Merge branch 'netem-use-a-seeded-prng-for-loss-and-corruption-events'

François Michel says:

====================
netem: use a seeded PRNG for loss and corruption events

In order to reproduce bugs or performance evaluation of
network protocols and applications, it is useful to have
reproducible test suites and tools. This patch adds
a way to specify a PRNG seed through the
TCA_NETEM_PRNG_SEED attribute for generating netem
loss and corruption events. Initializing the qdisc
with the same seed leads to the exact same loss
and corruption patterns. If no seed is explicitly
specified, the qdisc generates a random seed using
get_random_u64().

This patch can be and has been tested using tc from
the following iproute2-next fork:
https://github.com/francoismichel/iproute2-next

For instance, setting the seed 42424242 on the loopback
with a loss rate of 10% will systematically drop the 5th,
12th and 24th packet when sending 25 packets.
====================

Link: https://lore.kernel.org/r/20230815092348.1449179-1-francois.michel@uclouvain.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 35 insertions, 15 deletions

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 00f6ff0aff1ff..3f85ae5780563 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -603,6 +603,7 @@ enum {
 	TCA_NETEM_JITTER64,
 	TCA_NETEM_SLOT,
 	TCA_NETEM_SLOT_DIST,
+	TCA_NETEM_PRNG_SEED,
 	__TCA_NETEM_MAX,
 };
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 38d9aa0cd30e7..4ad39a4a3cf5b 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -105,6 +105,11 @@ struct netem_sched_data {
 		u32 rho;
 	} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
 
+	struct prng  {
+		u64 seed;
+		struct rnd_state prng_state;
+	} prng;
+
 	struct disttable *delay_dist;
 
 	enum  {
@@ -179,15 +184,16 @@ static void init_crandom(struct crndstate *state, unsigned long rho)
  * Next number depends on last value.
  * rho is scaled to avoid floating point.
  */
-static u32 get_crandom(struct crndstate *state)
+static u32 get_crandom(struct crndstate *state, struct prng *p)
 {
 	u64 value, rho;
 	unsigned long answer;
+	struct rnd_state *s = &p->prng_state;
 
 	if (!state || state->rho == 0)	/* no correlation */
-		return get_random_u32();
+		return prandom_u32_state(s);
 
-	value = get_random_u32();
+	value = prandom_u32_state(s);
 	rho = (u64)state->rho + 1;
 	answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32;
 	state->last = answer;
@@ -201,7 +207,7 @@ static u32 get_crandom(struct crndstate *state)
 static bool loss_4state(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
-	u32 rnd = get_random_u32();
+	u32 rnd = prandom_u32_state(&q->prng.prng_state);
 
 	/*
 	 * Makes a comparison between rnd and the transition
@@ -266,18 +272,19 @@ static bool loss_4state(struct netem_sched_data *q)
 static bool loss_gilb_ell(struct netem_sched_data *q)
 {
 	struct clgstate *clg = &q->clg;
+	struct rnd_state *s = &q->prng.prng_state;
 
 	switch (clg->state) {
 	case GOOD_STATE:
-		if (get_random_u32() < clg->a1)
+		if (prandom_u32_state(s) < clg->a1)
 			clg->state = BAD_STATE;
-		if (get_random_u32() < clg->a4)
+		if (prandom_u32_state(s) < clg->a4)
 			return true;
 		break;
 	case BAD_STATE:
-		if (get_random_u32() < clg->a2)
+		if (prandom_u32_state(s) < clg->a2)
 			clg->state = GOOD_STATE;
-		if (get_random_u32() > clg->a3)
+		if (prandom_u32_state(s) > clg->a3)
 			return true;
 	}
 
@@ -289,7 +296,7 @@ static bool loss_event(struct netem_sched_data *q)
 	switch (q->loss_model) {
 	case CLG_RANDOM:
 		/* Random packet drop 0 => none, ~0 => all */
-		return q->loss && q->loss >= get_crandom(&q->loss_cor);
+		return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng);
 
 	case CLG_4_STATES:
 		/* 4state loss model algorithm (used also for GI model)
@@ -318,6 +325,7 @@ static bool loss_event(struct netem_sched_data *q)
  */
 static s64 tabledist(s64 mu, s32 sigma,
 		     struct crndstate *state,
+		     struct prng *prng,
 		     const struct disttable *dist)
 {
 	s64 x;
@@ -327,7 +335,7 @@ static s64 tabledist(s64 mu, s32 sigma,
 	if (sigma == 0)
 		return mu;
 
-	rnd = get_crandom(state);
+	rnd = get_crandom(state, prng);
 
 	/* default uniform distribution */
 	if (dist == NULL)
@@ -449,7 +457,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	skb->prev = NULL;
 
 	/* Random duplication */
-	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
+	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng))
 		++count;
 
 	/* Drop packet? */
@@ -492,7 +500,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	 * If packet is going to be hardware checksummed, then
 	 * do it now in software before we mangle it.
 	 */
-	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) {
+	if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) {
 		if (skb_is_gso(skb)) {
 			skb = netem_segment(skb, sch, to_free);
 			if (!skb)
@@ -530,12 +538,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	cb = netem_skb_cb(skb);
 	if (q->gap == 0 ||		/* not doing reordering */
 	    q->counter < q->gap - 1 ||	/* inside last reordering gap */
-	    q->reorder < get_crandom(&q->reorder_cor)) {
+	    q->reorder < get_crandom(&q->reorder_cor, &q->prng)) {
 		u64 now;
 		s64 delay;
 
 		delay = tabledist(q->latency, q->jitter,
-				  &q->delay_cor, q->delay_dist);
+				  &q->delay_cor, &q->prng, q->delay_dist);
 
 		now = ktime_get_ns();
 
@@ -639,7 +647,7 @@ static void get_slot_next(struct netem_sched_data *q, u64 now)
 	else
 		next_delay = tabledist(q->slot_config.dist_delay,
 				       (s32)(q->slot_config.dist_jitter),
-				       NULL, q->slot_dist);
+				       NULL, &q->prng, q->slot_dist);
 
 	q->slot.slot_next = now + next_delay;
 	q->slot.packets_left = q->slot_config.max_packets;
@@ -922,6 +930,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_LATENCY64]	= { .type = NLA_S64 },
 	[TCA_NETEM_JITTER64]	= { .type = NLA_S64 },
 	[TCA_NETEM_SLOT]	= { .len = sizeof(struct tc_netem_slot) },
+	[TCA_NETEM_PRNG_SEED]	= { .type = NLA_U64 },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -1040,6 +1049,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	/* capping jitter to the range acceptable by tabledist() */
 	q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
 
+	if (tb[TCA_NETEM_PRNG_SEED])
+		q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]);
+	else
+		q->prng.seed = get_random_u64();
+	prandom_seed_state(&q->prng.prng_state, q->prng.seed);
+
 unlock:
 	sch_tree_unlock(sch);
 
@@ -1203,6 +1218,10 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 			goto nla_put_failure;
 	}
 
+	if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed,
+			      TCA_NETEM_PAD))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, nla);
 
 nla_put_failure: