[PATCH v2 net-next 0/4] ipv6: fix the reassembly expire code in nf_conntrack

[PATCH v2 net-next 0/4] ipv6: fix the reassembly expire code in nf_conntrack

[Cong Wang]

V2: use IS_ENABLED(CONFIG_IPV6) to fix a build error
    rebase to latest net-next

ipv6: add a new namespace for nf_conntrack_reasm
ipv6: unify conntrack reassembly expire code with standard one
ipv6: make ip6_frag_nqueues() and ip6_frag_mem() static
ipv6: unify fragment thresh handling code

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>

---

 include/net/inet_frag.h                 |    2 +-
 include/net/ipv6.h                      |   32 +++++-
 include/net/net_namespace.h             |    3 +
 include/net/netns/conntrack.h           |    6 +
 net/ipv4/inet_fragment.c                |    9 +-
 net/ipv4/ip_fragment.c                  |    5 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c |  196 ++++++++++++++++---------------
 net/ipv6/reassembly.c                   |   88 ++++----------
 8 files changed, 176 insertions(+), 165 deletions(-)

[PATCH 1/4] ipv6: add a new namespace for nf_conntrack_reasm

[Cong Wang]

As pointed by Michal, it is necessary to add a new
namespace for nf_conntrack_reasm code, this prepares
for the second patch.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: Cong Wang <amwang@redhat.com>
---
 include/net/net_namespace.h             |    3 +
 include/net/netns/conntrack.h           |    6 ++
 net/ipv6/netfilter/nf_conntrack_reasm.c |  135 +++++++++++++++++++++----------
 3 files changed, 102 insertions(+), 42 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 5ae57f1..5c467bb 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -93,6 +93,9 @@ struct net {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct netns_ct		ct;
 #endif
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+	struct netns_nf_ct	nf_ct;
+#endif
 	struct sock		*nfnl;
 	struct sock		*nfnl_stash;
 #endif
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index a1d83cc..13503be 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -96,4 +96,10 @@ struct netns_ct {
 #endif
 	char			*slabname;
 };
+
+struct netns_nf_ct {
+	struct netns_sysctl_ipv6 sysctl;
+	struct netns_frags	frags;
+};
+
 #endif
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index f94fb3a..fff5b71 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -71,27 +71,26 @@ struct nf_ct_frag6_queue
 };
 
 static struct inet_frags nf_frags;
-static struct netns_frags nf_init_frags;
 
 #ifdef CONFIG_SYSCTL
 static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_frag6_timeout",
-		.data		= &nf_init_frags.timeout,
+		.data		= &init_net.nf_ct.frags.timeout,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_frag6_low_thresh",
-		.data		= &nf_init_frags.low_thresh,
+		.data		= &init_net.nf_ct.frags.low_thresh,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
 	{
 		.procname	= "nf_conntrack_frag6_high_thresh",
-		.data		= &nf_init_frags.high_thresh,
+		.data		= &init_net.nf_ct.frags.high_thresh,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
@@ -99,7 +98,54 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
 	{ }
 };
 
-static struct ctl_table_header *nf_ct_frag6_sysctl_header;
+static int __net_init nf_ct_frag6_sysctl_register(struct net *net)
+{
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = nf_ct_frag6_sysctl_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table), GFP_KERNEL);
+		if (table == NULL)
+			goto err_alloc;
+
+		table[0].data = &net->ipv6.frags.high_thresh;
+		table[1].data = &net->ipv6.frags.low_thresh;
+		table[2].data = &net->ipv6.frags.timeout;
+	}
+
+	hdr = register_net_sysctl(net, "net/netfilter", table);
+	if (hdr == NULL)
+		goto err_reg;
+
+	net->ipv6.sysctl.frags_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->nf_ct.sysctl.frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->nf_ct.sysctl.frags_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+#else
+static int __net_init nf_ct_frag6_sysctl_register(struct net *net)
+{
+	return 0;
+}
+static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
+{
+}
 #endif
 
 static unsigned int nf_hashfn(struct inet_frag_queue *q)
@@ -131,13 +177,6 @@ static __inline__ void fq_kill(struct nf_ct_frag6_queue *fq)
 	inet_frag_kill(&fq->q, &nf_frags);
 }
 
