From 4b61d3e8d3daebbde7ec02d593f84248fdf8bec2 Mon Sep 17 00:00:00 2001
From: Po Liu <Po.Liu@nxp.com>
Date: Fri, 19 Jun 2020 14:01:07 +0800
Subject: net: qos offload add flow status with dropped count

This patch adds a drop frames counter to tc flower offloading.
Reporting h/w dropped frames is necessary for some actions.
Some actions like police action and the coming introduced stream gate
action would produce dropped frames which is necessary for user. Status
update shows how many filtered packets increasing and how many dropped
in those packets.

v2: Changes
 - Update commit comments suggest by Jiri Pirko.

Signed-off-by: Po Liu <Po.Liu@nxp.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c      | 10 ++++------
 net/sched/act_ct.c       |  6 +++---
 net/sched/act_gact.c     |  7 ++++---
 net/sched/act_gate.c     |  6 +++---
 net/sched/act_mirred.c   |  6 +++---
 net/sched/act_pedit.c    |  6 +++---
 net/sched/act_police.c   |  4 ++--
 net/sched/act_skbedit.c  |  5 +++--
 net/sched/act_vlan.c     |  6 +++---
 net/sched/cls_flower.c   |  1 +
 net/sched/cls_matchall.c |  3 ++-
 11 files changed, 31 insertions(+), 29 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 8ac7eb0a8309..4c4466f18801 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1059,14 +1059,13 @@ err:
 	return err;
 }
 
-void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets,
-			     bool drop, bool hw)
+void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets,
+			     u64 drops, bool hw)
 {
 	if (a->cpu_bstats) {
 		_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets);
 
-		if (drop)
-			this_cpu_ptr(a->cpu_qstats)->drops += packets;
+		this_cpu_ptr(a->cpu_qstats)->drops += drops;
 
 		if (hw)
 			_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw),
@@ -1075,8 +1074,7 @@ void tcf_action_update_stats(struct tc_action *a, u64 bytes, u32 packets,
 	}
 
 	_bstats_update(&a->tcfa_bstats, bytes, packets);
-	if (drop)
-		a->tcfa_qstats.drops += packets;
+	a->tcfa_qstats.drops += drops;
 	if (hw)
 		_bstats_update(&a->tcfa_bstats_hw, bytes, packets);
 }
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index e9f3576cbf71..1b9c6d4a1b6b 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -1450,12 +1450,12 @@ static int tcf_ct_search(struct net *net, struct tc_action **a, u32 index)
 	return tcf_idr_search(tn, a, index);
 }
 
-static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-			     u64 lastuse, bool hw)
+static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+			     u64 drops, u64 lastuse, bool hw)
 {
 	struct tcf_ct *c = to_ct(a);
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
 }
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 416065772719..410e3bbfb9ca 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -171,14 +171,15 @@ static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
 	return action;
 }
 
-static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-				  u64 lastuse, bool hw)
+static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+				  u64 drops, u64 lastuse, bool hw)
 {
 	struct tcf_gact *gact = to_gact(a);
 	int action = READ_ONCE(gact->tcf_action);
 	struct tcf_t *tm = &gact->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, action == TC_ACT_SHOT, hw);
+	tcf_action_update_stats(a, bytes, packets,
+				action == TC_ACT_SHOT ? packets : drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 9c628591f452..c818844846b1 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -568,13 +568,13 @@ static int tcf_gate_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
-static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-				  u64 lastuse, bool hw)
+static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+				  u64 drops, u64 lastuse, bool hw)
 {
 	struct tcf_gate *gact = to_gate(a);
 	struct tcf_t *tm = &gact->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 83dd82fc9f40..b2705318993b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -312,13 +312,13 @@ out:
 	return retval;
 }
 
-static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-			     u64 lastuse, bool hw)
+static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+			     u64 drops, u64 lastuse, bool hw)
 {
 	struct tcf_mirred *m = to_mirred(a);
 	struct tcf_t *tm = &m->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index d41d6200d9de..66986db062ed 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -409,13 +409,13 @@ done:
 	return p->tcf_action;
 }
 
-static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-				   u64 lastuse, bool hw)
+static void tcf_pedit_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+				   u64 drops, u64 lastuse, bool hw)
 {
 	struct tcf_pedit *d = to_pedit(a);
 	struct tcf_t *tm = &d->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 8b7a0ac96c51..0b431d493768 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -288,13 +288,13 @@ static void tcf_police_cleanup(struct tc_action *a)
 }
 
 static void tcf_police_stats_update(struct tc_action *a,
-				    u64 bytes, u32 packets,
+				    u64 bytes, u64 packets, u64 drops,
 				    u64 lastuse, bool hw)
 {
 	struct tcf_police *police = to_police(a);
 	struct tcf_t *tm = &police->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index b125b2be4467..361b863e0634 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -74,12 +74,13 @@ err:
 }
 
 static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes,
-				     u32 packets, u64 lastuse, bool hw)
+				     u64 packets, u64 drops,
+				     u64 lastuse, bool hw)
 {
 	struct tcf_skbedit *d = to_skbedit(a);
 	struct tcf_t *tm = &d->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index c91d3958fcbb..a5ff9f68ab02 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -302,13 +302,13 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb,
 	return tcf_generic_walker(tn, skb, cb, type, ops, extack);
 }
 
-static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u32 packets,
-				  u64 lastuse, bool hw)
+static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets,
+				  u64 drops, u64 lastuse, bool hw)
 {
 	struct tcf_vlan *v = to_vlan(a);
 	struct tcf_t *tm = &v->tcf_tm;
 
-	tcf_action_update_stats(a, bytes, packets, false, hw);
+	tcf_action_update_stats(a, bytes, packets, drops, hw);
 	tm->lastuse = max_t(u64, tm->lastuse, lastuse);
 }
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index b2da37286082..391971672d54 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -491,6 +491,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
 
 	tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes,
 			      cls_flower.stats.pkts,
+			      cls_flower.stats.drops,
 			      cls_flower.stats.lastused,
 			      cls_flower.stats.used_hw_stats,
 			      cls_flower.stats.used_hw_stats_valid);
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 8d39dbcf1746..cafb84480bab 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -338,7 +338,8 @@ static void mall_stats_hw_filter(struct tcf_proto *tp,
 	tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false, true);
 
 	tcf_exts_stats_update(&head->exts, cls_mall.stats.bytes,
-			      cls_mall.stats.pkts, cls_mall.stats.lastused,
+			      cls_mall.stats.pkts, cls_mall.stats.drops,
+			      cls_mall.stats.lastused,
 			      cls_mall.stats.used_hw_stats,
 			      cls_mall.stats.used_hw_stats_valid);
 }
-- 
cgit v1.2.3


From 11a33de2df06b4ed23844181cb5c03eea67bfed1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 18 Jun 2020 09:46:48 -0500
Subject: taprio: Use struct_size() in kzalloc()

Make use of the struct_size() helper instead of an open-coded version
in order to avoid any potential type mistakes. Also, remove unnecessary
variable _size_.

This code was detected with the help of Coccinelle and, audited and
fixed manually.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index b1eb12d33b9a..e981992634dd 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1108,11 +1108,10 @@ static void setup_txtime(struct taprio_sched *q,
 
 static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries)
 {
-	size_t size = sizeof(struct tc_taprio_sched_entry) * num_entries +
-		      sizeof(struct __tc_taprio_qopt_offload);
 	struct __tc_taprio_qopt_offload *__offload;
 
-	__offload = kzalloc(size, GFP_KERNEL);
+	__offload = kzalloc(struct_size(__offload, offload.entries, num_entries),
+			    GFP_KERNEL);
 	if (!__offload)
 		return NULL;
 
-- 
cgit v1.2.3


From c5eb179edd8a169949b1fb153ecfd04649a71c8d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 18 Jun 2020 09:53:42 -0500
Subject: net/sched: cls_u32: Use struct_size() in kzalloc()

Make use of the struct_size() helper instead of an open-coded version
in order to avoid any potential type mistakes.

This code was detected with the help of Coccinelle and, audited and
fixed manually.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index e15ff335953d..771b068f8254 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -796,9 +796,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 	struct tc_u32_sel *s = &n->sel;
 	struct tc_u_knode *new;
 
-	new = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key),
-		      GFP_KERNEL);
-
+	new = kzalloc(struct_size(new, sel.keys, s->nkeys), GFP_KERNEL);
 	if (!new)
 		return NULL;
 
-- 
cgit v1.2.3


From 8eaf8d99409009b7ab7853f3ac603928458c2022 Mon Sep 17 00:00:00 2001
From: Gaurav Singh <gaurav1086@gmail.com>
Date: Thu, 18 Jun 2020 16:36:31 -0400
Subject: Remove redundant condition in qdisc_graft

parent cannot be NULL here since its in the else part
of the if (parent == NULL) condition. Remove the extra
check on parent pointer.

Signed-off-by: Gaurav Singh <gaurav1086@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 9a3449b56bd6..11ebba60da3b 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1093,8 +1093,7 @@ skip:
 		int err;
 
 		/* Only support running class lockless if parent is lockless */
-		if (new && (new->flags & TCQ_F_NOLOCK) &&
-		    parent && !(parent->flags & TCQ_F_NOLOCK))
+		if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK))
 			qdisc_clear_nolock(new);
 
 		if (!cops || !cops->graft)
-- 
cgit v1.2.3


From 8bf1539515920810b86cf1783dc433b1a25d31df Mon Sep 17 00:00:00 2001
From: Gaurav Singh <gaurav1086@gmail.com>
Date: Fri, 19 Jun 2020 15:24:13 -0400
Subject: Remove redundant skb null check

Remove the redundant null check for skb.

Signed-off-by: Gaurav Singh <gaurav1086@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/sched')

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 4c4466f18801..063d8aaf2900 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1473,7 +1473,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_ROOT_MAX + 1];
-	u32 portid = skb ? NETLINK_CB(skb).portid : 0;
+	u32 portid = NETLINK_CB(skb).portid;
 	int ret = 0, ovr = 0;
 
 	if ((n->nlmsg_type != RTM_GETACTION) &&
-- 
cgit v1.2.3


From c5efcf17bf84b20dd76ca56de6dd99a40a89c4e3 Mon Sep 17 00:00:00 2001
From: Gaurav Singh <gaurav1086@gmail.com>
Date: Sun, 21 Jun 2020 22:24:30 -0400
Subject: tcindex_change: Remove redundant null check

arg cannot be NULL since its already being dereferenced
before. Remove the redundant NULL check.

