neigh: new unresolved queue limits

Le mercredi 09 novembre 2011 à 16:21 -0500, David Miller a écrit :
> From: David Miller <davem@davemloft.net>
> Date: Wed, 09 Nov 2011 16:16:44 -0500 (EST)
>
> > From: Eric Dumazet <eric.dumazet@gmail.com>
> > Date: Wed, 09 Nov 2011 12:14:09 +0100
> >
> >> unres_qlen is the number of frames we are able to queue per unresolved
> >> neighbour. Its default value (3) was never changed and is responsible
> >> for strange drops, especially if IP fragments are used, or multiple
> >> sessions start in parallel. Even a single tcp flow can hit this limit.
> >  ...
> >
> > Ok, I've applied this, let's see what happens :-)
>
> Early answer, build fails.
>
> Please test build this patch with DECNET enabled and resubmit.  The
> decnet neigh layer still refers to the removed ->queue_len member.
>
> Thanks.

Ouch, this was fixed on one machine yesterday, but not the other one I
used this morning, sorry.

[PATCH V5 net-next] neigh: new unresolved queue limits

unres_qlen is the number of frames we are able to queue per unresolved
neighbour. Its default value (3) was never changed and is responsible
for strange drops, especially if IP fragments are used, or multiple
sessions start in parallel. Even a single tcp flow can hit this limit.

$ arp -d 192.168.20.108 ; ping -c 2 -s 8000 192.168.20.108
PING 192.168.20.108 (192.168.20.108) 8000(8028) bytes of data.
8008 bytes from 192.168.20.108: icmp_seq=2 ttl=64 time=0.322 ms

Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 128 insertions, 56 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index f049a1ca186f..b8867061fce4 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -31,6 +31,16 @@ neigh/default/gc_thresh3 - INTEGER
 	when using large numbers of interfaces and when communicating
 	with large numbers of directly-connected peers.
 
+neigh/default/unres_qlen_bytes - INTEGER
+	The maximum number of bytes which may be used by packets
+	queued for each	unresolved address by other network layers.
+	(added in linux 3.3)
+
+neigh/default/unres_qlen - INTEGER
+	The maximum number of packets which may be queued for each
+	unresolved address by other network layers.
+	(deprecated in linux 3.3) : use unres_qlen_bytes instead.
+
 mtu_expires - INTEGER
 	Time, in seconds, that cached PMTU information is kept.
 
diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h
index a7003b7a695d..b188f68a08c9 100644
--- a/include/linux/neighbour.h
+++ b/include/linux/neighbour.h
@@ -116,6 +116,7 @@ enum {
 	NDTPA_PROXY_DELAY,		/* u64, msecs */
 	NDTPA_PROXY_QLEN,		/* u32 */
 	NDTPA_LOCKTIME,			/* u64, msecs */
+	NDTPA_QUEUE_LENBYTES,		/* u32 */
 	__NDTPA_MAX
 };
 #define NDTPA_MAX (__NDTPA_MAX - 1)
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 2720884287c3..7ae5acff96e9 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -59,7 +59,7 @@ struct neigh_parms {
 	int	reachable_time;
 	int	delay_probe_time;
 
-	int	queue_len;
+	int	queue_len_bytes;
 	int	ucast_probes;
 	int	app_probes;
 	int	mcast_probes;
@@ -99,6 +99,7 @@ struct neighbour {
 	rwlock_t		lock;
 	atomic_t		refcnt;
 	struct sk_buff_head	arp_queue;
+	unsigned int		arp_queue_len_bytes;
 	struct timer_list	timer;
 	unsigned long		used;
 	atomic_t		probes;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 852394072fa1..32c41b8a803e 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -329,7 +329,7 @@ static struct neigh_table clip_tbl = {
 		.gc_staletime 		= 60 * HZ,
 		.reachable_time 	= 30 * HZ,
 		.delay_probe_time 	= 5 * HZ,
-		.queue_len 		= 3,
+		.queue_len_bytes 	= 64 * 1024,
 		.ucast_probes 		= 3,
 		.mcast_probes 		= 3,
 		.anycast_delay 		= 1 * HZ,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 039d51e6c284..2684794458ca 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -238,6 +238,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
 				   it to safe state.
 				 */
 				skb_queue_purge(&n->arp_queue);
+				n->arp_queue_len_bytes = 0;
 				n->output = neigh_blackhole;
 				if (n->nud_state & NUD_VALID)
 					n->nud_state = NUD_NOARP;
@@ -702,6 +703,7 @@ void neigh_destroy(struct neighbour *neigh)
 		printk(KERN_WARNING "Impossible event.\n");
 
