Commit b0686260 authored by Dan Williams's avatar Dan Williams
Browse files

dax: introduce dax_direct_access() 



Replace bdev_direct_access() with dax_direct_access() that uses
dax_device and dax_operations instead of a block_device and
block_device_operations for dax. Once all consumers of the old api have
been converted bdev_direct_access() will be deleted.

Given that block device partitioning decisions can cause dax page
alignment constraints to be violated this also introduces the
bdev_dax_pgoff() helper. It handles calculating a logical pgoff relative
to the dax_device and also checks for page alignment.

Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
parent d8f07aee

block/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -6,6 +6,7 @@ menuconfig BLOCK 
       default y

       select SBITMAP

       select SRCU

       select DAX

       help

	 Provide block layer support for the kernel.

drivers/dax/super.c

+39 −0
Original line number Diff line number Diff line
@@ -65,6 +65,45 @@ struct dax_device { 
	const struct dax_operations *ops;

};



/**

 * dax_direct_access() - translate a device pgoff to an absolute pfn

 * @dax_dev: a dax_device instance representing the logical memory range

 * @pgoff: offset in pages from the start of the device to translate

 * @nr_pages: number of consecutive pages caller can handle relative to @pfn

 * @kaddr: output parameter that returns a virtual address mapping of pfn

 * @pfn: output parameter that returns an absolute pfn translation of @pgoff

 *

 * Return: negative errno if an error occurs, otherwise the number of

 * pages accessible at the device relative @pgoff.

 */

long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,

		void **kaddr, pfn_t *pfn)

{

	long avail;



	/*

	 * The device driver is allowed to sleep, in order to make the

	 * memory directly accessible.

	 */

	might_sleep();



	if (!dax_dev)

		return -EOPNOTSUPP;



	if (!dax_alive(dax_dev))

		return -ENXIO;



	if (nr_pages < 0)

		return nr_pages;



	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,

			kaddr, pfn);

	if (!avail)

		return -ERANGE;

	return min(avail, nr_pages);

}

EXPORT_SYMBOL_GPL(dax_direct_access);



bool dax_alive(struct dax_device *dax_dev)

{

	lockdep_assert_held(&dax_srcu);

fs/block_dev.c

+14 −0
Original line number Diff line number Diff line
@@ -18,6 +18,7 @@ 
#include <linux/module.h>

#include <linux/blkpg.h>

#include <linux/magic.h>

#include <linux/dax.h>

#include <linux/buffer_head.h>

#include <linux/swap.h>

#include <linux/pagevec.h>
@@ -762,6 +763,19 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) 
}

EXPORT_SYMBOL_GPL(bdev_direct_access);



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

include/linux/blkdev.h

+1 −0
Original line number Diff line number Diff line
@@ -1958,6 +1958,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, 
						struct writeback_control *);

extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *);

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;

include/linux/dax.h

+2 −0
Original line number Diff line number Diff line
@@ -27,6 +27,8 @@ 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);

long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,

		void **kaddr, pfn_t *pfn);



/*

 * We use lowest available bit in exceptional entry for locking, one bit for

CRA Git | Maintained and supported by SUSTech CRA and CCSE