mac80211: Dynamically set CoDel parameters per station

CoDel can be too aggressive if a station sends at a very low rate,
leading reduced throughput. This gets worse the more stations are
present, as each station gets more bursty the longer the round-robin
scheduling between stations takes.

This adds dynamic adjustment of CoDel parameters per station. It uses
the rate selection information to estimate throughput and sets more
lenient CoDel parameters if the estimated throughput is below a
threshold (modified by the number of active stations).

A new callback is added that drivers can use to notify mac80211 about
changes in expected throughput, so the same adjustment can be made for
cards that implement rate control in firmware. Drivers that don't use
this will just get the default parameters.

Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
[remove currently unnecessary EXPORT_SYMBOL, fix kernel-doc, remove
inline annotation]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 76ed24a..e01daff 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4205,6 +4205,22 @@
 			    int max_rates);
 
 /**
+ * ieee80211_sta_set_expected_throughput - set the expected tpt for a station
+ *
+ * Call this function to notify mac80211 about a change in expected throughput
+ * to a station. A driver for a device that does rate control in firmware can
+ * call this function when the expected throughput estimate towards a station
+ * changes. The information is used to tune the CoDel AQM applied to traffic
+ * going towards that station (which can otherwise be too aggressive and cause
+ * slow stations to starve).
+ *
+ * @pubsta: the station to set throughput for.
+ * @thr: the current expected throughput in kbps.
+ */
+void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta,
+					   u32 thr);
+
+/**
  * ieee80211_tx_status - transmit status callback
  *
  * Call this function for all transmitted frames after they have been
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 4260182..b15412c 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -154,6 +154,12 @@
 
 	p += scnprintf(p,
 		       bufsz+buf-p,
+		       "target %uus interval %uus ecn %s\n",
+		       codel_time_to_us(sta->cparams.target),
+		       codel_time_to_us(sta->cparams.interval),
+		       sta->cparams.ecn ? "yes" : "no");
+	p += scnprintf(p,
+		       bufsz+buf-p,
 		       "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n");
 
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index ea1f431..76f303f 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -943,6 +943,8 @@
 
 	drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
 
+	ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta));
+
 	return 0;
 }
 EXPORT_SYMBOL(rate_control_set_rates);
@@ -991,4 +993,3 @@
 	local->rate_ctrl = NULL;
 	rate_control_free(local, ref);
 }
-
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 7cdf7a8..f59434a 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -20,6 +20,7 @@
 #include <linux/timer.h>
 #include <linux/rtnetlink.h>
 
+#include <net/codel.h>
 #include <net/mac80211.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -425,6 +426,11 @@
 
 	sta->sta.max_rc_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA;
 
+	sta->cparams.ce_threshold = CODEL_DISABLED_THRESHOLD;
+	sta->cparams.target = MS2TIME(20);
+	sta->cparams.interval = MS2TIME(100);
+	sta->cparams.ecn = true;
+
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
 
 	return sta;
@@ -2310,3 +2316,27 @@
 		return stats->last_rx;
 	return sta->status_stats.last_ack;
 }
+
+static void sta_update_codel_params(struct sta_info *sta, u32 thr)
+{
+	if (!sta->sdata->local->ops->wake_tx_queue)
+		return;
+
+	if (thr && thr < STA_SLOW_THRESHOLD * sta->local->num_sta) {
+		sta->cparams.target = MS2TIME(50);
+		sta->cparams.interval = MS2TIME(300);
+		sta->cparams.ecn = false;
+	} else {
+		sta->cparams.target = MS2TIME(20);
+		sta->cparams.interval = MS2TIME(100);
+		sta->cparams.ecn = true;
+	}
+}
+
+void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta,
+					   u32 thr)
+{
+	struct sta_info *sta = container_of(pubsta, struct sta_info, sta);
+
+	sta_update_codel_params(sta, thr);
+}
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 5609cac..b58c3b1 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -394,6 +394,14 @@
 };
 
 /**
+ * The bandwidth threshold below which the per-station CoDel parameters will be
+ * scaled to be more lenient (to prevent starvation of slow stations). This
+ * value will be scaled by the number of active stations when it is being
+ * applied.
+ */
+#define STA_SLOW_THRESHOLD 6000 /* 6 Mbps */
+
+/**
  * struct sta_info - STA information
  *
  * This structure collects information about a station that
@@ -446,6 +454,7 @@
  * @known_smps_mode: the smps_mode the client thinks we are in. Relevant for
  *	AP only.
  * @cipher_scheme: optional cipher scheme for this station
+ * @cparams: CoDel parameters for this station.
  * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED)
  * @fast_tx: TX fastpath information
  * @fast_rx: RX fastpath information
@@ -549,6 +558,8 @@
 	enum ieee80211_smps_mode known_smps_mode;
 	const struct ieee80211_cipher_scheme *cipher_scheme;
 
+	struct codel_params cparams;
+
 	u8 reserved_tid;
 
 	struct cfg80211_chan_def tdls_chandef;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 04b22f8..b8dc411 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1340,9 +1340,16 @@
 
 	local = container_of(fq, struct ieee80211_local, fq);
 	txqi = container_of(tin, struct txq_info, tin);
-	cparams = &local->cparams;
 	cstats = &txqi->cstats;
 
+	if (txqi->txq.sta) {
+		struct sta_info *sta = container_of(txqi->txq.sta,
+						    struct sta_info, sta);
+		cparams = &sta->cparams;
+	} else {
+		cparams = &local->cparams;
+	}
+
 	if (flow == &txqi->def_flow)
 		cvars = &txqi->def_cvars;
 	else