linux/fs/erofs/internal.h

/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2021, Alibaba Cloud
 */
#ifndef __EROFS_INTERNAL_H
#define __EROFS_INTERNAL_H

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

__printf(2, 3) void _erofs_printk(struct super_block *sb, const char *fmt, ...);
#define erofs_err(sb, fmt, ...)	\
	_erofs_printk(sb, KERN_ERR fmt "\n", ##__VA_ARGS__)
#define erofs_warn(sb, fmt, ...) \
	_erofs_printk(sb, KERN_WARNING fmt "\n", ##__VA_ARGS__)
#define erofs_info(sb, fmt, ...) \
	_erofs_printk(sb, KERN_INFO fmt "\n", ##__VA_ARGS__)

#ifdef CONFIG_EROFS_FS_DEBUG
#define DBG_BUGON               BUG_ON
#else
#define DBG_BUGON(x)            ((void)(x))
#endif	/* !CONFIG_EROFS_FS_DEBUG */

/* 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;
typedef u64 erofs_blk_t;

struct erofs_device_info {
	char *path;
	struct file *file;
	struct dax_device *dax_dev;
	u64 fsoff, dax_part_off;

	erofs_blk_t blocks;
	erofs_blk_t uniaddr;
};

enum {
	EROFS_SYNC_DECOMPRESS_AUTO,
	EROFS_SYNC_DECOMPRESS_FORCE_ON,
	EROFS_SYNC_DECOMPRESS_FORCE_OFF
};

struct erofs_mount_opts {
	/* current strategy of how to use managed cache */
	unsigned char cache_strategy;
	unsigned int mount_opt;
};

struct erofs_dev_context {
	struct idr tree;
	struct rw_semaphore rwsem;

	unsigned int extra_devices;
	bool flatdev;
};

struct erofs_sb_lz4_info {
	u16 max_pclusterblks;	/* maximum physical blocks for LZ4 pclusters */
};

struct erofs_xattr_prefix_item {
	struct erofs_xattr_long_prefix *prefix;
	u8 infix_len;
};

struct erofs_sb_info {
	struct erofs_device_info dif0;
	struct erofs_mount_opts opt;	/* options */
#ifdef CONFIG_EROFS_FS_ZIP
	/* list for all registered superblocks, mainly for shrinker */
	struct list_head list;
	struct mutex umount_mutex;

	/* managed XArray arranged in physical block number */
	struct xarray managed_pslots;

	unsigned int sync_decompress;	/* strategy for sync decompression */
	unsigned int shrinker_run_no;

	struct erofs_sb_lz4_info lz4;
#endif	/* CONFIG_EROFS_FS_ZIP */
	struct inode *managed_cache; /* pseudo inode to cache physical data */
	struct inode *packed_inode;
	struct inode *metabox_inode;
	struct erofs_dev_context *devs;
	u64 total_blocks;

	u32 meta_blkaddr;
#ifdef CONFIG_EROFS_FS_XATTR
	u32 xattr_blkaddr;
	u32 xattr_prefix_start;
	u8 xattr_prefix_count;
	u8 ishare_xattr_prefix_id;
	struct erofs_xattr_prefix_item *xattr_prefixes;
	unsigned int xattr_filter_reserved;
#endif
	u16 device_id_mask;	/* valid bits of device id to be used */

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

	u32 sb_size;			/* total superblock size */
	u32 fixed_nsec;
	s64 epoch;

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

	char *volume_name;
	u32 feature_compat;
	u32 feature_incompat;
	u16 available_compr_algs;

	/* sysfs support */
	struct kobject s_kobj;		/* /sys/fs/erofs/<devname> */
	struct completion s_kobj_unregister;
	erofs_off_t dir_ra_bytes;

	char *domain_id;
};

#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_DAX_ALWAYS		0x00000040
#define EROFS_MOUNT_DAX_NEVER		0x00000080
#define EROFS_MOUNT_DIRECT_IO		0x00000100
#define EROFS_MOUNT_INODE_SHARE		0x00000200

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

static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi)
{
	return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file;
}

extern struct file_system_type erofs_anon_fs_type;

enum {
	EROFS_ZIP_CACHE_DISABLED,
	EROFS_ZIP_CACHE_READAHEAD,
	EROFS_ZIP_CACHE_READAROUND
};

struct erofs_buf {
	struct address_space *mapping;
	u64 off;
	struct page *page;
	void *base;
	bool mc;
};
#define __EROFS_BUF_INITIALIZER	((struct erofs_buf){ .page = NULL })

