Re: [RFC v2 3/7] net: netfilter conntrack - add per-net functionality for SCTP protocol

[Cyrill Gorcunov <gorcunov@gmail.com>]

[Patrick McHardy - Mon, Mar 16, 2009 at 07:29:02PM +0100]
...
> Its better than the macro and I don't really see a better way, so
> this is fine with me. About the other patches - I just stopped at
> SCTP since it was the first one I truely didn't like :)
>

Here is an updated version of the patch with assignment in cycle.
Please review. If all this series become a mess which hard to unwind
(ie what version of patch is last, which is not) -- I could resend
the whole series (excluding already applied). Just say. Thanks!
---

From: Cyrill Gorcunov <gorcunov@openvz.org>
Subject: [RFC v2 3/7] net: netfilter conntrack - add per-net functionality for SCTP protocol

Module specific data moved into per-net site and being allocated/freed
during net namespace creation/deletion.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
---
 net/netfilter/nf_conntrack_proto_sctp.c |  179 ++++++++++++++++++++++++--------
 1 file changed, 139 insertions(+), 40 deletions(-)

Index: linux-2.6.git/net/netfilter/nf_conntrack_proto_sctp.c
===================================================================
--- linux-2.6.git.orig/net/netfilter/nf_conntrack_proto_sctp.c
+++ linux-2.6.git/net/netfilter/nf_conntrack_proto_sctp.c
@@ -21,6 +21,9 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
@@ -49,16 +52,6 @@ static const char *const sctp_conntrack_
 #define HOURS * 60 MINS
 #define DAYS  * 24 HOURS
 
-static unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] __read_mostly = {
-	[SCTP_CONNTRACK_CLOSED]			= 10 SECS,
-	[SCTP_CONNTRACK_COOKIE_WAIT]		= 3 SECS,
-	[SCTP_CONNTRACK_COOKIE_ECHOED]		= 3 SECS,
-	[SCTP_CONNTRACK_ESTABLISHED]		= 5 DAYS,
-	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= 300 SECS / 1000,
-	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= 300 SECS / 1000,
-	[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]	= 3 SECS,
-};
-
 #define sNO SCTP_CONNTRACK_NONE
 #define	sCL SCTP_CONNTRACK_CLOSED
 #define	sCW SCTP_CONNTRACK_COOKIE_WAIT
@@ -130,6 +123,25 @@ static const u8 sctp_conntracks[2][9][SC
 	}
 };
 
+/* this module per-net specifics */
+static int sctp_net_id;
+struct sctp_net {
+	unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX];
+#ifdef CONFIG_SYSCTL
+	struct ctl_table_header *sysctl_header;
+	struct ctl_table *sysctl_table;
+#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
+	struct ctl_table_header *compat_sysctl_header;
+	struct ctl_table *compat_sysctl_table;
+#endif
+#endif
+};
+
+static inline struct sctp_net *sctp_pernet(struct net *net)
+{
+	return net_generic(net, sctp_net_id);
+}
+
 static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 			      struct nf_conntrack_tuple *tuple)
 {
@@ -297,6 +309,7 @@ static int sctp_packet(struct nf_conn *c
 	const struct sctp_chunkhdr *sch;
 	struct sctp_chunkhdr _sch;
 	u_int32_t offset, count;
+	struct sctp_net *sn;
 	unsigned long map[256 / sizeof(unsigned long)] = { 0 };
 
 	sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph);
@@ -373,7 +386,8 @@ static int sctp_packet(struct nf_conn *c
 	}
 	write_unlock_bh(&sctp_lock);
 
-	nf_ct_refresh_acct(ct, ctinfo, skb, sctp_timeouts[new_state]);
+	sn = sctp_pernet(nf_ct_net(ct));
+	nf_ct_refresh_acct(ct, ctinfo, skb, sn->sctp_timeouts[new_state]);
 
 	if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED &&
 	    dir == IP_CT_DIR_REPLY &&
@@ -540,54 +554,46 @@ static int nlattr_to_sctp(struct nlattr 
 #endif
 
 #ifdef CONFIG_SYSCTL
-static unsigned int sctp_sysctl_table_users;
-static struct ctl_table_header *sctp_sysctl_header;
+/* templates, data assigned later */
 static struct ctl_table sctp_sysctl_table[] = {
 	{
 		.procname	= "nf_conntrack_sctp_timeout_closed",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_CLOSED],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_sctp_timeout_cookie_wait",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_COOKIE_WAIT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_sctp_timeout_cookie_echoed",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_COOKIE_ECHOED],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_sctp_timeout_established",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_ESTABLISHED],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_sctp_timeout_shutdown_sent",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_sctp_timeout_shutdown_recd",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "nf_conntrack_sctp_timeout_shutdown_ack_sent",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -601,49 +607,42 @@ static struct ctl_table sctp_sysctl_tabl
 static struct ctl_table sctp_compat_sysctl_table[] = {
 	{
 		.procname	= "ip_conntrack_sctp_timeout_closed",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_CLOSED],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "ip_conntrack_sctp_timeout_cookie_wait",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_COOKIE_WAIT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "ip_conntrack_sctp_timeout_cookie_echoed",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_COOKIE_ECHOED],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "ip_conntrack_sctp_timeout_established",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_ESTABLISHED],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "ip_conntrack_sctp_timeout_shutdown_sent",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "ip_conntrack_sctp_timeout_shutdown_recd",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
 		.procname	= "ip_conntrack_sctp_timeout_shutdown_ack_sent",
-		.data		= &sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -653,7 +652,7 @@ static struct ctl_table sctp_compat_sysc
 	}
 };
 #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */
-#endif
+#endif /* CONFIG_SYSCTL */
 
 static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
 	.l3proto		= PF_INET,
@@ -673,14 +672,6 @@ static struct nf_conntrack_l4proto nf_co
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
 	.nla_policy		= nf_ct_port_nla_policy,
 #endif
-#ifdef CONFIG_SYSCTL
-	.ctl_table_users	= &sctp_sysctl_table_users,
-	.ctl_table_header	= &sctp_sysctl_header,
-	.ctl_table		= sctp_sysctl_table,
-#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
-	.ctl_compat_table	= sctp_compat_sysctl_table,
-#endif
-#endif
 };
 
