nfs: disintegrate UAPI for nfs

This is to complete part of the Userspace API (UAPI) disintegration for which
the preparatory patches were pulled recently.  After these patches, userspace
headers will be segregated into:

        include/uapi/linux/.../foo.h

for the userspace interface stuff, and:

        include/linux/.../foo.h

for the strictly kernel internal stuff.

Signed-off-by: J. Bruce Fields <bfields@redhat.com>

19 files changed, 139 insertions, 129 deletions

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index e3d2c78..102761d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -644,7 +644,7 @@ errout:
 }
 
 static int
-tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq,
+tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 portid, u32 seq,
 	     u16 flags, int event, int bind, int ref)
 {
 	struct tcamsg *t;
@@ -652,7 +652,7 @@ tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq,
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*t), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
 	t = nlmsg_data(nlh);
@@ -678,7 +678,7 @@ out_nlmsg_trim:
 }
 
 static int
-act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n,
+act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
 	       struct tc_action *a, int event)
 {
 	struct sk_buff *skb;
@@ -686,16 +686,16 @@ act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n,
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
-	if (tca_get_fill(skb, a, pid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
+	if (tca_get_fill(skb, a, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
 
-	return rtnl_unicast(skb, net, pid);
+	return rtnl_unicast(skb, net, portid);
 }
 
 static struct tc_action *
-tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 pid)
+tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid)
 {
 	struct nlattr *tb[TCA_ACT_MAX + 1];
 	struct tc_action *a;
@@ -762,7 +762,7 @@ static struct tc_action *create_a(int i)
 }
 
 static int tca_action_flush(struct net *net, struct nlattr *nla,
-			    struct nlmsghdr *n, u32 pid)
+			    struct nlmsghdr *n, u32 portid)
 {
 	struct sk_buff *skb;
 	unsigned char *b;
@@ -799,7 +799,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	if (a->ops == NULL)
 		goto err_out;
 
-	nlh = nlmsg_put(skb, pid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0);
+	nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0);
 	if (!nlh)
 		goto out_module_put;
 	t = nlmsg_data(nlh);
@@ -823,7 +823,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	nlh->nlmsg_flags |= NLM_F_ROOT;
 	module_put(a->ops->owner);
 	kfree(a);
-	err = rtnetlink_send(skb, net, pid, RTNLGRP_TC,
+	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
 			     n->nlmsg_flags & NLM_F_ECHO);
 	if (err > 0)
 		return 0;
@@ -841,7 +841,7 @@ noflush_out:
 
 static int
 tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
-	      u32 pid, int event)
+	      u32 portid, int event)
 {
 	int i, ret;
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
@@ -853,13 +853,13 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 
 	if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) {
 		if (tb[1] != NULL)
-			return tca_action_flush(net, tb[1], n, pid);
+			return tca_action_flush(net, tb[1], n, portid);
 		else
 			return -EINVAL;
 	}
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
-		act = tcf_action_get_1(tb[i], n, pid);
+		act = tcf_action_get_1(tb[i], n, portid);
 		if (IS_ERR(act)) {
 			ret = PTR_ERR(act);
 			goto err;
@@ -874,7 +874,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	}
 
 	if (event == RTM_GETACTION)
-		ret = act_get_notify(net, pid, n, head, event);
+		ret = act_get_notify(net, portid, n, head, event);
 	else { /* delete */
 		struct sk_buff *skb;
 
@@ -884,7 +884,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 			goto err;
 		}
 
