1 files changed, 76 insertions, 46 deletions

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 436160be9c18..dc187c7f06b1 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -91,7 +91,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch,
 		return fq_codel_hash(q, skb) + 1;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
-	result = tcf_classify(skb, filter, &res, false);
+	result = tcf_classify(skb, NULL, filter, &res, false);
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -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;
 		}
@@ -168,6 +168,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets,
 		skb = dequeue_head(flow);
 		len += qdisc_pkt_len(skb);
 		mem += get_codel_cb(skb)->mem_usage;
+		tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_OVERLIMIT);
 		__qdisc_drop(skb, to_free);
 	} while (++i < max_packets && len < threshold);
 
@@ -187,7 +188,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	unsigned int idx, prev_backlog, prev_qlen;
 	struct fq_codel_flow *flow;
-	int uninitialized_var(ret);
+	int ret;
 	unsigned int pkt_len;
 	bool memory_limited;
 
@@ -274,7 +275,7 @@ static void drop_func(struct sk_buff *skb, void *ctx)
 {
 	struct Qdisc *sch = ctx;
 
-	kfree_skb(skb);
+	qdisc_dequeue_drop(sch, skb, SKB_DROP_REASON_QDISC_CONGESTED);
 	qdisc_qstats_drop(sch);
 }
 
@@ -314,10 +315,8 @@ begin:
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
-	 * or HTB crashes. Defer it for next round.
-	 */
-	if (q->cstats.drop_count && sch->q.qlen) {
+
+	if (q->cstats.drop_count) {
 		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
 					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;
@@ -347,8 +346,6 @@ static void fq_codel_reset(struct Qdisc *sch)
 		codel_vars_init(&flow->cvars);
 	}
 	memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
-	sch->q.qlen = 0;
-	sch->qstats.backlog = 0;
 	q->memory_usage = 0;
 }
 
@@ -362,18 +359,19 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
 	[TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 },
 	[TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 },
 	[TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 },
+	[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR] = { .type = NLA_U8 },
+	[TCA_FQ_CODEL_CE_THRESHOLD_MASK] = { .type = NLA_U8 },
 };
 
 static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 			   struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_CODEL_MAX + 1];
+	u32 quantum = 0;
 	int err;
 
-	if (!opt)
-		return -EINVAL;
-
 	err = nla_parse_nested_deprecated(tb, TCA_FQ_CODEL_MAX, opt,
 					  fq_codel_policy, NULL);
 	if (err < 0)
@@ -386,52 +384,74 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 		    q->flows_cnt > 65536)
 			return -EINVAL;
 	}
+	if (tb[TCA_FQ_CODEL_QUANTUM]) {
+		quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
+		if (quantum > FQ_CODEL_QUANTUM_MAX) {
+			NL_SET_ERR_MSG(extack, "Invalid quantum");
+			return -EINVAL;
+		}
+	}
 	sch_tree_lock(sch);
 
 	if (tb[TCA_FQ_CODEL_TARGET]) {
 		u64 target = nla_get_u32(tb[TCA_FQ_CODEL_TARGET]);
 
-		q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT;
+		WRITE_ONCE(q->cparams.target,
+			   (target * NSEC_PER_USEC) >> CODEL_SHIFT);
 	}
 
 	if (tb[TCA_FQ_CODEL_CE_THRESHOLD]) {
 		u64 val = nla_get_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]);
 
-		q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT;
+		WRITE_ONCE(q->cparams.ce_threshold,
+			   (val * NSEC_PER_USEC) >> CODEL_SHIFT);
 	}
 
+	if (tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR])
+		WRITE_ONCE(q->cparams.ce_threshold_selector,
+			   nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]));
+	if (tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK])
+		WRITE_ONCE(q->cparams.ce_threshold_mask,
+			   nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]));
+
 	if (tb[TCA_FQ_CODEL_INTERVAL]) {
 		u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]);
 
-		q->cparams.interval = (interval * NSEC_PER_USEC) >> CODEL_SHIFT;
+		WRITE_ONCE(q->cparams.interval,
+			   (interval * NSEC_PER_USEC) >> CODEL_SHIFT);
 	}
 
 	if (tb[TCA_FQ_CODEL_LIMIT])
-		sch->limit = nla_get_u32(tb[TCA_FQ_CODEL_LIMIT]);
+		WRITE_ONCE(sch->limit,
+			   nla_get_u32(tb[TCA_FQ_CODEL_LIMIT]));
 
 	if (tb[TCA_FQ_CODEL_ECN])
-		q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]);
+		WRITE_ONCE(q->cparams.ecn,
+			   !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]));
 
