net_sched: restore "linklayer atm" handling

commit 56b765b79 ("htb: improved accuracy at high rates")
broke the "linklayer atm" handling.

 tc class add ... htb rate X ceil Y linklayer atm

The linklayer setting is implemented by modifying the rate table
which is send to the kernel.  No direct parameter were
transferred to the kernel indicating the linklayer setting.

The commit 56b765b79 ("htb: improved accuracy at high rates")
removed the use of the rate table system.

To keep compatible with older iproute2 utils, this patch detects
the linklayer by parsing the rate table.  It also supports future
versions of iproute2 to send this linklayer parameter to the
kernel directly. This is done by using the __reserved field in
struct tc_ratespec, to convey the choosen linklayer option, but
only using the lower 4 bits of this field.

Linklayer detection is limited to speeds below 100Mbit/s, because
at high rates the rtab is gets too inaccurate, so bad that
several fields contain the same values, this resembling the ATM
detect.  Fields even start to contain "0" time to send, e.g. at
1000Mbit/s sending a 96 bytes packet cost "0", thus the rtab have
been more broken than we first realized.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 17 insertions, 2 deletions

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6eab63363e59..e5ae0c50fa9c 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -683,13 +683,19 @@ struct psched_ratecfg {
 	u64	rate_bytes_ps; /* bytes per second */
 	u32	mult;
 	u16	overhead;
+	u8	linklayer;
 	u8	shift;
 };
 
 static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
 				unsigned int len)
 {
-	return ((u64)(len + r->overhead) * r->mult) >> r->shift;
+	len += r->overhead;
+
+	if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
+		return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
+
+	return ((u64)len * r->mult) >> r->shift;
 }
 
 extern void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf);
@@ -700,6 +706,7 @@ static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
 	memset(res, 0, sizeof(*res));
 	res->rate = r->rate_bytes_ps;
 	res->overhead = r->overhead;
+	res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
 }
 
 #endif
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index dbd71b0c7d8c..09d62b9228ff 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -73,9 +73,17 @@ struct tc_estimator {
 #define TC_H_ROOT	(0xFFFFFFFFU)
 #define TC_H_INGRESS    (0xFFFFFFF1U)
 
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+	TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+	TC_LINKLAYER_ETHERNET,
+	TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
 struct tc_ratespec {
 	unsigned char	cell_log;
-	unsigned char	__reserved;
+	__u8		linklayer; /* lower 4 bits */
 	unsigned short	overhead;
 	short		cell_align;
 	unsigned short	mpu;