#include "scm.h"
-spinlock_t unix_table_locks[2 * UNIX_HASH_SIZE];
-EXPORT_SYMBOL_GPL(unix_table_locks);
-struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
-EXPORT_SYMBOL_GPL(unix_socket_table);
static atomic_long_t unix_nr_socks;
+static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
+static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
/* SMP locking strategy:
- * hash table is protected with spinlock unix_table_locks
- * each socket state is protected by separate spin lock.
+ * hash table is protected with spinlock.
+ * each socket state is protected by separate spinlock.
*/
static unsigned int unix_unbound_hash(struct sock *sk)
hash ^= hash >> 8;
hash ^= sk->sk_type;
- return UNIX_HASH_SIZE + (hash & (UNIX_HASH_SIZE - 1));
+ return hash & UNIX_HASH_MOD;
}
static unsigned int unix_bsd_hash(struct inode *i)
{
- return i->i_ino & (UNIX_HASH_SIZE - 1);
+ return i->i_ino & UNIX_HASH_MOD;
}
static unsigned int unix_abstract_hash(struct sockaddr_un *sunaddr,
hash ^= hash >> 8;
hash ^= type;
- return hash & (UNIX_HASH_SIZE - 1);
+ return UNIX_HASH_MOD + 1 + (hash & UNIX_HASH_MOD);
}
-static void unix_table_double_lock(unsigned int hash1, unsigned int hash2)
+static void unix_table_double_lock(struct net *net,
+ unsigned int hash1, unsigned int hash2)
{
- /* hash1 and hash2 is never the same because
- * one is between 0 and UNIX_HASH_SIZE - 1, and
- * another is between UNIX_HASH_SIZE and UNIX_HASH_SIZE * 2.
- */
+ if (hash1 == hash2) {
+ spin_lock(&net->unx.table.locks[hash1]);
+ return;
+ }
+
if (hash1 > hash2)
swap(hash1, hash2);
- spin_lock(&unix_table_locks[hash1]);
- spin_lock_nested(&unix_table_locks[hash2], SINGLE_DEPTH_NESTING);
+ spin_lock(&net->unx.table.locks[hash1]);
+ spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING);
}
-static void unix_table_double_unlock(unsigned int hash1, unsigned int hash2)
+static void unix_table_double_unlock(struct net *net,
+ unsigned int hash1, unsigned int hash2)
{
- spin_unlock(&unix_table_locks[hash1]);
- spin_unlock(&unix_table_locks[hash2]);
+ if (hash1 == hash2) {
+ spin_unlock(&net->unx.table.locks[hash1]);
+ return;
+ }
+
+ spin_unlock(&net->unx.table.locks[hash1]);
+ spin_unlock(&net->unx.table.locks[hash2]);
}
#ifdef CONFIG_SECURITY_NETWORK
sk_del_node_init(sk);
}
-static void __unix_insert_socket(struct sock *sk)
+static void __unix_insert_socket(struct net *net, struct sock *sk)
{
DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk));
- sk_add_node(sk, &unix_socket_table[sk->sk_hash]);
+ sk_add_node(sk, &net->unx.table.buckets[sk->sk_hash]);
}
-static void __unix_set_addr_hash(struct sock *sk, struct unix_address *addr,
- unsigned int hash)
+static void __unix_set_addr_hash(struct net *net, struct sock *sk,
+ struct unix_address *addr, unsigned int hash)
{
__unix_remove_socket(sk);
smp_store_release(&unix_sk(sk)->addr, addr);
sk->sk_hash = hash;
- __unix_insert_socket(sk);
+ __unix_insert_socket(net, sk);
}
-static void unix_remove_socket(struct sock *sk)
+static void unix_remove_socket(struct net *net, struct sock *sk)
{
- spin_lock(&unix_table_locks[sk->sk_hash]);
+ spin_lock(&net->unx.table.locks[sk->sk_hash]);
__unix_remove_socket(sk);
- spin_unlock(&unix_table_locks[sk->sk_hash]);
+ spin_unlock(&net->unx.table.locks[sk->sk_hash]);
+}
+
+static void unix_insert_unbound_socket(struct net *net, struct sock *sk)
+{
+ spin_lock(&net->unx.table.locks[sk->sk_hash]);
+ __unix_insert_socket(net, sk);
+ spin_unlock(&net->unx.table.locks[sk->sk_hash]);
+}
+
+static void unix_insert_bsd_socket(struct sock *sk)
+{
+ spin_lock(&bsd_socket_locks[sk->sk_hash]);
+ sk_add_bind_node(sk, &bsd_socket_buckets[sk->sk_hash]);
+ spin_unlock(&bsd_socket_locks[sk->sk_hash]);
}
-static void unix_insert_unbound_socket(struct sock *sk)
