Merge branch 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into stable/for-linus-3.7

* 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (9690 commits)
  x86: Document x86_init.paging.pagetable_init()
  x86: xen: Cleanup and remove x86_init.paging.pagetable_setup_done()
  x86: Move paging_init() call to x86_init.paging.pagetable_init()
  x86: Rename pagetable_setup_start() to pagetable_init()
  x86: Remove base argument from x86_init.paging.pagetable_setup_start
  Linux 3.6-rc5
  HID: tpkbd: work even if the new Lenovo Keyboard driver is not configured
  Remove user-triggerable BUG from mpol_to_str
  xen/pciback: Fix proper FLR steps.
  uml: fix compile error in deliver_alarm()
  dj: memory scribble in logi_dj
  Fix order of arguments to compat_put_time[spec|val]
  xen: Use correct masking in xen_swiotlb_alloc_coherent.
  xen: fix logical error in tlb flushing
  xen/p2m: Fix one-off error in checking the P2M tree directory.
  powerpc: Don't use __put_user() in patch_instruction
  powerpc: Make sure IPI handlers see data written by IPI senders
  powerpc: Restore correct DSCR in context switch
  powerpc: Fix DSCR inheritance in copy_thread()
  powerpc: Keep thread.dscr and thread.dscr_inherit in sync
  ...

1 files changed, 107 insertions, 100 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 641f2e47f16..c5ee4ff6136 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -115,15 +115,24 @@
 #include <net/checksum.h>
 #include <linux/security.h>
 
-struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
+struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
 EXPORT_SYMBOL_GPL(unix_socket_table);
 DEFINE_SPINLOCK(unix_table_lock);
 EXPORT_SYMBOL_GPL(unix_table_lock);
 static atomic_long_t unix_nr_socks;
 
-#define unix_sockets_unbound	(&unix_socket_table[UNIX_HASH_SIZE])
 
-#define UNIX_ABSTRACT(sk)	(unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)
+static struct hlist_head *unix_sockets_unbound(void *addr)
+{
+	unsigned long hash = (unsigned long)addr;
+
+	hash ^= hash >> 16;
+	hash ^= hash >> 8;
+	hash %= UNIX_HASH_SIZE;
+	return &unix_socket_table[UNIX_HASH_SIZE + hash];
+}
+
+#define UNIX_ABSTRACT(sk)	(unix_sk(sk)->addr->hash < UNIX_HASH_SIZE)
 
 #ifdef CONFIG_SECURITY_NETWORK
 static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
@@ -645,7 +654,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock)
 	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->readlock); /* single task reading lock */
 	init_waitqueue_head(&u->peer_wait);
-	unix_insert_socket(unix_sockets_unbound, sk);
+	unix_insert_socket(unix_sockets_unbound(sk), sk);
 out:
 	if (sk == NULL)
 		atomic_long_dec(&unix_nr_socks);
@@ -814,6 +823,34 @@ fail:
 	return NULL;
 }
 
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
+{
+	struct dentry *dentry;
+	struct path path;
+	int err = 0;
+	/*
+	 * Get the parent directory, calculate the hash for last
+	 * component.
+	 */
+	dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+	err = PTR_ERR(dentry);
+	if (IS_ERR(dentry))
+		return err;
+
+	/*
+	 * All right, let's create it.
+	 */
+	err = security_path_mknod(&path, dentry, mode, 0);
+	if (!err) {
+		err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
+		if (!err) {
+			res->mnt = mntget(path.mnt);
+			res->dentry = dget(dentry);
+		}
+	}
+	done_path_create(&path, dentry);
+	return err;
+}
 
 static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
@@ -822,8 +859,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct unix_sock *u = unix_sk(sk);
 	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
 	char *sun_path = sunaddr->sun_path;
-	struct dentry *dentry = NULL;
-	struct path path;
 	int err;
 	unsigned int hash;
 	struct unix_address *addr;
@@ -860,43 +895,23 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	atomic_set(&addr->refcnt, 1);
 
 	if (sun_path[0]) {
-		umode_t mode;
-		err = 0;
-		/*
-		 * Get the parent directory, calculate the hash for last
-		 * component.
-		 */
-		dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-		err = PTR_ERR(dentry);
-		if (IS_ERR(dentry))
-			goto out_mknod_parent;
-
-		/*
-		 * All right, let's create it.
-		 */
-		mode = S_IFSOCK |
+		struct path path;
+		umode_t mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = mnt_want_write(path.mnt);
-		if (err)
-			goto out_mknod_dput;
-		err = security_path_mknod(&path, dentry, mode, 0);
-		if (err)
-			goto out_mknod_drop_write;
-		err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
-out_mknod_drop_write:
-		mnt_drop_write(path.mnt);
-		if (err)
-			goto out_mknod_dput;
-		mutex_unlock(&path.dentry->d_inode->i_mutex);
-		dput(path.dentry);
-		path.dentry = dentry;
-
+		err = unix_mknod(sun_path, mode, &path);
+		if (err) {
+			if (err == -EEXIST)
+				err = -EADDRINUSE;
+			unix_release_addr(addr);
+			goto out_up;
+		}
 		addr->hash = UNIX_HASH_SIZE;
-	}
-
-	spin_lock(&unix_table_lock);
-
-	if (!sun_path[0]) {
+		hash = path.dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1);
+		spin_lock(&unix_table_lock);
+		u->path = path;
+		list = &unix_socket_table[hash];
+	} else {
+		spin_lock(&unix_table_lock);
 		err = -EADDRINUSE;
 		if (__unix_find_socket_byname(net, sunaddr, addr_len,
 					      sk->sk_type, hash)) {
@@ -905,9 +920,6 @@ out_mknod_drop_write:
 		}
 
