diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 3998 |
1 files changed, 2432 insertions, 1566 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index 981874773e85..04ceeca12a0d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1,9 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H - +#include <linux/fs/super.h> +#include <linux/vfsdebug.h> #include <linux/linkage.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> @@ -12,14 +14,17 @@ #include <linux/list.h> #include <linux/llist.h> #include <linux/radix-tree.h> +#include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> +#include <linux/rwsem.h> +#include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> -#include <linux/fiemap.h> +#include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> @@ -27,15 +32,31 @@ #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> -#include <linux/blk_types.h> +#include <linux/workqueue.h> +#include <linux/delayed_call.h> +#include <linux/uuid.h> +#include <linux/errseq.h> +#include <linux/ioprio.h> +#include <linux/build_bug.h> +#include <linux/stddef.h> +#include <linux/mount.h> +#include <linux/cred.h> +#include <linux/mnt_idmapping.h> +#include <linux/slab.h> +#include <linux/maple_tree.h> +#include <linux/rw_hint.h> +#include <linux/file_ref.h> +#include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> -struct export_operations; +struct bdi_writeback; +struct bio; +struct io_comp_batch; +struct fiemap_extent_info; struct hd_geometry; struct iovec; -struct nameidata; struct kiocb; struct kobject; struct pipe_inode_info; @@ -46,25 +67,29 @@ struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; +struct iov_iter; +struct fsnotify_mark_connector; +struct fs_context; +struct fs_parameter_spec; +struct file_kattr; +struct iomap_ops; +struct delegated_inode; extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init files_init(unsigned long); +extern void __init files_init(void); +extern void __init files_maxfiles_init(void); -extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); -extern int sysctl_nr_open; -extern struct inodes_stat_t inodes_stat; -extern int leases_enable, lease_break_time; -extern int sysctl_protected_symlinks; -extern int sysctl_protected_hardlinks; +extern unsigned int sysctl_nr_open; + +typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); -typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, - ssize_t bytes, void *private, int ret, - bool is_async); +typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, + ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 @@ -78,32 +103,32 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond - * to O_WRONLY and O_RDWR via the strange trick in __dentry_open() + * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)0x1) +#define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)0x2) +#define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)0x4) +#define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)0x8) +#define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)0x10) +#define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)0x20) -/* File is opened with O_NDELAY (only set for block devices) */ -#define FMODE_NDELAY ((__force fmode_t)0x40) -/* File is opened with O_EXCL (only set for block devices) */ -#define FMODE_EXCL ((__force fmode_t)0x80) -/* File is opened using open(.., 3, ..) and is writeable only for ioctls - (specialy hack for floppy.c) */ -#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) +#define FMODE_EXEC ((__force fmode_t)(1 << 5)) +/* File writes are restricted (block device specific) */ +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) + +/* FMODE_* bit 8 */ + /* 32bit hashes as llseek() offset (for directories) */ -#define FMODE_32BITHASH ((__force fmode_t)0x200) +#define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ -#define FMODE_64BITHASH ((__force fmode_t)0x400) +#define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. @@ -111,85 +136,85 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)0x800) +#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ -#define FMODE_RANDOM ((__force fmode_t)0x1000) +#define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ -#define FMODE_PATH ((__force fmode_t)0x4000) +#define FMODE_PATH ((__force fmode_t)(1 << 14)) + +/* File needs atomic accesses to f_pos */ +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) +/* Write access to underlying fs */ +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) +/* Has read method(s) */ +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) +/* Has write method(s) */ +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) + +#define FMODE_OPENED ((__force fmode_t)(1 << 19)) +#define FMODE_CREATED ((__force fmode_t)(1 << 20)) + +/* File is stream-like */ +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) + +/* File supports DIRECT IO */ +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) -/* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x1000000) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) + +/* File is embedded in backing_file object */ +#define FMODE_BACKING ((__force fmode_t)(1 << 24)) /* - * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector - * that indicates that they should check the contents of the iovec are - * valid, but not check the memory that the iovec elements - * points too. + * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be + * generated (see below) */ -#define CHECK_IOVEC_ONLY -1 +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) /* - * The below are the various read and write types that we support. Some of - * them include behavioral modifiers that send information down to the - * block layer and IO scheduler. Terminology: - * - * The block layer uses device plugging to defer IO a little bit, in - * the hope that we will see more IO very shortly. This increases - * coalescing of adjacent IO and thus reduces the number of IOs we - * have to send to the device. It also allows for better queuing, - * if the IO isn't mergeable. If the caller is going to be waiting - * for the IO, then he must ensure that the device is unplugged so - * that the IO is dispatched to the driver. - * - * All IO is handled async in Linux. This is fine for background - * writes, but for reads or writes that someone waits for completion - * on, we want to notify the block layer and IO scheduler so that they - * know about it. That allows them to make better scheduling - * decisions. So when the below references 'sync' and 'async', it - * is referencing this priority hint. - * - * With that in mind, the available types are: - * - * READ A normal read operation. Device will be plugged. - * READ_SYNC A synchronous read. Device is not plugged, caller can - * immediately wait on this read without caring about - * unplugging. - * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this - * request if it runs into resource problems. - * WRITE A normal async write. Device will be plugged. - * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down - * the hint that someone will be waiting on this IO - * shortly. The write equivalent of READ_SYNC. - * WRITE_ODIRECT Special case write for O_DIRECT only. - * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush. - * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on - * non-volatile media on completion. - * WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded - * by a cache flush and data is guaranteed to be on - * non-volatile media on completion. - * - */ -#define RW_MASK REQ_WRITE -#define RWA_MASK REQ_RAHEAD - -#define READ 0 -#define WRITE RW_MASK -#define READA RWA_MASK -#define KERNEL_READ (READ|REQ_KERNEL) -#define KERNEL_WRITE (WRITE|REQ_KERNEL) - -#define READ_SYNC (READ | REQ_SYNC) -#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) -#define WRITE_ODIRECT (WRITE | REQ_SYNC) -#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) -#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) -#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) + +/* File is capable of returning -EAGAIN if I/O will block */ +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) + +/* File represents mount that needs unmounting */ +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) + +/* File does not contribute to nr_files count */ +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) + +/* + * The two FMODE_NONOTIFY* define which fsnotify events should not be generated + * for an open file. These are the possible values of + * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning: + * + * FMODE_NONOTIFY - suppress all (incl. non-permission) events. + * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. + * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM. + */ +#define FMODE_FSNOTIFY_MASK \ + (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) + +#define FMODE_FSNOTIFY_NONE(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +#define FMODE_FSNOTIFY_HSM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ + (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) +#define FMODE_FSNOTIFY_ACCESS_PERM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0) +#else +#define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0 +#define FMODE_FSNOTIFY_HSM(mode) 0 +#endif /* * Attribute flags. These should be or-ed together to figure out what @@ -205,13 +230,22 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ -#define ATTR_ATTR_FLAG (1 << 10) +#define ATTR_CTIME_SET (1 << 10) #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) +#define ATTR_TOUCH (1 << 17) +#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ + +/* + * Whiteout is represented by a char device. The following constants define the + * mode and device number to use. + */ +#define WHITEOUT_MODE 0 +#define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It @@ -225,12 +259,30 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, struct iattr { unsigned int ia_valid; umode_t ia_mode; - kuid_t ia_uid; - kgid_t ia_gid; + /* + * The two anonymous unions wrap structures with the same member. + * + * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which + * are a dedicated type requiring the filesystem to use the dedicated + * helpers. Other filesystem can continue to use ia_{g,u}id until they + * have been ported. + * + * They always contain the same value. In other words FS_ALLOW_IDMAP + * pass down the same value on idmapped mounts as they would on regular + * mounts. + */ + union { + kuid_t ia_uid; + vfsuid_t ia_vfsuid; + }; + union { + kgid_t ia_gid; + vfsgid_t ia_vfsgid; + }; loff_t ia_size; - struct timespec ia_atime; - struct timespec ia_mtime; - struct timespec ia_ctime; + struct timespec64 ia_atime; + struct timespec64 ia_mtime; + struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to @@ -241,9 +293,10 @@ struct iattr { }; /* - * Includes for diskquotas. + * Maximum number of layers of fs stack. Needs to be limited to + * prevent kernel stack overflow */ -#include <linux/quota.h> +#define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics @@ -263,7 +316,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(). + * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -276,225 +329,266 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */ -#define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */ -#define AOP_FLAG_NOFS 0x0004 /* used by filesystem to direct - * helper code (eg buffer layer) - * to clear GFP_FS from alloc */ - /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; +struct readahead_control; + +/* Match RWF_* bits to IOCB bits */ +#define IOCB_HIPRI (__force int) RWF_HIPRI +#define IOCB_DSYNC (__force int) RWF_DSYNC +#define IOCB_SYNC (__force int) RWF_SYNC +#define IOCB_NOWAIT (__force int) RWF_NOWAIT +#define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC +#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE +#define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL + +/* non-RWF related bits - start at 16 */ +#define IOCB_EVENTFD (1 << 16) +#define IOCB_DIRECT (1 << 17) +#define IOCB_WRITE (1 << 18) +/* iocb->ki_waitq is valid */ +#define IOCB_WAITQ (1 << 19) +#define IOCB_NOIO (1 << 20) +/* can use bio alloc cache */ +#define IOCB_ALLOC_CACHE (1 << 21) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 22) +#define IOCB_HAS_METADATA (1 << 23) + +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC" }, \ + { IOCB_DONTCACHE, "DONTCACHE" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ + { IOCB_AIO_RW, "AIO_RW" }, \ + { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } + +struct kiocb { + struct file *ki_filp; + loff_t ki_pos; + void (*ki_complete)(struct kiocb *iocb, long ret); + void *private; + int ki_flags; + u16 ki_ioprio; /* See linux/ioprio.h */ + u8 ki_write_stream; -struct iov_iter { - const struct iovec *iov; - unsigned long nr_segs; - size_t iov_offset; - size_t count; + /* + * Only used for async buffered reads, where it denotes the page + * waitqueue associated with completing the read. + * Valid IFF IOCB_WAITQ is set. + */ + struct wait_page_queue *ki_waitq; }; -size_t iov_iter_copy_from_user_atomic(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes); -size_t iov_iter_copy_from_user(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes); -void iov_iter_advance(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); -size_t iov_iter_single_seg_count(const struct iov_iter *i); - -static inline void iov_iter_init(struct iov_iter *i, - const struct iovec *iov, unsigned long nr_segs, - size_t count, size_t written) +static inline bool is_sync_kiocb(struct kiocb *kiocb) { - i->iov = iov; - i->nr_segs = nr_segs; - i->iov_offset = 0; - i->count = count + written; - - iov_iter_advance(i, written); + return kiocb->ki_complete == NULL; } -static inline size_t iov_iter_count(struct iov_iter *i) -{ - return i->count; -} - -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user *buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, - unsigned long, unsigned long); - struct address_space_operations { - int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty. Return true if this dirtied it */ - int (*set_page_dirty)(struct page *page); + /* Mark a folio dirty. Return true if this dirtied it */ + bool (*dirty_folio)(struct address_space *, struct folio *); - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); + void (*readahead)(struct readahead_control *); - int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - int (*write_end)(struct file *, struct address_space *mapping, + int (*write_begin)(const struct kiocb *, struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata); + int (*write_end)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); + struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - void (*invalidatepage) (struct page *, unsigned int, unsigned int); - int (*releasepage) (struct page *, gfp_t); - void (*freepage)(struct page *); - ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, - loff_t offset, unsigned long nr_segs); - int (*get_xip_mem)(struct address_space *, pgoff_t, int, - void **, unsigned long *); + void (*invalidate_folio) (struct folio *, size_t offset, size_t len); + bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *folio); + ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* - * migrate the contents of a page to the specified target. If + * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ - int (*migratepage) (struct address_space *, - struct page *, struct page *, enum migrate_mode); - int (*launder_page) (struct page *); - int (*is_partially_uptodate) (struct page *, read_descriptor_t *, - unsigned long); - void (*is_dirty_writeback) (struct page *, bool *, bool *); - int (*error_remove_page)(struct address_space *, struct page *); + int (*migrate_folio)(struct address_space *, struct folio *dst, + struct folio *src, enum migrate_mode); + int (*launder_folio)(struct folio *); + bool (*is_partially_uptodate) (struct folio *, size_t from, + size_t count); + void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); + int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; -/* - * pagecache_write_begin/pagecache_write_end must be used by general code - * to write into the pagecache. +/** + * struct address_space - Contents of a cacheable, mappable object. + * @host: Owner, either the inode or the block_device. + * @i_pages: Cached pages. + * @invalidate_lock: Guards coherency between page cache contents and + * file offset->disk block mappings in the filesystem during invalidates. + * It is also used to block modification of page cache contents through + * memory mappings. + * @gfp_mask: Memory allocation flags to use for allocating pages. + * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. + * @nr_thps: Number of THPs in the pagecache (non-shmem only). + * @i_mmap: Tree of private and shared mappings. + * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. + * @nrpages: Number of page entries, protected by the i_pages lock. + * @writeback_index: Writeback starts here. + * @a_ops: Methods. + * @flags: Error bits and flags (AS_*). + * @wb_err: The most recent error which has occurred. + * @i_private_lock: For use by the owner of the address_space. + * @i_private_list: For use by the owner of the address_space. + * @i_private_data: For use by the owner of the address_space. */ -int pagecache_write_begin(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - -int pagecache_write_end(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); - -struct backing_dev_info; struct address_space { - struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root page_tree; /* radix tree of all pages */ - spinlock_t tree_lock; /* and lock protecting it */ - unsigned int i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root i_mmap; /* tree of private and shared mappings */ - struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ - struct mutex i_mmap_mutex; /* protect tree, count, list */ - /* Protected by tree_lock together with the radix tree */ - unsigned long nrpages; /* number of total pages */ - pgoff_t writeback_index;/* writeback starts here */ - const struct address_space_operations *a_ops; /* methods */ - unsigned long flags; /* error bits/gfp mask */ - struct backing_dev_info *backing_dev_info; /* device readahead, etc */ - spinlock_t private_lock; /* for use by the address_space */ - struct list_head