mptcp: fix 'scheduling while atomic' in mptcp_pm_nl_append_new_local_addr

If multiple connection requests attempt to create an implicit mptcp
endpoint in parallel, more than one caller may end up in
mptcp_pm_nl_append_new_local_addr because none found the address in
local_addr_list during their call to mptcp_pm_nl_get_local_id.  In this
case, the concurrent new_local_addr calls may delete the address entry
created by the previous caller.  These deletes use synchronize_rcu, but
this is not permitted in some of the contexts where this function may be
called.  During packet recv, the caller may be in a rcu read critical
section and have preemption disabled.

An example stack:

   BUG: scheduling while atomic: swapper/2/0/0x00000302

   Call Trace:
   <IRQ>
   dump_stack_lvl+0x76/0xa0
   dump_stack+0x10/0x20
   __schedule_bug+0x64/0x80
   schedule_debug.constprop.0+0xdb/0x130
   __schedule+0x69/0x6a0
   schedule+0x33/0x110
   schedule_timeout+0x157/0x170
   wait_for_completion+0x88/0x150
   __wait_rcu_gp+0x150/0x160
   synchronize_rcu+0x12d/0x140
   mptcp_pm_nl_append_new_local_addr+0x1bd/0x280
   mptcp_pm_nl_get_local_id+0x121/0x160
   mptcp_pm_get_local_id+0x9d/0xe0
   subflow_check_req+0x1a8/0x460
   subflow_v4_route_req+0xb5/0x110
   tcp_conn_request+0x3a4/0xd00
   subflow_v4_conn_request+0x42/0xa0
   tcp_rcv_state_process+0x1e3/0x7e0
   tcp_v4_do_rcv+0xd3/0x2a0
   tcp_v4_rcv+0xbb8/0xbf0
   ip_protocol_deliver_rcu+0x3c/0x210
   ip_local_deliver_finish+0x77/0xa0
   ip_local_deliver+0x6e/0x120
   ip_sublist_rcv_finish+0x6f/0x80
   ip_sublist_rcv+0x178/0x230
   ip_list_rcv+0x102/0x140
   __netif_receive_skb_list_core+0x22d/0x250
   netif_receive_skb_list_internal+0x1a3/0x2d0
   napi_complete_done+0x74/0x1c0
   igb_poll+0x6c/0xe0 [igb]
   __napi_poll+0x30/0x200
   net_rx_action+0x181/0x2e0
   handle_softirqs+0xd8/0x340
   __irq_exit_rcu+0xd9/0x100
   irq_exit_rcu+0xe/0x20
   common_interrupt+0xa4/0xb0
   </IRQ>

This problem seems particularly prevalent if the user advertises an
endpoint that has a different external vs internal address.  In the case
where the external address is advertised and multiple connections
already exist, multiple subflow SYNs arrive in parallel which tends to
trigger the race during creation of the first local_addr_list entries
which have the internal address instead.

Fix by skipping the replacement of an existing implicit local address if
called via mptcp_pm_nl_get_local_id.

Cc: [email protected]
Fixes: d045b9e ("mptcp: introduce implicit endpoints")
Suggested-by: Paolo Abeni <[email protected]>
Signed-off-by: Krister Johansen <[email protected]>

Author: kmjohansen

net/mptcp/pm_netlink.c

@@ -977,7 +977,7 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 					     struct mptcp_pm_addr_entry *entry,
-					     bool needs_id)
+					     bool needs_id, bool replace)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
@@ -1017,6 +1017,17 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 			if (entry->addr.id)
 				goto out;
 
+			/* allow callers that only need to look up the local
+			 * addr's id to skip replacement. This allows them to
+			 * avoid calling synchronize_rcu in the packet recv
+			 * path.
+			 */
+			if (!replace) {
+				kfree(entry);
+				ret = cur->addr.id;
+				goto out;
+			}
+
 			pernet->addrs--;
 			entry->addr.id = cur->addr.id;
 			list_del_rcu(&cur->list);
@@ -1165,7 +1176,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	entry->ifindex = 0;
 	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
 	if (ret < 0)
 		kfree(entry);
 
@@ -1433,7 +1444,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
-						!mptcp_pm_has_addr_attr_id(attr, info));
+						!mptcp_pm_has_addr_attr_id(attr, info),
+						true);
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;