Signed-off-by: Gaurav Singh <gaurav1086@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/sched')

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 61e95029c18f..78bec347b8b6 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -533,7 +533,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 
 	pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p,"
 	    "p %p,r %p,*arg %p\n",
-	    tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL);
+	    tp, handle, tca, arg, opt, p, r, *arg);
 
 	if (!opt)
 		return 0;
-- 
cgit v1.2.3


From 19e528dc9af29169fa7cdfa61071805fdef504c6 Mon Sep 17 00:00:00 2001
From: Po Liu <Po.Liu@nxp.com>
Date: Wed, 24 Jun 2020 17:36:28 +0800
Subject: net: qos: add tc police offloading action with max frame size limit

Current police offloading support the 'burst'' and 'rate_bytes_ps'. Some
hardware own the capability to limit the frame size. If the frame size
larger than the setting, the frame would be dropped. For the police
action itself already accept the 'mtu' parameter in tc command. But not
extend to tc flower offloading. So extend 'mtu' to tc flower offloading.

Signed-off-by: Po Liu <Po.Liu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'net/sched')

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a00a203b2ef5..6aba7d5ba1ec 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3658,6 +3658,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->police.burst = tcf_police_tcfp_burst(act);
 			entry->police.rate_bytes_ps =
 				tcf_police_rate_bytes_ps(act);
+			entry->police.mtu = tcf_police_tcfp_mtu(act);
 		} else if (is_tcf_ct(act)) {
 			entry->id = FLOW_ACTION_CT;
 			entry->ct.action = tcf_ct_action(act);
-- 
cgit v1.2.3


From 627e39b1399e72e53895eec6bbec30199ed43de2 Mon Sep 17 00:00:00 2001
From: Po Liu <Po.Liu@nxp.com>
Date: Wed, 24 Jun 2020 17:36:30 +0800
Subject: net: qos: police action add index for tc flower offloading

Hardware device may include more than one police entry. Specifying the
action's index make it possible for several tc filters to share the same
police action when installing the filters.

Propagate this index to device drivers through the flow offload
intermediate representation, so that drivers could share a single
hardware policer between multiple filters.

v1->v2 changes:
- Update the commit message suggest by Ido Schimmel <idosch@idosch.org>

Signed-off-by: Po Liu <Po.Liu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'net/sched')

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 6aba7d5ba1ec..fdc4c89ca1fa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3659,6 +3659,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->police.rate_bytes_ps =
 				tcf_police_rate_bytes_ps(act);
 			entry->police.mtu = tcf_police_tcfp_mtu(act);
+			entry->police.index = act->tcfa_index;
 		} else if (is_tcf_ct(act)) {
 			entry->id = FLOW_ACTION_CT;
 			entry->ct.action = tcf_ct_action(act);
-- 
cgit v1.2.3


From b8392808eb3fc28e523e28cb258c81ca246deb9b Mon Sep 17 00:00:00 2001
From: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
Date: Thu, 25 Jun 2020 22:18:00 +0200
Subject: sch_cake: add RFC 8622 LE PHB support to CAKE diffserv handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Change tin mapping on diffserv3, 4 & 8 for LE PHB support, in essence
making LE a member of the Bulk tin.

Bulk has the least priority and minimum of 1/16th total bandwidth in the
face of higher priority traffic.

NB: Diffserv 3 & 4 swap tin 0 & 1 priorities from the default order as
found in diffserv8, in case anyone is wondering why it looks a bit odd.

Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
[ reword commit message slightly ]
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 60f8ae578819..cae367515804 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -312,8 +312,8 @@ static const u8 precedence[] = {
 };
 
 static const u8 diffserv8[] = {
-	2, 5, 1, 2, 4, 2, 2, 2,
-	0, 2, 1, 2, 1, 2, 1, 2,
+	2, 0, 1, 2, 4, 2, 2, 2,
+	1, 2, 1, 2, 1, 2, 1, 2,
 	5, 2, 4, 2, 4, 2, 4, 2,
 	3, 2, 3, 2, 3, 2, 3, 2,
 	6, 2, 3, 2, 3, 2, 3, 2,
@@ -323,7 +323,7 @@ static const u8 diffserv8[] = {
 };
 
 static const u8 diffserv4[] = {
-	0, 2, 0, 0, 2, 0, 0, 0,
+	0, 1, 0, 0, 2, 0, 0, 0,
 	1, 0, 0, 0, 0, 0, 0, 0,
 	2, 0, 2, 0, 2, 0, 2, 0,
 	2, 0, 2, 0, 2, 0, 2, 0,
@@ -334,7 +334,7 @@ static const u8 diffserv4[] = {
 };
 
 static const u8 diffserv3[] = {
-	0, 0, 0, 0, 2, 0, 0, 0,
+	0, 1, 0, 0, 2, 0, 0, 0,
 	1, 0, 0, 0, 0, 0, 0, 0,
 	0, 0, 0, 0, 0, 0, 0, 0,
 	0, 0, 0, 0, 0, 0, 0, 0,
-- 
cgit v1.2.3


From aebe4426ccaa4838f36ea805cdf7d76503e65117 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 27 Jun 2020 01:45:25 +0300
Subject: net: sched: Pass root lock to Qdisc_ops.enqueue

A following patch introduces qevents, points in qdisc algorithm where
packet can be processed by user-defined filters. Should this processing
lead to a situation where a new packet is to be enqueued on the same port,
holding the root lock would lead to deadlocks. To solve the issue, qevent
handler needs to unlock and relock the root lock when necessary.

To that end, add the root lock argument to the qdisc op enqueue, and
propagate throughout.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_atm.c       |  4 ++--
 net/sched/sch_blackhole.c |  2 +-
 net/sched/sch_cake.c      |  2 +-
 net/sched/sch_cbq.c       |  4 ++--
 net/sched/sch_cbs.c       | 18 +++++++++---------
 net/sched/sch_choke.c     |  2 +-
 net/sched/sch_codel.c     |  2 +-
 net/sched/sch_drr.c       |  4 ++--
 net/sched/sch_dsmark.c    |  4 ++--
 net/sched/sch_etf.c       |  2 +-
 net/sched/sch_ets.c       |  4 ++--
 net/sched/sch_fifo.c      |  6 +++---
 net/sched/sch_fq.c        |  2 +-
 net/sched/sch_fq_codel.c  |  2 +-
 net/sched/sch_fq_pie.c    |  2 +-
 net/sched/sch_generic.c   |  4 ++--
 net/sched/sch_gred.c      |  2 +-
 net/sched/sch_hfsc.c      |  6 +++---
 net/sched/sch_hhf.c       |  2 +-
 net/sched/sch_htb.c       |  4 ++--
 net/sched/sch_multiq.c    |  4 ++--
 net/sched/sch_netem.c     |  8 ++++----
 net/sched/sch_pie.c       |  2 +-
 net/sched/sch_plug.c      |  2 +-
 net/sched/sch_prio.c      |  6 +++---
 net/sched/sch_qfq.c       |  4 ++--
 net/sched/sch_red.c       |  4 ++--
 net/sched/sch_sfb.c       |  4 ++--
 net/sched/sch_sfq.c       |  2 +-
 net/sched/sch_skbprio.c   |  2 +-
 net/sched/sch_taprio.c    |  4 ++--
 net/sched/sch_tbf.c       | 10 +++++-----
 net/sched/sch_teql.c      |  4 ++--
 33 files changed, 67 insertions(+), 67 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index ee12ca9f55b4..fb6b16c4e46d 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -374,7 +374,7 @@ static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl,
 
 /* --------------------------- Qdisc operations ---------------------------- */
 
-static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			  struct sk_buff **to_free)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
@@ -432,7 +432,7 @@ done:
 #endif
 	}
 
-	ret = qdisc_enqueue(skb, flow->q, to_free);
+	ret = qdisc_enqueue(skb, flow->q, root_lock, to_free);
 	if (ret != NET_XMIT_SUCCESS) {
 drop: __maybe_unused
 		if (net_xmit_drop_count(ret)) {
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index a7f7667ae984..187644657c4f 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -13,7 +13,7 @@
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 
-static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			     struct sk_buff **to_free)
 {
 	qdisc_drop(skb, sch, to_free);
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 65a95cb094e8..e9c502dd29a2 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1687,7 +1687,7 @@ hash:
 
 static void cake_reconfigure(struct Qdisc *sch);
 
-static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			struct sk_buff **to_free)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 39b427dc7512..052d4a1af69a 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -356,7 +356,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
 }
 
 static int
-cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 	    struct sk_buff **to_free)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
@@ -373,7 +373,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		return ret;
 	}
 
-	ret = qdisc_enqueue(skb, cl->q, to_free);
+	ret = qdisc_enqueue(skb, cl->q, root_lock, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		cbq_mark_toplevel(q, cl);
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 2eaac2ff380f..7af15ebe07f7 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -77,7 +77,7 @@ struct cbs_sched_data {
 	s64 sendslope; /* in bytes/s */
 	s64 idleslope; /* in bytes/s */
 	struct qdisc_watchdog watchdog;
-	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch,
+	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free);
 	struct sk_buff *(*dequeue)(struct Qdisc *sch);
 	struct Qdisc *qdisc;
@@ -85,13 +85,13 @@ struct cbs_sched_data {
 };
 
 static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
-			     struct Qdisc *child,
+			     struct Qdisc *child, spinlock_t *root_lock,
 			     struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
 	int err;
 
-	err = child->ops->enqueue(skb, child, to_free);
+	err = child->ops->enqueue(skb, child, root_lock, to_free);
 	if (err != NET_XMIT_SUCCESS)
 		return err;
 
@@ -101,16 +101,16 @@ static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_SUCCESS;
 }
 
-static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch,
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			       struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct Qdisc *qdisc = q->qdisc;
 
-	return cbs_child_enqueue(skb, sch, qdisc, to_free);
+	return cbs_child_enqueue(skb, sch, qdisc, root_lock, to_free);
 }
 
-static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch,
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			    struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
@@ -124,15 +124,15 @@ static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch,
 		q->last = ktime_get_ns();
 	}
 
-	return cbs_child_enqueue(skb, sch, qdisc, to_free);
+	return cbs_child_enqueue(skb, sch, qdisc, root_lock, to_free);
 }
 
-static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 
-	return q->enqueue(skb, sch, to_free);
+	return q->enqueue(skb, sch, root_lock, to_free);
 }
 
 /* timediff is in ns, slope is in bytes/s */
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index bd618b00d319..baf3faee31aa 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -210,7 +210,7 @@ static bool choke_match_random(const struct choke_sched_data *q,
 	return choke_match_flow(oskb, nskb);
 }
 
-static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			 struct sk_buff **to_free)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 30169b3adbbb..1d94837abdd8 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -108,7 +108,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 	return skb;
 }
 
-static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			       struct sk_buff **to_free)
 {
 	struct codel_sched_data *q;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 07a2b0b35495..0d5c9a8ec61d 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -337,7 +337,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 	return NULL;
 }
 
-static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
@@ -355,7 +355,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 05605b30bef3..fbe49fffcdbb 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -198,7 +198,7 @@ static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl,
 
 /* --------------------------- Qdisc operations ---------------------------- */
 
-static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			  struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
@@ -267,7 +267,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		}
 	}
 
