aboutsummaryrefslogtreecommitdiff
path: root/fs/ext3
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext3')
-rw-r--r--fs/ext3/Kconfig19
-rw-r--r--fs/ext3/acl.c2
-rw-r--r--fs/ext3/balloc.c8
-rw-r--r--fs/ext3/dir.c2
-rw-r--r--fs/ext3/file.c6
-rw-r--r--fs/ext3/ialloc.c12
-rw-r--r--fs/ext3/inode.c160
-rw-r--r--fs/ext3/ioctl.c59
-rw-r--r--fs/ext3/namei.c41
-rw-r--r--fs/ext3/super.c67
-rw-r--r--fs/ext3/xattr.c6
11 files changed, 193 insertions, 189 deletions
diff --git a/fs/ext3/Kconfig b/fs/ext3/Kconfig
index 8e0cfe44b0f..fb3c1a21b13 100644
--- a/fs/ext3/Kconfig
+++ b/fs/ext3/Kconfig
@@ -28,6 +28,25 @@ config EXT3_FS
To compile this file system support as a module, choose M here: the
module will be called ext3.
+config EXT3_DEFAULTS_TO_ORDERED
+ bool "Default to 'data=ordered' in ext3 (legacy option)"
+ depends on EXT3_FS
+ help
+ If a filesystem does not explicitly specify a data ordering
+ mode, and the journal capability allowed it, ext3 used to
+ historically default to 'data=ordered'.
+
+ That was a rather unfortunate choice, because it leads to all
+ kinds of latency problems, and the 'data=writeback' mode is more
+ appropriate these days.
+
+ You should probably always answer 'n' here, and if you really
+ want to use 'data=ordered' mode, set it in the filesystem itself
+ with 'tune2fs -o journal_data_ordered'.
+
+ But if you really want to enable the legacy default, you can do
+ so by answering 'y' to this question.
+
config EXT3_FS_XATTR
bool "Ext3 extended attributes"
depends on EXT3_FS
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index b60bb241880..d81ef2fdb08 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -323,7 +323,7 @@ ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
return PTR_ERR(acl);
}
if (!acl)
- inode->i_mode &= ~current->fs->umask;
+ inode->i_mode &= ~current_umask();
}
if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
struct posix_acl *clone;
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 0dbf1c04847..225202db897 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -676,7 +676,7 @@ void ext3_free_blocks(handle_t *handle, struct inode *inode,
}
ext3_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
if (dquot_freed_blocks)
- DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
+ vfs_dq_free_block(inode, dquot_freed_blocks);
return;
}
@@ -1502,7 +1502,7 @@ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
/*
* Check quota for allocation of this block.
*/
- if (DQUOT_ALLOC_BLOCK(inode, num)) {
+ if (vfs_dq_alloc_block(inode, num)) {
*errp = -EDQUOT;
return 0;
}
@@ -1714,7 +1714,7 @@ allocated:
*errp = 0;
brelse(bitmap_bh);
- DQUOT_FREE_BLOCK(inode, *count-num);
+ vfs_dq_free_block(inode, *count-num);
*count = num;
return ret_block;
@@ -1729,7 +1729,7 @@ out:
* Undo the block allocation
*/
if (!performed_allocation)
- DQUOT_FREE_BLOCK(inode, *count);
+ vfs_dq_free_block(inode, *count);
brelse(bitmap_bh);
return 0;
}
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 5853f4440af..3d724a95882 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -42,7 +42,7 @@ const struct file_operations ext3_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
.readdir = ext3_readdir, /* we take BKL. needed?*/
- .ioctl = ext3_ioctl, /* BKL held */
+ .unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
#endif
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 3be1e0689c9..5b49704b231 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -33,6 +33,10 @@
*/
static int ext3_release_file (struct inode * inode, struct file * filp)
{
+ if (EXT3_I(inode)->i_state & EXT3_STATE_FLUSH_ON_CLOSE) {
+ filemap_flush(inode->i_mapping);
+ EXT3_I(inode)->i_state &= ~EXT3_STATE_FLUSH_ON_CLOSE;
+ }
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
(atomic_read(&inode->i_writecount) == 1))
@@ -112,7 +116,7 @@ const struct file_operations ext3_file_operations = {
.write = do_sync_write,
.aio_read = generic_file_aio_read,
.aio_write = ext3_file_write,
- .ioctl = ext3_ioctl,
+ .unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
#endif
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 8de6c720e51..dd13d60d524 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -123,10 +123,10 @@ void ext3_free_inode (handle_t *handle, struct inode * inode)
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
- DQUOT_INIT(inode);
+ vfs_dq_init(inode);
ext3_xattr_delete_inode(handle, inode);
- DQUOT_FREE_INODE(inode);
- DQUOT_DROP(inode);
+ vfs_dq_free_inode(inode);
+ vfs_dq_drop(inode);
is_directory = S_ISDIR(inode->i_mode);
@@ -589,7 +589,7 @@ got:
sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0;
ret = inode;
- if(DQUOT_ALLOC_INODE(inode)) {
+ if (vfs_dq_alloc_inode(inode)) {
err = -EDQUOT;
goto fail_drop;
}
@@ -620,10 +620,10 @@ really_out:
return ret;
fail_free_drop:
- DQUOT_FREE_INODE(inode);
+ vfs_dq_free_inode(inode);
fail_drop:
- DQUOT_DROP(inode);
+ vfs_dq_drop(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
unlock_new_inode(inode);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 5fa453b49a6..466a332e0bd 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1149,12 +1149,15 @@ static int ext3_write_begin(struct file *file, struct address_space *mapping,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
- int ret, needed_blocks = ext3_writepage_trans_blocks(inode);
+ int ret;
handle_t *handle;
int retries = 0;
struct page *page;
pgoff_t index;
unsigned from, to;
+ /* Reserve one block more for addition to orphan list in case
+ * we allocate blocks but write fails for some reason */
+ int needed_blocks = ext3_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
@@ -1184,15 +1187,20 @@ retry:
}
write_begin_failed:
if (ret) {
- ext3_journal_stop(handle);
- unlock_page(page);
- page_cache_release(page);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold i_mutex.
+ *
+ * Add inode to orphan list in case we crash before truncate
+ * finishes.
*/
if (pos + len > inode->i_size)
+ ext3_orphan_add(handle, inode);
+ ext3_journal_stop(handle);
+ unlock_page(page);
+ page_cache_release(page);
+ if (pos + len > inode->i_size)
vmtruncate(inode, inode->i_size);
}
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
@@ -1211,6 +1219,18 @@ int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
return err;
}
+/* For ordered writepage and write_end functions */
+static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
+{
+ /*
+ * Write could have mapped the buffer but it didn't copy the data in
+ * yet. So avoid filing such buffer into a transaction.
+ */
+ if (buffer_mapped(bh) && buffer_uptodate(bh))
+ return ext3_journal_dirty_data(handle, bh);
+ return 0;
+}
+
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
@@ -1221,26 +1241,20 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
}
/*
- * Generic write_end handler for ordered and writeback ext3 journal modes.
- * We can't use generic_write_end, because that unlocks the page and we need to
- * unlock the page after ext3_journal_stop, but ext3_journal_stop must run
- * after block_write_end.
+ * This is nasty and subtle: ext3_write_begin() could have allocated blocks
+ * for the whole page but later we failed to copy the data in. Update inode
+ * size according to what we managed to copy. The rest is going to be
+ * truncated in write_end function.
