On success you get a new struct file sharing the mount/dentry with the
original, on failure - ERR_PTR().
--
+ [mandatory]
+ ->clone_file_range() and ->dedupe_file_range have been replaced with
+ ->remap_file_range(). See Documentation/filesystems/vfs.txt for more
+ information.
++--
+[recommended]
+ ->lookup() instances doing an equivalent of
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+ return d_splice_alias(inode, dentry);
+ don't need to bother with the check - d_splice_alias() will do the
+ right thing when given ERR_PTR(...) as inode. Moreover, passing NULL
+ inode to d_splice_alias() will also do the right thing (equivalent of
+ d_add(dentry, NULL); return NULL;), so that kind of special cases
+ also doesn't need a separate treatment.
extern struct kmem_cache *btrfs_free_space_cachep;
struct btrfs_ordered_sum;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-#define STATIC noinline
-#else
-#define STATIC static noinline
-#endif
-
#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
#define BTRFS_MAX_MIRRORS 3
struct mutex lock_finishing_cancel_unmount;
rwlock_t lock;
- atomic_t read_locks;
atomic_t blocking_readers;
wait_queue_head_t read_lock_wq;
struct btrfs_scrub_progress scrub_progress;
+
+ struct percpu_counter bio_counter;
+ wait_queue_head_t replace_wait;
};
/* For raid type sysfs entries */
/* device replace state */
struct btrfs_dev_replace dev_replace;
- struct percpu_counter bio_counter;
- wait_queue_head_t replace_wait;
-
struct semaphore uuid_tree_rescan_sem;
/* Used to reclaim the metadata space in the background. */
int last_log_commit;
pid_t log_start_pid;
- u64 objectid;
u64 last_trans;
u32 type;
u64 highest_objectid;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- /* only used with CONFIG_BTRFS_FS_RUN_SANITY_TESTS is enabled */
- u64 alloc_bytenr;
-#endif
-
u64 defrag_trans_start;
struct btrfs_key defrag_progress;
struct btrfs_key defrag_max;
spinlock_t qgroup_meta_rsv_lock;
u64 qgroup_meta_rsv_pertrans;
u64 qgroup_meta_rsv_prealloc;
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ u64 alloc_bytenr;
+#endif
};
struct btrfs_file_private {
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
}
-int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
-int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
+int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans);
+int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
enum btrfs_reserve_flush_enum flush);
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv, u64 num_bytes,
- int update_size);
+ bool update_size);
int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *dest, u64 num_bytes,
int min_factor);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_clear_path_blocking(struct btrfs_path *p,
- struct extent_buffer *held, int held_rw);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
const char *name, int name_len);
-int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, const char *name,
+int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name,
int name_len, struct btrfs_inode *dir,
struct btrfs_key *location, u8 type, u64 index);
struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *was_new);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
- struct page *page, size_t pg_offset,
- u64 start, u64 end, int create);
+ struct page *page, size_t pg_offset,
+ u64 start, u64 end, int create);
int btrfs_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode);
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
extern const struct dentry_operations btrfs_dentry_operations;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-void btrfs_test_inode_set_ops(struct inode *inode);
-#endif
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
struct btrfs_ioctl_space_info *space);
void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_balance_args *bargs);
- int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff,
- struct file *dst_file, loff_t dst_loff,
- u64 olen);
/* file.c */
int __init btrfs_auto_defrag_init(void);
size_t num_pages, loff_t pos, size_t write_bytes,
struct extent_state **cached);
int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
- int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len);
+ loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags);
/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode);
void btrfs_test_destroy_inode(struct inode *inode);
-#endif
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO,
- &fs_info->fs_state)))
- return 1;
-#endif
+ return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
+}
+#else
+static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
+{
return 0;
}
+#endif
static inline void cond_wake_up(struct wait_queue_head *wq)
{
end_of_last_block = start_pos + num_bytes - 1;
+ /*
+ * The pages may have already been dirty, clear out old accounting so
+ * we can set things up properly
+ */
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, end_of_last_block,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached);
+
if (!btrfs_is_free_space_inode(BTRFS_I(inode))) {
if (start_pos >= isize &&
!(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) {
}
if (ordered)
btrfs_put_ordered_extent(ordered);
- clear_extent_bit(&inode->io_tree, start_pos, last_pos,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
- 0, 0, cached_state);
+
*lockstart = start_pos;
*lockend = last_pos;
ret = 1;
}
+ /*
+ * It's possible the pages are dirty right now, but we don't want
+ * to clean them yet because copy_from_user may catch a page fault
+ * and we might have to fall back to one page at a time. If that
+ * happens, we'll unlock these pages and we'd have a window where
+ * reclaim could sneak in and drop the once-dirty page on the floor
+ * without writing it.
+ *
+ * We have the pages locked and the extent range locked, so there's
+ * no way someone can start IO on any dirty pages in this range.
+ *
+ * We'll call btrfs_dirty_pages() later on, and that will flip around
+ * delalloc bits and dirty the pages as required.
+ */
for (i = 0; i < num_pages; i++) {
- if (clear_page_dirty_for_io(pages[i]))
- account_page_redirty(pages[i]);
set_page_extent_mapped(pages[i]);
WARN_ON(!PageLocked(pages[i]));
}
goto out;
inode_lock(inode);
+
+ /*
+ * We take the dio_sem here because the tree log stuff can race with
+ * lockless dio writes and get an extent map logged for an extent we
+ * never waited on. We need it this high up for lockdep reasons.
+ */
+ down_write(&BTRFS_I(inode)->dio_sem);
+
atomic_inc(&root->log_batch);
/*
*/
ret = btrfs_wait_ordered_range(inode, start, len);
if (ret) {
+ up_write(&BTRFS_I(inode)->dio_sem);
inode_unlock(inode);
goto out;
}
* checked called fsync.
*/
ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err);
+ up_write(&BTRFS_I(inode)->dio_sem);
inode_unlock(inode);
goto out;
}
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
+ up_write(&BTRFS_I(inode)->dio_sem);
inode_unlock(inode);
goto out;
}
* file again, but that will end up using the synchronization
* inside btrfs_sync_log to keep things safe.
*/
+ up_write(&BTRFS_I(inode)->dio_sem);
inode_unlock(inode);
/*
}
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv,
- min_size, 0);
+ min_size, false);
BUG_ON(ret);
trans->block_rsv = rsv;
}
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
- rsv, min_size, 0);
+ rsv, min_size, false);
BUG_ON(ret); /* shouldn't happen */
trans->block_rsv = rsv;
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_compat_ioctl,
#endif
- .clone_file_range = btrfs_clone_file_range,
- .dedupe_file_range = btrfs_dedupe_file_range,
+ .remap_file_range = btrfs_remap_file_range,
};
void __cold btrfs_auto_defrag_exit(void)
struct fstrim_range range;
u64 minlen = ULLONG_MAX;
u64 num_devices = 0;
- u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EOPNOTSUPP;
if (copy_from_user(&range, arg, sizeof(range)))
return -EFAULT;
- if (range.start > total_bytes ||
- range.len < fs_info->sb->s_blocksize)
+
+ /*
+ * NOTE: Don't truncate the range using super->total_bytes. Bytenr of
+ * block group is in the logical address space, which can be any
+ * sectorsize aligned bytenr in the range [0, U64_MAX].
+ */
+ if (range.len < fs_info->sb->s_blocksize)
return -EINVAL;
- range.len = min(range.len, total_bytes - range.start);
range.minlen = max(range.minlen, minlen);
ret = btrfs_trim_fs(fs_info, &range);
if (ret < 0)
goto fail;
}
- ret = btrfs_insert_dir_item(trans, root,
- name, namelen, BTRFS_I(dir), &key,
+ ret = btrfs_insert_dir_item(trans, name, namelen, BTRFS_I(dir), &key,
BTRFS_FT_DIR, index);
if (ret) {
btrfs_abort_transaction(trans, ret);
if (i_done != page_cnt) {
spin_lock(&BTRFS_I(inode)->lock);
- BTRFS_I(inode)->outstanding_extents++;
+ btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(inode, data_reserved,
start_index << PAGE_SHIFT,
return ret;
}
- int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff,
- struct file *dst_file, loff_t dst_loff,
- u64 olen)
- {
- struct inode *src = file_inode(src_file);
- struct inode *dst = file_inode(dst_file);
- u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
-
- if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
- /*
- * Btrfs does not support blocksize < page_size. As a
- * result, btrfs_cmp_data() won't correctly handle
- * this situation without an update.
- */
- return -EINVAL;
- }
-
- return btrfs_extent_same(src, src_loff, olen, dst, dst_loff);
- }
-
static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
struct inode *inode,
u64 endoff,
return ret;
}
- int btrfs_clone_file_range(struct file *src_file, loff_t off,
- struct file *dst_file, loff_t destoff, u64 len)
+ loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff, loff_t len,
+ unsigned int remap_flags)
{
- return btrfs_clone_files(dst_file, src_file, off, len, destoff);
+ int ret;
+
+ if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+ return -EINVAL;
+
+ if (remap_flags & REMAP_FILE_DEDUP) {
+ struct inode *src = file_inode(src_file);
+ struct inode *dst = file_inode(dst_file);
+ u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
+
+ if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
+ /*
+ * Btrfs does not support blocksize < page_size. As a
+ * result, btrfs_cmp_data() won't correctly handle
+ * this situation without an update.
+ */
+ return -EINVAL;
+ }
+
+ ret = btrfs_extent_same(src, off, len, dst, destoff);
+ } else {
+ ret = btrfs_clone_files(dst_file, src_file, off, len, destoff);
+ }
+ return ret < 0 ? ret : len;
}
static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
ret = PTR_ERR(new_root);
goto out;
}
- if (!is_fstree(new_root->objectid)) {
+ if (!is_fstree(new_root->root_key.objectid)) {
ret = -ENOENT;
goto out;
}
MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server for "
"CIFS/SMB1 dialect (N/A for SMB3) "
"Default: 32767 Range: 2 to 32767.");
+#ifdef CONFIG_CIFS_STATS2
+unsigned int slow_rsp_threshold = 1;
+module_param(slow_rsp_threshold, uint, 0644);
+MODULE_PARM_DESC(slow_rsp_threshold, "Amount of time (in seconds) to wait "
+ "before logging that a response is delayed. "
+ "Default: 1 (if set to 0 disables msg).");
+#endif /* STATS2 */
+
module_param(enable_oplocks, bool, 0644);
MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
seq_puts(s, ",unix");
else
seq_puts(s, ",nounix");
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)
+ seq_puts(s, ",nodfs");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
seq_puts(s, ",posixpaths");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
struct cifs_mnt_data mnt_data;
struct dentry *root;
- cifs_dbg(FYI, "Devname: %s flags: %d\n", dev_name, flags);
+ /*
+ * Prints in Kernel / CIFS log the attempted mount operation
+ * If CIFS_DEBUG && cifs_FYI
+ */
+ if (cifsFYI)
+ cifs_dbg(FYI, "Devname: %s flags: %d\n", dev_name, flags);
+ else
+ cifs_info("Attempting to mount %s\n", dev_name);
volume_info = cifs_get_volume_info((char *)data, dev_name, is_smb3);
if (IS_ERR(volume_info))
.listxattr = cifs_listxattr,
};
- static int cifs_clone_file_range(struct file *src_file, loff_t off,
- struct file *dst_file, loff_t destoff, u64 len)
+ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff, loff_t len,
+ unsigned int remap_flags)
{
struct inode *src_inode = file_inode(src_file);
struct inode *target_inode = file_inode(dst_file);
unsigned int xid;
int rc;
+ if (remap_flags & ~REMAP_FILE_ADVISORY)
+ return -EINVAL;
+
cifs_dbg(FYI, "clone range\n");
xid = get_xid();
unlock_two_nondirectories(src_inode, target_inode);
out:
free_xid(xid);
- return rc;
+ return rc < 0 ? rc : len;
}
ssize_t cifs_file_copychunk_range(unsigned int xid,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
.splice_write = iter_file_splice_write,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
.splice_write = iter_file_splice_write,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.read = generic_read_dir,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
- .clone_file_range = cifs_clone_file_range,
+ .remap_file_range = cifs_remap_file_range,
.llseek = generic_file_llseek,
.fsync = cifs_dir_fsync,
};
#ifdef CONFIG_CIFS_STATS2
atomic_set(&totBufAllocCount, 0);
atomic_set(&totSmBufAllocCount, 0);
+ if (slow_rsp_threshold < 1)
+ cifs_dbg(FYI, "slow_response_threshold msgs disabled\n");
+ else if (slow_rsp_threshold > 32767)
+ cifs_dbg(VFS,
+ "slow response threshold set higher than recommended (0 to 32767)\n");
#endif /* CONFIG_CIFS_STATS2 */
atomic_set(&midCount, 0);
cifs_proc_clean();
}
-MODULE_AUTHOR("Steve French <sfrench@us.ibm.com>");
+MODULE_AUTHOR("Steve French");
MODULE_LICENSE("GPL"); /* combination of LGPL + GPL source behaves as GPL */
MODULE_DESCRIPTION
- ("VFS to access servers complying with the SNIA CIFS Specification "
- "e.g. Samba and Windows");
+ ("VFS to access SMB3 servers e.g. Samba, Macs, Azure and Windows (and "
+ "also older servers complying with the SNIA CIFS Specification)");
MODULE_VERSION(CIFS_VERSION);
MODULE_SOFTDEP("pre: arc4");
MODULE_SOFTDEP("pre: des");
u64 off, u64 olen, u64 destoff)
{
struct fd src_file = fdget(srcfd);
+ loff_t cloned;
int ret;
if (!src_file.file)
ret = -EXDEV;
if (src_file.file->f_path.mnt != dst_file->f_path.mnt)
goto fdput;
- ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+ cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff,
+ olen, 0);
+ if (cloned < 0)
+ ret = cloned;
+ else if (olen && cloned != olen)
+ ret = -EINVAL;
+ else
+ ret = 0;
fdput:
fdput(src_file);
return ret;
return ioctl_fiemap(filp, arg);
case FIGETBSZ:
+ /* anon_bdev filesystems may not have a block size */
+ if (!inode->i_sb->s_blocksize)
+ return -EINVAL;
return put_user(inode->i_sb->s_blocksize, argp);
case FICLONE:
__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
u64 dst_pos, u64 count)
{
- return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos,
- count));
+ loff_t cloned;
+
+ cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0);
+ if (count && cloned != count)
+ cloned = -EINVAL;
+ return nfserrno(cloned < 0 ? cloned : 0);
}
ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
int host_err;
trace_nfsd_read_vector(rqstp, fhp, offset, *count);
- iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count);
+ iov_iter_kvec(&iter, READ, vec, vlen, *count);
host_err = vfs_iter_read(file, &iter, &offset, 0);
return nfsd_finish_read(rqstp, fhp, file, offset, count, host_err);
}
if (stable && !use_wgather)
flags |= RWF_SYNC;
- iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt);
+ iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt);
host_err = vfs_iter_write(file, &iter, &pos, flags);
if (host_err < 0)
goto out_nfserr;
int type, dev_t rdev, struct svc_fh *resfhp)
{
struct dentry *dentry, *dchild = NULL;
- struct inode *dirp;
__be32 err;
int host_err;
return err;
dentry = fhp->fh_dentry;
- dirp = d_inode(dentry);
host_err = fh_want_write(fhp);
if (host_err)
*created = 1;
break;
}
+ /* fall through */
case NFS4_CREATE_EXCLUSIVE4_1:
if ( d_inode(dchild)->i_mtime.tv_sec == v_mtime
&& d_inode(dchild)->i_atime.tv_sec == v_atime
*created = 1;
goto set_attr;
}
- /* fallthru */
+ /* fall through */
case NFS3_CREATE_GUARDED:
err = nfserr_exist;
}
struct buffer_head *ref_root_bh = NULL;
struct ocfs2_cached_dealloc_ctxt dealloc;
struct ocfs2_super *osb = OCFS2_SB(s_inode->i_sb);
- struct ocfs2_refcount_block *rb;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)s_bh->b_data;
struct ocfs2_refcount_tree *ref_tree;
mlog_errno(ret);
goto out;
}
- rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data;
ret = ocfs2_duplicate_extent_list(s_inode, t_inode, t_bh,
&ref_tree->rf_ci, ref_root_bh,
}
/* Update destination inode size, if necessary. */
- static int ocfs2_reflink_update_dest(struct inode *dest,
- struct buffer_head *d_bh,
- loff_t newlen)
+ int ocfs2_reflink_update_dest(struct inode *dest,
+ struct buffer_head *d_bh,
+ loff_t newlen)
{
handle_t *handle;
int ret;
}
/* Remap the range pos_in:len in s_inode to pos_out:len in t_inode. */
- static int ocfs2_reflink_remap_extent(struct inode *s_inode,
- struct buffer_head *s_bh,
- loff_t pos_in,
- struct inode *t_inode,
- struct buffer_head *t_bh,
- loff_t pos_out,
- loff_t len,
- struct ocfs2_cached_dealloc_ctxt *dealloc)
+ static loff_t ocfs2_reflink_remap_extent(struct inode *s_inode,
+ struct buffer_head *s_bh,
+ loff_t pos_in,
+ struct inode *t_inode,
+ struct buffer_head *t_bh,
+ loff_t pos_out,
+ loff_t len,
+ struct ocfs2_cached_dealloc_ctxt *dealloc)
{
struct ocfs2_extent_tree s_et;
struct ocfs2_extent_tree t_et;
struct buffer_head *ref_root_bh = NULL;
struct ocfs2_refcount_tree *ref_tree;
struct ocfs2_super *osb;
+ loff_t remapped_bytes = 0;
loff_t pstart, plen;
- u32 p_cluster, num_clusters, slast, spos, tpos;
+ u32 p_cluster, num_clusters, slast, spos, tpos, remapped_clus = 0;
unsigned int ext_flags;
int ret = 0;
next_loop:
spos += num_clusters;
tpos += num_clusters;
+ remapped_clus += num_clusters;
}
- out:
- return ret;
+ goto out;
out_unlock_refcount:
ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
brelse(ref_root_bh);
- return ret;
+ out:
+ remapped_bytes = ocfs2_clusters_to_bytes(t_inode->i_sb, remapped_clus);
+ remapped_bytes = min_t(loff_t, len, remapped_bytes);
+
+ return remapped_bytes > 0 ? remapped_bytes : ret;
}
/* Set up refcount tree and remap s_inode to t_inode. */
- static int ocfs2_reflink_remap_blocks(struct inode *s_inode,
- struct buffer_head *s_bh,
- loff_t pos_in,
- struct inode *t_inode,
- struct buffer_head *t_bh,
- loff_t pos_out,
- loff_t len)
+ loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode,
+ struct buffer_head *s_bh,
+ loff_t pos_in,
+ struct inode *t_inode,
+ struct buffer_head *t_bh,
+ loff_t pos_out,
+ loff_t len)
{
struct ocfs2_cached_dealloc_ctxt dealloc;
struct ocfs2_super *osb;
struct ocfs2_dinode *dis;
struct ocfs2_dinode *dit;
- int ret;
+ loff_t ret;
osb = OCFS2_SB(s_inode->i_sb);
dis = (struct ocfs2_dinode *)s_bh->b_data;
/* Actually remap extents now. */
ret = ocfs2_reflink_remap_extent(s_inode, s_bh, pos_in, t_inode, t_bh,
pos_out, len, &dealloc);
- if (ret) {
+ if (ret < 0) {
mlog_errno(ret);
goto out;
}
}
/* Lock an inode and grab a bh pointing to the inode. */
- static int ocfs2_reflink_inodes_lock(struct inode *s_inode,
- struct buffer_head **bh1,
- struct inode *t_inode,
- struct buffer_head **bh2)
+ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
+ struct buffer_head **bh1,
+ struct inode *t_inode,
+ struct buffer_head **bh2)
{
struct inode *inode1;
struct inode *inode2;
}
/* Unlock both inodes and release buffers. */
- static void ocfs2_reflink_inodes_unlock(struct inode *s_inode,
- struct buffer_head *s_bh,
- struct inode *t_inode,
- struct buffer_head *t_bh)
+ void ocfs2_reflink_inodes_unlock(struct inode *s_inode,
+ struct buffer_head *s_bh,
+ struct inode *t_inode,
+ struct buffer_head *t_bh)
{
ocfs2_inode_unlock(s_inode, 1);
ocfs2_rw_unlock(s_inode, 1);
}
unlock_two_nondirectories(s_inode, t_inode);
}
-
- /* Link a range of blocks from one file to another. */
- int ocfs2_reflink_remap_range(struct file *file_in,
- loff_t pos_in,
- struct file *file_out,
- loff_t pos_out,
- u64 len,
- bool is_dedupe)
- {
- struct inode *inode_in = file_inode(file_in);
- struct inode *inode_out = file_inode(file_out);
- struct ocfs2_super *osb = OCFS2_SB(inode_in->i_sb);
- struct buffer_head *in_bh = NULL, *out_bh = NULL;
- bool same_inode = (inode_in == inode_out);
- ssize_t ret;
-
- if (!ocfs2_refcount_tree(osb))
- return -EOPNOTSUPP;
- if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
- return -EROFS;
-
- /* Lock both files against IO */
- ret = ocfs2_reflink_inodes_lock(inode_in, &in_bh, inode_out, &out_bh);
- if (ret)
- return ret;
-
- /* Check file eligibility and prepare for block sharing. */
- ret = -EINVAL;
- if ((OCFS2_I(inode_in)->ip_flags & OCFS2_INODE_SYSTEM_FILE) ||
- (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE))
- goto out_unlock;
-
- ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
- &len, is_dedupe);
- if (ret <= 0)
- goto out_unlock;
-
- /* Lock out changes to the allocation maps and remap. */
- down_write(&OCFS2_I(inode_in)->ip_alloc_sem);
- if (!same_inode)
- down_write_nested(&OCFS2_I(inode_out)->ip_alloc_sem,
- SINGLE_DEPTH_NESTING);
-
- ret = ocfs2_reflink_remap_blocks(inode_in, in_bh, pos_in, inode_out,
- out_bh, pos_out, len);
-
- /* Zap any page cache for the destination file's range. */
- if (!ret)
- truncate_inode_pages_range(&inode_out->i_data, pos_out,
- PAGE_ALIGN(pos_out + len) - 1);
-
- up_write(&OCFS2_I(inode_in)->ip_alloc_sem);
- if (!same_inode)
- up_write(&OCFS2_I(inode_out)->ip_alloc_sem);
- if (ret) {
- mlog_errno(ret);
- goto out_unlock;
- }
-
- /*
- * Empty the extent map so that we may get the right extent
- * record from the disk.
- */
- ocfs2_extent_map_trunc(inode_in, 0);
- ocfs2_extent_map_trunc(inode_out, 0);
-
- ret = ocfs2_reflink_update_dest(inode_out, out_bh, pos_out + len);
- if (ret) {
- mlog_errno(ret);
- goto out_unlock;
- }
-
- ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh);
- return 0;
-
- out_unlock:
- ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh);
- return ret;
- }
struct file *new_file;
loff_t old_pos = 0;
loff_t new_pos = 0;
+ loff_t cloned;
int error = 0;
if (len == 0)
}
/* Try to use clone_file_range to clone up within the same fs */
- error = do_clone_file_range(old_file, 0, new_file, 0, len);
- if (!error)
+ cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0);
+ if (cloned == len)
goto out;
/* Couldn't clone, so now we try to copy the data */
- error = 0;
/* FIXME: copy up sparse files efficiently */
while (len) {
struct dentry *destdir;
struct qstr destname;
struct dentry *workdir;
- bool tmpfile;
bool origin;
bool indexed;
bool metacopy;
return err;
}
-static int ovl_install_temp(struct ovl_copy_up_ctx *c, struct dentry *temp,
- struct dentry **newdentry)
-{
- int err;
- struct dentry *upper;
- struct inode *udir = d_inode(c->destdir);
-
- upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
- if (IS_ERR(upper))
- return PTR_ERR(upper);
-
- if (c->tmpfile)
- err = ovl_do_link(temp, udir, upper);
- else
- err = ovl_do_rename(d_inode(c->workdir), temp, udir, upper, 0);
-
- if (!err)
- *newdentry = dget(c->tmpfile ? upper : temp);
- dput(upper);
-
- return err;
-}
-
-static struct dentry *ovl_get_tmpfile(struct ovl_copy_up_ctx *c)
-{
- int err;
- struct dentry *temp;
- const struct cred *old_creds = NULL;
- struct cred *new_creds = NULL;
- struct ovl_cattr cattr = {
- /* Can't properly set mode on creation because of the umask */
- .mode = c->stat.mode & S_IFMT,
- .rdev = c->stat.rdev,
- .link = c->link
- };
-
- err = security_inode_copy_up(c->dentry, &new_creds);
- temp = ERR_PTR(err);
- if (err < 0)
- goto out;
-
- if (new_creds)
- old_creds = override_creds(new_creds);
-
- if (c->tmpfile)
- temp = ovl_do_tmpfile(c->workdir, c->stat.mode);
- else
- temp = ovl_create_temp(c->workdir, &cattr);
-out:
- if (new_creds) {
- revert_creds(old_creds);
- put_cred(new_creds);
- }
-
- return temp;
-}
-
static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
{
int err;
return err;
}
-static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
+struct ovl_cu_creds {
+ const struct cred *old;
+ struct cred *new;
+};
+
+static int ovl_prep_cu_creds(struct dentry *dentry, struct ovl_cu_creds *cc)
+{
+ int err;
+
+ cc->old = cc->new = NULL;
+ err = security_inode_copy_up(dentry, &cc->new);
+ if (err < 0)
+ return err;
+
+ if (cc->new)
+ cc->old = override_creds(cc->new);
+
+ return 0;
+}
+
+static void ovl_revert_cu_creds(struct ovl_cu_creds *cc)
+{
+ if (cc->new) {
+ revert_creds(cc->old);
+ put_cred(cc->new);
+ }
+}
+
+/*
+ * Copyup using workdir to prepare temp file. Used when copying up directories,
+ * special files or when upper fs doesn't support O_TMPFILE.
+ */
+static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
{
- struct inode *udir = c->destdir->d_inode;
struct inode *inode;
- struct dentry *newdentry = NULL;
- struct dentry *temp;
+ struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir);
+ struct dentry *temp, *upper;
+ struct ovl_cu_creds cc;
int err;
+ struct ovl_cattr cattr = {
+ /* Can't properly set mode on creation because of the umask */
+ .mode = c->stat.mode & S_IFMT,
+ .rdev = c->stat.rdev,
+ .link = c->link
+ };
- temp = ovl_get_tmpfile(c);
+ err = ovl_lock_rename_workdir(c->workdir, c->destdir);
+ if (err)
+ return err;
+
+ err = ovl_prep_cu_creds(c->dentry, &cc);
+ if (err)
+ goto unlock;
+
+ temp = ovl_create_temp(c->workdir, &cattr);
+ ovl_revert_cu_creds(&cc);
+
+ err = PTR_ERR(temp);
if (IS_ERR(temp))
- return PTR_ERR(temp);
+ goto unlock;
err = ovl_copy_up_inode(c, temp);
if (err)
- goto out;
+ goto cleanup;
if (S_ISDIR(c->stat.mode) && c->indexed) {
err = ovl_create_index(c->dentry, c->lowerpath.dentry, temp);
if (err)
- goto out;
+ goto cleanup;
}
- if (c->tmpfile) {
- inode_lock_nested(udir, I_MUTEX_PARENT);
- err = ovl_install_temp(c, temp, &newdentry);
- inode_unlock(udir);
- } else {
- err = ovl_install_temp(c, temp, &newdentry);
- }
+ upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto cleanup;
+
+ err = ovl_do_rename(wdir, temp, udir, upper, 0);
+ dput(upper);
if (err)
- goto out;
+ goto cleanup;
if (!c->metacopy)
ovl_set_upperdata(d_inode(c->dentry));
inode = d_inode(c->dentry);
- ovl_inode_update(inode, newdentry);
+ ovl_inode_update(inode, temp);
if (S_ISDIR(inode->i_mode))
ovl_set_flag(OVL_WHITEOUTS, inode);
+unlock:
+ unlock_rename(c->workdir, c->destdir);
-out:
- if (err && !c->tmpfile)
- ovl_cleanup(d_inode(c->workdir), temp);
- dput(temp);
return err;
+cleanup:
+ ovl_cleanup(wdir, temp);
+ dput(temp);
+ goto unlock;
+}
+
+/* Copyup using O_TMPFILE which does not require cross dir locking */
+static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
+{
+ struct inode *udir = d_inode(c->destdir);
+ struct dentry *temp, *upper;
+ struct ovl_cu_creds cc;
+ int err;
+
+ err = ovl_prep_cu_creds(c->dentry, &cc);
+ if (err)
+ return err;
+
+ temp = ovl_do_tmpfile(c->workdir, c->stat.mode);
+ ovl_revert_cu_creds(&cc);
+
+ if (IS_ERR(temp))
+ return PTR_ERR(temp);
+
+ err = ovl_copy_up_inode(c, temp);
+ if (err)
+ goto out_dput;
+
+ inode_lock_nested(udir, I_MUTEX_PARENT);
+
+ upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
+ err = PTR_ERR(upper);
+ if (!IS_ERR(upper)) {
+ err = ovl_do_link(temp, udir, upper);
+ dput(upper);
+ }
+ inode_unlock(udir);
+
+ if (err)
+ goto out_dput;
+
+ if (!c->metacopy)
+ ovl_set_upperdata(d_inode(c->dentry));
+ ovl_inode_update(d_inode(c->dentry), temp);
+
+ return 0;
+
+out_dput:
+ dput(temp);
+ return err;
}
/*
}
/* Should we copyup with O_TMPFILE or with workdir? */
- if (S_ISREG(c->stat.mode) && ofs->tmpfile) {
- c->tmpfile = true;
- err = ovl_copy_up_locked(c);
- } else {
- err = ovl_lock_rename_workdir(c->workdir, c->destdir);
- if (!err) {
- err = ovl_copy_up_locked(c);
- unlock_rename(c->workdir, c->destdir);
- }
- }
-
-
+ if (S_ISREG(c->stat.mode) && ofs->tmpfile)
+ err = ovl_copy_up_tmpfile(c);
+ else
+ err = ovl_copy_up_workdir(c);
if (err)
goto out;
}
#endif
-#ifdef __ARCH_WANT_SYS_LLSEEK
+#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT)
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned long, offset_low, loff_t __user *, result,
unsigned int, whence)
goto fput_in;
if (!(out.file->f_mode & FMODE_WRITE))
goto fput_out;
- retval = -EINVAL;
in_inode = file_inode(in.file);
out_inode = file_inode(out.file);
out_pos = out.file->f_pos;
* Try cloning first, this is supported by more file systems, and
* more efficient if both clone and copy are supported (e.g. NFS).
*/
- if (file_in->f_op->clone_file_range) {
- ret = file_in->f_op->clone_file_range(file_in, pos_in,
- file_out, pos_out, len);
- if (ret == 0) {
- ret = len;
+ if (file_in->f_op->remap_file_range) {
+ loff_t cloned;
+
+ cloned = file_in->f_op->remap_file_range(file_in, pos_in,
+ file_out, pos_out,
+ min_t(loff_t, MAX_RW_COUNT, len),
+ REMAP_FILE_CAN_SHORTEN);
+ if (cloned > 0) {
+ ret = cloned;
goto done;
}
}
return ret;
}
- static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
+ static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
+ bool write)
{
struct inode *inode = file_inode(file);
- if (unlikely(pos < 0))
+ if (unlikely(pos < 0 || len < 0))
return -EINVAL;
if (unlikely((loff_t) (pos + len) < 0))
return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
}
+ /*
+ * Ensure that we don't remap a partial EOF block in the middle of something
+ * else. Assume that the offsets have already been checked for block
+ * alignment.
+ *
+ * For deduplication we always scale down to the previous block because we
+ * can't meaningfully compare post-EOF contents.
+ *
+ * For clone we only link a partial EOF block above the destination file's EOF.
+ *
+ * Shorten the request if possible.
+ */
+ static int generic_remap_check_len(struct inode *inode_in,
+ struct inode *inode_out,
+ loff_t pos_out,
+ loff_t *len,
+ unsigned int remap_flags)
+ {
+ u64 blkmask = i_blocksize(inode_in) - 1;
+ loff_t new_len = *len;
+
+ if ((*len & blkmask) == 0)
+ return 0;
+
+ if ((remap_flags & REMAP_FILE_DEDUP) ||
+ pos_out + *len < i_size_read(inode_out))
+ new_len &= ~blkmask;
+
+ if (new_len == *len)
+ return 0;
+
+ if (remap_flags & REMAP_FILE_CAN_SHORTEN) {
+ *len = new_len;
+ return 0;
+ }
+
+ return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
+ }
+
+ /*
+ * Read a page's worth of file data into the page cache. Return the page
+ * locked.
+ */
+ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
+ {
+ struct page *page;
+
+ page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL);
+ if (IS_ERR(page))
+ return page;
+ if (!PageUptodate(page)) {
+ put_page(page);
+ return ERR_PTR(-EIO);
+ }
+ lock_page(page);
+ return page;
+ }
+
+ /*
+ * Compare extents of two files to see if they are the same.
+ * Caller must have locked both inodes to prevent write races.
+ */
+ static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+ struct inode *dest, loff_t destoff,
+ loff_t len, bool *is_same)
+ {
+ loff_t src_poff;
+ loff_t dest_poff;
+ void *src_addr;
+ void *dest_addr;
+ struct page *src_page;
+ struct page *dest_page;
+ loff_t cmp_len;
+ bool same;
+ int error;
+
+ error = -EINVAL;
+ same = true;
+ while (len) {
+ src_poff = srcoff & (PAGE_SIZE - 1);
+ dest_poff = destoff & (PAGE_SIZE - 1);
+ cmp_len = min(PAGE_SIZE - src_poff,
+ PAGE_SIZE - dest_poff);
+ cmp_len = min(cmp_len, len);
+ if (cmp_len <= 0)
+ goto out_error;
+
+ src_page = vfs_dedupe_get_page(src, srcoff);
+ if (IS_ERR(src_page)) {
+ error = PTR_ERR(src_page);
+ goto out_error;
+ }
+ dest_page = vfs_dedupe_get_page(dest, destoff);
+ if (IS_ERR(dest_page)) {
+ error = PTR_ERR(dest_page);
+ unlock_page(src_page);
+ put_page(src_page);
+ goto out_error;
+ }
+ src_addr = kmap_atomic(src_page);
+ dest_addr = kmap_atomic(dest_page);
+
+ flush_dcache_page(src_page);
+ flush_dcache_page(dest_page);
+
+ if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
+ same = false;
+
+ kunmap_atomic(dest_addr);
+ kunmap_atomic(src_addr);
+ unlock_page(dest_page);
+ unlock_page(src_page);
+ put_page(dest_page);
+ put_page(src_page);
+
+ if (!same)
+ break;
+
+ srcoff += cmp_len;
+ destoff += cmp_len;
+ len -= cmp_len;
+ }
+
+ *is_same = same;
+ return 0;
+
+ out_error:
+ return error;
+ }
/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
- * Returns: 0 for "nothing to clone", 1 for "something to clone", or
- * the usual negative error code.
+ * If there's an error, then the usual negative error code is returned.
+ * Otherwise returns 0 with *len set to the request length.
*/
- int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
- struct inode *inode_out, loff_t pos_out,
- u64 *len, bool is_dedupe)
+ 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)
{
- loff_t bs = inode_out->i_sb->s_blocksize;
- loff_t blen;
- loff_t isize;
+ struct inode *inode_in = file_inode(file_in);
+ struct inode *inode_out = file_inode(file_out);
bool same_inode = (inode_in == inode_out);
int ret;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
- /* Are we going all the way to the end? */
- isize = i_size_read(inode_in);
- if (isize == 0)
- return 0;
-
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
- if (is_dedupe || pos_in == isize)
+ loff_t isize = i_size_read(inode_in);
+
+ if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
+ if (*len == 0)
+ return 0;
}
- /* Ensure offsets don't wrap and the input is inside i_size */
- if (pos_in + *len < pos_in || pos_out + *len < pos_out ||
- pos_in + *len > isize)
- return -EINVAL;
-
- /* Don't allow dedupe past EOF in the dest file */
- if (is_dedupe) {
- loff_t disize;
-
- disize = i_size_read(inode_out);
- if (pos_out >= disize || pos_out + *len > disize)
- return -EINVAL;
- }
-
- /* If we're linking to EOF, continue to the block boundary. */
- if (pos_in + *len == isize)
- blen = ALIGN(isize, bs) - pos_in;
- else
- blen = *len;
-
- /* Only reflink if we're aligned to block boundaries */
- if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
- !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
- return -EINVAL;
-
- /* Don't allow overlapped reflink within the same file */
- if (same_inode) {
- if (pos_out + blen > pos_in && pos_out < pos_in + blen)
- return -EINVAL;
- }
+ /* Check that we don't violate system file offset limits. */
+ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
+ remap_flags);
+ if (ret)
+ return ret;
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
/*
* Check that the extents are the same.
*/
- if (is_dedupe) {
+ if (remap_flags & REMAP_FILE_DEDUP) {
bool is_same = false;
ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
return -EBADE;
}
- return 1;
+ ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
+ remap_flags);
+ if (ret)
+ return ret;
+
+ /* If can't alter the file contents, we're done. */
+ if (!(remap_flags & REMAP_FILE_DEDUP)) {
+ /* Update the timestamps, since we can alter file contents. */
+ if (!(file_out->f_mode & FMODE_NOCMTIME)) {
+ ret = file_update_time(file_out);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Clear the security bits if the process is not being run by
+ * root. This keeps people from modifying setuid and setgid
+ * binaries.
+ */
+ ret = file_remove_privs(file_out);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
}
- EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
+ EXPORT_SYMBOL(generic_remap_file_range_prep);
- int do_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len)
+ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
- int ret;
+ loff_t ret;
+
+ WARN_ON_ONCE(remap_flags);
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
(file_out->f_flags & O_APPEND))
return -EBADF;
- if (!file_in->f_op->clone_file_range)
+ if (!file_in->f_op->remap_file_range)
return -EOPNOTSUPP;
- ret = clone_verify_area(file_in, pos_in, len, false);
+ ret = remap_verify_area(file_in, pos_in, len, false);
if (ret)
return ret;
- ret = clone_verify_area(file_out, pos_out, len, true);
+ ret = remap_verify_area(file_out, pos_out, len, true);
if (ret)
return ret;
- if (pos_in + len > i_size_read(inode_in))
- return -EINVAL;
-
- ret = file_in->f_op->clone_file_range(file_in, pos_in,
- file_out, pos_out, len);
- if (!ret) {
- fsnotify_access(file_in);
- fsnotify_modify(file_out);
- }
+ ret = file_in->f_op->remap_file_range(file_in, pos_in,
+ file_out, pos_out, len, remap_flags);
+ if (ret < 0)
+ return ret;
+ fsnotify_access(file_in);
+ fsnotify_modify(file_out);
return ret;
}
EXPORT_SYMBOL(do_clone_file_range);
- int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len)
+ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags)
{
- int ret;
+ loff_t ret;
file_start_write(file_out);
- ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+ ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len,
+ remap_flags);
file_end_write(file_out);
return ret;
}
EXPORT_SYMBOL(vfs_clone_file_range);
- /*
- * Read a page's worth of file data into the page cache. Return the page
- * locked.
- */
- static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
- {
- struct address_space *mapping;
- struct page *page;
- pgoff_t n;
-
- n = offset >> PAGE_SHIFT;
- mapping = inode->i_mapping;
- page = read_mapping_page(mapping, n, NULL);
- if (IS_ERR(page))
- return page;
- if (!PageUptodate(page)) {
- put_page(page);
- return ERR_PTR(-EIO);
- }
- lock_page(page);
- return page;
- }
-
- /*
- * Compare extents of two files to see if they are the same.
- * Caller must have locked both inodes to prevent write races.
- */
- int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
- struct inode *dest, loff_t destoff,
- loff_t len, bool *is_same)
- {
- loff_t src_poff;
- loff_t dest_poff;
- void *src_addr;
- void *dest_addr;
- struct page *src_page;
- struct page *dest_page;
- loff_t cmp_len;
- bool same;
- int error;
-
- error = -EINVAL;
- same = true;
- while (len) {
- src_poff = srcoff & (PAGE_SIZE - 1);
- dest_poff = destoff & (PAGE_SIZE - 1);
- cmp_len = min(PAGE_SIZE - src_poff,
- PAGE_SIZE - dest_poff);
- cmp_len = min(cmp_len, len);
- if (cmp_len <= 0)
- goto out_error;
-
- src_page = vfs_dedupe_get_page(src, srcoff);
- if (IS_ERR(src_page)) {
- error = PTR_ERR(src_page);
- goto out_error;
- }
- dest_page = vfs_dedupe_get_page(dest, destoff);
- if (IS_ERR(dest_page)) {
- error = PTR_ERR(dest_page);
- unlock_page(src_page);
- put_page(src_page);
- goto out_error;
- }
- src_addr = kmap_atomic(src_page);
- dest_addr = kmap_atomic(dest_page);
-
- flush_dcache_page(src_page);
- flush_dcache_page(dest_page);
-
- if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len))
- same = false;
-
- kunmap_atomic(dest_addr);
- kunmap_atomic(src_addr);
- unlock_page(dest_page);
- unlock_page(src_page);
- put_page(dest_page);
- put_page(src_page);
-
- if (!same)
- break;
-
- srcoff += cmp_len;
- destoff += cmp_len;
- len -= cmp_len;
- }
-
- *is_same = same;
- return 0;
-
- out_error:
- return error;
- }
- EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
-
+/* Check whether we are allowed to dedupe the destination file */
+static bool allow_file_dedupe(struct file *file)
+{
+ if (capable(CAP_SYS_ADMIN))
+ return true;
+ if (file->f_mode & FMODE_WRITE)
+ return true;
+ if (uid_eq(current_fsuid(), file_inode(file)->i_uid))
+ return true;
+ if (!inode_permission(file_inode(file), MAY_WRITE))
+ return true;
+ return false;
+}
+
- int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
- struct file *dst_file, loff_t dst_pos, u64 len)
+ 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)
{
- s64 ret;
+ loff_t ret;
+
+ WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP |
+ REMAP_FILE_CAN_SHORTEN));
ret = mnt_want_write_file(dst_file);
if (ret)
return ret;
- ret = clone_verify_area(dst_file, dst_pos, len, true);
+ ret = remap_verify_area(dst_file, dst_pos, len, true);
if (ret < 0)
goto out_drop_write;
- ret = -EINVAL;
- if (!(capable(CAP_SYS_ADMIN) || (dst_file->f_mode & FMODE_WRITE)))
+ ret = -EPERM;
+ if (!allow_file_dedupe(dst_file))
goto out_drop_write;
ret = -EXDEV;
goto out_drop_write;
ret = -EINVAL;
- if (!dst_file->f_op->dedupe_file_range)
+ if (!dst_file->f_op->remap_file_range)
goto out_drop_write;
- ret = dst_file->f_op->dedupe_file_range(src_file, src_pos,
- dst_file, dst_pos, len);
+ if (len == 0) {
+ ret = 0;
+ goto out_drop_write;
+ }
+
+ ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file,
+ dst_pos, len, remap_flags | REMAP_FILE_DEDUP);
out_drop_write:
mnt_drop_write_file(dst_file);
int i;
int ret;
u16 count = same->dest_count;
- int deduped;
+ loff_t deduped;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
if (!S_ISREG(src->i_mode))
goto out;
- ret = clone_verify_area(file, off, len, false);
+ ret = remap_verify_area(file, off, len, false);
if (ret < 0)
goto out;
ret = 0;
}
deduped = vfs_dedupe_file_range_one(file, off, dst_file,
- info->dest_offset, len);
+ info->dest_offset, len,
+ REMAP_FILE_CAN_SHORTEN);
if (deduped == -EBADE)
info->status = FILE_DEDUPE_RANGE_DIFFERS;
else if (deduped < 0)
xfs_reflink_trim_around_shared(
struct xfs_inode *ip,
struct xfs_bmbt_irec *irec,
- bool *shared,
- bool *trimmed)
+ bool *shared)
{
xfs_agnumber_t agno;
xfs_agblock_t agbno;
if (error)
return error;
- *shared = *trimmed = false;
+ *shared = false;
if (fbno == NULLAGBLOCK) {
/* No shared blocks at all. */
return 0;
*/
irec->br_blockcount = flen;
*shared = true;
- if (flen != aglen)
- *trimmed = true;
return 0;
} else {
/*
* start of the shared region.
*/
irec->br_blockcount = fbno - agbno;
- *trimmed = true;
return 0;
}
}
/*
* Trim the passed in imap to the next shared/unshared extent boundary, and
* if imap->br_startoff points to a shared extent reserve space for it in the
- * COW fork. In this case *shared is set to true, else to false.
+ * COW fork.
*
* Note that imap will always contain the block numbers for the existing blocks
* in the data fork, as the upper layers need them for read-modify-write
int
xfs_reflink_reserve_cow(
struct xfs_inode *ip,
- struct xfs_bmbt_irec *imap,
- bool *shared)
+ struct xfs_bmbt_irec *imap)
{
struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
struct xfs_bmbt_irec got;
int error = 0;
- bool eof = false, trimmed;
+ bool eof = false;
struct xfs_iext_cursor icur;
+ bool shared;
/*
* Search the COW fork extent list first. This serves two purposes:
if (!eof && got.br_startoff <= imap->br_startoff) {
trace_xfs_reflink_cow_found(ip, imap);
xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
-
- *shared = true;
return 0;
}
/* Trim the mapping to the nearest shared extent boundary. */
- error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+ error = xfs_reflink_trim_around_shared(ip, imap, &shared);
if (error)
return error;
/* Not shared? Just report the (potentially capped) extent. */
- if (!*shared)
+ if (!shared)
return 0;
/*
xfs_filblks_t count_fsb = imap->br_blockcount;
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec got;
- bool trimmed;
*found = false;
* If we don't find an overlapping extent, trim the range we need to
* allocate to fit the hole we found.
*/
- if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) ||
- got.br_startoff > offset_fsb)
- return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+ if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got))
+ got.br_startoff = offset_fsb + count_fsb;
+ if (got.br_startoff > offset_fsb) {
+ xfs_trim_extent(imap, imap->br_startoff,
+ got.br_startoff - imap->br_startoff);
+ return xfs_reflink_trim_around_shared(ip, imap, shared);
+ }
*shared = true;
if (isnullstartblock(got.br_startblock)) {
/*
* Update destination inode size & cowextsize hint, if necessary.
*/
- STATIC int
+ int
xfs_reflink_update_dest(
struct xfs_inode *dest,
xfs_off_t newlen,
xfs_extlen_t cowextsize,
- bool is_dedupe)
+ unsigned int remap_flags)
{
struct xfs_mount *mp = dest->i_mount;
struct xfs_trans *tp;
int error;
- if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
+ if (newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
return 0;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
}
- if (!is_dedupe) {
- xfs_trans_ichgtime(tp, dest,
- XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- }
xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
error = xfs_trans_commit(tp);
/*
* Iteratively remap one file's extents (and holes) to another's.
*/
- STATIC int
+ int
xfs_reflink_remap_blocks(
struct xfs_inode *src,
- xfs_fileoff_t srcoff,
+ loff_t pos_in,
struct xfs_inode *dest,
- xfs_fileoff_t destoff,
- xfs_filblks_t len,
- xfs_off_t new_isize)
+ loff_t pos_out,
+ loff_t remap_len,
+ loff_t *remapped)
{
struct xfs_bmbt_irec imap;
+ xfs_fileoff_t srcoff;
+ xfs_fileoff_t destoff;
+ xfs_filblks_t len;
+ xfs_filblks_t range_len;
+ xfs_filblks_t remapped_len = 0;
+ xfs_off_t new_isize = pos_out + remap_len;
int nimaps;
int error = 0;
- xfs_filblks_t range_len;
+
+ destoff = XFS_B_TO_FSBT(src->i_mount, pos_out);
+ srcoff = XFS_B_TO_FSBT(src->i_mount, pos_in);
+ len = XFS_B_TO_FSB(src->i_mount, remap_len);
/* drange = (destoff, destoff + len); srange = (srcoff, srcoff + len) */
while (len) {
error = xfs_bmapi_read(src, srcoff, len, &imap, &nimaps, 0);
xfs_iunlock(src, lock_mode);
if (error)
- goto err;
+ break;
ASSERT(nimaps == 1);
trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_IO_OVERWRITE,
error = xfs_reflink_remap_extent(dest, &imap, destoff,
new_isize);
if (error)
- goto err;
+ break;
if (fatal_signal_pending(current)) {
error = -EINTR;
- goto err;
+ break;
}
/* Advance drange/srange */
srcoff += range_len;
destoff += range_len;
len -= range_len;
+ remapped_len += range_len;
}
- return 0;
-
- err:
- trace_xfs_reflink_remap_blocks_error(dest, error, _RET_IP_);
+ if (error)
+ trace_xfs_reflink_remap_blocks_error(dest, error, _RET_IP_);
+ *remapped = min_t(loff_t, remap_len,
+ XFS_FSB_TO_B(src->i_mount, remapped_len));
return error;
}
}
/* Unlock both inodes after they've been prepped for a range clone. */
- STATIC void
+ void
xfs_reflink_remap_unlock(
struct file *file_in,
struct file *file_out)
* stale data in the destination file. Hence we reject these clone attempts with
* -EINVAL in this case.
*/
- STATIC int
+ int
xfs_reflink_remap_prep(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
- u64 *len,
- bool is_dedupe)
+ loff_t *len,
+ unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
bool same_inode = (inode_in == inode_out);
- u64 blkmask = i_blocksize(inode_in) - 1;
ssize_t ret;
/* Lock both files against IO */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
- ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
- len, is_dedupe);
- if (ret <= 0)
+ ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
+ len, remap_flags);
+ if (ret < 0 || *len == 0)
goto out_unlock;
- /*
- * If the dedupe data matches, chop off the partial EOF block
- * from the source file so we don't try to dedupe the partial
- * EOF block.
- */
- if (is_dedupe) {
- *len &= ~blkmask;
- } else if (*len & blkmask) {
- /*
- * The user is attempting to share a partial EOF block,
- * if it's inside the destination EOF then reject it.
- */
- if (pos_out + *len < i_size_read(inode_out)) {
- ret = -EINVAL;
- goto out_unlock;
- }
- }
-
/* Attach dquots to dest inode before changing block map */
ret = xfs_qm_dqattach(dest);
if (ret)
goto out_unlock;
/* Zap any page cache for the destination file's range. */
- truncate_inode_pages_range(&inode_out->i_data, pos_out,
- PAGE_ALIGN(pos_out + *len) - 1);
-
- /* If we're altering the file contents... */
- if (!is_dedupe) {
- /*
- * ...update the timestamps (which will grab the ilock again
- * from xfs_fs_dirty_inode, so we have to call it before we
- * take the ilock).
- */
- if (!(file_out->f_mode & FMODE_NOCMTIME)) {
- ret = file_update_time(file_out);
- if (ret)
- goto out_unlock;
- }
-
- /*
- * ...clear the security bits if the process is not being run
- * by root. This keeps people from modifying setuid and setgid
- * binaries.
- */
- ret = file_remove_privs(file_out);
- if (ret)
- goto out_unlock;
- }
+ truncate_inode_pages_range(&inode_out->i_data,
+ round_down(pos_out, PAGE_SIZE),
+ round_up(pos_out + *len, PAGE_SIZE) - 1);
return 1;
out_unlock:
}
/*
- * Link a range of blocks from one file to another.
- */
- int
- xfs_reflink_remap_range(
- struct file *file_in,
- loff_t pos_in,
- struct file *file_out,
- loff_t pos_out,
- u64 len,
- bool is_dedupe)
- {
- struct inode *inode_in = file_inode(file_in);
- struct xfs_inode *src = XFS_I(inode_in);
- struct inode *inode_out = file_inode(file_out);
- struct xfs_inode *dest = XFS_I(inode_out);
- struct xfs_mount *mp = src->i_mount;
- xfs_fileoff_t sfsbno, dfsbno;
- xfs_filblks_t fsblen;
- xfs_extlen_t cowextsize;
- ssize_t ret;
-
- if (!xfs_sb_version_hasreflink(&mp->m_sb))
- return -EOPNOTSUPP;
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
-
- /* Prepare and then clone file data. */
- ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out,
- &len, is_dedupe);
- if (ret <= 0)
- return ret;
-
- trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
-
- dfsbno = XFS_B_TO_FSBT(mp, pos_out);
- sfsbno = XFS_B_TO_FSBT(mp, pos_in);
- fsblen = XFS_B_TO_FSB(mp, len);
- ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
- pos_out + len);
- if (ret)
- goto out_unlock;
-
- /*
- * Carry the cowextsize hint from src to dest if we're sharing the
- * entire source file to the entire destination file, the source file
- * has a cowextsize hint, and the destination file does not.
- */
- cowextsize = 0;
- if (pos_in == 0 && len == i_size_read(inode_in) &&
- (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
- pos_out == 0 && len >= i_size_read(inode_out) &&
- !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
- cowextsize = src->i_d.di_cowextsize;
-
- ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
- is_dedupe);
-
- out_unlock:
- xfs_reflink_remap_unlock(file_in, file_out);
- if (ret)
- trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
- return ret;
- }
-
- /*
* The user wants to preemptively CoW all shared blocks in this file,
* which enables us to turn off the reflink flag. Iterate all
* extents which are not prealloc/delalloc to see which ranges are
xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen,
xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
- struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
+ struct xfs_bmbt_irec *irec, bool *shared);
extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
- struct xfs_bmbt_irec *imap, bool *shared);
+ struct xfs_bmbt_irec *imap);
extern int xfs_reflink_allocate_cow(struct xfs_inode *ip,
struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode);
extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t count);
extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
- extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
+ extern loff_t xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, loff_t len,
+ unsigned int remap_flags);
extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp,
struct xfs_inode *ip, bool *has_shared);
extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
struct xfs_trans **tpp);
extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
xfs_off_t len);
+ extern int xfs_reflink_remap_prep(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, loff_t *len,
+ unsigned int remap_flags);
+ extern int xfs_reflink_remap_blocks(struct xfs_inode *src, loff_t pos_in,
+ struct xfs_inode *dest, loff_t pos_out, loff_t remap_len,
+ loff_t *remapped);
+ extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen,
+ xfs_extlen_t cowextsize, unsigned int remap_flags);
+ extern void xfs_reflink_remap_unlock(struct file *file_in,
+ struct file *file_out);
#endif /* __XFS_REFLINK_H */
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
+/**
+ * struct address_space - Contents of a cacheable, mappable object.
+ * @host: Owner, either the inode or the block_device.
+ * @i_pages: Cached pages.
+ * @gfp_mask: Memory allocation flags to use for allocating pages.
+ * @i_mmap_writable: Number of VM_SHARED mappings.
+ * @i_mmap: Tree of private and shared mappings.
+ * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
+ * @nrpages: Number of page entries, protected by the i_pages lock.
+ * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock.
+ * @writeback_index: Writeback starts here.
+ * @a_ops: Methods.
+ * @flags: Error bits and flags (AS_*).
+ * @wb_err: The most recent error which has occurred.
+ * @private_lock: For use by the owner of the address_space.
+ * @private_list: For use by the owner of the address_space.
+ * @private_data: For use by the owner of the address_space.
+ */
struct address_space {
- struct inode *host; /* owner: inode, block_device */
- struct radix_tree_root i_pages; /* cached pages */
- atomic_t i_mmap_writable;/* count VM_SHARED mappings */
- struct rb_root_cached i_mmap; /* tree of private and shared mappings */
- struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */
- /* Protected by the i_pages lock */
- unsigned long nrpages; /* number of total pages */
- /* number of shadow or DAX exceptional entries */
+ struct inode *host;
+ struct xarray i_pages;
+ gfp_t gfp_mask;
+ atomic_t i_mmap_writable;
+ struct rb_root_cached i_mmap;
+ struct rw_semaphore i_mmap_rwsem;
+ unsigned long nrpages;
unsigned long nrexceptional;
- pgoff_t writeback_index;/* writeback starts here */
- const struct address_space_operations *a_ops; /* methods */
- unsigned long flags; /* error bits */
- spinlock_t private_lock; /* for use by the address_space */
- gfp_t gfp_mask; /* implicit gfp mask for allocations */
- struct list_head private_list; /* for use by the address_space */
- void *private_data; /* ditto */
+ pgoff_t writeback_index;
+ const struct address_space_operations *a_ops;
+ unsigned long flags;
errseq_t wb_err;
+ spinlock_t private_lock;
+ struct list_head private_list;
+ void *private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
/*
* On most architectures that alignment is already the case; but
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
+#define PAGECACHE_TAG_WRITEBACK XA_MARK_1
+#define PAGECACHE_TAG_TOWRITE XA_MARK_2
+
/*
- * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
- * radix trees
+ * Returns true if any of the pages in the mapping are marked with the tag.
*/
-#define PAGECACHE_TAG_DIRTY 0
-#define PAGECACHE_TAG_WRITEBACK 1
-#define PAGECACHE_TAG_TOWRITE 2
-
-int mapping_tagged(struct address_space *mapping, int tag);
+static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
+{
+ return xa_marked(&mapping->i_pages, tag);
+}
static inline void i_mmap_lock_write(struct address_space *mapping)
{
struct sb_writers s_writers;
+ /*
+ * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
+ * s_fsnotify_marks together for cache efficiency. They are frequently
+ * accessed and rarely modified.
+ */
+ void *s_fs_info; /* Filesystem private info */
+
+ /* Granularity of c/m/atime in ns (cannot be worse than a second) */
+ u32 s_time_gran;
+#ifdef CONFIG_FSNOTIFY
+ __u32 s_fsnotify_mask;
+ struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
+#endif
+
char s_id[32]; /* Informational name */
uuid_t s_uuid; /* UUID */
- void *s_fs_info; /* Filesystem private info */
unsigned int s_max_links;
fmode_t s_mode;
- /* Granularity of c/m/atime in ns.
- Cannot be worse than a second */
- u32 s_time_gran;
-
/*
* The next field is for VFS *only*. No filesystems have any business
* even looking at it. You had been warned.
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
+ /* Pending fsnotify inode refs */
+ atomic_long_t s_fsnotify_inode_refs;
+
/* Being remounted read-only */
int s_readonly_remount;
#define NOMMU_VMFLAGS \
(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
+ /*
+ * These flags control the behavior of the remap_file_range function pointer.
+ * If it is called with len == 0 that means "remap to end of source file".
+ * See Documentation/filesystems/vfs.txt for more details about this call.
+ *
+ * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate)
+ * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request
+ */
+ #define REMAP_FILE_DEDUP (1 << 0)
+ #define REMAP_FILE_CAN_SHORTEN (1 << 1)
+
+ /*
+ * These flags signal that the caller is ok with altering various aspects of
+ * the behavior of the remap operation. The changes must be made by the
+ * implementation; the vfs remap helper functions can take advantage of them.
+ * Flags in this category exist to preserve the quirky behavior of the hoisted
+ * btrfs clone/dedupe ioctls.
+ */
+ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN)
struct iov_iter;
#endif
ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
loff_t, size_t, unsigned int);
- int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
- u64);
- int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t,
- u64);
+ loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags);
int (*fadvise)(struct file *, loff_t, loff_t, int);
} __randomize_layout;
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 int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
- struct inode *inode_out, loff_t pos_out,
- u64 *len, bool is_dedupe);
- extern int do_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len);
- extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len);
- extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
- struct inode *dest, loff_t destoff,
- loff_t len, bool *is_same);
+ extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t *count,
+ unsigned int remap_flags);
+ extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags);
+ extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags);
extern int vfs_dedupe_file_range(struct file *file,
struct file_dedupe_range *same);
- extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
- struct file *dst_file, loff_t dst_pos,
- u64 len);
+ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+ struct file *dst_file, loff_t dst_pos,
+ loff_t len, unsigned int remap_flags);
struct super_operations {
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 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 *);
#include <linux/cleancache.h>
#include <linux/shmem_fs.h>
#include <linux/rmap.h>
+#include <linux/delayacct.h>
+#include <linux/psi.h>
#include "internal.h"
#define CREATE_TRACE_POINTS
* ->tasklist_lock (memory_failure, collect_procs_ao)
*/
-static int page_cache_tree_insert(struct address_space *mapping,
- struct page *page, void **shadowp)
-{
- struct radix_tree_node *node;
- void **slot;
- int error;
-
- error = __radix_tree_create(&mapping->i_pages, page->index, 0,
- &node, &slot);
- if (error)
- return error;
- if (*slot) {
- void *p;
-
- p = radix_tree_deref_slot_protected(slot,
- &mapping->i_pages.xa_lock);
- if (!radix_tree_exceptional_entry(p))
- return -EEXIST;
-
- mapping->nrexceptional--;
- if (shadowp)
- *shadowp = p;
- }
- __radix_tree_replace(&mapping->i_pages, node, slot, page,
- workingset_lookup_update(mapping));
- mapping->nrpages++;
- return 0;
-}
-
-static void page_cache_tree_delete(struct address_space *mapping,
+static void page_cache_delete(struct address_space *mapping,
struct page *page, void *shadow)
{
- int i, nr;
+ XA_STATE(xas, &mapping->i_pages, page->index);
+ unsigned int nr = 1;
+
+ mapping_set_update(&xas, mapping);
- /* hugetlb pages are represented by one entry in the radix tree */
- nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
+ /* hugetlb pages are represented by a single entry in the xarray */
+ if (!PageHuge(page)) {
+ xas_set_order(&xas, page->index, compound_order(page));
+ nr = 1U << compound_order(page);
+ }
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(nr != 1 && shadow, page);
- for (i = 0; i < nr; i++) {
- struct radix_tree_node *node;
- void **slot;
-
- __radix_tree_lookup(&mapping->i_pages, page->index + i,
- &node, &slot);
-
- VM_BUG_ON_PAGE(!node && nr != 1, page);
-
- radix_tree_clear_tags(&mapping->i_pages, node, slot);
- __radix_tree_replace(&mapping->i_pages, node, slot, shadow,
- workingset_lookup_update(mapping));
- }
+ xas_store(&xas, shadow);
+ xas_init_marks(&xas);
page->mapping = NULL;
/* Leave page->index set: truncation lookup relies upon it */
trace_mm_filemap_delete_from_page_cache(page);
unaccount_page_cache_page(mapping, page);
- page_cache_tree_delete(mapping, page, shadow);
+ page_cache_delete(mapping, page, shadow);
}
static void page_cache_free_page(struct address_space *mapping,
EXPORT_SYMBOL(delete_from_page_cache);
/*
- * page_cache_tree_delete_batch - delete several pages from page cache
+ * page_cache_delete_batch - delete several pages from page cache
* @mapping: the mapping to which pages belong
* @pvec: pagevec with pages to delete
*
*
* The function expects the i_pages lock to be held.
*/
-static void
-page_cache_tree_delete_batch(struct address_space *mapping,
+static void page_cache_delete_batch(struct address_space *mapping,
struct pagevec *pvec)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
int total_pages = 0;
int i = 0, tail_pages = 0;
struct page *page;
- pgoff_t start;
- start = pvec->pages[0]->index;
- radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
+ mapping_set_update(&xas, mapping);
+ xas_for_each(&xas, page, ULONG_MAX) {
if (i >= pagevec_count(pvec) && !tail_pages)
break;
- page = radix_tree_deref_slot_protected(slot,
- &mapping->i_pages.xa_lock);
- if (radix_tree_exceptional_entry(page))
+ if (xa_is_value(page))
continue;
if (!tail_pages) {
/*
* have our pages locked so they are protected from
* being removed.
*/
- if (page != pvec->pages[i])
+ if (page != pvec->pages[i]) {
+ VM_BUG_ON_PAGE(page->index >
+ pvec->pages[i]->index, page);
continue;
+ }
WARN_ON_ONCE(!PageLocked(page));
if (PageTransHuge(page) && !PageHuge(page))
tail_pages = HPAGE_PMD_NR - 1;
*/
i++;
} else {
+ VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages
+ != pvec->pages[i]->index, page);
tail_pages--;
}
- radix_tree_clear_tags(&mapping->i_pages, iter.node, slot);
- __radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL,
- workingset_lookup_update(mapping));
+ xas_store(&xas, NULL);
total_pages++;
}
mapping->nrpages -= total_pages;
unaccount_page_cache_page(mapping, pvec->pages[i]);
}
- page_cache_tree_delete_batch(mapping, pvec);
+ page_cache_delete_batch(mapping, pvec);
xa_unlock_irqrestore(&mapping->i_pages, flags);
for (i = 0; i < pagevec_count(pvec); i++)
bool filemap_range_has_page(struct address_space *mapping,
loff_t start_byte, loff_t end_byte)
{
- pgoff_t index = start_byte >> PAGE_SHIFT;
- pgoff_t end = end_byte >> PAGE_SHIFT;
struct page *page;
+ XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT);
+ pgoff_t max = end_byte >> PAGE_SHIFT;
if (end_byte < start_byte)
return false;
- if (mapping->nrpages == 0)
- return false;
+ rcu_read_lock();
+ for (;;) {
+ page = xas_find(&xas, max);
+ if (xas_retry(&xas, page))
+ continue;
+ /* Shadow entries don't count */
+ if (xa_is_value(page))
+ continue;
+ /*
+ * We don't need to try to pin this page; we're about to
+ * release the RCU lock anyway. It is enough to know that
+ * there was a page here recently.
+ */
+ break;
+ }
+ rcu_read_unlock();
- if (!find_get_pages_range(mapping, &index, end, 1, &page))
- return false;
- put_page(page);
- return true;
+ return page != NULL;
}
EXPORT_SYMBOL(filemap_range_has_page);
* locked. This function does not add the new page to the LRU, the
* caller must do that.
*
- * The remove + add is atomic. The only way this function can fail is
- * memory allocation failure.
+ * The remove + add is atomic. This function cannot fail.
*/
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
{
- int error;
+ struct address_space *mapping = old->mapping;
+ void (*freepage)(struct page *) = mapping->a_ops->freepage;
+ pgoff_t offset = old->index;
+ XA_STATE(xas, &mapping->i_pages, offset);
+ unsigned long flags;
VM_BUG_ON_PAGE(!PageLocked(old), old);
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
- error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
- if (!error) {
- struct address_space *mapping = old->mapping;
- void (*freepage)(struct page *);
- unsigned long flags;
-
- pgoff_t offset = old->index;
- freepage = mapping->a_ops->freepage;
-
- get_page(new);
- new->mapping = mapping;
- new->index = offset;
+ get_page(new);
+ new->mapping = mapping;
+ new->index = offset;
- xa_lock_irqsave(&mapping->i_pages, flags);
- __delete_from_page_cache(old, NULL);
- error = page_cache_tree_insert(mapping, new, NULL);
- BUG_ON(error);
+ xas_lock_irqsave(&xas, flags);
+ xas_store(&xas, new);
- /*
- * hugetlb pages do not participate in page cache accounting.
- */
- if (!PageHuge(new))
- __inc_node_page_state(new, NR_FILE_PAGES);
- if (PageSwapBacked(new))
- __inc_node_page_state(new, NR_SHMEM);
- xa_unlock_irqrestore(&mapping->i_pages, flags);
- mem_cgroup_migrate(old, new);
- radix_tree_preload_end();
- if (freepage)
- freepage(old);
- put_page(old);
- }
+ old->mapping = NULL;
+ /* hugetlb pages do not participate in page cache accounting. */
+ if (!PageHuge(old))
+ __dec_node_page_state(new, NR_FILE_PAGES);
+ if (!PageHuge(new))
+ __inc_node_page_state(new, NR_FILE_PAGES);
+ if (PageSwapBacked(old))
+ __dec_node_page_state(new, NR_SHMEM);
+ if (PageSwapBacked(new))
+ __inc_node_page_state(new, NR_SHMEM);
+ xas_unlock_irqrestore(&xas, flags);
+ mem_cgroup_migrate(old, new);
+ if (freepage)
+ freepage(old);
+ put_page(old);
- return error;
+ return 0;
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
pgoff_t offset, gfp_t gfp_mask,
void **shadowp)
{
+ XA_STATE(xas, &mapping->i_pages, offset);
int huge = PageHuge(page);
struct mem_cgroup *memcg;
int error;
+ void *old;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(page), page);
+ mapping_set_update(&xas, mapping);
if (!huge) {
error = mem_cgroup_try_charge(page, current->mm,
return error;
}
- error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
- if (error) {
- if (!huge)
- mem_cgroup_cancel_charge(page, memcg, false);
- return error;
- }
-
get_page(page);
page->mapping = mapping;
page->index = offset;
- xa_lock_irq(&mapping->i_pages);
- error = page_cache_tree_insert(mapping, page, shadowp);
- radix_tree_preload_end();
- if (unlikely(error))
- goto err_insert;
+ do {
+ xas_lock_irq(&xas);
+ old = xas_load(&xas);
+ if (old && !xa_is_value(old))
+ xas_set_err(&xas, -EEXIST);
+ xas_store(&xas, page);
+ if (xas_error(&xas))
+ goto unlock;
+
+ if (xa_is_value(old)) {
+ mapping->nrexceptional--;
+ if (shadowp)
+ *shadowp = old;
+ }
+ mapping->nrpages++;
+
+ /* hugetlb pages do not participate in page cache accounting */
+ if (!huge)
+ __inc_node_page_state(page, NR_FILE_PAGES);
+unlock:
+ xas_unlock_irq(&xas);
+ } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK));
+
+ if (xas_error(&xas))
+ goto error;
- /* hugetlb pages do not participate in page cache accounting. */
- if (!huge)
- __inc_node_page_state(page, NR_FILE_PAGES);
- xa_unlock_irq(&mapping->i_pages);
if (!huge)
mem_cgroup_commit_charge(page, memcg, false, false);
trace_mm_filemap_add_to_page_cache(page);
return 0;
-err_insert:
+error:
page->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
- xa_unlock_irq(&mapping->i_pages);
if (!huge)
mem_cgroup_cancel_charge(page, memcg, false);
put_page(page);
- return error;
+ return xas_error(&xas);
}
/**
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
*/
- if (!(gfp_mask & __GFP_WRITE) &&
- shadow && workingset_refault(shadow)) {
- SetPageActive(page);
- workingset_activation(page);
- } else
- ClearPageActive(page);
+ WARN_ON_ONCE(PageActive(page));
+ if (!(gfp_mask & __GFP_WRITE) && shadow)
+ workingset_refault(page, shadow);
lru_cache_add(page);
}
return ret;
{
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
+ bool thrashing = false;
+ unsigned long pflags;
int ret = 0;
+ if (bit_nr == PG_locked &&
+ !PageUptodate(page) && PageWorkingset(page)) {
+ if (!PageSwapBacked(page))
+ delayacct_thrashing_start();
+ psi_memstall_enter(&pflags);
+ thrashing = true;
+ }
+
init_wait(wait);
wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
wait->func = wake_page_function;
finish_wait(q, wait);
+ if (thrashing) {
+ if (!PageSwapBacked(page))
+ delayacct_thrashing_end();
+ psi_memstall_leave(&pflags);
+ }
+
/*
* A signal could leave PageWaiters set. Clearing it here if
* !waitqueue_active would be possible (by open-coding finish_wait),
}
/**
- * page_cache_next_hole - find the next hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
- *
- * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
- * lowest indexed hole.
- *
- * Returns: the index of the hole if found, otherwise returns an index
- * outside of the set specified (in which case 'return - index >=
- * max_scan' will be true). In rare cases of index wrap-around, 0 will
- * be returned.
- *
- * page_cache_next_hole may be called under rcu_read_lock. However,
- * like radix_tree_gang_lookup, this will not atomically search a
- * snapshot of the tree at a single point in time. For example, if a
- * hole is created at index 5, then subsequently a hole is created at
- * index 10, page_cache_next_hole covering both indexes may return 10
- * if called under rcu_read_lock.
+ * page_cache_next_miss() - Find the next gap in the page cache.
+ * @mapping: Mapping.
+ * @index: Index.
+ * @max_scan: Maximum range to search.
+ *
+ * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the
+ * gap with the lowest index.
+ *
+ * This function may be called under the rcu_read_lock. However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 5, then subsequently a gap is
+ * created at index 10, page_cache_next_miss covering both indices may
+ * return 10 if called under the rcu_read_lock.
+ *
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'return - index >= max_scan' will be true).
+ * In the rare case of index wrap-around, 0 will be returned.
*/
-pgoff_t page_cache_next_hole(struct address_space *mapping,
+pgoff_t page_cache_next_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
- unsigned long i;
-
- for (i = 0; i < max_scan; i++) {
- struct page *page;
+ XA_STATE(xas, &mapping->i_pages, index);
- page = radix_tree_lookup(&mapping->i_pages, index);
- if (!page || radix_tree_exceptional_entry(page))
+ while (max_scan--) {
+ void *entry = xas_next(&xas);
+ if (!entry || xa_is_value(entry))
break;
- index++;
- if (index == 0)
+ if (xas.xa_index == 0)
break;
}
- return index;
+ return xas.xa_index;
}
-EXPORT_SYMBOL(page_cache_next_hole);
+EXPORT_SYMBOL(page_cache_next_miss);
/**
- * page_cache_prev_hole - find the prev hole (not-present entry)
- * @mapping: mapping
- * @index: index
- * @max_scan: maximum range to search
- *
- * Search backwards in the range [max(index-max_scan+1, 0), index] for
- * the first hole.
- *
- * Returns: the index of the hole if found, otherwise returns an index
- * outside of the set specified (in which case 'index - return >=
- * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
- * will be returned.
- *
- * page_cache_prev_hole may be called under rcu_read_lock. However,
- * like radix_tree_gang_lookup, this will not atomically search a
- * snapshot of the tree at a single point in time. For example, if a
- * hole is created at index 10, then subsequently a hole is created at
- * index 5, page_cache_prev_hole covering both indexes may return 5 if
- * called under rcu_read_lock.
+ * page_cache_prev_miss() - Find the next gap in the page cache.
+ * @mapping: Mapping.
+ * @index: Index.
+ * @max_scan: Maximum range to search.
+ *
+ * Search the range [max(index - max_scan + 1, 0), index] for the
+ * gap with the highest index.
+ *
+ * This function may be called under the rcu_read_lock. However, this will
+ * not atomically search a snapshot of the cache at a single point in time.
+ * For example, if a gap is created at index 10, then subsequently a gap is
+ * created at index 5, page_cache_prev_miss() covering both indices may
+ * return 5 if called under the rcu_read_lock.
+ *
+ * Return: The index of the gap if found, otherwise an index outside the
+ * range specified (in which case 'index - return >= max_scan' will be true).
+ * In the rare case of wrap-around, ULONG_MAX will be returned.
*/
-pgoff_t page_cache_prev_hole(struct address_space *mapping,
+pgoff_t page_cache_prev_miss(struct address_space *mapping,
pgoff_t index, unsigned long max_scan)
{
- unsigned long i;
-
- for (i = 0; i < max_scan; i++) {
- struct page *page;
+ XA_STATE(xas, &mapping->i_pages, index);
- page = radix_tree_lookup(&mapping->i_pages, index);
- if (!page || radix_tree_exceptional_entry(page))
+ while (max_scan--) {
+ void *entry = xas_prev(&xas);
+ if (!entry || xa_is_value(entry))
break;
- index--;
- if (index == ULONG_MAX)
+ if (xas.xa_index == ULONG_MAX)
break;
}
- return index;
+ return xas.xa_index;
}
-EXPORT_SYMBOL(page_cache_prev_hole);
+EXPORT_SYMBOL(page_cache_prev_miss);
/**
* find_get_entry - find and get a page cache entry
*/
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
- void **pagep;
+ XA_STATE(xas, &mapping->i_pages, offset);
struct page *head, *page;
rcu_read_lock();
repeat:
- page = NULL;
- pagep = radix_tree_lookup_slot(&mapping->i_pages, offset);
- if (pagep) {
- page = radix_tree_deref_slot(pagep);
- if (unlikely(!page))
- goto out;
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page))
- goto repeat;
- /*
- * A shadow entry of a recently evicted page,
- * or a swap entry from shmem/tmpfs. Return
- * it without attempting to raise page count.
- */
- goto out;
- }
+ xas_reset(&xas);
+ page = xas_load(&xas);
+ if (xas_retry(&xas, page))
+ goto repeat;
+ /*
+ * A shadow entry of a recently evicted page, or a swap entry from
+ * shmem/tmpfs. Return it without attempting to raise page count.
+ */
+ if (!page || xa_is_value(page))
+ goto out;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- goto repeat;
+ head = compound_head(page);
+ if (!page_cache_get_speculative(head))
+ goto repeat;
- /* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ /* The page was split under us? */
+ if (compound_head(page) != head) {
+ put_page(head);
+ goto repeat;
+ }
- /*
- * Has the page moved?
- * This is part of the lockless pagecache protocol. See
- * include/linux/pagemap.h for details.
- */
- if (unlikely(page != *pagep)) {
- put_page(head);
- goto repeat;
- }
+ /*
+ * Has the page moved?
+ * This is part of the lockless pagecache protocol. See
+ * include/linux/pagemap.h for details.
+ */
+ if (unlikely(page != xas_reload(&xas))) {
+ put_page(head);
+ goto repeat;
}
out:
rcu_read_unlock();
repeat:
page = find_get_entry(mapping, offset);
- if (page && !radix_tree_exception(page)) {
+ if (page && !xa_is_value(page)) {
lock_page(page);
/* Has the page been truncated? */
if (unlikely(page_mapping(page) != mapping)) {
repeat:
page = find_get_entry(mapping, offset);
- if (radix_tree_exceptional_entry(page))
+ if (xa_is_value(page))
page = NULL;
if (!page)
goto no_page;
pgoff_t start, unsigned int nr_entries,
struct page **entries, pgoff_t *indices)
{
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, start);
+ struct page *page;
unsigned int ret = 0;
- struct radix_tree_iter iter;
if (!nr_entries)
return 0;
rcu_read_lock();
- radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
- struct page *head, *page;
-repeat:
- page = radix_tree_deref_slot(slot);
- if (unlikely(!page))
+ xas_for_each(&xas, page, ULONG_MAX) {
+ struct page *head;
+ if (xas_retry(&xas, page))
continue;
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
- /*
- * A shadow entry of a recently evicted page, a swap
- * entry from shmem/tmpfs or a DAX entry. Return it
- * without attempting to raise page count.
- */
+ /*
+ * A shadow entry of a recently evicted page, a swap
+ * entry from shmem/tmpfs or a DAX entry. Return it
+ * without attempting to raise page count.
+ */
+ if (xa_is_value(page))
goto export;
- }
head = compound_head(page);
if (!page_cache_get_speculative(head))
- goto repeat;
+ goto retry;
/* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ if (compound_head(page) != head)
+ goto put_page;
/* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
- }
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
+
export:
- indices[ret] = iter.index;
+ indices[ret] = xas.xa_index;
entries[ret] = page;
if (++ret == nr_entries)
break;
+ continue;
+put_page:
+ put_page(head);
+retry:
+ xas_reset(&xas);
}
rcu_read_unlock();
return ret;
pgoff_t end, unsigned int nr_pages,
struct page **pages)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, *start);
+ struct page *page;
unsigned ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
- radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, *start) {
- struct page *head, *page;
-
- if (iter.index > end)
- break;
-repeat:
- page = radix_tree_deref_slot(slot);
- if (unlikely(!page))
+ xas_for_each(&xas, page, end) {
+ struct page *head;
+ if (xas_retry(&xas, page))
continue;
-
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
- /*
- * A shadow entry of a recently evicted page,
- * or a swap entry from shmem/tmpfs. Skip
- * over it.
- */
+ /* Skip over shadow, swap and DAX entries */
+ if (xa_is_value(page))
continue;
- }
head = compound_head(page);
if (!page_cache_get_speculative(head))
- goto repeat;
+ goto retry;
/* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ if (compound_head(page) != head)
+ goto put_page;
/* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
- }
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
pages[ret] = page;
if (++ret == nr_pages) {
- *start = pages[ret - 1]->index + 1;
+ *start = page->index + 1;
goto out;
}
+ continue;
+put_page:
+ put_page(head);
+retry:
+ xas_reset(&xas);
}
/*
* We come here when there is no page beyond @end. We take care to not
* overflow the index @start as it confuses some of the callers. This
- * breaks the iteration when there is page at index -1 but that is
+ * breaks the iteration when there is a page at index -1 but that is
* already broken anyway.
*/
if (end == (pgoff_t)-1)
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
unsigned int nr_pages, struct page **pages)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, index);
+ struct page *page;
unsigned int ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
- radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) {
- struct page *head, *page;
-repeat:
- page = radix_tree_deref_slot(slot);
- /* The hole, there no reason to continue */
- if (unlikely(!page))
- break;
-
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
- /*
- * A shadow entry of a recently evicted page,
- * or a swap entry from shmem/tmpfs. Stop
- * looking for contiguous pages.
- */
+ for (page = xas_load(&xas); page; page = xas_next(&xas)) {
+ struct page *head;
+ if (xas_retry(&xas, page))
+ continue;
+ /*
+ * If the entry has been swapped out, we can stop looking.
+ * No current caller is looking for DAX entries.
+ */
+ if (xa_is_value(page))
break;
- }
head = compound_head(page);
if (!page_cache_get_speculative(head))
- goto repeat;
+ goto retry;
/* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ if (compound_head(page) != head)
+ goto put_page;
/* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
- }
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
/*
* must check mapping and index after taking the ref.
* otherwise we can get both false positives and false
* negatives, which is just confusing to the caller.
*/
- if (page->mapping == NULL || page_to_pgoff(page) != iter.index) {
+ if (!page->mapping || page_to_pgoff(page) != xas.xa_index) {
put_page(page);
break;
}
pages[ret] = page;
if (++ret == nr_pages)
break;
+ continue;
+put_page:
+ put_page(head);
+retry:
+ xas_reset(&xas);
}
rcu_read_unlock();
return ret;
* @tag. We update @index to index the next page for the traversal.
*/
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
- pgoff_t end, int tag, unsigned int nr_pages,
+ pgoff_t end, xa_mark_t tag, unsigned int nr_pages,
struct page **pages)
{
- struct radix_tree_iter iter;
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, *index);
+ struct page *page;
unsigned ret = 0;
if (unlikely(!nr_pages))
return 0;
rcu_read_lock();
- radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) {
- struct page *head, *page;
-
- if (iter.index > end)
- break;
-repeat:
- page = radix_tree_deref_slot(slot);
- if (unlikely(!page))
+ xas_for_each_marked(&xas, page, end, tag) {
+ struct page *head;
+ if (xas_retry(&xas, page))
continue;
-
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
- /*
- * A shadow entry of a recently evicted page.
- *
- * Those entries should never be tagged, but
- * this tree walk is lockless and the tags are
- * looked up in bulk, one radix tree node at a
- * time, so there is a sizable window for page
- * reclaim to evict a page we saw tagged.
- *
- * Skip over it.
- */
+ /*
+ * Shadow entries should never be tagged, but this iteration
+ * is lockless so there is a window for page reclaim to evict
+ * a page we saw tagged. Skip over it.
+ */
+ if (xa_is_value(page))
continue;
- }
head = compound_head(page);
if (!page_cache_get_speculative(head))
- goto repeat;
+ goto retry;
/* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ if (compound_head(page) != head)
+ goto put_page;
/* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
- }
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
pages[ret] = page;
if (++ret == nr_pages) {
- *index = pages[ret - 1]->index + 1;
+ *index = page->index + 1;
goto out;
}
+ continue;
+put_page:
+ put_page(head);
+retry:
+ xas_reset(&xas);
}
/*
- * We come here when we got at @end. We take care to not overflow the
+ * We come here when we got to @end. We take care to not overflow the
* index @index as it confuses some of the callers. This breaks the
- * iteration when there is page at index -1 but that is already broken
- * anyway.
+ * iteration when there is a page at index -1 but that is already
+ * broken anyway.
*/
if (end == (pgoff_t)-1)
*index = (pgoff_t)-1;
* @tag.
*/
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
- int tag, unsigned int nr_entries,
+ xa_mark_t tag, unsigned int nr_entries,
struct page **entries, pgoff_t *indices)
{
- void **slot;
+ XA_STATE(xas, &mapping->i_pages, start);
+ struct page *page;
unsigned int ret = 0;
- struct radix_tree_iter iter;
if (!nr_entries)
return 0;
rcu_read_lock();
- radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) {
- struct page *head, *page;
-repeat:
- page = radix_tree_deref_slot(slot);
- if (unlikely(!page))
+ xas_for_each_marked(&xas, page, ULONG_MAX, tag) {
+ struct page *head;
+ if (xas_retry(&xas, page))
continue;
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
-
- /*
- * A shadow entry of a recently evicted page, a swap
- * entry from shmem/tmpfs or a DAX entry. Return it
- * without attempting to raise page count.
- */
+ /*
+ * A shadow entry of a recently evicted page, a swap
+ * entry from shmem/tmpfs or a DAX entry. Return it
+ * without attempting to raise page count.
+ */
+ if (xa_is_value(page))
goto export;
- }
head = compound_head(page);
if (!page_cache_get_speculative(head))
- goto repeat;
+ goto retry;
/* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ if (compound_head(page) != head)
+ goto put_page;
/* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
- }
+ if (unlikely(page != xas_reload(&xas)))
+ goto put_page;
+
export:
- indices[ret] = iter.index;
+ indices[ret] = xas.xa_index;
entries[ret] = page;
if (++ret == nr_entries)
break;
+ continue;
+put_page:
+ put_page(head);
+retry:
+ xas_reset(&xas);
}
rcu_read_unlock();
return ret;
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
/* pipes can't handle partially uptodate pages */
- if (unlikely(iter->type & ITER_PIPE))
+ if (unlikely(iov_iter_is_pipe(iter)))
goto page_not_up_to_date;
if (!trylock_page(page))
goto page_not_up_to_date;
* system is low on memory, or a problem occurs while trying
* to schedule I/O.
*/
- if (error == -ENOMEM)
- return VM_FAULT_OOM;
- return VM_FAULT_SIGBUS;
+ return vmf_error(error);
page_not_uptodate:
/*
void filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff)
{
- struct radix_tree_iter iter;
- void **slot;
struct file *file = vmf->vma->vm_file;
struct address_space *mapping = file->f_mapping;
pgoff_t last_pgoff = start_pgoff;
unsigned long max_idx;
+ XA_STATE(xas, &mapping->i_pages, start_pgoff);
struct page *head, *page;
rcu_read_lock();
- radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) {
- if (iter.index > end_pgoff)
- break;
-repeat:
- page = radix_tree_deref_slot(slot);
- if (unlikely(!page))
- goto next;
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page)) {
- slot = radix_tree_iter_retry(&iter);
- continue;
- }
+ xas_for_each(&xas, page, end_pgoff) {
+ if (xas_retry(&xas, page))
+ continue;
+ if (xa_is_value(page))
goto next;
- }
head = compound_head(page);
if (!page_cache_get_speculative(head))
- goto repeat;
+ goto next;
/* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
+ if (compound_head(page) != head)
+ goto skip;
/* Has the page moved? */
- if (unlikely(page != *slot)) {
- put_page(head);
- goto repeat;
- }
+ if (unlikely(page != xas_reload(&xas)))
+ goto skip;
if (!PageUptodate(page) ||
PageReadahead(page) ||
if (file->f_ra.mmap_miss > 0)
file->f_ra.mmap_miss--;
- vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT;
+ vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
if (vmf->pte)
- vmf->pte += iter.index - last_pgoff;
- last_pgoff = iter.index;
+ vmf->pte += xas.xa_index - last_pgoff;
+ last_pgoff = xas.xa_index;
if (alloc_set_pte(vmf, NULL, page))
goto unlock;
unlock_page(page);
/* Huge page is mapped? No need to proceed. */
if (pmd_trans_huge(*vmf->pmd))
break;
- if (iter.index == end_pgoff)
- break;
}
rcu_read_unlock();
}
return generic_file_mmap(file, vma);
}
#else
-int filemap_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
{
- return -ENOSYS;
+ return VM_FAULT_SIGBUS;
}
int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
{
put_page(page);
if (err == -EEXIST)
goto repeat;
- /* Presumably ENOMEM for radix tree node */
+ /* Presumably ENOMEM for xarray node */
return ERR_PTR(err);
}
EXPORT_SYMBOL(read_cache_page_gfp);
/*
+ * Don't operate on ranges the page cache doesn't support, and don't exceed the
+ * LFS limits. If pos is under the limit it becomes a short access. If it
+ * exceeds the limit we return -EFBIG.
+ */
+ static int generic_access_check_limits(struct file *file, loff_t pos,
+ loff_t *count)
+ {
+ struct inode *inode = file->f_mapping->host;
+ loff_t max_size = inode->i_sb->s_maxbytes;
+
+ if (!(file->f_flags & O_LARGEFILE))
+ max_size = MAX_NON_LFS;
+
+ if (unlikely(pos >= max_size))
+ return -EFBIG;
+ *count = min(*count, max_size - pos);
+ return 0;
+ }
+
+ static int generic_write_check_limits(struct file *file, loff_t pos,
+ loff_t *count)
+ {
+ loff_t limit = rlimit(RLIMIT_FSIZE);
+
+ if (limit != RLIM_INFINITY) {
+ if (pos >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ return -EFBIG;
+ }
+ *count = min(*count, limit - pos);
+ }
+
+ return generic_access_check_limits(file, pos, count);
+ }
+
+ /*
* Performs necessary checks before doing a write
*
* Can adjust writing position or amount of bytes to write.
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- unsigned long limit = rlimit(RLIMIT_FSIZE);
- loff_t pos;
+ loff_t count;
+ int ret;
if (!iov_iter_count(from))
return 0;
if (iocb->ki_flags & IOCB_APPEND)
iocb->ki_pos = i_size_read(inode);
- pos = iocb->ki_pos;
-
if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
return -EINVAL;
- if (limit != RLIM_INFINITY) {
- if (iocb->ki_pos >= limit) {
- send_sig(SIGXFSZ, current, 0);
- return -EFBIG;
- }
- iov_iter_truncate(from, limit - (unsigned long)pos);
- }
+ count = iov_iter_count(from);
+ ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+ if (ret)
+ return ret;
+
+ iov_iter_truncate(from, count);
+ return iov_iter_count(from);
+ }
+ EXPORT_SYMBOL(generic_write_checks);
+
+ /*
+ * Performs necessary checks before doing a clone.
+ *
+ * Can adjust amount of bytes to clone.
+ * Returns appropriate error code that caller should return or
+ * zero in case the clone should be allowed.
+ */
+ int generic_remap_checks(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t *req_count, unsigned int remap_flags)
+ {
+ struct inode *inode_in = file_in->f_mapping->host;
+ struct inode *inode_out = file_out->f_mapping->host;
+ uint64_t count = *req_count;
+ uint64_t bcount;
+ loff_t size_in, size_out;
+ loff_t bs = inode_out->i_sb->s_blocksize;
+ int ret;
+
+ /* The start of both ranges must be aligned to an fs block. */
+ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs))
+ return -EINVAL;
+
+ /* Ensure offsets don't wrap. */
+ if (pos_in + count < pos_in || pos_out + count < pos_out)
+ return -EINVAL;
+
+ size_in = i_size_read(inode_in);
+ size_out = i_size_read(inode_out);
+
+ /* Dedupe requires both ranges to be within EOF. */
+ if ((remap_flags & REMAP_FILE_DEDUP) &&
+ (pos_in >= size_in || pos_in + count > size_in ||
+ pos_out >= size_out || pos_out + count > size_out))
+ return -EINVAL;
+
+ /* Ensure the infile range is within the infile. */
+ if (pos_in >= size_in)
+ return -EINVAL;
+ count = min(count, size_in - (uint64_t)pos_in);
+
+ ret = generic_access_check_limits(file_in, pos_in, &count);
+ if (ret)
+ return ret;
+
+ ret = generic_write_check_limits(file_out, pos_out, &count);
+ if (ret)
+ return ret;
/*
- * LFS rule
+ * If the user wanted us to link to the infile's EOF, round up to the
+ * next block boundary for this check.
+ *
+ * Otherwise, make sure the count is also block-aligned, having
+ * already confirmed the starting offsets' block alignment.
*/
- if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
- !(file->f_flags & O_LARGEFILE))) {
- if (pos >= MAX_NON_LFS)
- return -EFBIG;
- iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
+ if (pos_in + count == size_in) {
+ bcount = ALIGN(size_in, bs) - pos_in;
+ } else {
+ if (!IS_ALIGNED(count, bs))
+ count = ALIGN_DOWN(count, bs);
+ bcount = count;
}
+ /* Don't allow overlapped cloning within the same file. */
+ if (inode_in == inode_out &&
+ pos_out + bcount > pos_in &&
+ pos_out < pos_in + bcount)
+ return -EINVAL;
+
/*
- * Are we about to exceed the fs block limit ?
- *
- * If we have written data it becomes a short write. If we have
- * exceeded without writing data we send a signal and return EFBIG.
- * Linus frestrict idea will clean these up nicely..
+ * We shortened the request but the caller can't deal with that, so
+ * bounce the request back to userspace.
*/
- if (unlikely(pos >= inode->i_sb->s_maxbytes))
- return -EFBIG;
+ if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN))
+ return -EINVAL;
- iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
- return iov_iter_count(from);
+ *req_count = count;
+ return 0;
}
- EXPORT_SYMBOL(generic_write_checks);
int pagecache_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
if (iocb->ki_flags & IOCB_NOWAIT) {
/* If there are pages to writeback, return */
if (filemap_range_has_page(inode->i_mapping, pos,
- pos + iov_iter_count(from)))
+ pos + write_len))
return -EAGAIN;
} else {
written = filemap_write_and_wait_range(mapping, pos,