-		if (tca_get_fill(skb, head, pid, n->nlmsg_seq, 0, event,
+		if (tca_get_fill(skb, head, portid, n->nlmsg_seq, 0, event,
 				 0, 1) <= 0) {
 			kfree_skb(skb);
 			ret = -EINVAL;
@@ -893,7 +893,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 
 		/* now do the delete */
 		tcf_action_destroy(head, 0);
-		ret = rtnetlink_send(skb, net, pid, RTNLGRP_TC,
+		ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC,
 				     n->nlmsg_flags & NLM_F_ECHO);
 		if (ret > 0)
 			return 0;
@@ -905,7 +905,7 @@ err:
 }
 
 static int tcf_add_notify(struct net *net, struct tc_action *a,
-			  u32 pid, u32 seq, int event, u16 flags)
+			  u32 portid, u32 seq, int event, u16 flags)
 {
 	struct tcamsg *t;
 	struct nlmsghdr *nlh;
@@ -920,7 +920,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a,
 
 	b = skb_tail_pointer(skb);
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*t), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags);
 	if (!nlh)
 		goto out_kfree_skb;
 	t = nlmsg_data(nlh);
@@ -940,7 +940,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a,
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	NETLINK_CB(skb).dst_group = RTNLGRP_TC;
 
-	err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags & NLM_F_ECHO);
+	err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
 	if (err > 0)
 		err = 0;
 	return err;
@@ -953,7 +953,7 @@ out_kfree_skb:
 
 static int
 tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
-	       u32 pid, int ovr)
+	       u32 portid, int ovr)
 {
 	int ret = 0;
 	struct tc_action *act;
@@ -971,7 +971,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	/* dump then free all the actions after update; inserted policy
 	 * stays intact
 	 */
-	ret = tcf_add_notify(net, act, pid, seq, RTM_NEWACTION, n->nlmsg_flags);
+	ret = tcf_add_notify(net, act, portid, seq, RTM_NEWACTION, n->nlmsg_flags);
 	for (a = act; a; a = act) {
 		act = a->next;
 		kfree(a);
@@ -984,7 +984,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_ACT_MAX + 1];
-	u32 pid = skb ? NETLINK_CB(skb).pid : 0;
+	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
 	int ret = 0, ovr = 0;
 
 	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
@@ -1008,17 +1008,17 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
 replay:
-		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, pid, ovr);
+		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr);
 		if (ret == -EAGAIN)
 			goto replay;
 		break;
 	case RTM_DELACTION:
 		ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
-				    pid, RTM_DELACTION);
+				    portid, RTM_DELACTION);
 		break;
 	case RTM_GETACTION:
 		ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
-				    pid, RTM_GETACTION);
+				    portid, RTM_GETACTION);
 		break;
 	default:
 		BUG();
@@ -1085,7 +1085,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
 		goto out_module_put;
 	}
 
-	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq,
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
 			cb->nlh->nlmsg_type, sizeof(*t), 0);
 	if (!nlh)
 		goto out_module_put;
@@ -1109,7 +1109,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
 		nla_nest_cancel(skb, nest);
 
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
-	if (NETLINK_CB(cb->skb).pid && ret)
+	if (NETLINK_CB(cb->skb).portid && ret)
 		nlh->nlmsg_flags |= NLM_F_MULTI;
 	module_put(a_o->owner);
 	return skb->len;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index fe81cc1..9c0fd0c 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -200,13 +200,12 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 out:
 	if (err) {
 		m->tcf_qstats.overlimits++;
-		/* should we be asking for packet to be dropped?
-		 * may make sense for redirect case only
-		 */
-		retval = TC_ACT_SHOT;
-	} else {
+		if (m->tcfm_eaction != TCA_EGRESS_MIRROR)
+			retval = TC_ACT_SHOT;
+		else
+			retval = m->tcf_action;
+	} else
 		retval = m->tcf_action;
-	}
 	spin_unlock(&m->tcf_lock);
 
 	return retval;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 6dd1131..7ae0289 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -319,7 +319,7 @@ replay:
 		}
 	}
 
-	err = tp->ops->change(tp, cl, t->tcm_handle, tca, &fh);
+	err = tp->ops->change(skb, tp, cl, t->tcm_handle, tca, &fh);
 	if (err == 0) {
 		if (tp_created) {
 			spin_lock_bh(root_lock);
@@ -343,13 +343,13 @@ errout:
 }
 
 static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp,
-			 unsigned long fh, u32 pid, u32 seq, u16 flags, int event)
+			 unsigned long fh, u32 portid, u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
 	tcm = nlmsg_data(nlh);
@@ -381,18 +381,18 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 			  unsigned long fh, int event)
 {
 	struct sk_buff *skb;
-	u32 pid = oskb ? NETLINK_CB(oskb).pid : 0;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
 
-	if (tcf_fill_node(skb, tp, fh, pid, n->nlmsg_seq, 0, event) <= 0) {
+	if (tcf_fill_node(skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
 
-	return rtnetlink_send(skb, net, pid, RTNLGRP_TC,
+	return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
 			      n->nlmsg_flags & NLM_F_ECHO);
 }
 
@@ -407,7 +407,7 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n,
 {
 	struct tcf_dump_args *a = (void *)arg;
 
-	return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).pid,
+	return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).portid,
 			     a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER);
 }
 
@@ -465,7 +465,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 		if (t > s_t)
 			memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).pid,
+			if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
 				break;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 590960a..344a11b 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -162,7 +162,8 @@ errout:
 	return err;
 }
 
-static int basic_change(struct tcf_proto *tp, unsigned long base, u32 handle,
+static int basic_change(struct sk_buff *in_skb,
+			struct tcf_proto *tp, unsigned long base, u32 handle,
 			struct nlattr **tca, unsigned long *arg)
 {
 	int err;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 7743ea8..2ecde22 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -77,11 +77,18 @@ struct cgroup_subsys net_cls_subsys = {
 	.name		= "net_cls",
 	.create		= cgrp_create,
 	.destroy	= cgrp_destroy,
-#ifdef CONFIG_NET_CLS_CGROUP
 	.subsys_id	= net_cls_subsys_id,
-#endif
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
+
+	/*
+	 * While net_cls cgroup has the rudimentary hierarchy support of
+	 * inheriting the parent's classid on cgroup creation, it doesn't
+	 * properly propagates config changes in ancestors to their
+	 * descendents.  A child should follow the parent's configuration
+	 * but be allowed to override it.  Fix it and remove the following.
+	 */
+	.broken_hierarchy = true,
 };
 
 struct cls_cgroup_head {
@@ -151,7 +158,8 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
 	[TCA_CGROUP_EMATCHES]	= { .type = NLA_NESTED },
 };
 
-static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base,
+static int cls_cgroup_change(struct sk_buff *in_skb,
+			     struct tcf_proto *tp, unsigned long base,
 			     u32 handle, struct nlattr **tca,
 			     unsigned long *arg)
 {
@@ -283,12 +291,6 @@ static int __init init_cgroup_cls(void)
 	if (ret)
 		goto out;
 
-#ifndef CONFIG_NET_CLS_CGROUP
-	/* We can't use rcu_assign_pointer because this is an int. */
-	smp_wmb();
-	net_cls_subsys_id = net_cls_subsys.subsys_id;
-#endif
-
 	ret = register_tcf_proto_ops(&cls_cgroup_ops);
 	if (ret)
 		cgroup_unload_subsys(&net_cls_subsys);
@@ -301,11 +303,6 @@ static void __exit exit_cgroup_cls(void)
 {
 	unregister_tcf_proto_ops(&cls_cgroup_ops);
 
-#ifndef CONFIG_NET_CLS_CGROUP
-	net_cls_subsys_id = -1;
-	synchronize_rcu();
-#endif
-
 	cgroup_unload_subsys(&net_cls_subsys);
 }
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index ccd08c8..ce82d0c 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -193,15 +193,19 @@ static u32 flow_get_rtclassid(const struct sk_buff *skb)
 
 static u32 flow_get_skuid(const struct sk_buff *skb)
 {
-	if (skb->sk && skb->sk->sk_socket && skb->sk->sk_socket->file)
-		return skb->sk->sk_socket->file->f_cred->fsuid;
+	if (skb->sk && skb->sk->sk_socket && skb->sk->sk_socket->file) {
+		kuid_t skuid = skb->sk->sk_socket->file->f_cred->fsuid;
+		return from_kuid(&init_user_ns, skuid);
+	}
 	return 0;
 }
 
