* @inode: inode in question (we are only interested in its superblock)
* @i_block: block number to be parsed
* @offsets: array to store the offsets in
- * @boundary: set this non-zero if the referred-to block is likely to be
- * followed (on disk) by an indirect block.
+ * @boundary: set this non-zero if the referred-to block is likely to be
+ * followed (on disk) by an indirect block.
*
* To store the locations of file's data ext4 uses a data structure common
* for UNIX filesystems - tree of pointers anchored in the inode, with
/* We are done with atomic stuff, now do the rest of housekeeping */
- inode->i_ctime = CURRENT_TIME_SEC;
+ inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
/* had we spliced it onto indirect block? */
}
if (buffer_new(&dummy)) {
J_ASSERT(create != 0);
- J_ASSERT(handle != 0);
+ J_ASSERT(handle != NULL);
/*
* Now that we do not always journal data, we should
return ext4_journal_get_write_access(handle, bh);
}
-static int ext4_prepare_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int ext4_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = mapping->host;
int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
handle_t *handle;
int retries = 0;
+ struct page *page;
+ pgoff_t index;
+ unsigned from, to;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
retry:
- handle = ext4_journal_start(inode, needed_blocks);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ page = __grab_cache_page(mapping, index);
+ if (!page)
+ return -ENOMEM;
+ *pagep = page;
+
+ handle = ext4_journal_start(inode, needed_blocks);
+ if (IS_ERR(handle)) {
+ unlock_page(page);
+ page_cache_release(page);
+ ret = PTR_ERR(handle);
+ goto out;
}
- if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
- ret = nobh_prepare_write(page, from, to, ext4_get_block);
- else
- ret = block_prepare_write(page, from, to, ext4_get_block);
- if (ret)
- goto prepare_write_failed;
- if (ext4_should_journal_data(inode)) {
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+ ext4_get_block);
+
+ if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, do_journal_get_write_access);
}
-prepare_write_failed:
- if (ret)
+
+ if (ret) {
ext4_journal_stop(handle);
+ unlock_page(page);
+ page_cache_release(page);
+ }
+
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
out:
int err = jbd2_journal_dirty_data(handle, bh);
if (err)
ext4_journal_abort_handle(__FUNCTION__, __FUNCTION__,
- bh, handle,err);
+ bh, handle, err);
return err;
}
-/* For commit_write() in data=journal mode */
-static int commit_write_fn(handle_t *handle, struct buffer_head *bh)
+/* For write_end() in data=journal mode */
+static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
return ext4_journal_dirty_metadata(handle, bh);
}
+/*
+ * Generic write_end handler for ordered and writeback ext4 journal modes.
+ * We can't use generic_write_end, because that unlocks the page and we need to
+ * unlock the page after ext4_journal_stop, but ext4_journal_stop must run
+ * after block_write_end.
+ */
+static int ext4_generic_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ 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);
+ mark_inode_dirty(inode);
+ }
+
+ return copied;
+}
+
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
* ext4 never places buffers on inode->i_mapping->private_list. metadata
* buffers are managed internally.
