diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 2491 |
1 files changed, 1242 insertions, 1249 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index c1769a2c5d70..04ceeca12a0d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,8 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/fs/super.h> +#include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> @@ -10,7 +12,6 @@ #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> -#include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> @@ -36,22 +37,23 @@ #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> -#include <linux/fs_types.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 backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; -struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; @@ -65,16 +67,13 @@ struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; -struct workqueue_struct; struct iov_iter; -struct fscrypt_info; -struct fscrypt_operations; -struct fsverity_info; -struct fsverity_operations; +struct fsnotify_mark_connector; struct fs_context; struct fs_parameter_spec; -struct fileattr; +struct file_kattr; struct iomap_ops; +struct delegated_inode; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -108,28 +107,28 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ /* 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. @@ -137,52 +136,85 @@ typedef int (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/mem): 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)0x8000) +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ -#define FMODE_WRITER ((__force fmode_t)0x10000) +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ -#define FMODE_CAN_READ ((__force fmode_t)0x20000) +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ -#define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) -#define FMODE_OPENED ((__force fmode_t)0x80000) -#define FMODE_CREATED ((__force fmode_t)0x100000) +#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)0x200000) +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ -#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) + +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) + +/* File is embedded in backing_file object */ +#define FMODE_BACKING ((__force fmode_t)(1 << 24)) + +/* + * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) -/* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +/* + * 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)0x8000000) +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ -#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ -#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) - -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) +/* + * 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 @@ -198,6 +230,7 @@ typedef int (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_CTIME_SET (1 << 10) #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) @@ -205,6 +238,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #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 @@ -259,11 +293,6 @@ struct iattr { }; /* - * Includes for diskquotas. - */ -#include <linux/quota.h> - -/* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ @@ -308,25 +337,15 @@ struct address_space; struct writeback_control; struct readahead_control; -/* - * Write life time hint values. - * Stored in struct inode as u8. - */ -enum rw_hint { - WRITE_LIFE_NOT_SET = 0, - WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, - WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, - WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, - WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, - WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, -}; - /* 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) @@ -337,6 +356,27 @@ enum rw_hint { #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; @@ -345,7 +385,14 @@ struct kiocb { void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ - struct wait_page_queue *ki_waitq; /* for async buffered IO */ + u8 ki_write_stream; + + /* + * 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; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -354,7 +401,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) } struct address_space_operations { - int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ @@ -365,12 +411,12 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); - int (*write_begin)(struct file *, struct address_space *mapping, + int (*write_begin)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); - int (*write_end)(struct file *, struct address_space *mapping, + 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); @@ -388,7 +434,7 @@ struct address_space_operations { 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_page)(struct address_space *, struct page *); + int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, @@ -408,7 +454,7 @@ extern const struct address_space_operations empty_aops; * 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 mappings. + * @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. @@ -417,9 +463,9 @@ extern const struct address_space_operations empty_aops; * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. - * @private_lock: For use by the owner of the address_space. - * @private_list: For use by the owner of the address_space. - * @private_data: For use by the owner of the address_space. + * @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. */ struct address_space { struct inode *host; @@ -432,20 +478,20 @@ struct address_space { atomic_t nr_thps; #endif struct rb_root_cached i_mmap; - struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; - spinlock_t private_lock; - struct list_head private_list; - void *private_data; + 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. + * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ @@ -456,7 +502,7 @@ struct address_space { /* * Returns true if any of the pages in the mapping are marked with the tag. */ -static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } @@ -504,21 +550,21 @@ static inline void i_mmap_assert_write_locked(struct address_space *mapping) /* * 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.rb_root); } /* * Might pages of this file have been modified in userspace? - * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap + * 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 atomic_read(&mapping->i_mmap_writable) > 0; } @@ -577,13 +623,139 @@ 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_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 -struct fsnotify_mark_connector; +/* + * 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 @@ -593,14 +765,13 @@ struct fsnotify_mark_connector; 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; @@ -625,13 +796,17 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec64 i_atime; - struct timespec64 i_mtime; - struct timespec64 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; u8 i_blkbits; - u8 i_write_hint; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -639,7 +814,8 @@ struct inode { #endif /* Misc */ - unsigned long i_state; + struct inode_state_flags i_state; + /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ @@ -676,7 +852,10 @@ struct inode { }; struct file_lock_context *i_flctx; struct address_space i_data; - struct list_head i_devices; + union { + struct list_head i_devices; + int i_linklen; + }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; @@ -684,24 +863,114 @@ struct inode { unsigned i_dir_seq; }; - __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ + /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif -#ifdef CONFIG_FS_ENCRYPTION - struct fscrypt_info *i_crypt_info; -#endif - -#ifdef CONFIG_FS_VERITY - struct fsverity_info *i_verity_info; -#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) @@ -725,8 +994,10 @@ 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_mutex nesting subclasses for the lock validator: + * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent @@ -756,6 +1027,11 @@ 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); @@ -766,6 +1042,11 @@ 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); @@ -861,13 +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) @@ -883,7 +1165,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) 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 } @@ -898,6 +1185,7 @@ static inline unsigned imajor(const 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 */ @@ -913,6 +1201,7 @@ struct fown_struct { * 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. * @@ -924,7 +1213,8 @@ struct file_ra_state { unsigned int size; unsigned int async_size; unsigned int ra_pages; - unsigned int mmap_miss; + unsigned short order; + unsigned short mmap_miss; loff_t prev_pos; }; @@ -937,44 +1227,74 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } +/** + * 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 { + spinlock_t f_lock; + fmode_t f_mode; + const struct file_operations *f_op; + 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 { - struct llist_node f_llist; - struct rcu_head f_rcuhead; - unsigned int f_iocb_flags; + const struct path f_path; + struct path __f_path; }; - struct path f_path; - struct inode *f_inode; /* cached value */ - const struct file_operations *f_op; - - /* - * Protects f_ep, f_flags. - * Must not be taken from IRQ context. - */ - spinlock_t f_lock; - atomic_long_t f_count; - unsigned int f_flags; - fmode_t f_mode; - struct mutex f_pos_lock; - loff_t f_pos; - struct fown_struct f_owner; - const struct cred *f_cred; - struct file_ra_state f_ra; - - u64 f_version; + 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 hlist_head *f_ep; -#endif /* #ifdef CONFIG_EPOLL */ - struct address_space *f_mapping; - errseq_t f_wb_err; - errseq_t f_sb_err; /* for syncfs */ + 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 */ @@ -982,16 +1302,19 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[]; + 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 get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) -#define file_count(x) atomic_long_read(&(x)->f_count) + +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) @@ -1003,134 +1326,11 @@ static inline struct file *get_file(struct file *f) #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif -#define FL_POSIX 1 -#define FL_FLOCK 2 -#define FL_DELEG 4 /* NFSv4 delegation */ -#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 */ -#define FL_OFDLCK 1024 /* lock is "owned" by struct file */ -#define FL_LAYOUT 2048 /* outstanding pNFS layout */ -#define FL_RECLAIM 4096 /* reclaiming from a reboot server */ - -#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) - -/* - * Special return value from posix_lock_file() and vfs_lock_file() for - * asynchronous locking. - */ -#define FILE_LOCK_DEFERRED 1 - /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; - -struct file_lock_operations { - void (*fl_copy_lock)(struct file_lock *, struct file_lock *); - void (*fl_release_private)(struct file_lock *); -}; - -struct lock_manager_operations { - void *lm_mod_owner; - fl_owner_t (*lm_get_owner)(fl_owner_t); - void (*lm_put_owner)(fl_owner_t); - void (*lm_notify)(struct file_lock *); /* unblock callback */ - int (*lm_grant)(struct file_lock *, int); - bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock *, int, struct list_head *); - void (*lm_setup)(struct file_lock *, void **); - bool (*lm_breaker_owns_lease)(struct file_lock *); - bool (*lm_lock_expirable)(struct file_lock *cfl); - void (*lm_expire_lock)(void); -}; - -struct lock_manager { - struct list_head list; - /* - * NFSv4 and up also want opens blocked during the grace period; - * NLM doesn't care: - */ - bool block_opens; -}; - -struct net; -void locks_start_grace(struct net *, struct lock_manager *); -void locks_end_grace(struct lock_manager *); -bool locks_in_grace(struct net *); -bool opens_in_grace(struct net *); - -/* that will die - we need it for nfs_lock_info */ -#include <linux/nfs_fs_i.h> - -/* - * 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 varous i_flctx lists are ordered by: - * - * 1) lock owner - * 2) lock range start - * 3) lock range end - * - * Obviously, the last two criteria only matter for POSIX locks. - */ -struct file_lock { - struct file_lock *fl_blocker; /* The lock, that is blocking us */ - struct list_head fl_list; /* link into file_lock_context */ - struct hlist_node fl_link; /* node in global lists */ - struct list_head fl_blocked_requests; /* list of requests with - * ->fl_blocker pointing here - */ - struct list_head fl_blocked_member; /* node in - * ->fl_blocker->fl_blocked_requests - */ - 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? */ - 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 */ - unsigned int debug_id; - } afs; - struct { - struct inode *inode; - } ceph; - } fl_u; -} __randomize_layout; - -struct file_lock_context { - spinlock_t flc_lock; - struct list_head flc_flock; - struct list_head flc_posix; - struct list_head flc_lease; -}; +struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX @@ -1138,231 +1338,33 @@ struct file_lock_context { #define OFFT_OFFSET_MAX type_max(off_t) #endif -extern void send_sigio(struct fown_struct *fown, int fd, int band); - -#define locks_inode(f) file_inode(f) - -#ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, unsigned int, struct flock *); -extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock *); - -#if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); -extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 *); -#endif - -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_context(struct inode *inode); -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_conflock(struct file_lock *, struct file_lock *); -extern void locks_remove_posix(struct file *, fl_owner_t); -extern void locks_remove_file(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 locks_delete_block(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); -bool vfs_inode_has_locks(struct inode *inode); -extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); -extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); -extern