X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fnetlink%2Faf_netlink.c;h=a4957bf2ca60d6963e2d94f9b2e7679df3a0b4b6;hb=9f121a5a80b4417c6db5a35e26d2e79c29c3fc0d;hp=98e313e5e59440f0ed2b8283532cea179d267238;hpb=f937f1f46b6d2f9bef94e0d6b769a4c67615d34e;p=safe%2Fjmp%2Flinux-2.6 diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 98e313e..a4957bf 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1,7 +1,7 @@ /* * NETLINK Kernel-user communication protocol. * - * Authors: Alan Cox + * Authors: Alan Cox * Alexey Kuznetsov * * This program is free software; you can redistribute it and/or @@ -54,7 +54,6 @@ #include #include #include -#include #include #include @@ -84,8 +83,15 @@ struct netlink_sock { struct module *module; }; +struct listeners_rcu_head { + struct rcu_head rcu_head; + void *ptr; +}; + #define NETLINK_KERNEL_SOCKET 0x1 #define NETLINK_RECV_PKTINFO 0x2 +#define NETLINK_BROADCAST_SEND_ERROR 0x4 +#define NETLINK_RECV_NO_ENOBUFS 0x8 static inline struct netlink_sock *nlk_sk(struct sock *sk) { @@ -156,29 +162,33 @@ 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); + printk(KERN_ERR "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)->groups); + + WARN_ON(atomic_read(&sk->sk_rmem_alloc)); + WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(nlk_sk(sk)->groups); } -/* 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 +/* 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) +void netlink_table_grab(void) + __acquires(nl_table_lock) { + might_sleep(); + write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&nl_table_wait, &wait); - for(;;) { + for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&nl_table_users) == 0) break; @@ -192,13 +202,14 @@ static void netlink_table_grab(void) } } -static __inline__ void netlink_table_ungrab(void) +void netlink_table_ungrab(void) + __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); wake_up(&nl_table_wait); } -static __inline__ void +static inline void netlink_lock_table(void) { /* read_lock() synchronizes us to netlink_table_grab */ @@ -208,14 +219,15 @@ netlink_lock_table(void) read_unlock(&nl_table_lock); } -static __inline__ void +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(struct net *net, int protocol, u32 pid) +static inline struct sock *netlink_lookup(struct net *net, int protocol, + u32 pid) { struct nl_pid_hash *hash = &nl_table[protocol].hash; struct hlist_head *head; @@ -225,7 +237,7 @@ static __inline__ struct sock *netlink_lookup(struct net *net, int protocol, u32 read_lock(&nl_table_lock); head = nl_pid_hashfn(hash, pid); sk_for_each(sk, node, head) { - if ((sk->sk_net == net) && (nlk_sk(sk)->pid == pid)) { + if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->pid == pid)) { sock_hold(sk); goto found; } @@ -236,13 +248,14 @@ found: return sk; } -static inline struct hlist_head *nl_pid_hash_alloc(size_t size) +static inline struct hlist_head *nl_pid_hash_zalloc(size_t size) { if (size <= PAGE_SIZE) - return kmalloc(size, GFP_ATOMIC); + return kzalloc(size, GFP_ATOMIC); else return (struct hlist_head *) - __get_free_pages(GFP_ATOMIC, get_order(size)); + __get_free_pages(GFP_ATOMIC | __GFP_ZERO, + get_order(size)); } static inline void nl_pid_hash_free(struct hlist_head *table, size_t size) @@ -271,11 +284,10 @@ static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow) size *= 2; } - table = nl_pid_hash_alloc(size); + table = nl_pid_hash_zalloc(size); if (!table) return 0; - memset(table, 0, size); otable = hash->table; hash->table = table; hash->mask = mask; @@ -345,7 +357,7 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 pid) head = nl_pid_hashfn(hash, pid); len = 0; sk_for_each(osk, node, head) { - if ((osk->sk_net == net) && (nlk_sk(osk)->pid == pid)) + if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->pid == pid)) break; len++; } @@ -396,7 +408,7 @@ static int __netlink_create(struct net *net, struct socket *sock, sock->ops = &netlink_ops; - sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, 1); + sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto); if (!sk) return -ENOMEM; @@ -416,7 +428,8 @@ static int __netlink_create(struct net *net, struct socket *sock, return 0; } -static int netlink_create(struct net *net, struct socket *sock, int protocol) +static int netlink_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct module *module = NULL; struct mutex *cb_mutex; @@ -428,11 +441,11 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol) if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; - if (protocol<0 || protocol >= MAX_LINKS) + if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; netlink_lock_table(); -#ifdef CONFIG_KMOD +#ifdef CONFIG_MODULES if (!nl_table[protocol].registered) { netlink_unlock_table(); request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); @@ -445,9 +458,14 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol) cb_mutex = nl_table[protocol].cb_mutex; netlink_unlock_table(); - if ((err = __netlink_create(net, sock, cb_mutex, protocol)) < 0) + err = __netlink_create(net, sock, cb_mutex, protocol); + if (err < 0) goto out_module; + local_bh_disable(); + sock_prot_inuse_add(net, &netlink_proto, 1); + local_bh_enable(); + nlk = nlk_sk(sock->sk); nlk->module = module; out: @@ -480,9 +498,9 @@ static int netlink_release(struct socket *sock) skb_queue_purge(&sk->sk_write_queue); - if (nlk->pid && !nlk->subscriptions) { + if (nlk->pid) { struct netlink_notify n = { - .net = sk->sk_net, + .net = sock_net(sk), .protocol = sk->sk_protocol, .pid = nlk->pid, }; @@ -494,9 +512,12 @@ static int netlink_release(struct socket *sock) netlink_table_grab(); if (netlink_is_kernel(sk)) { - kfree(nl_table[sk->sk_protocol].listeners); - nl_table[sk->sk_protocol].module = NULL; - nl_table[sk->sk_protocol].registered = 0; + BUG_ON(nl_table[sk->sk_protocol].registered == 0); + if (--nl_table[sk->sk_protocol].registered == 0) { + kfree(nl_table[sk->sk_protocol].listeners); + nl_table[sk->sk_protocol].module = NULL; + nl_table[sk->sk_protocol].registered = 0; + } } else if (nlk->subscriptions) netlink_update_listeners(sk); netlink_table_ungrab(); @@ -504,6 +525,9 @@ static int netlink_release(struct socket *sock) kfree(nlk->groups); nlk->groups = NULL; + local_bh_disable(); + sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); + local_bh_enable(); sock_put(sk); return 0; } @@ -511,7 +535,7 @@ static int netlink_release(struct socket *sock) static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; struct hlist_head *head; struct sock *osk; @@ -525,7 +549,7 @@ retry: netlink_table_grab(); head = nl_pid_hashfn(hash, pid); sk_for_each(osk, node, head) { - if ((osk->sk_net != net)) + if (!net_eq(sock_net(osk), net)) continue; if (nlk_sk(osk)->pid == pid) { /* Bind collision, search negative pid values. */ @@ -590,7 +614,7 @@ static int netlink_realloc_groups(struct sock *sk) err = -ENOMEM; goto out_unlock; } - memset((char*)new_groups + NLGRPSZ(nlk->ngroups), 0, + memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); nlk->groups = new_groups; @@ -600,10 +624,11 @@ static int netlink_realloc_groups(struct sock *sk) return err; } -static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +static int netlink_bind(struct socket *sock, struct sockaddr *addr, + int addr_len) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; @@ -651,7 +676,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, int err = 0; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - struct sockaddr_nl *nladdr=(struct sockaddr_nl*)addr; + struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; if (addr->sa_family == AF_UNSPEC) { sk->sk_state = NETLINK_UNCONNECTED; @@ -678,11 +703,12 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return err; } -static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr_len, int peer) +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; + DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; @@ -700,10 +726,15 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, int *addr 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); + struct netlink_sock *nlk = nlk_sk(sk); + + if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) { + if (!test_and_set_bit(0, &nlk_sk(sk)->state)) { + sk->sk_err = ENOBUFS; + sk->sk_error_report(sk); + } } + atomic_inc(&sk->sk_drops); } static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid) @@ -711,7 +742,7 @@ static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid) struct sock *sock; struct netlink_sock *nlk; - sock = netlink_lookup(ssk->sk_net, ssk->sk_protocol, pid); + sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, pid); if (!sock) return ERR_PTR(-ECONNREFUSED); @@ -751,8 +782,8 @@ struct sock *netlink_getsockbyfilp(struct file *filp) * 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 sock *ssk) +int netlink_attachskb(struct sock *sk, struct sk_buff *skb, + long *timeo, struct sock *ssk) { struct netlink_sock *nlk; @@ -761,7 +792,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(0, &nlk->state)) { DECLARE_WAITQUEUE(wait, current); - if (!timeo) { + if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); @@ -775,7 +806,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(0, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) - timeo = schedule_timeout(timeo); + *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); @@ -783,7 +814,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock, if (signal_pending(current)) { kfree_skb(skb); - return sock_intr_errno(timeo); + return sock_intr_errno(*timeo); } return 1; } @@ -877,7 +908,14 @@ retry: if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb); - err = netlink_attachskb(sk, skb, nonblock, timeo, ssk); + if (sk_filter(sk, skb)) { + err = skb->len; + kfree_skb(skb); + sock_put(sk); + return err; + } + + err = netlink_attachskb(sk, skb, &timeo, ssk); if (err == 1) goto retry; if (err) @@ -885,6 +923,7 @@ retry: return netlink_sendskb(sk, skb); } +EXPORT_SYMBOL(netlink_unicast); int netlink_has_listeners(struct sock *sk, unsigned int group) { @@ -905,7 +944,8 @@ int netlink_has_listeners(struct sock *sk, unsigned int group) } EXPORT_SYMBOL_GPL(netlink_has_listeners); -static __inline__ int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) +static inline int netlink_broadcast_deliver(struct sock *sk, + struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); @@ -925,6 +965,7 @@ struct netlink_broadcast_data { u32 pid; u32 group; int failure; + int delivery_failure; int congested; int delivered; gfp_t allocation; @@ -944,7 +985,7 @@ static inline int do_one_broadcast(struct sock *sk, !test_bit(p->group - 1, nlk->groups)) goto out; - if ((sk->sk_net != p->net)) + if (!net_eq(sock_net(sk), p->net)) goto out; if (p->failure) { @@ -969,8 +1010,15 @@ static inline int do_one_broadcast(struct sock *sk, netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; + if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR) + p->delivery_failure = 1; + } else if (sk_filter(sk, p->skb2)) { + kfree_skb(p->skb2); + p->skb2 = NULL; } else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) { netlink_overrun(sk); + if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR) + p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; @@ -985,7 +1033,7 @@ out: int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, u32 group, gfp_t allocation) { - struct net *net = ssk->sk_net; + struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct hlist_node *node; struct sock *sk; @@ -997,6 +1045,7 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, info.pid = pid; info.group = group; info.failure = 0; + info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; @@ -1014,18 +1063,19 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, netlink_unlock_table(); - if (info.skb2) - kfree_skb(info.skb2); + kfree_skb(info.skb2); + + if (info.delivery_failure) + return -ENOBUFS; if (info.delivered) { if (info.congested && (allocation & __GFP_WAIT)) yield(); return 0; } - if (info.failure) - return -ENOBUFS; return -ESRCH; } +EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; @@ -1042,7 +1092,7 @@ static inline int do_one_set_err(struct sock *sk, if (sk == p->exclude_sk) goto out; - if (sk->sk_net != p->exclude_sk->sk_net) + if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups || @@ -1055,6 +1105,13 @@ out: return 0; } +/** + * netlink_set_err - report error to broadcast listeners + * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() + * @pid: the PID of a process that we want to skip (if any) + * @groups: the broadcast group that will notice the error + * @code: error code, must be negative (as usual in kernelspace) + */ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) { struct netlink_set_err_data info; @@ -1064,7 +1121,8 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) info.exclude_sk = ssk; info.pid = pid; info.group = group; - info.code = code; + /* sk->sk_err wants a positive error value */ + info.code = -code; read_lock(&nl_table_lock); @@ -1073,6 +1131,7 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) read_unlock(&nl_table_lock); } +EXPORT_SYMBOL(netlink_set_err); /* must be called with netlink table grabbed */ static void netlink_update_socket_mc(struct netlink_sock *nlk, @@ -1092,7 +1151,7 @@ static void netlink_update_socket_mc(struct netlink_sock *nlk, } static int netlink_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); @@ -1130,6 +1189,22 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, err = 0; break; } + case NETLINK_BROADCAST_ERROR: + if (val) + nlk->flags |= NETLINK_BROADCAST_SEND_ERROR; + else + nlk->flags &= ~NETLINK_BROADCAST_SEND_ERROR; + err = 0; + break; + case NETLINK_NO_ENOBUFS: + if (val) { + nlk->flags |= NETLINK_RECV_NO_ENOBUFS; + clear_bit(0, &nlk->state); + wake_up_interruptible(&nlk->wait); + } else + nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -1162,6 +1237,26 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, return -EFAULT; err = 0; break; + case NETLINK_BROADCAST_ERROR: + if (len < sizeof(int)) + return -EINVAL; + len = sizeof(int); + val = nlk->flags & NETLINK_BROADCAST_SEND_ERROR ? 1 : 0; + if (put_user(len, optlen) || + put_user(val, optval)) + return -EFAULT; + err = 0; + break; + case NETLINK_NO_ENOBUFS: + if (len < sizeof(int)) + return -EINVAL; + len = sizeof(int); + val = nlk->flags & NETLINK_RECV_NO_ENOBUFS ? 1 : 0; + if (put_user(len, optlen) || + put_user(val, optval)) + return -EFAULT; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -1182,7 +1277,7 @@ 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; + struct sockaddr_nl *addr = msg->msg_name; u32 dst_pid; u32 dst_group; struct sk_buff *skb; @@ -1221,13 +1316,14 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; err = -ENOBUFS; skb = alloc_skb(len, GFP_KERNEL); - if (skb==NULL) + if (skb == NULL) goto out; NETLINK_CB(skb).pid = nlk->pid; NETLINK_CB(skb).dst_group = dst_group; - NETLINK_CB(skb).loginuid = audit_get_loginuid(current->audit_context); - selinux_get_task_sid(current, &(NETLINK_CB(skb).sid)); + NETLINK_CB(skb).loginuid = audit_get_loginuid(current); + NETLINK_CB(skb).sessionid = audit_get_sessionid(current); + security_task_getsecid(current, &(NETLINK_CB(skb).sid)); memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); /* What can I do? Netlink is asynchronous, so that @@ -1237,7 +1333,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, */ err = -EFAULT; - if (memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len)) { + if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { kfree_skb(skb); goto out; } @@ -1268,7 +1364,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, struct netlink_sock *nlk = nlk_sk(sk); int noblock = flags&MSG_DONTWAIT; size_t copied; - struct sk_buff *skb; + struct sk_buff *skb, *frag __maybe_unused = NULL; int err; if (flags&MSG_OOB) @@ -1276,10 +1372,39 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, copied = 0; - skb = skb_recv_datagram(sk,flags,noblock,&err); - if (skb==NULL) + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (skb == NULL) goto out; +#ifdef CONFIG_COMPAT_NETLINK_MESSAGES + if (unlikely(skb_shinfo(skb)->frag_list)) { + bool need_compat = !!(flags & MSG_CMSG_COMPAT); + + /* + * If this skb has a frag_list, then here that means that + * we will have to use the frag_list skb for compat tasks + * and the regular skb for non-compat tasks. + * + * The skb might (and likely will) be cloned, so we can't + * just reset frag_list and go on with things -- we need to + * keep that. For the compat case that's easy -- simply get + * a reference to the compat skb and free the regular one + * including the frag. For the non-compat case, we need to + * avoid sending the frag to the user -- so assign NULL but + * restore it below before freeing the skb. + */ + if (need_compat) { + struct sk_buff *compskb = skb_shinfo(skb)->frag_list; + skb_get(compskb); + kfree_skb(skb); + skb = compskb; + } else { + frag = skb_shinfo(skb)->frag_list; + skb_shinfo(skb)->frag_list = NULL; + } + } +#endif + msg->msg_namelen = 0; copied = skb->len; @@ -1292,7 +1417,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, 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; + 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; @@ -1310,6 +1435,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, siocb->scm->creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = skb->len; + +#ifdef CONFIG_COMPAT_NETLINK_MESSAGES + skb_shinfo(skb)->frag_list = frag; +#endif + skb_free_datagram(sk, skb); if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) @@ -1344,23 +1474,32 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, BUG_ON(!nl_table); - if (unit<0 || unit>=MAX_LINKS) + if (unit < 0 || unit >= MAX_LINKS) return NULL; if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; - if (__netlink_create(net, sock, cb_mutex, unit) < 0) - goto out_sock_release; + /* + * We have to just have a reference on the net from sk, but don't + * get_net it. Besides, we cannot get and then put the net here. + * So we create one inside init_net and the move it to net. + */ + + if (__netlink_create(&init_net, sock, cb_mutex, unit) < 0) + goto out_sock_release_nosk; + + sk = sock->sk; + sk_change_net(sk, net); if (groups < 32) groups = 32; - listeners = kzalloc(NLGRPSZ(groups), GFP_KERNEL); + listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head), + GFP_KERNEL); if (!listeners) goto out_sock_release; - sk = sock->sk; sk->sk_data_ready = netlink_data_ready; if (input) nlk_sk(sk)->netlink_rcv = input; @@ -1380,16 +1519,73 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, nl_table[unit].registered = 1; } else { kfree(listeners); + nl_table[unit].registered++; } netlink_table_ungrab(); - return sk; out_sock_release: kfree(listeners); + netlink_kernel_release(sk); + return NULL; + +out_sock_release_nosk: sock_release(sock); return NULL; } +EXPORT_SYMBOL(netlink_kernel_create); + + +void +netlink_kernel_release(struct sock *sk) +{ + sk_release_kernel(sk); +} +EXPORT_SYMBOL(netlink_kernel_release); + + +static void netlink_free_old_listeners(struct rcu_head *rcu_head) +{ + struct listeners_rcu_head *lrh; + + lrh = container_of(rcu_head, struct listeners_rcu_head, rcu_head); + kfree(lrh->ptr); +} + +int __netlink_change_ngroups(struct sock *sk, unsigned int groups) +{ + unsigned long *listeners, *old = NULL; + struct listeners_rcu_head *old_rcu_head; + struct netlink_table *tbl = &nl_table[sk->sk_protocol]; + + if (groups < 32) + groups = 32; + + if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { + listeners = kzalloc(NLGRPSZ(groups) + + sizeof(struct listeners_rcu_head), + GFP_ATOMIC); + if (!listeners) + return -ENOMEM; + old = tbl->listeners; + memcpy(listeners, old, NLGRPSZ(tbl->groups)); + rcu_assign_pointer(tbl->listeners, listeners); + /* + * Free the old memory after an RCU grace period so we + * don't leak it. We use call_rcu() here in order to be + * able to call this function from atomic contexts. The + * allocation of this memory will have reserved enough + * space for struct listeners_rcu_head at the end. + */ + old_rcu_head = (void *)(tbl->listeners + + NLGRPLONGS(tbl->groups)); + old_rcu_head->ptr = old; + call_rcu(&old_rcu_head->rcu_head, netlink_free_old_listeners); + } + tbl->groups = groups; + + return 0; +} /** * netlink_change_ngroups - change number of multicast groups @@ -1405,33 +1601,24 @@ out_sock_release: */ 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; + int err; 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: + err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); - synchronize_rcu(); - kfree(old); + return err; } -EXPORT_SYMBOL(netlink_change_ngroups); + +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]; + + sk_for_each_bound(sk, node, &tbl->mc_list) + netlink_update_socket_mc(nlk_sk(sk), group, 0); +} /** * netlink_clear_multicast_users - kick off multicast listeners @@ -1443,29 +1630,21 @@ EXPORT_SYMBOL(netlink_change_ngroups); */ 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_clear_multicast_users(ksk, group); netlink_table_ungrab(); } -EXPORT_SYMBOL(netlink_clear_multicast_users); void netlink_set_nonroot(int protocol, unsigned int flags) { if ((unsigned int)protocol < MAX_LINKS) nl_table[protocol].nl_nonroot = flags; } +EXPORT_SYMBOL(netlink_set_nonroot); static void netlink_destroy_callback(struct netlink_callback *cb) { - if (cb->skb) - kfree_skb(cb->skb); + kfree_skb(cb->skb); kfree(cb); } @@ -1498,8 +1677,13 @@ static int netlink_dump(struct sock *sk) if (len > 0) { mutex_unlock(nlk->cb_mutex); - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, len); + + if (sk_filter(sk, skb)) + kfree_skb(skb); + else { + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + } return 0; } @@ -1509,8 +1693,12 @@ static int netlink_dump(struct sock *sk) memcpy(nlmsg_data(nlh), &len, sizeof(len)); - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + if (sk_filter(sk, skb)) + kfree_skb(skb); + else { + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); + } if (cb->done) cb->done(cb); @@ -1528,9 +1716,10 @@ errout: } 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*)) + const struct nlmsghdr *nlh, + int (*dump)(struct sk_buff *skb, + struct netlink_callback *), + int (*done)(struct netlink_callback *)) { struct netlink_callback *cb; struct sock *sk; @@ -1546,7 +1735,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, atomic_inc(&skb->users); cb->skb = skb; - sk = netlink_lookup(ssk->sk_net, ssk->sk_protocol, NETLINK_CB(skb).pid); + sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).pid); if (sk == NULL) { netlink_destroy_callback(cb); return -ECONNREFUSED; @@ -1565,8 +1754,13 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, netlink_dump(sk); sock_put(sk); - return 0; + + /* We successfully started a dump, by returning -EINTR we + * signal not to send ACK even if it was requested. + */ + return -EINTR; } +EXPORT_SYMBOL(netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) { @@ -1583,7 +1777,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) if (!skb) { struct sock *sk; - sk = netlink_lookup(in_skb->sk->sk_net, + sk = netlink_lookup(sock_net(in_skb->sk), in_skb->sk->sk_protocol, NETLINK_CB(in_skb).pid); if (sk) { @@ -1595,12 +1789,13 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) } rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, - NLMSG_ERROR, sizeof(struct nlmsgerr), 0); + NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = err; memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh)); netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); } +EXPORT_SYMBOL(netlink_ack); int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *)) @@ -1619,18 +1814,22 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) - goto skip; + goto ack; /* Skip control messages */ if (nlh->nlmsg_type < NLMSG_MIN_TYPE) - goto skip; + goto ack; err = cb(skb, nlh); -skip: + if (err == -EINTR) + goto skip; + +ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) netlink_ack(skb, nlh, err); - msglen = NLMSG_ALIGN(nlh->nlmsg_len); +skip: + msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); @@ -1638,6 +1837,7 @@ skip: return 0; } +EXPORT_SYMBOL(netlink_rcv_skb); /** * nlmsg_notify - send a notification netlink message @@ -1661,19 +1861,26 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid, exclude_pid = pid; } - /* errors reported via destination sk->sk_err */ - nlmsg_multicast(sk, skb, exclude_pid, group, flags); + /* errors reported via destination sk->sk_err, but propagate + * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ + err = nlmsg_multicast(sk, skb, exclude_pid, group, flags); } - if (report) - err = nlmsg_unicast(sk, skb, pid); + if (report) { + int err2; + + err2 = nlmsg_unicast(sk, skb, pid); + if (!err || err == -ESRCH) + err = err2; + } return err; } +EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { - struct net *net; + struct seq_net_private p; int link; int hash_idx; }; @@ -1686,12 +1893,12 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) struct hlist_node *node; loff_t off = 0; - for (i=0; imask; j++) { sk_for_each(s, node, &hash->table[j]) { - if (iter->net != s->sk_net) + if (sock_net(s) != seq_file_net(seq)) continue; if (off == pos) { iter->link = i; @@ -1706,6 +1913,7 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) } static void *netlink_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(nl_table_lock) { read_lock(&nl_table_lock); return *pos ? netlink_seq_socket_idx(seq, *pos - 1) : SEQ_START_TOKEN; @@ -1726,7 +1934,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) s = v; do { s = sk_next(s); - } while (s && (iter->net != s->sk_net)); + } while (s && sock_net(s) != seq_file_net(seq)); if (s) return s; @@ -1738,7 +1946,7 @@ 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 && (iter->net != s->sk_net)) + while (s && sock_net(s) != seq_file_net(seq)) s = sk_next(s); if (s) { iter->link = i; @@ -1754,6 +1962,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void netlink_seq_stop(struct seq_file *seq, void *v) + __releases(nl_table_lock) { read_unlock(&nl_table_lock); } @@ -1764,20 +1973,21 @@ static int netlink_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) seq_puts(seq, "sk Eth Pid Groups " - "Rmem Wmem Dump Locks\n"); + "Rmem Wmem Dump Locks Drops\n"); else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %d\n", + seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d\n", s, s->sk_protocol, nlk->pid, nlk->groups ? (u32)nlk->groups[0] : 0, - atomic_read(&s->sk_rmem_alloc), - atomic_read(&s->sk_wmem_alloc), + sk_rmem_alloc_get(s), + sk_wmem_alloc_get(s), nlk->cb, - atomic_read(&s->sk_refcnt) + atomic_read(&s->sk_refcnt), + atomic_read(&s->sk_drops) ); } @@ -1794,27 +2004,8 @@ static const struct seq_operations netlink_seq_ops = { static int netlink_seq_open(struct inode *inode, struct file *file) { - struct nl_seq_iter *iter; - - iter = __seq_open_private(file, &netlink_seq_ops, sizeof(*iter)); - if (!iter) - return -ENOMEM; - - iter->net = get_proc_net(inode); - if (!iter->net) { - seq_release_private(inode, file); - return -ENXIO; - } - - return 0; -} - -static int netlink_seq_release(struct inode *inode, struct file *file) -{ - struct seq_file *seq = file->private_data; - struct nl_seq_iter *iter = seq->private; - put_net(iter->net); - return seq_release_private(inode, file); + return seq_open_net(inode, file, &netlink_seq_ops, + sizeof(struct nl_seq_iter)); } static const struct file_operations netlink_seq_fops = { @@ -1822,7 +2013,7 @@ static const struct file_operations netlink_seq_fops = { .open = netlink_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = netlink_seq_release, + .release = seq_release_net, }; #endif @@ -1831,11 +2022,13 @@ int netlink_register_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&netlink_chain, nb); } +EXPORT_SYMBOL(netlink_register_notifier); int netlink_unregister_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&netlink_chain, nb); } +EXPORT_SYMBOL(netlink_unregister_notifier); static const struct proto_ops netlink_ops = { .family = PF_NETLINK, @@ -1858,7 +2051,7 @@ static const struct proto_ops netlink_ops = { .sendpage = sock_no_sendpage, }; -static struct net_proto_family netlink_family_ops = { +static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ @@ -1902,10 +2095,10 @@ static int __init netlink_proto_init(void) if (!nl_table) goto panic; - if (num_physpages >= (128 * 1024)) - limit = num_physpages >> (21 - PAGE_SHIFT); + if (totalram_pages >= (128 * 1024)) + limit = totalram_pages >> (21 - PAGE_SHIFT); else - limit = num_physpages >> (23 - PAGE_SHIFT); + limit = totalram_pages >> (23 - PAGE_SHIFT); order = get_bitmask_order(limit) - 1 + PAGE_SHIFT; limit = (1UL << order) / sizeof(struct hlist_head); @@ -1914,7 +2107,7 @@ static int __init netlink_proto_init(void) for (i = 0; i < MAX_LINKS; i++) { struct nl_pid_hash *hash = &nl_table[i].hash; - hash->table = nl_pid_hash_alloc(1 * sizeof(*hash->table)); + hash->table = nl_pid_hash_zalloc(1 * sizeof(*hash->table)); if (!hash->table) { while (i-- > 0) nl_pid_hash_free(nl_table[i].hash.table, @@ -1922,7 +2115,6 @@ static int __init netlink_proto_init(void) kfree(nl_table); goto panic; } - memset(hash->table, 0, 1 * sizeof(*hash->table)); hash->max_shift = order; hash->shift = 0; hash->mask = 0; @@ -1940,14 +2132,3 @@ panic: } core_initcall(netlink_proto_init); - -EXPORT_SYMBOL(netlink_ack); -EXPORT_SYMBOL(netlink_rcv_skb); -EXPORT_SYMBOL(netlink_broadcast); -EXPORT_SYMBOL(netlink_dump_start); -EXPORT_SYMBOL(netlink_kernel_create); -EXPORT_SYMBOL(netlink_register_notifier); -EXPORT_SYMBOL(netlink_set_nonroot); -EXPORT_SYMBOL(netlink_unicast); -EXPORT_SYMBOL(netlink_unregister_notifier); -EXPORT_SYMBOL(nlmsg_notify);