diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 1272 |
1 files changed, 534 insertions, 738 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index 7e29433c5ecc..04ceeca12a0d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,8 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/fs/super.h> +#include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> @@ -10,7 +12,6 @@ #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> -#include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> @@ -36,7 +37,6 @@ #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> -#include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> @@ -51,11 +51,9 @@ #include <asm/byteorder.h> #include <uapi/linux/fs.h> -struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; -struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; @@ -69,18 +67,13 @@ struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; -struct workqueue_struct; struct iov_iter; -struct fscrypt_inode_info; -struct fscrypt_operations; -struct fsverity_info; -struct fsverity_operations; struct fsnotify_mark_connector; -struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; -struct fileattr; +struct file_kattr; struct iomap_ops; +struct delegated_inode; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -148,7 +141,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* FMODE_* bit 13 */ +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) @@ -173,13 +167,20 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* FMODE_* bit 24 */ - /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)(1 << 25)) +#define FMODE_BACKING ((__force fmode_t)(1 << 24)) + +/* + * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) -/* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) +/* + * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be + * generated (see below) + */ +#define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) @@ -191,6 +192,31 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* + * The two FMODE_NONOTIFY* define which fsnotify events should not be generated + * for an open file. These are the possible values of + * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning: + * + * FMODE_NONOTIFY - suppress all (incl. non-permission) events. + * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. + * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM. + */ +#define FMODE_FSNOTIFY_MASK \ + (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) + +#define FMODE_FSNOTIFY_NONE(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) +#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS +#define FMODE_FSNOTIFY_HSM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ + (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) +#define FMODE_FSNOTIFY_ACCESS_PERM(mode) \ + ((mode & FMODE_FSNOTIFY_MASK) == 0) +#else +#define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0 +#define FMODE_FSNOTIFY_HSM(mode) 0 +#endif + +/* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ @@ -204,6 +230,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ +#define ATTR_CTIME_SET (1 << 10) #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) @@ -266,11 +293,6 @@ struct iattr { }; /* - * Includes for diskquotas. - */ -#include <linux/quota.h> - -/* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ @@ -322,6 +344,8 @@ struct readahead_control; #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC +#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE +#define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -332,22 +356,9 @@ struct readahead_control; #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) -/* - * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the - * iocb completion can be passed back to the owner for execution from a safe - * context rather than needing to be punted through a workqueue. If this - * flag is set, the bio completion handling may set iocb->dio_complete to a - * handler function and iocb->private to context information for that handler. - * The issuer should call the handler with that context information from task - * context to complete the processing of the iocb. Note that while this - * provides a task context for the dio_complete() callback, it should only be - * used on the completion side for non-IO generating completions. It's fine to - * call blocking functions from this callback, but they should not wait for - * unrelated IO (like cache flushing, new IO generation, etc). - */ -#define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ -#define IOCB_AIO_RW (1 << 23) +#define IOCB_AIO_RW (1 << 22) +#define IOCB_HAS_METADATA (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -356,14 +367,16 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ - { IOCB_ATOMIC, "ATOMIC"}, \ + { IOCB_ATOMIC, "ATOMIC" }, \ + { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ - { IOCB_DIO_CALLER_COMP, "CALLER_COMP" } + { IOCB_AIO_RW, "AIO_RW" }, \ + { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } struct kiocb { struct file *ki_filp; @@ -372,23 +385,14 @@ struct kiocb { void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ - union { - /* - * Only used for async buffered reads, where it denotes the - * page waitqueue associated with completing the read. Valid - * IFF IOCB_WAITQ is set. - */ - struct wait_page_queue *ki_waitq; - /* - * Can be used for O_DIRECT IO, where the completion handling - * is punted back to the issuer of the IO. May only be set - * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer - * must then check for presence of this handler when ki_complete - * is invoked. The data passed in to this handler must be - * assigned to ->private when dio_complete is assigned. - */ - ssize_t (*dio_complete)(void *data); - }; + u8 ki_write_stream; + + /* + * Only used for async buffered reads, where it denotes the page + * waitqueue associated with completing the read. + * Valid IFF IOCB_WAITQ is set. + */ + struct wait_page_queue *ki_waitq; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -397,7 +401,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) } struct address_space_operations { - int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ @@ -408,10 +411,10 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); - int (*write_begin)(struct file *, struct address_space *mapping, + int (*write_begin)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); - int (*write_end)(struct file *, struct address_space *mapping, + int (*write_end)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); @@ -488,7 +491,7 @@ struct address_space { /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit - * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. + * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ @@ -499,7 +502,7 @@ struct address_space { /* * Returns true if any of the pages in the mapping are marked with the tag. */ -static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } @@ -547,7 +550,7 @@ static inline void i_mmap_assert_write_locked(struct address_space *mapping) /* * Might pages of this file be mapped into userspace? */ -static inline int mapping_mapped(struct address_space *mapping) +static inline int mapping_mapped(const struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } @@ -561,7 +564,7 @@ static inline int mapping_mapped(struct address_space *mapping) * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ -static inline int mapping_writably_mapped(struct address_space *mapping) +static inline int mapping_writably_mapped(const struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } @@ -620,12 +623,139 @@ is_uncached_acl(struct posix_acl *acl) return (long)acl & 1; } -#define IOP_FASTPERM 0x0001 -#define IOP_LOOKUP 0x0002 -#define IOP_NOFOLLOW 0x0004 -#define IOP_XATTR 0x0008 +#define IOP_FASTPERM 0x0001 +#define IOP_LOOKUP 0x0002 +#define IOP_NOFOLLOW 0x0004 +#define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 -#define IOP_MGTIME 0x0020 +#define IOP_MGTIME 0x0020 +#define IOP_CACHED_LINK 0x0040 +#define IOP_FASTPERM_MAY_EXEC 0x0080 + +/* + * Inode state bits. Protected by inode->i_lock + * + * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, + * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. + * + * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, + * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at + * various stages of removing an inode. + * + * Two bits are used for locking and completion notification, I_NEW and I_SYNC. + * + * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on + * fdatasync() (unless I_DIRTY_DATASYNC is also set). + * Timestamp updates are the usual cause. + * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * these changes separately from I_DIRTY_SYNC so that we + * don't have to write inode on fdatasync() when only + * e.g. the timestamps have changed. + * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_DIRTY_TIME The inode itself has dirty timestamps, and the + * lazytime mount option is enabled. We keep track of this + * separately from I_DIRTY_SYNC in order to implement + * lazytime. This gets cleared if I_DIRTY_INODE + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But + * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already + * in place because writeback might already be in progress + * and we don't want to lose the time update + * I_NEW Serves as both a mutex and completion notification. + * New inodes set I_NEW. If two processes both create + * the same inode, one of them will release its inode and + * wait for I_NEW to be released before returning. + * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can + * also cause waiting on I_NEW, without I_NEW actually + * being set. find_inode() uses this to prevent returning + * nearly-dead inodes. + * I_WILL_FREE Must be set when calling write_inode_now() if i_count + * is zero. I_FREEING must be set when I_WILL_FREE is + * cleared. + * I_FREEING Set when inode is about to be freed but still has dirty + * pages or buffers attached or the inode itself is still + * dirty. + * I_CLEAR Added by clear_inode(). In this state the inode is + * clean and can be destroyed. Inode keeps I_FREEING. + * + * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are + * prohibited for many purposes. iget() must wait for + * the inode to be completely released, then create it + * anew. Other functions will just ignore such inodes, + * if appropriate. I_NEW is used for waiting. + * + * I_SYNC Writeback of inode is running. The bit is set during + * data writeback, and cleared with a wakeup on the bit + * address once it is done. The bit is also used to pin + * the inode in memory for flusher thread. + * + * I_REFERENCED Marks the inode as recently references on the LRU list. + * + * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to + * synchronize competing switching instances and to tell + * wb stat updates to grab the i_pages lock. See + * inode_switch_wbs_work_fn() for details. + * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * + * I_CREATING New object's inode in the middle of setting up. + * + * I_DONTCACHE Evict inode as soon as it is not used anymore. + * + * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. + * Used to detect that mark_inode_dirty() should not move + * inode between dirty lists. + * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * + * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. + */ + +enum inode_state_bits { + __I_NEW = 0U, + __I_SYNC = 1U, + __I_LRU_ISOLATING = 2U + /* reserved wait address bit 3 */ +}; + +enum inode_state_flags_enum { + I_NEW = (1U << __I_NEW), + I_SYNC = (1U << __I_SYNC), + I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), + /* reserved flag bit 3 */ + I_DIRTY_SYNC = (1U << 4), + I_DIRTY_DATASYNC = (1U << 5), + I_DIRTY_PAGES = (1U << 6), + I_WILL_FREE = (1U << 7), + I_FREEING = (1U << 8), + I_CLEAR = (1U << 9), + I_REFERENCED = (1U << 10), + I_LINKABLE = (1U << 11), + I_DIRTY_TIME = (1U << 12), + I_WB_SWITCH = (1U << 13), + I_OVL_INUSE = (1U << 14), + I_CREATING = (1U << 15), + I_DONTCACHE = (1U << 16), + I_SYNC_QUEUED = (1U << 17), + I_PINNING_NETFS_WB = (1U << 18) +}; + +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) +#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) +#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) + +/* + * Use inode_state_read() & friends to access. + */ +struct inode_state_flags { + enum inode_state_flags_enum __state; +}; /* * Keep mostly read-only and often accessed (especially for @@ -635,14 +765,13 @@ is_uncached_acl(struct posix_acl *acl) struct inode { umode_t i_mode; unsigned short i_opflags; - kuid_t i_uid; - kgid_t i_gid; unsigned int i_flags; - #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif + kuid_t i_uid; + kgid_t i_gid; const struct inode_operations *i_op; struct super_block *i_sb; @@ -685,7 +814,7 @@ struct inode { #endif /* Misc */ - u32 i_state; + struct inode_state_flags i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; @@ -723,7 +852,10 @@ struct inode { }; struct file_lock_context *i_flctx; struct address_space i_data; - struct list_head i_devices; + union { + struct list_head i_devices; + int i_linklen; + }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; @@ -738,18 +870,93 @@ struct inode { struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif -#ifdef CONFIG_FS_ENCRYPTION - struct fscrypt_inode_info *i_crypt_info; -#endif - -#ifdef CONFIG_FS_VERITY - struct fsverity_info *i_verity_info; -#endif - void *i_private; /* fs or device private pointer */ } __randomize_layout; /* + * i_state handling + * + * We hide all of it behind helpers so that we can validate consumers. + */ +static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode) +{ + return READ_ONCE(inode->i_state.__state); +} + +static inline enum inode_state_flags_enum inode_state_read(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + return inode->i_state.