+static void unix_remove_bsd_socket(struct sock *sk)
{
- spin_lock(&unix_table_locks[sk->sk_hash]);
- __unix_insert_socket(sk);
- spin_unlock(&unix_table_locks[sk->sk_hash]);
+ if (!hlist_unhashed(&sk->sk_bind_node)) {
+ spin_lock(&bsd_socket_locks[sk->sk_hash]);
+ __sk_del_bind_node(sk);
+ spin_unlock(&bsd_socket_locks[sk->sk_hash]);
+
+ sk_node_init(&sk->sk_bind_node);
+ }
}
static struct sock *__unix_find_socket_byname(struct net *net,
{
struct sock *s;
- sk_for_each(s, &unix_socket_table[hash]) {
+ sk_for_each(s, &net->unx.table.buckets[hash]) {
struct unix_sock *u = unix_sk(s);
- if (!net_eq(sock_net(s), net))
- continue;
-
if (u->addr->len == len &&
!memcmp(u->addr->name, sunname, len))
return s;
{
struct sock *s;
- spin_lock(&unix_table_locks[hash]);
+ spin_lock(&net->unx.table.locks[hash]);
s = __unix_find_socket_byname(net, sunname, len, hash);
if (s)
sock_hold(s);
- spin_unlock(&unix_table_locks[hash]);
+ spin_unlock(&net->unx.table.locks[hash]);
return s;
}
unsigned int hash = unix_bsd_hash(i);
struct sock *s;
- spin_lock(&unix_table_locks[hash]);
- sk_for_each(s, &unix_socket_table[hash]) {
+ spin_lock(&bsd_socket_locks[hash]);
+ sk_for_each_bound(s, &bsd_socket_buckets[hash]) {
struct dentry *dentry = unix_sk(s)->path.dentry;
if (dentry && d_backing_inode(dentry) == i) {
sock_hold(s);
- spin_unlock(&unix_table_locks[hash]);
+ spin_unlock(&bsd_socket_locks[hash]);
return s;
}
}
- spin_unlock(&unix_table_locks[hash]);
+ spin_unlock(&bsd_socket_locks[hash]);
return NULL;
}
static void unix_release_sock(struct sock *sk, int embrion)
{
struct unix_sock *u = unix_sk(sk);
- struct path path;
struct sock *skpair;
struct sk_buff *skb;
+ struct path path;
int state;
- unix_remove_socket(sk);
+ unix_remove_socket(sock_net(sk), sk);
+ unix_remove_bsd_socket(sk);
/* Clear state */
unix_state_lock(sk);
init_waitqueue_head(&u->peer_wait);
init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
memset(&u->scm_stat, 0, sizeof(struct scm_stat));
- unix_insert_unbound_socket(sk);
+ unix_insert_unbound_socket(net, sk);
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+ sock_prot_inuse_add(net, sk->sk_prot, 1);
return sk;
return 0;
}
-static struct sock *unix_find_bsd(struct net *net, struct sockaddr_un *sunaddr,
- int addr_len, int type)
+static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len,
+ int type)
{
struct inode *inode;
struct path path;
struct sock *sk;
if (sunaddr->sun_path[0])
- sk = unix_find_bsd(net, sunaddr, addr_len, type);
+ sk = unix_find_bsd(sunaddr, addr_len, type);
else
sk = unix_find_abstract(net, sunaddr, addr_len, type);
{
unsigned int new_hash, old_hash = sk->sk_hash;
struct unix_sock *u = unix_sk(sk);
+ struct net *net = sock_net(sk);
struct unix_address *addr;
u32 lastnum, ordernum;
int err;
sprintf(addr->name->sun_path + 1, "%05x", ordernum);
new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type);
- unix_table_double_lock(old_hash, new_hash);
+ unix_table_double_lock(net, old_hash, new_hash);
- if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len,
- new_hash)) {
- unix_table_double_unlock(old_hash, new_hash);
+ if (__unix_find_socket_byname(net, addr->name, addr->len, new_hash)) {
+ unix_table_double_unlock(net, old_hash, new_hash);
/* __unix_find_socket_byname() may take long time if many names
* are already in use.
goto retry;
}
- __unix_set_addr_hash(sk, addr, new_hash);
- unix_table_double_unlock(old_hash, new_hash);
+ __unix_set_addr_hash(net, sk, addr, new_hash);
+ unix_table_double_unlock(net, old_hash, new_hash);
err = 0;
out: mutex_unlock(&u->bindlock);
(SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask());
unsigned int new_hash, old_hash = sk->sk_hash;
struct unix_sock *u = unix_sk(sk);
+ struct net *net = sock_net(sk);
struct user_namespace *ns; // barf...
