From: John Garry <john.g.garry@oracle.com> mainline inclusion from mainline-v6.17-rc1 commit 68456d05eb57a5d16b4be2d3caf421bdcf2de72e category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ID2HML CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Atomic writes are not currently supported for DAX, but two problems exist: - we may go down DAX write path for IOCB_ATOMIC, which does not handle IOCB_ATOMIC properly - we report non-zero atomic write limits in statx (for DAX inodes) We may want atomic writes support on DAX in future, but just disallow for now. For this, ensure when IOCB_ATOMIC is set that we check the write size versus the atomic write min and max before branching off to the DAX write path. This is not strictly required for DAX, as we should not get this far in the write path as FMODE_CAN_ATOMIC_WRITE should not be set. In addition, due to reflink being supported for DAX, we automatically get CoW-based atomic writes support being advertised. Remedy this by disallowing atomic writes for a DAX inode for both sw and hw modes. Reported-by: Darrick J. Wong <djwong@kernel.org> Fixes: 9dffc58f2384 ("xfs: update atomic write limits") Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: John Garry <john.g.garry@oracle.com> Signed-off-by: Carlos Maiolino <cem@kernel.org> Conflicts: fs/xfs/xfs_inode.h Signed-off-by: Long Li <leo.lilong@huawei.com> --- fs/xfs/xfs_file.c | 6 +++--- fs/xfs/xfs_inode.h | 17 +++++++++++++++++ fs/xfs/xfs_iops.c | 5 +++-- 3 files changed, 23 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ff7326d84444..f85a92fbbca3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -909,9 +909,6 @@ xfs_file_write_iter( if (xfs_is_shutdown(ip->i_mount)) return -EIO; - if (IS_DAX(inode)) - return xfs_file_dax_write(iocb, from); - if (iocb->ki_flags & IOCB_ATOMIC) { if (ocount < xfs_get_atomic_write_min(ip)) return -EINVAL; @@ -924,6 +921,9 @@ xfs_file_write_iter( return ret; } + if (IS_DAX(inode)) + return xfs_file_dax_write(iocb, from); + if (iocb->ki_flags & IOCB_DIRECT) { /* * Allow a directio write to fall back to a buffered diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index b5bd4138cbfa..c33a96849a76 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -171,6 +171,12 @@ static inline struct inode *VFS_I(struct xfs_inode *ip) return &ip->i_vnode; } +/* convert from const xfs inode to const vfs inode */ +static inline const struct inode *VFS_IC(const struct xfs_inode *ip) +{ + return &ip->i_vnode; +} + /* * For regular files we only update the on-disk filesize when actually * writing data back to disk. Until then only the copy in the VFS inode @@ -323,9 +329,20 @@ static inline bool xfs_inode_has_bigrtalloc(struct xfs_inode *ip) static inline bool xfs_inode_can_hw_atomic_write(const struct xfs_inode *ip) { + if (IS_DAX(VFS_IC(ip))) + return false; + return xfs_inode_buftarg(ip)->bt_bdev_awu_max > 0; } +static inline bool xfs_inode_can_sw_atomic_write(const struct xfs_inode *ip) +{ + if (IS_DAX(VFS_IC(ip))) + return false; + + return xfs_can_sw_atomic_write(ip->i_mount); +} + /* * In-core inode flags. */ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 57223706f028..982e90daea73 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -577,7 +577,8 @@ xfs_get_atomic_write_min( * write of exactly one single fsblock if the bdev will make that * guarantee for us. */ - if (xfs_inode_can_hw_atomic_write(ip) || xfs_can_sw_atomic_write(mp)) + if (xfs_inode_can_hw_atomic_write(ip) || + xfs_inode_can_sw_atomic_write(ip)) return mp->m_sb.sb_blocksize; return 0; @@ -594,7 +595,7 @@ xfs_get_atomic_write_max( * write of exactly one single fsblock if the bdev will make that * guarantee for us. */ - if (!xfs_can_sw_atomic_write(mp)) { + if (!xfs_inode_can_sw_atomic_write(ip)) { if (xfs_inode_can_hw_atomic_write(ip)) return mp->m_sb.sb_blocksize; return 0; -- 2.39.2