Merge branch 'inet_frag_kill_lru_list'

Nikolay Aleksandrov says:

====================
inet: frag: cleanup and update

The end goal of this patchset is to remove the LRU list and to move the
frag eviction to a work queue. It also does a couple of necessary cleanups
and fixes. Brief patch descriptions:
Patches 1 - 3 inclusive: necessary clean ups
Patch 4 moves the eviction from the softirqs to a workqueue.
Patch 5 removes the nqueues counter which was protected by the LRU lock
Patch 6 removes the, by now unused, lru list.
Patch 7 moves the rebuild timer to the workqueue and schedules the rebuilds
        only if we've hit the maximum queue length on some of the chains.
Patch 8 migrate the rwlock to a seqlock since the rehash is usually a rare
        operation.
Patch 9 introduces an artificial global memory limit based on the value of
        init_net's high_thresh which is used to cap the high_thresh of the
        other namespaces. Also introduces some sane limits on the other
        tunables, and makes it impossible to have low_thresh > high_thresh.

Here are some numbers from running netperf before and after the patchset:
Each test consists of the following setting: -I 95,5 -i 15,10

1. Bound test (-T 4,4)
1.1 Virtio before the patchset -
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.177 () port 0 AF_INET : +/-2.500% @ 95% conf.  : cpu bind
Socket  Message  Elapsed      Messages                   CPU      Service
Size    Size     Time         Okay Errors   Throughput   Util     Demand
bytes   bytes    secs            #      #   10^6bits/sec % SS     us/KB

212992   64000   30.00      722177      0    12325.1     34.55    2.025
212992           30.00      368020            6280.9     34.05    0.752

1.2 Virtio after the patchset -
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.177 () port 0 AF_INET : +/-2.500% @ 95% conf.  : cpu bind
Socket  Message  Elapsed      Messages                   CPU      Service
Size    Size     Time         Okay Errors   Throughput   Util     Demand
bytes   bytes    secs            #      #   10^6bits/sec % SS     us/KB

212992   64000   30.00      727030      0    12407.9     35.45    1.876
212992           30.00      505405            8625.5     34.92    0.693

2. Virtio unbound test
2.1 Before the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.177 () port 0 AF_INET : +/-2.500% @ 95% conf.
Socket  Message  Elapsed      Messages
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

212992   64000   30.00      730008      0    12458.77
212992           30.00      416721           7112.02

2.2 After the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.177 () port 0 AF_INET : +/-2.500% @ 95% conf.
Socket  Message  Elapsed      Messages
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

212992   64000   30.00      731129      0    12477.89
212992           30.00      487707           8323.50

3. 10 gig unbound tests
3.1 Before the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.133.1 () port 0 AF_INET : +/-2.500% @ 95% conf.
Socket  Message  Elapsed      Messages
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

212992   64000   30.00      417209      0    7120.33
212992           30.00      416740           7112.33

3.2 After the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.133.1 () port 0 AF_INET : +/-2.500% @ 95% conf.
Socket  Message  Elapsed      Messages
Size    Size     Time         Okay Errors   Throughput
bytes   bytes    secs            #      #   10^6bits/sec

212992   64000   30.00      438009      0    7475.33
212992           30.00      437630           7468.87

Given the options each netperf ran between 10 and 15 times for 30 seconds
to get the necessary confidence, also the tests themselves ran 3 times and
were consistent.
Another set of tests that I ran were parallel stress tests which consisted
of flooding the machine with fragmented packets from different sources with
frag timeout set to 0 (so there're lots of timeouts) and low_thresh set to
1 byte (so evictions are happening all the time) and on top of that running
a namespace create/destroy endless loop with network interfaces and
addresses that got flooded (for the brief periods they were up) in parallel.
This test ran for an hour without any issues.
====================

Documentation/networking/ip-sysctl.txt

@@ -101,19 +101,17 @@ ipfrag_high_thresh - INTEGER
 	Maximum memory used to reassemble IP fragments. When
 	ipfrag_high_thresh bytes of memory is allocated for this purpose,
 	the fragment handler will toss packets until ipfrag_low_thresh
-	is reached.
+	is reached. This also serves as a maximum limit to namespaces
+	different from the initial one.
 
 ipfrag_low_thresh - INTEGER
-	See ipfrag_high_thresh
+	Maximum memory used to reassemble IP fragments before the kernel
+	begins to remove incomplete fragment queues to free up resources.
+	The kernel still accepts new fragments for defragmentation.
 
 ipfrag_time - INTEGER
 	Time in seconds to keep an IP fragment in memory.
 
-ipfrag_secret_interval - INTEGER
-	Regeneration interval (in seconds) of the hash secret (or lifetime
-	for the hash secret) for IP fragments.
-	Default: 600
-
 ipfrag_max_dist - INTEGER
 	ipfrag_max_dist is a non-negative integer value which defines the
 	maximum "disorder" which is allowed among fragments which share a
@@ -1162,11 +1160,6 @@ ip6frag_low_thresh - INTEGER
 ip6frag_time - INTEGER
 	Time in seconds to keep an IPv6 fragment in memory.
 
