) goto out; + if (!pskb_may_pull(skb, header_len)) + goto out_free_dgram; + qbit = (skb->data[0] & X25_Q_BIT) == X25_Q_BIT; - skb_pull(skb, x25->neighbour->extended ? - X25_EXT_MIN_LEN : X25_STD_MIN_LEN); + skb_pull(skb, header_len); if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { asmptr = skb_push(skb, 1); diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index e547ca1578c..fa2b41888bd 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -32,6 +32,9 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) unsigned short frametype; unsigned int lci; + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + return 0; + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); @@ -115,6 +118,9 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, goto drop; } + if (!pskb_may_pull(skb, 1)) + return 0; + switch (skb->data[0]) { case X25_IFACE_DATA: diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index f77e4e75f91..36384a1fa9f 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -44,7 +44,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask) { - unsigned char *p = skb->data; + unsigned char *p; unsigned int len; *vc_fac_mask = 0; @@ -60,14 +60,16 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, memset(dte_facs->called_ae, '\0', sizeof(dte_facs->called_ae)); memset(dte_facs->calling_ae, '\0', sizeof(dte_facs->calling_ae)); - if (skb->len < 1) + if (!pskb_may_pull(skb, 1)) return 0; - len = *p++; + len = skb->data[0]; - if (len >= skb->len) + if (!pskb_may_pull(skb, 1 + len)) return -1; + p = skb->data + 1; + while (len > 0) { switch (*p & X25_FAC_CLASS_MASK) { case X25_FAC_CLASS_A: diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 63488fd4885..a49cd4ec551 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -107,6 +107,8 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp /* * Parse the data in the frame. */ + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + goto out_clear; skb_pull(skb, X25_STD_MIN_LEN); len = x25_parse_address_block(skb, &source_addr, @@ -130,9 +132,8 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp if (skb->len > X25_MAX_CUD_LEN) goto out_clear; - skb_copy_from_linear_data(skb, - x25->calluserdata.cuddata, - skb->len); + skb_copy_bits(skb, 0, x25->calluserdata.cuddata, + skb->len); x25->calluserdata.cudlength = skb->len; } if (!sock_flag(sk, SOCK_DEAD)) @@ -140,6 +141,9 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; } case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]); break; @@ -167,6 +171,9 @@ static int x25_state2_machine(struct sock *sk, struct sk_buff *skb, int frametyp switch (frametype) { case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -180,6 +187,11 @@ static int x25_state2_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25_start_t23timer(sk); + return 0; } /* @@ -209,6 +221,9 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -307,6 +322,12 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return queued; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* @@ -316,13 +337,13 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp */ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametype) { + struct x25_sock *x25 = x25_sk(sk); + switch (frametype) { case X25_RESET_REQUEST: x25_write_internal(sk, X25_RESET_CONFIRMATION); case X25_RESET_CONFIRMATION: { - struct x25_sock *x25 = x25_sk(sk); - x25_stop_timer(sk); x25->condition = 0x00; x25->va = 0; @@ -334,6 +355,9 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; } case X25_CLEAR_REQUEST: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 2)) + goto out_clear; + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); x25_disconnect(sk, 0, skb->data[3], skb->data[4]); break; @@ -343,6 +367,12 @@ static int x25_state4_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* Higher level upcall for a LAPB frame */ diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 037958ff8ee..4acacf3c661 