[linux-2.6-block.git] / fs / erofs / internal.h

/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             http://www.huawei.com/
 * Created by Gao Xiang <gaoxiang25@huawei.com>
 */
#ifndef __EROFS_INTERNAL_H
#define __EROFS_INTERNAL_H

#include <linux/fs.h>
#include <linux/dcache.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include "erofs_fs.h"

/* redefine pr_fmt "erofs: " */
#undef pr_fmt
#define pr_fmt(fmt) "erofs: " fmt

#define errln(x, ...)   pr_err(x "\n", ##__VA_ARGS__)
#define infoln(x, ...)  pr_info(x "\n", ##__VA_ARGS__)
#ifdef CONFIG_EROFS_FS_DEBUG
#define debugln(x, ...) pr_debug(x "\n", ##__VA_ARGS__)
#define DBG_BUGON               BUG_ON
#else
#define debugln(x, ...)         ((void)0)
#define DBG_BUGON(x)            ((void)(x))
#endif	/* !CONFIG_EROFS_FS_DEBUG */

enum {
	FAULT_KMALLOC,
	FAULT_READ_IO,
	FAULT_MAX,
};

#ifdef CONFIG_EROFS_FAULT_INJECTION
extern const char *erofs_fault_name[FAULT_MAX];
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))

struct erofs_fault_info {
	atomic_t inject_ops;
	unsigned int inject_rate;
	unsigned int inject_type;
};
#endif	/* CONFIG_EROFS_FAULT_INJECTION */

/* EROFS_SUPER_MAGIC_V1 to represent the whole file system */
#define EROFS_SUPER_MAGIC   EROFS_SUPER_MAGIC_V1

typedef u64 erofs_nid_t;
typedef u64 erofs_off_t;
/* data type for filesystem-wide blocks number */
typedef u32 erofs_blk_t;

struct erofs_sb_info {
#ifdef CONFIG_EROFS_FS_ZIP
	/* list for all registered superblocks, mainly for shrinker */
	struct list_head list;
	struct mutex umount_mutex;

	/* the dedicated workstation for compression */
	struct radix_tree_root workstn_tree;

	/* threshold for decompression synchronously */
	unsigned int max_sync_decompress_pages;

	unsigned int shrinker_run_no;

	/* current strategy of how to use managed cache */
	unsigned char cache_strategy;

	/* pseudo inode to manage cached pages */
	struct inode *managed_cache;
#endif	/* CONFIG_EROFS_FS_ZIP */
	u32 blocks;
	u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
	u32 xattr_blkaddr;
#endif

	/* inode slot unit size in bit shift */
	unsigned char islotbits;

	u32 build_time_nsec;
	u64 build_time;

	/* what we really care is nid, rather than ino.. */
	erofs_nid_t root_nid;
	/* used for statfs, f_files - f_favail */
	u64 inos;

	u8 uuid[16];                    /* 128-bit uuid for volume */
	u8 volume_name[16];             /* volume name */
	u32 requirements;

	unsigned int mount_opt;

#ifdef CONFIG_EROFS_FAULT_INJECTION
	struct erofs_fault_info fault_info;	/* For fault injection */
#endif
};

#ifdef CONFIG_EROFS_FAULT_INJECTION
#define erofs_show_injection_info(type)					\
	infoln("inject %s in %s of %pS", erofs_fault_name[type],        \
		__func__, __builtin_return_address(0))

static inline bool time_to_inject(struct erofs_sb_info *sbi, int type)
{
	struct erofs_fault_info *ffi = &sbi->fault_info;

	if (!ffi->inject_rate)
		return false;

	if (!IS_FAULT_SET(ffi, type))
		return false;

	atomic_inc(&ffi->inject_ops);
	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
		atomic_set(&ffi->inject_ops, 0);
		return true;
	}
	return false;
}
#else
static inline bool time_to_inject(struct erofs_sb_info *sbi, int type)
{
	return false;
}

static inline void erofs_show_injection_info(int type)
{
}
#endif	/* !CONFIG_EROFS_FAULT_INJECTION */

static inline void *erofs_kmalloc(struct erofs_sb_info *sbi,
					size_t size, gfp_t flags)
{
	if (time_to_inject(sbi, FAULT_KMALLOC)) {
		erofs_show_injection_info(FAULT_KMALLOC);
		return NULL;
	}
	return kmalloc(size, flags);
}

#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
#define EROFS_I_SB(inode) ((struct erofs_sb_info *)(inode)->i_sb->s_fs_info)

/* Mount flags set via mount options or defaults */
#define EROFS_MOUNT_XATTR_USER		0x00000010
#define EROFS_MOUNT_POSIX_ACL		0x00000020
#define EROFS_MOUNT_FAULT_INJECTION	0x00000040

#define clear_opt(sbi, option)	((sbi)->mount_opt &= ~EROFS_MOUNT_##option)
#define set_opt(sbi, option)	((sbi)->mount_opt |= EROFS_MOUNT_##option)
#define test_opt(sbi, option)	((sbi)->mount_opt & EROFS_MOUNT_##option)

#ifdef CONFIG_EROFS_FS_ZIP
enum {
	EROFS_ZIP_CACHE_DISABLED,
	EROFS_ZIP_CACHE_READAHEAD,
	EROFS_ZIP_CACHE_READAROUND
};

#define EROFS_LOCKED_MAGIC     (INT_MIN | 0xE0F510CCL)

