diff options
Diffstat (limited to 'include/linux/fs.h')
-rw-r--r-- | include/linux/fs.h | 1609 |
1 files changed, 780 insertions, 829 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index abedbffe2c9e..e654435f1651 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -24,7 +24,6 @@ #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> -#include <linux/fiemap.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> @@ -40,6 +39,10 @@ #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 <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -47,7 +50,9 @@ 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; struct kiocb; @@ -68,21 +73,16 @@ struct fsverity_info; struct fsverity_operations; struct fs_context; struct fs_parameter_spec; +struct fileattr; +struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); -extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; -extern struct inodes_stat_t inodes_stat; -extern int leases_enable, lease_break_time; -extern int sysctl_protected_symlinks; -extern int sysctl_protected_hardlinks; -extern int sysctl_protected_fifos; -extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; @@ -142,7 +142,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) -/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ +/* File is huge (eg. /dev/mem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) /* File is opened with O_PATH; almost nothing can be done with it */ @@ -163,6 +163,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File supports DIRECT IO */ +#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -175,13 +178,11 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) -/* - * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector - * that indicates that they should check the contents of the iovec are - * valid, but not check the memory that the iovec elements - * points too. - */ -#define CHECK_IOVEC_ONLY -1 +/* File supports async buffered reads */ +#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) + +/* File supports async nowait buffered writes */ +#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) /* * Attribute flags. These should be or-ed together to figure out what @@ -224,8 +225,26 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, struct iattr { unsigned int ia_valid; umode_t ia_mode; - kuid_t ia_uid; - kgid_t ia_gid; + /* + * The two anonymous unions wrap structures with the same member. + * + * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which + * are a dedicated type requiring the filesystem to use the dedicated + * helpers. Other filesystem can continue to use ia_{g,u}id until they + * have been ported. + * + * They always contain the same value. In other words FS_ALLOW_IDMAP + * pass down the same value on idmapped mounts as they would on regular + * mounts. + */ + union { + kuid_t ia_uid; + vfsuid_t ia_vfsuid; + }; + union { + kgid_t ia_gid; + vfsgid_t ia_vfsgid; + }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; @@ -268,7 +287,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(). + * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -281,17 +300,13 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ -#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct - * helper code (eg buffer layer) - * to clear GFP_FS from alloc */ - /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; +struct readahead_control; /* * Write life time hint values. @@ -306,30 +321,31 @@ enum rw_hint { WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, }; -#define IOCB_EVENTFD (1 << 0) -#define IOCB_APPEND (1 << 1) -#define IOCB_DIRECT (1 << 2) -#define IOCB_HIPRI (1 << 3) -#define IOCB_DSYNC (1 << 4) -#define IOCB_SYNC (1 << 5) -#define IOCB_WRITE (1 << 6) -#define IOCB_NOWAIT (1 << 7) +/* 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 + +/* non-RWF related bits - start at 16 */ +#define IOCB_EVENTFD (1 << 16) +#define IOCB_DIRECT (1 << 17) +#define IOCB_WRITE (1 << 18) +/* iocb->ki_waitq is valid */ +#define IOCB_WAITQ (1 << 19) +#define IOCB_NOIO (1 << 20) +/* can use bio alloc cache */ +#define IOCB_ALLOC_CACHE (1 << 21) struct kiocb { struct file *ki_filp; - - /* The 'ki_filp' pointer is shared in a union for aio */ - randomized_struct_fields_start - loff_t ki_pos; - void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); + void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; - u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ - unsigned int ki_cookie; /* for ->iopoll */ - - randomized_struct_fields_end + struct wait_page_queue *ki_waitq; /* for async buffered IO */ }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -337,47 +353,20 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) return kiocb->ki_complete == NULL; } -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user *buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, - unsigned long, unsigned long); - struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty. Return true if this dirtied it */ - int (*set_page_dirty)(struct page *page); + /* Mark a folio dirty. Return true if this dirtied it */ + bool (*dirty_folio)(struct address_space *, struct folio *); - /* - * Reads in the requested pages. Unlike ->readpage(), this is - * PURELY used for read-ahead!. - */ - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); + void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -385,55 +374,45 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - void (*invalidatepage) (struct page *, unsigned int, unsigned int); - int (*releasepage) (struct page *, gfp_t); - void (*freepage)(struct page *); + void (*invalidate_folio) (struct folio *, size_t offset, size_t len); + bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* - * migrate the contents of a page to the specified target. If + * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ - int (*migratepage) (struct address_space *, - struct page *, struct page *, enum migrate_mode); - bool (*isolate_page)(struct page *, isolate_mode_t); - void (*putback_page)(struct page *); - int (*launder_page) (struct page *); - int (*is_partially_uptodate) (struct page *, unsigned long, - unsigned long); - void (*is_dirty_writeback) (struct page *, bool *, bool *); + int (*migrate_folio)(struct address_space *, struct folio *dst, + struct folio *src, enum migrate_mode); + int (*launder_folio)(struct folio *); + bool (*is_partially_uptodate) (struct folio *, size_t from, + size_t count); + void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; -/* - * pagecache_write_begin/pagecache_write_end must be used by general code - * to write into the pagecache. - */ -int pagecache_write_begin(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - -int pagecache_write_end(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); - /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. + * @invalidate_lock: Guards coherency between page cache contents and + * file offset->disk block mappings in the filesystem during invalidates. + * It is also used to block modification of page cache contents through + * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. - * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). @@ -445,6 +424,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; struct xarray i_pages; + struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -454,7 +434,6 @@ struct address_space { struct rb_root_cached i_mmap; struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; - unsigned long nrexceptional; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; @@ -468,45 +447,6 @@ struct address_space { * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ -struct request_queue; - -struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ - int bd_openers; - struct inode * bd_inode; /* will die */ - struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ - void * bd_claiming; - void * bd_holder; - int bd_holders; - bool bd_write_holder; -#ifdef CONFIG_SYSFS - struct list_head bd_holder_disks; -#endif - struct block_device * bd_contains; - unsigned bd_block_size; - u8 bd_partno; - struct hd_struct * bd_part; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - int bd_invalidated; - struct gendisk * bd_disk; - struct request_queue * bd_queue; - struct backing_dev_info *bd_bdi; - struct list_head bd_list; - /* - * Private data. You must have bd_claim'ed the block_device - * to use this. NOTE: bd_claim allows an owner to claim - * the same device multiple times, the owner must take special - * care to not mess up bd_private for that case. - */ - unsigned long bd_private; - - /* The counter of freeze processes */ - int bd_fsfreeze_count; - /* Mutex for freeze */ - struct mutex bd_fsfreeze_mutex; -} __randomize_layout; /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 @@ -526,11 +466,21 @@ static inline void i_mmap_lock_write(struct address_space *mapping) down_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_write(struct address_space *mapping) +{ + return down_write_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); @@ -541,6 +491,16 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) up_read(&mapping->i_mmap_rwsem); } +static inline void i_mmap_assert_locked(struct address_space *mapping) +{ + lockdep_assert_held(&mapping->i_mmap_rwsem); +} + +static inline void i_mmap_assert_write_locked(struct address_space *mapping) +{ + lockdep_assert_held_write(&mapping->i_mmap_rwsem); +} + /* * Might pages of this file be mapped into userspace? */ @@ -551,7 +511,7 @@ static inline int mapping_mapped(struct address_space *mapping) /* * Might pages of this file have been modified in userspace? - * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff + * Note that i_mmap_writable counts all VM_SHARED 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. * @@ -598,6 +558,11 @@ static inline void mapping_allow_writable(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +/* + * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to + * cache the ACL. This also means that ->get_acl() can be called in RCU mode + * with the LOOKUP_RCU flag. + */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * @@ -714,7 +679,6 @@ struct inode { struct list_head i_devices; union { struct pipe_inode_info *i_pipe; - struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; @@ -832,9 +796,42 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla down_read_nested(&inode->i_rwsem, subclass); } +static inline void filemap_invalidate_lock(struct address_space *mapping) +{ + down_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock(struct address_space *mapping) +{ + up_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_lock_shared(struct address_space *mapping) +{ + down_read(&mapping->invalidate_lock); +} + +static inline int filemap_invalidate_trylock_shared( + struct address_space *mapping) +{ + return down_read_trylock(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock_shared( + struct address_space *mapping) +{ + up_read(&mapping->invalidate_lock); +} + void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2); +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2); + + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic @@ -900,8 +897,6 @@ static inline unsigned imajor(const struct inode *inode) return MAJOR(inode->i_rdev); } -extern struct block_device *I_BDEV(struct inode *inode); - struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ @@ -910,18 +905,27 @@ struct fown_struct { int signum; /* posix.1b rt signal to be delivered on IO */ }; -/* - * Track a single file's readahead state +/** + * struct file_ra_state - Track a file's readahead state. + * @start: Where the most recent readahead started. + * @size: Number of pages read in the most recent readahead. + * @async_size: Numer of pages that were/are not needed immediately + * and so were/are genuinely "ahead". Start next readahead when + * the first of these pages is accessed. + * @ra_pages: Maximum size of a readahead request, copied from the bdi. + * @mmap_miss: How many mmap accesses missed in the page cache. + * @prev_pos: The last byte in the most recent read request. + * + * When this structure is passed to ->readahead(), the "most recent" + * readahead means the current readahead. */ struct file_ra_state { - pgoff_t start; /* where readahead started */ - unsigned int size; /* # of readahead pages */ - unsigned int async_size; /* do asynchronous readahead when - there are only # of pages ahead */ - - unsigned int ra_pages; /* Maximum readahead window */ - unsigned int mmap_miss; /* Cache miss stat for mmap accesses */ - loff_t prev_pos; /* Cache last read() position */ + pgoff_t start; + unsigned int size; + unsigned int async_size; + unsigned int ra_pages; + unsigned int mmap_miss; + loff_t prev_pos; }; /* @@ -935,19 +939,19 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) struct file { union { - struct llist_node fu_llist; - struct rcu_head fu_rcuhead; - } f_u; + struct llist_node f_llist; + struct rcu_head f_rcuhead; + unsigned int f_iocb_flags; + }; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; /* - * Protects f_ep_links, f_flags. + * Protects f_ep, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; - enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -966,11 +970,11 @@ struct file { #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ - struct list_head f_ep_links; - struct list_head f_tfile_llink; + 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 */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -978,7 +982,7 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) @@ -986,9 +990,7 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu_many(x, cnt) \ - atomic_long_add_unless(&(x)->f_count, (cnt), 0) -#define get_file_rcu(x) get_file_rcu_many((x), 1) +#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) @@ -1013,6 +1015,7 @@ static inline struct file *get_file(struct file *f) #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) @@ -1033,6 +1036,7 @@ struct file_lock_operations { }; 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 */ @@ -1040,6 +1044,9 @@ struct lock_manager_operations { 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 { @@ -1177,6 +1184,8 @@ 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); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1192,13 +1201,13 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file, #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 __user *user) + struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 __user *user) + unsigned int cmd, struct flock64 *user) { return -EACCES; } @@ -1312,6 +1321,11 @@ static inline int lease_modify(struct file_lock *fl, int arg, 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; +} #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) @@ -1371,6 +1385,7 @@ extern int send_sigurg(struct fown_struct *fown); #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 */ @@ -1383,6 +1398,12 @@ extern int send_sigurg(struct fown_struct *fown); #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) + /* * Umount options */ @@ -1397,13 +1418,18 @@ extern int send_sigurg(struct fown_struct *fown); #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_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ +#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 */ @@ -1418,7 +1444,7 @@ enum { struct sb_writers { int frozen; /* Is sb frozen? */ - wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */ + wait_queue_head_t wait_unfrozen; /* wait for thaw */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; @@ -1446,11 +1472,15 @@ struct super_block { const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; - struct key *s_master_keys; /* master crypto keys in use */ + 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; @@ -1499,22 +1529,23 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - /* - * Saved pool identifier for cleancache (-1 means none) - */ - int cleancache_poolid; - struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; - /* Pending fsnotify inode refs */ - atomic_long_t s_fsnotify_inode_refs; + /* + * 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; @@ -1551,6 +1582,11 @@ struct super_block { 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; +} + /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored @@ -1558,22 +1594,216 @@ struct super_block { */ static inline uid_t i_uid_read(const struct inode *inode) { - return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); + return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { - return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); + return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { - inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); + inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { - inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); + inode->i_gid = make_kgid(i_user_ns(inode), gid); +} + +/** + * i_uid_into_mnt - map an inode's i_uid down into a mnt_userns + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to map + * + * Note, this will eventually be removed completely in favor of the type-safe + * i_uid_into_vfsuid(). + * + * Return: the inode's i_uid mapped down according to @mnt_userns. + * If the inode's i_uid has no mapping INVALID_UID is returned. + */ +static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return AS_KUIDT(make_vfsuid(mnt_userns, i_user_ns(inode), inode->i_uid)); +} + +/** + * 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 + * @inode: inode to map + * + * Return: whe inode's i_uid mapped down according to @mnt_userns. + * 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, + const struct inode *inode) +{ + return make_vfsuid(mnt_userns, 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 + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Check whether the $inode's i_uid field needs to be updated taking idmapped + * mounts into account if the filesystem supports it. + * + * Return: true if @inode's i_uid field needs to be updated, false if not. + */ +static inline bool i_uid_needs_update(struct user_namespace *mnt_userns, + 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_update - update @inode's i_uid field + * @mnt_userns: user namespace 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, + const struct iattr *attr, + struct inode *inode) +{ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = from_vfsuid(mnt_userns, i_user_ns(inode), + attr->ia_vfsuid); +} + +/** + * i_gid_into_mnt - map an inode's i_gid down into a mnt_userns + * @mnt_userns: user namespace of the mount the inode was found from + * @inode: inode to map + * + * Note, this will eventually be removed completely in favor of the type-safe + * i_gid_into_vfsgid(). + * + * Return: the inode's i_gid mapped down according to @mnt_userns. + * If the inode's i_gid has no mapping INVALID_GID is returned. + */ +static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return AS_KGIDT(make_vfsgid(mnt_userns, i_user_ns(inode), inode->i_gid)); +} + +/** + * 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 + * @inode: inode to map + * + * Return: the inode's i_gid mapped down according to @mnt_userns. + * 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, + const struct inode *inode) +{ + return make_vfsgid(mnt_userns, 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 + * @attr: the new attributes of @inode + * @inode: the inode to update + * + * Check whether the $inode's i_gid field needs to be updated taking idmapped + * mounts into account if the filesystem supports it. + * + * Return: true if @inode's i_gid field needs to be updated, false if not. + */ +static inline bool i_gid_needs_update(struct user_namespace *mnt_userns, + 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_update - update @inode's i_gid field + * @mnt_userns: user namespace 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, + const struct iattr *attr, + struct inode *inode) +{ + if (attr->ia_valid & ATTR_GID) + inode->i_gid = from_vfsgid(mnt_userns, 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 + * + * 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. + */ +static inline void inode_fsuid_set(struct inode *inode, + struct user_namespace *mnt_userns) +{ + inode->i_uid = mapped_fsuid(mnt_userns, 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 + * + * 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. + */ +static inline void inode_fsgid_set(struct inode *inode, + struct user_namespace *mnt_userns) +{ + inode->i_gid = mapped_fsgid(mnt_userns, 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 + * + * 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. + * + * 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 user_namespace *fs_userns = sb->s_user_ns; + kuid_t kuid; + kgid_t kgid; + + kuid = mapped_fsuid(mnt_userns, fs_userns); + if (!uid_valid(kuid)) + return false; + kgid = mapped_fsgid(mnt_userns, 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); @@ -1582,14 +1812,35 @@ extern struct timespec64 current_time(struct inode *inode); * Snapshotting support. */ -void __sb_end_write(struct super_block *sb, int level); -int __sb_start_write(struct super_block *sb, int level, bool wait); +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level-1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read(sb->s_writers.rw_sem + level - 1); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} #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 bool sb_write_started(const struct super_block *sb) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); +} + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to @@ -1647,12 +1898,12 @@ static inline void sb_end_intwrite(struct super_block *sb) */ static inline void sb_start_write(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_WRITE, true); + __sb_start_write(sb, SB_FREEZE_WRITE); } -static inline int sb_start_write_trylock(struct super_block *sb) +static inline bool sb_start_write_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_WRITE, false); + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** @@ -1668,18 +1919,18 @@ static inline int sb_start_write_trylock(struct super_block *sb) * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault + * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * - * mmap_sem + * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } -/* +/** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * @@ -1694,37 +1945,77 @@ static inline void sb_start_pagefault(struct super_block *sb) */ static inline void sb_start_intwrite(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_FS, true); + __sb_start_write(sb, SB_FREEZE_FS); } -static inline int sb_start_intwrite_trylock(struct super_block *sb) +static inline bool sb_start_intwrite_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_FS, false); + return __sb_start_write_trylock(sb, SB_FREEZE_FS); } - -extern bool inode_owner_or_capable(const struct inode *inode); +bool inode_owner_or_capable(struct user_namespace *mnt_userns, + const struct inode *inode); /* * VFS helper functions.. */ -extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); -extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); -extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *); -extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); -extern int vfs_rmdir(struct inode *, struct dentry *); -extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); -extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); -extern int vfs_whiteout(struct inode *, struct dentry *); +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 **); + +/** + * 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 + * @old_dentry: source + * @new_mnt_userns: new user namespace of the mount the inode was found from + * @new_dir: 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 dentry *old_dentry; + struct user_namespace *new_mnt_userns; + struct inode *new_dir; + struct dentry *new_dentry; + struct inode **delegated_inode; + unsigned int flags; +} __randomize_layout; + +int vfs_rename(struct renamedata *); + +static inline int vfs_whiteout(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry) +{ + return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE, + WHITEOUT_DEV); +} -extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, - int open_flag); +struct file *vfs_tmpfile_open(struct user_namespace *mnt_userns, + const struct path *parentpath, + umode_t mode, int open_flag, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); +int vfs_fchown(struct file *file, uid_t user, gid_t group); +int vfs_fchmod(struct file *file, umode_t mode); +int vfs_utimes(const struct path *path, struct timespec64 *times); + extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT @@ -1737,31 +2028,21 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, /* * VFS file helper functions. */ -extern void inode_init_owner(struct inode *inode, const struct inode *dir, - umode_t mode); +void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, + const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); -/* - * VFS FS_IOC_FIEMAP helper definitions. - */ -struct fiemap_extent_info { - unsigned int fi_flags; /* Flags as passed from user */ - unsigned int fi_extents_mapped; /* Number of mapped extents */ - unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent __user *fi_extents_start; /* Start of - fiemap_extent array */ -}; -int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, - u64 phys, u64 len, u32 flags); -int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); +umode_t mode_strip_sgid(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. + * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; -typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, +typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { @@ -1769,14 +2050,6 @@ struct dir_context { loff_t pos; }; -struct block_device_operations; - -/* These macros are for out of kernel modules to test that - * the kernel supports the unlocked_ioctl and compat_ioctl - * fields in struct file_operations. */ -#define HAVE_COMPAT_IOCTL 1 -#define HAVE_UNLOCKED_IOCTL 1 - /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. @@ -1817,6 +2090,7 @@ struct block_device_operations; #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1825,7 +2099,8 @@ struct file_operations { ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); - int (*iopoll)(struct kiocb *kiocb, bool spin); + 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 *); @@ -1858,27 +2133,36 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); + int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, + unsigned int poll_flags); } __randomize_layout; 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 inode *, int); - struct posix_acl * (*get_acl)(struct inode *, int); + int (*permission) (struct user_namespace *, struct inode *, int); + struct posix_acl * (*get_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); - int (*create) (struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct user_namespace *, struct inode *,struct dentry *, + umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,umode_t); + int (*symlink) (struct user_namespace *, struct inode *,struct dentry *, + const char *); + int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *, + umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, + int (*mknod) (struct user_namespace *, struct inode *,struct dentry *, + umode_t,dev_t); + int (*rename) (struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*setattr) (struct user_namespace *, struct dentry *, + struct iattr *); + int (*getattr) (struct user_namespace *, 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); @@ -1886,8 +2170,13 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct inode *, struct dentry *, umode_t); - int (*set_acl)(struct inode *, struct posix_acl *, int); + int (*tmpfile) (struct user_namespace *, struct inode *, + struct file *, umode_t); + int (*set_acl)(struct user_namespace *, struct inode *, + 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); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, @@ -1907,25 +2196,20 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma) return file->f_op->mmap(file, vma); } -ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, - unsigned long nr_segs, unsigned long fast_segs, - struct iovec *fast_pointer, - struct iovec **ret_pointer); - -extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); -extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, rwf_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); -extern 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); +int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags, + const struct iomap_ops *dax_read_ops); +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, unsigned int remap_flags); extern loff_t 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); @@ -1967,7 +2251,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif - int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, @@ -1977,27 +2260,28 @@ struct super_operations { /* * Inode flags - they have no relation to superblock flags now */ -#define S_SYNC 1 /* Writes are synced at once */ -#define S_NOATIME 2 /* Do not update access times */ -#define S_APPEND 4 /* Append-only file */ -#define S_IMMUTABLE 8 /* Immutable file */ -#define S_DEAD 16 /* removed, but still open directory */ -#define S_NOQUOTA 32 /* Inode is not counted to quota */ -#define S_DIRSYNC 64 /* Directory modifications are synchronous */ -#define S_NOCMTIME 128 /* Do not update file c/mtime */ -#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ -#define S_PRIVATE 512 /* Inode is fs-internal */ -#define S_IMA 1024 /* Inode has an associated IMA struct */ -#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ -#define S_NOSEC 4096 /* no suid or xattr security attributes */ +#define S_SYNC (1 << 0) /* Writes are synced at once */ +#define S_NOATIME (1 << 1) /* Do not update access times */ +#define S_APPEND (1 << 2) /* Append-only file */ +#define S_IMMUTABLE (1 << 3) /* Immutable file */ +#define S_DEAD (1 << 4) /* removed, but still open directory */ +#define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ +#define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ +#define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ +#define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ +#define S_PRIVATE (1 << 9) /* Inode is fs-internal */ +#define S_IMA (1 << 10) /* Inode has an associated IMA struct */ +#define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ +#define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX -#define S_DAX 8192 /* Direct Access, avoiding the page cache */ +#define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else -#define S_DAX 0 /* Make all the DAX code disappear */ +#define S_DAX 0 /* Make all the DAX code disappear */ #endif -#define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ -#define S_CASEFOLD 32768 /* Casefolded file */ -#define S_VERITY 65536 /* Verity file (using fs/verity/) */ +#define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ +#define S_CASEFOLD (1 << 15) /* Casefolded file */ +#define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ +#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2044,36 +2328,18 @@ 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) -static inline bool HAS_UNMAPPED_ID(struct inode *inode) -{ - return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); -} - -static inline enum rw_hint file_write_hint(struct file *file) +static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, + struct inode *inode) { - if (file->f_write_hint != WRITE_LIFE_NOT_SET) - return file->f_write_hint; - - return file_inode(file)->i_write_hint; -} - -static inline int iocb_flags(struct file *file); - -static inline u16 ki_hint_validate(enum rw_hint hint) -{ - typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; - - if (hint <= max_hint) - return hint; - return 0; + return !