From: Jacobs Wu The firmware can join an existing cluster from inside the passive scan it runs at the start of NAN_START, so NAN_EVENT_ID_JOINED_CLUSTER lands while the start path is still executing and ieee80211_vif_nan_started() is not true yet. The handler dropped the event with a warning, leaving userspace unaware of the cluster it had joined, and service discovery then never completed: measured 4 failures in 12 NDP bring-ups on an MT7925 pair, each one accompanied by exactly one dropped event on the joining side and none on the side that created the cluster. NAN_EVENT_ID_STARTED_CLUSTER already defers past NAN_START through nan_deferred_work for the same reason; JOINED_CLUSTER is the other exit of the same firmware warm-up branch and needs the same treatment. Queue it on that work with its own cluster id, so a started and a joined event pending at once cannot overwrite each other. Fixes: a5487a682406 ("wifi: mt76: mt7925: add NAN MCU helpers") Co-developed-by: Sean Wang Signed-off-by: Sean Wang Signed-off-by: Jacobs Wu --- .../net/wireless/mediatek/mt76/mt7925/nan.c | 20 ++++++++++++++++++- .../net/wireless/mediatek/mt76/mt7925/nan.h | 1 + drivers/net/wireless/mediatek/mt76/mt792x.h | 1 + 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/nan.c b/drivers/net/wireless/mediatek/mt76/mt7925/nan.c index 715e080ce4ee..7aacfd6527e4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/nan.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/nan.c @@ -709,8 +709,20 @@ mt7925_nan_mcu_handle_de_event(struct mt792x_dev *dev, struct tlv *tlv) return; } + /* JOINED_CLUSTER has the same race as STARTED_CLUSTER above: the + * firmware joins an existing cluster from inside its start-up passive + * scan, so the event can land while NAN_START is still running and + * nan.started is not set yet. Defer it the same way instead of + * dropping it - a lost join leaves userspace unaware of the cluster it + * is in and service discovery never completes. + */ if (!dev->nan_vif || !ieee80211_vif_nan_started(dev->nan_vif)) { - dev_warn(dev->mt76.dev, "nan: joined-cluster event but NAN not started\n"); + spin_lock_bh(&dev->nan_deferred_lock); + memcpy(dev->nan_joined_cluster_id, cluster_id, ETH_ALEN); + set_bit(MT7925_NAN_DEFERRED_JOINED_CLUSTER, + &dev->nan_deferred_pending); + spin_unlock_bh(&dev->nan_deferred_lock); + ieee80211_queue_work(dev->mt76.hw, &dev->nan_deferred_work); return; } @@ -732,6 +744,7 @@ mt7925_nan_deferred_work(struct work_struct *work) { struct mt792x_dev *dev = container_of(work, struct mt792x_dev, nan_deferred_work); + u8 joined_cluster_id[ETH_ALEN]; struct ieee80211_vif *vif; unsigned long pending; u8 cluster_id[ETH_ALEN]; @@ -740,6 +753,7 @@ mt7925_nan_deferred_work(struct work_struct *work) pending = dev->nan_deferred_pending; dev->nan_deferred_pending = 0; memcpy(cluster_id, dev->nan_started_cluster_id, ETH_ALEN); + memcpy(joined_cluster_id, dev->nan_joined_cluster_id, ETH_ALEN); spin_unlock_bh(&dev->nan_deferred_lock); if (!pending) @@ -753,6 +767,10 @@ mt7925_nan_deferred_work(struct work_struct *work) if (test_bit(MT7925_NAN_DEFERRED_STARTED_CLUSTER, &pending)) ieee80211_nan_cluster_joined(vif, cluster_id, true, GFP_KERNEL); + if (test_bit(MT7925_NAN_DEFERRED_JOINED_CLUSTER, &pending)) + ieee80211_nan_cluster_joined(vif, joined_cluster_id, false, + GFP_KERNEL); + if (test_bit(MT7925_NAN_DEFERRED_SCHED_UPDATE_DONE, &pending)) ieee80211_nan_sched_update_done(vif); out: diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/nan.h b/drivers/net/wireless/mediatek/mt76/mt7925/nan.h index 415fd6b6f0e6..32740e3769d6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/nan.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/nan.h @@ -143,6 +143,7 @@ enum mt7925_nan_key_type { */ enum mt7925_nan_deferred_event { MT7925_NAN_DEFERRED_STARTED_CLUSTER, + MT7925_NAN_DEFERRED_JOINED_CLUSTER, MT7925_NAN_DEFERRED_SCHED_UPDATE_DONE, }; /* NAN 4.0 Table 79. Device Capability attribute format, Supported Bands */ diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h index ee462eab4028..8e1588970ac1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x.h +++ b/drivers/net/wireless/mediatek/mt76/mt792x.h @@ -446,6 +446,7 @@ struct mt792x_dev { spinlock_t nan_deferred_lock; unsigned long nan_deferred_pending; u8 nan_started_cluster_id[ETH_ALEN]; + u8 nan_joined_cluster_id[ETH_ALEN]; }; static inline struct mt792x_bss_conf * -- 2.43.0