For configurations that do not enable DAX filesystems or drivers, do not
require the DAX core to be built.
Given that the 'direct_access' method has been removed from
'block_device_operations', we can also go ahead and remove the
block-related dax helper functions from fs/block_dev.c to
drivers/dax/super.c. This keeps dax details out of the block layer and
lets the DAX core be built as a module in the FS_DAX=n case.
Filesystems need to include dax.h to call bdev_dax_supported().
Cc: Jan Kara <jack-IBi9RG/[email protected]>
Cc: [email protected]
Cc: Jens Axboe <axboe-tSWWG44O7X1aa/[email protected]>
Cc: "Theodore Ts'o" <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Alexander Viro <viro-RmSDqhL/[email protected]>
Cc: "Darrick J. Wong" <[email protected]>
Cc: Ross Zwisler <ross.zwisler-VuQAYsv1563Yd54FQh9/[email protected]>
Reported-by: Geert Uytterhoeven <[email protected]>
Signed-off-by: Dan Williams <[email protected]>
---
Changes in v2:
* kill off the remainder of the dax specific routines in the block layer
and move it to the drivers/dax core.
block/Kconfig | 1 -
drivers/dax/super.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++
fs/Kconfig | 1 +
fs/block_dev.c | 66 ---------------------------------------------
fs/ext2/super.c | 1 +
fs/ext4/super.c | 1 +
fs/xfs/xfs_super.c | 1 +
include/linux/blkdev.h | 2 -
include/linux/dax.h | 30 +++++++++++++++++++--
9 files changed, 102 insertions(+), 71 deletions(-)
diff --git a/block/Kconfig b/block/Kconfig
index 93da7fc3f254..e9f780f815f5 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -6,7 +6,6 @@ menuconfig BLOCK
default y
select SBITMAP
select SRCU
- select DAX
help
Provide block layer support for the kernel.
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 465dcd7317d5..e8998d15f3cd 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/magic.h>
+#include <linux/genhd.h>
#include <linux/cdev.h>
#include <linux/hash.h>
#include <linux/slab.h>
@@ -47,6 +48,75 @@ void dax_read_unlock(int id)
}
EXPORT_SYMBOL_GPL(dax_read_unlock);
+int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
+ pgoff_t *pgoff)
+{
+ phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
+
+ if (pgoff)
+ *pgoff = PHYS_PFN(phys_off);
+ if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
+ return -EINVAL;
+ return 0;
+}
+EXPORT_SYMBOL(bdev_dax_pgoff);
+
+/**
+ * __bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @sb: The superblock of the device
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: negative errno if unsupported, 0 if supported.
+ */
+int __bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+ struct block_device *bdev = sb->s_bdev;
+ struct dax_device *dax_dev;
+ pgoff_t pgoff;
+ int err, id;
+ void *kaddr;
+ pfn_t pfn;
+ long len;
+
+ if (blocksize != PAGE_SIZE) {
+ pr_err("VFS (%s): error: unsupported blocksize for dax\n",
+ sb->s_id);
+ return -EINVAL;
+ }
+
+ err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
+ if (err) {
+ pr_err("VFS (%s): error: unaligned partition for dax\n",
+ sb->s_id);
+ return err;
+ }
+
+ dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ if (!dax_dev) {
+ pr_err("VFS (%s): error: device does not support dax\n",
+ sb->s_id);
+ return -EOPNOTSUPP;
+ }
+
+ id = dax_read_lock();
+ len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
+ dax_read_unlock(id);
+
+ put_dax(dax_dev);
+
+ if (len < 1) {
+ pr_err("VFS (%s): error: dax access failed (%ld)",
+ sb->s_id, len);
+ return len < 0 ? len : -EIO;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__bdev_dax_supported);
+
/**
* struct dax_device - anchor object for dax services
* @inode: core vfs
diff --git a/fs/Kconfig b/fs/Kconfig
index 83eab52fb3f6..b0e42b6a96b9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -39,6 +39,7 @@ config FS_DAX
depends on MMU
depends on !(ARM || MIPS || SPARC)
select FS_IOMAP
+ select DAX
help
Direct Access (DAX) can be used on memory-backed block devices.
If the block device supports DAX and the filesystem supports DAX,
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 666367e13711..3096ecd48304 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -718,72 +718,6 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
}
EXPORT_SYMBOL_GPL(bdev_write_page);
-int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
- pgoff_t *pgoff)
-{
- phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
-
- if (pgoff)
- *pgoff = PHYS_PFN(phys_off);
- if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
- return -EINVAL;
- return 0;
-}
-EXPORT_SYMBOL(bdev_dax_pgoff);
-
-/**
- * bdev_dax_supported() - Check if the device supports dax for filesystem
- * @sb: The superblock of the device
- * @blocksize: The block size of the device
- *
- * This is a library function for filesystems to check if the block device
- * can be mounted with dax option.
- *
- * Return: negative errno if unsupported, 0 if supported.
- */
-int bdev_dax_supported(struct super_block *sb, int blocksize)
-{
- struct block_device *bdev = sb->s_bdev;
- struct dax_device *dax_dev;
- pgoff_t pgoff;
- int err, id;
- void *kaddr;
- pfn_t pfn;
- long len;
-
- if (blocksize != PAGE_SIZE) {
- vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
- return -EINVAL;
- }
-
- err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
- if (err) {
- vfs_msg(sb, KERN_ERR, "error: unaligned partition for dax");
- return err;
- }
-
- dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
- if (!dax_dev) {
- vfs_msg(sb, KERN_ERR, "error: device does not support dax");
- return -EOPNOTSUPP;
- }
-
- id = dax_read_lock();
- len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
- dax_read_unlock(id);
-
- put_dax(dax_dev);
-
- if (len < 1) {
- vfs_msg(sb, KERN_ERR,
- "error: dax access failed (%ld)", len);
- return len < 0 ? len : -EIO;
- }
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(bdev_dax_supported);
-
/*
* pseudo-fs
*/
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 9e25a71fe1a2..d07773b81da9 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -32,6 +32,7 @@
#include <linux/log2.h>
#include <linux/quotaops.h>
#include <linux/uaccess.h>
+#include <linux/dax.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a9448db1cf7e..bf6bb8997124 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -37,6 +37,7 @@
#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
+#include <linux/dax.h>
#include <linux/cleancache.h>
#include <linux/uaccess.h>
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 685c042a120f..f5c58d6dcafb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -52,6 +52,7 @@
#include "xfs_reflink.h"
#include <linux/namei.h>
+#include <linux/dax.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/mount.h>
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 848f87eb1905..e4d9899755a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1940,8 +1940,6 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *);
-extern int bdev_dax_supported(struct super_block *, int);
-int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
#else /* CONFIG_BLOCK */
struct block_device;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index d3158e74a59e..7fdf1d710042 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -18,12 +18,38 @@ struct dax_operations {
void **, pfn_t *);
};
+int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
+#if IS_ENABLED(CONFIG_FS_DAX)
+int __bdev_dax_supported(struct super_block *sb, int blocksize);
+static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+ return __bdev_dax_supported(sb, blocksize);
+}
+#else
+static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_DAX)
+struct dax_device *dax_get_by_host(const char *host);
+void put_dax(struct dax_device *dax_dev);
+#else
+static inline struct dax_device *dax_get_by_host(const char *host)
+{
+ return NULL;
+}
+
+static inline void put_dax(struct dax_device *dax_dev)
+{
+}
+#endif
+
int dax_read_lock(void);
void dax_read_unlock(int id);
-struct dax_device *dax_get_by_host(const char *host);
struct dax_device *alloc_dax(void *private, const char *host,
const struct dax_operations *ops);
-void put_dax(struct dax_device *dax_dev);
bool dax_alive(struct dax_device *dax_dev);
void kill_dax(struct dax_device *dax_dev);
void *dax_get_private(struct dax_device *dax_dev);
On Tue 09-05-17 07:17:04, Dan Williams wrote:
> For configurations that do not enable DAX filesystems or drivers, do not
> require the DAX core to be built.
>
> Given that the 'direct_access' method has been removed from
> 'block_device_operations', we can also go ahead and remove the
> block-related dax helper functions from fs/block_dev.c to
> drivers/dax/super.c. This keeps dax details out of the block layer and
> lets the DAX core be built as a module in the FS_DAX=n case.
>
> Filesystems need to include dax.h to call bdev_dax_supported().
>
> Cc: Jan Kara <jack-IBi9RG/[email protected]>
> Cc: [email protected]
> Cc: Jens Axboe <axboe-tSWWG44O7X1aa/[email protected]>
> Cc: "Theodore Ts'o" <[email protected]>
> Cc: Matthew Wilcox <[email protected]>
> Cc: Alexander Viro <viro-RmSDqhL/[email protected]>
> Cc: "Darrick J. Wong" <[email protected]>
> Cc: Ross Zwisler <ross.zwisler-VuQAYsv1563Yd54FQh9/[email protected]>
> Reported-by: Geert Uytterhoeven <[email protected]>
> Signed-off-by: Dan Williams <[email protected]>
Looks good to me. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> Changes in v2:
> * kill off the remainder of the dax specific routines in the block layer
> and move it to the drivers/dax core.
