[v14,01/07] dax: Introduce holder for dax_device

Commit Message

Shiyang Ruan May 8, 2022, 2:36 p.m. UTC

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.

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]>
---
 drivers/dax/super.c | 67 ++++++++++++++++++++++++++++++++++++++++++++-
 drivers/md/dm.c     |  2 +-
 fs/erofs/super.c    | 13 +++++----
 fs/ext2/super.c     |  7 +++--
 fs/ext4/super.c     |  9 +++---
 fs/xfs/xfs_buf.c    |  5 ++--
 include/linux/dax.h | 33 ++++++++++++++++------
 7 files changed, 112 insertions(+), 24 deletions(-)

Patch

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0211e6f7b47a..5ddb159c4653 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 {
@@ -194,6 +216,29 @@  int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 EXPORT_SYMBOL_GPL(dax_zero_page_range);
 
+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)
@@ -267,8 +312,15 @@  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);
 
@@ -410,6 +462,19 @@  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 9650ba2075b8..953d8b0ced84 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -755,7 +755,7 @@  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;
 }
 
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 37b39ec9c9c2..f112ae04f1e0 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -274,8 +274,8 @@  static int erofs_init_devices(struct super_block *sb,
 				break;
 			}
 			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);
@@ -658,6 +658,8 @@  static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_fs_info = sbi;
 	sbi->opt = ctx->opt;
 	ctx->opt.fsid = NULL;
+	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off,
+					  NULL, NULL);
 	sbi->devs = ctx->devs;
 	ctx->devs = NULL;
 
@@ -684,7 +686,8 @@  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);
@@ -776,7 +779,7 @@  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);
@@ -850,7 +853,7 @@  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 @@  static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 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 6900da973ce2..801ba7f6b088 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1304,7 +1304,7 @@  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);
@@ -4357,7 +4357,7 @@  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);
 }
 
@@ -4369,7 +4369,8 @@  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);
@@ -4381,7 +4382,7 @@  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 bf4e60871068..63b8d9b5096f 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
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9fc5f99a0ae2..9c426a207ba8 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -32,8 +32,21 @@  struct dax_operations {
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 };
 
+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);
@@ -53,6 +66,10 @@  static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	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)
 {
@@ -96,12 +113,9 @@  struct writeback_control;
 #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)
 {
@@ -111,11 +125,12 @@  static inline void dax_remove_host(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 */
@@ -185,6 +200,8 @@  size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		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,