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 <npiggin@suse.de>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: Dmitriy Monakhov <dmonakhov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 29 insertions, 1 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 86ce27c72554..e9344e6f877d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -394,6 +394,8 @@ enum positive_aop_returns {
         AOP_TRUNCATED_PAGE      = 0x80001,
 };
 
+#define AOP_FLAG_UNINTERRUPTIBLE        0x0001 /* will not do a short write */
+
 /*
  * oh the beauties of C type declarations.
  */
@@ -413,7 +415,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 size_t iov_iter_copy_from_user(struct page *page,
                 struct iov_iter *i, unsigned long offset, size_t bytes);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_readable(struct iov_iter *i);
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(struct iov_iter *i);
 
 static inline void iov_iter_init(struct iov_iter *i,
@@ -454,6 +456,14 @@ struct address_space_operations {
          */
         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);
+
         /* Unfortunately this kludge is needed for FIBMAP. Don't use it */
         sector_t (*bmap)(struct address_space *, sector_t);
         void (*invalidatepage) (struct page *, unsigned long);
@@ -468,6 +478,18 @@ struct address_space_operations {
         int (*launder_page) (struct page *);
 };
 
+/*
+ * pagecache_write_begin/pagecache_write_end must be used by general code
+ * to write into the pagecache.
+ */
+int pagecache_write_begin(struct file *, struct address_space *mapping,
+                                loff_t pos, unsigned len, unsigned flags,
+                                struct page **pagep, void **fsdata);
+
+int pagecache_write_end(struct file *, struct address_space *mapping,
+                                loff_t pos, unsigned len, unsigned copied,
+                                struct page *page, void *fsdata);
+
 struct backing_dev_info;
 struct address_space {
         struct inode            *host;          /* owner: inode, block_device */
@@ -1866,6 +1888,12 @@ extern int simple_prepare_write(struct file *file, struct page *page,
                         unsigned offset, unsigned to);
 extern int simple_commit_write(struct file *file, struct page *page,
                                 unsigned offset, unsigned to);
+extern int simple_write_begin(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned flags,
+                        struct page **pagep, void **fsdata);
+extern int simple_write_end(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned copied,
+                        struct page *page, void *fsdata);
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);