From ef3a62d272f033989e83eb1f26505f93f93e3e69 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 18 Jun 2008 15:39:48 -0700 Subject: mac80211: detect driver tx bugs When a driver rejects a frame in it's ->tx() callback, it must also stop queues, otherwise mac80211 can go into a loop here. Detect this situation and abort the loop after five retries, warning about the driver bug. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- net/mac80211/tx.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 28d8bd53bd3..c80d5899f27 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1132,7 +1132,7 @@ static int ieee80211_tx(struct net_device *dev, struct sk_buff *skb, ieee80211_tx_handler *handler; struct ieee80211_tx_data tx; ieee80211_tx_result res = TX_DROP, res_prepare; - int ret, i; + int ret, i, retries = 0; WARN_ON(__ieee80211_queue_pending(local, control->queue)); @@ -1216,6 +1216,13 @@ retry: if (!__ieee80211_queue_stopped(local, control->queue)) { clear_bit(IEEE80211_LINK_STATE_PENDING, &local->state[control->queue]); + retries++; + /* + * Driver bug, it's rejecting packets but + * not stopping queues. + */ + if (WARN_ON_ONCE(retries > 5)) + goto drop; goto retry; } memcpy(&store->control, control, -- cgit v1.2.2 From aea7427f70cce5fa8f99ce447b213e9e3b49f24c Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Thu, 19 Jun 2008 16:29:39 -0700 Subject: ipv6: Remove options header when setsockopt's optlen is 0 Remove the sticky Hop-by-Hop options header by calling setsockopt() for IPV6_HOPOPTS with a zero option length, per RFC3542. Routing header and Destination options header does the same as Hop-by-Hop options header. Signed-off-by: Shan Wei Acked-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- net/ipv6/ipv6_sockglue.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c042ce19bd1..86e28a75267 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -345,18 +345,21 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + + /* remove any sticky options header with a zero option + * length, per RFC3542. + */ if (optlen == 0) optval = NULL; + else if (optlen < sizeof(struct ipv6_opt_hdr) || + optlen & 0x7 || optlen > 8 * 255) + goto e_inval; /* hop-by-hop / destination options are privileged option */ retv = -EPERM; if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) break; - if (optlen < sizeof(struct ipv6_opt_hdr) || - optlen & 0x7 || optlen > 8 * 255) - goto e_inval; - opt = ipv6_renew_options(sk, np->opt, optname, (struct ipv6_opt_hdr __user *)optval, optlen); -- cgit v1.2.2 From f630e43a215a3129d0c1173cae0bce6ea4855cf7 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 19 Jun 2008 16:33:57 -0700 Subject: ipv6: Drop packets for loopback address from outside of the box. [ Based upon original report and patch by Karsten Keil. Karsten has verified that this fixes the TAHI test case "ICMPv6 test v6LC.5.1.2 Part F". -DaveM ] Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ipv6.h | 6 ++++++ net/ipv6/ip6_input.c | 9 +++++++++ 2 files changed, 15 insertions(+) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e0a612bc9c4..f422f7218e1 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -367,6 +367,12 @@ static inline int ipv6_addr_any(const struct in6_addr *a) a->s6_addr32[2] | a->s6_addr32[3] ) == 0); } +static inline int ipv6_addr_loopback(const struct in6_addr *a) +{ + return ((a->s6_addr32[0] | a->s6_addr32[1] | + a->s6_addr32[2] | (a->s6_addr32[3] ^ htonl(1))) == 0); +} + static inline int ipv6_addr_v4mapped(const struct in6_addr *a) { return ((a->s6_addr32[0] | a->s6_addr32[1] | diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 4e5c8615832..17eb48b8e32 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -102,6 +102,15 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (hdr->version != 6) goto err; + /* + * RFC4291 2.5.3 + * A packet received on an interface with a destination address + * of loopback must be dropped. + */ + if (!(dev->flags & IFF_LOOPBACK) && + ipv6_addr_loopback(&hdr->daddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); -- cgit v1.2.2 From 2645a3c3761ac25498db2e627271016c849c68e1 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 20 Jun 2008 21:58:02 -0700 Subject: pppoe: warning fix Fix warning: drivers/net/pppoe.c: In function 'pppoe_recvmsg': drivers/net/pppoe.c:945: warning: comparison of distinct pointer types lacks a cast because skb->len is unsigned int and total_len is size_t Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/pppoe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index bafb69b6f7c..fc6f4b8c64b 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -942,7 +942,7 @@ static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock, m->msg_namelen = 0; if (skb) { - total_len = min(total_len, skb->len); + total_len = min_t(size_t, total_len, skb->len); error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len); if (error == 0) error = total_len; -- cgit v1.2.2 From 735ce972fbc8a65fb17788debd7bbe7b4383cc62 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 20 Jun 2008 22:04:34 -0700 Subject: sctp: Make sure N * sizeof(union sctp_addr) does not overflow. As noticed by Gabriel Campana, the kmalloc() length arg passed in by sctp_getsockopt_local_addrs_old() can overflow if ->addr_num is large enough. Therefore, enforce an appropriate limit. Signed-off-by: David S. Miller --- net/sctp/socket.