From afddba49d18f346e5cc2938b6ed7c512db18ca68 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Tue, 16 Oct 2007 01:25:01 -0700 Subject: fs: introduce write_begin, write_end, and perform_write aops These are intended to replace prepare_write and commit_write with more flexible alternatives that are also able to avoid the buffered write deadlock problems efficiently (which prepare_write is unable to do). [mark.fasheh@oracle.com: API design contributions, code review and fixes] [akpm@linux-foundation.org: various fixes] [dmonakhov@sw.ru: new aop block_write_begin fix] Signed-off-by: Nick Piggin Signed-off-by: Mark Fasheh Signed-off-by: Dmitriy Monakhov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/Locking | 9 +++++--- Documentation/filesystems/vfs.txt | 45 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 3 deletions(-) (limited to 'Documentation/filesystems') diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index f0f825808ca4..fe26cc978523 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -178,15 +178,18 @@ prototypes: locking rules: All except set_page_dirty may block - BKL PageLocked(page) + BKL PageLocked(page) i_sem writepage: no yes, unlocks (see below) readpage: no yes, unlocks sync_page: no maybe writepages: no set_page_dirty no no readpages: no -prepare_write: no yes -commit_write: no yes +prepare_write: no yes yes +commit_write: no yes yes +write_begin: no locks the page yes +write_end: no yes, unlocks yes +perform_write: no n/a yes bmap: yes invalidatepage: no yes releasepage: no yes diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 045f3e055a28..281c19ff7f45 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -537,6 +537,12 @@ struct address_space_operations { struct list_head *pages, unsigned nr_pages); int (*prepare_write)(struct file *, struct page *, unsigned, unsigned); int (*commit_write)(struct file *, struct page *, unsigned, unsigned); + int (*write_begin)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata); + int (*write_end)(struct file *, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata); sector_t (*bmap)(struct address_space *, sector_t); int (*invalidatepage) (struct page *, unsigned long); int (*releasepage) (struct page *, int); @@ -633,6 +639,45 @@ struct address_space_operations { operations. It should avoid returning an error if possible - errors should have been handled by prepare_write. + write_begin: This is intended as a replacement for prepare_write. The + key differences being that: + - it returns a locked page (in *pagep) rather than being + given a pre locked page; + - it must be able to cope with short writes (where the + length passed to write_begin is greater than the number + of bytes copied into the page). + + Called by the generic buffered write code to ask the filesystem to + prepare to write len bytes at the given offset in the file. The + address_space should check that the write will be able to complete, + by allocating space if necessary and doing any other internal + housekeeping. If the write will update parts of any basic-blocks on + storage, then those blocks should be pre-read (if they haven't been + read already) so that the updated blocks can be written out properly. + + The filesystem must return the locked pagecache page for the specified + offset, in *pagep, for the caller to write into. + + flags is a field for AOP_FLAG_xxx flags, described in + include/linux/fs.h. + + A void * may be returned in fsdata, which then gets passed into + write_end. + + Returns 0 on success; < 0 on failure (which is the error code), in + which case write_end is not called. + + write_end: After a successful write_begin, and data copy, write_end must + be called. len is the original len passed to write_begin, and copied + is the amount that was able to be copied (copied == len is always true + if write_begin was called with the AOP_FLAG_UNINTERRUPTIBLE flag). + + The filesystem must take care of unlocking the page and releasing it + refcount, and updating i_size. + + Returns < 0 on failure, otherwise the number of bytes (<= 'copied') + that were able to be copied into pagecache. + bmap: called by the VFS to map a logical block offset within object to physical block number. This method is used by the FIBMAP ioctl and for working with swap-files. To be able to swap to -- cgit v1.2.3