*/
-static int ext4_ordered_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int ext4_ordered_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
- struct inode *inode = page->mapping->host;
+ struct inode *inode = file->f_mapping->host;
+ unsigned from, to;
int ret = 0, ret2;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
+
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, ext4_journal_dirty_data);
if (ret == 0) {
/*
- * generic_commit_write() will run mark_inode_dirty() if i_size
+ * 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 = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ new_i_size = pos + copied;
if (new_i_size > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = new_i_size;
- ret = generic_commit_write(file, page, from, to);
+ copied = ext4_generic_write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ if (copied < 0)
+ ret = copied;
}
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
- return ret;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret ? ret : copied;
}
-static int ext4_writeback_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int ext4_writeback_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
- struct inode *inode = page->mapping->host;
+ struct inode *inode = file->f_mapping->host;
int ret = 0, ret2;
loff_t new_i_size;
- new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ new_i_size = pos + copied;
if (new_i_size > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = new_i_size;
- if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
- ret = nobh_commit_write(file, page, from, to);
- else
- ret = generic_commit_write(file, page, from, to);
+ copied = ext4_generic_write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ if (copied < 0)
+ ret = copied;
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
- return ret;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret ? ret : copied;
}
-static int ext4_journalled_commit_write(struct file *file,
- struct page *page, unsigned from, unsigned to)
+static int ext4_journalled_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
- struct inode *inode = page->mapping->host;
+ struct inode *inode = mapping->host;
int ret = 0, ret2;
int partial = 0;
- loff_t pos;
+ unsigned from, to;
- /*
- * Here we duplicate the generic_commit_write() functionality
- */
- pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
+
+ if (copied < len) {
+ if (!PageUptodate(page))
+ copied = 0;
+ page_zero_new_buffers(page, from+copied, to);
+ }
ret = walk_page_buffers(handle, page_buffers(page), from,
- to, &partial, commit_write_fn);
+ to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
- if (pos > inode->i_size)
- i_size_write(inode, pos);
+ if (pos+copied > inode->i_size)
+ i_size_write(inode, pos+copied);
EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
if (inode->i_size > EXT4_I(inode)->i_disksize) {
EXT4_I(inode)->i_disksize = inode->i_size;
if (!ret)
ret = ret2;
}
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
- return ret;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret ? ret : copied;
}
/*
PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
err = walk_page_buffers(handle, page_buffers(page), 0,
- PAGE_CACHE_SIZE, NULL, commit_write_fn);
+ PAGE_CACHE_SIZE, NULL, write_end_fn);
if (ret == 0)
ret = err;
EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
.readpages = ext4_readpages,
.writepage = ext4_ordered_writepage,
.sync_page = block_sync_page,
- .prepare_write = ext4_prepare_write,
- .commit_write = ext4_ordered_commit_write,
+ .write_begin = ext4_write_begin,
+ .write_end = ext4_ordered_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.readpages = ext4_readpages,
.writepage = ext4_writeback_writepage,
.sync_page = block_sync_page,
- .prepare_write = ext4_prepare_write,
- .commit_write = ext4_writeback_commit_write,
+ .write_begin = ext4_write_begin,
+ .write_end = ext4_writeback_write_end,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.readpages = ext4_readpages,
.writepage = ext4_journalled_writepage,
.sync_page = block_sync_page,
- .prepare_write = ext4_prepare_write,
- .commit_write = ext4_journalled_commit_write,
+ .write_begin = ext4_write_begin,
+ .write_end = ext4_journalled_write_end,
.set_page_dirty = ext4_journalled_set_page_dirty,
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
struct inode *inode = mapping->host;
struct buffer_head *bh;
int err = 0;
- void *kaddr;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
*/
if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
ext4_should_writeback_data(inode) && PageUptodate(page)) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, length, KM_USER0);
set_page_dirty(page);
goto unlock;
}
goto unlock;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, length, KM_USER0);
BUFFER_TRACE(bh, "zeroed end of block");
ext4_discard_reservation(inode);
mutex_unlock(&ei->truncate_mutex);
- inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
/*
inode->i_flags |= S_DIRSYNC;
}
+/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
+void ext4_get_inode_flags(struct ext4_inode_info *ei)
