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 --- net/core/dev.c | 4 ++++ net/core/net_namespace.c | 3 +++ 2 files changed, 7 insertions(+) (limited to 'net/core') 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 v1.2.3 From db43a282d3ec92ea45109c5551fff3dcc5afef02 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Fri, 27 Jun 2008 17:27:21 -0700 Subject: tcp: fix for splice receive when used with software LRO If an skb has nr_frags set to zero but its frag_list is not empty (as it can happen if software LRO is enabled), and a previous tcp_read_sock has consumed the linear part of the skb, then __skb_splice_bits: (a) incorrectly reports an error and (b) forgets to update the offset to account for the linear part Any of the two problems will cause the subsequent __skb_splice_bits call (the one that handles the frag_list skbs) to either skip data, or, if the unadjusted offset is greater then the size of the next skb in the frag_list, make tcp_splice_read loop forever. Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- net/core/skbuff.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1e556d31211..366621610e7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1292,12 +1292,14 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, { unsigned int nr_pages = spd->nr_pages; unsigned int poff, plen, len, toff, tlen; - int headlen, seg; + int headlen, seg, error = 0; toff = *offset; tlen = *total_len; - if (!tlen) + if (!tlen) { + error = 1; goto err; + } /* * if the offset is greater than the linear part, go directly to @@ -1339,7 +1341,8 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, * just jump directly to update and return, no point * in going over fragments when the output is full. */ - if (spd_fill_page(spd, virt_to_page(p), plen, poff, skb)) + error = spd_fill_page(spd, virt_to_page(p), plen, poff, skb); + if (error) goto done; tlen -= plen; @@ -1369,7 +1372,8 @@ map_frag: if (!plen) break; - if (spd_fill_page(spd, f->page, plen, poff, skb)) + error = spd_fill_page(spd, f->page, plen, poff, skb); + if (error) break; tlen -= plen; @@ -1382,7 +1386,10 @@ done: return 0; } err: - return 1; + /* update the offset to reflect the linear part skip, if any */ + if (!error) + *offset = toff; + return error; } /* -- cgit v1.2.3 From 5dbaec5dc6a4895db8bf9765a867418481ed7311 Mon Sep 17 00:00:00 2001 From: Wang Chen Date: Fri, 27 Jun 2008 19:35:16 -0700 Subject: netdevice: Fix typo of dev_unicast_add() comment Signed-off-by: Wang Chen Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index c421a1f8f0b..56b46579ff4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2973,7 +2973,7 @@ EXPORT_SYMBOL(dev_unicast_delete); /** * dev_unicast_add - add a secondary unicast address * @dev: device - * @addr: address to delete + * @addr: address to add * @alen: length of @addr * * Add a secondary unicast address to the device or increase -- cgit v1.2.3