13 files changed, 451 insertions, 22 deletions

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index c03a32a..ad1f1d8 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -443,6 +443,16 @@ config NET_CLS_CGROUP
 	  To compile this code as a module, choose M here: the
 	  module will be called cls_cgroup.
 
+config NET_CLS_BPF
+	tristate "BPF-based classifier"
+	select NET_CLS
+	---help---
+	  If you say Y here, you will be able to classify packets based on
+	  programmable BPF (JIT'ed) filters as an alternative to ematches.
+
+	  To compile this code as a module, choose M here: the module will
+	  be called cls_bpf.
+
 config NET_EMATCH
 	bool "Extended Matches"
 	select NET_CLS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index e5f9abe..35fa47a 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_NET_CLS_RSVP6)	+= cls_rsvp6.o
 obj-$(CONFIG_NET_CLS_BASIC)	+= cls_basic.o
 obj-$(CONFIG_NET_CLS_FLOW)	+= cls_flow.o
 obj-$(CONFIG_NET_CLS_CGROUP)	+= cls_cgroup.o
+obj-$(CONFIG_NET_CLS_BPF)	+= cls_bpf.o
 obj-$(CONFIG_NET_EMATCH)	+= ematch.o
 obj-$(CONFIG_NET_EMATCH_CMP)	+= em_cmp.o
 obj-$(CONFIG_NET_EMATCH_NBYTE)	+= em_nbyte.o
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 189e3c5..272d8e9 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -231,14 +231,14 @@ override:
 	}
 	if (R_tab) {
 		police->rate_present = true;
-		psched_ratecfg_precompute(&police->rate, &R_tab->rate);
+		psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0);
 		qdisc_put_rtab(R_tab);
 	} else {
 		police->rate_present = false;
 	}
 	if (P_tab) {
 		police->peak_present = true;
-		psched_ratecfg_precompute(&police->peak, &P_tab->rate);
+		psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0);
 		qdisc_put_rtab(P_tab);
 	} else {
 		police->peak_present = false;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index d76a35d..636d913 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -137,7 +137,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp,
 			   struct nlattr **tb,
 			   struct nlattr *est)
 {
-	int err = -EINVAL;
+	int err;
 	struct tcf_exts e;
 	struct tcf_ematch_tree t;
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
new file mode 100644
index 0000000..1002a82
--- /dev/null
+++ b/net/sched/cls_bpf.c
@@ -0,0 +1,385 @@
+/*
+ * Berkeley Packet Filter based traffic classifier
+ *
+ * Might be used to classify traffic through flexible, user-defined and
+ * possibly JIT-ed BPF filters for traffic control as an alternative to
+ * ematches.
+ *
+ * (C) 2013 Daniel Borkmann <dborkman@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/sock.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
+MODULE_DESCRIPTION("TC BPF based classifier");
+
+struct cls_bpf_head {
+	struct list_head plist;
+	u32 hgen;
+};
+
+struct cls_bpf_prog {
+	struct sk_filter *filter;
+	struct sock_filter *bpf_ops;
+	struct tcf_exts exts;
+	struct tcf_result res;
+	struct list_head link;
+	u32 handle;
+	u16 bpf_len;
+};
+
+static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
+	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
+	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
+	[TCA_BPF_OPS]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static const struct tcf_ext_map bpf_ext_map = {
+	.action = TCA_BPF_ACT,
+	.police = TCA_BPF_POLICE,
+};
+
+static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
+			    struct tcf_result *res)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog;
+	int ret;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		int filter_res = SK_RUN_FILTER(prog->filter, skb);
+
+		if (filter_res == 0)
+			continue;
+
+		*res = prog->res;
+		if (filter_res != -1)
+			res->classid = filter_res;
+
+		ret = tcf_exts_exec(skb, &prog->exts, res);
+		if (ret < 0)
+			continue;
+
+		return ret;
+	}
+
+	return -1;
+}
+
+static int cls_bpf_init(struct tcf_proto *tp)
+{
+	struct cls_bpf_head *head;
+
+	head = kzalloc(sizeof(*head), GFP_KERNEL);
+	if (head == NULL)
+		return -ENOBUFS;
+
+	INIT_LIST_HEAD(&head->plist);
+	tp->root = head;
+
+	return 0;
+}
+
+static void cls_bpf_delete_prog(struct tcf_proto *tp, struct cls_bpf_prog *prog)
+{
+	tcf_unbind_filter(tp, &prog->res);
+	tcf_exts_destroy(tp, &prog->exts);
+
+	sk_unattached_filter_destroy(prog->filter);
+
+	kfree(prog->bpf_ops);
+	kfree(prog);
+}
+
+static int cls_bpf_delete(struct tcf_proto *tp, unsigned long arg)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog, *todel = (struct cls_bpf_prog *) arg;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (prog == todel) {
+			tcf_tree_lock(tp);
+			list_del(&prog->link);
+			tcf_tree_unlock(tp);
+
+			cls_bpf_delete_prog(tp, prog);
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+static void cls_bpf_destroy(struct tcf_proto *tp)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog, *tmp;
+
+	list_for_each_entry_safe(prog, tmp, &head->plist, link) {
+		list_del(&prog->link);
+		cls_bpf_delete_prog(tp, prog);
+	}
+
+	kfree(head);
+}
+
+static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog;
+	unsigned long ret = 0UL;
+
+	if (head == NULL)
+		return 0UL;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (prog->handle == handle) {
+			ret = (unsigned long) prog;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
+{
+}
+
+static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
+				   struct cls_bpf_prog *prog,
+				   unsigned long base, struct nlattr **tb,
+				   struct nlattr *est)
+{
+	struct sock_filter *bpf_ops, *bpf_old;
+	struct tcf_exts exts;
+	struct sock_fprog tmp;
+	struct sk_filter *fp, *fp_old;
+	u16 bpf_size, bpf_len;
+	u32 classid;
+	int ret;
+
+	if (!tb[TCA_BPF_OPS_LEN] || !tb[TCA_BPF_OPS] || !tb[TCA_BPF_CLASSID])
+		return -EINVAL;
+
+	ret = tcf_exts_validate(net, tp, tb, est, &exts, &bpf_ext_map);
+	if (ret < 0)
+		return ret;
+
+	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+	bpf_len = nla_get_u16(tb[TCA_BPF_OPS_LEN]);
+	if (bpf_len > BPF_MAXINSNS || bpf_len == 0) {
+		ret = -EINVAL;
+		goto errout;
+	}
+
+	bpf_size = bpf_len * sizeof(*bpf_ops);
+	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	if (bpf_ops == NULL) {
+		ret = -ENOMEM;
+		goto errout;
+	}
+
+	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
+
+	tmp.len = bpf_len;
+	tmp.filter = (struct sock_filter __user *) bpf_ops;
+
+	ret = sk_unattached_filter_create(&fp, &tmp);
+	if (ret)
+		goto errout_free;
+
+	tcf_tree_lock(tp);
+	fp_old = prog->filter;
+	bpf_old = prog->bpf_ops;
+
+	prog->bpf_len = bpf_len;
+	prog->bpf_ops = bpf_ops;
+	prog->filter = fp;
+	prog->res.classid = classid;
+	tcf_tree_unlock(tp);
+
+	tcf_bind_filter(tp, &prog->res, base);
+	tcf_exts_change(tp, &prog->exts, &exts);
+
+	if (fp_old)
+		sk_unattached_filter_destroy(fp_old);
+	if (bpf_old)
+		kfree(bpf_old);
+
+	return 0;
+
+errout_free:
+	kfree(bpf_ops);
+errout:
+	tcf_exts_destroy(tp, &exts);
+	return ret;
+}
+
+static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
+				   struct cls_bpf_head *head)
+{
+	unsigned int i = 0x80000000;
+
+	do {
+		if (++head->hgen == 0x7FFFFFFF)
