* 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;
}
/*
{
handle_t *handle;
+ if (!is_bad_inode(inode))
+ dquot_initialize(inode);
+
truncate_inode_pages(&inode->i_data, 0);
if (is_bad_inode(inode))
int err = 0;
struct ext3_block_alloc_info *block_i;
ext3_fsblk_t current_block;
+ struct ext3_inode_info *ei = EXT3_I(inode);
- block_i = EXT3_I(inode)->i_block_alloc_info;
+ block_i = ei->i_block_alloc_info;
/*
* If we're splicing into a [td]indirect block (as opposed to the
* inode) then we need to get write access to the [td]indirect block
inode->i_ctime = CURRENT_TIME_SEC;
ext3_mark_inode_dirty(handle, inode);
+ /* ext3_mark_inode_dirty already updated i_sync_tid */
+ atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
/* had we spliced it onto indirect block? */
if (where->bh) {
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];
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;
if (max_blocks > DIO_MAX_BLOCKS)
max_blocks = DIO_MAX_BLOCKS;
handle = ext3_journal_start(inode, DIO_CREDITS +
- 2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb));
+ EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
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.
return ext3_journal_get_write_access(handle, bh);
}
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static void ext3_truncate_failed_write(struct inode *inode)
+{
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ ext3_truncate(inode);
+}
+
static int ext3_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
unlock_page(page);
page_cache_release(page);
if (pos + len > inode->i_size)
- ext3_truncate(inode);
+ ext3_truncate_failed_write(inode);
}
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
goto retry;
page_cache_release(page);
if (pos + len > inode->i_size)
- ext3_truncate(inode);
+ ext3_truncate_failed_write(inode);
return ret ? ret : copied;
}
page_cache_release(page);
if (pos + len > inode->i_size)
- ext3_truncate(inode);
+ ext3_truncate_failed_write(inode);
return ret ? ret : copied;
}
*/
if (pos + len > inode->i_size && ext3_can_truncate(inode))
ext3_orphan_add(handle, inode);
- EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
+ ext3_set_inode_state(inode, EXT3_STATE_JDATA);
if (inode->i_size > EXT3_I(inode)->i_disksize) {
EXT3_I(inode)->i_disksize = inode->i_size;
ret2 = ext3_mark_inode_dirty(handle, inode);
page_cache_release(page);
if (pos + len > inode->i_size)
- ext3_truncate(inode);
+ ext3_truncate_failed_write(inode);
return ret ? ret : copied;
}
journal_t *journal;
int err;
- if (EXT3_I(inode)->i_state & EXT3_STATE_JDATA) {
+ if (ext3_test_inode_state(inode, EXT3_STATE_JDATA)) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
* everything they get.
*/
- EXT3_I(inode)->i_state &= ~EXT3_STATE_JDATA;
+ ext3_clear_inode_state(inode, EXT3_STATE_JDATA);
journal = EXT3_JOURNAL(inode);
journal_lock_updates(journal);
err = journal_flush(journal);
int err;
J_ASSERT(PageLocked(page));
+ WARN_ON_ONCE(IS_RDONLY(inode));
/*
* We give up here if we're reentered, because it might be for a
int ret = 0;
int err;
+ J_ASSERT(PageLocked(page));
+ WARN_ON_ONCE(IS_RDONLY(inode));
+
if (ext3_journal_current_handle())
goto out_fail;
int ret = 0;
int err;
+ J_ASSERT(PageLocked(page));
+ WARN_ON_ONCE(IS_RDONLY(inode));
+
if (ext3_journal_current_handle())
goto no_write;
PAGE_CACHE_SIZE, NULL, write_end_fn);
if (ret == 0)
ret = err;
- EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
+ ext3_set_inode_state(inode, EXT3_STATE_JDATA);
unlock_page(page);
} else {
/*
ssize_t ret;
int orphan = 0;
size_t count = iov_length(iov, nr_segs);
+ int retries = 0;
if (rw == WRITE) {
loff_t final_size = offset + count;
}
}
+retry:
ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext3_get_block, NULL);
+ if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
if (orphan) {
int err;
handle = ext3_journal_start(inode, 2);
if (IS_ERR(handle)) {
/* This is really bad luck. We've written the data
- * but cannot extend i_size. Bail out and pretend
- * the write failed... */
+ * but cannot extend i_size. Truncate allocated blocks
+ * and pretend the write failed... */
+ ext3_truncate(inode);
ret = PTR_ERR(handle);
goto out;
}
.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)
int k, err;
*top = 0;
- /* Make k index the deepest non-null offest + 1 */
+ /* Make k index the deepest non-null offset + 1 */
for (k = depth; k > 1 && !offsets[k-1]; k--)
;
partial = ext3_get_branch(inode, k, offsets, chain, &err);
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);
goto out_notrans;
if (inode->i_size == 0 && ext3_should_writeback_data(inode))
- ei->i_state |= EXT3_STATE_FLUSH_ON_CLOSE;
+ ext3_set_inode_state(inode, EXT3_STATE_FLUSH_ON_CLOSE);
/*
* We have to lock the EOF page here, because lock_page() nests
{
/* We have all inode data except xattrs in memory here. */
return __ext3_get_inode_loc(inode, iloc,
- !(EXT3_I(inode)->i_state & EXT3_STATE_XATTR));
+ !ext3_test_inode_state(inode, EXT3_STATE_XATTR));
}
void ext3_set_inode_flags(struct inode *inode)
struct ext3_inode_info *ei;
struct buffer_head *bh;
struct inode *inode;
+ journal_t *journal = EXT3_SB(sb)->s_journal;
+ transaction_t *transaction;
long ret;
int block;
inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0;
- ei->i_state = 0;
+ ei->i_state_flags = 0;
ei->i_dir_start_lookup = 0;
ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
/* We now have enough fields to check if the inode was active or not.
