[PATCH 2/4] wifi: ath9k: check all tx queues with one multi-read

[Nerijus Bendžiūnas]

Before a channel change ath9k_hw_channel_change() asks
ath9k_hw_numtxpending() about each of the ten queues in turn, and each
call reads AR_QSTS and then AR_Q_TXE, so confirming a drained radio
takes up to twenty register reads. On the USB devices those are twenty
synchronous WMI round trips, paid on every hop before any tuning starts.

Collect the ten queue status registers and AR_Q_TXE through
REG_READ_MULTI() instead, split into chunks the transport can carry, and
apply the same pending test to the results. PCI implements the
multi-read as a loop of ordinary reads, so it sees no change beyond the
loop moving.

Signed-off-by: Nerijus Bendžiūnas <nerijus.bendziunas@xxxxxxxxx>
---
 drivers/net/wireless/ath/ath9k/hw.c  | 13 +++++-----
 drivers/net/wireless/ath/ath9k/mac.c | 36 ++++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath9k/mac.h |  1 +
 3 files changed, 43 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index e08ab73fcacb..d204cdf3fa8f 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1547,7 +1547,7 @@ static bool ath9k_hw_channel_change(struct ath_hw *ah,
 	struct ath9k_hw_capabilities *pCap = &ah->caps;
 	bool band_switch = false, mode_diff = false;
 	u8 ini_reloaded = 0;
-	u32 qnum;
+	int qnum;
 	int r;
 
 	if (pCap->hw_caps & ATH9K_HW_CAP_FCC_BAND_SWITCH) {
@@ -1556,12 +1556,11 @@ static bool ath9k_hw_channel_change(struct ath_hw *ah,
 		mode_diff = !!(flags_diff & ~CHANNEL_HT);
 	}
 
-	for (qnum = 0; qnum < AR_NUM_QCU; qnum++) {
-		if (ath9k_hw_numtxpending(ah, qnum)) {
-			ath_dbg(common, QUEUE,
-				"Transmit frames pending on queue %d\n", qnum);
-			return false;
-		}
+	qnum = ath9k_hw_first_txpending(ah);
+	if (qnum >= 0) {
+		ath_dbg(common, QUEUE,
+			"Transmit frames pending on queue %d\n", qnum);
+		return false;
 	}
 
 	if (!ath9k_hw_rfbus_req(ah)) {
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index b070403e083f..0d8369bbbadf 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -77,6 +77,42 @@ u32 ath9k_hw_numtxpending(struct ath_hw *ah, u32 q)
 }
 EXPORT_SYMBOL(ath9k_hw_numtxpending);
 
+/*
+ * Asking ath9k_hw_numtxpending() about each queue in turn costs up to two
+ * register reads per queue, and on the USB devices every one of those is a
+ * synchronous WMI round trip. Collect the queue status registers and AR_Q_TXE
+ * with the multi-read op instead, in chunks the transport can carry.
+ *
+ * Returns the first queue that still has frames pending, or -1 if they are
+ * all drained.
+ */
+int ath9k_hw_first_txpending(struct ath_hw *ah)
+{
+	u32 addr[AR_NUM_QCU + 1];
+	u32 val[AR_NUM_QCU + 1];
+	u32 q, txe, done = 0;
+
+	for (q = 0; q < AR_NUM_QCU; q++)
+		addr[q] = AR_QSTS(q);
+	addr[AR_NUM_QCU] = AR_Q_TXE;
+
+	while (done < ARRAY_SIZE(addr)) {
+		u32 count = min_t(u32, ARRAY_SIZE(addr) - done,
+				  ATH9K_MULTI_READ_MAX);
+
+		REG_READ_MULTI(ah, addr + done, val + done, count);
+		done += count;
+	}
+
+	txe = val[AR_NUM_QCU];
+	for (q = 0; q < AR_NUM_QCU; q++) {
+		if ((val[q] & AR_Q_STS_PEND_FR_CNT) || (txe & BIT(q)))
+			return q;
+	}
+
+	return -1;
+}
+
 /**
  * ath9k_hw_updatetxtriglevel - adjusts the frame trigger level
  *
diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index 16203e7ecf29..5b94ce087be2 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -721,6 +721,7 @@ u32 ath9k_hw_gettxbuf(struct ath_hw *ah, u32 q);
 void ath9k_hw_puttxbuf(struct ath_hw *ah, u32 q, u32 txdp);
 void ath9k_hw_txstart(struct ath_hw *ah, u32 q);
 u32 ath9k_hw_numtxpending(struct ath_hw *ah, u32 q);
+int ath9k_hw_first_txpending(struct ath_hw *ah);
 bool ath9k_hw_updatetxtriglevel(struct ath_hw *ah, bool bIncTrigLevel);
 bool ath9k_hw_stop_dma_queue(struct ath_hw *ah, u32 q);
 void ath9k_hw_abort_tx_dma(struct ath_hw *ah);
-- 
2.55.0