xfs: reject all unaligned direct writes to reflinked files

We currently fall back from direct to buffered writes if we detect a
remaining shared extent in the iomap_begin callback.  But by the time
iomap_begin is called for the potentially unaligned end block we might
have already written most of the data to disk, which we'd now write
again using buffered I/O.  To avoid this reject all writes to reflinked
files before starting I/O so that we are guaranteed to only write the
data once.

The alternative would be to unshare the unaligned start and/or end block
before doing the I/O. I think that's doable, and will actually be
required to support reflinks on DAX file system.  But it will take a
little more time and I'd rather get rid of the double write ASAP.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 032c8a74824a38ad5da5bc95d844cde41da7a4a1..2a695a8f4fe7bb6a44277335422f4c4e16846607 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -527,6 +527,15 @@ xfs_file_dio_aio_write(
        if ((iocb->ki_pos & mp->m_blockmask) ||
            ((iocb->ki_pos + count) & mp->m_blockmask)) {
                unaligned_io = 1;
+
+               /*
+                * We can't properly handle unaligned direct I/O to reflink
+                * files yet, as we can't unshare a partial block.
+                */
+               if (xfs_is_reflink_inode(ip)) {
+                       trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
+                       return -EREMCHG;
+               }
                iolock = XFS_IOLOCK_EXCL;
        } else {
                iolock = XFS_IOLOCK_SHARED;

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 84fb8788431bb6f744cd2ed86a8ccef39cb55f06..52d9d1f61d4a61d8419b92c8a0b4c92da2169fac 100644 (file)
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1026,17 +1026,7 @@ xfs_file_iomap_begin(
                if (error)
                        goto out_unlock;
 
-               /*
-                * We're here because we're trying to do a directio write to a
-                * region that isn't aligned to a filesystem block.  If the
-                * extent is shared, fall back to buffered mode to handle the
-                * RMW.
-                */
-               if (!(flags & IOMAP_REPORT) && shared) {
-                       trace_xfs_reflink_bounce_dio_write(ip, &imap);
-                       error = -EREMCHG;
-                       goto out_unlock;
-               }
+               ASSERT((flags & IOMAP_REPORT) || !shared);
        }
 
        if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {

diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 9e9bb9538bb69797d930be47f7662db5148a471a..b654893130e2831a2d84a89cbb5f79a512f2a429 100644 (file)
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3249,7 +3249,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow);
 DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
 
-DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
+DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write);
 DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);