 		list = &unix_socket_table[addr->hash];
-	} else {
-		list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
-		u->path = path;
 	}
 
 	err = 0;
@@ -921,16 +933,6 @@ out_up:
 	mutex_unlock(&u->readlock);
 out:
 	return err;
-
-out_mknod_dput:
-	dput(dentry);
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
-	path_put(&path);
-out_mknod_parent:
-	if (err == -EEXIST)
-		err = -EADDRINUSE;
-	unix_release_addr(addr);
-	goto out_up;
 }
 
 static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
@@ -1448,7 +1450,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm);
+	err = scm_send(sock, msg, siocb->scm, false);
 	if (err < 0)
 		return err;
 
@@ -1617,7 +1619,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (NULL == siocb->scm)
 		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm);
+	err = scm_send(sock, msg, siocb->scm, false);
 	if (err < 0)
 		return err;
 
@@ -2239,47 +2241,54 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 }
 
 #ifdef CONFIG_PROC_FS
-static struct sock *first_unix_socket(int *i)
+
+#define BUCKET_SPACE (BITS_PER_LONG - (UNIX_HASH_BITS + 1) - 1)
+
+#define get_bucket(x) ((x) >> BUCKET_SPACE)
+#define get_offset(x) ((x) & ((1L << BUCKET_SPACE) - 1))
+#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
+
+static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos)
 {
-	for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) {
-		if (!hlist_empty(&unix_socket_table[*i]))
-			return __sk_head(&unix_socket_table[*i]);
+	unsigned long offset = get_offset(*pos);
+	unsigned long bucket = get_bucket(*pos);
+	struct sock *sk;
+	unsigned long count = 0;
+
+	for (sk = sk_head(&unix_socket_table[bucket]); sk; sk = sk_next(sk)) {
+		if (sock_net(sk) != seq_file_net(seq))
+			continue;
+		if (++count == offset)
+			break;
 	}
-	return NULL;
+
+	return sk;
 }
 
-static struct sock *next_unix_socket(int *i, struct sock *s)
+static struct sock *unix_next_socket(struct seq_file *seq,
+				     struct sock *sk,
+				     loff_t *pos)
 {
-	struct sock *next = sk_next(s);
-	/* More in this chain? */
-	if (next)
-		return next;
-	/* Look for next non-empty chain. */
-	for ((*i)++; *i <= UNIX_HASH_SIZE; (*i)++) {
-		if (!hlist_empty(&unix_socket_table[*i]))
-			return __sk_head(&unix_socket_table[*i]);
+	unsigned long bucket;
+
+	while (sk > (struct sock *)SEQ_START_TOKEN) {
+		sk = sk_next(sk);
+		if (!sk)
+			goto next_bucket;
+		if (sock_net(sk) == seq_file_net(seq))
+			return sk;
 	}
-	return NULL;
-}
 
-struct unix_iter_state {
-	struct seq_net_private p;
-	int i;
-};
+	do {
+		sk = unix_from_bucket(seq, pos);
+		if (sk)
+			return sk;
 
-static struct sock *unix_seq_idx(struct seq_file *seq, loff_t pos)
-{
-	struct unix_iter_state *iter = seq->private;
-	loff_t off = 0;
-	struct sock *s;
+next_bucket:
+		bucket = get_bucket(*pos) + 1;
+		*pos = set_bucket_offset(bucket, 1);
+	} while (bucket < ARRAY_SIZE(unix_socket_table));
 
-	for (s = first_unix_socket(&iter->i); s; s = next_unix_socket(&iter->i, s)) {
-		if (sock_net(s) != seq_file_net(seq))
-			continue;
-		if (off == pos)
-			return s;
-		++off;
-	}
 	return NULL;
 }
 
@@ -2287,22 +2296,20 @@ static void *unix_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(unix_table_lock)
 {
 	spin_lock(&unix_table_lock);
-	return *pos ? unix_seq_idx(seq, *pos - 1) : SEQ_START_TOKEN;
+
+	if (!*pos)
+		return SEQ_START_TOKEN;
+
+	if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table))
+		return NULL;
+
+	return unix_next_socket(seq, NULL, pos);
 }
 
 static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct unix_iter_state *iter = seq->private;
-	struct sock *sk = v;
 	++*pos;
-
-	if (v == SEQ_START_TOKEN)
-		sk = first_unix_socket(&iter->i);
-	else
-		sk = next_unix_socket(&iter->i, sk);
-	while (sk && (sock_net(sk) != seq_file_net(seq)))
-		sk = next_unix_socket(&iter->i, sk);
-	return sk;
+	return unix_next_socket(seq, v, pos);
 }
 
 static void unix_seq_stop(struct seq_file *seq, void *v)
@@ -2365,7 +2372,7 @@ static const struct seq_operations unix_seq_ops = {
 static int unix_seq_open(struct inode *inode, struct file *file)
 {
 	return seq_open_net(inode, file, &unix_seq_ops,
-			    sizeof(struct unix_iter_state));
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations unix_seq_fops = {