Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ef118b8..42d246a 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>
@@ -48,6 +47,7 @@
struct bdi_writeback;
struct bio;
struct export_operations;
+struct fiemap_extent_info;
struct hd_geometry;
struct iovec;
struct kiocb;
@@ -67,7 +67,7 @@
struct fsverity_info;
struct fsverity_operations;
struct fs_context;
-struct fs_parameter_description;
+struct fs_parameter_spec;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -175,13 +175,8 @@
/* 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)
/*
* Attribute flags. These should be or-ed together to figure out what
@@ -292,6 +287,7 @@
struct page;
struct address_space;
struct writeback_control;
+struct readahead_control;
/*
* Write life time hint values.
@@ -306,14 +302,20 @@
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)
struct kiocb {
struct file *ki_filp;
@@ -327,7 +329,10 @@
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
- unsigned int ki_cookie; /* for ->iopoll */
+ union {
+ unsigned int ki_cookie; /* for ->iopoll */
+ struct wait_page_queue *ki_waitq; /* for async buffered IO */
+ };
randomized_struct_fields_end
};
@@ -375,6 +380,7 @@
*/
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,
@@ -468,45 +474,6 @@
* 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
@@ -526,6 +493,11 @@
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);
@@ -541,6 +513,16 @@
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 +533,7 @@
/*
* 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.
*
@@ -856,7 +838,7 @@
i_size = inode->i_size;
} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
return i_size;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
loff_t i_size;
preempt_disable();
@@ -881,7 +863,7 @@
inode->i_size = i_size;
write_seqcount_end(&inode->i_size_seqcount);
preempt_enable();
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
preempt_disable();
inode->i_size = i_size;
preempt_enable();
@@ -900,8 +882,6 @@
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 */
@@ -971,6 +951,7 @@
#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 */
@@ -1040,6 +1021,7 @@
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 *);
};
struct lock_manager {
@@ -1371,6 +1353,7 @@
#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 +1366,12 @@
#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 +1386,15 @@
#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 */
+
/* Possible states of 'frozen' field */
enum {
SB_UNFROZEN = 0, /* FS is unfrozen */
@@ -1451,6 +1442,10 @@
#ifdef CONFIG_FS_VERITY
const struct fsverity_operations *s_vop;
#endif
+#ifdef 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;
@@ -1515,6 +1510,9 @@
/* 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;
@@ -1576,15 +1574,30 @@
inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
}
-extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran);
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_)
@@ -1648,12 +1661,12 @@
*/
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);
}
/**
@@ -1669,15 +1682,15 @@
*
* 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);
}
/*
@@ -1695,12 +1708,12 @@
*/
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);
}
@@ -1717,7 +1730,11 @@
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 *);
+
+static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry)
+{
+ return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+}
extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode,
int open_flag);
@@ -1726,6 +1743,10 @@
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
@@ -1741,19 +1762,6 @@
extern void inode_init_owner(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);
/*
* This is the "filldir" function type, used by readdir() to let
@@ -1770,14 +1778,6 @@
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.
@@ -1908,16 +1908,8 @@
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,
@@ -1978,27 +1970,27 @@
/*
* 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/) */
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
@@ -2079,6 +2071,18 @@
};
}
+static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
+ struct file *filp)
+{
+ *kiocb = (struct kiocb) {
+ .ki_filp = filp,
+ .ki_flags = kiocb_src->ki_flags,
+ .ki_hint = kiocb_src->ki_hint,
+ .ki_ioprio = kiocb_src->ki_ioprio,
+ .ki_pos = kiocb_src->ki_pos,
+ };
+}
+
/*
* Inode state bits. Protected by inode->i_lock
*
@@ -2140,6 +2144,8 @@
*
* 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.
@@ -2164,6 +2170,7 @@
#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_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
@@ -2207,6 +2214,8 @@
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))
@@ -2226,9 +2235,10 @@
#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_THP_SUPPORT 8192 /* Remove once all fs converted */
#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_description *parameters;
+ const struct fs_parameter_spec *parameters;
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
void (*kill_sb) (struct super_block *);
@@ -2248,18 +2258,9 @@
#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));
@@ -2268,14 +2269,7 @@
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
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);
@@ -2556,10 +2550,6 @@
int (*open)(struct inode *, struct file *));
extern int finish_no_open(struct file *file, struct dentry *dentry);
-/* fs/ioctl.c */
-
-extern int ioctl_preallocate(struct file *filp, void __user *argp);
-
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(void);
@@ -2569,99 +2559,16 @@
#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;
+ return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
}
-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;
-}
-
-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);
-extern int __blkdev_reread_part(struct block_device *bdev);
-extern int blkdev_reread_part(struct block_device *bdev);
-
-#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
@@ -2692,38 +2599,19 @@
__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 void check_disk_size_change(struct gendisk *disk,
- struct block_device *bdev, bool verbose);
-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);
+void invalidate_mapping_pagevec(struct address_space *mapping,
+ pgoff_t start, pgoff_t end,
+ unsigned long *nr_pagevec);
+
static inline void invalidate_remote_inode(struct inode *inode)
{
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
@@ -2749,7 +2637,6 @@
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
loff_t lend);
-extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
@@ -2759,6 +2646,11 @@
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);
@@ -2792,7 +2684,7 @@
}
/**
- * filemap_check_wb_error - has an error occurred since the mark was sampled?
+ * filemap_check_wb_err - has an error occurred since the mark was sampled?
* @mapping: mapping to check for writeback errors
* @since: previously-sampled errseq_t
*
@@ -2819,31 +2711,16 @@
return errseq_sample(&mapping->wb_err);
}
-static inline int filemap_nr_thps(struct address_space *mapping)
+/**
+ * file_sample_sb_err - sample the current errseq_t to test for later errors
+ * @file: file pointer to be sampled
+ *
+ * Grab the most current superblock-level errseq_t value for the given
+ * struct file.
+ */
+static inline errseq_t file_sample_sb_err(struct file *file)
{
-#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
+ return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err);
}
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
@@ -2873,9 +2750,16 @@
extern void emergency_sync(void);
extern void emergency_remount(void);
+
#ifdef CONFIG_BLOCK
-extern sector_t bmap(struct inode *, sector_t);
+extern int bmap(struct inode *inode, sector_t *block);
+#else
+static inline int bmap(struct inode *inode, sector_t *block)
+{
+ return -EINVAL;
+}
#endif
+
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
extern int inode_permission(struct inode *, int);
extern int generic_permission(struct inode *, int);
@@ -2886,18 +2770,23 @@
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)
@@ -2968,43 +2857,8 @@
#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 *);
@@ -3033,6 +2887,7 @@
{
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 *),
@@ -3052,6 +2907,9 @@
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
@@ -3064,6 +2922,21 @@
extern unsigned int get_next_ino(void);
extern void evict_inodes(struct super_block *sb);
+/*
+ * 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 *);
extern void clear_inode(struct inode *);
@@ -3089,23 +2962,17 @@
extern void inode_sb_list_add(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);
+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);
+extern ssize_t generic_file_buffered_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 *);
@@ -3116,6 +2983,10 @@
rwf_t flags);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
rwf_t flags);
+ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
+ struct iov_iter *iter);
+ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
+ struct iov_iter *iter);
/* fs/block_dev.c */
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
@@ -3163,9 +3034,6 @@
DIO_SKIP_HOLES = 0x02,
};
-void dio_end_io(struct bio *bio);
-void dio_warn_stale_pagecache(struct file *filp);
-
ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter,
get_block_t get_block,
@@ -3209,6 +3077,11 @@
wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}
+/*
+ * Warn about a page cache invalidation failure diring a direct I/O write.
+ */
+void dio_warn_stale_pagecache(struct file *filp);
+
extern void inode_set_flags(struct inode *inode, unsigned int flags,
unsigned int mask);
@@ -3245,42 +3118,22 @@
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);
+ return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
}
-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);
-}
-
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);
@@ -3307,6 +3160,8 @@
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(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,
@@ -3348,6 +3203,12 @@
extern int generic_check_addressable(unsigned, u64);
+#ifdef CONFIG_UNICODE
+extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+ const char *str, const struct qstr *name);
+#endif
+
#ifdef CONFIG_MIGRATION
extern int buffer_migrate_page(struct address_space *,
struct page *, struct page *,
@@ -3366,12 +3227,7 @@
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);
}
@@ -3395,7 +3251,7 @@
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))
res |= IOCB_DSYNC;
@@ -3406,22 +3262,26 @@
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;
}
@@ -3447,7 +3307,7 @@
*/
struct simple_transaction_argresp {
ssize_t size;
- char data[0];
+ char data[];
};
#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
@@ -3508,11 +3368,11 @@
struct ctl_table;
int proc_nr_files(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos);
+ void *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);
+ void *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);
+ void *buffer, size_t *lenp, loff_t *ppos);
int __init get_filesystem_list(char *buf);
#define __FMODE_EXEC ((__force int) FMODE_EXEC)
@@ -3599,15 +3459,6 @@
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);