struct unix_address *addr;
struct dentry *dentry;
goto out_unlock;
new_hash = unix_bsd_hash(d_backing_inode(dentry));
- unix_table_double_lock(old_hash, new_hash);
+ unix_table_double_lock(net, old_hash, new_hash);
u->path.mnt = mntget(parent.mnt);
u->path.dentry = dget(dentry);
- __unix_set_addr_hash(sk, addr, new_hash);
- unix_table_double_unlock(old_hash, new_hash);
+ __unix_set_addr_hash(net, sk, addr, new_hash);
+ unix_table_double_unlock(net, old_hash, new_hash);
+ unix_insert_bsd_socket(sk);
mutex_unlock(&u->bindlock);
done_path_create(&parent, dentry);
return 0;
{
unsigned int new_hash, old_hash = sk->sk_hash;
struct unix_sock *u = unix_sk(sk);
+ struct net *net = sock_net(sk);
struct unix_address *addr;
int err;
}
new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type);
- unix_table_double_lock(old_hash, new_hash);
+ unix_table_double_lock(net, old_hash, new_hash);
- if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len,
- new_hash))
+ if (__unix_find_socket_byname(net, addr->name, addr->len, new_hash))
goto out_spin;
- __unix_set_addr_hash(sk, addr, new_hash);
- unix_table_double_unlock(old_hash, new_hash);
+ __unix_set_addr_hash(net, sk, addr, new_hash);
+ unix_table_double_unlock(net, old_hash, new_hash);
mutex_unlock(&u->bindlock);
return 0;
out_spin:
- unix_table_double_unlock(old_hash, new_hash);
+ unix_table_double_unlock(net, old_hash, new_hash);
err = -EADDRINUSE;
out_mutex:
mutex_unlock(&u->bindlock);
static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
int alen, int flags)
{
- struct sock *sk = sock->sk;
- struct net *net = sock_net(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr;
+ struct sock *sk = sock->sk;
struct sock *other;
int err;
}
restart:
- other = unix_find_other(net, sunaddr, alen, sock->type);
+ other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type);
if (IS_ERR(other)) {
err = PTR_ERR(other);
goto out;
int addr_len, int flags)
{
struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
- struct sock *sk = sock->sk;
- struct net *net = sock_net(sk);
+ struct sock *sk = sock->sk, *newsk = NULL, *other = NULL;
struct unix_sock *u = unix_sk(sk), *newu, *otheru;
- struct sock *newsk = NULL;
- struct sock *other = NULL;
+ struct net *net = sock_net(sk);
struct sk_buff *skb = NULL;
- int st;
- int err;
long timeo;
+ int err;
+ int st;
err = unix_validate_addr(sunaddr, addr_len);
if (err)
*/
/* create new sock for complete connection */
- newsk = unix_create1(sock_net(sk), NULL, 0, sock->type);
+ newsk = unix_create1(net, NULL, 0, sock->type);
if (IS_ERR(newsk)) {
err = PTR_ERR(newsk);
newsk = NULL;
*
* The contents of *(otheru->addr) and otheru->path
* are seen fully set up here, since we have found
- * otheru in hash under unix_table_locks. Insertion
- * into the hash chain we'd found it in had been done
- * in an earlier critical area protected by unix_table_locks,
+ * otheru in hash under its lock. Insertion into the
+ * hash chain we'd found it in had been done in an
+ * earlier critical area protected by the chain's lock,
* the same one where we'd set *(otheru->addr) contents,
* as well as otheru->path and otheru->addr itself.
*
static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
size_t len)
{
- struct sock *sk = sock->sk;
- struct net *net = sock_net(sk);
- struct unix_sock *u = unix_sk(sk);
DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
- struct sock *other = NULL;
- int err;
- struct sk_buff *skb;
- long timeo;
+ struct sock *sk = sock->sk, *other = NULL;
+ struct unix_sock *u = unix_sk(sk);
struct scm_cookie scm;
+ struct sk_buff *skb;
int data_len = 0;
int sk_locked;
+ long timeo;
+ int err;
wait_for_unix_gc();
err = scm_send(sock, msg, &scm, false);
if (sunaddr == NULL)
goto out_free;
- other = unix_find_other(net, sunaddr, msg->msg_namelen,
+ other = unix_find_other(sock_net(sk), sunaddr, msg->msg_namelen,
sk->sk_type);
if (IS_ERR(other)) {
err = PTR_ERR(other);
{
unsigned long offset = get_offset(*pos);
unsigned long bucket = get_bucket(*pos);
- struct sock *sk;
unsigned long count = 0;
+ struct sock *sk;
- for (sk = sk_head(&unix_socket_table[bucket]); sk; sk = sk_next(sk)) {
- if (sock_net(sk) != seq_file_net(seq))
- continue;
+ for (sk = sk_head(&seq_file_net(seq)->unx.table.buckets[bucket]);
+ sk; sk = sk_next(sk)) {
if (++count == offset)
break;
}
static struct sock *unix_get_first(struct seq_file *seq, loff_t *pos)
{
unsigned long bucket = get_bucket(*pos);
+ struct net *net = seq_file_net(seq);
struct sock *sk;
- while (bucket < ARRAY_SIZE(unix_socket_table)) {
- spin_lock(&unix_table_locks[bucket]);
+ while (bucket < UNIX_HASH_SIZE) {
+ spin_lock(&net->unx.table.locks[bucket]);
sk = unix_from_bucket(seq, pos);
if (sk)
return sk;
- spin_unlock(&unix_table_locks[bucket]);
+ spin_unlock(&net->unx.table.locks[bucket]);
*pos = set_bucket_offset(++bucket, 1);
}
{
unsigned long bucket = get_bucket(*pos);
- for (sk = sk_next(sk); sk; sk = sk_next(sk))
- if (sock_net(sk) == seq_file_net(seq))
- return sk;
+ sk = sk_next(sk);
+ if (sk)
+ return sk;
+
- spin_unlock(&unix_table_locks[bucket]);
+ spin_unlock(&seq_file_net(seq)->unx.table.locks[bucket]);
*pos = set_bucket_offset(++bucket, 1);
struct sock *sk = v;
if (sk)
- spin_unlock(&unix_table_locks[sk->sk_hash]);
+ spin_unlock(&seq_file_net(seq)->unx.table.locks[sk->sk_hash]);
}
static int unix_seq_show(struct seq_file *seq, void *v)
(s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING),
sock_i_ino(s));
- if (u->addr) { // under unix_table_locks here
+ if (u->addr) { // under a hash table lock here
int i, len;
seq_putc(seq, ' ');
iter->batch[iter->end_sk++] = start_sk;
for (sk = sk_next(start_sk); sk; sk = sk_next(sk)) {
- if (sock_net(sk) != seq_file_net(seq))
- continue;
-
if (iter->end_sk < iter->max_sk) {
sock_hold(sk);
iter->batch[iter->end_sk++] = sk;
expected++;
}
- spin_unlock(&unix_table_locks[start_sk->sk_hash]);
+ spin_unlock(&seq_file_net(seq)->unx.table.locks[start_sk->sk_hash]);
return expected;
}
static int __net_init unix_net_init(struct net *net)
{
- int error = -ENOMEM;
+ int i;
net->unx.sysctl_max_dgram_qlen = 10;
if (unix_sysctl_register(net))
#ifdef CONFIG_PROC_FS
if (!proc_create_net("unix", 0, net->proc_net, &unix_seq_ops,
- sizeof(struct seq_net_private))) {
- unix_sysctl_unregister(net);
- goto out;
+ sizeof(struct seq_net_private)))
+ goto err_sysctl;
+#endif
+
+ net->unx.table.locks = kvmalloc_array(UNIX_HASH_SIZE,
+ sizeof(spinlock_t), GFP_KERNEL);
+ if (!net->unx.table.locks)
+ goto err_proc;
+
+ net->unx.table.buckets = kvmalloc_array(UNIX_HASH_SIZE,
+ sizeof(struct hlist_head),
+ GFP_KERNEL);
+ if (!net->unx.table.buckets)
+ goto free_locks;
+
+ for (i = 0; i < UNIX_HASH_SIZE; i++) {
+ spin_lock_init(&net->unx.table.locks[i]);
+ INIT_HLIST_HEAD(&net->unx.table.buckets[i]);
}
+
+ return 0;
+
+free_locks:
+ kvfree(net->unx.table.locks);
+err_proc:
+#ifdef CONFIG_PROC_FS
+ remove_proc_entry("unix", net->proc_net);
+err_sysctl:
#endif
- error = 0;
+ unix_sysctl_unregister(net);
out:
- return error;
+ return -ENOMEM;
}
static void __net_exit unix_net_exit(struct net *net)
{
+ kvfree(net->unx.table.buckets);
+ kvfree(net->unx.table.locks);
unix_sysctl_unregister(net);
remove_proc_entry("unix", net->proc_net);
}
BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb));
- for (i = 0; i < 2 * UNIX_HASH_SIZE; i++)
- spin_lock_init(&unix_table_locks[i]);
+ for (i = 0; i < UNIX_HASH_SIZE / 2; i++) {
+ spin_lock_init(&bsd_socket_locks[i]);
+ INIT_HLIST_HEAD(&bsd_socket_buckets[i]);
+ }
rc = proto_register(&unix_dgram_proto, 1);
if (rc != 0) {
projects / linux-2.6-microblaze.git / blobdiff