>
> block/Kconfig | 1 -
> drivers/dax/super.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++
> fs/Kconfig | 1 +
> fs/block_dev.c | 66 ---------------------------------------------
> fs/ext2/super.c | 1 +
> fs/ext4/super.c | 1 +
> fs/xfs/xfs_super.c | 1 +
> include/linux/blkdev.h | 2 -
> include/linux/dax.h | 30 +++++++++++++++++++--
> 9 files changed, 102 insertions(+), 71 deletions(-)
>
> diff --git a/block/Kconfig b/block/Kconfig
> index 93da7fc3f254..e9f780f815f5 100644
> --- a/block/Kconfig
> +++ b/block/Kconfig
> @@ -6,7 +6,6 @@ menuconfig BLOCK
> default y
> select SBITMAP
> select SRCU
> - select DAX
> help
> Provide block layer support for the kernel.
>
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index 465dcd7317d5..e8998d15f3cd 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -14,6 +14,7 @@
> #include <linux/module.h>
> #include <linux/mount.h>
> #include <linux/magic.h>
> +#include <linux/genhd.h>
> #include <linux/cdev.h>
> #include <linux/hash.h>
> #include <linux/slab.h>
> @@ -47,6 +48,75 @@ void dax_read_unlock(int id)
> }
> EXPORT_SYMBOL_GPL(dax_read_unlock);
>
> +int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
> + pgoff_t *pgoff)
> +{
> + phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
> +
> + if (pgoff)
> + *pgoff = PHYS_PFN(phys_off);
> + if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
> + return -EINVAL;
> + return 0;
> +}
> +EXPORT_SYMBOL(bdev_dax_pgoff);
> +
> +/**
> + * __bdev_dax_supported() - Check if the device supports dax for filesystem
> + * @sb: The superblock of the device
> + * @blocksize: The block size of the device
> + *
> + * This is a library function for filesystems to check if the block device
> + * can be mounted with dax option.
> + *
> + * Return: negative errno if unsupported, 0 if supported.
> + */
> +int __bdev_dax_supported(struct super_block *sb, int blocksize)
> +{
> + struct block_device *bdev = sb->s_bdev;
> + struct dax_device *dax_dev;
> + pgoff_t pgoff;
> + int err, id;
> + void *kaddr;
> + pfn_t pfn;
> + long len;
> +
> + if (blocksize != PAGE_SIZE) {
> + pr_err("VFS (%s): error: unsupported blocksize for dax\n",
> + sb->s_id);
> + return -EINVAL;
> + }
> +
> + err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
> + if (err) {
> + pr_err("VFS (%s): error: unaligned partition for dax\n",
> + sb->s_id);
> + return err;
> + }
> +
> + dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
> + if (!dax_dev) {
> + pr_err("VFS (%s): error: device does not support dax\n",
> + sb->s_id);
> + return -EOPNOTSUPP;
> + }
> +
> + id = dax_read_lock();
> + len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
> + dax_read_unlock(id);
> +
> + put_dax(dax_dev);
> +
> + if (len < 1) {
> + pr_err("VFS (%s): error: dax access failed (%ld)",
> + sb->s_id, len);
> + return len < 0 ? len : -EIO;
> + }
> +
> + return 0;
> +}
> +EXPORT_SYMBOL_GPL(__bdev_dax_supported);
> +
> /**
> * struct dax_device - anchor object for dax services
> * @inode: core vfs
> diff --git a/fs/Kconfig b/fs/Kconfig
> index 83eab52fb3f6..b0e42b6a96b9 100644
> --- a/fs/Kconfig
> +++ b/fs/Kconfig
> @@ -39,6 +39,7 @@ config FS_DAX
> depends on MMU
> depends on !(ARM || MIPS || SPARC)
> select FS_IOMAP
> + select DAX
> help
> Direct Access (DAX) can be used on memory-backed block devices.
> If the block device supports DAX and the filesystem supports DAX,
> diff --git a/fs/block_dev.c b/fs/block_dev.c
> index 666367e13711..3096ecd48304 100644
> --- a/fs/block_dev.c
> +++ b/fs/block_dev.c
> @@ -718,72 +718,6 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
> }
> EXPORT_SYMBOL_GPL(bdev_write_page);
>
> -int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
> - pgoff_t *pgoff)
> -{
> - phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
> -
> - if (pgoff)
> - *pgoff = PHYS_PFN(phys_off);
> - if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
> - return -EINVAL;
> - return 0;
> -}
> -EXPORT_SYMBOL(bdev_dax_pgoff);
> -
> -/**
> - * bdev_dax_supported() - Check if the device supports dax for filesystem
> - * @sb: The superblock of the device
> - * @blocksize: The block size of the device
> - *
> - * This is a library function for filesystems to check if the block device
> - * can be mounted with dax option.
