Re: [PATCH v5 4/4] wifi: ath12k: implement custom wake_tx_queue with flow control

[Jeff Johnson]

On 8/7/2026 3:58 AM, Jose Ignacio Tornos Martinez wrote:
> 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-ring locking (wake_tx_lock with spin_lock_bh) to serialize
>    concurrent wake_tx_queue calls targeting the same ring and to ensure
>    bottom halves are disabled as required by ieee80211_tx_dequeue()
> 3. Syncs with hardware state to get accurate free slot count
> 4. Resolves the target TCL ring once using get_ring_selector(txq->ac),
>    which selects the ring based on the access category
> 5. 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.

Tested-on missing

> 
> Signed-off-by: Jose Ignacio Tornos Martinez <jtornosm@xxxxxxxxxx>
> ---
> v5: Remove an unused variable
> v4: https://lore.kernel.org/all/20260724053121.15759-5-jtornosm@xxxxxxxxxx/
> 
>  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 | 76 +++++++++++++++++++++-
>  4 files changed, 79 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..071cb5d30931 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_GPL(ath12k_hal_srng_src_num_free);

NAK, must be EXPORT_SYMBOL()
The ath12k code was contributed under the license:
// SPDX-License-Identifier: BSD-3-Clause-Clear

>  
>  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 7436cf70925a..af0a3ba805dd 100644
> --- a/drivers/net/wireless/ath/ath12k/wifi7/hw.c
> +++ b/drivers/net/wireless/ath/ath12k/wifi7/hw.c
> @@ -1100,9 +1100,82 @@ 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_vif *ahvif = ath12k_vif_to_ahvif(txq->vif);
> +	struct ieee80211_tx_control control = {
> +		.sta = txq->sta,
> +	};
> +	struct ieee80211_vif *vif = txq->vif;
> +	struct ath12k_link_vif *arvif;
> +	struct dp_tx_ring *tx_ring;
> +	struct hal_srng *tcl_ring;
> +	struct ath12k_sta *ahsta;
> +	struct ath12k_dp *dp;
> +	struct sk_buff *skb;
> +	struct ath12k *ar;
> +	u8 ring_selector;
> +	int num_free;
> +	u8 ring_id;
> +	u8 link_id;
> +
> +	if (ieee80211_vif_is_mld(vif) && txq->sta) {
> +		ahsta = ath12k_sta_to_ahsta(txq->sta);
> +		link_id = ahsta->assoc_link_id;
> +	} else {
> +		link_id = ahvif->deflink.link_id;
> +	}
> +
> +	rcu_read_lock();

does this lock really need to be held for the entire function including the tx
loop?

> +
> +	arvif = rcu_dereference(ahvif->link[link_id]);
> +	if (!arvif || !arvif->ar) {
> +		rcu_read_unlock();
> +		return;
> +	}
> +
> +	ar = arvif->ar;
> +	dp = ar->ab->dp;

or is it sufficient to cache these values and then rcu_read_unlock() here?
my LLM reviewer seems to think that would be sufficient

note the spinlock in the while loop will cause the RCU read lock to be held
when invoking mac_op_tx(), satisfying the RCU lock requirement there.

> +
> +	ring_selector = dp->hw_params->hw_ops->get_ring_selector(txq->ac);
> +	ring_id = ring_selector % dp->hw_params->max_tx_ring;
> +	tx_ring = &dp->tx_ring[ring_id];
> +	tcl_ring = &dp->hal->srng_list[tx_ring->tcl_data_ring.ring_id];
> +
> +	while (1) {
> +		if (unlikely(test_bit(ATH12K_FLAG_CRASH_FLUSH,
> +				      &ar->ab->dev_flags)))
> +			break;
> +
> +		spin_lock_bh(&tx_ring->wake_tx_lock);

using guard(spinlock_bh)(&tx_ring->wake_tx_lock) would eliminate the need for
all the spin_unlock_bh(&tx_ring->wake_tx_lock) calls

> +
> +		spin_lock(&tcl_ring->lock);

seems this should be spin_lock_bh() to align with all other callers in the driver.

> +		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);
> +	}
> +
> +	rcu_read_unlock();
> +}
> +
>  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,