/* basic unit of the workstation of a super_block */
struct erofs_workgroup {
	/* the workgroup index in the workstation */
	pgoff_t index;

	/* overall workgroup reference count */
	atomic_t refcount;
};

#if defined(CONFIG_SMP)
static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
						 int val)
{
	preempt_disable();
	if (val != atomic_cmpxchg(&grp->refcount, val, EROFS_LOCKED_MAGIC)) {
		preempt_enable();
		return false;
	}
	return true;
}

static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
					    int orig_val)
{
	/*
	 * other observers should notice all modifications
	 * in the freezing period.
	 */
	smp_mb();
	atomic_set(&grp->refcount, orig_val);
	preempt_enable();
}

static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
{
	return atomic_cond_read_relaxed(&grp->refcount,
					VAL != EROFS_LOCKED_MAGIC);
}
#else
static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
						 int val)
{
	preempt_disable();
	/* no need to spin on UP platforms, let's just disable preemption. */
	if (val != atomic_read(&grp->refcount)) {
		preempt_enable();
		return false;
	}
	return true;
}

static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
					    int orig_val)
{
	preempt_enable();
}

static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
{
	int v = atomic_read(&grp->refcount);

	/* workgroup is never freezed on uniprocessor systems */
	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
	return v;
}
#endif	/* !CONFIG_SMP */

/* hard limit of pages per compressed cluster */
#define Z_EROFS_CLUSTER_MAX_PAGES       (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
#define EROFS_PCPUBUF_NR_PAGES          Z_EROFS_CLUSTER_MAX_PAGES
#else
#define EROFS_PCPUBUF_NR_PAGES          0
#endif	/* !CONFIG_EROFS_FS_ZIP */

/* we strictly follow PAGE_SIZE and no buffer head yet */
#define LOG_BLOCK_SIZE		PAGE_SHIFT

#undef LOG_SECTORS_PER_BLOCK
#define LOG_SECTORS_PER_BLOCK	(PAGE_SHIFT - 9)

#undef SECTORS_PER_BLOCK
#define SECTORS_PER_BLOCK	(1 << SECTORS_PER_BLOCK)

#define EROFS_BLKSIZ		(1 << LOG_BLOCK_SIZE)

#if (EROFS_BLKSIZ % 4096 || !EROFS_BLKSIZ)
#error erofs cannot be used in this platform
#endif

#define EROFS_IO_MAX_RETRIES_NOFAIL     5

#define ROOT_NID(sb)		((sb)->root_nid)

#define erofs_blknr(addr)       ((addr) / EROFS_BLKSIZ)
#define erofs_blkoff(addr)      ((addr) % EROFS_BLKSIZ)
#define blknr_to_addr(nr)       ((erofs_off_t)(nr) * EROFS_BLKSIZ)

static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid)
{
	return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits);
}

/* atomic flag definitions */
#define EROFS_V_EA_INITED_BIT	0
#define EROFS_V_Z_INITED_BIT	1

/* bitlock definitions (arranged in reverse order) */
#define EROFS_V_BL_XATTR_BIT	(BITS_PER_LONG - 1)
#define EROFS_V_BL_Z_BIT	(BITS_PER_LONG - 2)

struct erofs_vnode {
	erofs_nid_t nid;

	/* atomic flags (including bitlocks) */
	unsigned long flags;

	unsigned char datamode;
	unsigned char inode_isize;
	unsigned short xattr_isize;

	unsigned int xattr_shared_count;
	unsigned int *xattr_shared_xattrs;

	union {
		erofs_blk_t raw_blkaddr;
#ifdef CONFIG_EROFS_FS_ZIP
		struct {
			unsigned short z_advise;
			unsigned char  z_algorithmtype[2];
			unsigned char  z_logical_clusterbits;
			unsigned char  z_physical_clusterbits[2];
		};
#endif	/* CONFIG_EROFS_FS_ZIP */
	};
	/* the corresponding vfs inode */
	struct inode vfs_inode;
};

#define EROFS_V(ptr)	\
	container_of(ptr, struct erofs_vnode, vfs_inode)

#define __inode_advise(x, bit, bits) \
	(((x) >> (bit)) & ((1 << (bits)) - 1))

#define __inode_version(advise)	\
	__inode_advise(advise, EROFS_I_VERSION_BIT,	\
		EROFS_I_VERSION_BITS)

#define __inode_data_mapping(advise)	\
	__inode_advise(advise, EROFS_I_DATA_MAPPING_BIT,\
		EROFS_I_DATA_MAPPING_BITS)

static inline unsigned long inode_datablocks(struct inode *inode)
{
	/* since i_size cannot be changed */
	return DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
}

static inline bool is_inode_layout_compression(struct inode *inode)
{
	return erofs_inode_is_data_compressed(EROFS_V(inode)->datamode);
}

static inline bool is_inode_flat_inline(struct inode *inode)
{
	return EROFS_V(inode)->datamode == EROFS_INODE_FLAT_INLINE;
}

extern const struct super_operations erofs_sops;

extern const struct address_space_operations erofs_raw_access_aops;
#ifdef CONFIG_EROFS_FS_ZIP
extern const struct address_space_operations z_erofs_vle_normalaccess_aops;
#endif