__state; +} + +static inline void inode_state_set_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags); +} + +static inline void inode_state_set(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_set_raw(inode, flags); +} + +static inline void inode_state_clear_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags); +} + +static inline void inode_state_clear(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_clear_raw(inode, flags); +} + +static inline void inode_state_assign_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, flags); +} + +static inline void inode_state_assign(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace_raw(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + enum inode_state_flags_enum flags; + flags = inode->i_state.__state; + flags &= ~clearflags; + flags |= setflags; + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_replace_raw(inode, clearflags, setflags); +} + +static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) +{ + VFS_WARN_ON_INODE(strlen(link) != linklen, inode); + VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); + inode->i_link = link; + inode->i_linklen = linklen; + inode->i_opflags |= IOP_CACHED_LINK; +} + +/* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. */ @@ -787,8 +994,10 @@ static inline void inode_fake_hash(struct inode *inode) hlist_add_fake(&inode->i_hash); } +void wait_on_new_inode(struct inode *inode); + /* - * inode->i_mutex nesting subclasses for the lock validator: + * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent @@ -818,6 +1027,11 @@ static inline void inode_lock(struct inode *inode) down_write(&inode->i_rwsem); } +static inline __must_check int inode_lock_killable(struct inode *inode) +{ + return down_write_killable(&inode->i_rwsem); +} + static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); @@ -828,6 +1042,11 @@ static inline void inode_lock_shared(struct inode *inode) down_read(&inode->i_rwsem); } +static inline __must_check int inode_lock_shared_killable(struct inode *inode) +{ + return down_read_killable(&inode->i_rwsem); +} + static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); @@ -930,7 +1149,7 @@ static inline loff_t i_size_read(const struct inode *inode) /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it - * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount + * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) @@ -982,6 +1201,7 @@ struct fown_struct { * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. + * @order: Preferred folio order used for most recent readahead. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * @@ -993,7 +1213,8 @@ struct file_ra_state { unsigned int size; unsigned int async_size; unsigned int ra_pages; - unsigned int mmap_miss; + unsigned short order; + unsigned short mmap_miss; loff_t prev_pos; }; @@ -1008,7 +1229,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) /** * struct file - Represents a file - * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations @@ -1018,12 +1238,14 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener + * @f_owner: file owner * @f_path: path of the file + * @__f_path: writable alias for @f_path; *ONLY* for core VFS and only before + * the file gets open * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file - * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file @@ -1031,9 +1253,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) + * @f_ref: reference count */ struct file { - file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; @@ -1043,8 +1265,12 @@ struct file { unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; + struct fown_struct *f_owner; /* --- cacheline 1 boundary (64 bytes) --- */ - struct path f_path; + union { + const struct path f_path; + struct path __f_path; + }; union { /* regular files (with FMODE_ATOMIC_POS) and directories */ struct mutex f_pos_lock; @@ -1056,7 +1282,6 @@ struct file { void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ - struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL @@ -1068,6 +1293,7 @@ struct file { struct file_ra_state f_ra; freeptr_t f_freeptr; }; + file_ref_t f_ref; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1169,42 +1395,6 @@ extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* - * sb->s_flags. Note that these mirror the equivalent MS_* flags where - * represented in both. - */ -#define SB_RDONLY BIT(0) /* Mount read-only */ -#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ -#define SB_NODEV BIT(2) /* Disallow access to device special files */ -#define SB_NOEXEC BIT(3) /* Disallow program execution */ -#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ -#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ -#define SB_NOATIME BIT(10) /* Do not update access times. */ -#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ -#define SB_SILENT BIT(15) -#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ -#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ -#define SB_I_VERSION BIT(23) /* Update inode I_version field */ -#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define SB_DEAD BIT(21) -#define SB_DYING BIT(24) -#define SB_SUBMOUNT BIT(26) -#define SB_FORCE BIT(27) -#define SB_NOSEC BIT(28) -#define SB_BORN BIT(29) -#define SB_ACTIVE BIT(30) -#define SB_NOUSER BIT(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 */ @@ -1214,186 +1404,6 @@ extern int send_sigurg(struct file *file); #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -/* sb->s_iflags */ -#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ -#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ -#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ -#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ - -/* sb->s_iflags to limit user namespace mounts */ -#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 -#define SB_I_UNTRUSTED_MOUNTER 0x00000040 -#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 - -#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 */ -#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ -#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ - -/* Possible states of 'frozen' field */ -enum { - SB_UNFROZEN = 0, /* FS is unfrozen */ - SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ - SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ - SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop - * internal threads if needed) */ - SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ -}; - -#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) - -struct sb_writers { - unsigned short frozen; /* Is sb frozen? */ - int freeze_kcount; /* How many kernel freeze requests? */ - int freeze_ucount; /* How many userspace freeze requests? */ - struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; -}; - -struct super_block { - struct list_head s_list; /* Keep this first */ - dev_t s_dev; /* search index; _not_ kdev_t */ - unsigned