This series is a first attempt at porting the Airtime Queue Limits concept from
the out-of-tree ath10k implementation[0] to mac80211. This version takes Kan's
patch to do the throttling in mac80211, and replaces the driver API with the
mechanism from the previous version of my series, which instead calculated the
expected airtime at dequeue time inside mac80211, storing it in the SKB cb
field.
This series also imports Felix' airtime calculation code from mt76 into
mac80211, adjusting the API so it can be used from TX dequeue, by extracting the
latest TX rate from the tx_stats structure kept for each station.
As before, I've only compile tested this (lacking the proper hardware to do more
testing). So I'm hoping someone with a proper testing setup can take the whole
thing for a spin... :)
The series is also available in my git repo here:
https://git.kernel.org/pub/scm/linux/kernel/git/toke/linux.git/log/?h=mac80211-aql-02
Changelog:
v5:
- Add missing export of ieee80211_calc_rx_airtime() and make
ieee80211_calc_tx_airtime_rate() static (kbuildbot).
- Use skb_get_queue_mapping() to get the AC from the skb.
- Take basic rate configuration for the BSS into account when calculating
multicast rate.
v4:
- Fix calculation that clamps the maximum airtime to fit into 10 bits
- Incorporate Rich Brown's nits for the commit message in Kan's patch
- Add fewer local variables to ieee80211_tx_dequeue()
v3:
- Move the tx_time_est field so it's shared with ack_frame_id, and use units
of 4us for the value stored in it.
- Move the addition of the Ethernet header size into ieee80211_calc_expected_tx_airtime()
v2:
- Integrate Kan's approach to airtime throttling.
- Hopefully fix the cb struct alignment on big-endian architectures.
---
Kan Yan (1):
mac80211: Implement Airtime-based Queue Limit (AQL)
Toke Høiland-Jørgensen (3):
mac80211: Shrink the size of ack_frame_id to make room for tx_time_est
mac80211: Import airtime calculation code from mt76
mac80211: Use Airtime-based Queue Limits (AQL) on packet dequeue
include/net/cfg80211.h | 7 +
include/net/mac80211.h | 45 +++++
net/mac80211/Makefile | 3
net/mac80211/airtime.c | 390 ++++++++++++++++++++++++++++++++++++++++++++
net/mac80211/cfg.c | 2
net/mac80211/debugfs.c | 78 +++++++++
net/mac80211/debugfs_sta.c | 43 ++++-
net/mac80211/ieee80211_i.h | 8 +
net/mac80211/main.c | 9 +
net/mac80211/sta_info.c | 32 ++++
net/mac80211/sta_info.h | 8 +
net/mac80211/status.c | 28 +++
net/mac80211/tx.c | 69 +++++++-
13 files changed, 704 insertions(+), 18 deletions(-)
create mode 100644 net/mac80211/airtime.c
From: Toke Høiland-Jørgensen <[email protected]>
Felix recently added code to calculate airtime of packets to the mt76
driver. Import this into mac80211 so we can use it for airtime queue limit
calculations later.
The airtime.c file is copied verbatim from the mt76 driver, and adjusted to
use mac80211 data structures instead (which is fairly straight forward).
The per-rate TX rate calculation is split out to its own
function (ieee80211_calc_tx_airtime_rate()) so it can be used directly for
the AQL calculations added in a subsequent patch.
The only thing that it was not possible to port directly was the bit that
read the internal driver flags of struct ieee80211_rate to determine
whether a rate is using CCK or OFDM encoding. Instead, just look at the
rate index, since at least mt76 and ath10k both seem to have the same
number of CCK rates (4) in their tables.
Signed-off-by: Toke Høiland-Jørgensen <[email protected]>
---
include/net/mac80211.h | 29 +++
net/mac80211/Makefile | 3
net/mac80211/airtime.c | 390 ++++++++++++++++++++++++++++++++++++++++++++
net/mac80211/ieee80211_i.h | 4
4 files changed, 425 insertions(+), 1 deletion(-)
create mode 100644 net/mac80211/airtime.c
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 4288ace72c2b..8a3e0544a026 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6424,4 +6424,33 @@ void ieee80211_nan_func_match(struct ieee80211_vif *vif,
struct cfg80211_nan_match_params *match,
gfp_t gfp);
+/**
+ * ieee80211_calc_rx_airtime - calculate estimated transmission airtime for RX.
+ *
+ * This function calculates the estimated airtime usage of a frame based on the
+ * rate information in the RX status struct and the frame length.
+ *
+ * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @status: &struct ieee80211_rx_status containing the transmission rate
+ * information.
+ * @len: frame length in bytes
+ */
+u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_rx_status *status,
+ int len);
+
+/**
+ * ieee80211_calc_tx_airtime - calculate estimated transmission airtime for TX.
+ *
+ * This function calculates the estimated airtime usage of a frame based on the
+ * rate information in the TX info struct and the frame length.
+ *
+ * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @info: &struct ieee80211_tx_info of the frame.
+ * @len: frame length in bytes
+ */
+u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw,
+ struct ieee80211_tx_info *info,
+ int len);
+
#endif /* MAC80211_H */
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..a521f3730381
--- /dev/null
+++ b/net/mac80211/airtime.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (C) 2019 Felix Fietkau <[email protected]>
+ */
+
+#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 symbols for a packet with (bps) bits per symbol */
+#define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps))
+
+/* Transmission time (1024 usec) for a packet containing (syms) * symbols */
+#define MCS_SYMBOL_TIME(sgi, syms) \
+ (sgi ? \
+ ((syms) * 18 * 1024 + 4 * 1024) / 5 : /* syms * 3.6 us */ \
+ ((syms) * 1024) << 2 /* syms * 4 us */ \
+ )
+
+/* Transmit duration for the raw data part of an average sized packet */
+#define MCS_DURATION(streams, sgi, bps) \
+ MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps)))
+
+#define BW_20 0
+#define BW_40 1
+#define BW_80 2
+
+/*
+ * 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 6 /* BW(=3) * SGI(=2) */
+
+#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_GROUPS_NB (IEEE80211_HT_GROUPS_NB + \
+ IEEE80211_VHT_GROUPS_NB)
+
+#define IEEE80211_HT_GROUP_0 0
+#define IEEE80211_VHT_GROUP_0 (IEEE80211_HT_GROUP_0 + IEEE80211_HT_GROUPS_NB)
+
+#define MCS_GROUP_RATES 10
+#define CCK_NUM_RATES 4
+
+#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(_streams, _sgi, _ht40 ? 54 : 26) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 108 : 52) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 162 : 78) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 216 : 104) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 324 : 156) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 432 : 208) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 486 : 234) >> _s, \
+ MCS_DURATION(_streams, _sgi, _ht40 ? 540 : 260) >> _s \
+ } \
+}
+
+#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, r3, r2, r1) \
+ (_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(_streams, _sgi, \
+ BW2VBPS(_bw, 117, 54, 26)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 234, 108, 52)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 351, 162, 78)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 468, 216, 104)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 702, 324, 156)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 936, 432, 208)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 1053, 486, 234)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 1170, 540, 260)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 1404, 648, 312)) >> _s, \
+ MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 1560, 720, 346)) >> _s \
+ } \
+}
+
+#define VHT_GROUP_SHIFT(_streams, _sgi, _bw) \
+ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, \
+ BW2VBPS(_bw, 117, 54, 26)))
+
+#define VHT_GROUP(_streams, _sgi, _bw) \
+ __VHT_GROUP(_streams, _sgi, _bw, \
+ VHT_GROUP_SHIFT(_streams, _sgi, _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),
+};
+
+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;
+ u32 duration;
+ int group, idx;
+ 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;
+ 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 = (status->rate_idx < CCK_NUM_RATES);
+
+ 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;
+ default:
+ WARN_ON_ONCE(1);
+ return 0;
+ }
+
+ if (WARN_ON_ONCE(streams > 4))
+ 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 = (rateidx < CCK_NUM_RATES);
+
+ return ieee80211_calc_legacy_rate_duration(rate, short_pream, cck, len);
+}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 05406e9c05b3..225ea4e3cd76 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2249,6 +2249,10 @@ 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
From: Kan Yan <[email protected]>
In order for the Fq_CoDel algorithm integrated in mac80211 layer to operate
effectively to control excessive queueing latency, the CoDel algorithm
requires an accurate measure of how long packets stays in the queue, AKA
sojourn time. The sojourn time measured at the mac80211 layer doesn't
include queueing latency in the lower layer (firmware/hardware) and CoDel
expects lower layer to have a short queue. However, most 802.11ac chipsets
offload tasks such TX aggregation to firmware or hardware, thus have a deep
lower layer queue.