 	skb_queue_purge(&neigh->arp_queue);
+	neigh->arp_queue_len_bytes = 0;
 
 	dev_put(neigh->dev);
 	neigh_parms_put(neigh->parms);
@@ -842,6 +844,7 @@ static void neigh_invalidate(struct neighbour *neigh)
 		write_lock(&neigh->lock);
 	}
 	skb_queue_purge(&neigh->arp_queue);
+	neigh->arp_queue_len_bytes = 0;
 }
 
 static void neigh_probe(struct neighbour *neigh)
@@ -980,15 +983,20 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 
 	if (neigh->nud_state == NUD_INCOMPLETE) {
 		if (skb) {
-			if (skb_queue_len(&neigh->arp_queue) >=
-			    neigh->parms->queue_len) {
+			while (neigh->arp_queue_len_bytes + skb->truesize >
+			       neigh->parms->queue_len_bytes) {
 				struct sk_buff *buff;
+
 				buff = __skb_dequeue(&neigh->arp_queue);
+				if (!buff)
+					break;
+				neigh->arp_queue_len_bytes -= buff->truesize;
 				kfree_skb(buff);
 				NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
 			}
 			skb_dst_force(skb);
 			__skb_queue_tail(&neigh->arp_queue, skb);
+			neigh->arp_queue_len_bytes += skb->truesize;
 		}
 		rc = 1;
 	}
@@ -1175,6 +1183,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 			write_lock_bh(&neigh->lock);
 		}
 		skb_queue_purge(&neigh->arp_queue);
+		neigh->arp_queue_len_bytes = 0;
 	}
 out:
 	if (update_isrouter) {
@@ -1747,7 +1756,11 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
 		NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex);
 
 	NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt));
-	NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len);
+	NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes);
+	/* approximative value for deprecated QUEUE_LEN (in packets) */
+	NLA_PUT_U32(skb, NDTPA_QUEUE_LEN,
+		    DIV_ROUND_UP(parms->queue_len_bytes,
+				 SKB_TRUESIZE(ETH_FRAME_LEN)));
 	NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
 	NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
 	NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
@@ -1974,7 +1987,11 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 
 			switch (i) {
 			case NDTPA_QUEUE_LEN:
-				p->queue_len = nla_get_u32(tbp[i]);
+				p->queue_len_bytes = nla_get_u32(tbp[i]) *
+						     SKB_TRUESIZE(ETH_FRAME_LEN);
+				break;
+			case NDTPA_QUEUE_LENBYTES:
+				p->queue_len_bytes = nla_get_u32(tbp[i]);
 				break;
 			case NDTPA_PROXY_QLEN:
 				p->proxy_qlen = nla_get_u32(tbp[i]);
@@ -2635,117 +2652,158 @@ EXPORT_SYMBOL(neigh_app_ns);
 