/*
 * Logical to physical block mapping, used by erofs_map_blocks()
 *
 * Different with other file systems, it is used for 2 access modes:
 *
 * 1) RAW access mode:
 *
 * Users pass a valid (m_lblk, m_lofs -- usually 0) pair,
 * and get the valid m_pblk, m_pofs and the longest m_len(in bytes).
 *
 * Note that m_lblk in the RAW access mode refers to the number of
 * the compressed ondisk block rather than the uncompressed
 * in-memory block for the compressed file.
 *
 * m_pofs equals to m_lofs except for the inline data page.
 *
 * 2) Normal access mode:
 *
 * If the inode is not compressed, it has no difference with
 * the RAW access mode. However, if the inode is compressed,
 * users should pass a valid (m_lblk, m_lofs) pair, and get
 * the needed m_pblk, m_pofs, m_len to get the compressed data
 * and the updated m_lblk, m_lofs which indicates the start
 * of the corresponding uncompressed data in the file.
 */
enum {
	BH_Zipped = BH_PrivateStart,
	BH_FullMapped,
};

/* Has a disk mapping */
#define EROFS_MAP_MAPPED	(1 << BH_Mapped)
/* Located in metadata (could be copied from bd_inode) */
#define EROFS_MAP_META		(1 << BH_Meta)
/* The extent has been compressed */
#define EROFS_MAP_ZIPPED	(1 << BH_Zipped)
/* The length of extent is full */
#define EROFS_MAP_FULL_MAPPED	(1 << BH_FullMapped)

struct erofs_map_blocks {
	erofs_off_t m_pa, m_la;
	u64 m_plen, m_llen;

	unsigned int m_flags;

	struct page *mpage;
};

/* Flags used by erofs_map_blocks() */
#define EROFS_GET_BLOCKS_RAW    0x0001

/* zmap.c */
#ifdef CONFIG_EROFS_FS_ZIP
int z_erofs_fill_inode(struct inode *inode);
int z_erofs_map_blocks_iter(struct inode *inode,
			    struct erofs_map_blocks *map,
			    int flags);
#else
static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; }
static inline int z_erofs_map_blocks_iter(struct inode *inode,
					  struct erofs_map_blocks *map,
					  int flags)
{
	return -EOPNOTSUPP;
}
#endif	/* !CONFIG_EROFS_FS_ZIP */

/* data.c */
static inline struct bio *erofs_grab_bio(struct super_block *sb,
					 erofs_blk_t blkaddr,
					 unsigned int nr_pages,
					 void *bi_private, bio_end_io_t endio,
					 bool nofail)
{
	const gfp_t gfp = GFP_NOIO;
	struct bio *bio;

	do {
		if (nr_pages == 1) {
			bio = bio_alloc(gfp | (nofail ? __GFP_NOFAIL : 0), 1);
			if (!bio) {
				DBG_BUGON(nofail);
				return ERR_PTR(-ENOMEM);
			}
			break;
		}
		bio = bio_alloc(gfp, nr_pages);
		nr_pages /= 2;
	} while (!bio);

	bio->bi_end_io = endio;
	bio_set_dev(bio, sb->s_bdev);
	bio->bi_iter.bi_sector = (sector_t)blkaddr << LOG_SECTORS_PER_BLOCK;
	bio->bi_private = bi_private;
	return bio;
}

static inline void __submit_bio(struct bio *bio, unsigned int op,
				unsigned int op_flags)
{
	bio_set_op_attrs(bio, op, op_flags);
	submit_bio(bio);
}

struct page *__erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr,
				   bool prio, bool nofail);

static inline struct page *erofs_get_meta_page(struct super_block *sb,
	erofs_blk_t blkaddr, bool prio)
{
	return __erofs_get_meta_page(sb, blkaddr, prio, false);
}

int erofs_map_blocks(struct inode *, struct erofs_map_blocks *, int);

static inline struct page *erofs_get_inline_page(struct inode *inode,
						 erofs_blk_t blkaddr)
{
	return erofs_get_meta_page(inode->i_sb, blkaddr,
				   S_ISDIR(inode->i_mode));
}

/* inode.c */
static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
{
#if BITS_PER_LONG == 32
	return (nid >> 32) ^ (nid & 0xffffffff);
#else
	return nid;
#endif
}

extern const struct inode_operations erofs_generic_iops;
extern const struct inode_operations erofs_symlink_iops;
extern const struct inode_operations erofs_fast_symlink_iops;

static inline void set_inode_fast_symlink(struct inode *inode)
{
	inode->i_op = &erofs_fast_symlink_iops;
}

static inline bool is_inode_fast_symlink(struct inode *inode)
{
	return inode->i_op == &erofs_fast_symlink_iops;
}

struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid, bool dir);
int erofs_getattr(const struct path *path, struct kstat *stat,
		  u32 request_mask, unsigned int query_flags);

/* namei.c */
extern const struct inode_operations erofs_dir_iops;

int erofs_namei(struct inode *dir, struct qstr *name,
		erofs_nid_t *nid, unsigned int *d_type);

/* dir.c */
extern const struct file_operations erofs_dir_fops;

/* utils.c / zdata.c */
struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp, bool nofail);

#if (EROFS_PCPUBUF_NR_PAGES > 0)
void *erofs_get_pcpubuf(unsigned int pagenr);
#define erofs_put_pcpubuf(buf) do { \
	(void)&(buf);	\
	preempt_enable();	\
} while (0)
#else
static inline void *erofs_get_pcpubuf(unsigned int pagenr)
{
	return ERR_PTR(-EOPNOTSUPP);
}

