mac80211: Turn AQL into an NL80211_EXT_FEATURE

Instead of just having an airtime flag in debugfs, turn AQL into a proper
NL80211_EXT_FEATURE, so drivers can turn it on when they are ready, and so
we also expose the presence of the feature to userspace.

This also has the effect of flipping the default, so drivers have to opt in
to using AQL instead of getting it by default with TXQs. To keep
functionality the same as pre-patch, we set this feature for ath10k (which
is where it is needed the most).

While we're at it, split out the debugfs interface so AQL gets its own
per-station debugfs file instead of using the 'airtime' file.

[Johannes:]
This effectively disables AQL for iwlwifi, where it fixes a number of
issues:
* TSO in iwlwifi is causing underflows and associated warnings in AQL
* HE (802.11ax) rates aren't reported properly so at HE rates, AQL could
never have a valid estimate (it'd use 6 Mbps instead of up to 2400!)

Signed-off-by: Toke Høiland-Jørgensen <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Fixes: 3ace10f5b5ad ("mac80211: Implement Airtime-based Queue Limit (AQL)")
Signed-off-by: Johannes Berg <[e-mail]>

drivers/net/wireless/ath/ath10k/mac.c

···
 	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 	wiphy_ext_feature_set(ar->hw->wiphy,
 			      NL80211_EXT_FEATURE_SET_SCAN_DWELL);
+	wiphy_ext_feature_set(ar->hw->wiphy, NL80211_EXT_FEATURE_AQL);
 
 	if (test_bit(WMI_SERVICE_TX_DATA_ACK_RSSI, ar->wmi.svc_map) ||
 	    test_bit(WMI_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS, ar->wmi.svc_map))

include/uapi/linux/nl80211.h

···
  *	with VLAN tagged frames and separate VLAN-specific netdevs added using
  *	vconfig similarly to the Ethernet case.
  *
+ * @NL80211_EXT_FEATURE_AQL: The driver supports the Airtime Queue Limit (AQL)
+ *	feature, which prevents bufferbloat by using the expected transmission
+ *	time to limit the amount of data buffered in the hardware.
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
···
 	NL80211_EXT_FEATURE_STA_TX_PWR,
 	NL80211_EXT_FEATURE_SAE_OFFLOAD,
 	NL80211_EXT_FEATURE_VLAN_OFFLOAD,
+	NL80211_EXT_FEATURE_AQL,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,

net/mac80211/debugfs_sta.c

···
 	char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf;
 	u64 rx_airtime = 0, tx_airtime = 0;
 	s64 deficit[IEEE80211_NUM_ACS];
-	u32 q_depth[IEEE80211_NUM_ACS];
-	u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS];
 	ssize_t rv;
 	int ac;
 
···
 		rx_airtime += sta->airtime[ac].rx_airtime;
 		tx_airtime += sta->airtime[ac].tx_airtime;
 		deficit[ac] = sta->airtime[ac].deficit;
-		q_limit_l[ac] = sta->airtime[ac].aql_limit_low;
-		q_limit_h[ac] = sta->airtime[ac].aql_limit_high;
 		spin_unlock_bh(&local->active_txq_lock[ac]);
-		q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending);
 	}
 
 	p += scnprintf(p, bufsz + buf - p,
 		"RX: %llu us\nTX: %llu us\nWeight: %u\n"
-		"Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n"
-		"Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n"
-		"Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n",
+		"Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n",
 		rx_airtime, tx_airtime, sta->airtime_weight,
-		deficit[0], deficit[1], deficit[2], deficit[3],
-		q_depth[0], q_depth[1], q_depth[2], q_depth[3],
-		q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1],
-		q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]),
+		deficit[0], deficit[1], deficit[2], deficit[3]);
 
 	rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
 	kfree(buf);
···
 {
 	struct sta_info *sta = file->private_data;
 	struct ieee80211_local *local = sta->sdata->local;
-	u32 ac, q_limit_l, q_limit_h;
-	char _buf[100] = {}, *buf = _buf;
-
-	if (count > sizeof(_buf))
-		return -EINVAL;
-
-	if (copy_from_user(buf, userbuf, count))
-		return -EFAULT;
-
-	buf[sizeof(_buf) - 1] = '\0';
-	if (sscanf(buf, "queue limit %u %u %u", &ac, &q_limit_l, &q_limit_h)
-	    != 3)
-		return -EINVAL;
-
-	if (ac >= IEEE80211_NUM_ACS)
-		return -EINVAL;
-
-	sta->airtime[ac].aql_limit_low = q_limit_l;
-	sta->airtime[ac].aql_limit_high = q_limit_h;
+	int ac;
 
