xfs: allow read IO and FICLONE to run concurrently

One of our VM cluster management products needs to snapshot KVM image
files so that they can be restored in case of failure. Snapshotting is
done by redirecting VM disk writes to a sidecar file and using reflink
on the disk image, specifically the FICLONE ioctl as used by
"cp --reflink". Reflink locks the source and destination files while it
operates, which means that reads from the main vm disk image are blocked,
causing the vm to stall. When an image file is heavily fragmented, the
copy process could take several minutes. Some of the vm image files have
50-100 million extent records, and duplicating that much metadata locks
the file for 30 minutes or more. Having activities suspended for such
a long time in a cluster node could result in node eviction.

Clone operations and read IO do not change any data in the source file,
so they should be able to run concurrently. Demote the exclusive locks
taken by FICLONE to shared locks to allow reads while cloning. While a
clone is in progress, writes will take the IOLOCK_EXCL, so they block
until the clone completes.

Link: https://lore.kernel.org/linux-xfs/8911B94D-DD29-4D6E-B5BC-32EAF1866245@oracle.com/
Signed-off-by: Catherine Hoang <catherine.hoang@oracle.com>
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

1 files changed, 50 insertions, 13 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 203700278ddb..e33e5e13b95f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -214,6 +214,43 @@ xfs_ilock_iocb(
 	return 0;
 }
 
+static int
+xfs_ilock_iocb_for_write(
+	struct kiocb		*iocb,
+	unsigned int		*lock_mode)
+{
+	ssize_t			ret;
+	struct xfs_inode	*ip = XFS_I(file_inode(iocb->ki_filp));
+
+	ret = xfs_ilock_iocb(iocb, *lock_mode);
+	if (ret)
+		return ret;
+
+	if (*lock_mode == XFS_IOLOCK_EXCL)
+		return 0;
+	if (!xfs_iflags_test(ip, XFS_IREMAPPING))
+		return 0;
+
+	xfs_iunlock(ip, *lock_mode);
+	*lock_mode = XFS_IOLOCK_EXCL;
+	return xfs_ilock_iocb(iocb, *lock_mode);
+}
+
+static unsigned int
+xfs_ilock_for_write_fault(
+	struct xfs_inode	*ip)
+{
+	/* get a shared lock if no remapping in progress */
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	if (!xfs_iflags_test(ip, XFS_IREMAPPING))
+		return XFS_MMAPLOCK_SHARED;
+
+	/* wait for remapping to complete */
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+	return XFS_MMAPLOCK_EXCL;
+}
+
 STATIC ssize_t
 xfs_file_dio_read(
 	struct kiocb		*iocb,
@@ -551,7 +588,7 @@ xfs_file_dio_write_aligned(
 	unsigned int		iolock = XFS_IOLOCK_SHARED;
 	ssize_t			ret;
 
-	ret = xfs_ilock_iocb(iocb, iolock);
+	ret = xfs_ilock_iocb_for_write(iocb, &iolock);
 	if (ret)
 		return ret;
 	ret = xfs_file_write_checks(iocb, from, &iolock);
@@ -618,7 +655,7 @@ retry_exclusive:
 		flags = IOMAP_DIO_FORCE_WAIT;
 	}
 
-	ret = xfs_ilock_iocb(iocb, iolock);
+	ret = xfs_ilock_iocb_for_write(iocb, &iolock);
 	if (ret)
 		return ret;
 
@@ -1180,7 +1217,7 @@ xfs_file_remap_range(
 	if (xfs_file_sync_writes(file_in) || xfs_file_sync_writes(file_out))
 		xfs_log_force_inode(dest);
 out_unlock:
-	xfs_iunlock2_io_mmap(src, dest);
+	xfs_iunlock2_remapping(src, dest);
 	if (ret)
 		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
 	return remapped > 0 ? remapped : ret;
@@ -1328,6 +1365,7 @@ __xfs_filemap_fault(
 	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	vm_fault_t		ret;
+	unsigned int		lock_mode = 0;
 
 	trace_xfs_filemap_fault(ip, order, write_fault);
 
@@ -1336,25 +1374,24 @@ __xfs_filemap_fault(
 		file_update_time(vmf->vma->vm_file);
 	}
 
+	if (IS_DAX(inode) || write_fault)
+		lock_mode = xfs_ilock_for_write_fault(XFS_I(inode));
+
 	if (IS_DAX(inode)) {
 		pfn_t pfn;
 
-		xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 		ret = xfs_dax_fault(vmf, order, write_fault, &pfn);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, order, pfn);
-		xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	} else if (write_fault) {
+		ret = iomap_page_mkwrite(vmf, &xfs_page_mkwrite_iomap_ops);
 	} else {
-		if (write_fault) {
-			xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-			ret = iomap_page_mkwrite(vmf,
-					&xfs_page_mkwrite_iomap_ops);
-			xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-		} else {
-			ret = filemap_fault(vmf);
-		}
+		ret = filemap_fault(vmf);
 	}
 
+	if (lock_mode)
+		xfs_iunlock(XFS_I(inode), lock_mode);
+
 	if (write_fault)
 		sb_end_pagefault(inode->i_sb);
 	return ret;