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -90,6 +90,9 @@ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb, break; case X25_DIAGNOSTIC: + if (!pskb_may_pull(skb, X25_STD_MIN_LEN + 4)) + break; + printk(KERN_WARNING "x25: diagnostic #%d - %02X %02X %02X\n", skb->data[3], skb->data[4], skb->data[5], skb->data[6]); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 24a342ebc7f..5170d52bfd9 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -269,7 +269,11 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, int *d, int *m) { struct x25_sock *x25 = x25_sk(sk); - unsigned char *frame = skb->data; + unsigned char *frame; + + if (!pskb_may_pull(skb, X25_STD_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; *ns = *nr = *q = *d = *m = 0; @@ -294,6 +298,10 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, if (frame[2] == X25_RR || frame[2] == X25_RNR || frame[2] == X25_REJ) { + if (!pskb_may_pull(skb, X25_EXT_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; + *nr = (frame[3] >> 1) & 0x7F; return frame[2]; } @@ -308,6 +316,10 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, if (x25->neighbour->extended) { if ((frame[2] & 0x01) == X25_DATA) { + if (!pskb_may_pull(skb, X25_EXT_MIN_LEN)) + return X25_ILLEGAL; + frame = skb->data; + *q = (frame[0] & X25_Q_BIT) == X25_Q_BIT; *d = (frame[0] & X25_D_BIT) == X25_D_BIT; *m = (frame[3] & X25_EXT_M_BIT) == X25_EXT_M_BIT; -- cgit v1.2.3-70-g09d2 From 7f81e25befdfb3272345a2e775f520e1d515fa20 Mon Sep 17 00:00:00 2001 From: Matthew Daley Date: Fri, 14 Oct 2011 18:45:05 +0000 Subject: x25: Prevent skb overreads when checking call user data x25_find_listener does not check that the amount of call user data given in the skb is big enough in per-socket comparisons, hence buffer overreads may occur. Fix this by adding a check. Signed-off-by: Matthew Daley Cc: Eric Dumazet Cc: Andrew Hendry Cc: stable Acked-by: Andrew Hendry Signed-off-by: David S. Miller --- net/x25/af_x25.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index aa567b09ea9..5f03e4ea65b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -295,7 +295,8 @@ static struct sock *x25_find_listener(struct x25_address *addr, * Found a listening socket, now check the incoming * call user data vs this sockets call user data */ - if(skb->len > 0 && x25_sk(s)->cudmatchlength > 0) { + if (x25_sk(s)->cudmatchlength > 0 && + skb->len >= x25_sk(s)->cudmatchlength) { if((memcmp(x25_sk(s)->calluserdata.cuddata, skb->data, x25_sk(s)->cudmatchlength)) == 0) { -- cgit v1.2.3-70-g09d2 From 1ce5cce895309862d2c35d922816adebe094fe4a Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 6 Oct 2011 11:19:41 +0000 Subject: bridge: fix hang on removal of bridge via netlink Need to cleanup bridge device timers and ports when being bridge device is being removed via netlink. This fixes the problem of observed when doing: ip link add br0 type bridge ip link set dev eth1 master br0 ip link set br0 up ip link del br0 which would cause br0 to hang in unregister_netdev because of leftover reference count. Reported-by: Sridhar Samudrala Signed-off-by: Stephen Hemminger Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- net/bridge/br_if.c | 9 +++++---- net/bridge/br_netlink.c | 1 + net/bridge/br_private.h | 1 + 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index e73815456ad..1d420f64ff2 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -161,9 +161,10 @@ static void del_nbp(struct net_bridge_port *p) call_rcu(&p->rcu, destroy_nbp_rcu); } -/* called with RTNL */ -static void del_br(struct net_bridge *br, struct list_head *head) +/* Delete bridge device */ +void br_dev_delete(struct net_device *dev, struct list_head *head) { + struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p, *n; list_for_each_entry_safe(p, n, &br->port_list, list) { @@ -268,7 +269,7 @@ int br_del_bridge(struct net *net, const char *name) } else - del_br(netdev_priv(dev), NULL); + br_dev_delete(dev, NULL); rtnl_unlock(); return ret; @@ -449,7 +450,7 @@ void __net_exit br_net_exit(struct net *net) rtnl_lock(); for_each_netdev(net, dev) if (dev->priv_flags & IFF_EBRIDGE) - del_br(netdev_priv(dev), &list); + br_dev_delete(dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5b1ed1ba9aa..e5f9ece3c9a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -210,6 +210,7 @@ static struct rtnl_link_ops br_link_ops __read_mostly = { .