char s_blocksize_bits; - unsigned long s_blocksize; - loff_t s_maxbytes; /* Max file size */ - struct file_system_type *s_type; - const struct super_operations *s_op; - const struct dquot_operations *dq_op; - const struct quotactl_ops *s_qcop; - const struct export_operations *s_export_op; - unsigned long s_flags; - unsigned long s_iflags; /* internal SB_I_* flags */ - unsigned long s_magic; - struct dentry *s_root; - struct rw_semaphore s_umount; - int s_count; - atomic_t s_active; -#ifdef CONFIG_SECURITY - void *s_security; -#endif - const struct xattr_handler * const *s_xattr; -#ifdef CONFIG_FS_ENCRYPTION - const struct fscrypt_operations *s_cop; - struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ -#endif -#ifdef CONFIG_FS_VERITY - const struct fsverity_operations *s_vop; -#endif -#if IS_ENABLED(CONFIG_UNICODE) - struct unicode_map *s_encoding; - __u16 s_encoding_flags; -#endif - struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ - struct list_head s_mounts; /* list of mounts; _not_ for fs use */ - struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ - struct file *s_bdev_file; - struct backing_dev_info *s_bdi; - struct mtd_info *s_mtd; - struct hlist_node s_instances; - unsigned int s_quota_types; /* Bitmask of supported quota types */ - struct quota_info s_dquot; /* Diskquota specific options */ - - struct sb_writers s_writers; - - /* - * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and - * s_fsnotify_info together for cache efficiency. They are frequently - * accessed and rarely modified. - */ - void *s_fs_info; /* Filesystem private info */ - - /* Granularity of c/m/atime in ns (cannot be worse than a second) */ - u32 s_time_gran; - /* Time limits for c/m/atime in seconds */ - time64_t s_time_min; - time64_t s_time_max; -#ifdef CONFIG_FSNOTIFY - u32 s_fsnotify_mask; - struct fsnotify_sb_info *s_fsnotify_info; -#endif - - /* - * q: why are s_id and s_sysfs_name not the same? both are human - * readable strings that identify the filesystem - * a: s_id is allowed to change at runtime; it's used in log messages, - * and we want to when a device starts out as single device (s_id is dev - * name) but then a device is hot added and we have to switch to - * identifying it by UUID - * but s_sysfs_name is a handle for programmatic access, and can't - * change at runtime - */ - char s_id[32]; /* Informational name */ - uuid_t s_uuid; /* UUID */ - u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ - - /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ - char s_sysfs_name[UUID_STRING_LEN + 1]; - - unsigned int s_max_links; - - /* - * The next field is for VFS *only*. No filesystems have any business - * even looking at it. You had been warned. - */ - struct mutex s_vfs_rename_mutex; /* Kludge */ - - /* - * Filesystem subtype. If non-empty the filesystem type field - * in /proc/mounts will be "type.subtype" - */ - const char *s_subtype; - - const struct dentry_operations *s_d_op; /* default d_op for dentries */ - - struct shrinker *s_shrink; /* per-sb shrinker handle */ - - /* Number of inodes with nlink == 0 but still referenced */ - atomic_long_t s_remove_count; - - /* Read-only state of the superblock is being changed */ - int s_readonly_remount; - - /* per-sb errseq_t for reporting writeback errors via syncfs */ - errseq_t s_wb_err; - - /* AIO completions deferred from interrupt context */ - struct workqueue_struct *s_dio_done_wq; - struct hlist_head s_pins; - - /* - * Owning user namespace and default context in which to - * interpret filesystem uids, gids, quotas, device nodes, - * xattrs and security labels. - */ - struct user_namespace *s_user_ns; - - /* - * The list_lru structure is essentially just a pointer to a table - * of per-node lru lists, each of which has its own spinlock. - * There is no need to put them into separate cachelines. - */ - struct list_lru s_dentry_lru; - struct list_lru s_inode_lru; - struct rcu_head rcu; - struct work_struct destroy_work; - - struct mutex s_sync_lock; /* sync serialisation lock */ - - /* - * Indicates how deep in a filesystem stack this SB is - */ - int s_stack_depth; - - /* s_inode_list_lock protects s_inodes */ - spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; - struct list_head s_inodes; /* all inodes */ - - spinlock_t s_inode_wblist_lock; - struct list_head s_inodes_wb; /* writeback inodes */ -} __randomize_layout; - static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; @@ -1711,66 +1721,6 @@ struct timespec64 simple_inode_init_ts(struct inode *inode); * Snapshotting support. */ -/* - * 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], _THIS_IP_) - -/** - * __sb_write_started - check if sb freeze level is held - * @sb: the super we write to - * @level: the freeze level - * - * * > 0 - sb freeze level is held - * * 0 - sb freeze level is not held - * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN - */ -static inline int __sb_write_started(const struct super_block *sb, int level) -{ - return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); -} - -/** - * sb_write_started - check if SB_FREEZE_WRITE is held - * @sb: the super we write to - * - * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. - */ -static inline bool sb_write_started(const struct super_block *sb) -{ - return __sb_write_started(sb, SB_FREEZE_WRITE); -} - -/** - * sb_write_not_started - check if SB_FREEZE_WRITE is not held - * @sb: the super we write to - * - * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. - */ -static inline bool sb_write_not_started(const struct super_block *sb) -{ - return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; -} - /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to @@ -1801,157 +1751,44 @@ static inline bool file_write_not_started(const struct file *file) return sb_write_not_started(file_inode(file)->i_sb); } -/** - * sb_end_write - drop write access to a superblock - * @sb: the super we wrote to - * - * Decrement number of writers to the filesystem. Wake up possible waiters - * wanting to freeze the filesystem. - */ -static inline void sb_end_write(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_WRITE); -} - -/** - * sb_end_pagefault - drop write access to a superblock from a page fault - * @sb: the super we wrote to - * - * Decrement number of processes handling write page fault to the filesystem. - * Wake up possible waiters wanting to freeze the filesystem. - */ -static inline void sb_end_pagefault(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_PAGEFAULT); -} - -/** - * sb_end_intwrite - drop write access to a superblock for internal fs purposes - * @sb: the super we wrote to - * - * Decrement fs-internal number of writers to the filesystem. Wake up possible - * waiters wanting to freeze the filesystem. - */ -static inline void sb_end_intwrite(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_FS); -} - -/** - * sb_start_write - get write access to a superblock - * @sb: the super we write to - * - * When a process wants to write data or metadata to a file system (i.e. dirty - * a page or an inode), it should embed the operation in a sb_start_write() - - * sb_end_write() pair to get exclusion against file system freezing. This - * function increments number of writers preventing freezing. If the file - * system is already frozen, the function waits until the file system is - * thawed. - * - * Since freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. Generally, - * freeze protection should be the outermost lock. In particular, we have: - * - * sb_start_write - * -> i_mutex (write path, truncate, directory ops, ...) - * -> s_umount (freeze_super, thaw_super) - */ -static inline void sb_start_write(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_WRITE); -} - -static inline bool sb_start_write_trylock(struct super_block *sb) -{ - return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); -} - -/** - * sb_start_pagefault - get write access to a superblock from a page fault - * @sb: the super we write to - * - * When a process starts handling write page fault, it should embed the - * operation into sb_start_pagefault() - sb_end_pagefault() pair to get - * exclusion against file system freezing. This is needed since the page fault - * is going to dirty a page. This function increments number of running page - * faults preventing freezing. If the file system is already frozen, the - * function waits until the file system is thawed. - * - * Since page fault freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault - * handling code implies lock dependency: - * - * mmap_lock - * -> sb_start_pagefault - */ -static inline void sb_start_pagefault(struct super_block *sb) -{ - __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 - * - * This is the third level of protection against filesystem freezing. It is - * free for use by a filesystem. The only requirement is that it must rank - * below sb_start_pagefault. - * - * For example filesystem can call sb_start_intwrite() when starting a - * transaction which somewhat eases handling of freezing for internal sources - * of filesystem changes (internal fs threads, discarding preallocation on file - * close, etc.). - */ -static inline void sb_start_intwrite(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_FS); -} - -static inline bool sb_start_intwrite_trylock(struct super_block *sb) -{ - return __sb_start_write_trylock(sb, SB_FREEZE_FS); -} - bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ -int vfs_create(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t, bool); -int vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); +int vfs_create(struct mnt_idmap *, struct dentry *, umode_t, + struct delegated_inode *); +struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t, struct delegated_inode *); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, - umode_t, dev_t); + umode_t, dev_t, struct delegated_inode *); int vfs_symlink(struct mnt_idmap *, struct inode *, - struct dentry *, const char *); + struct dentry *, const char *, struct delegated_inode *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, - struct dentry *, struct inode **); -int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); + struct dentry *, struct delegated_inode *); +int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *, + struct delegated_inode *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, - struct inode **); + struct delegated_inode *); /** * struct renamedata - contains all information required for renaming - * @old_mnt_idmap: idmap of the old mount the inode was found from - * @old_dir: parent of source + * @mnt_idmap: idmap of the mount in which the rename is happening. + * @old_parent: parent of source * @old_dentry: source - * @new_mnt_idmap: idmap of the new mount the inode was found from - * @new_dir: parent of destination + * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { - struct mnt_idmap *old_mnt_idmap; - struct inode *old_dir; + struct mnt_idmap *mnt_idmap; + struct dentry *old_parent; struct dentry *old_dentry; - struct mnt_idmap *new_mnt_idmap; - struct inode *new_dir; + struct dentry *new_parent; struct dentry *new_dentry; - struct inode **delegated_inode; + struct delegated_inode *delegated_inode; unsigned int flags; } __randomize_layout; @@ -1961,7 +1798,7 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, - WHITEOUT_DEV); + WHITEOUT_DEV, NULL); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, @@ -1979,8 +1816,6 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); -extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); - #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); @@ -2013,8 +1848,18 @@ typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, struct dir_context { filldir_t actor; loff_t pos; + /* + * Filesystems MUST NOT MODIFY count, but may use as a hint: + * 0 unknown + * > 0 space in buffer (assume at least one entry) + * INT_MAX unlimited + */ + int count; }; +/* If OR-ed with d_type, pending signals are not checked */ +#define FILLDIR_FLAG_NOINTR 0x1000 + /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. @@ -2111,6 +1956,7 @@ struct file_operations { int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); + int (*mmap_prepare)(struct vm_area_desc *); } __randomize_layout; /* Supports async buffered reads */ @@ -2127,6 +1973,8 @@ struct file_operations { #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) +/* File system supports uncached read/write buffered IO */ +#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -2149,8 +1997,8 @@ struct inode_operations { int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); @@ -2173,16 +2021,43 @@ struct inode_operations { int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, - struct dentry *dentry, struct fileattr *fa); - int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); + struct dentry *dentry, struct file_kattr *fa); + int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; -static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +/* Did the driver provide valid mmap hook configuration? */ +static inline bool can_mmap_file(struct file *file) +{ + bool has_mmap = file->f_op->mmap; + bool has_mmap_prepare = file->f_op->mmap_prepare; + + /* Hooks are mutually exclusive. */ + if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) + return false; + if (!has_mmap && !has_mmap_prepare) + return false; + + return true; +} + +int __compat_vma_mmap(const struct file_operations *f_op, + struct file *file, struct vm_area_struct *vma); +int compat_vma_mmap(struct file *file, struct vm_area_struct *vma); + +static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { + if (file->f_op->mmap_prepare) + return compat_vma_mmap(file, vma); + return file->f_op->mmap(file, vma); } +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) +{ + return file->f_op->mmap_prepare(desc); +} + extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, @@ -2204,61 +2079,6 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); -/** - * enum freeze_holder - holder of the freeze - * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem - * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem - * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed - * - * Indicate who the owner of the freeze or thaw request is and whether - * the freeze needs to be exclusive or can nest. - * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the - * same holder aren't allowed. It is however allowed to hold a single - * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at - * the same time. This is relied upon by some filesystems during online - * repair or similar. - */ -enum freeze_holder { - FREEZE_HOLDER_KERNEL = (1U << 0), - FREEZE_HOLDER_USERSPACE = (1U << 1), - FREEZE_MAY_NEST = (1U << 2), -}; - -struct super_operations { - struct inode *(*alloc_inode)(struct super_block *sb); - void (*destroy_inode)(struct inode *); - void (*free_inode)(struct inode *); - - void (*dirty_inode) (struct inode *, int flags); - int (*write_inode) (struct inode *, struct writeback_control *wbc); - int (*drop_inode) (struct inode *); - void (*evict_inode) (struct inode *); - void (*put_super) (struct super_block *); - int (*sync_fs)(struct super_block *sb, int wait); - int (*freeze_super) (struct super_block *, enum freeze_holder who); - int (*freeze_fs) (struct super_block *); - int (*thaw_super) (struct super_block *, enum freeze_holder who); - int (*unfreeze_fs) (struct super_block *); - int (*statfs) (struct dentry *, struct kstatfs *); - int (*remount_fs) (struct super_block *, int *, char *); - void (*umount_begin) (struct super_block *); - - int (*show_options)(struct seq_file *, struct dentry *); - int (*show_devname)(struct seq_file *, struct dentry *); - int (*show_path)(struct seq_file *, struct dentry *); - int (*show_stats)(struct seq_file *, struct dentry *); -#ifdef CONFIG_QUOTA - ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); - ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); - struct dquot __rcu **(*get_dquots)(struct inode *); -#endif - long (*nr_cached_objects)(struct super_block *, - struct shrink_control *); - long (*free_cached_objects)(struct super_block *, - struct shrink_control *); - void (*shutdown)(struct super_block *sb); -}; - /* * Inode flags - they have no relation to superblock flags now */ @@ -2284,6 +2104,7 @@ struct super_operations { #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ +#define S_ANON_INODE (1 << 19) /* Inode is an anonymous inode */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2300,7 +2121,6 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) @@ -2340,6 +2160,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) +#define IS_ANON_FILE(inode) ((inode)->i_flags & S_ANON_INODE) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) @@ -2368,117 +2189,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, }; } -/* - * Inode state bits. Protected by inode->i_lock - * - * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, - * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. - * - * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, - * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at - * various stages of removing an inode. - * - * Two bits are used for locking and completion notification, I_NEW and I_SYNC. - * - * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync() (unless I_DIRTY_DATASYNC is also set). - * Timestamp updates are the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of - * these changes separately from I_DIRTY_SYNC so that we - * don't have to write inode on fdatasync() when only - * e.g. the timestamps have changed. - * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_DIRTY_TIME The inode itself has dirty timestamps, and the - * lazytime mount option is enabled. We keep track of this - * separately from I_DIRTY_SYNC in order to implement - * lazytime. This gets cleared if I_DIRTY_INODE - * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But - * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already - * in place because writeback might already be in progress - * and we don't want to lose the time update - * I_NEW Serves as both a mutex and completion notification. - * New inodes set I_NEW. If two processes both create - * the same inode, one of them will release its inode and - * wait for I_NEW to be released before returning. - * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can - * also cause waiting on I_NEW, without I_NEW actually - * being set. find_inode() uses this to prevent returning - * nearly-dead inodes. - * I_WILL_FREE Must be set when calling write_inode_now() if i_count - * is zero. I_FREEING must be set when I_WILL_FREE is - * cleared. - * I_FREEING Set when inode is about to be freed but still has dirty - * pages or buffers attached or the inode itself is still - * dirty. - * I_CLEAR Added by clear_inode(). In this state the inode is - * clean and can be destroyed. Inode keeps I_FREEING. - * - * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are - * prohibited for many purposes. iget() must wait for - * the inode to be completely released, then create it - * anew. Other functions will just ignore such inodes, - * if appropriate. I_NEW is used for waiting. - * - * I_SYNC Writeback of inode is running. The bit is set during - * data writeback, and cleared with a wakeup on the bit - * address once it is done. The bit is also used to pin - * the inode in memory for flusher thread. - * - * I_REFERENCED Marks the inode as recently references on the LRU list. - * - * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to - * synchronize competing switching instances and to tell - * wb stat updates to grab the i_pages lock. See - * inode_switch_wbs_work_fn() for details. - * - * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper - * and work dirs among overlayfs mounts. - * - * I_CREATING New object's inode in the middle of setting up. - * - * I_DONTCACHE Evict inode as soon as it is not used anymore. - * - * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. - * Used to detect that mark_inode_dirty() should not move - * inode between dirty lists. - * - * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. - * - * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding - * i_count. - * - * Q: What is the difference between I_WILL_FREE and I_FREEING? - * - * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait - * upon. There's one free address left. - */ -#define __I_NEW 0 -#define I_NEW (1 << __I_NEW) -#define __I_SYNC 1 -#define I_SYNC (1 << __I_SYNC) -#define __I_LRU_ISOLATING 2 -#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) - -#define I_DIRTY_SYNC (1 << 3) -#define I_DIRTY_DATASYNC (1 << 4) -#define I_DIRTY_PAGES (1 << 5) -#define I_WILL_FREE (1 << 6) -#define I_FREEING (1 << 7) -#define