 static u32 flow_get_skgid(const struct sk_buff *skb)
 {
-	if (skb->sk && skb->sk->sk_socket && skb->sk->sk_socket->file)
-		return skb->sk->sk_socket->file->f_cred->fsgid;
+	if (skb->sk && skb->sk->sk_socket && skb->sk->sk_socket->file) {
+		kgid_t skgid = skb->sk->sk_socket->file->f_cred->fsgid;
+		return from_kgid(&init_user_ns, skgid);
+	}
 	return 0;
 }
 
@@ -347,7 +351,8 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = {
 	[TCA_FLOW_PERTURB]	= { .type = NLA_U32 },
 };
 
-static int flow_change(struct tcf_proto *tp, unsigned long base,
+static int flow_change(struct sk_buff *in_skb, 
+		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle, struct nlattr **tca,
 		       unsigned long *arg)
 {
@@ -386,6 +391,10 @@ static int flow_change(struct tcf_proto *tp, unsigned long base,
 
 		if (fls(keymask) - 1 > FLOW_KEY_MAX)
 			return -EOPNOTSUPP;
+
+		if ((keymask & (FLOW_KEY_SKUID|FLOW_KEY_SKGID)) &&
+		    sk_user_ns(NETLINK_CB(in_skb).ssk) != &init_user_ns)
+			return -EOPNOTSUPP;
 	}
 
 	err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &flow_ext_map);
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 8384a47..4075a0ae 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -233,7 +233,8 @@ errout:
 	return err;
 }
 
-static int fw_change(struct tcf_proto *tp, unsigned long base,
+static int fw_change(struct sk_buff *in_skb,
+		     struct tcf_proto *tp, unsigned long base,
 		     u32 handle,
 		     struct nlattr **tca,
 		     unsigned long *arg)
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 44f405c..c10d57b 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -427,7 +427,8 @@ errout:
 	return err;
 }
 
-static int route4_change(struct tcf_proto *tp, unsigned long base,
+static int route4_change(struct sk_buff *in_skb,
+		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle,
 		       struct nlattr **tca,
 		       unsigned long *arg)
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 18ab93e..494bbb9 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -416,7 +416,8 @@ static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
 	[TCA_RSVP_PINFO]	= { .len = sizeof(struct tc_rsvp_pinfo) },
 };
 
-static int rsvp_change(struct tcf_proto *tp, unsigned long base,
+static int rsvp_change(struct sk_buff *in_skb,
+		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle,
 		       struct nlattr **tca,
 		       unsigned long *arg)
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index fe29420..a1293b4 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -332,7 +332,8 @@ errout:
 }
 
 static int
-tcindex_change(struct tcf_proto *tp, unsigned long base, u32 handle,
+tcindex_change(struct sk_buff *in_skb,
+	       struct tcf_proto *tp, unsigned long base, u32 handle,
 	       struct nlattr **tca, unsigned long *arg)
 {
 	struct nlattr *opt = tca[TCA_OPTIONS];
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index d45373f..c7c27bc 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -544,7 +544,8 @@ errout:
 	return err;
 }
 
-static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle,
+static int u32_change(struct sk_buff *in_skb,
+		      struct tcf_proto *tp, unsigned long base, u32 handle,
 		      struct nlattr **tca,
 		      unsigned long *arg)
 {
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 4ab6e33..7c3de6f 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -461,7 +461,7 @@ META_COLLECTOR(int_sk_sndtimeo)
 META_COLLECTOR(int_sk_sendmsg_off)
 {
 	SKIP_NONLOCAL(skb);
-	dst->value = skb->sk->sk_sndmsg_off;
+	dst->value = skb->sk->sk_frag.offset;
 }
 
 META_COLLECTOR(int_sk_write_pend)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index a08b4ab..a18d975 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1185,7 +1185,7 @@ graft:
 }
 
