dax: introduce holder for dax_device

Patch series "v14 fsdax-rmap + v11 fsdax-reflink", v2.

The patchset fsdax-rmap is aimed to support shared pages tracking for
fsdax.

It moves owner tracking from dax_assocaite_entry() to pmem device driver,
by introducing an interface ->memory_failure() for struct pagemap.  This
interface is called by memory_failure() in mm, and implemented by pmem
device.

Then call holder operations to find the filesystem which the corrupted
data located in, and call filesystem handler to track files or metadata
associated with this page.

Finally we are able to try to fix the corrupted data in filesystem and do
other necessary processing, such as killing processes who are using the
files affected.

The call trace is like this:
memory_failure()
|* fsdax case
|------------
|pgmap->ops->memory_failure()      => pmem_pgmap_memory_failure()
| dax_holder_notify_failure()      =>
|  dax_device->holder_ops->notify_failure() =>
|                                     - xfs_dax_notify_failure()
|  |* xfs_dax_notify_failure()
|  |--------------------------
|  |   xfs_rmap_query_range()
|  |    xfs_dax_failure_fn()
|  |    * corrupted on metadata
|  |       try to recover data, call xfs_force_shutdown()
|  |    * corrupted on file data
|  |       try to recover data, call mf_dax_kill_procs()
|* normal case
|-------------
|mf_generic_kill_procs()


The patchset fsdax-reflink attempts to add CoW support for fsdax, and
takes XFS, which has both reflink and fsdax features, as an example.

One of the key mechanisms needed to be implemented in fsdax is CoW.  Copy
the data from srcmap before we actually write data to the destination
iomap.  And we just copy range in which data won't be changed.

Another mechanism is range comparison.  In page cache case, readpage() is
used to load data on disk to page cache in order to be able to compare
data.  In fsdax case, readpage() does not work.  So, we need another
compare data with direct access support.

With the two mechanisms implemented in fsdax, we are able to make reflink
and fsdax work together in XFS.


This patch (of 14):

To easily track filesystem from a pmem device, we introduce a holder for
dax_device structure, and also its operation.  This holder is used to
remember who is using this dax_device:

 - When it is the backend of a filesystem, the holder will be the
   instance of this filesystem.
 - When this pmem device is one of the targets in a mapped device, the
   holder will be this mapped device.  In this case, the mapped device
   has its own dax_device and it will follow the first rule.  So that we
   can finally track to the filesystem we needed.

The holder and holder_ops will be set when filesystem is being mounted,
or an target device is being activated.

Link: https://lkml.kernel.org/r/20220603053738.1218681-1-ruansy.fnst@fujitsu.com
Link: https://lkml.kernel.org/r/20220603053738.1218681-2-ruansy.fnst@fujitsu.com
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.wiliams@intel.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.com>
Cc: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 18 insertions, 13 deletions

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 95addc5c9d34..3173debeaa5a 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -255,7 +255,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 		if (IS_ERR(bdev))
 			return PTR_ERR(bdev);
 		dif->bdev = bdev;
-		dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off);
+		dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off,
+						  NULL, NULL);
 	}
 
 	dif->blocks = le32_to_cpu(dis->blocks);
@@ -720,7 +721,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 		}
 
 		sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev,
-						  &sbi->dax_part_off);
+						  &sbi->dax_part_off,
+						  NULL, NULL);
 	}
 
 	err = erofs_read_superblock(sb);
@@ -812,7 +814,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
 {
 	struct erofs_device_info *dif = ptr;
 
-	fs_put_dax(dif->dax_dev);
+	fs_put_dax(dif->dax_dev, NULL);
 	if (dif->bdev)
 		blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL);
 	erofs_fscache_unregister_cookie(&dif->fscache);
@@ -886,7 +888,7 @@ static void erofs_kill_sb(struct super_block *sb)
 		return;
 
 	erofs_free_dev_context(sbi->devs);
-	fs_put_dax(sbi->dax_dev);
+	fs_put_dax(sbi->dax_dev, NULL);
 	erofs_fscache_unregister_cookie(&sbi->s_fscache);
 	erofs_fscache_unregister_fs(sb);
 	kfree(sbi->opt.fsid);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index f6a19f6d9f6d..4638946251b9 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -171,7 +171,7 @@ static void ext2_put_super (struct super_block * sb)
 	brelse (sbi->s_sbh);
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
-	fs_put_dax(sbi->s_daxdev);
+	fs_put_dax(sbi->s_daxdev, NULL);
 	kfree(sbi);
 }
 
@@ -835,7 +835,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb_block = sb_block;
-	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off,
+					   NULL, NULL);
 
 	spin_lock_init(&sbi->s_lock);
 	ret = -EINVAL;
@@ -1204,7 +1205,7 @@ failed_mount_group_desc:
 failed_mount:
 	brelse(bh);
 failed_sbi:
-	fs_put_dax(sbi->s_daxdev);
+	fs_put_dax(sbi->s_daxdev, NULL);
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 845f2f8aee5f..1f8bf507ba5a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1307,7 +1307,7 @@ static void ext4_put_super(struct super_block *sb)
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
-	fs_put_dax(sbi->s_daxdev);
+	fs_put_dax(sbi->s_daxdev, NULL);
 	fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
 #if IS_ENABLED(CONFIG_UNICODE)
 	utf8_unload(sb->s_encoding);
@@ -4272,7 +4272,7 @@ static void ext4_free_sbi(struct ext4_sb_info *sbi)
 		return;
 
 	kfree(sbi->s_blockgroup_lock);
-	fs_put_dax(sbi->s_daxdev);
+	fs_put_dax(sbi->s_daxdev, NULL);
 	kfree(sbi);
 }
 
@@ -4284,7 +4284,8 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb)
 	if (!sbi)
 		return NULL;
 
-	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off,
+					   NULL, NULL);
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
@@ -4296,7 +4297,7 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb)
 	sbi->s_sb = sb;
 	return sbi;
 err_out:
-	fs_put_dax(sbi->s_daxdev);
+	fs_put_dax(sbi->s_daxdev, NULL);
 	kfree(sbi);
 	return NULL;
 }
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 4aa9c9cf5b6e..1ec2a7b6d44e 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1911,7 +1911,7 @@ xfs_free_buftarg(
 	list_lru_destroy(&btp->bt_lru);
 
 	blkdev_issue_flush(btp->bt_bdev);
-	fs_put_dax(btp->bt_daxdev);
+	fs_put_dax(btp->bt_daxdev, NULL);
 
 	kmem_free(btp);
 }
@@ -1964,7 +1964,8 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
+	btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, NULL,
+					    NULL);
 
 	/*
 	 * Buffer IO error rate limiting. Limit it to no more than 10 messages