Re: [PATCH v13 1/7] dax: Introduce holder for dax_device
On Tue, Apr 19, 2022 at 12:50:39PM +0800, Shiyang Ruan wrote:
> 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
> Reviewed-by: Christoph Hellwig
> Reviewed-by: Dan Williams
LGTM
Reviewed-by: Darrick J. Wong
--D
> ---
> drivers/dax/super.c | 67 -
> drivers/md/dm.c | 2 +-
> fs/erofs/super.c| 10 ---
> fs/ext2/super.c | 7 +++--
> fs/ext4/super.c | 9 +++---
> fs/xfs/xfs_buf.c| 5 ++--
> include/linux/dax.h | 33 --
> 7 files changed, 110 insertions(+), 23 deletions(-)
>
> 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
[PATCH v13 1/7] dax: Introduce holder for dax_device
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
Reviewed-by: Christoph Hellwig
Reviewed-by: Dan Williams
---
drivers/dax/super.c | 67 -
drivers/md/dm.c | 2 +-
fs/erofs/super.c| 10 ---
fs/ext2/super.c | 7 +++--
fs/ext4/super.c | 9 +++---
fs/xfs/xfs_buf.c| 5 ++--
include/linux/dax.h | 33 --
7 files changed, 110 insertions(+), 23 deletions(-)
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_h
