#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/bio.h>
+#include <linux/fiemap.h>
+#include <linux/namei.h>
#include "xattr.h"
#include "acl.h"
BUFFER_TRACE(bh, "call ext3_journal_revoke");
err = ext3_journal_revoke(handle, blocknr, bh);
if (err)
- ext3_abort(inode->i_sb, __FUNCTION__,
+ ext3_abort(inode->i_sb, __func__,
"error %d when attempting revoke", err);
BUFFER_TRACE(bh, "exit");
return err;
int ext3_get_blocks_handle(handle_t *handle, struct inode *inode,
sector_t iblock, unsigned long maxblocks,
struct buffer_head *bh_result,
- int create, int extend_disksize)
+ int create)
{
int err = -EIO;
int offsets[4];
while (count < maxblocks && count <= blocks_to_boundary) {
ext3_fsblk_t blk;
- if (!verify_chain(chain, partial)) {
+ if (!verify_chain(chain, chain + depth - 1)) {
/*
* Indirect block might be removed by
* truncate while we were reading it.
if (!err)
err = ext3_splice_branch(handle, inode, iblock,
partial, indirect_blks, count);
- /*
- * i_disksize growing is protected by truncate_mutex. Don't forget to
- * protect it if you're about to implement concurrent
- * ext3_get_block() -bzzz
- */
- if (!err && extend_disksize && inode->i_size > ei->i_disksize)
- ei->i_disksize = inode->i_size;
mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
}
ret = ext3_get_blocks_handle(handle, inode, iblock,
- max_blocks, bh_result, create, 0);
+ max_blocks, bh_result, create);
if (ret > 0) {
bh_result->b_size = (ret << inode->i_blkbits);
ret = 0;
return ret;
}
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ return generic_block_fiemap(inode, fieinfo, start, len,
+ ext3_get_block);
+}
+
/*
* `handle' can be NULL if create is zero
*/
dummy.b_blocknr = -1000;
buffer_trace_init(&dummy.b_history);
err = ext3_get_blocks_handle(handle, inode, block, 1,
- &dummy, create, 1);
+ &dummy, create);
/*
* ext3_get_blocks_handle() returns number of blocks
* mapped. 0 in case of a HOLE.
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);
to = from + len;
retry:
- page = __grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
*pagep = page;
}
write_begin_failed:
if (ret) {
+ /*
+ * 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. Do this only if ext3_can_truncate() agrees so
+ * that orphan processing code is happy.
+ */
+ if (pos + len > inode->i_size && ext3_can_truncate(inode))
+ ext3_orphan_add(handle, inode);
ext3_journal_stop(handle);
unlock_page(page);
page_cache_release(page);
+ if (pos + len > inode->i_size)
+ ext3_truncate(inode);
}
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
goto retry;
{
int err = journal_dirty_data(handle, bh);
if (err)
- ext3_journal_abort_handle(__FUNCTION__, __FUNCTION__,
+ ext3_journal_abort_handle(__func__, __func__,
bh, handle, err);
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)
{
}
/*
- * 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;
}
/*
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);
-
- 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;
+ from, to, NULL, journal_dirty_data_fn);
- new_i_size = pos + copied;
- if (new_i_size > EXT3_I(inode)->i_disksize)
- EXT3_I(inode)->i_disksize = new_i_size;
- copied = ext3_generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
- if (copied < 0)
- ret = copied;
- }
+ 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_can_truncate(inode))
+ 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)
+ ext3_truncate(inode);
return ret ? ret : copied;
}
{
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;
-
- copied = ext3_generic_write_end(file, mapping, pos, len, copied,
- page, fsdata);
- if (copied < 0)
- ret = copied;
+ 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_can_truncate(inode))
+ ext3_orphan_add(handle, inode);
+ ret = ext3_journal_stop(handle);
unlock_page(page);
page_cache_release(page);
+ if (pos + len > inode->i_size)
+ ext3_truncate(inode);
return ret ? ret : copied;
}
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_can_truncate(inode))
+ 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;
unlock_page(page);
page_cache_release(page);
+ if (pos + len > inode->i_size)
+ ext3_truncate(inode);
return ret ? ret : copied;
}
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);
}
/*
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));
+ page_bufs = page_buffers(page);
+ } else {
+ page_bufs = page_buffers(page);
+ if (!walk_page_buffers(NULL, page_bufs, 0, PAGE_CACHE_SIZE,
+ NULL, buffer_unmapped)) {
+ /* Provide NULL get_block() to catch bugs if buffers
+ * weren't really mapped */
+ return block_write_full_page(page, NULL, wbc);
+ }
+ }
handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
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);
if (ext3_journal_current_handle())
goto out_fail;
+ if (page_has_buffers(page)) {
+ if (!walk_page_buffers(NULL, page_buffers(page), 0,
+ PAGE_CACHE_SIZE, NULL, buffer_unmapped)) {
+ /* Provide NULL get_block() to catch bugs if buffers
+ * weren't really mapped */
+ return block_write_full_page(page, NULL, wbc);
+ }
+ }
+
handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
}
static const struct address_space_operations ext3_ordered_aops = {
- .readpage = ext3_readpage,
- .readpages = ext3_readpages,
- .writepage = ext3_ordered_writepage,
- .sync_page = block_sync_page,
- .write_begin = ext3_write_begin,
- .write_end = ext3_ordered_write_end,
- .bmap = ext3_bmap,
- .invalidatepage = ext3_invalidatepage,
- .releasepage = ext3_releasepage,
- .direct_IO = ext3_direct_IO,
- .migratepage = buffer_migrate_page,
+ .readpage = ext3_readpage,
+ .readpages = ext3_readpages,
+ .writepage = ext3_ordered_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext3_write_begin,
+ .write_end = ext3_ordered_write_end,
+ .bmap = ext3_bmap,
+ .invalidatepage = ext3_invalidatepage,
+ .releasepage = ext3_releasepage,
+ .direct_IO = ext3_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext3_writeback_aops = {
- .readpage = ext3_readpage,
- .readpages = ext3_readpages,
- .writepage = ext3_writeback_writepage,
- .sync_page = block_sync_page,
- .write_begin = ext3_write_begin,
- .write_end = ext3_writeback_write_end,
- .bmap = ext3_bmap,
- .invalidatepage = ext3_invalidatepage,
- .releasepage = ext3_releasepage,
- .direct_IO = ext3_direct_IO,
- .migratepage = buffer_migrate_page,
+ .readpage = ext3_readpage,
+ .readpages = ext3_readpages,
+ .writepage = ext3_writeback_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext3_write_begin,
+ .write_end = ext3_writeback_write_end,
+ .bmap = ext3_bmap,
+ .invalidatepage = ext3_invalidatepage,
+ .releasepage = ext3_releasepage,
+ .direct_IO = ext3_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext3_journalled_aops = {
- .readpage = ext3_readpage,
- .readpages = ext3_readpages,
- .writepage = ext3_journalled_writepage,
- .sync_page = block_sync_page,
- .write_begin = ext3_write_begin,
- .write_end = ext3_journalled_write_end,
- .set_page_dirty = ext3_journalled_set_page_dirty,
- .bmap = ext3_bmap,
- .invalidatepage = ext3_invalidatepage,
- .releasepage = ext3_releasepage,
+ .readpage = ext3_readpage,
+ .readpages = ext3_readpages,
+ .writepage = ext3_journalled_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext3_write_begin,
+ .write_end = ext3_journalled_write_end,
+ .set_page_dirty = ext3_journalled_set_page_dirty,
+ .bmap = ext3_bmap,
+ .invalidatepage = ext3_invalidatepage,
+ .releasepage = ext3_releasepage,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
void ext3_set_aops(struct inode *inode)
if (this_bh) {
BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata");
- ext3_journal_dirty_metadata(handle, this_bh);
+
+ /*
+ * The buffer head should have an attached journal head at this
+ * point. However, if the data is corrupted and an indirect
+ * block pointed to itself, it would have been detached when
+ * the block was cleared. Check for this instead of OOPSing.
