Merge davem@nuts.davemloft.net:/disk1/BK/net-2.6

into kernel.bkbits.net:/home/davem/net-2.6

include/linux/pkt_sched.h

@@ -432,4 +432,10 @@ enum {
 
 #define TCA_ATM_MAX	TCA_ATM_STATE
 
+/* Delay section */
+struct tc_dly_qopt
+{
+	__u32	latency;
+	__u32   limit;
+};	
 #endif

include/net/flow.h

@@ -77,7 +77,7 @@ struct flowi {
 #define fl_icmp_type	uli_u.icmpt.type
 #define fl_icmp_code	uli_u.icmpt.code
 #define fl_ipsec_spi	uli_u.spi
-};
+} __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 #define FLOW_DIR_IN	0
 #define FLOW_DIR_OUT	1

net/key/af_key.c

@@ -901,6 +901,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 	struct sadb_sa *sa;
 	struct sadb_key *key;
 	uint16_t proto;
+	int err;
 	
 
 	sa = (struct sadb_sa *) ext_hdrs[SADB_EXT_SA-1];
@@ -922,6 +923,9 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 	if (proto == 0)
 		return ERR_PTR(-EINVAL);
 
+	/* default error is no buffer space */
+	err = -ENOBUFS;
+
 	/* RFC2367:
 
    Only SADB_SASTATE_MATURE SAs may be submitted in an SADB_ADD message.
@@ -980,8 +984,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 	if (sa->sadb_sa_auth) {
 		int keysize = 0;
 		struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth);
-		if (!a)
+		if (!a) {
+			err = -ENOSYS;
 			goto out;
+		}
 		if (key)
 			keysize = (key->sadb_key_bits + 7) / 8;
 		x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL);
@@ -999,8 +1005,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 	if (sa->sadb_sa_encrypt) {
 		if (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP) {
 			struct xfrm_algo_desc *a = xfrm_calg_get_byid(sa->sadb_sa_encrypt);
-			if (!a)
+			if (!a) {
+				err = -ENOSYS;
 				goto out;
+			}
 			x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL);
 			if (!x->calg)
 				goto out;
@@ -1009,8 +1017,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 		} else {
 			int keysize = 0;
 			struct xfrm_algo_desc *a = xfrm_ealg_get_byid(sa->sadb_sa_encrypt);
-			if (!a)
+			if (!a) {
+				err = -ENOSYS;
 				goto out;
+			}
 			key = (struct sadb_key*) ext_hdrs[SADB_EXT_KEY_ENCRYPT-1];
 			if (key)
 				keysize = (key->sadb_key_bits + 7) / 8;
@@ -1030,8 +1040,10 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 
 	x->props.family = pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_SRC-1], 
 						    &x->props.saddr);
-	if (!x->props.family)
+	if (!x->props.family) {
+		err = -EAFNOSUPPORT;
 		goto out;
+	}
 	pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_DST-1], 
 				  &x->id.daddr);
 
@@ -1076,10 +1088,14 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 	}
 
 	x->type = xfrm_get_type(proto, x->props.family);
-	if (x->type == NULL)
+	if (x->type == NULL) {
+		err = -ENOPROTOOPT;
 		goto out;
-	if (x->type->init_state(x, NULL))
+	}
+	if (x->type->init_state(x, NULL)) {
+		err = -EINVAL;
 		goto out;
+	}
 	x->km.seq = hdr->sadb_msg_seq;
 	x->km.state = XFRM_STATE_VALID;
 	return x;
@@ -1087,7 +1103,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct sadb_msg *hdr,
 out:
 	x->km.state = XFRM_STATE_DEAD;
 	xfrm_state_put(x);
-	return ERR_PTR(-ENOBUFS);
+	return ERR_PTR(err);
 }
 
 static int pfkey_reserved(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs)

net/sched/Kconfig

@@ -164,6 +164,17 @@ config NET_SCH_DSMARK
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_dsmark.
 
