Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 7e32aa4d authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'inet-frags-next' 



Nikolay Aleksandrov says:

====================
inet: frags: cleanup and kmem_cache use

This patchset does a couple of small cleanups in patches 1-5 and then in
patch 06 it introduces the use of kmem_cache for allocation/freeing of
inet_frag_queue+header objects.

v2: Broke up patch 02 into 3 patches as David suggested

Here are the results of a couple of netperf runs:
netperf options: -l 30 -I95,5 -i 15,10 -m 64k

- 10 gig before the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.155.1 () 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      442466      0    7551.39
212992           30.00      439130           7494.45

- 10 gig after the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.155.1 () 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      458846      0    7830.94
212992           30.00      457575           7809.25

- Virtio before the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.144.1 () 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      735000      0    12543.96
212992           30.00      560322           9562.79

- Virtio after the patchset
MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.144.1 () 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      731729      0    12488.14
212992           30.00      647241           11046.21
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents a5536e10 d4ad4d22

include/net/inet_frag.h

+38 −12
Original line number Diff line number Diff line
@@ -15,25 +15,49 @@ struct netns_frags { 
	int			low_thresh;

};



/**

 * fragment queue flags

 *

 * @INET_FRAG_FIRST_IN: first fragment has arrived

 * @INET_FRAG_LAST_IN: final fragment has arrived

 * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction

 * @INET_FRAG_EVICTED: frag queue is being evicted

 */

enum {

	INET_FRAG_FIRST_IN	= BIT(0),

	INET_FRAG_LAST_IN	= BIT(1),

	INET_FRAG_COMPLETE	= BIT(2),

	INET_FRAG_EVICTED	= BIT(3)

};



/**

 * struct inet_frag_queue - fragment queue

 *

 * @lock: spinlock protecting the queue

 * @timer: queue expiration timer

 * @list: hash bucket list

 * @refcnt: reference count of the queue

 * @fragments: received fragments head

 * @fragments_tail: received fragments tail

 * @stamp: timestamp of the last received fragment

 * @len: total length of the original datagram

 * @meat: length of received fragments so far

 * @flags: fragment queue flags

 * @max_size: (ipv4 only) maximum received fragment size with IP_DF set

 * @net: namespace that this frag belongs to

 */

struct inet_frag_queue {

	spinlock_t		lock;

	struct timer_list	timer;      /* when will this queue expire? */

	struct timer_list	timer;

	struct hlist_node	list;

	atomic_t		refcnt;

	struct sk_buff		*fragments; /* list of received fragments */

	struct sk_buff		*fragments;

	struct sk_buff		*fragments_tail;

	ktime_t			stamp;

	int			len;        /* total length of orig datagram */

	int			len;

	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



	__u8			flags;

	u16			max_size;



	struct netns_frags	*net;

};
@@ -77,9 +101,11 @@ struct inet_frags { 
	void			(*destructor)(struct inet_frag_queue *);

	void			(*skb_free)(struct sk_buff *);

	void			(*frag_expire)(unsigned long data);

	struct kmem_cache	*frags_cachep;

	const char		*frags_cache_name;

};



void inet_frags_init(struct inet_frags *);

int inet_frags_init(struct inet_frags *);

void inet_frags_fini(struct inet_frags *);



void inet_frags_init_net(struct netns_frags *nf);

net/ieee802154/reassembly.c

+13 −8
Original line number Diff line number Diff line
@@ -30,6 +30,8 @@ 


#include "reassembly.h"



static const char lowpan_frags_cache_name[] = "lowpan-frags";



struct lowpan_frag_info {

	__be16 d_tag;

	u16 d_size;
@@ -99,7 +101,7 @@ static void lowpan_frag_expire(unsigned long data) 


	spin_lock(&fq->q.lock);



	if (fq->q.last_in & INET_FRAG_COMPLETE)

	if (fq->q.flags & INET_FRAG_COMPLETE)

		goto out;



	inet_frag_kill(&fq->q, &lowpan_frags);
@@ -142,7 +144,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, 
	struct net_device *dev;

	int end, offset;



	if (fq->q.last_in & INET_FRAG_COMPLETE)

	if (fq->q.flags & INET_FRAG_COMPLETE)

		goto err;



	offset = lowpan_cb(skb)->d_offset << 3;
@@ -154,14 +156,14 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, 
		 * or have different end, the segment is corrupted.