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
-			 u32 pid, u32 seq, u16 flags, int event)
+			 u32 portid, u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
@@ -1193,7 +1193,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	struct gnet_dump d;
 	struct qdisc_size_table *stab;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
 	tcm = nlmsg_data(nlh);
@@ -1248,25 +1248,25 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
 			struct Qdisc *old, struct Qdisc *new)
 {
 	struct sk_buff *skb;
-	u32 pid = oskb ? NETLINK_CB(oskb).pid : 0;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
 
 	if (old && !tc_qdisc_dump_ignore(old)) {
-		if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq,
+		if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq,
 				  0, RTM_DELQDISC) < 0)
 			goto err_out;
 	}
 	if (new && !tc_qdisc_dump_ignore(new)) {
-		if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq,
+		if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq,
 				  old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
 			goto err_out;
 	}
 
 	if (skb->len)
-		return rtnetlink_send(skb, net, pid, RTNLGRP_TC,
+		return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
 				      n->nlmsg_flags & NLM_F_ECHO);
 
 err_out:
@@ -1289,7 +1289,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 		q_idx++;
 	} else {
 		if (!tc_qdisc_dump_ignore(q) &&
-		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid,
+		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0)
 			goto done;
 		q_idx++;
@@ -1300,7 +1300,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 			continue;
 		}
 		if (!tc_qdisc_dump_ignore(q) &&
-		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid,
+		    tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0)
 			goto done;
 		q_idx++;
@@ -1375,7 +1375,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl = 0;
 	unsigned long new_cl;
-	u32 pid = tcm->tcm_parent;
+	u32 portid = tcm->tcm_parent;
 	u32 clid = tcm->tcm_handle;
 	u32 qid = TC_H_MAJ(clid);
 	int err;
@@ -1403,8 +1403,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 
 	/* Step 1. Determine qdisc handle X:0 */
 
-	if (pid != TC_H_ROOT) {
-		u32 qid1 = TC_H_MAJ(pid);
+	if (portid != TC_H_ROOT) {
+		u32 qid1 = TC_H_MAJ(portid);
 
 		if (qid && qid1) {
 			/* If both majors are known, they must be identical. */
@@ -1418,10 +1418,10 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 		/* Now qid is genuine qdisc handle consistent
 		 * both with parent and child.
 		 *
-		 * TC_H_MAJ(pid) still may be unspecified, complete it now.
+		 * TC_H_MAJ(portid) still may be unspecified, complete it now.
 		 */
-		if (pid)
-			pid = TC_H_MAKE(qid, pid);
+		if (portid)
+			portid = TC_H_MAKE(qid, portid);
 	} else {
 		if (qid == 0)
 			qid = dev->qdisc->handle;
@@ -1439,7 +1439,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 
 	/* Now try to get class */
 	if (clid == 0) {
-		if (pid == TC_H_ROOT)
+		if (portid == TC_H_ROOT)
 			clid = qid;
 	} else
 		clid = TC_H_MAKE(qid, clid);
@@ -1478,7 +1478,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
 	new_cl = cl;
 	err = -EOPNOTSUPP;
 	if (cops->change)
-		err = cops->change(q, clid, pid, tca, &new_cl);
+		err = cops->change(q, clid, portid, tca, &new_cl);
 	if (err == 0)
 		tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS);
 
@@ -1492,7 +1492,7 @@ out:
 
 static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
 			  unsigned long cl,
-			  u32 pid, u32 seq, u16 flags, int event)
+			  u32 portid, u32 seq, u16 flags, int event)
 {
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
@@ -1500,7 +1500,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q,
 	struct gnet_dump d;
 	const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops;
 
-	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags);
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
 		goto out_nlmsg_trim;
 	tcm = nlmsg_data(nlh);
@@ -1540,18 +1540,18 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb,
 			 unsigned long cl, int event)
 {
 	struct sk_buff *skb;
-	u32 pid = oskb ? NETLINK_CB(oskb).pid : 0;
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb)
 		return -ENOBUFS;
 