*/
-static int ext3_generic_write_end(struct file *file,
- struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+static void update_file_sizes(struct inode *inode, loff_t pos, unsigned copied)
{
- struct inode *inode = file->f_mapping->host;
-
- copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
- if (pos+copied > inode->i_size) {
- i_size_write(inode, pos+copied);
+ /* What matters to us is i_disksize. We don't write i_size anywhere */
+ if (pos + copied > inode->i_size)
+ i_size_write(inode, pos + copied);
+ if (pos + copied > EXT3_I(inode)->i_disksize) {
+ EXT3_I(inode)->i_disksize = pos + copied;
mark_inode_dirty(inode);
}
-
- return copied;
}
/*
@@ -1260,35 +1274,29 @@ static int ext3_ordered_write_end(struct file *file,
unsigned from, to;
int ret = 0, ret2;
- from = pos & (PAGE_CACHE_SIZE - 1);
- to = from + len;
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + copied;
ret = walk_page_buffers(handle, page_buffers(page),
- from, to, NULL, ext3_journal_dirty_data);
+ from, to, NULL, journal_dirty_data_fn);
- if (ret == 0) {
- /*
- * generic_write_end() will run mark_inode_dirty() if i_size
- * changes. So let's piggyback the i_disksize mark_inode_dirty
- * into that.
- */
- loff_t new_i_size;
-
- new_i_size = pos + copied;
- if (new_i_size > EXT3_I(inode)->i_disksize)
- EXT3_I(inode)->i_disksize = new_i_size;
- ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
- copied = ret2;
- if (ret2 < 0)
- ret = ret2;
- }
+ if (ret == 0)
+ update_file_sizes(inode, pos, copied);
+ /*
+ * There may be allocated blocks outside of i_size because
+ * we failed to copy some data. Prepare for truncate.
+ */
+ if (pos + len > inode->i_size)
+ ext3_orphan_add(handle, inode);
ret2 = ext3_journal_stop(handle);
if (!ret)
ret = ret2;
unlock_page(page);
page_cache_release(page);
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
return ret ? ret : copied;
}
@@ -1299,25 +1307,22 @@ static int ext3_writeback_write_end(struct file *file,
{
handle_t *handle = ext3_journal_current_handle();
struct inode *inode = file->f_mapping->host;
- int ret = 0, ret2;
- loff_t new_i_size;
-
- new_i_size = pos + copied;
- if (new_i_size > EXT3_I(inode)->i_disksize)
- EXT3_I(inode)->i_disksize = new_i_size;
-
- ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
- copied = ret2;
- if (ret2 < 0)
- ret = ret2;
+ int ret;
- ret2 = ext3_journal_stop(handle);
- if (!ret)
- ret = ret2;
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+ update_file_sizes(inode, pos, copied);
+ /*
+ * There may be allocated blocks outside of i_size because
+ * we failed to copy some data. Prepare for truncate.
+ */
+ if (pos + len > inode->i_size)
+ ext3_orphan_add(handle, inode);
+ ret = ext3_journal_stop(handle);
unlock_page(page);
page_cache_release(page);
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
return ret ? ret : copied;
}
@@ -1338,15 +1343,23 @@ static int ext3_journalled_write_end(struct file *file,
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
- page_zero_new_buffers(page, from+copied, to);
+ page_zero_new_buffers(page, from + copied, to);
+ to = from + copied;
}
ret = walk_page_buffers(handle, page_buffers(page), from,
to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
- if (pos+copied > inode->i_size)
- i_size_write(inode, pos+copied);
+
+ if (pos + copied > inode->i_size)
+ i_size_write(inode, pos + copied);
+ /*
+ * There may be allocated blocks outside of i_size because
+ * we failed to copy some data. Prepare for truncate.
