fs: introduce new truncate sequence

Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.

simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.

simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).

To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
  the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
  the event of write failure after allocation, so this must be performed
  in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
  cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
  variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
  to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.

Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed.  This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).

Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 35 insertions, 1 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 05e5f5996216..1b9ba193b789 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -203,6 +203,9 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 int block_read_full_page(struct page*, get_block_t*);
 int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
                                 unsigned long from);
+int block_write_begin_newtrunc(struct file *, struct address_space *,
+                                loff_t, unsigned, unsigned,
+                                struct page **, void **, get_block_t*);
 int block_write_begin(struct file *, struct address_space *,
                                 loff_t, unsigned, unsigned,
                                 struct page **, void **, get_block_t*);
@@ -214,6 +217,9 @@ int generic_write_end(struct file *, struct address_space *,
                                 struct page *, void *);
 void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
 int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
+int cont_write_begin_newtrunc(struct file *, struct address_space *, loff_t,
+                        unsigned, unsigned, struct page **, void **,
+                        get_block_t *, loff_t *);
 int cont_write_begin(struct file *, struct address_space *, loff_t,
                         unsigned, unsigned, struct page **, void **,
                         get_block_t *, loff_t *);
@@ -225,6 +231,9 @@ void block_sync_page(struct page *);
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
 int file_fsync(struct file *, int);
+int nobh_write_begin_newtrunc(struct file *, struct address_space *,
+                                loff_t, unsigned, unsigned,
+                                struct page **, void **, get_block_t*);
 int nobh_write_begin(struct file *, struct address_space *,
                                 loff_t, unsigned, unsigned,
                                 struct page **, void **, get_block_t*);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index acf6c52a50dd..3428393942a6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2257,6 +2257,10 @@ typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
                             loff_t file_offset);
 void dio_end_io(struct bio *bio, int error);
 
+ssize_t __blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode,
+        struct block_device *bdev, const struct iovec *iov, loff_t offset,
+        unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+        dio_submit_t submit_io, int lock_type);
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         struct block_device *bdev, const struct iovec *iov, loff_t offset,
         unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
@@ -2270,6 +2274,24 @@ enum {
         DIO_SKIP_HOLES  = 0x02,
 };
 
+static inline ssize_t blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb,
+        struct inode *inode, struct block_device *bdev, const struct iovec *iov,
+        loff_t offset, unsigned long nr_segs, get_block_t get_block,
+        dio_iodone_t end_io)
+{
+        return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset,
+                                    nr_segs, get_block, end_io, NULL,
+                                    DIO_LOCKING | DIO_SKIP_HOLES);
+}
+
+static inline ssize_t blockdev_direct_IO_no_locking_newtrunc(int rw, struct kiocb *iocb,
+        struct inode *inode, struct block_device *bdev, const struct iovec *iov,
+        loff_t offset, unsigned long nr_segs, get_block_t get_block,
+        dio_iodone_t end_io)
+{
+        return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset,
+                                nr_segs, get_block, end_io, NULL, 0);
+}
 static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
         struct inode *inode, struct block_device *bdev, const struct iovec *iov,
         loff_t offset, unsigned long nr_segs, get_block_t get_block,
@@ -2342,12 +2364,14 @@ extern int dcache_dir_open(struct inode *, struct file *);
 extern int dcache_dir_close(struct inode *, struct file *);
 extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
 extern int dcache_readdir(struct file *, void *, filldir_t);
+extern int simple_setattr(struct dentry *, struct iattr *);
 extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int simple_statfs(struct dentry *, struct kstatfs *);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
 extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+extern int simple_setsize(struct inode *, loff_t);
 extern int noop_fsync(struct file *, int);
 extern int simple_empty(struct dentry *);
 extern int simple_readpage(struct file *file, struct page *page);
@@ -2384,7 +2408,8 @@ extern int buffer_migrate_page(struct address_space *,
 
 extern int inode_change_ok(const struct inode *, struct iattr *);
 extern int inode_newsize_ok(const struct inode *, loff_t offset);
-extern int __must_check inode_setattr(struct inode *, struct iattr *);
+extern int __must_check inode_setattr(struct inode *, const struct iattr *);
+extern void generic_setattr(struct inode *inode, const struct iattr *attr);
 
 extern void file_update_time(struct file *file);