ext4: fix ext4_dax_read/write inode locking sequence for IOCB_NOWAIT

[ Upstream commit f629afe3369e9885fd6e9cc7a4f514b6a65cf9e9 ]

Apparently our current rwsem code doesn't like doing the trylock, then
lock for real scheme.  So change our dax read/write methods to just do the
trylock for the RWF_NOWAIT case.
This seems to fix AIM7 regression in some scalable filesystems upto ~25%
in some cases. Claimed in commit 942491c9e6d6 ("xfs: fix AIM7 regression")

Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
Tested-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Link: https://lore.kernel.org/r/20191212055557.11151-2-riteshh@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index f4a24a4..52d155b 100644 (file)
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -40,9 +40,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
        struct inode *inode = file_inode(iocb->ki_filp);
        ssize_t ret;
 
-       if (!inode_trylock_shared(inode)) {
-               if (iocb->ki_flags & IOCB_NOWAIT)
+       if (iocb->ki_flags & IOCB_NOWAIT) {
+               if (!inode_trylock_shared(inode))
                        return -EAGAIN;
+       } else {
                inode_lock_shared(inode);
        }
        /*
@@ -190,9 +191,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
        struct inode *inode = file_inode(iocb->ki_filp);
        ssize_t ret;
 
-       if (!inode_trylock(inode)) {
-               if (iocb->ki_flags & IOCB_NOWAIT)
+       if (iocb->ki_flags & IOCB_NOWAIT) {
+               if (!inode_trylock(inode))
                        return -EAGAIN;
+       } else {
                inode_lock(inode);
        }
        ret = ext4_write_checks(iocb, from);