[PATCH net 1/6] net/smc: protect link down work from execute after lgr freed

[Guangguan Wang]

link down work may be scheduled before lgr freed but execute
after lgr freed, which may result in crash. So it is need to
hold a reference before shedule link down work, and put the
reference after work executed or canceled.

The relevant crash call stack as follows:
 list_del corruption. prev->next should be ffffb638c9c0fe20,
    but was 0000000000000000
 ------------[ cut here ]------------
 kernel BUG at lib/list_debug.c:51!
 invalid opcode: 0000 [#1] SMP NOPTI
 CPU: 6 PID: 978112 Comm: kworker/6:119 Kdump: loaded Tainted: G #1
 Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 2221b89 04/01/2014
 Workqueue: events smc_link_down_work [smc]
 RIP: 0010:__list_del_entry_valid.cold+0x31/0x47
 RSP: 0018:ffffb638c9c0fdd8 EFLAGS: 00010086
 RAX: 0000000000000054 RBX: ffff942fb75e5128 RCX: 0000000000000000
 RDX: ffff943520930aa0 RSI: ffff94352091fc80 RDI: ffff94352091fc80
 RBP: 0000000000000000 R08: 0000000000000000 R09: ffffb638c9c0fc38
 R10: ffffb638c9c0fc30 R11: ffffffffa015eb28 R12: 0000000000000002
 R13: ffffb638c9c0fe20 R14: 0000000000000001 R15: ffff942f9cd051c0
 FS:  0000000000000000(0000) GS:ffff943520900000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f4f25214000 CR3: 000000025fbae004 CR4: 00000000007706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  rwsem_down_write_slowpath+0x17e/0x470
  smc_link_down_work+0x3c/0x60 [smc]
  process_one_work+0x1ac/0x350
  worker_thread+0x49/0x2f0
  ? rescuer_thread+0x360/0x360
  kthread+0x118/0x140
  ? __kthread_bind_mask+0x60/0x60
  ret_from_fork+0x1f/0x30

Fixes: 541afa10c126 ("net/smc: add smcr_port_err() and smcr_link_down() processing")
Signed-off-by: Guangguan Wang <guangguan.wang@xxxxxxxxxxxxxxxxx>
Reviewed-by: Tony Lu <tonylu@xxxxxxxxxxxxxxxxx>
---
 net/smc/smc_core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 500952c2e67b..3b125d348b4a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1818,7 +1818,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk)
 {
 	if (smc_link_downing(&lnk->state)) {
 		trace_smcr_link_down(lnk, __builtin_return_address(0));
-		schedule_work(&lnk->link_down_wrk);
+		smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */
+		if (!schedule_work(&lnk->link_down_wrk))
+			smcr_link_put(lnk);
 	}
 }
 
@@ -1850,11 +1852,14 @@ static void smc_link_down_work(struct work_struct *work)
 	struct smc_link_group *lgr = link->lgr;
 
 	if (list_empty(&lgr->list))
-		return;
+		goto out;
 	wake_up_all(&lgr->llc_msg_waiter);
 	down_write(&lgr->llc_conf_mutex);
 	smcr_link_down(link);
 	up_write(&lgr->llc_conf_mutex);
+
+out:
+	smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */
 }
 
 static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev,
-- 
2.24.3 (Apple Git-128)