Commit 6eaf4782 authored by Maxim Patlasov's avatar Maxim Patlasov Committed by Miklos Szeredi
Browse files

fuse: writepages: crop secondary requests 



If writeback happens while fuse is in FUSE_NOWRITE condition, the request
will be queued but not processed immediately (see fuse_flush_writepages()).
Until FUSE_NOWRITE becomes relaxed, more writebacks can happen.  They will
be queued as "secondary" requests to that first ("primary") request.

Existing implementation crops only primary request.  This is not correct
because a subsequent extending write(2) may increase i_size and then
secondary requests won't be cropped properly.  The result would be stale
data written to the server to a file offset where zeros must be.

Similar problem may happen if secondary requests are attached to an
in-flight request that was already cropped.

The patch solves the issue by cropping all secondary requests in
fuse_writepage_end().  Thanks to Miklos for idea.

Signed-off-by: default avatarMaxim Patlasov <MPatlasov@parallels.com>
Signed-off-by: default avatarMiklos Szeredi <mszeredi@suse.cz>
parent f6011081

fs/fuse/file.c

+31 −5
Original line number Diff line number Diff line
@@ -1436,12 +1436,12 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) 
}



/* Called under fc->lock, may release and reacquire it */

static void fuse_send_writepage(struct fuse_conn *fc, struct fuse_req *req)

static void fuse_send_writepage(struct fuse_conn *fc, struct fuse_req *req,

				loff_t size)

__releases(fc->lock)

__acquires(fc->lock)

{

	struct fuse_inode *fi = get_fuse_inode(req->inode);

	loff_t size = i_size_read(req->inode);

	struct fuse_write_in *inarg = &req->misc.write.in;

	__u64 data_size = req->num_pages * PAGE_CACHE_SIZE;
@@ -1482,12 +1482,13 @@ __acquires(fc->lock) 
{

	struct fuse_conn *fc = get_fuse_conn(inode);

	struct fuse_inode *fi = get_fuse_inode(inode);

	size_t crop = i_size_read(inode);

	struct fuse_req *req;



	while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) {

		req = list_entry(fi->queued_writes.next, struct fuse_req, list);

		list_del_init(&req->list);

		fuse_send_writepage(fc, req);

		fuse_send_writepage(fc, req, crop);

	}

}
@@ -1499,12 +1500,37 @@ static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_req *req) 
	mapping_set_error(inode->i_mapping, req->out.h.error);

	spin_lock(&fc->lock);

	while (req->misc.write.next) {

		struct fuse_conn *fc = get_fuse_conn(inode);

		struct fuse_write_in *inarg = &req->misc.write.in;

		struct fuse_req *next = req->misc.write.next;

		req->misc.write.next = next->misc.write.next;

		next->misc.write.next = NULL;

		list_add(&next->writepages_entry, &fi->writepages);

		list_add_tail(&next->list, &fi->queued_writes);

		fuse_flush_writepages(inode);



		/*

		 * Skip fuse_flush_writepages() to make it easy to crop requests

		 * based on primary request size.

		 *

		 * 1st case (trivial): there are no concurrent activities using

		 * fuse_set/release_nowrite.  Then we're on safe side because

		 * fuse_flush_writepages() would call fuse_send_writepage()

		 * anyway.

		 *

		 * 2nd case: someone called fuse_set_nowrite and it is waiting

		 * now for completion of all in-flight requests.  This happens

		 * rarely and no more than once per page, so this should be

		 * okay.

		 *

		 * 3rd case: someone (e.g. fuse_do_setattr()) is in the middle

		 * of fuse_set_nowrite..fuse_release_nowrite section.  The fact

		 * that fuse_set_nowrite returned implies that all in-flight

		 * requests were completed along with all of their secondary

		 * requests.  Further primary requests are blocked by negative

		 * writectr.  Hence there cannot be any in-flight requests and

		 * no invocations of fuse_writepage_end() while we're in

		 * fuse_set_nowrite..fuse_release_nowrite section.

		 */

		fuse_send_writepage(fc, next, inarg->offset + inarg->size);

	}

	fi->writectr--;

	fuse_writepage_finish(fc, req);

CRA Git | Maintained and supported by SUSTech CRA and CCSE