Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull ext3 improvements, cleanups, reiserfs fix from Jan Kara:
 "various cleanups for ext2, ext3, udf, isofs, a documentation update
  for quota, and a fix of a race in reiserfs readdir implementation"

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  reiserfs: fix race in readdir
  ext2: acl: remove unneeded include of linux/capability.h
  ext3: explicitly remove inode from orphan list after failed direct io
  fs/isofs/inode.c add __init to init_inodecache()
  ext3: Speedup WB_SYNC_ALL pass
  fs/quota/Kconfig: Update filesystems
  ext3: Update outdated comment before ext3_ordered_writepage()
  ext3: Update PF_MEMALLOC handling in ext3_write_inode()
  ext2/3: use prandom_u32() instead of get_random_bytes()
  ext3: remove an unneeded check in ext3_new_blocks()
  ext3: remove unneeded check in ext3_ordered_writepage()
  fs: Mark function as static in ext3/xattr_security.c
  fs: Mark function as static in ext3/dir.c
  fs: Mark function as static in ext2/xattr_security.c
  ext3: Add __init macro to init_inodecache
  ext2: Add __init macro to init_inodecache
  udf: Add __init macro to init_inodecache
  fs: udf: parse_options: blocksize check

14 files changed, 51 insertions, 83 deletions

diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 1b8001b..27695e6 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -4,7 +4,6 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
-#include <linux/capability.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 7cadd82..7d66fb0 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -284,7 +284,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 		int best_ndir = inodes_per_group;
 		int best_group = -1;
 
-		get_random_bytes(&group, sizeof(group));
+		group = prandom_u32();
 		parent_group = (unsigned)group % ngroups;
 		for (i = 0; i < ngroups; i++) {
 			group = (parent_group + i) % ngroups;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index d260115..3750031 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -192,7 +192,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	ext2_inode_cachep = kmem_cache_create("ext2_inode_cache",
 					     sizeof(struct ext2_inode_info),
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index cfedb2c..c0ebc4d 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -42,8 +42,8 @@ ext2_xattr_security_set(struct dentry *dentry, const char *name,
 			      value, size, flags);
 }
 
-int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
-		    void *fs_info)
+static int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+			   void *fs_info)
 {
 	const struct xattr *xattr;
 	int err = 0;
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 22548f5..158b5d4 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -1727,10 +1727,7 @@ allocated:
 	percpu_counter_sub(&sbi->s_freeblocks_counter, num);
 
 	BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
-	err = ext3_journal_dirty_metadata(handle, gdp_bh);
-	if (!fatal)
-		fatal = err;
-
+	fatal = ext3_journal_dirty_metadata(handle, gdp_bh);
 	if (fatal)
 		goto out;
 
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index e66e480..17742ee 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -275,7 +275,7 @@ static inline loff_t ext3_get_htree_eof(struct file *filp)
  * NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX)
  *       will be invalid once the directory was converted into a dx directory
  */
-loff_t ext3_dir_llseek(struct file *file, loff_t offset, int whence)
+static loff_t ext3_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
 	int dx_dir = is_dx_dir(inode);
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 082afd7..a1b8102 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -215,7 +215,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
 		int best_ndir = inodes_per_group;
 		int best_group = -1;
 
-		get_random_bytes(&group, sizeof(group));
+		group = prandom_u32();
 		parent_group = (unsigned)group % ngroups;
 		for (i = 0; i < ngroups; i++) {
 			group = (parent_group + i) % ngroups;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index efce2bb..f5157d0 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1559,56 +1559,17 @@ static int buffer_unmapped(handle_t *handle, struct buffer_head *bh)
 }
 