-ip6frag_secret_interval - INTEGER
-	Regeneration interval (in seconds) of the hash secret (or lifetime
-	for the hash secret) for IPv6 fragments.
-	Default: 600
-
 conf/default/*:
 	Change the interface-specific default settings.
 

include/net/inet_frag.h

@@ -4,10 +4,6 @@
 #include <linux/percpu_counter.h>
 
 struct netns_frags {
-	int			nqueues;
-	struct list_head	lru_list;
-	spinlock_t		lru_lock;
-
 	/* The percpu_counter "mem" need to be cacheline aligned.
 	 *  mem.count must not share cacheline with other writers
 	 */
@@ -22,7 +18,6 @@ struct netns_frags {
 struct inet_frag_queue {
 	spinlock_t		lock;
 	struct timer_list	timer;      /* when will this queue expire? */
-	struct list_head	lru_list;   /* lru list member */
 	struct hlist_node	list;
 	atomic_t		refcnt;
 	struct sk_buff		*fragments; /* list of received fragments */
@@ -32,6 +27,7 @@ struct inet_frag_queue {
 	int			meat;
 	__u8			last_in;    /* first/last segment arrived? */
 
+#define INET_FRAG_EVICTED	8
 #define INET_FRAG_COMPLETE	4
 #define INET_FRAG_FIRST_IN	2
 #define INET_FRAG_LAST_IN	1
@@ -48,7 +44,7 @@ struct inet_frag_queue {
  *	       rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
  *	       struct frag_queue))
  */
-#define INETFRAGS_MAXDEPTH		128
+#define INETFRAGS_MAXDEPTH	128
 
 struct inet_frag_bucket {
 	struct hlist_head	chain;
@@ -57,24 +53,27 @@ struct inet_frag_bucket {
 
 struct inet_frags {
 	struct inet_frag_bucket	hash[INETFRAGS_HASHSZ];
-	/* This rwlock is a global lock (seperate per IPv4, IPv6 and
-	 * netfilter). Important to keep this on a seperate cacheline.
-	 * Its primarily a rebuild protection rwlock.
-	 */
-	rwlock_t		lock ____cacheline_aligned_in_smp;
-	int			secret_interval;
-	struct timer_list	secret_timer;
+
+	struct work_struct	frags_work;
+	unsigned int next_bucket;
+	unsigned long last_rebuild_jiffies;
+	bool rebuild;
 
 	/* The first call to hashfn is responsible to initialize
 	 * rnd. This is best done with net_get_random_once.
+	 *
+	 * rnd_seqlock is used to let hash insertion detect
+	 * when it needs to re-lookup the hash chain to use.
 	 */
 	u32			rnd;
+	seqlock_t		rnd_seqlock;
 	int			qsize;
 
-	unsigned int		(*hashfn)(struct inet_frag_queue *);
-	bool			(*match)(struct inet_frag_queue *q, void *arg);
+	unsigned int		(*hashfn)(const struct inet_frag_queue *);
+	bool			(*match)(const struct inet_frag_queue *q,
+					 const void *arg);
 	void			(*constructor)(struct inet_frag_queue *q,
-						void *arg);
+					       const void *arg);
 	void			(*destructor)(struct inet_frag_queue *);
 	void			(*skb_free)(struct sk_buff *);
 	void			(*frag_expire)(unsigned long data);
@@ -87,19 +86,17 @@ void inet_frags_init_net(struct netns_frags *nf);
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);
 
 void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f);
-void inet_frag_destroy(struct inet_frag_queue *q,
-				struct inet_frags *f, int *work);
-int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force);
+void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
-		struct inet_frags *f, void *key, unsigned int hash)
-	__releases(&f->lock);
+		struct inet_frags *f, void *key, unsigned int hash);
+
 void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
 				   const char *prefix);
 
 static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
 {
 	if (atomic_dec_and_test(&q->refcnt))
-		inet_frag_destroy(q, f, NULL);
+		inet_frag_destroy(q, f);
 }
 
 /* Memory Tracking Functions. */
@@ -131,9 +128,9 @@ static inline void init_frag_mem_limit(struct netns_frags *nf)
 	percpu_counter_init(&nf->mem, 0);
 }
 
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
+static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf)
 {
-	int res;
+	unsigned int res;
 
 	local_bh_disable();
 	res = percpu_counter_sum_positive(&nf->mem);
@@ -142,31 +139,6 @@ static inline int sum_frag_mem_limit(struct netns_frags *nf)
 	return res;
 }
 
-static inline void inet_frag_lru_move(struct inet_frag_queue *q)
-{
-	spin_lock(&q->net->lru_lock);
-	if (!list_empty(&q->lru_list))
-		list_move_tail(&q->lru_list, &q->net->lru_list);
-	spin_unlock(&q->net->lru_lock);
-}
-
-static inline void inet_frag_lru_del(struct inet_frag_queue *q)
-{
-	spin_lock(&q->net->lru_lock);
-	list_del_init(&q->lru_list);
-	q->net->nqueues--;
-	spin_unlock(&q->net->lru_lock);
-}
-
-static inline void inet_frag_lru_add(struct netns_frags *nf,
-				     struct inet_frag_queue *q)
-{
-	spin_lock(&nf->lru_lock);
-	list_add_tail(&q->lru_list, &nf->lru_list);
-	q->net->nqueues++;
-	spin_unlock(&nf->lru_lock);
-}
-
 /* RFC 3168 support :
  * We want to check ECN values of all fragments, do detect invalid combinations.
  * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.

include/net/ip.h

@@ -495,7 +495,6 @@ static inline struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 }
 #endif
 int ip_frag_mem(struct net *net);
-int ip_frag_nqueues(struct net *net);
 