-static void nf_ct_frag6_evictor(void)
-{
-	local_bh_disable();
-	inet_frag_evictor(&nf_init_frags, &nf_frags);
-	local_bh_enable();
-}
-
 static void nf_ct_frag6_expire(unsigned long data)
 {
 	struct nf_ct_frag6_queue *fq;
@@ -159,8 +198,8 @@ out:
 
 /* Creation primitives. */
 
-static __inline__ struct nf_ct_frag6_queue *
-fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst)
+static __inline__ struct nf_ct_frag6_queue*
+fq_find(struct net *net, __be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst)
 {
 	struct inet_frag_queue *q;
 	struct ip6_create_arg arg;
@@ -174,7 +213,7 @@ fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst)
 	read_lock_bh(&nf_frags.lock);
 	hash = inet6_hash_frag(id, src, dst, nf_frags.rnd);
 
-	q = inet_frag_find(&nf_init_frags, &nf_frags, &arg, hash);
+	q = inet_frag_find(&net->nf_ct.frags, &nf_frags, &arg, hash);
 	local_bh_enable();
 	if (q == NULL)
 		goto oom;
@@ -186,7 +225,7 @@ oom:
 }
 
 
-static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
+static int nf_ct_frag6_queue(struct nf_ct_frag6_queue*fq, struct sk_buff *skb,
 			     const struct frag_hdr *fhdr, int nhoff)
 {
 	struct sk_buff *prev, *next;
@@ -312,7 +351,7 @@ found:
 	fq->q.meat += skb->len;
 	if (payload_len > fq->q.max_size)
 		fq->q.max_size = payload_len;
-	atomic_add(skb->truesize, &nf_init_frags.mem);
+	atomic_add(skb->truesize, &fq->q.net->mem);
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
@@ -322,7 +361,7 @@ found:
 		fq->q.last_in |= INET_FRAG_FIRST_IN;
 	}
 	write_lock(&nf_frags.lock);
-	list_move_tail(&fq->q.lru_list, &nf_init_frags.lru_list);
+	list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
 	write_unlock(&nf_frags.lock);
 	return 0;
 
@@ -391,7 +430,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
 		clone->ip_summed = head->ip_summed;
 
 		NFCT_FRAG6_CB(clone)->orig = NULL;
-		atomic_add(clone->truesize, &nf_init_frags.mem);
+		atomic_add(clone->truesize, &fq->q.net->mem);
 	}
 
 	/* We have to remove fragment header from datagram and to relocate
@@ -415,7 +454,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
 			head->csum = csum_add(head->csum, fp->csum);
 		head->truesize += fp->truesize;
 	}
-	atomic_sub(head->truesize, &nf_init_frags.mem);
+	atomic_sub(head->truesize, &fq->q.net->mem);
 
 	head->local_df = 1;
 	head->next = NULL;
@@ -527,6 +566,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 {
 	struct sk_buff *clone;
 	struct net_device *dev = skb->dev;
+	struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
 	struct frag_hdr *fhdr;
 	struct nf_ct_frag6_queue *fq;
 	struct ipv6hdr *hdr;
@@ -560,10 +600,13 @@ 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);
 
-	if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh)
-		nf_ct_frag6_evictor();
+	if (atomic_read(&net->nf_ct.frags.mem) > net->nf_ct.frags.high_thresh) {
+		local_bh_disable();
+		inet_frag_evictor(&net->nf_ct.frags, &nf_frags);
+		local_bh_enable();
+	}
 
-	fq = fq_find(fhdr->identification, user, &hdr->saddr, &hdr->daddr);
+	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr);
 	if (fq == NULL) {
 		pr_debug("Can't find and can't create new queue\n");
 		goto ret_orig;
@@ -621,8 +664,31 @@ void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
 	nf_conntrack_put_reasm(skb);
 }
 
