: ktime clocksource + hrtimer

index f6afee7..1c12afd 100644
@@ -2,6 +2,7 @@ #ifndef __NET_PKT_SCHED_H
 #define __NET_PKT_SCHED_H
 
 #include <linux/jiffies.h>
+#include <linux/ktime.h>
 #include <net/sch_generic.h>
 
 struct qdisc_walker

@@ -37,176 +38,32 @@ static inline void *qdisc_priv(struct Qd
    The things are not so bad, because we may use artifical
    clock evaluated by integration of network data flow
    in the most critical places.
-
-   Note: we do not use fastgettimeofday.
-   The reason is that, when it is not the same thing as
-   gettimeofday, it returns invalid timestamp, which is
-   not updated, when net_bh is active.
  */
 
-/* General note about internal clock.
-
-   Any clock source returns time intervals, measured in units
-   close to 1usec. With source CONFIG_NET_SCH_CLK_GETTIMEOFDAY it is precisely
-   microseconds, otherwise something close but different chosen to minimize
-   arithmetic cost. Ratio usec/internal untis in form nominator/denominator
-   may be read from /proc/net/psched.
- */
-
-
-#ifdef CONFIG_NET_SCH_CLK_GETTIMEOFDAY
-
-typedef struct timeval	psched_time_t;
-typedef long		psched_tdiff_t;
-
-#define PSCHED_GET_TIME(stamp) do_gettimeofday(&(stamp))
-#define PSCHED_US2JIFFIE(usecs) usecs_to_jiffies(usecs)
-#define PSCHED_JIFFIE2US(delay) jiffies_to_usecs(delay)
-
-#else /* !CONFIG_NET_SCH_CLK_GETTIMEOFDAY */
-
 typedef u64	psched_time_t;
 typedef long	psched_tdiff_t;
 
-#ifdef CONFIG_NET_SCH_CLK_JIFFIES
-
-#if HZ < 96
-#define PSCHED_JSCALE 14
-#elif HZ >= 96 && HZ < 192
-#define PSCHED_JSCALE 13
-#elif HZ >= 192 && HZ < 384
-#define PSCHED_JSCALE 12
-#elif HZ >= 384 && HZ < 768
-#define PSCHED_JSCALE 11
-#elif HZ >= 768
-#define PSCHED_JSCALE 10
-#endif
-
-#define PSCHED_GET_TIME(stamp) ((stamp) = (get_jiffies_64()<<PSCHED_JSCALE))
-#define PSCHED_US2JIFFIE(delay) (((delay)+(1<<PSCHED_JSCALE)-1)>>PSCHED_JSCALE)
-#define PSCHED_JIFFIE2US(delay) ((delay)<<PSCHED_JSCALE)
-
-#endif /* CONFIG_NET_SCH_CLK_JIFFIES */
-#ifdef CONFIG_NET_SCH_CLK_CPU
-#include <asm/timex.h>
-
-extern psched_tdiff_t psched_clock_per_hz;
-extern int psched_clock_scale;
-extern psched_time_t psched_time_base;
-extern cycles_t psched_time_mark;
-
-#define PSCHED_GET_TIME(stamp)						\
-do {									\
-	cycles_t cur = get_cycles();					\
-	if (sizeof(cycles_t) == sizeof(u32)) {				\
-		if (cur <= psched_time_mark)				\
-			psched_time_base += 0x100000000ULL;		\
-		psched_time_mark = cur;					\
-		(stamp) = (psched_time_base + cur)>>psched_clock_scale;	\
-	} else {							\
-		(stamp) = cur>>psched_clock_scale;			\
-	}								\
-} while (0)
-#define PSCHED_US2JIFFIE(delay) (((delay)+psched_clock_per_hz-1)/psched_clock_per_hz)
-#define PSCHED_JIFFIE2US(delay) ((delay)*psched_clock_per_hz)
-
-#endif /* CONFIG_NET_SCH_CLK_CPU */
-
-#endif /* !CONFIG_NET_SCH_CLK_GETTIMEOFDAY */
-
-#ifdef CONFIG_NET_SCH_CLK_GETTIMEOFDAY
-#define PSCHED_TDIFF(tv1, tv2) \
-({ \
-	   int __delta_sec = (tv1).tv_sec - (tv2).tv_sec; \
-	   int __delta = (tv1).tv_usec - (tv2).tv_usec; \
-	   if (__delta_sec) { \
-	           switch (__delta_sec) { \
-		   default: \
-			   __delta = 0; \
-		   case 2: \
-			   __delta += USEC_PER_SEC; \
-		   case 1: \
-			   __delta += USEC_PER_SEC; \
-	           } \
-	   } \
-	   __delta; \
-})
-
-static inline int
-psched_tod_diff(int delta_sec, int bound)
-{
-	int delta;
-
-	if (bound <= USEC_PER_SEC || delta_sec > (0x7FFFFFFF/USEC_PER_SEC)-1)
-		return bound;
-	delta = delta_sec * USEC_PER_SEC;
-	if (delta > bound || delta < 0)
-		delta = bound;
-	return delta;
-}
-
-#define PSCHED_TDIFF_SAFE(tv1, tv2, bound) \
-({ \
-	   int __delta_sec = (tv1).tv_sec - (tv2).tv_sec; \
-	   int __delta = (tv1).tv_usec - (tv2).tv_usec; \
-	   switch (__delta_sec) { \
-	   default: \
-		   __delta = psched_tod_diff(__delta_sec, bound);  break; \
-	   case 2: \
-		   __delta += USEC_PER_SEC; \
-	   case 1: \
-		   __delta += USEC_PER_SEC; \
-	   case 0: \
- 		   if (__delta > bound || __delta < 0) \
- 			__delta = bound; \
-	   } \
-	   __delta; \
-})
-
-#define PSCHED_TLESS(tv1, tv2) (((tv1).tv_usec < (tv2).tv_usec && \
-				(tv1).tv_sec <= (tv2).tv_sec) || \
-				 (tv1).tv_sec < (tv2).tv_sec)
-
-#define PSCHED_TADD2(tv, delta, tv_res) \
-({ \
-	   int __delta = (tv).tv_usec + (delta); \
-	   (tv_res).tv_sec = (tv).tv_sec; \
-	   while (__delta >= USEC_PER_SEC) { (tv_res).tv_sec++; __delta -= USEC_PER_SEC; } \
-	   (tv_res).tv_usec = __delta; \
-})
-
-#define PSCHED_TADD(tv, delta) \
-({ \
-	   (tv).tv_usec += (delta); \
-	   while ((tv).tv_usec >= USEC_PER_SEC) { (tv).tv_sec++; \
-		 (tv).tv_usec -= USEC_PER_SEC; } \
-})
-
-/* Set/check that time is in the "past perfect";
-   it depends on concrete representation of system time
- */
-
-#define PSCHED_SET_PASTPERFECT(t)	((t).tv_sec = 0)
-#define PSCHED_IS_PASTPERFECT(t)	((t).tv_sec == 0)
+/* Avoid doing 64 bit divide by 1000 */
+#define PSCHED_US2NS(x)			((s64)(x) << 10)
+#define PSCHED_NS2US(x)			((x) >> 10)
 
-#define	PSCHED_AUDIT_TDIFF(t) ({ if ((t) > 2000000) (t) = 2000000; })
+#define PSCHED_TICKS_PER_SEC		PSCHED_NS2US(NSEC_PER_SEC)
+#define PSCHED_GET_TIME(stamp) \
+	((stamp) = PSCHED_NS2US(ktime_to_ns(ktime_get())))
 
-#else /* !CONFIG_NET_SCH_CLK_GETTIMEOFDAY */
+#define PSCHED_US2JIFFIE(usecs)		usecs_to_jiffies(PSCHED_US2NS((usecs)) / NSEC_PER_USEC)
+#define PSCHED_JIFFIE2US(delay)		PSCHED_NS2US(jiffies_to_usecs((delay)) * NSEC_PER_USEC)
 
-#define PSCHED_TDIFF(tv1, tv2) (long)((tv1) - (tv2))
+#define PSCHED_TDIFF(tv1, tv2)		(long)((tv1) - (tv2))
 #define PSCHED_TDIFF_SAFE(tv1, tv2, bound) \
-	min_t(long long, (tv1) - (tv2), bound)
-
-
-#define PSCHED_TLESS(tv1, tv2) ((tv1) < (tv2))
+					min_t(long long, (tv1) - (tv2), bound)
+#define PSCHED_TLESS(tv1, tv2)		((tv1) < (tv2))
 #define PSCHED_TADD2(tv, delta, tv_res) ((tv_res) = (tv) + (delta))
-#define PSCHED_TADD(tv, delta) ((tv) += (delta))
+#define PSCHED_TADD(tv, delta)		((tv) += (delta))
 #define PSCHED_SET_PASTPERFECT(t)	((t) = 0)
 #define PSCHED_IS_PASTPERFECT(t)	((t) == 0)
 #define	PSCHED_AUDIT_TDIFF(t)
 
-#endif /* !CONFIG_NET_SCH_CLK_GETTIMEOFDAY */
-
 extern struct Qdisc_ops pfifo_qdisc_ops;
 extern struct Qdisc_ops bfifo_qdisc_ops;
 

index ec4cb9f..8eda12c 100644
@@ -59,6 +59,7 @@ ktime_t ktime_get(void)
 
 	return timespec_to_ktime(now);
 }
+EXPORT_SYMBOL_GPL(ktime_get);
 
 /**
  * ktime_get_real - get the real (wall-) time in ktime_t format

97 lines not on this page · raw message

index 396deb7..09cf6e4 100644
@@ -195,20 +195,6 @@ struct hfsc_sched
 	struct timer_list wd_timer;		/* watchdog timer */
 };
 
-/*
- * macros
- */
-#ifdef CONFIG_NET_SCH_CLK_GETTIMEOFDAY
-#include <linux/time.h>
-#undef PSCHED_GET_TIME
-#define PSCHED_GET_TIME(stamp)						\
-do {									\
-	struct timeval tv;						\
-	do_gettimeofday(&tv);						\
-	(stamp) = 1ULL * USEC_PER_SEC * tv.tv_sec + tv.tv_usec;		\
-} while (0)
-#endif
-
 #define	HT_INFINITY	0xffffffffffffffffULL	/* infinite time value */
 
 

@@ -394,28 +380,17 @@ cftree_update(struct hfsc_class *cl)
  *	ism: (psched_us/byte) << ISM_SHIFT
  *	dx: psched_us
  *
- * Clock source resolution (CONFIG_NET_SCH_CLK_*)
- *  JIFFIES: for 48<=HZ<=1534 resolution is between 0.63us and 1.27us.
- *  CPU: resolution is between 0.5us and 1us.
- *  GETTIMEOFDAY: resolution is exactly 1us.
+ * The clock source resolution with ktime is 1.024us.
  *
  * sm and ism are scaled in order to keep effective digits.
  * SM_SHIFT and ISM_SHIFT are selected to keep at least 4 effective
  * digits in decimal using the following table.
  *
- * Note: We can afford the additional accuracy (altq hfsc keeps at most
- * 3 effective digits) thanks to the fact that linux clock is bounded
- * much more tightly.
- *
  *  bits/sec      100Kbps     1Mbps     10Mbps     100Mbps    1Gbps
  *  ------------+-------------------------------------------------------
- *  bytes/0.5us   6.25e-3    62.5e-3    625e-3     6250e-e    62500e-3
- *  bytes/us      12.5e-3    125e-3     1250e-3    12500e-3   125000e-3
- *  bytes/1.27us  15.875e-3  158.75e-3  1587.5e-3  15875e-3   158750e-3
+ *  bytes/1.024us 12.8e-3    128e-3     1280e-3    12800e-3   128000e-3
  *
- *  0.5us/byte    160        16         1.6        0.16       0.016
- *  us/byte       80         8          0.8        0.08       0.008
- *  1.27us/byte   63         6.3        0.63       0.063      0.0063
+ *  1.024us/byte  78.125     7.8125     0.78125    0.078125   0.0078125
  */
 #define	SM_SHIFT	20
 #define	ISM_SHIFT	18

index 1c12afd..b090d55 100644
@@ -64,6 +64,16 @@ #define PSCHED_SET_PASTPERFECT(t)	((t) =
 #define PSCHED_IS_PASTPERFECT(t)	((t) == 0)
 #define	PSCHED_AUDIT_TDIFF(t)
 
