+From: Eric Dumazet <edumazet@google.com>
+Date: Fri, 6 May 2016 08:55:12 -0700
+Subject: [PATCH] fq_codel: add memory limitation per queue
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+On small embedded routers, one wants to control maximal amount of
+memory used by fq_codel, instead of controlling number of packets or
+bytes, since GRO/TSO make these not practical.
+
+Assuming skb->truesize is accurate, we have to keep track of
+skb->truesize sum for skbs in queue.
+
+This patch adds a new TCA_FQ_CODEL_MEMORY_LIMIT attribute.
+
+I chose a default value of 32 MBytes, which looks reasonable even
+for heavy duty usages. (Prior fq_codel users should not be hurt
+when they upgrade their kernels)
+
+Two fields are added to tc_fq_codel_qd_stats to report :
+ - Current memory usage
+ - Number of drops caused by memory limits
+
+# tc qd replace dev eth1 root est 1sec 4sec fq_codel memory_limit 4M
+..
+# tc -s -d qd sh dev eth1
+qdisc fq_codel 8008: root refcnt 257 limit 10240p flows 1024
+ quantum 1514 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
+ Sent 2083566791363 bytes 1376214889 pkt (dropped 4994406, overlimits 0
+requeues 21705223)
+ rate 9841Mbit 812549pps backlog 3906120b 376p requeues 21705223
+ maxpacket 68130 drop_overlimit 4994406 new_flow_count 28855414
+ ecn_mark 0 memory_used 4190048 drop_overmemory 4994406
+ new_flows_len 1 old_flows_len 177
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Cc: Jesper Dangaard Brouer <brouer@redhat.com>
+Cc: Dave Täht <dave.taht@gmail.com>
+Cc: Sebastian Möller <moeller0@gmx.de>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/include/uapi/linux/pkt_sched.h
++++ b/include/uapi/linux/pkt_sched.h
+@@ -712,6 +712,7 @@ enum {
+ TCA_FQ_CODEL_QUANTUM,
+ TCA_FQ_CODEL_CE_THRESHOLD,
+ TCA_FQ_CODEL_DROP_BATCH_SIZE,
++ TCA_FQ_CODEL_MEMORY_LIMIT,
+ __TCA_FQ_CODEL_MAX
+ };
+
+@@ -736,6 +737,8 @@ struct tc_fq_codel_qd_stats {
+ __u32 new_flows_len; /* count of flows in new list */
+ __u32 old_flows_len; /* count of flows in old list */
+ __u32 ce_mark; /* packets above ce_threshold */
++ __u32 memory_usage; /* in bytes */
++ __u32 drop_overmemory;
+ };
+
+ struct tc_fq_codel_cl_stats {
+--- a/net/sched/sch_fq_codel.c
++++ b/net/sched/sch_fq_codel.c
+@@ -58,8 +58,11 @@ struct fq_codel_sched_data {
+ u32 perturbation; /* hash perturbation */
+ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */
+ u32 drop_batch_size;
++ u32 memory_limit;
+ struct codel_params cparams;
+ struct codel_stats cstats;
++ u32 memory_usage;
++ u32 drop_overmemory;
+ u32 drop_overlimit;
+ u32 new_flow_count;
+
+@@ -141,6 +144,7 @@ static unsigned int fq_codel_drop(struct
+ unsigned int maxbacklog = 0, idx = 0, i, len;
+ struct fq_codel_flow *flow;
+ unsigned int threshold;
++ unsigned int mem = 0;
+
+ /* Queue is full! Find the fat flow and drop packet(s) from it.
