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 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e0a612bc9c4e..f422f7218e1c 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] | -- cgit v1.2.3 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(+) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index aa540e6be502..d9dd0f707296 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 68d8df0992ab..c421a1f8f0b9 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 72b4c184dd84..7c52fe277b62 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 v1.2.3 From c88e6f51c2154c7606f7e281bcca2d1a2c89d7b2 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Fri, 27 Jun 2008 19:54:54 -0700 Subject: include/linux/netdevice.h: don't export MAX_HEADER to userspace Due to the CONFIG_'s the value is anyway not correct in userspace. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f27fd2009334..25f87102ab66 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -88,6 +88,8 @@ struct wireless_dev; #define NETDEV_TX_BUSY 1 /* driver tx path was busy*/ #define NETDEV_TX_LOCKED -1 /* driver tx lock was already taken */ +#ifdef __KERNEL__ + /* * Compute the worst case header length according to the protocols * used. @@ -114,6 +116,8 @@ struct wireless_dev; #define MAX_HEADER (LL_MAX_HEADER + 48) #endif +#endif /* __KERNEL__ */ + struct net_device_subqueue { /* Give a control state for each queue. This struct may contain -- cgit v1.2.3 From 251a4b320f2352598f84e4452ab538aa8064af52 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 27 Jun 2008 20:09:00 -0700 Subject: net/inet_lro: remove setting skb->ip_summed when not LRO-able When an SKB cannot be chained to a session, the current code attempts to "restore" its ip_summed field from lro_mgr->ip_summed. However, lro_mgr->ip_summed does not hold the original value; in fact, we'd better not touch skb->ip_summed since it is not modified by the code in the path leading to a failure to chain it. Also use a cleaer comment to the describe the ip_summed field of struct net_lro_mgr. Issue raised by Or Gerlitz Signed-off-by: Eli Cohen Signed-off-by: David S. Miller --- include/linux/inet_lro.h | 6 +++++- net/ipv4/inet_lro.c | 3 +-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/inet_lro.h b/include/linux/inet_lro.h index 80335b7d77c5..c4335faebb63 100644 --- a/include/linux/inet_lro.h +++ b/include/linux/inet_lro.h @@ -84,7 +84,11 @@ struct net_lro_mgr { from received packets and eth protocol is still ETH_P_8021Q */ - u32 ip_summed; /* Set in non generated SKBs in page mode */ + /* + * Set for generated SKBs that are not added to + * the frag list in fragmented mode + */ + u32 ip_summed; u32 ip_summed_aggr; /* Set in aggregated SKBs: CHECKSUM_UNNECESSARY * or CHECKSUM_NONE */ diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 4a4d49fca1f2..cfd034a2b96e 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -383,8 +383,7 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, out2: /* send aggregated SKBs to stack */ lro_flush(lro_mgr, lro_desc); -out: /* Original SKB has to be posted to stack */ - skb->ip_summed = lro_mgr->ip_summed; +out: return 1; } -- cgit v1.2.3