-	err = qdisc_enqueue(skb, p->q, to_free);
+	err = qdisc_enqueue(skb, p->q, root_lock, to_free);
 	if (err != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(err))
 			qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index c48f91075b5c..7a7c50a68115 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -160,7 +160,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 }
 
 static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
-				      struct sk_buff **to_free)
+				      spinlock_t *root_lock, struct sk_buff **to_free)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
 	struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL;
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index a87e9159338c..373dc5855d4e 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -415,7 +415,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch,
 	return &q->classes[band];
 }
 
-static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			     struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
@@ -433,7 +433,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index a579a4131d22..b4da5b624ad8 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -16,7 +16,7 @@
 
 /* 1 band FIFO pseudo-"scheduler" */
 
-static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			 struct sk_buff **to_free)
 {
 	if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit))
@@ -25,7 +25,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	return qdisc_drop(skb, sch, to_free);
 }
 
-static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			 struct sk_buff **to_free)
 {
 	if (likely(sch->q.qlen < sch->limit))
@@ -34,7 +34,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	return qdisc_drop(skb, sch, to_free);
 }
 
-static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			      struct sk_buff **to_free)
 {
 	unsigned int prev_backlog;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 2fb76fc0cc31..a90d745c41e0 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -439,7 +439,7 @@ static bool fq_packet_beyond_horizon(const struct sk_buff *skb,
 	return unlikely((s64)skb->tstamp > (s64)(q->ktime_cache + q->horizon));
 }
 
-static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		      struct sk_buff **to_free)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 459a784056c0..6bf979f95509 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -181,7 +181,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets,
 	return idx;
 }
 
-static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			    struct sk_buff **to_free)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index fb760cee824e..a27a250ab8f9 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -125,7 +125,7 @@ static inline void flow_queue_add(struct fq_pie_flow *flow,
 	skb->next = NULL;
 }
 
-static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 				struct sk_buff **to_free)
 {
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 265a61d011df..715cde1df9e4 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -520,7 +520,7 @@ EXPORT_SYMBOL(netif_carrier_off);
    cheaper.
  */
 
-static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
+static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, spinlock_t *root_lock,
 			struct sk_buff **to_free)
 {
 	__qdisc_drop(skb, to_free);
@@ -614,7 +614,7 @@ static inline struct skb_array *band2list(struct pfifo_fast_priv *priv,
 	return &priv->q[band];
 }
 
-static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
+static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, spinlock_t *root_lock,
 			      struct sk_buff **to_free)
 {
 	int band = prio2band[skb->priority & TC_PRIO_MAX];
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 8599c6f31b05..7d67c6cd6605 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -161,7 +161,7 @@ static bool gred_per_vq_red_flags_used(struct gred_sched *table)
 	return false;
 }
 
-static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			struct sk_buff **to_free)
 {
 	struct gred_sched_data *q = NULL;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 433f2190960f..7f6670044f0a 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1528,8 +1528,8 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
 	return -1;
 }
 
-static int
-hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
+static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+			struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
 	struct hfsc_class *cl;
@@ -1545,7 +1545,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	}
 
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 420ede875322..ddc6bf1d85d0 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -368,7 +368,7 @@ static unsigned int hhf_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return bucket - q->buckets;
 }
 
-static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 8184c87da8be..52fc513688b1 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -576,7 +576,7 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
 	cl->prio_activity = 0;
 }
 
-static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	int uninitialized_var(ret);
@@ -599,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		__qdisc_drop(skb, to_free);
 		return ret;
 #endif
-	} else if ((ret = qdisc_enqueue(skb, cl->leaf.q,
+	} else if ((ret = qdisc_enqueue(skb, cl->leaf.q, root_lock,
 					to_free)) != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret)) {
 			qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 1330ad224931..648611f5c105 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -57,7 +57,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 }
 
 static int
-multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 	       struct sk_buff **to_free)
 {
 	struct Qdisc *qdisc;
@@ -74,7 +74,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc, to_free);
+	ret = qdisc_enqueue(skb, qdisc, root_lock, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 84f82771cdf5..8fb17483a34f 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -431,7 +431,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch,
  * 	NET_XMIT_DROP: queue length didn't change.
  *      NET_XMIT_SUCCESS: one skb was queued.
  */
-static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			 struct sk_buff **to_free)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
@@ -480,7 +480,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
 
 		q->duplicate = 0;
-		rootq->enqueue(skb2, rootq, to_free);
+		rootq->enqueue(skb2, rootq, root_lock, to_free);
 		q->duplicate = dupsave;
 		rc_drop = NET_XMIT_SUCCESS;
 	}
@@ -604,7 +604,7 @@ finish_segs:
 			skb_mark_not_on_list(segs);
 			qdisc_skb_cb(segs)->pkt_len = segs->len;
 			last_len = segs->len;
-			rc = qdisc_enqueue(segs, sch, to_free);
+			rc = qdisc_enqueue(segs, sch, root_lock, to_free);
 			if (rc != NET_XMIT_SUCCESS) {
 				if (net_xmit_drop_count(rc))
 					qdisc_qstats_drop(sch);
@@ -720,7 +720,7 @@ deliver:
 				struct sk_buff *to_free = NULL;
 				int err;
 
-				err = qdisc_enqueue(skb, q->qdisc, &to_free);
+				err = qdisc_enqueue(skb, q->qdisc, NULL, &to_free);
 				kfree_skb_list(to_free);
 				if (err != NET_XMIT_SUCCESS &&
 				    net_xmit_drop_count(err)) {
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index c65077f0c0f3..b305313b64e3 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -82,7 +82,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
 }
 EXPORT_SYMBOL_GPL(pie_drop_early);
 
-static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			     struct sk_buff **to_free)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index cbc2ebca4548..e5f8b4769b4d 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -84,7 +84,7 @@ struct plug_sched_data {
 	u32 pkts_to_release;
 };
 
-static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			struct sk_buff **to_free)
 {
 	struct plug_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 647941702f9f..a3e187f2603c 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -65,8 +65,8 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	return q->queues[band];
 }
 
-static int
-prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
+static int prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+			struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
 	struct Qdisc *qdisc;
@@ -83,7 +83,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc, to_free);
+	ret = qdisc_enqueue(skb, qdisc, root_lock, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->qstats.backlog += len;
 		sch->q.qlen++;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 0b05ac7c848e..ede854516825 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1194,7 +1194,7 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q)
 	return agg;
 }
 
-static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb), gso_segs;
@@ -1225,7 +1225,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
 		if (net_xmit_drop_count(err)) {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 555a1b9e467f..6ace7d757e8b 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -65,7 +65,7 @@ static int red_use_nodrop(struct red_sched_data *q)
 	return q->flags & TC_RED_NODROP;
 }
 
-static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
@@ -118,7 +118,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		break;
 	}
 
-	ret = qdisc_enqueue(skb, child, to_free);
+	ret = qdisc_enqueue(skb, child, root_lock, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 4074c50ac3d7..d2a6e78262bb 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -276,7 +276,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 	return false;
 }
 
-static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 
@@ -399,7 +399,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 enqueue:
-	ret = qdisc_enqueue(skb, child, to_free);
+	ret = qdisc_enqueue(skb, child, root_lock, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 5a6def5e4e6d..46cdefd69e44 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -343,7 +343,7 @@ static int sfq_headdrop(const struct sfq_sched_data *q)
 }
 
 static int
-sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
+sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	unsigned int hash, dropped;
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index 7a5e4c454715..f75f237c4436 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -65,7 +65,7 @@ static u16 calc_new_low_prio(const struct skbprio_sched_data *q)
 	return SKBPRIO_MAX_PRIORITY - 1;
 }
 
-static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			  struct sk_buff **to_free)
 {
 	const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1;
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index e981992634dd..daef2ff60a98 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -410,7 +410,7 @@ done:
 	return txtime;
 }
 
-static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 			  struct sk_buff **to_free)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
@@ -435,7 +435,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
-	return qdisc_enqueue(skb, child, to_free);
+	return qdisc_enqueue(skb, child, root_lock, to_free);
 }
 
 static struct sk_buff *taprio_peek_soft(struct Qdisc *sch)
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 78e79029dc63..c3eb5cdb83a8 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -187,7 +187,7 @@ static int tbf_offload_dump(struct Qdisc *sch)
 /* GSO packet is too big, segment it so that tbf can transmit
  * each segment in time
  */
-static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
+static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
@@ -206,7 +206,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
 		skb_mark_not_on_list(segs);
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
 		len += segs->len;
-		ret = qdisc_enqueue(segs, q->qdisc, to_free);
+		ret = qdisc_enqueue(segs, q->qdisc, root_lock, to_free);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
 				qdisc_qstats_drop(sch);
@@ -221,7 +221,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
 
-static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		       struct sk_buff **to_free)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
@@ -231,10 +231,10 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (qdisc_pkt_len(skb) > q->max_size) {
 		if (skb_is_gso(skb) &&
 		    skb_gso_validate_mac_len(skb, q->max_size))
-			return tbf_segment(skb, sch, to_free);
+			return tbf_segment(skb, sch, root_lock, to_free);
 		return qdisc_drop(skb, sch, to_free);
 	}
-	ret = qdisc_enqueue(skb, q->qdisc, to_free);
+	ret = qdisc_enqueue(skb, q->qdisc, root_lock, to_free);
 	if (ret != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret))
 			qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 689ef6f3ded8..511964653476 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -72,8 +72,8 @@ struct teql_sched_data {
 
 /* "teql*" qdisc routines */
 
-static int
-teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
+static int teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+			struct sk_buff **to_free)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct teql_sched_data *q = qdisc_priv(sch);
-- 
cgit v1.2.3


From 3625750f05ecce21a0fce429c1ff85acfffb461b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 27 Jun 2020 01:45:26 +0300
Subject: net: sched: Introduce helpers for qevent blocks

Qevents are attach points for TC blocks, where filters can be put that are
executed when "interesting events" take place in a qdisc. The data to keep
and the functions to invoke to maintain a qevent will be largely the same
between qevents. Therefore introduce sched-wide helpers for qevent
management.

Currently, similarly to ingress and egress blocks of clsact pseudo-qdisc,
blocks attachment cannot be changed after the qdisc is created. To that
end, add a helper tcf_qevent_validate_change(), which verifies whether
block index attribute is not attached, or if it is, whether its value
matches the current one (i.e. there is no material change).

