Message ID | 1492211174-28936-3-git-send-email-azhou@ovn.org |
---|---|
State | Accepted |
Headers | show |
On 14 April 2017 at 16:06, Andy Zhou <azhou@ovn.org> wrote: > From: Eric Dumazet <edumazet@google.com> > > Upstream commit: > ipv6: orphan skbs in reassembly unit > > Andrey reported a use-after-free in IPv6 stack. > > Issue here is that we free the socket while it still has skb > in TX path and in some queues. > > It happens here because IPv6 reassembly unit messes skb->truesize, > breaking skb_set_owner_w() badly. > > We fixed a similar issue for IPV4 in commit 8282f27449bf ("inet: frag: > Always orphan skbs inside ip_defrag()") > Acked-by: Joe Stringer <joe@ovn.org> > > ================================================================== > BUG: KASAN: use-after-free in sock_wfree+0x118/0x120 > Read of size 8 at addr ffff880062da0060 by task a.out/4140 > > page:ffffea00018b6800 count:1 mapcount:0 mapping: (null) > index:0x0 compound_mapcount: 0 > flags: 0x100000000008100(slab|head) > raw: 0100000000008100 0000000000000000 0000000000000000 0000000180130013 > raw: dead000000000100 dead000000000200 ffff88006741f140 0000000000000000 > page dumped because: kasan: bad access detected > > CPU: 0 PID: 4140 Comm: a.out Not tainted 4.10.0-rc3+ #59 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 > Call Trace: > __dump_stack lib/dump_stack.c:15 > dump_stack+0x292/0x398 lib/dump_stack.c:51 > describe_address mm/kasan/report.c:262 > kasan_report_error+0x121/0x560 mm/kasan/report.c:370 > kasan_report mm/kasan/report.c:392 > __asan_report_load8_noabort+0x3e/0x40 mm/kasan/report.c:413 > sock_flag ./arch/x86/include/asm/bitops.h:324 > sock_wfree+0x118/0x120 net/core/sock.c:1631 > skb_release_head_state+0xfc/0x250 net/core/skbuff.c:655 > skb_release_all+0x15/0x60 net/core/skbuff.c:668 > __kfree_skb+0x15/0x20 net/core/skbuff.c:684 > kfree_skb+0x16e/0x4e0 net/core/skbuff.c:705 > inet_frag_destroy+0x121/0x290 net/ipv4/inet_fragment.c:304 > inet_frag_put ./include/net/inet_frag.h:133 > nf_ct_frag6_gather+0x1125/0x38b0 net/ipv6/netfilter/nf_conntrack_reasm.c:617 > ipv6_defrag+0x21b/0x350 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68 > nf_hook_entry_hookfn ./include/linux/netfilter.h:102 > nf_hook_slow+0xc3/0x290 net/netfilter/core.c:310 > nf_hook ./include/linux/netfilter.h:212 > __ip6_local_out+0x52c/0xaf0 net/ipv6/output_core.c:160 > ip6_local_out+0x2d/0x170 net/ipv6/output_core.c:170 > ip6_send_skb+0xa1/0x340 net/ipv6/ip6_output.c:1722 > ip6_push_pending_frames+0xb3/0xe0 net/ipv6/ip6_output.c:1742 > rawv6_push_pending_frames net/ipv6/raw.c:613 > rawv6_sendmsg+0x2cff/0x4130 net/ipv6/raw.c:927 > inet_sendmsg+0x164/0x5b0 net/ipv4/af_inet.c:744 > sock_sendmsg_nosec net/socket.c:635 > sock_sendmsg+0xca/0x110 net/socket.c:645 > sock_write_iter+0x326/0x620 net/socket.c:848 > new_sync_write fs/read_write.c:499 > __vfs_write+0x483/0x760 fs/read_write.c:512 > vfs_write+0x187/0x530 fs/read_write.c:560 > SYSC_write fs/read_write.c:607 > SyS_write+0xfb/0x230 fs/read_write.c:599 > entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203 > RIP: 0033:0x7ff26e6f5b79 > RSP: 002b:00007ff268e0ed98 EFLAGS: 00000206 ORIG_RAX: 0000000000000001 > RAX: ffffffffffffffda RBX: 00007ff268e0f9c0 RCX: 00007ff26e6f5b79 > RDX: 0000000000000010 RSI: 0000000020f50fe1 RDI: 0000000000000003 > RBP: 00007ff26ebc1220 R08: 0000000000000000 R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000000 > R13: 00007ff268e0f9c0 R14: 00007ff26efec040 R15: 0000000000000003 > > The buggy address belongs to the object at ffff880062da0000 > which belongs to the cache RAWv6 of size 1504 > The buggy address ffff880062da0060 is located 96 bytes inside > of 1504-byte region [ffff880062da0000, ffff880062da05e0) > > Freed by task 4113: > save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57 > save_stack+0x43/0xd0 mm/kasan/kasan.c:502 > set_track mm/kasan/kasan.c:514 > kasan_slab_free+0x73/0xc0 mm/kasan/kasan.c:578 > slab_free_hook mm/slub.c:1352 > slab_free_freelist_hook mm/slub.c:1374 > slab_free mm/slub.c:2951 > kmem_cache_free+0xb2/0x2c0 mm/slub.c:2973 > sk_prot_free net/core/sock.c:1377 > __sk_destruct+0x49c/0x6e0 net/core/sock.c:1452 > sk_destruct+0x47/0x80 net/core/sock.c:1460 > __sk_free+0x57/0x230 net/core/sock.c:1468 > sk_free+0x23/0x30 net/core/sock.c:1479 > sock_put ./include/net/sock.h:1638 > sk_common_release+0x31e/0x4e0 net/core/sock.c:2782 > rawv6_close+0x54/0x80 net/ipv6/raw.c:1214 > inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425 > inet6_release+0x50/0x70 net/ipv6/af_inet6.c:431 > sock_release+0x8d/0x1e0 net/socket.c:599 > sock_close+0x16/0x20 net/socket.c:1063 > __fput+0x332/0x7f0 fs/file_table.c:208 > ____fput+0x15/0x20 fs/file_table.c:244 > task_work_run+0x19b/0x270 kernel/task_work.c:116 > exit_task_work ./include/linux/task_work.h:21 > do_exit+0x186b/0x2800 kernel/exit.c:839 > do_group_exit+0x149/0x420 kernel/exit.c:943 > SYSC_exit_group kernel/exit.c:954 > SyS_exit_group+0x1d/0x20 kernel/exit.c:952 > entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203 > > Allocated by task 4115: > save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:57 > save_stack+0x43/0xd0 mm/kasan/kasan.c:502 > set_track mm/kasan/kasan.c:514 > kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:605 > kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:544 > slab_post_alloc_hook mm/slab.h:432 > slab_alloc_node mm/slub.c:2708 > slab_alloc mm/slub.c:2716 > kmem_cache_alloc+0x1af/0x250 mm/slub.c:2721 > sk_prot_alloc+0x65/0x2a0 net/core/sock.c:1334 > sk_alloc+0x105/0x1010 net/core/sock.c:1396 > inet6_create+0x44d/0x1150 net/ipv6/af_inet6.c:183 > __sock_create+0x4f6/0x880 net/socket.c:1199 > sock_create net/socket.c:1239 > SYSC_socket net/socket.c:1269 > SyS_socket+0xf9/0x230 net/socket.c:1249 > entry_SYSCALL_64_fastpath+0x1f/0xc2 arch/x86/entry/entry_64.S:203 > > Memory state around the buggy address: > ffff880062d9ff00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc > ffff880062d9ff80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc > >ffff880062da0000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb > ^ > ffff880062da0080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb > ffff880062da0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb > ================================================================== > > Reported-by: Andrey Konovalov <andreyknvl@google.com> > Signed-off-by: Eric Dumazet <edumazet@google.com> > Signed-off-by: David S. Miller <davem@davemloft.net> > > This patch is a bugfix, and will be progressively backported to earlier > kernels. If it is backported to any kernel 4.5 through 4.10, then users > use that updated kernel with the OVS kernel module prior to this patch, it > could cause a crash. The compat code here resolves such issues. > > Upstream: 48cac18ecf1d ("ipv6: orphan skbs in reassembly unit") > Signed-off-by: Joe Stringer <joe@ovn.org> > Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Joe Stringer <joe@ovn.org>