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .validate = br_validate, + .dellink = br_dev_delete, }; int __init br_netlink_init(void) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 78cc364997d..857a021deea 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -294,6 +294,7 @@ static inline int br_is_root_bridge(const struct net_bridge *br) /* br_device.c */ extern void br_dev_setup(struct net_device *dev); +extern void br_dev_delete(struct net_device *dev, struct list_head *list); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev); #ifdef CONFIG_NET_POLL_CONTROLLER -- cgit v1.2.3-70-g09d2 From 835acf5da239b91edb9f7ebe36516999e156e6ee Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 7 Oct 2011 05:35:46 +0000 Subject: l2tp: fix a potential skb leak in l2tp_xmit_skb() l2tp_xmit_skb() can leak one skb if skb_cow_head() returns an error. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ad4ac2601a5..34b2ddeacb6 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1045,8 +1045,10 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + hdr_len; old_headroom = skb_headroom(skb); - if (skb_cow_head(skb, headroom)) + if (skb_cow_head(skb, headroom)) { + dev_kfree_skb(skb); goto abort; + } new_headroom = skb_headroom(skb); skb_orphan(skb); -- cgit v1.2.3-70-g09d2 From 6230c9b4f8957c8938ee4cf2d03166d3c2dc89de Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 7 Oct 2011 09:40:59 +0000 Subject: bluetooth: Properly clone LSM attributes to newly created child connections The Bluetooth stack has internal connection handlers for all of the various Bluetooth protocols, and unfortunately, they are currently lacking the LSM hooks found in the core network stack's connection handlers. I say unfortunately, because this can cause problems for users who have have an LSM enabled and are using certain Bluetooth devices. See one problem report below: * http://bugzilla.redhat.com/show_bug.cgi?id=741703 In order to keep things simple at this point in time, this patch fixes the problem by cloning the parent socket's LSM attributes to the newly created child socket. If we decide we need a more elaborate LSM marking mechanism for Bluetooth (I somewhat doubt this) we can always revisit this decision in the future. Reported-by: James M. Cape Signed-off-by: Paul Moore Acked-by: James Morris Signed-off-by: David S. Miller --- net/bluetooth/l2cap_sock.c | 4 ++++ net/bluetooth/rfcomm/sock.c | 3 +++ net/bluetooth/sco.c | 5 ++++- security/security.c | 1 + 4 files changed, 12 insertions(+), 1 deletion(-) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 61f1f623091..e8292369cdc 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -26,6 +26,8 @@ /* Bluetooth L2CAP sockets. */ +#include + #include #include #include @@ -933,6 +935,8 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->force_reliable = pchan->force_reliable; chan->flushable = pchan->flushable; chan->force_active = pchan->force_active; + + security_sk_clone(parent, sk); } else { switch (sk->sk_type) { diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 482722bbc7a..5417f612732 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -264,6 +265,8 @@ static void rfcomm_sock_init(struct sock *sk, struct sock *parent) pi->sec_level = rfcomm_pi(parent)->sec_level; pi->role_switch = rfcomm_pi(parent)->role_switch; + + security_sk_clone(parent, sk); } else { pi->dlc->defer_setup = 0; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8270f05e3f1..a324b009e34 