The function tcf_qevent_handle() should be invoked when qdisc hits the
"interesting event" corresponding to a block. This function releases root
lock for the duration of executing the attached filters, to allow packets
generated through user actions (notably mirred) to be reinserted to the
same qdisc tree.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 119 insertions(+)

(limited to 'net/sched')

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5bfa6b985bb8..1b14d5f57e7f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3748,6 +3748,125 @@ unsigned int tcf_exts_num_actions(struct tcf_exts *exts)
 }
 EXPORT_SYMBOL(tcf_exts_num_actions);
 
+#ifdef CONFIG_NET_CLS_ACT
+static int tcf_qevent_parse_block_index(struct nlattr *block_index_attr,
+					u32 *p_block_index,
+					struct netlink_ext_ack *extack)
+{
+	*p_block_index = nla_get_u32(block_index_attr);
+	if (!*p_block_index) {
+		NL_SET_ERR_MSG(extack, "Block number may not be zero");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch,
+		    enum flow_block_binder_type binder_type,
+		    struct nlattr *block_index_attr,
+		    struct netlink_ext_ack *extack)
+{
+	u32 block_index;
+	int err;
+
+	if (!block_index_attr)
+		return 0;
+
+	err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack);
+	if (err)
+		return err;
+
+	if (!block_index)
+		return 0;
+
+	qe->info.binder_type = binder_type;
+	qe->info.chain_head_change = tcf_chain_head_change_dflt;
+	qe->info.chain_head_change_priv = &qe->filter_chain;
+	qe->info.block_index = block_index;
+
+	return tcf_block_get_ext(&qe->block, sch, &qe->info, extack);
+}
+EXPORT_SYMBOL(tcf_qevent_init);
+
+void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch)
+{
+	if (qe->info.block_index)
+		tcf_block_put_ext(qe->block, sch, &qe->info);
+}
+EXPORT_SYMBOL(tcf_qevent_destroy);
+
+int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr,
+			       struct netlink_ext_ack *extack)
+{
+	u32 block_index;
+	int err;
+
+	if (!block_index_attr)
+		return 0;
+
+	err = tcf_qevent_parse_block_index(block_index_attr, &block_index, extack);
+	if (err)
+		return err;
+
+	/* Bounce newly-configured block or change in block. */
+	if (block_index != qe->info.block_index) {
+		NL_SET_ERR_MSG(extack, "Change of blocks is not supported");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(tcf_qevent_validate_change);
+
+struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
+				  spinlock_t *root_lock, struct sk_buff **to_free, int *ret)
+{
+	struct tcf_result cl_res;
+	struct tcf_proto *fl;
+
+	if (!qe->info.block_index)
+		return skb;
+
+	fl = rcu_dereference_bh(qe->filter_chain);
+
+	if (root_lock)
+		spin_unlock(root_lock);
+
+	switch (tcf_classify(skb, fl, &cl_res, false)) {
+	case TC_ACT_SHOT:
+		qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
+		*ret = __NET_XMIT_BYPASS;
+		return NULL;
+	case TC_ACT_STOLEN:
+	case TC_ACT_QUEUED:
+	case TC_ACT_TRAP:
+		__qdisc_drop(skb, to_free);
+		*ret = __NET_XMIT_STOLEN;
+		return NULL;
+	case TC_ACT_REDIRECT:
+		skb_do_redirect(skb);
+		*ret = __NET_XMIT_STOLEN;
+		return NULL;
+	}
+
+	if (root_lock)
+		spin_lock(root_lock);
+
+	return skb;
+}
+EXPORT_SYMBOL(tcf_qevent_handle);
+
+int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe)
+{
+	if (!qe->info.block_index)
+		return 0;
+	return nla_put_u32(skb, attr_name, qe->info.block_index);
+}
+EXPORT_SYMBOL(tcf_qevent_dump);
+#endif
+
 static __net_init int tcf_net_init(struct net *net)
 {
 	struct tcf_net *tn = net_generic(net, tcf_net_id);
-- 
cgit v1.2.3


From 65545ea24998bb9aab1ce713a67c693dc7a947ec Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 27 Jun 2020 01:45:27 +0300
Subject: net: sched: sch_red: Split init and change callbacks

In the following patches, RED will get two qevents. The implementation will
be clearer if the callback for change is not a pure subset of the callback
for init. Split the two and promote attribute parsing to the callbacks
themselves from the common code, because it will be handy there.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_red.c | 42 ++++++++++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 12 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6ace7d757e8b..225ce370e5a8 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -215,12 +215,11 @@ static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
 	[TCA_RED_FLAGS] = NLA_POLICY_BITFIELD32(TC_RED_SUPPORTED_FLAGS),
 };
 
-static int red_change(struct Qdisc *sch, struct nlattr *opt,
-		      struct netlink_ext_ack *extack)
+static int __red_change(struct Qdisc *sch, struct nlattr **tb,
+			struct netlink_ext_ack *extack)
 {
 	struct Qdisc *old_child = NULL, *child = NULL;
 	struct red_sched_data *q = qdisc_priv(sch);
-	struct nlattr *tb[TCA_RED_MAX + 1];
 	struct nla_bitfield32 flags_bf;
 	struct tc_red_qopt *ctl;
 	unsigned char userbits;
@@ -228,14 +227,6 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 	int err;
 	u32 max_P;
 
-	if (opt == NULL)
-		return -EINVAL;
-
-	err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy,
-					  NULL);
-	if (err < 0)
-		return err;
-
 	if (tb[TCA_RED_PARMS] == NULL ||
 	    tb[TCA_RED_STAB] == NULL)
 		return -EINVAL;
@@ -323,11 +314,38 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 		    struct netlink_ext_ack *extack)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_RED_MAX + 1];
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy,
+					  extack);
+	if (err < 0)
+		return err;
 
 	q->qdisc = &noop_qdisc;
 	q->sch = sch;
 	timer_setup(&q->adapt_timer, red_adaptative_timer, 0);
-	return red_change(sch, opt, extack);
+	return __red_change(sch, tb, extack);
+}
+
+static int red_change(struct Qdisc *sch, struct nlattr *opt,
+		      struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_RED_MAX + 1];
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy,
+					  extack);
+	if (err < 0)
+		return err;
+
+	return __red_change(sch, tb, extack);
 }
 
 static int red_dump_offload_stats(struct Qdisc *sch)
-- 
cgit v1.2.3


From aee9caa03fc3c8b02f8f31824354d85f30e562e0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 27 Jun 2020 01:45:28 +0300
Subject: net: sched: sch_red: Add qevents "early_drop" and "mark"

In order to allow acting on dropped and/or ECN-marked packets, add two new
qevents to the RED qdisc: "early_drop" and "mark". Filters attached at
"early_drop" block are executed as packets are early-dropped, those
attached at the "mark" block are executed as packets are ECN-marked.

Two new attributes are introduced: TCA_RED_EARLY_DROP_BLOCK with the block
index for the "early_drop" qevent, and TCA_RED_MARK_BLOCK for the "mark"
qevent. Absence of these attributes signifies "don't care": no block is
allocated in that case, or the existing blocks are left intact in case of
the change callback.

For purposes of offloading, blocks attached to these qevents appear with
newly-introduced binder types, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP and
FLOW_BLOCK_BINDER_TYPE_RED_MARK.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_red.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 56 insertions(+), 2 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 225ce370e5a8..de2be4d04ed6 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -46,6 +46,8 @@ struct red_sched_data {
 	struct red_vars		vars;
 	struct red_stats	stats;
 	struct Qdisc		*qdisc;
+	struct tcf_qevent	qe_early_drop;
+	struct tcf_qevent	qe_mark;
 };
 
 #define TC_RED_SUPPORTED_FLAGS (TC_RED_HISTORIC_FLAGS | TC_RED_NODROP)
@@ -92,6 +94,9 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 
 		if (INET_ECN_set_ce(skb)) {
 			q->stats.prob_mark++;
+			skb = tcf_qevent_handle(&q->qe_mark, sch, skb, root_lock, to_free, &ret);
+			if (!skb)
+				return NET_XMIT_CN | ret;
 		} else if (!red_use_nodrop(q)) {
 			q->stats.prob_drop++;
 			goto congestion_drop;
@@ -109,6 +114,9 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 
 		if (INET_ECN_set_ce(skb)) {
 			q->stats.forced_mark++;
+			skb = tcf_qevent_handle(&q->qe_mark, sch, skb, root_lock, to_free, &ret);
+			if (!skb)
+				return NET_XMIT_CN | ret;
 		} else if (!red_use_nodrop(q)) {
 			q->stats.forced_drop++;
 			goto congestion_drop;
@@ -129,6 +137,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 	return ret;
 
 congestion_drop:
+	skb = tcf_qevent_handle(&q->qe_early_drop, sch, skb, root_lock, to_free, &ret);
+	if (!skb)
+		return NET_XMIT_CN | ret;
+
 	qdisc_drop(skb, sch, to_free);
 	return NET_XMIT_CN;
 }
@@ -202,6 +214,8 @@ static void red_destroy(struct Qdisc *sch)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 
+	tcf_qevent_destroy(&q->qe_mark, sch);
+	tcf_qevent_destroy(&q->qe_early_drop, sch);
 	del_timer_sync(&q->adapt_timer);
 	red_offload(sch, false);
 	qdisc_put(q->qdisc);
@@ -213,6 +227,8 @@ static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
 	[TCA_RED_STAB]	= { .len = RED_STAB_SIZE },
 	[TCA_RED_MAX_P] = { .type = NLA_U32 },
 	[TCA_RED_FLAGS] = NLA_POLICY_BITFIELD32(TC_RED_SUPPORTED_FLAGS),
+	[TCA_RED_EARLY_DROP_BLOCK] = { .type = NLA_U32 },
+	[TCA_RED_MARK_BLOCK] = { .type = NLA_U32 },
 };
 
 static int __red_change(struct Qdisc *sch, struct nlattr **tb,
@@ -328,12 +344,38 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 	q->qdisc = &noop_qdisc;
 	q->sch = sch;
 	timer_setup(&q->adapt_timer, red_adaptative_timer, 0);
-	return __red_change(sch, tb, extack);
+
+	err = __red_change(sch, tb, extack);
+	if (err)
+		return err;
+
+	err = tcf_qevent_init(&q->qe_early_drop, sch,
+			      FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP,
+			      tb[TCA_RED_EARLY_DROP_BLOCK], extack);
+	if (err)
+		goto err_early_drop_init;
+
+	err = tcf_qevent_init(&q->qe_mark, sch,
+			      FLOW_BLOCK_BINDER_TYPE_RED_MARK,
+			      tb[TCA_RED_MARK_BLOCK], extack);
+	if (err)
+		goto err_mark_init;
+
+	return 0;
+
+err_mark_init:
+	tcf_qevent_destroy(&q->qe_early_drop, sch);
+err_early_drop_init:
+	del_timer_sync(&q->adapt_timer);
+	red_offload(sch, false);
+	qdisc_put(q->qdisc);
+	return err;
 }
 
 static int red_change(struct Qdisc *sch, struct nlattr *opt,
 		      struct netlink_ext_ack *extack)
 {
+	struct red_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_RED_MAX + 1];
 	int err;
 
@@ -345,6 +387,16 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		return err;
 
+	err = tcf_qevent_validate_change(&q->qe_early_drop,
+					 tb[TCA_RED_EARLY_DROP_BLOCK], extack);
+	if (err)
+		return err;
+
+	err = tcf_qevent_validate_change(&q->qe_mark,
+					 tb[TCA_RED_MARK_BLOCK], extack);
+	if (err)
+		return err;
+
 	return __red_change(sch, tb, extack);
 }
 
@@ -389,7 +441,9 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) ||
 	    nla_put_u32(skb, TCA_RED_MAX_P, q->parms.max_P) ||
 	    nla_put_bitfield32(skb, TCA_RED_FLAGS,
-			       q->flags, TC_RED_SUPPORTED_FLAGS))
+			       q->flags, TC_RED_SUPPORTED_FLAGS) ||
+	    tcf_qevent_dump(skb, TCA_RED_MARK_BLOCK, &q->qe_mark) ||
+	    tcf_qevent_dump(skb, TCA_RED_EARLY_DROP_BLOCK, &q->qe_early_drop))
 		goto nla_put_failure;
 	return nla_nest_end(skb, opts);
 
-- 
cgit v1.2.3


From 5f035af76e51cd622abc6564d5512ffeb9e06917 Mon Sep 17 00:00:00 2001
From: Po Liu <po.liu@nxp.com>
Date: Mon, 29 Jun 2020 14:54:16 +0800
Subject: net:qos: police action offloading parameter 'burst' change to the
 original value

Since 'tcfp_burst' with TICK factor, driver side always need to recover
it to the original value, this patch moves the generic calculation and
recover to the 'burst' original value before offloading to device driver.