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
+ /*
+ * Set transaction id's of transactions that have to be committed
+ * to finish f[data]sync. We set them to currently running transaction
+ * as we cannot be sure that the inode or some of its metadata isn't
+ * part of the transaction - the inode could have been reclaimed and
+ * now it is reread from disk.
+ */
+ if (journal) {
+ tid_t tid;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction)
+ transaction = journal->j_running_transaction;
+ else
+ transaction = journal->j_committing_transaction;
+ if (transaction)
+ tid = transaction->t_tid;
+ else
+ tid = journal->j_commit_sequence;
+ spin_unlock(&journal->j_state_lock);
+ atomic_set(&ei->i_sync_tid, tid);
+ atomic_set(&ei->i_datasync_tid, tid);
+ }
+
if (inode->i_ino >= EXT3_FIRST_INO(inode->i_sb) + 1 &&
EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) {
/*
EXT3_GOOD_OLD_INODE_SIZE +
ei->i_extra_isize;
if (*magic == cpu_to_le32(EXT3_XATTR_MAGIC))
- ei->i_state |= EXT3_STATE_XATTR;
+ ext3_set_inode_state(inode, EXT3_STATE_XATTR);
}
} else
ei->i_extra_isize = 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 (ext3_test_inode_state(inode, EXT3_STATE_NEW))
memset(raw_inode, 0, EXT3_SB(inode->i_sb)->s_inode_size);
ext3_get_inode_flags(ei);
/* 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);
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;
- ei->i_state &= ~EXT3_STATE_NEW;
+ ext3_clear_inode_state(inode, EXT3_STATE_NEW);
+ atomic_set(&ei->i_sync_tid, handle->h_transaction->t_tid);
out_brelse:
brelse (bh);
ext3_std_error(inode->i_sb, err);
* `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, int wait)
+int ext3_write_inode(struct inode *inode, struct writeback_control *wbc)
{
if (current->flags & PF_MEMALLOC)
return 0;
return -EIO;
}
- if (!wait)
+ if (wbc->sync_mode != WB_SYNC_ALL)
return 0;
return ext3_force_commit(inode->i_sb);
if (error)
return error;
+ if (ia_valid & ATTR_SIZE)
+ dquot_initialize(inode);
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
- handle = ext3_journal_start(inode, 2*(EXT3_QUOTA_INIT_BLOCKS(inode->i_sb)+
- EXT3_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
+ handle = ext3_journal_start(inode, EXT3_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
+ EXT3_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)+3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
}
- error = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0;
+ error = dquot_transfer(inode, attr);
if (error) {
ext3_journal_stop(handle);
return error;
ret = 2 * (bpp + indirects) + 2;
#ifdef CONFIG_QUOTA
- /* We know that structure was already allocated during vfs_dq_init so
+ /* We know that structure was already allocated during dquot_initialize so
* we will be updating only the data blocks + inodes */
- ret += 2*EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb);
+ ret += EXT3_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
#endif
return ret;
* i_size has been changed by generic_commit_write() and we thus need
* to include the updated inode in the current transaction.
*
- * Also, vfs_dq_alloc_space() will always dirty the inode when blocks
+ * Also, dquot_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
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff