Merge tag 'mac80211-next-for-net-next-2019-11-22' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next

Johannes Berg says:

====================
The interesting new thing here is AQL, the Airtime Queue Limit
patchset from Kan Yan (Google) and Toke Høiland-Jørgensen (Redhat).
The effect is intended to eventually be similar to BQL, but byte
queue limits are not useful in wifi where the actual throughput can
vary by around 4 orders of magnitude. There are more details in the
patches themselves.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 900 insertions, 24 deletions

diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 4f03ebe732fa..6cbb1286d6c0 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -32,7 +32,8 @@ mac80211-y := \
 	chan.o \
 	trace.o mlme.o \
 	tdls.o \
-	ocb.o
+	ocb.o \
+	airtime.o
 
 mac80211-$(CONFIG_MAC80211_LEDS) += led.o
 mac80211-$(CONFIG_MAC80211_DEBUGFS) += \
diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c
new file mode 100644
index 000000000000..63cb0028b02d
--- /dev/null
+++ b/net/mac80211/airtime.c
@@ -0,0 +1,597 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (C) 2019 Felix Fietkau <nbd@nbd.name>
+ */
+
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+#include "sta_info.h"
+
+#define AVG_PKT_SIZE	1024
+
+/* Number of bits for an average sized packet */
+#define MCS_NBITS (AVG_PKT_SIZE << 3)
+
+/* Number of kilo-symbols (symbols * 1024) for a packet with (bps) bits per
+ * symbol. We use k-symbols to avoid rounding in the _TIME macros below.
+ */
+#define MCS_N_KSYMS(bps) DIV_ROUND_UP(MCS_NBITS << 10, (bps))
+
+/* Transmission time (in 1024 * usec) for a packet containing (ksyms) * 1024
+ * symbols.
+ */
+#define MCS_SYMBOL_TIME(sgi, ksyms)					\
+	(sgi ?								\
+	  ((ksyms) * 4 * 18) / 20 :		/* 3.6 us per sym */	\
+	  ((ksyms) * 4)			/* 4.0 us per sym */	\
+	)
+
+/* Transmit duration for the raw data part of an average sized packet */
+#define MCS_DURATION(streams, sgi, bps) \
+	((u32)MCS_SYMBOL_TIME(sgi, MCS_N_KSYMS((streams) * (bps))))
+
+#define MCS_DURATION_S(shift, streams, sgi, bps)		\
+	((u16)((MCS_DURATION(streams, sgi, bps) >> shift)))
+
+/* These should match the values in enum nl80211_he_gi */
+#define HE_GI_08 0
+#define HE_GI_16 1
+#define HE_GI_32 2
+
+/* Transmission time (1024 usec) for a packet containing (ksyms) * k-symbols */
+#define HE_SYMBOL_TIME(gi, ksyms)					\
+	(gi == HE_GI_08 ?						\
+	 ((ksyms) * 16 * 17) / 20 :		/* 13.6 us per sym */	\
+	 (gi == HE_GI_16 ?						\
+	  ((ksyms) * 16 * 18) / 20 :		/* 14.4 us per sym */	\
+	  ((ksyms) * 16)			/* 16.0 us per sym */	\
+	 ))
+
+/* Transmit duration for the raw data part of an average sized packet */
+#define HE_DURATION(streams, gi, bps) \
+	((u32)HE_SYMBOL_TIME(gi, MCS_N_KSYMS((streams) * (bps))))
+
+#define HE_DURATION_S(shift, streams, gi, bps)		\
+	(HE_DURATION(streams, gi, bps) >> shift)
+
+#define BW_20			0
+#define BW_40			1
+#define BW_80			2
+#define BW_160			3
+
+/*
+ * Define group sort order: HT40 -> SGI -> #streams
+ */
+#define IEEE80211_MAX_STREAMS		4
+#define IEEE80211_HT_STREAM_GROUPS	4 /* BW(=2) * SGI(=2) */
+#define IEEE80211_VHT_STREAM_GROUPS	8 /* BW(=4) * SGI(=2) */
+
+#define IEEE80211_HE_MAX_STREAMS	8
+#define IEEE80211_HE_STREAM_GROUPS	12 /* BW(=4) * GI(=3) */
+
+#define IEEE80211_HT_GROUPS_NB	(IEEE80211_MAX_STREAMS *	\
+				 IEEE80211_HT_STREAM_GROUPS)
+#define IEEE80211_VHT_GROUPS_NB	(IEEE80211_MAX_STREAMS *	\
+					 IEEE80211_VHT_STREAM_GROUPS)
+#define IEEE80211_HE_GROUPS_NB	(IEEE80211_HE_MAX_STREAMS *	\
+				 IEEE80211_HE_STREAM_GROUPS)
+#define IEEE80211_GROUPS_NB	(IEEE80211_HT_GROUPS_NB +	\
+				 IEEE80211_VHT_GROUPS_NB +	\
+				 IEEE80211_HE_GROUPS_NB)
+
+#define IEEE80211_HT_GROUP_0	0
+#define IEEE80211_VHT_GROUP_0	(IEEE80211_HT_GROUP_0 + IEEE80211_HT_GROUPS_NB)
+#define IEEE80211_HE_GROUP_0	(IEEE80211_VHT_GROUP_0 + IEEE80211_VHT_GROUPS_NB)
+
+#define MCS_GROUP_RATES		12
+
+#define HT_GROUP_IDX(_streams, _sgi, _ht40)	\
+	IEEE80211_HT_GROUP_0 +			\
+	IEEE80211_MAX_STREAMS * 2 * _ht40 +	\
+	IEEE80211_MAX_STREAMS * _sgi +		\
+	_streams - 1
+
+#define _MAX(a, b) (((a)>(b))?(a):(b))
+
+#define GROUP_SHIFT(duration)						\
+	_MAX(0, 16 - __builtin_clz(duration))
+
+/* MCS rate information for an MCS group */
+#define __MCS_GROUP(_streams, _sgi, _ht40, _s)				\
+	[HT_GROUP_IDX(_streams, _sgi, _ht40)] = {			\
+	.shift = _s,							\
+	.duration = {							\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 54 : 26),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 108 : 52),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 162 : 78),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 216 : 104),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 324 : 156),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 432 : 208),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 486 : 234),	\
+		MCS_DURATION_S(_s, _streams, _sgi, _ht40 ? 540 : 260)	\
+	}								\
+}
+
+#define MCS_GROUP_SHIFT(_streams, _sgi, _ht40)				\
+	GROUP_SHIFT(MCS_DURATION(_streams, _sgi, _ht40 ? 54 : 26))
+
+#define MCS_GROUP(_streams, _sgi, _ht40)				\
+	__MCS_GROUP(_streams, _sgi, _ht40,				\
+		    MCS_GROUP_SHIFT(_streams, _sgi, _ht40))
+
+#define VHT_GROUP_IDX(_streams, _sgi, _bw)				\
+	(IEEE80211_VHT_GROUP_0 +					\
+	 IEEE80211_MAX_STREAMS * 2 * (_bw) +				\
+	 IEEE80211_MAX_STREAMS * (_sgi) +				\
+	 (_streams) - 1)
+
+#define BW2VBPS(_bw, r4, r3, r2, r1)					\
+	(_bw == BW_160 ? r4 : _bw == BW_80 ? r3 : _bw == BW_40 ? r2 : r1)
+
+#define __VHT_GROUP(_streams, _sgi, _bw, _s)				\
+	[VHT_GROUP_IDX(_streams, _sgi, _bw)] = {			\
+	.shift = _s,							\
+	.duration = {							\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw,  234,  117,  54,  26)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw,  468,  234, 108,  52)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw,  702,  351, 162,  78)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw,  936,  468, 216, 104)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw, 1404,  702, 324, 156)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw, 1872,  936, 432, 208)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw, 2106, 1053, 486, 234)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw, 2340, 1170, 540, 260)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw, 2808, 1404, 648, 312)),	\
+		MCS_DURATION_S(_s, _streams, _sgi,			\
+			       BW2VBPS(_bw, 3120, 1560, 720, 346))	\
+        }								\
+}
+
+#define VHT_GROUP_SHIFT(_streams, _sgi, _bw)				\
+	GROUP_SHIFT(MCS_DURATION(_streams, _sgi,			\
+				 BW2VBPS(_bw, 243, 117,  54,  26)))
+
+#define VHT_GROUP(_streams, _sgi, _bw)					\
+	__VHT_GROUP(_streams, _sgi, _bw,				\
+		    VHT_GROUP_SHIFT(_streams, _sgi, _bw))
+
+
+#define HE_GROUP_IDX(_streams, _gi, _bw)				\
+	(IEEE80211_HE_GROUP_0 +					\
+	 IEEE80211_HE_MAX_STREAMS * 3 * (_bw) +			\
+	 IEEE80211_HE_MAX_STREAMS * (_gi) +				\
+	 (_streams) - 1)
+
+#define __HE_GROUP(_streams, _gi, _bw, _s)				\
+	[HE_GROUP_IDX(_streams, _gi, _bw)] = {			\
+	.shift = _s,							\
+	.duration = {							\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,   979,  489,  230,  115)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  1958,  979,  475,  230)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  2937, 1468,  705,  345)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  3916, 1958,  936,  475)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  5875, 2937, 1411,  705)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  7833, 3916, 1872,  936)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  8827, 4406, 2102, 1051)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw,  9806, 4896, 2347, 1166)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw, 11764, 5875, 2808, 1411)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw, 13060, 6523, 3124, 1555)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw, 14702, 7344, 3513, 1756)),	\
+		HE_DURATION_S(_s, _streams, _gi,			\
+			      BW2VBPS(_bw, 16329, 8164, 3902, 1944))	\
+        }								\
+}
+
+#define HE_GROUP_SHIFT(_streams, _gi, _bw)				\
+	GROUP_SHIFT(HE_DURATION(_streams, _gi,			\
+				BW2VBPS(_bw,   979,  489,  230,  115)))
+
+#define HE_GROUP(_streams, _gi, _bw)					\
+	__HE_GROUP(_streams, _gi, _bw,				\
+		   HE_GROUP_SHIFT(_streams, _gi, _bw))
+struct mcs_group {
+	u8 shift;
+	u16 duration[MCS_GROUP_RATES];
+};
+
+static const struct mcs_group airtime_mcs_groups[] = {
+	MCS_GROUP(1, 0, BW_20),
+	MCS_GROUP(2, 0, BW_20),
+	MCS_GROUP(3, 0, BW_20),
+	MCS_GROUP(4, 0, BW_20),
+
+	MCS_GROUP(1, 1, BW_20),
+	MCS_GROUP(2, 1, BW_20),
+	MCS_GROUP(3, 1, BW_20),
+	MCS_GROUP(4, 1, BW_20),
+
+	MCS_GROUP(1, 0, BW_40),
+	MCS_GROUP(2, 0, BW_40),
+	MCS_GROUP(3, 0, BW_40),
+	MCS_GROUP(4, 0, BW_40),
+
+	MCS_GROUP(1, 1, BW_40),
+	MCS_GROUP(2, 1, BW_40),
+	MCS_GROUP(3, 1, BW_40),
+	MCS_GROUP(4, 1, BW_40),
+
+	VHT_GROUP(1, 0, BW_20),
+	VHT_GROUP(2, 0, BW_20),
+	VHT_GROUP(3, 0, BW_20),
+	VHT_GROUP(4, 0, BW_20),
+
+	VHT_GROUP(1, 1, BW_20),
+	VHT_GROUP(2, 1, BW_20),
+	VHT_GROUP(3, 1, BW_20),
+	VHT_GROUP(4, 1, BW_20),
+
+	VHT_GROUP(1, 0, BW_40),
+	VHT_GROUP(2, 0, BW_40),
+	VHT_GROUP(3, 0, BW_40),
+	VHT_GROUP(4, 0, BW_40),