#define erofs_put_pcpubuf(buf) do {} while (0)
#endif

#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
					     pgoff_t index, bool *tag);
int erofs_register_workgroup(struct super_block *sb,
			     struct erofs_workgroup *grp, bool tag);
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
void erofs_shrinker_register(struct super_block *sb);
void erofs_shrinker_unregister(struct super_block *sb);
int __init erofs_init_shrinker(void);
void erofs_exit_shrinker(void);
int __init z_erofs_init_zip_subsystem(void);
void z_erofs_exit_zip_subsystem(void);
int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
				       struct erofs_workgroup *egrp);
int erofs_try_to_free_cached_page(struct address_space *mapping,
				  struct page *page);
#else
static inline void erofs_shrinker_register(struct super_block *sb) {}
static inline void erofs_shrinker_unregister(struct super_block *sb) {}
static inline int erofs_init_shrinker(void) { return 0; }
static inline void erofs_exit_shrinker(void) {}
static inline int z_erofs_init_zip_subsystem(void) { return 0; }
static inline void z_erofs_exit_zip_subsystem(void) {}
#endif	/* !CONFIG_EROFS_FS_ZIP */

#define EFSCORRUPTED    EUCLEAN         /* Filesystem is corrupted */

#endif	/* __EROFS_INTERNAL_H */
Commit	Line	Data
29b24f6c GX	1	/* SPDX-License-Identifier: GPL-2.0-only */
29b24f6c GX	2	/*
bfb8674d GX	3	* Copyright (C) 2017-2018 HUAWEI, Inc.
	4	* http://www.huawei.com/
	5	* Created by Gao Xiang <gaoxiang25@huawei.com>
bfb8674d	6	*/
14f362b4 GX	7	#ifndef __EROFS_INTERNAL_H
14f362b4 GX	8	#define __EROFS_INTERNAL_H
bfb8674d GX	9
	10	#include <linux/fs.h>
	11	#include <linux/dcache.h>
	12	#include <linux/mm.h>
	13	#include <linux/pagemap.h>
	14	#include <linux/bio.h>
	15	#include <linux/buffer_head.h>
47e4937a	16	#include <linux/magic.h>
bfb8674d GX	17	#include <linux/slab.h>
	18	#include <linux/vmalloc.h>
	19	#include "erofs_fs.h"
	20
	21	/* redefine pr_fmt "erofs: " */
	22	#undef pr_fmt
	23	#define pr_fmt(fmt) "erofs: " fmt
	24
	25	#define errln(x, ...) pr_err(x "\n", ##__VA_ARGS__)
	26	#define infoln(x, ...) pr_info(x "\n", ##__VA_ARGS__)
	27	#ifdef CONFIG_EROFS_FS_DEBUG
	28	#define debugln(x, ...) pr_debug(x "\n", ##__VA_ARGS__)
bfb8674d GX	29	#define DBG_BUGON BUG_ON
	30	#else
	31	#define debugln(x, ...) ((void)0)
eef16878	32	#define DBG_BUGON(x) ((void)(x))
14f362b4	33	#endif /* !CONFIG_EROFS_FS_DEBUG */
bfb8674d	34
9c07b3b3 CY	35	enum {
9c07b3b3 CY	36	FAULT_KMALLOC,
14a56ec6	37	FAULT_READ_IO,
9c07b3b3 CY	38	FAULT_MAX,
	39	};
	40
f8499d6e	41	#ifdef CONFIG_EROFS_FAULT_INJECTION
14a56ec6	42	extern const char *erofs_fault_name[FAULT_MAX];
9c07b3b3 CY	43	#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
	44
	45	struct erofs_fault_info {
	46	atomic_t inject_ops;
	47	unsigned int inject_rate;
	48	unsigned int inject_type;
	49	};
14f362b4	50	#endif /* CONFIG_EROFS_FAULT_INJECTION */
9c07b3b3	51
bfb8674d GX	52	/* EROFS_SUPER_MAGIC_V1 to represent the whole file system */
	53	#define EROFS_SUPER_MAGIC EROFS_SUPER_MAGIC_V1
	54
	55	typedef u64 erofs_nid_t;
14f362b4 GX	56	typedef u64 erofs_off_t;
	57	/* data type for filesystem-wide blocks number */
	58	typedef u32 erofs_blk_t;
bfb8674d GX	59
bfb8674d GX	60	struct erofs_sb_info {
22fe04a7	61	#ifdef CONFIG_EROFS_FS_ZIP
2497ee41 GX	62	/* list for all registered superblocks, mainly for shrinker */
2497ee41 GX	63	struct list_head list;
a1581312	64	struct mutex umount_mutex;
2497ee41	65
e7e9a307 GX	66	/* the dedicated workstation for compression */
e7e9a307 GX	67	struct radix_tree_root workstn_tree;
105d4ad8	68
5fb76bb0 GX	69	/* threshold for decompression synchronously */
	70	unsigned int max_sync_decompress_pages;
	71
22fe04a7 GX	72	unsigned int shrinker_run_no;
22fe04a7 GX	73
4279f3f9 GX	74	/* current strategy of how to use managed cache */
4279f3f9 GX	75	unsigned char cache_strategy;
105d4ad8	76
4279f3f9 GX	77	/* pseudo inode to manage cached pages */
4279f3f9 GX	78	struct inode *managed_cache;
22fe04a7 GX	79	#endif /* CONFIG_EROFS_FS_ZIP */
	80	u32 blocks;