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -403,8 +404,10 @@ static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); - if (parent) + if (parent) { sk->sk_type = parent->sk_type; + security_sk_clone(parent, sk); + } } static struct proto sco_proto = { diff --git a/security/security.c b/security/security.c index 0e4fccfef12..d9e15339092 100644 --- a/security/security.c +++ b/security/security.c @@ -1097,6 +1097,7 @@ void security_sk_clone(const struct sock *sk, struct sock *newsk) { security_ops->sk_clone_security(sk, newsk); } +EXPORT_SYMBOL(security_sk_clone); void security_sk_classify_flow(struct sock *sk, struct flowi *fl) { -- cgit v1.2.3-70-g09d2 From d5123480b1d6f7d1a5fe1a13520cef88fb5d4c84 Mon Sep 17 00:00:00 2001 From: Gao feng Date: Tue, 11 Oct 2011 16:08:11 +0000 Subject: netconsole: enable netconsole can make net_device refcnt incorrent There is no check if netconsole is enabled current. so when exec echo 1 > enabled; the reference of net_device will increment always. Signed-off-by: Gao feng Acked-by: Flavio Leitner Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index ed2a3977c6e..e8882023576 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -307,6 +307,11 @@ static ssize_t store_enabled(struct netconsole_target *nt, return err; if (enabled < 0 || enabled > 1) return -EINVAL; + if (enabled == nt->enabled) { + printk(KERN_INFO "netconsole: network logging has already %s\n", + nt->enabled ? "started" : "stopped"); + return -EINVAL; + } if (enabled) { /* 1 */ -- cgit v1.2.3-70-g09d2 From e730c82347b9dc75914da998c44c3f348965db41 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 11 Oct 2011 23:00:41 +0000 Subject: tg3: negate USE_PHYLIB flag check USE_PHYLIB flag in tg3_remove_one() is being checked incorrectly. This results tg3_phy_fini->phy_disconnect is never called and when tg3 module is removed. In my case this resulted in panics in phy_state_machine calling function phydev->adjust_link. So correct this check. Signed-off-by: Jiri Pirko Acked-by: Matt Carlson Signed-off-by: David S. Miller --- drivers/net/tg3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 4a1374df608..c11a2b8327f 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -15577,7 +15577,7 @@ static void __devexit tg3_remove_one(struct pci_dev *pdev) cancel_work_sync(&tp->reset_task); - if (!tg3_flag(tp, USE_PHYLIB)) { + if (tg3_flag(tp, USE_PHYLIB)) { tg3_phy_fini(tp); tg3_mdio_fini(tp); } -- cgit v1.2.3-70-g09d2 From 28c213793c994e4aac5f669ce856b5682a549bbb Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Wed, 12 Oct 2011 02:29:39 +0000 Subject: smsc911x: Add support for SMSC LAN89218 LAN89218 is register compatible with LAN911x. Signed-off-by: Phil Edworthy Signed-off-by: David S. Miller --- drivers/net/smsc911x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index b9016a30cdc..c90ddb61cc5 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -26,6 +26,7 @@ * LAN9215, LAN9216, LAN9217, LAN9218 * LAN9210, LAN9211 * LAN9220, LAN9221 + * LAN89218 * */ @@ -1983,6 +1984,7 @@ static int __devinit smsc911x_init(struct net_device *dev) case 0x01170000: case 0x01160000: case 0x01150000: + case 0x218A0000: /* LAN911[5678] family */ pdata->generation = pdata->idrev & 0x0000FFFF; break; -- cgit v1.2.3-70-g09d2 From 4d97480b1806e883eb1c7889d4e7a87e936e06d9 Mon Sep 17 00:00:00 2001 From: Mitsuo Hayasaka Date: Wed, 12 Oct 2011 16:04:29 +0000 Subject: bonding: use local function pointer of bond->recv_probe in bond_handle_frame The bond->recv_probe is called in bond_handle_frame() when a packet is received, but bond_close() sets it to NULL. So, a panic occurs when both functions work in parallel. Why this happen: After null pointer check of bond->recv_probe, an sk_buff is duplicated and bond->recv_probe is called in bond_handle_frame. So, a panic occurs when bond_close() is called between the check and call of bond->recv_probe. Patch: This patch uses a local function pointer of bond->recv_probe