 /*
- * Note that we always start a transaction even if we're not journalling
- * data.  This is to preserve ordering: any hole instantiation within
- * __block_write_full_page -> ext3_get_block() should be journalled
- * along with the data so we don't crash and then get metadata which
+ * Note that whenever we need to map blocks we start a transaction even if
+ * we're not journalling data.  This is to preserve ordering: any hole
+ * instantiation within __block_write_full_page -> ext3_get_block() should be
+ * journalled along with the data so we don't crash and then get metadata which
  * refers to old data.
  *
  * In all journalling modes block_write_full_page() will start the I/O.
  *
- * Problem:
- *
- *	ext3_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
- *		ext3_writepage()
- *
- * Similar for:
- *
- *	ext3_file_write() -> generic_file_write() -> __alloc_pages() -> ...
- *
- * Same applies to ext3_get_block().  We will deadlock on various things like
- * lock_journal and i_truncate_mutex.
- *
- * Setting PF_MEMALLOC here doesn't work - too many internal memory
- * allocations fail.
- *
- * 16May01: If we're reentered then journal_current_handle() will be
- *	    non-zero. We simply *return*.
- *
- * 1 July 2001: @@@ FIXME:
- *   In journalled data mode, a data buffer may be metadata against the
- *   current transaction.  But the same file is part of a shared mapping
- *   and someone does a writepage() on it.
- *
- *   We will move the buffer onto the async_data list, but *after* it has
- *   been dirtied. So there's a small window where we have dirty data on
- *   BJ_Metadata.
- *
- *   Note that this only applies to the last partial page in the file.  The
- *   bit which block_write_full_page() uses prepare/commit for.  (That's
- *   broken code anyway: it's wrong for msync()).
- *
- *   It's a rare case: affects the final partial page, for journalled data
- *   where the file is subject to bith write() and writepage() in the same
- *   transction.  To fix it we'll need a custom block_write_full_page().
- *   We'll probably need that anyway for journalling writepage() output.
- *
  * We don't honour synchronous mounts for writepage().  That would be
  * disastrous.  Any write() or metadata operation will sync the fs for
  * us.
- *
- * AKPM2: if all the page's buffers are mapped to disk and !data=journal,
- * we don't need to open a transaction here.
  */
 static int ext3_ordered_writepage(struct page *page,
 				struct writeback_control *wbc)
@@ -1673,12 +1634,9 @@ static int ext3_ordered_writepage(struct page *page,
 	 * block_write_full_page() succeeded.  Otherwise they are unmapped,
 	 * and generally junk.
 	 */
-	if (ret == 0) {
-		err = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
+	if (ret == 0)
+		ret = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
 					NULL, journal_dirty_data_fn);
-		if (!ret)
-			ret = err;
-	}
 	walk_page_buffers(handle, page_bufs, 0,
 			PAGE_CACHE_SIZE, NULL, bput_one);
 	err = ext3_journal_stop(handle);
@@ -1925,6 +1883,8 @@ retry:
 			 * and pretend the write failed... */
 			ext3_truncate_failed_direct_write(inode);
 			ret = PTR_ERR(handle);
+			if (inode->i_nlink)
+				ext3_orphan_del(NULL, inode);
 			goto out;
 		}
 		if (inode->i_nlink)
@@ -3212,21 +3172,20 @@ out_brelse:
  *
  * We are called from a few places:
  *
- * - Within generic_file_write() for O_SYNC files.
+ * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files.
  *   Here, there will be no transaction running. We wait for any running
  *   transaction to commit.
  *
- * - Within sys_sync(), kupdate and such.
- *   We wait on commit, if tol to.
+ * - Within flush work (for sys_sync(), kupdate and such).
+ *   We wait on commit, if told to.
  *
- * - Within prune_icache() (PF_MEMALLOC == true)
- *   Here we simply return.  We can't afford to block kswapd on the
- *   journal commit.
+ * - Within iput_final() -> write_inode_now()
+ *   We wait on commit, if told to.
  *
  * In all cases it is actually safe for us to return without doing anything,
  * because the inode has been copied into a raw inode buffer in
- * ext3_mark_inode_dirty().  This is a correctness thing for O_SYNC and for
- * knfsd.
+ * ext3_mark_inode_dirty().  This is a correctness thing for WB_SYNC_ALL
+ * writeback.
  *
  * Note that we are absolutely dependent upon all inode dirtiers doing the
  * right thing: they *must* call mark_inode_dirty() after dirtying info in
@@ -3238,13 +3197,13 @@ out_brelse:
  *	stuff();
  *	inode->i_size = expr;
  *
- * is in error because a kswapd-driven write_inode() could occur while
- * `stuff()' is running, and the new i_size will be lost.  Plus the inode
- * will no longer be on the superblock's dirty inode list.
+ * is in error because write_inode() could occur while `stuff()' is running,
+ * and the new i_size will be lost.  Plus the inode will no longer be on the
+ * superblock's dirty inode list.
  */
 int ext3_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-	if (current->flags & PF_MEMALLOC)
+	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
 		return 0;
 
 	if (ext3_journal_current_handle()) {
@@ -3253,7 +3212,12 @@ int ext3_write_inode(struct inode *inode, struct writeback_control *wbc)
 		return -EIO;
 	}
 