 /*
  *	Functions provided by ip_forward.c

include/net/ipv6.h

@@ -299,11 +299,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_nqueues(struct net *net)
-{
-	return net->ipv6.frags.nqueues;
-}
-
 static inline int ip6_frag_mem(struct net *net)
 {
 	return sum_frag_mem_limit(&net->ipv6.frags);
@@ -496,8 +491,8 @@ struct ip6_create_arg {
 	u8 ecn;
 };
 
-void ip6_frag_init(struct inet_frag_queue *q, void *a);
-bool ip6_frag_match(struct inet_frag_queue *q, void *a);
+void ip6_frag_init(struct inet_frag_queue *q, const void *a);
+bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
 
 /*
  *	Equivalent of ipv4 struct ip

net/ieee802154/reassembly.c

@@ -50,29 +50,25 @@ static unsigned int lowpan_hash_frag(__be16 tag, u16 d_size,
 				     const struct ieee802154_addr *saddr,
 				     const struct ieee802154_addr *daddr)
 {
-	u32 c;
-
 	net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
-	c = jhash_3words(ieee802154_addr_hash(saddr),
-			 ieee802154_addr_hash(daddr),
-			 (__force u32)(tag + (d_size << 16)),
-			 lowpan_frags.rnd);
-
-	return c & (INETFRAGS_HASHSZ - 1);
+	return jhash_3words(ieee802154_addr_hash(saddr),
+			    ieee802154_addr_hash(daddr),
+			    (__force u32)(tag + (d_size << 16)),
+			    lowpan_frags.rnd);
 }
 
-static unsigned int lowpan_hashfn(struct inet_frag_queue *q)
+static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
 {
-	struct lowpan_frag_queue *fq;
+	const struct lowpan_frag_queue *fq;
 
 	fq = container_of(q, struct lowpan_frag_queue, q);
 	return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
 }
 
-static bool lowpan_frag_match(struct inet_frag_queue *q, void *a)
+static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
 {
-	struct lowpan_frag_queue *fq;
-	struct lowpan_create_arg *arg = a;
+	const struct lowpan_frag_queue *fq;
+	const struct lowpan_create_arg *arg = a;
 
 	fq = container_of(q, struct lowpan_frag_queue, q);
 	return	fq->tag == arg->tag && fq->d_size == arg->d_size &&
@@ -80,10 +76,10 @@ static bool lowpan_frag_match(struct inet_frag_queue *q, void *a)
 		ieee802154_addr_equal(&fq->daddr, arg->dst);
 }
 
-static void lowpan_frag_init(struct inet_frag_queue *q, void *a)
+static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 {
+	const struct lowpan_create_arg *arg = a;
 	struct lowpan_frag_queue *fq;
-	struct lowpan_create_arg *arg = a;
 
 	fq = container_of(q, struct lowpan_frag_queue, q);
 
@@ -128,7 +124,6 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info,
 	arg.src = src;
 	arg.dst = dst;
 
-	read_lock(&lowpan_frags.lock);
 	hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst);
 
 	q = inet_frag_find(&ieee802154_lowpan->frags,
@@ -223,7 +218,6 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
 		return res;
 	}
 
-	inet_frag_lru_move(&fq->q);
 	return -1;
 err:
 	kfree_skb(skb);
@@ -373,8 +367,6 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
 	if (frag_info->d_size > ieee802154_lowpan->max_dsize)
 		goto err;
 
-	inet_frag_evictor(&ieee802154_lowpan->frags, &lowpan_frags, false);
-
 	fq = fq_find(net, frag_info, &source, &dest);
 	if (fq != NULL) {
 		int ret;
@@ -394,20 +386,25 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
 EXPORT_SYMBOL(lowpan_frag_rcv);
 
 #ifdef CONFIG_SYSCTL
+static int zero;
+
 static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 	{
 		.procname	= "6lowpanfrag_high_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.high_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.ieee802154_lowpan.frags.low_thresh
 	},
 	{
 		.procname	= "6lowpanfrag_low_thresh",
 		.data		= &init_net.ieee802154_lowpan.frags.low_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &init_net.ieee802154_lowpan.frags.high_thresh
 	},
 	{
 		.procname	= "6lowpanfrag_time",
@@ -426,10 +423,12 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = {
 	{ }
 };
 
+/* secret interval has been deprecated */
+static int lowpan_frags_secret_interval_unused;
 static struct ctl_table lowpan_frags_ctl_table[] = {
 	{
 		.procname	= "6lowpanfrag_secret_interval",
-		.data		= &lowpan_frags.secret_interval,
+		.data		= &lowpan_frags_secret_interval_unused,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -452,7 +451,10 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
 			goto err_alloc;
 
 		table[0].data = &ieee802154_lowpan->frags.high_thresh;
+		table[0].extra1 = &ieee802154_lowpan->frags.low_thresh;
+		table[0].extra2 = &init_net.ieee802154_lowpan.frags.high_thresh;
 		table[1].data = &ieee802154_lowpan->frags.low_thresh;
+		table[1].extra2 = &ieee802154_lowpan->frags.high_thresh;
 		table[2].data = &ieee802154_lowpan->frags.timeout;
 		table[3].data = &ieee802154_lowpan->max_dsize;
 
