[PATCH ath-next v5 9/9] wifi: ath11k: budget the tx completion handler

[Julius Bairaktaris]

ath11k_dp_tx_completion_handler() reaps the whole release ring, and
ath11k_dp_service_srng() charges none of it against the NAPI budget,
unlike the receive handlers. Since the handler now ends in a scheduling
round, a full ring gets one round for all of it. Reap at most the budget
per poll and return the count, so a round runs once per budget of
completions; NAPI polls again at once for the rest.

BE aql_txq_limit 500/1000 us, three interleaved runs per arm: both arms
reach 94.4 to 94.8 Mbit/s, and the sender retransmits 4, 6 and 8
segments with this patch against 8, 644 and 296 without.

Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.9.0.1-02146-QCAHKSWPL_SILICONZ-1

Assisted-by: Claude:claude-opus-5-5
Signed-off-by: Julius Bairaktaris <julius at bairaktaris.de>
---
 drivers/net/wireless/ath/ath11k/dp.c    | 10 ++++++++--
 drivers/net/wireless/ath/ath11k/dp_tx.c | 11 +++++++++--
 drivers/net/wireless/ath/ath11k/dp_tx.h |  3 ++-
 3 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index 3e0a6bdfa0505..5775ad4269393 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -783,8 +783,14 @@ int ath11k_dp_service_srng(struct ath11k_base *ab,
 
 	for (i = 0; i < ab->hw_params.hal_params->num_tx_rings; i++) {
 		if (BIT(ab->hw_params.hal_params->tcl2wbm_rbm_map[i].wbm_ring_num) &
-		    ab->hw_params.ring_mask->tx[grp_id])
-			ath11k_dp_tx_completion_handler(ab, i);
+		    ab->hw_params.ring_mask->tx[grp_id]) {
+			work_done =
+				ath11k_dp_tx_completion_handler(ab, i, budget);
+			budget -= work_done;
+			tot_work_done += work_done;
+			if (budget <= 0)
+				goto done;
+		}
 	}
 
 	if (ab->hw_params.ring_mask->rx_err[grp_id]) {
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.c b/drivers/net/wireless/ath/ath11k/dp_tx.c
index fb6a43dc45b81..13c464dce2943 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.c
@@ -692,7 +692,8 @@ static inline void ath11k_dp_tx_status_parse(struct ath11k_base *ab,
 		ts->rate_stats = 0;
 }
 
-void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
+int ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id,
+				    int budget)
 {
 	struct ath11k *ar;
 	struct ath11k_dp *dp = &ab->dp;
@@ -702,6 +703,7 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 	struct hal_tx_status ts = {};
 	struct dp_tx_ring *tx_ring = &dp->tx_ring[ring_id];
 	unsigned long push = 0;
+	int done = 0;
 	u32 *desc;
 	u32 msdu_id;
 	u8 mac_id, i;
@@ -730,10 +732,13 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 
 	spin_unlock_bh(&status_ring->lock);
 
-	while (ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_tail) != tx_ring->tx_status_head) {
+	while (done < budget &&
+	       ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_tail) !=
+	       tx_ring->tx_status_head) {
 		struct hal_wbm_release_ring *tx_status;
 		u32 desc_id;
 
+		done++;
 		tx_ring->tx_status_tail =
 			ATH11K_TX_COMPL_NEXT(tx_ring->tx_status_tail);
 		tx_status = &tx_ring->tx_status[tx_ring->tx_status_tail];
@@ -789,6 +794,8 @@ void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id)
 	for_each_set_bit(i, &push, ab->num_radios * IEEE80211_NUM_ACS)
 		ath11k_mac_tx_push_pending(ab->pdevs[i / IEEE80211_NUM_ACS].ar,
 					   i % IEEE80211_NUM_ACS);
+
+	return done;
 }
 
 int ath11k_dp_tx_send_reo_cmd(struct ath11k_base *ab, struct dp_rx_tid *rx_tid,
diff --git a/drivers/net/wireless/ath/ath11k/dp_tx.h b/drivers/net/wireless/ath/ath11k/dp_tx.h
index 9303b5ba6e012..b5296cda73e30 100644
--- a/drivers/net/wireless/ath/ath11k/dp_tx.h
+++ b/drivers/net/wireless/ath/ath11k/dp_tx.h
@@ -21,7 +21,8 @@ void ath11k_dp_tx_update_txcompl(struct ath11k *ar, struct hal_tx_status *ts);
 int ath11k_dp_tx_htt_h2t_ver_req_msg(struct ath11k_base *ab);
 int ath11k_dp_tx(struct ath11k *ar, struct ath11k_vif *arvif,
 		 struct ath11k_sta *arsta, struct sk_buff *skb);
-void ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id);
+int ath11k_dp_tx_completion_handler(struct ath11k_base *ab, int ring_id,
+				    int budget);
 int ath11k_dp_tx_send_reo_cmd(struct ath11k_base *ab, struct dp_rx_tid *rx_tid,
 			      enum hal_reo_cmd_type type,
 			      struct ath11k_hal_reo_cmd *cmd,
-- 
2.53.0