Received-SPF: pass (google.com: best guess record for domain of linux-ext4-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Ritesh Harjani <riteshh@linux.ibm.com>
To:     jack@suse.cz, tytso@mit.edu, linux-ext4@vger.kernel.org
Cc:     linux-fsdevel@vger.kernel.org, mbobrowski@mbobrowski.org,
        riteshh@linux.ibm.com
Subject: [RFCv3 1/4] ext4: fix ext4_dax_read/write inode locking sequence for IOCB_NOWAIT
Date:   Wed, 20 Nov 2019 10:30:21 +0530
In-Reply-To: <20191120050024.11161-1-riteshh@linux.ibm.com>
References: <20191120050024.11161-1-riteshh@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Message-Id: <20191120050024.11161-2-riteshh@linux.ibm.com>
Sender: linux-ext4-owner@vger.kernel.org
Precedence: bulk

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")

Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
---
 fs/ext4/file.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6a7293a5cda2..977ac58dc718 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -88,9 +88,10 @@ 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);
 	}
 	/*
@@ -487,9 +488,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	bool extend = false;
 	struct inode *inode = file_inode(iocb->ki_filp);
 
-	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);
 	}
 
-- 
2.21.0