Message ID | 1348487060-19598-7-git-send-email-dmonakhov@openvz.org |
---|---|
State | Superseded, archived |
Headers | show |
On Mon 24-09-12 15:44:16, Dmitry Monakhov wrote: > punch_hole are the places 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. Even more i_mutex is not holded while punch_hole > 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 > truncate_pagecache_range() is not completely reliable and where > is no easy way to stop writeback while punch_hole is in progress. The race I know about is writing via mmap after truncate_pagecache_range() but before buffers are really truncated. Do you know about something else? > Changes from V1: > Add flag checks once we hold i_mutex Looks good. You can add: Reviewed-by: Jan Kara <jack@suse.cz> Honza > > Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> > --- > fs/ext4/extents.c | 48 ++++++++++++++++++++++++++++++++---------------- > 1 files changed, 32 insertions(+), 16 deletions(-) > > diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c > index 6326874..2d58f4c 100644 > --- a/fs/ext4/extents.c > +++ b/fs/ext4/extents.c > @@ -4821,9 +4821,29 @@ 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); > + /* Need recheck file flags under mutex */ > + /* It's not possible punch hole on append only file */ > + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) > + return -EPERM; > + if (IS_SWAPFILE(inode)) > + return -ETXTBSY; > + > /* 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 > @@ -4841,31 +4861,23 @@ 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); > ext4_unwritten_wait(inode); > > 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; > + } > > > /* > @@ -4955,6 +4967,10 @@ 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, > -- > 1.7.7.6 >
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 6326874..2d58f4c 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4821,9 +4821,29 @@ 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); + /* Need recheck file flags under mutex */ + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return -EPERM; + if (IS_SWAPFILE(inode)) + return -ETXTBSY; + /* 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 @@ -4841,31 +4861,23 @@ 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); ext4_unwritten_wait(inode); 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; + } /* @@ -4955,6 +4967,10 @@ 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,
punch_hole are the places 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. Even more i_mutex is not holded while punch_hole 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 truncate_pagecache_range() is not completely reliable and where is no easy way to stop writeback while punch_hole is in progress. Changes from V1: Add flag checks once we hold i_mutex Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> --- fs/ext4/extents.c | 48 ++++++++++++++++++++++++++++++++---------------- 1 files changed, 32 insertions(+), 16 deletions(-)