	81	u32 meta_blkaddr;
	82	#ifdef CONFIG_EROFS_FS_XATTR
	83	u32 xattr_blkaddr;
02827e17	84	#endif
bfb8674d	85
22fe04a7 GX	86	/* inode slot unit size in bit shift */
	87	unsigned char islotbits;
	88
bfb8674d GX	89	u32 build_time_nsec;
	90	u64 build_time;
	91
	92	/* what we really care is nid, rather than ino.. */
	93	erofs_nid_t root_nid;
	94	/* used for statfs, f_files - f_favail */
	95	u64 inos;
	96
	97	u8 uuid[16]; /* 128-bit uuid for volume */
	98	u8 volume_name[16]; /* volume name */
5efe5137 GX	99	u32 requirements;
5efe5137 GX	100
bfb8674d	101	unsigned int mount_opt;
9c07b3b3 CY	102
	103	#ifdef CONFIG_EROFS_FAULT_INJECTION
	104	struct erofs_fault_info fault_info; /* For fault injection */
	105	#endif
bfb8674d GX	106	};
bfb8674d GX	107
9c07b3b3 CY	108	#ifdef CONFIG_EROFS_FAULT_INJECTION
	109	#define erofs_show_injection_info(type) \
	110	infoln("inject %s in %s of %pS", erofs_fault_name[type], \
	111	__func__, __builtin_return_address(0))
	112
	113	static inline bool time_to_inject(struct erofs_sb_info *sbi, int type)
	114	{
	115	struct erofs_fault_info *ffi = &sbi->fault_info;
	116
	117	if (!ffi->inject_rate)
	118	return false;
	119
	120	if (!IS_FAULT_SET(ffi, type))
	121	return false;
	122
	123	atomic_inc(&ffi->inject_ops);
	124	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
	125	atomic_set(&ffi->inject_ops, 0);
	126	return true;
	127	}
	128	return false;
	129	}
f8499d6e CX	130	#else
	131	static inline bool time_to_inject(struct erofs_sb_info *sbi, int type)
	132	{
	133	return false;
	134	}
	135
	136	static inline void erofs_show_injection_info(int type)
	137	{
	138	}
14f362b4	139	#endif /* !CONFIG_EROFS_FAULT_INJECTION */
9c07b3b3 CY	140
	141	static inline void erofs_kmalloc(struct erofs_sb_info sbi,
	142	size_t size, gfp_t flags)
	143	{
9c07b3b3 CY	144	if (time_to_inject(sbi, FAULT_KMALLOC)) {
	145	erofs_show_injection_info(FAULT_KMALLOC);
	146	return NULL;
	147	}
9c07b3b3 CY	148	return kmalloc(size, flags);
	149	}
	150
bfb8674d GX	151	#define EROFS_SB(sb) ((struct erofs_sb_info *)(sb)->s_fs_info)
	152	#define EROFS_I_SB(inode) ((struct erofs_sb_info *)(inode)->i_sb->s_fs_info)
	153
b17500a0 GX	154	/* Mount flags set via mount options or defaults */
	155	#define EROFS_MOUNT_XATTR_USER 0x00000010
	156	#define EROFS_MOUNT_POSIX_ACL 0x00000020
9c07b3b3	157	#define EROFS_MOUNT_FAULT_INJECTION 0x00000040
b17500a0	158
bfb8674d GX	159	#define clear_opt(sbi, option) ((sbi)->mount_opt &= ~EROFS_MOUNT_##option)
	160	#define set_opt(sbi, option) ((sbi)->mount_opt \|= EROFS_MOUNT_##option)
	161	#define test_opt(sbi, option) ((sbi)->mount_opt & EROFS_MOUNT_##option)
	162
e7e9a307	163	#ifdef CONFIG_EROFS_FS_ZIP
4279f3f9 GX	164	enum {
	165	EROFS_ZIP_CACHE_DISABLED,
	166	EROFS_ZIP_CACHE_READAHEAD,
	167	EROFS_ZIP_CACHE_READAROUND
	168	};
	169
14f362b4 GX	170	#define EROFS_LOCKED_MAGIC (INT_MIN \| 0xE0F510CCL)
14f362b4 GX	171
e7e9a307 GX	172	/* basic unit of the workstation of a super_block */
	173	struct erofs_workgroup {
	174	/* the workgroup index in the workstation */
	175	pgoff_t index;
	176
	177	/* overall workgroup reference count */
	178	atomic_t refcount;
	179	};
	180
73f5c66d GX	181	#if defined(CONFIG_SMP)
	182	static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
	183	int val)
e7e9a307	184	{
e7e9a307	185	preempt_disable();
73f5c66d	186	if (val != atomic_cmpxchg(&grp->refcount, val, EROFS_LOCKED_MAGIC)) {
e7e9a307 GX	187	preempt_enable();
	188	return false;
	189	}
e7e9a307 GX	190	return true;
	191	}
	192
73f5c66d GX	193	static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
73f5c66d GX	194	int orig_val)
e7e9a307	195	{
948bbdb1 GX	196	/*
	197	* other observers should notice all modifications
	198	* in the freezing period.
	199	*/
	200	smp_mb();
73f5c66d	201	atomic_set(&grp->refcount, orig_val);
e7e9a307 GX	202	preempt_enable();
	203	}
	204
df134b8d GX	205	static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
	206	{
	207	return atomic_cond_read_relaxed(&grp->refcount,
	208	VAL != EROFS_LOCKED_MAGIC);
	209	}
	210	#else
