[patch 0/3] dynamic generic netlink multicast

[patch 0/3] dynamic generic netlink multicast

[Johannes Berg]

This patch series adds dynamic generic netlink multicast groups.
The ACPI people are open to rebasing their patches on top of this.
Both Jamal and Patrick gave it a quick review (Patrick said he'll
review it again when he gets around) and we've discussed the API
for a while ending up with this. Please apply.

johannes

[patch 1/3] netlink: allocate group bitmaps dynamically

[Johannes Berg]

[-- Attachment #1: 020-netlink-groups.patch --]
[-- Type: text/plain, Size: 5234 bytes --]

Allow changing the number of groups for a netlink family
after it has been created, use RCU to protect the listeners
bitmap keeping netlink_has_listeners() lock-free.

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>

---
 include/linux/netlink.h  |    1 
 net/netlink/af_netlink.c |   86 +++++++++++++++++++++++++++++++++++------------
 2 files changed, 66 insertions(+), 21 deletions(-)

--- wireless-dev.orig/net/netlink/af_netlink.c	2007-07-17 14:05:30.210964463 +0200
+++ wireless-dev/net/netlink/af_netlink.c	2007-07-17 14:05:30.720964463 +0200
@@ -62,6 +62,7 @@
 #include <net/netlink.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
+#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
@@ -314,10 +315,12 @@ netlink_update_listeners(struct sock *sk
 	unsigned long mask;
 	unsigned int i;
 
-	for (i = 0; i < NLGRPSZ(tbl->groups)/sizeof(unsigned long); i++) {
+	for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
 		mask = 0;
-		sk_for_each_bound(sk, node, &tbl->mc_list)
-			mask |= nlk_sk(sk)->groups[i];
+		sk_for_each_bound(sk, node, &tbl->mc_list) {
+			if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
+				mask |= nlk_sk(sk)->groups[i];
+		}
 		tbl->listeners[i] = mask;
 	}
 	/* this function is only called with the netlink table "grabbed", which
@@ -555,26 +558,37 @@ netlink_update_subscriptions(struct sock
 	nlk->subscriptions = subscriptions;
 }
 
-static int netlink_alloc_groups(struct sock *sk)
+static int netlink_realloc_groups(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	unsigned int groups;
+	unsigned long *new_groups;
 	int err = 0;
 
 	netlink_lock_table();
 	groups = nl_table[sk->sk_protocol].groups;
 	if (!nl_table[sk->sk_protocol].registered)
 		err = -ENOENT;
-	netlink_unlock_table();
 
 	if (err)
-		return err;
+		goto out_unlock;
 
-	nlk->groups = kzalloc(NLGRPSZ(groups), GFP_KERNEL);
-	if (nlk->groups == NULL)
-		return -ENOMEM;
+	if (nlk->ngroups >= groups)
+		goto out_unlock;
+
+	new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_KERNEL);
+	if (new_groups == NULL) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	memset((char*)new_groups + NLGRPSZ(nlk->ngroups), 0,
+	       NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
+
+	nlk->groups = new_groups;
 	nlk->ngroups = groups;
-	return 0;
+ out_unlock:
+	netlink_unlock_table();
+	return err;
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
@@ -591,11 +605,9 @@ static int netlink_bind(struct socket *s
 	if (nladdr->nl_groups) {
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
-			if (err)
-				return err;
-		}
+		err = netlink_realloc_groups(sk);
+		if (err)
+			return err;
 	}
 
 	if (nlk->pid) {
@@ -839,10 +851,18 @@ retry:
 int netlink_has_listeners(struct sock *sk, unsigned int group)
 {
 	int res = 0;
+	unsigned long *listeners;
 
 	BUG_ON(!(nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET));
+
+	rcu_read_lock();
+	listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);
+
 	if (group - 1 < nl_table[sk->sk_protocol].groups)
-		res = test_bit(group - 1, nl_table[sk->sk_protocol].listeners);
+		res = test_bit(group - 1, listeners);
+
+	rcu_read_unlock();
+
 	return res;
 }
 EXPORT_SYMBOL_GPL(netlink_has_listeners);
@@ -1037,11 +1057,9 @@ static int netlink_setsockopt(struct soc
 
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
-			if (err)
-				return err;
-		}
+		err = netlink_realloc_groups(sk);
+		if (err)
+			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		netlink_table_grab();
@@ -1328,6 +1346,32 @@ out_sock_release:
 	return NULL;
 }
 
+int netlink_change_ngroups(int unit, unsigned int groups)
+{
+	unsigned long *listeners, old = NULL;
+	int err = 0;
+
+	netlink_table_grab();
+	if (NLGRPSZ(nl_table[unit].groups) < NLGRPSZ(groups)) {
+		listeners = kzalloc(NLGRPSZ(groups), GFP_ATOMIC);
+		if (!listeners) {
+			err = -ENOMEM;
+			goto out_ungrab;
+		}
+		old = nl_table[unit].listeners;
+		memcpy(listeners, old, NLGRPSZ(nl_table[unit].groups));
+		rcu_assign_pointer(nl_table[unit].listeners, listeners);
+	}
+	nl_table[unit].groups = groups;
+
+ out_ungrab:
+	netlink_table_ungrab();
+	synchronize_rcu();
+	kfree(old);
+	return err;
+}
+EXPORT_SYMBOL(netlink_change_ngroups);
+
 void netlink_set_nonroot(int protocol, unsigned int flags)
 {
 	if ((unsigned int)protocol < MAX_LINKS)
--- wireless-dev.orig/include/linux/netlink.h	2007-07-17 14:05:14.400964463 +0200
+++ wireless-dev/include/linux/netlink.h	2007-07-17 14:05:30.720964463 +0200
@@ -161,6 +161,7 @@ extern struct sock *netlink_kernel_creat
 					  void (*input)(struct sock *sk, int len),
 					  struct mutex *cb_mutex,
 					  struct module *module);
+extern int netlink_change_ngroups(int unit, unsigned int groups);
 extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
 extern int netlink_has_listeners(struct sock *sk, unsigned int group);
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);

-- 

Re: [patch 1/3] netlink: allocate group bitmaps dynamically

[Patrick McHardy]

Johannes Berg wrote:
> Allow changing the number of groups for a netlink family
> after it has been created, use RCU to protect the listeners
> bitmap keeping netlink_has_listeners() lock-free.
> 
> Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
> 
> ---
>  include/linux/netlink.h  |    1 
>  net/netlink/af_netlink.c |   86 +++++++++++++++++++++++++++++++++++------------
>  2 files changed, 66 insertions(+), 21 deletions(-)
> 
> --- wireless-dev.orig/net/netlink/af_netlink.c	2007-07-17 14:05:30.210964463 +0200
> +++ wireless-dev/net/netlink/af_netlink.c	2007-07-17 14:05:30.720964463 +0200
> -static int netlink_alloc_groups(struct sock *sk)
> +static int netlink_realloc_groups(struct sock *sk)
>  {
>  	struct netlink_sock *nlk = nlk_sk(sk);
>  	unsigned int groups;
> +	unsigned long *new_groups;
>  	int err = 0;
>  
>  	netlink_lock_table();


This is actually a bug in the current code I think, netlink_lock_table
is a reader lock.