Signed-off-by: Po Liu <po.liu@nxp.com>
Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/sched')

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1b14d5f57e7f..e9e119ea6813 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3660,7 +3660,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			tcf_sample_get_group(entry, act);
 		} else if (is_tcf_police(act)) {
 			entry->id = FLOW_ACTION_POLICE;
-			entry->police.burst = tcf_police_tcfp_burst(act);
+			entry->police.burst = tcf_police_burst(act);
 			entry->police.rate_bytes_ps =
 				tcf_police_rate_bytes_ps(act);
 			entry->police.mtu = tcf_police_tcfp_mtu(act);
-- 
cgit v1.2.3


From b97e9d9d67c88bc413a3c27734d45d98d8d52b00 Mon Sep 17 00:00:00 2001
From: Danny Lin <danny@kdrag0n.dev>
Date: Wed, 1 Jul 2020 16:01:52 -0700
Subject: net: sched: Allow changing default qdisc to FQ-PIE

Similar to fq_codel and the other qdiscs that can set as default,
fq_pie is also suitable for general use without explicit configuration,
which makes it a valid choice for this.

This is useful in situations where a painless out-of-the-box solution
for reducing bufferbloat is desired but fq_codel is not necessarily the
best choice. For example, fq_pie can be better for DASH streaming, but
there could be more cases where it's the better choice of the two simple
AQMs available in the kernel.

Signed-off-by: Danny Lin <danny@kdrag0n.dev>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'net/sched')

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 84badf00647e..a3b37d88800e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -468,6 +468,9 @@ choice
 	config DEFAULT_FQ_CODEL
 		bool "Fair Queue Controlled Delay" if NET_SCH_FQ_CODEL
 
+	config DEFAULT_FQ_PIE
+		bool "Flow Queue Proportional Integral controller Enhanced" if NET_SCH_FQ_PIE
+
 	config DEFAULT_SFQ
 		bool "Stochastic Fair Queue" if NET_SCH_SFQ
 
@@ -480,6 +483,7 @@ config DEFAULT_NET_SCH
 	default "pfifo_fast" if DEFAULT_PFIFO_FAST
 	default "fq" if DEFAULT_FQ
 	default "fq_codel" if DEFAULT_FQ_CODEL
+	default "fq_pie" if DEFAULT_FQ_PIE
 	default "sfq" if DEFAULT_SFQ
 	default "pfifo_fast"
 endif
-- 
cgit v1.2.3


From 964201de695b8afca80652f048a95dc2cb68fcb7 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 7 Jul 2020 12:21:38 -0500
Subject: net/sched: Use fallthrough pseudo-keyword

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary
fall-through markings when it is the case.

[1] https://www.kernel.org/doc/html/latest/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_csum.c     | 3 ++-
 net/sched/act_ct.c       | 2 +-
 net/sched/sch_cbq.c      | 2 +-
 net/sched/sch_drr.c      | 2 +-
 net/sched/sch_ets.c      | 2 +-
 net/sched/sch_fq_codel.c | 2 +-
 net/sched/sch_fq_pie.c   | 2 +-
 net/sched/sch_hfsc.c     | 2 +-
 net/sched/sch_htb.c      | 2 +-
 net/sched/sch_multiq.c   | 2 +-
 net/sched/sch_prio.c     | 2 +-
 net/sched/sch_qfq.c      | 2 +-
 net/sched/sch_sfb.c      | 2 +-
 net/sched/sch_sfq.c      | 2 +-
 14 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index cb8608f0a77a..9035355e867f 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -598,7 +598,8 @@ again:
 		if (!tcf_csum_ipv6(skb, update_flags))
 			goto drop;
 		break;
-	case cpu_to_be16(ETH_P_8021AD): /* fall through */
+	case cpu_to_be16(ETH_P_8021AD):
+		fallthrough;
 	case cpu_to_be16(ETH_P_8021Q):
 		if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) {
 			protocol = skb->protocol;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 1b9c6d4a1b6b..fadfd6b0033b 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -783,7 +783,7 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 			}
 		}
 		/* Non-ICMP, fall thru to initialize if needed. */
-		/* fall through */
+		fallthrough;
 	case IP_CT_NEW:
 		/* Seen it before?  This can happen for loopback, retrans,
 		 * or local packets.
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 052d4a1af69a..9e16fdf47fe7 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -250,7 +250,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		case TC_ACT_RECLASSIFY:
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 0d5c9a8ec61d..ad14df2ecf3a 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -324,7 +324,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 373dc5855d4e..1af86f30b18e 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -397,7 +397,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 6bf979f95509..bca016ffc069 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -99,7 +99,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return 0;
 		}
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index a27a250ab8f9..741840b9994f 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -102,7 +102,7 @@ static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return 0;
 		}
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 7f6670044f0a..13ba8648bb63 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1136,7 +1136,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 52fc513688b1..b07f29059f47 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -239,7 +239,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 648611f5c105..56bdc4bcdc63 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -43,7 +43,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	case TC_ACT_QUEUED:
 	case TC_ACT_TRAP:
 		*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-		/* fall through */
+		fallthrough;
 	case TC_ACT_SHOT:
 		return NULL;
 	}
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index a3e187f2603c..46b7ce81c6e3 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -46,7 +46,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index ede854516825..3cfe6262eb00 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -699,7 +699,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_STOLEN:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return NULL;
 		}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index d2a6e78262bb..356f6d1d30db 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -265,7 +265,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return false;
 		}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 46cdefd69e44..a1314510dc69 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -186,7 +186,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
 		case TC_ACT_QUEUED:
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
-			/* fall through */
+			fallthrough;
 		case TC_ACT_SHOT:
 			return 0;
 		}
-- 
cgit v1.2.3


From 90ac5d0301db7cefc4129f89a858f66913a1c8f4 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Mon, 13 Jul 2020 01:15:11 +0200
Subject: net: sched: kerneldoc fixes

Simple fixes which require no deep knowledge of the code.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/em_canid.c | 1 +
 net/sched/ematch.c   | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
index b9a94fdf9397..5ea84decec19 100644
--- a/net/sched/em_canid.c
+++ b/net/sched/em_canid.c
@@ -40,6 +40,7 @@ struct canid_match {
 
 /**
  * em_canid_get_id() - Extracts Can ID out of the sk_buff structure.
+ * @skb: buffer to extract Can ID from
  */
 static canid_t em_canid_get_id(struct sk_buff *skb)
 {
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index dd3b8c11a2e0..f885bea5b452 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -389,7 +389,6 @@ EXPORT_SYMBOL(tcf_em_tree_validate);
 /**
  * tcf_em_tree_destroy - destroy an ematch tree
  *
- * @tp: classifier kind handle
  * @tree: ematch tree to be deleted
  *
  * This functions destroys an ematch tree previously created by
@@ -425,7 +424,7 @@ EXPORT_SYMBOL(tcf_em_tree_destroy);
  * tcf_em_tree_dump - dump ematch tree into a rtnl message
  *
  * @skb: skb holding the rtnl message
- * @t: ematch tree to be dumped
+ * @tree: ematch tree to be dumped
  * @tlv: TLV type to be used to encapsulate the tree
  *
  * This function dumps a ematch tree into a rtnl message. It is valid to
-- 
cgit v1.2.3


From c40f4e50b6cfc7c66f69d12c6b3fbcd954f1ded5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 11 Jul 2020 00:55:03 +0300
Subject: net: sched: Pass qdisc reference in struct flow_block_offload

Previously, shared blocks were only relevant for the pseudo-qdiscs ingress
and clsact. Recently, a qevent facility was introduced, which allows to
bind blocks to well-defined slots of a qdisc instance. RED in particular
got two qevents: early_drop and mark. Drivers that wish to offload these
blocks will be sent the usual notification, and need to know which qdisc it
is related to.