private_list; /* ditto */ - void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); + struct inode *host; + struct xarray i_pages; + struct rw_semaphore invalidate_lock; + gfp_t gfp_mask; + atomic_t i_mmap_writable; +#ifdef CONFIG_READ_ONLY_THP_FOR_FS + /* number of thp, only for non-shmem files */ + atomic_t nr_thps; +#endif + struct rb_root_cached i_mmap; + unsigned long nrpages; + pgoff_t writeback_index; + const struct address_space_operations *a_ops; + unsigned long flags; + errseq_t wb_err; + spinlock_t i_private_lock; + struct list_head i_private_list; + struct rw_semaphore i_mmap_rwsem; + void * i_private_data; +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit - * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. - */ -struct request_queue; - -struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ - int bd_openers; - struct inode * bd_inode; /* will die */ - struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ - struct list_head bd_inodes; - void * bd_claiming; - void * bd_holder; - int bd_holders; - bool bd_write_holder; -#ifdef CONFIG_SYSFS - struct list_head bd_holder_disks; -#endif - struct block_device * bd_contains; - unsigned bd_block_size; - struct hd_struct * bd_part; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - int bd_invalidated; - struct gendisk * bd_disk; - struct request_queue * bd_queue; - struct list_head bd_list; - /* - * Private data. You must have bd_claim'ed the block_device - * to use this. NOTE: bd_claim allows an owner to claim - * the same device multiple times, the owner must take special - * care to not mess up bd_private for that case. + * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON. */ - unsigned long bd_private; - /* The counter of freeze processes */ - int bd_fsfreeze_count; - /* Mutex for freeze */ - struct mutex bd_fsfreeze_mutex; -}; +/* XArray tags, for tagging dirty and writeback pages in the pagecache. */ +#define PAGECACHE_TAG_DIRTY XA_MARK_0 +#define PAGECACHE_TAG_WRITEBACK XA_MARK_1 +#define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* - * Radix-tree tags, for tagging dirty and writeback pages within the pagecache - * radix trees + * Returns true if any of the pages in the mapping are marked with the tag. */ -#define PAGECACHE_TAG_DIRTY 0 -#define PAGECACHE_TAG_WRITEBACK 1 -#define PAGECACHE_TAG_TOWRITE 2 +static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag) +{ + return xa_marked(&mapping->i_pages, tag); +} + +static inline void i_mmap_lock_write(struct address_space *mapping) +{ + down_write(&mapping->i_mmap_rwsem); +} + +static inline int i_mmap_trylock_write(struct address_space *mapping) +{ + return down_write_trylock(&mapping->i_mmap_rwsem); +} -int mapping_tagged(struct address_space *mapping, int tag); +static inline void i_mmap_unlock_write(struct address_space *mapping) +{ + up_write(&mapping->i_mmap_rwsem); +} + +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_lock_read(struct address_space *mapping) +{ + down_read(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_unlock_read(struct address_space *mapping) +{ + up_read(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_assert_locked(struct address_space *mapping) +{ + lockdep_assert_held(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_assert_write_locked(struct address_space *mapping) +{ + lockdep_assert_held_write(&mapping->i_mmap_rwsem); +} /* * Might pages of this file be mapped into userspace? */ -static inline int mapping_mapped(struct address_space *mapping) +static inline int mapping_mapped(const struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap) || - !list_empty(&mapping->i_mmap_nonlinear); + return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? - * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff + * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. + * + * If i_mmap_writable is negative, no new writable mappings are allowed. You + * can only deny writable mappings, if none exists right now. */ -static inline int mapping_writably_mapped(struct address_space *mapping) +static inline int mapping_writably_mapped(const struct address_space *mapping) { - return mapping->i_mmap_writable != 0; + return atomic_read(&mapping->i_mmap_writable) > 0; +} + +static inline int mapping_map_writable(struct address_space *mapping) +{ + return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? + 0 : -EPERM; +} + +static inline void mapping_unmap_writable(struct address_space *mapping) +{ + atomic_dec(&mapping->i_mmap_writable); +} + +static inline int mapping_deny_writable(struct address_space *mapping) +{ + return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? + 0 : -EBUSY; +} + +static inline void mapping_allow_writable(struct address_space *mapping) +{ + atomic_inc(&mapping->i_mmap_writable); } /* @@ -510,10 +604,158 @@ static inline int mapping_writably_mapped(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +/* + * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to + * cache the ACL. This also means that ->get_inode_acl() can be called in RCU + * mode with the LOOKUP_RCU flag. + */ +#define ACL_DONT_CACHE ((void *)(-3)) -#define IOP_FASTPERM 0x0001 -#define IOP_LOOKUP 0x0002 -#define IOP_NOFOLLOW 0x0004 +static inline struct posix_acl * +uncached_acl_sentinel(struct task_struct *task) +{ + return (void *)task + 1; +} + +static inline bool +is_uncached_acl(struct posix_acl *acl) +{ + return (long)acl & 1; +} + +#define IOP_FASTPERM 0x0001 +#define IOP_LOOKUP 0x0002 +#define IOP_NOFOLLOW 0x0004 +#define IOP_XATTR 0x0008 +#define IOP_DEFAULT_READLINK 0x0010 +#define IOP_MGTIME 0x0020 +#define IOP_CACHED_LINK 0x0040 +#define IOP_FASTPERM_MAY_EXEC 0x0080 + +/* + * Inode state bits. Protected by inode->i_lock + * + * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, + * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. + * + * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, + * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at + * various stages of removing an inode. + * + * Two bits are used for locking and completion notification, I_NEW and I_SYNC. + * + * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on + * fdatasync() (unless I_DIRTY_DATASYNC is also set). + * Timestamp updates are the usual cause. + * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * these changes separately from I_DIRTY_SYNC so that we + * don't have to write inode on fdatasync() when only + * e.g. the timestamps have changed. + * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_DIRTY_TIME The inode itself has dirty timestamps, and the + * lazytime mount option is enabled. We keep track of this + * separately from I_DIRTY_SYNC in order to implement + * lazytime. This gets cleared if I_DIRTY_INODE + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But + * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already + * in place because writeback might already be in progress + * and we don't want to lose the time update + * I_NEW Serves as both a mutex and completion notification. + * New inodes set I_NEW. If two processes both create + * the same inode, one of them will release its inode and + * wait for I_NEW to be released before returning. + * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can + * also cause waiting on I_NEW, without I_NEW actually + * being set. find_inode() uses this to prevent returning + * nearly-dead inodes. + * I_WILL_FREE Must be set when calling write_inode_now() if i_count + * is zero. I_FREEING must be set when I_WILL_FREE is + * cleared. + * I_FREEING Set when inode is about to be freed but still has dirty + * pages or buffers attached or the inode itself is still + * dirty. + * I_CLEAR Added by clear_inode(). In this state the inode is + * clean and can be destroyed. Inode keeps I_FREEING. + * + * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are + * prohibited for many purposes. iget() must wait for + * the inode to be completely released, then create it + * anew. Other functions will just ignore such inodes, + * if appropriate. I_NEW is used for waiting. + * + * I_SYNC Writeback of inode is running. The bit is set during + * data writeback, and cleared with a wakeup on the bit + * address once it is done. The bit is also used to pin + * the inode in memory for flusher thread. + * + * I_REFERENCED Marks the inode as recently references on the LRU list. + * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab the i_pages lock. See + * inode_switch_wbs_work_fn() for details. + * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * + * I_CREATING New object's inode in the middle of setting up. + * + * I_DONTCACHE Evict inode as soon as it is not used anymore. + * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * + * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. + */ + +enum inode_state_bits { + __I_NEW = 0U, + __I_SYNC = 1U, + __I_LRU_ISOLATING = 2U + /* reserved wait address bit 3 */ +}; + +enum inode_state_flags_enum { + I_NEW = (1U << __I_NEW), + I_SYNC = (1U << __I_SYNC), + I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), + /* reserved flag bit 3 */ + I_DIRTY_SYNC = (1U << 4), + I_DIRTY_DATASYNC = (1U << 5), + I_DIRTY_PAGES = (1U << 6), + I_WILL_FREE = (1U << 7), + I_FREEING = (1U << 8), + I_CLEAR = (1U << 9), + I_REFERENCED = (1U << 10), + I_LINKABLE = (1U << 11), + I_DIRTY_TIME = (1U << 12), + I_WB_SWITCH = (1U << 13), + I_OVL_INUSE = (1U << 14), + I_CREATING = (1U << 15), + I_DONTCACHE = (1U << 16), + I_SYNC_QUEUED = (1U << 17), + I_PINNING_NETFS_WB = (1U << 18) +}; + +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) +#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) +#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) + +/* + * Use inode_state_read() & friends to access. + */ +struct inode_state_flags { + enum inode_state_flags_enum __state; +}; /* * Keep mostly read-only and often accessed (especially for @@ -523,14 +765,13 @@ struct posix_acl; struct inode { umode_t i_mode; unsigned short i_opflags; - kuid_t i_uid; - kgid_t i_gid; unsigned int i_flags; - #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif + kuid_t i_uid; + kgid_t i_gid; const struct inode_operations *i_op; struct super_block *i_sb; @@ -555,12 +796,17 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec i_atime; - struct timespec i_mtime; - struct timespec i_ctime; + time64_t i_atime_sec; + time64_t i_mtime_sec; + time64_t i_ctime_sec; + u32 i_atime_nsec; + u32 i_mtime_nsec; + u32 i_ctime_nsec; + u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; - unsigned int i_blkbits; + u8 i_blkbits; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -568,48 +814,169 @@ struct inode { #endif /* Misc */ - unsigned long i_state; - struct mutex i_mutex; + struct inode_state_flags i_state; + /* 32-bit hole */ + struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ + unsigned long dirtied_time_when; struct hlist_node i_hash; - struct list_head i_wb_list; /* backing dev IO list */ + struct list_head i_io_list; /* backing dev IO list */ +#ifdef CONFIG_CGROUP_WRITEBACK + struct bdi_writeback *i_wb; /* the associated cgroup wb */ + + /* foreign inode detection, see wbc_detach_inode() */ + int i_wb_frn_winner; + u16 i_wb_frn_avg_time; + u16 i_wb_frn_history; +#endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; + struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; - u64 i_version; + atomic64_t i_version; + atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; - const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ - struct file_lock *i_flock; - struct address_space i_data; -#ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; +#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) + atomic_t i_readcount; /* struct files open RO */ #endif - struct list_head i_devices; + union { + const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ + void (*free_inode)(struct inode *); + }; + struct file_lock_context *i_flctx; + struct address_space i_data; + union { + struct list_head i_devices; + int i_linklen; + }; union { struct pipe_inode_info *i_pipe; - struct block_device *i_bdev; struct cdev *i_cdev; + char *i_link; + unsigned i_dir_seq; }; - __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ - struct hlist_head i_fsnotify_marks; + /* 32-bit hole reserved for expanding i_fsnotify_mask */ + struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif -#ifdef CONFIG_IMA - atomic_t i_readcount; /* struct files open RO */ -#endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; + +/* + * i_state handling + * + * We hide all of it behind helpers so that we can validate consumers. + */ +static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode) +{ + return READ_ONCE(inode->i_state.__state); +} + +static inline enum inode_state_flags_enum inode_state_read(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + return inode->i_state.__state; +} + +static inline void inode_state_set_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags); +} + +static inline void inode_state_set(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_set_raw(inode, flags); +} + +static inline void inode_state_clear_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags); +} + +static inline void inode_state_clear(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_clear_raw(inode, flags); +} + +static inline void inode_state_assign_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, flags); +} + +static inline void inode_state_assign(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace_raw(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + enum inode_state_flags_enum flags; + flags = inode->i_state.__state; + flags &= ~clearflags; + flags |= setflags; + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_replace_raw(inode, clearflags, setflags); +} + +static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) +{ + VFS_WARN_ON_INODE(strlen(link) != linklen, inode); + VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); + inode->i_link = link; + inode->i_linklen = linklen; + inode->i_opflags |= IOP_CACHED_LINK; +} + +/* + * Get bit address from inode->i_state to use with wait_var_event() + * infrastructre. + */ +#define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) + +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit); + +static inline void inode_wake_up_bit(struct inode *inode, u32 bit) +{ + /* Caller is responsible for correct memory barriers. */ + wake_up_var(inode_state_wait_address(inode, bit)); +} + +struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); + +static inline unsigned int i_blocksize(const struct inode *node) +{ + return (1 << node->i_blkbits); +} static inline int inode_unhashed(struct inode *inode) { @@ -617,15 +984,33 @@ static inline int inode_unhashed(struct inode *inode) } /* - * inode->i_mutex nesting subclasses for the lock validator: + * __mark_inode_dirty expects inodes to be hashed. Since we don't + * want special inodes in the fileset inode space, we make them + * appear hashed, but do not put on any lists. hlist_del() + * will work fine and require no locking. + */ +static inline void inode_fake_hash(struct inode *inode) +{ + hlist_add_fake(&inode->i_hash); +} + +void wait_on_new_inode(struct inode *inode); + +/* + * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target - * 3: quota file + * 3: xattr + * 4: second non-directory + * 5: second parent (when locking independent directories in rename) + * + * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two + * non-directories at once. * * The locking order between these classes is - * parent -> child -> normal -> xattr -> quota + * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { @@ -633,9 +1018,101 @@ enum inode_i_mutex_lock_class I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, - I_MUTEX_QUOTA + I_MUTEX_NONDIR2, + I_MUTEX_PARENT2, }; +static inline void inode_lock(struct inode *inode) +{ + down_write(&inode->i_rwsem); +} + +static inline __must_check int inode_lock_killable(struct inode *inode) +{ + return down_write_killable(&inode->i_rwsem); +} + +static inline void inode_unlock(struct inode *inode) +{ + up_write(&inode->i_rwsem); +} + +static inline void inode_lock_shared(struct inode *inode) +{ + down_read(&inode->i_rwsem); +} + +static inline __must_check int inode_lock_shared_killable(struct inode *inode) +{ + return down_read_killable(&inode->i_rwsem); +} + +static inline void inode_unlock_shared(struct inode *inode) +{ + up_read(&inode->i_rwsem); +} + +static inline int inode_trylock(struct inode *inode) +{ + return down_write_trylock(&inode->i_rwsem); +} + +static inline int inode_trylock_shared(struct inode *inode) +{ + return down_read_trylock(&inode->i_rwsem); +} + +static inline int inode_is_locked(struct inode *inode) +{ + return rwsem_is_locked(&inode->i_rwsem); +} + +static inline void inode_lock_nested(struct inode *inode, unsigned subclass) +{ + down_write_nested(&inode->i_rwsem, subclass); +} + +static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) +{ + down_read_nested(&inode->i_rwsem, subclass); +} + +static inline void filemap_invalidate_lock(struct address_space *mapping) +{ + down_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock(struct address_space *mapping) +{ + up_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_lock_shared(struct address_space *mapping) +{ + down_read(&mapping->invalidate_lock); +} + +static inline int filemap_invalidate_trylock_shared( + struct address_space *mapping) +{ + return down_read_trylock(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock_shared( + struct address_space *mapping) +{ + up_read(&mapping->invalidate_lock); +} + +void lock_two_nondirectories(struct inode *, struct inode*); +void unlock_two_nondirectories(struct inode *, struct inode*); + +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2); +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2); + + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic @@ -657,7 +1134,7 @@ static inline loff_t i_size_read(const struct inode *inode) i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); @@ -665,13 +1142,14 @@ static inline loff_t i_size_read(const struct inode *inode) preempt_enable(); return i_size; #else - return inode->i_size; + /* Pairs with smp_store_release() in i_size_write() */ + return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it - * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount + * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) @@ -682,40 +1160,20 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else - inode->i_size = i_size; + /* + * Pairs with smp_load_acquire() in i_size_read() to ensure + * changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&inode->i_size, i_size); #endif } -/* Helper functions so that in most cases filesystems will - * not need to deal directly with kuid_t and kgid_t and can - * instead deal with the raw numeric values that are stored - * in the filesystem. - */ -static inline uid_t i_uid_read(const struct inode *inode) -{ - return from_kuid(&init_user_ns, inode->i_uid); -} - -static inline gid_t i_gid_read(const struct inode *inode) -{ - return from_kgid(&init_user_ns, inode->i_gid); -} - -static inline void i_uid_write(struct inode *inode, uid_t uid) -{ - inode->i_uid = make_kuid(&init_user_ns, uid); -} - -static inline void i_gid_write(struct inode *inode, gid_t gid) -{ - inode->i_gid = make_kgid(&init_user_ns, gid); -} - static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); @@ -726,9 +1184,8 @@ static inline unsigned imajor(const struct inode *inode) return MAJOR(inode->i_rdev); } -extern struct block_device *I_BDEV(struct inode *inode); - struct fown_struct { + struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ @@ -736,18 +1193,29 @@ struct fown_struct { int signum; /* posix.1b rt signal to be delivered on IO */ }; -/* - * Track a single file's readahead state +/** + * struct file_ra_state - Track a file's readahead state. + * @start: Where the most recent readahead started. + * @size: Number of pages read in the most recent readahead. + * @async_size: Numer of pages that were/are not needed immediately + * and so were/are genuinely "ahead". Start next readahead when + * the first of these pages is accessed. + * @ra_pages: Maximum size of a readahead request, copied from the bdi. + * @order: Preferred folio order used for most recent readahead. + * @mmap_miss: How many mmap accesses missed in the page cache. + * @prev_pos: The last byte in the most recent read request. + * + * When this structure is passed to ->readahead(), the "most recent" + * readahead means the current readahead. */ struct file_ra_state { - pgoff_t start; /* where readahead started */ - unsigned int size; /* # of readahead pages */ - unsigned int async_size; /* do asynchronous readahead when - there are only # of pages ahead */ - - unsigned int ra_pages; /* Maximum readahead window */ - unsigned int mmap_miss; /* Cache miss stat for mmap accesses */ - loff_t prev_pos; /* Cache last read() position */ + pgoff_t start; + unsigned int size; + unsigned int async_size; + unsigned int ra_pages; + unsigned short order; + unsigned short mmap_miss; + loff_t prev_pos; }; /* @@ -759,781 +1227,704 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } -#define FILE_MNT_WRITE_TAKEN 1 -#define FILE_MNT_WRITE_RELEASED 2 - +/** + * struct file - Represents a file + * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. + * @f_mode: FMODE_* flags often used in hotpaths + * @f_op: file operations + * @f_mapping: Contents of a cacheable, mappable object. + * @private_data: filesystem or driver specific data + * @f_inode: cached inode + * @f_flags: file flags + * @f_iocb_flags: iocb flags + * @f_cred: stashed credentials of creator/opener + * @f_owner: file owner + * @f_path: path of the file + * @__f_path: writable alias for @f_path; *ONLY* for core VFS and only before + * the file gets open + * @f_pos_lock: lock protecting file position + * @f_pipe: specific to pipes + * @f_pos: file position + * @f_security: LSM security context of this file + * @f_wb_err: writeback error + * @f_sb_err: per sb writeback errors + * @f_ep: link of all epoll hooks for this file + * @f_task_work: task work entry point + * @f_llist: work queue entrypoint + * @f_ra: file's readahead state + * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) + * @f_ref: reference count + */ struct file { - /* - * fu_list becomes invalid after file_free is called and queued via - * fu_rcuhead for RCU freeing - */ - union { - struct list_head fu_list; - struct llist_node fu_llist; - struct rcu_head fu_rcuhead; - } f_u; - struct path f_path; -#define f_dentry f_path.dentry - struct inode *f_inode; /* cached value */ + spinlock_t f_lock; + fmode_t f_mode; const struct file_operations *f_op; - - /* - * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR. - * Must not be taken from IRQ context. - */ - spinlock_t f_lock; -#ifdef CONFIG_SMP - int f_sb_list_cpu; -#endif - atomic_long_t f_count; - unsigned int f_flags; - fmode_t f_mode; - loff_t f_pos; - struct fown_struct f_owner; - const struct cred *f_cred; - struct file_ra_state f_ra; - - u64 f_version; + struct address_space *f_mapping; + void *private_data; + struct inode *f_inode; + unsigned int f_flags; + unsigned int f_iocb_flags; + const struct cred *f_cred; + struct fown_struct *f_owner; + /* --- cacheline 1 boundary (64 bytes) --- */ + union { + const struct path f_path; + struct path __f_path; + }; + union { + /* regular files (with FMODE_ATOMIC_POS) and directories */ + struct mutex f_pos_lock; + /* pipes */ + u64 f_pipe; + }; + loff_t f_pos; #ifdef CONFIG_SECURITY - void *f_security; + void *f_security; #endif - /* needed for tty driver, and maybe others */ - void *private_data; - + /* --- cacheline 2 boundary (128 bytes) --- */ + errseq_t f_wb_err; + errseq_t f_sb_err; #ifdef CONFIG_EPOLL - /* Used by fs/eventpoll.c to link all the hooks to this file */ - struct list_head f_ep_links; - struct list_head f_tfile_llink; -#endif /* #ifdef CONFIG_EPOLL */ - struct address_space *f_mapping; -#ifdef CONFIG_DEBUG_WRITECOUNT - unsigned long f_mnt_write_state; + struct hlist_head *f_ep; #endif -}; + union { + struct callback_head f_task_work; + struct llist_node f_llist; + struct file_ra_state f_ra; + freeptr_t f_freeptr; + }; + file_ref_t f_ref; + /* --- cacheline 3 boundary (192 bytes) --- */ +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { - atomic_long_inc(&f->f_count); + file_ref_inc(&f->f_ref); return f; } -#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) -#define file_count(x) atomic_long_read(&(x)->f_count) -#ifdef CONFIG_DEBUG_WRITECOUNT -static inline void file_take_write(struct file *f) -{ - WARN_ON(f->f_mnt_write_state != 0); - f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN; -} -static inline void file_release_write(struct file *f) -{ - f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED; -} -static inline void file_reset_write(struct file *f) -{ - f->f_mnt_write_state = 0; -} -static inline void file_check_state(struct file *f) -{ - /* - * At this point, either both or neither of these bits - * should be set. - */ - WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN); - WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED); -} -static inline int file_check_writeable(struct file *f) -{ - if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN) - return 0; - printk(KERN_WARNING "writeable file with no " - "mnt_want_write()\n"); - WARN_ON(1); - return -EINVAL; -} -#else /* !CONFIG_DEBUG_WRITECOUNT */ -static inline void file_take_write(struct file *filp) {} -static inline void file_release_write(struct file *filp) {} -static inline void file_reset_write(struct file *filp) {} -static inline void file_check_state(struct file *filp) {} -static inline int file_check_writeable(struct file *filp) -{ - return 0; -} -#endif /* CONFIG_DEBUG_WRITECOUNT */ +struct file *get_file_rcu(struct file __rcu **f); +struct file *get_file_active(struct file **f); + +#define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 -#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) +#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif -#define FL_POSIX 1 -#define FL_FLOCK 2 -#define FL_ACCESS 8 /* not trying to lock, just looking */ -#define FL_EXISTS 16 /* when unlocking, test for existence */ -#define FL_LEASE 32 /* lease held on this file */ -#define FL_CLOSE 64 /* unlock on close */ -#define FL_SLEEP 128 /* A blocking lock */ -#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ -#define FL_UNLOCK_PENDING 512 /* Lease is being broken */ +/* legacy typedef, should eventually be removed */ +typedef void *fl_owner_t; -/* - * Special return value from posix_lock_file() and vfs_lock_file() for - * asynchronous locking. - */ -#define FILE_LOCK_DEFERRED 1 +struct file_lock; +struct file_lease; -/* - * The POSIX file lock owner is determined by - * the "struct files_struct" in the thread group - * (or NULL for no owner - BSD locks). - * - * Lockd stuffs a "host" pointer into this. - */ -typedef struct files_struct *fl_owner_t; +/* The following constant reflects the upper bound of the file/locking space */ +#ifndef OFFSET_MAX +#define OFFSET_MAX type_max(loff_t) +#define OFFT_OFFSET_MAX type_max(off_t) +#endif -struct file_lock_operations { - void (*fl_copy_lock)(struct file_lock *, struct file_lock *); - void (*fl_release_private)(struct file_lock *); -}; +int file_f_owner_allocate(struct file *file); +static inline struct fown_struct *file_f_owner(const struct file *file) +{ + return READ_ONCE(file->f_owner); +} -struct lock_manager_operations { - int (*lm_compare_owner)(struct file_lock *, struct file_lock *); - unsigned long (*lm_owner_key)(struct file_lock *); - void (*lm_notify)(struct file_lock *); /* unblock callback */ - int (*lm_grant)(struct file_lock *, struct file_lock *, int); - void (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock **, int); -}; +extern void send_sigio(struct fown_struct *fown, int fd, int band); -struct lock_manager { - struct list_head list; -}; +static inline struct inode *file_inode(const struct file *f) +{ + return f->f_inode; +} -struct net; -void locks_start_grace(struct net *, struct lock_manager *); -void locks_end_grace(struct lock_manager *); -int locks_in_grace(struct net *); +/* + * file_dentry() is a relic from the days that overlayfs was using files with a + * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. + * In those days, file_dentry() was needed to get the underlying fs dentry that + * matches f_inode. + * Files with "fake" path should not exist nowadays, so use an assertion to make + * sure that file_dentry() was not papering over filesystem bugs. + */ +static inline struct dentry *file_dentry(const struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; -/* that will die - we need it for nfs_lock_info */ -#include <linux/nfs_fs_i.h> + WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); + return dentry; +} -/* - * struct file_lock represents a generic "file lock". It's used to represent - * POSIX byte range locks, BSD (flock) locks, and leases. It's important to - * note that the same struct is used to represent both a request for a lock and - * the lock itself, but the same object is never used for both. - * - * FIXME: should we create a separate "struct lock_request" to help distinguish - * these two uses? - * - * The i_flock list is ordered by: - * - * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX - * 2) lock owner - * 3) lock range start - * 4) lock range end - * - * Obviously, the last two criteria only matter for POSIX locks. - */ -struct file_lock { - struct file_lock *fl_next; /* singly linked list for this inode */ - struct hlist_node fl_link; /* node in global lists */ - struct list_head fl_block; /* circular list of blocked processes */ - fl_owner_t fl_owner; - unsigned int fl_flags; - unsigned char fl_type; - unsigned int fl_pid; - int fl_link_cpu; /* what cpu's list is this on? */ - struct pid *fl_nspid; - wait_queue_head_t fl_wait; - struct file *fl_file; - loff_t fl_start; - loff_t fl_end; - - struct fasync_struct * fl_fasync; /* for lease break notifications */ - /* for lease breaks: */ - unsigned long fl_break_time; - unsigned long fl_downgrade_time; - - const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ - const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ - union { - struct nfs_lock_info nfs_fl; - struct nfs4_lock_info nfs4_fl; - struct { - struct list_head link; /* link in AFS vnode's pending_locks list */ - int state; /* state of grant or error if -ve */ - } afs; - } fl_u; +struct fasync_struct { + rwlock_t fa_lock; + int magic; + int fa_fd; + struct fasync_struct *fa_next; /* singly linked list */ + struct file *fa_file; + struct rcu_head fa_rcu; }; -/* The following constant reflects the upper bound of the file/locking space */ -#ifndef OFFSET_MAX -#define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) -#define OFFSET_MAX INT_LIMIT(loff_t) -#define OFFT_OFFSET_MAX INT_LIMIT(off_t) -#endif +#define FASYNC_MAGIC 0x4601 -#include <linux/fcntl.h> +/* SMP safe fasync helpers: */ +extern int fasync_helper(int, struct file *, int, struct fasync_struct **); +extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); +extern int fasync_remove_entry(struct file *, struct fasync_struct **); +extern struct fasync_struct *fasync_alloc(void); +extern void fasync_free(struct fasync_struct *); -extern void send_sigio(struct fown_struct *fown, int fd, int band); +/* can be called from interrupts */ +extern void kill_fasync(struct fasync_struct **, int, int); -#ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, struct flock __user *); -extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock __user *); +extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); +extern int f_setown(struct file *filp, int who, int force); +extern void f_delown(struct file *filp); +extern pid_t f_getown(struct file *filp); +extern int send_sigurg(struct file *file); -#if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, struct flock64 __user *); -extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 __user *); -#endif +/* + * Umount options + */ -extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); -extern int fcntl_getlease(struct file *filp); - -/* fs/locks.c */ -void locks_free_lock(struct file_lock *fl); -extern void locks_init_lock(struct file_lock *); -extern struct file_lock * locks_alloc_lock(void); -extern void locks_copy_lock(struct file_lock *, struct file_lock *); -extern void __locks_copy_lock(struct file_lock *, const struct file_lock *); -extern void locks_remove_posix(struct file *, fl_owner_t); -extern void locks_remove_flock(struct file *); -extern void locks_release_private(struct file_lock *); -extern void posix_test_lock(struct file *, struct file_lock *); -extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); -extern int posix_lock_file_wait(struct file *, struct file_lock *); -extern int posix_unblock_lock(struct file_lock *); -extern int vfs_test_lock(struct file *, struct file_lock *); -extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); -extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); -extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); -extern int __break_lease(struct inode *inode, unsigned int flags); -extern void lease_get_mtime(struct inode *, struct timespec *time); -extern int generic_setlease(struct file *, long, struct file_lock **); -extern int vfs_setlease(struct file *, long, struct file_lock **); -extern int lease_modify(struct file_lock **, int); -extern int lock_may_read(struct inode *, loff_t start, unsigned long count); -extern int lock_may_write(struct inode *, loff_t start, unsigned long count); -#else /* !CONFIG_FILE_LOCKING */ -static inline int fcntl_getlk(struct file *file, struct flock __user *user) -{ - return -EINVAL; -} +#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ +#define MNT_DETACH 0x00000002 /* Just detach from the tree */ +#define MNT_EXPIRE 0x00000004 /* Mark for expiry */ +#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ +#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -static inline int fcntl_setlk(unsigned int fd, struct file *file, - unsigned int cmd, struct flock __user *user) +static inline struct user_namespace *i_user_ns(const struct inode *inode) { - return -EACCES; + return inode->i_sb->s_user_ns; } -#if BITS_PER_LONG == 32 -static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user) +/* Helper functions so that in most cases filesystems will + * not need to deal directly with kuid_t and kgid_t and can + * instead deal with the raw numeric values that are stored + * in the filesystem. + */ +static inline uid_t i_uid_read(const struct inode *inode) { - return -EINVAL; + return from_kuid(i_user_ns(inode), inode->i_uid); } -static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 __user *user) -{ - return -EACCES; -} -#endif -static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) +static inline gid_t i_gid_read(const struct inode *inode) { - return 0; + return from_kgid(i_user_ns(inode), inode->i_gid); } -static inline int fcntl_getlease(struct file *filp) +static inline void i_uid_write(struct inode *inode, uid_t uid) { - return 0; + inode->i_uid = make_kuid(i_user_ns(inode), uid); } -static inline void locks_init_lock(struct file_lock *fl) +static inline void i_gid_write(struct inode *inode, gid_t gid) { - return; + inode->i_gid = make_kgid(i_user_ns(inode), gid); } -static inline void __locks_copy_lock(struct file_lock *new, struct file_lock *fl) +/** + * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping + * @idmap: idmap of the mount the inode was found from + * @inode: inode to map + * + * Return: whe inode's i_uid mapped down according to @idmap. + * If the inode's i_uid has no mapping INVALID_VFSUID is returned. + */ +static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, + const struct inode *inode) { - return; + return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } -static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) +/** + * i_uid_needs_update - check whether inode's i_uid needs to be updated + * @idmap: idmap of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Check whether the $inode's i_uid field needs to be updated taking idmapped + * mounts into account if the filesystem supports it. + * + * Return: true if @inode's i_uid field needs to be updated, false if not. + */ +static inline bool i_uid_needs_update(struct mnt_idmap *idmap, + const struct iattr *attr, + const struct inode *inode) { - return; + return ((attr->ia_valid & ATTR_UID) && + !vfsuid_eq(attr->ia_vfsuid, + i_uid_into_vfsuid(idmap, inode))); } -static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) +/** + * i_uid_update - update @inode's i_uid field + * @idmap: idmap of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Safely update @inode's i_uid field translating the vfsuid of any idmapped + * mount into the filesystem kuid. + */ +static inline void i_uid_update(struct mnt_idmap *idmap, + const struct iattr *attr, + struct inode *inode) { - return; + if (attr->ia_valid & ATTR_UID) + inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), + attr->ia_vfsuid); } -static inline void locks_remove_flock(struct file *filp) +/** + * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping + * @idmap: idmap of the mount the inode was found from + * @inode: inode to map + * + * Return: the inode's i_gid mapped down according to @idmap. + * If the inode's i_gid has no mapping INVALID_VFSGID is returned. + */ +static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, + const struct inode *inode) { - return; + return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } -static inline void posix_test_lock(struct file *filp, struct file_lock *fl) +/** + * i_gid_needs_update - check whether inode's i_gid needs to be updated + * @idmap: idmap of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Check whether the $inode's i_gid field needs to be updated taking idmapped + * mounts into account if the filesystem supports it. + * + * Return: true if @inode's i_gid field needs to be updated, false if not. + */ +static inline bool i_gid_needs_update(struct mnt_idmap *idmap, + const struct iattr *attr, + const struct inode *inode) { - return; + return ((attr->ia_valid & ATTR_GID) && + !vfsgid_eq(attr->ia_vfsgid, + i_gid_into_vfsgid(idmap, inode))); } -static inline int posix_lock_file(struct file *filp, struct file_lock *fl, - struct file_lock *conflock) +/** + * i_gid_update - update @inode's i_gid field + * @idmap: idmap of the mount the inode was found from + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Safely update @inode's i_gid field translating the vfsgid of any idmapped + * mount into the filesystem kgid. + */ +static inline void i_gid_update(struct mnt_idmap *idmap, + const struct iattr *attr, + struct inode *inode) { - return -ENOLCK; + if (attr->ia_valid & ATTR_GID) + inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), + attr->ia_vfsgid); } -static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl) +/** + * inode_fsuid_set - initialize inode's i_uid field with callers fsuid + * @inode: inode to initialize + * @idmap: idmap of the mount the inode was found from + * + * Initialize the i_uid field of @inode. If the inode was found/created via + * an idmapped mount map the caller's fsuid according to @idmap. + */ +static inline void inode_fsuid_set(struct inode *inode, + struct mnt_idmap *idmap) { - return -ENOLCK; + inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } -static inline int posix_unblock_lock(struct file_lock *waiter) +/** + * inode_fsgid_set - initialize inode's i_gid field with callers fsgid + * @inode: inode to initialize + * @idmap: idmap of the mount the inode was found from + * + * Initialize the i_gid field of @inode. If the inode was found/created via + * an idmapped mount map the caller's fsgid according to @idmap. + */ +static inline void inode_fsgid_set(struct inode *inode, + struct mnt_idmap *idmap) { - return -ENOENT; + inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } -static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) +/** + * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped + * @sb: the superblock we want a mapping in + * @idmap: idmap of the relevant mount + * + * Check whether the caller's fsuid and fsgid have a valid mapping in the + * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map + * the caller's fsuid and fsgid according to the @idmap first. + * + * Return: true if fsuid and fsgid is mapped, false if not. + */ +static inline bool fsuidgid_has_mapping(struct super_block *sb, + struct mnt_idmap *idmap) { - return 0; + struct user_namespace *fs_userns = sb->s_user_ns; + kuid_t kuid; + kgid_t kgid; + + kuid = mapped_fsuid(idmap, fs_userns); + if (!uid_valid(kuid)) + return false; + kgid = mapped_fsgid(idmap, fs_userns); + if (!gid_valid(kgid)) + return false; + return kuid_has_mapping(fs_userns, kuid) && + kgid_has_mapping(fs_userns, kgid); } -static inline int vfs_lock_file(struct file *filp, unsigned int cmd, - struct file_lock *fl, struct file_lock *conf) +struct timespec64 current_time(struct inode *inode); +struct timespec64 inode_set_ctime_current(struct inode *inode); +struct timespec64 inode_set_ctime_deleg(struct inode *inode, + struct timespec64 update); + +static inline time64_t inode_get_atime_sec(const struct inode *inode) { - return -ENOLCK; + return inode->i_atime_sec; } -static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) +static inline long inode_get_atime_nsec(const struct inode *inode) { - return 0; + return inode->i_atime_nsec; } -static inline int flock_lock_file_wait(struct file *filp, - struct file_lock *request) +static inline struct timespec64 inode_get_atime(const struct inode *inode) { - return -ENOLCK; + struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), + .tv_nsec = inode_get_atime_nsec(inode) }; + + return ts; } -static inline int __break_lease(struct inode *inode, unsigned int mode) +static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, + struct timespec64 ts) { - return 0; + inode->i_atime_sec = ts.tv_sec; + inode->i_atime_nsec = ts.tv_nsec; + return ts; } -static inline void lease_get_mtime(struct inode *inode, struct timespec *time) +static inline struct timespec64 inode_set_atime(struct inode *inode, + time64_t sec, long nsec) { - return; + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + + return inode_set_atime_to_ts(inode, ts); } -static inline int generic_setlease(struct file *filp, long arg, - struct file_lock **flp) +static inline time64_t inode_get_mtime_sec(const struct inode *inode) { - return -EINVAL; + return inode->i_mtime_sec; } -static inline int vfs_setlease(struct file *filp, long arg, - struct file_lock **lease) +static inline long inode_get_mtime_nsec(const struct inode *inode) { - return -EINVAL; + return inode->i_mtime_nsec; } -static inline int lease_modify(struct file_lock **before, int arg) +static inline struct timespec64 inode_get_mtime(const struct inode *inode) { - return -EINVAL; + struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), + .tv_nsec = inode_get_mtime_nsec(inode) }; + return ts; } -static inline int lock_may_read(struct inode *inode, loff_t start, - unsigned long len) +static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, + struct timespec64 ts) { - return 1; + inode->i_mtime_sec = ts.tv_sec; + inode->i_mtime_nsec = ts.tv_nsec; + return ts; } -static inline int lock_may_write(struct inode *inode, loff_t start, - unsigned long len) +static inline struct timespec64 inode_set_mtime(struct inode *inode, + time64_t sec, long nsec) { - return 1; + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + return inode_set_mtime_to_ts(inode, ts); } -#endif /* !CONFIG_FILE_LOCKING */ - - -struct fasync_struct { - spinlock_t fa_lock; - int magic; - int fa_fd; - struct fasync_struct *fa_next; /* singly linked list */ - struct file *fa_file; - struct rcu_head fa_rcu; -}; - -#define FASYNC_MAGIC 0x4601 - -/* SMP safe fasync helpers: */ -extern int fasync_helper(int, struct file *, int, struct fasync_struct **); -extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); -extern int fasync_remove_entry(struct file *, struct fasync_struct **); -extern struct fasync_struct *fasync_alloc(void); -extern void fasync_free(struct fasync_struct *); - -/* can be called from interrupts */ -extern void kill_fasync(struct fasync_struct **, int, int); - -extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force); -extern int f_setown(struct file *filp, unsigned long arg, int force); -extern void f_delown(struct file *filp); -extern pid_t f_getown(struct file *filp); -extern int send_sigurg(struct fown_struct *fown); - -struct mm_struct; /* - * Umount options + * Multigrain timestamps + * + * Conditionally use fine-grained ctime and mtime timestamps when there + * are users actively observing them via getattr. The primary use-case + * for this is NFS clients that use the ctime to distinguish between + * different states of the file, and that are often fooled by multiple + * operations that occur in the same coarse-grained timer tick. */ +#define I_CTIME_QUERIED ((u32)BIT(31)) -#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ -#define MNT_DETACH 0x00000002 /* Just detach from the tree */ -#define MNT_EXPIRE 0x00000004 /* Mark for expiry */ -#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ -#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ - -extern struct list_head super_blocks; -extern spinlock_t sb_lock; - -/* Possible states of 'frozen' field */ -enum { - SB_UNFROZEN = 0, /* FS is unfrozen */ - SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ - SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ - SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop - * internal threads if needed) */ - SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ -}; - -#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) - -struct sb_writers { - /* Counters for counting writers at each level */ - struct percpu_counter counter[SB_FREEZE_LEVELS]; - wait_queue_head_t wait; /* queue for waiting for - writers / faults to finish */ - int frozen; /* Is sb frozen? */ - wait_queue_head_t wait_unfrozen; /* queue for waiting for - sb to be thawed */ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map lock_map[SB_FREEZE_LEVELS]; -#endif -}; - -struct super_block { - struct list_head s_list; /* Keep this first */ - dev_t s_dev; /* search index; _not_ kdev_t */ - unsigned char s_blocksize_bits; - unsigned long s_blocksize; - loff_t s_maxbytes; /* Max file size */ - struct file_system_type *s_type; - const struct super_operations *s_op; - const struct dquot_operations *dq_op; - const struct quotactl_ops *s_qcop; - const struct export_operations *s_export_op; - unsigned long s_flags; - unsigned long s_magic; - struct dentry *s_root; - struct rw_semaphore s_umount; - int s_count; - atomic_t s_active; -#ifdef CONFIG_SECURITY - void *s_security; -#endif - const struct xattr_handler **s_xattr; - - struct list_head s_inodes; /* all inodes */ - struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ -#ifdef CONFIG_SMP - struct list_head __percpu *s_files; -#else - struct list_head s_files; -#endif - struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ - struct list_head s_dentry_lru; /* unused dentry lru */ - int s_nr_dentry_unused; /* # of dentry on lru */ - - /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ - spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; - struct list_head s_inode_lru; /* unused inode lru */ - int s_nr_inodes_unused; /* # of inodes on lru */ - - struct block_device *s_bdev; - struct backing_dev_info *s_bdi; - struct mtd_info *s_mtd; - struct hlist_node s_instances; - struct quota_info s_dquot; /* Diskquota specific options */ - - struct sb_writers s_writers; - - char s_id[32]; /* Informational name */ - u8 s_uuid[16]; /* UUID */ - - void *s_fs_info; /* Filesystem private info */ - unsigned int s_max_links; - fmode_t s_mode; - - /* Granularity of c/m/atime in ns. - Cannot be worse than a second */ - u32 s_time_gran; - - /* - * The next field is for VFS *only*. No filesystems have any business - * even looking at it. You had been warned. - */ - struct mutex s_vfs_rename_mutex; /* Kludge */ - - /* - * Filesystem subtype. If non-empty the filesystem type field - * in /proc/mounts will be "type.subtype" - */ - char *s_subtype; +static inline time64_t inode_get_ctime_sec(const struct inode *inode) +{ + return inode->i_ctime_sec; +} - /* - * Saved mount options for lazy filesystems using - * generic_show_options() - */ - char __rcu *s_options; - const struct dentry_operations *s_d_op; /* default d_op for dentries */ +static inline long inode_get_ctime_nsec(const struct inode *inode) +{ + return inode->i_ctime_nsec & ~I_CTIME_QUERIED; +} - /* - * Saved pool identifier for cleancache (-1 means none) - */ - int cleancache_poolid; +static inline struct timespec64 inode_get_ctime(const struct inode *inode) +{ + struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), + .tv_nsec = inode_get_ctime_nsec(inode) }; - struct shrinker s_shrink; /* per-sb shrinker handle */ + return ts; +} - /* Number of inodes with nlink == 0 but still referenced */ - atomic_long_t s_remove_count; +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); - /* Being remounted read-only */ - int s_readonly_remount; -}; +/** + * inode_set_ctime - set the ctime in the inode + * @inode: inode in which to set the ctime + * @sec: tv_sec value to set + * @nsec: tv_nsec value to set + * + * Set the ctime in @inode to { @sec, @nsec } + */ +static inline struct timespec64 inode_set_ctime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; -/* superblock cache pruning functions */ -extern void prune_icache_sb(struct super_block *sb, int nr_to_scan); -extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan); + return inode_set_ctime_to_ts(inode, ts); +} -extern struct timespec current_fs_time(struct super_block *sb); +struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ -void __sb_end_write(struct super_block *sb, int level); -int __sb_start_write(struct super_block *sb, int level, bool wait); - /** - * sb_end_write - drop write access to a superblock - * @sb: the super we wrote to + * file_write_started - check if SB_FREEZE_WRITE is held + * @file: the file we write to * - * Decrement number of writers to the filesystem. Wake up possible waiters - * wanting to freeze the filesystem. + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + * May be false positive with !S_ISREG, because file_start_write() has + * no effect on !S_ISREG. */ -static inline void sb_end_write(struct super_block *sb) +static inline bool file_write_started(const struct file *file) { - __sb_end_write(sb, SB_FREEZE_WRITE); + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return sb_write_started(file_inode(file)->i_sb); } /** - * sb_end_pagefault - drop write access to a superblock from a page fault - * @sb: the super we wrote to + * file_write_not_started - check if SB_FREEZE_WRITE is not held + * @file: the file we write to * - * Decrement number of processes handling write page fault to the filesystem. - * Wake up possible waiters wanting to freeze the filesystem. + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + * May be false positive with !S_ISREG, because file_start_write() has + * no effect on !S_ISREG. */ -static inline void sb_end_pagefault(struct super_block *sb) +static inline bool file_write_not_started(const struct file *file) { - __sb_end_write(sb, SB_FREEZE_PAGEFAULT); + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return sb_write_not_started(file_inode(file)->i_sb); } -/** - * sb_end_intwrite - drop write access to a superblock for internal fs purposes - * @sb: the super we wrote to - * - * Decrement fs-internal number of writers to the filesystem. Wake up possible - * waiters wanting to freeze the filesystem. +bool inode_owner_or_capable(struct mnt_idmap *idmap, + const struct inode *inode); + +/* + * VFS helper functions.. */ -static inline void sb_end_intwrite(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_FS); -} +int vfs_create(struct mnt_idmap *, struct dentry *, umode_t, + struct delegated_inode *); +struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t, struct delegated_inode *); +int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, + umode_t, dev_t, struct delegated_inode *); +int vfs_symlink(struct mnt_idmap *, struct inode *, + struct dentry *, const char *, struct delegated_inode *); +int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, + struct dentry *, struct delegated_inode *); +int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *, + struct delegated_inode *); +int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, + struct delegated_inode *); /** - * sb_start_write - get write access to a superblock - * @sb: the super we write to - * - * When a process wants to write data or metadata to a file system (i.e. dirty - * a page or an inode), it should embed the operation in a sb_start_write() - - * sb_end_write() pair to get exclusion against file system freezing. This - * function increments number of writers preventing freezing. If the file - * system is already frozen, the function waits until the file system is - * thawed. - * - * Since freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. Generally, - * freeze protection should be the outermost lock. In particular, we have: - * - * sb_start_write - * -> i_mutex (write path, truncate, directory ops, ...) - * -> s_umount (freeze_super, thaw_super) + * struct renamedata - contains all information required for renaming + * @mnt_idmap: idmap of the mount in which the rename is happening. + * @old_parent: parent of source + * @old_dentry: source + * @new_parent: parent of destination + * @new_dentry: destination + * @delegated_inode: returns an inode needing a delegation break + * @flags: rename flags */ -static inline void sb_start_write(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_WRITE, true); -} - -static inline int sb_start_write_trylock(struct super_block *sb) -{ - return __sb_start_write(sb, SB_FREEZE_WRITE, false); -} +struct renamedata { + struct mnt_idmap *mnt_idmap; + struct dentry *old_parent; + struct dentry *old_dentry; + struct dentry *new_parent; + struct dentry *new_dentry; + struct delegated_inode *delegated_inode; + unsigned int flags; +} __randomize_layout; + +int vfs_rename(struct renamedata *); + +static inline int vfs_whiteout(struct mnt_idmap *idmap, + struct inode *dir, struct dentry *dentry) +{ + return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, + WHITEOUT_DEV, NULL); +} + +struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, + const struct path *parentpath, + umode_t mode, int open_flag, + const struct cred *cred); +struct file *kernel_file_open(const struct path *path, int flags, + const struct cred *cred); + +int vfs_mkobj(struct dentry *, umode_t, + int (*f)(struct dentry *, umode_t, void *), + void *); + +int vfs_fchown(struct file *file, uid_t user, gid_t group); +int vfs_fchmod(struct file *file, umode_t