>  	groups = nl_table[sk->sk_protocol].groups;
>  	if (!nl_table[sk->sk_protocol].registered)
>  		err = -ENOENT;
> -	netlink_unlock_table();
>  
>  	if (err)
> -		return err;
> +		goto out_unlock;
>  
> -	nlk->groups = kzalloc(NLGRPSZ(groups), GFP_KERNEL);
> -	if (nlk->groups == NULL)
> -		return -ENOMEM;
> +	if (nlk->ngroups >= groups)
> +		goto out_unlock;
> +
> +	new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_KERNEL);
> +	if (new_groups == NULL) {
> +		err = -ENOMEM;
> +		goto out_unlock;
> +	}
> +	memset((char*)new_groups + NLGRPSZ(nlk->ngroups), 0,
> +	       NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
> +
> +	nlk->groups = new_groups;
>  	nlk->ngroups = groups;
> -	return 0;
> + out_unlock:
> +	netlink_unlock_table();
> +	return err;
>  }


> +int netlink_change_ngroups(int unit, unsigned int groups)


I think it would be more consistent to pass the kernel socket
instead of the unit.

> +{
> +	unsigned long *listeners, old = NULL;
> +	int err = 0;
> +
> +	netlink_table_grab();
> +	if (NLGRPSZ(nl_table[unit].groups) < NLGRPSZ(groups)) {
> +		listeners = kzalloc(NLGRPSZ(groups), GFP_ATOMIC);
> +		if (!listeners) {
> +			err = -ENOMEM;
> +			goto out_ungrab;
> +		}
> +		old = nl_table[unit].listeners;
> +		memcpy(listeners, old, NLGRPSZ(nl_table[unit].groups));
> +		rcu_assign_pointer(nl_table[unit].listeners, listeners);
> +	}
> +	nl_table[unit].groups = groups;


This might set the group to a value < 32. I don't expect it matters,
but when I changed to old code to support > 32 groups I enforced
a minimum of 32 so anything outside the kernel multicasting on them
would still work (even though its a really stupid idea). So for
consistency this should probably also use a minimum of 32.

Re: [patch 1/3] netlink: allocate group bitmaps dynamically

[Johannes Berg]

[-- Attachment #1: Type: text/plain, Size: 1292 bytes --]

On Tue, 2007-07-17 at 17:45 +0200, Patrick McHardy wrote:

> > --- wireless-dev.orig/net/netlink/af_netlink.c	2007-07-17 14:05:30.210964463 +0200
> > +++ wireless-dev/net/netlink/af_netlink.c	2007-07-17 14:05:30.720964463 +0200
> > -static int netlink_alloc_groups(struct sock *sk)
> > +static int netlink_realloc_groups(struct sock *sk)
> >  {
> >  	struct netlink_sock *nlk = nlk_sk(sk);
> >  	unsigned int groups;
> > +	unsigned long *new_groups;
> >  	int err = 0;
> >  
> >  	netlink_lock_table();
> 
> 
> This is actually a bug in the current code I think, netlink_lock_table
> is a reader lock.

Looks like, changed to netlink_table_grab()


> > +int netlink_change_ngroups(int unit, unsigned int groups)
> 
> 
> I think it would be more consistent to pass the kernel socket
> instead of the unit.

Alright, changed. Also added kernel doc for the function.

> This might set the group to a value < 32. I don't expect it matters,
> but when I changed to old code to support > 32 groups I enforced
> a minimum of 32 so anything outside the kernel multicasting on them
> would still work (even though its a really stupid idea). So for
> consistency this should probably also use a minimum of 32.

Huh ok. Fixed, and added to documentation.

johannes

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 190 bytes --]

[patch 2/3] netlink: allow removing multicast groups

[Johannes Berg]

[-- Attachment #1: 021-netlink-mc-groups.patch --]
[-- Type: text/plain, Size: 3370 bytes --]

Allow kicking listeners out of a multicast group when necessary
(for example if that group is going to be removed.)

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>

---
 include/linux/netlink.h  |    1 +
 net/netlink/af_netlink.c |   47 ++++++++++++++++++++++++++++++++++-------------
 2 files changed, 35 insertions(+), 13 deletions(-)

--- wireless-dev.orig/include/linux/netlink.h	2007-07-17 14:05:30.720964463 +0200
+++ wireless-dev/include/linux/netlink.h	2007-07-17 14:05:31.250964463 +0200
@@ -162,6 +162,7 @@ extern struct sock *netlink_kernel_creat
 					  struct mutex *cb_mutex,
 					  struct module *module);
 extern int netlink_change_ngroups(int unit, unsigned int groups);
+extern void netlink_clear_multicast_users(int unit, unsigned int group);
 extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
 extern int netlink_has_listeners(struct sock *sk, unsigned int group);
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);
--- wireless-dev.orig/net/netlink/af_netlink.c	2007-07-17 14:05:30.720964463 +0200
+++ wireless-dev/net/netlink/af_netlink.c	2007-07-17 14:05:31.250964463 +0200
@@ -1027,6 +1027,24 @@ void netlink_set_err(struct sock *ssk, u
 	read_unlock(&nl_table_lock);
 }
 
+static void netlink_update_socket_mc(struct netlink_sock *nlk,
+				     unsigned int group,
+				     int is_new)
+{
+	int old, new = !!is_new, subscriptions;
+
+	netlink_table_grab();
+	old = test_bit(group - 1, nlk->groups);
+	subscriptions = nlk->subscriptions - old + new;
+	if (new)
+		__set_bit(group - 1, nlk->groups);
+	else
+		__clear_bit(group - 1, nlk->groups);
+	netlink_update_subscriptions(&nlk->sk, subscriptions);
+	netlink_update_listeners(&nlk->sk);
+	netlink_table_ungrab();
+}
+
 static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			      char __user *optval, int optlen)
 {
@@ -1052,9 +1070,6 @@ static int netlink_setsockopt(struct soc
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		unsigned int subscriptions;
-		int old, new = optname == NETLINK_ADD_MEMBERSHIP ? 1 : 0;
-
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
@@ -1062,16 +1077,8 @@ static int netlink_setsockopt(struct soc
 			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
-		netlink_table_grab();
-		old = test_bit(val - 1, nlk->groups);
-		subscriptions = nlk->subscriptions - old + new;
-		if (new)
-			__set_bit(val - 1, nlk->groups);
-		else
-			__clear_bit(val - 1, nlk->groups);
-		netlink_update_subscriptions(sk, subscriptions);
-		netlink_update_listeners(sk);
-		netlink_table_ungrab();
+		netlink_update_socket_mc(nlk, val,
+					 optname == NETLINK_ADD_MEMBERSHIP);
 		err = 0;
 		break;
 	}
@@ -1372,6 +1379,20 @@ int netlink_change_ngroups(int unit, uns
 }
 EXPORT_SYMBOL(netlink_change_ngroups);
 
+void netlink_clear_multicast_users(int unit, unsigned int group)
+{
+	struct sock *sk;
+	struct hlist_node *node;
+
+	read_lock(&nl_table_lock);
+
+	sk_for_each_bound(sk, node, &nl_table[unit].mc_list)
+		netlink_update_socket_mc(nlk_sk(sk), group, 0);
+
+	read_unlock(&nl_table_lock);
+}
+EXPORT_SYMBOL(netlink_clear_multicast_users);
+
 void netlink_set_nonroot(int protocol, unsigned int flags)
 {
 	if ((unsigned int)protocol < MAX_LINKS)

-- 

Re: [patch 2/3] netlink: allow removing multicast groups

[Patrick McHardy]

Johannes Berg wrote:
> +static void netlink_update_socket_mc(struct netlink_sock *nlk,
> +				     unsigned int group,
> +				     int is_new)
> +{
> +	int old, new = !!is_new, subscriptions;
> +
> +	netlink_table_grab();


Having the caller lock the table would save lots of atomic operation
in case of netlink_clear_multicast_users.

> +	old = test_bit(group - 1, nlk->groups);
> +	subscriptions = nlk->subscriptions - old + new;
> +	if (new)
> +		__set_bit(group - 1, nlk->groups);
> +	else
> +		__clear_bit(group - 1, nlk->groups);
> +	netlink_update_subscriptions(&nlk->sk, subscriptions);
> +	netlink_update_listeners(&nlk->sk);
> +	netlink_table_ungrab();
> +}
> +

> +void netlink_clear_multicast_users(int unit, unsigned int group)

Same as in the last patch, passing the kernel socket would be nicer IMO.

> +{
> +	struct sock *sk;
> +	struct hlist_node *node;
> +
> +	read_lock(&nl_table_lock);

Won't this deadlock? netlink_table_grab takes a write-lock.

> +
> +	sk_for_each_bound(sk, node, &nl_table[unit].mc_list)
> +		netlink_update_socket_mc(nlk_sk(sk), group, 0);
> +
> +	read_unlock(&nl_table_lock);
> +}
> +EXPORT_SYMBOL(netlink_clear_multicast_users);
> +
>  void netlink_set_nonroot(int protocol, unsigned int flags)
>  {
>  	if ((unsigned int)protocol < MAX_LINKS)
> 

Re: [patch 2/3] netlink: allow removing multicast groups

[Johannes Berg]

[-- Attachment #1: Type: text/plain, Size: 675 bytes --]

On Tue, 2007-07-17 at 17:50 +0200, Patrick McHardy wrote:

> Having the caller lock the table would save lots of atomic operation
> in case of netlink_clear_multicast_users.

Good point.

> > +void netlink_clear_multicast_users(int unit, unsigned int group)
> 
> Same as in the last patch, passing the kernel socket would be nicer IMO.

Changed.

> > +	read_lock(&nl_table_lock);
> 
> Won't this deadlock? netlink_table_grab takes a write-lock.

I guess it's valid to update a read lock to a write lock? Or I was just
lucky on UP. But moving the lock out of netlink_clear_multicast_users()
made this obvious and I just use the write lock now.

johannes

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 190 bytes --]

[patch 3/3] generic netlink: dynamic multicast groups

[Johannes Berg]

[-- Attachment #1: 022-genl-multicast-groups.patch --]
[-- Type: text/plain, Size: 10370 bytes --]

Introduce API to dynamically register and unregister multicast groups.

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 include/linux/genetlink.h |   13 +++
 include/net/genetlink.h   |   22 +++++
 net/netlink/genetlink.c   |  190 ++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 218 insertions(+), 7 deletions(-)

--- wireless-dev.orig/include/net/genetlink.h	2007-07-17 14:05:13.760964463 +0200
+++ wireless-dev/include/net/genetlink.h	2007-07-17 14:05:31.780964463 +0200
@@ -5,6 +5,22 @@
 #include <net/netlink.h>
 
 /**
+ * struct genl_multicast_group - generic netlink multicast group
+ * @name: name of the multicast group, names are per-family
+ * @id: multicast group ID, assigned by the core, to use with
+ *      genlmsg_multicast().
+ * @list: list entry for linking
+ * @family: pointer to family, need not be set before registering
+ */
+struct genl_multicast_group
+{
+	struct genl_family	*family;	/* private */
+	struct list_head	list;		/* private */
+	char			name[GENL_NAMSIZ];
+	u32			id;
+};
+
+/**
  * struct genl_family - generic netlink family
  * @id: protocol family idenfitier
  * @hdrsize: length of user specific header in bytes
@@ -14,6 +30,7 @@
  * @attrbuf: buffer to store parsed attributes
  * @ops_list: list of all assigned operations
  * @family_list: family list
+ * @mcast_groups: multicast groups list
  */
 struct genl_family
 {
@@ -25,6 +42,7 @@ struct genl_family
 	struct nlattr **	attrbuf;	/* private */
 	struct list_head	ops_list;	/* private */
 	struct list_head	family_list;	/* private */
+	struct list_head	mcast_groups;	/* private */
 };
 
 /**
@@ -73,6 +91,10 @@ extern int genl_register_family(struct g
 extern int genl_unregister_family(struct genl_family *family);
 extern int genl_register_ops(struct genl_family *, struct genl_ops *ops);
 extern int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
+extern int genl_register_mc_group(struct genl_family *family,
+				  struct genl_multicast_group *grp);
+extern void genl_unregister_mc_group(struct genl_family *family,
+				     struct genl_multicast_group *grp);
 
 extern struct sock *genl_sock;
 
--- wireless-dev.orig/net/netlink/genetlink.c	2007-07-17 14:05:13.860964463 +0200
+++ wireless-dev/net/netlink/genetlink.c	2007-07-17 14:05:31.780964463 +0200
@@ -3,6 +3,7 @@
  *
  * 		Authors:	Jamal Hadi Salim
  * 				Thomas Graf <tgraf@suug.ch>
+ *				Johannes Berg <johannes@sipsolutions.net>
  */
 
 #include <linux/module.h>
@@ -13,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/skbuff.h>
 #include <linux/mutex.h>
+#include <linux/bitmap.h>
 #include <net/sock.h>
 #include <net/genetlink.h>
 
@@ -42,6 +44,17 @@ static void genl_unlock(void)
 #define GENL_FAM_TAB_MASK	(GENL_FAM_TAB_SIZE - 1)
 
 static struct list_head family_ht[GENL_FAM_TAB_SIZE];
+/*
+ * Bitmap of multicast groups that are currently in use.
+ *
+ * To avoid an allocation at boot of just one unsigned long,
+ * declare it global instead.
+ * Bit 0 is marked as already used since group 0 is invalid,
+ * bit 1 is marked as already used since group 1 is the controller group.
+ */
+static unsigned long mc_group_start = 0x3;
+static unsigned long *mc_groups = &mc_group_start;
+static unsigned long mc_groups_longs = 1;
 
 static int genl_ctrl_event(int event, void *data);
 
@@ -116,6 +129,77 @@ static inline u16 genl_generate_id(void)
 	return id_gen_idx;
 }
 
