| Message ID | 20250213135619.1148432-9-john.g.garry@oracle.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | large atomic writes for xfs with CoW | expand |
On Thu, Feb 13, 2025 at 01:56:16PM +0000, John Garry wrote: > Add xfs_file_dio_write_atomic() for dedicated handling of atomic writes. > > In case of -EAGAIN being returned from iomap_dio_rw(), reissue the write > in CoW-based atomic write mode. > > For CoW-based mode, ensure that we have no outstanding IOs which we > may trample on. > > Signed-off-by: John Garry <john.g.garry@oracle.com> Looks fine, Reviewed-by: "Darrick J. Wong" <djwong@kernel.org> --D > --- > fs/xfs/xfs_file.c | 42 ++++++++++++++++++++++++++++++++++++++++++ > 1 file changed, 42 insertions(+) > > diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c > index 258c82cbce12..9762fa503a41 100644 > --- a/fs/xfs/xfs_file.c > +++ b/fs/xfs/xfs_file.c > @@ -619,6 +619,46 @@ xfs_file_dio_write_aligned( > return ret; > } > > +static noinline ssize_t > +xfs_file_dio_write_atomic( > + struct xfs_inode *ip, > + struct kiocb *iocb, > + struct iov_iter *from) > +{ > + unsigned int iolock = XFS_IOLOCK_SHARED; > + unsigned int dio_flags = 0; > + ssize_t ret; > + > +retry: > + ret = xfs_ilock_iocb_for_write(iocb, &iolock); > + if (ret) > + return ret; > + > + ret = xfs_file_write_checks(iocb, from, &iolock); > + if (ret) > + goto out_unlock; > + > + if (dio_flags & IOMAP_DIO_FORCE_WAIT) > + inode_dio_wait(VFS_I(ip)); > + > + trace_xfs_file_direct_write(iocb, from); > + ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, > + &xfs_dio_write_ops, dio_flags, NULL, 0); > + > + if (ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT) && > + !(dio_flags & IOMAP_DIO_ATOMIC_COW)) { > + xfs_iunlock(ip, iolock); > + dio_flags = IOMAP_DIO_ATOMIC_COW | IOMAP_DIO_FORCE_WAIT; > + iolock = XFS_IOLOCK_EXCL; > + goto retry; > + } > + > +out_unlock: > + if (iolock) > + xfs_iunlock(ip, iolock); > + return ret; > +} > + > /* > * Handle block unaligned direct I/O writes > * > @@ -723,6 +763,8 @@ xfs_file_dio_write( > return -EINVAL; > if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask) > return xfs_file_dio_write_unaligned(ip, iocb, from); > + if (iocb->ki_flags & IOCB_ATOMIC) > + return xfs_file_dio_write_atomic(ip, iocb, from); > return xfs_file_dio_write_aligned(ip, iocb, from); > } > > -- > 2.31.1 > >
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 258c82cbce12..9762fa503a41 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -619,6 +619,46 @@ xfs_file_dio_write_aligned( return ret; } +static noinline ssize_t +xfs_file_dio_write_atomic( + struct xfs_inode *ip, + struct kiocb *iocb, + struct iov_iter *from) +{ + unsigned int iolock = XFS_IOLOCK_SHARED; + unsigned int dio_flags = 0; + ssize_t ret; + +retry: + ret = xfs_ilock_iocb_for_write(iocb, &iolock); + if (ret) + return ret; + + ret = xfs_file_write_checks(iocb, from, &iolock); + if (ret) + goto out_unlock; + + if (dio_flags & IOMAP_DIO_FORCE_WAIT) + inode_dio_wait(VFS_I(ip)); + + trace_xfs_file_direct_write(iocb, from); + ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, + &xfs_dio_write_ops, dio_flags, NULL, 0); + + if (ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT) && + !(dio_flags & IOMAP_DIO_ATOMIC_COW)) { + xfs_iunlock(ip, iolock); + dio_flags = IOMAP_DIO_ATOMIC_COW | IOMAP_DIO_FORCE_WAIT; + iolock = XFS_IOLOCK_EXCL; + goto retry; + } + +out_unlock: + if (iolock) + xfs_iunlock(ip, iolock); + return ret; +} + /* * Handle block unaligned direct I/O writes * @@ -723,6 +763,8 @@ xfs_file_dio_write( return -EINVAL; if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask) return xfs_file_dio_write_unaligned(ip, iocb, from); + if (iocb->ki_flags & IOCB_ATOMIC) + return xfs_file_dio_write_atomic(ip, iocb, from); return xfs_file_dio_write_aligned(ip, iocb, from); }
Add xfs_file_dio_write_atomic() for dedicated handling of atomic writes. In case of -EAGAIN being returned from iomap_dio_rw(), reissue the write in CoW-based atomic write mode. For CoW-based mode, ensure that we have no outstanding IOs which we may trample on. Signed-off-by: John Garry <john.g.garry@oracle.com> --- fs/xfs/xfs_file.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+)