7 files changed, 143 insertions, 56 deletions

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 7bac249258e3..59d3e71f8b85 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -1,6 +1,43 @@
 #
 # Traffic control configuration.
 # 
+
+menuconfig NET_SCHED
+        bool "QoS and/or fair queueing"
+        ---help---
+          When the kernel has several packets to send out over a network
+          device, it has to decide which ones to send first, which ones to
+          delay, and which ones to drop. This is the job of the packet
+          scheduler, and several different algorithms for how to do this
+          "fairly" have been proposed.
+
+          If you say N here, you will get the standard packet scheduler, which
+          is a FIFO (first come, first served). If you say Y here, you will be
+          able to choose from among several alternative algorithms which can
+          then be attached to different network devices. This is useful for
+          example if some of your network devices are real time devices that
+          need a certain minimum data flow rate, or if you need to limit the
+          maximum data flow rate for traffic which matches specified criteria.
+          This code is considered to be experimental.
+
+          To administer these schedulers, you'll need the user-level utilities
+          from the package iproute2+tc at <ftp://ftp.tux.org/pub/net/ip-routing/>.
+          That package also contains some documentation; for more, check out
+          <http://snafu.freedom.org/linux2.2/iproute-notes.html>.
+
+          This Quality of Service (QoS) support will enable you to use
+          Differentiated Services (diffserv) and Resource Reservation Protocol
+          (RSVP) on your Linux router if you also say Y to "QoS support",
+          "Packet classifier API" and to some classifiers below. Documentation
+          and software is at <http://diffserv.sourceforge.net/>.
+
+          If you say Y here and to "/proc file system" below, you will be able
+          to read status information about packet schedulers from the file
+          /proc/net/psched.
+
+          The available schedulers are listed in the following questions; you
+          can say Y to as many as you like. If unsure, say N now.
+
 choice
         prompt "Packet scheduler clock source"
         depends on NET_SCHED
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 8f58cecd6266..e48d0d456b3e 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -4,7 +4,7 @@
 
 obj-y   := sch_generic.o
 
-obj-$(CONFIG_NET_SCHED)         += sch_api.o sch_fifo.o
+obj-$(CONFIG_NET_SCHED)         += sch_api.o sch_fifo.o sch_blackhole.o
 obj-$(CONFIG_NET_CLS)           += cls_api.o
 obj-$(CONFIG_NET_CLS_ACT)       += act_api.o
 obj-$(CONFIG_NET_ACT_POLICE)    += police.o
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 48bb23c2a35a..53d98f8d3d80 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -205,11 +205,6 @@ META_COLLECTOR(int_protocol)
         dst->value = skb->protocol;
 }
 
-META_COLLECTOR(int_security)
-{
-        dst->value = skb->security;
-}
-
 META_COLLECTOR(int_pkttype)
 {
         dst->value = skb->pkt_type;
@@ -524,7 +519,6 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = {
                 [META_ID(REALDEV)]              = META_FUNC(int_realdev),
                 [META_ID(PRIORITY)]             = META_FUNC(int_priority),
                 [META_ID(PROTOCOL)]             = META_FUNC(int_protocol),
-                [META_ID(SECURITY)]             = META_FUNC(int_security),
                 [META_ID(PKTTYPE)]              = META_FUNC(int_pkttype),
                 [META_ID(PKTLEN)]               = META_FUNC(int_pktlen),
                 [META_ID(DATALEN)]              = META_FUNC(int_datalen),
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 05e6e0a799da..b9a069af4a02 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -399,10 +399,8 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp)
 {
         int err;
         struct rtattr *kind = tca[TCA_KIND-1];
-        void *p = NULL;
         struct Qdisc *sch;
         struct Qdisc_ops *ops;
-        int size;
 
         ops = qdisc_lookup_ops(kind);
 #ifdef CONFIG_KMOD
@@ -437,64 +435,55 @@ qdisc_create(struct net_device *dev, u32 handle, struct rtattr **tca, int *errp)
         if (ops == NULL)
                 goto err_out;
 
-        /* ensure that the Qdisc and the private data are 32-byte aligned */
-        size = ((sizeof(*sch) + QDISC_ALIGN_CONST) & ~QDISC_ALIGN_CONST);
-        size += ops->priv_size + QDISC_ALIGN_CONST;
-
-        p = kmalloc(size, GFP_KERNEL);
-        err = -ENOBUFS;
-        if (!p)
+        sch = qdisc_alloc(dev, ops);
+        if (IS_ERR(sch)) {
+                err = PTR_ERR(sch);
                 goto err_out2;
-        memset(p, 0, size);
-        sch = (struct Qdisc *)(((unsigned long)p + QDISC_ALIGN_CONST)
-                               & ~QDISC_ALIGN_CONST);
-        sch->padded = (char *)sch - (char *)p;
-
-        INIT_LIST_HEAD(&sch->list);
-        skb_queue_head_init(&sch->q);
+        }
 
-        if (handle == TC_H_INGRESS)
+        if (handle == TC_H_INGRESS) {
                 sch->flags |= TCQ_F_INGRESS;
-
-        sch->ops = ops;
-        sch->enqueue = ops->enqueue;
-        sch->dequeue = ops->dequeue;
-        sch->dev = dev;
-        dev_hold(dev);
-        atomic_set(&sch->refcnt, 1);
-        sch->stats_lock = &dev->queue_lock;
-        if (handle == 0) {
+                handle = TC_H_MAKE(TC_H_INGRESS, 0);
+        } else if (handle == 0) {
                 handle = qdisc_alloc_handle(dev);
                 err = -ENOMEM;
                 if (handle == 0)
                         goto err_out3;
         }
 
-        if (handle == TC_H_INGRESS)
-                sch->handle =TC_H_MAKE(TC_H_INGRESS, 0);
-        else
-                sch->handle = handle;
+        sch->handle = handle;
 
         if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS-1])) == 0) {
+#ifdef CONFIG_NET_ESTIMATOR
+                if (tca[TCA_RATE-1]) {
+                        err = gen_new_estimator(&sch->bstats, &sch->rate_est,
+                                                sch->stats_lock,
+                                                tca[TCA_RATE-1]);
+                        if (err) {
+                                /*
+                                 * Any broken qdiscs that would require
+                                 * a ops->reset() here? The qdisc was never
+                                 * in action so it shouldn't be necessary.
+                                 */
+                                if (ops->destroy)
+                                        ops->destroy(sch);
+                                goto err_out3;
+                        }
+                }
+#endif
                 qdisc_lock_tree(dev);
                 list_add_tail(&sch->list, &dev->qdisc_list);
                 qdisc_unlock_tree(dev);
 
-#ifdef CONFIG_NET_ESTIMATOR
-                if (tca[TCA_RATE-1])
-                        gen_new_estimator(&sch->bstats, &sch->rate_est,
-                                sch->stats_lock, tca[TCA_RATE-1]);
-#endif
                 return sch;
         }
 err_out3:
         dev_put(dev);
+        kfree((char *) sch - sch->padded);
 err_out2:
         module_put(ops->owner);
 err_out:
         *errp = err;
-        if (p)
-                kfree(p);
         return NULL;
 }
 
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
new file mode 100644
index 000000000000..81f0b8346d17
--- /dev/null
+++ b/net/sched/sch_blackhole.c
@@ -0,0 +1,54 @@
+/*
+ * net/sched/sch_blackhole.c    Black hole queue
+ *
+ *              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:     Thomas Graf <tgraf@suug.ch>
+ *
+ * Note: Quantum tunneling is not supported.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <net/pkt_sched.h>
+
+static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch)
+{
+        qdisc_drop(skb, sch);
+        return NET_XMIT_SUCCESS;
+}
+
+static struct sk_buff *blackhole_dequeue(struct Qdisc *sch)
+{
+        return NULL;
+}
+
+static struct Qdisc_ops blackhole_qdisc_ops = {
+        .id             = "blackhole",
+        .priv_size      = 0,
+        .enqueue        = blackhole_enqueue,
+        .dequeue        = blackhole_dequeue,
+        .owner          = THIS_MODULE,
+};
+
+static int __init blackhole_module_init(void)
+{
+        return register_qdisc(&blackhole_qdisc_ops);
+}
+
+static void __exit blackhole_module_exit(void)
+{
+        unregister_qdisc(&blackhole_qdisc_ops);
+}
+
+module_init(blackhole_module_init)
+module_exit(blackhole_module_exit)
+
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7683b34dc6a9..73e218e646ac 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -395,24 +395,23 @@ static struct Qdisc_ops pfifo_fast_ops = {
         .owner          =       THIS_MODULE,
 };
 
-struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops)
+struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops)
 {
         void *p;
         struct Qdisc *sch;
-        int size;
+        unsigned int size;
+        int err = -ENOBUFS;
 
         /* ensure that the Qdisc and the private data are 32-byte aligned */
-        size = ((sizeof(*sch) + QDISC_ALIGN_CONST) & ~QDISC_ALIGN_CONST);
-        size += ops->priv_size + QDISC_ALIGN_CONST;
+        size = QDISC_ALIGN(sizeof(*sch));
+        size += ops->priv_size + (QDISC_ALIGNTO - 1);
 
         p = kmalloc(size, GFP_KERNEL);
         if (!p)
-                return NULL;
+                goto errout;
         memset(p, 0, size);
-
-        sch = (struct Qdisc *)(((unsigned long)p + QDISC_ALIGN_CONST) 
-                               & ~QDISC_ALIGN_CONST);
-        sch->padded = (char *)sch - (char *)p;
+        sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
+        sch->padded = (char *) sch - (char *) p;
 
         INIT_LIST_HEAD(&sch->list);
         skb_queue_head_init(&sch->q);
@@ -423,11 +422,24 @@ struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops)
         dev_hold(dev);
         sch->stats_lock = &dev->queue_lock;
         atomic_set(&sch->refcnt, 1);
+
+        return sch;
+errout:
+        return ERR_PTR(-err);
+}
+
+struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops)
+{
+        struct Qdisc *sch;
+        
+        sch = qdisc_alloc(dev, ops);
+        if (IS_ERR(sch))
+                goto errout;
+
         if (!ops->init || ops->init(sch, NULL) == 0)
                 return sch;
 
-        dev_put(dev);
-        kfree(p);
+errout:
         return NULL;
 }
 
@@ -591,6 +603,7 @@ EXPORT_SYMBOL(__netdev_watchdog_up);
 EXPORT_SYMBOL(noop_qdisc);
 EXPORT_SYMBOL(noop_qdisc_ops);
 EXPORT_SYMBOL(qdisc_create_dflt);
+EXPORT_SYMBOL(qdisc_alloc);
 EXPORT_SYMBOL(qdisc_destroy);
 EXPORT_SYMBOL(qdisc_reset);
 EXPORT_SYMBOL(qdisc_restart);
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 664d0e47374f..7845d045eec4 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -385,7 +385,7 @@ static int red_change(struct Qdisc *sch, struct rtattr *opt)
         memcpy(q->Stab, RTA_DATA(tb[TCA_RED_STAB-1]), 256);
 
         q->qcount = -1;
-        if (skb_queue_len(&sch->q) == 0)
+        if (skb_queue_empty(&sch->q))
                 PSCHED_SET_PASTPERFECT(q->qidlestart);
         sch_tree_unlock(sch);
         return 0;