Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 74c0f65..42e557d 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1,11 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* net/sched/sch_netem.c Network emulator
*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License.
- *
* Many of the algorithms and ideas for this came from
* NIST Net which is not copyrighted.
*
@@ -77,6 +73,10 @@
/* internal t(ime)fifo qdisc uses t_root and sch->limit */
struct rb_root t_root;
+ /* a linear queue; reduces rbtree rebalancing when jitter is low */
+ struct sk_buff *t_head;
+ struct sk_buff *t_tail;
+
/* optional qdisc for classful handling (NULL at netem init) */
struct Qdisc *qdisc;
@@ -369,26 +369,39 @@
rb_erase(&skb->rbnode, &q->t_root);
rtnl_kfree_skbs(skb, skb);
}
+
+ rtnl_kfree_skbs(q->t_head, q->t_tail);
+ q->t_head = NULL;
+ q->t_tail = NULL;
}
static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
u64 tnext = netem_skb_cb(nskb)->time_to_send;
- struct rb_node **p = &q->t_root.rb_node, *parent = NULL;
- while (*p) {
- struct sk_buff *skb;
-
- parent = *p;
- skb = rb_to_skb(parent);
- if (tnext >= netem_skb_cb(skb)->time_to_send)
- p = &parent->rb_right;
+ if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) {
+ if (q->t_tail)
+ q->t_tail->next = nskb;
else
- p = &parent->rb_left;
+ q->t_head = nskb;
+ q->t_tail = nskb;
+ } else {
+ struct rb_node **p = &q->t_root.rb_node, *parent = NULL;
+
+ while (*p) {
+ struct sk_buff *skb;
+
+ parent = *p;
+ skb = rb_to_skb(parent);
+ if (tnext >= netem_skb_cb(skb)->time_to_send)
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+ rb_link_node(&nskb->rbnode, parent, p);
+ rb_insert_color(&nskb->rbnode, &q->t_root);
}
- rb_link_node(&nskb->rbnode, parent, p);
- rb_insert_color(&nskb->rbnode, &q->t_root);
sch->q.qlen++;
}
@@ -412,16 +425,6 @@
return segs;
}
-static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb)
-{
- skb->next = qh->head;
-
- if (!qh->head)
- qh->tail = skb;
- qh->head = skb;
- qh->qlen++;
-}
-
/*
* Insert one skb into qdisc.
* Note: parent depends on return value to account for queue length.
@@ -436,10 +439,10 @@
struct netem_skb_cb *cb;
struct sk_buff *skb2;
struct sk_buff *segs = NULL;
- unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb);
- int nb = 0;
+ unsigned int prev_len = qdisc_pkt_len(skb);
int count = 1;
int rc = NET_XMIT_SUCCESS;
+ int rc_drop = NET_XMIT_DROP;
/* Do not fool qdisc_drop_all() */
skb->prev = NULL;
@@ -473,12 +476,13 @@
* skb will be queued.
*/
if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
- struct Qdisc *rootq = qdisc_root(sch);
+ struct Qdisc *rootq = qdisc_root_bh(sch);
u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
q->duplicate = 0;
rootq->enqueue(skb2, rootq, to_free);
q->duplicate = dupsave;
+ rc_drop = NET_XMIT_SUCCESS;
}
/*
@@ -489,16 +493,14 @@
*/
if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
if (skb_is_gso(skb)) {
- segs = netem_segment(skb, sch, to_free);
- if (!segs)
- return NET_XMIT_DROP;
- } else {
- segs = skb;
+ skb = netem_segment(skb, sch, to_free);
+ if (!skb)
+ return rc_drop;
+ segs = skb->next;
+ skb_mark_not_on_list(skb);
+ qdisc_skb_cb(skb)->pkt_len = skb->len;
}
- skb = segs;
- segs = segs->next;
-
skb = skb_unshare(skb, GFP_ATOMIC);
if (unlikely(!skb)) {
qdisc_qstats_drop(sch);
@@ -507,6 +509,7 @@
if (skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_help(skb)) {
qdisc_drop(skb, sch, to_free);
+ skb = NULL;
goto finish_segs;
}
@@ -514,8 +517,12 @@
1<<(prandom_u32() % 8);
}
- if (unlikely(sch->q.qlen >= sch->limit))
- return qdisc_drop_all(skb, sch, to_free);
+ if (unlikely(sch->q.qlen >= sch->limit)) {
+ /* re-link segs, so that qdisc_drop_all() frees them all */
+ skb->next = segs;
+ qdisc_drop_all(skb, sch, to_free);
+ return rc_drop;
+ }
qdisc_qstats_backlog_inc(sch, skb);
@@ -543,9 +550,16 @@
t_skb = skb_rb_last(&q->t_root);
t_last = netem_skb_cb(t_skb);
if (!last ||
- t_last->time_to_send > last->time_to_send) {
+ t_last->time_to_send > last->time_to_send)
last = t_last;
- }
+ }
+ if (q->t_tail) {
+ struct netem_skb_cb *t_last =
+ netem_skb_cb(q->t_tail);
+
+ if (!last ||
+ t_last->time_to_send > last->time_to_send)
+ last = t_last;
}
if (last) {
@@ -573,15 +587,21 @@
cb->time_to_send = ktime_get_ns();
q->counter = 0;
- netem_enqueue_skb_head(&sch->q, skb);
+ __qdisc_enqueue_head(skb, &sch->q);
sch->qstats.requeues++;
}
finish_segs:
if (segs) {
+ unsigned int len, last_len;
+ int nb;
+
+ len = skb ? skb->len : 0;
+ nb = skb ? 1 : 0;
+
while (segs) {
skb2 = segs->next;
- segs->next = NULL;
+ 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);
@@ -594,9 +614,10 @@
}
segs = skb2;
}
- sch->q.qlen += nb;
- if (nb > 1)
- qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len);
+ /* Parent qdiscs accounted for 1 skb of size @prev_len */
+ qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len));
+ } else if (!skb) {
+ return NET_XMIT_DROP;
}
return NET_XMIT_SUCCESS;
}
@@ -624,11 +645,38 @@
q->slot.bytes_left = q->slot_config.max_bytes;
}
+static struct sk_buff *netem_peek(struct netem_sched_data *q)
+{
+ struct sk_buff *skb = skb_rb_first(&q->t_root);
+ u64 t1, t2;
+
+ if (!skb)
+ return q->t_head;
+ if (!q->t_head)
+ return skb;
+
+ t1 = netem_skb_cb(skb)->time_to_send;
+ t2 = netem_skb_cb(q->t_head)->time_to_send;
+ if (t1 < t2)
+ return skb;
+ return q->t_head;
+}
+
+static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb)
+{
+ if (skb == q->t_head) {
+ q->t_head = skb->next;
+ if (!q->t_head)
+ q->t_tail = NULL;
+ } else {
+ rb_erase(&skb->rbnode, &q->t_root);
+ }
+}
+
static struct sk_buff *netem_dequeue(struct Qdisc *sch)
{
struct netem_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
- struct rb_node *p;
tfifo_dequeue:
skb = __qdisc_dequeue_head(&sch->q);
@@ -638,20 +686,18 @@
qdisc_bstats_update(sch, skb);
return skb;
}
- p = rb_first(&q->t_root);
- if (p) {
+ skb = netem_peek(q);
+ if (skb) {
u64 time_to_send;
u64 now = ktime_get_ns();
- skb = rb_to_skb(p);
-
/* if more time remaining? */
time_to_send = netem_skb_cb(skb)->time_to_send;
if (q->slot.slot_next && q->slot.slot_next < time_to_send)
get_slot_next(q, now);
- if (time_to_send <= now && q->slot.slot_next <= now) {
- rb_erase(p, &q->t_root);
+ if (time_to_send <= now && q->slot.slot_next <= now) {
+ netem_erase_head(q, skb);
sch->q.qlen--;
qdisc_qstats_backlog_dec(sch, skb);
skb->next = NULL;
@@ -661,15 +707,6 @@
*/
skb->dev = qdisc_dev(sch);
-#ifdef CONFIG_NET_CLS_ACT
- /*
- * If it's at ingress let's pretend the delay is
- * from the network (tstamp will be updated).
- */
- if (skb->tc_redirected && skb->tc_from_ingress)
- skb->tstamp = 0;
-#endif
-
if (q->slot.slot_next) {
q->slot.packets_left--;
q->slot.bytes_left -= qdisc_pkt_len(skb);
@@ -745,7 +782,7 @@
struct disttable *d;
int i;
- if (n > NETEM_DIST_MAX)
+ if (!n || n > NETEM_DIST_MAX)
return -EINVAL;
d = kvmalloc(sizeof(struct disttable) + n * sizeof(s16), GFP_KERNEL);
@@ -901,8 +938,9 @@
}
if (nested_len >= nla_attr_size(0))
- return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
- nested_len, policy, NULL);
+ return nla_parse_deprecated(tb, maxtype,
+ nla_data(nla) + NLA_ALIGN(len),
+ nested_len, policy, NULL);
memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
return 0;
@@ -1035,7 +1073,7 @@
qdisc_watchdog_cancel(&q->watchdog);
if (q->qdisc)
- qdisc_destroy(q->qdisc);
+ qdisc_put(q->qdisc);
dist_free(q->delay_dist);
dist_free(q->slot_dist);
}
@@ -1045,7 +1083,7 @@
{
struct nlattr *nest;
- nest = nla_nest_start(skb, TCA_NETEM_LOSS);
+ nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS);
if (nest == NULL)
goto nla_put_failure;