in bond_handle_frame(). So, it can avoid the null pointer dereference. Signed-off-by: Mitsuo Hayasaka Cc: Jay Vosburgh Cc: Andy Gospodarek Cc: Eric Dumazet Cc: WANG Cong Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6d79b78cfc7..de3d351ccb6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1435,6 +1435,8 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) struct sk_buff *skb = *pskb; struct slave *slave; struct bonding *bond; + void (*recv_probe)(struct sk_buff *, struct bonding *, + struct slave *); skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) @@ -1448,11 +1450,12 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) if (bond->params.arp_interval) slave->dev->last_rx = jiffies; - if (bond->recv_probe) { + recv_probe = ACCESS_ONCE(bond->recv_probe); + if (recv_probe) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (likely(nskb)) { - bond->recv_probe(nskb, bond, slave); + recv_probe(nskb, bond, slave); dev_kfree_skb(nskb); } } -- cgit v1.2.3-70-g09d2 From 8bae8bd6cb24eecad9fda3e125d36ab9c67d3fd7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Oct 2011 17:01:47 +0000 Subject: pptp: fix skb leak in pptp_xmit() In case we cant transmit skb, we must free it Signed-off-by: Eric Dumazet CC: Dmitry Kozlov Signed-off-by: David S. Miller --- drivers/net/pptp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c index eae542a7e98..9c0403d0107 100644 --- a/drivers/net/pptp.c +++ b/drivers/net/pptp.c @@ -285,8 +285,10 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) ip_send_check(iph); ip_local_out(skb); + return 1; tx_error: + kfree_skb(skb); return 1; } -- cgit v1.2.3-70-g09d2 From 58af19e387d8821927e49be3f467da5e6a0aa8fd Mon Sep 17 00:00:00 2001 From: KOVACS Krisztian Date: Tue, 18 Oct 2011 10:17:35 +0000 Subject: tproxy: copy transparent flag when creating a time wait The transparent socket option setting was not copied to the time wait socket when an inet socket was being replaced by a time wait socket. This broke the --transparent option of the socket match and may have caused that FIN packets belonging to sockets in FIN_WAIT2 or TIME_WAIT state were being dropped by the packet filter. Signed-off-by: KOVACS Krisztian Signed-off-by: David S. Miller --- net/ipv4/tcp_minisocks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d2fe4e06b47..0ce3d06dce6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -328,6 +328,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); + tw->tw_transparent = inet_sk(sk)->transparent; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; -- cgit v1.2.3-70-g09d2 From 4ea2739ea89883ddf79980a8aa27d5e57093e464 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Oct 2011 17:59:53 +0000 Subject: pptp: pptp_rcv_core() misses pskb_may_pull() call e1000e uses paged frags, so any layer incorrectly pulling bytes from skb can trigger a BUG in skb_pull() [951.142737] [] skb_pull+0x15/0x17 [951.142737] [] pptp_rcv_core+0x126/0x19a [pptp] [951.152725] [] sk_receive_skb+0x69/0x105 [951.163558] [] pptp_rcv+0xc8/0xdc [pptp] [951.165092] [] gre_rcv+0x62/0x75 [gre] [951.165092] [] ip_local_deliver_finish+0x150/0x1c1 [951.177599] [] ? ip_local_deliver_finish+0x0/0x1c1 [951.177599] [] NF_HOOK.clone.7+0x51/0x58 [951.177599] [] ip_local_deliver+0x51/0x55 [951.177599] [] ip_rcv_finish+0x31a/0x33e [951.177599] [] ? ip_rcv_finish+0x0/0x33e [951.204898] [] NF_HOOK.clone.7+0x51/0x58 [951.214651] [] ip_rcv+0x21b/0x246 pptp_rcv_core() is a nice example of a function assuming everything it needs is available in skb head. Reported-by: Bradley Peterson Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/pptp.