This patch is inspired by Dan's "mm, dax, pmem: Introduce dev_pagemap_failure()"[1]. With the help of dax_holder and ->notify_failure() mechanism, the pmem driver is able to ask filesystem (or mapped device) on it to unmap all files in use and notify processes who are using those files. Call trace: trigger unbind -> unbind_store() -> ... (skip) -> pmem driver ->remove() -> kill_dax() -> dax_holder_notify_failure(dax_dev, 0, U64_MAX, MF_MEM_REMOVE) -> xfs_dax_notify_failure() Introduce MF_MEM_REMOVE to let filesystem know this is a remove event. So do not shutdown filesystem directly if something not supported, or if failure range includes metadata area. Make sure all files and processes are handled correctly. Based on "[PATCH v12] fsdax: introduce fs query to support reflink"[2] [1]: https://lore.kernel.org/linux-mm/161604050314.1463742.14151665140035795571.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/ [2]: https://lore.kernel.org/linux-xfs/20220410160904.3758789-1-ruansy.fnst@xxxxxxxxxxx/T/#t Signed-off-by: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx> --- drivers/dax/super.c | 2 +- drivers/nvdimm/pmem.c | 3 ++- fs/xfs/xfs_notify_failure.c | 6 +++++- include/linux/mm.h | 1 + 4 files changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 619a05615497..52f820fdd8ff 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -312,7 +312,7 @@ void kill_dax(struct dax_device *dax_dev) return; if (dax_dev->holder_data != NULL) - dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0); + dax_holder_notify_failure(dax_dev, 0, U64_MAX, MF_MEM_REMOVE); clear_bit(DAXDEV_ALIVE, &dax_dev->flags); synchronize_srcu(&dax_srcu); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index bd502957cfdf..72d9e69aea98 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -359,7 +359,6 @@ static void pmem_release_disk(void *__pmem) struct pmem_device *pmem = __pmem; dax_remove_host(pmem->disk); - kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); @@ -597,6 +596,8 @@ static void nd_pmem_remove(struct device *dev) pmem->bb_state = NULL; } nvdimm_flush(to_nd_region(dev->parent), NULL); + + kill_dax(pmem->dax_dev); } static void nd_pmem_shutdown(struct device *dev) diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index aac44f54feb4..f8b41085218b 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -73,7 +73,9 @@ xfs_dax_failure_fn( struct failure_info *notify = data; int error = 0; - if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || + /* Do not shutdown so early when device is to be removed */ + if (!(notify->mf_flags & MF_MEM_REMOVE) || + XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) || (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); return -EFSCORRUPTED; @@ -181,6 +183,8 @@ xfs_dax_notify_failure( if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev && mp->m_logdev_targp != mp->m_ddev_targp) { + if (mf_flags & MF_MEM_REMOVE) + return -EOPNOTSUPP; xfs_err(mp, "ondisk log corrupt, shutting down fs!"); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK); return -EFSCORRUPTED; diff --git a/include/linux/mm.h b/include/linux/mm.h index 742604feef28..b47c3745782d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3225,6 +3225,7 @@ enum mf_flags { MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, + MF_MEM_REMOVE = 1 << 5, }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); -- 2.35.1