diff options
author | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-04-16 15:20:36 -0700 |
commit | 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 (patch) | |
tree | 0bba044c4ce775e45a88a51686b5d9f90697ea9d /net/netlink |
Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Diffstat (limited to 'net/netlink')
-rw-r--r-- | net/netlink/Makefile | 5 | ||||
-rw-r--r-- | net/netlink/af_netlink.c | 1454 |
2 files changed, 1459 insertions, 0 deletions
diff --git a/net/netlink/Makefile b/net/netlink/Makefile new file mode 100644 index 000000000000..39d9c2dcd03c --- /dev/null +++ b/net/netlink/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the netlink driver. +# + +obj-y := af_netlink.o diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c new file mode 100644 index 000000000000..1d5905c90cd4 --- /dev/null +++ b/net/netlink/af_netlink.c @@ -0,0 +1,1454 @@ +/* + * NETLINK Kernel-user communication protocol. + * + * Authors: Alan Cox <alan@redhat.com> + * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith + * added netlink_proto_exit + * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> + * use nlk_sk, as sk->protinfo is on a diet 8) + * + */ + +#include <linux/config.h> +#include <linux/module.h> + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/major.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/socket.h> +#include <linux/un.h> +#include <linux/fcntl.h> +#include <linux/termios.h> +#include <linux/sockios.h> +#include <linux/net.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include <asm/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/smp_lock.h> +#include <linux/notifier.h> +#include <linux/security.h> +#include <linux/jhash.h> +#include <linux/jiffies.h> +#include <linux/random.h> +#include <linux/bitops.h> +#include <linux/mm.h> +#include <linux/types.h> +#include <net/sock.h> +#include <net/scm.h> + +#define Nprintk(a...) + +struct netlink_sock { + /* struct sock has to be the first member of netlink_sock */ + struct sock sk; + u32 pid; + unsigned int groups; + u32 dst_pid; + unsigned int dst_groups; + unsigned long state; + wait_queue_head_t wait; + struct netlink_callback *cb; + spinlock_t cb_lock; + void (*data_ready)(struct sock *sk, int bytes); +}; + +static inline struct netlink_sock *nlk_sk(struct sock *sk) +{ + return (struct netlink_sock *)sk; +} + +struct nl_pid_hash { + struct hlist_head *table; + unsigned long rehash_time; + + unsigned int mask; + unsigned int shift; + + unsigned int entries; + unsigned int max_shift; + + u32 rnd; +}; + +struct netlink_table { + struct nl_pid_hash hash; + struct hlist_head mc_list; + unsigned int nl_nonroot; +}; + +static struct netlink_table *nl_table; + +static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); + +static int netlink_dump(struct sock *sk); +static void netlink_destroy_callback(struct netlink_callback *cb); + +static DEFINE_RWLOCK(nl_table_lock); +static atomic_t nl_table_users = ATOMIC_INIT(0); + +static struct notifier_block *netlink_chain; + +static struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid) +{ + return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask]; +} + +static void netlink_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); + + if (!sock_flag(sk, SOCK_DEAD)) { + printk("Freeing alive netlink socket %p\n", sk); + return; + } + BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc)); + BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc)); + BUG_TRAP(!nlk_sk(sk)->cb); +} + +/* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on SMP. + * Look, when several writers sleep and reader wakes them up, all but one + * immediately hit write lock and grab all the cpus. Exclusive sleep solves + * this, _but_ remember, it adds useless work on UP machines. + */ + +static void netlink_table_grab(void) +{ + write_lock_bh(&nl_table_lock); + + if (atomic_read(&nl_table_users)) { + DECLARE_WAITQUEUE(wait, current); + + add_wait_queue_exclusive(&nl_table_wait, &wait); + for(;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (atomic_read(&nl_table_users) == 0) + break; + write_unlock_bh(&nl_table_lock); + schedule(); + write_lock_bh(&nl_table_lock); + } + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nl_table_wait, &wait); + } +} + +static __inline__ void netlink_table_ungrab(void) +{ + write_unlock_bh(&nl_table_lock); + wake_up(&nl_table_wait); +} + +static __inline__ void +netlink_lock_table(void) +{ + /* read_lock() synchronizes us to netlink_table_grab */ + + read_lock(&nl_table_lock); + atomic_inc(&nl_table_users); + read_unlock(&nl_table_lock); +} + +static __inline__ void +netlink_unlock_table(void) +{ + if (atomic_dec_and_test(&nl_table_users)) + wake_up(&nl_table_wait); +} + +static __inline__ struct sock *netlink_lookup(int protocol, u32 pid) +{ + struct nl_pid_hash *hash = &nl_table[protocol].hash; + struct hlist_head *head; + struct sock *sk; + struct hlist_node *node; + + read_lock(&nl_table_lock); + head = nl_pid_hashfn(hash, pid); + sk_for_each(sk, node, head) { + if (nlk_sk(sk)->pid == pid) { + sock_hold(sk); + goto found; + } + } + sk = NULL; +found: + read_unlock(&nl_table_lock); + return sk; +} + +static inline struct hlist_head *nl_pid_hash_alloc(size_t size) +{ + if (size <= PAGE_SIZE) + return kmalloc(size, GFP_ATOMIC); + else + return (struct hlist_head *) + __get_free_pages(GFP_ATOMIC, get_order(size)); +} + +static inline void nl_pid_hash_free(struct hlist_head *table, size_t size) +{ + if (size <= PAGE_SIZE) + kfree(table); + else + free_pages((unsigned long)table, get_order(size)); +} + +static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow) +{ + unsigned int omask, mask, shift; + size_t osize, size; + struct hlist_head *otable, *table; + int i; + + omask = mask = hash->mask; + osize = size = (mask + 1) * sizeof(*table); + shift = hash->shift; + + if (grow) { + if (++shift > hash->max_shift) + return 0; + mask = mask * 2 + 1; + size *= 2; + } + + table = nl_pid_hash_alloc(size); + if (!table) + return 0; + + memset(table, 0, size); + otable = hash->table; + hash->table = table; + hash->mask = mask; + hash->shift = shift; + get_random_bytes(&hash->rnd, sizeof(hash->rnd)); + + for (i = 0; i <= omask; i++) { + struct sock *sk; + struct hlist_node *node, *tmp; + + sk_for_each_safe(sk, node, tmp, &otable[i]) + __sk_add_node(sk, nl_pid_hashfn(hash, nlk_sk(sk)->pid)); + } + + nl_pid_hash_free(otable, osize); + hash->rehash_time = jiffies + 10 * 60 * HZ; + return 1; +} + +static inline int nl_pid_hash_dilute(struct nl_pid_hash *hash, int len) +{ + int avg = hash->entries >> hash->shift; + + if (unlikely(avg > 1) && nl_pid_hash_rehash(hash, 1)) + return 1; + + if (unlikely(len > avg) && time_after(jiffies, hash->rehash_time)) { + nl_pid_hash_rehash(hash, 0); + return 1; + } + + return 0; +} + +static struct proto_ops netlink_ops; + +static int netlink_insert(struct sock *sk, u32 pid) +{ + struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; + struct hlist_head *head; + int err = -EADDRINUSE; + struct sock *osk; + struct hlist_node *node; + int len; + + netlink_table_grab(); + head = nl_pid_hashfn(hash, pid); + len = 0; + sk_for_each(osk, node, head) { + if (nlk_sk(osk)->pid == pid) + break; + len++; + } + if (node) + goto err; + + err = -EBUSY; + if (nlk_sk(sk)->pid) + goto err; + + err = -ENOMEM; + if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX)) + goto err; + + if (len && nl_pid_hash_dilute(hash, len)) + head = nl_pid_hashfn(hash, pid); + hash->entries++; + nlk_sk(sk)->pid = pid; + sk_add_node(sk, head); + err = 0; + +err: + netlink_table_ungrab(); + return err; +} + +static void netlink_remove(struct sock *sk) +{ + netlink_table_grab(); + nl_table[sk->sk_protocol].hash.entries--; + sk_del_node_init(sk); + if (nlk_sk(sk)->groups) + __sk_del_bind_node(sk); + netlink_table_ungrab(); +} + +static struct proto netlink_proto = { + .name = "NETLINK", + .owner = THIS_MODULE, + .obj_size = sizeof(struct netlink_sock), +}; + +static int netlink_create(struct socket *sock, int protocol) +{ + struct sock *sk; + struct netlink_sock *nlk; + + sock->state = SS_UNCONNECTED; + + if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) + return -ESOCKTNOSUPPORT; + + if (protocol<0 || protocol >= MAX_LINKS) + return -EPROTONOSUPPORT; + + sock->ops = &netlink_ops; + + sk = sk_alloc(PF_NETLINK, GFP_KERNEL, &netlink_proto, 1); + if (!sk) + return -ENOMEM; + + sock_init_data(sock, sk); + + nlk = nlk_sk(sk); + + spin_lock_init(&nlk->cb_lock); + init_waitqueue_head(&nlk->wait); + sk->sk_destruct = netlink_sock_destruct; + + sk->sk_protocol = protocol; + return 0; +} + +static int netlink_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk; + + if (!sk) + return 0; + + netlink_remove(sk); + nlk = nlk_sk(sk); + + spin_lock(&nlk->cb_lock); + if (nlk->cb) { + nlk->cb->done(nlk->cb); + netlink_destroy_callback(nlk->cb); + nlk->cb = NULL; + __sock_put(sk); + } + spin_unlock(&nlk->cb_lock); + + /* OK. Socket is unlinked, and, therefore, + no new packets will arrive */ + + sock_orphan(sk); + sock->sk = NULL; + wake_up_interruptible_all(&nlk->wait); + + skb_queue_purge(&sk->sk_write_queue); + + if (nlk->pid && !nlk->groups) { + struct netlink_notify n = { + .protocol = sk->sk_protocol, + .pid = nlk->pid, + }; + notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); + } + + sock_put(sk); + return 0; +} + +static int netlink_autobind(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; + struct hlist_head *head; + struct sock *osk; + struct hlist_node *node; + s32 pid = current->pid; + int err; + static s32 rover = -4097; + +retry: + cond_resched(); + netlink_table_grab(); + head = nl_pid_hashfn(hash, pid); + sk_for_each(osk, node, head) { + if (nlk_sk(osk)->pid == pid) { + /* Bind collision, search negative pid values. */ + pid = rover--; + if (rover > -4097) + rover = -4097; + netlink_table_ungrab(); + goto retry; + } + } + netlink_table_ungrab(); + + err = netlink_insert(sk, pid); + if (err == -EADDRINUSE) + goto retry; + return 0; +} + +static inline int netlink_capable(struct socket *sock, unsigned int flag) +{ + return (nl_table[sock->sk->sk_protocol].nl_nonroot & flag) || + capable(CAP_NET_ADMIN); +} + +static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; + int err; + + if (nladdr->nl_family != AF_NETLINK) + return -EINVAL; + + /* Only superuser is allowed to listen multicasts */ + if (nladdr->nl_groups && !netlink_capable(sock, NL_NONROOT_RECV)) + return -EPERM; + + if (nlk->pid) { + if (nladdr->nl_pid != nlk->pid) + return -EINVAL; + } else { + err = nladdr->nl_pid ? + netlink_insert(sk, nladdr->nl_pid) : + netlink_autobind(sock); + if (err) + return err; + } + + if (!nladdr->nl_groups && !nlk->groups) + return 0; + + netlink_table_grab(); + if (nlk->groups && !nladdr->nl_groups) + __sk_del_bind_node(sk); + else if (!nlk->groups && nladdr->nl_groups) + sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); + nlk->groups = nladdr->nl_groups; + netlink_table_ungrab(); + + return 0; +} + +static int netlink_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags) +{ + int err = 0; + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + struct sockaddr_nl *nladdr=(struct sockaddr_nl*)addr; + + if (addr->sa_family == AF_UNSPEC) { + sk->sk_state = NETLINK_UNCONNECTED; + nlk->dst_pid = 0; + nlk->dst_groups = 0; + return 0; + } + if (addr->sa_family != AF_NETLINK) + return -EINVAL; + + /* Only superuser is allowed to send multicasts */ + if (nladdr->nl_groups && !netlink_capable(sock, NL_NONROOT_SEND)) + return -EPERM; + + if (!nlk->pid) + err = netlink_autobind(sock); + + if (err == 0) { + sk->sk_state = NETLINK_CONNECTED; + nlk->dst_pid = nladdr->nl_pid; + nlk->dst_groups = nladdr->nl_groups; + } + + return err; +} + +static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr_len, int peer) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + struct sockaddr_nl *nladdr=(struct sockaddr_nl *)addr; + + nladdr->nl_family = AF_NETLINK; + nladdr->nl_pad = 0; + *addr_len = sizeof(*nladdr); + + if (peer) { + nladdr->nl_pid = nlk->dst_pid; + nladdr->nl_groups = nlk->dst_groups; + } else { + nladdr->nl_pid = nlk->pid; + nladdr->nl_groups = nlk->groups; + } + return 0; +} + +static void netlink_overrun(struct sock *sk) +{ + if (!test_and_set_bit(0, &nlk_sk(sk)->state)) { + sk->sk_err = ENOBUFS; + sk->sk_error_report(sk); + } +} + +static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid) +{ + int protocol = ssk->sk_protocol; + struct sock *sock; + struct netlink_sock *nlk; + + sock = netlink_lookup(protocol, pid); + if (!sock) + return ERR_PTR(-ECONNREFUSED); + + /* Don't bother queuing skb if kernel socket has no input function */ + nlk = nlk_sk(sock); + if ((nlk->pid == 0 && !nlk->data_ready) || + (sock->sk_state == NETLINK_CONNECTED && + nlk->dst_pid != nlk_sk(ssk)->pid)) { + sock_put(sock); + return ERR_PTR(-ECONNREFUSED); + } + return sock; +} + +struct sock *netlink_getsockbyfilp(struct file *filp) +{ + struct inode *inode = filp->f_dentry->d_inode; + struct sock *sock; + + if (!S_ISSOCK(inode->i_mode)) + return ERR_PTR(-ENOTSOCK); + + sock = SOCKET_I(inode)->sk; + if (sock->sk_family != AF_NETLINK) + return ERR_PTR(-EINVAL); + + sock_hold(sock); + return sock; +} + +/* + * Attach a skb to a netlink socket. + * The caller must hold a reference to the destination socket. On error, the + * reference is dropped. The skb is not send to the destination, just all + * all error checks are performed and memory in the queue is reserved. + * Return values: + * < 0: error. skb freed, reference to sock dropped. + * 0: continue + * 1: repeat lookup - reference dropped while waiting for socket memory. + */ +int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, long timeo) +{ + struct netlink_sock *nlk; + + nlk = nlk_sk(sk); + + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || + test_bit(0, &nlk->state)) { + DECLARE_WAITQUEUE(wait, current); + if (!timeo) { + if (!nlk->pid) + netlink_overrun(sk); + sock_put(sk); + kfree_skb(skb); + return -EAGAIN; + } + + __set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&nlk->wait, &wait); + + if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || + test_bit(0, &nlk->state)) && + !sock_flag(sk, SOCK_DEAD)) + timeo = schedule_timeout(timeo); + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nlk->wait, &wait); + sock_put(sk); + + if (signal_pending(current)) { + kfree_skb(skb); + return sock_intr_errno(timeo); + } + return 1; + } + skb_set_owner_r(skb, sk); + return 0; +} + +int netlink_sendskb(struct sock *sk, struct sk_buff *skb, int protocol) +{ + struct netlink_sock *nlk; + int len = skb->len; + + nlk = nlk_sk(sk); + + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, len); + sock_put(sk); + return len; +} + +void netlink_detachskb(struct sock *sk, struct sk_buff *skb) +{ + kfree_skb(skb); + sock_put(sk); +} + +static inline struct sk_buff *netlink_trim(struct sk_buff *skb, int allocation) +{ + int delta; + + skb_orphan(skb); + + delta = skb->end - skb->tail; + if (delta * 2 < skb->truesize) + return skb; + + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, allocation); + if (!nskb) + return skb; + kfree_skb(skb); + skb = nskb; + } + + if (!pskb_expand_head(skb, 0, -delta, allocation)) + skb->truesize -= delta; + + return skb; +} + +int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 pid, int nonblock) +{ + struct sock *sk; + int err; + long timeo; + + skb = netlink_trim(skb, gfp_any()); + + timeo = sock_sndtimeo(ssk, nonblock); +retry: + sk = netlink_getsockbypid(ssk, pid); + if (IS_ERR(sk)) { + kfree_skb(skb); + return PTR_ERR(sk); + } + err = netlink_attachskb(sk, skb, nonblock, timeo); + if (err == 1) + goto retry; + if (err) + return err; + + return netlink_sendskb(sk, skb, ssk->sk_protocol); +} + +static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !test_bit(0, &nlk->state)) { + skb_set_owner_r(skb, sk); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + return atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf; + } + return -1; +} + +struct netlink_broadcast_data { + struct sock *exclude_sk; + u32 pid; + u32 group; + int failure; + int congested; + int delivered; + int allocation; + struct sk_buff *skb, *skb2; +}; + +static inline int do_one_broadcast(struct sock *sk, + struct netlink_broadcast_data *p) +{ + struct netlink_sock *nlk = nlk_sk(sk); + int val; + + if (p->exclude_sk == sk) + goto out; + + if (nlk->pid == p->pid || !(nlk->groups & p->group)) + goto out; + + if (p->failure) { + netlink_overrun(sk); + goto out; + } + + sock_hold(sk); + if (p->skb2 == NULL) { + if (atomic_read(&p->skb->users) != 1) { + p->skb2 = skb_clone(p->skb, p->allocation); + } else { + p->skb2 = p->skb; + atomic_inc(&p->skb->users); + } + } + if (p->skb2 == NULL) { + netlink_overrun(sk); + /* Clone failed. Notify ALL listeners. */ + p->failure = 1; + } else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) { + netlink_overrun(sk); + } else { + p->congested |= val; + p->delivered = 1; + p->skb2 = NULL; + } + sock_put(sk); + +out: + return 0; +} + +int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, + u32 group, int allocation) +{ + struct netlink_broadcast_data info; + struct hlist_node *node; + struct sock *sk; + + skb = netlink_trim(skb, allocation); + + info.exclude_sk = ssk; + info.pid = pid; + info.group = group; + info.failure = 0; + info.congested = 0; + info.delivered = 0; + info.allocation = allocation; + info.skb = skb; + info.skb2 = NULL; + + /* While we sleep in clone, do not allow to change socket list */ + + netlink_lock_table(); + + sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) + do_one_broadcast(sk, &info); + + netlink_unlock_table(); + + if (info.skb2) + kfree_skb(info.skb2); + kfree_skb(skb); + + if (info.delivered) { + if (info.congested && (allocation & __GFP_WAIT)) + yield(); + return 0; + } + if (info.failure) + return -ENOBUFS; + return -ESRCH; +} + +struct netlink_set_err_data { + struct sock *exclude_sk; + u32 pid; + u32 group; + int code; +}; + +static inline int do_one_set_err(struct sock *sk, + struct netlink_set_err_data *p) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (sk == p->exclude_sk) + goto out; + + if (nlk->pid == p->pid || !(nlk->groups & p->group)) + goto out; + + sk->sk_err = p->code; + sk->sk_error_report(sk); +out: + return 0; +} + +void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) +{ + struct netlink_set_err_data info; + struct hlist_node *node; + struct sock *sk; + + info.exclude_sk = ssk; + info.pid = pid; + info.group = group; + info.code = code; + + read_lock(&nl_table_lock); + + sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) + do_one_set_err(sk, &info); + + read_unlock(&nl_table_lock); +} + +static inline void netlink_rcv_wake(struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (!skb_queue_len(&sk->sk_receive_queue)) + clear_bit(0, &nlk->state); + if (!test_bit(0, &nlk->state)) + wake_up_interruptible(&nlk->wait); +} + +static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ + 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; + u32 dst_pid; + u32 dst_groups; + struct sk_buff *skb; + int err; + struct scm_cookie scm; + + if (msg->msg_flags&MSG_OOB) + return -EOPNOTSUPP; + + if (NULL == siocb->scm) + siocb->scm = &scm; + err = scm_send(sock, msg, siocb->scm); + if (err < 0) + return err; + + if (msg->msg_namelen) { + if (addr->nl_family != AF_NETLINK) + return -EINVAL; + dst_pid = addr->nl_pid; + dst_groups = addr->nl_groups; + if (dst_groups && !netlink_capable(sock, NL_NONROOT_SEND)) + return -EPERM; + } else { + dst_pid = nlk->dst_pid; + dst_groups = nlk->dst_groups; + } + + if (!nlk->pid) { + err = netlink_autobind(sock); + if (err) + goto out; + } + + err = -EMSGSIZE; + if (len > sk->sk_sndbuf - 32) + goto out; + err = -ENOBUFS; + skb = alloc_skb(len, GFP_KERNEL); + if (skb==NULL) + goto out; + + NETLINK_CB(skb).pid = nlk->pid; + NETLINK_CB(skb).groups = nlk->groups; + NETLINK_CB(skb).dst_pid = dst_pid; + NETLINK_CB(skb).dst_groups = dst_groups; + memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); + + /* What can I do? Netlink is asynchronous, so that + we will have to save current capabilities to + check them, when this message will be delivered + to corresponding kernel module. --ANK (980802) + */ + + err = -EFAULT; + if (memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len)) { + kfree_skb(skb); + goto out; + } + + err = security_netlink_send(sk, skb); + if (err) { + kfree_skb(skb); + goto out; + } + + if (dst_groups) { + atomic_inc(&skb->users); + netlink_broadcast(sk, skb, dst_pid, dst_groups, GFP_KERNEL); + } + err = netlink_unicast(sk, skb, dst_pid, msg->msg_flags&MSG_DONTWAIT); + +out: + return err; +} + +static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, + struct msghdr *msg, size_t len, + int flags) +{ + struct sock_iocb *siocb = kiocb_to_siocb(kiocb); + struct scm_cookie scm; + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + int noblock = flags&MSG_DONTWAIT; + size_t copied; + struct sk_buff *skb; + int err; + + if (flags&MSG_OOB) + return -EOPNOTSUPP; + + copied = 0; + + skb = skb_recv_datagram(sk,flags,noblock,&err); + if (skb==NULL) + goto out; + + msg->msg_namelen = 0; + + copied = skb->len; + if (len < copied) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + skb->h.raw = skb->data; + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + + if (msg->msg_name) { + struct sockaddr_nl *addr = (struct sockaddr_nl*)msg->msg_name; + addr->nl_family = AF_NETLINK; + addr->nl_pad = 0; + addr->nl_pid = NETLINK_CB(skb).pid; + addr->nl_groups = NETLINK_CB(skb).dst_groups; + msg->msg_namelen = sizeof(*addr); + } + + if (NULL == siocb->scm) { + memset(&scm, 0, sizeof(scm)); + siocb->scm = &scm; + } + siocb->scm->creds = *NETLINK_CREDS(skb); + skb_free_datagram(sk, skb); + + if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) + netlink_dump(sk); + + scm_recv(sock, msg, siocb->scm, flags); + +out: + netlink_rcv_wake(sk); + return err ? : copied; +} + +static void netlink_data_ready(struct sock *sk, int len) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (nlk->data_ready) + nlk->data_ready(sk, len); + netlink_rcv_wake(sk); +} + +/* + * We export these functions to other modules. They provide a + * complete set of kernel non-blocking support for message + * queueing. + */ + +struct sock * +netlink_kernel_create(int unit, void (*input)(struct sock *sk, int len)) +{ + struct socket *sock; + struct sock *sk; + + if (!nl_table) + return NULL; + + if (unit<0 || unit>=MAX_LINKS) + return NULL; + + if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) + return NULL; + + if (netlink_create(sock, unit) < 0) { + sock_release(sock); + return NULL; + } + sk = sock->sk; + sk->sk_data_ready = netlink_data_ready; + if (input) + nlk_sk(sk)->data_ready = input; + + if (netlink_insert(sk, 0)) { + sock_release(sock); + return NULL; + } + return sk; +} + +void netlink_set_nonroot(int protocol, unsigned int flags) +{ + if ((unsigned int)protocol < MAX_LINKS) + nl_table[protocol].nl_nonroot = flags; +} + +static void netlink_destroy_callback(struct netlink_callback *cb) +{ + if (cb->skb) + kfree_skb(cb->skb); + kfree(cb); +} + +/* + * It looks a bit ugly. + * It would be better to create kernel thread. + */ + +static int netlink_dump(struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + struct netlink_callback *cb; + struct sk_buff *skb; + struct nlmsghdr *nlh; + int len; + + skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + spin_lock(&nlk->cb_lock); + + cb = nlk->cb; + if (cb == NULL) { + spin_unlock(&nlk->cb_lock); + kfree_skb(skb); + return -EINVAL; + } + + len = cb->dump(skb, cb); + + if (len > 0) { + spin_unlock(&nlk->cb_lock); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, len); + return 0; + } + + nlh = __nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLMSG_DONE, sizeof(int)); + nlh->nlmsg_flags |= NLM_F_MULTI; + memcpy(NLMSG_DATA(nlh), &len, sizeof(len)); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + + cb->done(cb); + nlk->cb = NULL; + spin_unlock(&nlk->cb_lock); + + netlink_destroy_callback(cb); + __sock_put(sk); + return 0; +} + +int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, + struct nlmsghdr *nlh, + int (*dump)(struct sk_buff *skb, struct netlink_callback*), + int (*done)(struct netlink_callback*)) +{ + struct netlink_callback *cb; + struct sock *sk; + struct netlink_sock *nlk; + + cb = kmalloc(sizeof(*cb), GFP_KERNEL); + if (cb == NULL) + return -ENOBUFS; + + memset(cb, 0, sizeof(*cb)); + cb->dump = dump; + cb->done = done; + cb->nlh = nlh; + atomic_inc(&skb->users); + cb->skb = skb; + + sk = netlink_lookup(ssk->sk_protocol, NETLINK_CB(skb).pid); + if (sk == NULL) { + netlink_destroy_callback(cb); + return -ECONNREFUSED; + } + nlk = nlk_sk(sk); + /* A dump is in progress... */ + spin_lock(&nlk->cb_lock); + if (nlk->cb) { + spin_unlock(&nlk->cb_lock); + netlink_destroy_callback(cb); + sock_put(sk); + return -EBUSY; + } + nlk->cb = cb; + sock_hold(sk); + spin_unlock(&nlk->cb_lock); + + netlink_dump(sk); + sock_put(sk); + return 0; +} + +void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) +{ + struct sk_buff *skb; + struct nlmsghdr *rep; + struct nlmsgerr *errmsg; + int size; + + if (err == 0) + size = NLMSG_SPACE(sizeof(struct nlmsgerr)); + else + size = NLMSG_SPACE(4 + NLMSG_ALIGN(nlh->nlmsg_len)); + + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) { + struct sock *sk; + + sk = netlink_lookup(in_skb->sk->sk_protocol, + NETLINK_CB(in_skb).pid); + if (sk) { + sk->sk_err = ENOBUFS; + sk->sk_error_report(sk); + sock_put(sk); + } + return; + } + + rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + NLMSG_ERROR, sizeof(struct nlmsgerr)); + errmsg = NLMSG_DATA(rep); + errmsg->error = err; + memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(struct nlmsghdr)); + netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); +} + + +#ifdef CONFIG_PROC_FS +struct nl_seq_iter { + int link; + int hash_idx; +}; + +static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) +{ + struct nl_seq_iter *iter = seq->private; + int i, j; + struct sock *s; + struct hlist_node *node; + loff_t off = 0; + + for (i=0; i<MAX_LINKS; i++) { + struct nl_pid_hash *hash = &nl_table[i].hash; + + for (j = 0; j <= hash->mask; j++) { + sk_for_each(s, node, &hash->table[j]) { + if (off == pos) { + iter->link = i; + iter->hash_idx = j; + return s; + } + ++off; + } + } + } + return NULL; +} + +static void *netlink_seq_start(struct seq_file *seq, loff_t *pos) +{ + read_lock(&nl_table_lock); + return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN; +} + +static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock *s; + struct nl_seq_iter *iter; + int i, j; + + ++*pos; + + if (v == SEQ_START_TOKEN) + return netlink_seq_socket_idx(seq, 0); + + s = sk_next(v); + if (s) + return s; + + iter = seq->private; + i = iter->link; + j = iter->hash_idx + 1; + + do { + struct nl_pid_hash *hash = &nl_table[i].hash; + + for (; j <= hash->mask; j++) { + s = sk_head(&hash->table[j]); + if (s) { + iter->link = i; + iter->hash_idx = j; + return s; + } + } + + j = 0; + } while (++i < MAX_LINKS); + + return NULL; +} + +static void netlink_seq_stop(struct seq_file *seq, void *v) +{ + read_unlock(&nl_table_lock); +} + + +static int |