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/net/pptp.c b/drivers/net/pptp.c index 9c0403d0107..89f829f5f72 100644 --- a/drivers/net/pptp.c +++ b/drivers/net/pptp.c @@ -307,11 +307,18 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) } header = (struct pptp_gre_header *)(skb->data); + headersize = sizeof(*header); /* test if acknowledgement present */ if (PPTP_GRE_IS_A(header->ver)) { - __u32 ack = (PPTP_GRE_IS_S(header->flags)) ? - header->ack : header->seq; /* ack in different place if S = 0 */ + __u32 ack; + + if (!pskb_may_pull(skb, headersize)) + goto drop; + header = (struct pptp_gre_header *)(skb->data); + + /* ack in different place if S = 0 */ + ack = PPTP_GRE_IS_S(header->flags) ? header->ack : header->seq; ack = ntohl(ack); @@ -320,21 +327,18 @@ static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) /* also handle sequence number wrap-around */ if (WRAPPED(ack, opt->ack_recv)) opt->ack_recv = ack; + } else { + headersize -= sizeof(header->ack); } - /* test if payload present */ if (!PPTP_GRE_IS_S(header->flags)) goto drop; - headersize = sizeof(*header); payload_len = ntohs(header->payload_len); seq = ntohl(header->seq); - /* no ack present? */ - if (!PPTP_GRE_IS_A(header->ver)) - headersize -= sizeof(header->ack); /* check for incomplete packet (length smaller than expected) */ - if (skb->len - headersize < payload_len) + if (!pskb_may_pull(skb, headersize + payload_len)) goto drop; payload = skb->data + headersize; -- cgit v1.2.3-70-g09d2 From 34b1901abdf8793cd679d0e48012d3d7570f88d6 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 13 Oct 2011 09:56:19 +0000 Subject: ehea: Change maintainer to me MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Breno Leitao has passed the maintainership to me. Signed-off-by: Thadeu Lima de Souza Cascardo Cc: Breno Leitao Acked-by: Breno Leitão Signed-off-by: David S. Miller --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 5483e0c93b4..b3bc88d9c03 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2460,7 +2460,7 @@ S: Supported F: drivers/infiniband/hw/ehca/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Breno Leitao +M: Thadeu Lima de Souza Cascardo L: netdev@vger.kernel.org S: Maintained F: drivers/net/ehea/ -- cgit v1.2.3-70-g09d2 From 649b3b8c4e8681de443b4dc9e387c3036369e02e Mon Sep 17 00:00:00 2001 From: françois romieu Date: Fri, 14 Oct 2011 00:57:45 +0000 Subject: r8169: fix driver shutdown WoL regression. Due to commit 92fc43b4159b518f5baae57301f26d770b0834c9 ("r8169: modify the flow of the hw reset."), rtl8169_hw_reset stomps during driver shutdown on RxConfig bits which are needed for WOL on some versions of the hardware. As these bits were formerly set from the r81{0x, 68}_pll_power_down methods, factor them out for use in the driver shutdown (rtl_shutdown) handler. I favored __rtl8169_get_wol() -hardware state indication- over RTL_FEATURE_WOL as the latter has become a good candidate for removal. Signed-off-by: Francois Romieu Cc: Hayes Tested-by: Marc Ballarin Signed-off-by: David S. Miller --- drivers/net/r8169.c | 88 ++++++++++++++++++++++++++++++++++------------------- 1 file changed, 56 insertions(+), 32 deletions(-) diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index c2366701792..24219ec0de1 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -3316,6 +3316,37 @@ static void __devinit rtl_init_mdio_ops(struct rtl8169_private *tp) } } +static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) +{ + void __iomem *ioaddr = tp->mmio_addr; + + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_29: + case RTL_GIGA_MAC_VER_30: + case RTL_GIGA_MAC_VER_32: + case RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_34: + RTL_W32(RxConfig, RTL_R32(RxConfig) | + AcceptBroadcast | AcceptMulticast | AcceptMyPhys); + break; + default: + break; + } +} + +static bool rtl_wol_pll_power_down(struct rtl8169_private *tp) +{ + if (!(__rtl8169_get_wol(tp) & WAKE_ANY)) + return false; + + rtl_writephy(tp, 0x1f, 0x0000); + rtl_writephy(tp, MII_BMCR, 0x0000); + + rtl_wol_suspend_quirk(tp); + + return true; +} + static void r810x_phy_power_down(struct rtl8169_private *tp) { rtl_writephy(tp, 0x1f, 0x0000); @@ -3330,18 +3361,8 @@ static void r810x_phy_power_up(struct rtl8169_private *tp) static void r810x_pll_power_down(struct rtl8169_private *tp) { - void __iomem *ioaddr = tp->mmio_addr; - - if (__rtl8169_get_wol(tp) & WAKE_ANY) { - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, MII_BMCR, 0x0000); - - if (tp->mac_version == RTL_GIGA_MAC_VER_29 || - tp->mac_version == RTL_GIGA_MAC_VER_30) - RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast | - AcceptMulticast | AcceptMyPhys); + if (rtl_wol_pll_power_down(tp)) return; - } r810x_phy_power_down(tp); } @@ -3430,17 +3451,8 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) tp->mac_version == RTL_GIGA_MAC_VER_33) rtl_ephy_write(ioaddr, 0x19, 0xff64); - if (__rtl8169_get_wol(tp) & WAKE_ANY) { - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, MII_BMCR, 0x0000); - - if (tp->mac_version == RTL_GIGA_MAC_VER_32 || - tp->mac_version == RTL_GIGA_MAC_VER_33 || - tp->mac_version == RTL_GIGA_MAC_VER_34) - RTL_W32(RxConfig, RTL_R32(RxConfig) | AcceptBroadcast | - AcceptMulticast | AcceptMyPhys); + if (rtl_wol_pll_power_down(tp)) return; - } r8168_phy_power_down(tp); @@ -5788,11 +5800,30 @@ static const struct dev_pm_ops rtl8169_pm_ops = { #endif /* !CONFIG_PM */ +static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) +{ + void __iomem *ioaddr = tp->mmio_addr; + + /* WoL fails with 8168b when the receiver is disabled. */ + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_11: + case RTL_GIGA_MAC_VER_12: + case RTL_GIGA_MAC_VER_17: + pci_clear_master(tp->pci_dev); + + RTL_W8(ChipCmd, CmdRxEnb); + /* PCI commit */ + RTL_R8(ChipCmd); + break; + default: + break; + } +} + static void rtl_shutdown(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct rtl8169_private *tp = netdev_priv(dev); - void __iomem *ioaddr = tp->mmio_addr; rtl8169_net_suspend(dev); @@ -5806,16 +5837,9 @@ static void rtl_shutdown(struct pci_dev *pdev) spin_unlock_irq(&tp->lock); if (system_state == SYSTEM_POWER_OFF) { - /* WoL fails with 8168b when the receiver is disabled. */ - if ((tp->mac_version == RTL_GIGA_MAC_VER_11 || - tp->mac_version == RTL_GIGA_MAC_VER_12 || - tp->mac_version == RTL_GIGA_MAC_VER_17) && - (tp->features & RTL_FEATURE_WOL)) { - pci_clear_master(pdev); - - RTL_W8(ChipCmd, CmdRxEnb); - /* PCI commit */ - RTL_R8(ChipCmd); + if (__rtl8169_get_wol(tp) & WAKE_ANY) { + rtl_wol_suspend_quirk(tp); + rtl_wol_shutdown_quirk(tp); } pci_wake_from_d3(pdev, true); -- cgit v1.2.3-70-g09d2 From 1b23a3e3d1b969e285c57a2d38f3739283ecfb80 Mon Sep 17 00:00:00 2001 From: hayeswang Date: Thu, 13 Oct 2011 20:14:37 +0000 Subject: r8169: fix wrong eee setting for rlt8111evl Correct the wrong parameter for setting EEE for RTL8111E-VL. Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/r8169.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 24219ec0de1..6d657cabb95 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -2859,7 +2859,7 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp) rtl_writephy(tp, 0x1f, 0x0004); rtl_writephy(tp, 0x1f, 0x0007); rtl_writephy(tp, 0x1e, 0x0020); - rtl_w1w0_phy(tp, 0x06, 0x0000, 0x0100); + rtl_w1w0_phy(tp, 0x15, 0x0000, 0x0100); rtl_writephy(tp, 0x1f, 0x0002); rtl_writephy(tp, 0x1f, 0x0000); rtl_writephy(tp, 0x0d, 0x0007); -- cgit v1.2.3-70-g09d2 From afaef734e5f0004916d07ecf7d86292cdd00d59b Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 17 Oct 2011 15:20:28 +0000 Subject: fib_rules: fix unresolved_rules counting we should decrease ops->unresolved_rules when deleting a unresolved rule. Signed-off-by: Zheng Yan Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/fib_rules.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3231b468bb7..27071ee2a4e 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -475,8 +475,11 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_del_rcu(&rule->list); - if (rule->action == FR_ACT_GOTO) + if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } /* * Check if this rule is a target to any of them. If so, -- cgit v1.2.3-70-g09d2