 #ifdef CONFIG_SYSCTL
 
-#define NEIGH_VARS_MAX 19
+static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer,
+			   size_t *lenp, loff_t *ppos)
+{
+	int size, ret;
+	ctl_table tmp = *ctl;
+
+	tmp.data = &size;
+	size = DIV_ROUND_UP(*(int *)ctl->data, SKB_TRUESIZE(ETH_FRAME_LEN));
+	ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+	if (write && !ret)
+		*(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN);
+	return ret;
+}
+
+enum {
+	NEIGH_VAR_MCAST_PROBE,
+	NEIGH_VAR_UCAST_PROBE,
+	NEIGH_VAR_APP_PROBE,
+	NEIGH_VAR_RETRANS_TIME,
+	NEIGH_VAR_BASE_REACHABLE_TIME,
+	NEIGH_VAR_DELAY_PROBE_TIME,
+	NEIGH_VAR_GC_STALETIME,
+	NEIGH_VAR_QUEUE_LEN,
+	NEIGH_VAR_QUEUE_LEN_BYTES,
+	NEIGH_VAR_PROXY_QLEN,
+	NEIGH_VAR_ANYCAST_DELAY,
+	NEIGH_VAR_PROXY_DELAY,
+	NEIGH_VAR_LOCKTIME,
+	NEIGH_VAR_RETRANS_TIME_MS,
+	NEIGH_VAR_BASE_REACHABLE_TIME_MS,
+	NEIGH_VAR_GC_INTERVAL,
+	NEIGH_VAR_GC_THRESH1,
+	NEIGH_VAR_GC_THRESH2,
+	NEIGH_VAR_GC_THRESH3,
+	NEIGH_VAR_MAX
+};
 
 static struct neigh_sysctl_table {
 	struct ctl_table_header *sysctl_header;
-	struct ctl_table neigh_vars[NEIGH_VARS_MAX];
+	struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1];
 	char *dev_name;
 } neigh_sysctl_template __read_mostly = {
 	.neigh_vars = {
-		{
+		[NEIGH_VAR_MCAST_PROBE] = {
 			.procname	= "mcast_solicit",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_UCAST_PROBE] = {
 			.procname	= "ucast_solicit",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_APP_PROBE] = {
 			.procname	= "app_solicit",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_RETRANS_TIME] = {
 			.procname	= "retrans_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_BASE_REACHABLE_TIME] = {
 			.procname	= "base_reachable_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_DELAY_PROBE_TIME] = {
 			.procname	= "delay_first_probe_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_GC_STALETIME] = {
 			.procname	= "gc_stale_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_QUEUE_LEN] = {
 			.procname	= "unres_qlen",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
+			.proc_handler	= proc_unres_qlen,
+		},
+		[NEIGH_VAR_QUEUE_LEN_BYTES] = {
+			.procname	= "unres_qlen_bytes",
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_PROXY_QLEN] = {
 			.procname	= "proxy_qlen",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_ANYCAST_DELAY] = {
 			.procname	= "anycast_delay",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_PROXY_DELAY] = {
 			.procname	= "proxy_delay",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_LOCKTIME] = {
 			.procname	= "locktime",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_RETRANS_TIME_MS] = {
 			.procname	= "retrans_time_ms",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_ms_jiffies,
 		},
-		{
+		[NEIGH_VAR_BASE_REACHABLE_TIME_MS] = {
 			.procname	= "base_reachable_time_ms",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_ms_jiffies,
 		},
-		{
+		[NEIGH_VAR_GC_INTERVAL] = {
 			.procname	= "gc_interval",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_GC_THRESH1] = {
 			.procname	= "gc_thresh1",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_GC_THRESH2] = {
 			.procname	= "gc_thresh2",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_GC_THRESH3] = {
 			.procname	= "gc_thresh3",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
@@ -2778,47 +2836,49 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 	if (!t)
 		goto err;
 
-	t->neigh_vars[0].data  = &p->mcast_probes;
-	t->neigh_vars[1].data  = &p->ucast_probes;
-	t->neigh_vars[2].data  = &p->app_probes;
-	t->neigh_vars[3].data  = &p->retrans_time;
-	t->neigh_vars[4].data  = &p->base_reachable_time;
-	t->neigh_vars[5].data  = &p->delay_probe_time;
-	t->neigh_vars[6].data  = &p->gc_staletime;
-	t->neigh_vars[7].data  = &p->queue_len;
-	t->neigh_vars[8].data  = &p->proxy_qlen;
-	t->neigh_vars[9].data  = &p->anycast_delay;
-	t->neigh_vars[10].data = &p->proxy_delay;
-	t->neigh_vars[11].data = &p->locktime;
-	t->neigh_vars[12].data  = &p->retrans_time;
-	t->neigh_vars[13].data  = &p->base_reachable_time;
+	t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data  = &p->mcast_probes;
+	t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data  = &p->ucast_probes;
+	t->neigh_vars[NEIGH_VAR_APP_PROBE].data  = &p->app_probes;
+	t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data  = &p->retrans_time;
+	t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data  = &p->base_reachable_time;
+	t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data  = &p->delay_probe_time;
+	t->neigh_vars[NEIGH_VAR_GC_STALETIME].data  = &p->gc_staletime;
+	t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data  = &p->queue_len_bytes;
+	t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data  = &p->queue_len_bytes;
+	t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data  = &p->proxy_qlen;
+	t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data  = &p->anycast_delay;
+	t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay;
+	t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime;
+	t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data  = &p->retrans_time;
+	t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data  = &p->base_reachable_time;
 
 	if (dev) {
 		dev_name_source = dev->name;
 		/* Terminate the table early */
-		memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14]));
+		memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0,
+		       sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL]));
 	} else {
 		dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname;
-		t->neigh_vars[14].data = (int *)(p + 1);
-		t->neigh_vars[15].data = (int *)(p + 1) + 1;
-		t->neigh_vars[16].data = (int *)(p + 1) + 2;
-		t->neigh_vars[17].data = (int *)(p + 1) + 3;
+		t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1);
+		t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3;
 	}
 
 
 	if (handler) {
 		/* RetransTime */
-		t->neigh_vars[3].proc_handler = handler;
-		t->neigh_vars[3].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev;
 		/* ReachableTime */
-		t->neigh_vars[4].proc_handler = handler;
-		t->neigh_vars[4].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev;
 		/* RetransTime (in milliseconds)*/
-		t->neigh_vars[12].proc_handler = handler;
-		t->neigh_vars[12].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev;
 		/* ReachableTime (in milliseconds) */
-		t->neigh_vars[13].proc_handler = handler;
-		t->neigh_vars[13].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev;
 	}
 
 	t->dev_name = kstrdup(dev_name_source, GFP_KERNEL);
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index 7f0eb087dc11..3532ac64c82d 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -107,7 +107,7 @@ struct neigh_table dn_neigh_table = {
 		.gc_staletime =	60 * HZ,
 		.reachable_time =		30 * HZ,
 		.delay_probe_time =	5 * HZ,
-		.queue_len =		3,
+		.queue_len_bytes =	64*1024,
 		.ucast_probes =	0,
 		.app_probes =		0,
 		.mcast_probes =	0,
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 96a164aa1367..d732827b32b9 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -177,7 +177,7 @@ struct neigh_table arp_tbl = {
 		.gc_staletime		= 60 * HZ,
 		.reachable_time		= 30 * HZ,
 		.delay_probe_time	= 5 * HZ,
-		.queue_len		= 3,
+		.queue_len_bytes	= 64*1024,
 		.ucast_probes		= 3,
 		.mcast_probes		= 3,
 		.anycast_delay		= 1 * HZ,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 44e5b7f2a6c1..4a2098222625 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -141,7 +141,7 @@ struct neigh_table nd_tbl = {
 		.gc_staletime		= 60 * HZ,
 		.reachable_time		= ND_REACHABLE_TIME,
 		.delay_probe_time	= 5 * HZ,
-		.queue_len		= 3,
+		.queue_len_bytes	= 64*1024,
 		.ucast_probes		= 3,
 		.mcast_probes		= 3,
 		.anycast_delay		= 1 * HZ,