+
+	VHT_GROUP(1, 1, BW_40),
+	VHT_GROUP(2, 1, BW_40),
+	VHT_GROUP(3, 1, BW_40),
+	VHT_GROUP(4, 1, BW_40),
+
+	VHT_GROUP(1, 0, BW_80),
+	VHT_GROUP(2, 0, BW_80),
+	VHT_GROUP(3, 0, BW_80),
+	VHT_GROUP(4, 0, BW_80),
+
+	VHT_GROUP(1, 1, BW_80),
+	VHT_GROUP(2, 1, BW_80),
+	VHT_GROUP(3, 1, BW_80),
+	VHT_GROUP(4, 1, BW_80),
+
+	VHT_GROUP(1, 0, BW_160),
+	VHT_GROUP(2, 0, BW_160),
+	VHT_GROUP(3, 0, BW_160),
+	VHT_GROUP(4, 0, BW_160),
+
+	VHT_GROUP(1, 1, BW_160),
+	VHT_GROUP(2, 1, BW_160),
+	VHT_GROUP(3, 1, BW_160),
+	VHT_GROUP(4, 1, BW_160),
+
+	HE_GROUP(1, HE_GI_08, BW_20),
+	HE_GROUP(2, HE_GI_08, BW_20),
+	HE_GROUP(3, HE_GI_08, BW_20),
+	HE_GROUP(4, HE_GI_08, BW_20),
+	HE_GROUP(5, HE_GI_08, BW_20),
+	HE_GROUP(6, HE_GI_08, BW_20),
+	HE_GROUP(7, HE_GI_08, BW_20),
+	HE_GROUP(8, HE_GI_08, BW_20),
+
+	HE_GROUP(1, HE_GI_16, BW_20),
+	HE_GROUP(2, HE_GI_16, BW_20),
+	HE_GROUP(3, HE_GI_16, BW_20),
+	HE_GROUP(4, HE_GI_16, BW_20),
+	HE_GROUP(5, HE_GI_16, BW_20),
+	HE_GROUP(6, HE_GI_16, BW_20),
+	HE_GROUP(7, HE_GI_16, BW_20),
+	HE_GROUP(8, HE_GI_16, BW_20),
+
+	HE_GROUP(1, HE_GI_32, BW_20),
+	HE_GROUP(2, HE_GI_32, BW_20),
+	HE_GROUP(3, HE_GI_32, BW_20),
+	HE_GROUP(4, HE_GI_32, BW_20),
+	HE_GROUP(5, HE_GI_32, BW_20),
+	HE_GROUP(6, HE_GI_32, BW_20),
+	HE_GROUP(7, HE_GI_32, BW_20),
+	HE_GROUP(8, HE_GI_32, BW_20),
+
+	HE_GROUP(1, HE_GI_08, BW_40),
+	HE_GROUP(2, HE_GI_08, BW_40),
+	HE_GROUP(3, HE_GI_08, BW_40),
+	HE_GROUP(4, HE_GI_08, BW_40),
+	HE_GROUP(5, HE_GI_08, BW_40),
+	HE_GROUP(6, HE_GI_08, BW_40),
+	HE_GROUP(7, HE_GI_08, BW_40),
+	HE_GROUP(8, HE_GI_08, BW_40),
+
+	HE_GROUP(1, HE_GI_16, BW_40),
+	HE_GROUP(2, HE_GI_16, BW_40),
+	HE_GROUP(3, HE_GI_16, BW_40),
+	HE_GROUP(4, HE_GI_16, BW_40),
+	HE_GROUP(5, HE_GI_16, BW_40),
+	HE_GROUP(6, HE_GI_16, BW_40),
+	HE_GROUP(7, HE_GI_16, BW_40),
+	HE_GROUP(8, HE_GI_16, BW_40),
+
+	HE_GROUP(1, HE_GI_32, BW_40),
+	HE_GROUP(2, HE_GI_32, BW_40),
+	HE_GROUP(3, HE_GI_32, BW_40),
+	HE_GROUP(4, HE_GI_32, BW_40),
+	HE_GROUP(5, HE_GI_32, BW_40),
+	HE_GROUP(6, HE_GI_32, BW_40),
+	HE_GROUP(7, HE_GI_32, BW_40),
+	HE_GROUP(8, HE_GI_32, BW_40),
+
+	HE_GROUP(1, HE_GI_08, BW_80),
+	HE_GROUP(2, HE_GI_08, BW_80),
+	HE_GROUP(3, HE_GI_08, BW_80),
+	HE_GROUP(4, HE_GI_08, BW_80),
+	HE_GROUP(5, HE_GI_08, BW_80),
+	HE_GROUP(6, HE_GI_08, BW_80),
+	HE_GROUP(7, HE_GI_08, BW_80),
+	HE_GROUP(8, HE_GI_08, BW_80),
+
+	HE_GROUP(1, HE_GI_16, BW_80),
+	HE_GROUP(2, HE_GI_16, BW_80),
+	HE_GROUP(3, HE_GI_16, BW_80),
+	HE_GROUP(4, HE_GI_16, BW_80),
+	HE_GROUP(5, HE_GI_16, BW_80),
+	HE_GROUP(6, HE_GI_16, BW_80),
+	HE_GROUP(7, HE_GI_16, BW_80),
+	HE_GROUP(8, HE_GI_16, BW_80),
+
+	HE_GROUP(1, HE_GI_32, BW_80),
+	HE_GROUP(2, HE_GI_32, BW_80),
+	HE_GROUP(3, HE_GI_32, BW_80),
+	HE_GROUP(4, HE_GI_32, BW_80),
+	HE_GROUP(5, HE_GI_32, BW_80),
+	HE_GROUP(6, HE_GI_32, BW_80),
+	HE_GROUP(7, HE_GI_32, BW_80),
+	HE_GROUP(8, HE_GI_32, BW_80),
+
+	HE_GROUP(1, HE_GI_08, BW_160),
+	HE_GROUP(2, HE_GI_08, BW_160),
+	HE_GROUP(3, HE_GI_08, BW_160),
+	HE_GROUP(4, HE_GI_08, BW_160),
+	HE_GROUP(5, HE_GI_08, BW_160),
+	HE_GROUP(6, HE_GI_08, BW_160),
+	HE_GROUP(7, HE_GI_08, BW_160),
+	HE_GROUP(8, HE_GI_08, BW_160),
+
+	HE_GROUP(1, HE_GI_16, BW_160),
+	HE_GROUP(2, HE_GI_16, BW_160),
+	HE_GROUP(3, HE_GI_16, BW_160),
+	HE_GROUP(4, HE_GI_16, BW_160),
+	HE_GROUP(5, HE_GI_16, BW_160),
+	HE_GROUP(6, HE_GI_16, BW_160),
+	HE_GROUP(7, HE_GI_16, BW_160),
+	HE_GROUP(8, HE_GI_16, BW_160),
+
+	HE_GROUP(1, HE_GI_32, BW_160),
+	HE_GROUP(2, HE_GI_32, BW_160),
+	HE_GROUP(3, HE_GI_32, BW_160),
+	HE_GROUP(4, HE_GI_32, BW_160),
+	HE_GROUP(5, HE_GI_32, BW_160),
+	HE_GROUP(6, HE_GI_32, BW_160),
+	HE_GROUP(7, HE_GI_32, BW_160),
+	HE_GROUP(8, HE_GI_32, BW_160),
+};
+
+static u32
+ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre,
+				    bool cck, int len)
+{
+	u32 duration;
+
+	if (cck) {
+		duration = 144 + 48; /* preamble + PLCP */
+		if (short_pre)
+			duration >>= 1;
+
+		duration += 10; /* SIFS */
+	} else {
+		duration = 20 + 16; /* premable + SIFS */
+	}
+
+	len <<= 3;
+	duration += (len * 10) / bitrate;
+
+	return duration;
+}
+
+u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
+			      struct ieee80211_rx_status *status,
+			      int len)
+{
+	struct ieee80211_supported_band *sband;
+	const struct ieee80211_rate *rate;
+	bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI;
+	bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE;
+	int bw, streams;
+	int group, idx;
+	u32 duration;
+	bool cck;
+
+	switch (status->bw) {
+	case RATE_INFO_BW_20:
+		bw = BW_20;
+		break;
+	case RATE_INFO_BW_40:
+		bw = BW_40;
+		break;
+	case RATE_INFO_BW_80:
