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/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Shiyang Ruan <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Dan Williams <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
Cc: Dave Chinner <[e-mail]>
Cc: Jane Chu <[e-mail]>
Cc: Goldwyn Rodrigues <[e-mail]>
Cc: Al Viro <[e-mail]>
Cc: Matthew Wilcox <[e-mail]>
Cc: Naoya Horiguchi <[e-mail]>
Cc: Miaohe Lin <[e-mail]>
Cc: Dan Williams <[e-mail]>
Cc: Goldwyn Rodrigues <[e-mail]>
Cc: Ritesh Harjani <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

drivers/dax/super.c

···
  * @private: dax driver private data
  * @flags: state and boolean properties
  * @ops: operations for this device
+ * @holder_data: holder of a dax_device: could be filesystem or mapped device
+ * @holder_ops: operations for the inner holder
  */
 struct dax_device {
 	struct inode inode;
···
 	void *private;
 	unsigned long flags;
 	const struct dax_operations *ops;
+	void *holder_data;
+	const struct dax_holder_operations *holder_ops;
 };
 
 static dev_t dax_devt;
···
  * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
  * @bdev: block device to find a dax_device for
  * @start_off: returns the byte offset into the dax_device that @bdev starts
+ * @holder: filesystem or mapped device inside the dax_device
+ * @ops: operations for the inner holder
  */
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
+		void *holder, const struct dax_holder_operations *ops)
 {
 	struct dax_device *dax_dev;
 	u64 part_size;
···
 	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
 	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
 		dax_dev = NULL;
+	else if (holder) {
+		if (!cmpxchg(&dax_dev->holder_data, NULL, holder))
+			dax_dev->holder_ops = ops;
+		else
+			dax_dev = NULL;
+	}
 	dax_read_unlock(id);
 
 	return dax_dev;
 }
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
+
+void fs_put_dax(struct dax_device *dax_dev, void *holder)
+{
+	if (dax_dev && holder &&
+	    cmpxchg(&dax_dev->holder_data, holder, NULL) == holder)
+		dax_dev->holder_ops = NULL;
+	put_dax(dax_dev);
+}
+EXPORT_SYMBOL_GPL(fs_put_dax);
 #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
 enum dax_device_flags {
···
 }
 EXPORT_SYMBOL_GPL(dax_recovery_write);
 
+int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off,
+			      u64 len, int mf_flags)
+{
+	int rc, id;
+
+	id = dax_read_lock();
+	if (!dax_alive(dax_dev)) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	if (!dax_dev->holder_ops) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags);
+out:
+	dax_read_unlock(id);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dax_holder_notify_failure);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
···
 	if (!dax_dev)
 		return;
 
+	if (dax_dev->holder_data != NULL)
+		dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0);
+
 	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
 	synchronize_srcu(&dax_srcu);
+
+	/* clear holder data */
+	dax_dev->holder_ops = NULL;
+	dax_dev->holder_data = NULL;
 }
 EXPORT_SYMBOL_GPL(kill_dax);
 
···
 	iput(&dax_dev->inode);
 }
 EXPORT_SYMBOL_GPL(put_dax);
+
+/**
+ * dax_holder() - obtain the holder of a dax device
+ * @dax_dev: a dax_device instance
+
+ * Return: the holder's data which represents the holder if registered,
+ * otherwize NULL.
+ */
+void *dax_holder(struct dax_device *dax_dev)
+{
+	return dax_dev->holder_data;
+}
+EXPORT_SYMBOL_GPL(dax_holder);
 
 /**
  * inode_dax: convert a public inode into its dax_dev

drivers/md/dm.c

···
 	}
 
 	td->dm_dev.bdev = bdev;
-	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off);
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off, NULL, NULL);
 	return 0;
 }
 

fs/erofs/super.c

···
 		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);
···
 		}
 
 		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);
···
 {
 	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);
···
 		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);

fs/ext2/super.c

···
 	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);
 }
 
···
 	}
 	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;
···
 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);

fs/ext4/super.c

···
 	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);
···
 		return;
 
 	kfree(sbi->s_blockgroup_lock);
-	fs_put_dax(sbi->s_daxdev);
+	fs_put_dax(sbi->s_daxdev, NULL);
 	kfree(sbi);
 }
 
···
 	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);
···
 	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;
 }

fs/xfs/xfs_buf.c

···
 	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);
 }
···
 	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

include/linux/dax.h

···
 			void *addr, size_t bytes, struct iov_iter *iter);
 };
 
+struct dax_holder_operations {
+	/*
+	 * notify_failure - notify memory failure into inner holder device
+	 * @dax_dev: the dax device which contains the holder
+	 * @offset: offset on this dax device where memory failure occurs
+	 * @len: length of this memory failure event
+	 * @flags: action flags for memory failure handler
+	 */
+	int (*notify_failure)(struct dax_device *dax_dev, u64 offset,
+			u64 len, int mf_flags);
+};
+
 #if IS_ENABLED(CONFIG_DAX)
 struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
+void *dax_holder(struct dax_device *dax_dev);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
···
 	return dax_synchronous(dax_dev);
 }
 #else
+static inline void *dax_holder(struct dax_device *dax_dev)
+{
+	return NULL;
+}
 static inline struct dax_device *alloc_dax(void *private,
 		const struct dax_operations *ops)
 {
···
 #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
 int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
 void dax_remove_host(struct gendisk *disk);
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
-		u64 *start_off);
-static inline void fs_put_dax(struct dax_device *dax_dev)
-{
-	put_dax(dax_dev);
-}
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
+		void *holder, const struct dax_holder_operations *ops);
+void fs_put_dax(struct dax_device *dax_dev, void *holder);
 #else
 static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 {
···
 {
 }
 static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
-		u64 *start_off)
+		u64 *start_off, void *holder,
+		const struct dax_holder_operations *ops)
 {
 	return NULL;
 }
-static inline void fs_put_dax(struct dax_device *dax_dev)
+static inline void fs_put_dax(struct dax_device *dax_dev, void *holder)
 {
 }
 #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
···
 		size_t bytes, struct iov_iter *i);
 int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 			size_t nr_pages);
+int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len,
+		int mf_flags);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,