Without a mechanism to control the lower layer queue size, packets only
stay in mac80211 layer transiently before being sent to firmware queue.
As a result, the sojourn time measured by CoDel in the mac80211 layer is
almost always lower than the CoDel latency target, hence CoDel does little
to control the latency, even when the lower layer queue causes excessive
latency.
The Byte Queue Limits (BQL) mechanism is commonly used to address the
similar issue with wired network interface. However, this method cannot be
applied directly to the wireless network interface. "Bytes" is not a
suitable measure of queue depth in the wireless network, as the data rate
can vary dramatically from station to station in the same network, from a
few Mbps to over Gbps.
This patch implements an Airtime-based Queue Limit (AQL) to make CoDel work
effectively with wireless drivers that utilized firmware/hardware
offloading. AQL allows each txq to release just enough packets to the lower
layer to form 1-2 large aggregations to keep hardware fully utilized and
retains the rest of the frames in mac80211 layer to be controlled by the
CoDel algorithm.
Signed-off-by: Kan Yan <[email protected]>
[ Toke: Keep API to set pending airtime internal, fix nits in commit msg ]
Signed-off-by: Toke Høiland-Jørgensen <[email protected]>
---
include/net/cfg80211.h | 7 ++++
include/net/mac80211.h | 12 +++++++
net/mac80211/debugfs.c | 78 ++++++++++++++++++++++++++++++++++++++++++++
net/mac80211/debugfs_sta.c | 43 +++++++++++++++++++-----
net/mac80211/ieee80211_i.h | 4 ++
net/mac80211/main.c | 9 +++++
net/mac80211/sta_info.c | 32 ++++++++++++++++++
net/mac80211/sta_info.h | 8 +++++
net/mac80211/tx.c | 46 ++++++++++++++++++++++++--
9 files changed, 225 insertions(+), 14 deletions(-)
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ff45c3e1abff..8d50c0a60dbd 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2602,6 +2602,13 @@ enum wiphy_params_flags {
#define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256
+/* The per TXQ device queue limit in airtime */
+#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L 4000
+#define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H 8000
+
+/* The per interface airtime threshold to switch to lower queue limit */
+#define IEEE80211_AQL_THRESHOLD 24000
+
/**
* struct cfg80211_pmksa - PMK Security Association
*
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8a3e0544a026..2bc0f2538a36 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -5565,6 +5565,18 @@ void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid);
void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid,
u32 tx_airtime, u32 rx_airtime);
+/**
+ * ieee80211_txq_airtime_check - check if a txq can send frame to device
+ *
+ * @hw: pointer obtained from ieee80211_alloc_hw()
+ * @txq: pointer obtained from station or virtual interface
+ *
+ * Return true if the AQL's airtime limit has not been reached and the txq can
+ * continue to send more packets to the device. Otherwise return false.
+ */
+bool
+ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
+
/**
* ieee80211_iter_keys - iterate keys programmed into the device
* @hw: pointer obtained from ieee80211_alloc_hw()
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 568b3b276931..d77ea0e51c1d 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -148,6 +148,80 @@ 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;
+ 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;
+
+ 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) {
+ 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,
@@ -441,6 +515,10 @@ 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..9f9b8f5ed86a 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;
+ q_depth[ac] = sta->airtime[ac].aql_tx_pending;
spin_unlock_bh(&local->active_txq_lock[ac]);
}
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 225ea4e3cd76..6fa690757388 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;
+ u32 aql_total_pending_airtime;
const struct ieee80211_ops *ops;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index aba094b4ccfc..0792c9b9c850 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -667,8 +667,15 @@ 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;
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 bd11fef2139f..64bacf4f068c 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -396,6 +396,9 @@ 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;
+ 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 +1896,35 @@ 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)
+{
+ spin_lock_bh(&local->active_txq_lock[ac]);
+ if (tx_completed) {
+ if (sta) {