		 */

		if (end < fq->q.len ||

		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))

		    ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))

			goto err;

		fq->q.last_in |= INET_FRAG_LAST_IN;

		fq->q.flags |= INET_FRAG_LAST_IN;

		fq->q.len = end;

	} else {

		if (end > fq->q.len) {

			/* Some bits beyond end -> corruption. */

			if (fq->q.last_in & INET_FRAG_LAST_IN)

			if (fq->q.flags & INET_FRAG_LAST_IN)

				goto err;

			fq->q.len = end;

		}
@@ -201,13 +203,13 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, 
	if (frag_type == LOWPAN_DISPATCH_FRAG1) {

		/* Calculate uncomp. 6lowpan header to estimate full size */

		fq->q.meat += lowpan_uncompress_size(skb, NULL);

		fq->q.last_in |= INET_FRAG_FIRST_IN;

		fq->q.flags |= INET_FRAG_FIRST_IN;

	} else {

		fq->q.meat += skb->len;

	}

	add_frag_mem_limit(&fq->q, skb->truesize);



	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&

	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&

	    fq->q.meat == fq->q.len) {

		int res;

		unsigned long orefdst = skb->_skb_refdst;
@@ -571,7 +573,10 @@ 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;

	inet_frags_init(&lowpan_frags);

	lowpan_frags.frags_cache_name = lowpan_frags_cache_name;

	ret = inet_frags_init(&lowpan_frags);

	if (ret)

		goto err_pernet;



	return ret;

err_pernet:

net/ipv4/inet_fragment.c

+25 −16
Original line number Diff line number Diff line
@@ -151,9 +151,7 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) 
			goto evict_again;

		}



		/* suppress xmit of (icmp) error packet */

		fq->last_in &= ~INET_FRAG_FIRST_IN;

		fq->last_in |= INET_FRAG_EVICTED;

		fq->flags |= INET_FRAG_EVICTED;

		hlist_del(&fq->list);

		hlist_add_head(&fq->list, &expired);

		++evicted;
@@ -200,7 +198,7 @@ static void inet_frag_schedule_worker(struct inet_frags *f) 
		schedule_work(&f->frags_work);

}



void inet_frags_init(struct inet_frags *f)

int inet_frags_init(struct inet_frags *f)

{

	int i;
@@ -215,6 +213,12 @@ void inet_frags_init(struct inet_frags *f) 


	seqlock_init(&f->rnd_seqlock);

	f->last_rebuild_jiffies = 0;

	f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,

					    NULL);

	if (!f->frags_cachep)

		return -ENOMEM;



	return 0;

}

EXPORT_SYMBOL(inet_frags_init);
@@ -227,6 +231,7 @@ EXPORT_SYMBOL(inet_frags_init_net); 
void inet_frags_fini(struct inet_frags *f)

{

	cancel_work_sync(&f->frags_work);

	kmem_cache_destroy(f->frags_cachep);

}

EXPORT_SYMBOL(inet_frags_fini);
@@ -289,10 +294,10 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) 
	if (del_timer(&fq->timer))

		atomic_dec(&fq->refcnt);



	if (!(fq->last_in & INET_FRAG_COMPLETE)) {

	if (!(fq->flags & INET_FRAG_COMPLETE)) {

		fq_unlink(fq, f);

		atomic_dec(&fq->refcnt);

		fq->last_in |= INET_FRAG_COMPLETE;

		fq->flags |= INET_FRAG_COMPLETE;

	}

}

EXPORT_SYMBOL(inet_frag_kill);
@@ -311,7 +316,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) 
	struct netns_frags *nf;

	unsigned int sum, sum_truesize = 0;



	WARN_ON(!(q->last_in & INET_FRAG_COMPLETE));