void lease_get_mtime(struct inode *, struct timespec64 *time); -extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); -extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock *, int, struct list_head *); - -struct notifier_block; -extern int lease_register_notifier(struct notifier_block *); -extern void lease_unregister_notifier(struct notifier_block *); - -struct files_struct; -extern void show_fd_locks(struct seq_file *f, - struct file *filp, struct files_struct *files); -extern bool locks_owner_has_blockers(struct file_lock_context *flctx, - fl_owner_t owner); - -static inline struct file_lock_context * -locks_inode_context(const struct inode *inode) -{ - return smp_load_acquire(&inode->i_flctx); -} - -#else /* !CONFIG_FILE_LOCKING */ -static inline int fcntl_getlk(struct file *file, unsigned int cmd, - struct flock __user *user) -{ - return -EINVAL; -} - -static inline int fcntl_setlk(unsigned int fd, struct file *file, - unsigned int cmd, struct flock __user *user) -{ - return -EACCES; -} - -#if BITS_PER_LONG == 32 -static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 *user) -{ - return -EINVAL; -} - -static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 *user) -{ - return -EACCES; -} -#endif -static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) -{ - return -EINVAL; -} - -static inline int fcntl_getlease(struct file *filp) -{ - return F_UNLCK; -} - -static inline void -locks_free_lock_context(struct inode *inode) -{ -} - -static inline void locks_init_lock(struct file_lock *fl) -{ - return; -} - -static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) -{ - return; -} - -static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) -{ - return; -} - -static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) -{ - return; -} - -static inline void locks_remove_file(struct file *filp) -{ - return; -} - -static inline void posix_test_lock(struct file *filp, struct file_lock *fl) -{ - return; -} - -static inline int posix_lock_file(struct file *filp, struct file_lock *fl, - struct file_lock *conflock) -{ - return -ENOLCK; -} - -static inline int locks_delete_block(struct file_lock *waiter) -{ - return -ENOENT; -} - -static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) -{ - return 0; -} - -static inline int vfs_lock_file(struct file *filp, unsigned int cmd, - struct file_lock *fl, struct file_lock *conf) -{ - return -ENOLCK; -} - -static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) -{ - return 0; -} - -static inline bool vfs_inode_has_locks(struct inode *inode) -{ - return false; -} - -static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) -{ - return -ENOLCK; -} - -static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) -{ - return 0; -} - -static inline void lease_get_mtime(struct inode *inode, - struct timespec64 *time) -{ - return; -} - -static inline int generic_setlease(struct file *filp, long arg, - struct file_lock **flp, void **priv) -{ - return -EINVAL; -} - -static inline int vfs_setlease(struct file *filp, long arg, - struct file_lock **lease, void **priv) -{ - return -EINVAL; -} - -static inline int lease_modify(struct file_lock *fl, int arg, - struct list_head *dispose) +int file_f_owner_allocate(struct file *file); +static inline struct fown_struct *file_f_owner(const struct file *file) { - return -EINVAL; + return READ_ONCE(file->f_owner); } -struct files_struct; -static inline void show_fd_locks(struct seq_file *f, - struct file *filp, struct files_struct *files) {} -static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, - fl_owner_t owner) -{ - return false; -} - -static inline struct file_lock_context * -locks_inode_context(const struct inode *inode) -{ - return NULL; -} - -#endif /* !CONFIG_FILE_LOCKING */ +extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } +/* + * 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) { - return d_real(file->f_path.dentry, file_inode(file)); -} + struct dentry *dentry = file->f_path.dentry; -static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -{ - return locks_lock_inode_wait(locks_inode(filp), fl); + WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); + return dentry; } struct fasync_struct { @@ -1387,44 +1389,10 @@ extern void fasync_free(struct fasync_struct *); extern void kill_fasync(struct fasync_struct **, int, int); extern void __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 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 fown_struct *fown); - -/* - * sb->s_flags. Note that these mirror the equivalent MS_* flags where - * represented in both. - */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) - -/* These flags relate to encoding and casefolding */ -#define SB_ENC_STRICT_MODE_FL (1 << 0) - -#define sb_has_strict_encoding(sb) \ - (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) +extern int send_sigurg(struct file *file); /* * Umount options @@ -1436,174 +1404,6 @@ extern int send_sigurg(struct fown_struct *fown); #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -/* sb->s_iflags */ -#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ -#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ -#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ -#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ - -/* sb->s_iflags to limit user namespace mounts */ -#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 -#define SB_I_UNTRUSTED_MOUNTER 0x00000040 - -#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ -#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ -#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ -#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ - -/* 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 { - int frozen; /* Is sb frozen? */ - wait_queue_head_t wait_unfrozen; /* wait for thaw */ - struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; -}; - -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_iflags; /* internal SB_I_* 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; -#ifdef CONFIG_FS_ENCRYPTION - const struct fscrypt_operations *s_cop; - struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ -#endif -#ifdef CONFIG_FS_VERITY - const struct fsverity_operations *s_vop; -#endif -#if IS_ENABLED(CONFIG_UNICODE) - struct unicode_map *s_encoding; - __u16 s_encoding_flags; -#endif - struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ - struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - struct block_device *s_bdev; - struct backing_dev_info *s_bdi; - struct mtd_info *s_mtd; - struct hlist_node s_instances; - unsigned int s_quota_types; /* Bitmask of supported quota types */ - struct quota_info s_dquot; /* Diskquota specific options */ - - struct sb_writers s_writers; - - /* - * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and - * s_fsnotify_marks together for cache efficiency. They are frequently - * accessed and rarely modified. - */ - void *s_fs_info; /* Filesystem private info */ - - /* Granularity of c/m/atime in ns (cannot be worse than a second) */ - u32 s_time_gran; - /* Time limits for c/m/atime