+{
+ unsigned int flags = ei->vfs_inode.i_flags;
+
+ ei->i_flags &= ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
+ EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|EXT4_DIRSYNC_FL);
+ if (flags & S_SYNC)
+ ei->i_flags |= EXT4_SYNC_FL;
+ if (flags & S_APPEND)
+ ei->i_flags |= EXT4_APPEND_FL;
+ if (flags & S_IMMUTABLE)
+ ei->i_flags |= EXT4_IMMUTABLE_FL;
+ if (flags & S_NOATIME)
+ ei->i_flags |= EXT4_NOATIME_FL;
+ if (flags & S_DIRSYNC)
+ ei->i_flags |= EXT4_DIRSYNC_FL;
+}
+
void ext4_read_inode(struct inode * inode)
{
struct ext4_iloc iloc;
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
- 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_dir_start_lookup = 0;
}
inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
-#ifdef EXT4_FRAGMENTS
- ei->i_faddr = le32_to_cpu(raw_inode->i_faddr);
- ei->i_frag_no = raw_inode->i_frag;
- ei->i_frag_size = raw_inode->i_fsize;
-#endif
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
*/
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
- EXT4_INODE_SIZE(inode->i_sb))
+ EXT4_INODE_SIZE(inode->i_sb)) {
+ brelse (bh);
goto bad_inode;
+ }
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
ei->i_extra_isize = sizeof(struct ext4_inode) -
} else
ei->i_extra_isize = 0;
+ EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode);
+ EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode);
+ EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
+ EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
+
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
if (ei->i_state & EXT4_STATE_NEW)
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
+ ext4_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if(!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le32(ei->i_disksize);
- raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
- raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
- raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
+
+ EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
+ EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
+ EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
+ EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
+
raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
raw_inode->i_flags = cpu_to_le32(ei->i_flags);
-#ifdef EXT4_FRAGMENTS
- raw_inode->i_faddr = cpu_to_le32(ei->i_faddr);
- raw_inode->i_frag = ei->i_frag_no;
- raw_inode->i_fsize = ei->i_frag_size;
-#endif
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
raw_inode->i_file_acl_high =
return 0;
if (ext4_journal_current_handle()) {
- jbd_debug(0, "called recursively, non-PF_MEMALLOC!\n");
+ jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
dump_stack();
return -EIO;
}
return err;
}
+/*
+ * Expand an inode by new_extra_isize bytes.
+ * Returns 0 on success or negative error number on failure.
+ */
+int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize,
+ struct ext4_iloc iloc, handle_t *handle)
+{
+ struct ext4_inode *raw_inode;
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_entry *entry;
+
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+ return 0;
+
+ raw_inode = ext4_raw_inode(&iloc);
+
+ header = IHDR(inode, raw_inode);
+ entry = IFIRST(header);
+
+ /* No extended attributes present */
+ if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR) ||
+ header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
+ new_extra_isize);
+ EXT4_I(inode)->i_extra_isize = new_extra_isize;
+ return 0;
+ }
+
+ /* try to expand with EAs present */
+ return ext4_expand_extra_isize_ea(inode, new_extra_isize,
+ raw_inode, handle);
+}
+
/*
* What we do here is to mark the in-core inode as clean with respect to inode
* dirtiness (it may still be data-dirty).
int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
{
struct ext4_iloc iloc;
- int err;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ static unsigned int mnt_count;
+ int err, ret;
might_sleep();
err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+ !(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
+ /*
+ * We need extra buffer credits since we may write into EA block
+ * with this same handle. If journal_extend fails, then it will
+ * only result in a minor loss of functionality for that inode.
+ * If this is felt to be critical, then e2fsck should be run to
+ * force a large enough s_min_extra_isize.
+ */
+ if ((jbd2_journal_extend(handle,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) {
+ ret = ext4_expand_extra_isize(inode,
+ sbi->s_want_extra_isize,
+ iloc, handle);
+ if (ret) {
+ EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+ if (mnt_count !=
+ le16_to_cpu(sbi->s_es->s_mnt_count)) {
+ ext4_warning(inode->i_sb, __FUNCTION__,
+ "Unable to expand inode %lu. Delete"
+ " some EAs or run e2fsck.",
+ inode->i_ino);
+ mnt_count =
+ le16_to_cpu(sbi->s_es->s_mnt_count);
+ }
+ }
+ }
+ }
if (!err)
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
return err;
*/
journal = EXT4_JOURNAL(inode);
- if (is_journal_aborted(journal) || IS_RDONLY(inode))
+ if (is_journal_aborted(journal))
return -EROFS;
jbd2_journal_lock_updates(journal);