73f5c66d GX	211	static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
	212	int val)
	213	{
	214	preempt_disable();
	215	/* no need to spin on UP platforms, let's just disable preemption. */
	216	if (val != atomic_read(&grp->refcount)) {
	217	preempt_enable();
	218	return false;
	219	}
	220	return true;
	221	}
	222
	223	static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
	224	int orig_val)
	225	{
	226	preempt_enable();
	227	}
	228
df134b8d GX	229	static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
	230	{
	231	int v = atomic_read(&grp->refcount);
	232
	233	/* workgroup is never freezed on uniprocessor systems */
	234	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
	235	return v;
	236	}
14f362b4	237	#endif /* !CONFIG_SMP */
105d4ad8	238
14f362b4 GX	239	/* hard limit of pages per compressed cluster */
	240	#define Z_EROFS_CLUSTER_MAX_PAGES (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
	241	#define EROFS_PCPUBUF_NR_PAGES Z_EROFS_CLUSTER_MAX_PAGES
0a0b7e62	242	#else
14f362b4	243	#define EROFS_PCPUBUF_NR_PAGES 0
14f362b4	244	#endif /* !CONFIG_EROFS_FS_ZIP */
e7e9a307	245
bfb8674d GX	246	/* we strictly follow PAGE_SIZE and no buffer head yet */
	247	#define LOG_BLOCK_SIZE PAGE_SHIFT
	248
	249	#undef LOG_SECTORS_PER_BLOCK
	250	#define LOG_SECTORS_PER_BLOCK (PAGE_SHIFT - 9)
	251
	252	#undef SECTORS_PER_BLOCK
	253	#define SECTORS_PER_BLOCK (1 << SECTORS_PER_BLOCK)
	254
	255	#define EROFS_BLKSIZ (1 << LOG_BLOCK_SIZE)
	256
	257	#if (EROFS_BLKSIZ % 4096 \|\| !EROFS_BLKSIZ)
	258	#error erofs cannot be used in this platform
	259	#endif
	260
beb5f3c4 GX	261	#define EROFS_IO_MAX_RETRIES_NOFAIL 5
beb5f3c4 GX	262
bfb8674d GX	263	#define ROOT_NID(sb) ((sb)->root_nid)
bfb8674d GX	264
bfb8674d GX	265	#define erofs_blknr(addr) ((addr) / EROFS_BLKSIZ)
	266	#define erofs_blkoff(addr) ((addr) % EROFS_BLKSIZ)
	267	#define blknr_to_addr(nr) ((erofs_off_t)(nr) * EROFS_BLKSIZ)
	268
	269	static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid)
	270	{
	271	return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits);
	272	}
	273
62dc4597 GX	274	/* atomic flag definitions */
62dc4597 GX	275	#define EROFS_V_EA_INITED_BIT 0
152a333a	276	#define EROFS_V_Z_INITED_BIT 1
62dc4597 GX	277
	278	/* bitlock definitions (arranged in reverse order) */
	279	#define EROFS_V_BL_XATTR_BIT (BITS_PER_LONG - 1)
152a333a	280	#define EROFS_V_BL_Z_BIT (BITS_PER_LONG - 2)
bfb8674d GX	281
	282	struct erofs_vnode {
	283	erofs_nid_t nid;
62dc4597 GX	284
	285	/* atomic flags (including bitlocks) */
	286	unsigned long flags;
bfb8674d	287
76bc27a2	288	unsigned char datamode;
bfb8674d GX	289	unsigned char inode_isize;
	290	unsigned short xattr_isize;
	291
e82a9a17 PS	292	unsigned int xattr_shared_count;
e82a9a17 PS	293	unsigned int *xattr_shared_xattrs;
bfb8674d	294
152a333a GX	295	union {
	296	erofs_blk_t raw_blkaddr;
	297	#ifdef CONFIG_EROFS_FS_ZIP
	298	struct {
	299	unsigned short z_advise;
	300	unsigned char z_algorithmtype[2];
	301	unsigned char z_logical_clusterbits;
	302	unsigned char z_physical_clusterbits[2];
	303	};
14f362b4	304	#endif /* CONFIG_EROFS_FS_ZIP */
152a333a	305	};
bfb8674d GX	306	/* the corresponding vfs inode */
	307	struct inode vfs_inode;
	308	};
	309
	310	#define EROFS_V(ptr) \
	311	container_of(ptr, struct erofs_vnode, vfs_inode)
	312
	313	#define __inode_advise(x, bit, bits) \
	314	(((x) >> (bit)) & ((1 << (bits)) - 1))
	315
	316	#define __inode_version(advise) \
	317	__inode_advise(advise, EROFS_I_VERSION_BIT, \
	318	EROFS_I_VERSION_BITS)
	319
	320	#define __inode_data_mapping(advise) \
	321	__inode_advise(advise, EROFS_I_DATA_MAPPING_BIT,\
	322	EROFS_I_DATA_MAPPING_BITS)
	323
	324	static inline unsigned long inode_datablocks(struct inode *inode)
	325	{
	326	/* since i_size cannot be changed */
	327	return DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ);
	328	}
	329
bfb8674d GX	330	static inline bool is_inode_layout_compression(struct inode *inode)
bfb8674d GX	331	{
ec8c2442	332	return erofs_inode_is_data_compressed(EROFS_V(inode)->datamode);
