Automatic merge with /usr/src/ntfs-2.6.git.

87 files changed, 25295 insertions, 23056 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 062177956239..5d0c4be43dba 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -29,6 +29,7 @@ config EXT2_FS_XATTR
 config EXT2_FS_POSIX_ACL
 	bool "Ext2 POSIX Access Control Lists"
 	depends on EXT2_FS_XATTR
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -114,6 +115,7 @@ config EXT3_FS_XATTR
 config EXT3_FS_POSIX_ACL
 	bool "Ext3 POSIX Access Control Lists"
 	depends on EXT3_FS_XATTR
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -241,6 +243,7 @@ config REISERFS_FS_XATTR
 config REISERFS_FS_POSIX_ACL
 	bool "ReiserFS POSIX Access Control Lists"
 	depends on REISERFS_FS_XATTR
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -274,6 +277,7 @@ config JFS_FS
 config JFS_POSIX_ACL
 	bool "JFS POSIX Access Control Lists"
 	depends on JFS_FS
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -318,8 +322,7 @@ config FS_POSIX_ACL
 # 	Never use this symbol for ifdefs.
 #
 	bool
-	depends on EXT2_FS_POSIX_ACL || EXT3_FS_POSIX_ACL || JFS_POSIX_ACL || REISERFS_FS_POSIX_ACL || NFSD_V4
-	default y
+	default n
 
 source "fs/xfs/Kconfig"
 
@@ -356,6 +359,19 @@ config ROMFS_FS
 	  If you don't know whether you need it, then you don't need it:
 	  answer N.
 
+config INOTIFY
+	bool "Inotify file change notification support"
+	default y
+	---help---
+	  Say Y here to enable inotify support and the /dev/inotify character
+	  device.  Inotify is a file change notification system and a
+	  replacement for dnotify.  Inotify fixes numerous shortcomings in
+	  dnotify and introduces several new features.  It allows monitoring
+	  of both files and directories via a single open fd.  Multiple file
+	  events are supported.
+
+	  If unsure, say Y.
+
 config QUOTA
 	bool "Quota support"
 	help
@@ -1036,26 +1052,18 @@ config JFFS2_FS_DEBUG
 	  If reporting bugs, please try to have available a full dump of the
 	  messages at debug level 1 while the misbehaviour was occurring.
 
-config JFFS2_FS_NAND
-	bool "JFFS2 support for NAND flash"
+config JFFS2_FS_WRITEBUFFER
+	bool "JFFS2 write-buffering support"
 	depends on JFFS2_FS
-	default n
+	default y
 	help
-	  This enables the support for NAND flash in JFFS2. NAND is a newer
-	  type of flash chip design than the traditional NOR flash, with
-	  higher density but a handful of characteristics which make it more
-	  interesting for the file system to use.
-
-	  Say 'N' unless you have NAND flash.
+	  This enables the write-buffering support in JFFS2.
 
-config JFFS2_FS_NOR_ECC
-        bool "JFFS2 support for ECC'd NOR flash (EXPERIMENTAL)"
-        depends on JFFS2_FS && EXPERIMENTAL
-        default n
-        help
-          This enables the experimental support for NOR flash with transparent
-          ECC for JFFS2. This type of flash chip is not common, however it is
-          available from ST Microelectronics.
+	  This functionality is required to support JFFS2 on the following
+	  types of flash devices:
+	    - NAND flash
+	    - NOR flash with transparent ECC
+	    - DataFlash
 
 config JFFS2_COMPRESSION_OPTIONS
 	bool "Advanced compression options for JFFS2"
@@ -1438,6 +1446,7 @@ config NFSD_V4
 	select NFSD_TCP
 	select CRYPTO_MD5
 	select CRYPTO
+	select FS_POSIX_ACL
 	help
 	  If you would like to include the NFSv4 server as well as the NFSv2
 	  and NFSv3 servers, say Y here.  This feature is experimental, and
diff --git a/fs/Makefile b/fs/Makefile
index 20edcf28bfd2..cf95eb894fd5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -12,6 +12,7 @@ obj-y :=	open.o read_write.o file_table.o buffer.o  bio.o super.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
 		ioprio.o
 
+obj-$(CONFIG_INOTIFY)		+= inotify.o
 obj-$(CONFIG_EPOLL)		+= eventpoll.o
 obj-$(CONFIG_COMPAT)		+= compat.o
 
diff --git a/fs/attr.c b/fs/attr.c
index c3c76fe78346..b1796fb9e524 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -10,7 +10,7 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/smp_lock.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
 #include <linux/fcntl.h>
 #include <linux/quotaops.h>
 #include <linux/security.h>
@@ -107,31 +107,8 @@ int inode_setattr(struct inode * inode, struct iattr * attr)
 out:
 	return error;
 }
-
 EXPORT_SYMBOL(inode_setattr);
 
