diff options
Diffstat (limited to 'net/netlink')
| -rw-r--r-- | net/netlink/Kconfig | 19 | ||||
| -rw-r--r-- | net/netlink/Makefile | 8 | ||||
| -rw-r--r-- | net/netlink/af_netlink.c | 3184 | ||||
| -rw-r--r-- | net/netlink/af_netlink.h | 79 | ||||
| -rw-r--r-- | net/netlink/diag.c | 238 | ||||
| -rw-r--r-- | net/netlink/genetlink.c | 1154 |
6 files changed, 4682 insertions, 0 deletions
diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig new file mode 100644 index 000000000..2c5e95e9b --- /dev/null +++ b/net/netlink/Kconfig @@ -0,0 +1,19 @@ +# +# Netlink Sockets +# + +config NETLINK_MMAP + bool "NETLINK: mmaped IO" + ---help--- + This option enables support for memory mapped netlink IO. This + reduces overhead by avoiding copying data between kernel- and + userspace. + + If unsure, say N. + +config NETLINK_DIAG + tristate "NETLINK: socket monitoring interface" + default n + ---help--- + Support for NETLINK socket monitoring interface used by the ss tool. + If unsure, say Y. diff --git a/net/netlink/Makefile b/net/netlink/Makefile new file mode 100644 index 000000000..e837917f6 --- /dev/null +++ b/net/netlink/Makefile @@ -0,0 +1,8 @@ +# +# Makefile for the netlink driver. +# + +obj-y := af_netlink.o genetlink.o + +obj-$(CONFIG_NETLINK_DIAG) += netlink_diag.o +netlink_diag-y := diag.o diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c new file mode 100644 index 000000000..bf6e76643 --- /dev/null +++ b/net/netlink/af_netlink.c @@ -0,0 +1,3184 @@ +/* + * NETLINK Kernel-user communication protocol. + * + * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> + * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> + * Patrick McHardy <kaber@trash.net> + * + * 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) + * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> + * - inc module use count of module that owns + * the kernel socket in case userspace opens + * socket of same protocol + * - remove all module support, since netlink is + * mandatory if CONFIG_NET=y these days + */ + +#include <linux/module.h> + +#include <linux/capability.h> +#include <linux/kernel.h> +#include <linux/init.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/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 <linux/audit.h> +#include <linux/mutex.h> +#include <linux/vmalloc.h> +#include <linux/if_arp.h> +#include <linux/rhashtable.h> +#include <asm/cacheflush.h> +#include <linux/hash.h> +#include <linux/genetlink.h> + +#include <net/net_namespace.h> +#include <net/sock.h> +#include <net/scm.h> +#include <net/netlink.h> + +#include "af_netlink.h" + +struct listeners { + struct rcu_head rcu; + unsigned long masks[0]; +}; + +/* state bits */ +#define NETLINK_CONGESTED 0x0 + +/* flags */ +#define NETLINK_KERNEL_SOCKET 0x1 +#define NETLINK_RECV_PKTINFO 0x2 +#define NETLINK_BROADCAST_SEND_ERROR 0x4 +#define NETLINK_RECV_NO_ENOBUFS 0x8 + +static inline int netlink_is_kernel(struct sock *sk) +{ + return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET; +} + +struct netlink_table *nl_table __read_mostly; +EXPORT_SYMBOL_GPL(nl_table); + +static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); + +static int netlink_dump(struct sock *sk); +static void netlink_skb_destructor(struct sk_buff *skb); + +/* nl_table locking explained: + * Lookup and traversal are protected with an RCU read-side lock. Insertion + * and removal are protected with per bucket lock while using RCU list + * modification primitives and may run in parallel to RCU protected lookups. + * Destruction of the Netlink socket may only occur *after* nl_table_lock has + * been acquired * either during or after the socket has been removed from + * the list and after an RCU grace period. + */ +DEFINE_RWLOCK(nl_table_lock); +EXPORT_SYMBOL_GPL(nl_table_lock); +static atomic_t nl_table_users = ATOMIC_INIT(0); + +#define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); + +static ATOMIC_NOTIFIER_HEAD(netlink_chain); + +static DEFINE_SPINLOCK(netlink_tap_lock); +static struct list_head netlink_tap_all __read_mostly; + +static const struct rhashtable_params netlink_rhashtable_params; + +static inline u32 netlink_group_mask(u32 group) +{ + return group ? 1 << (group - 1) : 0; +} + +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); + + __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; + + /* 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: + return true; + } + + return false; +} + +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; + skb_reset_network_header(nskb); + 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); + + if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) { + if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) { + sk->sk_err = ENOBUFS; + sk->sk_error_report(sk); + } + } + atomic_inc(&sk->sk_drops); +} + +static void netlink_rcv_wake(struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (skb_queue_empty(&sk->sk_receive_queue)) + clear_bit(NETLINK_CONGESTED, &nlk->state); + if (!test_bit(NETLINK_CONGESTED, &nlk->state)) + wake_up_interruptible(&nlk->wait); +} + +#ifdef CONFIG_NETLINK_MMAP +static bool netlink_skb_is_mmaped(const struct sk_buff *skb) +{ + return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; +} + +static bool netlink_rx_is_mmaped(struct sock *sk) +{ + return nlk_sk(sk)->rx_ring.pg_vec != NULL; +} + +static bool netlink_tx_is_mmaped(struct sock *sk) +{ + return nlk_sk(sk)->tx_ring.pg_vec != NULL; +} + +static __pure struct page *pgvec_to_page(const void *addr) +{ + if (is_vmalloc_addr(addr)) + return vmalloc_to_page(addr); + else + return virt_to_page(addr); +} + +static void free_pg_vec(void **pg_vec, unsigned int order, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len; i++) { + if (pg_vec[i] != NULL) { + if (is_vmalloc_addr(pg_vec[i])) + vfree(pg_vec[i]); + else + free_pages((unsigned long)pg_vec[i], order); + } + } + kfree(pg_vec); +} + +static void *alloc_one_pg_vec_page(unsigned long order) +{ + void *buffer; + gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | + __GFP_NOWARN | __GFP_NORETRY; + + buffer = (void *)__get_free_pages(gfp_flags, order); + if (buffer != NULL) + return buffer; + + buffer = vzalloc((1 << order) * PAGE_SIZE); + if (buffer != NULL) + return buffer; + + gfp_flags &= ~__GFP_NORETRY; + return (void *)__get_free_pages(gfp_flags, order); +} + +static void **alloc_pg_vec(struct netlink_sock *nlk, + struct nl_mmap_req *req, unsigned int order) +{ + unsigned int block_nr = req->nm_block_nr; + unsigned int i; + 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] = alloc_one_pg_vec_page(order); + if (pg_vec[i] == NULL) + goto err1; + } + + return pg_vec; +err1: + free_pg_vec(pg_vec, order, block_nr); + return NULL; +} + +static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, + bool closing, bool tx_ring) +{ + struct netlink_sock *nlk = nlk_sk(sk); + struct netlink_ring *ring; + struct sk_buff_head *queue; + void **pg_vec = NULL; + unsigned int order = 0; + int err; + + ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring; + queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; + + if (!closing) { + if (atomic_read(&nlk->mapped)) + return -EBUSY; + if (atomic_read(&ring->pending)) + return -EBUSY; + } + + if (req->nm_block_nr) { + if (ring->pg_vec != NULL) + return -EBUSY; + + if ((int)req->nm_block_size <= 0) + return -EINVAL; + if (!PAGE_ALIGNED(req->nm_block_size)) + return -EINVAL; + if (req->nm_frame_size < NL_MMAP_HDRLEN) + return -EINVAL; + if (!IS_ALIGNED(req->nm_frame_size, NL_MMAP_MSG_ALIGNMENT)) + return -EINVAL; + + ring->frames_per_block = req->nm_block_size / + req->nm_frame_size; + if (ring->frames_per_block == 0) + return -EINVAL; + if (ring->frames_per_block * req->nm_block_nr != + req->nm_frame_nr) + return -EINVAL; + + order = get_order(req->nm_block_size); + pg_vec = alloc_pg_vec(nlk, req, order); + if (pg_vec == NULL) + return -ENOMEM; + } else { + if (req->nm_frame_nr) + return -EINVAL; + } + + err = -EBUSY; + mutex_lock(&nlk->pg_vec_lock); + if (closing || atomic_read(&nlk->mapped) == 0) { + err = 0; + spin_lock_bh(&queue->lock); + + ring->frame_max = req->nm_frame_nr - 1; + ring->head = 0; + ring->frame_size = req->nm_frame_size; + ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE; + + swap(ring->pg_vec_len, req->nm_block_nr); + swap(ring->pg_vec_order, order); + swap(ring->pg_vec, pg_vec); + + __skb_queue_purge(queue); + spin_unlock_bh(&queue->lock); + + WARN_ON(atomic_read(&nlk->mapped)); + } + mutex_unlock(&nlk->pg_vec_lock); + + if (pg_vec) + free_pg_vec(pg_vec, order, req->nm_block_nr); + return err; +} + +static void netlink_mm_open(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct socket *sock = file->private_data; + struct sock *sk = sock->sk; + + if (sk) + atomic_inc(&nlk_sk(sk)->mapped); +} + +static void netlink_mm_close(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct socket *sock = file->private_data; + struct sock *sk = sock->sk; + + if (sk) + atomic_dec(&nlk_sk(sk)->mapped); +} + +static const struct vm_operations_struct netlink_mmap_ops = { + .open = netlink_mm_open, + .close = netlink_mm_close, +}; + +static int netlink_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + struct netlink_ring *ring; + unsigned long start, size, expected; + unsigned int i; + int err = -EINVAL; + + if (vma->vm_pgoff) + return -EINVAL; + + mutex_lock(&nlk->pg_vec_lock); + + expected = 0; + for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) { + if (ring->pg_vec == NULL) + continue; + expected += ring->pg_vec_len * ring->pg_vec_pages * PAGE_SIZE; + } + + if (expected == 0) + goto out; + + size = vma->vm_end - vma->vm_start; + if (size != expected) + goto out; + + start = vma->vm_start; + for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) { + if (ring->pg_vec == NULL) + continue; + + for (i = 0; i < ring->pg_vec_len; i++) { + struct page *page; + void *kaddr = ring->pg_vec[i]; + unsigned int pg_num; + + for (pg_num = 0; pg_num < ring->pg_vec_pages; pg_num++) { + page = pgvec_to_page(kaddr); + err = vm_insert_page(vma, start, page); + if (err < 0) + goto out; + start += PAGE_SIZE; + kaddr += PAGE_SIZE; + } + } + } + + atomic_inc(&nlk->mapped); + vma->vm_ops = &netlink_mmap_ops; + err = 0; +out: + mutex_unlock(&nlk->pg_vec_lock); + return err; +} + +static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len) +{ +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 + struct page *p_start, *p_end; + + /* First page is flushed through netlink_{get,set}_status */ + p_start = pgvec_to_page(hdr + PAGE_SIZE); + p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1); + while (p_start <= p_end) { + flush_dcache_page(p_start); + p_start++; + } +#endif +} + +static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr) +{ + smp_rmb(); + flush_dcache_page(pgvec_to_page(hdr)); + return hdr->nm_status; +} + +static void netlink_set_status(struct nl_mmap_hdr *hdr, + enum nl_mmap_status status) +{ + smp_mb(); + hdr->nm_status = status; + flush_dcache_page(pgvec_to_page(hdr)); +} + +static struct nl_mmap_hdr * +__netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos) +{ + unsigned int pg_vec_pos, frame_off; + + pg_vec_pos = pos / ring->frames_per_block; + frame_off = pos % ring->frames_per_block; + + return ring->pg_vec[pg_vec_pos] + (frame_off * ring->frame_size); +} + +static struct nl_mmap_hdr * +netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos, + enum nl_mmap_status status) +{ + struct nl_mmap_hdr *hdr; + + hdr = __netlink_lookup_frame(ring, pos); + if (netlink_get_status(hdr) != status) + return NULL; + + return hdr; +} + +static struct nl_mmap_hdr * +netlink_current_frame(const struct netlink_ring *ring, + enum nl_mmap_status status) +{ + return netlink_lookup_frame(ring, ring->head, status); +} + +static struct nl_mmap_hdr * +netlink_previous_frame(const struct netlink_ring *ring, + enum nl_mmap_status status) +{ + unsigned int prev; + + prev = ring->head ? ring->head - 1 : ring->frame_max; + return netlink_lookup_frame(ring, prev, status); +} + +static void netlink_increment_head(struct netlink_ring *ring) +{ + ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0; +} + +static void netlink_forward_ring(struct netlink_ring *ring) +{ + unsigned int head = ring->head, pos = head; + const struct nl_mmap_hdr *hdr; + + do { + hdr = __netlink_lookup_frame(ring, pos); + if (hdr->nm_status == NL_MMAP_STATUS_UNUSED) + break; + if (hdr->nm_status != NL_MMAP_STATUS_SKIP) + break; + netlink_increment_head(ring); + } while (ring->head != head); +} + +static bool netlink_dump_space(struct netlink_sock *nlk) +{ + struct netlink_ring *ring = &nlk->rx_ring; + struct nl_mmap_hdr *hdr; + unsigned int n; + + hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); + if (hdr == NULL) + return false; + + n = ring->head + ring->frame_max / 2; + if (n > ring->frame_max) + n -= ring->frame_max; + + hdr = __netlink_lookup_frame(ring, n); + + return hdr->nm_status == NL_MMAP_STATUS_UNUSED; +} + +static unsigned int netlink_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + unsigned int mask; + int err; + + if (nlk->rx_ring.pg_vec != NULL) { + /* Memory mapped sockets don't call recvmsg(), so flow control + * for dumps is performed here. A dump is allowed to continue + * if at least half the ring is unused. + */ + while (nlk->cb_running && netlink_dump_space(nlk)) { + err = netlink_dump(sk); + if (err < 0) { + sk->sk_err = -err; + sk->sk_error_report(sk); + break; + } + } + netlink_rcv_wake(sk); + } + + mask = datagram_poll(file, sock, wait); + + spin_lock_bh(&sk->sk_receive_queue.lock); + if (nlk->rx_ring.pg_vec) { + netlink_forward_ring(&nlk->rx_ring); + if (!netlink_previous_frame(&nlk->rx_ring, NL_MMAP_STATUS_UNUSED)) + mask |= POLLIN | POLLRDNORM; + } + spin_unlock_bh(&sk->sk_receive_queue.lock); + + spin_lock_bh(&sk->sk_write_queue.lock); + if (nlk->tx_ring.pg_vec) { + if (netlink_current_frame(&nlk->tx_ring, NL_MMAP_STATUS_UNUSED)) + mask |= POLLOUT | POLLWRNORM; + } + spin_unlock_bh(&sk->sk_write_queue.lock); + + return mask; +} + +static struct nl_mmap_hdr *netlink_mmap_hdr(struct sk_buff *skb) +{ + return (struct nl_mmap_hdr *)(skb->head - NL_MMAP_HDRLEN); +} + +static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk, + struct netlink_ring *ring, + struct nl_mmap_hdr *hdr) +{ + unsigned int size; + void *data; + + size = ring->frame_size - NL_MMAP_HDRLEN; + data = (void *)hdr + NL_MMAP_HDRLEN; + + skb->head = data; + skb->data = data; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; + skb->len = 0; + + skb->destructor = netlink_skb_destructor; + NETLINK_CB(skb).flags |= NETLINK_SKB_MMAPED; + NETLINK_CB(skb).sk = sk; +} + +static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, + u32 dst_portid, u32 dst_group, + struct scm_cookie *scm) +{ + struct netlink_sock *nlk = nlk_sk(sk); + struct netlink_ring *ring; + struct nl_mmap_hdr *hdr; + struct sk_buff *skb; + unsigned int maxlen; + int err = 0, len = 0; + + mutex_lock(&nlk->pg_vec_lock); + + ring = &nlk->tx_ring; + maxlen = ring->frame_size - NL_MMAP_HDRLEN; + + do { + unsigned int nm_len; + + hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID); + if (hdr == NULL) { + if (!(msg->msg_flags & MSG_DONTWAIT) && + atomic_read(&nlk->tx_ring.pending)) + schedule(); + continue; + } + + nm_len = ACCESS_ONCE(hdr->nm_len); + if (nm_len > maxlen) { + err = -EINVAL; + goto out; + } + + netlink_frame_flush_dcache(hdr, nm_len); + + skb = alloc_skb(nm_len, GFP_KERNEL); + if (skb == NULL) { + err = -ENOBUFS; + goto out; + } + __skb_put(skb, nm_len); + memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len); + netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); + + netlink_increment_head(ring); + + NETLINK_CB(skb).portid = nlk->portid; + NETLINK_CB(skb).dst_group = dst_group; + NETLINK_CB(skb).creds = scm->creds; + + err = security_netlink_send(sk, skb); + if (err) { + kfree_skb(skb); + goto out; + } + + if (unlikely(dst_group)) { + atomic_inc(&skb->users); + netlink_broadcast(sk, skb, dst_portid, dst_group, + GFP_KERNEL); + } + err = netlink_unicast(sk, skb, dst_portid, + msg->msg_flags & MSG_DONTWAIT); + if (err < 0) + goto out; + len += err; + + } while (hdr != NULL || + (!(msg->msg_flags & MSG_DONTWAIT) && + atomic_read(&nlk->tx_ring.pending))); + + if (len > 0) + err = len; +out: + mutex_unlock(&nlk->pg_vec_lock); + return err; +} + +static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb) +{ + struct nl_mmap_hdr *hdr; + + hdr = netlink_mmap_hdr(skb); + hdr->nm_len = skb->len; + hdr->nm_group = NETLINK_CB(skb).dst_group; + hdr->nm_pid = NETLINK_CB(skb).creds.pid; + hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); + hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); + netlink_frame_flush_dcache(hdr, hdr->nm_len); + netlink_set_status(hdr, NL_MMAP_STATUS_VALID); + + NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED; + kfree_skb(skb); +} + +static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb) +{ + struct netlink_sock *nlk = nlk_sk(sk); + struct netlink_ring *ring = &nlk->rx_ring; + struct nl_mmap_hdr *hdr; + + spin_lock_bh(&sk->sk_receive_queue.lock); + hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); + if (hdr == NULL) { + spin_unlock_bh(&sk->sk_receive_queue.lock); + kfree_skb(skb); + netlink_overrun(sk); + return; + } + netlink_increment_head(ring); + __skb_queue_tail(&sk->sk_receive_queue, skb); + spin_unlock_bh(&sk->sk_receive_queue.lock); + + hdr->nm_len = skb->len; + hdr->nm_group = NETLINK_CB(skb).dst_group; + hdr->nm_pid = NETLINK_CB(skb).creds.pid; + hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); + hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); + netlink_set_status(hdr, NL_MMAP_STATUS_COPY); +} + +#else /* CONFIG_NETLINK_MMAP */ +#define netlink_skb_is_mmaped(skb) false +#define netlink_rx_is_mmaped(sk) false +#define netlink_tx_is_mmaped(sk) false +#define netlink_mmap sock_no_mmap +#define netlink_poll datagram_poll +#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm) 0 +#endif /* CONFIG_NETLINK_MMAP */ + +static void netlink_skb_destructor(struct sk_buff *skb) +{ +#ifdef CONFIG_NETLINK_MMAP + struct nl_mmap_hdr *hdr; + struct netlink_ring *ring; + struct sock *sk; + + /* If a packet from the kernel to userspace was freed because of an + * error without being delivered to userspace, the kernel must reset + * the status. In the direction userspace to kernel, the status is + * always reset here after the packet was processed and freed. + */ + if (netlink_skb_is_mmaped(skb)) { + hdr = netlink_mmap_hdr(skb); + sk = NETLINK_CB(skb).sk; + + if (NETLINK_CB(skb).flags & NETLINK_SKB_TX) { + netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); + ring = &nlk_sk(sk)->tx_ring; + } else { + if (!(NETLINK_CB(skb).flags & NETLINK_SKB_DELIVERED)) { + hdr->nm_len = 0; + netlink_set_status(hdr, NL_MMAP_STATUS_VALID); + } + ring = &nlk_sk(sk)->rx_ring; + } + + WARN_ON(atomic_read(&ring->pending) == 0); + atomic_dec(&ring->pending); + sock_put(sk); + + skb->head = NULL; + } +#endif + if (is_vmalloc_addr(skb->head)) { + if (!skb->cloned || + !atomic_dec_return(&(skb_shinfo(skb)->dataref))) + vfree(skb->head); + + skb->head = NULL; + } + if (skb->sk != NULL) + sock_rfree(skb); +} + +static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) +{ + WARN_ON(skb->sk != NULL); + skb->sk = sk; + skb->destructor = netlink_skb_destructor; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_charge(sk, skb->truesize); +} + +static void netlink_sock_destruct(struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (nlk->cb_running) { + if (nlk->cb.done) + nlk->cb.done(&nlk->cb); + + module_put(nlk->cb.module); + kfree_skb(nlk->cb.skb); + } + + skb_queue_purge(&sk->sk_receive_queue); +#ifdef CONFIG_NETLINK_MMAP + if (1) { + struct nl_mmap_req req; + + memset(&req, 0, sizeof(req)); + if (nlk->rx_ring.pg_vec) + netlink_set_ring(sk, &req, true, false); + memset(&req, 0, sizeof(req)); + if (nlk->tx_ring.pg_vec) + netlink_set_ring(sk, &req, true, true); + } +#endif /* CONFIG_NETLINK_MMAP */ + + if (!sock_flag(sk, SOCK_DEAD)) { + printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); + return; + } + + 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 + * immediately hit write lock and grab all the cpus. Exclusive sleep solves + * this, _but_ remember, it adds useless work on UP machines. + */ + +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 (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (atomic_read(&nl_table_users) == 0) + break; + write_unlock_irq(&nl_table_lock); + schedule(); + write_lock_irq(&nl_table_lock); + } + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nl_table_wait, &wait); + } +} + +void netlink_table_ungrab(void) + __releases(nl_table_lock) +{ + write_unlock_irq(&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); +} + +struct netlink_compare_arg +{ + possible_net_t pnet; + u32 portid; +}; + +/* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ +#define netlink_compare_arg_len \ + (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) + +static inline int netlink_compare(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct netlink_compare_arg *x = arg->key; + const struct netlink_sock *nlk = ptr; + + return nlk->portid != x->portid || + !