From: Emmanuel Grumbach <redacted>

[ Upstream commit d6843d1ee283137723b4a8c76244607ce6db1951 ]

After channel switch, we should consider any beacon with a
CSA IE as a new switch. If the CSA IE is a leftover from
before the switch that the AP forgot to remove, we'll get
a CSA-to-Self.

This caused issues in iwlwifi where the firmware saw a beacon
with a CSA-to-Self with mode = 1 on the new channel after a
switch. The firmware considered this a new switch and closed
its queues. Since the beacon didn't change between before and
after the switch, we wouldn't handle it (the CRC is the same)
and we wouldn't let the firmware open its queues again or
disconnect if the CSA IE stays for too long.

Clear the CRC valid state after we switch to make sure that
we handle the beacon and handle the CSA IE as required.

Signed-off-by: Emmanuel Grumbach <redacted>
Link: https://lore.kernel.org/r/20210408143124.b9e68aa98304.I465afb55ca2c7d59f7bf610c6046a1fd732b4c28@changeid (local)
Signed-off-by: Johannes Berg <redacted>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/mac80211/mlme.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 17a3a1c938be..44fd922cc32a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c

@@ -1215,6 +1215,11 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata)
 
 	sdata->vif.csa_active = false;
 	ifmgd->csa_waiting_bcn = false;
+	/*
+	 * If the CSA IE is still present on the beacon after the switch,
+	 * we need to consider it as a new CSA (possibly to self).
+	 */
+	ifmgd->beacon_crc_valid = false;
 
 	ret = drv_post_channel_switch(sdata);
 	if (ret) {

-- 
2.30.2