> - *
> - * Return: negative errno if unsupported, 0 if supported.
> - */
> -int bdev_dax_supported(struct super_block *sb, int blocksize)
> -{
> - struct block_device *bdev = sb->s_bdev;
> - struct dax_device *dax_dev;
> - pgoff_t pgoff;
> - int err, id;
> - void *kaddr;
> - pfn_t pfn;
> - long len;
> -
> - if (blocksize != PAGE_SIZE) {
> - vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
> - return -EINVAL;
> - }
> -
> - err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
> - if (err) {
> - vfs_msg(sb, KERN_ERR, "error: unaligned partition for dax");
> - return err;
> - }
> -
> - dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
> - if (!dax_dev) {
> - vfs_msg(sb, KERN_ERR, "error: device does not support dax");
> - return -EOPNOTSUPP;
> - }
> -
> - id = dax_read_lock();
> - len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
> - dax_read_unlock(id);
> -
> - put_dax(dax_dev);
> -
> - if (len < 1) {
> - vfs_msg(sb, KERN_ERR,
> - "error: dax access failed (%ld)", len);
> - return len < 0 ? len : -EIO;
> - }
> -
> - return 0;
> -}
> -EXPORT_SYMBOL_GPL(bdev_dax_supported);
> -
> /*
> * pseudo-fs
> */
> diff --git a/fs/ext2/super.c b/fs/ext2/super.c
> index 9e25a71fe1a2..d07773b81da9 100644
> --- a/fs/ext2/super.c
> +++ b/fs/ext2/super.c
> @@ -32,6 +32,7 @@
> #include <linux/log2.h>
> #include <linux/quotaops.h>
> #include <linux/uaccess.h>
> +#include <linux/dax.h>
> #include "ext2.h"
> #include "xattr.h"
> #include "acl.h"
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index a9448db1cf7e..bf6bb8997124 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -37,6 +37,7 @@
> #include <linux/ctype.h>
> #include <linux/log2.h>
> #include <linux/crc16.h>
> +#include <linux/dax.h>
> #include <linux/cleancache.h>
> #include <linux/uaccess.h>
>
> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
> index 685c042a120f..f5c58d6dcafb 100644
> --- a/fs/xfs/xfs_super.c
> +++ b/fs/xfs/xfs_super.c
> @@ -52,6 +52,7 @@
> #include "xfs_reflink.h"
>
> #include <linux/namei.h>
> +#include <linux/dax.h>
> #include <linux/init.h>
> #include <linux/slab.h>
> #include <linux/mount.h>
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 848f87eb1905..e4d9899755a7 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -1940,8 +1940,6 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
> extern int bdev_read_page(struct block_device *, sector_t, struct page *);
> extern int bdev_write_page(struct block_device *, sector_t, struct page *,
> struct writeback_control *);
> -extern int bdev_dax_supported(struct super_block *, int);
> -int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
> #else /* CONFIG_BLOCK */
>
> struct block_device;
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index d3158e74a59e..7fdf1d710042 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -18,12 +18,38 @@ struct dax_operations {
> void **, pfn_t *);
> };
>
> +int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
> +#if IS_ENABLED(CONFIG_FS_DAX)
> +int __bdev_dax_supported(struct super_block *sb, int blocksize);
> +static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
> +{
> + return __bdev_dax_supported(sb, blocksize);
> +}
> +#else
> +static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
> +{
> + return -EOPNOTSUPP;
> +}
> +#endif
> +
> +#if IS_ENABLED(CONFIG_DAX)
> +struct dax_device *dax_get_by_host(const char *host);
> +void put_dax(struct dax_device *dax_dev);
> +#else
> +static inline struct dax_device *dax_get_by_host(const char *host)
> +{
> + return NULL;
> +}
> +
> +static inline void put_dax(struct dax_device *dax_dev)
> +{
> +}
> +#endif
> +
> int dax_read_lock(void);
> void dax_read_unlock(int id);
> -struct dax_device *dax_get_by_host(const char *host);
> struct dax_device *alloc_dax(void *private, const char *host,
> const struct dax_operations *ops);
> -void put_dax(struct dax_device *dax_dev);
> bool dax_alive(struct dax_device *dax_dev);
> void kill_dax(struct dax_device *dax_dev);
> void *dax_get_private(struct dax_device *dax_dev);
>
>
--
Jan Kara <jack-IBi9RG/[email protected]>
SUSE Labs, CR