Under heavy traffic, ath11k experiences frequent -ENOMEM errors ("failed to transmit frame -12") when the hardware TCL ring fills up. This issue is more commonly observed in VMs with PCIe passthrough but also occurs on bare metal systems. It is particularly problematic on devices with a single shared TCL ring where all traffic classes compete for the same 512 descriptor slots. Implement a custom wake_tx_queue operation that: 1. Checks hardware ring space before dequeuing packets from mac80211 2. Uses per-packet locking to serialize ring access and prevent races 3. Syncs with hardware state to get accurate free slot count 4. Returns early during firmware crash in the same way as other tx paths This approach follows the pattern used in the iwlwifi driver, adapted for ath11k's hardware ring architecture. This eliminates -ENOMEM errors and improves throughput by optimizing resource usage and preventing unnecessary packet drops. Signed-off-by: Jose Ignacio Tornos Martinez --- drivers/net/wireless/ath/ath11k/dp.c | 1 + drivers/net/wireless/ath/ath11k/dp.h | 2 ++ drivers/net/wireless/ath/ath11k/mac.c | 49 ++++++++++++++++++++++++++- 3 files changed, 51 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c index f389b97acbdd..2e5978ec2b05 100644 --- a/drivers/net/wireless/ath/ath11k/dp.c +++ b/drivers/net/wireless/ath/ath11k/dp.c @@ -1087,6 +1087,7 @@ int ath11k_dp_alloc(struct ath11k_base *ab) for (i = 0; i < ab->hw_params.hal_params->num_tx_rings; i++) { idr_init(&dp->tx_ring[i].txbuf_idr); spin_lock_init(&dp->tx_ring[i].tx_idr_lock); + spin_lock_init(&dp->tx_ring[i].wake_tx_lock); dp->tx_ring[i].tcl_data_ring_id = i; dp->tx_ring[i].tx_status_head = 0; diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h index 84f66839f0c6..6d99501aa269 100644 --- a/drivers/net/wireless/ath/ath11k/dp.h +++ b/drivers/net/wireless/ath/ath11k/dp.h @@ -87,6 +87,8 @@ struct dp_tx_ring { struct idr txbuf_idr; /* Protects txbuf_idr and num_pending */ spinlock_t tx_idr_lock; + /* Serializes wake_tx_queue operations for this ring */ + spinlock_t wake_tx_lock; struct hal_wbm_release_ring *tx_status; int tx_status_head; int tx_status_tail; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 2d55cdc4d165..48a9e2b45e3d 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -10065,9 +10065,56 @@ static int ath11k_mac_op_sta_state(struct ieee80211_hw *hw, return ret; } +static void ath11k_mac_op_wake_tx_queue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_tx_control control = { + .sta = txq->sta, + }; + struct ath11k *ar = hw->priv; + struct dp_tx_ring *tx_ring; + struct hal_srng *tcl_ring; + struct sk_buff *skb; + int num_free; + u8 ring_id; + + if (!ar) + return; + + if (unlikely(test_bit(ATH11K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))) + return; + + ring_id = txq->ac % ar->ab->hw_params.hal_params->num_tx_rings; + tx_ring = &ar->ab->dp.tx_ring[ring_id]; + tcl_ring = &ar->ab->hal.srng_list[tx_ring->tcl_data_ring.ring_id]; + + while (1) { + spin_lock_bh(&tx_ring->wake_tx_lock); + + spin_lock(&tcl_ring->lock); + num_free = ath11k_hal_srng_src_num_free(ar->ab, tcl_ring, true); + spin_unlock(&tcl_ring->lock); + + if (num_free == 0) { + spin_unlock_bh(&tx_ring->wake_tx_lock); + break; + } + + skb = ieee80211_tx_dequeue(hw, txq); + if (!skb) { + spin_unlock_bh(&tx_ring->wake_tx_lock); + break; + } + + ath11k_mac_op_tx(hw, &control, skb); + + spin_unlock_bh(&tx_ring->wake_tx_lock); + } +} + static const struct ieee80211_ops ath11k_ops = { .tx = ath11k_mac_op_tx, - .wake_tx_queue = ieee80211_handle_wake_tx_queue, + .wake_tx_queue = ath11k_mac_op_wake_tx_queue, .start = ath11k_mac_op_start, .stop = ath11k_mac_op_stop, .reconfig_complete = ath11k_mac_op_reconfig_complete, -- 2.54.0 Under heavy traffic, ath12k can hang and experiences -ENOMEM errors ("failed to transmit frame -12") when the hardware TCL ring fills up. This issue is more commonly observed in VMs with PCIe passthrough but also occurs on bare metal systems. Implement