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		spin_lock_bh(&local->active_txq_lock[ac]);
···
 	return count;
 }
 STA_OPS_RW(airtime);
+
+static ssize_t sta_aql_read(struct file *file, char __user *userbuf,
+				size_t count, loff_t *ppos)
+{
+	struct sta_info *sta = file->private_data;
+	struct ieee80211_local *local = sta->sdata->local;
+	size_t bufsz = 400;
+	char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf;
+	u32 q_depth[IEEE80211_NUM_ACS];
+	u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS];
+	ssize_t rv;
+	int ac;
+
+	if (!buf)
+		return -ENOMEM;
+
+	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+		spin_lock_bh(&local->active_txq_lock[ac]);
+		q_limit_l[ac] = sta->airtime[ac].aql_limit_low;
+		q_limit_h[ac] = sta->airtime[ac].aql_limit_high;
+		spin_unlock_bh(&local->active_txq_lock[ac]);
+		q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending);
+	}
+
+	p += scnprintf(p, bufsz + buf - p,
+		"Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n"
+		"Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n",
+		q_depth[0], q_depth[1], q_depth[2], q_depth[3],
+		q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1],
+		q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]),
+
+	rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
+	kfree(buf);
+	return rv;
+}
+
+static ssize_t sta_aql_write(struct file *file, const char __user *userbuf,
+				 size_t count, loff_t *ppos)
+{
+	struct sta_info *sta = file->private_data;
+	u32 ac, q_limit_l, q_limit_h;
+	char _buf[100] = {}, *buf = _buf;
+
+	if (count > sizeof(_buf))
+		return -EINVAL;
+
+	if (copy_from_user(buf, userbuf, count))
+		return -EFAULT;
+
+	buf[sizeof(_buf) - 1] = '\0';
+	if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h)
+	    != 3)
+		return -EINVAL;
+
+	if (ac >= IEEE80211_NUM_ACS)
+		return -EINVAL;
+
+	sta->airtime[ac].aql_limit_low = q_limit_l;
+	sta->airtime[ac].aql_limit_high = q_limit_h;
+
+	return count;
+}
+STA_OPS_RW(aql);
+
 
 static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
 					size_t count, loff_t *ppos)
···
 	if (wiphy_ext_feature_isset(local->hw.wiphy,
 				    NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
 		DEBUGFS_ADD(airtime);
+
+	if (wiphy_ext_feature_isset(local->hw.wiphy,
+				    NL80211_EXT_FEATURE_AQL))
+		DEBUGFS_ADD(aql);
 
 	debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir,
 			   &sta->driver_buffered_tids);

net/mac80211/main.c

···
 			IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H;
 	}
 
-	local->airtime_flags = AIRTIME_USE_TX |
-			       AIRTIME_USE_RX |
-			       AIRTIME_USE_AQL;
+	local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX;
 	local->aql_threshold = IEEE80211_AQL_THRESHOLD;
 	atomic_set(&local->aql_total_pending_airtime, 0);
 

net/mac80211/sta_info.c

···
 {
 	int tx_pending;
 
+	if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL))
+		return;
+
 	if (!tx_completed) {
 		if (sta)
 			atomic_add(tx_airtime,

net/mac80211/sta_info.h

···
 /* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */
 #define AIRTIME_USE_TX		BIT(0)
 #define AIRTIME_USE_RX		BIT(1)
-#define AIRTIME_USE_AQL		BIT(2)
 
 struct airtime_info {
 	u64 rx_airtime;

net/mac80211/tx.c

···
 
 	IEEE80211_SKB_CB(skb)->control.vif = vif;
 
-	if (local->airtime_flags & AIRTIME_USE_AQL) {
+	if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) {
 		u32 airtime;
 
 		airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta,
···
 	struct sta_info *sta;
 	struct ieee80211_local *local = hw_to_local(hw);
 
-	if (!(local->airtime_flags & AIRTIME_USE_AQL))
+	if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL))
 		return true;
 
 	if (!txq->sta)