* so before we call here everything must be consistently dirtied against
* this transaction.
*/
-static int ext3_journal_test_restart(handle_t *handle, struct inode *inode)
+static int truncate_restart_transaction(handle_t *handle, struct inode *inode)
{
+ int ret;
+
jbd_debug(2, "restarting handle %p\n", handle);
- return ext3_journal_restart(handle, blocks_for_truncate(inode));
+ /*
+ * Drop truncate_mutex to avoid deadlock with ext3_get_blocks_handle
+ * At this moment, get_block can be called only for blocks inside
+ * i_size since page cache has been already dropped and writes are
+ * blocked by i_mutex. So we can safely drop the truncate_mutex.
+ */
+ mutex_unlock(&EXT3_I(inode)->truncate_mutex);
+ ret = ext3_journal_restart(handle, blocks_for_truncate(inode));
+ mutex_lock(&EXT3_I(inode)->truncate_mutex);
+ return ret;
}
/*
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;
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);
}
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. 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)
- vmtruncate(inode, inode->i_size);
+ ext3_truncate(inode);
}
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
goto retry;
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);
+ 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_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;
-
- 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_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)
-{
- if (buffer_mapped(bh))
- return ext3_journal_dirty_data(handle, bh);
- return 0;
-}
-
static int buffer_unmapped(handle_t *handle, struct buffer_head *bh)
{
return !buffer_mapped(bh);
}
+
/*
* Note that we always start a transaction even if we're not journalling
* data. This is to preserve ordering: any hole instantiation within
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);
+ } 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);
+ }
}
- page_bufs = page_buffers(page);
-
handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
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);
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext3_writeback_aops = {
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext3_journalled_aops = {
.invalidatepage = ext3_invalidatepage,
.releasepage = ext3_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
void ext3_set_aops(struct inode *inode)
ext3_journal_dirty_metadata(handle, bh);
}
ext3_mark_inode_dirty(handle, inode);
- ext3_journal_test_restart(handle, inode);
+ truncate_restart_transaction(handle, inode);
if (bh) {
BUFFER_TRACE(bh, "retaking write access");
ext3_journal_get_write_access(handle, bh);
return;
if (try_to_extend_transaction(handle, inode)) {
ext3_mark_inode_dirty(handle, inode);
- ext3_journal_test_restart(handle, inode);
+ truncate_restart_transaction(handle, inode);
}
ext3_free_blocks(handle, inode, nr, 1);
struct page *page;
if (!ext3_can_truncate(inode))
- return;
+ 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,
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);
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
+again:
+ /* we can't allow multiple procs in here at once, its a bit racey */
+ lock_buffer(bh);
+
/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ei->i_state & EXT3_STATE_NEW)
/* If this is the first large file
* created, add a flag to the superblock.
*/
+ unlock_buffer(bh);
err = ext3_journal_get_write_access(handle,
EXT3_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+
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);
+ /* get our lock and start over */
+ goto again;
}
}
}
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
+ unlock_buffer(bh);
rc = ext3_journal_dirty_metadata(handle, bh);
if (!err)
err = rc;
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