aboutsummaryrefslogtreecommitdiff
path: root/net/netlink
diff options
context:
space:
mode:
Diffstat (limited to 'net/netlink')
-rw-r--r--net/netlink/af_netlink.c491
-rw-r--r--net/netlink/af_netlink.h10
-rw-r--r--net/netlink/genetlink.c609
3 files changed, 694 insertions, 416 deletions
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 275d901d7e4..e6fac7e3db5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -57,6 +57,7 @@
#include <linux/audit.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
+#include <linux/if_arp.h>
#include <asm/cacheflush.h>
#include <net/net_namespace.h>
@@ -101,6 +102,9 @@ static atomic_t nl_table_users = ATOMIC_INIT(0);
static ATOMIC_NOTIFIER_HEAD(netlink_chain);
+static DEFINE_SPINLOCK(netlink_tap_lock);
+static struct list_head netlink_tap_all __read_mostly;
+
static inline u32 netlink_group_mask(u32 group)
{
return group ? 1 << (group - 1) : 0;
@@ -111,6 +115,138 @@ static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u
return &hash->table[jhash_1word(portid, hash->rnd) & hash->mask];
}
+int netlink_add_tap(struct netlink_tap *nt)
+{
+ if (unlikely(nt->dev->type != ARPHRD_NETLINK))
+ return -EINVAL;
+
+ spin_lock(&netlink_tap_lock);
+ list_add_rcu(&nt->list, &netlink_tap_all);
+ spin_unlock(&netlink_tap_lock);
+
+ if (nt->module)
+ __module_get(nt->module);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netlink_add_tap);
+
+static int __netlink_remove_tap(struct netlink_tap *nt)
+{
+ bool found = false;
+ struct netlink_tap *tmp;
+
+ spin_lock(&netlink_tap_lock);
+
+ list_for_each_entry(tmp, &netlink_tap_all, list) {
+ if (nt == tmp) {
+ list_del_rcu(&nt->list);
+ found = true;
+ goto out;
+ }
+ }
+
+ pr_warn("__netlink_remove_tap: %p not found\n", nt);
+out:
+ spin_unlock(&netlink_tap_lock);
+
+ if (found && nt->module)
+ module_put(nt->module);
+
+ return found ? 0 : -ENODEV;
+}
+
+int netlink_remove_tap(struct netlink_tap *nt)
+{
+ int ret;
+
+ ret = __netlink_remove_tap(nt);
+ synchronize_net();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(netlink_remove_tap);
+
+static bool netlink_filter_tap(const struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ bool pass = false;
+
+ /* We take the more conservative approach and
+ * whitelist socket protocols that may pass.
+ */
+ switch (sk->sk_protocol) {
+ case NETLINK_ROUTE:
+ case NETLINK_USERSOCK:
+ case NETLINK_SOCK_DIAG:
+ case NETLINK_NFLOG:
+ case NETLINK_XFRM:
+ case NETLINK_FIB_LOOKUP:
+ case NETLINK_NETFILTER:
+ case NETLINK_GENERIC:
+ pass = true;
+ break;
+ }
+
+ return pass;
+}
+
+static int __netlink_deliver_tap_skb(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct sk_buff *nskb;
+ struct sock *sk = skb->sk;
+ int ret = -ENOMEM;
+
+ dev_hold(dev);
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (nskb) {
+ nskb->dev = dev;
+ nskb->protocol = htons((u16) sk->sk_protocol);
+ nskb->pkt_type = netlink_is_kernel(sk) ?
+ PACKET_KERNEL : PACKET_USER;
+
+ ret = dev_queue_xmit(nskb);
+ if (unlikely(ret > 0))
+ ret = net_xmit_errno(ret);
+ }
+
+ dev_put(dev);
+ return ret;
+}
+
+static void __netlink_deliver_tap(struct sk_buff *skb)
+{
+ int ret;
+ struct netlink_tap *tmp;
+
+ if (!netlink_filter_tap(skb))
+ return;
+
+ list_for_each_entry_rcu(tmp, &netlink_tap_all, list) {
+ ret = __netlink_deliver_tap_skb(skb, tmp->dev);
+ if (unlikely(ret))
+ break;
+ }
+}
+
+static void netlink_deliver_tap(struct sk_buff *skb)
+{
+ rcu_read_lock();
+
+ if (unlikely(!list_empty(&netlink_tap_all)))
+ __netlink_deliver_tap(skb);
+
+ rcu_read_unlock();
+}
+
+static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
+ struct sk_buff *skb)
+{
+ if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
+ netlink_deliver_tap(skb);
+}
+
static void netlink_overrun(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -196,14 +332,14 @@ static void **alloc_pg_vec(struct netlink_sock *nlk,
{
unsigned int block_nr = req->nm_block_nr;
unsigned int i;
- void **pg_vec, *ptr;
+ void **pg_vec;
pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL);
if (pg_vec == NULL)
return NULL;
for (i = 0; i < block_nr; i++) {
- pg_vec[i] = ptr = alloc_one_pg_vec_page(order);
+ pg_vec[i] = alloc_one_pg_vec_page(order);
if (pg_vec[i] == NULL)
goto err1;
}
@@ -497,10 +633,10 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
* for dumps is performed here. A dump is allowed to continue
* if at least half the ring is unused.
*/
- while (nlk->cb != NULL && netlink_dump_space(nlk)) {
+ while (nlk->cb_running && netlink_dump_space(nlk)) {
err = netlink_dump(sk);
if (err < 0) {
- sk->sk_err = err;
+ sk->sk_err = -err;
sk->sk_error_report(sk);
break;
}
@@ -704,18 +840,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb) 0
#endif /* CONFIG_NETLINK_MMAP */
-static void netlink_destroy_callback(struct netlink_callback *cb)
-{
- kfree_skb(cb->skb);
- kfree(cb);
-}
-
-static void netlink_consume_callback(struct netlink_callback *cb)
-{
- consume_skb(cb->skb);
- kfree(cb);
-}
-
static void netlink_skb_destructor(struct sk_buff *skb)
{
#ifdef CONFIG_NETLINK_MMAP
@@ -751,7 +875,10 @@ static void netlink_skb_destructor(struct sk_buff *skb)
}
#endif
if (is_vmalloc_addr(skb->head)) {
- vfree(skb->head);
+ if (!skb->cloned ||
+ !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
+ vfree(skb->head);
+
skb->head = NULL;
}
if (skb->sk != NULL)
@@ -771,12 +898,12 @@ static void netlink_sock_destruct(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
- if (nlk->cb) {
- if (nlk->cb->done)
- nlk->cb->done(nlk->cb);
+ if (nlk->cb_running) {
+ if (nlk->cb.done)
+ nlk->cb.done(&nlk->cb);
- module_put(nlk->cb->module);
- netlink_destroy_callback(nlk->cb);
+ module_put(nlk->cb.module);
+ kfree_skb(nlk->cb.skb);
}
skb_queue_purge(&sk->sk_receive_queue);
@@ -1079,7 +1206,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
struct module *module = NULL;
struct mutex *cb_mutex;
struct netlink_sock *nlk;
- void (*bind)(int group);
+ int (*bind)(int group);
+ void (*unbind)(int group);
int err = 0;
sock->state = SS_UNCONNECTED;
@@ -1105,6 +1233,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
err = -EPROTONOSUPPORT;
cb_mutex = nl_table[protocol].cb_mutex;
bind = nl_table[protocol].bind;
+ unbind = nl_table[protocol].unbind;
netlink_unlock_table();
if (err < 0)
@@ -1121,6 +1250,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
nlk = nlk_sk(sock->sk);
nlk->module = module;
nlk->netlink_bind = bind;
+ nlk->netlink_unbind = unbind;
out:
return err;
@@ -1174,6 +1304,7 @@ 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].unbind = NULL;
nl_table[sk->sk_protocol].flags = 0;
nl_table[sk->sk_protocol].registered = 0;
}
@@ -1233,7 +1364,74 @@ retry:
return err;
}
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+ struct user_namespace *user_ns, int cap)
+{
+ return ((nsp->flags & NETLINK_SKB_DST) ||
+ file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+ ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+ struct user_namespace *user_ns, int cap)
+{
+ return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+ return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+ return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].flags & flag) ||
ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1284,6 +1482,19 @@ static int netlink_realloc_groups(struct sock *sk)
return err;
}
+static void netlink_unbind(int group, long unsigned int groups,
+ struct netlink_sock *nlk)
+{
+ int undo;
+
+ if (!nlk->netlink_unbind)
+ return;
+
+ for (undo = 0; undo < group; undo++)
+ if (test_bit(group, &groups))
+ nlk->netlink_unbind(undo);
+}
+
static int netlink_bind(struct socket *sock, struct sockaddr *addr,
int addr_len)
{
@@ -1292,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
struct netlink_sock *nlk = nlk_sk(sk);
struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
int err;
+ long unsigned int groups = nladdr->nl_groups;
if (addr_len < sizeof(struct sockaddr_nl))
return -EINVAL;
@@ -1300,45 +1512,53 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
return -EINVAL;
/* Only superuser is allowed to listen multicasts */
- if (nladdr->nl_groups) {
- if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+ if (groups) {
+ if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
return err;
}
- if (nlk->portid) {
+ if (nlk->portid)
if (nladdr->nl_pid != nlk->portid)
return -EINVAL;
- } else {
+
+ if (nlk->netlink_bind && groups) {
+ int group;
+
+ for (group = 0; group < nlk->ngroups; group++) {
+ if (!test_bit(group, &groups))
+ continue;
+ err = nlk->netlink_bind(group);
+ if (!err)
+ continue;
+ netlink_unbind(group, groups, nlk);
+ return err;
+ }
+ }
+
+ if (!nlk->portid) {
err = nladdr->nl_pid ?
netlink_insert(sk, net, nladdr->nl_pid) :
netlink_autobind(sock);
- if (err)
+ if (err) {
+ netlink_unbind(nlk->ngroups - 1, groups, nlk);
return err;
+ }
}
- if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
+ if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
return 0;
netlink_table_grab();
netlink_update_subscriptions(sk, nlk->subscriptions +
- hweight32(nladdr->nl_groups) -
+ hweight32(groups) -
hweight32(nlk->groups[0]));
- nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
+ nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups;
netlink_update_listeners(sk);
netlink_table_ungrab();
- if (nlk->netlink_bind && nlk->groups[0]) {
- int i;
-
- for (i=0; i<nlk->ngroups; i++) {
- if (test_bit(i, nlk->groups))
- nlk->netlink_bind(i);
- }
- }
-
return 0;
}
@@ -1362,8 +1582,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
if (addr->sa_family != AF_NETLINK)
return -EINVAL;
- /* Only superuser is allowed to send multicasts */
- if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ if ((nladdr->nl_groups || nladdr->nl_pid) &&
+ !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
if (!nlk->portid)
@@ -1434,33 +1654,31 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
return sock;
}
-static struct sk_buff *netlink_alloc_large_skb(unsigned int size)
+static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
+ int broadcast)
{
struct sk_buff *skb;
void *data;
- if (size <= NLMSG_GOODSIZE)
+ if (size <= NLMSG_GOODSIZE || broadcast)
return alloc_skb(size, GFP_KERNEL);
- skb = alloc_skb_head(GFP_KERNEL);
- if (skb == NULL)
- return NULL;
+ size = SKB_DATA_ALIGN(size) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
data = vmalloc(size);
if (data == NULL)
- goto err;
+ return NULL;
- skb->head = data;
- skb->data = data;
- skb_reset_tail_pointer(skb);
- skb->end = skb->tail + size;
- skb->len = 0;
- skb->destructor = netlink_skb_destructor;
+ skb = build_skb(data, size);
+ if (skb == NULL)
+ vfree(data);
+ else {
+ skb->head_frag = 0;
+ skb->destructor = netlink_skb_destructor;
+ }
return skb;
-err:
- kfree_skb(skb);
- return NULL;
}
/*
@@ -1518,6 +1736,8 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = skb->len;
+ netlink_deliver_tap(skb);
+
#ifdef CONFIG_NETLINK_MMAP
if (netlink_skb_is_mmaped(skb))
netlink_queue_mmaped_skb(sk, skb);
@@ -1526,7 +1746,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
else
#endif /* CONFIG_NETLINK_MMAP */
skb_queue_tail(&sk->sk_receive_queue, skb);
- sk->sk_data_ready(sk, len);
+ sk->sk_data_ready(sk);
return len;
}
@@ -1581,6 +1801,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
ret = skb->len;
netlink_skb_set_owner_r(skb, sk);
NETLINK_CB(skb).sk = ssk;
+ netlink_deliver_tap_kernel(sk, ssk, skb);
nlk->netlink_rcv(skb);
consume_skb(skb);
} else {
@@ -1645,6 +1866,9 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
if (ring->pg_vec == NULL)
goto out_put;
+ if (ring->frame_size - NL_MMAP_HDRLEN < size)
+ goto out_put;
+
skb = alloc_skb_head(gfp_mask);
if (skb == NULL)
goto err1;
@@ -1654,6 +1878,7 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
if (ring->pg_vec == NULL)
goto out_free;
+ /* check again under lock */
maxlen = ring->frame_size - NL_MMAP_HDRLEN;
if (maxlen < size)
goto out_free;
@@ -1893,7 +2118,7 @@ out:
* netlink_set_err - report error to broadcast listeners
* @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
* @portid: the PORTID of a process that we want to skip (if any)
- * @groups: the broadcast group that will notice the error
+ * @group: the broadcast group that will notice the error
* @code: error code, must be negative (as usual in kernelspace)
*
* This function returns the number of broadcast listeners that have set the
@@ -1964,20 +2189,24 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
break;
case NETLINK_ADD_MEMBERSHIP:
case NETLINK_DROP_MEMBERSHIP: {
- if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+ if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
return err;
if (!val || val - 1 >= nlk->ngroups)
return -EINVAL;
+ if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
+ err = nlk->netlink_bind(val);
+ if (err)
+ return err;
+ }
netlink_table_grab();
netlink_update_socket_mc(nlk, val,
optname == NETLINK_ADD_MEMBERSHIP);
netlink_table_ungrab();
-
- if (nlk->netlink_bind)
- nlk->netlink_bind(val);
+ if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
+ nlk->netlink_unbind(val);
err = 0;
break;
@@ -2090,12 +2319,13 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
struct sock *sk = sock->sk;
struct netlink_sock *nlk = nlk_sk(sk);
- struct sockaddr_nl *addr = msg->msg_name;
+ DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
u32 dst_portid;
u32 dst_group;
struct sk_buff *skb;
int err;
struct scm_cookie scm;
+ u32 netlink_skb_flags = 0;
if (msg->msg_flags&MSG_OOB)
return -EOPNOTSUPP;
@@ -2115,8 +2345,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
dst_group = ffs(addr->nl_groups);
err = -EPERM;
if ((dst_group || dst_portid) &&
- !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
goto out;
+ netlink_skb_flags |= NETLINK_SKB_DST;
} else {
dst_portid = nlk->dst_portid;
dst_group = nlk->dst_group;
@@ -2139,13 +2370,14 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
if (len > sk->sk_sndbuf - 32)
goto out;
err = -ENOBUFS;
- skb = netlink_alloc_large_skb(len);
+ skb = netlink_alloc_large_skb(len, dst_group);
if (skb == NULL)
goto out;
NETLINK_CB(skb).portid = nlk->portid;
NETLINK_CB(skb).dst_group = dst_group;
NETLINK_CB(skb).creds = siocb->scm->creds;
+ NETLINK_CB(skb).flags = netlink_skb_flags;
err = -EFAULT;
if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2211,7 +2443,10 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
}
#endif
- msg->msg_namelen = 0;
+ /* Record the max length of recvmsg() calls for future allocations */
+ nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
+ nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
+ 16384);
copied = data_skb->len;
if (len < copied) {
@@ -2223,7 +2458,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
if (msg->msg_name) {
- struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
+ DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
addr->nl_family = AF_NETLINK;
addr->nl_pad = 0;
addr->nl_pid = NETLINK_CB(skb).portid;
@@ -2244,10 +2479,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
skb_free_datagram(sk, skb);
- if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
+ if (nlk->cb_running &&
+ atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
ret = netlink_dump(sk);
if (ret) {
- sk->sk_err = ret;
+ sk->sk_err = -ret;
sk->sk_error_report(sk);
}
}
@@ -2258,7 +2494,7 @@ out:
return err ? : copied;
}
-static void netlink_data_ready(struct sock *sk, int len)
+static void netlink_data_ready(struct sock *sk)
{
BUG();
}
@@ -2412,28 +2648,13 @@ void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
netlink_update_socket_mc(nlk_sk(sk), group, 0);
}
-/**
- * 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)
-{
- netlink_table_grab();
- __netlink_clear_multicast_users(ksk, group);
- netlink_table_ungrab();
-}
-
struct nlmsghdr *
__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags)
{
struct nlmsghdr *nlh;
int size = nlmsg_msg_size(len);
- nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
+ nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size));
nlh->nlmsg_type = type;
nlh->nlmsg_len = size;
nlh->nlmsg_flags = flags;
@@ -2460,19 +2681,38 @@ static int netlink_dump(struct sock *sk)
int alloc_size;
mutex_lock(nlk->cb_mutex);
-
- cb = nlk->cb;
- if (cb == NULL) {
+ if (!nlk->cb_running) {
err = -EINVAL;
goto errout_skb;
}
+ cb = &nlk->cb;
alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
if (!netlink_rx_is_mmaped(sk) &&
atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
goto errout_skb;
- skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
+
+ /* NLMSG_GOODSIZE is small to avoid high order allocations being
+ * required, but it makes sense to _attempt_ a 16K bytes allocation
+ * to reduce number of system calls on dump operations, if user
+ * ever provided a big enough buffer.
+ */
+ if (alloc_size < nlk->max_recvmsg_len) {
+ skb = netlink_alloc_skb(sk,
+ nlk->max_recvmsg_len,
+ nlk->portid,
+ GFP_KERNEL |
+ __GFP_NOWARN |
+ __GFP_NORETRY);
+ /* available room should be exact amount to avoid MSG_TRUNC */
+ if (skb)
+ skb_reserve(skb, skb_tailroom(skb) -
+ nlk->max_recvmsg_len);
+ }
+ if (!skb)
+ skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
+ GFP_KERNEL);
if (!skb)
goto errout_skb;
netlink_skb_set_owner_r(skb, sk);
@@ -2504,11 +2744,11 @@ static int netlink_dump(struct sock *sk)
if (cb->done)
cb->done(cb);
- nlk->cb = NULL;
- mutex_unlock(nlk->cb_mutex);
+ nlk->cb_running = false;
+ mutex_unlock(nlk->cb_mutex);
module_put(cb->module);
- netlink_consume_callback(cb);
+ consume_skb(cb->skb);
return 0;
errout_skb:
@@ -2526,59 +2766,51 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
struct netlink_sock *nlk;
int ret;
- cb = kzalloc(sizeof(*cb), GFP_KERNEL);
- if (cb == NULL)
- return -ENOBUFS;
-
/* Memory mapped dump requests need to be copied to avoid looping
* on the pending state in netlink_mmap_sendmsg() while the CB hold
* a reference to the skb.
*/
if (netlink_skb_is_mmaped(skb)) {
skb = skb_copy(skb, GFP_KERNEL);
- if (skb == NULL) {
- kfree(cb);
+ if (skb == NULL)
return -ENOBUFS;
- }
} else
atomic_inc(&skb->users);
- cb->dump = control->dump;
- cb->done = control->done;
- cb->nlh = nlh;
- cb->data = control->data;
- cb->module = control->module;
- cb->min_dump_alloc = control->min_dump_alloc;
- cb->skb = skb;
-
sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid);
if (sk == NULL) {
- netlink_destroy_callback(cb);
- return -ECONNREFUSED;
+ ret = -ECONNREFUSED;
+ goto error_free;
}
- nlk = nlk_sk(sk);
+ nlk = nlk_sk(sk);
mutex_lock(nlk->cb_mutex);
/* A dump is in progress... */
- if (nlk->cb) {
- mutex_unlock(nlk->cb_mutex);
- netlink_destroy_callback(cb);
+ if (nlk->cb_running) {
ret = -EBUSY;
- goto out;
+ goto error_unlock;
}
/* add reference of module which cb->dump belongs to */
- if (!try_module_get(cb->module)) {
- mutex_unlock(nlk->cb_mutex);
- netlink_destroy_callback(cb);
+ if (!try_module_get(control->module)) {
ret = -EPROTONOSUPPORT;
- goto out;
+ goto error_unlock;
}
- nlk->cb = cb;
+ cb = &nlk->cb;
+ memset(cb, 0, sizeof(*cb));
+ cb->dump = control->dump;
+ cb->done = control->done;
+ cb->nlh = nlh;
+ cb->data = control->data;
+ cb->module = control->module;
+ cb->min_dump_alloc = control->min_dump_alloc;
+ cb->skb = skb;
+
+ nlk->cb_running = true;
+
mutex_unlock(nlk->cb_mutex);
ret = netlink_dump(sk);
-out:
sock_put(sk);
if (ret)
@@ -2588,6 +2820,13 @@ out:
* signal not to send ACK even if it was requested.
*/
return -EINTR;
+
+error_unlock:
+ sock_put(sk);
+ mutex_unlock(nlk->cb_mutex);
+error_free:
+ kfree_skb(skb);
+ return ret;
}
EXPORT_SYMBOL(__netlink_dump_start);
@@ -2810,14 +3049,14 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
struct sock *s = v;
struct netlink_sock *nlk = nlk_sk(s);
- seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %pK %-8d %-8d %-8lu\n",
+ seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n",
s,
s->sk_protocol,
nlk->portid,
nlk->groups ? (u32)nlk->groups[0] : 0,
sk_rmem_alloc_get(s),
sk_wmem_alloc_get(s),
- nlk->cb,
+ nlk->cb_running,
atomic_read(&s->sk_refcnt),
atomic_read(&s->sk_drops),
sock_i_ino(s)
@@ -2975,6 +3214,8 @@ static int __init netlink_proto_init(void)
nl_table[i].compare = netlink_compare;
}
+ INIT_LIST_HEAD(&netlink_tap_all);
+
netlink_add_usersock_entry();
sock_register(&netlink_family_ops);
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index eaa88d187cd..0b59d441f5b 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -31,12 +31,15 @@ struct netlink_sock {
u32 ngroups;
unsigned long *groups;
unsigned long state;
+ size_t max_recvmsg_len;
wait_queue_head_t wait;
- struct netlink_callback *cb;
+ bool cb_running;
+ struct netlink_callback cb;
struct mutex *cb_mutex;
struct mutex cb_def_mutex;
void (*netlink_rcv)(struct sk_buff *skb);
- void (*netlink_bind)(int group);
+ int (*netlink_bind)(int group);
+ void (*netlink_unbind)(int group);
struct module *module;
#ifdef CONFIG_NETLINK_MMAP
struct mutex pg_vec_lock;
@@ -72,7 +75,8 @@ struct netlink_table {
unsigned int groups;
struct mutex *cb_mutex;
struct module *module;
- void (*bind)(int group);
+ int (*bind)(int group);
+ void (*unbind)(int group);
bool (*compare)(struct net *net, struct sock *sock);
int registered;
};
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 2fd6dbea327..76393f2f4b2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -65,12 +65,27 @@ static struct list_head family_ht[GENL_FAM_TAB_SIZE];
* 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 the drop-monitor code
+ * abuses the API and thinks it can statically use group 1.
+ * That group will typically conflict with other groups that
+ * any proper users use.
+ * Bit 16 is marked as used since it's used for generic netlink
+ * and the code no longer marks pre-reserved IDs as used.
+ * Bit 17 is marked as already used since the VFS quota code
+ * also abused this API and relied on family == group ID, we
+ * cater to that by giving it a static family and group ID.
+ * Bit 18 is marked as already used since the PMCRAID driver
+ * did the same thing as the VFS quota code (maybe copied?)
*/
-static unsigned long mc_group_start = 0x1;
+static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) |
+ BIT(GENL_ID_VFS_DQUOT) |
+ BIT(GENL_ID_PMCRAID);
static unsigned long *mc_groups = &mc_group_start;
static unsigned long mc_groups_longs = 1;
-static int genl_ctrl_event(int event, void *data);
+static int genl_ctrl_event(int event, struct genl_family *family,
+ const struct genl_multicast_group *grp,
+ int grp_id);
static inline unsigned int genl_family_hash(unsigned int id)
{
@@ -106,13 +121,13 @@ static struct genl_family *genl_family_find_byname(char *name)
return NULL;
}
-static struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family)
+static const struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family)
{
- struct genl_ops *ops;
+ int i;
- list_for_each_entry(ops, &family->ops_list, ops_list)
- if (ops->cmd == cmd)
- return ops;
+ for (i = 0; i < family->n_ops; i++)
+ if (family->ops[i].cmd == cmd)
+ return &family->ops[i];
return NULL;
}
@@ -126,7 +141,9 @@ static u16 genl_generate_id(void)
int i;
for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) {
- if (!genl_family_find_byid(id_gen_idx))
+ if (id_gen_idx != GENL_ID_VFS_DQUOT &&
+ id_gen_idx != GENL_ID_PMCRAID &&
+ !genl_family_find_byid(id_gen_idx))
return id_gen_idx;
if (++id_gen_idx > GENL_MAX_ID)
id_gen_idx = GENL_MIN_ID;
@@ -135,62 +152,113 @@ static u16 genl_generate_id(void)
return 0;
}
-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)
+static int genl_allocate_reserve_groups(int n_groups, int *first_id)
{
- int id;
unsigned long *new_groups;
- int err = 0;
+ int start = 0;
+ int i;
+ int id;
+ bool fits;
+
+ do {
+ if (start == 0)
+ id = find_first_zero_bit(mc_groups,
+ mc_groups_longs *
+ BITS_PER_LONG);
+ else
+ id = find_next_zero_bit(mc_groups,
+ mc_groups_longs * BITS_PER_LONG,
+ start);
+
+ fits = true;
+ for (i = id;
+ i < min_t(int, id + n_groups,
+ mc_groups_longs * BITS_PER_LONG);
+ i++) {
+ if (test_bit(i, mc_groups)) {
+ start = i;
+ fits = false;
+ break;
+ }
+ }
+
+ if (id >= mc_groups_longs * BITS_PER_LONG) {
+ unsigned long new_longs = mc_groups_longs +
+ BITS_TO_LONGS(n_groups);
+ size_t nlen = new_longs * sizeof(unsigned long);
+
+ if (mc_groups == &mc_group_start) {
+ new_groups = kzalloc(nlen, GFP_KERNEL);
+ if (!new_groups)
+ return -ENOMEM;
+ mc_groups = new_groups;
+ *mc_groups = mc_group_start;
+ } else {
+ new_groups = krealloc(mc_groups, nlen,
+ GFP_KERNEL);
+ if (!new_groups)
+ return -ENOMEM;
+ mc_groups = new_groups;
+ for (i = 0; i < BITS_TO_LONGS(n_groups); i++)
+ mc_groups[mc_groups_longs + i] = 0;
+ }
+ mc_groups_longs = new_longs;
+ }
+ } while (!fits);
- BUG_ON(grp->name[0] == '\0');
- BUG_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL);
+ for (i = id; i < id + n_groups; i++)
+ set_bit(i, mc_groups);
+ *first_id = id;
+ return 0;
+}
- genl_lock_all();
+static struct genl_family genl_ctrl;
+
+static int genl_validate_assign_mc_groups(struct genl_family *family)
+{
+ int first_id;
+ int n_groups = family->n_mcgrps;
+ int err = 0, i;
+ bool groups_allocated = false;
- /* 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 (!n_groups)
+ return 0;
+ for (i = 0; i < n_groups; i++) {
+ const struct genl_multicast_group *grp = &family->mcgrps[i];
- if (id >= mc_groups_longs * BITS_PER_LONG) {
- size_t nlen = (mc_groups_longs + 1) * sizeof(unsigned long);
+ if (WARN_ON(grp->name[0] == '\0'))
+ return -EINVAL;
+ if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL))
+ return -EINVAL;
+ }
- 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++;
+ /* special-case our own group and hacks */
+ if (family == &genl_ctrl) {
+ first_id = GENL_ID_CTRL;
+ BUG_ON(n_groups != 1);
+ } else if (strcmp(family->name, "NET_DM") == 0) {
+ first_id = 1;
+ BUG_ON(n_groups != 1);
+ } else if (family->id == GENL_ID_VFS_DQUOT) {
+ first_id = GENL_ID_VFS_DQUOT;
+ BUG_ON(n_groups != 1);
+ } else if (family->id == GENL_ID_PMCRAID) {
+ first_id = GENL_ID_PMCRAID;
+ BUG_ON(n_groups != 1);
+ } else {
+ groups_allocated = true;
+ err = genl_allocate_reserve_groups(n_groups, &first_id);
+ if (err)
+ return err;
}
+ family->mcgrp_offset = first_id;
+
+ /* if still initializing, can't and don't need to to realloc bitmaps */
+ if (!init_net.genl_sock)
+ return 0;
+
if (family->netnsok) {
struct net *net;
@@ -206,9 +274,7 @@ int genl_register_mc_group(struct genl_family *family,
* number of _possible_ groups has been
* increased on some sockets which is ok.
*/
- rcu_read_unlock();
- netlink_table_ungrab();
- goto out;
+ break;
}
}
rcu_read_unlock();
@@ -216,155 +282,66 @@ int genl_register_mc_group(struct genl_family *family,
} else {
err = netlink_change_ngroups(init_net.genl_sock,
mc_groups_longs * BITS_PER_LONG);
- if (err)
- goto out;
}
- grp->id = id;
- set_bit(id, mc_groups);
- list_add_tail(&grp->list, &family->mcast_groups);
- grp->family = family;
+ if (groups_allocated && err) {
+ for (i = 0; i < family->n_mcgrps; i++)
+ clear_bit(family->mcgrp_offset + i, mc_groups);
+ }
- genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, grp);
- out:
- genl_unlock_all();
return err;
}
-EXPORT_SYMBOL(genl_register_mc_group);
-static void __genl_unregister_mc_group(struct genl_family *family,
- struct genl_multicast_group *grp)
+static void genl_unregister_mc_groups(struct genl_family *family)
{
struct net *net;
- BUG_ON(grp->family != family);
+ int i;
netlink_table_grab();
rcu_read_lock();
- for_each_net_rcu(net)
- __netlink_clear_multicast_users(net->genl_sock, grp->id);
+ for_each_net_rcu(net) {
+ for (i = 0; i < family->n_mcgrps; i++)
+ __netlink_clear_multicast_users(
+ net->genl_sock, family->mcgrp_offset + i);
+ }
rcu_read_unlock();
netlink_table_ungrab();
- 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_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)
-{
- genl_lock_all();
- __genl_unregister_mc_group(family, grp);
- genl_unlock_all();
-}
-EXPORT_SYMBOL(genl_unregister_mc_group);
-
-static void genl_unregister_mc_groups(struct genl_family *family)
-{
- struct genl_multicast_group *grp, *tmp;
+ for (i = 0; i < family->n_mcgrps; i++) {
+ int grp_id = family->mcgrp_offset + i;
- list_for_each_entry_safe(grp, tmp, &family->mcast_groups, list)
- __genl_unregister_mc_group(family, grp);
+ if (grp_id != 1)
+ clear_bit(grp_id, mc_groups);
+ genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family,
+ &family->mcgrps[i], grp_id);
+ }
}
-/**
- * genl_register_ops - register generic netlink operations
- * @family: generic netlink family
- * @ops: operations to be registered
- *
- * Registers the specified operations and assigns them to the specified
- * family. Either a doit or dumpit callback must be specified or the
- * operation will fail. Only one operation structure per command
- * identifier may be registered.
- *
- * See include/net/genetlink.h for more documenation on the operations
- * structure.
- *
- * Returns 0 on success or a negative error code.
- */
-int genl_register_ops(struct genl_family *family, struct genl_ops *ops)
+static int genl_validate_ops(const struct genl_family *family)
{
- int err = -EINVAL;
-
- if (ops->dumpit == NULL && ops->doit == NULL)
- goto errout;
-
- if (genl_get_cmd(ops->cmd, family)) {
- err = -EEXIST;
- goto errout;
- }
-
- if (ops->dumpit)
- ops->flags |= GENL_CMD_CAP_DUMP;
- if (ops->doit)
- ops->flags |= GENL_CMD_CAP_DO;
- if (ops->policy)
- ops->flags |= GENL_CMD_CAP_HASPOL;
-
- genl_lock_all();
- list_add_tail(&ops->ops_list, &family->ops_list);
- genl_unlock_all();
+ const struct genl_ops *ops = family->ops;
+ unsigned int n_ops = family->n_ops;
+ int i, j;
- genl_ctrl_event(CTRL_CMD_NEWOPS, ops);
- err = 0;
-errout:
- return err;
-}
-EXPORT_SYMBOL(genl_register_ops);
+ if (WARN_ON(n_ops && !ops))
+ return -EINVAL;
-/**
- * genl_unregister_ops - unregister generic netlink operations
- * @family: generic netlink family
- * @ops: operations to be unregistered
- *
- * Unregisters the specified operations and unassigns them from the
- * specified family. The operation blocks until the current message
- * processing has finished and doesn't start again until the
- * unregister process has finished.
- *
- * Note: It is not necessary to unregister all operations before
- * unregistering the family, unregistering the family will cause
- * all assigned operations to be unregistered automatically.
- *
- * Returns 0 on success or a negative error code.
- */
-int genl_unregister_ops(struct genl_family *family, struct genl_ops *ops)
-{
- struct genl_ops *rc;
+ if (!n_ops)
+ return 0;
- genl_lock_all();
- list_for_each_entry(rc, &family->ops_list, ops_list) {
- if (rc == ops) {
- list_del(&ops->ops_list);
- genl_unlock_all();
- genl_ctrl_event(CTRL_CMD_DELOPS, ops);
- return 0;
- }
+ for (i = 0; i < n_ops; i++) {
+ if (ops[i].dumpit == NULL && ops[i].doit == NULL)
+ return -EINVAL;
+ for (j = i + 1; j < n_ops; j++)
+ if (ops[i].cmd == ops[j].cmd)
+ return -EINVAL;
}
- genl_unlock_all();
- return -ENOENT;
+ return 0;
}
-EXPORT_SYMBOL(genl_unregister_ops);
/**
- * genl_register_family - register a generic netlink family
+ * __genl_register_family - register a generic netlink family
* @family: generic netlink family
*
* Registers the specified family after validating it first. Only one
@@ -372,11 +349,14 @@ EXPORT_SYMBOL(genl_unregister_ops);
* The family id may equal GENL_ID_GENERATE causing an unique id to
* be automatically generated and assigned.
*
+ * The family's ops array must already be assigned, you can use the
+ * genl_register_family_with_ops() helper function.
+ *
* Return 0 on success or a negative error code.
*/
-int genl_register_family(struct genl_family *family)
+int __genl_register_family(struct genl_family *family)
{
- int err = -EINVAL;
+ int err = -EINVAL, i;
if (family->id && family->id < GENL_MIN_ID)
goto errout;
@@ -384,8 +364,9 @@ int genl_register_family(struct genl_family *family)
if (family->id > GENL_MAX_ID)
goto errout;
- INIT_LIST_HEAD(&family->ops_list);
- INIT_LIST_HEAD(&family->mcast_groups);
+ err = genl_validate_ops(family);
+ if (err)
+ return err;
genl_lock_all();
@@ -418,10 +399,18 @@ int genl_register_family(struct genl_family *family)
} else
family->attrbuf = NULL;
+ err = genl_validate_assign_mc_groups(family);
+ if (err)
+ goto errout_locked;
+
list_add_tail(&family->family_list, genl_family_chain(family->id));
genl_unlock_all();
- genl_ctrl_event(CTRL_CMD_NEWFAMILY, family);
+ /* send all events */
+ genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL, 0);
+ for (i = 0; i < family->n_mcgrps; i++)
+ genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family,
+ &family->mcgrps[i], family->mcgrp_offset + i);
return 0;
@@ -430,53 +419,7 @@ errout_locked:
errout:
return err;
}
-EXPORT_SYMBOL(genl_register_family);
-
-/**
- * genl_register_family_with_ops - register a generic netlink family
- * @family: generic netlink family
- * @ops: operations to be registered
- * @n_ops: number of elements to register
- *
- * Registers the specified family and operations from the specified table.
- * Only one family may be registered with the same family name or identifier.
- *
- * The family id may equal GENL_ID_GENERATE causing an unique id to
- * be automatically generated and assigned.
- *
- * Either a doit or dumpit callback must be specified for every registered
- * operation or the function will fail. Only one operation structure per
- * command identifier may be registered.
- *
- * See include/net/genetlink.h for more documenation on the operations
- * structure.
- *
- * This is equivalent to calling genl_register_family() followed by
- * genl_register_ops() for every operation entry in the table taking
- * care to unregister the family on error path.
- *
- * Return 0 on success or a negative error code.
- */
-int genl_register_family_with_ops(struct genl_family *family,
- struct genl_ops *ops, size_t n_ops)
-{
- int err, i;
-
- err = genl_register_family(family);
- if (err)
- return err;
-
- for (i = 0; i < n_ops; ++i, ++ops) {
- err = genl_register_ops(family, ops);
- if (err)
- goto err_out;
- }
- return 0;
-err_out:
- genl_unregister_family(family);
- return err;
-}
-EXPORT_SYMBOL(genl_register_family_with_ops);
+EXPORT_SYMBOL(__genl_register_family);
/**
* genl_unregister_family - unregister generic netlink family
@@ -499,11 +442,11 @@ int genl_unregister_family(struct genl_family *family)
continue;
list_del(&rc->family_list);
- INIT_LIST_HEAD(&family->ops_list);
+ family->n_ops = 0;
genl_unlock_all();
kfree(family->attrbuf);
- genl_ctrl_event(CTRL_CMD_DELFAMILY, family);
+ genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
return 0;
}
@@ -514,6 +457,26 @@ int genl_unregister_family(struct genl_family *family)
EXPORT_SYMBOL(genl_unregister_family);
/**
+ * genlmsg_new_unicast - Allocate generic netlink message for unicast
+ * @payload: size of the message payload
+ * @info: information on destination
+ * @flags: the type of memory to allocate
+ *
+ * Allocates a new sk_buff large enough to cover the specified payload
+ * plus required Netlink headers. Will check receiving socket for
+ * memory mapped i/o capability and use it if enabled. Will fall back
+ * to non-mapped skb if message size exceeds the frame size of the ring.
+ */
+struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info,
+ gfp_t flags)
+{
+ size_t len = nlmsg_total_size(genlmsg_total_size(payload));
+
+ return netlink_alloc_skb(info->dst_sk, len, info->snd_portid, flags);
+}
+EXPORT_SYMBOL_GPL(genlmsg_new_unicast);
+
+/**
* genlmsg_put - Add generic netlink header to netlink message
* @skb: socket buffer holding the message
* @portid: netlink portid the message is addressed to
@@ -544,11 +507,37 @@ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq,
}
EXPORT_SYMBOL(genlmsg_put);
+static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ /* our ops are always const - netlink API doesn't propagate that */
+ const struct genl_ops *ops = cb->data;
+ int rc;
+
+ genl_lock();
+ rc = ops->dumpit(skb, cb);
+ genl_unlock();
+ return rc;
+}
+
+static int genl_lock_done(struct netlink_callback *cb)
+{
+ /* our ops are always const - netlink API doesn't propagate that */
+ const struct genl_ops *ops = cb->data;
+ int rc = 0;
+
+ if (ops->done) {
+ genl_lock();
+ rc = ops->done(cb);
+ genl_unlock();
+ }
+ return rc;
+}
+
static int genl_family_rcv_msg(struct genl_family *family,
struct sk_buff *skb,
struct nlmsghdr *nlh)
{
- struct genl_ops *ops;
+ const struct genl_ops *ops;
struct net *net = sock_net(skb->sk);
struct genl_info info;
struct genlmsghdr *hdr = nlmsg_data(nlh);
@@ -568,19 +557,39 @@ static int genl_family_rcv_msg(struct genl_family *family,
return -EOPNOTSUPP;
if ((ops->flags & GENL_ADMIN_PERM) &&
- !capable(CAP_NET_ADMIN))
+ !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
- if (nlh->nlmsg_flags & NLM_F_DUMP) {
- struct netlink_dump_control c = {
- .dump = ops->dumpit,
- .done = ops->done,
- };
+ if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) {
+ int rc;
if (ops->dumpit == NULL)
return -EOPNOTSUPP;
- return netlink_dump_start(net->genl_sock, skb, nlh, &c);
+ if (!family->parallel_ops) {
+ struct netlink_dump_control c = {
+ .module = family->module,
+ /* we have const, but the netlink API doesn't */
+ .data = (void *)ops,
+ .dump = genl_lock_dumpit,
+ .done = genl_lock_done,
+ };
+
+ genl_unlock();
+ rc = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
+ genl_lock();
+
+ } else {
+ struct netlink_dump_control c = {
+ .module = family->module,
+ .dump = ops->dumpit,
+ .done = ops->done,
+ };
+
+ rc = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
+ }
+
+ return rc;
}
if (ops->doit == NULL)
@@ -607,6 +616,7 @@ static int genl_family_rcv_msg(struct genl_family *family,
info.genlhdr = nlmsg_data(nlh);
info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN;
info.attrs = attrbuf;
+ info.dst_sk = skb->sk;
genl_info_net_set(&info, net);
memset(&info.user_ptr, 0, sizeof(info.user_ptr));
@@ -683,24 +693,32 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr))
goto nla_put_failure;
- if (!list_empty(&family->ops_list)) {
+ if (family->n_ops) {
struct nlattr *nla_ops;
- struct genl_ops *ops;
- int idx = 1;
+ int i;
nla_ops = nla_nest_start(skb, CTRL_ATTR_OPS);
if (nla_ops == NULL)
goto nla_put_failure;
- list_for_each_entry(ops, &family->ops_list, ops_list) {
+ for (i = 0; i < family->n_ops; i++) {
struct nlattr *nest;
+ const struct genl_ops *ops = &family->ops[i];
+ u32 op_flags = ops->flags;
+
+ if (ops->dumpit)
+ op_flags |= GENL_CMD_CAP_DUMP;
+ if (ops->doit)
+ op_flags |= GENL_CMD_CAP_DO;
+ if (ops->policy)
+ op_flags |= GENL_CMD_CAP_HASPOL;
- nest = nla_nest_start(skb, idx++);
+ nest = nla_nest_start(skb, i + 1);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) ||
- nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, ops->flags))
+ nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags))
goto nla_put_failure;
nla_nest_end(skb, nest);
@@ -709,23 +727,26 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
nla_nest_end(skb, nla_ops);
}
- if (!list_empty(&family->mcast_groups)) {
- struct genl_multicast_group *grp;
+ if (family->n_mcgrps) {
struct nlattr *nla_grps;
- int idx = 1;
+ int i;
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) {
+ for (i = 0; i < family->n_mcgrps; i++) {
struct nlattr *nest;
+ const struct genl_multicast_group *grp;
- nest = nla_nest_start(skb, idx++);
+ grp = &family->mcgrps[i];
+
+ nest = nla_nest_start(skb, i + 1);
if (nest == NULL)
goto nla_put_failure;
- if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id) ||
+ if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID,