+ */
+ if (pos + len > inode->i_size)
+ ext3_orphan_add(handle, inode);
EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
if (inode->i_size > EXT3_I(inode)->i_disksize) {
EXT3_I(inode)->i_disksize = inode->i_size;
@@ -1361,6 +1374,8 @@ static int ext3_journalled_write_end(struct file *file,
unlock_page(page);
page_cache_release(page);
+ if (pos + len > inode->i_size)
+ vmtruncate(inode, inode->i_size);
return ret ? ret : copied;
}
@@ -1428,11 +1443,9 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
return 0;
}
-static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
+static int buffer_unmapped(handle_t *handle, struct buffer_head *bh)
{
- if (buffer_mapped(bh))
- return ext3_journal_dirty_data(handle, bh);
- return 0;
+ return !buffer_mapped(bh);
}
/*
@@ -1505,6 +1518,15 @@ static int ext3_ordered_writepage(struct page *page,
if (ext3_journal_current_handle())
goto out_fail;
+ if (!page_has_buffers(page)) {
+ create_empty_buffers(page, inode->i_sb->s_blocksize,
+ (1 << BH_Dirty)|(1 << BH_Uptodate));
+ } else if (!walk_page_buffers(NULL, page_buffers(page), 0, PAGE_CACHE_SIZE, NULL, buffer_unmapped)) {
+ /* Provide NULL instead of get_block so that we catch bugs if buffers weren't really mapped */
+ return block_write_full_page(page, NULL, wbc);
+ }
+ page_bufs = page_buffers(page);
+
handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
@@ -1512,11 +1534,6 @@ static int ext3_ordered_writepage(struct page *page,
goto out_fail;
}
- if (!page_has_buffers(page)) {
- create_empty_buffers(page, inode->i_sb->s_blocksize,
- (1 << BH_Dirty)|(1 << BH_Uptodate));
- }
- page_bufs = page_buffers(page);
walk_page_buffers(handle, page_bufs, 0,
PAGE_CACHE_SIZE, NULL, bget_one);
@@ -2346,6 +2363,9 @@ void ext3_truncate(struct inode *inode)
if (!ext3_can_truncate(inode))
return;
+ if (inode->i_size == 0 && ext3_should_writeback_data(inode))
+ ei->i_state |= EXT3_STATE_FLUSH_ON_CLOSE;
+
/*
* We have to lock the EOF page here, because lock_page() nests
* outside journal_start().
@@ -3055,7 +3075,7 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr)
error = PTR_ERR(handle);
goto err_out;
}
- error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
+ error = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0;
if (error) {
ext3_journal_stop(handle);
return error;
@@ -3146,7 +3166,7 @@ static int ext3_writepage_trans_blocks(struct inode *inode)
ret = 2 * (bpp + indirects) + 2;
#ifdef CONFIG_QUOTA
- /* We know that structure was already allocated during DQUOT_INIT so
+ /* We know that structure was already allocated during vfs_dq_init so
* we will be updating only the data blocks + inodes */
ret += 2*EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb);
#endif
@@ -3237,7 +3257,7 @@ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode)
* i_size has been changed by generic_commit_write() and we thus need
* to include the updated inode in the current transaction.
*
- * Also, DQUOT_ALLOC_SPACE() will always dirty the inode when blocks
+ * Also, vfs_dq_alloc_space() will always dirty the inode when blocks
* are allocated to the file.
*
* If the inode is marked synchronous, we don't honour that here - doing
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 5e86ce9a86e..88974814783 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -15,12 +15,11 @@
#include <linux/mount.h>
#include <linux/time.h>
#include <linux/compat.h>
-#include <linux/smp_lock.h>
#include <asm/uaccess.h>
-int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
- unsigned long arg)
+long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
+ struct inode *inode = filp->f_dentry->d_inode;
struct ext3_inode_info *ei = EXT3_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
@@ -39,29 +38,25 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
unsigned int oldflags;
unsigned int jflag;
+ if (!is_owner_or_cap(inode))
+ return -EACCES;
+
+ if (get_user(flags, (int __user *) arg))
+ return -EFAULT;
+
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
- if (!is_owner_or_cap(inode)) {
- err = -EACCES;
- goto flags_out;
- }
-
- if (get_user(flags, (int __user *) arg)) {
- err = -EFAULT;
- goto flags_out;
- }
-
flags = ext3_mask_flags(inode->i_mode, flags);
mutex_lock(&inode->i_mutex);
+
/* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode)) {
- mutex_unlock(&inode->i_mutex);
- err = -EPERM;
+ err = -EPERM;
+ if (IS_NOQUOTA(inode))
goto flags_out;
- }
+
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
@@ -74,11 +69,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT3_APPEND_FL | EXT3_IMMUTABLE_FL)) {
- if (!capable(CAP_LINUX_IMMUTABLE)) {
- mutex_unlock(&inode->i_mutex);
- err = -EPERM;
+ if (!capable(CAP_LINUX_IMMUTABLE))
goto flags_out;
- }
}
/*
@@ -86,17 +78,12 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
* the relevant capability.
*/
if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) {
- if (!capable(CAP_SYS_RESOURCE)) {
- mutex_unlock(&inode->i_mutex);
- err = -EPERM;
+ if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
- }
}
-
handle = ext3_journal_start(inode, 1);
if (IS_ERR(handle)) {
- mutex_unlock(&inode->i_mutex);
err = PTR_ERR(handle);
goto flags_out;
}
@@ -116,15 +103,13 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
err = ext3_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext3_journal_stop(handle);
- if (err) {
- mutex_unlock(&inode->i_mutex);
- return err;
- }
+ if (err)
+ goto flags_out;
if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL))
err = ext3_change_inode_journal_flag(inode, jflag);
- mutex_unlock(&inode->i_mutex);
flags_out:
+ mutex_unlock(&inode->i_mutex);
mnt_drop_write(filp->f_path.mnt);
return err;
}
@@ -140,6 +125,7 @@ flags_out:
if (!is_owner_or_cap(inode))
return -EPERM;
+
err = mnt_want_write(filp->f_path.mnt);
if (err)
return err;
@@ -147,6 +133,7 @@ flags_out:
err = -EFAULT;
goto setversion_out;
}
+
handle = ext3_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
@@ -299,9 +286,6 @@ group_add_out:
#ifdef CONFIG_COMPAT
long ext3_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = file->f_path.dentry->d_inode;
- int ret;
-
/* These are just misnamed, they actually get/put from/to user an int */
switch (cmd) {
case EXT3_IOC32_GETFLAGS:
@@ -341,9 +325,6 @@ long ext3_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
default:
return -ENOIOCTLCMD;
}
- lock_kernel();
- ret = ext3_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
- unlock_kernel();
- return ret;
+ return ext3_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
}
#endif
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 4db4ffa1eda..6ff7b973023 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -161,12 +161,12 @@ static struct dx_frame *dx_probe(struct qstr *entry,
struct dx_frame *frame,
int *err);
static void dx_release (struct dx_frame *frames);
-static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
+static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize,
struct dx_hash_info *hinfo, struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
static struct ext3_dir_entry_2 *dx_move_dirents (char *from, char *to,
struct dx_map_entry *offsets, int count);
-static struct ext3_dir_entry_2* dx_pack_dirents (char *base, int size);
+static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize);
static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block);
static int ext3_htree_next_block(struct inode *dir, __u32 hash,
struct dx_frame *frame,
@@ -708,14 +708,14 @@ errout:
* Create map of hash values, offsets, and sizes, stored at end of block.
* Returns number of entries mapped.
*/
-static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
- struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
+static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize,
+ struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
{
int count = 0;
char *base = (char *) de;
struct dx_hash_info h = *hinfo;
- while ((char *) de < base + size)
+ while ((char *) de < base + blocksize)
{
if (de->name_len && de->inode) {
ext3fs_dirhash(de->name, de->name_len, &h);
@@ -1047,8 +1047,16 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str
return ERR_PTR(-EIO);
}
inode = ext3_iget(dir->i_sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
+ if (unlikely(IS_ERR(inode))) {
+ if (PTR_ERR(inode) == -ESTALE) {
+ ext3_error(dir->i_sb, __func__,
+ "deleted inode referenced: %lu",
+ ino);
+ return ERR_PTR(-EIO);
+ } else {
+ return ERR_CAST(inode);
+ }
+ }
}
return d_splice_alias(inode, dentry);
}
@@ -1120,13 +1128,14 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
* Compact each dir entry in the range to the minimal rec_len.
* Returns pointer to last entry in range.
*/
-static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
+static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize)
{
- struct ext3_dir_entry_2 *next, *to, *prev, *de = (struct ext3_dir_entry_2 *) base;
+ struct ext3_dir_entry_2 *next, *to, *prev;
+ struct ext3_dir_entry_2 *de = (struct ext3_dir_entry_2 *)base;
unsigned rec_len = 0;
prev = to = de;
- while ((char*)de < base + size) {
+ while ((char *)de < base + blocksize) {
next = ext3_next_entry(de);
if (de->inode && de->name_len) {
rec_len = EXT3_DIR_REC_LEN(de->name_len);
@@ -2049,7 +2058,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry)
/* Initialize quotas before so that eventual writes go in
* separate transaction */
- DQUOT_INIT(dentry->d_inode);
+ vfs_dq_init(dentry->d_inode);
handle = ext3_journal_start(dir, EXT3_DELETE_TRANS_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2108,7 +2117,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry)
/* Initialize quotas before so that eventual writes go
* in separate transaction */
- DQUOT_INIT(dentry->d_inode);
+ vfs_dq_init(dentry->d_inode);
handle = ext3_journal_start(dir, EXT3_DELETE_TRANS_BLOCKS(dir->i_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2265,14 +2274,14 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
struct inode * old_inode, * new_inode;
struct buffer_head * old_bh, * new_bh, * dir_bh;
struct ext3_dir_entry_2 * old_de, * new_de;
- int retval;
+ int retval, flush_file = 0;
old_bh = new_bh = dir_bh = NULL;
/* Initialize quotas before so that eventual writes go
* in separate transaction */
if (new_dentry->d_inode)
- DQUOT_INIT(new_dentry->d_inode);
+ vfs_dq_init(new_dentry->d_inode);
handle = ext3_journal_start(old_dir, 2 *
EXT3_DATA_TRANS_BLOCKS(old_dir->i_sb) +
EXT3_INDEX_EXTRA_TRANS_BLOCKS + 2);
@@ -2401,6 +2410,8 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
ext3_mark_inode_dirty(handle, new_inode);
if (!new_inode->i_nlink)
ext3_orphan_add(handle, new_inode);
+ if (ext3_should_writeback_data(new_inode))
+ flush_file = 1;
}
retval = 0;
@@ -2409,6 +2420,8 @@ end_rename:
brelse (old_bh);
brelse (new_bh);
ext3_journal_stop(handle);
+ if (retval == 0 && flush_file)
+ filemap_flush(old_inode->i_mapping);
return retval;
}
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index b70d90e08a3..599dbfe504c 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -44,6 +44,12 @@
#include "acl.h"
#include "namei.h"
+#ifdef CONFIG_EXT3_DEFAULTS_TO_ORDERED
+ #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_ORDERED_DATA
+#else
+ #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_WRITEBACK_DATA
+#endif
+
static int ext3_load_journal(struct super_block *, struct ext3_super_block *,
unsigned long journal_devnum);
static int ext3_create_journal(struct super_block *, struct ext3_super_block *,
@@ -707,8 +713,6 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
-static int ext3_dquot_initialize(struct inode *inode, int type);
-static int ext3_dquot_drop(struct inode *inode);
static int ext3_write_dquot(struct dquot *dquot);
static int ext3_acquire_dquot(struct dquot *dquot);
static int ext3_release_dquot(struct dquot *dquot);
@@ -723,8 +727,8 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off);
static struct dquot_operations ext3_quota_operations = {
- .initialize = ext3_dquot_initialize,
- .drop = ext3_dquot_drop,
+ .initialize = dquot_initialize,
+ .drop = dquot_drop,
.alloc_space = dquot_alloc_space,
.alloc_inode = dquot_alloc_inode,
.free_space = dquot_free_space,
@@ -1438,7 +1442,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
}
list_add(&EXT3_I(inode)->i_orphan, &EXT3_SB(sb)->s_orphan);
- DQUOT_INIT(inode);
+ vfs_dq_init(inode);
if (inode->i_nlink) {
printk(KERN_DEBUG
"%s: truncating inode %lu to %Ld bytes\n",
@@ -1921,7 +1925,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
cope, else JOURNAL_DATA */
if (journal_check_available_features
(sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE))
- set_opt(sbi->s_mount_opt, ORDERED_DATA);
+ set_opt(sbi->s_mount_opt, DEFAULT_DATA_MODE);
else
set_opt(sbi->s_mount_opt, JOURNAL_DATA);
break;
@@ -2428,12 +2432,13 @@ static void ext3_write_super (struct super_block * sb)
static int ext3_sync_fs(struct super_block *sb, int wait)
{
- sb->s_dirt = 0;
- if (wait)
- ext3_force_commit(sb);
- else
- journal_start_commit(EXT3_SB(sb)->s_journal, NULL);
+ tid_t target;
+ sb->s_dirt = 0;
+ if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
+ if (wait)
+ log_wait_commit(EXT3_SB(sb)->s_journal, target);
+ }
return 0;
}
@@ -2701,7 +2706,7 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
* Process 1 Process 2
* ext3_create() quota_sync()
* journal_start() write_dquot()
- * DQUOT_INIT() down(dqio_mutex)
+ * vfs_dq_init() down(dqio_mutex)
* down(dqio_mutex) journal_start()
*
*/
@@ -2713,44 +2718,6 @@ static inline struct inode *dquot_to_inode(struct dquot *dquot)
return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
}
-static int ext3_dquot_initialize(struct inode *inode, int type)
-{
- handle_t *handle;
- int ret, err;
-
- /* We may create quota structure so we need to reserve enough blocks */
- handle = ext3_journal_start(inode, 2*EXT3_QUOTA_INIT_BLOCKS(inode->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
- ret = dquot_initialize(inode, type);
- err = ext3_journal_stop(handle);
- if (!ret)
- ret = err;
- return ret;
-}
-
-static int ext3_dquot_drop(struct inode *inode)
-{
- handle_t *handle;
- int ret, err;
-
- /* We may delete quota structure so we need to reserve enough blocks */
- handle = ext3_journal_start(inode, 2*EXT3_QUOTA_DEL_BLOCKS(inode->i_sb));
- if (IS_ERR(handle)) {
- /*
- * We call dquot_drop() anyway to at least release references
- * to quota structures so that umount does not hang.
- */
- dquot_drop(inode);
- return PTR_ERR(handle);
- }
- ret = dquot_drop(inode);
- err = ext3_journal_stop(handle);
- if (!ret)
- ret = err;
- return ret;
-}
-
static int ext3_write_dquot(struct dquot *dquot)
{
int ret, err;
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index 175414ac221..83b7be849bd 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -498,7 +498,7 @@ ext3_xattr_release_block(handle_t *handle, struct inode *inode,
error = ext3_journal_dirty_metadata(handle, bh);
if (IS_SYNC(inode))
handle->h_sync = 1;
- DQUOT_FREE_BLOCK(inode, 1);
+ vfs_dq_free_block(inode, 1);
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
if (ce)
@@ -774,7 +774,7 @@ inserted:
/* The old block is released after updating
the inode. */
error = -EDQUOT;
- if (DQUOT_ALLOC_BLOCK(inode, 1))
+ if (vfs_dq_alloc_block(inode, 1))
goto cleanup;
error = ext3_journal_get_write_access(handle,
new_bh);
@@ -848,7 +848,7 @@ cleanup:
return error;
cleanup_dquot:
- DQUOT_FREE_BLOCK(inode, 1);
+ vfs_dq_free_block(inode, 1);
goto cleanup;
bad_block:
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-01 03:33:48 +0000