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)) || + !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, - .ki_flags = iocb_flags(filp), - .ki_hint = ki_hint_validate(file_write_hint(filp)), + .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } @@ -2084,7 +2350,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, - .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; @@ -2093,8 +2358,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, /* * Inode state bits. Protected by inode->i_lock * - * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, - * I_DIRTY_DATASYNC and I_DIRTY_PAGES. + * Four bits 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 @@ -2103,12 +2368,21 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync(). i_atime is the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * 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 - * mtime has changed in it. + * 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 @@ -2151,6 +2425,14 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * 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) @@ -2168,11 +2450,12 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define __I_DIRTY_TIME_EXPIRED 12 -#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #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) @@ -2189,6 +2472,21 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +/* + * Returns true if the given inode itself only has dirty timestamps (its pages + * may still be dirty) and isn't currently being allocated or freed. + * Filesystems should call this if when writing an inode when lazytime is + * enabled, they want to opportunistically write the timestamps of other inodes + * located very nearby on-disk, e.g. in the same inode block. This returns true + * if the given inode is in need of such an opportunistic update. Requires + * i_lock, or at least later re-checking under i_lock. + */ +static inline bool inode_is_dirtytime_only(struct inode *inode) +{ + return (inode->i_state & (I_DIRTY_TIME | I_NEW | + I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; +} + extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); @@ -2215,6 +2513,8 @@ 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); + static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) @@ -2222,8 +2522,8 @@ static inline void file_accessed(struct file *file) } extern int file_modified(struct file *file); +int kiocb_modified(struct kiocb *iocb); -int sync_inode(struct inode *inode, struct writeback_control *wbc); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { @@ -2234,6 +2534,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #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_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; @@ -2251,23 +2552,15 @@ struct file_system_type { struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; + struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -#ifdef CONFIG_BLOCK 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)); -#else -static inline 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)) -{ - return ERR_PTR(-ENODEV); -} -#endif extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2275,15 +2568,9 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); 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); -#ifdef CONFIG_BLOCK void kill_block_super(struct super_block *sb); -#else -static inline void kill_block_super(struct super_block *sb) -{ - BUG(); -} -#endif void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); @@ -2319,22 +2606,11 @@ struct super_block *sget(struct file_system_type *type, extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); -extern struct vfsmount *kern_mount(struct file_system_type *); -extern void kern_unmount(struct vfsmount *mnt); -extern int may_umount_tree(struct vfsmount *); -extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char __user *, - const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(const struct path *); -extern void drop_collected_mounts(struct vfsmount *); -extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - struct vfsmount *); 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 bool our_mnt(struct vfsmount *mnt); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -2350,90 +2626,6 @@ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) -#ifdef CONFIG_MANDATORY_FILE_LOCKING -extern int locks_mandatory_locked(struct file *); -extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char); - -/* - * Candidates for mandatory locking have the setgid bit set - * but no group execute bit - an otherwise meaningless combination. - */ - -static inline int __mandatory_lock(struct inode *ino) -{ - return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; -} - -/* - * ... and these candidates should be on SB_MANDLOCK mounted fs, - * otherwise these will be advisory locks - */ - -static inline int mandatory_lock(struct inode *ino) -{ - return IS_MANDLOCK(ino) && __mandatory_lock(ino); -} - -static inline int locks_verify_locked(struct file *file) -{ - if (mandatory_lock(locks_inode(file))) - return locks_mandatory_locked(file); - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, - struct file *f, - loff_t size) -{ - if (!inode->i_flctx || !mandatory_lock(inode)) - return 0; - - if (size < inode->i_size) { - return locks_mandatory_area(inode, f, size, inode->i_size - 1, - F_WRLCK); - } else { - return locks_mandatory_area(inode, f, inode->i_size, size - 1, - F_WRLCK); - } -} - -#else /* !CONFIG_MANDATORY_FILE_LOCKING */ - -static inline int locks_mandatory_locked(struct file *file) -{ - return 0; -} - -static inline int locks_mandatory_area(struct inode *inode, struct file *filp, - loff_t start, loff_t end, unsigned char type) -{ - return 0; -} - -static inline int __mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int locks_verify_locked(struct file *file) -{ - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, struct file *filp, - size_t size) -{ - return 0; -} - -#endif /* CONFIG_MANDATORY_FILE_LOCKING */ - - #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { @@ -2535,18 +2727,45 @@ struct filename { }; 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); +} + +/** + * is_idmapped_mnt - check whether a mount is mapped + * @mnt: the mount to check + * + * If @mnt has an idmapping attached different from the + * filesystem's idmapping then @mnt is mapped. + * + * Return: true if mount is mapped, false if not. + */ +static inline bool is_idmapped_mnt(const struct vfsmount *mnt) +{ + return mnt_user_ns(mnt) != mnt->mnt_sb->s_user_ns; +} + extern long vfs_truncate(const struct path *, loff_t); -extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, - struct file *filp); +int do_truncate(struct user_namespace *, 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); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); -extern struct file *file_open_root(struct