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>

2 files changed, 67 insertions, 2 deletions

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 50a08b2ec247..9b5e2a5eb0ae 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -22,6 +22,8 @@
  * @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;
@@ -29,6 +31,8 @@ struct dax_device {
 	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;
@@ -71,8 +75,11 @@ EXPORT_SYMBOL_GPL(dax_remove_host);
  * 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;
@@ -92,11 +99,26 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off)
 	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 {
@@ -204,6 +226,29 @@ size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 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)
@@ -277,8 +322,15 @@ void kill_dax(struct dax_device *dax_dev)
 	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);
 
@@ -421,6 +473,19 @@ void put_dax(struct dax_device *dax_dev)
 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
  * @inode: An inode with i_cdev pointing to a dax_dev
  *
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2b75f1ef7386..0177a4ce9a18 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -758,7 +758,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
 	}
 
 	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;
 }