+struct qdisc_watchdog {
+	struct hrtimer	timer;
+	struct Qdisc	*qdisc;
+};
+
+extern void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
+extern void qdisc_watchdog_schedule(struct qdisc_watchdog *wd,
+				    psched_time_t expires);
+extern void qdisc_watchdog_cancel(struct qdisc_watchdog *wd);
+
 extern struct Qdisc_ops pfifo_qdisc_ops;
 extern struct Qdisc_ops bfifo_qdisc_ops;
 

index d71bf79..6bc395c 100644
@@ -34,6 +34,7 @@ #include <linux/seq_file.h>
 #include <linux/kmod.h>
 #include <linux/list.h>
 #include <linux/bitops.h>
+#include <linux/hrtimer.h>
 
 #include <net/sock.h>
 #include <net/pkt_sched.h>

@@ -291,6 +292,41 @@ void qdisc_put_rtab(struct qdisc_rate_ta
 	}
 }
 
+static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
+{
+	struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
+						 timer);
+
+	wd->qdisc->flags &= ~TCQ_F_THROTTLED;
+	netif_schedule(wd->qdisc->dev);
+	return HRTIMER_NORESTART;
+}
+
+void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+{
+	hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	wd->timer.function = qdisc_watchdog;
+	wd->qdisc = qdisc;
+}
+EXPORT_SYMBOL(qdisc_watchdog_init);
+
+void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires)
+{
+	ktime_t time;
+
+	wd->qdisc->flags |= TCQ_F_THROTTLED;
+	time = ktime_set(0, 0);
+	time = ktime_add_ns(time, PSCHED_US2NS(expires));
+	hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS);
+}
+EXPORT_SYMBOL(qdisc_watchdog_schedule);
+
+void qdisc_watchdog_cancel(struct qdisc_watchdog *wd)
+{
+	hrtimer_cancel(&wd->timer);
+	wd->qdisc->flags &= ~TCQ_F_THROTTLED;
+}
+EXPORT_SYMBOL(qdisc_watchdog_cancel);
 
 /* Allocate an unique handle from space managed by kernel */
 

index 09cf6e4..49cae7d 100644
@@ -59,7 +59,6 @@ #include <linux/spinlock.h>
 #include <linux/skbuff.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <linux/timer.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/init.h>

@@ -192,7 +191,7 @@ struct hfsc_sched
 	struct list_head droplist;		/* active leaf class list (for
 						   dropping) */
 	struct sk_buff_head requeue;		/* requeued packet */
-	struct timer_list wd_timer;		/* watchdog timer */
+	struct qdisc_watchdog watchdog;		/* watchdog timer */
 };
 
 #define	HT_INFINITY	0xffffffffffffffffULL	/* infinite time value */

@@ -1432,21 +1431,11 @@ hfsc_walk(struct Qdisc *sch, struct qdis
 }
 
 static void
-hfsc_watchdog(unsigned long arg)
-{
-	struct Qdisc *sch = (struct Qdisc *)arg;
-
-	sch->flags &= ~TCQ_F_THROTTLED;
-	netif_schedule(sch->dev);
-}
-
-static void
-hfsc_schedule_watchdog(struct Qdisc *sch, u64 cur_time)
+hfsc_schedule_watchdog(struct Qdisc *sch)
 {
 	struct hfsc_sched *q = qdisc_priv(sch);
 	struct hfsc_class *cl;
 	u64 next_time = 0;
-	long delay;
 
 	if ((cl = eltree_get_minel(q)) != NULL)
 		next_time = cl->cl_e;

@@ -1455,11 +1444,7 @@ hfsc_schedule_watchdog(struct Qdisc *sch
 			next_time = q->root.cl_cfmin;
 	}
 	WARN_ON(next_time == 0);
-	delay = next_time - cur_time;
-	delay = PSCHED_US2JIFFIE(delay);
-
-	sch->flags |= TCQ_F_THROTTLED;
-	mod_timer(&q->wd_timer, jiffies + delay);
+	qdisc_watchdog_schedule(&q->watchdog, next_time);
 }
 
 static int

@@ -1496,9 +1481,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struc
 
 	list_add(&q->root.hlist, &q->clhash[hfsc_hash(q->root.classid)]);
 
-	init_timer(&q->wd_timer);
-	q->wd_timer.function = hfsc_watchdog;
-	q->wd_timer.data = (unsigned long)sch;
+	qdisc_watchdog_init(&q->watchdog, sch);
 
 	return 0;
 }

@@ -1568,8 +1551,7 @@ hfsc_reset_qdisc(struct Qdisc *sch)
 	__skb_queue_purge(&q->requeue);
 	q->eligible = RB_ROOT;
 	INIT_LIST_HEAD(&q->droplist);
-	del_timer(&q->wd_timer);
-	sch->flags &= ~TCQ_F_THROTTLED;
+	qdisc_watchdog_cancel(&q->watchdog);
 	sch->q.qlen = 0;
 }
 

@@ -1585,7 +1567,7 @@ hfsc_destroy_qdisc(struct Qdisc *sch)
 			hfsc_destroy_class(sch, cl);
 	}
 	__skb_queue_purge(&q->requeue);
-	del_timer(&q->wd_timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 }
 
 static int

@@ -1671,7 +1653,7 @@ hfsc_dequeue(struct Qdisc *sch)
 		cl = vttree_get_minvt(&q->root, cur_time);
 		if (cl == NULL) {
 			sch->qstats.overlimits++;
-			hfsc_schedule_watchdog(sch, cur_time);
+			hfsc_schedule_watchdog(sch);
 			return NULL;
 		}
 	}

index 85da8da..f14692f 100644
@@ -127,8 +127,8 @@ struct tbf_sched_data
 	long	tokens;			/* Current number of B tokens */
 	long	ptokens;		/* Current number of P tokens */
 	psched_time_t	t_c;		/* Time check-point */
-	struct timer_list wd_timer;	/* Watchdog timer */
 	struct Qdisc	*qdisc;		/* Inner qdisc, default - bfifo queue */
+	struct qdisc_watchdog watchdog;	/* Watchdog timer */
 };
 
 #define L2T(q,L)   ((q)->R_tab->data[(L)>>(q)->R_tab->rate.cell_log])

@@ -185,14 +185,6 @@ static unsigned int tbf_drop(struct Qdis
 	return len;
 }
 
-static void tbf_watchdog(unsigned long arg)
-{
-	struct Qdisc *sch = (struct Qdisc*)arg;
-
-	sch->flags &= ~TCQ_F_THROTTLED;
-	netif_schedule(sch->dev);
-}
-
 static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);

@@ -202,7 +194,7 @@ static struct sk_buff *tbf_dequeue(struc
 
 	if (skb) {
 		psched_time_t now;
-		long toks, delay;
+		long toks;
 		long ptoks = 0;
 		unsigned int len = skb->len;
 

@@ -230,12 +222,8 @@ static struct sk_buff *tbf_dequeue(struc
 			return skb;
 		}
 
-		delay = PSCHED_US2JIFFIE(max_t(long, -toks, -ptoks));
-
-		if (delay == 0)
-			delay = 1;
-
-		mod_timer(&q->wd_timer, jiffies+delay);
+		qdisc_watchdog_schedule(&q->watchdog,
+					now + max_t(long, -toks, -ptoks));
 
 		/* Maybe we have a shorter packet in the queue,
 		   which can be sent now. It sounds cool,

@@ -254,7 +242,6 @@ static struct sk_buff *tbf_dequeue(struc
 			sch->qstats.drops++;
 		}
 
-		sch->flags |= TCQ_F_THROTTLED;
 		sch->qstats.overlimits++;
 	}
 	return NULL;

@@ -269,8 +256,7 @@ static void tbf_reset(struct Qdisc* sch)
 	PSCHED_GET_TIME(q->t_c);
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
-	sch->flags &= ~TCQ_F_THROTTLED;
-	del_timer(&q->wd_timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 }
 
 static struct Qdisc *tbf_create_dflt_qdisc(struct Qdisc *sch, u32 limit)

@@ -378,10 +364,7 @@ static int tbf_init(struct Qdisc* sch, s
 		return -EINVAL;
 
 	PSCHED_GET_TIME(q->t_c);
-	init_timer(&q->wd_timer);
-	q->wd_timer.function = tbf_watchdog;
-	q->wd_timer.data = (unsigned long)sch;
-
+	qdisc_watchdog_init(&q->watchdog, sch);
 	q->qdisc = &noop_qdisc;
 
 	return tbf_change(sch, opt);

@@ -391,7 +374,7 @@ static void tbf_destroy(struct Qdisc *sc
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
-	del_timer(&q->wd_timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 
 	if (q->P_tab)
 		qdisc_put_rtab(q->P_tab);

index 1ccbfb5..915f82a 100644
@@ -54,7 +54,7 @@ #define VERSION "1.2"
 
 struct netem_sched_data {
 	struct Qdisc	*qdisc;
-	struct timer_list timer;
+	struct qdisc_watchdog watchdog;
 
 	u32 latency;
 	u32 loss;

@@ -284,7 +284,7 @@ static struct sk_buff *netem_dequeue(str
 			sch->flags &= ~TCQ_F_THROTTLED;
 			return skb;
 		} else {
-			psched_tdiff_t delay = PSCHED_TDIFF(cb->time_to_send, now);
+			qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send);
 
 			if (q->qdisc->ops->requeue(skb, q->qdisc) != NET_XMIT_SUCCESS) {
 				qdisc_tree_decrease_qlen(q->qdisc, 1);

@@ -292,32 +292,19 @@ static struct sk_buff *netem_dequeue(str
 				printk(KERN_ERR "netem: queue discpline %s could not requeue\n",
 				       q->qdisc->ops->id);
 			}
-
-			mod_timer(&q->timer, jiffies + PSCHED_US2JIFFIE(delay));
-			sch->flags |= TCQ_F_THROTTLED;
 		}
 	}
 
 	return NULL;
 }
 
-static void netem_watchdog(unsigned long arg)
-{
-	struct Qdisc *sch = (struct Qdisc *)arg;
-
-	pr_debug("netem_watchdog qlen=%d\n", sch->q.qlen);
-	sch->flags &= ~TCQ_F_THROTTLED;
-	netif_schedule(sch->dev);
-}
-
 static void netem_reset(struct Qdisc *sch)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
 	sch->q.qlen = 0;
-	sch->flags &= ~TCQ_F_THROTTLED;
-	del_timer_sync(&q->timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 }
 
 /* Pass size change message down to embedded FIFO */

@@ -567,9 +554,7 @@ static int netem_init(struct Qdisc *sch,
 	if (!opt)
 		return -EINVAL;
 
-	init_timer(&q->timer);
-	q->timer.function = netem_watchdog;
-	q->timer.data = (unsigned long) sch;
+	qdisc_watchdog_init(&q->watchdog, sch);
 
 	q->qdisc = qdisc_create_dflt(sch->dev, &tfifo_qdisc_ops,
 				     TC_H_MAKE(sch->handle, 1));

