linux/net/ipv4/datagram.c

130 lines
3.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* common UDP/RAW code
* Linux INET implementation
*
* Authors:
* Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
*/
#include <linux/types.h>
#include <linux/module.h>
#include <linux/in.h>
#include <net/ip.h>
#include <net/sock.h>
#include <net/route.h>
#include <net/tcp_states.h>
#include <net/sock_reuseport.h>
int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
struct flowi4 *fl4;
struct rtable *rt;
__be32 saddr;
int oif;
int err;
if (addr_len < sizeof(*usin))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
sk_dst_reset(sk);
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
if (!oif || netif_index_is_l3_master(sock_net(sk), oif))
oif = READ_ONCE(inet->mc_index);
if (!saddr)
saddr = READ_ONCE(inet->mc_addr);
net-next: Fix IP_UNICAST_IF option behavior for connected sockets The IP_UNICAST_IF socket option is used to set the outgoing interface for outbound packets. The IP_UNICAST_IF socket option was added as it was needed by the Wine project, since no other existing option (SO_BINDTODEVICE socket option, IP_PKTINFO socket option or the bind function) provided the needed characteristics needed by the IP_UNICAST_IF socket option. [1] The IP_UNICAST_IF socket option works well for unconnected sockets, that is, the interface specified by the IP_UNICAST_IF socket option is taken into consideration in the route lookup process when a packet is being sent. However, for connected sockets, the outbound interface is chosen when connecting the socket, and in the route lookup process which is done when a packet is being sent, the interface specified by the IP_UNICAST_IF socket option is being ignored. This inconsistent behavior was reported and discussed in an issue opened on systemd's GitHub project [2]. Also, a bug report was submitted in the kernel's bugzilla [3]. To understand the problem in more detail, we can look at what happens for UDP packets over IPv4 (The same analysis was done separately in the referenced systemd issue). When a UDP packet is sent the udp_sendmsg function gets called and the following happens: 1. The oif member of the struct ipcm_cookie ipc (which stores the output interface of the packet) is initialized by the ipcm_init_sk function to inet->sk.sk_bound_dev_if (the device set by the SO_BINDTODEVICE socket option). 2. If the IP_PKTINFO socket option was set, the oif member gets overridden by the call to the ip_cmsg_send function. 3. If no output interface was selected yet, the interface specified by the IP_UNICAST_IF socket option is used. 4. If the socket is connected and no destination address is specified in the send function, the struct ipcm_cookie ipc is not taken into consideration and the cached route, that was calculated in the connect function is being used. Thus, for a connected socket, the IP_UNICAST_IF sockopt isn't taken into consideration. This patch corrects the behavior of the IP_UNICAST_IF socket option for connect()ed sockets by taking into consideration the IP_UNICAST_IF sockopt when connecting the socket. In order to avoid reconnecting the socket, this option is still ignored when applied on an already connected socket until connect() is called again by the Richard Gobert. Change the __ip4_datagram_connect function, which is called during socket connection, to take into consideration the interface set by the IP_UNICAST_IF socket option, in a similar way to what is done in the udp_sendmsg function. [1] https://lore.kernel.org/netdev/1328685717.4736.4.camel@edumazet-laptop/T/ [2] https://github.com/systemd/systemd/issues/11935#issuecomment-618691018 [3] https://bugzilla.kernel.org/show_bug.cgi?id=210255 Signed-off-by: Richard Gobert <richardbgobert@gmail.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://lore.kernel.org/r/20220829111554.GA1771@debian Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-08-29 14:18:51 +03:00
} else if (!oif) {
oif = READ_ONCE(inet->uc_index);
}
fl4 = &inet->cork.fl.u.ip4;
ipv4: Avoid using RTO_ONLINK with ip_route_connect(). Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally, we don't have to rely on the RTO_ONLINK bit to properly set the scope of a flowi4 structure. We can just set ->flowi4_scope explicitly and avoid using RTO_ONLINK in ->flowi4_tos. This patch converts callers of ip_route_connect(). Instead of setting the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can: 1- Drop the tos parameter from ip_route_connect(): its value was entirely based on sk, which is also passed as parameter. 2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option instead of always initialising it with RT_SCOPE_UNIVERSE (let's define ip_sock_rt_scope() for this purpose). 3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is now properly initialised, we don't need to tell ip_rt_fix_tos() to adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(), which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK bit overload. Note: In the original ip_route_connect() code, __ip_route_output_key() might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the original tos variable. Now that we don't set RTO_ONLINK any more, this is not a problem and we can use fl4->flowi4_tos in flowi4_update_output(). Signed-off-by: Guillaume Nault <gnault@redhat.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-04-21 02:21:33 +03:00
rt = ip_route_connect(fl4, usin->sin_addr.s_addr, saddr, oif,
sk->sk_protocol, inet->inet_sport,
usin->sin_port, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
goto out;
}
if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) {
ip_rt_put(rt);