@@ -569,7 +571,6 @@ int __init lowpan_net_frag_init(void)
 	lowpan_frags.qsize = sizeof(struct frag_queue);
 	lowpan_frags.match = lowpan_frag_match;
 	lowpan_frags.frag_expire = lowpan_frag_expire;
-	lowpan_frags.secret_interval = 10 * 60 * HZ;
 	inet_frags_init(&lowpan_frags);
 
 	return ret;

net/ipv4/inet_fragment.c

@@ -25,6 +25,12 @@
 #include <net/inet_frag.h>
 #include <net/inet_ecn.h>
 
+#define INETFRAGS_EVICT_BUCKETS   128
+#define INETFRAGS_EVICT_MAX	  512
+
+/* don't rebuild inetfrag table with new secret more often than this */
+#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
+
 /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
  * Value : 0xff if frame should be dropped.
  *         0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -46,24 +52,39 @@ const u8 ip_frag_ecn_table[16] = {
 };
 EXPORT_SYMBOL(ip_frag_ecn_table);
 
-static void inet_frag_secret_rebuild(unsigned long dummy)
+static unsigned int
+inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
+{
+	return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
+}
+
+static bool inet_frag_may_rebuild(struct inet_frags *f)
+{
+	return time_after(jiffies,
+	       f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
+}
+
+static void inet_frag_secret_rebuild(struct inet_frags *f)
 {
-	struct inet_frags *f = (struct inet_frags *)dummy;
-	unsigned long now = jiffies;
 	int i;
 
-	/* Per bucket lock NOT needed here, due to write lock protection */
-	write_lock(&f->lock);
+	write_seqlock_bh(&f->rnd_seqlock);
+
+	if (!inet_frag_may_rebuild(f))
+		goto out;
 
 	get_random_bytes(&f->rnd, sizeof(u32));
+
 	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
 		struct inet_frag_bucket *hb;
 		struct inet_frag_queue *q;
 		struct hlist_node *n;
 
 		hb = &f->hash[i];
+		spin_lock(&hb->chain_lock);
+
 		hlist_for_each_entry_safe(q, n, &hb->chain, list) {
-			unsigned int hval = f->hashfn(q);
+			unsigned int hval = inet_frag_hashfn(f, q);
 
 			if (hval != i) {
 				struct inet_frag_bucket *hb_dest;
@@ -72,76 +93,195 @@ static void inet_frag_secret_rebuild(unsigned long dummy)
 
 				/* Relink to new hash chain. */
 				hb_dest = &f->hash[hval];
+
+				/* This is the only place where we take
+				 * another chain_lock while already holding
+				 * one.  As this will not run concurrently,
+				 * we cannot deadlock on hb_dest lock below, if its
+				 * already locked it will be released soon since
+				 * other caller cannot be waiting for hb lock
+				 * that we've taken above.
+				 */
+				spin_lock_nested(&hb_dest->chain_lock,
+						 SINGLE_DEPTH_NESTING);
 				hlist_add_head(&q->list, &hb_dest->chain);
+				spin_unlock(&hb_dest->chain_lock);
 			}
 		}
+		spin_unlock(&hb->chain_lock);
 	}
-	write_unlock(&f->lock);
 
-	mod_timer(&f->secret_timer, now + f->secret_interval);
+	f->rebuild = false;
+	f->last_rebuild_jiffies = jiffies;
+out:
+	write_sequnlock_bh(&f->rnd_seqlock);
+}
+
+static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
+{
+	return q->net->low_thresh == 0 ||
+	       frag_mem_limit(q->net) >= q->net->low_thresh;
+}
+
+static unsigned int
+inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
+{
+	struct inet_frag_queue *fq;
+	struct hlist_node *n;
+	unsigned int evicted = 0;
+	HLIST_HEAD(expired);
+
+evict_again:
+	spin_lock(&hb->chain_lock);
+
+	hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
+		if (!inet_fragq_should_evict(fq))
+			continue;
+
+		if (!del_timer(&fq->timer)) {
+			/* q expiring right now thus increment its refcount so
+			 * it won't be freed under us and wait until the timer
+			 * has finished executing then destroy it
+			 */
+			atomic_inc(&fq->refcnt);
+			spin_unlock(&hb->chain_lock);
+			del_timer_sync(&fq->timer);
+			WARN_ON(atomic_read(&fq->refcnt) != 1);
+			inet_frag_put(fq, f);
+			goto evict_again;
+		}
+
+		/* suppress xmit of (icmp) error packet */
+		fq->last_in &= ~INET_FRAG_FIRST_IN;
+		fq->last_in |= INET_FRAG_EVICTED;
+		hlist_del(&fq->list);
+		hlist_add_head(&fq->list, &expired);
+		++evicted;
+	}
+
+	spin_unlock(&hb->chain_lock);
+
+	hlist_for_each_entry_safe(fq, n, &expired, list)
+		f->frag_expire((unsigned long) fq);
+
+	return evicted;
+}
+
+static void inet_frag_worker(struct work_struct *work)
+{
+	unsigned int budget = INETFRAGS_EVICT_BUCKETS;
+	unsigned int i, evicted = 0;
+	struct inet_frags *f;
+
+	f = container_of(work, struct inet_frags, frags_work);
+
+	BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
+
+	local_bh_disable();
+
+	for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) {
+		evicted += inet_evict_bucket(f, &f->hash[i]);
+		i = (i + 1) & (INETFRAGS_HASHSZ - 1);
+		if (evicted > INETFRAGS_EVICT_MAX)
+			break;
+	}
+
+	f->next_bucket = i;
+
+	local_bh_enable();
+
+	if (f->rebuild && inet_frag_may_rebuild(f))
+		inet_frag_secret_rebuild(f);
+}
+
+static void inet_frag_schedule_worker(struct inet_frags *f)
+{
+	if (unlikely(!work_pending(&f->frags_work)))
+		schedule_work(&f->frags_work);
 }
 
 void inet_frags_init(struct inet_frags *f)
 {
 	int i;
 
