Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   1) Support SPI based w5100 devices, from Akinobu Mita.

   2) Partial Segmentation Offload, from Alexander Duyck.

   3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE.

   4) Allow cls_flower stats offload, from Amir Vadai.

   5) Implement bpf blinding, from Daniel Borkmann.

   6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is
      actually using FASYNC these atomics are superfluous.  From Eric
      Dumazet.

   7) Run TCP more preemptibly, also from Eric Dumazet.

   8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e
      driver, from Gal Pressman.

   9) Allow creating ppp devices via rtnetlink, from Guillaume Nault.

  10) Improve BPF usage documentation, from Jesper Dangaard Brouer.

  11) Support tunneling offloads in qed, from Manish Chopra.

  12) aRFS offloading in mlx5e, from Maor Gottlieb.

  13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo
      Leitner.

  14) Add MSG_EOR support to TCP, this allows controlling packet
      coalescing on application record boundaries for more accurate
      socket timestamp sampling.  From Martin KaFai Lau.

  15) Fix alignment of 64-bit netlink attributes across the board, from
      Nicolas Dichtel.

  16) Per-vlan stats in bridging, from Nikolay Aleksandrov.

  17) Several conversions of drivers to ethtool ksettings, from Philippe
      Reynes.

  18) Checksum neutral ILA in ipv6, from Tom Herbert.

  19) Factorize all of the various marvell dsa drivers into one, from
      Vivien Didelot

  20) Add VF support to qed driver, from Yuval Mintz"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits)
  Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m"
  Revert "phy dp83867: Make rgmii parameters optional"
  r8169: default to 64-bit DMA on recent PCIe chips
  phy dp83867: Make rgmii parameters optional
  phy dp83867: Fix compilation with CONFIG_OF_MDIO=m
  bpf: arm64: remove callee-save registers use for tmp registers
  asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions
  switchdev: pass pointer to fib_info instead of copy
  net_sched: close another race condition in tcf_mirred_release()
  tipc: fix nametable publication field in nl compat
  drivers: net: Don't print unpopulated net_device name
  qed: add support for dcbx.
  ravb: Add missing free_irq() calls to ravb_close()
  qed: Remove a stray tab
  net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fec-mpc52xx: use phydev from struct net_device
  bpf, doc: fix typo on bpf_asm descriptions
  stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set
  net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fs-enet: use phydev from struct net_device
  ...

1 files changed, 86 insertions, 25 deletions

diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index d3fc8f9dd3d4..6883a8971562 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -24,6 +24,8 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/codel.h>
+#include <net/codel_impl.h>
+#include <net/codel_qdisc.h>
 
 /*	Fair Queue CoDel.
  *
@@ -57,8 +59,12 @@ struct fq_codel_sched_data {
 	u32		flows_cnt;	/* number of flows */
 	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;
 
@@ -133,17 +139,21 @@ static inline void flow_queue_add(struct fq_codel_flow *flow,
 	skb->next = NULL;
 }
 
-static unsigned int fq_codel_drop(struct Qdisc *sch)
+static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
 	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 from it.
+	/* Queue is full! Find the fat flow and drop packet(s) from it.
 	 * This might sound expensive, but with 1024 flows, we scan
 	 * 4KB of memory, and we dont need to handle a complex tree
 	 * in fast path (packet queue/enqueue) with many cache misses.
+	 * In stress mode, we'll try to drop 64 packets from the flow,
+	 * amortizing this linear lookup to one cache line per drop.
 	 */
 	for (i = 0; i < q->flows_cnt; i++) {
 		if (q->backlogs[i] > maxbacklog) {
@@ -151,15 +161,26 @@ static unsigned int fq_codel_drop(struct Qdisc *sch)
 			idx = i;
 		}
 	}
+
+	/* Our goal is to drop half of this fat flow backlog */
+	threshold = maxbacklog >> 1;
+
 	flow = &q->flows[idx];
-	skb = dequeue_head(flow);
-	len = qdisc_pkt_len(skb);
+	len = 0;
+	i = 0;
+	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;
-	sch->q.qlen--;
-	qdisc_qstats_drop(sch);
-	qdisc_qstats_backlog_dec(sch, skb);
-	kfree_skb(skb);
-	flow->dropped++;
+	q->memory_usage -= mem;
+	sch->qstats.drops += i;
+	sch->qstats.backlog -= len;
+	sch->q.qlen -= i;
 	return idx;
 }
 