#define erofs_blknr(sb, pos)	((erofs_blk_t)((pos) >> (sb)->s_blocksize_bits))
#define erofs_blkoff(sb, pos)	((pos) & ((sb)->s_blocksize - 1))
#define erofs_pos(sb, blk)	((erofs_off_t)(blk) << (sb)->s_blocksize_bits)
#define erofs_iblks(i)	(round_up((i)->i_size, i_blocksize(i)) >> (i)->i_blkbits)

#define EROFS_FEATURE_FUNCS(name, compat, feature) \
static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
{ \
	return sbi->feature_##compat & EROFS_FEATURE_##feature; \
}

EROFS_FEATURE_FUNCS(lz4_0padding, incompat, INCOMPAT_LZ4_0PADDING)
EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS)
EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
EROFS_FEATURE_FUNCS(chunked_file, incompat, INCOMPAT_CHUNKED_FILE)
EROFS_FEATURE_FUNCS(device_table, incompat, INCOMPAT_DEVICE_TABLE)
EROFS_FEATURE_FUNCS(compr_head2, incompat, INCOMPAT_COMPR_HEAD2)
EROFS_FEATURE_FUNCS(ztailpacking, incompat, INCOMPAT_ZTAILPACKING)
EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS)
EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE)
EROFS_FEATURE_FUNCS(xattr_prefixes, incompat, INCOMPAT_XATTR_PREFIXES)
EROFS_FEATURE_FUNCS(48bit, incompat, INCOMPAT_48BIT)
EROFS_FEATURE_FUNCS(metabox, incompat, INCOMPAT_METABOX)
EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER)
EROFS_FEATURE_FUNCS(shared_ea_in_metabox, compat, COMPAT_SHARED_EA_IN_METABOX)
EROFS_FEATURE_FUNCS(plain_xattr_pfx, compat, COMPAT_PLAIN_XATTR_PFX)
EROFS_FEATURE_FUNCS(ishare_xattrs, compat, COMPAT_ISHARE_XATTRS)

static inline u64 erofs_nid_to_ino64(struct erofs_sb_info *sbi, erofs_nid_t nid)
{
	if (!erofs_sb_has_metabox(sbi))
		return nid;

	/*
	 * When metadata compression is enabled, avoid generating excessively
	 * large inode numbers for metadata-compressed inodes.  Shift NIDs in
	 * the 31-62 bit range left by one and move the metabox flag to bit 31.
	 *
	 * Note: on-disk NIDs remain unchanged as they are primarily used for
	 * compatibility with non-LFS 32-bit applications.
	 */
	return ((nid << 1) & GENMASK_ULL(63, 32)) | (nid & GENMASK(30, 0)) |
		((nid >> EROFS_DIRENT_NID_METABOX_BIT) << 31);
}

/* atomic flag definitions */
#define EROFS_I_EA_INITED_BIT	0
#define EROFS_I_Z_INITED_BIT	1

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

/* default readahead size of directories */
#define EROFS_DIR_RA_BYTES	16384

struct erofs_inode_fingerprint {
	u8 *opaque;
	int size;
};

struct erofs_inode {
	erofs_nid_t nid;

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

	unsigned char datalayout;
	unsigned char inode_isize;
	bool dot_omitted;
	unsigned int xattr_isize;

	unsigned int xattr_name_filter;
	unsigned int xattr_shared_count;
	unsigned int *xattr_shared_xattrs;

	union {
		erofs_blk_t startblk;
		struct {
			unsigned short	chunkformat;
			unsigned char	chunkbits;
		};
#ifdef CONFIG_EROFS_FS_ZIP
		struct {
			unsigned short z_advise;
			unsigned char  z_algofmt[2];
			unsigned char  z_lclusterbits;
			union {
				u64    z_tailextent_headlcn;
				u64    z_extents;
			};
			erofs_off_t    z_fragmentoff;
			unsigned short z_idata_size;
		};
#endif	/* CONFIG_EROFS_FS_ZIP */
	};
#ifdef CONFIG_EROFS_FS_PAGE_CACHE_SHARE
	struct list_head ishare_list;
	union {
		/* for each anon shared inode */
		struct {
			struct erofs_inode_fingerprint fingerprint;
			spinlock_t ishare_lock;
		};
		/* for each real filesystem inode */
		struct dentry *sharedentry;
	};
#endif
	/* the corresponding vfs inode */
	struct inode vfs_inode;
};

#define EROFS_I(ptr)	container_of(ptr, struct erofs_inode, vfs_inode)

static inline bool erofs_inode_in_metabox(struct inode *inode)
{
	return EROFS_I(inode)->nid & BIT_ULL(EROFS_DIRENT_NID_METABOX_BIT);
}

static inline erofs_off_t erofs_iloc(struct inode *inode)
{
	struct erofs_sb_info *sbi = EROFS_I_SB(inode);
	erofs_nid_t nid_lo = EROFS_I(inode)->nid & EROFS_DIRENT_NID_MASK;

	if (erofs_inode_in_metabox(inode))
		return nid_lo << sbi->islotbits;
	return erofs_pos(inode->i_sb, sbi->meta_blkaddr) +
		(nid_lo << sbi->islotbits);
}

static inline unsigned int erofs_inode_version(unsigned int ifmt)
{
	return (ifmt >> EROFS_I_VERSION_BIT) & EROFS_I_VERSION_MASK;
}

static inline unsigned int erofs_inode_datalayout(unsigned int ifmt)
{
	return (ifmt >> EROFS_I_DATALAYOUT_BIT) & EROFS_I_DATALAYOUT_MASK;
}

/* reclaiming is never triggered when allocating new folios. */
static inline struct folio *erofs_grab_folio_nowait(struct address_space *as,
						    pgoff_t index)
{
	return __filemap_get_folio(as, index,
			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
			readahead_gfp_mask(as) & ~__GFP_RECLAIM);
}

/* Allocated on disk at @m_pa (e.g. NOT a fragment extent) */
#define EROFS_MAP_MAPPED		0x0001
/* Located in metadata (could be copied from bd_inode) */
#define EROFS_MAP_META			0x0002
/* @m_llen may be truncated by the runtime compared to the on-disk record */
#define EROFS_MAP_PARTIAL_MAPPED	0x0004
/* The on-disk @m_llen may cover only part of the encoded data */
#define EROFS_MAP_PARTIAL_REF		0x0008
/* Located in the special packed inode */
#define EROFS_MAP_FRAGMENT		0x0010
/* The encoded on-disk data will be fully handled (decompressed) */
#define EROFS_MAP_FULL(f)	(!((f) & (EROFS_MAP_PARTIAL_MAPPED | \
					  EROFS_MAP_PARTIAL_REF)))

struct erofs_map_blocks {
	struct erofs_buf buf;

	erofs_off_t m_pa, m_la;
	u64 m_plen, m_llen;

	unsigned short m_deviceid;
	char m_algorithmformat;
	unsigned int m_flags;
};

/*
 * Used to get the exact decompressed length, e.g. fiemap (consider lookback
 * approach instead if possible since it's more metadata lightweight.)
 */
#define EROFS_GET_BLOCKS_FIEMAP		0x0001
/* Used to map the whole extent if non-negligible data is requested for LZMA */
#define EROFS_GET_BLOCKS_READMORE	0x0002
/* Used to map tail extent for tailpacking inline or fragment pcluster */
#define EROFS_GET_BLOCKS_FINDTAIL	0x0004

enum {
	Z_EROFS_COMPRESSION_SHIFTED = Z_EROFS_COMPRESSION_MAX,
	Z_EROFS_COMPRESSION_INTERLACED,
	Z_EROFS_COMPRESSION_RUNTIME_MAX
};

struct erofs_map_dev {
	struct super_block *m_sb;
	struct erofs_device_info *m_dif;
	struct block_device *m_bdev;

	erofs_off_t m_pa;
	unsigned int m_deviceid;
};

extern const struct super_operations erofs_sops;
extern const struct address_space_operations erofs_aops;
extern const struct address_space_operations erofs_fileio_aops;
extern const struct address_space_operations z_erofs_aops;

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;
extern const struct inode_operations erofs_dir_iops;

extern const struct file_operations erofs_file_fops;
extern const struct file_operations erofs_dir_fops;
extern const struct file_operations erofs_ishare_fops;

extern const struct iomap_ops z_erofs_iomap_report_ops;