I_CLEAR (1 << 8) -#define I_REFERENCED (1 << 9) -#define I_LINKABLE (1 << 10) -#define I_DIRTY_TIME (1 << 11) -#define I_WB_SWITCH (1 << 12) -#define I_OVL_INUSE (1 << 13) -#define I_CREATING (1 << 14) -#define I_DONTCACHE (1 << 15) -#define I_SYNC_QUEUED (1 << 16) -#define I_PINNING_NETFS_WB (1 << 17) - -#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) -#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) -#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) - extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { @@ -2490,6 +2200,11 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline int icount_read(const struct inode *inode) +{ + return atomic_read(&inode->i_count); +} + /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. @@ -2501,8 +2216,8 @@ static inline void mark_inode_dirty_sync(struct inode *inode) */ static inline bool inode_is_dirtytime_only(struct inode *inode) { - return (inode->i_state & (I_DIRTY_TIME | I_NEW | - I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; + return (inode_state_read_once(inode) & + (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); @@ -2554,6 +2269,8 @@ struct file_system_type { #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ +#define FS_LBS 128 /* FS supports LBS */ +#define FS_POWER_FREEZE 256 /* Always freeze on suspend/hibernate */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2588,21 +2305,11 @@ static inline bool is_mgtime(const struct inode *inode) return inode->i_opflags & IOP_MGTIME; } -extern struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_single(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_nodev(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); -void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); @@ -2647,8 +2354,6 @@ extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); -int freeze_super(struct super_block *super, enum freeze_holder who); -int thaw_super(struct super_block *super, enum freeze_holder who); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -2691,10 +2396,9 @@ static inline void super_set_sysfs_name_generic(struct super_block *sb, const ch va_end(args); } -extern int current_umask(void); - extern void ihold(struct inode * inode); extern void iput(struct inode *); +void iput_not_last(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); @@ -2732,13 +2436,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) return mnt_idmap(mnt) != &nop_mnt_idmap; } -extern long vfs_truncate(const struct path *, loff_t); +int vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); +int do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, @@ -2751,9 +2455,11 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); +struct file *dentry_open_nonotify(const struct path *path, int flags, + const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); -struct path *backing_file_user_path(struct file *f); +const struct path *backing_file_user_path(const struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file @@ -2765,14 +2471,14 @@ struct path *backing_file_user_path(struct file *f); * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ -static inline const struct path *file_user_path(struct file *f) +static inline const struct path *file_user_path(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ -static inline const struct inode *file_user_inode(struct file *f) +static inline const struct inode *file_user_inode(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); @@ -2787,7 +2493,10 @@ extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); -extern struct filename *getname(const char __user *); +static inline struct filename *getname(const char __user *name) +{ + return getname_flags(name, 0); +} extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) @@ -2800,6 +2509,13 @@ static inline struct filename *getname_maybe_null(const char __user *name, int f return __getname_maybe_null(name); } extern void putname(struct filename *name); +DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) + +static inline struct filename *refname(struct filename *name) +{ + atomic_inc(&name->refcnt); + return name; +} extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); @@ -2823,12 +2539,6 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -extern struct super_block *blockdev_superblock; -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; -} - void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; @@ -2874,6 +2584,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); +int filemap_flush_range(struct address_space *mapping, loff_t start, + loff_t end); static inline int file_write_and_wait(struct file *file) { @@ -2906,6 +2618,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; + } else if (iocb->ki_flags & IOCB_DONTCACHE) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + + filemap_flush_range(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); } return count; @@ -2924,7 +2641,7 @@ static inline int bmap(struct inode *inode, sector_t *block) #endif int notify_change(struct mnt_idmap *, struct dentry *, - struct iattr *, struct inode **); + struct iattr *, struct delegated_inode *); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) @@ -2954,7 +2671,7 @@ static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * - * This is a variant of sb_start_write() which is a noop on non-regualr file. + * This is a variant of sb_start_write() which is a noop on non-regular file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) @@ -3059,6 +2776,34 @@ static inline void allow_write_access(struct file *file) if (file) atomic_inc(&file_inode(file)->i_writecount); } + +/* + * Do not prevent write to executable file when watched by pre-content events. + * + * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at + * the time of file open and remains constant for entire lifetime of the file, + * so if pre-content watches are added post execution or removed before the end + * of the execution, it will not cause i_writecount reference leak. + */ +static inline int exe_file_deny_write_access(struct file *exe_file) +{ + if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return 0; + return deny_write_access(exe_file); +} +static inline void exe_file_allow_write_access(struct file *exe_file) +{ + if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) + return; + allow_write_access(exe_file); +} + +static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) +{ + file->f_mode &= ~FMODE_FSNOTIFY_MASK; + file->f_mode |= mode; +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; @@ -3094,6 +2839,7 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); +u64 vfsmount_to_propagation_flags(struct vfsmount *mnt); extern char *file_path(struct file *, char *, int); @@ -3108,6 +2854,22 @@ static inline bool is_dot_dotdot(const char *name, size_t len) (len == 1 || (len == 2 && name[1] == '.')); } +/** + * name_contains_dotdot - check if a file name contains ".." path components + * @name: File path string to check + * Search for ".." surrounded by either '/' or start/end of string. + */ +static inline bool name_contains_dotdot(const char *name) +{ + size_t name_len; + + name_len = strlen(name); + return strcmp(name, "..") == 0 || + strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0); +} + #include <linux/err.h> /* needed for stackable file system support */ @@ -3126,8 +2888,8 @@ extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); -extern int generic_delete_inode(struct inode *inode); -static inline int generic_drop_inode(struct inode *inode) +extern int inode_just_drop(struct inode *inode); +static inline int inode_generic_drop(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } @@ -3135,7 +2897,7 @@ extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), - void *data); + void *data, bool *isnew); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); @@ -3187,22 +2949,23 @@ static inline bool is_zero_ino(ino_t ino) return (u32)ino == 0; } -/* - * inode->i_lock must be held - */ static inline void __iget(struct inode *inode) { + lockdep_assert_held(&inode->i_lock); atomic_inc(&inode->i_count); } extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode_pseudo(struct super_block *sb); +struct inode *alloc_inode(struct super_block *sb); +static inline struct inode *new_inode_pseudo(struct super_block *sb) +{ + return alloc_inode(sb); +} extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); -extern int file_remove_privs_flags(struct file *file, unsigned int flags); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); @@ -3227,13 +2990,12 @@ static inline void remove_inode_hash(struct inode *inode) } extern void inode_sb_list_add(struct inode *inode); -extern void inode_add_lru(struct inode *inode); +extern void inode_lru_list_add(struct inode *inode); -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 *); +int generic_file_mmap(struct file *, struct vm_area_struct *); +int generic_file_mmap_prepare(struct vm_area_desc *desc); +int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, @@ -3351,8 +3113,10 @@ extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) -extern int readlink_copy(char __user *, int, const char *); +extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); +extern const char *page_get_link_raw(struct dentry *, struct inode *, + struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); @@ -3364,7 +3128,8 @@ void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, - unsigned int unit_max); + unsigned int unit_max, + unsigned int unit_max_opt); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); @@ -3404,9 +3169,13 @@ extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); -extern void iterate_supers(void (*)(struct super_block *, void *), void *); +extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); +void filesystems_freeze(bool freeze_all); +void filesystems_thaw(void); + +void end_dirop(struct dentry *de); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); @@ -3421,6 +3190,8 @@ extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); +extern void __simple_unlink(struct inode *, struct dentry *); +extern void __simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, @@ -3430,17 +3201,23 @@ extern int simple_rename(struct mnt_idmap *, struct inode *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); +extern void simple_remove_by_name(struct dentry *, const char *, + void (*callback)(struct dentry *)); +extern void locked_recursive_removal(struct dentry *, + void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct folio **foliop, void **fsdata); +extern int simple_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); +struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, + const struct inode *context_inode); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); -extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); @@ -3454,6 +3231,8 @@ extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); +struct dentry *simple_start_creating(struct dentry *, const char *); +void simple_done_creating(struct dentry *); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); @@ -3468,7 +3247,6 @@ struct offset_ctx { void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); -int simple_offset_empty(struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, @@ -3517,7 +3295,8 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, * happens when a directory is casefolded and the filesystem is strict * about its encoding. */ -static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +static inline bool generic_ci_validate_strict_name(struct inode *dir, + const struct qstr *name) { if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) return true; @@ -3532,21 +3311,13 @@ static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qst return !utf8_validate(dir->i_sb->s_encoding, name); } #else -static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +static inline bool generic_ci_validate_strict_name(struct inode *dir, + const struct qstr *name) { return true; } #endif -static inline bool sb_has_encoding(const struct super_block *sb) -{ -#if IS_ENABLED(CONFIG_UNICODE) - return !!sb->s_encoding; -#else - return false; -#endif -} - int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); @@ -3556,9 +3327,14 @@ void setattr_copy(struct mnt_idmap *, struct inode *inode, extern int file_update_time(struct file *file); +static inline bool file_is_dax(const struct file *file) +{ + return file && IS_DAX(file->f_mapping->host); +} + static inline bool vma_is_dax(const struct vm_area_struct *vma) { - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); + return file_is_dax(vma->vm_file); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) @@ -3614,6 +3390,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } + if (flags & RWF_DONTCACHE) { + /* file system must support it */ + if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) + return -EOPNOTSUPP; + /* DAX mappings not supported */ + if (IS_DAX(ki->ki_filp->f_mapping->host)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3707,11 +3491,9 @@ struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) -#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) -#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & __FMODE_NONOTIFY))) +#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { @@ -3810,4 +3592,18 @@ static inline bool vfs_empty_path(int dfd, const char __user *path) int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); +static inline bool extensible_ioctl_valid(unsigned int cmd_a, + unsigned int cmd_b, size_t min_size) +{ + if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b)) + return false; + if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b)) + return false; + if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b)) + return false; + if (_IOC_SIZE(cmd_a) < min_size) + return false; + return true; +} + #endif /* _LINUX_FS_H */ |