From: Darrick J. Wong Date: Sat, 6 Jul 2019 16:29:01 +0000 (-0700) Subject: xfs: don't update lastino for FSBULKSTAT_SINGLE X-Git-Url: http://git.lede-project.org./?a=commitdiff_plain;h=211bbf3c38ed90f43a3ec905e246014f96bceed7;p=openwrt%2Fstaging%2Fblogic.git xfs: don't update lastino for FSBULKSTAT_SINGLE The kernel test robot found a regression of xfs/054 in the conversion of bulkstat to use the new iwalk infrastructure -- if a caller set *lastip = 128 and invoked FSBULKSTAT_SINGLE, the bstat info would be for inode 128, but *lastip would be increased by the kernel to 129. FSBULKSTAT_SINGLE never incremented lastip before, so it's incorrect to make such an update to the internal lastino value now. Fixes: 2810bd6840e463 ("xfs: convert bulkstat to new iwalk infrastructure") Reported-by: kernel test robot Signed-off-by: Darrick J. Wong Reviewed-by: Allison Collins Reviewed-by: Brian Foster --- diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6bf04e71325b..1876461e5104 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -797,7 +797,6 @@ xfs_ioc_fsbulkstat( breq.startino = lastino; breq.icount = 1; error = xfs_bulkstat_one(&breq, xfs_fsbulkstat_one_fmt); - lastino = breq.startino; } else { /* XFS_IOC_FSBULKSTAT */ breq.startino = lastino ? lastino + 1 : 0; error = xfs_bulkstat(&breq, xfs_fsbulkstat_one_fmt);