While running stress tests in roaming scenarios (switching ap's every 5 seconds, we discovered a issue which leads to tx hangings of exactly 5 seconds while or after scanning for new accesspoints. We found out that this hanging is triggered by ath10k_mac_wait_tx_complete since the empty_tx_wq was not wake when the num_tx_pending counter reaches zero. To fix this, we simply move the wake_up call to htt_tx_dec_pending, since this call was missed on several locations within the ath10k code. Signed-off-by: Sebastian Gottschall <s.gottschall@xxxxxxxxxx> --- drivers/net/wireless/ath/ath10k/htt_tx.c | 3 +++ drivers/net/wireless/ath/ath10k/txrx.c | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c index d6b8bdcef416..b793eac2cfac 100644 --- a/drivers/net/wireless/ath/ath10k/htt_tx.c +++ b/drivers/net/wireless/ath/ath10k/htt_tx.c @@ -147,6 +147,9 @@ void ath10k_htt_tx_dec_pending(struct ath10k_htt *htt) htt->num_pending_tx--; if (htt->num_pending_tx == htt->max_num_pending_tx - 1) ath10k_mac_tx_unlock(htt->ar, ATH10K_TX_PAUSE_Q_FULL); + + if (htt->num_pending_tx == 0) + wake_up(&htt->empty_tx_wq); } int ath10k_htt_tx_inc_pending(struct ath10k_htt *htt) diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c index 7c9ea0c073d8..6f8b64218894 100644 --- a/drivers/net/wireless/ath/ath10k/txrx.c +++ b/drivers/net/wireless/ath/ath10k/txrx.c @@ -82,8 +82,6 @@ int ath10k_txrx_tx_unref(struct ath10k_htt *htt, flags = skb_cb->flags; ath10k_htt_tx_free_msdu_id(htt, tx_done->msdu_id); ath10k_htt_tx_dec_pending(htt); - if (htt->num_pending_tx == 0) - wake_up(&htt->empty_tx_wq); spin_unlock_bh(&htt->tx_lock); rcu_read_lock(); -- 2.31.1