+static int nf_ct_net_init(struct net *net)
+{
+	net->nf_ct.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+	net->nf_ct.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+	net->nf_ct.frags.timeout = IPV6_FRAG_TIMEOUT;
+	inet_frags_init_net(&net->nf_ct.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
+}
+
+static void nf_ct_net_exit(struct net *net)
+{
+	nf_ct_frags6_sysctl_unregister(net);
+	inet_frags_exit_net(&net->nf_ct.frags, &nf_frags);
+}
+
+static struct pernet_operations nf_ct_net_ops = {
+	.init = nf_ct_net_init,
+	.exit = nf_ct_net_exit,
+};
+
 int nf_ct_frag6_init(void)
 {
+	int ret = 0;
+
 	nf_frags.hashfn = nf_hashfn;
 	nf_frags.constructor = ip6_frag_init;
 	nf_frags.destructor = NULL;
@@ -631,32 +697,17 @@ int nf_ct_frag6_init(void)
 	nf_frags.match = ip6_frag_match;
 	nf_frags.frag_expire = nf_ct_frag6_expire;
 	nf_frags.secret_interval = 10 * 60 * HZ;
-	nf_init_frags.timeout = IPV6_FRAG_TIMEOUT;
-	nf_init_frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
-	nf_init_frags.low_thresh = IPV6_FRAG_LOW_THRESH;
-	inet_frags_init_net(&nf_init_frags);
 	inet_frags_init(&nf_frags);
 
-#ifdef CONFIG_SYSCTL
-	nf_ct_frag6_sysctl_header = register_net_sysctl(&init_net, "net/netfilter",
-							nf_ct_frag6_sysctl_table);
-	if (!nf_ct_frag6_sysctl_header) {
+	ret = register_pernet_subsys(&nf_ct_net_ops);
+	if (ret)
 		inet_frags_fini(&nf_frags);
-		return -ENOMEM;
-	}
-#endif
 
-	return 0;
+	return ret;
 }
 
 void nf_ct_frag6_cleanup(void)
 {
-#ifdef CONFIG_SYSCTL
-	unregister_net_sysctl_table(nf_ct_frag6_sysctl_header);
-	nf_ct_frag6_sysctl_header = NULL;
-#endif
+	unregister_pernet_subsys(&nf_ct_net_ops);
 	inet_frags_fini(&nf_frags);
-
-	nf_init_frags.low_thresh = 0;
-	nf_ct_frag6_evictor();
 }
-- 
1.7.7.6

[PATCH 2/4] ipv6: unify conntrack reassembly expire code with standard one

[Cong Wang]

Two years ago, Shan Wei tried to fix this:
http://patchwork.ozlabs.org/patch/43905/

The problem is that RFC2460 requires an ICMP Time
Exceeded -- Fragment Reassembly Time Exceeded message should be
sent to the source of that fragment, if the defragmentation
times out.

"
   If insufficient fragments are received to complete reassembly of a
   packet within 60 seconds of the reception of the first-arriving
   fragment of that packet, reassembly of that packet must be
   abandoned and all the fragments that have been received for that
   packet must be discarded.  If the first fragment (i.e., the one
   with a Fragment Offset of zero) has been received, an ICMP Time
   Exceeded -- Fragment Reassembly Time Exceeded message should be
   sent to the source of that fragment.
"

As Herbert suggested, we could actually use the standard IPv6
reassembly code which follows RFC2460.

With this patch applied, I can see ICMP Time Exceeded sent
from the receiver when the sender sent out 3/4 fragmented
IPv6 UPD packet.

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: Cong Wang <amwang@redhat.com>
---
 include/net/ipv6.h                      |   19 ++++++++
 net/ipv6/netfilter/nf_conntrack_reasm.c |   71 +++++++-----------------------
 net/ipv6/reassembly.c                   |   62 ++++++++-------------------
 3 files changed, 54 insertions(+), 98 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 9bed5d4..81d4455 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -411,6 +411,25 @@ struct ip6_create_arg {
 void ip6_frag_init(struct inet_frag_queue *q, void *a);
 bool ip6_frag_match(struct inet_frag_queue *q, void *a);
 
+/*
+ *	Equivalent of ipv4 struct ip
+ */
+struct frag_queue {
+	struct inet_frag_queue	q;
+
+	__be32			id;		/* fragment id		*/
+	u32			user;
+	struct in6_addr		saddr;
+	struct in6_addr		daddr;
+
+	int			iif;
+	unsigned int		csum;
+	__u16			nhoffset;
+};
+
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
+			   struct inet_frags *frags);
+
 static inline bool ipv6_addr_any(const struct in6_addr *a)
 {
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index fff5b71..ecefb31 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -57,19 +57,6 @@ struct nf_ct_frag6_skb_cb
 