+	INIT_WORK(&f->frags_work, inet_frag_worker);
+
 	for (i = 0; i < INETFRAGS_HASHSZ; i++) {
 		struct inet_frag_bucket *hb = &f->hash[i];
 
 		spin_lock_init(&hb->chain_lock);
 		INIT_HLIST_HEAD(&hb->chain);
 	}
-	rwlock_init(&f->lock);
 
-	setup_timer(&f->secret_timer, inet_frag_secret_rebuild,
-			(unsigned long)f);
-	f->secret_timer.expires = jiffies + f->secret_interval;
-	add_timer(&f->secret_timer);
+	seqlock_init(&f->rnd_seqlock);
+	f->last_rebuild_jiffies = 0;
 }
 EXPORT_SYMBOL(inet_frags_init);
 
 void inet_frags_init_net(struct netns_frags *nf)
 {
-	nf->nqueues = 0;
 	init_frag_mem_limit(nf);
-	INIT_LIST_HEAD(&nf->lru_list);
-	spin_lock_init(&nf->lru_lock);
 }
 EXPORT_SYMBOL(inet_frags_init_net);
 
 void inet_frags_fini(struct inet_frags *f)
 {
-	del_timer(&f->secret_timer);
+	cancel_work_sync(&f->frags_work);
 }
 EXPORT_SYMBOL(inet_frags_fini);
 
 void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 {
-	nf->low_thresh = 0;
+	unsigned int seq;
+	int i;
 
+	nf->low_thresh = 0;
 	local_bh_disable();
-	inet_frag_evictor(nf, f, true);
+
+evict_again:
+	seq = read_seqbegin(&f->rnd_seqlock);
+
+	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
+		inet_evict_bucket(f, &f->hash[i]);
+
+	if (read_seqretry(&f->rnd_seqlock, seq))
+		goto evict_again;
+
 	local_bh_enable();
 
 	percpu_counter_destroy(&nf->mem);
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
 
-static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+static struct inet_frag_bucket *
+get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
+__acquires(hb->chain_lock)
 {
 	struct inet_frag_bucket *hb;
-	unsigned int hash;
+	unsigned int seq, hash;
+
+ restart:
+	seq = read_seqbegin(&f->rnd_seqlock);
 
-	read_lock(&f->lock);
-	hash = f->hashfn(fq);
+	hash = inet_frag_hashfn(f, fq);
 	hb = &f->hash[hash];
 
 	spin_lock(&hb->chain_lock);
+	if (read_seqretry(&f->rnd_seqlock, seq)) {
+		spin_unlock(&hb->chain_lock);
+		goto restart;
+	}
+
+	return hb;
+}
+
+static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
+{
+	struct inet_frag_bucket *hb;
+
+	hb = get_frag_bucket_locked(fq, f);
 	hlist_del(&fq->list);
 	spin_unlock(&hb->chain_lock);
-
-	read_unlock(&f->lock);
-	inet_frag_lru_del(fq);
 }
 
 void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
@@ -165,8 +305,7 @@ static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f,
 	kfree_skb(skb);
 }
 
-void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
-					int *work)
+void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
 {
 	struct sk_buff *fp;
 	struct netns_frags *nf;
@@ -186,86 +325,30 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
 		fp = xp;
 	}
 	sum = sum_truesize + f->qsize;
-	if (work)
-		*work -= sum;
 	sub_frag_mem_limit(q, sum);
 
 	if (f->destructor)
 		f->destructor(q);
 	kfree(q);
-
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
-int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
-{
-	struct inet_frag_queue *q;
-	int work, evicted = 0;
-
-	if (!force) {
-		if (frag_mem_limit(nf) <= nf->high_thresh)
-			return 0;
-	}
-
-	work = frag_mem_limit(nf) - nf->low_thresh;
-	while (work > 0 || force) {
-		spin_lock(&nf->lru_lock);
-
-		if (list_empty(&nf->lru_list)) {
-			spin_unlock(&nf->lru_lock);
-			break;
-		}
-
-		q = list_first_entry(&nf->lru_list,
-				struct inet_frag_queue, lru_list);
-		atomic_inc(&q->refcnt);
-		/* Remove q from list to avoid several CPUs grabbing it */
-		list_del_init(&q->lru_list);
-
-		spin_unlock(&nf->lru_lock);
-
-		spin_lock(&q->lock);
-		if (!(q->last_in & INET_FRAG_COMPLETE))
-			inet_frag_kill(q, f);
-		spin_unlock(&q->lock);
-
-		if (atomic_dec_and_test(&q->refcnt))
-			inet_frag_destroy(q, f, &work);
-		evicted++;
-	}
-
-	return evicted;
-}
-EXPORT_SYMBOL(inet_frag_evictor);
-
 static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
 		struct inet_frag_queue *qp_in, struct inet_frags *f,
 		void *arg)
 {
-	struct inet_frag_bucket *hb;
+	struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
 	struct inet_frag_queue *qp;
-	unsigned int hash;
-
-	read_lock(&f->lock); /* Protects against hash rebuild */
-	/*
-	 * While we stayed w/o the lock other CPU could update
-	 * the rnd seed, so we need to re-calculate the hash
-	 * chain. Fortunatelly the qp_in can be used to get one.
-	 */
-	hash = f->hashfn(qp_in);
-	hb = &f->hash[hash];
-	spin_lock(&hb->chain_lock);
 
 #ifdef CONFIG_SMP
 	/* With SMP race we have to recheck hash table, because
-	 * such entry could be created on other cpu, while we
-	 * released the hash bucket lock.
+	 * such entry could have been created on other cpu before
+	 * we acquired hash bucket lock.
 	 */
 	hlist_for_each_entry(qp, &hb->chain, list) {
 		if (qp->net == nf && f->match(qp, arg)) {
 			atomic_inc(&qp->refcnt);
 			spin_unlock(&hb->chain_lock);
-			read_unlock(&f->lock);
 			qp_in->last_in |= INET_FRAG_COMPLETE;
 			inet_frag_put(qp_in, f);
 			return qp;
@@ -278,9 +361,8 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
 
 	atomic_inc(&qp->refcnt);
 	hlist_add_head(&qp->list, &hb->chain);
-	inet_frag_lru_add(nf, qp);
+
 	spin_unlock(&hb->chain_lock);
-	read_unlock(&f->lock);
 
 	return qp;
 }
@@ -290,6 +372,11 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 {
 	struct inet_frag_queue *q;
 
+	if (frag_mem_limit(nf) > nf->high_thresh) {
+		inet_frag_schedule_worker(f);
+		return NULL;
+	}
+
 	q = kzalloc(f->qsize, GFP_ATOMIC);
 	if (q == NULL)
 		return NULL;
@@ -301,7 +388,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
 	atomic_set(&q->refcnt, 1);
-	INIT_LIST_HEAD(&q->lru_list);
 
 	return q;
 }
@@ -320,12 +406,15 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
 
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		struct inet_frags *f, void *key, unsigned int hash)
-	__releases(&f->lock)
 {
 	struct inet_frag_bucket *hb;
 	struct inet_frag_queue *q;
 	int depth = 0;
 
+	if (frag_mem_limit(nf) > nf->low_thresh)
+		inet_frag_schedule_worker(f);
+
+	hash &= (INETFRAGS_HASHSZ - 1);
 	hb = &f->hash[hash];
 
 	spin_lock(&hb->chain_lock);
@@ -333,18 +422,22 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		if (q->net == nf && f->match(q, key)) {
 			atomic_inc(&q->refcnt);
 			spin_unlock(&hb->chain_lock);
-			read_unlock(&f->lock);
 			return q;
 		}
 		depth++;
 	}
 	spin_unlock(&hb->chain_lock);
-	read_unlock(&f->lock);
 
 	if (depth <= INETFRAGS_MAXDEPTH)
 		return inet_frag_create(nf, f, key);
-	else
-		return ERR_PTR(-ENOBUFS);
+
+	if (inet_frag_may_rebuild(f)) {
+		if (!f->rebuild)
+			f->rebuild = true;
+		inet_frag_schedule_worker(f);
+	}
+
+	return ERR_PTR(-ENOBUFS);
 }
 EXPORT_SYMBOL(inet_frag_find);
 

net/ipv4/ip_fragment.c

@@ -86,11 +86,6 @@ static inline u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-int ip_frag_nqueues(struct net *net)
-{
-	return net->ipv4.frags.nqueues;
-}
-
 int ip_frag_mem(struct net *net)
 {
 	return sum_frag_mem_limit(&net->ipv4.frags);
@@ -109,21 +104,21 @@ static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
 	net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
 	return jhash_3words((__force u32)id << 16 | prot,
 			    (__force u32)saddr, (__force u32)daddr,
-			    ip4_frags.rnd) & (INETFRAGS_HASHSZ - 1);
+			    ip4_frags.rnd);
 }
 
-static unsigned int ip4_hashfn(struct inet_frag_queue *q)
+static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
 {
-	struct ipq *ipq;
+	const struct ipq *ipq;
 
 	ipq = container_of(q, struct ipq, q);
 	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
 }
 
-static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
+static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
 {
-	struct ipq *qp;
-	struct ip4_create_arg *arg = a;
+	const struct ipq *qp;
+	const struct ip4_create_arg *arg = a;
 
 	qp = container_of(q, struct ipq, q);
 	return	qp->id == arg->iph->id &&
@@ -133,14 +128,14 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
 		qp->user == arg->user;
 }
 
-static void ip4_frag_init(struct inet_frag_queue *q, void *a)
+static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct ipq *qp = container_of(q, struct ipq, q);
 	struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4,
 					       frags);
 	struct net *net = container_of(ipv4, struct net, ipv4);
 
-	struct ip4_create_arg *arg = a;
+	const struct ip4_create_arg *arg = a;
 
 	qp->protocol = arg->iph->protocol;
 	qp->id = arg->iph->id;
@@ -177,18 +172,6 @@ static void ipq_kill(struct ipq *ipq)
 	inet_frag_kill(&ipq->q, &ip4_frags);
 }
 
-/* Memory limiting on fragments.  Evictor trashes the oldest
- * fragment queue until we are back under the threshold.
- */
-static void ip_evictor(struct net *net)
-{
-	int evicted;
-
-	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false);
-	if (evicted)
-		IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted);
-}
-
 /*
  * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
  */
@@ -207,7 +190,8 @@ static void ip_expire(unsigned long arg)
 
 	ipq_kill(qp);
 
