[PATCH net-next RFC] netlink: Add compare function for netlink_table
by Gao feng
As we know, netlink sockets are private resource of
net namespace, they can communicate with each other
only when they in the same net namespace. this works
well until we try to add namespace support for other
subsystems which use netlink.
Don't like ipv4 and route table.., it is not suited to
make these subsytems belong to net namespace, Such as
audit and crypto subsystems,they are more suitable to
user namespace.
So we must have the ability to make the netlink sockets
in same user namespace can communicate with each other.
This patch adds a new function pointer "compare" for
netlink_table, we can decide if the netlink sockets can
communicate with each other through this netlink_table
self-defined compare function.
The behavior isn't changed if we don't provide the compare
function for netlink_table.
Signed-off-by: Gao feng <gaofeng(a)cn.fujitsu.com>
---
Actually I already send a patchset to add namespace support
for audit subsystem [1]. this patch is a part of the patchset.
I think it's better to send this patch out separately, since
some people may have comments on this one. I need to know what's
the idea of network guy.
[1] http://lwn.net/Articles/549546/
include/linux/netlink.h | 1 +
net/netlink/af_netlink.c | 33 +++++++++++++++++++++++++--------
net/netlink/af_netlink.h | 1 +
3 files changed, 27 insertions(+), 8 deletions(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 6358da5..f78b430 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -46,6 +46,7 @@ struct netlink_kernel_cfg {
void (*input)(struct sk_buff *skb);
struct mutex *cb_mutex;
void (*bind)(int group);
+ bool (*compare)(struct net *net, struct sock *sk);
};
extern struct sock *__netlink_kernel_create(struct net *net, int unit,
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 12ac6b4..e399877 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -854,16 +854,23 @@ netlink_unlock_table(void)
wake_up(&nl_table_wait);
}
+static bool netlink_compare(struct net *net, struct sock *sk)
+{
+ return net_eq(sock_net(sk), net);
+}
+
static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid)
{
- struct nl_portid_hash *hash = &nl_table[protocol].hash;
+ struct netlink_table *table = &nl_table[protocol];
+ struct nl_portid_hash *hash = &table->hash;
struct hlist_head *head;
struct sock *sk;
read_lock(&nl_table_lock);
head = nl_portid_hashfn(hash, portid);
sk_for_each(sk, head) {
- if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->portid == portid)) {
+ if (table->compare(net, sk) &&
+ (nlk_sk(sk)->portid == portid)) {
sock_hold(sk);
goto found;
}
@@ -976,7 +983,8 @@ netlink_update_listeners(struct sock *sk)
static int netlink_insert(struct sock *sk, struct net *net, u32 portid)
{
- struct nl_portid_hash *hash = &nl_table[sk->sk_protocol].hash;
+ struct netlink_table *table = &nl_table[sk->sk_protocol];
+ struct nl_portid_hash *hash = &table->hash;
struct hlist_head *head;
int err = -EADDRINUSE;
struct sock *osk;
@@ -986,7 +994,8 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 portid)
head = nl_portid_hashfn(hash, portid);
len = 0;
sk_for_each(osk, head) {
- if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->portid == portid))
+ if (table->compare(net, osk) &&
+ (nlk_sk(osk)->portid == portid))
break;
len++;
}
@@ -1161,6 +1170,7 @@ static int netlink_release(struct socket *sock)
kfree_rcu(old, rcu);
nl_table[sk->sk_protocol].module = NULL;
nl_table[sk->sk_protocol].bind = NULL;
+ nl_table[sk->sk_protocol].compare = NULL;
nl_table[sk->sk_protocol].flags = 0;
nl_table[sk->sk_protocol].registered = 0;
}
@@ -1183,7 +1193,8 @@ static int netlink_autobind(struct socket *sock)
{
struct sock *sk = sock->sk;
struct net *net = sock_net(sk);
- struct nl_portid_hash *hash = &nl_table[sk->sk_protocol].hash;
+ struct netlink_table *table = &nl_table[sk->sk_protocol];
+ struct nl_portid_hash *hash = &table->hash;
struct hlist_head *head;
struct sock *osk;
s32 portid = task_tgid_vnr(current);
@@ -1195,7 +1206,7 @@ retry:
netlink_table_grab();
head = nl_portid_hashfn(hash, portid);
sk_for_each(osk, head) {
- if (!net_eq(sock_net(osk), net))
+ if (!table->compare(net, osk))
continue;
if (nlk_sk(osk)->portid == portid) {
/* Bind collision, search negative portid values. */
@@ -2282,9 +2293,12 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module,
rcu_assign_pointer(nl_table[unit].listeners, listeners);
nl_table[unit].cb_mutex = cb_mutex;
nl_table[unit].module = module;
+ nl_table[unit].compare = netlink_compare;
if (cfg) {
nl_table[unit].bind = cfg->bind;
nl_table[unit].flags = cfg->flags;
+ if (cfg->compare)
+ nl_table[unit].compare = cfg->compare;
}
nl_table[unit].registered = 1;
} else {
@@ -2707,6 +2721,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *s;
struct nl_seq_iter *iter;
+ struct net *net;
int i, j;
++*pos;
@@ -2714,11 +2729,12 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
if (v == SEQ_START_TOKEN)
return netlink_seq_socket_idx(seq, 0);
+ net = seq_file_net(seq);
iter = seq->private;
s = v;
do {
s = sk_next(s);
- } while (s && sock_net(s) != seq_file_net(seq));
+ } while (s && !nl_table[s->sk_protocol].compare(net, s));
if (s)
return s;
@@ -2730,7 +2746,8 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
for (; j <= hash->mask; j++) {
s = sk_head(&hash->table[j]);
- while (s && sock_net(s) != seq_file_net(seq))
+
+ while (s && !nl_table[s->sk_protocol].compare(net, s))
s = sk_next(s);
if (s) {
iter->link = i;
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index ed85222..eaa88d1 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -73,6 +73,7 @@ struct netlink_table {
struct mutex *cb_mutex;
struct module *module;
void (*bind)(int group);
+ bool (*compare)(struct net *net, struct sock *sock);
int registered;
};
--
1.8.1.4
11 years, 4 months
lists
by Oleg Popenko
lists
________________________________
This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you are not the intended recipient, please note that any review, dissemination, disclosure, alteration, printing, circulation, retention or transmission of this e-mail and/or any file or attachment transmitted with it, is prohibited and may be unlawful. If you have received this e-mail or any file or attachment transmitted with it in error please notify postmaster(a)openet.com. Although Openet has taken reasonable precautions to ensure no viruses are present in this email, we cannot accept responsibility for any loss or damage arising from the use of this email or attachments.
11 years, 5 months
[PATCH 02/47] Audit: remove duplicate comments
by Gao feng
Remove it.
Signed-off-by: Gao feng <gaofeng(a)cn.fujitsu.com>
---
kernel/audit.c | 7 -------
1 file changed, 7 deletions(-)
diff --git a/kernel/audit.c b/kernel/audit.c
index 3a5d3f5..5653dae 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1067,13 +1067,6 @@ static void wait_for_auditd(unsigned long sleep_time)
remove_wait_queue(&audit_backlog_wait, &wait);
}
-/* Obtain an audit buffer. This routine does locking to obtain the
- * audit buffer, but then no locking is required for calls to
- * audit_log_*format. If the tsk is a task that is currently in a
- * syscall, then the syscall is marked as auditable and an audit record
- * will be written at syscall exit. If there is no associated task, tsk
- * should be NULL. */
-
/**
* audit_log_start - obtain an audit buffer
* @ctx: audit_context (may be NULL)
--
1.8.1.4
11 years, 5 months
[PATCH 01/47] Audit: change type of audit_ever_enabled to bool
by Gao feng
It's better to define audit_ever_enabled as bool.
Signed-off-by: Gao feng <gaofeng(a)cn.fujitsu.com>
---
kernel/audit.c | 2 +-
kernel/audit.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/audit.c b/kernel/audit.c
index 21c7fa6..3a5d3f5 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -78,7 +78,7 @@ static int audit_initialized;
#define AUDIT_ON 1
#define AUDIT_LOCKED 2
int audit_enabled;
-int audit_ever_enabled;
+bool audit_ever_enabled;
EXPORT_SYMBOL_GPL(audit_enabled);
diff --git a/kernel/audit.h b/kernel/audit.h
index 1c95131..2258827 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -205,7 +205,7 @@ struct audit_context {
#endif
};
-extern int audit_ever_enabled;
+extern bool audit_ever_enabled;
extern void audit_copy_inode(struct audit_names *name,
const struct dentry *dentry,
--
1.8.1.4
11 years, 5 months