err = -EACCES;
goto out;
}
if (!inet->inet_saddr)
inet->inet_saddr = fl4->saddr; /* Update source address */
if (!inet->inet_rcv_saddr) {
inet->inet_rcv_saddr = fl4->saddr;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
}
inet->inet_daddr = fl4->daddr;
inet->inet_dport = usin->sin_port;
udp: Update reuse->has_conns under reuseport_lock. When we call connect() for a UDP socket in a reuseport group, we have to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket. However, the current way to set has_conns is illegal and possible to trigger that problem. reuseport_has_conns() changes has_conns under rcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock, reuseport_lock, but it doesn't for now. For this reason, there is a race below where we fail to set has_conns resulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking. cpu1 cpu2 +----+ +----+ __ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHED Note the likely(reuse) in reuseport_has_conns_set() is always true, but we put the test there for ease of review. [0] For the record, usually, sk_reuseport_cb is changed under lock_sock(). The only exception is reuseport_grow() & TCP reqsk migration case. 1) shutdown() TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk. 2) New listen() overflows reuse->socks[] and call reuseport_grow(). 3) reuse->max_socks overflows u16 with the new listener. 4) reuseport_grow() pops the old shutdown()ed listener from the array and update its sk->sk_reuseport_cb as NULL without lock_sock(). shutdown()ed TCP sk->sk_reuseport_cb can be changed without lock_sock(), but, reuseport_has_conns_set() is called only for UDP under lock_sock(), so likely(reuse) never be false in reuseport_has_conns_set(). [0]: https://lore.kernel.org/netdev/CANn89iLja=eQHbsM_Ta2sQF0tOGU8vAGrh_izRuuHjuO1ouUag@mail.gmail.com/ Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets") Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Link: https://lore.kernel.org/r/20221014182625.89913-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-10-14 21:26:25 +03:00
reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
ipv4: fix data-races around inet->inet_id UDP sendmsg() is lockless, so ip_select_ident_segs() can very well be run from multiple cpus [1] Convert inet->inet_id to an atomic_t, but implement a dedicated path for TCP, avoiding cost of a locked instruction (atomic_add_return()) Note that this patch will cause a trivial merge conflict because we added inet->flags in net-next tree. v2: added missing change in drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c (David Ahern) [1] BUG: KCSAN: data-race in __ip_make_skb / __ip_make_skb read-write to 0xffff888145af952a of 2 bytes by task 7803 on cpu 1: ip_select_ident_segs include/net/ip.h:542 [inline] ip_select_ident include/net/ip.h:556 [inline] __ip_make_skb+0x844/0xc70 net/ipv4/ip_output.c:1446 ip_make_skb+0x233/0x2c0 net/ipv4/ip_output.c:1560 udp_sendmsg+0x1199/0x1250 net/ipv4/udp.c:1260 inet_sendmsg+0x63/0x80 net/ipv4/af_inet.c:830 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg net/socket.c:748 [inline] ____sys_sendmsg+0x37c/0x4d0 net/socket.c:2494 ___sys_sendmsg net/socket.c:2548 [inline] __sys_sendmmsg+0x269/0x500 net/socket.c:2634 __do_sys_sendmmsg net/socket.c:2663 [inline] __se_sys_sendmmsg net/socket.c:2660 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2660 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff888145af952a of 2 bytes by task 7804 on cpu 0: ip_select_ident_segs include/net/ip.h:541 [inline] ip_select_ident include/net/ip.h:556 [inline] __ip_make_skb+0x817/0xc70 net/ipv4/ip_output.c:1446 ip_make_skb+0x233/0x2c0 net/ipv4/ip_output.c:1560 udp_sendmsg+0x1199/0x1250 net/ipv4/udp.c:1260 inet_sendmsg+0x63/0x80 net/ipv4/af_inet.c:830 sock_sendmsg_nosec net/socket.c:725 [inline] sock_sendmsg net/socket.c:748 [inline] ____sys_sendmsg+0x37c/0x4d0 net/socket.c:2494 ___sys_sendmsg net/socket.c:2548 [inline] __sys_sendmmsg+0x269/0x500 net/socket.c:2634 __do_sys_sendmmsg net/socket.c:2663 [inline] __se_sys_sendmmsg net/socket.c:2660 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2660 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x184d -> 0x184e Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7804 Comm: syz-executor.1 Not tainted 6.5.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 ================================================================== Fixes: 23f57406b82d ("ipv4: avoid using shared IP generator for connected sockets") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-08-19 06:17:07 +03:00
atomic_set(&inet->inet_id, get_random_u16());
sk_dst_set(sk, &rt->dst);
err = 0;
out:
return err;
}
EXPORT_SYMBOL(__ip4_datagram_connect);
int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
int res;
lock_sock(sk);
res = __ip4_datagram_connect(sk, uaddr, addr_len);
release_sock(sk);
return res;
}
EXPORT_SYMBOL(ip4_datagram_connect);
ipv4: fix a race in ip4_datagram_release_cb() Alexey gave a AddressSanitizer[1] report that finally gave a good hint at where was the origin of various problems already reported by Dormando in the past [2] Problem comes from the fact that UDP can have a lockless TX path, and concurrent threads can manipulate sk_dst_cache, while another thread, is holding socket lock and calls __sk_dst_set() in ip4_datagram_release_cb() (this was added in linux-3.8) It seems that all we need to do is to use sk_dst_check() and sk_dst_set() so that all the writers hold same spinlock (sk->sk_dst_lock) to prevent corruptions. TCP stack do not need this protection, as all sk_dst_cache writers hold the socket lock. [1] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel AddressSanitizer: heap-use-after-free in ipv4_dst_check Read of size 2 by thread T15453: [<ffffffff817daa3a>] ipv4_dst_check+0x1a/0x90 ./net/ipv4/route.c:1116 [<ffffffff8175b789>] __sk_dst_check+0x89/0xe0 ./net/core/sock.c:531 [<ffffffff81830a36>] ip4_datagram_release_cb+0x46/0x390 ??:0 [<ffffffff8175eaea>] release_sock+0x17a/0x230 ./net/core/sock.c:2413 [<ffffffff81830882>] ip4_datagram_connect+0x462/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Freed by thread T15455: [<ffffffff8178d9b8>] dst_destroy+0xa8/0x160 ./net/core/dst.c:251 [<ffffffff8178de25>] dst_release+0x45/0x80 ./net/core/dst.c:280 [<ffffffff818304c1>] ip4_datagram_connect+0xa1/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Allocated by thread T15453: [<ffffffff8178d291>] dst_alloc+0x81/0x2b0 ./net/core/dst.c:171 [<ffffffff817db3b7>] rt_dst_alloc+0x47/0x50 ./net/ipv4/route.c:1406 [< inlined >] __ip_route_output_key+0x3e8/0xf70 __mkroute_output ./net/ipv4/route.c:1939 [<ffffffff817dde08>] __ip_route_output_key+0x3e8/0xf70 ./net/ipv4/route.c:2161 [<ffffffff817deb34>] ip_route_output_flow+0x14/0x30 ./net/ipv4/route.c:2249 [<ffffffff81830737>] ip4_datagram_connect+0x317/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 [2] <4>[196727.311203] general protection fault: 0000 [#1] SMP <4>[196727.311224] Modules linked in: xt_TEE xt_dscp xt_DSCP macvlan bridge coretemp crc32_pclmul ghash_clmulni_intel gpio_ich microcode ipmi_watchdog ipmi_devintf sb_edac edac_core lpc_ich mfd_core tpm_tis tpm tpm_bios ipmi_si ipmi_msghandler isci igb libsas i2c_algo_bit ixgbe ptp pps_core mdio <4>[196727.311333] CPU: 17 PID: 0 Comm: swapper/17 Not tainted 3.10.26 #1 <4>[196727.311344] Hardware name: Supermicro X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.0 07/05/2013 <4>[196727.311364] task: ffff885e6f069700 ti: ffff885e6f072000 task.ti: ffff885e6f072000 <4>[196727.311377] RIP: 0010:[<ffffffff815f8c7f>] [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.311399] RSP: 0018:ffff885effd23a70 EFLAGS: 00010282 <4>[196727.311409] RAX: dead000000200200 RBX: ffff8854c398ecc0 RCX: 0000000000000040 <4>[196727.311423] RDX: dead000000100100 RSI: dead000000100100 RDI: dead000000200200 <4>[196727.311437] RBP: ffff885effd23a80 R08: ffffffff815fd9e0 R09: ffff885d5a590800 <4>[196727.311451] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>[196727.311464] R13: ffffffff81c8c280 R14: 0000000000000000 R15: ffff880e85ee16ce <4>[196727.311510] FS: 0000000000000000(0000) GS:ffff885effd20000(0000) knlGS:0000000000000000 <4>[196727.311554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[196727.311581] CR2: 00007a46751eb000 CR3: 0000005e65688000 CR4: 00000000000407e0 <4>[196727.311625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>[196727.311669] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 <4>[196727.311713] Stack: <4>[196727.311733] ffff8854c398ecc0 ffff8854c398ecc0 ffff885effd23ab0 ffffffff815b7f42 <4>[196727.311784] ffff88be6595bc00 ffff8854c398ecc0 0000000000000000 ffff8854c398ecc0 <4>[196727.311834] ffff885effd23ad0 ffffffff815b86c6 ffff885d5a590800 ffff8816827821c0 <4>[196727.311885] Call Trace: <4>[196727.311907] <IRQ> <4>[196727.311912] [<ffffffff815b7f42>] dst_destroy+0x32/0xe0 <4>[196727.311959] [<ffffffff815b86c6>] dst_release+0x56/0x80 <4>[196727.311986] [<ffffffff81620bd5>] tcp_v4_do_rcv+0x2a5/0x4a0 <4>[196727.312013] [<ffffffff81622b5a>] tcp_v4_rcv+0x7da/0x820 <4>[196727.312041] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312070] [<ffffffff815de02d>] ? nf_hook_slow+0x7d/0x150 <4>[196727.312097] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312125] [<ffffffff815fda92>] ip_local_deliver_finish+0xb2/0x230 <4>[196727.312154] [<ffffffff815fdd9a>] ip_local_deliver+0x4a/0x90 <4>[196727.312183] [<ffffffff815fd799>] ip_rcv_finish+0x119/0x360 <4>[196727.312212] [<ffffffff815fe00b>] ip_rcv+0x22b/0x340 <4>[196727.312242] [<ffffffffa0339680>] ? macvlan_broadcast+0x160/0x160 [macvlan] <4>[196727.312275] [<ffffffff815b0c62>] __netif_receive_skb_core+0x512/0x640 <4>[196727.312308] [<ffffffff811427fb>] ? kmem_cache_alloc+0x13b/0x150 <4>[196727.312338] [<ffffffff815b0db1>] __netif_receive_skb+0x21/0x70 <4>[196727.312368] [<ffffffff815b0fa1>] netif_receive_skb+0x31/0xa0 <4>[196727.312397] [<ffffffff815b1ae8>] napi_gro_receive+0xe8/0x140 <4>[196727.312433] [<ffffffffa00274f1>] ixgbe_poll+0x551/0x11f0 [ixgbe] <4>[196727.312463] [<ffffffff815fe00b>] ? ip_rcv+0x22b/0x340 <4>[196727.312491] [<ffffffff815b1691>] net_rx_action+0x111/0x210 <4>[196727.312521] [<ffffffff815b0db1>] ? __netif_receive_skb+0x21/0x70 <4>[196727.312552] [<ffffffff810519d0>] __do_softirq+0xd0/0x270 <4>[196727.312583] [<ffffffff816cef3c>] call_softirq+0x1c/0x30 <4>[196727.312613] [<ffffffff81004205>] do_softirq+0x55/0x90 <4>[196727.312640] [<ffffffff81051c85>] irq_exit+0x55/0x60 <4>[196727.312668] [<ffffffff816cf5c3>] do_IRQ+0x63/0xe0 <4>[196727.312696] [<ffffffff816c5aaa>] common_interrupt+0x6a/0x6a <4>[196727.312722] <EOI> <1>[196727.313071] RIP [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.313100] RSP <ffff885effd23a70> <4>[196727.313377] ---[ end trace 64b3f14fae0f2e29 ]--- <0>[196727.380908] Kernel panic - not syncing: Fatal exception in interrupt Reported-by: Alexey Preobrazhensky <preobr@google.com> Reported-by: dormando <dormando@rydia.ne> Signed-off-by: Eric Dumazet <edumazet@google.com> Fixes: 8141ed9fcedb2 ("ipv4: Add a socket release callback for datagram sockets") Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-10 17:43:01 +04:00
/* Because UDP xmit path can manipulate sk_dst_cache without holding
* socket lock, we need to use sk_dst_set() here,
* even if we own the socket lock.
