From: Xiubo Li <xiubli@redhat.com>
Date: Mon, 3 Feb 2020 21:28:25 -0500
Subject: ceph: do not execute direct write in parallel if O_APPEND is specified
Git-commit: 8e4473bb50a1796c9c32b244e5dbc5ee24ead937
Patch-mainline: v5.6-rc2
References: jsc#SES-1134

In O_APPEND & O_DIRECT mode, the data from different writers will
be possibly overlapping each other since they take the shared lock.

For example, both Writer1 and Writer2 are in O_APPEND and O_DIRECT
mode:

          Writer1                         Writer2

     shared_lock()                   shared_lock()
     getattr(CAP_SIZE)               getattr(CAP_SIZE)
     iocb->ki_pos = EOF              iocb->ki_pos = EOF
     write(data1)
                                     write(data2)
     shared_unlock()                 shared_unlock()

The data2 will overlap the data1 from the same file offset, the
old EOF.

Switch to exclusive lock instead when O_APPEND is specified.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Acked-by: Luis Henriques <lhenriques@suse.com>
---
 fs/ceph/file.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c3b8e8e0bf17..7e0190b1f821 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1418,6 +1418,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct ceph_cap_flush *prealloc_cf;
 	ssize_t count, written = 0;
 	int err, want, got;
+	bool direct_lock = false;
 	loff_t pos;
 	loff_t limit = max(i_size_read(inode), fsc->max_file_size);
 
@@ -1428,8 +1429,11 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (!prealloc_cf)
 		return -ENOMEM;
 
+	if ((iocb->ki_flags & (IOCB_DIRECT | IOCB_APPEND)) == IOCB_DIRECT)
+		direct_lock = true;
+
 retry_snap:
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (direct_lock)
 		ceph_start_io_direct(inode);
 	else
 		ceph_start_io_write(inode);
@@ -1519,14 +1523,15 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 		/* we might need to revert back to that point */
 		data = *from;
-		if (iocb->ki_flags & IOCB_DIRECT) {
+		if (iocb->ki_flags & IOCB_DIRECT)
 			written = ceph_direct_read_write(iocb, &data, snapc,
 							 &prealloc_cf);
-			ceph_end_io_direct(inode);
-		} else {
+		else
 			written = ceph_sync_write(iocb, &data, pos, snapc);
+		if (direct_lock)
+			ceph_end_io_direct(inode);
+		else
 			ceph_end_io_write(inode);
-		}
 		if (written > 0)
 			iov_iter_advance(from, written);
 		ceph_put_snap_context(snapc);
@@ -1577,7 +1582,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	goto out_unlocked;
 out:
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (direct_lock)
 		ceph_end_io_direct(inode);
 	else
 		ceph_end_io_write(inode);