	WARN_ON(!(q->flags & INET_FRAG_COMPLETE));

	WARN_ON(del_timer(&q->timer) != 0);



	/* Release all fragment data. */
@@ -329,12 +334,13 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) 


	if (f->destructor)

		f->destructor(q);

	kfree(q);

	kmem_cache_free(f->frags_cachep, q);

}

EXPORT_SYMBOL(inet_frag_destroy);



static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,

		struct inet_frag_queue *qp_in, struct inet_frags *f,

						struct inet_frag_queue *qp_in,

						struct inet_frags *f,

						void *arg)

{

	struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
@@ -349,7 +355,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, 
		if (qp->net == nf && f->match(qp, arg)) {

			atomic_inc(&qp->refcnt);

			spin_unlock(&hb->chain_lock);

			qp_in->last_in |= INET_FRAG_COMPLETE;

			qp_in->flags |= INET_FRAG_COMPLETE;

			inet_frag_put(qp_in, f);

			return qp;

		}
@@ -368,7 +374,8 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, 
}



static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,

		struct inet_frags *f, void *arg)

					       struct inet_frags *f,

					       void *arg)

{

	struct inet_frag_queue *q;
@@ -377,7 +384,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, 
		return NULL;

	}



	q = kzalloc(f->qsize, GFP_ATOMIC);

	q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);

	if (q == NULL)

		return NULL;
@@ -393,7 +400,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, 
}



static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,

		struct inet_frags *f, void *arg)

						struct inet_frags *f,

						void *arg)

{

	struct inet_frag_queue *q;
@@ -405,7 +413,8 @@ 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)

				       struct inet_frags *f, void *key,

				       unsigned int hash)

{

	struct inet_frag_bucket *hb;

	struct inet_frag_queue *q;

net/ipv4/ip_fragment.c

+19 −16
Original line number Diff line number Diff line
@@ -55,6 +55,7 @@ 
 */



static int sysctl_ipfrag_max_dist __read_mostly = 64;

static const char ip_frag_cache_name[] = "ip4-frags";



struct ipfrag_skb_cb

{
@@ -185,20 +186,22 @@ static void ip_expire(unsigned long arg) 


	spin_lock(&qp->q.lock);



	if (qp->q.last_in & INET_FRAG_COMPLETE)

	if (qp->q.flags & INET_FRAG_COMPLETE)

		goto out;



	ipq_kill(qp);



	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) {

	if (!(qp->q.flags & INET_FRAG_EVICTED)) {

		struct sk_buff *head = qp->q.fragments;

		const struct iphdr *iph;

		int err;



		IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);



		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)

			goto out;



		rcu_read_lock();

		head->dev = dev_get_by_index_rcu(net, qp->iif);

		if (!head->dev)
@@ -211,8 +214,7 @@ static void ip_expire(unsigned long arg) 
		if (err)

			goto out_rcu_unlock;



		/*

		 * Only an end host needs to send an ICMP

		/* Only an end host needs to send an ICMP

		 * "Fragment Reassembly Timeout" message, per RFC792.

		 */

		if (qp->user == IP_DEFRAG_AF_PACKET ||
@@ -221,7 +223,6 @@ static void ip_expire(unsigned long arg) 
		     (skb_rtable(head)->rt_type != RTN_LOCAL)))

			goto out_rcu_unlock;





		/* Send an ICMP "Fragment Reassembly Timeout" message. */

		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);

out_rcu_unlock:
@@ -302,7 +303,7 @@ static int ip_frag_reinit(struct ipq *qp) 
	} while (fp);

	sub_frag_mem_limit(&qp->q, sum_truesize);



	qp->q.last_in = 0;

	qp->q.flags = 0;

	qp->q.len = 0;

	qp->q.meat = 0;

	qp->q.fragments = NULL;
@@ -323,7 +324,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) 
	int err = -ENOENT;

	u8 ecn;



	if (qp->q.last_in & INET_FRAG_COMPLETE)

	if (qp->q.flags & INET_FRAG_COMPLETE)

		goto err;



	if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
@@ -350,9 +351,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) 
		 * or have different end, the segment is corrupted.