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e7e3baf7009..0dbcde6758e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4401,7 +4401,9 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, if (copy_from_user(&getaddrs, optval, len)) return -EFAULT; - if (getaddrs.addr_num <= 0) return -EINVAL; + if (getaddrs.addr_num <= 0 || + getaddrs.addr_num >= (INT_MAX / sizeof(union sctp_addr))) + return -EINVAL; /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound -- cgit v1.2.2 From b9f75f45a6b46a0ab4eb0857d437a0845871f314 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 20 Jun 2008 22:16:51 -0700 Subject: netns: Don't receive new packets in a dead network namespace. Alexey Dobriyan writes: > Subject: ICMP sockets destruction vs ICMP packets oops > After icmp_sk_exit() nuked ICMP sockets, we get an interrupt. > icmp_reply() wants ICMP socket. > > Steps to reproduce: > > launch shell in new netns > move real NIC to netns > setup routing > ping -i 0 > exit from shell > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 > IP: [] icmp_sk+0x17/0x30 > PGD 17f3cd067 PUD 17f3ce067 PMD 0 > Oops: 0000 [1] PREEMPT SMP DEBUG_PAGEALLOC > CPU 0 > Modules linked in: usblp usbcore > Pid: 0, comm: swapper Not tainted 2.6.26-rc6-netns-ct #4 > RIP: 0010:[] [] icmp_sk+0x17/0x30 > RSP: 0018:ffffffff8057fc30 EFLAGS: 00010286 > RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff81017c7db900 > RDX: 0000000000000034 RSI: ffff81017c7db900 RDI: ffff81017dc41800 > RBP: ffffffff8057fc40 R08: 0000000000000001 R09: 000000000000a815 > R10: 0000000000000000 R11: 0000000000000001 R12: ffffffff8057fd28 > R13: ffffffff8057fd00 R14: ffff81017c7db938 R15: ffff81017dc41800 > FS: 0000000000000000(0000) GS:ffffffff80525000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 000000017fcda000 CR4: 00000000000006e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Process swapper (pid: 0, threadinfo ffffffff8053a000, task ffffffff804fa4a0) > Stack: 0000000000000000 ffff81017c7db900 ffffffff8057fcf0 ffffffff803fcfe4 > ffffffff804faa38 0000000000000246 0000000000005a40 0000000000000246 > 000000000001ffff ffff81017dd68dc0 0000000000005a40 0000000055342436 > Call Trace: > [] icmp_reply+0x44/0x1e0 > [] ? ip_route_input+0x23a/0x1360 > [] icmp_echo+0x65/0x70 > [] icmp_rcv+0x180/0x1b0 > [] ip_local_deliver+0xf4/0x1f0 > [] ip_rcv+0x33b/0x650 > [] netif_receive_skb+0x27a/0x340 > [] process_backlog+0x9d/0x100 > [] net_rx_action+0x18d/0x250 > [] __do_softirq+0x75/0x100 > [] call_softirq+0x1c/0x30 > [] do_softirq+0x65/0xa0 > [] irq_exit+0x97/0xa0 > [] do_IRQ+0xa8/0x130 > [] ? mwait_idle+0x0/0x60 > [] ret_from_intr+0x0/0xf > [] ? mwait_idle+0x4c/0x60 > [] ? mwait_idle+0x43/0x60 > [] ? cpu_idle+0x57/0xa0 > [] ? rest_init+0x70/0x80 > Code: 10 5b 41 5c 41 5d 41 5e c9 c3 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 53 > 48 83 ec 08 48 8b 9f 78 01 00 00 e8 2b c7 f1 ff 89 c0 <48> 8b 04 c3 48 83 c4 08 > 5b c9 c3 66 66 66 66 66 2e 0f 1f 84 00 > RIP [] icmp_sk+0x17/0x30 > RSP > CR2: 0000000000000000 > ---[ end trace ea161157b76b33e8 ]--- > Kernel panic - not syncing: Aiee, killing interrupt handler! Receiving packets while we are cleaning up a network namespace is a racy proposition. It is possible when the packet arrives that we have removed some but not all of the state we need to fully process it. We have the choice of either playing wack-a-mole with the cleanup routines or simply dropping packets when we don't have a network namespace to handle them. Since the check looks inexpensive in netif_receive_skb let's just drop the incoming packets. Signed-off-by: Eric W. Biederman Signed-off-by: David S. Miller --- include/net/net_namespace.h | 11 +++++++++++ net/core/dev.c | 4 ++++ net/core/net_namespace.c | 3 +++ 3 files changed, 18 insertions(+) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index aa540e6be50..d9dd0f70729 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -95,6 +95,11 @@ extern struct list_head net_namespace_list; #ifdef CONFIG_NET_NS extern void __put_net(struct net *net); +static inline int net_alive(struct net *net) +{ + return net && atomic_read(&net->count); +} + static inline struct net *get_net(struct net *net) { atomic_inc(&net->count); @@ -125,6 +130,12 @@ int net_eq(const struct net *net1, const struct net *net2) return net1 == net2; } #else + +static inline int net_alive(struct net *net) +{ + return 1; +} + static inline struct net *get_net(struct net *net) { return net; diff --git a/net/core/dev.c b/net/core/dev.c index 68d8df0992a..c421a1f8f0b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2077,6 +2077,10 @@ int netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); + /* Don't receive packets in an exiting network namespace */ + if (!net_alive(dev_net(skb->dev))) + goto out; + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 72b4c184dd8..7c52fe277b6 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -140,6 +140,9 @@ static void cleanup_net(struct work_struct *work) struct pernet_operations *ops; struct net *net; + /* Be very certain incoming network packets will not find us */ + rcu_barrier(); + net = container_of(work, struct net, work); mutex_lock(&net_mutex); -- cgit v1.2.2