mode); +int vfs_utimes(const struct path *path, struct timespec64 *times); + +#ifdef CONFIG_COMPAT +extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#else +#define compat_ptr_ioctl NULL +#endif -/** - * sb_start_pagefault - get write access to a superblock from a page fault - * @sb: the super we write to - * - * When a process starts handling write page fault, it should embed the - * operation into sb_start_pagefault() - sb_end_pagefault() pair to get - * exclusion against file system freezing. This is needed since the page fault - * is going to dirty a page. This function increments number of running page - * faults preventing freezing. If the file system is already frozen, the - * function waits until the file system is thawed. - * - * Since page fault freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault - * handling code implies lock dependency: - * - * mmap_sem - * -> sb_start_pagefault +/* + * VFS file helper functions. */ -static inline void sb_start_pagefault(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); -} +void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, + const struct inode *dir, umode_t mode); +extern bool may_open_dev(const struct path *path); +umode_t mode_strip_sgid(struct mnt_idmap *idmap, + const struct inode *dir, umode_t mode); +bool in_group_or_capable(struct mnt_idmap *idmap, + const struct inode *inode, vfsgid_t vfsgid); /* - * sb_start_intwrite - get write access to a superblock for internal fs purposes - * @sb: the super we write to - * - * This is the third level of protection against filesystem freezing. It is - * free for use by a filesystem. The only requirement is that it must rank - * below sb_start_pagefault. - * - * For example filesystem can call sb_start_intwrite() when starting a - * transaction which somewhat eases handling of freezing for internal sources - * of filesystem changes (internal fs threads, discarding preallocation on file - * close, etc.). + * This is the "filldir" function type, used by readdir() to let + * the kernel specify what kind of dirent layout it wants to have. + * This allows the kernel to read directories into kernel space or + * to have different dirent layouts depending on the binary type. + * Return 'true' to keep going and 'false' if there are no more entries. */ -static inline void sb_start_intwrite(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_FS, true); -} +struct dir_context; +typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, + unsigned); +struct dir_context { + filldir_t actor; + loff_t pos; + /* + * Filesystems MUST NOT MODIFY count, but may use as a hint: + * 0 unknown + * > 0 space in buffer (assume at least one entry) + * INT_MAX unlimited + */ + int count; +}; -extern bool inode_owner_or_capable(const struct inode *inode); +/* If OR-ed with d_type, pending signals are not checked */ +#define FILLDIR_FLAG_NOINTR 0x1000 /* - * VFS helper functions.. + * These flags let !MMU mmap() govern direct device mapping vs immediate + * copying more easily for MAP_PRIVATE, especially for ROM filesystems. + * + * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) + * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) + * NOMMU_MAP_READ: Can be mapped for reading + * NOMMU_MAP_WRITE: Can be mapped for writing + * NOMMU_MAP_EXEC: Can be mapped for execution */ -extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); -extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); -extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *); -extern int vfs_link(struct dentry *, struct inode *, struct dentry *); -extern int vfs_rmdir(struct inode *, struct dentry *); -extern int vfs_unlink(struct inode *, struct dentry *); -extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); +#define NOMMU_MAP_COPY 0x00000001 +#define NOMMU_MAP_DIRECT 0x00000008 +#define NOMMU_MAP_READ VM_MAYREAD +#define NOMMU_MAP_WRITE VM_MAYWRITE +#define NOMMU_MAP_EXEC VM_MAYEXEC -/* - * VFS dentry helper functions. - */ -extern void dentry_unhash(struct dentry *dentry); +#define NOMMU_VMFLAGS \ + (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* - * VFS file helper functions. + * These flags control the behavior of the remap_file_range function pointer. + * If it is called with len == 0 that means "remap to end of source file". + * See Documentation/filesystems/vfs.rst for more details about this call. + * + * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ -extern void inode_init_owner(struct inode *inode, const struct inode *dir, - umode_t mode); -/* - * VFS FS_IOC_FIEMAP helper definitions. - */ -struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ -}; -int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, - u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); +#define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) /* - * File types - * - * NOTE! These match bits 12..15 of stat.st_mode - * (ie "(i_mode >> 12) & 15"). + * These flags signal that the caller is ok with altering various aspects of + * the behavior of the remap operation. The changes must be made by the + * implementation; the vfs remap helper functions can take advantage of them. + * Flags in this category exist to preserve the quirky behavior of the hoisted + * btrfs clone/dedupe ioctls. */ -#define DT_UNKNOWN 0 -#define DT_FIFO 1 -#define DT_CHR 2 -#define DT_DIR 4 -#define DT_BLK 6 -#define DT_REG 8 -#define DT_LNK 10 -#define DT_SOCK 12 -#define DT_WHT 14 +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* - * This is the "filldir" function type, used by readdir() to let - * the kernel specify what kind of dirent layout it wants to have. - * This allows the kernel to read directories into kernel space or - * to have different dirent layouts depending on the binary type. + * These flags control the behavior of vfs_copy_file_range(). + * They are not available to the user via syscall. + * + * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ -typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); -struct dir_context { - const filldir_t actor; - loff_t pos; -}; +#define COPY_FILE_SPLICE (1 << 0) -struct block_device_operations; +struct iov_iter; +struct io_uring_cmd; +struct offset_ctx; -/* These macros are for out of kernel modules to test that - * the kernel supports the unlocked_ioctl and compat_ioctl - * fields in struct file_operations. */ -#define HAVE_COMPAT_IOCTL 1 -#define HAVE_UNLOCKED_IOCTL 1 +typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; + fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); - ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); - ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); - int (*iterate) (struct file *, struct dir_context *); - unsigned int (*poll) (struct file *, struct poll_table_struct *); + ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); + ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); + int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, + unsigned int flags); + int (*iterate_shared) (struct file *, struct dir_context *); + __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); @@ -1541,111 +1932,179 @@ struct file_operations { int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); - int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); - int (*setlease)(struct file *, long, struct file_lock **); + void (*splice_eof)(struct file *file); + int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); - int (*show_fdinfo)(struct seq_file *m, struct file *f); -}; + void (*show_fdinfo)(struct seq_file *m, struct file *f); +#ifndef CONFIG_MMU + unsigned (*mmap_capabilities)(struct file *); +#endif + ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, + loff_t, size_t, unsigned int); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); + int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); + int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, + unsigned int poll_flags); + int (*mmap_prepare)(struct vm_area_desc *); +} __randomize_layout; + +/* Supports async buffered reads */ +#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) +/* Supports async buffered writes */ +#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) +/* Supports synchronous page faults for mappings */ +#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) +/* Supports non-exclusive O_DIRECT writes from multiple threads */ +#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) +/* Contains huge pages */ +#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) +/* Treat loff_t as unsigned (e.g., /dev/mem) */ +#define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) +/* Supports asynchronous lock callbacks */ +#define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) +/* File system supports uncached read/write buffered IO */ +#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) + +/* Wrap a directory iterator that needs exclusive inode access */ +int wrap_directory_iterator(struct file *, struct dir_context *, + int (*) (struct file *, struct dir_context *)); +#define WRAP_DIR_ITER(x) \ + static int shared_##x(struct file *file , struct dir_context *ctx) \ + { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - void * (*follow_link) (struct dentry *, struct nameidata *); - int (*permission) (struct inode *, int); - struct posix_acl * (*get_acl)(struct inode *, int); + const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); + int (*permission) (struct mnt_idmap *, struct inode *, int); + struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); - void (*put_link) (struct dentry *, struct nameidata *, void *); - int (*create) (struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, + umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,umode_t); + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, + const char *); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, - struct inode *, struct dentry *); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); - int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); - ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, + umode_t,dev_t); + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, + struct inode *, struct dentry *, unsigned int); + int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); + int (*getattr) (struct mnt_idmap *, const struct path *, + struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); - int (*removexattr) (struct dentry *, const char *); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); - int (*update_time)(struct inode *, struct timespec *, int); + int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, - umode_t create_mode, int *opened); - int (*tmpfile) (struct inode *, struct dentry *, umode_t); + umode_t create_mode); + int (*tmpfile) (struct mnt_idmap *, struct inode *, + struct file *, umode_t); + struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, + int); + int (*set_acl)(struct mnt_idmap *, struct dentry *, + struct posix_acl *, int); + int (*fileattr_set)(struct mnt_idmap *idmap, + struct dentry *dentry, struct file_kattr *fa); + int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa); + struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; -ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - unsigned long nr_segs, unsigned long fast_segs, - struct iovec *fast_pointer, - struct iovec **ret_pointer); +/* Did the driver provide valid mmap hook configuration? */ +static inline bool can_mmap_file(struct file *file) +{ + bool has_mmap = file->f_op->mmap; + bool has_mmap_prepare = file->f_op->mmap_prepare; + + /* Hooks are mutually exclusive. */ + if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) + return false; + if (!has_mmap && !has_mmap_prepare) + return false; + + return true; +} + +int __compat_vma_mmap(const struct file_operations *f_op, + struct file *file, struct vm_area_struct *vma); +int compat_vma_mmap(struct file *file, struct vm_area_struct *vma); + +static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (file->f_op->mmap_prepare) + return compat_vma_mmap(file, vma); + + return file->f_op->mmap(file, vma); +} + +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) +{ + return file->f_op->mmap_prepare(desc); +} extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *); -extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *); - -struct super_operations { - struct inode *(*alloc_inode)(struct super_block *sb); - void (*destroy_inode)(struct inode *); - - void (*dirty_inode) (struct inode *, int flags); - int (*write_inode) (struct inode *, struct writeback_control *wbc); - int (*drop_inode) (struct inode *); - void (*evict_inode) (struct inode *); - void (*put_super) (struct super_block *); - int (*sync_fs)(struct super_block *sb, int wait); - int (*freeze_fs) (struct super_block *); - int (*unfreeze_fs) (struct super_block *); - int (*statfs) (struct dentry *, struct kstatfs *); - int (*remount_fs) (struct super_block *, int *, char *); - void (*umount_begin) (struct super_block *); - - int (*show_options)(struct seq_file *, struct dentry *); - int (*show_devname)(struct seq_file *, struct dentry *); - int (*show_path)(struct seq_file *, struct dentry *); - int (*show_stats)(struct seq_file *, struct dentry *); -#ifdef CONFIG_QUOTA - ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); - ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); -#endif - int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - int (*nr_cached_objects)(struct super_block *); - void (*free_cached_objects)(struct super_block *, int); -}; +extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, + loff_t, size_t, unsigned int); +int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); +int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *dax_read_ops); +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, unsigned int remap_flags); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); +extern int vfs_dedupe_file_range(struct file *file, + struct file_dedupe_range *same); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len, unsigned int remap_flags); /* * Inode flags - they have no relation to superblock flags now */ -#define S_SYNC 1 /* Writes are synced at once */ -#define S_NOATIME 2 /* Do not update access times */ -#define S_APPEND 4 /* Append-only file */ -#define S_IMMUTABLE 8 /* Immutable file */ -#define S_DEAD 16 /* removed, but still open directory */ -#define S_NOQUOTA 32 /* Inode is not counted to quota */ -#define S_DIRSYNC 64 /* Directory modifications are synchronous */ -#define S_NOCMTIME 128 /* Do not update file c/mtime */ -#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ -#define S_PRIVATE 512 /* Inode is fs-internal */ -#define S_IMA 1024 /* Inode has an associated IMA struct */ -#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ -#define S_NOSEC 4096 /* no suid or xattr security attributes */ +#define S_SYNC (1 << 0) /* Writes are synced at once */ +#define S_NOATIME (1 << 1) /* Do not update access times */ +#define S_APPEND (1 << 2) /* Append-only file */ +#define S_IMMUTABLE (1 << 3) /* Immutable file */ +#define S_DEAD (1 << 4) /* removed, but still open directory */ +#define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ +#define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ +#define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ +#define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ +#define S_PRIVATE (1 << 9) /* Inode is fs-internal */ +#define S_IMA (1 << 10) /* Inode has an associated IMA struct */ +#define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ +#define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ +#ifdef CONFIG_FS_DAX +#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ +#else +#define S_DAX 0 /* Make all the DAX code disappear */ +#endif +#define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ +#define S_CASEFOLD (1 << 15) /* Casefolded file */ +#define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ +#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ +#define S_ANON_INODE (1 << 19) /* Inode is an anonymous inode */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -1653,7 +2112,7 @@ struct super_operations { * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * - * Exception: MS_RDONLY is always applied to the entire file system. + * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their @@ -1662,97 +2121,73 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY) -#define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ +#define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) +#define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) -#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ +#define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) -#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) -#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME) -#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION) +#define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) +#define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) +#define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) -#define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL) + +#ifdef CONFIG_FS_POSIX_ACL +#define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) +#else +#define IS_POSIXACL(inode) 0 +#endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) + +#ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#else +#define IS_SWAPFILE(inode) ((void)(inode), 0U) +#endif + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) +#define IS_DAX(inode) ((inode)->i_flags & S_DAX) +#define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) +#define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) +#define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) -/* - * Inode state bits. Protected by inode->i_lock - * - * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, - * I_DIRTY_DATASYNC and I_DIRTY_PAGES. - * - * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, - * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at - * various stages of removing an inode. - * - * Two bits are used for locking and completion notification, I_NEW and I_SYNC. - * - * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync(). i_atime is the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of - * these changes separately from I_DIRTY_SYNC so that we - * don't have to write inode on fdatasync() when only - * mtime has changed in it. - * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_NEW Serves as both a mutex and completion notification. - * New inodes set I_NEW. If two processes both create - * the same inode, one of them will release its inode and - * wait for I_NEW to be released before returning. - * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can - * also cause waiting on I_NEW, without I_NEW actually - * being set. find_inode() uses this to prevent returning - * nearly-dead inodes. - * I_WILL_FREE Must be set when calling write_inode_now() if i_count - * is zero. I_FREEING must be set when I_WILL_FREE is - * cleared. - * I_FREEING Set when inode is about to be freed but still has dirty - * pages or buffers attached or the inode itself is still - * dirty. - * I_CLEAR Added by clear_inode(). In this state the inode is - * clean and can be destroyed. Inode keeps I_FREEING. - * - * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are - * prohibited for many purposes. iget() must wait for - * the inode to be completely released, then create it - * anew. Other functions will just ignore such inodes, - * if appropriate. I_NEW is used for waiting. - * - * I_SYNC Writeback of inode is running. The bit is set during - * data writeback, and cleared with a wakeup on the bit - * address once it is done. The bit is also used to pin - * the inode in memory for flusher thread. - * - * I_REFERENCED Marks the inode as recently references on the LRU list. - * - * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). - * - * Q: What is the difference between I_WILL_FREE and I_FREEING? - */ -#define I_DIRTY_SYNC (1 << 0) -#define I_DIRTY_DATASYNC (1 << 1) -#define I_DIRTY_PAGES (1 << 2) -#define __I_NEW 3 -#define I_NEW (1 << __I_NEW) -#define I_WILL_FREE (1 << 4) -#define I_FREEING (1 << 5) -#define I_CLEAR (1 << 6) -#define __I_SYNC 7 -#define I_SYNC (1 << __I_SYNC) -#define I_REFERENCED (1 << 8) -#define __I_DIO_WAKEUP 9 -#define I_DIO_WAKEUP (1 << I_DIO_WAKEUP) -#define I_LINKABLE (1 << 10) - -#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) +#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ + (inode)->i_rdev == WHITEOUT_DEV) +#define IS_ANON_FILE(inode) ((inode)->i_flags & S_ANON_INODE) + +static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, + struct inode *inode) +{ + return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); +} + +static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = filp->f_iocb_flags, + .ki_ioprio = get_current_ioprio(), + }; +} + +static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, + struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = kiocb_src->ki_flags, + .ki_ioprio = kiocb_src->ki_ioprio, + .ki_pos = kiocb_src->ki_pos, + }; +} extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) @@ -1765,6 +2200,26 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline int icount_read(const struct inode *inode) +{ + return atomic_read(&inode->i_count); +} + +/* + * Returns true if the given inode itself only has dirty timestamps (its pages + * may still be dirty) and isn't currently being allocated or freed. + * Filesystems should call this if when writing an inode when lazytime is + * enabled, they want to opportunistically write the timestamps of other inodes + * located very nearby on-disk, e.g. in the same inode block. This returns true + * if the given inode is in need of such an opportunistic update. Requires + * i_lock, or at least later re-checking under i_lock. + */ +static inline bool inode_is_dirtytime_only(struct inode *inode) +{ + return (inode_state_read_once(inode) & + (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; +} + extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); @@ -1782,21 +2237,6 @@ static inline void inode_dec_link_count(struct inode *inode) mark_inode_dirty(inode); } -/** - * inode_inc_iversion - increments i_version - * @inode: inode that need to be updated - * - * Every time the inode is modified, the i_version field will be incremented. - * The filesystem has to be mounted with i_version flag - */ - -static inline void inode_inc_iversion(struct inode *inode) -{ - spin_lock(&inode->i_lock); - inode->i_version++; - spin_unlock(&inode->i_lock); -} - enum file_time_flags { S_ATIME = 1, S_MTIME = 2, @@ -1804,14 +2244,19 @@ enum file_time_flags { S_VERSION = 8, }; -extern void touch_atime(struct path *); +extern bool atime_needs_update(const struct path *, struct inode *); +extern void touch_atime(const struct path *); +int inode_update_time(struct inode *inode, int flags); + static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } -int sync_inode(struct inode *inode, struct writeback_control *wbc); +extern int file_modified(struct file *file); +int kiocb_modified(struct kiocb *iocb); + int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { @@ -1821,8 +2266,14 @@ struct file_system_type { #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ -#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ +#define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ +#define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ +#define FS_MGTIME 64 /* FS uses multigrain timestamps */ +#define FS_LBS 128 /* FS supports LBS */ +#define FS_POWER_FREEZE 256 /* Always freeze on suspend/hibernate */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ + int (*init_fs_context)(struct fs_context *); + const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); @@ -1837,292 +2288,270 @@ struct file_system_type { struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; + struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags, - void *data, int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_single(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_nodev(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); +/** + * is_mgtime: is this inode using multigrain timestamps + * @inode: inode to test for multigrain timestamps + * + * Return true if the inode uses multigrain timestamps, false otherwise. + */ +static inline bool is_mgtime(const struct inode *inode) +{ + return inode->i_opflags & IOP_MGTIME; +} + extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); +void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); -void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); +int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); +struct super_block *sget_fc(struct fs_context *fc, + int (*test)(struct super_block *, struct fs_context *), + int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); -extern struct dentry *mount_pseudo(struct file_system_type *, char *, - const struct super_operations *ops, - const struct dentry_operations *dops, - unsigned long); +struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -#define fops_get(fops) \ - (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) -#define fops_put(fops) \ - do { if (fops) module_put((fops)->owner); } while(0) +#define fops_get(fops) ({ \ + const struct file_operations *_fops = (fops); \ + (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ +}) + +#define fops_put(fops) ({ \ + const struct file_operations *_fops = (fops); \ + if (_fops) \ + module_put((_fops)->owner); \ +}) + +/* + * This one is to be used *ONLY* from ->open() instances. + * fops must be non-NULL, pinned down *and* module dependencies + * should be sufficient to pin the caller down as well. + */ +#define replace_fops(f, fops) \ + do { \ + struct file *__file = (f); \ + fops_put(__file->f_op); \ + BUG_ON(!(__file->f_op = (fops))); \ + } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); -extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data); -#define kern_mount(type) kern_mount_data(type, NULL) -extern void kern_unmount(struct vfsmount *mnt); -extern int may_umount_tree(struct vfsmount *); -extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char *, const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(struct path *); -extern void drop_collected_mounts(struct vfsmount *); -extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - struct vfsmount *); -extern int vfs_statfs(struct path *, struct kstatfs *); +extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); -extern int vfs_ustat(dev_t, struct kstatfs *); -extern int freeze_super(struct super_block *super); -extern int thaw_super(struct super_block *super); -extern bool our_mnt(struct vfsmount *mnt); - -extern int current_umask(void); - -/* /sys/fs */ -extern struct kobject *fs_kobj; - -#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) - -#define FLOCK_VERIFY_READ 1 -#define FLOCK_VERIFY_WRITE 2 - -#ifdef CONFIG_FILE_LOCKING -extern int locks_mandatory_locked(struct inode *); -extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t); +extern __printf(2, 3) +int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); +extern int super_setup_bdi(struct super_block *sb); -/* - * Candidates for mandatory locking have the setgid bit set - * but no group execute bit - an otherwise meaningless combination. - */ - -static inline int __mandatory_lock(struct inode *ino) +static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { - return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; + if (WARN_ON(len > sizeof(sb->s_uuid))) + len = sizeof(sb->s_uuid); + sb->s_uuid_len = len; + memcpy(&sb->s_uuid, uuid, len); } -/* - * ... and these candidates should be on MS_MANDLOCK mounted fs, - * otherwise these will be advisory locks - */ - -static inline int mandatory_lock(struct inode *ino) +/* set sb sysfs name based on sb->s_bdev */ +static inline void super_set_sysfs_name_bdev(struct super_block *sb) { - return IS_MANDLOCK(ino) && __mandatory_lock(ino); + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } -static inline int locks_verify_locked(struct inode *inode) +/* set sb sysfs name based on sb->s_uuid */ +static inline void super_set_sysfs_name_uuid(struct super_block *sb) { - if (mandatory_lock(inode)) - return locks_mandatory_locked(inode); - return 0; + WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } -static inline int locks_verify_truncate(struct inode *inode, - struct file *filp, - loff_t size) +/* set sb sysfs name based on sb->s_id */ +static inline void super_set_sysfs_name_id(struct super_block *sb) { - if (inode->i_flock && mandatory_lock(inode)) - return locks_mandatory_area( - FLOCK_VERIFY_WRITE, inode, filp, - size < inode->i_size ? size : inode->i_size, - (size < inode->i_size ? inode->i_size - size - : size - inode->i_size) - ); - return 0; + strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } -static inline int break_lease(struct inode *inode, unsigned int mode) +/* try to use something standard before you use this */ +__printf(2, 3) +static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { - if (inode->i_flock) - return __break_lease(inode, mode); - return 0; -} -#else /* !CONFIG_FILE_LOCKING */ -static inline int locks_mandatory_locked(struct inode *inode) -{ - return 0; + va_list args; + + va_start(args, fmt); + vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); + va_end(args); } -static inline int locks_mandatory_area(int rw, struct inode *inode, - struct file *filp, loff_t offset, - size_t count) +extern void ihold(struct inode * inode); +extern void iput(struct inode *); +void iput_not_last(struct inode *); +int inode_update_timestamps(struct inode *inode, int flags); +int generic_update_time(struct inode *, int); + +/* /sys/fs */ +extern struct kobject *fs_kobj; + +#define MAX_RW_COUNT (INT_MAX & PAGE_MASK) + +/* fs/open.c */ +struct audit_names; +struct filename { + const char *name; /* pointer to actual string */ + const __user char *uptr; /* original userland pointer */ + atomic_t refcnt; + struct audit_names *aname; + const char iname[]; +}; +static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); + +static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { - return 0; + return mnt_idmap(file->f_path.mnt); } -static inline int __mandatory_lock(struct inode *inode) +/** + * is_idmapped_mnt - check whether a mount is mapped + * @mnt: the mount to check + * + * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. + * + * Return: true if mount is mapped, false if not. + */ +static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { - return 0; + return mnt_idmap(mnt) != &nop_mnt_idmap; } -static inline int mandatory_lock(struct inode *inode) +int vfs_truncate(const struct path *, loff_t); +int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, + unsigned int time_attrs, struct file *filp); +extern int vfs_fallocate(struct file *file, int mode, loff_t offset, + loff_t len); +int do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); +extern struct file *file_open_name(struct filename *, int, umode_t); +extern struct file *filp_open(const char *, int, umode_t); +extern struct file *file_open_root(const struct path *, + const char *, int, umode_t); +static inline struct file *file_open_root_mnt(struct vfsmount *mnt, + const char *name, int flags, umode_t mode) +{ + return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, + name, flags, mode); +} +struct file *dentry_open(const struct path *path, int flags, + const struct cred *creds); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred); +struct file *dentry_create(const struct path *path, int flags, umode_t mode, + const struct cred *cred); +const struct path *backing_file_user_path(const struct file *f); + +/* + * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file + * stored in ->vm_file is a backing file whose f_inode is on the underlying + * filesystem. When the mapped file path and inode number are displayed to + * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the + * path and inode number to display to the user, which is the path of the fd + * that user has requested to map and the inode number that would be returned + * by fstat() on that same fd. + */ +/* Get the path to display in /proc/<pid>/maps */ +static inline const struct path *file_user_path(const struct file *f) { - return 0; + if (unlikely(f->f_mode & FMODE_BACKING)) + return backing_file_user_path(f); + return &f->f_path; } - -static inline int locks_verify_locked(struct inode *inode) +/* Get the inode whose inode number to display in /proc/<pid>/maps */ +static inline const struct inode *file_user_inode(const struct file *f) { - return 0; + if (unlikely(f->f_mode & FMODE_BACKING)) + return d_inode(backing_file_user_path(f)->dentry); + return file_inode(f); } -static inline int locks_verify_truncate(struct inode *inode, struct file *filp, - size_t size) +static inline struct file *file_clone_open(struct file *file) { - return 0; + return dentry_open(&file->f_path, file->f_flags, file->f_cred); } +extern int filp_close(struct file *, fl_owner_t id); -static inline int break_lease(struct inode *inode, unsigned int mode) +extern struct filename *getname_flags(const char __user *, int); +extern struct filename *getname_uflags(const char __user *, int); +static inline struct filename *getname(const char __user *name) { - return 0; + return getname_flags(name, 0); } +extern struct filename *getname_kernel(const char *); +extern struct filename *__getname_maybe_null(const char __user *); +static inline struct filename *getname_maybe_null(const char __user *name, int flags) +{ + if (!(flags & AT_EMPTY_PATH)) + return getname(name); -#endif /* CONFIG_FILE_LOCKING */ - -/* fs/open.c */ -struct audit_names; -struct filename { - const char *name; /* pointer to actual string */ - const __user char *uptr; /* original userland pointer */ - struct audit_names *aname; - bool separate; /* should "name" be freed? */ -}; - -extern long vfs_truncate(struct path *, loff_t); -extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, - struct file *filp); -extern int do_fallocate(struct file *file, int mode, loff_t offset, - loff_t len); -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); -extern struct file *file_open_name(struct filename *, int, umode_t); -extern struct file *filp_open(const char *, int, umode_t); -extern struct file *file_open_root(struct dentry *, struct vfsmount *, - const char *, int); -extern struct file * dentry_open(const struct path *, int, const struct cred *); -extern int filp_close(struct file *, fl_owner_t id); + if (!name) + return NULL; + return __getname_maybe_null(name); +} +extern void putname(struct filename *name); +DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) -extern struct filename *getname(const char __user *); +static inline struct filename *refname(struct filename *name) +{ + atomic_inc(&name->refcnt); + return name; +} -enum { - FILE_CREATED = 1, - FILE_OPENED = 2 -}; extern int finish_open(struct file *file, struct dentry *dentry, - int (*open)(struct inode *, struct file *), - int *opened); + int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); -/* fs/ioctl.c */ +/* Helper for the simple case when original dentry is used */ +static inline int finish_open_simple(struct file *file, int error) +{ + if (error) + return error; -extern int ioctl_preallocate(struct file *filp, void __user *argp); + return finish_open(file, file->f_path.dentry, NULL); +} /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -extern void __init vfs_caches_init(unsigned long); +extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; -extern void final_putname(struct filename *name); - #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -#ifndef CONFIG_AUDITSYSCALL -#define putname(name) final_putname(name) -#else -extern void putname(struct filename *name); -#endif - -#ifdef CONFIG_BLOCK -extern int register_blkdev(unsigned int, const char *); -extern void unregister_blkdev(unsigned int, const char *); -extern struct block_device *bdget(dev_t); -extern struct block_device *bdgrab(struct block_device *bdev); -extern void bd_set_size(struct block_device *, loff_t size); -extern void bd_forget(struct inode *inode); -extern void bdput(struct block_device *); -extern void invalidate_bdev(struct block_device *); -extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); -extern int sync_blockdev(struct block_device *bdev); -extern void kill_bdev(struct block_device *); -extern struct super_block *freeze_bdev(struct block_device *); -extern void emergency_thaw_all(void); -extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); -extern int fsync_bdev(struct block_device *); -#else -static inline void bd_forget(struct inode *inode) {} -static inline int sync_blockdev(struct block_device *bdev) { return 0; } -static inline void kill_bdev(struct block_device *bdev) {} -static inline void invalidate_bdev(struct block_device *bdev) {} -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; -} - -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) -{ -} -#endif +void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -extern const struct file_operations bad_sock_fops; -#ifdef CONFIG_BLOCK -extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); -extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, - void *holder); -extern void blkdev_put(struct block_device *bdev, fmode_t mode); -#ifdef CONFIG_SYSFS -extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -extern void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -#endif -#endif /* fs/char_dev.c */ -#define CHRDEV_MAJOR_HASH_SIZE 255 +#define CHRDEV_MAJOR_MAX 512 +/* Marks the bottom of the first segment of free char majors */ +#define CHRDEV_MAJOR_DYN_END 234 +/* Marks the top and bottom of the second segment of free char majors */ +#define CHRDEV_MAJOR_DYN_EXT_START 511 +#define CHRDEV_MAJOR_DYN_EXT_END 384 + extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, @@ -2144,125 +2573,185 @@ static inline void unregister_chrdev(unsigned int major, const char *name) __unregister_chrdev(major, 0, 256, name); } -/* fs/block_dev.c */ -#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ -#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ - -#ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_HASH_SIZE 255 -extern const char *__bdevname(dev_t, char *buffer); -extern const char *bdevname(struct block_device *bdev, char *buffer); -extern struct block_device *lookup_bdev(const char *); -extern void blkdev_show(struct seq_file *,off_t); - -#else -#define BLKDEV_MAJOR_HASH_SIZE 0 -#endif - extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); -extern int is_bad_inode(struct inode *); +extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK -/* - * return READ, READA, or WRITE - */ -#define bio_rw(bio) ((bio)->bi_rw & (RW_MASK | RWA_MASK)) - -/* - * return data direction, READ or WRITE - */ -#define bio_data_dir(bio) ((bio)->bi_rw & 1) +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); +extern int __must_check file_check_and_advance_wb_err(struct file *file); +extern int __must_check file_write_and_wait_range(struct file *file, + loff_t start, loff_t end); +int filemap_flush_range(struct address_space *mapping, loff_t start, + loff_t end); -extern void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev); -extern int revalidate_disk(struct gendisk *); -extern int check_disk_change(struct block_device *); -extern int __invalidate_device(struct block_device *, bool); -extern int invalidate_partition(struct gendisk *, int); -#endif -unsigned long invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end); - -static inline void invalidate_remote_inode(struct inode *inode) -{ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) - invalidate_mapping_pages(inode->i_mapping, 0, -1); -} -extern int invalidate_inode_pages2(struct address_space *mapping); -extern int invalidate_inode_pages2_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); -extern int write_inode_now(struct inode *, int); -extern int filemap_fdatawrite(struct address_space *); -extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait(struct address_space *); -extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_write_and_wait(struct address_space *mapping); -extern int filemap_write_and_wait_range(struct address_space *mapping, - loff_t lstart, loff_t lend); -extern int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); -extern int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end); +static inline int file_write_and_wait(struct file *file) +{ + return file_write_and_wait_range(file, 0, LLONG_MAX); +} extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); -extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); + +extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, + unsigned int flags); + +static inline bool iocb_is_dsync(const struct kiocb *iocb) +{ + return (iocb->ki_flags & IOCB_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host); +} + +/* + * Sync the bytes written if this was a synchronous write. Expect ki_pos + * to already be updated for the write, and will return either the amount + * of bytes passed in, or an error if syncing the file failed. + */ +static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) +{ + if (iocb_is_dsync(iocb)) { + int ret = vfs_fsync_range(iocb->ki_filp, + iocb->ki_pos - count, iocb->ki_pos - 1, + (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); + if (ret) + return ret; + } else if (iocb->ki_flags & IOCB_DONTCACHE) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + + filemap_flush_range(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); + } + + return count; +} + extern void emergency_sync(void); extern void emergency_remount(void); + #ifdef CONFIG_BLOCK -extern sector_t bmap(struct inode *, sector_t); +extern int bmap(struct inode *inode, sector_t *block); +#else +static inline int bmap(struct inode *inode, sector_t *block) +{ + return -EINVAL; +} #endif -extern int notify_change(struct dentry *, struct iattr *); -extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int); + +int notify_change(struct mnt_idmap *, struct dentry *, + struct iattr *, struct delegated_inode *); +int inode_permission(struct mnt_idmap *, struct inode *, int); +int generic_permission(struct mnt_idmap *, struct inode *, int); +static inline int file_permission(struct file *file, int mask) +{ + return inode_permission(file_mnt_idmap(file), + file_inode(file), mask); +} +static inline int path_permission(const struct path *path, int mask) +{ + return inode_permission(mnt_idmap(path->mnt), + d_inode(path->dentry), mask); +} +int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, + struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } -static inline struct inode *file_inode(struct file *f) +static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { - return f->f_inode; + return (inode->i_mode ^ mode) & S_IFMT; } +/** + * file_start_write - get write access to a superblock for regular file io + * @file: the file we want to write to + * + * This is a variant of sb_start_write() which is a noop on non-regular file. + * Should be matched with a call to file_end_write(). + */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; - return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); + return sb_start_write_trylock(file_inode(file)->i_sb); } +/** + * file_end_write - drop write access to a superblock of a regular file + * @file: the file we wrote to + * + * Should be matched with a call to file_start_write(). + */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); + sb_end_write(file_inode(file)->i_sb); +} + +/** + * kiocb_start_write - get write access to a superblock for async file io + * @iocb: the io context we want to submit the write with + * + * This is a variant of sb_start_write() for async io submission. + * Should be matched with a call to kiocb_end_write(). + */ +static inline void kiocb_start_write(struct kiocb *iocb) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + sb_start_write(inode->i_sb); + /* + * Fool lockdep by telling it the lock got released so that it + * doesn't complain about the held lock when we return to userspace. + */ + __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); +} + +/** + * kiocb_end_write - drop write access to a superblock after async file io + * @iocb: the io context we sumbitted the write with + * + * Should be matched with a call to kiocb_start_write(). + */ +static inline void kiocb_end_write(struct kiocb *iocb) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + /* + * Tell lockdep we inherited freeze protection from submission thread. + */ + __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); + sb_end_write(inode->i_sb); } /* + * This is used for regular files where some users -- especially the + * currently executed binary in a process, previously handled via + * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap + * read-write shared) accesses. + * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. - * This is used for regular files. - * We cannot support write (and maybe mmap read-write shared) accesses and - * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode - * can have the following values: - * 0: no writers, no VM_DENYWRITE mappings - * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist - * > 0: (i_writecount) users are writing to the file. + * deny_write_access() denies write access to a file. + * allow_write_access() re-enables write access to a file. + * + * The i_writecount field of an inode can have the following values: + * 0: no write access, no denied write access + * < 0: (-i_writecount) users that denied write access to the file. + * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to @@ -2287,11 +2776,43 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file_inode(file)->i_writecount); } -#ifdef CONFIG_IMA + +/* + * Do not prevent write to executable file when watched by pre-content events. + * + * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at + * the time of file open and remains constant for entire lifetime of the file, + * so if pre-content watches are added post execution or removed before the end + * of the execution, it will not cause i_writecount reference leak. + */ +static inline int exe_file_deny_write_access(struct file *exe_file) +{ + if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return 0; + return deny_write_access(exe_file); +} +static inline void exe_file_allow_write_access(struct file *exe_file) +{ + if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return; + allow_write_access(exe_file); +} + +static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) +{ + file->f_mode &= ~FMODE_FSNOTIFY_MASK; + file->f_mode |= mode; +} + +static inline bool inode_is_open_for_write(const struct inode *inode) +{ + return atomic_read(&inode->i_writecount) > 0; +} + +#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { - BUG_ON(!atomic_read(&inode->i_readcount)); - atomic_dec(&inode->i_readcount); + BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { @@ -2309,13 +2830,45 @@ static inline void i_readcount_inc(struct inode *inode) #endif extern int do_pipe_flags(int *, int); -extern int kernel_read(struct file *, loff_t, char *, unsigned long); -extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); +extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); +ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); +extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); +extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -extern int is_subdir(struct dentry *, struct dentry *); -extern int path_is_under(struct path *, struct path *); +extern bool is_subdir(struct dentry *, struct dentry *); +extern bool path_is_under(const struct path *, const struct path *); +u64 vfsmount_to_propagation_flags(struct vfsmount *mnt); + +extern char *file_path(struct file *, char *, int); + +/** + * is_dot_dotdot - returns true only if @name is "." or ".." + * @name: file name to check + * @len: length of file name, in bytes + */ +static inline bool is_dot_dotdot(const char *name, size_t len) +{ + return len && unlikely(name[0] == '.') && + (len == 1 || (len == 2 && name[1] == '.')); +} + +/** + * name_contains_dotdot - check if a file name contains ".." path components + * @name: File path string to check + * Search for ".." surrounded by either '/' or start/end of string. + */ +static inline bool name_contains_dotdot(const char *name) +{ + size_t name_len; + + name_len = strlen(name); + return strcmp(name, "..") == 0 || + strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0); +} #include <linux/err.h> @@ -2324,29 +2877,50 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); -extern int inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t); +static inline int inode_init_always(struct super_block *sb, struct inode *inode) +{ + return inode_init_always_gfp(sb, inode, GFP_NOFS); +} + extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); -extern void ihold(struct inode * inode); -extern void iput(struct inode *); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); -extern int generic_delete_inode(struct inode *inode); -static inline int generic_drop_inode(struct inode *inode) +extern int inode_just_drop(struct inode *inode); +static inline int inode_generic_drop(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } +extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), - void *data); + void *data, bool *isnew); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); -extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); +extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), + void *data); +struct inode *iget5_locked(struct super_block *, unsigned long, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *); +struct inode *iget5_locked_rcu(struct super_block *, unsigned long, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); +extern struct inode *find_inode_nowait(struct super_block *, + unsigned long, + int (*match)(struct inode *, + unsigned long, void *), + void *data); +extern struct inode *find_inode_rcu(struct super_block *, unsigned long, + int (*)(struct inode *, void *), void *); +extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -2355,17 +2929,52 @@ extern void lockdep_annotate_inode_mutex_key(struct inode *inode); static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); +extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); +extern void evict_inodes(struct super_block *sb); +void dump_mapping(const struct address_space *); + +/* + * Userspace may rely on the inode number being non-zero. For example, glibc + * simply ignores files with zero i_ino in unlink() and other places. + * + * As an additional complication, if userspace was compiled with + * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the + * lower 32 bits, so we need to check that those aren't zero explicitly. With + * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but + * better safe than sorry. + */ +static inline bool is_zero_ino(ino_t ino) +{ + return (u32)ino == 0; +} + +static inline void __iget(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + atomic_inc(&inode->i_count); +} -extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode_pseudo(struct super_block *sb); +struct inode *alloc_inode(struct super_block *sb); +static inline struct inode *new_inode_pseudo(struct super_block *sb) +{ + return alloc_inode(sb); +} extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); -extern int should_remove_suid(struct dentry *); -extern int file_remove_suid(struct file *); +extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); +extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct mnt_idmap *idmap, + const struct inode *inode); + +/* + * This must be used for allocating filesystems specific inodes to set + * up the inode reclaim context correctly. + */ +#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) @@ -2376,85 +2985,72 @@ static inline void insert_inode_hash(struct inode *inode) extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { - if (!inode_unhashed(inode)) + if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); - -#ifdef CONFIG_BLOCK -extern void submit_bio(int, struct bio *); -extern int bdev_read_only(struct block_device *); -#endif -extern int set_blocksize(struct block_device *, int); -extern int sb_set_blocksize(struct super_block *, int); -extern int sb_min_blocksize(struct super_block *, int); - -extern int generic_file_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, - unsigned long size, pgoff_t pgoff); -extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); -int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); -extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, - loff_t *); -extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, - unsigned long *, loff_t, loff_t *, size_t, size_t); -extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, - unsigned long, loff_t, loff_t *, size_t, ssize_t); -extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); -extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); -extern int generic_segment_checks(const struct iovec *iov, - unsigned long *nr_segs, size_t *count, int access_flags); - -/* fs/block_dev.c */ -extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, - int datasync); -extern void block_sync_page(struct page *page); +extern void inode_lru_list_add(struct inode *inode); + +int generic_file_mmap(struct file *, struct vm_area_struct *); +int generic_file_mmap_prepare(struct vm_area_desc *desc); +int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc); +extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +int generic_write_checks_count(struct kiocb *iocb, loff_t *count); +extern int generic_write_check_limits(struct file *file, loff_t pos, + loff_t *count); +extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); +ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, + ssize_t already_read); +extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); +extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); +extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); +extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); +ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); +ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, + ssize_t direct_written, ssize_t buffered_written); + +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags); +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags); +ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, + struct iov_iter *iter); +ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, + struct iov_iter *iter); /* fs/splice.c */ -extern ssize_t generic_file_splice_read(struct file *, loff_t *, - struct pipe_inode_info *, size_t, unsigned int); -extern ssize_t default_file_splice_read(struct file *, loff_t *, - struct pipe_inode_info *, size_t, unsigned int); -extern ssize_t generic_file_splice_write(struct pipe_inode_info *, +ssize_t filemap_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); +ssize_t copy_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); +extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); -extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, - struct file *out, loff_t *, size_t len, unsigned int flags); + extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); -extern loff_t no_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); +loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, + u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); +extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); +extern loff_t no_seek_end_llseek(struct file *, loff_t, int); +int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); - -#ifdef CONFIG_FS_XIP -extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len, - loff_t *ppos); -extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma); -extern ssize_t xip_file_write(struct file *filp, const char __user *buf, - size_t len, loff_t *ppos); -extern int xip_truncate_page(struct address_space *mapping, loff_t from); -#else -static inline int xip_truncate_page(struct address_space *mapping, loff_t from) -{ - return 0; -} -#endif +extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK -typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, +typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { @@ -2465,150 +3061,357 @@ enum { DIO_SKIP_HOLES = 0x02, }; -void dio_end_io(struct bio *bio, int error); - -ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags); +ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, struct iov_iter *iter, + get_block_t get_block, + dio_iodone_t end_io, + int flags); -static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, - struct inode *inode, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_block_t get_block) +static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, + struct inode *inode, + struct iov_iter *iter, + get_block_t get_block) { - return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, get_block, NULL, NULL, - DIO_LOCKING | DIO_SKIP_HOLES); + return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, + get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif +bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); -void inode_dio_done(struct inode *inode); +void inode_dio_wait_interruptible(struct inode *inode); + +/** + * inode_dio_begin - signal start of a direct I/O requests + * @inode: inode the direct I/O happens on + * + * This is called once we've finished processing a direct I/O request, + * and is used to wake up callers waiting for direct I/O to be quiesced. + */ +static inline void inode_dio_begin(struct inode *inode) +{ + atomic_inc(&inode->i_dio_count); +} + +/** + * inode_dio_end - signal finish of a direct I/O requests + * @inode: inode the direct I/O happens on + * + * This is called once we've finished processing a direct I/O request, + * and is used to wake up callers waiting for direct I/O to be quiesced. + */ +static inline void inode_dio_end(struct inode *inode) +{ + if (atomic_dec_and_test(&inode->i_dio_count)) + wake_up_var(&inode->i_dio_count); +} + +extern void inode_set_flags(struct inode *inode, unsigned int flags, + unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) -extern int vfs_readlink(struct dentry *, char __user *, int, const char *); -extern int vfs_follow_link(struct nameidata *, const char *); +extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); -extern void *page_follow_link_light(struct dentry *, struct nameidata *); -extern void page_put_link(struct dentry *, struct nameidata *, void *); -extern int __page_symlink(struct inode *inode, const char *symname, int len, - int nofs); +extern const char *page_get_link_raw(struct dentry *, struct inode *, + struct delayed_call *); +extern const char *page_get_link(struct dentry *, struct inode *, + struct delayed_call *); +extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; -extern int generic_readlink(struct dentry *, char __user *, int); -extern void generic_fillattr(struct inode *, struct kstat *); -extern int vfs_getattr(struct path *, struct kstat *); +extern void kfree_link(void *); +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); +void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); +void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max, + unsigned int unit_max_opt); +extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); +extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); +void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); +static inline loff_t __inode_get_bytes(struct inode *inode) +{ + return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; +} loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); +const char *simple_get_link(struct dentry *, struct inode *, + struct delayed_call *); +extern const struct inode_operations simple_symlink_inode_operations; -extern int vfs_readdir(struct file *, filldir_t, void *); extern int iterate_dir(struct file *, struct dir_context *); -extern int vfs_stat(const char __user *, struct kstat *); -extern int vfs_lstat(const char __user *, struct kstat *); -extern int vfs_fstat(unsigned int, struct kstat *); -extern int vfs_fstatat(int , const char __user *, struct kstat *, int); - -extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, - unsigned long arg); -extern int __generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, - get_block_t *get_block); -extern int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block); - -extern void get_filesystem(struct file_system_type *fs); +int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, + int flags); +int vfs_fstat(int fd, struct kstat *stat); + +static inline int vfs_stat(const char __user *filename, struct kstat *stat) +{ + return vfs_fstatat(AT_FDCWD, filename, stat, 0); +} +static inline int vfs_lstat(const char __user *name, struct kstat *stat) +{ + return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); +} + +extern const char *vfs_get_link(struct dentry *, struct delayed_call *); +extern int vfs_readlink(struct dentry *, char __user *, int); + +extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); -extern struct super_block *get_super(struct block_device *); -extern struct super_block *get_super_thawed(struct block_device *); -extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); -extern void iterate_supers(void (*)(struct super_block *, void *), void *); +extern void drop_super_exclusive(struct super_block *sb); +extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); +void filesystems_freeze(bool freeze_all); +void filesystems_thaw(void); + +void end_dirop(struct dentry *de); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); -extern int simple_setattr(struct dentry *, struct iattr *); -extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); +extern int simple_setattr(struct mnt_idmap *, struct dentry *, + struct iattr *); +extern int simple_getattr(struct mnt_idmap *, const struct path *, + struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); -extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); +extern void __simple_unlink(struct inode *, struct dentry *); +extern void __simple_rmdir(struct inode *, struct dentry *); +void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); +extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); +extern int simple_rename(struct mnt_idmap *, struct inode *, + struct dentry *, struct inode *, struct dentry *, + unsigned int); +extern void simple_recursive_removal(struct dentry *, + void (*callback)(struct dentry *)); +extern void simple_remove_by_name(struct dentry *, const char *, + void (*callback)(struct dentry *)); +extern void locked_recursive_removal(struct dentry *, + void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); +extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_readpage(struct file *file, struct page *page); -extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); -extern int simple_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); +extern int simple_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata); +extern const struct address_space_operations ram_aops; +extern int always_delete_dentry(const struct dentry *); +extern struct inode *alloc_anon_inode(struct super_block *); +struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, + const struct inode *context_inode); +extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; -struct tree_descr { char *name; const struct file_operations *ops; int mode; }; +extern void make_empty_dir_inode(struct inode *inode); +extern bool is_empty_dir_inode(struct inode *inode); +struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); -extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *); +extern int simple_fill_super(struct super_block *, unsigned long, + const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); +struct dentry *simple_start_creating(struct dentry *, const char *); +void simple_done_creating(struct dentry *); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); +struct offset_ctx { + struct maple_tree mt; + unsigned long next_offset; +}; + +void simple_offset_init(struct offset_ctx *octx); +int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); +void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); +int simple_offset_rename_exchange(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry); +void simple_offset_destroy(struct offset_ctx *octx); + +extern const struct file_operations simple_offset_dir_operations; + +extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -#ifdef CONFIG_MIGRATION -extern int buffer_migrate_page(struct address_space *, - struct page *, struct page *, - enum migrate_mode); +extern void generic_set_sb_d_ops(struct super_block *sb); +extern int generic_ci_match(const struct inode *parent, + const struct qstr *name, + const struct qstr *folded_name, + const u8 *de_name, u32 de_name_len); + +#if IS_ENABLED(CONFIG_UNICODE) +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); +int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name); + +/** + * generic_ci_validate_strict_name - Check if a given name is suitable + * for a directory + * + * This functions checks if the proposed filename is valid for the + * parent directory. That means that only valid UTF-8 filenames will be + * accepted for casefold directories from filesystems created with the + * strict encoding flag. That also means that any name will be + * accepted for directories that doesn't have casefold enabled, or + * aren't being strict with the encoding. + * + * @dir: inode of the directory where the new file will be created + * @name: name of the new file + * + * Return: + * * True: if the filename is suitable for this directory. It can be + * true if a given name is not suitable for a strict encoding + * directory, but the directory being used isn't strict + * * False if the filename isn't suitable for this directory. This only + * happens when a directory is casefolded and the filesystem is strict + * about its encoding. + */ +static inline bool generic_ci_validate_strict_name(struct inode *dir, + const struct qstr *name) +{ + if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) + return true; + + /* + * A casefold dir must have a encoding set, unless the filesystem + * is corrupted + */ + if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) + return true; + + return !utf8_validate(dir->i_sb->s_encoding, name); +} #else -#define buffer_migrate_page NULL +static inline bool generic_ci_validate_strict_name(struct inode *dir, + const struct qstr *name) +{ + return true; +} #endif -extern int inode_change_ok(const struct inode *, struct iattr *); +int may_setattr(struct mnt_idmap *idmap, struct inode *inode, + unsigned int ia_valid); +int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern void setattr_copy(struct inode *inode, const struct iattr *attr); +void setattr_copy(struct mnt_idmap *, struct inode *inode, + const struct iattr *attr); extern int file_update_time(struct file *file); -extern int generic_show_options(struct seq_file *m, struct dentry *root); -extern void save_mount_options(struct super_block *sb, char *options); -extern void replace_mount_options(struct super_block *sb, char *options); +static inline bool file_is_dax(const struct file *file) +{ + return file && IS_DAX(file->f_mapping->host); +} -static inline ino_t parent_ino(struct dentry *dentry) +static inline bool vma_is_dax(const struct vm_area_struct *vma) { - ino_t res; + return file_is_dax(vma->vm_file); +} - /* - * Don't strictly need d_lock here? If the parent ino could change - * then surely we'd have a deeper race in the caller? - */ - spin_lock(&dentry->d_lock); - res = dentry->d_parent->d_inode->i_ino; - spin_unlock(&dentry->d_lock); +static inline bool vma_is_fsdax(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) + return false; + if (!vma_is_dax(vma)) + return false; + inode = file_inode(vma->vm_file); + if (S_ISCHR(inode->i_mode)) + return false; /* device-dax */ + return true; +} + +static inline int iocb_flags(struct file *file) +{ + int res = 0; + if (file->f_flags & O_APPEND) + res |= IOCB_APPEND; + if (file->f_flags & O_DIRECT) + res |= IOCB_DIRECT; + if (file->f_flags & O_DSYNC) + res |= IOCB_DSYNC; + if (file->f_flags & __O_SYNC) + res |= IOCB_SYNC; return res; } +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) +{ + int kiocb_flags = 0; + + /* make sure there's no overlap between RWF and private IOCB flags */ + BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); + + if (!flags) + return 0; + if (unlikely(flags & ~RWF_SUPPORTED)) + return -EOPNOTSUPP; + if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) + return -EINVAL; + + if (flags & RWF_NOWAIT) { + if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) + return -EOPNOTSUPP; + } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } + if (flags & RWF_DONTCACHE) { + /* file system must support it */ + if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) + return -EOPNOTSUPP; + /* DAX mappings not supported */ + if (IS_DAX(ki->ki_filp->f_mapping->host)) + return -EOPNOTSUPP; + } + kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); + if (flags & RWF_SYNC) + kiocb_flags |= IOCB_DSYNC; + + if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { + if (IS_APPEND(file_inode(ki->ki_filp))) + return -EPERM; + ki->ki_flags &= ~IOCB_APPEND; + } + + ki->ki_flags |= kiocb_flags; + return 0; +} + /* Transaction based IO helpers */ /* @@ -2617,7 +3420,7 @@ static inline ino_t parent_ino(struct dentry *dentry) */ struct simple_transaction_argresp { ssize_t size; - char data[0]; + char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) @@ -2646,7 +3449,7 @@ void simple_transaction_set(struct file *file, size_t n); * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ -#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ +#define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ @@ -2657,9 +3460,15 @@ static const struct file_operations __fops = { \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ - .write = simple_attr_write, \ + .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ -}; +} + +#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ + DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) + +#define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ + DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) @@ -2675,49 +3484,57 @@ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); +ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_dentry(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_inodes(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -int __init get_filesystem_list(char *buf); +int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) -#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) -#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & __FMODE_NONOTIFY))) +#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) + +static inline bool is_sxid(umode_t mode) +{ + return mode & (S_ISUID | S_ISGID); +} -static inline int is_sxid(umode_t mode) +static inline int check_sticky(struct mnt_idmap *idmap, + struct inode *dir, struct inode *inode) { - return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); + if (!(dir->i_mode & S_ISVTX)) + return 0; + + return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { - if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) + if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } +static inline bool is_root_inode(struct inode *inode) +{ + return inode == inode->i_sb->s_root->d_inode; +} + static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { - return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0; + return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, - file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0; + file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, - parent_ino(file->f_path.dentry), DT_DIR) == 0; + d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { @@ -2735,9 +3552,58 @@ static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) } static inline bool dir_relax(struct inode *inode) { - mutex_unlock(&inode->i_mutex); - mutex_lock(&inode->i_mutex); + inode_unlock(inode); + inode_lock(inode); + return !IS_DEADDIR(inode); +} + +static inline bool dir_relax_shared(struct inode *inode) +{ + inode_unlock_shared(inode); + inode_lock_shared(inode); return !IS_DEADDIR(inode); } +extern bool path_noexec(const struct path *path); +extern void inode_nohighmem(struct inode *inode); + +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); +extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + +static inline bool vfs_empty_path(int dfd, const char __user *path) +{ + char c; + + if (dfd < 0) + return false; + + /* We now allow NULL to be used for empty path. */ + if (!path) + return true; + + if (unlikely(get_user(c, path))) + return false; + + return !c; +} + +int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); + +static inline bool extensible_ioctl_valid(unsigned int cmd_a, + unsigned int cmd_b, size_t min_size) +{ + if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b)) + return false; + if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b)) + return false; + if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b)) + return false; + if (_IOC_SIZE(cmd_a) < min_size) + return false; + return true; +} + #endif /* _LINUX_FS_H */ |