		 */

		if (end < qp->q.len ||

		    ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))

		    ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))

			goto err;

		qp->q.last_in |= INET_FRAG_LAST_IN;

		qp->q.flags |= INET_FRAG_LAST_IN;

		qp->q.len = end;

	} else {

		if (end&7) {
@@ -362,7 +363,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) 
		}

		if (end > qp->q.len) {

			/* Some bits beyond end -> corruption. */

			if (qp->q.last_in & INET_FRAG_LAST_IN)

			if (qp->q.flags & INET_FRAG_LAST_IN)

				goto err;

			qp->q.len = end;

		}
@@ -471,13 +472,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) 
	qp->ecn |= ecn;

	add_frag_mem_limit(&qp->q, skb->truesize);

	if (offset == 0)

		qp->q.last_in |= INET_FRAG_FIRST_IN;

		qp->q.flags |= INET_FRAG_FIRST_IN;



	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&

	    skb->len + ihl > qp->q.max_size)

		qp->q.max_size = skb->len + ihl;



	if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&

	if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&

	    qp->q.meat == qp->q.len) {

		unsigned long orefdst = skb->_skb_refdst;
@@ -860,5 +861,7 @@ void __init ipfrag_init(void) 
	ip4_frags.qsize = sizeof(struct ipq);

	ip4_frags.match = ip4_frag_match;

	ip4_frags.frag_expire = ip_expire;

	inet_frags_init(&ip4_frags);

	ip4_frags.frags_cache_name = ip_frag_cache_name;

	if (inet_frags_init(&ip4_frags))

		panic("IP: failed to allocate ip4_frags cache\n");

}

net/ipv6/netfilter/nf_conntrack_reasm.c

+12 −8
Original line number Diff line number Diff line
@@ -50,6 +50,7 @@ 
#include <linux/module.h>

#include <net/netfilter/ipv6/nf_defrag_ipv6.h>



static const char nf_frags_cache_name[] = "nf-frags";



struct nf_ct_frag6_skb_cb

{
@@ -222,7 +223,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, 
	int offset, end;

	u8 ecn;



	if (fq->q.last_in & INET_FRAG_COMPLETE) {

	if (fq->q.flags & INET_FRAG_COMPLETE) {

		pr_debug("Already completed\n");

		goto err;

	}
@@ -253,11 +254,11 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, 
		 * or have different end, the segment is corrupted.

		 */

		if (end < fq->q.len ||

		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) {

		    ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) {

			pr_debug("already received last fragment\n");

			goto err;

		}

		fq->q.last_in |= INET_FRAG_LAST_IN;

		fq->q.flags |= INET_FRAG_LAST_IN;

		fq->q.len = end;

	} else {

		/* Check if the fragment is rounded to 8 bytes.
@@ -272,7 +273,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, 
		}

		if (end > fq->q.len) {

			/* Some bits beyond end -> corruption. */

			if (fq->q.last_in & INET_FRAG_LAST_IN) {

			if (fq->q.flags & INET_FRAG_LAST_IN) {

				pr_debug("last packet already reached.\n");

				goto err;

			}
@@ -354,7 +355,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, 
	 */

	if (offset == 0) {

		fq->nhoffset = nhoff;

		fq->q.last_in |= INET_FRAG_FIRST_IN;

		fq->q.flags |= INET_FRAG_FIRST_IN;

	}



	return 0;
@@ -617,7 +618,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) 
		goto ret_orig;

	}



	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&

	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&

	    fq->q.meat == fq->q.len) {

		ret_skb = nf_ct_frag6_reasm(fq, dev);

		if (ret_skb == NULL)
@@ -677,12 +678,15 @@ 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;

	inet_frags_init(&nf_frags);



	nf_frags.frags_cache_name = nf_frags_cache_name;

	ret = inet_frags_init(&nf_frags);

	if (ret)

		goto out;

	ret = register_pernet_subsys(&nf_ct_net_ops);

	if (ret)

		inet_frags_fini(&nf_frags);



out:

	return ret;

}