-	if (tc_fill_tclass(skb, q, cl, pid, n->nlmsg_seq, 0, event) < 0) {
+	if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
 
-	return rtnetlink_send(skb, net, pid, RTNLGRP_TC,
+	return rtnetlink_send(skb, net, portid, RTNLGRP_TC,
 			      n->nlmsg_flags & NLM_F_ECHO);
 }
 
@@ -1565,7 +1565,7 @@ static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walk
 {
 	struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg;
 
-	return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).pid,
+	return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid,
 			      a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS);
 }
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 6aabd77..564b9fc 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -250,10 +250,11 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 			else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL)
 				cl = defmap[TC_PRIO_BESTEFFORT];
 
-			if (cl == NULL || cl->level >= head->level)
+			if (cl == NULL)
 				goto fallback;
 		}
-
+		if (cl->level >= head->level)
+			goto fallback;
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
 		case TC_ACT_QUEUED:
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 9ce0b4f..71e50c8 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -352,7 +352,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct drr_sched *q = qdisc_priv(sch);
 	struct drr_class *cl;
-	int err;
+	int err = 0;
 
 	cl = drr_classify(skb, sch, &err);
 	if (cl == NULL) {
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 9fc1c62..4e606fc 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -191,7 +191,6 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 
 	if (list_empty(&flow->flowchain)) {
 		list_add_tail(&flow->flowchain, &q->new_flows);
-		codel_vars_init(&flow->cvars);
 		q->new_flow_count++;
 		flow->deficit = q->quantum;
 		flow->dropped = 0;
@@ -418,6 +417,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 			struct fq_codel_flow *flow = q->flows + i;
 
 			INIT_LIST_HEAD(&flow->flowchain);
+			codel_vars_init(&flow->cvars);
 		}
 	}
 	if (sch->limit >= 1)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 511323e..aefc150 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -324,24 +324,6 @@ void netif_carrier_off(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_carrier_off);
 
-/**
- * 	netif_notify_peers - notify network peers about existence of @dev
- * 	@dev: network device
- *
- * Generate traffic such that interested network peers are aware of
- * @dev, such as by generating a gratuitous ARP. This may be used when
- * a device wants to inform the rest of the network about some sort of
- * reconfiguration such as a failover event or virtual machine
- * migration.
- */
-void netif_notify_peers(struct net_device *dev)
-{
-	rtnl_lock();
-	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
-	rtnl_unlock();
-}
-EXPORT_SYMBOL(netif_notify_peers);
-
 /* "NOOP" scheduler: the best scheduler, recommended for all interfaces
    under all circumstances. It is difficult to invent anything faster or
    cheaper.
@@ -545,6 +527,8 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 };
 EXPORT_SYMBOL(pfifo_fast_ops);
 
+static struct lock_class_key qdisc_tx_busylock;
+
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  struct Qdisc_ops *ops)
 {
@@ -552,6 +536,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	struct Qdisc *sch;
 	unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
 	int err = -ENOBUFS;
+	struct net_device *dev = dev_queue->dev;
 
 	p = kzalloc_node(size, GFP_KERNEL,
 			 netdev_queue_numa_node_read(dev_queue));
@@ -571,12 +556,16 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	}
 	INIT_LIST_HEAD(&sch->list);
 	skb_queue_head_init(&sch->q);
+
 	spin_lock_init(&sch->busylock);
+	lockdep_set_class(&sch->busylock,
+			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+
 	sch->ops = ops;
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
 	sch->dev_queue = dev_queue;
-	dev_hold(qdisc_dev(sch));
+	dev_hold(dev);
 	atomic_set(&sch->refcnt, 1);
 
 	return sch;
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index e901583..d42234c 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -102,9 +102,8 @@ static inline int gred_wred_mode_check(struct Qdisc *sch)
 		if (q == NULL)
 			continue;
 
-		for (n = 0; n < table->DPs; n++)
-			if (table->tab[n] && table->tab[n] != q &&
-			    table->tab[n]->prio == q->prio)
+		for (n = i + 1; n < table->DPs; n++)
+			if (table->tab[n] && table->tab[n]->prio == q->prio)
 				return 1;
 	}
 
@@ -137,6 +136,7 @@ static inline void gred_store_wred_set(struct gred_sched *table,
 				       struct gred_sched_data *q)
 {
 	table->wred_set.qavg = q->vars.qavg;
+	table->wred_set.qidlestart = q->vars.qidlestart;
 }
 
 static inline int gred_use_ecn(struct gred_sched *t)
@@ -176,7 +176,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		skb->tc_index = (skb->tc_index & ~GRED_VQ_MASK) | dp;
 	}
 
-	/* sum up all the qaves of prios <= to ours to get the new qave */
+	/* sum up all the qaves of prios < ours to get the new qave */
 	if (!gred_wred_mode(t) && gred_rio_mode(t)) {
 		int i;
 
@@ -260,16 +260,18 @@ static struct sk_buff *gred_dequeue(struct Qdisc *sch)
 		} else {
 			q->backlog -= qdisc_pkt_len(skb);
 
-			if (!q->backlog && !gred_wred_mode(t))
-				red_start_of_idle_period(&q->vars);
+			if (gred_wred_mode(t)) {
+				if (!sch->qstats.backlog)
+					red_start_of_idle_period(&t->wred_set);
+			} else {
+				if (!q->backlog)
+					red_start_of_idle_period(&q->vars);
+			}
 		}
 
 		return skb;
 	}
 
-	if (gred_wred_mode(t) && !red_is_idling(&t->wred_set))
-		red_start_of_idle_period(&t->wred_set);
-
 	return NULL;
 }
 
@@ -291,19 +293,20 @@ static unsigned int gred_drop(struct Qdisc *sch)
 			q->backlog -= len;
 			q->stats.other++;
 
-			if (!q->backlog && !gred_wred_mode(t))
-				red_start_of_idle_period(&q->vars);
+			if (gred_wred_mode(t)) {
+				if (!sch->qstats.backlog)
+					red_start_of_idle_period(&t->wred_set);
+			} else {
+				if (!q->backlog)
+					red_start_of_idle_period(&q->vars);
+			}
 		}
 
 		qdisc_drop(skb, sch);
 		return len;
 	}
 
-	if (gred_wred_mode(t) && !red_is_idling(&t->wred_set))
-		red_start_of_idle_period(&t->wred_set);
-
 	return 0;
-
 }
 
 static void gred_reset(struct Qdisc *sch)
@@ -535,6 +538,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 	for (i = 0; i < MAX_DPs; i++) {
 		struct gred_sched_data *q = table->tab[i];
 		struct tc_gred_qopt opt;
+		unsigned long qavg;
 
 		memset(&opt, 0, sizeof(opt));
 
@@ -566,7 +570,9 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 		if (gred_wred_mode(table))
 			gred_load_wred_set(table, q);
 
-		opt.qave = red_calc_qavg(&q->parms, &q->vars, q->vars.qavg);
+		qavg = red_calc_qavg(&q->parms, &q->vars,
+				     q->vars.qavg >> q->parms.Wlog);
+		opt.qave = qavg >> q->parms.Wlog;
 
 append_opt:
 		if (nla_append(skb, sizeof(opt), &opt) < 0)
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index e4723d3..f0dd83c 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -865,7 +865,10 @@ static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl)
 		if (mask) {
 			struct qfq_group *next = qfq_ffs(q, mask);
 			if (qfq_gt(roundedF, next->F)) {
-				cl->S = next->F;
+				if (qfq_gt(limit, next->F))
+					cl->S = next->F;
+				else /* preserve timestamp correctness */
+					cl->S = limit;
 				return;
 			}
 		}
@@ -878,7 +881,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl;
-	int err;
+	int err = 0;
 
 	cl = qfq_classify(skb, sch, &err);
 	if (cl == NULL) {