On Sun, Jul 03, 2022 at 09:08:38PM +0800, Shiyang Ruan wrote:
> 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)
> -> devres_release_all() # was pmem driver ->remove() in v1
> -> 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.
>
> ==
> Changes since v3:
> 1. Flush dirty files and logs when pmem is about to be removed.
> 2. Rebased on next-20220701
>
> Changes since v2:
> 1. Rebased on next-20220615
>
> Changes since v1:
> 1. Drop the needless change of moving {kill,put}_dax()
> 2. Rebased on '[PATCHSETS] v14 fsdax-rmap + v11 fsdax-reflink'[2]
>
> [1]:
> https://lore.kernel.org/linux-mm/161604050314.1463742.14151665140035795571.st...@dwillia2-desk3.amr.corp.intel.com/
> [2]:
> https://lore.kernel.org/linux-xfs/20220508143620.1775214-1-ruansy.f...@fujitsu.com/
>
> Signed-off-by: Shiyang Ruan <ruansy.f...@fujitsu.com>
> ---
> drivers/dax/super.c | 2 +-
> fs/xfs/xfs_notify_failure.c | 23 ++++++++++++++++++++++-
> include/linux/mm.h | 1 +
> 3 files changed, 24 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index 9b5e2a5eb0ae..d4bc83159d46 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -323,7 +323,7 @@ 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/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
> index aa8dc27c599c..269e21b3341c 100644
> --- a/fs/xfs/xfs_notify_failure.c
> +++ b/fs/xfs/xfs_notify_failure.c
> @@ -18,6 +18,7 @@
> #include "xfs_rmap_btree.h"
> #include "xfs_rtalloc.h"
> #include "xfs_trans.h"
> +#include "xfs_log.h"
>
> #include <linux/mm.h>
> #include <linux/dax.h>
> @@ -75,6 +76,10 @@ xfs_dax_failure_fn(
>
> if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
> (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
> + /* Do not shutdown so early when device is to be removed */
> + if (notify->mf_flags & MF_MEM_REMOVE) {
> + return 0;
> + }
> xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
> return -EFSCORRUPTED;
> }
> @@ -168,6 +173,7 @@ xfs_dax_notify_failure(
> struct xfs_mount *mp = dax_holder(dax_dev);
> u64 ddev_start;
> u64 ddev_end;
> + int error;
>
> if (!(mp->m_sb.sb_flags & SB_BORN)) {
> xfs_warn(mp, "filesystem is not ready for notify_failure()!");
> @@ -182,6 +188,13 @@ 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) {
> + /* Flush the log since device is about to be removed. */
If MF_MEM_REMOVE means "storage is about to go away" then perhaps the
only thing we need to do in xfs_dax_notify_failure is log a message
about the pending failure and then call sync_filesystem()? This I think
could come before we even start looking at which device -- if any of the
filesystem blockdevs are about to be removed, the best we can do is
flush all the dirty data to disk.
--D
> + error = xfs_log_force(mp, XFS_LOG_SYNC);
> + if (error)
> + return error;
> + return -EOPNOTSUPP;
> + }
> xfs_err(mp, "ondisk log corrupt, shutting down fs!");
> xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
> return -EFSCORRUPTED;
> @@ -211,8 +224,16 @@ xfs_dax_notify_failure(
> if (offset + len > ddev_end)
> len -= ddev_end - offset;
>
> - return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
> + error = xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
> mf_flags);
> + if (error)
> + return error;
> +
> + if (mf_flags & MF_MEM_REMOVE) {
> + xfs_flush_inodes(mp);
> + error = xfs_log_force(mp, XFS_LOG_SYNC);
> + }
> + return error;
> }
>
> const struct dax_holder_operations xfs_dax_holder_operations = {
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index a2270e35a676..e66d23188323 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3236,6 +3236,7 @@ enum mf_flags {
> MF_SOFT_OFFLINE = 1 << 3,
> MF_UNPOISON = 1 << 4,
> MF_SW_SIMULATED = 1 << 5,
> + MF_MEM_REMOVE = 1 << 6,
> };
> int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
> unsigned long count, int mf_flags);
> --
> 2.36.1
>
>
>