diff --git a/AUTHORS.rst b/AUTHORS.rst index a8592f063f77..39bbd2c92613 100644 --- a/AUTHORS.rst +++ b/AUTHORS.rst @@ -116,6 +116,7 @@ Aymerich Edward edward.aymerich@hpe.com Edward Tomasz NapieraĆa trasz@freebsd.org Eitan Eliahu eliahue@vmware.com Eohyung Lee liquidnuker@gmail.com +Eric Dumazet edumazet@google.com Eric Garver e@erig.me Eric Sesterhenn eric.sesterhenn@lsexperts.de Ethan J. Jackson ejj@eecs.berkeley.edu diff --git a/acinclude.m4 b/acinclude.m4 index 744d8f89525c..a7aaf48b5d2f 100644 --- a/acinclude.m4 +++ b/acinclude.m4 @@ -548,10 +548,6 @@ AC_DEFUN([OVS_CHECK_LINUX_COMPAT], [ [OVS_DEFINE([HAVE_NF_CONNLABELS_GET_TAKES_BIT])]) OVS_FIND_FIELD_IFELSE([$KSRC/include/net/netfilter/nf_conntrack_labels.h], [nf_conn_labels], [words]) - OVS_GREP_IFELSE([$KSRC/include/net/netfilter/ipv6/nf_defrag_ipv6.h], - [nf_ct_frag6_consume_orig]) - OVS_GREP_IFELSE([$KSRC/include/net/netfilter/ipv6/nf_defrag_ipv6.h], - [nf_ct_frag6_output]) OVS_GREP_IFELSE([$KSRC/include/net/netfilter/nf_nat.h], [nf_ct_nat_ext_add]) OVS_GREP_IFELSE([$KSRC/include/net/netfilter/nf_nat.h], [nf_nat_alloc_null_binding]) OVS_GREP_IFELSE([$KSRC/include/net/netfilter/nf_conntrack_seqadj.h], [nf_ct_seq_adjust]) diff --git a/datapath/conntrack.c b/datapath/conntrack.c index 99a0201cc189..109b2970cc85 100644 --- a/datapath/conntrack.c +++ b/datapath/conntrack.c @@ -519,7 +519,6 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); if (err) { diff --git a/datapath/linux/compat/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/datapath/linux/compat/include/net/netfilter/ipv6/nf_defrag_ipv6.h index c65e7f2feb03..2ab6c0aa79a1 100644 --- a/datapath/linux/compat/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/datapath/linux/compat/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -5,11 +5,14 @@ #include_next <net/netfilter/ipv6/nf_defrag_ipv6.h> /* Upstream commit 029f7f3b8701 ("netfilter: ipv6: nf_defrag: avoid/free clone - * operations") changed the semantics of nf_ct_frag6_gather(), so we backport - * it for all prior kernels. + * operations") changed the semantics of nf_ct_frag6_gather(), so we need + * to backport for all prior kernels, i.e. kernel < 4.5.0. + * + * Upstream commit 48cac18ecf1d ("ipv6: orphan skbs in reassembly unit") fixes + * a bug that requires all kernels prior to this fix, i.e. kernel < 4.11.0 + * to be backported. */ -#if defined(HAVE_NF_CT_FRAG6_CONSUME_ORIG) || \ - defined(HAVE_NF_CT_FRAG6_OUTPUT) +#if LINUX_VERSION_CODE < KERNEL_VERSION(4,11,0) #define OVS_NF_DEFRAG6_BACKPORT 1 int rpl_nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user); #define nf_ct_frag6_gather rpl_nf_ct_frag6_gather diff --git a/datapath/linux/compat/nf_conntrack_reasm.c b/datapath/linux/compat/nf_conntrack_reasm.c index e633443d16e0..0bc4d9e4816c 100644 --- a/datapath/linux/compat/nf_conntrack_reasm.c +++ b/datapath/linux/compat/nf_conntrack_reasm.c @@ -498,7 +498,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) +int rpl_nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev; int fhoff, nhoff, ret; @@ -530,6 +530,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) local_bh_enable(); #endif + skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, ip6_frag_ecn(hdr)); if (fq == NULL)