@@ -590,7 +575,7 @@ static void netem_destroy(struct Qdisc *
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
 
-	del_timer_sync(&q->timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 	qdisc_destroy(q->qdisc);
 	kfree(q->delay_dist);
 }

index 76c92e7..d29d121 100644
@@ -181,11 +181,11 @@ #endif
 	unsigned		pmask;
 
 	struct timer_list	delay_timer;
-	struct timer_list	wd_timer;	/* Watchdog timer,
+	struct qdisc_watchdog	watchdog;	/* Watchdog timer,
 						   started when CBQ has
 						   backlog, but cannot
 						   transmit just now */
-	long			wd_expires;
+	psched_tdiff_t		wd_expires;
 	int			toplevel;
 	u32			hgenerator;
 };

@@ -604,14 +604,6 @@ static void cbq_ovl_drop(struct cbq_clas
 	cbq_ovl_classic(cl);
 }
 
-static void cbq_watchdog(unsigned long arg)
-{
-	struct Qdisc *sch = (struct Qdisc*)arg;
-
-	sch->flags &= ~TCQ_F_THROTTLED;
-	netif_schedule(sch->dev);
-}
-
 static unsigned long cbq_undelay_prio(struct cbq_sched_data *q, int prio)
 {
 	struct cbq_class *cl;

@@ -1063,13 +1055,9 @@ cbq_dequeue(struct Qdisc *sch)
 
 	if (sch->q.qlen) {
 		sch->qstats.overlimits++;
-		if (q->wd_expires) {
-			long delay = PSCHED_US2JIFFIE(q->wd_expires);
-			if (delay <= 0)
-				delay = 1;
-			mod_timer(&q->wd_timer, jiffies + delay);
-			sch->flags |= TCQ_F_THROTTLED;
-		}
+		if (q->wd_expires)
+			qdisc_watchdog_schedule(&q->watchdog,
+						q->now + q->wd_expires);
 	}
 	return NULL;
 }

@@ -1276,7 +1264,7 @@ cbq_reset(struct Qdisc* sch)
 	q->pmask = 0;
 	q->tx_class = NULL;
 	q->tx_borrowed = NULL;
-	del_timer(&q->wd_timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 	del_timer(&q->delay_timer);
 	q->toplevel = TC_CBQ_MAXLEVEL;
 	PSCHED_GET_TIME(q->now);

@@ -1446,9 +1434,7 @@ static int cbq_init(struct Qdisc *sch, s
 	q->link.minidle = -0x7FFFFFFF;
 	q->link.stats_lock = &sch->dev->queue_lock;
 
-	init_timer(&q->wd_timer);
-	q->wd_timer.data = (unsigned long)sch;
-	q->wd_timer.function = cbq_watchdog;
+	qdisc_watchdog_init(&q->watchdog, sch);
 	init_timer(&q->delay_timer);
 	q->delay_timer.data = (unsigned long)sch;
 	q->delay_timer.function = cbq_undelay;

index d29d121..32f6a30 100644
@@ -612,7 +612,7 @@ static unsigned long cbq_undelay_prio(st
 	unsigned long sched = now;
 
 	if (cl_prev == NULL)
-		return now;
+		return 0;
 
 	do {
 		cl = cl_prev->next_alive;

index 32f6a30..ed7d540 100644
@@ -112,7 +112,7 @@ #endif
 
 	/* Overlimit strategy parameters */
 	void			(*overlimit)(struct cbq_class *cl);
-	long			penalty;
+	psched_tdiff_t		penalty;
 
 	/* General scheduler (WRR) parameters */
 	long			allot;

@@ -143,7 +143,7 @@ #endif
 	psched_time_t		undertime;
 	long			avgidle;
 	long			deficit;	/* Saved deficit for WRR */
-	unsigned long		penalized;
+	psched_time_t		penalized;
 	struct gnet_stats_basic bstats;
 	struct gnet_stats_queue qstats;
 	struct gnet_stats_rate_est rate_est;

@@ -180,7 +180,7 @@ #endif
 	psched_time_t		now_rt;		/* Cached real time */
 	unsigned		pmask;
 
-	struct timer_list	delay_timer;
+	struct hrtimer		delay_timer;
 	struct qdisc_watchdog	watchdog;	/* Watchdog timer,
 						   started when CBQ has
 						   backlog, but cannot

@@ -549,7 +549,8 @@ static void cbq_ovl_delay(struct cbq_cla
 	psched_tdiff_t delay = PSCHED_TDIFF(cl->undertime, q->now);
 
 	if (!cl->delayed) {
-		unsigned long sched = jiffies;
+		psched_time_t sched = q->now;
+		ktime_t expires;
 
 		delay += cl->offtime;
 		if (cl->avgidle < 0)

@@ -559,14 +560,18 @@ static void cbq_ovl_delay(struct cbq_cla
 		PSCHED_TADD2(q->now, delay, cl->undertime);
 
 		if (delay > 0) {
-			sched += PSCHED_US2JIFFIE(delay) + cl->penalty;
+			sched += delay + cl->penalty;
 			cl->penalized = sched;
 			cl->cpriority = TC_CBQ_MAXPRIO;
 			q->pmask |= (1<<TC_CBQ_MAXPRIO);
-			if (del_timer(&q->delay_timer) &&
-			    (long)(q->delay_timer.expires - sched) > 0)
-				q->delay_timer.expires = sched;
-			add_timer(&q->delay_timer);
+
+			expires = ktime_set(0, 0);
+			expires = ktime_add_ns(expires, PSCHED_US2NS(sched));
+			if (hrtimer_try_to_cancel(&q->delay_timer) &&
+			    ktime_to_ns(ktime_sub(q->delay_timer.expires,
+			    			  expires)) > 0)
+				q->delay_timer.expires = expires;
+			hrtimer_restart(&q->delay_timer);
 			cl->delayed = 1;
 			cl->xstats.overactions++;
 			return;

@@ -583,7 +588,7 @@ static void cbq_ovl_lowprio(struct cbq_c
 {
 	struct cbq_sched_data *q = qdisc_priv(cl->qdisc);
 
-	cl->penalized = jiffies + cl->penalty;
+	cl->penalized = q->now + cl->penalty;
 
 	if (cl->cpriority != cl->priority2) {
 		cl->cpriority = cl->priority2;

@@ -604,19 +609,19 @@ static void cbq_ovl_drop(struct cbq_clas
 	cbq_ovl_classic(cl);
 }
 
-static unsigned long cbq_undelay_prio(struct cbq_sched_data *q, int prio)
+static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio,
+				       psched_time_t now)
 {
 	struct cbq_class *cl;
 	struct cbq_class *cl_prev = q->active[prio];
-	unsigned long now = jiffies;
-	unsigned long sched = now;
+	psched_time_t sched = now;
 
 	if (cl_prev == NULL)
 		return 0;
 
 	do {
 		cl = cl_prev->next_alive;
-		if ((long)(now - cl->penalized) > 0) {
+		if (now - cl->penalized > 0) {
 			cl_prev->next_alive = cl->next_alive;
 			cl->next_alive = NULL;
 			cl->cpriority = cl->priority;

@@ -632,30 +637,34 @@ static unsigned long cbq_undelay_prio(st
 			}
 
 			cl = cl_prev->next_alive;
-		} else if ((long)(sched - cl->penalized) > 0)
+		} else if (sched - cl->penalized > 0)
 			sched = cl->penalized;
 	} while ((cl_prev = cl) != q->active[prio]);
 
-	return (long)(sched - now);
+	return sched - now;
 }
 
-static void cbq_undelay(unsigned long arg)
+static enum hrtimer_restart cbq_undelay(struct hrtimer *timer)
 {
-	struct Qdisc *sch = (struct Qdisc*)arg;
-	struct cbq_sched_data *q = qdisc_priv(sch);
-	long delay = 0;
+	struct cbq_sched_data *q = container_of(timer, struct cbq_sched_data,
+						delay_timer);
+	struct Qdisc *sch = q->watchdog.qdisc;
+	psched_time_t now;
+	psched_tdiff_t delay = 0;
 	unsigned pmask;
 
+	PSCHED_GET_TIME(now);
+
 	pmask = q->pmask;
 	q->pmask = 0;
 
 	while (pmask) {
 		int prio = ffz(~pmask);
-		long tmp;
+		psched_tdiff_t tmp;
 
 		pmask &= ~(1<<prio);
 
-		tmp = cbq_undelay_prio(q, prio);
+		tmp = cbq_undelay_prio(q, prio, now);
 		if (tmp > 0) {
 			q->pmask |= 1<<prio;
 			if (tmp < delay || delay == 0)

@@ -664,12 +673,16 @@ static void cbq_undelay(unsigned long ar
 	}
 
 	if (delay) {
-		q->delay_timer.expires = jiffies + delay;
-		add_timer(&q->delay_timer);
+		ktime_t time;
+
+		time = ktime_set(0, 0);
+		time = ktime_add_ns(time, PSCHED_US2NS(now + delay));
+		hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS);
 	}
 
 	sch->flags &= ~TCQ_F_THROTTLED;
 	netif_schedule(sch->dev);
+	return HRTIMER_NORESTART;
 }
 
 

@@ -1265,7 +1278,7 @@ cbq_reset(struct Qdisc* sch)
 	q->tx_class = NULL;
 	q->tx_borrowed = NULL;
 	qdisc_watchdog_cancel(&q->watchdog);
-	del_timer(&q->delay_timer);
+	hrtimer_cancel(&q->delay_timer);
 	q->toplevel = TC_CBQ_MAXLEVEL;
 	PSCHED_GET_TIME(q->now);
 	q->now_rt = q->now;

@@ -1367,7 +1380,7 @@ static int cbq_set_overlimit(struct cbq_
 	default:
 		return -EINVAL;
 	}
-	cl->penalty = (ovl->penalty*HZ)/1000;
+	cl->penalty = ovl->penalty;
 	return 0;
 }
 

@@ -1435,8 +1448,7 @@ static int cbq_init(struct Qdisc *sch, s
 	q->link.stats_lock = &sch->dev->queue_lock;
 
 	qdisc_watchdog_init(&q->watchdog, sch);
-	init_timer(&q->delay_timer);
-	q->delay_timer.data = (unsigned long)sch;
+	hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	q->delay_timer.function = cbq_undelay;
 	q->toplevel = TC_CBQ_MAXLEVEL;
 	PSCHED_GET_TIME(q->now);

@@ -1514,7 +1526,7 @@ static __inline__ int cbq_dump_ovl(struc
 	opt.strategy = cl->ovl_strategy;
 	opt.priority2 = cl->priority2+1;
 	opt.pad = 0;
-	opt.penalty = (cl->penalty*1000)/HZ;
+	opt.penalty = cl->penalty;
 	RTA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt);
 	return skb->len;
 

index 97cbb9a..b00cef7 100644
@@ -128,7 +128,7 @@ #endif
 	} un;
 	struct rb_node node[TC_HTB_NUMPRIO];	/* node for self or feed tree */
 	struct rb_node pq_node;	/* node for event queue */
-	unsigned long pq_key;	/* the same type as jiffies global */
+	psched_time_t pq_key;
 
 	int prio_activity;	/* for which prios are we active */
 	enum htb_cmode cmode;	/* current mode of the class */

@@ -179,10 +179,7 @@ struct htb_sched {
 	struct rb_root wait_pq[TC_HTB_MAXDEPTH];
 
 	/* time of nearest event per level (row) */
-	unsigned long near_ev_cache[TC_HTB_MAXDEPTH];
-
-	/* cached value of jiffies in dequeue */
-	unsigned long jiffies;
+	psched_time_t near_ev_cache[TC_HTB_MAXDEPTH];
 
 	/* whether we hit non-work conserving class during this dequeue; we use */
 	int nwc_hit;		/* this to disable mindelay complaint in dequeue */

@@ -195,7 +192,7 @@ struct htb_sched {
 
 	int rate2quantum;	/* quant = rate / rate2quantum */
 	psched_time_t now;	/* cached dequeue time */
-	struct timer_list timer;	/* send delay timer */
+	struct qdisc_watchdog watchdog;
 #ifdef HTB_RATECM
 	struct timer_list rttim;	/* rate computer timer */
 	int recmp_bucket;	/* which hash bucket to recompute next */

@@ -342,19 +339,19 @@ static void htb_add_to_wait_tree(struct 
 {
 	struct rb_node **p = &q->wait_pq[cl->level].rb_node, *parent = NULL;
 
-	cl->pq_key = q->jiffies + PSCHED_US2JIFFIE(delay);
-	if (cl->pq_key == q->jiffies)
+	cl->pq_key = q->now + delay;
+	if (cl->pq_key == q->now)
 		cl->pq_key++;
 
 	/* update the nearest event cache */
-	if (time_after(q->near_ev_cache[cl->level], cl->pq_key))
+	if (q->near_ev_cache[cl->level] > cl->pq_key)
 		q->near_ev_cache[cl->level] = cl->pq_key;
 
 	while (*p) {
 		struct htb_class *c;
 		parent = *p;
 		c = rb_entry(parent, struct htb_class, pq_node);
-		if (time_after_eq(cl->pq_key, c->pq_key))
+		if (cl->pq_key >= c->pq_key)
 			p = &parent->rb_right;
 		else
 			p = &parent->rb_left;

@@ -679,14 +676,6 @@ static int htb_requeue(struct sk_buff *s
 	return NET_XMIT_SUCCESS;
 }
 
-static void htb_timer(unsigned long arg)
-{
-	struct Qdisc *sch = (struct Qdisc *)arg;
-	sch->flags &= ~TCQ_F_THROTTLED;
-	wmb();
-	netif_schedule(sch->dev);
-}
-
 #ifdef HTB_RATECM
 #define RT_GEN(D,R) R+=D-(R/HTB_EWMAC);D=0
 static void htb_rate_timer(unsigned long arg)

@@ -778,11 +767,11 @@ #endif
 /**
  * htb_do_events - make mode changes to classes at the level
  *
- * Scans event queue for pending events and applies them. Returns jiffies to
+ * Scans event queue for pending events and applies them. Returns time of
  * next pending event (0 for no event in pq).
- * Note: Aplied are events whose have cl->pq_key <= jiffies.
+ * Note: Applied are events whose have cl->pq_key <= q->now.
  */
-static long htb_do_events(struct htb_sched *q, int level)
+static psched_time_t htb_do_events(struct htb_sched *q, int level)
 {
 	int i;
 

@@ -795,9 +784,9 @@ static long htb_do_events(struct htb_sch
 			return 0;
 
 		cl = rb_entry(p, struct htb_class, pq_node);
-		if (time_after(cl->pq_key, q->jiffies)) {
-			return cl->pq_key - q->jiffies;
-		}
+		if (cl->pq_key > q->now)
+			return cl->pq_key;
+
 		htb_safe_rb_erase(p, q->wait_pq + level);
 		diff = PSCHED_TDIFF_SAFE(q->now, cl->t_c, (u32) cl->mbuffer);
 		htb_change_class_mode(q, cl, &diff);

@@ -806,7 +795,7 @@ static long htb_do_events(struct htb_sch
 	}
 	if (net_ratelimit())
 		printk(KERN_WARNING "htb: too many events !\n");
-	return HZ / 10;
+	return q->now + PSCHED_TICKS_PER_SEC / 10;
 }
 
 /* Returns class->node+prio from id-tree where classe's id is >= id. NULL

@@ -958,30 +947,12 @@ next:
 	return skb;
 }
 
-static void htb_delay_by(struct Qdisc *sch, long delay)
-{
-	struct htb_sched *q = qdisc_priv(sch);
-	if (delay <= 0)
-		delay = 1;
-	if (unlikely(delay > 5 * HZ)) {
-		if (net_ratelimit())
-			printk(KERN_INFO "HTB delay %ld > 5sec\n", delay);
-		delay = 5 * HZ;
-	}
-	/* why don't use jiffies here ? because expires can be in past */
-	mod_timer(&q->timer, q->jiffies + delay);
-	sch->flags |= TCQ_F_THROTTLED;
-	sch->qstats.overlimits++;
-}
-
 static struct sk_buff *htb_dequeue(struct Qdisc *sch)
 {
 	struct sk_buff *skb = NULL;
 	struct htb_sched *q = qdisc_priv(sch);
 	int level;
-	long min_delay;
-
-	q->jiffies = jiffies;
+	psched_time_t next_event;
 
 	/* try to dequeue direct packets as high prio (!) to minimize cpu work */
 	skb = __skb_dequeue(&q->direct_queue);

@@ -995,21 +966,23 @@ static struct sk_buff *htb_dequeue(struc
 		goto fin;
 	PSCHED_GET_TIME(q->now);
 
-	min_delay = LONG_MAX;
+	next_event = q->now + 5 * PSCHED_TICKS_PER_SEC;
 	q->nwc_hit = 0;
 	for (level = 0; level < TC_HTB_MAXDEPTH; level++) {
 		/* common case optimization - skip event handler quickly */
 		int m;
-		long delay;
-		if (time_after_eq(q->jiffies, q->near_ev_cache[level])) {
-			delay = htb_do_events(q, level);
-			q->near_ev_cache[level] =
-			    q->jiffies + (delay ? delay : HZ);
+		psched_time_t event;
+
+		if (q->now >= q->near_ev_cache[level]) {
+			event = htb_do_events(q, level);
+			q->near_ev_cache[level] = event ? event :
+							  PSCHED_TICKS_PER_SEC;
 		} else
-			delay = q->near_ev_cache[level] - q->jiffies;
+			event = q->near_ev_cache[level];
+
+		if (event && next_event > event)
+			next_event = event;
 
