mac80211: minstrel_ht: automatically calculate rate duration shift

A per-group shift was added to reduce the size of the per-rate transmit
duration field to u16 without sacrificing a lot of precision
This patch changes the macros to automatically calculate the best value for
this shift based on the lowest rate within the group.
This simplifies adding more groups and slightly improves accuracy for some of
the existing groups.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

1 files changed, 80 insertions, 54 deletions

diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 00a3a8ce27fe..8b168724c5e7 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -51,8 +51,13 @@
 	MINSTREL_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)				\
+#define __MCS_GROUP(_streams, _sgi, _ht40, _s)				\
 	[GROUP_IDX(_streams, _sgi, _ht40)] = {				\
 	.streams = _streams,						\
 	.shift = _s,							\
@@ -72,6 +77,13 @@
 	}								\
 }
 
+#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)				\
 	(MINSTREL_VHT_GROUP_0 +						\
 	 MINSTREL_MAX_STREAMS * 2 * (_bw) +				\
@@ -81,7 +93,7 @@
 #define BW2VBPS(_bw, r3, r2, r1)					\
 	(_bw == BW_80 ? r3 : _bw == BW_40 ? r2 : r1)
 
-#define VHT_GROUP(_streams, _sgi, _bw, _s)				\
+#define __VHT_GROUP(_streams, _sgi, _bw, _s)				\
 	[VHT_GROUP_IDX(_streams, _sgi, _bw)] = {			\
 	.streams = _streams,						\
 	.shift = _s,							\
@@ -114,6 +126,14 @@
 	}								\
 }
 
+#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))
+
 #define CCK_DURATION(_bitrate, _short, _len)		\
 	(1000 * (10 /* SIFS */ +			\
 	 (_short ? 72 + 24 : 144 + 48) +		\
@@ -129,7 +149,7 @@
 	CCK_ACK_DURATION(55, _short) >> _s,		\
 	CCK_ACK_DURATION(110, _short) >> _s
 
-#define CCK_GROUP(_s)					\
+#define __CCK_GROUP(_s)					\
 	[MINSTREL_CCK_GROUP] = {			\
 		.streams = 1,				\
 		.flags = 0,				\
@@ -140,6 +160,12 @@
 		}					\
 	}
 
+#define CCK_GROUP_SHIFT					\
+	GROUP_SHIFT(CCK_ACK_DURATION(10, false))
+
+#define CCK_GROUP __CCK_GROUP(CCK_GROUP_SHIFT)
+
+
 static bool minstrel_vht_only = true;
 module_param(minstrel_vht_only, bool, 0644);
 MODULE_PARM_DESC(minstrel_vht_only,
@@ -154,57 +180,57 @@ MODULE_PARM_DESC(minstrel_vht_only,
  * BW -> SGI -> #streams
  */
 const struct mcs_group minstrel_mcs_groups[] = {
-	MCS_GROUP(1, 0, BW_20, 5),
-	MCS_GROUP(2, 0, BW_20, 4),
-	MCS_GROUP(3, 0, BW_20, 4),
-	MCS_GROUP(4, 0, BW_20, 4),
-
-	MCS_GROUP(1, 1, BW_20, 5),
-	MCS_GROUP(2, 1, BW_20, 4),
-	MCS_GROUP(3, 1, BW_20, 4),
-	MCS_GROUP(4, 1, BW_20, 4),
-
-	MCS_GROUP(1, 0, BW_40, 4),
-	MCS_GROUP(2, 0, BW_40, 4),
-	MCS_GROUP(3, 0, BW_40, 4),
-	MCS_GROUP(4, 0, BW_40, 4),
-
-	MCS_GROUP(1, 1, BW_40, 4),
-	MCS_GROUP(2, 1, BW_40, 4),
-	MCS_GROUP(3, 1, BW_40, 4),
-	MCS_GROUP(4, 1, BW_40, 4),
-
-	CCK_GROUP(8),
-
-	VHT_GROUP(1, 0, BW_20, 5),
-	VHT_GROUP(2, 0, BW_20, 4),
-	VHT_GROUP(3, 0, BW_20, 4),
-	VHT_GROUP(4, 0, BW_20, 4),
-
-	VHT_GROUP(1, 1, BW_20, 5),
-	VHT_GROUP(2, 1, BW_20, 4),
-	VHT_GROUP(3, 1, BW_20, 4),
-	VHT_GROUP(4, 1, BW_20, 4),
-
-	VHT_GROUP(1, 0, BW_40, 4),
-	VHT_GROUP(2, 0, BW_40, 4),
-	VHT_GROUP(3, 0, BW_40, 4),
-	VHT_GROUP(4, 0, BW_40, 3),
-
-	VHT_GROUP(1, 1, BW_40, 4),
-	VHT_GROUP(2, 1, BW_40, 4),
-	VHT_GROUP(3, 1, BW_40, 4),
-	VHT_GROUP(4, 1, BW_40, 3),
-
-	VHT_GROUP(1, 0, BW_80, 4),
-	VHT_GROUP(2, 0, BW_80, 4),
-	VHT_GROUP(3, 0, BW_80, 4),
-	VHT_GROUP(4, 0, BW_80, 2),
-
-	VHT_GROUP(1, 1, BW_80, 4),
-	VHT_GROUP(2, 1, BW_80, 4),
-	VHT_GROUP(3, 1, BW_80, 4),
-	VHT_GROUP(4, 1, BW_80, 2),
+	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),
+
+	CCK_GROUP,
+
+	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 u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly;