Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 92 insertions, 47 deletions

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 9d75b7761313..d2922c0ef57a 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -71,6 +71,12 @@ enum htb_cmode {
 	HTB_CAN_SEND		/* class can send */
 };
 
+struct htb_rate_cfg {
+	u64 rate_bps;
+	u32 mult;
+	u32 shift;
+};
+
 /* interior & leaf nodes; props specific to leaves are marked L: */
 struct htb_class {
 	struct Qdisc_class_common common;
@@ -118,11 +124,11 @@ struct htb_class {
 	int filter_cnt;
 
 	/* token bucket parameters */
-	struct qdisc_rate_table *rate;	/* rate table of the class itself */
-	struct qdisc_rate_table *ceil;	/* ceiling rate (limits borrows too) */
-	long buffer, cbuffer;	/* token bucket depth/rate */
+	struct htb_rate_cfg rate;
+	struct htb_rate_cfg ceil;
+	s64 buffer, cbuffer;	/* token bucket depth/rate */
 	psched_tdiff_t mbuffer;	/* max wait time */
-	long tokens, ctokens;	/* current number of tokens */
+	s64 tokens, ctokens;	/* current number of tokens */
 	psched_time_t t_c;	/* checkpoint time */
 };
 
@@ -162,6 +168,45 @@ struct htb_sched {
 	struct work_struct work;
 };
 
+static u64 l2t_ns(struct htb_rate_cfg *r, unsigned int len)
+{
+	return ((u64)len * r->mult) >> r->shift;
+}
+
+static void htb_precompute_ratedata(struct htb_rate_cfg *r)
+{
+	u64 factor;
+	u64 mult;
+	int shift;
+
+	r->shift = 0;
+	r->mult = 1;
+	/*
+	 * Calibrate mult, shift so that token counting is accurate
+	 * for smallest packet size (64 bytes).  Token (time in ns) is
+	 * computed as (bytes * 8) * NSEC_PER_SEC / rate_bps.  It will
+	 * work as long as the smallest packet transfer time can be
+	 * accurately represented in nanosec.
+	 */
+	if (r->rate_bps > 0) {
+		/*
+		 * Higher shift gives better accuracy.  Find the largest
+		 * shift such that mult fits in 32 bits.
+		 */
+		for (shift = 0; shift < 16; shift++) {
+			r->shift = shift;
+			factor = 8LLU * NSEC_PER_SEC * (1 << r->shift);
+			mult = div64_u64(factor, r->rate_bps);
+			if (mult > UINT_MAX)
+				break;
+		}
+
+		r->shift = shift - 1;
+		factor = 8LLU * NSEC_PER_SEC * (1 << r->shift);
+		r->mult = div64_u64(factor, r->rate_bps);
+	}
+}
+
 /* find class in global hash table using given handle */
 static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch)
 {
@@ -273,7 +318,7 @@ static void htb_add_to_id_tree(struct rb_root *root,
  * already in the queue.
  */
 static void htb_add_to_wait_tree(struct htb_sched *q,
-				 struct htb_class *cl, long delay)
+				 struct htb_class *cl, s64 delay)
 {
 	struct rb_node **p = &q->wait_pq[cl->level].rb_node, *parent = NULL;
 
@@ -441,14 +486,14 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl)
 		htb_remove_class_from_row(q, cl, mask);
 }
 
-static inline long htb_lowater(const struct htb_class *cl)
+static inline s64 htb_lowater(const struct htb_class *cl)
 {
 	if (htb_hysteresis)
 		return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0;
 	else
 		return 0;
 }
-static inline long htb_hiwater(const struct htb_class *cl)
+static inline s64 htb_hiwater(const struct htb_class *cl)
 {
 	if (htb_hysteresis)
 		return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0;
@@ -469,9 +514,9 @@ static inline long htb_hiwater(const struct htb_class *cl)
  * mode transitions per time unit. The speed gain is about 1/6.
  */
 static inline enum htb_cmode
-htb_class_mode(struct htb_class *cl, long *diff)
+htb_class_mode(struct htb_class *cl, s64 *diff)
 {
-	long toks;
+	s64 toks;
 
 	if ((toks = (cl->ctokens + *diff)) < htb_lowater(cl)) {
 		*diff = -toks;
@@ -495,7 +540,7 @@ htb_class_mode(struct htb_class *cl, long *diff)
  * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree).
  */
 static void
-htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff)
+htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
 {
 	enum htb_cmode new_mode = htb_class_mode(cl, diff);
 
@@ -581,26 +626,26 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	return NET_XMIT_SUCCESS;
 }
 
-static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, long diff)
+static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, s64 diff)
 {
-	long toks = diff + cl->tokens;
+	s64 toks = diff + cl->tokens;
 
 	if (toks > cl->buffer)
 		toks = cl->buffer;
-	toks -= (long) qdisc_l2t(cl->rate, bytes);
+	toks -= (s64) l2t_ns(&cl->rate, bytes);
 	if (toks <= -cl->mbuffer)
 		toks = 1 - cl->mbuffer;
 
 	cl->tokens = toks;
 }
 
-static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, long diff)
+static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff)
 {
-	long toks = diff + cl->ctokens;
+	s64 toks = diff + cl->ctokens;
 
 	if (toks > cl->cbuffer)
 		toks = cl->cbuffer;
-	toks -= (long) qdisc_l2t(cl->ceil, bytes);
+	toks -= (s64) l2t_ns(&cl->ceil, bytes);
 	if (toks <= -cl->mbuffer)
 		toks = 1 - cl->mbuffer;
 
@@ -623,10 +668,10 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
 {
 	int bytes = qdisc_pkt_len(skb);
 	enum htb_cmode old_mode;
-	long diff;
+	s64 diff;
 
 	while (cl) {
-		diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
+		diff = min_t(s64, q->now - cl->t_c, cl->mbuffer);
 		if (cl->level >= level) {
 			if (cl->level == level)
 				cl->xstats.lends++;
@@ -673,7 +718,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level,
 	unsigned long stop_at = start + 2;
 	while (time_before(jiffies, stop_at)) {
 		struct htb_class *cl;
-		long diff;
+		s64 diff;
 		struct rb_node *p = rb_first(&q->wait_pq[level]);
 
 		if (!p)
@@ -684,7 +729,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level,
 			return cl->pq_key;
 
 		htb_safe_rb_erase(p, q->wait_pq + level);
-		diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
+		diff = min_t(s64, q->now - cl->t_c, cl->mbuffer);
 		htb_change_class_mode(q, cl, &diff);
 		if (cl->cmode != HTB_CAN_SEND)
 			htb_add_to_wait_tree(q, cl, diff);
@@ -871,10 +916,10 @@ ok:
 
 	if (!sch->q.qlen)
 		goto fin;
-	q->now = psched_get_time();
+	q->now = ktime_to_ns(ktime_get());
 	start_at = jiffies;
 
-	next_event = q->now + 5 * PSCHED_TICKS_PER_SEC;
+	next_event = q->now + 5 * NSEC_PER_SEC;
 
 	for (level = 0; level < TC_HTB_MAXDEPTH; level++) {
 		/* common case optimization - skip event handler quickly */
@@ -884,7 +929,7 @@ ok:
 		if (q->now >= q->near_ev_cache[level]) {
 			event = htb_do_events(q, level, start_at);
 			if (!event)
-				event = q->now + PSCHED_TICKS_PER_SEC;
+				event = q->now + NSEC_PER_SEC;
 			q->near_ev_cache[level] = event;
 		} else
 			event = q->near_ev_cache[level];
@@ -903,10 +948,17 @@ ok:
 		}
 	}
 	sch->qstats.overlimits++;
-	if (likely(next_event > q->now))
-		qdisc_watchdog_schedule(&q->watchdog, next_event);
-	else
+	if (likely(next_event > q->now)) {
+		if (!test_bit(__QDISC_STATE_DEACTIVATED,
+			      &qdisc_root_sleeping(q->watchdog.qdisc)->state)) {
+			ktime_t time = ns_to_ktime(next_event);
+			qdisc_throttled(q->watchdog.qdisc);
+			hrtimer_start(&q->watchdog.timer, time,
+				      HRTIMER_MODE_ABS);
+		}
+	} else {
 		schedule_work(&q->work);
+	}
 fin:
 	return skb;
 }
@@ -1082,9 +1134,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
 