 #define NFCT_FRAG6_CB(skb)	((struct nf_ct_frag6_skb_cb*)((skb)->cb))
 
-struct nf_ct_frag6_queue
-{
-	struct inet_frag_queue	q;
-
-	__be32			id;		/* fragment id		*/
-	u32			user;
-	struct in6_addr		saddr;
-	struct in6_addr		daddr;
-
-	unsigned int		csum;
-	__u16			nhoffset;
-};
-
 static struct inet_frags nf_frags;
 
 #ifdef CONFIG_SYSCTL
@@ -150,9 +137,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
 
 static unsigned int nf_hashfn(struct inet_frag_queue *q)
 {
-	const struct nf_ct_frag6_queue *nq;
+	const struct frag_queue *nq;
 
-	nq = container_of(q, struct nf_ct_frag6_queue, q);
+	nq = container_of(q, struct frag_queue, q);
 	return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd);
 }
 
@@ -162,43 +149,19 @@ static void nf_skb_free(struct sk_buff *skb)
 		kfree_skb(NFCT_FRAG6_CB(skb)->orig);
 }
 
-/* Destruction primitives. */
-
-static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
-{
-	inet_frag_put(&fq->q, &nf_frags);
-}
-
-/* Kill fq entry. It is not destroyed immediately,
- * because caller (and someone more) holds reference count.
- */
-static __inline__ void fq_kill(struct nf_ct_frag6_queue *fq)
-{
-	inet_frag_kill(&fq->q, &nf_frags);
-}
-
 static void nf_ct_frag6_expire(unsigned long data)
 {
-	struct nf_ct_frag6_queue *fq;
-
-	fq = container_of((struct inet_frag_queue *)data,
-			struct nf_ct_frag6_queue, q);
-
-	spin_lock(&fq->q.lock);
+	struct frag_queue *fq;
+	struct net *net;
 
-	if (fq->q.last_in & INET_FRAG_COMPLETE)
-		goto out;
+	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	net = container_of(fq->q.net, struct net, nf_ct.frags);
 
-	fq_kill(fq);
-
-out:
-	spin_unlock(&fq->q.lock);
-	fq_put(fq);
+	ip6_expire_frag_queue(net, fq, &nf_frags);
 }
 
 /* Creation primitives. */
-
-static __inline__ struct nf_ct_frag6_queue*
+static __inline__ struct frag_queue *
 fq_find(struct net *net, __be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst)
 {
 	struct inet_frag_queue *q;
@@ -218,14 +181,14 @@ fq_find(struct net *net, __be32 id, u32 user, struct in6_addr *src, struct in6_a
 	if (q == NULL)
 		goto oom;
 
-	return container_of(q, struct nf_ct_frag6_queue, q);
+	return container_of(q, struct frag_queue, q);
 
 oom:
 	return NULL;
 }
 
 
-static int nf_ct_frag6_queue(struct nf_ct_frag6_queue*fq, struct sk_buff *skb,
+static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 			     const struct frag_hdr *fhdr, int nhoff)
 {
 	struct sk_buff *prev, *next;
@@ -366,7 +329,7 @@ found:
 	return 0;
 
 discard_fq:
-	fq_kill(fq);
+	inet_frag_kill(&fq->q, &nf_frags);
 err:
 	return -1;
 }
@@ -381,12 +344,12 @@ err:
  *	the last and the first frames arrived and all the bits are here.
  */
 static struct sk_buff *
-nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
+nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 {
 	struct sk_buff *fp, *op, *head = fq->q.fragments;
 	int    payload_len;
 
-	fq_kill(fq);
+	inet_frag_kill(&fq->q, &nf_frags);
 
 	WARN_ON(head == NULL);
 	WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
@@ -568,7 +531,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	struct net_device *dev = skb->dev;
 	struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
 	struct frag_hdr *fhdr;
-	struct nf_ct_frag6_queue *fq;
+	struct frag_queue *fq;
 	struct ipv6hdr *hdr;
 	int fhoff, nhoff;
 	u8 prevhdr;
@@ -617,7 +580,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
 		spin_unlock_bh(&fq->q.lock);
 		pr_debug("Can't insert skb to queue\n");
-		fq_put(fq);
+		inet_frag_put(&fq->q, &nf_frags);
 		goto ret_orig;
 	}
 
@@ -629,7 +592,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
 	}
 	spin_unlock_bh(&fq->q.lock);
 
-	fq_put(fq);
+	inet_frag_put(&fq->q, &nf_frags);
 	return ret_skb;
 
 ret_orig:
@@ -693,7 +656,7 @@ int nf_ct_frag6_init(void)
 	nf_frags.constructor = ip6_frag_init;
 	nf_frags.destructor = NULL;
 	nf_frags.skb_free = nf_skb_free;
-	nf_frags.qsize = sizeof(struct nf_ct_frag6_queue);
+	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;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 4ff9af6..8508c8c 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -65,24 +65,6 @@ struct ip6frag_skb_cb
 #define FRAG6_CB(skb)	((struct ip6frag_skb_cb*)((skb)->cb))
 
 
-/*
- *	Equivalent of ipv4 struct ipq
- */
-
-struct frag_queue
-{
-	struct inet_frag_queue	q;
-
-	__be32			id;		/* fragment id		*/
-	u32			user;
-	struct in6_addr		saddr;
-	struct in6_addr		daddr;
-
-	int			iif;
-	unsigned int		csum;
-	__u16			nhoffset;
-};
-
 static struct inet_frags ip6_frags;
 
 int ip6_frag_nqueues(struct net *net)
@@ -159,21 +141,6 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a)
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
-/* Destruction primitives. */
-
-static __inline__ void fq_put(struct frag_queue *fq)
-{
-	inet_frag_put(&fq->q, &ip6_frags);
-}
-
-/* Kill fq entry. It is not destroyed immediately,
- * because caller (and someone more) holds reference count.
- */
-static __inline__ void fq_kill(struct frag_queue *fq)
-{
-	inet_frag_kill(&fq->q, &ip6_frags);
-}
-
 static void ip6_evictor(struct net *net, struct inet6_dev *idev)
 {
 	int evicted;
@@ -183,22 +150,17 @@ static void ip6_evictor(struct net *net, struct inet6_dev *idev)
 		IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted);
 }
 
-static void ip6_frag_expire(unsigned long data)
+void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, struct inet_frags *frags)
 {
-	struct frag_queue *fq;
 	struct net_device *dev = NULL;
-	struct net *net;
-
-	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
 
 	spin_lock(&fq->q.lock);
 
 	if (fq->q.last_in & INET_FRAG_COMPLETE)
 		goto out;
 
-	fq_kill(fq);
+	inet_frag_kill(&fq->q, frags);
 
-	net = container_of(fq->q.net, struct net, ipv6.frags);
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(net, fq->iif);
 	if (!dev)
@@ -222,7 +184,19 @@ out_rcu_unlock:
 	rcu_read_unlock();
 out:
 	spin_unlock(&fq->q.lock);
-	fq_put(fq);
+	inet_frag_put(&fq->q, frags);
+}
+EXPORT_SYMBOL(ip6_expire_frag_queue);
+
+static void ip6_frag_expire(unsigned long data)
+{
+	struct frag_queue *fq;
+	struct net *net;
+
+	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	net = container_of(fq->q.net, struct net, ipv6.frags);
+
+	ip6_expire_frag_queue(net, fq, &ip6_frags);
 }
 
 static __inline__ struct frag_queue *
@@ -391,7 +365,7 @@ found:
 	return -1;
 
 discard_fq:
-	fq_kill(fq);
+	inet_frag_kill(&fq->q, &ip6_frags);
 err:
 	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 		      IPSTATS_MIB_REASMFAILS);
@@ -417,7 +391,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	unsigned int nhoff;
 	int sum_truesize;
 
-	fq_kill(fq);
+	inet_frag_kill(&fq->q, &ip6_frags);
 
 	/* Make the one we just received the head. */
 	if (prev) {
@@ -586,7 +560,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
 
 		spin_unlock(&fq->q.lock);
-		fq_put(fq);
+		inet_frag_put(&fq->q, &ip6_frags);
 		return ret;
 	}
 
-- 
1.7.7.6

[PATCH 3/4] ipv6: make ip6_frag_nqueues() and ip6_frag_mem() static inline

[Cong Wang]

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
 include/net/ipv6.h    |   13 +++++++++++--
 net/ipv6/reassembly.c |   10 ----------
 2 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 81d4455..979bf6c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -271,8 +271,17 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 
 extern bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);
 
-int ip6_frag_nqueues(struct net *net);
-int ip6_frag_mem(struct net *net);
+#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 atomic_read(&net->ipv6.frags.mem);
+}
+#endif
 
 #define IPV6_FRAG_HIGH_THRESH	(256 * 1024)	/* 262144 */
 #define IPV6_FRAG_LOW_THRESH	(192 * 1024)	/* 196608 */
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 8508c8c..cac690c 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -67,16 +67,6 @@ struct ip6frag_skb_cb
 
 static struct inet_frags ip6_frags;
 
-int ip6_frag_nqueues(struct net *net)
-{
-	return net->ipv6.frags.nqueues;
-}
-
-int ip6_frag_mem(struct net *net)
-{
-	return atomic_read(&net->ipv6.frags.mem);
-}
-
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 			  struct net_device *dev);
 
-- 
1.7.7.6

[PATCH 4/4] ipv6: unify fragment thresh handling code

[Cong Wang]

Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Michal Kubeček <mkubecek@suse.cz>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
 include/net/inet_frag.h                 |    2 +-
 net/ipv4/inet_fragment.c                |    9 +++++++--
 net/ipv4/ip_fragment.c                  |    5 ++---
 net/ipv6/netfilter/nf_conntrack_reasm.c |    8 +++-----
 net/ipv6/reassembly.c                   |   16 +++++-----------
 5 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 5098ee7..32786a0 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -61,7 +61,7 @@ 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);
+int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		struct inet_frags *f, void *key, unsigned int hash)
 	__releases(&f->lock);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 85190e6..4750d2b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -89,7 +89,7 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
 	nf->low_thresh = 0;
 
 	local_bh_disable();
-	inet_frag_evictor(nf, f);
+	inet_frag_evictor(nf, f, true);
 	local_bh_enable();
 }
 EXPORT_SYMBOL(inet_frags_exit_net);
@@ -158,11 +158,16 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f,
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
-int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f)
+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 (atomic_read(&nf->mem) <= nf->high_thresh)
+			return 0;
+	}
+
 	work = atomic_read(&nf->mem) - nf->low_thresh;
 	while (work > 0) {
 		read_lock(&f->lock);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index fa6a12c..448e685 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -219,7 +219,7 @@ static void ip_evictor(struct net *net)
 {
 	int evicted;
 
-	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags);
+	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false);
 	if (evicted)
 		IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted);
 }
@@ -684,8 +684,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
 
 	/* Start by cleaning up the memory. */
-	if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh)
-		ip_evictor(net);
+	ip_evictor(net);
 
 	/* Lookup (or create) queue header */
 	if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ecefb31..22e9e55 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -563,11 +563,9 @@ 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);
 
-	if (atomic_read(&net->nf_ct.frags.mem) > net->nf_ct.frags.high_thresh) {
-		local_bh_disable();
-		inet_frag_evictor(&net->nf_ct.frags, &nf_frags);
-		local_bh_enable();
-	}
+	local_bh_disable();
+	inet_frag_evictor(&net->nf_ct.frags, &nf_frags, false);
+	local_bh_enable();
 
 	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr);
 	if (fq == NULL) {
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index cac690c..a1610ac 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -131,15 +131,6 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a)
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
-static void ip6_evictor(struct net *net, struct inet6_dev *idev)
-{
-	int evicted;
-
-	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags);
-	if (evicted)
-		IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted);
-}
-
 void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, struct inet_frags *frags)
 {
 	struct net_device *dev = NULL;
@@ -514,6 +505,7 @@ 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;
 
 	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
 
@@ -538,8 +530,10 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
-	if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh)
-		ip6_evictor(net, ip6_dst_idev(skb_dst(skb)));
+	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);
 	if (fq != NULL) {
-- 
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 1/4] ipv6: add a new namespace for nf_conntrack_reasm

[Pablo Neira Ayuso]

On Tue, Sep 18, 2012 at 12:29:39PM +0800, Cong Wang wrote:
> As pointed by Michal, it is necessary to add a new
> namespace for nf_conntrack_reasm code, this prepares
> for the second patch.

This looks good to me, but there are some comestical changes I have to
request.

> Cc: Herbert Xu <herbert@gondor.apana.org.au>
> Cc: Michal Kubeček <mkubecek@suse.cz>
> Cc: David Miller <davem@davemloft.net>
> Cc: Patrick McHardy <kaber@trash.net>
> Cc: Pablo Neira Ayuso <pablo@netfilter.org>
> Cc: netfilter-devel@vger.kernel.org
> Signed-off-by: Cong Wang <amwang@redhat.com>
> ---
>  include/net/net_namespace.h             |    3 +
>  include/net/netns/conntrack.h           |    6 ++
>  net/ipv6/netfilter/nf_conntrack_reasm.c |  135 +++++++++++++++++++++----------
>  3 files changed, 102 insertions(+), 42 deletions(-)
> 
> diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
> index 5ae57f1..5c467bb 100644
> --- a/include/net/net_namespace.h
> +++ b/include/net/net_namespace.h
> @@ -93,6 +93,9 @@ struct net {
>  #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
>  	struct netns_ct		ct;
>  #endif
> +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
> +	struct netns_nf_ct	nf_ct;
> +#endif

There's above one "struct netns_ct" that already encapsulates
netfilter conntrack netns parameters.

However, I'd prefer if, while at it, you define some struct
netns_nf_frag instead.

In net/ipv6/netfilter/Makefile, it says:

# defrag
nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o

Note that nf defragmentation is not glued to conntrack anymore. So I'd
go for one netns_nf_frag for this in include/net/net_namespace.h

Thanks.
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH 1/4] ipv6: add a new namespace for nf_conntrack_reasm

[Cong Wang]

On Tue, 2012-09-18 at 09:37 +0200, Pablo Neira Ayuso wrote:
> > +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
> > +	struct netns_nf_ct	nf_ct;
> > +#endif
> 
> There's above one "struct netns_ct" that already encapsulates
> netfilter conntrack netns parameters.
> 
> However, I'd prefer if, while at it, you define some struct
> netns_nf_frag instead.
> 
> In net/ipv6/netfilter/Makefile, it says:
> 
> # defrag
> nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
> 
> Note that nf defragmentation is not glued to conntrack anymore. So I'd
> go for one netns_nf_frag for this in include/net/net_namespace.h
> 

Sure, I will rename that struct to 'struct netns_nf_frag'.

Thanks for review!

Re: [PATCH v2 net-next 0/4] ipv6: fix the reassembly expire code in nf_conntrack

[David Miller]

From: Cong Wang <amwang@redhat.com>
Date: Tue, 18 Sep 2012 12:29:38 +0800

> V2: use IS_ENABLED(CONFIG_IPV6) to fix a build error
>     rebase to latest net-next
> 
> ipv6: add a new namespace for nf_conntrack_reasm
> ipv6: unify conntrack reassembly expire code with standard one
> ipv6: make ip6_frag_nqueues() and ip6_frag_mem() static
> ipv6: unify fragment thresh handling code
> 
> Cc: Herbert Xu <herbert@gondor.apana.org.au>
> Cc: "David S. Miller" <davem@davemloft.net>
> Signed-off-by: Cong Wang <amwang@redhat.com>

Please address Pedro's feedback and resubmit, thanks.

Re: [PATCH v2 net-next 0/4] ipv6: fix the reassembly expire code in nf_conntrack

[David Miller]

From: David Miller <davem@davemloft.net>
Date: Tue, 18 Sep 2012 17:44:22 -0400 (EDT)

> From: Cong Wang <amwang@redhat.com>
> Date: Tue, 18 Sep 2012 12:29:38 +0800
> 
>> V2: use IS_ENABLED(CONFIG_IPV6) to fix a build error
>>     rebase to latest net-next
>> 
>> ipv6: add a new namespace for nf_conntrack_reasm
>> ipv6: unify conntrack reassembly expire code with standard one
>> ipv6: make ip6_frag_nqueues() and ip6_frag_mem() static
>> ipv6: unify fragment thresh handling code
>> 
>> Cc: Herbert Xu <herbert@gondor.apana.org.au>
>> Cc: "David S. Miller" <davem@davemloft.net>
>> Signed-off-by: Cong Wang <amwang@redhat.com>
> 
> Please address Pedro's feedback and resubmit, thanks.

Of course I meant "Pablo", and I meant to reply to v3 of your patches,
sorry :-)