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>
diff --git a/fs/libfs.c b/fs/libfs.c
index 5294de1..f2b32d3 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -351,6 +351,26 @@
return 0;
}
+int simple_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
+{
+ struct page *page;
+ pgoff_t index;
+ unsigned from;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+
+ page = __grab_cache_page(mapping, index);
+ if (!page)
+ return -ENOMEM;
+
+ *pagep = page;
+
+ return simple_prepare_write(file, page, from, from+len);
+}
+
int simple_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
@@ -369,6 +389,28 @@
return 0;
}
+int simple_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+
+ /* zero the stale part of the page if we did a short copy */
+ if (copied < len) {
+ void *kaddr = kmap_atomic(page, KM_USER0);
+ memset(kaddr + from + copied, 0, len - copied);
+ flush_dcache_page(page);
+ kunmap_atomic(kaddr, KM_USER0);
+ }
+
+ simple_commit_write(file, page, from, from+copied);
+
+ unlock_page(page);
+ page_cache_release(page);
+
+ return copied;
+}
+
/*
* the inodes created here are not hashed. If you use iunique to generate
* unique inode values later for this filesystem, then you must take care
@@ -642,6 +684,8 @@
EXPORT_SYMBOL(dcache_readdir);
EXPORT_SYMBOL(generic_read_dir);
EXPORT_SYMBOL(get_sb_pseudo);
+EXPORT_SYMBOL(simple_write_begin);
+EXPORT_SYMBOL(simple_write_end);
EXPORT_SYMBOL(simple_commit_write);
EXPORT_SYMBOL(simple_dir_inode_operations);
EXPORT_SYMBOL(simple_dir_operations);