+config NET_SCH_DELAY
+	tristate "Delay simulator"
+	depends on NET_SCHED
+	help
+	  Say Y if you want to delay packets by a fixed amount of
+	  time. This is often useful to simulate network delay when
+	  testing applications or protocols.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_delay.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_SCHED && NETFILTER

net/sched/Makefile

@@ -22,6 +22,7 @@ obj-$(CONFIG_NET_SCH_TBF)	+= sch_tbf.o
 obj-$(CONFIG_NET_SCH_TEQL)	+= sch_teql.o
 obj-$(CONFIG_NET_SCH_PRIO)	+= sch_prio.o
 obj-$(CONFIG_NET_SCH_ATM)	+= sch_atm.o
+obj-$(CONFIG_NET_SCH_DELAY)	+= sch_delay.o
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
 obj-$(CONFIG_NET_CLS_FW)	+= cls_fw.o

net/sched/sch_delay.c

+/*
+ * net/sched/sch_delay.c	Simple constant delay
+ *
+ * 		This program is free software; you can redistribute it and/or
+ * 		modify it under the terms of the GNU General Public License
+ * 		as published by the Free Software Foundation; either version
+ * 		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Stephen Hemminger <shemminger@osdl.org>
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/if_ether.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/notifier.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/pkt_sched.h>
+
+/*	Network delay simulator
+	This scheduler adds a fixed delay to all packets.
+	Similar to NISTnet and BSD Dummynet.
+
+	It uses byte fifo underneath similar to TBF */
+struct dly_sched_data {
+	u32	latency;
+	u32	limit;
+	struct timer_list timer;
+	struct Qdisc *qdisc;
+};
+
+/* Time stamp put into socket buffer control block */
+struct dly_skb_cb {
+	psched_time_t	queuetime;
+};
+
+/* Enqueue packets with underlying discipline (fifo)
+ * but mark them with current time first.
+ */
+static int dly_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+	struct dly_skb_cb *cb = (struct dly_skb_cb *)skb->cb;
+	int ret;
+
+	PSCHED_GET_TIME(cb->queuetime);
+
+	/* Queue to underlying scheduler */
+	ret = q->qdisc->enqueue(skb, q->qdisc);
+	if (ret)
+		sch->stats.drops++;
+	else {
+		sch->q.qlen++;
+		sch->stats.bytes += skb->len;
+		sch->stats.packets++;
+	}
+	return 0;
+}
+
+/* Requeue packets but don't change time stamp */
+static int dly_requeue(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+	int ret;
+
+	ret = q->qdisc->ops->requeue(skb, q->qdisc);
+	if (ret == 0)
+		sch->q.qlen++;
+	return ret;
+}
+
+static unsigned int dly_drop(struct Qdisc *sch)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+	unsigned int len;
+
+	len = q->qdisc->ops->drop(q->qdisc);
+	if (len) {
+		sch->q.qlen--;
+		sch->stats.drops++;
+	}
+	return len;
+}
+
+/* Dequeue packet.
+ * If packet needs to be held up, then stop the
+ * queue and set timer to wakeup later.
+ */
+static struct sk_buff *dly_dequeue(struct Qdisc *sch)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+	struct sk_buff *skb = q->qdisc->dequeue(q->qdisc);
+
+	if (skb) {
+		struct dly_skb_cb *cb = (struct dly_skb_cb *)skb->cb;
+		psched_time_t now;
+		long diff;
+
+		PSCHED_GET_TIME(now);
+		diff = q->latency - PSCHED_TDIFF(now, cb->queuetime);
+
+		if (diff <= 0) {
+			sch->q.qlen--;
+			sch->flags &= ~TCQ_F_THROTTLED;
+			return skb;
+		}
+
+		if (!netif_queue_stopped(sch->dev)) {
+			long delay = PSCHED_US2JIFFIE(diff);
+			if (delay <= 0)
+				delay = 1;
+			mod_timer(&q->timer, jiffies+delay);
+		}
+
+		if (q->qdisc->ops->requeue(skb, q->qdisc) != NET_XMIT_SUCCESS) {
+			sch->q.qlen--;
+			sch->stats.drops++;
+		}
+		sch->flags |= TCQ_F_THROTTLED;
+	}
+	return NULL;
+}
+
+static void dly_reset(struct Qdisc *sch)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+
+	qdisc_reset(q->qdisc);
+	sch->q.qlen = 0;
+	sch->flags &= ~TCQ_F_THROTTLED;
+	del_timer(&q->timer);
+}
+
+static void dly_timer(unsigned long arg)
+{
+	struct Qdisc *sch = (struct Qdisc *)arg;
+
+	sch->flags &= ~TCQ_F_THROTTLED;
+	netif_schedule(sch->dev);
+}
+
+/* Tell Fifo the new limit. */
+static int change_limit(struct Qdisc *q, u32 limit)
+{
+	struct rtattr *rta;
+	int ret;
+
+	rta = kmalloc(RTA_LENGTH(sizeof(struct tc_fifo_qopt)), GFP_KERNEL);
+	if (!rta)
+		return -ENOMEM;
+
+	rta->rta_type = RTM_NEWQDISC;
+	((struct tc_fifo_qopt *)RTA_DATA(rta))->limit = limit;
+	ret = q->ops->change(q, rta);
+	kfree(rta);
+
+	return ret;
+}
+
+/* Setup underlying FIFO discipline */
+static int dly_change(struct Qdisc *sch, struct rtattr *opt)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+	struct tc_dly_qopt *qopt = RTA_DATA(opt);
+	int err;
+
+	if (q->qdisc == &noop_qdisc) {
+		struct Qdisc *child
+			= qdisc_create_dflt(sch->dev, &bfifo_qdisc_ops);
+		if (!child)
+			return -EINVAL;
+		q->qdisc = child;
+	}
+
+	err = change_limit(q->qdisc, qopt->limit);
+	if (err) {
+		qdisc_destroy(q->qdisc);
+		q->qdisc = &noop_qdisc;
+	} else {
+		q->latency = qopt->latency;
+		q->limit = qopt->limit;
+	}
+	return err;
+}
+
+static int dly_init(struct Qdisc *sch, struct rtattr *opt)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+
+	if (!opt)
+		return -EINVAL;
+
+	init_timer(&q->timer);
+	q->timer.function = dly_timer;
+	q->timer.data = (unsigned long) sch;
+	q->qdisc = &noop_qdisc;
+
+	return dly_change(sch, opt);
+}
+
+static void dly_destroy(struct Qdisc *sch)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+
+	del_timer(&q->timer);
+	qdisc_destroy(q->qdisc);
+	q->qdisc = &noop_qdisc;
+}
+
+static int dly_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct dly_sched_data *q = (struct dly_sched_data *)sch->data;
+	unsigned char	 *b = skb->tail;
+	struct tc_dly_qopt qopt;
+
+	qopt.latency = q->latency;
+	qopt.limit = q->limit;
+
+	RTA_PUT(skb, TCA_OPTIONS, sizeof(qopt), &qopt);
+
+	return skb->len;
+
+rtattr_failure:
+	skb_trim(skb, b - skb->data);
+	return -1;
+}
+
+static struct Qdisc_ops dly_qdisc_ops = {
+	.id		=	"delay",
+	.priv_size	=	sizeof(struct dly_sched_data),
+	.enqueue	=	dly_enqueue,
+	.dequeue	=	dly_dequeue,
+	.requeue	=	dly_requeue,
+	.drop		=	dly_drop,
+	.init		=	dly_init,
+	.reset		=	dly_reset,
+	.destroy	=	dly_destroy,
+	.change		=	dly_change,
+	.dump		=	dly_dump,
+	.owner		=	THIS_MODULE,
+};
+
+
+static int __init dly_module_init(void)
+{
+	return register_qdisc(&dly_qdisc_ops);
+}
+static void __exit dly_module_exit(void)
+{
+	unregister_qdisc(&dly_qdisc_ops);
+}
+module_init(dly_module_init)
+module_exit(dly_module_exit)
+MODULE_LICENSE("GPL");

net/sched/sch_hfsc.c

@@ -118,7 +118,7 @@ enum hfsc_class_flags
 
 struct hfsc_class
 {
-	u32	classid;	/* class id */
+	u32		classid;	/* class id */
 	unsigned int	refcnt;		/* usage count */
 
 	struct tc_stats	stats;		/* generic statistics */
@@ -138,28 +138,28 @@ struct hfsc_class
 	struct list_head hlist;		/* hash list member */
 	struct list_head dlist;		/* drop list member */
 
-	u64	cl_total;	/* total work in bytes */
-	u64	cl_cumul;	/* cumulative work in bytes done by
+	u64	cl_total;		/* total work in bytes */
+	u64	cl_cumul;		/* cumulative work in bytes done by
 					   real-time criteria */
 
-	u64 	cl_d;		/* deadline*/
-	u64 	cl_e;		/* eligible time */
-	u64	cl_vt;		/* virtual time */
-	u64	cl_f;		/* time when this class will fit for
+	u64 	cl_d;			/* deadline*/
+	u64 	cl_e;			/* eligible time */
+	u64	cl_vt;			/* virtual time */
+	u64	cl_f;			/* time when this class will fit for
 					   link-sharing, max(myf, cfmin) */
-	u64	cl_myf;		/* my fit-time (calculated from this
+	u64	cl_myf;			/* my fit-time (calculated from this
 					   class's own upperlimit curve) */
-	u64	cl_myfadj;	/* my fit-time adjustment (to cancel
+	u64	cl_myfadj;		/* my fit-time adjustment (to cancel
 					   history dependence) */
-	u64	cl_cfmin;	/* earliest children's fit-time (used
+	u64	cl_cfmin;		/* earliest children's fit-time (used
 					   with cl_myf to obtain cl_f) */
-	u64	cl_cvtmin;	/* minimal virtual time among the
+	u64	cl_cvtmin;		/* minimal virtual time among the
 					   children fit for link-sharing
 					   (monotonic within a period) */
-	u64	cl_vtadj;	/* intra-period cumulative vt
+	u64	cl_vtadj;		/* intra-period cumulative vt
 					   adjustment */
-	u64	cl_vtoff;	/* inter-period cumulative vt offset */
-	u64	cl_cvtmax;	/* max child's vt in the last period */
+	u64	cl_vtoff;		/* inter-period cumulative vt offset */
+	u64	cl_cvtmax;		/* max child's vt in the last period */
 
 	struct internal_sc cl_rsc;	/* internal real-time service curve */
 	struct internal_sc cl_fsc;	/* internal fair service curve */
@@ -179,15 +179,13 @@ struct hfsc_class
 
 struct hfsc_sched
 {
-	u16	defcls;			/* default class id */
-
+	u16	defcls;				/* default class id */
 	struct hfsc_class root;			/* root class */
-	struct hfsc_class *last_xmit;		/* class that transmitted last
-						   packet (for requeueing) */
 	struct list_head clhash[HFSC_HSIZE];	/* class hash */
 	struct list_head eligible;		/* eligible list */
 	struct list_head droplist;		/* active leaf class list (for
 						   dropping) */
+	struct sk_buff_head requeue;		/* requeued packet */
 	struct timer_list wd_timer;		/* watchdog timer */
 };
 
@@ -566,8 +564,7 @@ sc2isc(struct tc_service_curve *sc, struct internal_sc *isc)
  * service curve starting at (x, y).
  */
 static void
-rtsc_init(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x,
-                                                            u64 y)
+rtsc_init(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y)
 {
 	rtsc->x	   = x;
 	rtsc->y    = y;
@@ -626,8 +623,7 @@ rtsc_x2y(struct runtime_sc *rtsc, u64 x)
  * runtime service curve and the service curve starting at (x, y).
  */
 static void
-rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x,
-                                                           u64 y)
+rtsc_min(struct runtime_sc *rtsc, struct internal_sc *isc, u64 x, u64 y)
 {
 	u64 y1, y2, dx, dy;
 	u32 dsm;
@@ -1231,9 +1227,6 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg)
 	list_del(&cl->siblings);
 	hfsc_adjust_levels(cl->cl_parent);
 	hfsc_purge_queue(sch, cl);
-	if (q->last_xmit == cl)
-		q->last_xmit = NULL;
-
 	if (--cl->refcnt == 0)
 		hfsc_destroy_class(sch, cl);
 
@@ -1541,6 +1534,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct rtattr *opt)
 		INIT_LIST_HEAD(&q->clhash[i]);
 	INIT_LIST_HEAD(&q->eligible);
 	INIT_LIST_HEAD(&q->droplist);
+	skb_queue_head_init(&q->requeue);
 
 	q->root.refcnt  = 1;
 	q->root.classid = sch->handle;
@@ -1619,10 +1613,9 @@ hfsc_reset_qdisc(struct Qdisc *sch)
 		list_for_each_entry(cl, &q->clhash[i], hlist)
 			hfsc_reset_class(cl);
 	}
-
+	__skb_queue_purge(&q->requeue);
 	INIT_LIST_HEAD(&q->eligible);
 	INIT_LIST_HEAD(&q->droplist);
-	q->last_xmit = NULL;
 	del_timer(&q->wd_timer);
 	sch->flags &= ~TCQ_F_THROTTLED;
 	sch->q.qlen = 0;
@@ -1639,7 +1632,7 @@ hfsc_destroy_qdisc(struct Qdisc *sch)
 		list_for_each_entry_safe(cl, next, &q->clhash[i], hlist)
 			hfsc_destroy_class(sch, cl);
 	}
-
+	__skb_queue_purge(&q->requeue);
 	del_timer(&q->wd_timer);
 }
 
@@ -1708,6 +1701,8 @@ hfsc_dequeue(struct Qdisc *sch)
 
 	if (sch->q.qlen == 0)
 		return NULL;
+	if ((skb = __skb_dequeue(&q->requeue)))
+		goto out;
 
 	PSCHED_GET_TIME(cur_time);
 
@@ -1757,7 +1752,7 @@ hfsc_dequeue(struct Qdisc *sch)
 		set_passive(cl);
 	}
 
-	q->last_xmit = cl;
+ out:
 	sch->flags &= ~TCQ_F_THROTTLED;
 	sch->q.qlen--;
 
@@ -1768,28 +1763,10 @@ static int
 hfsc_requeue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct hfsc_sched *q = (struct hfsc_sched *)sch->data;
-	struct hfsc_class *cl = q->last_xmit;
-	unsigned int len = skb->len;
-	int ret;
-
-	if (cl == NULL) {
-		kfree_skb(skb);
-		sch->stats.drops++;
-		return NET_XMIT_DROP;
-	}
 
-	ret = cl->qdisc->ops->requeue(skb, cl->qdisc);
-	if (ret == NET_XMIT_SUCCESS) {
-		if (cl->qdisc->q.qlen == 1)
-			set_active(cl, len);
-		sch->q.qlen++;
-	} else {
-		cl->stats.drops++;
-		sch->stats.drops++;
-	}
-	q->last_xmit = NULL;
-
-	return ret;
+	__skb_queue_head(&q->requeue, skb);
+	sch->q.qlen++;
+	return NET_XMIT_SUCCESS;
 }
 
 static unsigned int