-	if (wbc->sync_mode != WB_SYNC_ALL)
+	/*
+	 * No need to force transaction in WB_SYNC_NONE mode. Also
+	 * ext3_sync_fs() will force the commit after everything is
+	 * written.
+	 */
+	if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
 		return 0;
 
 	return ext3_force_commit(inode->i_sb);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 95c6c5a..08cdfe5 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -527,7 +527,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	ext3_inode_cachep = kmem_cache_create("ext3_inode_cache",
 					     sizeof(struct ext3_inode_info),
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 3387664..722c2bf 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -43,8 +43,9 @@ ext3_xattr_security_set(struct dentry *dentry, const char *name,
 			      name, value, size, flags);
 }
 
-int ext3_initxattrs(struct inode *inode, const struct xattr *xattr_array,
-		    void *fs_info)
+static int ext3_initxattrs(struct inode *inode,
+			   const struct xattr *xattr_array,
+			   void *fs_info)
 {
 	const struct xattr *xattr;
 	handle_t *handle = fs_info;
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 6af66ee..4556ce1 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -93,7 +93,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	isofs_inode_cachep = kmem_cache_create("isofs_inode_cache",
 					sizeof(struct iso_inode_info),
diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index 880fd98..c51df1d 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -8,9 +8,10 @@ config QUOTA
 	help
 	  If you say Y here, you will be able to set per user limits for disk
 	  usage (also called disk quotas). Currently, it works for the
-	  ext2, ext3, and reiserfs file system. ext3 also supports journalled
-	  quotas for which you don't need to run quotacheck(8) after an unclean
-	  shutdown.
+	  ext2, ext3, ext4, jfs, ocfs2 and reiserfs file systems.
+	  Note that gfs2 and xfs use their own quota system.
+	  Ext3, ext4 and reiserfs also support journaled quotas for which
+	  you don't need to run quotacheck(8) after an unclean shutdown.
 	  For further details, read the Quota mini-HOWTO, available from
 	  <http://www.tldp.org/docs.html#howto>, or the documentation provided
 	  with the quota tools. Probably the quota support is only useful for
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 1fd2051..af67735 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -125,6 +125,7 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 				int d_reclen;
 				char *d_name;
 				ino_t d_ino;
+				loff_t cur_pos = deh_offset(deh);
 
 				if (!de_visible(deh))
 					/* it is hidden entry */
@@ -196,8 +197,9 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 				if (local_buf != small_buf) {
 					kfree(local_buf);
 				}
-				// next entry should be looked for with such offset
-				next_pos = deh_offset(deh) + 1;
+
+				/* deh_offset(deh) may be invalid now. */
+				next_pos = cur_pos + 1;
 
 				if (item_moved(&tmp_ih, &path_to_entry)) {
 					set_cpu_key_k_offset(&pos_key,
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 64f2b73..3286db0 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -175,7 +175,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-static int init_inodecache(void)
+static int __init init_inodecache(void)
 {
 	udf_inode_cachep = kmem_cache_create("udf_inode_cache",
 					     sizeof(struct udf_inode_info),
@@ -505,6 +505,7 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
 	while ((p = strsep(&options, ",")) != NULL) {
 		substring_t args[MAX_OPT_ARGS];
 		int token;
+		unsigned n;
 		if (!*p)
 			continue;
 
@@ -516,7 +517,10 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
 		case Opt_bs:
 			if (match_int(&args[0], &option))
 				return 0;
-			uopt->blocksize = option;
+			n = option;
+			if (n != 512 && n != 1024 && n != 2048 && n != 4096)
+				return 0;
+			uopt->blocksize = n;
 			uopt->flags |= (1 << UDF_FLAG_BLOCKSIZE_SET);
 			break;
 		case Opt_unhide: