[PATCH net] net: fix __this_cpu_add() in preemptible code in dev_xmit_recursion_inc/dec

[PATCH net] net: fix __this_cpu_add() in preemptible code in dev_xmit_recursion_inc/dec

[Jiayuan Chen]

dev_xmit_recursion_inc/dec() use __this_cpu_inc/dec() which requires
migration to be disabled. However, some callers like SCTP's UDP
encapsulation path invoke iptunnel_xmit() from process context without
disabling BH or preemption:

  sctp_inet_connect -> __sctp_connect -> sctp_do_sm ->
  sctp_outq_flush -> sctp_packet_transmit -> sctp_v4_xmit ->
  udp_tunnel_xmit_skb -> iptunnel_xmit -> dev_xmit_recursion_inc

This triggers the following warning on PREEMPT(full) kernels:

  BUG: using __this_cpu_add() in preemptible [00000000]
  caller is dev_xmit_recursion_inc include/linux/netdevice.h:3595 [inline]
  caller is iptunnel_xmit+0x1cd/0xb80 net/ipv4/ip_tunnel_core.c:72
  Tainted: [L]=SOFTLOCKUP
  Call Trace:
   <TASK>
   __dump_stack lib/dump_stack.c:94 [inline]
   dump_stack_lvl+0x100/0x190 lib/dump_stack.c:120
   check_preemption_disabled+0xd8/0xe0 lib/smp_processor_id.c:47
   dev_xmit_recursion_inc include/linux/netdevice.h:3595 [inline]
   iptunnel_xmit+0x1cd/0xb80 net/ipv4/ip_tunnel_core.c:72
   sctp_v4_xmit+0x75f/0x1060 net/sctp/protocol.c:1073
   sctp_packet_transmit+0x22ec/0x3060 net/sctp/output.c:653
   sctp_packet_singleton+0x19e/0x370 net/sctp/outqueue.c:783
   sctp_outq_flush_ctrl net/sctp/outqueue.c:914 [inline]
   sctp_outq_flush+0x315/0x3350 net/sctp/outqueue.c:1212
   sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1824 [inline]
   sctp_side_effects net/sctp/sm_sideeffect.c:1204 [inline]
   sctp_do_sm+0xce1/0x5be0 net/sctp/sm_sideeffect.c:1175
   sctp_primitive_ASSOCIATE+0x9c/0xd0 net/sctp/primitive.c:73
   __sctp_connect+0x9fc/0xc70 net/sctp/socket.c:1235
   sctp_connect net/sctp/socket.c:4818 [inline]
   sctp_inet_connect+0x15f/0x220 net/sctp/socket.c:4833
   __sys_connect_file+0x141/0x1a0 net/socket.c:2089
   __sys_connect+0x141/0x170 net/socket.c:2108
   __do_sys_connect net/socket.c:2114 [inline]
   __se_sys_connect net/socket.c:2111 [inline]
   __x64_sys_connect+0x72/0xb0 net/socket.c:2111
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0x106/0xf80 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fix this by adding migrate_disable/enable() around the __this_cpu
operations in dev_xmit_recursion_inc/dec() to ensure the per-cpu
variable is accessed on the same CPU throughout the inc/dec pair.

Fixes: 6f1a9140ecda ("net: add xmit recursion limit to tunnel xmit functions")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
---
 include/linux/netdevice.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ca01eb3f7d2..6b1cd5380d70 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3591,14 +3591,19 @@ static inline bool dev_xmit_recursion(void)
 			XMIT_RECURSION_LIMIT);
 }
 
+/* Non PREEMPT_RT version: inc and dec must run on the same CPU,
+ * migrate_disable is sufficient.
+ */
 static inline void dev_xmit_recursion_inc(void)
 {
+	migrate_disable();
 	__this_cpu_inc(softnet_data.xmit.recursion);
 }
 
 static inline void dev_xmit_recursion_dec(void)
 {
 	__this_cpu_dec(softnet_data.xmit.recursion);
+	migrate_enable();
 }
 #else
 static inline int dev_recursion_level(void)
-- 
2.43.0