+		bw = BW_80;
+		break;
+	case RATE_INFO_BW_160:
+		bw = BW_160;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	switch (status->encoding) {
+	case RX_ENC_LEGACY:
+		if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ))
+			return 0;
+
+		sband = hw->wiphy->bands[status->band];
+		if (!sband || status->rate_idx > sband->n_bitrates)
+			return 0;
+
+		rate = &sband->bitrates[status->rate_idx];
+		cck = rate->flags & IEEE80211_RATE_MANDATORY_B;
+
+		return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp,
+							   cck, len);
+
+	case RX_ENC_VHT:
+		streams = status->nss;
+		idx = status->rate_idx;
+		group = VHT_GROUP_IDX(streams, sgi, bw);
+		break;
+	case RX_ENC_HT:
+		streams = ((status->rate_idx >> 3) & 3) + 1;
+		idx = status->rate_idx & 7;
+		group = HT_GROUP_IDX(streams, sgi, bw);
+		break;
+	case RX_ENC_HE:
+		streams = status->nss;
+		idx = status->rate_idx;
+		group = HE_GROUP_IDX(streams, status->he_gi, bw);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	if (WARN_ON_ONCE((status->encoding != RX_ENC_HE && streams > 4) ||
+			 (status->encoding == RX_ENC_HE && streams > 8)))
+		return 0;
+
+	duration = airtime_mcs_groups[group].duration[idx];
+	duration <<= airtime_mcs_groups[group].shift;
+	duration *= len;
+	duration /= AVG_PKT_SIZE;
+	duration /= 1024;
+
+	duration += 36 + (streams << 2);
+
+	return duration;
+}
+EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime);
+
+static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw,
+					  struct ieee80211_tx_rate *rate,
+					  u8 band, int len)
+{
+	struct ieee80211_rx_status stat = {
+		.band = band,
+	};
+
+	if (rate->idx < 0 || !rate->count)
+		return 0;
+
+	if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+		stat.bw = RATE_INFO_BW_80;
+	else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+		stat.bw = RATE_INFO_BW_40;
+	else
+		stat.bw = RATE_INFO_BW_20;
+
+	stat.enc_flags = 0;
+	if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
+		stat.enc_flags |= RX_ENC_FLAG_SHORTPRE;
+	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+		stat.enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	stat.rate_idx = rate->idx;
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		stat.encoding = RX_ENC_VHT;
+		stat.rate_idx = ieee80211_rate_get_vht_mcs(rate);
+		stat.nss = ieee80211_rate_get_vht_nss(rate);
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		stat.encoding = RX_ENC_HT;
+	} else {
+		stat.encoding = RX_ENC_LEGACY;
+	}
+
+	return ieee80211_calc_rx_airtime(hw, &stat, len);
+}
+
+u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw,
+			      struct ieee80211_tx_info *info,
+			      int len)
+{
+	u32 duration = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(info->status.rates); i++) {
+		struct ieee80211_tx_rate *rate = &info->status.rates[i];
+		u32 cur_duration;
+
+		cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate,
+							      info->band, len);
+		if (!cur_duration)
+			break;
+
+		duration += cur_duration * rate->count;
+	}
+
+	return duration;
+}
+EXPORT_SYMBOL_GPL(ieee80211_calc_tx_airtime);
+
+u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_sta *pubsta,
+				       int len)
+{
+	struct ieee80211_supported_band *sband;
+	struct ieee80211_chanctx_conf *conf;
+	int rateidx, shift = 0;
+	bool cck, short_pream;
+	u32 basic_rates;
+	u8 band = 0;
+	u16 rate;
+
+	len += 38; /* Ethernet header length */
+
+	conf = rcu_dereference(vif->chanctx_conf);
+	if (conf) {
+		band = conf->def.chan->band;
+		shift = ieee80211_chandef_get_shift(&conf->def);
+	}
+
+	if (pubsta) {
+		struct sta_info *sta = container_of(pubsta, struct sta_info,
+						    sta);
+
+		return ieee80211_calc_tx_airtime_rate(hw,
+						      &sta->tx_stats.last_rate,
+						      band, len);
+	}
+
+	if (!conf)
+		return 0;
+
+	/* No station to get latest rate from, so calculate the worst-case
+	 * duration using the lowest configured basic rate.
+	 */
+	sband = hw->wiphy->bands[band];
+
+	basic_rates = vif->bss_conf.basic_rates;
+	short_pream = vif->bss_conf.use_short_preamble;
+
+	rateidx = basic_rates ? ffs(basic_rates) - 1 : 0;
+	rate = sband->bitrates[rateidx].bitrate << shift;
+	cck = sband->bitrates[rateidx].flags & IEEE80211_RATE_MANDATORY_B;
+
+	return ieee80211_calc_legacy_rate_duration(rate, short_pream, cck, len);
+}
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 568b3b276931..ad41d74530c6 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -59,6 +59,8 @@ static const struct file_operations name## _ops = {			\
 	debugfs_create_file(#name, mode, phyd, local, &name## _ops);
 