+ family->mcgrp_offset + i) ||
nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME,
grp->name))
goto nla_put_failure;
@@ -742,9 +763,10 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 portid,
- u32 seq, u32 flags, struct sk_buff *skb,
- u8 cmd)
+static int ctrl_fill_mcgrp_info(struct genl_family *family,
+ const struct genl_multicast_group *grp,
+ int grp_id, u32 portid, u32 seq, u32 flags,
+ struct sk_buff *skb, u8 cmd)
{
void *hdr;
struct nlattr *nla_grps;
@@ -754,8 +776,8 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 portid,
if (hdr == NULL)
return -1;
- if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, grp->family->name) ||
- nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, grp->family->id))
+ if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) ||
+ nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id))
goto nla_put_failure;
nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
@@ -766,7 +788,7 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 portid,
if (nest == NULL)
goto nla_put_failure;
- if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp->id) ||
+ if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp_id) ||
nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME,
grp->name))
goto nla_put_failure;
@@ -832,8 +854,10 @@ static struct sk_buff *ctrl_build_family_msg(struct genl_family *family,
return skb;
}
-static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
- u32 portid, int seq, u8 cmd)
+static struct sk_buff *
+ctrl_build_mcgrp_msg(struct genl_family *family,
+ const struct genl_multicast_group *grp,
+ int grp_id, u32 portid, int seq, u8 cmd)
{
struct sk_buff *skb;
int err;
@@ -842,7 +866,8 @@ static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp,
if (skb == NULL)
return ERR_PTR(-ENOBUFS);
- err = ctrl_fill_mcgrp_info(grp, portid, seq, 0, skb, cmd);
+ err = ctrl_fill_mcgrp_info(family, grp, grp_id, portid,
+ seq, 0, skb, cmd);
if (err < 0) {
nlmsg_free(skb);
return ERR_PTR(err);
@@ -877,8 +902,10 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info)
#ifdef CONFIG_MODULES
if (res == NULL) {
genl_unlock();
+ up_read(&cb_lock);
request_module("net-pf-%d-proto-%d-family-%s",
PF_NETLINK, NETLINK_GENERIC, name);
+ down_read(&cb_lock);
genl_lock();
res = genl_family_find_byname(name);
}
@@ -902,11 +929,11 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info)
return genlmsg_reply(msg, info);
}
-static int genl_ctrl_event(int event, void *data)
+static int genl_ctrl_event(int event, struct genl_family *family,
+ const struct genl_multicast_group *grp,
+ int grp_id)
{
struct sk_buff *msg;
- struct genl_family *family;
- struct genl_multicast_group *grp;
/* genl is still initialising */
if (!init_net.genl_sock)
@@ -915,14 +942,13 @@ static int genl_ctrl_event(int event, void *data)
switch (event) {
case CTRL_CMD_NEWFAMILY:
case CTRL_CMD_DELFAMILY:
- family = data;
+ WARN_ON(grp);
msg = ctrl_build_family_msg(family, 0, 0, event);
break;
case CTRL_CMD_NEWMCAST_GRP:
case CTRL_CMD_DELMCAST_GRP:
- grp = data;
- family = grp->family;
- msg = ctrl_build_mcgrp_msg(data, 0, 0, event);
+ BUG_ON(!grp);
+ msg = ctrl_build_mcgrp_msg(family, grp, grp_id, 0, 0, event);
break;
default:
return -EINVAL;
@@ -932,26 +958,29 @@ static int genl_ctrl_event(int event, void *data)
return PTR_ERR(msg);
if (!family->netnsok) {
- genlmsg_multicast_netns(&init_net, msg, 0,
- GENL_ID_CTRL, GFP_KERNEL);
+ genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0,
+ 0, GFP_KERNEL);
} else {
rcu_read_lock();
- genlmsg_multicast_allns(msg, 0, GENL_ID_CTRL, GFP_ATOMIC);
+ genlmsg_multicast_allns(&genl_ctrl, msg, 0,
+ 0, GFP_ATOMIC);
rcu_read_unlock();
}
return 0;
}
-static struct genl_ops genl_ctrl_ops = {
- .cmd = CTRL_CMD_GETFAMILY,
- .doit = ctrl_getfamily,
- .dumpit = ctrl_dumpfamily,
- .policy = ctrl_policy,
+static struct genl_ops genl_ctrl_ops[] = {
+ {
+ .cmd = CTRL_CMD_GETFAMILY,
+ .doit = ctrl_getfamily,
+ .dumpit = ctrl_dumpfamily,
+ .policy = ctrl_policy,
+ },
};
-static struct genl_multicast_group notify_grp = {
- .name = "notify",
+static struct genl_multicast_group genl_ctrl_groups[] = {
+ { .name = "notify", },
};
static int __net_init genl_pernet_init(struct net *net)
@@ -991,7 +1020,8 @@ static int __init genl_init(void)
for (i = 0; i < GENL_FAM_TAB_SIZE; i++)
INIT_LIST_HEAD(&family_ht[i]);
- err = genl_register_family_with_ops(&genl_ctrl, &genl_ctrl_ops, 1);
+ err = genl_register_family_with_ops_groups(&genl_ctrl, genl_ctrl_ops,
+ genl_ctrl_groups);
if (err < 0)
goto problem;
@@ -999,10 +1029,6 @@ static int __init genl_init(void)
if (err)
goto problem;
- err = genl_register_mc_group(&genl_ctrl, &notify_grp);
- if (err < 0)
- goto problem;
-
return 0;
problem:
@@ -1040,14 +1066,18 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group,
return err;
}
-int genlmsg_multicast_allns(struct sk_buff *skb, u32 portid, unsigned int group,
- gfp_t flags)
+int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb,
+ u32 portid, unsigned int group, gfp_t flags)
{
+ if (WARN_ON_ONCE(group >= family->n_mcgrps))
+ return -EINVAL;
+ group = family->mcgrp_offset + group;
return genlmsg_mcast(skb, portid, group, flags);
}
EXPORT_SYMBOL(genlmsg_multicast_allns);
-void genl_notify(struct sk_buff *skb, struct net *net, u32 portid, u32 group,
+void genl_notify(struct genl_family *family,
+ struct sk_buff *skb, struct net *net, u32 portid, u32 group,
struct nlmsghdr *nlh, gfp_t flags)
{
struct sock *sk = net->genl_sock;
@@ -1056,6 +1086,9 @@ void genl_notify(struct sk_buff *skb, struct net *net, u32 portid, u32 group,
if (nlh)
report = nlmsg_report(nlh);
+ if (WARN_ON_ONCE(group >= family->n_mcgrps))
+ return;
+ group = family->mcgrp_offset + group;
nlmsg_notify(sk, skb, portid, group, report, flags);
}
EXPORT_SYMBOL(genl_notify);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 04:30:09 +0000