To that end, extend flow_block_offload with a "sch" pointer, and initialize
as appropriate. This prompts changes in the indirect block facility, which
now tracks the scheduler in addition to the netdevice. Update signatures of
several functions similarly.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e617f3e27ec0..322b279154de 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -622,7 +622,7 @@ static int tcf_block_setup(struct tcf_block *block,
 			   struct flow_block_offload *bo);
 
 static void tcf_block_offload_init(struct flow_block_offload *bo,
-				   struct net_device *dev,
+				   struct net_device *dev, struct Qdisc *sch,
 				   enum flow_block_command command,
 				   enum flow_block_binder_type binder_type,
 				   struct flow_block *flow_block,
@@ -634,6 +634,7 @@ static void tcf_block_offload_init(struct flow_block_offload *bo,
 	bo->block = flow_block;
 	bo->block_shared = shared;
 	bo->extack = extack;
+	bo->sch = sch;
 	INIT_LIST_HEAD(&bo->cb_list);
 }
 
@@ -644,10 +645,11 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 {
 	struct tcf_block *block = block_cb->indr.data;
 	struct net_device *dev = block_cb->indr.dev;
+	struct Qdisc *sch = block_cb->indr.sch;
 	struct netlink_ext_ack extack = {};
 	struct flow_block_offload bo;
 
-	tcf_block_offload_init(&bo, dev, FLOW_BLOCK_UNBIND,
+	tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND,
 			       block_cb->indr.binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       &extack);
@@ -666,14 +668,14 @@ static bool tcf_block_offload_in_use(struct tcf_block *block)
 }
 
 static int tcf_block_offload_cmd(struct tcf_block *block,
-				 struct net_device *dev,
+				 struct net_device *dev, struct Qdisc *sch,
 				 struct tcf_block_ext_info *ei,
 				 enum flow_block_command command,
 				 struct netlink_ext_ack *extack)
 {
 	struct flow_block_offload bo = {};
 
-	tcf_block_offload_init(&bo, dev, command, ei->binder_type,
+	tcf_block_offload_init(&bo, dev, sch, command, ei->binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       extack);
 
@@ -690,7 +692,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
 		return tcf_block_setup(block, &bo);
 	}
 
-	flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo,
+	flow_indr_dev_setup_offload(dev, sch, TC_SETUP_BLOCK, block, &bo,
 				    tc_block_indr_cleanup);
 	tcf_block_setup(block, &bo);
 
@@ -717,7 +719,7 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 		goto err_unlock;
 	}
 
-	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack);
+	err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_BIND, extack);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_inc;
 	if (err)
@@ -744,7 +746,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 	int err;
 
 	down_write(&block->cb_lock);
-	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
+	err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_UNBIND, NULL);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_dec;
 	up_write(&block->cb_lock);
-- 
cgit v1.2.3


From 55f656cdb851bae32980d83d2494201e79d93b63 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 14 Jul 2020 20:03:07 +0300
Subject: net: sched: Do not drop root lock in tcf_qevent_handle()

Mirred currently does not mix well with blocks executed after the qdisc
root lock is taken. This includes classification blocks (such as in PRIO,
ETS, DRR qdiscs) and qevents. The locking caused by the packet mirrored by
mirred can cause deadlocks: either when the thread of execution attempts to
take the lock a second time, or when two threads end up waiting on each
other's locks.

The qevent patchset attempted to not introduce further badness of this
sort, and dropped the lock before executing the qevent block. However this
lead to too little locking and races between qdisc configuration and packet
enqueue in the RED qdisc.

Before the deadlock issues are solved in a way that can be applied across
many qdiscs reasonably easily, do for qevents what is done for the
classification blocks and just keep holding the root lock.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/cls_api.c | 8 +-------
 net/sched/sch_red.c | 6 +++---
 2 files changed, 4 insertions(+), 10 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 322b279154de..b2b7440c2ae7 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3822,7 +3822,7 @@ int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index
 EXPORT_SYMBOL(tcf_qevent_validate_change);
 
 struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb,
-				  spinlock_t *root_lock, struct sk_buff **to_free, int *ret)
+				  struct sk_buff **to_free, int *ret)
 {
 	struct tcf_result cl_res;
 	struct tcf_proto *fl;
@@ -3832,9 +3832,6 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, stru
 
 	fl = rcu_dereference_bh(qe->filter_chain);
 
-	if (root_lock)
-		spin_unlock(root_lock);
-
 	switch (tcf_classify(skb, fl, &cl_res, false)) {
 	case TC_ACT_SHOT:
 		qdisc_qstats_drop(sch);
@@ -3853,9 +3850,6 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, stru
 		return NULL;
 	}
 
-	if (root_lock)
-		spin_lock(root_lock);
-
 	return skb;
 }
 EXPORT_SYMBOL(tcf_qevent_handle);
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index de2be4d04ed6..a79602f7fab8 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -94,7 +94,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 
 		if (INET_ECN_set_ce(skb)) {
 			q->stats.prob_mark++;
-			skb = tcf_qevent_handle(&q->qe_mark, sch, skb, root_lock, to_free, &ret);
+			skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret);
 			if (!skb)
 				return NET_XMIT_CN | ret;
 		} else if (!red_use_nodrop(q)) {
@@ -114,7 +114,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 
 		if (INET_ECN_set_ce(skb)) {
 			q->stats.forced_mark++;
-			skb = tcf_qevent_handle(&q->qe_mark, sch, skb, root_lock, to_free, &ret);
+			skb = tcf_qevent_handle(&q->qe_mark, sch, skb, to_free, &ret);
 			if (!skb)
 				return NET_XMIT_CN | ret;
 		} else if (!red_use_nodrop(q)) {
@@ -137,7 +137,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 	return ret;
 
 congestion_drop:
-	skb = tcf_qevent_handle(&q->qe_early_drop, sch, skb, root_lock, to_free, &ret);
+	skb = tcf_qevent_handle(&q->qe_early_drop, sch, skb, to_free, &ret);
 	if (!skb)
 		return NET_XMIT_CN | ret;
 
-- 
cgit v1.2.3


From ac5c66f261b7174d0d9aaeb2bf9f8c2c2dbad0bd Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 14 Jul 2020 20:03:08 +0300
Subject: Revert "net: sched: Pass root lock to Qdisc_ops.enqueue"

This reverts commit aebe4426ccaa4838f36ea805cdf7d76503e65117.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_atm.c       |  4 ++--
 net/sched/sch_blackhole.c |  2 +-
 net/sched/sch_cake.c      |  2 +-
 net/sched/sch_cbq.c       |  4 ++--
 net/sched/sch_cbs.c       | 18 +++++++++---------
 net/sched/sch_choke.c     |  2 +-
 net/sched/sch_codel.c     |  2 +-
 net/sched/sch_drr.c       |  4 ++--
 net/sched/sch_dsmark.c    |  4 ++--
 net/sched/sch_etf.c       |  2 +-
 net/sched/sch_ets.c       |  4 ++--
 net/sched/sch_fifo.c      |  6 +++---
 net/sched/sch_fq.c        |  2 +-
 net/sched/sch_fq_codel.c  |  2 +-
 net/sched/sch_fq_pie.c    |  2 +-
 net/sched/sch_generic.c   |  4 ++--
 net/sched/sch_gred.c      |  2 +-
 net/sched/sch_hfsc.c      |  6 +++---
 net/sched/sch_hhf.c       |  2 +-
 net/sched/sch_htb.c       |  4 ++--
 net/sched/sch_multiq.c    |  4 ++--
 net/sched/sch_netem.c     |  8 ++++----
 net/sched/sch_pie.c       |  2 +-
 net/sched/sch_plug.c      |  2 +-
 net/sched/sch_prio.c      |  6 +++---
 net/sched/sch_qfq.c       |  4 ++--
 net/sched/sch_red.c       |  4 ++--
 net/sched/sch_sfb.c       |  4 ++--
 net/sched/sch_sfq.c       |  2 +-
 net/sched/sch_skbprio.c   |  2 +-
 net/sched/sch_taprio.c    |  4 ++--
 net/sched/sch_tbf.c       | 10 +++++-----
 net/sched/sch_teql.c      |  4 ++--
 33 files changed, 67 insertions(+), 67 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1d5e422d9be2..1c281cc81f57 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -374,7 +374,7 @@ static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl,
 
 /* --------------------------- Qdisc operations ---------------------------- */
 
-static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			  struct sk_buff **to_free)
 {
 	struct atm_qdisc_data *p = qdisc_priv(sch);
@@ -432,7 +432,7 @@ done:
 #endif
 	}
 
-	ret = qdisc_enqueue(skb, flow->q, root_lock, to_free);
+	ret = qdisc_enqueue(skb, flow->q, to_free);
 	if (ret != NET_XMIT_SUCCESS) {
 drop: __maybe_unused
 		if (net_xmit_drop_count(ret)) {
diff --git a/net/sched/sch_blackhole.c b/net/sched/sch_blackhole.c
index 187644657c4f..a7f7667ae984 100644
--- a/net/sched/sch_blackhole.c
+++ b/net/sched/sch_blackhole.c
@@ -13,7 +13,7 @@
 #include <linux/skbuff.h>
 #include <net/pkt_sched.h>
 
-static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int blackhole_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)
 {
 	qdisc_drop(skb, sch, to_free);
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index b3cdcd86cbfd..561d20c9adca 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1687,7 +1687,7 @@ hash:
 
 static void cake_reconfigure(struct Qdisc *sch);
 
-static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			struct sk_buff **to_free)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 9e16fdf47fe7..b2130df933a7 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -356,7 +356,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
 }
 
 static int
-cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	    struct sk_buff **to_free)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
@@ -373,7 +373,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 		return ret;
 	}
 
-	ret = qdisc_enqueue(skb, cl->q, root_lock, to_free);
+	ret = qdisc_enqueue(skb, cl->q, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		cbq_mark_toplevel(q, cl);
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 7af15ebe07f7..2eaac2ff380f 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -77,7 +77,7 @@ struct cbs_sched_data {
 	s64 sendslope; /* in bytes/s */
 	s64 idleslope; /* in bytes/s */
 	struct qdisc_watchdog watchdog;
-	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free);
 	struct sk_buff *(*dequeue)(struct Qdisc *sch);
 	struct Qdisc *qdisc;
@@ -85,13 +85,13 @@ struct cbs_sched_data {
 };
 
 static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
-			     struct Qdisc *child, spinlock_t *root_lock,
+			     struct Qdisc *child,
 			     struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
 	int err;
 
-	err = child->ops->enqueue(skb, child, root_lock, to_free);
+	err = child->ops->enqueue(skb, child, to_free);
 	if (err != NET_XMIT_SUCCESS)
 		return err;
 
@@ -101,16 +101,16 @@ static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	return NET_XMIT_SUCCESS;
 }
 
-static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch,
 			       struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 	struct Qdisc *qdisc = q->qdisc;
 
-	return cbs_child_enqueue(skb, sch, qdisc, root_lock, to_free);
+	return cbs_child_enqueue(skb, sch, qdisc, to_free);
 }
 
-static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch,
 			    struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
@@ -124,15 +124,15 @@ static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *
 		q->last = ktime_get_ns();
 	}
 
-	return cbs_child_enqueue(skb, sch, qdisc, root_lock, to_free);
+	return cbs_child_enqueue(skb, sch, qdisc, to_free);
 }
 
-static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 
-	return q->enqueue(skb, sch, root_lock, to_free);
+	return q->enqueue(skb, sch, to_free);
 }
 
 /* timediff is in ns, slope is in bytes/s */
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index baf3faee31aa..bd618b00d319 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -210,7 +210,7 @@ static bool choke_match_random(const struct choke_sched_data *q,
 	return choke_match_flow(oskb, nskb);
 }
 
-static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			 struct sk_buff **to_free)
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 1d94837abdd8..30169b3adbbb 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -108,7 +108,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 	return skb;
 }
 
-static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int codel_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			       struct sk_buff **to_free)
 {
 	struct codel_sched_data *q;
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index ad14df2ecf3a..dde564670ad8 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -337,7 +337,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
 	return NULL;
 }
 
-static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
@@ -355,7 +355,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 	}
 
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 76a9c4f277f2..2b88710994d7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -198,7 +198,7 @@ static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl,
 
 /* --------------------------- Qdisc operations ---------------------------- */
 
-static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			  struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
@@ -267,7 +267,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *ro
 		}
 	}
 