@@ -168,16 +189,17 @@ static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
 	unsigned int prev_backlog;
 
 	prev_backlog = sch->qstats.backlog;
-	fq_codel_drop(sch);
+	fq_codel_drop(sch, 1U);
 	return prev_backlog - sch->qstats.backlog;
 }
 
 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;
+	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) {
@@ -200,28 +222,38 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		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;
-	q->drop_overlimit++;
-	/* Return Congestion Notification only if we dropped a packet
-	 * from this flow.
+	prev_qlen = sch->q.qlen;
+
+	/* fq_codel_drop() is quite expensive, as it performs a linear search
+	 * in q->backlogs[] to find a fat flow.
+	 * So instead of dropping a single packet, drop half of its backlog
+	 * with a 64 packets limit to not add a too big cpu spike here.
 	 */
-	if (fq_codel_drop(sch) == idx)
-		return NET_XMIT_CN;
+	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);
 
-	/* As we dropped a packet, better let upper stack know this */
-	qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog);
-	return NET_XMIT_SUCCESS;
+	return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
 }
 
 /* This is the specific function called from codel_dequeue()
  * to dequeue a packet from queue. Note: backlog is handled in
  * codel, we dont need to reduce it here.
  */
-static struct sk_buff *dequeue(struct codel_vars *vars, struct Qdisc *sch)
+static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx)
 {
+	struct Qdisc *sch = ctx;
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct fq_codel_flow *flow;
 	struct sk_buff *skb = NULL;
@@ -230,11 +262,20 @@ static struct sk_buff *dequeue(struct codel_vars *vars, struct Qdisc *sch)
 	if (flow->head) {
 		skb = dequeue_head(flow);
 		q->backlogs[flow - q->flows] -= qdisc_pkt_len(skb);
+		q->memory_usage -= skb->truesize;
 		sch->q.qlen--;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
 	}
 	return skb;
 }
 
+static void drop_func(struct sk_buff *skb, void *ctx)
+{
+	struct Qdisc *sch = ctx;
+
+	qdisc_drop(skb, sch);
+}
+
 static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
@@ -263,8 +304,9 @@ begin:
 	prev_ecn_mark = q->cstats.ecn_mark;
 	prev_backlog = sch->qstats.backlog;
 
-	skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats,
-			    dequeue);
+	skb = codel_dequeue(sch, &sch->qstats.backlog, &q->cparams,
+			    &flow->cvars, &q->cstats, qdisc_pkt_len,
+			    codel_get_enqueue_time, drop_func, dequeue_func);
 
 	flow->dropped += q->cstats.drop_count - prev_drop_count;
 	flow->dropped += q->cstats.ecn_mark - prev_ecn_mark;
@@ -313,6 +355,7 @@ static void fq_codel_reset(struct Qdisc *sch)
 	}
 	memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
 	sch->q.qlen = 0;
+	q->memory_usage = 0;
 }
 
 static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
@@ -323,6 +366,8 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
 	[TCA_FQ_CODEL_FLOWS]	= { .type = NLA_U32 },
 	[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)
@@ -374,7 +419,14 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_FQ_CODEL_QUANTUM])
 		q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM]));
 
-	while (sch->q.qlen > sch->limit) {
+	if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])
+		q->drop_batch_size = min(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]));
+
+	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);
@@ -419,13 +471,16 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt)
 
 	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();
 	INIT_LIST_HEAD(&q->new_flows);
 	INIT_LIST_HEAD(&q->old_flows);
-	codel_params_init(&q->cparams, sch);
+	codel_params_init(&q->cparams);
 	codel_stats_init(&q->cstats);
 	q->cparams.ecn = true;
+	q->cparams.mtu = psched_mtu(qdisc_dev(sch));
 
 	if (opt) {
 		int err = fq_codel_change(sch, opt);
@@ -476,6 +531,10 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 			q->cparams.ecn) ||
 	    nla_put_u32(skb, TCA_FQ_CODEL_QUANTUM,
 			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;
@@ -504,6 +563,8 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	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++;