dentry *, struct vfsmount *, +extern struct file *file_open_root(const struct path *, const char *, int, umode_t); +static inline struct file *file_open_root_mnt(struct vfsmount *mnt, + const char *name, int flags, umode_t mode) +{ + return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, + name, flags, mode); +} 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 *); static inline struct file *file_clone_open(struct file *file) @@ -2556,6 +2775,7 @@ static inline struct file *file_clone_open(struct file *file) extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); +extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); @@ -2564,6 +2784,15 @@ extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); +/* Helper for the simple case when original dentry is used */ +static inline int finish_open_simple(struct file *file, int error) +{ + if (error) + return error; + + return finish_open(file, file->f_path.dentry, NULL); +} + /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); @@ -2573,97 +2802,16 @@ 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)) -#ifdef CONFIG_BLOCK -extern int register_blkdev(unsigned int, const char *); -extern void unregister_blkdev(unsigned int, const char *); -extern void bdev_unhash_inode(dev_t dev); -extern struct block_device *bdget(dev_t); -extern struct block_device *bdgrab(struct block_device *bdev); -extern void bd_set_size(struct block_device *, loff_t size); -extern void bd_forget(struct inode *inode); -extern void bdput(struct block_device *); -extern void invalidate_bdev(struct block_device *); -extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); -extern int sync_blockdev(struct block_device *bdev); -extern void kill_bdev(struct block_device *); -extern struct super_block *freeze_bdev(struct block_device *); -extern void emergency_thaw_all(void); -extern void emergency_thaw_bdev(struct super_block *sb); -extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); -extern int fsync_bdev(struct block_device *); - extern struct super_block *blockdev_superblock; - static inline bool sb_is_blkdev_sb(struct super_block *sb) { - return sb == blockdev_superblock; -} -#else -static inline void bd_forget(struct inode *inode) {} -static inline int sync_blockdev(struct block_device *bdev) { return 0; } -static inline void kill_bdev(struct block_device *bdev) {} -static inline void invalidate_bdev(struct block_device *bdev) {} - -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; -} - -static inline int emergency_thaw_bdev(struct super_block *sb) -{ - return 0; + return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) -{ -} - -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return false; -} -#endif +void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -#ifdef CONFIG_BLOCK -extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); -extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, - void *holder); -extern struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder); -extern void bd_finish_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); -extern void bd_abort_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); -extern void blkdev_put(struct block_device *bdev, fmode_t mode); - -#ifdef CONFIG_SYSFS -extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -extern void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -#endif -#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 @@ -2694,75 +2842,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name) __unregister_chrdev(major, 0, 256, name); } -/* fs/block_dev.c */ -#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ -#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ - -#ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_MAX 512 -extern const char *__bdevname(dev_t, char *buffer); -extern const char *bdevname(struct block_device *bdev, char *buffer); -extern struct block_device *lookup_bdev(const char *); -extern void blkdev_show(struct seq_file *,off_t); - -#else -#define BLKDEV_MAJOR_MAX 0 -#endif - extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK -extern int revalidate_disk(struct gendisk *); -extern int check_disk_change(struct block_device *); -extern int __invalidate_device(struct block_device *, bool); -extern int invalidate_partition(struct gendisk *, int); -#endif -unsigned long invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end); - -static inline void invalidate_remote_inode(struct inode *inode) -{ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) - invalidate_mapping_pages(inode->i_mapping, 0, -1); -} -extern int invalidate_inode_pages2(struct address_space *mapping); -extern int invalidate_inode_pages2_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); -extern int write_inode_now(struct inode *, int); -extern int filemap_fdatawrite(struct address_space *); -extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait_keep_errors(struct address_space *mapping); -extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, - loff_t start_byte, loff_t end_byte); - -static inline int filemap_fdatawait(struct address_space *mapping) -{ - return filemap_fdatawait_range(mapping, 0, LLONG_MAX); -} - -extern bool filemap_range_has_page(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_write_and_wait_range(struct address_space *mapping, - loff_t lstart, loff_t lend); -extern int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); -extern int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end); -extern int filemap_check_errors(struct address_space *mapping); -extern void __filemap_set_wb_err(struct address_space *mapping, int err); - -static inline int filemap_write_and_wait(struct address_space *mapping) -{ - return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); -} - extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); @@ -2774,82 +2859,6 @@ static inline int file_write_and_wait(struct file *file) return file_write_and_wait_range(file, 0, LLONG_MAX); } -/** - * filemap_set_wb_err - set a writeback error on an address_space - * @mapping: mapping in which to set writeback error - * @err: error to be set in mapping - * - * When writeback fails in some way, we must record that error so that - * userspace can be informed when fsync and the like are called. We endeavor - * to report errors on any file that was open at the time of the error. Some - * internal callers also need to know when writeback errors have occurred. - * - * When a writeback error occurs, most filesystems will want to call - * filemap_set_wb_err to record the error in the mapping so that it will be - * automatically reported whenever fsync is called on the file. - */ -static inline void filemap_set_wb_err(struct address_space *mapping, int err) -{ - /* Fastpath for common case of no error */ - if (unlikely(err)) - __filemap_set_wb_err(mapping, err); -} - -/** - * filemap_check_wb_error - has an error occurred since the mark was sampled? - * @mapping: mapping to check for writeback errors - * @since: previously-sampled errseq_t - * - * Grab the errseq_t value from the mapping, and see if it has changed "since" - * the given value was sampled. - * - * If it has then report the latest error set, otherwise return 0. - */ -static inline int filemap_check_wb_err(struct address_space *mapping, - errseq_t since) -{ - return errseq_check(&mapping->wb_err, since); -} - -/** - * filemap_sample_wb_err - sample the current errseq_t to test for later errors - * @mapping: mapping to be sampled - * - * Writeback errors are always reported relative to a particular sample point - * in the past. This function provides those sample points. - */ -static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) -{ - return errseq_sample(&mapping->wb_err); -} - -static inline int