-	err = qdisc_enqueue(skb, p->q, root_lock, to_free);
+	err = qdisc_enqueue(skb, p->q, to_free);
 	if (err != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(err))
 			qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 7a7c50a68115..c48f91075b5c 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -160,7 +160,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
 }
 
 static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
-				      spinlock_t *root_lock, struct sk_buff **to_free)
+				      struct sk_buff **to_free)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
 	struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL;
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 1af86f30b18e..c1e84d1eeaba 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -415,7 +415,7 @@ static struct ets_class *ets_classify(struct sk_buff *skb, struct Qdisc *sch,
 	return &q->classes[band];
 }
 
-static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
@@ -433,7 +433,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t
 	}
 
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index b4da5b624ad8..a579a4131d22 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -16,7 +16,7 @@
 
 /* 1 band FIFO pseudo-"scheduler" */
 
-static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			 struct sk_buff **to_free)
 {
 	if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit))
@@ -25,7 +25,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *roo
 	return qdisc_drop(skb, sch, to_free);
 }
 
-static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			 struct sk_buff **to_free)
 {
 	if (likely(sch->q.qlen < sch->limit))
@@ -34,7 +34,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *roo
 	return qdisc_drop(skb, sch, to_free);
 }
 
-static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			      struct sk_buff **to_free)
 {
 	unsigned int prev_backlog;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index a90d745c41e0..2fb76fc0cc31 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -439,7 +439,7 @@ static bool fq_packet_beyond_horizon(const struct sk_buff *skb,
 	return unlikely((s64)skb->tstamp > (s64)(q->ktime_cache + q->horizon));
 }
 
-static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		      struct sk_buff **to_free)
 {
 	struct fq_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index bca016ffc069..3106653c17f3 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -181,7 +181,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets,
 	return idx;
 }
 
-static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			    struct sk_buff **to_free)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 741840b9994f..f98c74018805 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -125,7 +125,7 @@ static inline void flow_queue_add(struct fq_pie_flow *flow,
 	skb->next = NULL;
 }
 
-static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 				struct sk_buff **to_free)
 {
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 715cde1df9e4..265a61d011df 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -520,7 +520,7 @@ EXPORT_SYMBOL(netif_carrier_off);
    cheaper.
  */
 
-static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, spinlock_t *root_lock,
+static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 			struct sk_buff **to_free)
 {
 	__qdisc_drop(skb, to_free);
@@ -614,7 +614,7 @@ static inline struct skb_array *band2list(struct pfifo_fast_priv *priv,
 	return &priv->q[band];
 }
 
-static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, spinlock_t *root_lock,
+static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 			      struct sk_buff **to_free)
 {
 	int band = prio2band[skb->priority & TC_PRIO_MAX];
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 7d67c6cd6605..8599c6f31b05 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -161,7 +161,7 @@ static bool gred_per_vq_red_flags_used(struct gred_sched *table)
 	return false;
 }
 
-static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			struct sk_buff **to_free)
 {
 	struct gred_sched_data *q = NULL;
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 13ba8648bb63..0f5f121404f3 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1528,8 +1528,8 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
 	return -1;
 }
 
-static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
-			struct sk_buff **to_free)
+static int
+hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
 	struct hfsc_class *cl;
@@ -1545,7 +1545,7 @@ static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root
 	}
 
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		if (net_xmit_drop_count(err)) {
 			cl->qstats.drops++;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index ddc6bf1d85d0..420ede875322 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -368,7 +368,7 @@ static unsigned int hhf_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return bucket - q->buckets;
 }
 
-static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	struct hhf_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index b07f29059f47..ba37defaca7a 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -576,7 +576,7 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
 	cl->prio_activity = 0;
 }
 
-static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	int uninitialized_var(ret);
@@ -599,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 		__qdisc_drop(skb, to_free);
 		return ret;
 #endif
-	} else if ((ret = qdisc_enqueue(skb, cl->leaf.q, root_lock,
+	} else if ((ret = qdisc_enqueue(skb, cl->leaf.q,
 					to_free)) != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret)) {
 			qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 56bdc4bcdc63..5c27b4270b90 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -57,7 +57,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 }
 
 static int
-multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	       struct sk_buff **to_free)
 {
 	struct Qdisc *qdisc;
@@ -74,7 +74,7 @@ multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc, root_lock, to_free);
+	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 8fb17483a34f..84f82771cdf5 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -431,7 +431,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch,
  * 	NET_XMIT_DROP: queue length didn't change.
  *      NET_XMIT_SUCCESS: one skb was queued.
  */
-static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			 struct sk_buff **to_free)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
@@ -480,7 +480,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *roo
 		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
 
 		q->duplicate = 0;
-		rootq->enqueue(skb2, rootq, root_lock, to_free);
+		rootq->enqueue(skb2, rootq, to_free);
 		q->duplicate = dupsave;
 		rc_drop = NET_XMIT_SUCCESS;
 	}
@@ -604,7 +604,7 @@ finish_segs:
 			skb_mark_not_on_list(segs);
 			qdisc_skb_cb(segs)->pkt_len = segs->len;
 			last_len = segs->len;
-			rc = qdisc_enqueue(segs, sch, root_lock, to_free);
+			rc = qdisc_enqueue(segs, sch, to_free);
 			if (rc != NET_XMIT_SUCCESS) {
 				if (net_xmit_drop_count(rc))
 					qdisc_qstats_drop(sch);
@@ -720,7 +720,7 @@ deliver:
 				struct sk_buff *to_free = NULL;
 				int err;
 
-				err = qdisc_enqueue(skb, q->qdisc, NULL, &to_free);
+				err = qdisc_enqueue(skb, q->qdisc, &to_free);
 				kfree_skb_list(to_free);
 				if (err != NET_XMIT_SUCCESS &&
 				    net_xmit_drop_count(err)) {
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index b305313b64e3..c65077f0c0f3 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -82,7 +82,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params,
 }
 EXPORT_SYMBOL_GPL(pie_drop_early);
 
-static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			     struct sk_buff **to_free)
 {
 	struct pie_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index e5f8b4769b4d..cbc2ebca4548 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -84,7 +84,7 @@ struct plug_sched_data {
 	u32 pkts_to_release;
 };
 
-static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			struct sk_buff **to_free)
 {
 	struct plug_sched_data *q = qdisc_priv(sch);
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 46b7ce81c6e3..3eabb871a1d5 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -65,8 +65,8 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
 	return q->queues[band];
 }
 
-static int prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
-			struct sk_buff **to_free)
+static int
+prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb);
 	struct Qdisc *qdisc;
@@ -83,7 +83,7 @@ static int prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root
 	}
 #endif
 
-	ret = qdisc_enqueue(skb, qdisc, root_lock, to_free);
+	ret = qdisc_enqueue(skb, qdisc, to_free);
 	if (ret == NET_XMIT_SUCCESS) {
 		sch->qstats.backlog += len;
 		sch->q.qlen++;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 3cfe6262eb00..6335230a971e 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1194,7 +1194,7 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q)
 	return agg;
 }
 
-static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	unsigned int len = qdisc_pkt_len(skb), gso_segs;
@@ -1225,7 +1225,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 
 	gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
 	first = !cl->qdisc->q.qlen;
-	err = qdisc_enqueue(skb, cl->qdisc, root_lock, to_free);
+	err = qdisc_enqueue(skb, cl->qdisc, to_free);
 	if (unlikely(err != NET_XMIT_SUCCESS)) {
 		pr_debug("qfq_enqueue: enqueue failed %d\n", err);
 		if (net_xmit_drop_count(err)) {
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index a79602f7fab8..4cc0ad0b1189 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -67,7 +67,7 @@ static int red_use_nodrop(struct red_sched_data *q)
 	return q->flags & TC_RED_NODROP;
 }
 
-static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
@@ -126,7 +126,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 		break;
 	}
 
-	ret = qdisc_enqueue(skb, child, root_lock, to_free);
+	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 356f6d1d30db..da047a37a3bf 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -276,7 +276,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl,
 	return false;
 }
 
-static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 
@@ -399,7 +399,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 	}
 
 enqueue:
-	ret = qdisc_enqueue(skb, child, root_lock, to_free);
+	ret = qdisc_enqueue(skb, child, to_free);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index a1314510dc69..cae5dbbadc1c 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -343,7 +343,7 @@ static int sfq_headdrop(const struct sfq_sched_data *q)
 }
 
 static int
-sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock, struct sk_buff **to_free)
+sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct sfq_sched_data *q = qdisc_priv(sch);
 	unsigned int hash, dropped;
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
index f75f237c4436..7a5e4c454715 100644
--- a/net/sched/sch_skbprio.c
+++ b/net/sched/sch_skbprio.c
@@ -65,7 +65,7 @@ static u16 calc_new_low_prio(const struct skbprio_sched_data *q)
 	return SKBPRIO_MAX_PRIORITY - 1;
 }
 
-static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			  struct sk_buff **to_free)
 {
 	const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1;
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index daef2ff60a98..e981992634dd 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -410,7 +410,7 @@ done:
 	return txtime;
 }
 
-static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			  struct sk_buff **to_free)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
@@ -435,7 +435,7 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *ro
 	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 
-	return qdisc_enqueue(skb, child, root_lock, to_free);
+	return qdisc_enqueue(skb, child, to_free);
 }
 
 static struct sk_buff *taprio_peek_soft(struct Qdisc *sch)
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index c3eb5cdb83a8..78e79029dc63 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -187,7 +187,7 @@ static int tbf_offload_dump(struct Qdisc *sch)
 /* GSO packet is too big, segment it so that tbf can transmit
  * each segment in time
  */
-static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
@@ -206,7 +206,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 		skb_mark_not_on_list(segs);
 		qdisc_skb_cb(segs)->pkt_len = segs->len;
 		len += segs->len;
-		ret = qdisc_enqueue(segs, q->qdisc, root_lock, to_free);
+		ret = qdisc_enqueue(segs, q->qdisc, to_free);
 		if (ret != NET_XMIT_SUCCESS) {
 			if (net_xmit_drop_count(ret))
 				qdisc_qstats_drop(sch);
@@ -221,7 +221,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
 
-static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
+static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		       struct sk_buff **to_free)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
@@ -231,10 +231,10 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_
 	if (qdisc_pkt_len(skb) > q->max_size) {
 		if (skb_is_gso(skb) &&
 		    skb_gso_validate_mac_len(skb, q->max_size))
-			return tbf_segment(skb, sch, root_lock, to_free);
+			return tbf_segment(skb, sch, to_free);
 		return qdisc_drop(skb, sch, to_free);
 	}
-	ret = qdisc_enqueue(skb, q->qdisc, root_lock, to_free);
+	ret = qdisc_enqueue(skb, q->qdisc, to_free);
 	if (ret != NET_XMIT_SUCCESS) {
 		if (net_xmit_drop_count(ret))
 			qdisc_qstats_drop(sch);
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index b586eec2eaeb..2f1f0a378408 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -72,8 +72,8 @@ struct teql_sched_data {
 