-	if (tb[TCA_FQ_CODEL_QUANTUM])
-		q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
+	if (quantum)
+		WRITE_ONCE(q->quantum, quantum);
 
 	if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
-		q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
+		WRITE_ONCE(q->drop_batch_size,
+			   max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])));
 
 	if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
-		q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]));
+		WRITE_ONCE(q->memory_limit,
+			   min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])));
 
 	while (sch->q.qlen > sch->limit ||
 	       q->memory_usage > q->memory_limit) {
-		struct sk_buff *skb = fq_codel_dequeue(sch);
+		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
-		q->cstats.drop_len += qdisc_pkt_len(skb);
+		if (!skb)
+			break;
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_kfree_skbs(skb, skb);
-		q->cstats.drop_count++;
 	}
-	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
-	q->cstats.drop_count = 0;
-	q->cstats.drop_len = 0;
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return 0;
@@ -499,6 +519,9 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 		sch->flags |= TCQ_F_CAN_BYPASS;
 	else
 		sch->flags &= ~TCQ_F_CAN_BYPASS;
+
+	sch->flags |= TCQ_F_DEQUEUE_DROPS;
+
 	return 0;
 
 alloc_failure:
@@ -512,6 +535,7 @@ init_failure:
 static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
+	codel_time_t ce_threshold;
 	struct nlattr *opts;
 
 	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
@@ -519,27 +543,35 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, TCA_FQ_CODEL_TARGET,
-			codel_time_to_us(q->cparams.target)) ||
+			codel_time_to_us(READ_ONCE(q->cparams.target))) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_LIMIT,
-			sch->limit) ||
+			READ_ONCE(sch->limit)) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_INTERVAL,
-			codel_time_to_us(q->cparams.interval)) ||
+			codel_time_to_us(READ_ONCE(q->cparams.interval))) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_ECN,
-			q->cparams.ecn) ||
+			READ_ONCE(q->cparams.ecn)) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_QUANTUM,
-			q->quantum) ||
+			READ_ONCE(q->quantum)) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_DROP_BATCH_SIZE,
-			q->drop_batch_size) ||
+			READ_ONCE(q->drop_batch_size)) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_MEMORY_LIMIT,
-			q->memory_limit) ||
+			READ_ONCE(q->memory_limit)) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_FLOWS,
-			q->flows_cnt))
+			READ_ONCE(q->flows_cnt)))
 		goto nla_put_failure;
 
-	if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD &&
-	    nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD,
-			codel_time_to_us(q->cparams.ce_threshold)))
-		goto nla_put_failure;
+	ce_threshold = READ_ONCE(q->cparams.ce_threshold);
+	if (ce_threshold != CODEL_DISABLED_THRESHOLD) {
+		if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD,
+				codel_time_to_us(ce_threshold)))
+			goto nla_put_failure;
+		if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR,
+			       READ_ONCE(q->cparams.ce_threshold_selector)))
+			goto nla_put_failure;
+		if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK,
+			       READ_ONCE(q->cparams.ce_threshold_mask)))
+			goto nla_put_failure;
+	}
 
 	return nla_nest_end(skb, opts);
 
@@ -667,16 +699,12 @@ static void fq_codel_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 		return;
 
 	for (i = 0; i < q->flows_cnt; i++) {
-		if (list_empty(&q->flows[i].flowchain) ||
-		    arg->count < arg->skip) {
+		if (list_empty(&q->flows[i].flowchain)) {
 			arg->count++;
 			continue;
 		}
-		if (arg->fn(sch, i + 1, arg) < 0) {
-			arg->stop = 1;
+		if (!tc_qdisc_stats_dump(sch, i + 1, arg))
 			break;
-		}
-		arg->count++;
 	}
 }
 
@@ -706,6 +734,7 @@ static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = {
 	.dump_stats =	fq_codel_dump_stats,
 	.owner		=	THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("fq_codel");
 
 static int __init fq_codel_module_init(void)
 {
@@ -721,3 +750,4 @@ module_init(fq_codel_module_init)
 module_exit(fq_codel_module_exit)
 MODULE_AUTHOR("Eric Dumazet");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Fair Queue CoDel discipline");