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); +} + +static void netlink_compare_arg_init(struct netlink_compare_arg *arg, + struct net *net, u32 portid) +{ + memset(arg, 0, sizeof(*arg)); + write_pnet(&arg->pnet, net); + arg->portid = portid; +} + +static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, + struct net *net) +{ + struct netlink_compare_arg arg; + + netlink_compare_arg_init(&arg, net, portid); + return rhashtable_lookup_fast(&table->hash, &arg, + netlink_rhashtable_params); +} + +static int __netlink_insert(struct netlink_table *table, struct sock *sk) +{ + struct netlink_compare_arg arg; + + netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); + return rhashtable_lookup_insert_key(&table->hash, &arg, + &nlk_sk(sk)->node, + netlink_rhashtable_params); +} + +static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) +{ + struct netlink_table *table = &nl_table[protocol]; + struct sock *sk; + + rcu_read_lock(); + sk = __netlink_lookup(table, portid, net); + if (sk) + sock_hold(sk); + rcu_read_unlock(); + + return sk; +} + +static const struct proto_ops netlink_ops; + +static void +netlink_update_listeners(struct sock *sk) +{ + struct netlink_table *tbl = &nl_table[sk->sk_protocol]; + unsigned long mask; + unsigned int i; + struct listeners *listeners; + + listeners = nl_deref_protected(tbl->listeners); + if (!listeners) + return; + + for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { + mask = 0; + sk_for_each_bound(sk, &tbl->mc_list) { + if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) + mask |= nlk_sk(sk)->groups[i]; + } + listeners->masks[i] = mask; + } + /* this function is only called with the netlink table "grabbed", which + * makes sure updates are visible before bind or setsockopt return. */ +} + +static int netlink_insert(struct sock *sk, u32 portid) +{ + struct netlink_table *table = &nl_table[sk->sk_protocol]; + int err; + + lock_sock(sk); + + err = -EBUSY; + if (nlk_sk(sk)->portid) + goto err; + + err = -ENOMEM; + if (BITS_PER_LONG > 32 && + unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) + goto err; + + nlk_sk(sk)->portid = portid; + sock_hold(sk); + + err = __netlink_insert(table, sk); + if (err) { + if (err == -EEXIST) + err = -EADDRINUSE; + nlk_sk(sk)->portid = 0; + sock_put(sk); + } + +err: + release_sock(sk); + return err; +} + +static void netlink_remove(struct sock *sk) +{ + struct netlink_table *table; + + table = &nl_table[sk->sk_protocol]; + if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, + netlink_rhashtable_params)) { + WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + __sock_put(sk); + } + + netlink_table_grab(); + if (nlk_sk(sk)->subscriptions) { + __sk_del_bind_node(sk); + netlink_update_listeners(sk); + } + if (sk->sk_protocol == NETLINK_GENERIC) + atomic_inc(&genl_sk_destructing_cnt); + netlink_table_ungrab(); +} + +static struct proto netlink_proto = { + .name = "NETLINK", + .owner = THIS_MODULE, + .obj_size = sizeof(struct netlink_sock), +}; + +static int __netlink_create(struct net *net, struct socket *sock, + struct mutex *cb_mutex, int protocol) +{ + struct sock *sk; + struct netlink_sock *nlk; + + sock->ops = &netlink_ops; + + sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto); + if (!sk) + return -ENOMEM; + + sock_init_data(sock, sk); + + nlk = nlk_sk(sk); + if (cb_mutex) { + nlk->cb_mutex = cb_mutex; + } else { + nlk->cb_mutex = &nlk->cb_def_mutex; + mutex_init(nlk->cb_mutex); + } + init_waitqueue_head(&nlk->wait); +#ifdef CONFIG_NETLINK_MMAP + mutex_init(&nlk->pg_vec_lock); +#endif + + sk->sk_destruct = netlink_sock_destruct; + sk->sk_protocol = protocol; + return 0; +} + +static int netlink_create(struct net *net, struct socket *sock, int protocol, + int kern) +{ + struct module *module = NULL; + struct mutex *cb_mutex; + struct netlink_sock *nlk; + int (*bind)(struct net *net, int group); + void (*unbind)(struct net *net, int group); + int err = 0; + + sock->state = SS_UNCONNECTED; + + if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) + return -ESOCKTNOSUPPORT; + + if (protocol < 0 || protocol >= MAX_LINKS) + return -EPROTONOSUPPORT; + + netlink_lock_table(); +#ifdef CONFIG_MODULES + if (!nl_table[protocol].registered) { + netlink_unlock_table(); + request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); + netlink_lock_table(); + } +#endif + if (nl_table[protocol].registered && + try_module_get(nl_table[protocol].module)) + module = nl_table[protocol].module; + else + 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) + goto out; + + 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; + nlk->netlink_bind = bind; + nlk->netlink_unbind = unbind; +out: + return err; + +out_module: + module_put(module); + goto out; +} + +static void deferred_put_nlk_sk(struct rcu_head *head) +{ + struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); + + sock_put(&nlk->sk); +} + +static int netlink_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk; + + if (!sk) + return 0; + + netlink_remove(sk); + sock_orphan(sk); + nlk = nlk_sk(sk); + + /* + * OK. Socket is unlinked, any packets that arrive now + * will be purged. + */ + + /* must not acquire netlink_table_lock in any way again before unbind + * and notifying genetlink is done as otherwise it might deadlock + */ + if (nlk->netlink_unbind) { + int i; + + for (i = 0; i < nlk->ngroups; i++) + if (test_bit(i, nlk->groups)) + nlk->netlink_unbind(sock_net(sk), i + 1); + } + if (sk->sk_protocol == NETLINK_GENERIC && + atomic_dec_return(&genl_sk_destructing_cnt) == 0) + wake_up(&genl_sk_destructing_waitq); + + sock->sk = NULL; + wake_up_interruptible_all(&nlk->wait); + + skb_queue_purge(&sk->sk_write_queue); + + if (nlk->portid) { + struct netlink_notify n = { + .net = sock_net(sk), + .protocol = sk->sk_protocol, + .portid = nlk->portid, + }; + atomic_notifier_call_chain(&netlink_chain, + NETLINK_URELEASE, &n); + } + + module_put(nlk->module); + + if (netlink_is_kernel(sk)) { + netlink_table_grab(); + BUG_ON(nl_table[sk->sk_protocol].registered == 0); + if (--nl_table[sk->sk_protocol].registered == 0) { + struct listeners *old; + + old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); + RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); + 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; + } + netlink_table_ungrab(); + } + + kfree(nlk->groups); + nlk->groups = NULL; + + local_bh_disable(); + sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); + local_bh_enable(); + call_rcu(&nlk->rcu, deferred_put_nlk_sk); + return 0; +} + +static int netlink_autobind(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + struct netlink_table *table = &nl_table[sk->sk_protocol]; + s32 portid = task_tgid_vnr(current); + int err; + static s32 rover = -4097; + +retry: + cond_resched(); + rcu_read_lock(); + if (__netlink_lookup(table, portid, net)) { + /* Bind collision, search negative portid values. */ + portid = rover--; + if (rover > -4097) + rover = -4097; + rcu_read_unlock(); + goto retry; + } + rcu_read_unlock(); + + err = netlink_insert(sk, portid); + if (err == -EADDRINUSE) + goto retry; + + /* If 2 threads race to autobind, that is fine. */ + if (err == -EBUSY) + err = 0; + + return err; +} + +/** + * __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); +} + +static void +netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (nlk->subscriptions && !subscriptions) + __sk_del_bind_node(sk); + else if (!nlk->subscriptions && subscriptions) + sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); + nlk->subscriptions = subscriptions; +} + +static int netlink_realloc_groups(struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + unsigned int groups; + unsigned long *new_groups; + int err = 0; + + netlink_table_grab(); + + groups = nl_table[sk->sk_protocol].groups; + if (!nl_table[sk->sk_protocol].registered) { + err = -ENOENT; + goto out_unlock; + } + + if (nlk->ngroups >= groups) + goto out_unlock; + + new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); + if (new_groups == NULL) { + err = -ENOMEM; + goto out_unlock; + } + memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, + NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); + + nlk->groups = new_groups; + nlk->ngroups = groups; + out_unlock: + netlink_table_ungrab(); + return err; +} + +static void netlink_undo_bind(int group, long unsigned int groups, + struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + int undo; + + if (!nlk->netlink_unbind) + return; + + for (undo = 0; undo < group; undo++) + if (test_bit(undo, &groups)) + nlk->netlink_unbind(sock_net(sk), undo + 1); +} + +static int netlink_bind(struct socket *sock, struct sockaddr *addr, + int addr_len) +{ + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + 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; + + if (nladdr->nl_family != AF_NETLINK) + return -EINVAL; + + /* Only superuser is allowed to listen multicasts */ + 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 (nladdr->nl_pid != nlk->portid) + return -EINVAL; + + if (nlk->netlink_bind && groups) { + int group; + + for (group = 0; group < nlk->ngroups; group++) { + if (!test_bit(group, &groups)) + continue; + err = nlk->netlink_bind(net, group + 1); + if (!err) + continue; + netlink_undo_bind(group, groups, sk); + return err; + } + } + + if (!nlk->portid) { + err = nladdr->nl_pid ? + netlink_insert(sk, nladdr->nl_pid) : + netlink_autobind(sock); + if (err) { + netlink_undo_bind(nlk->ngroups, groups, sk); + return err; + } + } + + if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) + return 0; + + netlink_table_grab(); + netlink_update_subscriptions(sk, nlk->subscriptions + + hweight32(groups) - + hweight32(nlk->groups[0])); + nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; + netlink_update_listeners(sk); + 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 (alen < sizeof(addr->sa_family)) + return -EINVAL; + + if (addr->sa_family == AF_UNSPEC) { + sk->sk_state = NETLINK_UNCONNECTED; + nlk->dst_portid = 0; + nlk->dst_group = 0; + return 0; + } + if (addr->sa_family != AF_NETLINK) + return -EINVAL; + + if ((nladdr->nl_groups || nladdr->nl_pid) && + !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) + return -EPERM; + + if (!nlk->portid) + err = netlink_autobind(sock); + + if (err == 0) { + sk->sk_state = NETLINK_CONNECTED; + nlk->dst_portid = nladdr->nl_pid; + nlk->dst_group = ffs(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); + DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); + + nladdr->nl_family = AF_NETLINK; + nladdr->nl_pad = 0; + *addr_len = sizeof(*nladdr); + + if (peer) { + nladdr->nl_pid = nlk->dst_portid; + nladdr->nl_groups = netlink_group_mask(nlk->dst_group); + } else { + nladdr->nl_pid = nlk->portid; + nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; + } + return 0; +} + +static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) +{ + struct sock *sock; + struct netlink_sock *nlk; + + sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); + if (!sock) + return ERR_PTR(-ECONNREFUSED); + + /* Don't bother queuing skb if kernel socket has no input function */ + nlk = nlk_sk(sock); + if (sock->sk_state == NETLINK_CONNECTED && + nlk->dst_portid != nlk_sk(ssk)->portid) { + sock_put(sock); + return ERR_PTR(-ECONNREFUSED); + } + return sock; +} + +struct sock *netlink_getsockbyfilp(struct file *filp) +{ + struct inode *inode = file_inode(filp); + 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; +} + +static struct sk_buff *netlink_alloc_large_skb(unsigned int size, + int broadcast) +{ + struct sk_buff *skb; + void *data; + + if (size <= NLMSG_GOODSIZE || broadcast) + return alloc_skb(size, GFP_KERNEL); + + size = SKB_DATA_ALIGN(size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + data = vmalloc(size); + if (data == NULL) + return NULL; + + skb = __build_skb(data, size); + if (skb == NULL) + vfree(data); + else + skb->destructor = netlink_skb_destructor; + + return skb; +} + +/* + * 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, + long *timeo, struct sock *ssk) +{ + struct netlink_sock *nlk; + + nlk = nlk_sk(sk); + + if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || + test_bit(NETLINK_CONGESTED, &nlk->state)) && + !netlink_skb_is_mmaped(skb)) { + DECLARE_WAITQUEUE(wait, current); + if (!*timeo) { + if (!ssk || netlink_is_kernel(ssk)) + 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(NETLINK_CONGESTED, &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; + } + netlink_skb_set_owner_r(skb, sk); + return 0; +} + +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); + else if (netlink_rx_is_mmaped(sk)) + netlink_ring_set_copied(sk, skb); + else +#endif /* CONFIG_NETLINK_MMAP */ + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk); + return len; +} + +int netlink_sendskb(struct sock *sk, struct sk_buff *skb) +{ + int len = __netlink_sendskb(sk, skb); + + sock_put(sk); + return len; +} + +void netlink_detachskb(struct sock *sk, struct sk_buff *skb) +{ + kfree_skb(skb); + sock_put(sk); +} + +static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) +{ + int delta; + + WARN_ON(skb->sk != NULL); + if (netlink_skb_is_mmaped(skb)) + return skb; + + delta = skb->end - skb->tail; + if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) + return skb; + + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, allocation); + if (!nskb) + return skb; + consume_skb(skb); + skb = nskb; + } + + if (!pskb_expand_head(skb, 0, -delta, allocation)) + skb->truesize -= delta; + + return skb; +} + +static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, + struct sock *ssk) +{ + int ret; + struct netlink_sock *nlk = nlk_sk(sk); + + ret = -ECONNREFUSED; + if (nlk->netlink_rcv != NULL) { + 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 { + kfree_skb(skb); + } + sock_put(sk); + return ret; +} + +int netlink_unicast(struct sock *ssk, struct sk_buff *skb, + u32 portid, int nonblock) +{ + struct sock *sk; + int err; + long timeo; + + skb = netlink_trim(skb, gfp_any()); + + timeo = sock_sndtimeo(ssk, nonblock); +retry: + sk = netlink_getsockbyportid(ssk, portid); + if (IS_ERR(sk)) { + kfree_skb(skb); + return PTR_ERR(sk); + } + if (netlink_is_kernel(sk)) + return netlink_unicast_kernel(sk, skb, 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) + return err; + + return netlink_sendskb(sk, skb); +} +EXPORT_SYMBOL(netlink_unicast); + +struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, + u32 dst_portid, gfp_t gfp_mask) +{ +#ifdef CONFIG_NETLINK_MMAP + struct sock *sk = NULL; + struct sk_buff *skb; + struct netlink_ring *ring; + struct nl_mmap_hdr *hdr; + unsigned int maxlen; + + sk = netlink_getsockbyportid(ssk, dst_portid); + if (IS_ERR(sk)) + goto out; + + ring = &nlk_sk(sk)->rx_ring; + /* fast-path without atomic ops for common case: non-mmaped receiver */ + 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; + + spin_lock_bh(&sk->sk_receive_queue.lock); + /* check again under lock */ + 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; + + netlink_forward_ring(ring); + hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); + if (hdr == NULL) + goto err2; + netlink_ring_setup_skb(skb, sk, ring, hdr); + netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); + atomic_inc(&ring->pending); + netlink_increment_head(ring); + + spin_unlock_bh(&sk->sk_receive_queue.lock); + return skb; + +err2: + kfree_skb(skb); + spin_unlock_bh(&sk->sk_receive_queue.lock); + netlink_overrun(sk); +err1: + sock_put(sk); + return NULL; + +out_free: + kfree_skb(skb); + spin_unlock_bh(&sk->sk_receive_queue.lock); +out_put: + sock_put(sk); +out: +#endif + return alloc_skb(size, gfp_mask); +} +EXPORT_SYMBOL_GPL(netlink_alloc_skb); + +int netlink_has_listeners(struct sock *sk, unsigned int group) +{ + int res = 0; + struct listeners *listeners; + + BUG_ON(!netlink_is_kernel(sk)); + + rcu_read_lock(); + listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); + + if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) + res = test_bit(group - 1, listeners->masks); + + rcu_read_unlock(); + + return res; +} +EXPORT_SYMBOL_GPL(netlink_has_listeners); + +static 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(NETLINK_CONGESTED, &nlk->state)) { + netlink_skb_set_owner_r(skb, sk); + __netlink_sendskb(sk, skb); + return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); + } + return -1; +} + +struct netlink_broadcast_data { + struct sock *exclude_sk; + struct net *net; + u32 portid; + u32 group; + int failure; + int delivery_failure; + int congested; + int delivered; + gfp_t allocation; + struct sk_buff *skb, *skb2; + int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); + void *tx_data; +}; + +static void 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) + return; + + if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || + !test_bit(p->group - 1, nlk->groups)) + return; + + if (!net_eq(sock_net(sk), p->net)) + return; + + if (p->failure) { + netlink_overrun(sk); + return; + } + + sock_hold(sk); + if (p->skb2 == NULL) { + if (skb_shared(p->skb)) { + p->skb2 = skb_clone(p->skb, p->allocation); + } else { + p->skb2 = skb_get(p->skb); + /* + * skb ownership may have been set when + * delivered to a previous socket. + */ + skb_orphan(p->skb2); + } + } + if (p->skb2 == NULL) { + netlink_overrun(sk); + /* Clone failed. Notify ALL listeners. */ + p->failure = 1; + if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR) + p->delivery_failure = 1; + } else if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { + kfree_skb(p->skb2); + p->skb2 = NULL; + } 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; + p->skb2 = NULL; + } + sock_put(sk); +} + +int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, + u32 group, gfp_t allocation, + int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), + void *filter_data) +{ + struct net *net = sock_net(ssk); + struct netlink_broadcast_data info; + struct sock *sk; + + skb = netlink_trim(skb, allocation); + + info.exclude_sk = ssk; + info.net = net; + info.portid = portid; + info.group = group; + info.failure = 0; + info.delivery_failure = 0; + info.congested = 0; + info.delivered = 0; + info.allocation = allocation; + info.skb = skb; + info.skb2 = NULL; + info.tx_filter = filter; + info.tx_data = filter_data; + + /* While we sleep in clone, do not allow to change socket list */ + + netlink_lock_table(); + + sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) + do_one_broadcast(sk, &info); + + consume_skb(skb); + + netlink_unlock_table(); + + if (info.delivery_failure) { + kfree_skb(info.skb2); + return -ENOBUFS; + } + consume_skb(info.skb2); + + if (info.delivered) { + if (info.congested && (allocation & __GFP_WAIT)) + yield(); + return 0; + } + return -ESRCH; +} +EXPORT_SYMBOL(netlink_broadcast_filtered); + +int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, + u32 group, gfp_t allocation) +{ + return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, + NULL, NULL); +} +EXPORT_SYMBOL(netlink_broadcast); + +struct netlink_set_err_data { + struct sock *exclude_sk; + u32 portid; + u32 group; + int code; +}; + +static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) +{ + struct netlink_sock *nlk = nlk_sk(sk); + int ret = 0; + + if (sk == p->exclude_sk) + goto out; + + if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) + goto out; + + if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || + !test_bit(p->group - 1, nlk->groups)) + goto out; + + if (p->code == ENOBUFS && nlk->flags & NETLINK_RECV_NO_ENOBUFS) { + ret = 1; + goto out; + } + + sk->sk_err = p->code; + sk->sk_error_report(sk); +out: + return ret; +} + +/** + * 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) + * @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 + * NETLINK_RECV_NO_ENOBUFS socket option. + */ +int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) +{ + struct netlink_set_err_data info; + struct sock *sk; + int ret = 0; + + info.exclude_sk = ssk; + info.portid = portid; + info.group = group; + /* sk->sk_err wants a positive error value */ + info.code = -code; + + read_lock(&nl_table_lock); + + sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) + ret += do_one_set_err(sk, &info); + + read_unlock(&nl_table_lock); + return ret; +} +EXPORT_SYMBOL(netlink_set_err); + +/* must be called with netlink table grabbed */ +static void netlink_update_socket_mc(struct netlink_sock *nlk, + unsigned int group, + int is_new) +{ + int old, new = !!is_new, subscriptions; + + old = test_bit(group - 1, nlk->groups); + subscriptions = nlk->subscriptions - old + new; + if (new) + __set_bit(group - 1, nlk->groups); + else + __clear_bit(group - 1, nlk->groups); + netlink_update_subscriptions(&nlk->sk, subscriptions); + netlink_update_listeners(&nlk->sk); +} + +static int netlink_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + unsigned int val = 0; + int err; + + if (level != SOL_NETLINK) + return -ENOPROTOOPT; + + if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING && + optlen >= sizeof(int) && + get_user(val, (unsigned int __user *)optval)) + return -EFAULT; + + switch (optname) { + case NETLINK_PKTINFO: + if (val) + nlk->flags |= NETLINK_RECV_PKTINFO; + else + nlk->flags &= ~NETLINK_RECV_PKTINFO; + err = 0; + break; + case NETLINK_ADD_MEMBERSHIP: + case NETLINK_DROP_MEMBERSHIP: { + 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(sock_net(sk), val); + if (err) + return err; + } + netlink_table_grab(); + netlink_update_socket_mc(nlk, val, + optname == NETLINK_ADD_MEMBERSHIP); + netlink_table_ungrab(); + if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) + nlk->netlink_unbind(sock_net(sk), val); + + 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(NETLINK_CONGESTED, &nlk->state); + wake_up_interruptible(&nlk->wait); + } else { + nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS; + } + err = 0; + break; +#ifdef CONFIG_NETLINK_MMAP + case NETLINK_RX_RING: + case NETLINK_TX_RING: { + struct nl_mmap_req req; + + /* Rings might consume more memory than queue limits, require + * CAP_NET_ADMIN. + */ + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (optlen < sizeof(req)) + return -EINVAL; + if (copy_from_user(&req, optval, sizeof(req))) + return -EFAULT; + err = netlink_set_ring(sk, &req, false, + optname == NETLINK_TX_RING); + break; + } +#endif /* CONFIG_NETLINK_MMAP */ + default: + err = -ENOPROTOOPT; + } + return err; +} + +static int netlink_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + int len, val, err; + + if (level != SOL_NETLINK) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < 0) + return -EINVAL; + + switch (optname) { + case NETLINK_PKTINFO: + if (len < sizeof(int)) + return -EINVAL; + len = sizeof(int); + val = nlk->flags & NETLINK_RECV_PKTINFO ? 