+ */
+ if (bh2jh(this_bh))
+ ext3_journal_dirty_metadata(handle, this_bh);
+ else
+ ext3_error(inode->i_sb, "ext3_free_data",
+ "circular indirect block detected, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long)this_bh->b_blocknr);
}
}
}
}
+int ext3_can_truncate(struct inode *inode)
+{
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+ return 0;
+ if (S_ISREG(inode->i_mode))
+ return 1;
+ if (S_ISDIR(inode->i_mode))
+ return 1;
+ if (S_ISLNK(inode->i_mode))
+ return !ext3_inode_is_fast_symlink(inode);
+ return 0;
+}
+
/*
* ext3_truncate()
*
unsigned blocksize = inode->i_sb->s_blocksize;
struct page *page;
- if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- S_ISLNK(inode->i_mode)))
- return;
- if (ext3_inode_is_fast_symlink(inode))
- return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- return;
+ if (!ext3_can_truncate(inode))
+ goto out_notrans;
+
+ 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
page = grab_cache_page(mapping,
inode->i_size >> PAGE_CACHE_SHIFT);
if (!page)
- return;
+ goto out_notrans;
}
handle = start_transaction(inode);
unlock_page(page);
page_cache_release(page);
}
- return; /* AKPM: return what? */
+ goto out_notrans;
}
last_block = (inode->i_size + blocksize-1)
ext3_orphan_del(handle, inode);
ext3_journal_stop(handle);
+ return;
+out_notrans:
+ /*
+ * Delete the inode from orphan list so that it doesn't stay there
+ * forever and trigger assertion on umount.
+ */
+ if (inode->i_nlink)
+ ext3_orphan_del(NULL, inode);
}
static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb,
}
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
+
+ /*
+ * If the buffer has the write error flag, we have failed
+ * to write out another inode in the same block. In this
+ * case, we don't have to read the block because we may
+ * read the old inode data successfully.
+ */
+ if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+ set_buffer_uptodate(bh);
+
if (buffer_uptodate(bh)) {
/* someone brought it uptodate while we waited */
unlock_buffer(bh);
return inode;
ei = EXT3_I(inode);
-#ifdef CONFIG_EXT3_FS_POSIX_ACL
- ei->i_acl = EXT3_ACL_NOT_CACHED;
- ei->i_default_acl = EXT3_ACL_NOT_CACHED;
-#endif
ei->i_block_alloc_info = NULL;
ret = __ext3_get_inode_loc(inode, &iloc, 0);
inode->i_op = &ext3_dir_inode_operations;
inode->i_fop = &ext3_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
- if (ext3_inode_is_fast_symlink(inode))
+ if (ext3_inode_is_fast_symlink(inode)) {
inode->i_op = &ext3_fast_symlink_inode_operations;
- else {
+ nd_terminate_link(ei->i_data, inode->i_size,
+ sizeof(ei->i_data) - 1);
+ } else {
inode->i_op = &ext3_symlink_inode_operations;
ext3_set_aops(inode);
}
ext3_update_dynamic_rev(sb);
EXT3_SET_RO_COMPAT_FEATURE(sb,
EXT3_FEATURE_RO_COMPAT_LARGE_FILE);
- sb->s_dirt = 1;
handle->h_sync = 1;
err = ext3_journal_dirty_metadata(handle,
EXT3_SB(sb)->s_sbh);
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;
rc = inode_setattr(inode, attr);
- /* If inode_setattr's call to ext3_truncate failed to get a
- * transaction handle at all, we need to clean up the in-core
- * orphan list manually. */
- if (inode->i_nlink)
- ext3_orphan_del(NULL, inode);
-
if (!rc && (ia_valid & ATTR_MODE))
rc = ext3_acl_chmod(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
* 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
current_handle->h_transaction != handle->h_transaction) {
/* This task has a transaction open against a different fs */
printk(KERN_EMERG "%s: transactions do not match!\n",
- __FUNCTION__);
+ __func__);
} else {
jbd_debug(5, "marking dirty. outer handle=%p\n",
current_handle);