+int genl_register_mc_group(struct genl_family *family,
+			   struct genl_multicast_group *grp)
+{
+	int id = find_first_zero_bit(mc_groups,
+				     mc_groups_longs * BITS_PER_LONG);
+	unsigned long *new_groups;
+	size_t nlen = (mc_groups_longs + 1) * sizeof(unsigned long);
+	int err;
+
+	genl_lock();
+
+	if (id >= mc_groups_longs * BITS_PER_LONG) {
+		if (mc_groups == &mc_group_start) {
+			new_groups = kzalloc(nlen, GFP_KERNEL);
+			if (!mc_groups) {
+				err = -ENOMEM;
+				goto out;
+			}
+			mc_groups = new_groups;
+			*mc_groups = mc_group_start;
+		} else {
+			new_groups = krealloc(mc_groups, nlen, GFP_KERNEL);
+			if (!new_groups) {
+				err = -ENOMEM;
+				goto out;
+			}
+			mc_groups = new_groups;
+			mc_groups[mc_groups_longs] = 0;
+		}
+		mc_groups_longs++;
+	}
+
+	err = netlink_change_ngroups(NETLINK_GENERIC,
+				     sizeof(unsigned long) * NETLINK_GENERIC);
+	if (err)
+		goto out;
+
+	grp->id = id;
+	set_bit(id, mc_groups);
+	list_add_tail(&grp->list, &family->mcast_groups);
+	grp->family = family;
+
+	genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, grp);
+ out:
+	genl_unlock();
+	return 0;
+}
+EXPORT_SYMBOL(genl_register_mc_group);
+
+void genl_unregister_mc_group(struct genl_family *family,
+			      struct genl_multicast_group *grp)
+{
+	BUG_ON(grp->family != family);
+	genl_lock();
+	netlink_clear_multicast_users(NETLINK_GENERIC, grp->id);
+	clear_bit(grp->id, mc_groups);
+	list_del(&grp->list);
+	genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, grp);
+	grp->id = 0;
+	grp->family = NULL;
+	genl_unlock();
+}
+
+static void genl_unregister_mc_groups(struct genl_family *family)
+{
+	struct genl_multicast_group *grp, *tmp;
+
+	list_for_each_entry_safe(grp, tmp, &family->mcast_groups, list)
+		genl_unregister_mc_group(family, grp);
+}
+
 /**
  * genl_register_ops - register generic netlink operations
  * @family: generic netlink family
@@ -216,6 +300,7 @@ int genl_register_family(struct genl_fam
 		goto errout;
 
 	INIT_LIST_HEAD(&family->ops_list);
+	INIT_LIST_HEAD(&family->mcast_groups);
 
 	genl_lock();
 
@@ -275,6 +360,8 @@ int genl_unregister_family(struct genl_f
 {
 	struct genl_family *rc;
 
+	genl_unregister_mc_groups(family);
+
 	genl_lock();
 
 	list_for_each_entry(rc, genl_family_chain(family->id), family_list) {
@@ -410,6 +497,67 @@ static int ctrl_fill_info(struct genl_fa
 		nla_nest_end(skb, nla_ops);
 	}
 
+	if (!list_empty(&family->mcast_groups)) {
+		struct genl_multicast_group *grp;
+		struct nlattr *nla_grps;
+		int idx = 1;
+
+		nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+		if (nla_grps == NULL)
+			goto nla_put_failure;
+
+		list_for_each_entry(grp, &family->mcast_groups, list) {
+			struct nlattr *nest;
+
+			nest = nla_nest_start(skb, idx++);
+			if (nest == NULL)
+				goto nla_put_failure;
+
+			NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id);
+			NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME,
+				       grp->name);
+
+			nla_nest_end(skb, nest);
+		}
+		nla_nest_end(skb, nla_grps);
+	}
+
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	return genlmsg_cancel(skb, hdr);
+}
+
+static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid,
+				u32 seq, u32 flags, struct sk_buff *skb,
+				u8 cmd)
+{
+	void *hdr;
+	struct nlattr *nla_grps;
+	struct nlattr *nest;
+
+	hdr = genlmsg_put(skb, pid, seq, &genl_ctrl, flags, cmd);
+	if (hdr == NULL)
+		return -1;
+
+	NLA_PUT_STRING(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name);
+	NLA_PUT_U16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id);
+
+	nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+	if (nla_grps == NULL)
+		goto nla_put_failure;
+
+	nest = nla_nest_start(skb, 1);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id);
+	NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME,
+		       grp->name);
+
+	nla_nest_end(skb, nest);
+	nla_nest_end(skb, nla_grps);
+
 	return genlmsg_end(skb, hdr);
 
 nla_put_failure:
@@ -453,8 +601,8 @@ errout:
 	return skb->len;
 }
 
-static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid,
-				      int seq, u8 cmd)
+static struct sk_buff *ctrl_build_family_msg(struct genl_family *family,
+					     u32 pid, int seq, u8 cmd)
 {
 	struct sk_buff *skb;
 	int err;
@@ -472,6 +620,25 @@ static struct sk_buff *ctrl_build_msg(st
 	return skb;
 }
 
+static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
+					    u32 pid, int seq, u8 cmd)
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb == NULL)
+		return ERR_PTR(-ENOBUFS);
+
+	err = ctrl_fill_mcgrp_info(grp, pid, seq, 0, skb, cmd);
+	if (err < 0) {
+		nlmsg_free(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
 static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = {
 	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
 	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
@@ -501,8 +668,8 @@ static int ctrl_getfamily(struct sk_buff
 		goto errout;
 	}
 
-	msg = ctrl_build_msg(res, info->snd_pid, info->snd_seq,
-			     CTRL_CMD_NEWFAMILY);
+	msg = ctrl_build_family_msg(res, info->snd_pid, info->snd_seq,
+				    CTRL_CMD_NEWFAMILY);
 	if (IS_ERR(msg)) {
 		err = PTR_ERR(msg);
 		goto errout;
@@ -523,7 +690,15 @@ static int genl_ctrl_event(int event, vo
 	switch (event) {
 	case CTRL_CMD_NEWFAMILY:
 	case CTRL_CMD_DELFAMILY:
-		msg = ctrl_build_msg(data, 0, 0, event);
+		msg = ctrl_build_family_msg(data, 0, 0, event);
+		if (IS_ERR(msg))
+			return PTR_ERR(msg);
+
+		genlmsg_multicast(msg, 0, GENL_ID_CTRL, GFP_KERNEL);
+		break;
+	case CTRL_CMD_NEWMCAST_GRP:
+	case CTRL_CMD_DELMCAST_GRP:
+		msg = ctrl_build_mcgrp_msg(data, 0, 0, event);
 		if (IS_ERR(msg))
 			return PTR_ERR(msg);
 
@@ -557,8 +732,9 @@ static int __init genl_init(void)
 		goto errout_register;
 
 	netlink_set_nonroot(NETLINK_GENERIC, NL_NONROOT_RECV);
-	genl_sock = netlink_kernel_create(NETLINK_GENERIC, GENL_MAX_ID,
-					  genl_rcv, NULL, THIS_MODULE);
+	/* only one static multicast group */
+	genl_sock = netlink_kernel_create(NETLINK_GENERIC, 1, genl_rcv,
+					  NULL, THIS_MODULE);
 	if (genl_sock == NULL)
 		panic("GENL: Cannot initialize generic netlink\n");
 
--- wireless-dev.orig/include/linux/genetlink.h	2007-07-17 14:05:13.800964463 +0200
+++ wireless-dev/include/linux/genetlink.h	2007-07-17 14:05:31.780964463 +0200
@@ -39,6 +39,9 @@ enum {
 	CTRL_CMD_NEWOPS,
 	CTRL_CMD_DELOPS,
 	CTRL_CMD_GETOPS,
+	CTRL_CMD_NEWMCAST_GRP,
+	CTRL_CMD_DELMCAST_GRP,
+	CTRL_CMD_GETMCAST_GRP, /* unused */
 	__CTRL_CMD_MAX,
 };
 
@@ -52,6 +55,7 @@ enum {
 	CTRL_ATTR_HDRSIZE,
 	CTRL_ATTR_MAXATTR,
 	CTRL_ATTR_OPS,
+	CTRL_ATTR_MCAST_GROUPS,
 	__CTRL_ATTR_MAX,
 };
 
@@ -66,4 +70,13 @@ enum {
 
 #define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1)
 
+enum {
+	CTRL_ATTR_MCAST_GRP_UNSPEC,
+	CTRL_ATTR_MCAST_GRP_NAME,
+	CTRL_ATTR_MCAST_GRP_ID,
+	__CTRL_ATTR_MCAST_GRP_MAX,
+};
+
+#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
+
 #endif	/* __LINUX_GENERIC_NETLINK_H */

-- 

[PATCH v2 2/3] netlink: allow removing multicast groups

[Johannes Berg]

Allow kicking listeners out of a multicast group when necessary
(for example if that group is going to be removed.)

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>

---
Changes: incorporate Patrick's comments, add kernel-doc.

 include/linux/netlink.h  |    1 
 net/netlink/af_netlink.c |   57 +++++++++++++++++++++++++++++++++++++----------
 2 files changed, 46 insertions(+), 12 deletions(-)

--- wireless-dev.orig/include/linux/netlink.h	2007-07-18 15:01:06.042900849 +0200
+++ wireless-dev/include/linux/netlink.h	2007-07-18 15:01:22.542900849 +0200
@@ -162,6 +162,7 @@ extern struct sock *netlink_kernel_creat
 					  struct mutex *cb_mutex,
 					  struct module *module);
 extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
+extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group);
 extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
 extern int netlink_has_listeners(struct sock *sk, unsigned int group);
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);
--- wireless-dev.orig/net/netlink/af_netlink.c	2007-07-18 15:01:10.482900849 +0200
+++ wireless-dev/net/netlink/af_netlink.c	2007-07-18 15:02:09.642900849 +0200
@@ -1027,6 +1027,23 @@ void netlink_set_err(struct sock *ssk, u
 	read_unlock(&nl_table_lock);
 }
 
+/* must be called with netlink table grabbed */
+static void netlink_update_socket_mc(struct netlink_sock *nlk,
+				     unsigned int group,
+				     int is_new)
+{
+	int old, new = !!is_new, subscriptions;
+
+	old = test_bit(group - 1, nlk->groups);
+	subscriptions = nlk->subscriptions - old + new;
+	if (new)
+		__set_bit(group - 1, nlk->groups);
+	else
+		__clear_bit(group - 1, nlk->groups);
+	netlink_update_subscriptions(&nlk->sk, subscriptions);
+	netlink_update_listeners(&nlk->sk);
+}
+
 static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			      char __user *optval, int optlen)
 {
@@ -1052,9 +1069,6 @@ static int netlink_setsockopt(struct soc
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		unsigned int subscriptions;
-		int old, new = optname == NETLINK_ADD_MEMBERSHIP ? 1 : 0;
-
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
@@ -1063,14 +1077,8 @@ static int netlink_setsockopt(struct soc
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		netlink_table_grab();
-		old = test_bit(val - 1, nlk->groups);
-		subscriptions = nlk->subscriptions - old + new;
-		if (new)
-			__set_bit(val - 1, nlk->groups);
-		else
-			__clear_bit(val - 1, nlk->groups);
-		netlink_update_subscriptions(sk, subscriptions);
-		netlink_update_listeners(sk);
+		netlink_update_socket_mc(nlk, val,
+					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
 		err = 0;
 		break;
@@ -1351,7 +1359,9 @@ out_sock_release:
  *
  * This changes the number of multicast groups that are available
  * on a certain netlink family. Note that it is not possible to
- * change the number of groups to below 32.
+ * change the number of groups to below 32. Also note that it does
+ * not implicitly call netlink_clear_multicast_users() when the
+ * number of groups is reduced.
  *
  * @sk: The kernel netlink socket, as returned by netlink_kernel_create().
  * @groups: The new number of groups.
@@ -1386,6 +1396,29 @@ int netlink_change_ngroups(struct sock *
 }
 EXPORT_SYMBOL(netlink_change_ngroups);
 
+/**
+ * netlink_clear_multicast_users - kick off multicast listeners
+ *
+ * This function removes all listeners from the given group.
+ * @ksk: The kernel netlink socket, as returned by
+ *	netlink_kernel_create().
+ * @group: The multicast group to clear.
+ */
+void netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
+{
+	struct sock *sk;
+	struct hlist_node *node;
+	struct netlink_table *tbl = &nl_table[ksk->sk_protocol];
+
+	netlink_table_grab();
+
+	sk_for_each_bound(sk, node, &tbl->mc_list)
+		netlink_update_socket_mc(nlk_sk(sk), group, 0);
+
+	netlink_table_ungrab();
+}
+EXPORT_SYMBOL(netlink_clear_multicast_users);
+
 void netlink_set_nonroot(int protocol, unsigned int flags)
 {
 	if ((unsigned int)protocol < MAX_LINKS)

Re: [PATCH v2 2/3] netlink: allow removing multicast groups

[David Miller]

Please don't resubmit sub-patches, I delete entire patch
series from my inbox when some of them need revisions.

Please resubmit the whole set once everything is worked
out.

Thanks.

[PATCH v2 1/3] netlink: allocate group bitmaps dynamically

[Johannes Berg]

Allow changing the number of groups for a netlink family
after it has been created, use RCU to protect the listeners
bitmap keeping netlink_has_listeners() lock-free.

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>

---
Changes: incorporate Patrick's comments, add kernel-doc

 include/linux/netlink.h  |    1 
 net/netlink/af_netlink.c |  106 ++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 83 insertions(+), 24 deletions(-)

--- wireless-dev.orig/net/netlink/af_netlink.c	2007-07-18 15:09:02.952900849 +0200
+++ wireless-dev/net/netlink/af_netlink.c	2007-07-18 16:33:33.691236687 +0200
@@ -62,6 +62,7 @@
 #include <net/netlink.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
+#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
 
 struct netlink_sock {
 	/* struct sock has to be the first member of netlink_sock */
@@ -314,10 +315,12 @@ netlink_update_listeners(struct sock *sk
 	unsigned long mask;
 	unsigned int i;
 
-	for (i = 0; i < NLGRPSZ(tbl->groups)/sizeof(unsigned long); i++) {
+	for (i = 0; i < NLGRPLONGS(tbl->groups); i++) {
 		mask = 0;
-		sk_for_each_bound(sk, node, &tbl->mc_list)
-			mask |= nlk_sk(sk)->groups[i];
+		sk_for_each_bound(sk, node, &tbl->mc_list) {
+			if (i < NLGRPLONGS(nlk_sk(sk)->ngroups))
+				mask |= nlk_sk(sk)->groups[i];
+		}
 		tbl->listeners[i] = mask;
 	}
 	/* this function is only called with the netlink table "grabbed", which
@@ -555,26 +558,37 @@ netlink_update_subscriptions(struct sock
 	nlk->subscriptions = subscriptions;
 }
 