+ * This might sound expensive, but with 1024 flows, we scan
+@@ -165,11 +169,13 @@ static unsigned int fq_codel_drop(struct
+ do {
+ skb = dequeue_head(flow);
+ len += qdisc_pkt_len(skb);
++ mem += skb->truesize;
+ kfree_skb(skb);
+ } while (++i < max_packets && len < threshold);
+
+ flow->dropped += i;
+ q->backlogs[idx] -= len;
++ q->memory_usage -= mem;
+ sch->qstats.drops += i;
+ sch->qstats.backlog -= len;
+ sch->q.qlen -= i;
+@@ -191,6 +197,7 @@ static int fq_codel_enqueue(struct sk_bu
+ unsigned int idx, prev_backlog, prev_qlen;
+ struct fq_codel_flow *flow;
+ int uninitialized_var(ret);
++ bool memory_limited;
+
+ idx = fq_codel_classify(skb, sch, &ret);
+ if (idx == 0) {
+@@ -213,7 +220,9 @@ static int fq_codel_enqueue(struct sk_bu
+ flow->deficit = q->quantum;
+ flow->dropped = 0;
+ }
+- if (++sch->q.qlen <= sch->limit)
++ q->memory_usage += skb->truesize;
++ memory_limited = q->memory_usage > q->memory_limit;
++ if (++sch->q.qlen <= sch->limit && !memory_limited)
+ return NET_XMIT_SUCCESS;
+
+ prev_backlog = sch->qstats.backlog;
+@@ -227,7 +236,8 @@ static int fq_codel_enqueue(struct sk_bu
+ ret = fq_codel_drop(sch, q->drop_batch_size);
+
+ q->drop_overlimit += prev_qlen - sch->q.qlen;
+-
++ if (memory_limited)
++ q->drop_overmemory += prev_qlen - sch->q.qlen;
+ /* As we dropped packet(s), better let upper stack know this */
+ qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
+ prev_backlog - sch->qstats.backlog);
+@@ -296,6 +306,7 @@ begin:
+ list_del_init(&flow->flowchain);
+ goto begin;
+ }
++ q->memory_usage -= skb->truesize;
+ qdisc_bstats_update(sch, skb);
+ flow->deficit -= qdisc_pkt_len(skb);
+ /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
+@@ -343,6 +354,7 @@ static const struct nla_policy fq_codel_
+ [TCA_FQ_CODEL_QUANTUM] = { .type = NLA_U32 },
+ [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 },
+ };
+
+ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
+@@ -397,7 +409,11 @@ static int fq_codel_change(struct Qdisc
+ if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
+ q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]));
+
+- while (sch->q.qlen > sch->limit) {
++ if (tb[TCA_FQ_CODEL_MEMORY_LIMIT])
++ 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);
+
+ q->cstats.drop_len += qdisc_pkt_len(skb);
+@@ -442,6 +458,7 @@ static int fq_codel_init(struct Qdisc *s
+
+ sch->limit = 10*1024;
+ q->flows_cnt = 1024;
++ q->memory_limit = 32 << 20; /* 32 MBytes */
+ q->drop_batch_size = 64;
+ q->quantum = psched_mtu(qdisc_dev(sch));
+ q->perturbation = prandom_u32();
+@@ -502,6 +519,8 @@ static int fq_codel_dump(struct Qdisc *s
+ q->quantum) ||
+ nla_put_u32(skb, TCA_FQ_CODEL_DROP_BATCH_SIZE,
+ q->drop_batch_size) ||
++ nla_put_u32(skb, TCA_FQ_CODEL_MEMORY_LIMIT,
++ q->memory_limit) ||
+ nla_put_u32(skb, TCA_FQ_CODEL_FLOWS,
+ q->flows_cnt))
+ goto nla_put_failure;
+@@ -530,6 +549,8 @@ static int fq_codel_dump_stats(struct Qd
+ st.qdisc_stats.ecn_mark = q->cstats.ecn_mark;
+ st.qdisc_stats.new_flow_count = q->new_flow_count;
+ st.qdisc_stats.ce_mark = q->cstats.ce_mark;
++ st.qdisc_stats.memory_usage = q->memory_usage;
++ st.qdisc_stats.drop_overmemory = q->drop_overmemory;
+
+ list_for_each(pos, &q->new_flows)
+ st.qdisc_stats.new_flows_len++;