1 : 0; + if (put_user(len, optlen) || + put_user(val, optval)) + 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; + } + return err; +} + +static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) +{ + struct nl_pktinfo info; + + info.group = NETLINK_CB(skb).dst_group; + put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); +} + +static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + struct netlink_sock *nlk = nlk_sk(sk); + 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; + + err = scm_send(sock, msg, &scm, true); + if (err < 0) + return err; + + if (msg->msg_namelen) { + err = -EINVAL; + if (addr->nl_family != AF_NETLINK) + goto out; + dst_portid = addr->nl_pid; + dst_group = ffs(addr->nl_groups); + err = -EPERM; + if ((dst_group || dst_portid) && + !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; + } + + if (!nlk->portid) { + err = netlink_autobind(sock); + if (err) + goto out; + } + + /* It's a really convoluted way for userland to ask for mmaped + * sendmsg(), but that's what we've got... + */ + if (netlink_tx_is_mmaped(sk) && + msg->msg_iter.type == ITER_IOVEC && + msg->msg_iter.nr_segs == 1 && + msg->msg_iter.iov->iov_base == NULL) { + err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, + &scm); + goto out; + } + + err = -EMSGSIZE; + if (len > sk->sk_sndbuf - 32) + goto out; + err = -ENOBUFS; + 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 = scm.creds; + NETLINK_CB(skb).flags = netlink_skb_flags; + + err = -EFAULT; + if (memcpy_from_msg(skb_put(skb, len), msg, len)) { + kfree_skb(skb); + goto out; + } + + err = security_netlink_send(sk, skb); + if (err) { + kfree_skb(skb); + goto out; + } + + if (dst_group) { + atomic_inc(&skb->users); + netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); + } + err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT); + +out: + scm_destroy(&scm); + return err; +} + +static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + 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, *data_skb; + int err, ret; + + if (flags&MSG_OOB) + return -EOPNOTSUPP; + + copied = 0; + + skb = skb_recv_datagram(sk, flags, noblock, &err); + if (skb == NULL) + goto out; + + data_skb = skb; + +#ifdef CONFIG_COMPAT_NETLINK_MESSAGES + if (unlikely(skb_shinfo(skb)->frag_list)) { + /* + * If this skb has a frag_list, then here that means that we + * will have to use the frag_list skb's data for compat tasks + * and the regular skb's data for normal (non-compat) tasks. + * + * If we need to send the compat skb, assign it to the + * 'data_skb' variable so that it will be used below for data + * copying. We keep 'skb' for everything else, including + * freeing both later. + */ + if (flags & MSG_CMSG_COMPAT) + data_skb = skb_shinfo(skb)->frag_list; + } +#endif + + /* 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) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + skb_reset_transport_header(data_skb); + err = skb_copy_datagram_msg(data_skb, 0, msg, copied); + + if (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; + addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); + msg->msg_namelen = sizeof(*addr); + } + + if (nlk->flags & NETLINK_RECV_PKTINFO) + netlink_cmsg_recv_pktinfo(msg, skb); + + memset(&scm, 0, sizeof(scm)); + scm.creds = *NETLINK_CREDS(skb); + if (flags & MSG_TRUNC) + copied = data_skb->len; + + skb_free_datagram(sk, skb); + + 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_error_report(sk); + } + } + + scm_recv(sock, msg, &scm, flags); +out: + netlink_rcv_wake(sk); + return err ? : copied; +} + +static void netlink_data_ready(struct sock *sk) +{ + BUG(); +} + +/* + * 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(struct net *net, int unit, struct module *module, + struct netlink_kernel_cfg *cfg) +{ + struct socket *sock; + struct sock *sk; + struct netlink_sock *nlk; + struct listeners *listeners = NULL; + struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; + unsigned int groups; + + BUG_ON(!nl_table); + + if (unit < 0 || unit >= MAX_LINKS) + return NULL; + + if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) + return NULL; + + /* + * 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 (!cfg || cfg->groups < 32) + groups = 32; + else + groups = cfg->groups; + + listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); + if (!listeners) + goto out_sock_release; + + sk->sk_data_ready = netlink_data_ready; + if (cfg && cfg->input) + nlk_sk(sk)->netlink_rcv = cfg->input; + + if (netlink_insert(sk, 0)) + goto out_sock_release; + + nlk = nlk_sk(sk); + nlk->flags |= NETLINK_KERNEL_SOCKET; + + netlink_table_grab(); + if (!nl_table[unit].registered) { + nl_table[unit].groups = groups; + rcu_assign_pointer(nl_table[unit].listeners, listeners); + nl_table[unit].cb_mutex = cb_mutex; + nl_table[unit].module = module; + if (cfg) { + nl_table[unit].bind = cfg->bind; + nl_table[unit].unbind = cfg->unbind; + nl_table[unit].flags = cfg->flags; + if (cfg->compare) + nl_table[unit].compare = cfg->compare; + } + 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); + +int __netlink_change_ngroups(struct sock *sk, unsigned int groups) +{ + struct listeners *new, *old; + struct netlink_table *tbl = &nl_table[sk->sk_protocol]; + + if (groups < 32) + groups = 32; + + if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { + new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); + if (!new) + return -ENOMEM; + old = nl_deref_protected(tbl->listeners); + memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); + rcu_assign_pointer(tbl->listeners, new); + + kfree_rcu(old, rcu); + } + tbl->groups = groups; + + return 0; +} + +/** + * netlink_change_ngroups - change number of multicast groups + * + * This changes the number of multicast groups that are available + * on a certain netlink family. Note that it is not possible to + * change the number of groups to below 32. Also note that it does + * not implicitly call netlink_clear_multicast_users() when the + * number of groups is reduced. + * + * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). + * @groups: The new number of groups. + */ +int netlink_change_ngroups(struct sock *sk, unsigned int groups) +{ + int err; + + netlink_table_grab(); + err = __netlink_change_ngroups(sk, groups); + netlink_table_ungrab(); + + return err; +} + +void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) +{ + struct sock *sk; + struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; + + sk_for_each_bound(sk, &tbl->mc_list) + netlink_update_socket_mc(nlk_sk(sk), group, 0); +} + +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->nlmsg_type = type; + nlh->nlmsg_len = size; + nlh->nlmsg_flags = flags; + nlh->nlmsg_pid = portid; + nlh->nlmsg_seq = seq; + if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) + memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); + return nlh; +} +EXPORT_SYMBOL(__nlmsg_put); + +/* + * 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 = NULL; + struct nlmsghdr *nlh; + int len, err = -ENOBUFS; + int alloc_size; + + mutex_lock(nlk->cb_mutex); + 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; + + /* 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); + + len = cb->dump(skb, cb); + + if (len > 0) { + mutex_unlock(nlk->cb_mutex); + + if (sk_filter(sk, skb)) + kfree_skb(skb); + else + __netlink_sendskb(sk, skb); + return 0; + } + + nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); + if (!nlh) + goto errout_skb; + + nl_dump_check_consistent(cb, nlh); + + memcpy(nlmsg_data(nlh), &len, sizeof(len)); + + if (sk_filter(sk, skb)) + kfree_skb(skb); + else + __netlink_sendskb(sk, skb); + + if (cb->done) + cb->done(cb); + + nlk->cb_running = false; + mutex_unlock(nlk->cb_mutex); + module_put(cb->module); + consume_skb(cb->skb); + return 0; + +errout_skb: + mutex_unlock(nlk->cb_mutex); + kfree_skb(skb); + return err; +} + +int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *control) +{ + struct netlink_callback *cb; + struct sock *sk; + struct netlink_sock *nlk; + int ret; + + /* 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) + return -ENOBUFS; + } else + atomic_inc(&skb->users); + + sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); + if (sk == NULL) { + ret = -ECONNREFUSED; + goto error_free; + } + + nlk = nlk_sk(sk); + mutex_lock(nlk->cb_mutex); + /* A dump is in progress... */ + if (nlk->cb_running) { + ret = -EBUSY; + goto error_unlock; + } + /* add reference of module which cb->dump belongs to */ + if (!try_module_get(control->module)) { + ret = -EPROTONOSUPPORT; + goto error_unlock; + } + + 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); + sock_put(sk); + + if (ret) + return ret; + + /* We successfully started a dump, by returning -EINTR we + * 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); + +void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) +{ + struct sk_buff *skb; + struct nlmsghdr *rep; + struct nlmsgerr *errmsg; + size_t payload = sizeof(*errmsg); + + /* error messages get the original request appened */ + if (err) + payload += nlmsg_len(nlh); + + skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload), + NETLINK_CB(in_skb).portid, GFP_KERNEL); + if (!skb) { + struct sock *sk; + + sk = netlink_lookup(sock_net(in_skb->sk), + in_skb->sk->sk_protocol, + NETLINK_CB(in_skb).portid); + if (sk) { + sk->sk_err = ENOBUFS; + sk->sk_error_report(sk); + sock_put(sk); + } + return; + } + + rep = __nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, + 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).portid, MSG_DONTWAIT); +} +EXPORT_SYMBOL(netlink_ack); + +int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, + struct nlmsghdr *)) +{ + struct nlmsghdr *nlh; + int err; + + while (skb->len >= nlmsg_total_size(0)) { + int msglen; + + nlh = nlmsg_hdr(skb); + err = 0; + + if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) + return 0; + + /* Only requests are handled by the kernel */ + if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) + goto ack; + + /* Skip control messages */ + if (nlh->nlmsg_type < NLMSG_MIN_TYPE) + goto ack; + + err = cb(skb, nlh); + if (err == -EINTR) + goto skip; + +ack: + if (nlh->nlmsg_flags & NLM_F_ACK || err) + netlink_ack(skb, nlh, err); + +skip: + msglen = NLMSG_ALIGN(nlh->nlmsg_len); + if (msglen > skb->len) + msglen = skb->len; + skb_pull(skb, msglen); + } + + return 0; +} +EXPORT_SYMBOL(netlink_rcv_skb); + +/** + * nlmsg_notify - send a notification netlink message + * @sk: netlink socket to use + * @skb: notification message + * @portid: destination netlink portid for reports or 0 + * @group: destination multicast group or 0 + * @report: 1 to report back, 0 to disable + * @flags: allocation flags + */ +int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, + unsigned int group, int report, gfp_t flags) +{ + int err = 0; + + if (group) { + int exclude_portid = 0; + + if (report) { + atomic_inc(&skb->users); + exclude_portid = portid; + } + + /* errors reported via destination sk->sk_err, but propagate + * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ + err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); + } + + if (report) { + int err2; + + err2 = nlmsg_unicast(sk, skb, portid); + if (!err || err == -ESRCH) + err = err2; + } + + return err; +} +EXPORT_SYMBOL(nlmsg_notify); + +#ifdef CONFIG_PROC_FS +struct nl_seq_iter { + struct seq_net_private p; + struct rhashtable_iter hti; + int link; +}; + +static int netlink_walk_start(struct nl_seq_iter *iter) +{ + int err; + + err = rhashtable_walk_init(&nl_table[iter->link].hash, &iter->hti); + if (err) { + iter->link = MAX_LINKS; + return err; + } + + err = rhashtable_walk_start(&iter->hti); + return err == -EAGAIN ? 0 : err; +} + +static void netlink_walk_stop(struct nl_seq_iter *iter) +{ + rhashtable_walk_stop(&iter->hti); + rhashtable_walk_exit(&iter->hti); +} + +static void *__netlink_seq_next(struct seq_file *seq) +{ + struct nl_seq_iter *iter = seq->private; + struct netlink_sock *nlk; + + do { + for (;;) { + int err; + + nlk = rhashtable_walk_next(&iter->hti); + + if (IS_ERR(nlk)) { + if (PTR_ERR(nlk) == -EAGAIN) + continue; + + return nlk; + } + + if (nlk) + break; + + netlink_walk_stop(iter); + if (++iter->link >= MAX_LINKS) + return NULL; + + err = netlink_walk_start(iter); + if (err) + return ERR_PTR(err); + } + } while (sock_net(&nlk->sk) != seq_file_net(seq)); + + return nlk; +} + +static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) +{ + struct nl_seq_iter *iter = seq->private; + void *obj = SEQ_START_TOKEN; + loff_t pos; + int err; + + iter->link = 0; + + err = netlink_walk_start(iter); + if (err) + return ERR_PTR(err); + + for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) + obj = __netlink_seq_next(seq); + + return obj; +} + +static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return __netlink_seq_next(seq); +} + +static void netlink_seq_stop(struct seq_file *seq, void *v) +{ + struct nl_seq_iter *iter = seq->private; + + if (iter->link >= MAX_LINKS) + return; + + netlink_walk_stop(iter); +} + + +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 Drops Inode\n"); + } else { + struct sock *s = v; + struct netlink_sock *nlk = nlk_sk(s); + + 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_running, + atomic_read(&s->sk_refcnt), + atomic_read(&s->sk_drops), + sock_i_ino(s) + ); + + } + return 0; +} + +static const struct seq_operations netlink_seq_ops = { + .start = netlink_seq_start, + .next = netlink_seq_next, + .stop = netlink_seq_stop, + .show = netlink_seq_show, +}; + + +static int netlink_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &netlink_seq_ops, + sizeof(struct nl_seq_iter)); +} + +static const struct file_operations netlink_seq_fops = { + .owner = THIS_MODULE, + .open = netlink_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +#endif + +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, + .owner = THIS_MODULE, + .release = netlink_release, + .bind = netlink_bind, + .connect = netlink_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = netlink_getname, + .poll = netlink_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = netlink_setsockopt, + .getsockopt = netlink_getsockopt, + .sendmsg = netlink_sendmsg, + .recvmsg = netlink_recvmsg, + .mmap = netlink_mmap, + .sendpage = sock_no_sendpage, +}; + +static const struct net_proto_family netlink_family_ops = { + .family = PF_NETLINK, + .create = netlink_create, + .owner = THIS_MODULE, /* for consistency 8) */ +}; + +static int __net_init netlink_net_init(struct net *net) +{ +#ifdef CONFIG_PROC_FS + if (!proc_create("netlink", 0, net->proc_net, &netlink_seq_fops)) + return -ENOMEM; +#endif + return 0; +} + +static void __net_exit netlink_net_exit(struct net *net) +{ +#ifdef CONFIG_PROC_FS + remove_proc_entry("netlink", net->proc_net); +#endif +} + +static void __init netlink_add_usersock_entry(void) +{ + struct listeners *listeners; + int groups = 32; + + listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); + if (!listeners) + panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); + + netlink_table_grab(); + + nl_table[NETLINK_USERSOCK].groups = groups; + rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); + nl_table[NETLINK_USERSOCK].module = THIS_MODULE; + nl_table[NETLINK_USERSOCK].registered = 1; + nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; + + netlink_table_ungrab(); +} + +static struct pernet_operations __net_initdata netlink_net_ops = { + .init = netlink_net_init, + .exit = netlink_net_exit, +}; + +static inline u32 netlink_hash(const void *data, u32 len, u32 seed) +{ + const struct netlink_sock *nlk = data; + struct netlink_compare_arg arg; + + netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); + return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); +} + +static const struct rhashtable_params netlink_rhashtable_params = { + .head_offset = offsetof(struct netlink_sock, node), + .key_len = netlink_compare_arg_len, + .obj_hashfn = netlink_hash, + .obj_cmpfn = netlink_compare, + .automatic_shrinking = true, +}; + +static int __init netlink_proto_init(void) +{ + int i; + int err = proto_register(&netlink_proto, 0); + + if (err != 0) + goto out; + + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + + nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); + if (!nl_table) + goto panic; + + for (i = 0; i < MAX_LINKS; i++) { + if (rhashtable_init(&nl_table[i].hash, + &netlink_rhashtable_params) < 0) { + while (--i > 0) + rhashtable_destroy(&nl_table[i].hash); + kfree(nl_table); + goto panic; + } + } + + INIT_LIST_HEAD(&netlink_tap_all); + + netlink_add_usersock_entry(); + + sock_register(&netlink_family_ops); + register_pernet_subsys(&netlink_net_ops); + /* The netlink device handler may be needed early. */ + rtnetlink_init(); +out: + return err; +panic: + panic("netlink_init: Cannot allocate nl_table\n"); +} + +core_initcall(netlink_proto_init); diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h new file mode 100644 index 000000000..89008405d --- /dev/null +++ b/net/netlink/af_netlink.h @@ -0,0 +1,79 @@ +#ifndef _AF_NETLINK_H +#define _AF_NETLINK_H + +#include <linux/rhashtable.h> +#include <linux/atomic.h> +#include <net/sock.h> + +#define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) +#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long)) + +struct netlink_ring { + void **pg_vec; + unsigned int head; + unsigned int frames_per_block; + unsigned int frame_size; + unsigned int frame_max; + + unsigned int pg_vec_order; + unsigned int pg_vec_pages; + unsigned int pg_vec_len; + + atomic_t pending; +}; + +struct netlink_sock { + /* struct sock has to be the first member of netlink_sock */ + struct sock sk; + u32 portid; + u32 dst_portid; + u32 dst_group; + u32 flags; + u32 subscriptions; + u32 ngroups; + unsigned long *groups; + unsigned long state; + size_t max_recvmsg_len; + wait_queue_head_t wait; + bool cb_running; + struct netlink_callback cb; + struct mutex *cb_mutex; + struct mutex cb_def_mutex; + void (*netlink_rcv)(struct sk_buff *skb); + int (*netlink_bind)(struct net *net, int group); + void (*netlink_unbind)(struct net *net, int group); + struct module *module; +#ifdef CONFIG_NETLINK_MMAP + struct mutex pg_vec_lock; + struct netlink_ring rx_ring; + struct netlink_ring tx_ring; + atomic_t mapped; +#endif /* CONFIG_NETLINK_MMAP */ + + struct rhash_head node; + struct rcu_head rcu; +}; + +static inline struct netlink_sock *nlk_sk(struct sock *sk) +{ + return container_of(sk, struct netlink_sock, sk); +} + +struct netlink_table { + struct rhashtable hash; + struct hlist_head mc_list; + struct listeners __rcu *listeners; + unsigned int flags; + unsigned int groups; + struct mutex *cb_mutex; + struct module *module; + int (*bind)(struct net *net, int group); + void (*unbind)(struct net *net, int group); + bool (*compare)(struct net *net, struct sock *sock); + int registered; +}; + +extern struct netlink_table *nl_table; +extern rwlock_t nl_table_lock; + +#endif diff --git a/net/netlink/diag.c b/net/netlink/diag.c new file mode 100644 index 000000000..3ee63a3cf --- /dev/null +++ b/net/netlink/diag.c @@ -0,0 +1,238 @@ +#include <linux/module.h> + +#include <net/sock.h> +#include <linux/netlink.h> +#include <linux/sock_diag.h> +#include <linux/netlink_diag.h> +#include <linux/rhashtable.h> + +#include "af_netlink.h" + +#ifdef CONFIG_NETLINK_MMAP +static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type, + struct sk_buff *nlskb) +{ + struct netlink_diag_ring ndr; + + ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT; + ndr.ndr_block_nr = ring->pg_vec_len; + ndr.ndr_frame_size = ring->frame_size; + ndr.ndr_frame_nr = ring->frame_max + 1; + + return nla_put(nlskb, nl_type, sizeof(ndr), &ndr); +} + +static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb) +{ + struct netlink_sock *nlk = nlk_sk(sk); + int ret; + + mutex_lock(&nlk->pg_vec_lock); + ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb); + if (!ret) + ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING, + nlskb); + mutex_unlock(&nlk->pg_vec_lock); + + return ret; +} +#else +static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb) +{ + return 0; +} +#endif + +static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (nlk->groups == NULL) + return 0; + + return nla_put(nlskb, NETLINK_DIAG_GROUPS, NLGRPSZ(nlk->ngroups), + nlk->groups); +} + +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + struct netlink_diag_req *req, + u32 portid, u32 seq, u32 flags, int sk_ino) +{ + struct nlmsghdr *nlh; + struct netlink_diag_msg *rep; + struct netlink_sock *nlk = nlk_sk(sk); + + nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), + flags); + if (!nlh) + return -EMSGSIZE; + + rep = nlmsg_data(nlh); + rep->ndiag_family = AF_NETLINK; + rep->ndiag_type = sk->sk_type; + rep->ndiag_protocol = sk->sk_protocol; + rep->ndiag_state = sk->sk_state; + + rep->ndiag_ino = sk_ino; + rep->ndiag_portid = nlk->portid; + rep->ndiag_dst_portid = nlk->dst_portid; + rep->ndiag_dst_group = nlk->dst_group; + sock_diag_save_cookie(sk, rep->ndiag_cookie); + + if ((req->ndiag_show & NDIAG_SHOW_GROUPS) && + sk_diag_dump_groups(sk, skb)) + goto out_nlmsg_trim; + + if ((req->ndiag_show & NDIAG_SHOW_MEMINFO) && + sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO)) + goto out_nlmsg_trim; + + if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) && + sk_diag_put_rings_cfg(sk, skb)) + goto out_nlmsg_trim; + + nlmsg_end(skb, nlh); + return 0; + +out_nlmsg_trim: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + int protocol, int s_num) +{ + struct netlink_table *tbl = &nl_table[protocol]; + struct rhashtable *ht = &tbl->hash; + const struct bucket_table *htbl = rht_dereference_rcu(ht->tbl, ht); + struct net *net = sock_net(skb->sk); + struct netlink_diag_req *req; + struct netlink_sock *nlsk; + struct sock *sk; + int ret = 0, num = 0, i; + + req = nlmsg_data(cb->nlh); + + for (i = 0; i < htbl->size; i++) { + struct rhash_head *pos; + + rht_for_each_entry_rcu(nlsk, pos, htbl, i, node) { + sk = (struct sock *)nlsk; + + if (!net_eq(sock_net(sk), net)) + continue; + if (num < s_num) { + num++; + continue; + } + + if (sk_diag_fill(sk, skb, req, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + sock_i_ino(sk)) < 0) { + ret = 1; + goto done; + } + + num++; + } + } + + sk_for_each_bound(sk, &tbl->mc_list) { + if (sk_hashed(sk)) + continue; + if (!net_eq(sock_net(sk), net)) + continue; + if (num < s_num) { + num++; + continue; + } + + if (sk_diag_fill(sk, skb, req, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, + sock_i_ino(sk)) < 0) { + ret = 1; + goto done; + } + num++; + } +done: + cb->args[0] = num; + cb->args[1] = protocol; + + return ret; +} + +static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct netlink_diag_req *req; + int s_num = cb->args[0]; + + req = nlmsg_data(cb->nlh); + + rcu_read_lock(); + read_lock(&nl_table_lock); + + if (req->sdiag_protocol == NDIAG_PROTO_ALL) { + int i; + + for (i = cb->args[1]; i < MAX_LINKS; i++) { + if (__netlink_diag_dump(skb, cb, i, s_num)) + break; + s_num = 0; + } + } else { + if (req->sdiag_protocol >= MAX_LINKS) { + read_unlock(&nl_table_lock); + rcu_read_unlock(); + return -ENOENT; + } + + __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num); + } + + read_unlock(&nl_table_lock); + rcu_read_unlock(); + + return skb->len; +} + +static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +{ + int hdrlen = sizeof(struct netlink_diag_req); + struct net *net = sock_net(skb->sk); + + if (nlmsg_len(h) < hdrlen) + return -EINVAL; + + if (h->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = netlink_diag_dump, + }; + return netlink_dump_start(net->diag_nlsk, skb, h, &c); + } else + return -EOPNOTSUPP; +} + +static const struct sock_diag_handler netlink_diag_handler = { + .family = AF_NETLINK, + .dump = netlink_diag_handler_dump, +}; + +static int __init netlink_diag_init(void) +{ + return sock_diag_register(&netlink_diag_handler); +} + +static void __exit netlink_diag_exit(void) +{ + sock_diag_unregister(&netlink_diag_handler); +} + +module_init(netlink_diag_init); +module_exit(netlink_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 16 /* AF_NETLINK */); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c new file mode 100644 index 000000000..2ed5f9647 --- /dev/null +++ b/net/netlink/genetlink.c @@ -0,0 +1,1154 @@ +/* + * NETLINK Generic Netlink Family + * + * Authors: Jamal Hadi Salim + * Thomas Graf <tgraf@suug.ch> + * Johannes Berg <johannes@sipsolutions.net> + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/string.h> +#include <linux/skbuff.h> +#include <linux/mutex.h> +#include <linux/bitmap.h> +#include <linux/rwsem.h> +#include <net/sock.h> +#include <net/genetlink.h> + +static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ +static DECLARE_RWSEM(cb_lock); + +atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); +DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); + +void genl_lock(void) +{ + mutex_lock(&genl_mutex); +} +EXPORT_SYMBOL(genl_lock); + +void genl_unlock(void) +{ + mutex_unlock(&genl_mutex); +} +EXPORT_SYMBOL(genl_unlock); + +#ifdef CONFIG_LOCKDEP +int lockdep_genl_is_held(void) +{ + return lockdep_is_held(&genl_mutex); +} +EXPORT_SYMBOL(lockdep_genl_is_held); +#endif + +static void genl_lock_all(void) +{ + down_write(&cb_lock); + genl_lock(); +} + +static void genl_unlock_all(void) +{ + genl_unlock(); + up_write(&cb_lock); +} + +#define GENL_FAM_TAB_SIZE 16 +#define GENL_FAM_TAB_MASK (GENL_FAM_TAB_SIZE - 1) + +static struct list_head family_ht[GENL_FAM_TAB_SIZE]; +/* + * Bitmap of multicast groups that are currently in use. + * + * To avoid an allocation at boot of just one unsigned long, + * declare it global instead. + * Bit 0 is marked as already used since group 0 is invalid. + * Bit 1 is marked as already used since 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 = 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, struct genl_family *family, + const struct genl_multicast_group *grp, + int grp_id); + +static inline unsigned int genl_family_hash(unsigned int id) +{ + return id & GENL_FAM_TAB_MASK; +} + +static inline struct list_head *genl_family_chain(unsigned int id) +{ + return &family_ht[genl_family_hash(id)]; +} + +static struct genl_family *genl_family_find_byid(unsigned int id) +{ + struct genl_family *f; + + list_for_each_entry(f, genl_family_chain(id), family_list) + if (f->id == id) + return f; + + return NULL; +} + +static struct genl_family *genl_family_find_byname(char *name) +{ + struct genl_family *f; + int i; + + for (i = 0; i < GENL_FAM_TAB_SIZE; i++) + list_for_each_entry(f, genl_family_chain(i), family_list) + if (strcmp(f->name, name) == 0) + return f; + + return NULL; +} + +static const struct genl_ops *genl_get_cmd(u8 cmd, struct genl_family *family) +{ + int i; + + for (i = 0; i < family->n_ops; i++) + if (family->ops[i].cmd == cmd) + return &family->ops[i]; + + return NULL; +} + +/* Of course we are going to have problems once we hit + * 2^16 alive types, but that can only happen by year 2K +*/ +static u16 genl_generate_id(void) +{ + static u16 id_gen_idx = GENL_MIN_ID; + int i; + + for (i = 0; i <= GENL_MAX_ID - GENL_MIN_ID; i++) { + 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; + } + + return 0; +} + +static int genl_allocate_reserve_groups(int n_groups, int *first_id) +{ + unsigned long *new_groups; + 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); + + for (i = id; i < id + n_groups; i++) + set_bit(i, mc_groups); + *first_id = id; + return 0; +} + +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; + + if (!n_groups) + return 0; + + for (i = 0; i < n_groups; i++) { + const struct genl_multicast_group *grp = &family->mcgrps[i]; + + if (WARN_ON(grp->name[0] == '\0')) + return -EINVAL; + if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL)) + return -EINVAL; + } + + /* 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; + + netlink_table_grab(); + rcu_read_lock(); + for_each_net_rcu(net) { + err = __netlink_change_ngroups(net->genl_sock, + mc_groups_longs * BITS_PER_LONG); + if (err) { + /* + * No need to roll back, can only fail if + * memory allocation fails and then the + * number of _possible_ groups has been + * increased on some sockets which is ok. + */ + break; + } + } + rcu_read_unlock(); + netlink_table_ungrab(); + } else { + err = netlink_change_ngroups(init_net.genl_sock, + mc_groups_longs * BITS_PER_LONG); + } + + if (groups_allocated && err) { + for (i = 0; i < family->n_mcgrps; i++) + clear_bit(family->mcgrp_offset + i, mc_groups); + } + + return err; +} + +static void genl_unregister_mc_groups(struct genl_family *family) +{ + struct net *net; + int i; + + netlink_table_grab(); + rcu_read_lock(); + 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(); + + for (i = 0; i < family->n_mcgrps; i++) { + int grp_id = family->mcgrp_offset + i; + + if (grp_id != 1) + clear_bit(grp_id, mc_groups); + genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family, + &family->mcgrps[i], grp_id); + } +} + +static int genl_validate_ops(const struct genl_family *family) +{ + const struct genl_ops *ops = family->ops; + unsigned int n_ops = family->n_ops; + int i, j; + + if (WARN_ON(n_ops && !ops)) + return -EINVAL; + + if (!n_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; + } + + return 0; +} + +/** + * __genl_register_family - register a generic netlink family + * @family: generic netlink family + * + * Registers the specified family after validating it first. 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. + * + * 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 err = -EINVAL, i; + + if (family->id && family->id < GENL_MIN_ID) + goto errout; + + if (family->id > GENL_MAX_ID) + goto errout; + + err = genl_validate_ops(family); + if (err) + return err; + + genl_lock_all(); + + if (genl_family_find_byname(family->name)) { + err = -EEXIST; + goto errout_locked; + } + + if (family->id == GENL_ID_GENERATE) { + u16 newid = genl_generate_id(); + + if (!newid) { + err = -ENOMEM; + goto errout_locked; + } + + family->id = newid; + } else if (genl_family_find_byid(family->id)) { + err = -EEXIST; + goto errout_locked; + } + + if (family->maxattr && !family->parallel_ops) { + family->attrbuf = kmalloc((family->maxattr+1) * + sizeof(struct nlattr *), GFP_KERNEL); + if (family->attrbuf == NULL) { + err = -ENOMEM; + goto errout_locked; + } + } 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(); + + /* 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; + +errout_locked: + genl_unlock_all(); +errout: + return err; +} +EXPORT_SYMBOL(__genl_register_family); + +/** + * genl_unregister_family - unregister generic netlink family + * @family: generic netlink family + * + * Unregisters the specified family. + * + * Returns 0 on success or a negative error code. + */ +int genl_unregister_family(struct genl_family *family) +{ + struct genl_family *rc; + + genl_lock_all(); + + list_for_each_entry(rc, genl_family_chain(family->id), family_list) { + if (family->id != rc->id || strcmp(rc->name, family->name)) + continue; + + genl_unregister_mc_groups(family); + + list_del(&rc->family_list); + family->n_ops = 0; + up_write(&cb_lock); + wait_event(genl_sk_destructing_waitq, + atomic_read(&genl_sk_destructing_cnt) == 0); + genl_unlock(); + + kfree(family->attrbuf); + genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); + return 0; + } + + genl_unlock_all(); + + return -ENOENT; +} +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 + * @seq: sequence number (usually the one of the sender) + * @family: generic netlink family + * @flags: netlink message flags + * @cmd: generic netlink command + * + * Returns pointer to user specific header + */ +void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, + struct genl_family *family, int flags, u8 cmd) +{ + struct nlmsghdr *nlh; + struct genlmsghdr *hdr; + + nlh = nlmsg_put(skb, portid, seq, family->id, GENL_HDRLEN + + family->hdrsize, flags); + if (nlh == NULL) + return NULL; + + hdr = nlmsg_data(nlh); + hdr->cmd = cmd; + hdr->version = family->version; + hdr->reserved = 0; + + return (char *) hdr + GENL_HDRLEN; +} +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) +{ + const struct genl_ops *ops; + struct net *net = sock_net(skb->sk); + struct genl_info info; + struct genlmsghdr *hdr = nlmsg_data(nlh); + struct nlattr **attrbuf; + int hdrlen, err; + + /* this family doesn't exist in this netns */ + if (!family->netnsok && !net_eq(net, &init_net)) + return -ENOENT; + + hdrlen = GENL_HDRLEN + family->hdrsize; + if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) + return -EINVAL; + + ops = genl_get_cmd(hdr->cmd, family); + if (ops == NULL) + return -EOPNOTSUPP; + + if ((ops->flags & GENL_ADMIN_PERM) && + !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) { + int rc; + + if (ops->dumpit == NULL) + return -EOPNOTSUPP; + + 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) + return -EOPNOTSUPP; + + if (family->maxattr && family->parallel_ops) { + attrbuf = kmalloc((family->maxattr+1) * + sizeof(struct nlattr *), GFP_KERNEL); + if (attrbuf == NULL) + return -ENOMEM; + } else + attrbuf = family->attrbuf; + + if (attrbuf) { + err = nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, + ops->policy); + if (err < 0) + goto out; + } + + info.snd_seq = nlh->nlmsg_seq; + info.snd_portid = NETLINK_CB(skb).portid; + info.nlhdr = nlh; + 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)); + + if (family->pre_doit) { + err = family->pre_doit(ops, skb, &info); + if (err) + goto out; + } + + err = ops->doit(skb, &info); + + if (family->post_doit) + family->post_doit(ops, skb, &info); + +out: + if (family->parallel_ops) + kfree(attrbuf); + + return err; +} + +static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct genl_family *family; + int err; + + family = genl_family_find_byid(nlh->nlmsg_type); + if (family == NULL) + return -ENOENT; + + if (!family->parallel_ops) + genl_lock(); + + err = genl_family_rcv_msg(family, skb, nlh); + + if (!family->parallel_ops) + genl_unlock(); + + return err; +} + +static void genl_rcv(struct sk_buff *skb) +{ + down_read(&cb_lock); + netlink_rcv_skb(skb, &genl_rcv_msg); + up_read(&cb_lock); +} + +/************************************************************************** + * Controller + **************************************************************************/ + +static struct genl_family genl_ctrl = { + .id = GENL_ID_CTRL, + .name = "nlctrl", + .version = 0x2, + .maxattr = CTRL_ATTR_MAX, + .netnsok = true, +}; + +static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq, + u32 flags, struct sk_buff *skb, u8 cmd) +{ + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); + if (hdr == NULL) + return -1; + + if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || + nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || + nla_put_u32(skb, CTRL_ATTR_VERSION, family->version) || + nla_put_u32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize) || + nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) + goto nla_put_failure; + + if (family->n_ops) { + struct nlattr *nla_ops; + int i; + + nla_ops = nla_nest_start(skb, CTRL_ATTR_OPS); + if (nla_ops == NULL) + goto nla_put_failure; + + 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, 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, op_flags)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + } + + nla_nest_end(skb, nla_ops); + } + + if (family->n_mcgrps) { + struct nlattr *nla_grps; + int i; + + nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS); + if (nla_grps == NULL) + goto nla_put_failure; + + for (i = 0; i < family->n_mcgrps; i++) { + struct nlattr *nest; + const struct genl_multicast_group *grp; + + 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, + family->mcgrp_offset + i) || + nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, + grp->name)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + } + nla_nest_end(skb, nla_grps); + } + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +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; + struct nlattr *nest; + + hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); + if (hdr == NULL) + return -1; + + 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); + if (nla_grps == NULL) + goto nla_put_failure; + + nest = nla_nest_start(skb, 1); + if (nest == NULL) + goto nla_put_failure; + + 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; + + nla_nest_end(skb, nest); + nla_nest_end(skb, nla_grps); + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) +{ + + int i, n = 0; + struct genl_family *rt; + struct net *net = sock_net(skb->sk); + int chains_to_skip = cb->args[0]; + int fams_to_skip = cb->args[1]; + + for (i = chains_to_skip; i < GENL_FAM_TAB_SIZE; i++) { + n = 0; + list_for_each_entry(rt, genl_family_chain(i), family_list) { + if (!rt->netnsok && !net_eq(net, &init_net)) + continue; + if (++n < fams_to_skip) + continue; + if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, CTRL_CMD_NEWFAMILY) < 0) + goto errout; + } + + fams_to_skip = 0; + } + +errout: + cb->args[0] = i; + cb->args[1] = n; + + return skb->len; +} + +static struct sk_buff *ctrl_build_family_msg(struct genl_family *family, + u32 portid, int seq, u8 cmd) +{ + struct sk_buff *skb; + int err; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb == NULL) + return ERR_PTR(-ENOBUFS); + + err = ctrl_fill_info(family, portid, seq, 0, skb, cmd); + if (err < 0) { + nlmsg_free(skb); + return ERR_PTR(err); + } + + return skb; +} + +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; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (skb == NULL) + return ERR_PTR(-ENOBUFS); + + err = ctrl_fill_mcgrp_info(family, grp, grp_id, portid, + seq, 0, skb, cmd); + if (err < 0) { + nlmsg_free(skb); + return ERR_PTR(err); + } + + return skb; +} + +static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = { + [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, + [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, + .len = GENL_NAMSIZ - 1 }, +}; + +static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + struct genl_family *res = NULL; + int err = -EINVAL; + + if (info->attrs[CTRL_ATTR_FAMILY_ID]) { + u16 id = nla_get_u16(info->attrs[CTRL_ATTR_FAMILY_ID]); + res = genl_family_find_byid(id); + err = -ENOENT; + } + + if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { + char *name; + + name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); + res = genl_family_find_byname(name); +#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); + } +#endif + err = -ENOENT; + } + + if (res == NULL) + return err; + + if (!res->netnsok && !net_eq(genl_info_net(info), &init_net)) { + /* family doesn't exist here */ + return -ENOENT; + } + + msg = ctrl_build_family_msg(res, info->snd_portid, info->snd_seq, + CTRL_CMD_NEWFAMILY); + if (IS_ERR(msg)) + return PTR_ERR(msg); + + return genlmsg_reply(msg, info); +} + +static int genl_ctrl_event(int event, struct genl_family *family, + const struct genl_multicast_group *grp, + int grp_id) +{ + struct sk_buff *msg; + + /* genl is still initialising */ + if (!init_net.genl_sock) + return 0; + + switch (event) { + case CTRL_CMD_NEWFAMILY: + case CTRL_CMD_DELFAMILY: + WARN_ON(grp); + msg = ctrl_build_family_msg(family, 0, 0, event); + break; + case CTRL_CMD_NEWMCAST_GRP: + case CTRL_CMD_DELMCAST_GRP: + BUG_ON(!grp); + msg = ctrl_build_mcgrp_msg(family, grp, grp_id, 0, 0, event); + break; + default: + return -EINVAL; + } + + if (IS_ERR(msg)) + return PTR_ERR(msg); + + if (!family->netnsok) { + genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0, + 0, GFP_KERNEL); + } else { + rcu_read_lock(); + 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_multicast_group genl_ctrl_groups[] = { + { .name = "notify", }, +}; + +static int genl_bind(struct net *net, int group) +{ + int i, err = -ENOENT; + + down_read(&cb_lock); + for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { + struct genl_family *f; + + list_for_each_entry(f, genl_family_chain(i), family_list) { + if (group >= f->mcgrp_offset && + group < f->mcgrp_offset + f->n_mcgrps) { + int fam_grp = group - f->mcgrp_offset; + + if (!f->netnsok && net != &init_net) + err = -ENOENT; + else if (f->mcast_bind) + err = f->mcast_bind(net, fam_grp); + else + err = 0; + break; + } + } + } + up_read(&cb_lock); + + return err; +} + +static void genl_unbind(struct net *net, int group) +{ + int i; + + down_read(&cb_lock); + for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { + struct genl_family *f; + + list_for_each_entry(f, genl_family_chain(i), family_list) { + if (group >= f->mcgrp_offset && + group < f->mcgrp_offset + f->n_mcgrps) { + int fam_grp = group - f->mcgrp_offset; + + if (f->mcast_unbind) + f->mcast_unbind(net, fam_grp); + break; + } + } + } + up_read(&cb_lock); +} + +static int __net_init genl_pernet_init(struct net *net) +{ + struct netlink_kernel_cfg cfg = { + .input = genl_rcv, + .flags = NL_CFG_F_NONROOT_RECV, + .bind = genl_bind, + .unbind = genl_unbind, + }; + + /* we'll bump the group number right afterwards */ + net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, &cfg); + + if (!net->genl_sock && net_eq(net, &init_net)) + panic("GENL: Cannot initialize generic netlink\n"); + + if (!net->genl_sock) + return -ENOMEM; + + return 0; +} + +static void __net_exit genl_pernet_exit(struct net *net) +{ + netlink_kernel_release(net->genl_sock); + net->genl_sock = NULL; +} + +static struct pernet_operations genl_pernet_ops = { + .init = genl_pernet_init, + .exit = genl_pernet_exit, +}; + +static int __init genl_init(void) +{ + int i, err; + + for (i = 0; i < GENL_FAM_TAB_SIZE; i++) + INIT_LIST_HEAD(&family_ht[i]); + + err = genl_register_family_with_ops_groups(&genl_ctrl, genl_ctrl_ops, + genl_ctrl_groups); + if (err < 0) + goto problem; + + err = register_pernet_subsys(&genl_pernet_ops); + if (err) + goto problem; + + return 0; + +problem: + panic("GENL: Cannot register controller: %d\n", err); +} + +subsys_initcall(genl_init); + +static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, + gfp_t flags) +{ + struct sk_buff *tmp; + struct net *net, *prev = NULL; + int err; + + for_each_net_rcu(net) { + if (prev) { + tmp = skb_clone(skb, flags); + if (!tmp) { + err = -ENOMEM; + goto error; + } + err = nlmsg_multicast(prev->genl_sock, tmp, + portid, group, flags); + if (err) + goto error; + } + + prev = net; + } + + return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); + error: + kfree_skb(skb); + return err; +} + +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 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; + int report = 0; + + 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); |