From:   Shiyang Ruan <ruansy.fnst@fujitsu.com>
To:     <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
        <nvdimm@lists.linux.dev>, <linux-mm@kvack.org>,
        <linux-fsdevel@vger.kernel.org>
CC:     <djwong@kernel.org>, <dan.j.williams@intel.com>,
        <david@fromorbit.com>, <hch@infradead.org>, <jane.chu@oracle.com>
Subject: [PATCH v9 3/3] mm, pmem, xfs: Introduce MF_MEM_REMOVE for unbind
Date:   Sat, 4 Feb 2023 14:58:38 +0000
Message-ID: <1675522718-88-4-git-send-email-ruansy.fnst@fujitsu.com>
In-Reply-To: <1675522718-88-1-git-send-email-ruansy.fnst@fujitsu.com>
References: <1675522718-88-1-git-send-email-ruansy.fnst@fujitsu.com>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

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_PRE_REMOVE)
      -> xfs_dax_notify_failure()

Introduce MF_MEM_PRE_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.

[1]: https://lore.kernel.org/linux-mm/161604050314.1463742.14151665140035795571.stgit@dwillia2-desk3.amr.corp.intel.com/

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
---
 drivers/dax/super.c         |  3 ++-
 fs/xfs/xfs_notify_failure.c | 28 +++++++++++++++++++++++++++-
 include/linux/mm.h          |  1 +
 3 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index da4438f3188c..40274d19f4f9 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -323,7 +323,8 @@ 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_PRE_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 3830f908e215..5c1e678a1285 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -22,6 +22,7 @@
 
 #include <linux/mm.h>
 #include <linux/dax.h>
+#include <linux/fs.h>
 
 struct xfs_failure_info {
 	xfs_agblock_t		startblock;
@@ -77,6 +78,9 @@ xfs_dax_failure_fn(
 
 	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
 	    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+		/* The device is about to be removed.  Not a really failure. */
+		if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+			return 0;
 		notify->want_shutdown = true;
 		return 0;
 	}
@@ -168,7 +172,9 @@ xfs_dax_notify_ddev_failure(
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
 		if (!error)
 			error = -EFSCORRUPTED;
-	}
+	} else if (mf_flags & MF_MEM_PRE_REMOVE)
+		xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+
 	return error;
 }
 
@@ -182,12 +188,24 @@ xfs_dax_notify_failure(
 	struct xfs_mount	*mp = dax_holder(dax_dev);
 	u64			ddev_start;
 	u64			ddev_end;
+	int			error;
 
 	if (!(mp->m_super->s_flags & SB_BORN)) {
 		xfs_warn(mp, "filesystem is not ready for notify_failure()!");
 		return -EIO;
 	}
 
+	if (mf_flags & MF_MEM_PRE_REMOVE) {
+		xfs_info(mp, "device is about to be removed!");
+		down_write(&mp->m_super->s_umount);
+		error = sync_filesystem(mp->m_super);
+		/* invalidate_inode_pages2() invalidates dax mapping */
+		super_drop_pagecache(mp->m_super, invalidate_inode_pages2);
+		up_write(&mp->m_super->s_umount);
+		if (error)
+			return error;
+	}
+
 	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
 		xfs_debug(mp,
 			 "notify_failure() not supported on realtime device!");
@@ -196,6 +214,8 @@ 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_PRE_REMOVE)
+			return 0;
 		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
 		return -EFSCORRUPTED;
@@ -209,6 +229,12 @@ xfs_dax_notify_failure(
 	ddev_start = mp->m_ddev_targp->bt_dax_part_off;
 	ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
 
+	/* Notify failure on the whole device */
+	if (offset == 0 && len == U64_MAX) {
+		offset = ddev_start;
+		len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
+	}
+
 	/* Ignore the range out of filesystem area */
 	if (offset + len - 1 < ddev_start)
 		return -ENXIO;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8f857163ac89..9711dbc9451f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3424,6 +3424,7 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
 	MF_NO_RETRY = 1 << 6,
+	MF_MEM_PRE_REMOVE = 1 << 7,
 };
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
-- 
2.39.1