From 05f136220d17839eb7c155f015ace9152f603225 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 29 Aug 2023 20:16:11 +0200 Subject: wifi: mac80211: fix BA session teardown race As previously reported by Alexander, whose commit 69403bad97aa ("wifi: mac80211: sdata can be NULL during AMPDU start") I'm reverting as part of this commit, there's a race between station destruction and aggregation setup, where the aggregation setup can happen while the station is being removed and queue the work after ieee80211_sta_tear_down_BA_sessions() has already run in __sta_info_destroy_part1(), and thus the worker will run with a now freed station. In his case, this manifested in a NULL sdata pointer, but really there's no guarantee whatsoever. The real issue seems to be that it's possible at all to have a situation where this occurs - we want to stop the BA sessions when doing _part1, but we cannot be sure, and WLAN_STA_BLOCK_BA isn't necessarily effective since we don't know that the setup isn't concurrently running and already got past the check. Simply call ieee80211_sta_tear_down_BA_sessions() again in the second part of station destruction, since at that point really nothing else can hold a reference to the station any more. Also revert the sdata checks since those are just misleading at this point. Signed-off-by: Johannes Berg --- net/mac80211/agg-tx.c | 6 +----- net/mac80211/driver-ops.c | 3 --- net/mac80211/sta_info.c | 14 ++++++++++++++ 3 files changed, 15 insertions(+), 8 deletions(-) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 0627abb09f0e..b8a278355e18 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -497,7 +497,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; - struct ieee80211_sub_if_data *sdata; + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_START, @@ -525,7 +525,6 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ synchronize_net(); - sdata = sta->sdata; params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); tid_tx->ssn = params.ssn; @@ -539,9 +538,6 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state); } else if (ret) { - if (!sdata) - return; - ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", sta->sta.addr, tid); diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 919300750527..169dbbca54b6 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -409,9 +409,6 @@ int drv_ampdu_action(struct ieee80211_local *local, might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); - if (!sdata) - return -EIO; - sdata = get_bss_sdata(sdata); if (!check_sdata_in_driver(sdata)) return -EIO; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index abcc280acd38..2a61269a4b54 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1385,6 +1385,20 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) * after _part1 and before _part2! */ + /* + * There's a potential race in _part1 where we set WLAN_STA_BLOCK_BA + * but someone might have just gotten past a check, and not yet into + * queuing the work/creating the data/etc. + * + * Do another round of destruction so that the worker is certainly + * canceled before we later free the station. + * + * Since this is after synchronize_rcu()/synchronize_net() we're now + * certain that nobody can actually hold a reference to the STA and + * be calling e.g. ieee80211_start_tx_ba_session(). + */ + ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); + might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); -- cgit