From: Christoph Hellwig <hch@xxxxxx>
Return IOMAP_F_NEEDDSYNC from xfs_file_iomap_begin() for a synchronous
write fault when inode is pinned, and has dirty fields other than the
timestamps. In xfs_filemap_huge_fault() we then detect this case and
call dax_finish_sync_fault() to make sure all metadata is committed, and
to insert the page table entry.
Note that this will also dirty corresponding radix tree entry which is
what we want - fsync(2) will still provide data integrity guarantees for
applications not using userspace flushing. And applications using
userspace flushing can avoid calling fsync(2) and thus avoid the
performance overhead.
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
fs/xfs/xfs_file.c | 6 +++++-
fs/xfs/xfs_iomap.c | 5 +++++
2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7c6b8def6eed..c45f24ffab22 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1040,7 +1040,11 @@ __xfs_filemap_fault(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = dax_iomap_fault(vmf, pe_size, NULL, &xfs_iomap_ops);
+ pfn_t pfn;
+
+ ret = dax_iomap_fault(vmf, pe_size, &pfn, &xfs_iomap_ops);
+ if (ret & VM_FAULT_NEEDDSYNC)
+ ret = dax_finish_sync_fault(vmf, pe_size, pfn);
} else {
if (write_fault)
ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index f179bdf1644d..b43be199fbdf 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -33,6 +33,7 @@
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
+#include "xfs_inode_item.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
@@ -1086,6 +1087,10 @@ xfs_file_iomap_begin(
trace_xfs_iomap_found(ip, offset, length, 0, &imap);
}
+ if ((flags & IOMAP_WRITE) && xfs_ipincount(ip) &&
+ (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
+ iomap->flags |= IOMAP_F_DIRTY;
+
xfs_bmbt_to_iomap(ip, iomap, &imap);
if (shared)
--
2.12.3
