From 02d262dffcf4c74e5c4612ee736bdb94f18ed5b9 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Sun, 30 Sep 2012 23:03:42 -0400 Subject: [PATCH] ext4: punch_hole should wait for DIO writers punch_hole is the place where we have to wait for all existing writers (writeback, aio, dio), but currently we simply flush pended end_io request which is not sufficient. Other issue is that punch_hole performed w/o i_mutex held which obviously result in dangerous data corruption due to write-after-free. This patch performs following changes: - Guard punch_hole with i_mutex - Recheck inode flags under i_mutex - Block all new dio readers in order to prevent information leak caused by read-after-free pattern. - punch_hole now wait for all writers in flight NOTE: XXX write-after-free race is still possible because new dirty pages may appear due to mmap(), and currently there is no easy way to stop writeback while punch_hole is in progress. [ Fixed error return from ext4_ext_punch_hole() to make sure that we release i_mutex before returning EPERM or ETXTBUSY -- Ted ] Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 53 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 36 insertions(+), 17 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 232077439aa8..5920e75fc05f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4794,9 +4794,32 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) loff_t first_page_offset, last_page_offset; int credits, err = 0; + /* + * Write out all dirty pages to avoid race conditions + * Then release them. + */ + if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + err = filemap_write_and_wait_range(mapping, + offset, offset + length - 1); + + if (err) + return err; + } + + mutex_lock(&inode->i_mutex); + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + err = -EPERM; + goto out_mutex; + } + if (IS_SWAPFILE(inode)) { + err = -ETXTBSY; + goto out_mutex; + } + /* No need to punch hole beyond i_size */ if (offset >= inode->i_size) - return 0; + goto out_mutex; /* * If the hole extends beyond i_size, set the hole @@ -4814,33 +4837,25 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) first_page_offset = first_page << PAGE_CACHE_SHIFT; last_page_offset = last_page << PAGE_CACHE_SHIFT; - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - - if (err) - return err; - } - /* Now release the pages */ if (last_page_offset > first_page_offset) { truncate_pagecache_range(inode, first_page_offset, last_page_offset - 1); } - /* finish any pending end_io work */ + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); err = ext4_flush_completed_IO(inode); if (err) - return err; + goto out_dio; credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_dio; + } /* @@ -4930,6 +4945,10 @@ out: inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); return err; } int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,