+			head->hgen = 1;
+	} while (--i > 0 && cls_bpf_get(tp, head->hgen));
+	if (i == 0)
+		pr_err("Insufficient number of handles\n");
+
+	return i;
+}
+
+static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
+			  struct tcf_proto *tp, unsigned long base,
+			  u32 handle, struct nlattr **tca,
+			  unsigned long *arg)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg;
+	struct nlattr *tb[TCA_BPF_MAX + 1];
+	int ret;
+
+	if (tca[TCA_OPTIONS] == NULL)
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy);
+	if (ret < 0)
+		return ret;
+
+	if (prog != NULL) {
+		if (handle && prog->handle != handle)
+			return -EINVAL;
+		return cls_bpf_modify_existing(net, tp, prog, base, tb,
+					       tca[TCA_RATE]);
+	}
+
+	prog = kzalloc(sizeof(*prog), GFP_KERNEL);
+	if (prog == NULL)
+		return -ENOBUFS;
+
+	if (handle == 0)
+		prog->handle = cls_bpf_grab_new_handle(tp, head);
+	else
+		prog->handle = handle;
+	if (prog->handle == 0) {
+		ret = -EINVAL;
+		goto errout;
+	}
+
+	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE]);
+	if (ret < 0)
+		goto errout;
+
+	tcf_tree_lock(tp);
+	list_add(&prog->link, &head->plist);
+	tcf_tree_unlock(tp);
+
+	*arg = (unsigned long) prog;
+
+	return 0;
+errout:
+	if (*arg == 0UL && prog)
+		kfree(prog);
+
+	return ret;
+}
+
+static int cls_bpf_dump(struct tcf_proto *tp, unsigned long fh,
+			struct sk_buff *skb, struct tcmsg *tm)
+{
+	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
+	struct nlattr *nest, *nla;
+
+	if (prog == NULL)
+		return skb->len;
+
+	tm->tcm_handle = prog->handle;
+
+	nest = nla_nest_start(skb, TCA_OPTIONS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
+		goto nla_put_failure;
+	if (nla_put_u16(skb, TCA_BPF_OPS_LEN, prog->bpf_len))
+		goto nla_put_failure;
+
+	nla = nla_reserve(skb, TCA_BPF_OPS, prog->bpf_len *
+			  sizeof(struct sock_filter));
+	if (nla == NULL)
+		goto nla_put_failure;
+
+        memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla));
+
+	if (tcf_exts_dump(skb, &prog->exts, &bpf_ext_map) < 0)
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	if (tcf_exts_dump_stats(skb, &prog->exts, &bpf_ext_map) < 0)
+		goto nla_put_failure;
+
+	return skb->len;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg)
+{
+	struct cls_bpf_head *head = tp->root;
+	struct cls_bpf_prog *prog;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (arg->count < arg->skip)
+			goto skip;
+		if (arg->fn(tp, (unsigned long) prog, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+skip:
+		arg->count++;
+	}
+}
+
+static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
+	.kind		=	"bpf",
+	.owner		=	THIS_MODULE,
+	.classify	=	cls_bpf_classify,
+	.init		=	cls_bpf_init,
+	.destroy	=	cls_bpf_destroy,
+	.get		=	cls_bpf_get,
+	.put		=	cls_bpf_put,
+	.change		=	cls_bpf_change,
+	.delete		=	cls_bpf_delete,
+	.walk		=	cls_bpf_walk,
+	.dump		=	cls_bpf_dump,
+};
+
+static int __init cls_bpf_init_mod(void)
+{
+	return register_tcf_proto_ops(&cls_bpf_ops);
+}
+
+static void __exit cls_bpf_exit_mod(void)
+{
+	unregister_tcf_proto_ops(&cls_bpf_ops);
+}
+
+module_init(cls_bpf_init_mod);
+module_exit(cls_bpf_exit_mod);
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 867b4a3..16006c9 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -72,11 +72,11 @@ static void cgrp_attach(struct cgroup_subsys_state *css,
 			struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
-	void *v;
+	struct cgroup_cls_state *cs = css_cls_state(css);
+	void *v = (void *)(unsigned long)cs->classid;
 
 	cgroup_taskset_for_each(p, css, tset) {
 		task_lock(p);
-		v = (void *)(unsigned long)task_cls_classid(p);
 		iterate_fd(p->files, 0, update_classid, v);
 		task_unlock(p);
 	}
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index 938b7cb..527aeb7 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -24,11 +24,12 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
 {
 	struct xt_set_info *set = data;
 	ip_set_id_t index;
+	struct net *net = dev_net(qdisc_dev(tp->q));
 
 	if (data_len != sizeof(*set))
 		return -EINVAL;
 
-	index = ip_set_nfnl_get_byindex(set->index);
+	index = ip_set_nfnl_get_byindex(net, set->index);
 	if (index == IPSET_INVALID_ID)
 		return -ENOENT;
 
@@ -37,7 +38,7 @@ static int em_ipset_change(struct tcf_proto *tp, void *data, int data_len,
 	if (em->data)
 		return 0;
 
-	ip_set_nfnl_put(index);
+	ip_set_nfnl_put(net, index);
 	return -ENOMEM;
 }
 
@@ -45,7 +46,7 @@ static void em_ipset_destroy(struct tcf_proto *p, struct tcf_ematch *em)
 {
 	const struct xt_set_info *set = (const void *) em->data;
 	if (set) {
-		ip_set_nfnl_put(set->index);
+		ip_set_nfnl_put(dev_net(qdisc_dev(p->q)), set->index);
 		kfree((void *) em->data);
 	}
 }
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 7c3de6f..e5cef956 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -793,8 +793,10 @@ static int em_meta_change(struct tcf_proto *tp, void *data, int len,
 		goto errout;
 
 	meta = kzalloc(sizeof(*meta), GFP_KERNEL);
-	if (meta == NULL)
+	if (meta == NULL) {
+		err = -ENOMEM;
 		goto errout;
+	}
 
 	memcpy(&meta->lvalue.hdr, &hdr->left, sizeof(hdr->left));
 	memcpy(&meta->rvalue.hdr, &hdr->right, sizeof(hdr->right));
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2adda7f..cd81505 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -737,9 +737,11 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
+	int drops;
 
 	if (n == 0)
 		return;
+	drops = max_t(int, n, 0);
 	while ((parentid = sch->parent)) {
 		if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
 			return;
@@ -756,6 +758,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
 			cops->put(sch, cl);
 		}
 		sch->q.qlen -= n;
+		sch->qstats.drops += drops;
 	}
 }
 EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a74e278..922a094 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-		ret = dev_hard_start_xmit(skb, dev, txq);
+		ret = dev_hard_start_xmit(skb, dev, txq, NULL);
 
 	HARD_TX_UNLOCK(dev, txq);
 
@@ -829,7 +829,7 @@ void dev_deactivate_many(struct list_head *head)
 	struct net_device *dev;
 	bool sync_needed = false;
 
-	list_for_each_entry(dev, head, unreg_list) {
+	list_for_each_entry(dev, head, close_list) {
 		netdev_for_each_tx_queue(dev, dev_deactivate_queue,
 					 &noop_qdisc);
 		if (dev_ingress_queue(dev))
@@ -848,7 +848,7 @@ void dev_deactivate_many(struct list_head *head)
 		synchronize_net();
 
 	/* Wait for outstanding qdisc_run calls. */
-	list_for_each_entry(dev, head, unreg_list)
+	list_for_each_entry(dev, head, close_list)
 		while (some_qdisc_is_busy(dev))
 			yield();
 }
@@ -857,7 +857,7 @@ void dev_deactivate(struct net_device *dev)
 {
 	LIST_HEAD(single);
 
-	list_add(&dev->unreg_list, &single);
+	list_add(&dev->close_list, &single);
 	dev_deactivate_many(&single);
 	list_del(&single);
 }
@@ -910,11 +910,12 @@ void dev_shutdown(struct net_device *dev)
 }
 
 void psched_ratecfg_precompute(struct psched_ratecfg *r,
-			       const struct tc_ratespec *conf)
+			       const struct tc_ratespec *conf,
+			       u64 rate64)
 {
 	memset(r, 0, sizeof(*r));
 	r->overhead = conf->overhead;
-	r->rate_bytes_ps = conf->rate;
+	r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
 	r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
 	r->mult = 1;
 	/*
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 863846c..0e1e38b 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -997,6 +997,8 @@ static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
 	[TCA_HTB_CTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_HTB_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_HTB_DIRECT_QLEN] = { .type = NLA_U32 },
+	[TCA_HTB_RATE64] = { .type = NLA_U64 },
+	[TCA_HTB_CEIL64] = { .type = NLA_U64 },
 };
 
 static void htb_work_func(struct work_struct *work)
@@ -1114,6 +1116,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
 	opt.level = cl->level;
 	if (nla_put(skb, TCA_HTB_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
+	if ((cl->rate.rate_bytes_ps >= (1ULL << 32)) &&
+	    nla_put_u64(skb, TCA_HTB_RATE64, cl->rate.rate_bytes_ps))
+		goto nla_put_failure;
+	if ((cl->ceil.rate_bytes_ps >= (1ULL << 32)) &&
+	    nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps))
+		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 	spin_unlock_bh(root_lock);
@@ -1332,6 +1340,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
 	struct nlattr *tb[TCA_HTB_MAX + 1];
 	struct tc_htb_opt *hopt;
+	u64 rate64, ceil64;
 
 	/* extract all subattrs from opt attr */
 	if (!opt)
@@ -1491,8 +1500,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			cl->prio = TC_HTB_NUMPRIO - 1;
 	}
 
-	psched_ratecfg_precompute(&cl->rate, &hopt->rate);
-	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
+	rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0;
+
+	ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0;
+
+	psched_ratecfg_precompute(&cl->rate, &hopt->rate, rate64);
+	psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64);
 
 	cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
 	cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b87e83d..75c94e5 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -235,7 +235,6 @@ static bool loss_4state(struct netem_sched_data *q)
 			clg->state = 2;
 		else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) {
 			clg->state = 1;
-			return true;
 		} else if (clg->a2 + clg->a3 < rnd) {
 			clg->state = 3;
 			return true;
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1aaf1b6..68f9859 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -266,20 +266,23 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
 	[TCA_TBF_PARMS]	= { .len = sizeof(struct tc_tbf_qopt) },
 	[TCA_TBF_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
 };
 
 static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	int err;
 	struct tbf_sched_data *q = qdisc_priv(sch);
-	struct nlattr *tb[TCA_TBF_PTAB + 1];
+	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
 	struct qdisc_rate_table *rtab = NULL;
 	struct qdisc_rate_table *ptab = NULL;
 	struct Qdisc *child = NULL;
 	int max_size, n;
+	u64 rate64 = 0, prate64 = 0;
 
-	err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy);
+	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
 	if (err < 0)
 		return err;
 
@@ -341,9 +344,13 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-	psched_ratecfg_precompute(&q->rate, &rtab->rate);
+	if (tb[TCA_TBF_RATE64])
+		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
+	psched_ratecfg_precompute(&q->rate, &rtab->rate, rate64);
 	if (ptab) {
-		psched_ratecfg_precompute(&q->peak, &ptab->rate);
+		if (tb[TCA_TBF_PRATE64])
+			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
+		psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64);
 		q->peak_present = true;
 	} else {
 		q->peak_present = false;
@@ -402,6 +409,13 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	opt.buffer = PSCHED_NS2TICKS(q->buffer);
 	if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
+	if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps))
+		goto nla_put_failure;
+	if (q->peak_present &&
+	    q->peak.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps))
+		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 	return skb->len;