+ if (WARN_ONCE(sta->airtime[ac].aql_tx_pending < tx_airtime,
+ "TXQ pending airtime underflow: %u, %u",
+ sta->airtime[ac].aql_tx_pending, tx_airtime))
+ sta->airtime[ac].aql_tx_pending = 0;
+ else
+ sta->airtime[ac].aql_tx_pending -= tx_airtime;
+ }
+
+ if (WARN_ONCE(local->aql_total_pending_airtime < tx_airtime,
+ "Device pending airtime underflow: %u, %u",
+ local->aql_total_pending_airtime, tx_airtime))
+ local->aql_total_pending_airtime = 0;
+ else
+ local->aql_total_pending_airtime -= tx_airtime;
+ } else {
+ if (sta)
+ sta->airtime[ac].aql_tx_pending += tx_airtime;
+ local->aql_total_pending_airtime += tx_airtime;
+ }
+ spin_unlock_bh(&local->active_txq_lock[ac]);
+}
+
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..4e4d76e81b0f 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;
+ u32 aql_tx_pending; /* Estimated airtime for frames pending in queue */
+ 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;
/**
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index a16c2f863702..12653d873b8c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3665,7 +3665,8 @@ 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]);
@@ -3676,13 +3677,26 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
if (!txqi)
goto out;
+ if (txqi == head && !found_eligible_txq)
+ goto out;
+
+ 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;
@@ -3736,6 +3750,32 @@ 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 (sta->airtime[txq->ac].aql_tx_pending <
+ sta->airtime[txq->ac].aql_limit_low)
+ return true;
+
+ if (local->aql_total_pending_airtime < local->aql_threshold &&
+ 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)
{
From: Toke Høiland-Jørgensen <[email protected]>
The previous commit added the ability to throttle stations when they queue
too much airtime in the hardware. This commit enables the functionality by
calculating the expected airtime usage of each packet that is dequeued from
the TXQs in mac80211, and accounting that as pending airtime.
The estimated airtime for each skb is stored in the tx_info, so we can
subtract the same amount from the running total when the skb is freed or
recycled. The throttling mechanism relies on this accounting to be
accurate (i.e., that we are not freeing skbs without subtracting any
airtime they were accounted for), so we put the subtraction into
ieee80211_report_used_skb(). As an optimisation, we also subtract the
airtime on regular TX completion, zeroing out the value stored in the
packet afterwards, to avoid having to do an expensive lookup of the station
from the packet data on every packet.
This patch does *not* include any mechanism to wake a throttled TXQ again,
on the assumption that this will happen anyway as a side effect of whatever
freed the skb (most commonly a TX completion).
Signed-off-by: Toke Høiland-Jørgensen <[email protected]>
---
net/mac80211/status.c | 28 ++++++++++++++++++++++++++++
net/mac80211/tx.c | 21 +++++++++++++++++++++
2 files changed, 49 insertions(+)
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index ab8ba5835ca0..f125984d5beb 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -676,6 +676,23 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local,
if (dropped)
acked = false;
+ if (info->tx_time_est) {
+ struct ieee80211_sub_if_data *sdata;
+ struct sta_info *sta = NULL;
+
+ rcu_read_lock();
+
+ sdata = ieee80211_sdata_from_skb(local, skb);
+ if (sdata)
+ sta = sta_info_get_bss(sdata, skb_mac_header(skb));
+
+ ieee80211_sta_update_pending_airtime(local, sta,
+ skb_get_queue_mapping(skb),
+ info->tx_time_est << 2,
+ true);
+ rcu_read_unlock();
+ }
+
if (info->flags & IEEE80211_TX_INTFL_MLME_CONN_TX) {
struct ieee80211_sub_if_data *sdata;
@@ -930,6 +947,17 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
tid = qc[0] & 0xf;
}
+ if (info->tx_time_est) {
+ /* 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),
+ info->tx_time_est << 2,
+ true);
+ info->tx_time_est = 0;
+ }
+
if (!acked && ieee80211_is_back_req(fc)) {
u16 control;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 12653d873b8c..1405304d8994 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3542,6 +3542,9 @@ 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);
@@ -3652,6 +3655,24 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
}
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) {
+ /* We only have 10 bits in tx_time_est, so store airtime
+ * in increments of 4us and clamp the maximum to 2**12-1
+ */
+ airtime = min_t(u32, airtime, 4095) & ~3U;
+ info->tx_time_est = airtime >> 2;
+ ieee80211_sta_update_pending_airtime(local, tx.sta,
+ txq->ac, airtime,
+ false);
+ }
+ }
+
return skb;
out: