#include "xfs_pnfs.h"
#include "xfs_iomap.h"
#include "xfs_reflink.h"
+ #include "xfs_file.h"
#include <linux/dax.h>
#include <linux/falloc.h>
* Decide if the given file range is aligned to the size of the fundamental
* allocation unit for the file.
*/
- static bool
+ bool
xfs_is_falloc_aligned(
struct xfs_inode *ip,
loff_t pos,
long long int len)
{
- struct xfs_mount *mp = ip->i_mount;
- uint64_t mask;
-
- if (XFS_IS_REALTIME_INODE(ip)) {
- if (!is_power_of_2(mp->m_sb.sb_rextsize)) {
- u64 rextbytes;
- u32 mod;
-
- rextbytes = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize);
- div_u64_rem(pos, rextbytes, &mod);
- if (mod)
- return false;
- div_u64_rem(len, rextbytes, &mod);
- return mod == 0;
- }
- mask = XFS_FSB_TO_B(mp, mp->m_sb.sb_rextsize) - 1;
- } else {
- mask = mp->m_sb.sb_blocksize - 1;
- }
+ unsigned int alloc_unit = xfs_inode_alloc_unitsize(ip);
+
+ if (!is_power_of_2(alloc_unit))
+ return isaligned_64(pos, alloc_unit) &&
+ isaligned_64(len, alloc_unit);
- return !((pos | len) & mask);
+ return !((pos | len) & (alloc_unit - 1));
}
/*
return xfs_file_buffered_write(iocb, from);
}
- static void
- xfs_wait_dax_page(
- struct inode *inode)
- {
- struct xfs_inode *ip = XFS_I(inode);
-
- xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
- schedule();
- xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
- }
-
- int
- xfs_break_dax_layouts(
- struct inode *inode,
- bool *retry)
- {
- struct page *page;
-
- xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL);
-
- page = dax_layout_busy_page(inode->i_mapping);
- if (!page)
- return 0;
-
- *retry = true;
- return ___wait_var_event(&page->_refcount,
- atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
- 0, 0, xfs_wait_dax_page(inode));
- }
-
- int
- xfs_break_layouts(
- struct inode *inode,
- uint *iolock,
- enum layout_break_reason reason)
- {
- bool retry;
- int error;
-
- xfs_assert_ilocked(XFS_I(inode), XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL);
-
- do {
- retry = false;
- switch (reason) {
- case BREAK_UNMAP:
- error = xfs_break_dax_layouts(inode, &retry);
- if (error || retry)
- break;
- fallthrough;
- case BREAK_WRITE:
- error = xfs_break_leased_layouts(inode, iolock, &retry);
- break;
- default:
- WARN_ON_ONCE(1);
- error = -EINVAL;
- }
- } while (error == 0 && retry);
-
- return error;
- }
-
/* Does this file, inode, or mount want synchronous writes? */
static inline bool xfs_file_sync_writes(struct file *filp)
{
{
if (xfs_is_shutdown(XFS_M(inode->i_sb)))
return -EIO;
- file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC |
- FMODE_DIO_PARALLEL_WRITE | FMODE_CAN_ODIRECT;
+ file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
return generic_file_open(inode, file);
}
unsigned int mode;
int error;
- error = xfs_file_open(inode, file);
+ if (xfs_is_shutdown(ip->i_mount))
+ return -EIO;
+ error = generic_file_open(inode, file);
if (error)
return error;
.compat_ioctl = xfs_file_compat_ioctl,
#endif
.mmap = xfs_file_mmap,
- .mmap_supported_flags = MAP_SYNC,
.open = xfs_file_open,
.release = xfs_file_release,
.fsync = xfs_file_fsync,
.fallocate = xfs_file_fallocate,
.fadvise = xfs_file_fadvise,
.remap_file_range = xfs_file_remap_range,
+ .fop_flags = FOP_MMAP_SYNC | FOP_BUFFER_RASYNC |
+ FOP_BUFFER_WASYNC | FOP_DIO_PARALLEL_WRITE,
};
const struct file_operations xfs_dir_file_operations = {
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;
*/
/* file is open for reading */
-#define FMODE_READ ((__force fmode_t)0x1)
+#define FMODE_READ ((__force fmode_t)(1 << 0))
/* file is open for writing */
-#define FMODE_WRITE ((__force fmode_t)0x2)
+#define FMODE_WRITE ((__force fmode_t)(1 << 1))
/* file is seekable */
-#define FMODE_LSEEK ((__force fmode_t)0x4)
+#define FMODE_LSEEK ((__force fmode_t)(1 << 2))
/* file can be accessed using pread */
-#define FMODE_PREAD ((__force fmode_t)0x8)
+#define FMODE_PREAD ((__force fmode_t)(1 << 3))
/* file can be accessed using pwrite */
-#define FMODE_PWRITE ((__force fmode_t)0x10)
+#define FMODE_PWRITE ((__force fmode_t)(1 << 4))
/* File is opened for execution with sys_execve / sys_uselib */
-#define FMODE_EXEC ((__force fmode_t)0x20)
+#define FMODE_EXEC ((__force fmode_t)(1 << 5))
/* File writes are restricted (block device specific) */
-#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40)
+#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6))
+
+/* FMODE_* bits 7 to 8 */
+
/* 32bit hashes as llseek() offset (for directories) */
-#define FMODE_32BITHASH ((__force fmode_t)0x200)
+#define FMODE_32BITHASH ((__force fmode_t)(1 << 9))
/* 64bit hashes as llseek() offset (for directories) */
-#define FMODE_64BITHASH ((__force fmode_t)0x400)
+#define FMODE_64BITHASH ((__force fmode_t)(1 << 10))
/*
* Don't update ctime and mtime.
* Currently a special hack for the XFS open_by_handle ioctl, but we'll
* hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
*/
-#define FMODE_NOCMTIME ((__force fmode_t)0x800)
+#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11))
/* Expect random access pattern */
-#define FMODE_RANDOM ((__force fmode_t)0x1000)
+#define FMODE_RANDOM ((__force fmode_t)(1 << 12))
/* File is huge (eg. /dev/mem): treat loff_t as unsigned */
-#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
+#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13))
/* File is opened with O_PATH; almost nothing can be done with it */
-#define FMODE_PATH ((__force fmode_t)0x4000)
+#define FMODE_PATH ((__force fmode_t)(1 << 14))
/* File needs atomic accesses to f_pos */
-#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000)
+#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15))
/* Write access to underlying fs */
-#define FMODE_WRITER ((__force fmode_t)0x10000)
+#define FMODE_WRITER ((__force fmode_t)(1 << 16))
/* Has read method(s) */
-#define FMODE_CAN_READ ((__force fmode_t)0x20000)
+#define FMODE_CAN_READ ((__force fmode_t)(1 << 17))
/* Has write method(s) */
-#define FMODE_CAN_WRITE ((__force fmode_t)0x40000)
+#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18))
-#define FMODE_OPENED ((__force fmode_t)0x80000)
-#define FMODE_CREATED ((__force fmode_t)0x100000)
+#define FMODE_OPENED ((__force fmode_t)(1 << 19))
+#define FMODE_CREATED ((__force fmode_t)(1 << 20))
/* File is stream-like */
-#define FMODE_STREAM ((__force fmode_t)0x200000)
+#define FMODE_STREAM ((__force fmode_t)(1 << 21))
/* File supports DIRECT IO */
-#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000)
+#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22))
-#define FMODE_NOREUSE ((__force fmode_t)0x800000)
+#define FMODE_NOREUSE ((__force fmode_t)(1 << 23))
-/* File supports non-exclusive O_DIRECT writes from multiple threads */
-#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000)
+/* FMODE_* bit 24 */
/* File is embedded in backing_file object */
-#define FMODE_BACKING ((__force fmode_t)0x2000000)
+#define FMODE_BACKING ((__force fmode_t)(1 << 25))
/* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
+#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26))
/* File is capable of returning -EAGAIN if I/O will block */
-#define FMODE_NOWAIT ((__force fmode_t)0x8000000)
+#define FMODE_NOWAIT ((__force fmode_t)(1 << 27))
/* File represents mount that needs unmounting */
-#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000)
+#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28))
/* File does not contribute to nr_files count */
-#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000)
-
-/* File supports async buffered reads */
-#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000)
-
-/* File supports async nowait buffered writes */
-#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000)
+#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29))
/*
* Attribute flags. These should be or-ed together to figure out what
#define IOP_XATTR 0x0008
#define IOP_DEFAULT_READLINK 0x0010
-struct fsnotify_mark_connector;
-
/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
__u32 handle_bytes;
int handle_type;
/* file identifier */
- unsigned char f_handle[];
+ unsigned char f_handle[] __counted_by(handle_bytes);
};
static inline struct file *get_file(struct file *f)
{
- atomic_long_inc(&f->f_count);
+ long prior = atomic_long_fetch_inc_relaxed(&f->f_count);
+ WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n");
return f;
}
#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_UNSUPPORTED 0x00000080
+#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 */
/*
* Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
- * s_fsnotify_marks together for cache efficiency. They are frequently
+ * s_fsnotify_info together for cache efficiency. They are frequently
* accessed and rarely modified.
*/
void *s_fs_info; /* Filesystem private info */
time64_t s_time_max;
#ifdef CONFIG_FSNOTIFY
__u32 s_fsnotify_mask;
- struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
+ struct fsnotify_sb_info *s_fsnotify_info;
#endif
/*
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
- /*
- * Number of inode/mount/sb objects that are being watched, note that
- * inodes objects are currently double-accounted.
- */
- atomic_long_t s_fsnotify_connectors;
-
/* Read-only state of the superblock is being changed */
int s_readonly_remount;
struct io_uring_cmd;
struct offset_ctx;
+typedef unsigned int __bitwise fop_flags_t;
+
struct file_operations {
struct module *owner;
+ fop_flags_t fop_flags;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
- unsigned long mmap_supported_flags;
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
unsigned int poll_flags);
} __randomize_layout;
+/* Supports async buffered reads */
+#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0))
+/* Supports async buffered writes */
+#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1))
+/* Supports synchronous page faults for mappings */
+#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2))
+/* Supports non-exclusive O_DIRECT writes from multiple threads */
+#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3))
+/* Contains huge pages */
+#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4))
+
/* Wrap a directory iterator that needs exclusive inode access */
int wrap_directory_iterator(struct file *, struct dir_context *,
int (*) (struct file *, struct dir_context *));
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
+ int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write);
int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags,
#define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
+
+#ifdef CONFIG_SWAP
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
+#else
+#define IS_SWAPFILE(inode) ((void)(inode), 0U)
+#endif
+
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
* This must be used for allocating filesystems specific inodes to set
* up the inode reclaim context correctly.
*/
-static inline void *
-alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp)
-{
- return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp);
-}
+#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp)
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
static inline void insert_inode_hash(struct inode *inode)
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,
struct dentry *old_dentry,
struct inode *new_dir,