a custom wake_tx_queue operation that: 1. Checks hardware ring space before dequeuing packets from mac80211 2. Uses per-packet locking to serialize ring access and prevent races 3. Syncs with hardware state to get accurate free slot count 4. Returns early during firmware crash in the same way as other tx paths This approach follows the pattern used in the iwlwifi driver, adapted for ath12k's hardware ring architecture. This prevents hangs, eliminates -ENOMEM errors, and improves throughput by optimizing resource usage and preventing unnecessary packet drops. Signed-off-by: Jose Ignacio Tornos Martinez --- drivers/net/wireless/ath/ath12k/dp.c | 1 + drivers/net/wireless/ath/ath12k/dp.h | 2 + drivers/net/wireless/ath/ath12k/hal.c | 1 + drivers/net/wireless/ath/ath12k/wifi7/hw.c | 50 +++++++++++++++++++++- 4 files changed, 53 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c index af5f11fc1d84..3d46cfbf0a1c 100644 --- a/drivers/net/wireless/ath/ath12k/dp.c +++ b/drivers/net/wireless/ath/ath12k/dp.c @@ -1539,6 +1539,7 @@ static int ath12k_dp_setup(struct ath12k_base *ab) } for (i = 0; i < ab->hw_params->max_tx_ring; i++) { + spin_lock_init(&dp->tx_ring[i].wake_tx_lock); dp->tx_ring[i].tcl_data_ring_id = i; dp->tx_ring[i].tx_status_head = 0; diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h index f8cfc7bb29dd..68d2020be9b8 100644 --- a/drivers/net/wireless/ath/ath12k/dp.h +++ b/drivers/net/wireless/ath/ath12k/dp.h @@ -58,6 +58,8 @@ struct dp_tx_ring { u8 tcl_data_ring_id; struct dp_srng tcl_data_ring; struct dp_srng tcl_comp_ring; + /* Serializes wake_tx_queue operations for this ring */ + spinlock_t wake_tx_lock; struct hal_wbm_completion_ring_tx *tx_status; int tx_status_head; int tx_status_tail; diff --git a/drivers/net/wireless/ath/ath12k/hal.c b/drivers/net/wireless/ath/ath12k/hal.c index a164563fff28..c1c656e4550b 100644 --- a/drivers/net/wireless/ath/ath12k/hal.c +++ b/drivers/net/wireless/ath/ath12k/hal.c @@ -390,6 +390,7 @@ int ath12k_hal_srng_src_num_free(struct ath12k_base *ab, struct hal_srng *srng, else return ((srng->ring_size - hp + tp) / srng->entry_size) - 1; } +EXPORT_SYMBOL(ath12k_hal_srng_src_num_free); void *ath12k_hal_srng_src_next_peek(struct ath12k_base *ab, struct hal_srng *srng) diff --git a/drivers/net/wireless/ath/ath12k/wifi7/hw.c b/drivers/net/wireless/ath/ath12k/wifi7/hw.c index d9fdd2fc8298..e3a6f9cdee24 100644 --- a/drivers/net/wireless/ath/ath12k/wifi7/hw.c +++ b/drivers/net/wireless/ath/ath12k/wifi7/hw.c @@ -1100,9 +1100,57 @@ static void ath12k_wifi7_mac_op_tx(struct ieee80211_hw *hw, } } +static void ath12k_wifi7_mac_op_wake_tx_queue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ath12k_hw *ah = ath12k_hw_to_ah(hw); + struct ieee80211_tx_control control = { + .sta = txq->sta, + }; + struct ath12k *ar = ah->radio; + struct dp_tx_ring *tx_ring; + struct hal_srng *tcl_ring; + struct ath12k_dp *dp; + struct sk_buff *skb; + int num_free; + + if (!ar) + return; + + if (unlikely(test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))) + return; + + dp = ar->ab->dp; + tx_ring = &dp->tx_ring[txq->ac % dp->hw_params->max_tx_ring]; + tcl_ring = &dp->hal->srng_list[tx_ring->tcl_data_ring.ring_id]; + + while (1) { + spin_lock_bh(&tx_ring->wake_tx_lock); + + spin_lock(&tcl_ring->lock); + num_free = ath12k_hal_srng_src_num_free(ar->ab, tcl_ring, true); + spin_unlock(&tcl_ring->lock); + + if (num_free == 0) { + spin_unlock_bh(&tx_ring->wake_tx_lock); + break; + } + + skb = ieee80211_tx_dequeue(hw, txq); + if (!skb) { + spin_unlock_bh(&tx_ring->wake_tx_lock); + break; + } + + ath12k_wifi7_mac_op_tx(hw, &control, skb); + + spin_unlock_bh(&tx_ring->wake_tx_lock); + } +} + static const struct ieee80211_ops ath12k_ops_wifi7 = { .tx = ath12k_wifi7_mac_op_tx, - .wake_tx_queue = ieee80211_handle_wake_tx_queue, + .wake_tx_queue = ath12k_wifi7_mac_op_wake_tx_queue, .start = ath12k_mac_op_start, .stop = ath12k_mac_op_stop, .reconfig_complete = ath12k_mac_op_reconfig_complete, -- 2.54.0