[PATCH] wifi: mac80211: Fix deadlock in ieee80211_sta_ps_deliver_wakeup()

[Remi Pommarel]

The ieee80211_sta_ps_deliver_wakeup() function takes sta->ps_lock to
synchronizes with ieee80211_tx_h_unicast_ps_buf() which is called from
softirq context. However using only spin_lock() to get sta->ps_lock in
ieee80211_sta_ps_deliver_wakeup() does not prevent softirq to execute
on this same CPU, to run ieee80211_tx_h_unicast_ps_buf() and try to
take this same lock ending in deadlock. Below is an example of rcu stall
that arises in such situation.

 rcu: INFO: rcu_sched self-detected stall on CPU
 rcu:    2-....: (42413413 ticks this GP) idle=b154/1/0x4000000000000000 softirq=1763/1765 fqs=21206996
 rcu:    (t=42586894 jiffies g=2057 q=362405 ncpus=4)
 CPU: 2 PID: 719 Comm: wpa_supplicant Tainted: G        W          6.4.0-02158-g1b062f552873 #742
 Hardware name: RPT (r1) (DT)
 pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : queued_spin_lock_slowpath+0x58/0x2d0
 lr : invoke_tx_handlers_early+0x5b4/0x5c0
 sp : ffff00001ef64660
 x29: ffff00001ef64660 x28: ffff000009bc1070 x27: ffff000009bc0ad8
 x26: ffff000009bc0900 x25: ffff00001ef647a8 x24: 0000000000000000
 x23: ffff000009bc0900 x22: ffff000009bc0900 x21: ffff00000ac0e000
 x20: ffff00000a279e00 x19: ffff00001ef646e8 x18: 0000000000000000
 x17: ffff800016468000 x16: ffff00001ef608c0 x15: 0010533c93f64f80
 x14: 0010395c9faa3946 x13: 0000000000000000 x12: 00000000fa83b2da
 x11: 000000012edeceea x10: ffff0000010fbe00 x9 : 0000000000895440
 x8 : 000000000010533c x7 : ffff00000ad8b740 x6 : ffff00000c350880
 x5 : 0000000000000007 x4 : 0000000000000001 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 0000000000000001 x0 : ffff00000ac0e0e8
 Call trace:
  queued_spin_lock_slowpath+0x58/0x2d0
  ieee80211_tx+0x80/0x12c
  ieee80211_tx_pending+0x110/0x278
  tasklet_action_common.constprop.0+0x10c/0x144
  tasklet_action+0x20/0x28
  _stext+0x11c/0x284
  ____do_softirq+0xc/0x14
  call_on_irq_stack+0x24/0x34
  do_softirq_own_stack+0x18/0x20
  do_softirq+0x74/0x7c
  __local_bh_enable_ip+0xa0/0xa4
  _ieee80211_wake_txqs+0x3b0/0x4b8
  __ieee80211_wake_queue+0x12c/0x168
  ieee80211_add_pending_skbs+0xec/0x138
  ieee80211_sta_ps_deliver_wakeup+0x2a4/0x480
  ieee80211_mps_sta_status_update.part.0+0xd8/0x11c
  ieee80211_mps_sta_status_update+0x18/0x24
  sta_apply_parameters+0x3bc/0x4c0
  ieee80211_change_station+0x1b8/0x2dc
  nl80211_set_station+0x444/0x49c
  genl_family_rcv_msg_doit.isra.0+0xa4/0xfc
  genl_rcv_msg+0x1b0/0x244
  netlink_rcv_skb+0x38/0x10c
  genl_rcv+0x34/0x48
  netlink_unicast+0x254/0x2bc
  netlink_sendmsg+0x190/0x3b4
  ____sys_sendmsg+0x1e8/0x218
  ___sys_sendmsg+0x68/0x8c
  __sys_sendmsg+0x44/0x84
  __arm64_sys_sendmsg+0x20/0x28
  do_el0_svc+0x6c/0xe8
  el0_svc+0x14/0x48
  el0t_64_sync_handler+0xb0/0xb4
  el0t_64_sync+0x14c/0x150

Using spin_lock_bh()/spin_unlock_bh() instead prevents softirq to raise
on the same CPU that is holding the lock.

Fixes: 1d147bfa6429 ("mac80211: fix AP powersave TX vs. wakeup race")
Signed-off-by: Remi Pommarel <repk@xxxxxxxxxxxx>
---
 net/mac80211/sta_info.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index da5fdd6f5c85..aa22f09e6d14 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1724,7 +1724,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	skb_queue_head_init(&pending);
 
 	/* sync with ieee80211_tx_h_unicast_ps_buf */
-	spin_lock(&sta->ps_lock);
+	spin_lock_bh(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1753,7 +1753,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	 */
 	clear_sta_flag(sta, WLAN_STA_PSPOLL);
 	clear_sta_flag(sta, WLAN_STA_UAPSD);
-	spin_unlock(&sta->ps_lock);
+	spin_unlock_bh(&sta->ps_lock);
 
 	atomic_dec(&ps->num_sta_ps);
 
-- 
2.40.0