Commit 1ac0fc8a authored by Yan, Zheng's avatar Yan, Zheng Committed by Sage Weil
Browse files

ceph: fix race between writepages and truncate 



ceph_writepages_start() reads inode->i_size in two places. It can get
different values between successive read, because truncate can change
inode->i_size at any time. The race can lead to mismatch between data
length of osd request and pages marked as writeback. When osd request
finishes, it clear writeback page according to its data length. So
some pages can be left in writeback state forever. The fix is only
read inode->i_size once, save its value to a local variable and use
the local variable when i_size is needed.

Signed-off-by: default avatarYan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: default avatarAlex Elder <elder@inktank.com>
parent 03d254ed

fs/ceph/addr.c

+7 −7
Original line number Diff line number Diff line
@@ -671,7 +671,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
	unsigned wsize = 1 << inode->i_blkbits;

	struct ceph_osd_request *req = NULL;

	int do_sync;

	u64 snap_size = 0;

	u64 snap_size;



	/*

	 * Include a 'sync' in the OSD request if this is a data
@@ -717,6 +717,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
retry:

	/* find oldest snap context with dirty data */

	ceph_put_snap_context(snapc);

	snap_size = 0;

	snapc = get_oldest_context(inode, &snap_size);

	if (!snapc) {

		/* hmm, why does writepages get called when there
@@ -724,6 +725,8 @@ retry: 
		dout(" no snap context with dirty data?\n");

		goto out;

	}

	if (snap_size == 0)

		snap_size = i_size_read(inode);

	dout(" oldest snapc is %p seq %lld (%d snaps)\n",

	     snapc, snapc->seq, snapc->num_snaps);

	if (last_snapc && snapc != last_snapc) {
@@ -795,11 +798,8 @@ get_more_pages: 
				dout("waiting on writeback %p\n", page);

				wait_on_page_writeback(page);

			}

			if ((snap_size && page_offset(page) > snap_size) ||

			    (!snap_size &&

			     page_offset(page) > i_size_read(inode))) {

				dout("%p page eof %llu\n", page, snap_size ?

				     snap_size : i_size_read(inode));

			if (page_offset(page) >= snap_size) {

				dout("%p page eof %llu\n", page, snap_size);

				done = 1;

				unlock_page(page);

				break;
@@ -911,7 +911,7 @@ get_more_pages: 
		/* Format the osd request message and submit the write */



		offset = page_offset(pages[0]);

		len = min((snap_size ? snap_size : i_size_read(inode)) - offset,

		len = min(snap_size - offset,

			  (u64)locked_pages << PAGE_CACHE_SHIFT);

		dout("writepages got %d pages at %llu~%llu\n",

		     locked_pages, offset, len);

CRA Git | Maintained and supported by SUSTech CRA and CCSE