-static int netlink_alloc_groups(struct sock *sk)
+static int netlink_realloc_groups(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	unsigned int groups;
+	unsigned long *new_groups;
 	int err = 0;
 
-	netlink_lock_table();
+	netlink_table_grab();
+
 	groups = nl_table[sk->sk_protocol].groups;
-	if (!nl_table[sk->sk_protocol].registered)
+	if (!nl_table[sk->sk_protocol].registered) {
 		err = -ENOENT;
-	netlink_unlock_table();
+		goto out_unlock;
+	}
 
-	if (err)
-		return err;
+	if (nlk->ngroups >= groups)
+		goto out_unlock;
 
-	nlk->groups = kzalloc(NLGRPSZ(groups), GFP_KERNEL);
-	if (nlk->groups == NULL)
-		return -ENOMEM;
+	new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC);
+	if (new_groups == NULL) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	memset((char*)new_groups + NLGRPSZ(nlk->ngroups), 0,
+	       NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups));
+
+	nlk->groups = new_groups;
 	nlk->ngroups = groups;
-	return 0;
+ out_unlock:
+	netlink_table_ungrab();
+	return err;
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
@@ -591,11 +605,9 @@ static int netlink_bind(struct socket *s
 	if (nladdr->nl_groups) {
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
-			if (err)
-				return err;
-		}
+		err = netlink_realloc_groups(sk);
+		if (err)
+			return err;
 	}
 
 	if (nlk->pid) {
@@ -839,10 +851,18 @@ retry:
 int netlink_has_listeners(struct sock *sk, unsigned int group)
 {
 	int res = 0;
+	unsigned long *listeners;
 
 	BUG_ON(!(nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET));
+
+	rcu_read_lock();
+	listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners);
+
 	if (group - 1 < nl_table[sk->sk_protocol].groups)
-		res = test_bit(group - 1, nl_table[sk->sk_protocol].listeners);
+		res = test_bit(group - 1, listeners);
+
+	rcu_read_unlock();
+
 	return res;
 }
 EXPORT_SYMBOL_GPL(netlink_has_listeners);
@@ -1037,11 +1057,9 @@ static int netlink_setsockopt(struct soc
 
 		if (!netlink_capable(sock, NL_NONROOT_RECV))
 			return -EPERM;
-		if (nlk->groups == NULL) {
-			err = netlink_alloc_groups(sk);
-			if (err)
-				return err;
-		}
+		err = netlink_realloc_groups(sk);
+		if (err)
+			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
 		netlink_table_grab();
@@ -1328,6 +1346,46 @@ out_sock_release:
 	return NULL;
 }
 
+/**
+ * netlink_change_ngroups - change number of multicast groups
+ *
+ * This changes the number of multicast groups that are available
+ * on a certain netlink family. Note that it is not possible to
+ * change the number of groups to below 32.
+ *
+ * @sk: The kernel netlink socket, as returned by netlink_kernel_create().
+ * @groups: The new number of groups.
+ */
+int netlink_change_ngroups(struct sock *sk, unsigned int groups)
+{
+	unsigned long *listeners, *old = NULL;
+	struct netlink_table *tbl = &nl_table[sk->sk_protocol];
+	int err = 0;
+
+	if (groups < 32)
+		groups = 32;
+
+	netlink_table_grab();
+	if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) {
+		listeners = kzalloc(NLGRPSZ(groups), GFP_ATOMIC);
+		if (!listeners) {
+			err = -ENOMEM;
+			goto out_ungrab;
+		}
+		old = tbl->listeners;
+		memcpy(listeners, old, NLGRPSZ(tbl->groups));
+		rcu_assign_pointer(tbl->listeners, listeners);
+	}
+	tbl->groups = groups;
+
+ out_ungrab:
+	netlink_table_ungrab();
+	synchronize_rcu();
+	kfree(old);
+	return err;
+}
+EXPORT_SYMBOL(netlink_change_ngroups);
+
 void netlink_set_nonroot(int protocol, unsigned int flags)
 {
 	if ((unsigned int)protocol < MAX_LINKS)
--- wireless-dev.orig/include/linux/netlink.h	2007-07-18 15:08:48.132900849 +0200
+++ wireless-dev/include/linux/netlink.h	2007-07-18 16:31:43.061236687 +0200
@@ -161,6 +161,7 @@ extern struct sock *netlink_kernel_creat
 					  void (*input)(struct sock *sk, int len),
 					  struct mutex *cb_mutex,
 					  struct module *module);
+extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
 extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
 extern int netlink_has_listeners(struct sock *sk, unsigned int group);
 extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);

Re: [PATCH v2 1/3] netlink: allocate group bitmaps dynamically

[Patrick McHardy]

Johannes Berg wrote:
> Allow changing the number of groups for a netlink family
> after it has been created, use RCU to protect the listeners
> bitmap keeping netlink_has_listeners() lock-free.
> 
> Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
> 
> ---
> Changes: incorporate Patrick's comments, add kernel-doc


All three patches look good to me.

Acked-by: Patrick McHardy <kaber@trash.net>

and for Jamal again ..

Acked-by: Jamal Hadi Salim <hadi@cyberus.ca>

Re: [PATCH v2 1/3] netlink: allocate group bitmaps dynamically

[David Miller]

From: Patrick McHardy <kaber@trash.net>
Date: Wed, 18 Jul 2007 18:30:04 +0200

> Johannes Berg wrote:
> > Allow changing the number of groups for a netlink family
> > after it has been created, use RCU to protect the listeners
> > bitmap keeping netlink_has_listeners() lock-free.
> > 
> > Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
> > 
> > ---
> > Changes: incorporate Patrick's comments, add kernel-doc
> 
> 
> All three patches look good to me.
> 
> Acked-by: Patrick McHardy <kaber@trash.net>
> 
> and for Jamal again ..
> 
> Acked-by: Jamal Hadi Salim <hadi@cyberus.ca>

Aha, Johannes did resubmit all 3 patches, they arrived out
of order here which confused me :-)

I'll apply these, thanks.

Re: [PATCH v2 1/3] netlink: allocate group bitmaps dynamically

[Johannes Berg]

[-- Attachment #1: Type: text/plain, Size: 532 bytes --]

On Wed, 2007-07-18 at 15:34 -0700, David Miller wrote:

> > All three patches look good to me.
> > 
> > Acked-by: Patrick McHardy <kaber@trash.net>
> > 
> > and for Jamal again ..
> > 
> > Acked-by: Jamal Hadi Salim <hadi@cyberus.ca>
> 
> Aha, Johannes did resubmit all 3 patches, they arrived out
> of order here which confused me :-)
> 
> I'll apply these, thanks.

Thanks. And sorry about the out-of-order, my mistake because I'd noticed
a small bug in one patch and didn't rewrite all three emails.

johannes

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 190 bytes --]

[PATCH v2 3/3] generic netlink: dynamic multicast groups

[Johannes Berg]

Introduce API to dynamically register and unregister multicast groups.

Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
Changes: update for slightly changed API from v2 of patch 1 and 2, add
kernel-doc, properly register the generic netlink group as well, fix bug
with that group (it isn't ID 1 but ID 0x10) 

 include/linux/genetlink.h |   13 ++
 include/net/genetlink.h   |   22 ++++
 net/netlink/genetlink.c   |  235 ++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 263 insertions(+), 7 deletions(-)

--- wireless-dev.orig/include/net/genetlink.h	2007-07-18 16:52:31.366081353 +0200
+++ wireless-dev/include/net/genetlink.h	2007-07-18 16:54:30.716081353 +0200
@@ -5,6 +5,22 @@
 #include <net/netlink.h>
 
 /**
+ * struct genl_multicast_group - generic netlink multicast group
+ * @name: name of the multicast group, names are per-family
+ * @id: multicast group ID, assigned by the core, to use with
+ *      genlmsg_multicast().
+ * @list: list entry for linking
+ * @family: pointer to family, need not be set before registering
+ */
+struct genl_multicast_group
+{
+	struct genl_family	*family;	/* private */
+	struct list_head	list;		/* private */
+	char			name[GENL_NAMSIZ];
+	u32			id;
+};
+
+/**
  * struct genl_family - generic netlink family
  * @id: protocol family idenfitier
  * @hdrsize: length of user specific header in bytes
@@ -14,6 +30,7 @@
  * @attrbuf: buffer to store parsed attributes
  * @ops_list: list of all assigned operations
  * @family_list: family list
+ * @mcast_groups: multicast groups list
  */
 struct genl_family
 {
@@ -25,6 +42,7 @@ struct genl_family
 	struct nlattr **	attrbuf;	/* private */
 	struct list_head	ops_list;	/* private */
 	struct list_head	family_list;	/* private */
+	struct list_head	mcast_groups;	/* private */
 };
 
 /**
@@ -73,6 +91,10 @@ extern int genl_register_family(struct g
 extern int genl_unregister_family(struct genl_family *family);
 extern int genl_register_ops(struct genl_family *, struct genl_ops *ops);
 extern int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
+extern int genl_register_mc_group(struct genl_family *family,
+				  struct genl_multicast_group *grp);
+extern void genl_unregister_mc_group(struct genl_family *family,
+				     struct genl_multicast_group *grp);
 
 extern struct sock *genl_sock;
 
--- wireless-dev.orig/net/netlink/genetlink.c	2007-07-18 16:52:31.456081353 +0200
+++ wireless-dev/net/netlink/genetlink.c	2007-07-18 17:04:45.706081353 +0200
@@ -3,6 +3,7 @@
  *
  * 		Authors:	Jamal Hadi Salim
  * 				Thomas Graf <tgraf@suug.ch>
+ *				Johannes Berg <johannes@sipsolutions.net>
  */
 
 #include <linux/module.h>
@@ -13,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/skbuff.h>
 #include <linux/mutex.h>
+#include <linux/bitmap.h>
 #include <net/sock.h>
 #include <net/genetlink.h>
 
@@ -42,6 +44,16 @@ static void genl_unlock(void)
 #define GENL_FAM_TAB_MASK	(GENL_FAM_TAB_SIZE - 1)
 
 static struct list_head family_ht[GENL_FAM_TAB_SIZE];
+/*
+ * Bitmap of multicast groups that are currently in use.
+ *
+ * To avoid an allocation at boot of just one unsigned long,
+ * declare it global instead.
+ * Bit 0 is marked as already used since group 0 is invalid.
+ */
+static unsigned long mc_group_start = 0x1;
+static unsigned long *mc_groups = &mc_group_start;
+static unsigned long mc_groups_longs = 1;
 
 static int genl_ctrl_event(int event, void *data);
 
@@ -116,6 +128,114 @@ static inline u16 genl_generate_id(void)
 	return id_gen_idx;
 }
 
+static struct genl_multicast_group notify_grp;
+
+/**
+ * genl_register_mc_group - register a multicast group
+ *
+ * Registers the specified multicast group and notifies userspace
+ * about the new group.
+ *
+ * Returns 0 on success or a negative error code.
+ *
+ * @family: The generic netlink family the group shall be registered for.
+ * @grp: The group to register, must have a name.
+ */
+int genl_register_mc_group(struct genl_family *family,
+			   struct genl_multicast_group *grp)
+{
+	int id;
+	unsigned long *new_groups;
+	int err;
+
+	BUG_ON(grp->name[0] == '\0');
+
+	genl_lock();
+
+	/* special-case our own group */
+	if (grp == &notify_grp)
+		id = GENL_ID_CTRL;
+	else
+		id = find_first_zero_bit(mc_groups,
+					 mc_groups_longs * BITS_PER_LONG);
+
+
+	if (id >= mc_groups_longs * BITS_PER_LONG) {
+		size_t nlen = (mc_groups_longs + 1) * sizeof(unsigned long);
+
+		if (mc_groups == &mc_group_start) {
+			new_groups = kzalloc(nlen, GFP_KERNEL);
+			if (!new_groups) {
+				err = -ENOMEM;
+				goto out;
+			}
+			mc_groups = new_groups;
+			*mc_groups = mc_group_start;
+		} else {
+			new_groups = krealloc(mc_groups, nlen, GFP_KERNEL);
+			if (!new_groups) {
+				err = -ENOMEM;
+				goto out;
+			}
+			mc_groups = new_groups;
+			mc_groups[mc_groups_longs] = 0;
+		}
+		mc_groups_longs++;
+	}
+
+	err = netlink_change_ngroups(genl_sock,
+				     sizeof(unsigned long) * NETLINK_GENERIC);
+	if (err)
+		goto out;
+
+	grp->id = id;
+	set_bit(id, mc_groups);
+	list_add_tail(&grp->list, &family->mcast_groups);
+	grp->family = family;
+
+	genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, grp);
+ out:
+	genl_unlock();
+	return 0;
+}
+EXPORT_SYMBOL(genl_register_mc_group);
+
+/**
+ * genl_unregister_mc_group - unregister a multicast group
+ *
+ * Unregisters the specified multicast group and notifies userspace
+ * about it. All current listeners on the group are removed.
+ *
+ * Note: It is not necessary to unregister all multicast groups before
+ *       unregistering the family, unregistering the family will cause
+ *       all assigned multicast groups to be unregistered automatically.
+ *
+ * @family: Generic netlink family the group belongs to.
+ * @grp: The group to unregister, must have been registered successfully
+ *	 previously.
+ */
+void genl_unregister_mc_group(struct genl_family *family,
+			      struct genl_multicast_group *grp)
+{
+	BUG_ON(grp->family != family);
+	genl_lock();
+	netlink_clear_multicast_users(genl_sock, grp->id);
+	clear_bit(grp->id, mc_groups);
+	list_del(&grp->list);
+	genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, grp);
+	grp->id = 0;
+	grp->family = NULL;
+	genl_unlock();
+}
+
+static void genl_unregister_mc_groups(struct genl_family *family)
+{
+	struct genl_multicast_group *grp, *tmp;
+
+	list_for_each_entry_safe(grp, tmp, &family->mcast_groups, list)
+		genl_unregister_mc_group(family, grp);
+}
+
 /**
  * genl_register_ops - register generic netlink operations
  * @family: generic netlink family
@@ -216,6 +336,7 @@ int genl_register_family(struct genl_fam
 		goto errout;
 
 	INIT_LIST_HEAD(&family->ops_list);
+	INIT_LIST_HEAD(&family->mcast_groups);
 
 	genl_lock();
 
@@ -275,6 +396,8 @@ int genl_unregister_family(struct genl_f
 {
 	struct genl_family *rc;
 
+	genl_unregister_mc_groups(family);
+
 	genl_lock();
 
 	list_for_each_entry(rc, genl_family_chain(family->id), family_list) {
@@ -410,6 +533,67 @@ static int ctrl_fill_info(struct genl_fa
 		nla_nest_end(skb, nla_ops);
 	}
 
+	if (!list_empty(&family->mcast_groups)) {
+		struct genl_multicast_group *grp;
+		struct nlattr *nla_grps;
+		int idx = 1;
+
+		nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+		if (nla_grps == NULL)
+			goto nla_put_failure;
+
+		list_for_each_entry(grp, &family->mcast_groups, list) {
+			struct nlattr *nest;
+
+			nest = nla_nest_start(skb, idx++);
+			if (nest == NULL)
+				goto nla_put_failure;
+
+			NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id);
+			NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME,
+				       grp->name);
+
+			nla_nest_end(skb, nest);
+		}
+		nla_nest_end(skb, nla_grps);
+	}
+
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	return genlmsg_cancel(skb, hdr);
+}
+
+static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid,
+				u32 seq, u32 flags, struct sk_buff *skb,
+				u8 cmd)
+{
+	void *hdr;
+	struct nlattr *nla_grps;
+	struct nlattr *nest;
+
+	hdr = genlmsg_put(skb, pid, seq, &genl_ctrl, flags, cmd);
+	if (hdr == NULL)
+		return -1;
+
+	NLA_PUT_STRING(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name);
+	NLA_PUT_U16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id);
+
+	nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+	if (nla_grps == NULL)
+		goto nla_put_failure;
+
+	nest = nla_nest_start(skb, 1);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	NLA_PUT_U32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id);
+	NLA_PUT_STRING(skb, CTRL_ATTR_MCAST_GRP_NAME,
+		       grp->name);
+
+	nla_nest_end(skb, nest);
+	nla_nest_end(skb, nla_grps);
+
 	return genlmsg_end(skb, hdr);
 
 nla_put_failure:
@@ -453,8 +637,8 @@ errout:
 	return skb->len;
 }
 
-static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid,
-				      int seq, u8 cmd)
+static struct sk_buff *ctrl_build_family_msg(struct genl_family *family,
+					     u32 pid, int seq, u8 cmd)
 {
 	struct sk_buff *skb;
 	int err;
@@ -472,6 +656,25 @@ static struct sk_buff *ctrl_build_msg(st
 	return skb;
 }
 
+static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
+					    u32 pid, int seq, u8 cmd)
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb == NULL)
+		return ERR_PTR(-ENOBUFS);
+
+	err = ctrl_fill_mcgrp_info(grp, pid, seq, 0, skb, cmd);
+	if (err < 0) {
+		nlmsg_free(skb);
+		return ERR_PTR(err);
+	}
+
+	return skb;
+}
+
 static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = {
 	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
 	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
@@ -501,8 +704,8 @@ static int ctrl_getfamily(struct sk_buff
 		goto errout;
 	}
 
-	msg = ctrl_build_msg(res, info->snd_pid, info->snd_seq,
-			     CTRL_CMD_NEWFAMILY);
+	msg = ctrl_build_family_msg(res, info->snd_pid, info->snd_seq,
+				    CTRL_CMD_NEWFAMILY);
 	if (IS_ERR(msg)) {
 		err = PTR_ERR(msg);
 		goto errout;
@@ -523,7 +726,15 @@ static int genl_ctrl_event(int event, vo
 	switch (event) {
 	case CTRL_CMD_NEWFAMILY:
 	case CTRL_CMD_DELFAMILY:
-		msg = ctrl_build_msg(data, 0, 0, event);
+		msg = ctrl_build_family_msg(data, 0, 0, event);
+		if (IS_ERR(msg))
+			return PTR_ERR(msg);
+
+		genlmsg_multicast(msg, 0, GENL_ID_CTRL, GFP_KERNEL);
+		break;
+	case CTRL_CMD_NEWMCAST_GRP:
+	case CTRL_CMD_DELMCAST_GRP:
+		msg = ctrl_build_mcgrp_msg(data, 0, 0, event);
 		if (IS_ERR(msg))
 			return PTR_ERR(msg);
 
@@ -541,6 +752,10 @@ static struct genl_ops genl_ctrl_ops = {
 	.policy		= ctrl_policy,
 };
 
+static struct genl_multicast_group notify_grp = {
+	.name		= "notify",
+};
+
 static int __init genl_init(void)
 {
 	int i, err;
@@ -557,11 +772,17 @@ static int __init genl_init(void)
 		goto errout_register;
 
 	netlink_set_nonroot(NETLINK_GENERIC, NL_NONROOT_RECV);
-	genl_sock = netlink_kernel_create(NETLINK_GENERIC, GENL_MAX_ID,
-					  genl_rcv, NULL, THIS_MODULE);
+
+	/* we'll bump the group number right afterwards */
+	genl_sock = netlink_kernel_create(NETLINK_GENERIC, 0, genl_rcv,
+					  NULL, THIS_MODULE);
 	if (genl_sock == NULL)
 		panic("GENL: Cannot initialize generic netlink\n");
 
+	err = genl_register_mc_group(&genl_ctrl, &notify_grp);
+	if (err < 0)
+		goto errout_register;
+
 	return 0;
 
 errout_register:
--- wireless-dev.orig/include/linux/genetlink.h	2007-07-18 16:52:31.416081353 +0200
+++ wireless-dev/include/linux/genetlink.h	2007-07-18 16:54:30.716081353 +0200
@@ -39,6 +39,9 @@ enum {
 	CTRL_CMD_NEWOPS,
 	CTRL_CMD_DELOPS,
 	CTRL_CMD_GETOPS,
+	CTRL_CMD_NEWMCAST_GRP,
+	CTRL_CMD_DELMCAST_GRP,
+	CTRL_CMD_GETMCAST_GRP, /* unused */
 	__CTRL_CMD_MAX,
 };
 
@@ -52,6 +55,7 @@ enum {
 	CTRL_ATTR_HDRSIZE,
 	CTRL_ATTR_MAXATTR,
 	CTRL_ATTR_OPS,
+	CTRL_ATTR_MCAST_GROUPS,
 	__CTRL_ATTR_MAX,
 };
 
@@ -66,4 +70,13 @@ enum {
 
 #define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1)
 
+enum {
+	CTRL_ATTR_MCAST_GRP_UNSPEC,
+	CTRL_ATTR_MCAST_GRP_NAME,
+	CTRL_ATTR_MCAST_GRP_ID,
+	__CTRL_ATTR_MCAST_GRP_MAX,
+};
+
+#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
+
 #endif	/* __LINUX_GENERIC_NETLINK_H */

Re: [patch 0/3] dynamic generic netlink multicast

[Johannes Berg]

[-- Attachment #1: Type: text/plain, Size: 270 bytes --]

Oh, this patchset triggers a current bug in slub, see:

http://article.gmane.org/gmane.linux.kernel/556887

I forgot mentioning that yesterday, I hope it's not causing any trouble.
Also, I had expected it to be fixed soonish, but can't see that it is.

johannes

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 190 bytes --]