 static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
@@ -701,21 +692,126 @@ static struct nf_conntrack_l4proto nf_co
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
 	.nla_policy		= nf_ct_port_nla_policy,
 #endif
+};
+
+static __net_init int sctp_net_init(struct net *net)
+{
+	struct sctp_net *sn;
+	int err;
+
+	sn = kmalloc(sizeof(*sn), GFP_KERNEL);
+	if (!sn)
+		return -ENOMEM;
+
+	/* default values */
+	sn->sctp_timeouts[SCTP_CONNTRACK_CLOSED]	= 10 SECS;
+	sn->sctp_timeouts[SCTP_CONNTRACK_COOKIE_WAIT]	= 3 SECS;
+	sn->sctp_timeouts[SCTP_CONNTRACK_COOKIE_ECHOED]	= 3 SECS;
+	sn->sctp_timeouts[SCTP_CONNTRACK_ESTABLISHED]	= 5 DAYS;
+	sn->sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]	= 300 SECS / 1000;
+	sn->sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]	= 300 SECS / 1000;
+	sn->sctp_timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS;
+
+	err = net_assign_generic(net, sctp_net_id, sn);
+	if (err)
+		goto out;
+
+	/*
+	 * Pin per-net data to sysctl tables
+	 *
+	 * We allocate new ctrl tables from predefined templates
+	 * and then assign .data fields iteratively, we allowed
+	 * to do so since SCTP_CONNTRACK_... (enum sctp_conntrack)
+	 * is a part of userspace ABI and it's hardly that the enum
+	 * entries will be rearranged
+	 */
+
 #ifdef CONFIG_SYSCTL
-	.ctl_table_users	= &sctp_sysctl_table_users,
-	.ctl_table_header	= &sctp_sysctl_header,
-	.ctl_table		= sctp_sysctl_table,
+	{
+	int i;
+	err = -ENOMEM;
+	sn->sysctl_table = kmemdup(sctp_sysctl_table,
+			sizeof(sctp_sysctl_table), GFP_KERNEL);
+	if (!sn->sysctl_table)
+		goto out;
+
+	for (i = SCTP_CONNTRACK_CLOSED; i < SCTP_CONNTRACK_MAX; i++)
+		sn->sysctl_table[i - 1].data = &sn->sctp_timeouts[i];
+
+	sn->sysctl_header = register_net_sysctl_table(net,
+			nf_net_netfilter_sysctl_path, sn->sysctl_table);
+	if (!sn->sysctl_header)
+		goto out_free;
+
+#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
+	sn->compat_sysctl_table = kmemdup(sctp_compat_sysctl_table,
+			sizeof(sctp_compat_sysctl_table), GFP_KERNEL);
+	if (!sn->compat_sysctl_table)
+		goto out_sysctl;
+
+	for (i = SCTP_CONNTRACK_CLOSED; i < SCTP_CONNTRACK_MAX; i++)
+		sn->compat_sysctl_table[err - 1].data = &sn->sctp_timeouts[i];
+
+	sn->compat_sysctl_header = register_net_sysctl_table(net,
+			nf_net_ipv4_netfilter_sysctl_path, sn->compat_sysctl_table);
+	if (!sn->compat_sysctl_header)
+		goto out_free_compat;
+#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */
+	}
+#endif /* CONFIG_SYSCTL */
+
+	return 0;
+
+#ifdef CONFIG_SYSCTL
+
+#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
+out_free_compat:
+	kfree(sn->compat_sysctl_table);
+#endif
+out_sysctl:
+	unregister_net_sysctl_table(sn->sysctl_header);
+out_free:
+	kfree(sn->sysctl_table);
+#endif
+
+out:
+	kfree(sn);
+	return err;
+}
+
+static __net_exit void sctp_net_exit(struct net *net)
+{
+	struct sctp_net *sn = sctp_pernet(net);
+#ifdef CONFIG_SYSCTL
+	unregister_net_sysctl_table(sn->sysctl_header);
+#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
+	unregister_net_sysctl_table(sn->compat_sysctl_header);
+	kfree(sn->compat_sysctl_table);
 #endif
+	kfree(sn->sysctl_table);
+#endif
+	kfree(sn);
+
+	net_assign_generic(net, sctp_net_id, NULL);
+}
+
+static struct pernet_operations sctp_net_ops = {
+	.init = sctp_net_init,
+	.exit = sctp_net_exit,
 };
 
 static int __init nf_conntrack_proto_sctp_init(void)
 {
 	int ret;
 
+	ret = register_pernet_gen_subsys(&sctp_net_id, &sctp_net_ops);
+	if (ret < 0)
+		goto out;
+
 	ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_sctp4);
 	if (ret) {
 		printk("nf_conntrack_l4proto_sctp4: protocol register failed\n");
-		goto out;
+		goto cleanup_net;
 	}
 	ret = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_sctp6);
 	if (ret) {
@@ -727,12 +823,15 @@ static int __init nf_conntrack_proto_sct
 
  cleanup_sctp4:
 	nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp4);
+ cleanup_net:
+	unregister_pernet_gen_subsys(sctp_net_id, &sctp_net_ops);
  out:
 	return ret;
 }
 
 static void __exit nf_conntrack_proto_sctp_fini(void)
 {
+	unregister_pernet_gen_subsys(sctp_net_id, &sctp_net_ops);
 	nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp6);
 	nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_sctp4);
 }