 
+DEBUGFS_READONLY_FILE(hw_conf, "%x",
+		      local->hw.conf.flags);
 DEBUGFS_READONLY_FILE(user_power, "%d",
 		      local->user_power_level);
 DEBUGFS_READONLY_FILE(power, "%d",
@@ -148,6 +150,87 @@ static const struct file_operations aqm_ops = {
 	.llseek = default_llseek,
 };
 
+static ssize_t aql_txq_limit_read(struct file *file,
+				  char __user *user_buf,
+				  size_t count,
+				  loff_t *ppos)
+{
+	struct ieee80211_local *local = file->private_data;
+	char buf[400];
+	int len = 0;
+
+	len = scnprintf(buf, sizeof(buf),
+			"AC	AQL limit low	AQL limit high\n"
+			"VO	%u		%u\n"
+			"VI	%u		%u\n"
+			"BE	%u		%u\n"
+			"BK	%u		%u\n",
+			local->aql_txq_limit_low[IEEE80211_AC_VO],
+			local->aql_txq_limit_high[IEEE80211_AC_VO],
+			local->aql_txq_limit_low[IEEE80211_AC_VI],
+			local->aql_txq_limit_high[IEEE80211_AC_VI],
+			local->aql_txq_limit_low[IEEE80211_AC_BE],
+			local->aql_txq_limit_high[IEEE80211_AC_BE],
+			local->aql_txq_limit_low[IEEE80211_AC_BK],
+			local->aql_txq_limit_high[IEEE80211_AC_BK]);
+	return simple_read_from_buffer(user_buf, count, ppos,
+				       buf, len);
+}
+
+static ssize_t aql_txq_limit_write(struct file *file,
+				   const char __user *user_buf,
+				   size_t count,
+				   loff_t *ppos)
+{
+	struct ieee80211_local *local = file->private_data;
+	char buf[100];
+	size_t len;
+	u32 ac, q_limit_low, q_limit_high, q_limit_low_old, q_limit_high_old;
+	struct sta_info *sta;
+
+	if (count > sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[sizeof(buf) - 1] = 0;
+	len = strlen(buf);
+	if (len > 0 && buf[len - 1] == '\n')
+		buf[len - 1] = 0;
+
+	if (sscanf(buf, "%u %u %u", &ac, &q_limit_low, &q_limit_high) != 3)
+		return -EINVAL;
+
+	if (ac >= IEEE80211_NUM_ACS)
+		return -EINVAL;
+
+	q_limit_low_old = local->aql_txq_limit_low[ac];
+	q_limit_high_old = local->aql_txq_limit_high[ac];
+
+	local->aql_txq_limit_low[ac] = q_limit_low;
+	local->aql_txq_limit_high[ac] = q_limit_high;
+
+	mutex_lock(&local->sta_mtx);
+	list_for_each_entry(sta, &local->sta_list, list) {
+		/* If a sta has customized queue limits, keep it */
+		if (sta->airtime[ac].aql_limit_low == q_limit_low_old &&
+		    sta->airtime[ac].aql_limit_high == q_limit_high_old) {
+			sta->airtime[ac].aql_limit_low = q_limit_low;
+			sta->airtime[ac].aql_limit_high = q_limit_high;
+		}
+	}
+	mutex_unlock(&local->sta_mtx);
+	return count;
+}
+
+static const struct file_operations aql_txq_limit_ops = {
+	.write = aql_txq_limit_write,
+	.read = aql_txq_limit_read,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
 static ssize_t force_tx_status_read(struct file *file,
 				    char __user *user_buf,
 				    size_t count,
@@ -433,6 +516,7 @@ void debugfs_hw_add(struct ieee80211_local *local)
 	DEBUGFS_ADD(hwflags);
 	DEBUGFS_ADD(user_power);
 	DEBUGFS_ADD(power);
+	DEBUGFS_ADD(hw_conf);
 	DEBUGFS_ADD_MODE(force_tx_status, 0600);
 