 	memset(&opt, 0, sizeof(opt));
 
-	opt.rate = cl->rate->rate;
+	opt.rate.rate = cl->rate.rate_bps >> 3;
 	opt.buffer = cl->buffer;
-	opt.ceil = cl->ceil->rate;
+	opt.ceil.rate = cl->ceil.rate_bps >> 3;
 	opt.cbuffer = cl->cbuffer;
 	opt.quantum = cl->quantum;
 	opt.prio = cl->prio;
@@ -1203,9 +1255,6 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
 		qdisc_destroy(cl->un.leaf.q);
 	}
 	gen_kill_estimator(&cl->bstats, &cl->rate_est);
-	qdisc_put_rtab(cl->rate);
-	qdisc_put_rtab(cl->ceil);
-
 	tcf_destroy_chain(&cl->filter_list);
 	kfree(cl);
 }
@@ -1307,7 +1356,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	struct htb_sched *q = qdisc_priv(sch);
 	struct htb_class *cl = (struct htb_class *)*arg, *parent;
 	struct nlattr *opt = tca[TCA_OPTIONS];
-	struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
 	struct nlattr *tb[__TCA_HTB_MAX];
 	struct tc_htb_opt *hopt;
 
@@ -1326,10 +1374,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	parent = parentid == TC_H_ROOT ? NULL : htb_find(parentid, sch);
 
 	hopt = nla_data(tb[TCA_HTB_PARMS]);
-
-	rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
-	ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
-	if (!rtab || !ctab)
+	if (!hopt->rate.rate || !hopt->ceil.rate)
 		goto failure;
 
 	if (!cl) {		/* new class */
@@ -1439,7 +1484,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	 * is really leaf before changing cl->un.leaf !
 	 */
 	if (!cl->level) {
-		cl->quantum = rtab->rate.rate / q->rate2quantum;
+		cl->quantum = hopt->rate.rate / q->rate2quantum;
 		if (!hopt->quantum && cl->quantum < 1000) {
 			pr_warning(
 			       "HTB: quantum of class %X is small. Consider r2q change.\n",
@@ -1460,12 +1505,16 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 
 	cl->buffer = hopt->buffer;
 	cl->cbuffer = hopt->cbuffer;
-	if (cl->rate)
-		qdisc_put_rtab(cl->rate);
-	cl->rate = rtab;
-	if (cl->ceil)
-		qdisc_put_rtab(cl->ceil);
-	cl->ceil = ctab;
+
+	cl->rate.rate_bps = (u64)hopt->rate.rate << 3;
+	cl->ceil.rate_bps = (u64)hopt->ceil.rate << 3;
+
+	htb_precompute_ratedata(&cl->rate);
+	htb_precompute_ratedata(&cl->ceil);
+
+	cl->buffer = hopt->buffer << PSCHED_SHIFT;
+	cl->cbuffer = hopt->buffer << PSCHED_SHIFT;
+
 	sch_tree_unlock(sch);
 
 	qdisc_class_hash_grow(sch, &q->clhash);
@@ -1474,10 +1523,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	return 0;
 
 failure:
-	if (rtab)
-		qdisc_put_rtab(rtab);
-	if (ctab)
-		qdisc_put_rtab(ctab);
 	return err;
 }