filemap_nr_thps(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - return atomic_read(&mapping->nr_thps); -#else - return 0; -#endif -} - -static inline void filemap_nr_thps_inc(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - atomic_inc(&mapping->nr_thps); -#else - WARN_ON_ONCE(1); -#endif -} - -static inline void filemap_nr_thps_dec(struct address_space *mapping) -{ -#ifdef CONFIG_READ_ONLY_THP_FOR_FS - atomic_dec(&mapping->nr_thps); -#else - WARN_ON_ONCE(1); -#endif -} - extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); @@ -2857,6 +2866,12 @@ extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); +static inline bool iocb_is_dsync(const struct kiocb *iocb) +{ + return (iocb->ki_flags & IOCB_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host); +} + /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount @@ -2864,7 +2879,7 @@ extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { - if (iocb->ki_flags & IOCB_DSYNC) { + if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); @@ -2887,28 +2902,45 @@ static inline int bmap(struct inode *inode, sector_t *block) } #endif -extern int notify_change(struct dentry *, struct iattr *, struct inode **); -extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int); -extern int __check_sticky(struct inode *dir, struct inode *inode); +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); +static inline int file_permission(struct file *file, int mask) +{ + return inode_permission(file_mnt_user_ns(file), + file_inode(file), mask); +} +static inline int path_permission(const struct path *path, int mask) +{ + return inode_permission(mnt_user_ns(path->mnt), + d_inode(path->dentry), mask); +} +int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, + struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } +static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) +{ + return (inode->i_mode ^ mode) & S_IFMT; +} + static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; - return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); + return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) @@ -2919,15 +2951,20 @@ static inline void file_end_write(struct file *file) } /* + * This is used for regular files where some users -- especially the + * currently executed binary in a process, previously handled via + * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap + * read-write shared) accesses. + * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. - * This is used for regular files. - * We cannot support write (and maybe mmap read-write shared) accesses and - * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode - * can have the following values: - * 0: no writers, no VM_DENYWRITE mappings - * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist - * > 0: (i_writecount) users are writing to the file. + * deny_write_access() denies write access to a file. + * allow_write_access() re-enables write access to a file. + * + * The i_writecount field of an inode can have the following values: + * 0: no write access, no denied write access + * < 0: (-i_writecount) users that denied write access to the file. + * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to @@ -2979,43 +3016,8 @@ static inline void i_readcount_inc(struct inode *inode) #endif extern int do_pipe_flags(int *, int); -#define __kernel_read_file_id(id) \ - id(UNKNOWN, unknown) \ - id(FIRMWARE, firmware) \ - id(FIRMWARE_PREALLOC_BUFFER, firmware) \ - id(MODULE, kernel-module) \ - id(KEXEC_IMAGE, kexec-image) \ - id(KEXEC_INITRAMFS, kexec-initramfs) \ - id(POLICY, security-policy) \ - id(X509_CERTIFICATE, x509-certificate) \ - id(MAX_ID, ) - -#define __fid_enumify(ENUM, dummy) READING_ ## ENUM, -#define __fid_stringify(dummy, str) #str, - -enum kernel_read_file_id { - __kernel_read_file_id(__fid_enumify) -}; - -static const char * const kernel_read_file_str[] = { - __kernel_read_file_id(__fid_stringify) -}; - -static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) -{ - if ((unsigned)id >= READING_MAX_ID) - return kernel_read_file_str[READING_UNKNOWN]; - - return kernel_read_file_str[id]; -} - -extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, - enum kernel_read_file_id); -extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t, - enum kernel_read_file_id); -extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, - enum kernel_read_file_id); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); +ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); @@ -3044,6 +3046,7 @@ static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } +extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), @@ -3063,6 +3066,9 @@ extern struct inode *find_inode_nowait(struct super_block *, int (*match)(struct inode *, unsigned long, void *), void *data); +extern struct inode *find_inode_rcu(struct super_block *, unsigned long, + int (*)(struct inode *, void *), void *); +extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -3074,6 +3080,22 @@ extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +void dump_mapping(const struct address_space *); + +/* + * Userspace may rely on the the inode number being non-zero. For example, glibc + * simply ignores files with zero i_ino in unlink() and other places. + * + * As an additional complication, if userspace was compiled with + * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the + * lower 32 bits, so we need to check that those aren't zero explicitly. With + * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but + * better safe than sorry. + */ +static inline bool is_zero_ino(ino_t ino) +{ + return (u32)ino == 0; +} extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); @@ -3085,6 +3107,16 @@ extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); +/* + * 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); +} + extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { @@ -3099,29 +3131,25 @@ 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); -#ifdef CONFIG_BLOCK -extern int bdev_read_only(struct block_device *); -#endif -extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); -extern int generic_remap_checks(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - loff_t *count, unsigned int remap_flags); +int generic_write_checks_count(struct kiocb *iocb, loff_t *count); +extern int generic_write_check_limits(struct file *file, loff_t pos, + loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); -extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t *count, unsigned int flags); +ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, + ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); -extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); +ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); @@ -3132,13 +3160,6 @@ ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); -/* fs/block_dev.c */ -extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); -extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from); -extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, - int datasync); -extern void block_sync_page(struct page *page); - /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); @@ -3153,7 +3174,7 @@ extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); -extern loff_t no_llseek(struct file *file, loff_t offset, int whence); +#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, @@ -3162,6 +3183,7 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); +int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); @@ -3178,8 +3200,6 @@ enum { DIO_SKIP_HOLES = 0x02, }; -void dio_end_io(struct bio *bio); - ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, @@ -3198,7 +3218,7 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, void inode_dio_wait(struct inode *inode); -/* +/** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * @@ -3210,7 +3230,7 @@ static inline void inode_dio_begin(struct inode *inode) atomic_inc(&inode->i_dio_count); } -/* +/** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * @@ -3240,12 +3260,11 @@ extern int page_readlink(struct dentry *, char __user *, int); 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, - int nofs); 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 *); -extern void generic_fillattr(struct inode *, struct kstat *); +void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); +void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); 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); @@ -3264,48 +3283,26 @@ extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); -extern int vfs_statx(int, const char __user *, int, struct kstat *, u32); -extern int vfs_statx_fd(unsigned int, struct kstat *, u32, unsigned int); +int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, + int flags); +int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { - return vfs_statx(AT_FDCWD, filename, AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); + return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { - return vfs_statx(AT_FDCWD, name, AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); -} -static inline int vfs_fstatat(int dfd, const char __user *filename, - struct kstat *stat, int flags) -{ - return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); -} -static inline int vfs_fstat(int fd, struct kstat *stat) -{ - return vfs_statx_fd(fd, stat, STATX_BASIC_STATS, 0); + return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } - extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); -extern int __generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, - loff_t start, loff_t len, - get_block_t *get_block); -extern int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, - u64 len, get_block_t *get_block); - extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); -extern struct super_block *get_super_thawed(struct block_device *); -extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev); 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); @@ -3317,30 +3314,29 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); -extern int simple_setattr(struct dentry *, struct iattr *); -extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int simple_setattr(struct user_namespace *, struct dentry *, + struct iattr *); +extern int simple_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); -extern int simple_rename(struct inode *, struct dentry *, - struct inode *, struct dentry *, unsigned int); +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 *, + struct dentry *, struct inode *, struct dentry *, + unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); -extern int noop_set_page_dirty(struct page *page); -extern void noop_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); -extern int simple_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); +extern 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 **); @@ -3369,30 +3365,18 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -#ifdef CONFIG_MIGRATION -extern int buffer_migrate_page(struct address_space *, - struct page *, struct page *, - enum migrate_mode); -extern int buffer_migrate_page_norefs(struct address_space *, - struct page *, struct page *, - enum migrate_mode); -#else -#define buffer_migrate_page NULL -#define buffer_migrate_page_norefs NULL -#endif +extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); -extern int setattr_prepare(struct dentry *, struct iattr *); +int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, + unsigned int ia_valid); +int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern void setattr_copy(struct inode *inode, const struct iattr *attr); +void setattr_copy(struct user_namespace *, struct inode *inode, + const struct iattr *attr); extern int file_update_time(struct file *file); -static inline bool io_is_direct(struct file *filp) -{ - return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); -} - -static inline bool vma_is_dax(struct vm_area_struct *vma) +static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } @@ -3401,7 +3385,7 @@ static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; - if (!vma->vm_file) + if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; @@ -3416,9 +3400,9 @@ static inline int iocb_flags(struct file *file) int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; - if (io_is_direct(file)) + if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; - if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) + if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; @@ -3427,22 +3411,26 @@ static inline int iocb_flags(struct file *file) static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { + int kiocb_flags = 0; + + /* make sure there's no overlap between RWF and private IOCB flags */ + BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); + + if (!flags) + return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; - ki->ki_flags |= IOCB_NOWAIT; + kiocb_flags |= IOCB_NOIO; } - if (flags & RWF_HIPRI) - ki->ki_flags |= IOCB_HIPRI; - if (flags & RWF_DSYNC) - ki->ki_flags |= IOCB_DSYNC; + kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) - ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC); - if (flags & RWF_APPEND) - ki->ki_flags |= IOCB_APPEND; + kiocb_flags |= IOCB_DSYNC; + + ki->ki_flags |= kiocb_flags; return 0; } @@ -3468,7 +3456,7 @@ static inline ino_t parent_ino(struct dentry *dentry) */ struct simple_transaction_argresp { ssize_t size; - char data[0]; + char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) @@ -3528,13 +3516,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_dentry(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_inodes(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); -int __init get_filesystem_list(char *buf); +int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) @@ -3548,12 +3530,13 @@ static inline bool is_sxid(umode_t mode) return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); } -static inline int check_sticky(struct inode *dir, struct inode *inode) +static inline int check_sticky(struct user_namespace *mnt_userns, + struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; - return __check_sticky(dir, inode); + return __check_sticky(mnt_userns, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) @@ -3571,17 +3554,17 @@ static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { - return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0; + return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, - file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0; + file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, - parent_ino(file->f_path.dentry), DT_DIR) == 0; + parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { @@ -3620,36 +3603,4 @@ 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); -#if defined(CONFIG_IO_URING) -extern struct sock *io_uring_get_socket(struct file *file); -#else -static inline struct sock *io_uring_get_socket(struct file *file) -{ - return NULL; -} -#endif - -int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, - unsigned int flags); - -int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, - struct fsxattr *fa); - -static inline void simple_fill_fsxattr(struct fsxattr *fa, __u32 xflags) -{ - memset(fa, 0, sizeof(*fa)); - fa->fsx_xflags = xflags; -} - -/* - * Flush file data before changing attributes. Caller must hold any locks - * required to prevent further writes to this file until we're done setting - * flags. - */ -static inline int inode_drain_writes(struct inode *inode) -{ - inode_dio_wait(inode); - return filemap_write_and_wait(inode->i_mapping); -} - #endif /* _LINUX_FS_H */ |