bfb8674d GX	333	}
bfb8674d GX	334
ec8c2442	335	static inline bool is_inode_flat_inline(struct inode *inode)
bfb8674d	336	{
ec8c2442	337	return EROFS_V(inode)->datamode == EROFS_INODE_FLAT_INLINE;
bfb8674d GX	338	}
	339
	340	extern const struct super_operations erofs_sops;
bfb8674d GX	341
bfb8674d GX	342	extern const struct address_space_operations erofs_raw_access_aops;
3883a79a GX	343	#ifdef CONFIG_EROFS_FS_ZIP
	344	extern const struct address_space_operations z_erofs_vle_normalaccess_aops;
	345	#endif
bfb8674d GX	346
	347	/*
	348	* Logical to physical block mapping, used by erofs_map_blocks()
	349	*
	350	* Different with other file systems, it is used for 2 access modes:
	351	*
	352	* 1) RAW access mode:
	353	*
	354	* Users pass a valid (m_lblk, m_lofs -- usually 0) pair,
	355	* and get the valid m_pblk, m_pofs and the longest m_len(in bytes).
	356	*
	357	* Note that m_lblk in the RAW access mode refers to the number of
	358	* the compressed ondisk block rather than the uncompressed
	359	* in-memory block for the compressed file.
	360	*
	361	* m_pofs equals to m_lofs except for the inline data page.
	362	*
	363	* 2) Normal access mode:
	364	*
	365	* If the inode is not compressed, it has no difference with
	366	* the RAW access mode. However, if the inode is compressed,
	367	* users should pass a valid (m_lblk, m_lofs) pair, and get
	368	* the needed m_pblk, m_pofs, m_len to get the compressed data
	369	* and the updated m_lblk, m_lofs which indicates the start
	370	* of the corresponding uncompressed data in the file.
	371	*/
	372	enum {
	373	BH_Zipped = BH_PrivateStart,
b6a76183	374	BH_FullMapped,
bfb8674d GX	375	};
	376
	377	/* Has a disk mapping */
	378	#define EROFS_MAP_MAPPED (1 << BH_Mapped)
	379	/* Located in metadata (could be copied from bd_inode) */
	380	#define EROFS_MAP_META (1 << BH_Meta)
	381	/* The extent has been compressed */
	382	#define EROFS_MAP_ZIPPED (1 << BH_Zipped)
b6a76183 GX	383	/* The length of extent is full */
b6a76183 GX	384	#define EROFS_MAP_FULL_MAPPED (1 << BH_FullMapped)
bfb8674d GX	385
	386	struct erofs_map_blocks {
	387	erofs_off_t m_pa, m_la;
	388	u64 m_plen, m_llen;
	389
	390	unsigned int m_flags;
3b423417 CY	391
3b423417 CY	392	struct page *mpage;
bfb8674d GX	393	};
	394
	395	/* Flags used by erofs_map_blocks() */
	396	#define EROFS_GET_BLOCKS_RAW 0x0001
	397
152a333a	398	/* zmap.c */
3b423417	399	#ifdef CONFIG_EROFS_FS_ZIP
152a333a	400	int z_erofs_fill_inode(struct inode *inode);
3b423417 CY	401	int z_erofs_map_blocks_iter(struct inode *inode,
	402	struct erofs_map_blocks *map,
	403	int flags);
	404	#else
ff784a78	405	static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; }
3b423417 CY	406	static inline int z_erofs_map_blocks_iter(struct inode *inode,
	407	struct erofs_map_blocks *map,
	408	int flags)
	409	{
ff784a78	410	return -EOPNOTSUPP;
3b423417	411	}
14f362b4	412	#endif /* !CONFIG_EROFS_FS_ZIP */
3b423417	413
bfb8674d	414	/* data.c */
14f362b4 GX	415	static inline struct bio erofs_grab_bio(struct super_block sb,
	416	erofs_blk_t blkaddr,
	417	unsigned int nr_pages,
	418	void *bi_private, bio_end_io_t endio,
	419	bool nofail)
55441958	420	{
8be31270 GX	421	const gfp_t gfp = GFP_NOIO;
	422	struct bio *bio;
	423
	424	do {
	425	if (nr_pages == 1) {
	426	bio = bio_alloc(gfp \| (nofail ? __GFP_NOFAIL : 0), 1);
8d8a09b0	427	if (!bio) {
8be31270 GX	428	DBG_BUGON(nofail);
8be31270 GX	429	return ERR_PTR(-ENOMEM);
55441958	430	}
8be31270 GX	431	break;
	432	}
	433	bio = bio_alloc(gfp, nr_pages);
	434	nr_pages /= 2;
8d8a09b0	435	} while (!bio);
55441958 GX	436
	437	bio->bi_end_io = endio;
	438	bio_set_dev(bio, sb->s_bdev);
eed276c0	439	bio->bi_iter.bi_sector = (sector_t)blkaddr << LOG_SECTORS_PER_BLOCK;
14a56ec6	440	bio->bi_private = bi_private;
55441958 GX	441	return bio;
	442	}
	443
e82a9a17 PS	444	static inline void __submit_bio(struct bio *bio, unsigned int op,
e82a9a17 PS	445	unsigned int op_flags)
55441958 GX	446	{
	447	bio_set_op_attrs(bio, op, op_flags);
	448	submit_bio(bio);
	449	}
	450