in seconds */ - time64_t s_time_min; - time64_t s_time_max; -#ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; -#endif - - char s_id[32]; /* Informational name */ - uuid_t s_uuid; /* UUID */ - - unsigned int s_max_links; - fmode_t s_mode; - - /* - * 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" - */ - const char *s_subtype; - - const struct dentry_operations *s_d_op; /* default d_op for dentries */ - - struct shrinker s_shrink; /* per-sb shrinker handle */ - - /* Number of inodes with nlink == 0 but still referenced */ - atomic_long_t s_remove_count; - - /* - * Number of inode/mount/sb objects that are being watched, note that - * inodes objects are currently double-accounted. - */ - atomic_long_t s_fsnotify_connectors; - - /* Being remounted read-only */ - int s_readonly_remount; - - /* per-sb errseq_t for reporting writeback errors via syncfs */ - errseq_t s_wb_err; - - /* AIO completions deferred from interrupt context */ - struct workqueue_struct *s_dio_done_wq; - struct hlist_head s_pins; - - /* - * Owning user namespace and default context in which to - * interpret filesystem uids, gids, quotas, device nodes, - * xattrs and security labels. - */ - struct user_namespace *s_user_ns; - - /* - * The list_lru structure is essentially just a pointer to a table - * of per-node lru lists, each of which has its own spinlock. - * There is no need to put them into separate cachelines. - */ - struct list_lru s_dentry_lru; - struct list_lru s_inode_lru; - struct rcu_head rcu; - struct work_struct destroy_work; - - struct mutex s_sync_lock; /* sync serialisation lock */ - - /* - * Indicates how deep in a filesystem stack this SB is - */ - int s_stack_depth; - - /* s_inode_list_lock protects s_inodes */ - spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; - struct list_head s_inodes; /* all inodes */ - - spinlock_t s_inode_wblist_lock; - struct list_head s_inodes_wb; /* writeback inodes */ -} __randomize_layout; - static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; @@ -1635,22 +1435,22 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) } /** - * i_uid_into_vfsuid - map an inode's i_uid down into a mnt_userns - * @mnt_userns: user namespace of the mount the inode was found from + * 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 @mnt_userns. + * 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 user_namespace *mnt_userns, +static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { - return make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid); + return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * @@ -1659,50 +1459,50 @@ static inline vfsuid_t i_uid_into_vfsuid(struct user_namespace *mnt_userns, * * Return: true if @inode's i_uid field needs to be updated, false if not. */ -static inline bool i_uid_needs_update(struct user_namespace *mnt_userns, +static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, - i_uid_into_vfsuid(mnt_userns, inode))); + i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field - * @mnt_userns: user namespace of the mount the inode was found from + * @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 user_namespace *mnt_userns, +static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) - inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode), + inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** - * i_gid_into_vfsgid - map an inode's i_gid down into a mnt_userns - * @mnt_userns: user namespace of the mount the inode was found from + * 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 @mnt_userns. + * 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 user_namespace *mnt_userns, +static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { - return make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid); + return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated - * @mnt_userns: user namespace of the mount the inode was found from + * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * @@ -1711,290 +1511,302 @@ static inline vfsgid_t i_gid_into_vfsgid(struct user_namespace *mnt_userns, * * Return: true if @inode's i_gid field needs to be updated, false if not. */ -static inline bool i_gid_needs_update(struct user_namespace *mnt_userns, +static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, - i_gid_into_vfsgid(mnt_userns, inode))); + i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field - * @mnt_userns: user namespace of the mount the inode was found from + * @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 user_namespace *mnt_userns, +static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) - inode->i_gid = from_vfsgid(mnt_userns, i_user_ns(inode), + inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize - * @mnt_userns: user namespace of the mount the inode was found from + * @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 @mnt_users. + * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { - inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); + inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize - * @mnt_userns: user namespace of the mount the inode was found from + * @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 @mnt_users. + * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, - struct user_namespace *mnt_userns) + struct mnt_idmap *idmap) { - inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); + inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in - * @mnt_userns: user namespace of the relevant mount + * @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 @mnt_userns first. + * 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 user_namespace *mnt_userns) + struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; - kuid = mapped_fsuid(mnt_userns, fs_userns); + kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns, fs_userns); + 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); } -extern struct timespec64 current_time(struct inode *inode); +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); -/* - * Snapshotting support. - */ +static inline time64_t inode_get_atime_sec(const struct inode *inode) +{ + return inode->i_atime_sec; +} -/* - * These are internal functions, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -static inline void __sb_end_write(struct super_block *sb, int level) +static inline long inode_get_atime_nsec(const struct inode *inode) { - percpu_up_read(sb->s_writers.rw_sem + level-1); + return inode->i_atime_nsec; } -static inline void __sb_start_write(struct super_block *sb, int level) +static inline struct timespec64 inode_get_atime(const struct inode *inode) { - percpu_down_read(sb->s_writers.rw_sem + level - 1); + struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), + .tv_nsec = inode_get_atime_nsec(inode) }; + + return ts; } -static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, + struct timespec64 ts) { - return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); + inode->i_atime_sec = ts.tv_sec; + inode->i_atime_nsec = ts.tv_nsec; + return ts; } -#define __sb_writers_acquired(sb, lev) \ - percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) -#define __sb_writers_release(sb, lev) \ - percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +static inline struct timespec64 inode_set_atime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; -static inline bool sb_write_started(const struct super_block *sb) + return inode_set_atime_to_ts(inode, ts); +} + +static inline time64_t inode_get_mtime_sec(const struct inode *inode) { - return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); + return inode->i_mtime_sec; } -/** - * sb_end_write - drop write access to a superblock - * @sb: the super we wrote to - * - * Decrement number of writers to the filesystem. Wake up possible waiters - * wanting to freeze the filesystem. - */ -static inline void sb_end_write(struct super_block *sb) +static inline long inode_get_mtime_nsec(const struct inode *inode) { - __sb_end_write(sb, SB_FREEZE_WRITE); + return inode->i_mtime_nsec; } -/** - * sb_end_pagefault - drop write access to a superblock from a page fault - * @sb: the super we wrote to - * - * Decrement number of processes handling write page fault to the filesystem. - * Wake up possible waiters wanting to freeze the filesystem. - */ -static inline void sb_end_pagefault(struct super_block *sb) +static inline struct timespec64 inode_get_mtime(const struct inode *inode) { - __sb_end_write(sb, SB_FREEZE_PAGEFAULT); + struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), + .tv_nsec = inode_get_mtime_nsec(inode) }; + return ts; } -/** - * 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. - */ -static inline void sb_end_intwrite(struct super_block *sb) +static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, + struct timespec64 ts) { - __sb_end_write(sb, SB_FREEZE_FS); + inode->i_mtime_sec = ts.tv_sec; + inode->i_mtime_nsec = ts.tv_nsec; + return ts; } -/** - * 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: +static inline struct timespec64 inode_set_mtime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + return inode_set_mtime_to_ts(inode, ts); +} + +/* + * Multigrain timestamps * - * sb_start_write - * -> i_mutex (write path, truncate, directory ops, ...) - * -> s_umount (freeze_super, thaw_super) + * 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. */ -static inline void sb_start_write(struct super_block *sb) +#define I_CTIME_QUERIED ((u32)BIT(31)) + +static inline time64_t inode_get_ctime_sec(const struct inode *inode) +{ + return inode->i_ctime_sec; +} + +static inline long inode_get_ctime_nsec(const struct inode *inode) { - __sb_start_write(sb, SB_FREEZE_WRITE); + return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } -static inline bool sb_start_write_trylock(struct super_block *sb) +static inline struct timespec64 inode_get_ctime(const struct inode *inode) { - return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); + struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), + .tv_nsec = inode_get_ctime_nsec(inode) }; + + return ts; } +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); + /** - * 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_lock in lock ordering. Page fault - * handling code implies lock dependency: + * 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 * - * mmap_lock - * -> sb_start_pagefault + * Set the ctime in @inode to { @sec, @nsec } */ -static inline void sb_start_pagefault(struct super_block *sb) +static inline struct timespec64 inode_set_ctime(struct inode *inode, + time64_t sec, long nsec) { - __sb_start_write(sb, SB_FREEZE_PAGEFAULT); + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + + return inode_set_ctime_to_ts(inode, ts); } +struct timespec64 simple_inode_init_ts(struct inode *inode); + +/* + * Snapshotting support. + */ + /** - * 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. + * file_write_started - check if SB_FREEZE_WRITE is held + * @file: the file we write to * - * 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.). + * 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_start_intwrite(struct super_block *sb) +static inline bool file_write_started(const struct file *file) { - __sb_start_write(sb, SB_FREEZE_FS); + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return sb_write_started(file_inode(file)->i_sb); } -static inline bool sb_start_intwrite_trylock(struct super_block *sb) +/** + * file_write_not_started - check if SB_FREEZE_WRITE is not held + * @file: the file we write to + * + * 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 bool file_write_not_started(const struct file *file) { - return __sb_start_write_trylock(sb, SB_FREEZE_FS); + if (!S_ISREG(file_inode(file)->i_mode)) + return true; + return sb_write_not_started(file_inode(file)->i_sb); } -bool inode_owner_or_capable(struct user_namespace *mnt_userns, +bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ -int vfs_create(struct user_namespace *, struct inode *, - struct dentry *, umode_t, bool); -int vfs_mkdir(struct user_namespace *, struct inode *, - struct dentry *, umode_t); -int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *, - umode_t, dev_t); -int vfs_symlink(struct user_namespace *, struct inode *, - struct dentry *, const char *); -int vfs_link(struct dentry *, struct user_namespace *, struct inode *, - struct dentry *, struct inode **); -int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *); -int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *, - struct inode **); +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 *); /** * struct renamedata - contains all information required for renaming - * @old_mnt_userns: old user namespace of the mount the inode was found from - * @old_dir: parent of source + * @mnt_idmap: idmap of the mount in which the rename is happening. + * @old_parent: parent of source * @old_dentry: source - * @new_mnt_userns: new user namespace of the mount the inode was found from - * @new_dir: parent of destination + * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { - struct user_namespace *old_mnt_userns; - struct inode *old_dir; + struct mnt_idmap *mnt_idmap; + struct dentry *old_parent; struct dentry *old_dentry; - struct user_namespace *new_mnt_userns; - struct inode *new_dir; + struct dentry *new_parent; struct dentry *new_dentry; - struct inode **delegated_inode; + struct delegated_inode *delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); -static inline int vfs_whiteout(struct user_namespace *mnt_userns, +static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { - return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE, - WHITEOUT_DEV); + return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, + WHITEOUT_DEV, NULL); } -struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, - const struct path *parentpath, - umode_t mode, int open_flag, const struct cred *cred); +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 *), @@ -2004,8 +1816,6 @@ 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); -extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); - #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -2016,11 +1826,13 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, /* * VFS file helper functions. */ -void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, +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 user_namespace *mnt_userns, +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); /* * This is the "filldir" function type, used by readdir() to let @@ -2036,8 +1848,18 @@ typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, 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; }; +/* If OR-ed with d_type, pending signals are not checked */ +#define FILLDIR_FLAG_NOINTR 0x1000 + /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. @@ -2087,9 +1909,13 @@ struct dir_context { struct iov_iter; struct io_uring_cmd; +struct offset_ctx; + +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 *); @@ -2097,26 +1923,24 @@ struct file_operations { ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); - int (*iterate) (struct file *, struct dir_context *); 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 *); - unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); 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 (*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 **); + 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); void (*show_fdinfo)(struct seq_file *m, struct file *f); @@ -2132,75 +1956,113 @@ struct file_operations { 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); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct user_namespace *, struct inode *, int); + 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); - int (*create) (struct user_namespace *, struct inode *,struct dentry *, + 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 user_namespace *, struct inode *,struct dentry *, + int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *, - umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct user_namespace *, struct inode *,struct dentry *, + int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); - int (*rename) (struct user_namespace *, struct inode *, struct dentry *, + int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); - int (*setattr) (struct user_namespace *, struct dentry *, - struct iattr *); - int (*getattr) (struct user_namespace *, const struct path *, + 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 (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); - int (*update_time)(struct inode *, struct timespec64 *, int); + int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct user_namespace *, struct inode *, + int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); - struct posix_acl *(*get_acl)(struct user_namespace *, struct dentry *, + struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); - int (*set_acl)(struct user_namespace *, struct dentry *, + int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); - int (*fileattr_set)(struct user_namespace *mnt_userns, - struct dentry *dentry, struct fileattr *fa); - int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); + 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; -static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, - struct iov_iter *iter) +/* Did the driver provide valid mmap hook configuration? */ +static inline bool can_mmap_file(struct file *file) { - return file->f_op->read_iter(kio, iter); + 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; } -static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, - struct iov_iter *iter) +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) { - return file->f_op->write_iter(kio, iter); + if (file->f_op->mmap_prepare) + return compat_vma_mmap(file, vma); + + return file->f_op->mmap(file, vma); } -static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) { - return file->f_op->mmap(file, vma); + 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_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags); +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, @@ -2208,9 +2070,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, 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 do_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 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); @@ -2220,41 +2079,6 @@ 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); - -struct super_operations { - struct inode *(*alloc_inode)(struct super_block *sb); - void (*destroy_inode)(struct inode *); - void (*free_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_super) (struct super_block *); - int (*freeze_fs) (struct super_block *); - int (*thaw_super) (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); - struct dquot **(*get_dquots)(struct inode *); -#endif - long (*nr_cached_objects)(struct super_block *, - struct shrink_control *); - long (*free_cached_objects)(struct super_block *, - struct shrink_control *); -}; - /* * Inode flags - they have no relation to superblock flags now */ @@ -2280,6 +2104,7 @@ struct super_operations { #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 @@ -2296,7 +2121,6 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) @@ -2309,11 +2133,22 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #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) + +#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) @@ -2325,12 +2160,13 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #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 user_namespace *mnt_userns, +static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { - return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || - !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, 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) @@ -2353,112 +2189,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, }; } -/* - * 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_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). - * - * 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. - * - * 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_TIME (1 << 11) -#define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) -#define I_CREATING (1 << 15) -#define I_DONTCACHE (1 << 16) -#define I_SYNC_QUEUED (1 << 17) -#define I_PINNING_FSCACHE_WB (1 << 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) - extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { @@ -2470,6 +2200,11 @@ 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. @@ -2481,8 +2216,8 @@ static inline void mark_inode_dirty_sync(struct inode *inode) */ static inline bool inode_is_dirtytime_only(struct inode *inode) { - return (inode->i_state & (I_DIRTY_TIME | I_NEW | - I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; + 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); @@ -2511,7 +2246,7 @@ enum file_time_flags { extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); -int inode_update_time(struct inode *inode, struct timespec64 *time, int flags); +int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { @@ -2533,6 +2268,9 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #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; @@ -2556,21 +2294,22 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -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); @@ -2584,12 +2323,20 @@ 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); +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 @@ -2607,130 +2354,71 @@ extern int unregister_filesystem(struct file_system_type *); 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 freeze_super(struct super_block *super); -extern int thaw_super(struct super_block *super); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); -extern int current_umask(void); - -extern void ihold(struct inode * inode); -extern void iput(struct inode *); -extern int generic_update_time(struct inode *, struct timespec64 *, int); - -/* /sys/fs */ -extern struct kobject *fs_kobj; - -#define MAX_RW_COUNT (INT_MAX & PAGE_MASK) - -#ifdef CONFIG_FILE_LOCKING -static inline int break_lease(struct inode *inode, unsigned int mode) +static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { - /* - * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking i_flctx->flc_lease. Otherwise, we - * could end up racing with tasks trying to set a new lease on this - * file. - */ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, mode, FL_LEASE); - return 0; + if (WARN_ON(len > sizeof(sb->s_uuid))) + len = sizeof(sb->s_uuid); + sb->s_uuid_len = len; + memcpy(&sb->s_uuid, uuid, len); } -static inline int break_deleg(struct inode *inode, unsigned int mode) +/* set sb sysfs name based on sb->s_bdev */ +static inline void super_set_sysfs_name_bdev(struct super_block *sb) { - /* - * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking i_flctx->flc_lease. Otherwise, we - * could end up racing with tasks trying to set a new lease on this - * file. - */ - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, mode, FL_DELEG); - return 0; + snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +/* set sb sysfs name based on sb->s_uuid */ +static inline void super_set_sysfs_name_uuid(struct super_block *sb) { - int ret; - - ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); - if (ret == -EWOULDBLOCK && delegated_inode) { - *delegated_inode = inode; - ihold(inode); - } - return ret; -} - -static inline int break_deleg_wait(struct inode **delegated_inode) -{ - int ret; - - ret = break_deleg(*delegated_inode, O_WRONLY); - iput(*delegated_inode); - *delegated_inode = NULL; - return ret; + 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 break_layout(struct inode *inode, bool wait) +/* set sb sysfs name based on sb->s_id */ +static inline void super_set_sysfs_name_id(struct super_block *sb) { - smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, - wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, - FL_LAYOUT); - return 0; + strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } -#else /* !CONFIG_FILE_LOCKING */ -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, ...) { - return 0; -} - -static inline int break_deleg(struct inode *inode, unsigned int mode) -{ - return 0; -} + va_list args; -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) -{ - return 0; + va_start(args, fmt); + vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); + va_end(args); } -static inline int break_deleg_wait(struct inode **delegated_inode) -{ - BUG(); - return 0; -} +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); -static inline int break_layout(struct inode *inode, bool wait) -{ - return 0; -} +/* /sys/fs */ +extern struct kobject *fs_kobj; -#endif /* CONFIG_FILE_LOCKING */ +#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 */ - int refcnt; + atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); -static inline struct user_namespace *file_mnt_user_ns(struct file *file) -{ - return mnt_user_ns(file->f_path.mnt); -} - -static inline struct mnt_idmap *file_mnt_idmap(struct file *file) +static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } @@ -2748,13 +2436,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) return mnt_idmap(mnt) != &nop_mnt_idmap; } -extern long vfs_truncate(const struct path *, loff_t); -int do_truncate(struct user_namespace *, struct dentry *, loff_t start, +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); -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); +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 *, @@ -2765,22 +2453,69 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } -extern struct file * dentry_open(const struct path *, int, const struct cred *); -extern struct file *dentry_create(const struct path *path, int flags, - umode_t mode, const struct cred *cred); -extern struct file * open_with_fake_path(const struct path *, int, - struct inode*, const struct cred *); +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) +{ + if (unlikely(f->f_mode & FMODE_BACKING)) + return backing_file_user_path(f); + return &f->f_path; +} +/* Get the inode whose inode number to display in /proc/<pid>/maps */ +static inline const struct inode *file_user_inode(const struct file *f) +{ + if (unlikely(f->f_mode & FMODE_BACKING)) + return d_inode(backing_file_user_path(f)->dentry); + return file_inode(f); +} + static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); -extern struct filename *getname_flags(const char __user *, int, int *); +extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); -extern struct filename *getname(const char __user *); +static inline struct filename *getname(const char __user *name) +{ + 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); + + 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)) + +static inline struct filename *refname(struct filename *name) +{ + atomic_inc(&name->refcnt); + return name; +} extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); @@ -2804,12 +2539,6 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -extern struct super_block *blockdev_superblock; -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; -} - void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; @@ -2855,6 +2584,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, 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); static inline int file_write_and_wait(struct file *file) { @@ -2887,6 +2618,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) (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; @@ -2904,21 +2640,21 @@ static inline int bmap(struct inode *inode, sector_t *block) } #endif -int notify_change(struct user_namespace *, struct dentry *, - struct iattr *, struct inode **); -int inode_permission(struct user_namespace *, struct inode *, int); -int generic_permission(struct user_namespace *, 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_user_ns(file), + 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_user_ns(path->mnt), + return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } -int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, +int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) @@ -2931,6 +2667,13 @@ static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) 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)) @@ -2945,11 +2688,53 @@ static inline bool file_start_write_trylock(struct file *file) 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); } /* @@ -2991,6 +2776,34 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file_inode(file)->i_writecount); } + +/* + * 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; @@ -2999,8 +2812,7 @@ static inline bool inode_is_open_for_write(const struct inode *inode) #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) { @@ -3027,9 +2839,37 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ 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> /* needed for stackable file system support */ @@ -3037,14 +2877,19 @@ 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 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); } @@ -3052,7 +2897,7 @@ 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); @@ -3061,7 +2906,12 @@ extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); -extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); +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, @@ -3085,7 +2935,7 @@ extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* - * Userspace may rely on the the inode number being non-zero. For example, glibc + * 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 @@ -3099,25 +2949,32 @@ static inline bool is_zero_ino(ino_t ino) return (u32)ino == 0; } -extern void __iget(struct inode * inode); +static inline void __iget(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + atomic_inc(&inode->i_count); +} + 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 setattr_should_drop_suidgid(struct user_namespace *, struct inode *); +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. */ -static inline void * -alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) -{ - return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); -} +#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) @@ -3133,13 +2990,12 @@ static inline void remove_inode_hash(struct inode *inode) } extern void inode_sb_list_add(struct inode *inode); -extern void inode_add_lru(struct inode *inode); - -extern int sb_set_blocksize(struct super_block *, int); -extern int sb_min_blocksize(struct super_block *, int); +extern void inode_lru_list_add(struct inode *inode); -extern int generic_file_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +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, @@ -3152,6 +3008,8 @@ 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); @@ -3163,24 +3021,25 @@ 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); +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 long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - loff_t *opos, 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); -#define no_llseek NULL 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); @@ -3205,7 +3064,7 @@ enum { 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, dio_submit_t submit_io, + dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, @@ -3214,11 +3073,13 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); + 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_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests @@ -3242,14 +3103,9 @@ static inline void inode_dio_begin(struct inode *inode) static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) - wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); + wake_up_var(&inode->i_dio_count); } -/* - * Warn about a page cache invalidation failure diring a direct I/O write. - */ -void dio_warn_stale_pagecache(struct file *filp); - extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); @@ -3257,16 +3113,23 @@ 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 readlink_copy(char __user *, int, const char *); +extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); +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 void kfree_link(void *); -void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); +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); @@ -3304,45 +3167,57 @@ 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_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); -extern void iterate_supers(void (*)(struct super_block *, void *), void *); +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 user_namespace *, struct dentry *, +extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); -extern int simple_getattr(struct user_namespace *, const struct path *, +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 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 user_namespace *, struct inode *, +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_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct page **pagep, 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 *); -extern int simple_nosetlease(struct file *, long, struct file_lock **, void **); -extern const struct dentry_operations simple_dentry_operations; +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 *); @@ -3356,31 +3231,110 @@ 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); -extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); +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 +static inline bool generic_ci_validate_strict_name(struct inode *dir, + const struct qstr *name) +{ + return true; +} +#endif -int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, +int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); -int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); +int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -void setattr_copy(struct user_namespace *, struct inode *inode, +void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); +static inline bool file_is_dax(const struct file *file) +{ + return file && IS_DAX(file->f_mapping->host); +} + static inline bool vma_is_dax(const struct vm_area_struct *vma) { - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); + return file_is_dax(vma->vm_file); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) @@ -3411,7 +3365,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3422,34 +3377,41 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t 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; - kiocb_flags |= IOCB_NOIO; + } + 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; } -static inline ino_t parent_ino(struct dentry *dentry) -{ - ino_t res; - - /* - * 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); - return res; -} - /* Transaction based IO helpers */ /* @@ -3529,24 +3491,22 @@ struct ctl_table; 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 check_sticky(struct user_namespace *mnt_userns, +static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; - return __check_sticky(mnt_userns, dir, inode); + return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) @@ -3574,7 +3534,7 @@ static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) 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); + d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { @@ -3613,4 +3573,37 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, 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 */ |