int erofs_setup_managed_cache(struct super_block *sb);
#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
int erofs_read_meta_folio(struct file *file, struct folio *folio);
#else
#define erofs_read_meta_folio NULL
#endif
void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf,
			  erofs_off_t *offset, int *lengthp);
void erofs_unmap_metabuf(struct erofs_buf *buf);
void erofs_put_metabuf(struct erofs_buf *buf);
void *erofs_bread(struct erofs_buf *buf, erofs_off_t offset, bool need_kmap);
int erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb,
		       bool in_metabox);
void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb,
			 erofs_off_t offset, bool in_metabox);
int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev);
int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		 u64 start, u64 len);
loff_t erofs_file_llseek(struct file *file, loff_t offset, int whence);
int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map);
void erofs_onlinefolio_init(struct folio *folio);
void erofs_onlinefolio_split(struct folio *folio);
void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty);
struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid);
int erofs_getattr(struct mnt_idmap *idmap, const struct path *path,
		  struct kstat *stat, u32 request_mask,
		  unsigned int query_flags);
int erofs_namei(struct inode *dir, const struct qstr *name,
		erofs_nid_t *nid, unsigned int *d_type);

static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
{
	int retried = 0;

	while (1) {
		void *p = vm_map_ram(pages, count, -1);

		/* retry two more times (totally 3 times) */
		if (p || ++retried >= 3)
			return p;
		vm_unmap_aliases();
	}
	return NULL;
}

static inline const struct address_space_operations *
erofs_get_aops(struct inode *realinode)
{
	if (erofs_inode_is_data_compressed(EROFS_I(realinode)->datalayout)) {
		if (!IS_ENABLED(CONFIG_EROFS_FS_ZIP))
			return ERR_PTR(-EOPNOTSUPP);
		DO_ONCE_LITE_IF(realinode->i_blkbits != PAGE_SHIFT,
			  erofs_info, realinode->i_sb,
			  "EXPERIMENTAL EROFS subpage compressed block support in use. Use at your own risk!");
		return &z_erofs_aops;
	}
	if (IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) &&
	    erofs_is_fileio_mode(EROFS_SB(realinode->i_sb)))
		return &erofs_fileio_aops;
	return &erofs_aops;
}

int erofs_register_sysfs(struct super_block *sb);
void erofs_unregister_sysfs(struct super_block *sb);
int __init erofs_init_sysfs(void);
void erofs_exit_sysfs(void);

struct page *__erofs_allocpage(struct page **pagepool, gfp_t gfp, bool tryrsv);
static inline struct page *erofs_allocpage(struct page **pagepool, gfp_t gfp)
{
	return __erofs_allocpage(pagepool, gfp, false);
}
static inline void erofs_pagepool_add(struct page **pagepool, struct page *page)
{
	set_page_private(page, (unsigned long)*pagepool);
	*pagepool = page;
}
void erofs_release_pages(struct page **pagepool);

#ifdef CONFIG_EROFS_FS_ZIP
#define MNGD_MAPPING(sbi)	((sbi)->managed_cache->i_mapping)

extern atomic_long_t erofs_global_shrink_cnt;
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_subsystem(void);
void z_erofs_exit_subsystem(void);
int z_erofs_init_super(struct super_block *sb);
unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi,
				  unsigned long nr_shrink);
int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
			    int flags);
void *z_erofs_get_gbuf(unsigned int requiredpages);
void z_erofs_put_gbuf(void *ptr);
int z_erofs_gbuf_growsize(unsigned int nrpages);
int __init z_erofs_gbuf_init(void);
void z_erofs_gbuf_exit(void);
#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_subsystem(void) { return 0; }
static inline void z_erofs_exit_subsystem(void) {}
static inline int z_erofs_init_super(struct super_block *sb) { return 0; }
#endif	/* !CONFIG_EROFS_FS_ZIP */
int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb);

#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE
struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev);
void erofs_fileio_submit_bio(struct bio *bio);
#else
static inline struct bio *erofs_fileio_bio_alloc(struct erofs_map_dev *mdev) { return NULL; }
static inline void erofs_fileio_submit_bio(struct bio *bio) {}
#endif

#ifdef CONFIG_EROFS_FS_PAGE_CACHE_SHARE
int __init erofs_init_ishare(void);
void erofs_exit_ishare(void);
bool erofs_ishare_fill_inode(struct inode *inode);
void erofs_ishare_free_inode(struct inode *inode);
struct inode *erofs_real_inode(struct inode *inode, bool *need_iput);
#else
static inline int erofs_init_ishare(void) { return 0; }
static inline void erofs_exit_ishare(void) {}
static inline bool erofs_ishare_fill_inode(struct inode *inode) { return false; }
static inline void erofs_ishare_free_inode(struct inode *inode) {}
static inline struct inode *erofs_real_inode(struct inode *inode, bool *need_iput)
{
	*need_iput = false;
	return inode;
}
#endif

long erofs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
long erofs_compat_ioctl(struct file *filp, unsigned int cmd,
			unsigned long arg);

#endif	/* __EROFS_INTERNAL_H */