summaryrefslogtreecommitdiff
path: root/net/sched/sch_netem.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched/sch_netem.c')
-rw-r--r--net/sched/sch_netem.c96
1 files changed, 54 insertions, 42 deletions
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 5da548fa7ae9..298c0ddfb57e 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -26,6 +26,7 @@
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/inet_ecn.h>
#define VERSION "1.3"
@@ -78,6 +79,7 @@ struct netem_sched_data {
psched_tdiff_t jitter;
u32 loss;
+ u32 ecn;
u32 limit;
u32 counter;
u32 gap;
@@ -329,29 +331,22 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche
return PSCHED_NS2TICKS(ticks);
}
-static int tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
+static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch)
{
struct sk_buff_head *list = &sch->q;
psched_time_t tnext = netem_skb_cb(nskb)->time_to_send;
- struct sk_buff *skb;
-
- if (likely(skb_queue_len(list) < sch->limit)) {
- skb = skb_peek_tail(list);
- /* Optimize for add at tail */
- if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send))
- return qdisc_enqueue_tail(nskb, sch);
+ struct sk_buff *skb = skb_peek_tail(list);
- skb_queue_reverse_walk(list, skb) {
- if (tnext >= netem_skb_cb(skb)->time_to_send)
- break;
- }
+ /* Optimize for add at tail */
+ if (likely(!skb || tnext >= netem_skb_cb(skb)->time_to_send))
+ return __skb_queue_tail(list, nskb);
- __skb_queue_after(list, skb, nskb);
- sch->qstats.backlog += qdisc_pkt_len(nskb);
- return NET_XMIT_SUCCESS;
+ skb_queue_reverse_walk(list, skb) {
+ if (tnext >= netem_skb_cb(skb)->time_to_send)
+ break;
}
- return qdisc_reshape_fail(nskb, sch);
+ __skb_queue_after(list, skb, nskb);
}
/*
@@ -366,7 +361,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
/* We don't fill cb now as skb_unshare() may invalidate it */
struct netem_skb_cb *cb;
struct sk_buff *skb2;
- int ret;
int count = 1;
/* Random duplication */
@@ -374,16 +368,26 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
++count;
/* Drop packet? */
- if (loss_event(q))
- --count;
-
+ if (loss_event(q)) {
+ if (q->ecn && INET_ECN_set_ce(skb))
+ sch->qstats.drops++; /* mark packet */
+ else
+ --count;
+ }
if (count == 0) {
sch->qstats.drops++;
kfree_skb(skb);
return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
}
- skb_orphan(skb);
+ /* If a delay is expected, orphan the skb. (orphaning usually takes
+ * place at TX completion time, so _before_ the link transit delay)
+ * Ideally, this orphaning should be done after the rate limiting
+ * module, because this breaks TCP Small Queue, and other mechanisms
+ * based on socket sk_wmem_alloc.
+ */
+ if (q->latency || q->jitter)
+ skb_orphan(skb);
/*
* If we need to duplicate packet, then re-insert at top of the
@@ -408,14 +412,17 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
if (!(skb = skb_unshare(skb, GFP_ATOMIC)) ||
(skb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_help(skb))) {
- sch->qstats.drops++;
- return NET_XMIT_DROP;
- }
+ skb_checksum_help(skb)))
+ return qdisc_drop(skb, sch);
skb->data[net_random() % skb_headlen(skb)] ^= 1<<(net_random() % 8);
}
+ if (unlikely(skb_queue_len(&sch->q) >= sch->limit))
+ return qdisc_reshape_fail(skb, sch);
+
+ sch->qstats.backlog += qdisc_pkt_len(skb);
+
cb = netem_skb_cb(skb);
if (q->gap == 0 || /* not doing reordering */
q->counter < q->gap - 1 || /* inside last reordering gap */
@@ -447,7 +454,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
cb->time_to_send = now + delay;
++q->counter;
- ret = tfifo_enqueue(skb, sch);
+ tfifo_enqueue(skb, sch);
} else {
/*
* Do re-ordering by putting one out of N packets at the front
@@ -457,16 +464,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
q->counter = 0;
__skb_queue_head(&sch->q, skb);
- sch->qstats.backlog += qdisc_pkt_len(skb);
sch->qstats.requeues++;
- ret = NET_XMIT_SUCCESS;
- }
-
- if (ret != NET_XMIT_SUCCESS) {
- if (net_xmit_drop_count(ret)) {
- sch->qstats.drops++;
- return ret;
- }
}
return NET_XMIT_SUCCESS;
@@ -706,6 +704,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
[TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) },
[TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) },
[TCA_NETEM_LOSS] = { .type = NLA_NESTED },
+ [TCA_NETEM_ECN] = { .type = NLA_U32 },
};
static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -776,6 +775,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
if (tb[TCA_NETEM_RATE])
get_rate(sch, tb[TCA_NETEM_RATE]);
+ if (tb[TCA_NETEM_ECN])
+ q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]);
+
q->loss_model = CLG_RANDOM;
if (tb[TCA_NETEM_LOSS])
ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
@@ -834,7 +836,8 @@ static int dump_loss_model(const struct netem_sched_data *q,
.p23 = q->clg.a5,
};
- NLA_PUT(skb, NETEM_LOSS_GI, sizeof(gi), &gi);
+ if (nla_put(skb, NETEM_LOSS_GI, sizeof(gi), &gi))
+ goto nla_put_failure;
break;
}
case CLG_GILB_ELL: {
@@ -845,7 +848,8 @@ static int dump_loss_model(const struct netem_sched_data *q,
.k1 = q->clg.a4,
};
- NLA_PUT(skb, NETEM_LOSS_GE, sizeof(ge), &ge);
+ if (nla_put(skb, NETEM_LOSS_GE, sizeof(ge), &ge))
+ goto nla_put_failure;
break;
}
}
@@ -874,26 +878,34 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
qopt.loss = q->loss;
qopt.gap = q->gap;
qopt.duplicate = q->duplicate;
- NLA_PUT(skb, TCA_OPTIONS, sizeof(qopt), &qopt);
+ if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt))
+ goto nla_put_failure;
cor.delay_corr = q->delay_cor.rho;
cor.loss_corr = q->loss_cor.rho;
cor.dup_corr = q->dup_cor.rho;
- NLA_PUT(skb, TCA_NETEM_CORR, sizeof(cor), &cor);
+ if (nla_put(skb, TCA_NETEM_CORR, sizeof(cor), &cor))
+ goto nla_put_failure;
reorder.probability = q->reorder;
reorder.correlation = q->reorder_cor.rho;
- NLA_PUT(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder);
+ if (nla_put(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder))
+ goto nla_put_failure;
corrupt.probability = q->corrupt;
corrupt.correlation = q->corrupt_cor.rho;
- NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt);
+ if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt))
+ goto nla_put_failure;
rate.rate = q->rate;
rate.packet_overhead = q->packet_overhead;
rate.cell_size = q->cell_size;
rate.cell_overhead = q->cell_overhead;
- NLA_PUT(skb, TCA_NETEM_RATE, sizeof(rate), &rate);
+ if (nla_put(skb, TCA_NETEM_RATE, sizeof(rate), &rate))
+ goto nla_put_failure;
+
+ if (q->ecn && nla_put_u32(skb, TCA_NETEM_ECN, q->ecn))
+ goto nla_put_failure;
if (dump_loss_model(q, skb) != 0)
goto nla_put_failure;
generated by cgit v1.2.3 (git 2.0.4) at 2025-09-14 16:13:01 +0000