-	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
+	if (!(qp->q.last_in & INET_FRAG_EVICTED))
+		IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
 	if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
@@ -260,7 +244,6 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 	arg.iph = iph;
 	arg.user = user;
 
-	read_lock(&ip4_frags.lock);
 	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
 	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
@@ -505,7 +488,6 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	}
 
 	skb_dst_drop(skb);
-	inet_frag_lru_move(&qp->q);
 	return -EINPROGRESS;
 
 err:
@@ -655,9 +637,6 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 	net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
 
-	/* Start by cleaning up the memory. */
-	ip_evictor(net);
-
 	/* Lookup (or create) queue header */
 	if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) {
 		int ret;
@@ -721,14 +700,17 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
 		.data		= &init_net.ipv4.frags.high_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.ipv4.frags.low_thresh
 	},
 	{
 		.procname	= "ipfrag_low_thresh",
 		.data		= &init_net.ipv4.frags.low_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &init_net.ipv4.frags.high_thresh
 	},
 	{
 		.procname	= "ipfrag_time",
@@ -740,10 +722,12 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
 	{ }
 };
 
+/* secret interval has been deprecated */
+static int ip4_frags_secret_interval_unused;
 static struct ctl_table ip4_frags_ctl_table[] = {
 	{
 		.procname	= "ipfrag_secret_interval",
-		.data		= &ip4_frags.secret_interval,
+		.data		= &ip4_frags_secret_interval_unused,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -771,7 +755,10 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net)
 			goto err_alloc;
 
 		table[0].data = &net->ipv4.frags.high_thresh;
+		table[0].extra1 = &net->ipv4.frags.low_thresh;
+		table[0].extra2 = &init_net.ipv4.frags.high_thresh;
 		table[1].data = &net->ipv4.frags.low_thresh;
+		table[1].extra2 = &net->ipv4.frags.high_thresh;
 		table[2].data = &net->ipv4.frags.timeout;
 
 		/* Don't export sysctls to unprivileged users */
@@ -873,6 +860,5 @@ void __init ipfrag_init(void)
 	ip4_frags.qsize = sizeof(struct ipq);
 	ip4_frags.match = ip4_frag_match;
 	ip4_frags.frag_expire = ip_expire;
-	ip4_frags.secret_interval = 10 * 60 * HZ;
 	inet_frags_init(&ip4_frags);
 }

net/ipv4/proc.c

@@ -52,6 +52,7 @@
 static int sockstat_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
+	unsigned int frag_mem;
 	int orphans, sockets;
 
 	local_bh_disable();
@@ -71,8 +72,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
 		   sock_prot_inuse_get(net, &raw_prot));
-	seq_printf(seq,  "FRAG: inuse %d memory %d\n",
-			ip_frag_nqueues(net), ip_frag_mem(net));
+	frag_mem = ip_frag_mem(net);
+	seq_printf(seq,  "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
 	return 0;
 }
 

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -63,6 +63,8 @@ struct nf_ct_frag6_skb_cb
 static struct inet_frags nf_frags;
 
 #ifdef CONFIG_SYSCTL
+static int zero;
+
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_timeout",
@@ -76,14 +78,17 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 		.data		= &init_net.nf_frag.frags.low_thresh,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &init_net.nf_frag.frags.high_thresh
 	},
 	{
 		.procname	= "nf_conntrack_frag6_high_thresh",
 		.data		= &init_net.nf_frag.frags.high_thresh,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.nf_frag.frags.low_thresh
 	},
 	{ }
 };
@@ -102,7 +107,10 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
 
 		table[0].data = &net->nf_frag.frags.timeout;
 		table[1].data = &net->nf_frag.frags.low_thresh;
+		table[1].extra2 = &net->nf_frag.frags.high_thresh;
 		table[2].data = &net->nf_frag.frags.high_thresh;
+		table[2].extra1 = &net->nf_frag.frags.low_thresh;
+		table[2].extra2 = &init_net.nf_frag.frags.high_thresh;
 	}
 
 	hdr = register_net_sysctl(net, "net/netfilter", table);
@@ -147,16 +155,13 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
 				 const struct in6_addr *daddr)
 {
-	u32 c;
-
 	net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
-	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			 (__force u32)id, nf_frags.rnd);
-	return c & (INETFRAGS_HASHSZ - 1);
+	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
+			    (__force u32)id, nf_frags.rnd);
 }
 
 
-static unsigned int nf_hashfn(struct inet_frag_queue *q)
+static unsigned int nf_hashfn(const struct inet_frag_queue *q)
 {
 	const struct frag_queue *nq;
 
@@ -196,7 +201,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 	arg.dst = dst;
 	arg.ecn = ecn;
 
-	read_lock_bh(&nf_frags.lock);
+	local_bh_disable();
 	hash = nf_hash_frag(id, src, dst);
 
 	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
@@ -352,7 +357,6 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 		fq->q.last_in |= INET_FRAG_FIRST_IN;
 	}
 
-	inet_frag_lru_move(&fq->q);
 	return 0;
 
 discard_fq:
@@ -597,10 +601,6 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(clone);
 	fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
-	local_bh_disable();
-	inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false);
-	local_bh_enable();
-
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
 		     ip6_frag_ecn(hdr));
 	if (fq == NULL) {
@@ -677,7 +677,6 @@ int nf_ct_frag6_init(void)
 	nf_frags.qsize = sizeof(struct frag_queue);
 	nf_frags.match = ip6_frag_match;
 	nf_frags.frag_expire = nf_ct_frag6_expire;
-	nf_frags.secret_interval = 10 * 60 * HZ;
 	inet_frags_init(&nf_frags);
 
 	ret = register_pernet_subsys(&nf_ct_net_ops);

net/ipv6/proc.c

@@ -33,6 +33,7 @@
 static int sockstat6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = seq->private;
+	unsigned int frag_mem = ip6_frag_mem(net);
 
 	seq_printf(seq, "TCP6: inuse %d\n",
 		       sock_prot_inuse_get(net, &tcpv6_prot));
@@ -42,8 +43,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
 			sock_prot_inuse_get(net, &udplitev6_prot));
 	seq_printf(seq, "RAW6: inuse %d\n",
 		       sock_prot_inuse_get(net, &rawv6_prot));
-	seq_printf(seq, "FRAG6: inuse %d memory %d\n",
-		       ip6_frag_nqueues(net), ip6_frag_mem(net));
+	seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
 	return 0;
 }
 

net/ipv6/reassembly.c

@@ -85,27 +85,23 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
 				    const struct in6_addr *daddr)
 {
-	u32 c;
-
 	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
-	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			 (__force u32)id, ip6_frags.rnd);
-
-	return c & (INETFRAGS_HASHSZ - 1);
+	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
+			    (__force u32)id, ip6_frags.rnd);
 }
 
-static unsigned int ip6_hashfn(struct inet_frag_queue *q)
+static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
 {
-	struct frag_queue *fq;
+	const struct frag_queue *fq;
 
 	fq = container_of(q, struct frag_queue, q);
 	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
 }
 
-bool ip6_frag_match(struct inet_frag_queue *q, void *a)
+bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
 {
-	struct frag_queue *fq;
-	struct ip6_create_arg *arg = a;
+	const struct frag_queue *fq;
+	const struct ip6_create_arg *arg = a;
 
 	fq = container_of(q, struct frag_queue, q);
 	return	fq->id == arg->id &&
@@ -115,10 +111,10 @@ bool ip6_frag_match(struct inet_frag_queue *q, void *a)
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
-void ip6_frag_init(struct inet_frag_queue *q, void *a)
+void ip6_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	struct ip6_create_arg *arg = a;
+	const struct ip6_create_arg *arg = a;
 
 	fq->id = arg->id;
 	fq->user = arg->user;
@@ -145,7 +141,9 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
 	if (!dev)
 		goto out_rcu_unlock;
 
-	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+	if (!(fq->q.last_in & INET_FRAG_EVICTED))
+		IP6_INC_STATS_BH(net, __in6_dev_get(dev),
+				 IPSTATS_MIB_REASMTIMEOUT);
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
 
 	/* Don't send error if the first segment did not arrive. */
@@ -192,7 +190,6 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.dst = dst;
 	arg.ecn = ecn;
 
-	read_lock(&ip6_frags.lock);
 	hash = inet6_hash_frag(id, src, dst);
 
 	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
@@ -353,7 +350,6 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 	}
 
 	skb_dst_drop(skb);
-	inet_frag_lru_move(&fq->q);
 	return -1;
 
 discard_fq:
@@ -523,7 +519,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
-	int evicted;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -552,11 +547,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
-	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false);
-	if (evicted)
-		IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
-				 IPSTATS_MIB_REASMFAILS, evicted);
-
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
 		     ip6_frag_ecn(hdr));
 	if (fq != NULL) {
@@ -588,20 +578,25 @@ static const struct inet6_protocol frag_protocol =
 };
 
 #ifdef CONFIG_SYSCTL
+static int zero;
+
 static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ip6frag_high_thresh",
 		.data		= &init_net.ipv6.frags.high_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.ipv6.frags.low_thresh
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
 		.data		= &init_net.ipv6.frags.low_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &init_net.ipv6.frags.high_thresh
 	},
 	{
 		.procname	= "ip6frag_time",
@@ -613,10 +608,12 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{ }
 };
 
+/* secret interval has been deprecated */
+static int ip6_frags_secret_interval_unused;
 static struct ctl_table ip6_frags_ctl_table[] = {
 	{
 		.procname	= "ip6frag_secret_interval",
-		.data		= &ip6_frags.secret_interval,
+		.data		= &ip6_frags_secret_interval_unused,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -636,7 +633,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 			goto err_alloc;
 
 		table[0].data = &net->ipv6.frags.high_thresh;
+		table[0].extra1 = &net->ipv6.frags.low_thresh;
+		table[0].extra2 = &init_net.ipv6.frags.high_thresh;
 		table[1].data = &net->ipv6.frags.low_thresh;
+		table[1].extra2 = &net->ipv6.frags.high_thresh;
 		table[2].data = &net->ipv6.frags.timeout;
 
 		/* Don't export sysctls to unprivileged users */
@@ -746,7 +746,6 @@ int __init ipv6_frag_init(void)
 	ip6_frags.qsize = sizeof(struct frag_queue);
 	ip6_frags.match = ip6_frag_match;
 	ip6_frags.frag_expire = ip6_frag_expire;
-	ip6_frags.secret_interval = 10 * 60 * HZ;
 	inet_frags_init(&ip6_frags);
 out:
 	return ret;