 	if (local->ops->wake_tx_queue)
@@ -441,6 +525,10 @@ void debugfs_hw_add(struct ieee80211_local *local)
 	debugfs_create_u16("airtime_flags", 0600,
 			   phyd, &local->airtime_flags);
 
+	DEBUGFS_ADD(aql_txq_limit);
+	debugfs_create_u32("aql_threshold", 0600,
+			   phyd, &local->aql_threshold);
+
 	statsd = debugfs_create_dir("statistics", phyd);
 
 	/* if the dir failed, don't put all the other things into the root! */
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index c8ad20c28c43..0185e6e5e5d1 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -197,10 +197,12 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf,
 {
 	struct sta_info *sta = file->private_data;
 	struct ieee80211_local *local = sta->sdata->local;
-	size_t bufsz = 200;
+	size_t bufsz = 400;
 	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;
 
@@ -212,19 +214,22 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf,
 		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",
-		rx_airtime,
-		tx_airtime,
-		sta->airtime_weight,
-		deficit[0],
-		deficit[1],
-		deficit[2],
-		deficit[3]);
+		"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",
+		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]),
 
 	rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
 	kfree(buf);
@@ -236,7 +241,25 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf,
 {
 	struct sta_info *sta = file->private_data;
 	struct ieee80211_local *local = sta->sdata->local;
-	int ac;
+	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;
 
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		spin_lock_bh(&local->active_txq_lock[ac]);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 05406e9c05b3..ad15b3be8bb3 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1142,6 +1142,10 @@ struct ieee80211_local {
 	u16 schedule_round[IEEE80211_NUM_ACS];
 
 	u16 airtime_flags;
+	u32 aql_txq_limit_low[IEEE80211_NUM_ACS];
+	u32 aql_txq_limit_high[IEEE80211_NUM_ACS];
+	u32 aql_threshold;
+	atomic_t aql_total_pending_airtime;
 
 	const struct ieee80211_ops *ops;
 
@@ -2249,6 +2253,10 @@ const char *ieee80211_get_reason_code_string(u16 reason_code);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
+u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_sta *pubsta,
+				       int len);
 #ifdef CONFIG_MAC80211_NOINLINE
 #define debug_noinline noinline
 #else
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 2d05c4cfaf6d..6cca0853f183 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -667,8 +667,16 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
 	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
 		INIT_LIST_HEAD(&local->active_txqs[i]);
 		spin_lock_init(&local->active_txq_lock[i]);
+		local->aql_txq_limit_low[i] = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L;
+		local->aql_txq_limit_high[i] =
+			IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H;
 	}
-	local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX;
+
+	local->airtime_flags = AIRTIME_USE_TX |
+			       AIRTIME_USE_RX |
+			       AIRTIME_USE_AQL;
+	local->aql_threshold = IEEE80211_AQL_THRESHOLD;
+	atomic_set(&local->aql_total_pending_airtime, 0);
 
 	INIT_LIST_HEAD(&local->chanctx_list);
 	mutex_init(&local->chanctx_mtx);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 8d3a2389b055..8eafd81e97b4 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -210,6 +210,20 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
 	return NULL;
 }
 
+struct sta_info *sta_info_get_by_addrs(struct ieee80211_local *local,
+				       const u8 *sta_addr, const u8 *vif_addr)
+{
+	struct rhlist_head *tmp;
+	struct sta_info *sta;
+
+	for_each_sta_info(local, sta_addr, sta, tmp) {
+		if (ether_addr_equal(vif_addr, sta->sdata->vif.addr))
+			return sta;
+	}
+
+	return NULL;
+}
+
 struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
 				     int idx)
 {
@@ -396,6 +410,9 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 		skb_queue_head_init(&sta->ps_tx_buf[i]);
 		skb_queue_head_init(&sta->tx_filtered[i]);
 		sta->airtime[i].deficit = sta->airtime_weight;
+		atomic_set(&sta->airtime[i].aql_tx_pending, 0);
+		sta->airtime[i].aql_limit_low = local->aql_txq_limit_low[i];
+		sta->airtime[i].aql_limit_high = local->aql_txq_limit_high[i];
 	}
 
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++)
@@ -1893,6 +1910,41 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid,
 }
 EXPORT_SYMBOL(ieee80211_sta_register_airtime);
 
+void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local,
+					  struct sta_info *sta, u8 ac,
+					  u16 tx_airtime, bool tx_completed)
+{
+	int tx_pending;
+
+	if (!tx_completed) {
+		if (sta)
+			atomic_add(tx_airtime,
+				   &sta->airtime[ac].aql_tx_pending);
+
+		atomic_add(tx_airtime, &local->aql_total_pending_airtime);
+		return;
+	}
+
+	if (sta) {
+		tx_pending = atomic_sub_return(tx_airtime,
+					       &sta->airtime[ac].aql_tx_pending);
+		if (WARN_ONCE(tx_pending < 0,
+			      "STA %pM AC %d txq pending airtime underflow: %u, %u",
+			      sta->addr, ac, tx_pending, tx_airtime))
+			atomic_cmpxchg(&sta->airtime[ac].aql_tx_pending,
+				       tx_pending, 0);
+	}
+
+	tx_pending = atomic_sub_return(tx_airtime,
+				       &local->aql_total_pending_airtime);
+	if (WARN_ONCE(tx_pending < 0,
+		      "Device %s AC %d pending airtime underflow: %u, %u",
+		      wiphy_name(local->hw.wiphy), ac, tx_pending,
+		      tx_airtime))
+		atomic_cmpxchg(&local->aql_total_pending_airtime,
+			       tx_pending, 0);
+}
+
 int sta_info_move_state(struct sta_info *sta,
 			enum ieee80211_sta_state new_state)
 {
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 369c2dddce52..ad5d8a4ae56d 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -127,13 +127,21 @@ enum ieee80211_agg_stop_reason {
 /* 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;
 	u64 tx_airtime;
 	s64 deficit;
+	atomic_t aql_tx_pending; /* Estimated airtime for frames pending */
+	u32 aql_limit_low;
+	u32 aql_limit_high;
 };
 
+void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local,
+					  struct sta_info *sta, u8 ac,
+					  u16 tx_airtime, bool tx_completed);
+
 struct sta_info;
 
 /**
@@ -725,6 +733,10 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
 struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
 				  const u8 *addr);
 
+/* user must hold sta_mtx or be in RCU critical section */
+struct sta_info *sta_info_get_by_addrs(struct ieee80211_local *local,
+				       const u8 *sta_addr, const u8 *vif_addr);
+
 #define for_each_sta_info(local, _addr, _sta, _tmp)			\
 	rhl_for_each_entry_rcu(_sta, _tmp,				\
 			       sta_info_hash_lookup(local, _addr), hash_node)
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index ab8ba5835ca0..b720feaf9a74 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -670,12 +670,26 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
 				      struct sk_buff *skb, bool dropped)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	u16 tx_time_est = ieee80211_info_get_tx_time_est(info);
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	bool acked = info->flags & IEEE80211_TX_STAT_ACK;
 
 	if (dropped)
 		acked = false;
 
+	if (tx_time_est) {
+		struct sta_info *sta;
+
+		rcu_read_lock();
+
+		sta = sta_info_get_by_addrs(local, hdr->addr1, hdr->addr2);
+		ieee80211_sta_update_pending_airtime(local, sta,
+						     skb_get_queue_mapping(skb),
+						     tx_time_est,
+						     true);
+		rcu_read_unlock();
+	}
+
 	if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) {
 		struct ieee80211_sub_if_data *sdata;
 
@@ -877,6 +891,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 	struct ieee80211_bar *bar;
 	int shift = 0;
 	int tid = IEEE80211_NUM_TIDS;
+	u16 tx_time_est;
 
 	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
 
@@ -986,6 +1001,17 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 			ieee80211_sta_register_airtime(&sta->sta, tid,
 						       info->status.tx_time, 0);
 
+		if ((tx_time_est = ieee80211_info_get_tx_time_est(info)) > 0) {
+			/* Do this here to avoid the expensive lookup of the sta
+			 * in ieee80211_report_used_skb().
+			 */
+			ieee80211_sta_update_pending_airtime(local, sta,
+							     skb_get_queue_mapping(skb),
+							     tx_time_est,
+							     true);
+			ieee80211_info_set_tx_time_est(info, 0);
+		}
+
 		if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
 			if (info->flags & IEEE80211_TX_STAT_ACK) {
 				if (sta->status_stats.lost_packets)
@@ -1030,7 +1056,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 			I802_DEBUG_INC(local->dot11FailedCount);
 	}
 
-	if (ieee80211_is_nullfunc(fc) && ieee80211_has_pm(fc) &&
+	if ((ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)) &&
+	    ieee80211_has_pm(fc) &&
 	    ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) &&
 	    !(info->flags & IEEE80211_TX_CTL_INJECTED) &&
 	    local->ps_sdata && !(local->scanning)) {
@@ -1073,19 +1100,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 		.skb = skb,
 		.info = IEEE80211_SKB_CB(skb),
 	};
-	struct rhlist_head *tmp;
 	struct sta_info *sta;
 
 	rcu_read_lock();
 
-	for_each_sta_info(local, hdr->addr1, sta, tmp) {
-		/* skip wrong virtual interface */
-		if (!ether_addr_equal(hdr->addr2, sta->sdata->vif.addr))
-			continue;
-
+	sta = sta_info_get_by_addrs(local, hdr->addr1, hdr->addr2);
+	if (sta)
 		status.sta = &sta->sta;
-		break;
-	}
 
 	__ieee80211_tx_status(hw, &status);
 	rcu_read_unlock();
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index db38be1b75fa..b696b9136f4c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2270,6 +2270,9 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	 * isn't always enough to find the interface to use; for proper
 	 * VLAN/WDS support we will need a different mechanism (which
 	 * likely isn't going to be monitor interfaces).
+	 *
+	 * This is necessary, for example, for old hostapd versions that
+	 * don't use nl80211-based management TX/RX.
 	 */
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
@@ -3551,6 +3554,9 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 
 	WARN_ON_ONCE(softirq_count() == 0);
 
+	if (!ieee80211_txq_airtime_check(hw, txq))
+		return NULL;
+
 begin:
 	spin_lock_bh(&fq->lock);
 
@@ -3661,6 +3667,21 @@ begin:
 	}
 
 	IEEE80211_SKB_CB(skb)->control.vif = vif;
+
+	if (local->airtime_flags & AIRTIME_USE_AQL) {
+		u32 airtime;
+
+		airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta,
+							     skb->len);
+		if (airtime) {
+			airtime = ieee80211_info_set_tx_time_est(info, airtime);
+			ieee80211_sta_update_pending_airtime(local, tx.sta,
+							     txq->ac,
+							     airtime,
+							     false);
+		}
+	}
+
 	return skb;
 
 out:
@@ -3674,7 +3695,8 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 	struct ieee80211_txq *ret = NULL;
-	struct txq_info *txqi = NULL;
+	struct txq_info *txqi = NULL, *head = NULL;
+	bool found_eligible_txq = false;
 
 	spin_lock_bh(&local->active_txq_lock[ac]);
 
@@ -3685,13 +3707,30 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
 	if (!txqi)
 		goto out;
 
+	if (txqi == head) {
+		if (!found_eligible_txq)
+			goto out;
+		else
+			found_eligible_txq = false;
+	}
+
+	if (!head)
+		head = txqi;
+
 	if (txqi->txq.sta) {
 		struct sta_info *sta = container_of(txqi->txq.sta,
-						struct sta_info, sta);
+						    struct sta_info, sta);
+		bool aql_check = ieee80211_txq_airtime_check(hw, &txqi->txq);
+		s64 deficit = sta->airtime[txqi->txq.ac].deficit;
+
+		if (aql_check)
+			found_eligible_txq = true;
 
-		if (sta->airtime[txqi->txq.ac].deficit < 0) {
+		if (deficit < 0)
 			sta->airtime[txqi->txq.ac].deficit +=
 				sta->airtime_weight;
+
+		if (deficit < 0 || !aql_check) {
 			list_move_tail(&txqi->schedule_order,
 				       &local->active_txqs[txqi->txq.ac]);
 			goto begin;
@@ -3745,6 +3784,33 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL(__ieee80211_schedule_txq);
 
+bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw,
+				 struct ieee80211_txq *txq)
+{
+	struct sta_info *sta;
+	struct ieee80211_local *local = hw_to_local(hw);
+
+	if (!(local->airtime_flags & AIRTIME_USE_AQL))
+		return true;
+
+	if (!txq->sta)
+		return true;
+
+	sta = container_of(txq->sta, struct sta_info, sta);
+	if (atomic_read(&sta->airtime[txq->ac].aql_tx_pending) <
+	    sta->airtime[txq->ac].aql_limit_low)
+		return true;
+
+	if (atomic_read(&local->aql_total_pending_airtime) <
+	    local->aql_threshold &&
+	    atomic_read(&sta->airtime[txq->ac].aql_tx_pending) <
+	    sta->airtime[txq->ac].aql_limit_high)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(ieee80211_txq_airtime_check);
+
 bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
 				struct ieee80211_txq *txq)
 {