-int setattr_mask(unsigned int ia_valid)
-{
-	unsigned long dn_mask = 0;
-
-	if (ia_valid & ATTR_UID)
-		dn_mask |= DN_ATTRIB;
-	if (ia_valid & ATTR_GID)
-		dn_mask |= DN_ATTRIB;
-	if (ia_valid & ATTR_SIZE)
-		dn_mask |= DN_MODIFY;
-	/* both times implies a utime(s) call */
-	if ((ia_valid & (ATTR_ATIME|ATTR_MTIME)) == (ATTR_ATIME|ATTR_MTIME))
-		dn_mask |= DN_ATTRIB;
-	else if (ia_valid & ATTR_ATIME)
-		dn_mask |= DN_ACCESS;
-	else if (ia_valid & ATTR_MTIME)
-		dn_mask |= DN_MODIFY;
-	if (ia_valid & ATTR_MODE)
-		dn_mask |= DN_ATTRIB;
-	return dn_mask;
-}
-
 int notify_change(struct dentry * dentry, struct iattr * attr)
 {
 	struct inode *inode = dentry->d_inode;
@@ -197,11 +174,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
 	if (ia_valid & ATTR_SIZE)
 		up_write(&dentry->d_inode->i_alloc_sem);
 
-	if (!error) {
-		unsigned long dn_mask = setattr_mask(ia_valid);
-		if (dn_mask)
-			dnotify_parent(dentry, dn_mask);
-	}
+	if (!error)
+		fsnotify_change(dentry, ia_valid);
+
 	return error;
 }
 
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index fa2348dcd671..3df86285a1c7 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -231,8 +231,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 		int type = (notify == NFY_MOUNT ?
 			autofs_ptype_missing : autofs_ptype_expire_multi);
 
-		DPRINTK(("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			(unsigned long) wq->wait_queue_token, wq->len, wq->name, notify));
+		DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			(unsigned long) wq->wait_queue_token, wq->len, wq->name, notify);
 
 		/* autofs4_notify_daemon() may block */
 		autofs4_notify_daemon(sbi, wq, type);
diff --git a/fs/bio.c b/fs/bio.c
index 3a1472acc361..ca8f7a850fe3 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -52,7 +52,7 @@ struct biovec_slab {
  */
 
 #define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
-static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] = {
+static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
 	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
 };
 #undef BV
diff --git a/fs/buffer.c b/fs/buffer.c
index 561e63a14966..6a25d7df89b1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -513,8 +513,8 @@ static void free_more_memory(void)
  */
 static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 {
-	static DEFINE_SPINLOCK(page_uptodate_lock);
 	unsigned long flags;
+	struct buffer_head *first;
 	struct buffer_head *tmp;
 	struct page *page;
 	int page_uptodate = 1;
@@ -536,7 +536,9 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	 * two buffer heads end IO at almost the same time and both
 	 * decide that the page is now completely done.
 	 */
-	spin_lock_irqsave(&page_uptodate_lock, flags);
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -549,7 +551,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 
 	/*
 	 * If none of the buffers had errors and they are all
@@ -561,7 +564,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	return;
 
 still_busy:
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	return;
 }
 
@@ -572,8 +576,8 @@ still_busy:
 void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
 	char b[BDEVNAME_SIZE];
-	static DEFINE_SPINLOCK(page_uptodate_lock);
 	unsigned long flags;
+	struct buffer_head *first;
 	struct buffer_head *tmp;
 	struct page *page;
 
@@ -594,7 +598,10 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		SetPageError(page);
 	}
 
-	spin_lock_irqsave(&page_uptodate_lock, flags);
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+
 	clear_buffer_async_write(bh);
 	unlock_buffer(bh);
 	tmp = bh->b_this_page;
@@ -605,12 +612,14 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	}
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	end_page_writeback(page);
 	return;
 
 still_busy:
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	return;
 }
 
diff --git a/fs/char_dev.c b/fs/char_dev.c
index a69a5d8a406f..3b1b1eefdbb0 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -277,8 +277,9 @@ static struct kobject *cdev_get(struct cdev *p)
 void cdev_put(struct cdev *p)
 {
 	if (p) {
+		struct module *owner = p->owner;
 		kobject_put(&p->kobj);
-		module_put(p->owner);
+		module_put(owner);
 	}
 }
 
diff --git a/fs/compat.c b/fs/compat.c
index 728cd8365384..6b06b6bae35e 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -37,7 +37,7 @@
 #include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/dirent.h>
-#include <linux/dnotify.h>
+#include <linux/fsnotify.h>
 #include <linux/highuid.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/nfsd/nfsd.h>
@@ -1307,9 +1307,13 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 out:
 	if (iov != iovstack)
 		kfree(iov);
-	if ((ret + (type == READ)) > 0)
-		dnotify_parent(file->f_dentry,
-				(type == READ) ? DN_ACCESS : DN_MODIFY);
+	if ((ret + (type == READ)) > 0) {
+		struct dentry *dentry = file->f_dentry;
+		if (type == READ)
+			fsnotify_access(dentry);
+		else
+			fsnotify_modify(dentry);
+	}
 	return ret;
 }
 
diff --git a/fs/dcookies.c b/fs/dcookies.c
index 581aac959cd3..02aa0ddc582a 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -94,12 +94,10 @@ static struct dcookie_struct * alloc_dcookie(struct dentry * dentry,
 	if (!dcs)
 		return NULL;
 
-	atomic_inc(&dentry->d_count);
-	atomic_inc(&vfsmnt->mnt_count);
 	dentry->d_cookie = dcs;
 
-	dcs->dentry = dentry;
-	dcs->vfsmnt = vfsmnt;
+	dcs->dentry = dget(dentry);
+	dcs->vfsmnt = mntget(vfsmnt);
 	hash_dcookie(dcs);
 
 	return dcs;
diff --git a/fs/exec.c b/fs/exec.c
index 48871917d363..222ab1c572d8 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -642,6 +642,18 @@ static inline int de_thread(struct task_struct *tsk)
 	count = 2;
 	if (thread_group_leader(current))
 		count = 1;
+	else {
+		/*
+		 * The SIGALRM timer survives the exec, but needs to point
+		 * at us as the new group leader now.  We have a race with
+		 * a timer firing now getting the old leader, so we need to
+		 * synchronize with any firing (by calling del_timer_sync)
+		 * before we can safely let the old group leader die.
+		 */
+		sig->real_timer.data = (unsigned long)current;
+		if (del_timer_sync(&sig->real_timer))
+			add_timer(&sig->real_timer);
+	}
 	while (atomic_read(&sig->count) > count) {
 		sig->group_exit_task = current;
 		sig->notify_count = count;
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index eed521d22cf0..e977f8566d14 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -2,6 +2,15 @@
 #include <linux/ext2_fs.h>
 
 /*
+ * ext2 mount options
+ */
+struct ext2_mount_options {
+	unsigned long s_mount_opt;
+	uid_t s_resuid;
+	gid_t s_resgid;
+};
+
+/*
  * second extended file system inode data in memory
  */
 struct ext2_inode_info {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 876e391f2871..dcfe331dc4c4 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -936,12 +936,23 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	struct ext2_sb_info * sbi = EXT2_SB(sb);
 	struct ext2_super_block * es;
 	unsigned long old_mount_opt = sbi->s_mount_opt;
+	struct ext2_mount_options old_opts;
+	unsigned long old_sb_flags;
+	int err;
+
+	/* Store the old options */
+	old_sb_flags = sb->s_flags;
+	old_opts.s_mount_opt = sbi->s_mount_opt;
+	old_opts.s_resuid = sbi->s_resuid;
+	old_opts.s_resgid = sbi->s_resgid;
 
 	/*
 	 * Allow the "check" option to be passed as a remount option.
 	 */
-	if (!parse_options (data, sbi))
-		return -EINVAL;
+	if (!parse_options (data, sbi)) {
+		err = -EINVAL;
+		goto restore_opts;
+	}
 
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
@@ -971,7 +982,8 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 			printk("EXT2-fs: %s: couldn't remount RDWR because of "
 			       "unsupported optional features (%x).\n",
 			       sb->s_id, le32_to_cpu(ret));
-			return -EROFS;
+			err = -EROFS;
+			goto restore_opts;
 		}
 		/*
 		 * Mounting a RDONLY partition read-write, so reread and
@@ -984,6 +996,12 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	}
 	ext2_sync_super(sb, es);
 	return 0;
+restore_opts:
+	sbi->s_mount_opt = old_opts.s_mount_opt;
+	sbi->s_resuid = old_opts.s_resuid;
+	sbi->s_resgid = old_opts.s_resgid;