*/
void ip4_datagram_release_cb(struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
ipv4: fix a race in ip4_datagram_release_cb() Alexey gave a AddressSanitizer[1] report that finally gave a good hint at where was the origin of various problems already reported by Dormando in the past [2] Problem comes from the fact that UDP can have a lockless TX path, and concurrent threads can manipulate sk_dst_cache, while another thread, is holding socket lock and calls __sk_dst_set() in ip4_datagram_release_cb() (this was added in linux-3.8) It seems that all we need to do is to use sk_dst_check() and sk_dst_set() so that all the writers hold same spinlock (sk->sk_dst_lock) to prevent corruptions. TCP stack do not need this protection, as all sk_dst_cache writers hold the socket lock. [1] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel AddressSanitizer: heap-use-after-free in ipv4_dst_check Read of size 2 by thread T15453: [<ffffffff817daa3a>] ipv4_dst_check+0x1a/0x90 ./net/ipv4/route.c:1116 [<ffffffff8175b789>] __sk_dst_check+0x89/0xe0 ./net/core/sock.c:531 [<ffffffff81830a36>] ip4_datagram_release_cb+0x46/0x390 ??:0 [<ffffffff8175eaea>] release_sock+0x17a/0x230 ./net/core/sock.c:2413 [<ffffffff81830882>] ip4_datagram_connect+0x462/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Freed by thread T15455: [<ffffffff8178d9b8>] dst_destroy+0xa8/0x160 ./net/core/dst.c:251 [<ffffffff8178de25>] dst_release+0x45/0x80 ./net/core/dst.c:280 [<ffffffff818304c1>] ip4_datagram_connect+0xa1/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Allocated by thread T15453: [<ffffffff8178d291>] dst_alloc+0x81/0x2b0 ./net/core/dst.c:171 [<ffffffff817db3b7>] rt_dst_alloc+0x47/0x50 ./net/ipv4/route.c:1406 [< inlined >] __ip_route_output_key+0x3e8/0xf70 __mkroute_output ./net/ipv4/route.c:1939 [<ffffffff817dde08>] __ip_route_output_key+0x3e8/0xf70 ./net/ipv4/route.c:2161 [<ffffffff817deb34>] ip_route_output_flow+0x14/0x30 ./net/ipv4/route.c:2249 [<ffffffff81830737>] ip4_datagram_connect+0x317/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 [2] <4>[196727.311203] general protection fault: 0000 [#1] SMP <4>[196727.311224] Modules linked in: xt_TEE xt_dscp xt_DSCP macvlan bridge coretemp crc32_pclmul ghash_clmulni_intel gpio_ich microcode ipmi_watchdog ipmi_devintf sb_edac edac_core lpc_ich mfd_core tpm_tis tpm tpm_bios ipmi_si ipmi_msghandler isci igb libsas i2c_algo_bit ixgbe ptp pps_core mdio <4>[196727.311333] CPU: 17 PID: 0 Comm: swapper/17 Not tainted 3.10.26 #1 <4>[196727.311344] Hardware name: Supermicro X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.0 07/05/2013 <4>[196727.311364] task: ffff885e6f069700 ti: ffff885e6f072000 task.ti: ffff885e6f072000 <4>[196727.311377] RIP: 0010:[<ffffffff815f8c7f>] [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.311399] RSP: 0018:ffff885effd23a70 EFLAGS: 00010282 <4>[196727.311409] RAX: dead000000200200 RBX: ffff8854c398ecc0 RCX: 0000000000000040 <4>[196727.311423] RDX: dead000000100100 RSI: dead000000100100 RDI: dead000000200200 <4>[196727.311437] RBP: ffff885effd23a80 R08: ffffffff815fd9e0 R09: ffff885d5a590800 <4>[196727.311451] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>[196727.311464] R13: ffffffff81c8c280 R14: 0000000000000000 R15: ffff880e85ee16ce <4>[196727.311510] FS: 0000000000000000(0000) GS:ffff885effd20000(0000) knlGS:0000000000000000 <4>[196727.311554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[196727.311581] CR2: 00007a46751eb000 CR3: 0000005e65688000 CR4: 00000000000407e0 <4>[196727.311625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>[196727.311669] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 <4>[196727.311713] Stack: <4>[196727.311733] ffff8854c398ecc0 ffff8854c398ecc0 ffff885effd23ab0 ffffffff815b7f42 <4>[196727.311784] ffff88be6595bc00 ffff8854c398ecc0 0000000000000000 ffff8854c398ecc0 <4>[196727.311834] ffff885effd23ad0 ffffffff815b86c6 ffff885d5a590800 ffff8816827821c0 <4>[196727.311885] Call Trace: <4>[196727.311907] <IRQ> <4>[196727.311912] [<ffffffff815b7f42>] dst_destroy+0x32/0xe0 <4>[196727.311959] [<ffffffff815b86c6>] dst_release+0x56/0x80 <4>[196727.311986] [<ffffffff81620bd5>] tcp_v4_do_rcv+0x2a5/0x4a0 <4>[196727.312013] [<ffffffff81622b5a>] tcp_v4_rcv+0x7da/0x820 <4>[196727.312041] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312070] [<ffffffff815de02d>] ? nf_hook_slow+0x7d/0x150 <4>[196727.312097] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312125] [<ffffffff815fda92>] ip_local_deliver_finish+0xb2/0x230 <4>[196727.312154] [<ffffffff815fdd9a>] ip_local_deliver+0x4a/0x90 <4>[196727.312183] [<ffffffff815fd799>] ip_rcv_finish+0x119/0x360 <4>[196727.312212] [<ffffffff815fe00b>] ip_rcv+0x22b/0x340 <4>[196727.312242] [<ffffffffa0339680>] ? macvlan_broadcast+0x160/0x160 [macvlan] <4>[196727.312275] [<ffffffff815b0c62>] __netif_receive_skb_core+0x512/0x640 <4>[196727.312308] [<ffffffff811427fb>] ? kmem_cache_alloc+0x13b/0x150 <4>[196727.312338] [<ffffffff815b0db1>] __netif_receive_skb+0x21/0x70 <4>[196727.312368] [<ffffffff815b0fa1>] netif_receive_skb+0x31/0xa0 <4>[196727.312397] [<ffffffff815b1ae8>] napi_gro_receive+0xe8/0x140 <4>[196727.312433] [<ffffffffa00274f1>] ixgbe_poll+0x551/0x11f0 [ixgbe] <4>[196727.312463] [<ffffffff815fe00b>] ? ip_rcv+0x22b/0x340 <4>[196727.312491] [<ffffffff815b1691>] net_rx_action+0x111/0x210 <4>[196727.312521] [<ffffffff815b0db1>] ? __netif_receive_skb+0x21/0x70 <4>[196727.312552] [<ffffffff810519d0>] __do_softirq+0xd0/0x270 <4>[196727.312583] [<ffffffff816cef3c>] call_softirq+0x1c/0x30 <4>[196727.312613] [<ffffffff81004205>] do_softirq+0x55/0x90 <4>[196727.312640] [<ffffffff81051c85>] irq_exit+0x55/0x60 <4>[196727.312668] [<ffffffff816cf5c3>] do_IRQ+0x63/0xe0 <4>[196727.312696] [<ffffffff816c5aaa>] common_interrupt+0x6a/0x6a <4>[196727.312722] <EOI> <1>[196727.313071] RIP [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.313100] RSP <ffff885effd23a70> <4>[196727.313377] ---[ end trace 64b3f14fae0f2e29 ]--- <0>[196727.380908] Kernel panic - not syncing: Fatal exception in interrupt Reported-by: Alexey Preobrazhensky <preobr@google.com> Reported-by: dormando <dormando@rydia.ne> Signed-off-by: Eric Dumazet <edumazet@google.com> Fixes: 8141ed9fcedb2 ("ipv4: Add a socket release callback for datagram sockets") Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-10 17:43:01 +04:00
struct dst_entry *dst;
struct flowi4 fl4;
struct rtable *rt;
rcu_read_lock();
ipv4: fix a race in ip4_datagram_release_cb() Alexey gave a AddressSanitizer[1] report that finally gave a good hint at where was the origin of various problems already reported by Dormando in the past [2] Problem comes from the fact that UDP can have a lockless TX path, and concurrent threads can manipulate sk_dst_cache, while another thread, is holding socket lock and calls __sk_dst_set() in ip4_datagram_release_cb() (this was added in linux-3.8) It seems that all we need to do is to use sk_dst_check() and sk_dst_set() so that all the writers hold same spinlock (sk->sk_dst_lock) to prevent corruptions. TCP stack do not need this protection, as all sk_dst_cache writers hold the socket lock. [1] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel AddressSanitizer: heap-use-after-free in ipv4_dst_check Read of size 2 by thread T15453: [<ffffffff817daa3a>] ipv4_dst_check+0x1a/0x90 ./net/ipv4/route.c:1116 [<ffffffff8175b789>] __sk_dst_check+0x89/0xe0 ./net/core/sock.c:531 [<ffffffff81830a36>] ip4_datagram_release_cb+0x46/0x390 ??:0 [<ffffffff8175eaea>] release_sock+0x17a/0x230 ./net/core/sock.c:2413 [<ffffffff81830882>] ip4_datagram_connect+0x462/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Freed by thread T15455: [<ffffffff8178d9b8>] dst_destroy+0xa8/0x160 ./net/core/dst.c:251 [<ffffffff8178de25>] dst_release+0x45/0x80 ./net/core/dst.c:280 [<ffffffff818304c1>] ip4_datagram_connect+0xa1/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Allocated by thread T15453: [<ffffffff8178d291>] dst_alloc+0x81/0x2b0 ./net/core/dst.c:171 [<ffffffff817db3b7>] rt_dst_alloc+0x47/0x50 ./net/ipv4/route.c:1406 [< inlined >] __ip_route_output_key+0x3e8/0xf70 __mkroute_output ./net/ipv4/route.c:1939 [<ffffffff817dde08>] __ip_route_output_key+0x3e8/0xf70 ./net/ipv4/route.c:2161 [<ffffffff817deb34>] ip_route_output_flow+0x14/0x30 ./net/ipv4/route.c:2249 [<ffffffff81830737>] ip4_datagram_connect+0x317/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 [2] <4>[196727.311203] general protection fault: 0000 [#1] SMP <4>[196727.311224] Modules