[mirror_ubuntu-artful-kernel.git] / include / linux / dax.h

#ifndef _LINUX_DAX_H
#define _LINUX_DAX_H

#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/radix-tree.h>
#include <asm/pgtable.h>

struct iomap_ops;
struct dax_device;
struct dax_operations {
	/*
	 * direct_access: translate a device-relative
	 * logical-page-offset into an absolute physical pfn. Return the
	 * number of pages available for DAX at that pfn.
	 */
	long (*direct_access)(struct dax_device *, pgoff_t, long,
			void **, pfn_t *);
};

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);
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
 * the entry size (PMD) and two more to tell us if the entry is a huge zero
 * page (HZP) or an empty entry that is just used for locking.  In total four
 * special bits.
 *
 * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
 * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
 * block allocation.
 */
#define RADIX_DAX_SHIFT	(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))

static inline unsigned long dax_radix_sector(void *entry)
{
	return (unsigned long)entry >> RADIX_DAX_SHIFT;
}

static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
{
	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
			((unsigned long)sector << RADIX_DAX_SHIFT) |
			RADIX_DAX_ENTRY_LOCK);
}

ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
		const struct iomap_ops *ops);
int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
		    const struct iomap_ops *ops);
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
				      pgoff_t index);
void dax_wake_mapping_entry_waiter(struct address_space *mapping,
		pgoff_t index, void *entry, bool wake_all);

#ifdef CONFIG_FS_DAX
int __dax_zero_page_range(struct block_device *bdev,
		struct dax_device *dax_dev, sector_t sector,
		unsigned int offset, unsigned int length);
#else
static inline int __dax_zero_page_range(struct block_device *bdev,
		struct dax_device *dax_dev, sector_t sector,
		unsigned int offset, unsigned int length)
{
	return -ENXIO;
}
#endif

#ifdef CONFIG_FS_DAX_PMD
static inline unsigned int dax_radix_order(void *entry)
{
	if ((unsigned long)entry & RADIX_DAX_PMD)
		return PMD_SHIFT - PAGE_SHIFT;
	return 0;
}
#else
static inline unsigned int dax_radix_order(void *entry)
{
	return 0;
}
#endif
int dax_pfn_mkwrite(struct vm_fault *vmf);

static inline bool vma_is_dax(struct vm_area_struct *vma)
{
	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}

static inline bool dax_mapping(struct address_space *mapping)
{
	return mapping->host && IS_DAX(mapping->host);
}

struct writeback_control;
int dax_writeback_mapping_range(struct address_space *mapping,
		struct block_device *bdev, struct writeback_control *wbc);
#endif
Commit	Line	Data
c94c2acf MW	1	#ifndef _LINUX_DAX_H
	2	#define _LINUX_DAX_H
	3
	4	#include <linux/fs.h>
	5	#include <linux/mm.h>
4f622938	6	#include <linux/radix-tree.h>
c94c2acf MW	7	#include <asm/pgtable.h>
c94c2acf MW	8
a254e568	9	struct iomap_ops;
6568b08b DW	10	struct dax_device;
	11	struct dax_operations {
	12	/*
	13	* direct_access: translate a device-relative
	14	* logical-page-offset into an absolute physical pfn. Return the
	15	* number of pages available for DAX at that pfn.
	16	*/
	17	long (direct_access)(struct dax_device , pgoff_t, long,
	18	void *, pfn_t );
	19	};
a254e568	20
7b6be844 DW	21	int dax_read_lock(void);
7b6be844 DW	22	void dax_read_unlock(int id);
72058005	23	struct dax_device dax_get_by_host(const char host);
c1d6e828 DW	24	struct dax_device alloc_dax(void private, const char *host,
	25	const struct dax_operations *ops);
	26	void put_dax(struct dax_device *dax_dev);
	27	bool dax_alive(struct dax_device *dax_dev);
	28	void kill_dax(struct dax_device *dax_dev);
	29	void dax_get_private(struct dax_device dax_dev);
b0686260 DW	30	long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
b0686260 DW	31	void *kaddr, pfn_t pfn);
7b6be844	32
fa28f729	33	/*
642261ac RZ	34	* We use lowest available bit in exceptional entry for locking, one bit for
	35	* the entry size (PMD) and two more to tell us if the entry is a huge zero
	36	* page (HZP) or an empty entry that is just used for locking. In total four
	37	* special bits.
	38	*
	39	* If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
	40	* EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
	41	* block allocation.
fa28f729	42	*/
642261ac	43	#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
e804315d	44	#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
642261ac RZ	45	#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
	46	#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
	47	#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
fa28f729	48
642261ac RZ	49	static inline unsigned long dax_radix_sector(void *entry)
	50	{
	51	return (unsigned long)entry >> RADIX_DAX_SHIFT;
	52	}
	53
	54	static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
	55	{
	56	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY \| flags \|
	57	((unsigned long)sector << RADIX_DAX_SHIFT) \|
	58	RADIX_DAX_ENTRY_LOCK);
	59	}
e804315d	60
11c59c92	61	ssize_t dax_iomap_rw(struct kiocb iocb, struct iov_iter iter,
8ff6daa1	62	const struct iomap_ops *ops);
c791ace1 DJ	63	int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
c791ace1 DJ	64	const struct iomap_ops *ops);
ac401cc7	65	int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
c6dcf52c JK	66	int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
	67	int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
	68	pgoff_t index);
ac401cc7	69	void dax_wake_mapping_entry_waiter(struct address_space *mapping,
63e95b5c	70	pgoff_t index, void *entry, bool wake_all);
d1a5f2b4 DW	71
d1a5f2b4 DW	72	#ifdef CONFIG_FS_DAX
cccbce67 DW	73	int __dax_zero_page_range(struct block_device *bdev,
cccbce67 DW	74	struct dax_device *dax_dev, sector_t sector,
679c8bd3	75	unsigned int offset, unsigned int length);
d1a5f2b4	76	#else
679c8bd3	77	static inline int __dax_zero_page_range(struct block_device *bdev,
cccbce67 DW	78	struct dax_device *dax_dev, sector_t sector,
cccbce67 DW	79	unsigned int offset, unsigned int length)
679c8bd3 CH	80	{
	81	return -ENXIO;
	82	}
d1a5f2b4 DW	83	#endif
d1a5f2b4 DW	84
642261ac RZ	85	#ifdef CONFIG_FS_DAX_PMD
	86	static inline unsigned int dax_radix_order(void *entry)
	87	{
	88	if ((unsigned long)entry & RADIX_DAX_PMD)
	89	return PMD_SHIFT - PAGE_SHIFT;
	90	return 0;
	91	}
642261ac RZ	92	#else
	93	static inline unsigned int dax_radix_order(void *entry)
	94	{
	95	return 0;
	96	}
642261ac	97	#endif
11bac800	98	int dax_pfn_mkwrite(struct vm_fault *vmf);
c94c2acf	99
4897c765 MW	100	static inline bool vma_is_dax(struct vm_area_struct *vma)
	101	{
	102	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
	103	}
f9fe48be RZ	104
	105	static inline bool dax_mapping(struct address_space *mapping)
	106	{
	107	return mapping->host && IS_DAX(mapping->host);
	108	}
7f6d5b52 RZ	109
	110	struct writeback_control;
	111	int dax_writeback_mapping_range(struct address_space *mapping,
	112	struct block_device bdev, struct writeback_control wbc);
c94c2acf	113	#endif