 /* "teql*" qdisc routines */
 
-static int teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, spinlock_t *root_lock,
-			struct sk_buff **to_free)
+static int
+teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct teql_sched_data *q = qdisc_priv(sch);
-- 
cgit v1.2.3


From a8b7b2d0b3fc965d823e362840e5451e2eb4a71b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 20 Jul 2020 10:10:41 +0200
Subject: sched: sch_api: add missing rcu read lock to silence the warning

In case the qdisc_match_from_root function() is called from non-rcu path
with rtnl mutex held, a suspiciout rcu usage warning appears:

[  241.504354] =============================
[  241.504358] WARNING: suspicious RCU usage
[  241.504366] 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32 Not tainted
[  241.504370] -----------------------------
[  241.504378] net/sched/sch_api.c:270 RCU-list traversed in non-reader section!!
[  241.504382]
               other info that might help us debug this:
[  241.504388]
               rcu_scheduler_active = 2, debug_locks = 1
[  241.504394] 1 lock held by tc/1391:
[  241.504398]  #0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0
[  241.504431]
               stack backtrace:
[  241.504440] CPU: 0 PID: 1391 Comm: tc Not tainted 5.8.0-rc4-custom-01521-g72a7c7d549c3 #32
[  241.504446] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
[  241.504453] Call Trace:
[  241.504465]  dump_stack+0x100/0x184
[  241.504482]  lockdep_rcu_suspicious+0x153/0x15d
[  241.504499]  qdisc_match_from_root+0x293/0x350

Fix this by passing the rtnl held lockdep condition down to
hlist_for_each_entry_rcu()

Reported-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 11ebba60da3b..2a76a2f5ed88 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -267,7 +267,8 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
 	    root->handle == handle)
 		return root;
 
-	hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle) {
+	hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle,
+				   lockdep_rtnl_is_held()) {
 		if (q->handle == handle)
 			return q;
 	}
-- 
cgit v1.2.3


From 5923b8f7fa218a9bccd730c0a9692635eb2fc740 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Thu, 23 Jul 2020 01:03:01 +0300
Subject: net/sched: cls_flower: Add hash info to flow classification

Adding new cls flower keys for hash value and hash
mask and dissect the hash info from the skb into
the flow key towards flow classication.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'net/sched')

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index acd8e05c2ba5..a4f7ef1de7e7 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -64,6 +64,7 @@ struct fl_flow_key {
 		};
 	} tp_range;
 	struct flow_dissector_key_ct ct;
+	struct flow_dissector_key_hash hash;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -318,6 +319,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
 				    fl_ct_info_to_flower_map,
 				    ARRAY_SIZE(fl_ct_info_to_flower_map));
+		skb_flow_dissect_hash(skb, &mask->dissector, &skb_key);
 		skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
 
 		f = fl_mask_lookup(mask, &skb_key);
@@ -695,6 +697,9 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_CT_LABELS_MASK]	= { .type = NLA_BINARY,
 					    .len = 128 / BITS_PER_BYTE },
 	[TCA_FLOWER_FLAGS]		= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_HASH]		= { .type = NLA_U32 },
+	[TCA_FLOWER_KEY_HASH_MASK]	= { .type = NLA_U32 },
+
 };
 
 static const struct nla_policy
@@ -1626,6 +1631,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 
 	fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip);
 
+	fl_set_key_val(tb, &key->hash.hash, TCA_FLOWER_KEY_HASH,
+		       &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK,
+		       sizeof(key->hash.hash));
+
 	if (tb[TCA_FLOWER_KEY_ENC_OPTS]) {
 		ret = fl_set_enc_opt(tb, key, mask, extack);
 		if (ret)
@@ -1740,6 +1749,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_CT, ct);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_HASH, hash);
 
 	skb_flow_dissector_init(dissector, keys, cnt);
 }
@@ -2960,6 +2971,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 	if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
 		goto nla_put_failure;
 
+	if (fl_dump_key_val(skb, &key->hash.hash, TCA_FLOWER_KEY_HASH,
+			     &mask->hash.hash, TCA_FLOWER_KEY_HASH_MASK,
+			     sizeof(key->hash.hash)))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
-- 
cgit v1.2.3


From 608b4adab17889576c6636311f495b1a52418c69 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 25 Jul 2020 13:17:07 -0700
Subject: net_sched: initialize timer earlier in red_init()

When red_init() fails, red_destroy() is called to clean up.
If the timer is not initialized yet, del_timer_sync() will
complain. So we have to move timer_setup() before any failure.

Reported-and-tested-by: syzbot+6e95a4fabf88dc217145@syzkaller.appspotmail.com
Fixes: aee9caa03fc3 ("net: sched: sch_red: Add qevents "early_drop" and "mark"")
Cc: Petr Machata <petrm@mellanox.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_red.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 4cc0ad0b1189..deac82f3ad7b 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -333,6 +333,10 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 	struct nlattr *tb[TCA_RED_MAX + 1];
 	int err;
 
+	q->qdisc = &noop_qdisc;
+	q->sch = sch;
+	timer_setup(&q->adapt_timer, red_adaptative_timer, 0);
+
 	if (!opt)
 		return -EINVAL;
 
@@ -341,10 +345,6 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		return err;
 
-	q->qdisc = &noop_qdisc;
-	q->sch = sch;
-	timer_setup(&q->adapt_timer, red_adaptative_timer, 0);
-
 	err = __red_change(sch, tb, extack);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From a0d716d8e42abcb973afed27c6fa44bd146d2616 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 29 Jul 2020 22:17:00 -0500
Subject: net/sched: act_pedit: Use flex_array_size() helper in memcpy()

Make use of the flex_array_size() helper to calculate the size of a
flexible array member within an enclosing structure.

This helper offers defense-in-depth against potential integer
overflows, while at the same time makes it explicitly clear that
we are dealing with a flexible array member.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 66986db062ed..c158bfed86d5 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -436,8 +436,7 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 		return -ENOBUFS;
 
 	spin_lock_bh(&p->tcf_lock);
-	memcpy(opt->keys, p->tcfp_keys,
-	       p->tcfp_nkeys * sizeof(struct tc_pedit_key));
+	memcpy(opt->keys, p->tcfp_keys, flex_array_size(opt, keys, p->tcfp_nkeys));
 	opt->index = p->tcf_index;
 	opt->nkeys = p->tcfp_nkeys;
 	opt->flags = p->tcfp_flags;
-- 
cgit v1.2.3


From 77aec5e1c4935e37c8cbb818a69f2f7d3433ede5 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 30 Jul 2020 11:03:14 -0500
Subject: net/sched: cls_u32: Use struct_size() helper

Make use of the struct_size() helper, in multiple places, instead
of an open-coded version in order to avoid any potential type
mistakes and protect against potential integer overflows.

Also, remove unnecessary object identifier size.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 771b068f8254..7b69ab1993ba 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -852,9 +852,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	u32 htid, flags = 0;
 	size_t sel_size;
 	int err;
-#ifdef CONFIG_CLS_U32_PERF
-	size_t size;
-#endif
 
 	if (!opt) {
 		if (handle) {
@@ -1022,15 +1019,15 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		goto erridr;
 	}
 
-	n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL);
+	n = kzalloc(struct_size(n, sel.keys, s->nkeys), GFP_KERNEL);
 	if (n == NULL) {
 		err = -ENOBUFS;
 		goto erridr;
 	}
 
 #ifdef CONFIG_CLS_U32_PERF
-	size = sizeof(struct tc_u32_pcnt) + s->nkeys * sizeof(u64);
-	n->pf = __alloc_percpu(size, __alignof__(struct tc_u32_pcnt));
+	n->pf = __alloc_percpu(struct_size(n->pf, kcnts, s->nkeys),
+			       __alignof__(struct tc_u32_pcnt));
 	if (!n->pf) {
 		err = -ENOBUFS;
 		goto errfree;
@@ -1294,8 +1291,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		int cpu;
 #endif
 
-		if (nla_put(skb, TCA_U32_SEL,
-			    sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key),
+		if (nla_put(skb, TCA_U32_SEL, struct_size(&n->sel, keys, n->sel.nkeys),
 			    &n->sel))
 			goto nla_put_failure;
 
@@ -1345,9 +1341,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
 				goto nla_put_failure;
 		}
 #ifdef CONFIG_CLS_U32_PERF
-		gpf = kzalloc(sizeof(struct tc_u32_pcnt) +
-			      n->sel.nkeys * sizeof(u64),
-			      GFP_KERNEL);
+		gpf = kzalloc(struct_size(gpf, kcnts, n->sel.nkeys), GFP_KERNEL);
 		if (!gpf)
 			goto nla_put_failure;
 
@@ -1361,9 +1355,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
 				gpf->kcnts[i] += pf->kcnts[i];
 		}
 
-		if (nla_put_64bit(skb, TCA_U32_PCNT,
-				  sizeof(struct tc_u32_pcnt) +
-				  n->sel.nkeys * sizeof(u64),
+		if (nla_put_64bit(skb, TCA_U32_PCNT, struct_size(gpf, kcnts, n->sel.nkeys),
 				  gpf, TCA_U32_PAD)) {
 			kfree(gpf);
 			goto nla_put_failure;
-- 
cgit v1.2.3


From 038ebb1a713d114d54dbf14868a73181c0c92758 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Fri, 31 Jul 2020 10:45:01 +0800
Subject: net/sched: act_ct: fix miss set mru for ovs after defrag in act_ct

When openvswitch conntrack offload with act_ct action. Fragment packets
defrag in the ingress tc act_ct action and miss the next chain. Then the
packet pass to the openvswitch datapath without the mru. The over
mtu packet will be dropped in output action in openvswitch for over mtu.

"kernel: net2: dropped over-mtu packet: 1528 > 1500"

This patch add mru in the tc_skb_ext for adefrag and miss next chain
situation. And also add mru in the qdisc_skb_cb. The act_ct set the mru
to the qdisc_skb_cb when the packet defrag. And When the chain miss,
The mru is set to tc_skb_ext which can be got by ovs datapath.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c  | 8 ++++++--
 net/sched/cls_api.c | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'net/sched')

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 97e27946897f..e6ad42b11835 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -706,8 +706,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IPCB(skb)->frag_max_size;
+		}
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 		enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
@@ -717,8 +719,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		if (err && err != -EINPROGRESS)
 			goto out_free;
 
-		if (!err)
+		if (!err) {
 			*defrag = true;
+			cb.mru = IP6CB(skb)->frag_max_size;
+		}
 #else
 		err = -EOPNOTSUPP;
 		goto out_free;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0b8623b3b24f..41a55c6cbeb8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb,
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
+		ext->mru = qdisc_skb_cb(skb)->mru;
 	}
 
 	return ret;
-- 
cgit v1.2.3