2e1d6637 GX	451	struct page __erofs_get_meta_page(struct super_block sb, erofs_blk_t blkaddr,
2e1d6637 GX	452	bool prio, bool nofail);
6e78901a GX	453
	454	static inline struct page erofs_get_meta_page(struct super_block sb,
	455	erofs_blk_t blkaddr, bool prio)
	456	{
	457	return __erofs_get_meta_page(sb, blkaddr, prio, false);
	458	}
	459
2e1d6637	460	int erofs_map_blocks(struct inode , struct erofs_map_blocks , int);
bfb8674d	461
14f362b4 GX	462	static inline struct page erofs_get_inline_page(struct inode inode,
14f362b4 GX	463	erofs_blk_t blkaddr)
bfb8674d	464	{
14f362b4 GX	465	return erofs_get_meta_page(inode->i_sb, blkaddr,
14f362b4 GX	466	S_ISDIR(inode->i_mode));
bfb8674d GX	467	}
	468
	469	/* inode.c */
2abd7814 GX	470	static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
	471	{
	472	#if BITS_PER_LONG == 32
	473	return (nid >> 32) ^ (nid & 0xffffffff);
	474	#else
	475	return nid;
	476	#endif
	477	}
	478
60939826 GX	479	extern const struct inode_operations erofs_generic_iops;
	480	extern const struct inode_operations erofs_symlink_iops;
	481	extern const struct inode_operations erofs_fast_symlink_iops;
b17500a0	482
bfb8674d GX	483	static inline void set_inode_fast_symlink(struct inode *inode)
bfb8674d GX	484	{
60939826	485	inode->i_op = &erofs_fast_symlink_iops;
bfb8674d GX	486	}
	487
	488	static inline bool is_inode_fast_symlink(struct inode *inode)
	489	{
60939826 GX	490	return inode->i_op == &erofs_fast_symlink_iops;
	491	}
	492
2e1d6637	493	struct inode erofs_iget(struct super_block sb, erofs_nid_t nid, bool dir);
89f27ede GX	494	int erofs_getattr(const struct path path, struct kstat stat,
89f27ede GX	495	u32 request_mask, unsigned int query_flags);
2e1d6637	496
60939826 GX	497	/* namei.c */
	498	extern const struct inode_operations erofs_dir_iops;
	499
	500	int erofs_namei(struct inode dir, struct qstr name,
	501	erofs_nid_t nid, unsigned int d_type);
	502
	503	/* dir.c */
	504	extern const struct file_operations erofs_dir_fops;
	505
14f362b4	506	/* utils.c / zdata.c */
b25a1519	507	struct page erofs_allocpage(struct list_head pool, gfp_t gfp, bool nofail);
fa61a33f GX	508
	509	#if (EROFS_PCPUBUF_NR_PAGES > 0)
	510	void *erofs_get_pcpubuf(unsigned int pagenr);
	511	#define erofs_put_pcpubuf(buf) do { \
	512	(void)&(buf); \
	513	preempt_enable(); \
	514	} while (0)
	515	#else
	516	static inline void *erofs_get_pcpubuf(unsigned int pagenr)
	517	{
ff784a78	518	return ERR_PTR(-EOPNOTSUPP);
fa61a33f GX	519	}
	520
	521	#define erofs_put_pcpubuf(buf) do {} while (0)
	522	#endif
	523
22fe04a7	524	#ifdef CONFIG_EROFS_FS_ZIP
14f362b4 GX	525	int erofs_workgroup_put(struct erofs_workgroup *grp);
	526	struct erofs_workgroup erofs_find_workgroup(struct super_block sb,
	527	pgoff_t index, bool *tag);
	528	int erofs_register_workgroup(struct super_block *sb,
	529	struct erofs_workgroup *grp, bool tag);
14f362b4	530	void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
22fe04a7 GX	531	void erofs_shrinker_register(struct super_block *sb);
	532	void erofs_shrinker_unregister(struct super_block *sb);
	533	int __init erofs_init_shrinker(void);
	534	void erofs_exit_shrinker(void);
	535	int __init z_erofs_init_zip_subsystem(void);
	536	void z_erofs_exit_zip_subsystem(void);
14f362b4 GX	537	int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
	538	struct erofs_workgroup *egrp);
	539	int erofs_try_to_free_cached_page(struct address_space *mapping,
	540	struct page *page);
22fe04a7 GX	541	#else
	542	static inline void erofs_shrinker_register(struct super_block *sb) {}
	543	static inline void erofs_shrinker_unregister(struct super_block *sb) {}
	544	static inline int erofs_init_shrinker(void) { return 0; }
	545	static inline void erofs_exit_shrinker(void) {}
	546	static inline int z_erofs_init_zip_subsystem(void) { return 0; }
	547	static inline void z_erofs_exit_zip_subsystem(void) {}
	548	#endif /* !CONFIG_EROFS_FS_ZIP */
2e1d6637	549
a6b9b1d5 GX	550	#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
a6b9b1d5 GX	551
14f362b4	552	#endif /* __EROFS_INTERNAL_H */
bfb8674d	553