linked in: xt_TEE xt_dscp xt_DSCP macvlan bridge coretemp crc32_pclmul ghash_clmulni_intel gpio_ich microcode ipmi_watchdog ipmi_devintf sb_edac edac_core lpc_ich mfd_core tpm_tis tpm tpm_bios ipmi_si ipmi_msghandler isci igb libsas i2c_algo_bit ixgbe ptp pps_core mdio <4>[196727.311333] CPU: 17 PID: 0 Comm: swapper/17 Not tainted 3.10.26 #1 <4>[196727.311344] Hardware name: Supermicro X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.0 07/05/2013 <4>[196727.311364] task: ffff885e6f069700 ti: ffff885e6f072000 task.ti: ffff885e6f072000 <4>[196727.311377] RIP: 0010:[<ffffffff815f8c7f>] [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.311399] RSP: 0018:ffff885effd23a70 EFLAGS: 00010282 <4>[196727.311409] RAX: dead000000200200 RBX: ffff8854c398ecc0 RCX: 0000000000000040 <4>[196727.311423] RDX: dead000000100100 RSI: dead000000100100 RDI: dead000000200200 <4>[196727.311437] RBP: ffff885effd23a80 R08: ffffffff815fd9e0 R09: ffff885d5a590800 <4>[196727.311451] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>[196727.311464] R13: ffffffff81c8c280 R14: 0000000000000000 R15: ffff880e85ee16ce <4>[196727.311510] FS: 0000000000000000(0000) GS:ffff885effd20000(0000) knlGS:0000000000000000 <4>[196727.311554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[196727.311581] CR2: 00007a46751eb000 CR3: 0000005e65688000 CR4: 00000000000407e0 <4>[196727.311625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>[196727.311669] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 <4>[196727.311713] Stack: <4>[196727.311733] ffff8854c398ecc0 ffff8854c398ecc0 ffff885effd23ab0 ffffffff815b7f42 <4>[196727.311784] ffff88be6595bc00 ffff8854c398ecc0 0000000000000000 ffff8854c398ecc0 <4>[196727.311834] ffff885effd23ad0 ffffffff815b86c6 ffff885d5a590800 ffff8816827821c0 <4>[196727.311885] Call Trace: <4>[196727.311907] <IRQ> <4>[196727.311912] [<ffffffff815b7f42>] dst_destroy+0x32/0xe0 <4>[196727.311959] [<ffffffff815b86c6>] dst_release+0x56/0x80 <4>[196727.311986] [<ffffffff81620bd5>] tcp_v4_do_rcv+0x2a5/0x4a0 <4>[196727.312013] [<ffffffff81622b5a>] tcp_v4_rcv+0x7da/0x820 <4>[196727.312041] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312070] [<ffffffff815de02d>] ? nf_hook_slow+0x7d/0x150 <4>[196727.312097] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312125] [<ffffffff815fda92>] ip_local_deliver_finish+0xb2/0x230 <4>[196727.312154] [<ffffffff815fdd9a>] ip_local_deliver+0x4a/0x90 <4>[196727.312183] [<ffffffff815fd799>] ip_rcv_finish+0x119/0x360 <4>[196727.312212] [<ffffffff815fe00b>] ip_rcv+0x22b/0x340 <4>[196727.312242] [<ffffffffa0339680>] ? macvlan_broadcast+0x160/0x160 [macvlan] <4>[196727.312275] [<ffffffff815b0c62>] __netif_receive_skb_core+0x512/0x640 <4>[196727.312308] [<ffffffff811427fb>] ? kmem_cache_alloc+0x13b/0x150 <4>[196727.312338] [<ffffffff815b0db1>] __netif_receive_skb+0x21/0x70 <4>[196727.312368] [<ffffffff815b0fa1>] netif_receive_skb+0x31/0xa0 <4>[196727.312397] [<ffffffff815b1ae8>] napi_gro_receive+0xe8/0x140 <4>[196727.312433] [<ffffffffa00274f1>] ixgbe_poll+0x551/0x11f0 [ixgbe] <4>[196727.312463] [<ffffffff815fe00b>] ? ip_rcv+0x22b/0x340 <4>[196727.312491] [<ffffffff815b1691>] net_rx_action+0x111/0x210 <4>[196727.312521] [<ffffffff815b0db1>] ? __netif_receive_skb+0x21/0x70 <4>[196727.312552] [<ffffffff810519d0>] __do_softirq+0xd0/0x270 <4>[196727.312583] [<ffffffff816cef3c>] call_softirq+0x1c/0x30 <4>[196727.312613] [<ffffffff81004205>] do_softirq+0x55/0x90 <4>[196727.312640] [<ffffffff81051c85>] irq_exit+0x55/0x60 <4>[196727.312668] [<ffffffff816cf5c3>] do_IRQ+0x63/0xe0 <4>[196727.312696] [<ffffffff816c5aaa>] common_interrupt+0x6a/0x6a <4>[196727.312722] <EOI> <1>[196727.313071] RIP [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.313100] RSP <ffff885effd23a70> <4>[196727.313377] ---[ end trace 64b3f14fae0f2e29 ]--- <0>[196727.380908] Kernel panic - not syncing: Fatal exception in interrupt Reported-by: Alexey Preobrazhensky <preobr@google.com> Reported-by: dormando <dormando@rydia.ne> Signed-off-by: Eric Dumazet <edumazet@google.com> Fixes: 8141ed9fcedb2 ("ipv4: Add a socket release callback for datagram sockets") Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-10 17:43:01 +04:00
dst = __sk_dst_get(sk);
if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
rcu_read_unlock();
return;
}
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr,
inet->inet_saddr, inet->inet_dport,
inet->inet_sport, sk->sk_protocol,
ipv4: Set the routing scope properly in ip_route_output_ports(). Set scope automatically in ip_route_output_ports() (using the socket SOCK_LOCALROUTE flag). This way, callers don't have to overload the tos with the RTO_ONLINK flag, like RT_CONN_FLAGS() does. For callers that don't pass a struct sock, this doesn't change anything as the scope is still set to RT_SCOPE_UNIVERSE when sk is NULL. Callers that passed a struct sock and used RT_CONN_FLAGS(sk) or RT_CONN_FLAGS_TOS(sk, tos) for the tos are modified to use ip_sock_tos(sk) and RT_TOS(tos) respectively, as overloading tos with the RTO_ONLINK flag now becomes unnecessary. In drivers/net/amt.c, all ip_route_output_ports() calls use a 0 tos parameter, ignoring the SOCK_LOCALROUTE flag of the socket. But the sk parameter is a kernel socket, which doesn't have any configuration path for setting SOCK_LOCALROUTE anyway. Therefore, ip_route_output_ports() will continue to initialise scope with RT_SCOPE_UNIVERSE and amt.c doesn't need to be modified. Also, remove RT_CONN_FLAGS() and RT_CONN_FLAGS_TOS() from route.h as these macros are now unused. The objective is to eventually remove RTO_ONLINK entirely to allow converting ->flowi4_tos to dscp_t. This will ensure proper isolation between the DSCP and ECN bits, thus minimising the risk of introducing bugs where TOS values interfere with ECN. Signed-off-by: Guillaume Nault <gnault@redhat.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://lore.kernel.org/r/dacfd2ab40685e20959ab7b53c427595ba229e7d.1707496938.git.gnault@redhat.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-09 19:43:37 +03:00
ip_sock_rt_tos(sk), sk->sk_bound_dev_if);
ipv4: fix a race in ip4_datagram_release_cb() Alexey gave a AddressSanitizer[1] report that finally gave a good hint at where was the origin of various problems already reported by Dormando in the past [2] Problem comes from the fact that UDP can have a lockless TX path, and concurrent threads can manipulate sk_dst_cache, while another thread, is holding socket lock and calls __sk_dst_set() in ip4_datagram_release_cb() (this was added in linux-3.8) It seems that all we need to do is to use sk_dst_check() and sk_dst_set() so that all the writers hold same spinlock (sk->sk_dst_lock) to prevent corruptions. TCP stack do not need this protection, as all sk_dst_cache writers hold the socket lock. [1] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel AddressSanitizer: heap-use-after-free in ipv4_dst_check Read of size 2 by thread T15453: [<ffffffff817daa3a>] ipv4_dst_check+0x1a/0x90 ./net/ipv4/route.c:1116 [<ffffffff8175b789>] __sk_dst_check+0x89/0xe0 ./net/core/sock.c:531 [<ffffffff81830a36>] ip4_datagram_release_cb+0x46/0x390 ??:0 [<ffffffff8175eaea>] release_sock+0x17a/0x230 ./net/core/sock.c:2413 [<ffffffff81830882>] ip4_datagram_connect+0x462/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Freed by thread T15455: [<ffffffff8178d9b8>] dst_destroy+0xa8/0x160 ./net/core/dst.c:251 [<ffffffff8178de25>] dst_release+0x45/0x80 ./net/core/dst.c:280 [<ffffffff818304c1>] ip4_datagram_connect+0xa1/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 Allocated by thread T15453: [<ffffffff8178d291>] dst_alloc+0x81/0x2b0 ./net/core/dst.c:171 [<ffffffff817db3b7>] rt_dst_alloc+0x47/0x50 ./net/ipv4/route.c:1406 [< inlined >] __ip_route_output_key+0x3e8/0xf70 __mkroute_output ./net/ipv4/route.c:1939 [<ffffffff817dde08>] __ip_route_output_key+0x3e8/0xf70 ./net/ipv4/route.c:2161 [<ffffffff817deb34>] ip_route_output_flow+0x14/0x30 ./net/ipv4/route.c:2249 [<ffffffff81830737>] ip4_datagram_connect+0x317/0x5d0 ??:0 [<ffffffff81846d06>] inet_dgram_connect+0x76/0xd0 ./net/ipv4/af_inet.c:534 [<ffffffff817580ac>] SYSC_connect+0x15c/0x1c0 ./net/socket.c:1701 [<ffffffff817596ce>] SyS_connect+0xe/0x10 ./net/socket.c:1682 [<ffffffff818b0a29>] system_call_fastpath+0x16/0x1b ./arch/x86/kernel/entry_64.S:629 [2] <4>[196727.311203] general protection fault: 0000 [#1] SMP <4>[196727.311224] Modules linked in: xt_TEE xt_dscp xt_DSCP macvlan bridge coretemp crc32_pclmul ghash_clmulni_intel gpio_ich microcode ipmi_watchdog ipmi_devintf sb_edac edac_core lpc_ich mfd_core tpm_tis tpm tpm_bios ipmi_si ipmi_msghandler isci igb libsas i2c_algo_bit ixgbe ptp pps_core mdio <4>[196727.311333] CPU: 17 PID: 0 Comm: swapper/17 Not tainted 3.10.26 #1 <4>[196727.311344] Hardware name: Supermicro X9DRi-LN4+/X9DR3-LN4+/X9DRi-LN4+/X9DR3-LN4+, BIOS 3.0 07/05/2013 <4>[196727.311364] task: ffff885e6f069700 ti: ffff885e6f072000 task.ti: ffff885e6f072000 <4>[196727.311377] RIP: 0010:[<ffffffff815f8c7f>] [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.311399] RSP: 0018:ffff885effd23a70 EFLAGS: 00010282 <4>[196727.311409] RAX: dead000000200200 RBX: ffff8854c398ecc0 RCX: 0000000000000040 <4>[196727.311423] RDX: dead000000100100 RSI: dead000000100100 RDI: dead000000200200 <4>[196727.311437] RBP: ffff885effd23a80 R08: ffffffff815fd9e0 R09: ffff885d5a590800 <4>[196727.311451] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>[196727.311464] R13: ffffffff81c8c280 R14: 0000000000000000 R15: ffff880e85ee16ce <4>[196727.311510] FS: 0000000000000000(0000) GS:ffff885effd20000(0000) knlGS:0000000000000000 <4>[196727.311554] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[196727.311581] CR2: 00007a46751eb000 CR3: 0000005e65688000 CR4: 00000000000407e0 <4>[196727.311625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>[196727.311669] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 <4>[196727.311713] Stack: <4>[196727.311733] ffff8854c398ecc0 ffff8854c398ecc0 ffff885effd23ab0 ffffffff815b7f42 <4>[196727.311784] ffff88be6595bc00 ffff8854c398ecc0 0000000000000000 ffff8854c398ecc0 <4>[196727.311834] ffff885effd23ad0 ffffffff815b86c6 ffff885d5a590800 ffff8816827821c0 <4>[196727.311885] Call Trace: <4>[196727.311907] <IRQ> <4>[196727.311912] [<ffffffff815b7f42>] dst_destroy+0x32/0xe0 <4>[196727.311959] [<ffffffff815b86c6>] dst_release+0x56/0x80 <4>[196727.311986] [<ffffffff81620bd5>] tcp_v4_do_rcv+0x2a5/0x4a0 <4>[196727.312013] [<ffffffff81622b5a>] tcp_v4_rcv+0x7da/0x820 <4>[196727.312041] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312070] [<ffffffff815de02d>] ? nf_hook_slow+0x7d/0x150 <4>[196727.312097] [<ffffffff815fd9e0>] ? ip_rcv_finish+0x360/0x360 <4>[196727.312125] [<ffffffff815fda92>] ip_local_deliver_finish+0xb2/0x230 <4>[196727.312154] [<ffffffff815fdd9a>] ip_local_deliver+0x4a/0x90 <4>[196727.312183] [<ffffffff815fd799>] ip_rcv_finish+0x119/0x360 <4>[196727.312212] [<ffffffff815fe00b>] ip_rcv+0x22b/0x340 <4>[196727.312242] [<ffffffffa0339680>] ? macvlan_broadcast+0x160/0x160 [macvlan] <4>[196727.312275] [<ffffffff815b0c62>] __netif_receive_skb_core+0x512/0x640 <4>[196727.312308] [<ffffffff811427fb>] ? kmem_cache_alloc+0x13b/0x150 <4>[196727.312338] [<ffffffff815b0db1>] __netif_receive_skb+0x21/0x70 <4>[196727.312368] [<ffffffff815b0fa1>] netif_receive_skb+0x31/0xa0 <4>[196727.312397] [<ffffffff815b1ae8>] napi_gro_receive+0xe8/0x140 <4>[196727.312433] [<ffffffffa00274f1>] ixgbe_poll+0x551/0x11f0 [ixgbe] <4>[196727.312463] [<ffffffff815fe00b>] ? ip_rcv+0x22b/0x340 <4>[196727.312491] [<ffffffff815b1691>] net_rx_action+0x111/0x210 <4>[196727.312521] [<ffffffff815b0db1>] ? __netif_receive_skb+0x21/0x70 <4>[196727.312552] [<ffffffff810519d0>] __do_softirq+0xd0/0x270 <4>[196727.312583] [<ffffffff816cef3c>] call_softirq+0x1c/0x30 <4>[196727.312613] [<ffffffff81004205>] do_softirq+0x55/0x90 <4>[196727.312640] [<ffffffff81051c85>] irq_exit+0x55/0x60 <4>[196727.312668] [<ffffffff816cf5c3>] do_IRQ+0x63/0xe0 <4>[196727.312696] [<ffffffff816c5aaa>] common_interrupt+0x6a/0x6a <4>[196727.312722] <EOI> <1>[196727.313071] RIP [<ffffffff815f8c7f>] ipv4_dst_destroy+0x4f/0x80 <4>[196727.313100] RSP <ffff885effd23a70> <4>[196727.313377] ---[ end trace 64b3f14fae0f2e29 ]--- <0>[196727.380908] Kernel panic - not syncing: Fatal exception in interrupt Reported-by: Alexey Preobrazhensky <preobr@google.com> Reported-by: dormando <dormando@rydia.ne> Signed-off-by: Eric Dumazet <edumazet@google.com> Fixes: 8141ed9fcedb2 ("ipv4: Add a socket release callback for datagram sockets") Cc: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-06-10 17:43:01 +04:00
dst = !IS_ERR(rt) ? &rt->dst : NULL;
sk_dst_set(sk, dst);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);