-		if (delay && min_delay > delay)
-			min_delay = delay;
 		m = ~q->row_mask[level];
 		while (m != (int)(-1)) {
 			int prio = ffz(m);

@@ -1022,7 +995,8 @@ static struct sk_buff *htb_dequeue(struc
 			}
 		}
 	}
-	htb_delay_by(sch, min_delay > 5 * HZ ? 5 * HZ : min_delay);
+	sch->qstats.overlimits++;
+	qdisc_watchdog_schedule(&q->watchdog, next_event);
 fin:
 	return skb;
 }

@@ -1075,8 +1049,7 @@ static void htb_reset(struct Qdisc *sch)
 
 		}
 	}
-	sch->flags &= ~TCQ_F_THROTTLED;
-	del_timer(&q->timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 	__skb_queue_purge(&q->direct_queue);
 	sch->q.qlen = 0;
 	memset(q->row, 0, sizeof(q->row));

@@ -1113,14 +1086,12 @@ static int htb_init(struct Qdisc *sch, s
 	for (i = 0; i < TC_HTB_NUMPRIO; i++)
 		INIT_LIST_HEAD(q->drops + i);
 
-	init_timer(&q->timer);
+	qdisc_watchdog_init(&q->watchdog, sch);
 	skb_queue_head_init(&q->direct_queue);
 
 	q->direct_qlen = sch->dev->tx_queue_len;
 	if (q->direct_qlen < 2)	/* some devices have zero tx_queue_len */
 		q->direct_qlen = 2;
-	q->timer.function = htb_timer;
-	q->timer.data = (unsigned long)sch;
 
 #ifdef HTB_RATECM
 	init_timer(&q->rttim);

@@ -1341,7 +1312,7 @@ static void htb_destroy(struct Qdisc *sc
 {
 	struct htb_sched *q = qdisc_priv(sch);
 
-	del_timer_sync(&q->timer);
+	qdisc_watchdog_cancel(&q->watchdog);
 #ifdef HTB_RATECM
 	del_timer_sync(&q->rttim);
 #endif

index b090d55..6555e57 100644
@@ -51,9 +51,6 @@ #define PSCHED_TICKS_PER_SEC		PSCHED_NS2
 #define PSCHED_GET_TIME(stamp) \
 	((stamp) = PSCHED_NS2US(ktime_to_ns(ktime_get())))
 
-#define PSCHED_US2JIFFIE(usecs)		usecs_to_jiffies(PSCHED_US2NS((usecs)) / NSEC_PER_USEC)
-#define PSCHED_JIFFIE2US(delay)		PSCHED_NS2US(jiffies_to_usecs((delay)) * NSEC_PER_USEC)
-
 #define PSCHED_TDIFF(tv1, tv2)		(long)((tv1) - (tv2))
 #define PSCHED_TDIFF_SAFE(tv1, tv2, bound) \
 					min_t(long long, (tv1) - (tv2), bound)

index 49cae7d..522018b 100644
@@ -434,8 +434,8 @@ m2sm(u32 m)
 	u64 sm;
 
 	sm = ((u64)m << SM_SHIFT);
-	sm += PSCHED_JIFFIE2US(HZ) - 1;
-	do_div(sm, PSCHED_JIFFIE2US(HZ));
+	sm += PSCHED_TICKS_PER_SEC - 1;
+	do_div(sm, PSCHED_TICKS_PER_SEC);
 	return sm;
 }
 

@@ -448,7 +448,7 @@ m2ism(u32 m)
 	if (m == 0)
 		ism = HT_INFINITY;
 	else {
-		ism = ((u64)PSCHED_JIFFIE2US(HZ) << ISM_SHIFT);
+		ism = ((u64)PSCHED_TICKS_PER_SEC << ISM_SHIFT);
 		ism += m - 1;
 		do_div(ism, m);
 	}

@@ -461,7 +461,7 @@ d2dx(u32 d)
 {
 	u64 dx;
 
-	dx = ((u64)d * PSCHED_JIFFIE2US(HZ));
+	dx = ((u64)d * PSCHED_TICKS_PER_SEC);
 	dx += USEC_PER_SEC - 1;
 	do_div(dx, USEC_PER_SEC);
 	return dx;

@@ -473,7 +473,7 @@ sm2m(u64 sm)
 {
 	u64 m;
 
-	m = (sm * PSCHED_JIFFIE2US(HZ)) >> SM_SHIFT;
+	m = (sm * PSCHED_TICKS_PER_SEC) >> SM_SHIFT;
 	return (u32)m;
 }
 

@@ -484,7 +484,7 @@ dx2d(u64 dx)
 	u64 d;
 
 	d = dx * USEC_PER_SEC;
-	do_div(d, PSCHED_JIFFIE2US(HZ));
+	do_div(d, PSCHED_TICKS_PER_SEC);
 	return (u32)d;
 }
 

index b00cef7..1721043 100644
@@ -1469,7 +1469,7 @@ static int htb_change_class(struct Qdisc
 		/* set class to be in HTB_CAN_SEND state */
 		cl->tokens = hopt->buffer;
 		cl->ctokens = hopt->cbuffer;
-		cl->mbuffer = PSCHED_JIFFIE2US(HZ * 60);	/* 1min */
+		cl->mbuffer = 60 * PSCHED_TICKS_PER_SEC;	/* 1min */
 		PSCHED_GET_TIME(cl->t_c);
 		cl->cmode = HTB_CAN_SEND;
 

index 0491fad..d83414d 100644
@@ -1070,7 +1070,7 @@ cbq_dequeue(struct Qdisc *sch)
 		sch->qstats.overlimits++;
 		if (q->wd_expires)
 			qdisc_watchdog_schedule(&q->watchdog,
-						q->now + q->wd_expires);
+						now + q->wd_expires);
 	}
 	return NULL;
 }