int scanned = 0;
if (!xattr_access) {
- xattr_access = btrfs_name_hash(POSIX_ACL_XATTR_ACCESS,
- strlen(POSIX_ACL_XATTR_ACCESS));
- xattr_default = btrfs_name_hash(POSIX_ACL_XATTR_DEFAULT,
- strlen(POSIX_ACL_XATTR_DEFAULT));
+ xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS,
+ strlen(XATTR_NAME_POSIX_ACL_ACCESS));
+ xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT,
+ strlen(XATTR_NAME_POSIX_ACL_DEFAULT));
}
slot++;
break;
case S_IFLNK:
inode->i_op = &btrfs_symlink_inode_operations;
+ inode_nohighmem(inode);
inode->i_mapping->a_ops = &btrfs_symlink_aops;
break;
default:
char *name_ptr;
int name_len;
int is_curr = 0; /* ctx->pos points to the current index? */
+ bool emitted;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
if (ret < 0)
goto err;
+ emitted = false;
while (1) {
leaf = path->nodes[0];
slot = path->slots[0];
if (over)
goto nopos;
+ emitted = true;
di_len = btrfs_dir_name_len(leaf, di) +
btrfs_dir_data_len(leaf, di) + sizeof(*di);
di_cur += di_len;
if (key_type == BTRFS_DIR_INDEX_KEY) {
if (is_curr)
ctx->pos++;
- ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+ ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
if (ret)
goto nopos;
}
+ /*
+ * If we haven't emitted any dir entry, we must not touch ctx->pos as
+ * it was was set to the termination value in previous call. We assume
+ * that "." and ".." were emitted if we reach this point and set the
+ * termination value as well for an empty directory.
+ */
+ if (ctx->pos > 2 && !emitted)
+ goto nopos;
+
/* Reached end of directory/root. Bump pos past the last item. */
ctx->pos++;
* not unlock the i_mutex at this case.
*/
if (offset + count <= inode->i_size) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
relock = true;
}
ret = btrfs_delalloc_reserve_space(inode, offset, count);
if (wakeup)
inode_dio_end(inode);
if (relock)
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
return ret;
}
{
btrfs_inode_cachep = kmem_cache_create("btrfs_inode",
sizeof(struct btrfs_inode), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, init_once);
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT,
+ init_once);
if (!btrfs_inode_cachep)
goto fail;
btrfs_free_path(path);
inode->i_op = &btrfs_symlink_inode_operations;
+ inode_nohighmem(inode);
inode->i_mapping->a_ops = &btrfs_symlink_aops;
inode_set_bytes(inode, name_len);
btrfs_i_size_write(inode, name_len);
.setattr = btrfs_setattr,
.mknod = btrfs_mknod,
.setxattr = btrfs_setxattr,
- .getxattr = btrfs_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.setxattr = btrfs_setxattr,
- .getxattr = btrfs_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
- .getxattr = btrfs_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.get_acl = btrfs_get_acl,
};
static const struct inode_operations btrfs_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = page_follow_link_light,
- .put_link = page_put_link,
+ .get_link = page_get_link,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
- .getxattr = btrfs_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.update_time = btrfs_update_time,
if (ret)
return ret;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
ip_oldflags = ip->flags;
i_oldflags = inode->i_flags;
}
out_unlock:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
mnt_drop_write_file(file);
return ret;
}
out_dput:
dput(dentry);
out_unlock:
- mutex_unlock(&dir->i_mutex);
+ inode_unlock(dir);
return error;
}
ra_index += cluster;
}
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
BTRFS_I(inode)->force_compress = compress_type;
ret = cluster_pages_for_defrag(inode, pages, i, cluster);
if (ret < 0) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out_ra;
}
defrag_count += ret;
balance_dirty_pages_ratelimited(inode->i_mapping);
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
if (newer_than) {
if (newer_off == (u64)-1)
out_ra:
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
}
if (!file)
kfree(ra);
goto out_dput;
}
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
/*
* Don't allow to delete a subvolume with send in progress. This is
spin_unlock(&dest->root_item_lock);
}
out_unlock_inode:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
if (!err) {
d_invalidate(dentry);
btrfs_invalidate_inodes(dest);
out_dput:
dput(dentry);
out_unlock_dir:
- mutex_unlock(&dir->i_mutex);
+ inode_unlock(dir);
out_drop_write:
mnt_drop_write_file(file);
out:
static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
{
struct page *page;
- struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
page = grab_cache_page(inode->i_mapping, index);
if (!page)
- return NULL;
+ return ERR_PTR(-ENOMEM);
if (!PageUptodate(page)) {
- if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
- 0))
- return NULL;
+ int ret;
+
+ ret = btrfs_readpage(NULL, page);
+ if (ret)
+ return ERR_PTR(ret);
lock_page(page);
if (!PageUptodate(page)) {
unlock_page(page);
page_cache_release(page);
- return NULL;
+ return ERR_PTR(-EIO);
+ }
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+ page_cache_release(page);
+ return ERR_PTR(-EAGAIN);
}
}
- unlock_page(page);
return page;
}
pgoff_t index = off >> PAGE_CACHE_SHIFT;
for (i = 0; i < num_pages; i++) {
+ again:
pages[i] = extent_same_get_page(inode, index + i);
- if (!pages[i])
- return -ENOMEM;
+ if (IS_ERR(pages[i])) {
+ int err = PTR_ERR(pages[i]);
+
+ if (err == -EAGAIN)
+ goto again;
+ pages[i] = NULL;
+ return err;
+ }
}
return 0;
}
- static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+ static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+ bool retry_range_locking)
{
- /* do any pending delalloc/csum calc on src, one way or
- another, and lock file content */
+ /*
+ * Do any pending delalloc/csum calculations on inode, one way or
+ * another, and lock file content.
+ * The locking order is:
+ *
+ * 1) pages
+ * 2) range in the inode's io tree
+ */
while (1) {
struct btrfs_ordered_extent *ordered;
lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
if (ordered)
btrfs_put_ordered_extent(ordered);
+ if (!retry_range_locking)
+ return -EAGAIN;
btrfs_wait_ordered_range(inode, off, len);
}
+ return 0;
}
static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
{
- mutex_unlock(&inode1->i_mutex);
- mutex_unlock(&inode2->i_mutex);
+ inode_unlock(inode1);
+ inode_unlock(inode2);
}
static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
if (inode1 < inode2)
swap(inode1, inode2);
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+ inode_lock_nested(inode1, I_MUTEX_PARENT);
+ inode_lock_nested(inode2, I_MUTEX_CHILD);
}
static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}
- static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
- struct inode *inode2, u64 loff2, u64 len)
+ static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len,
+ bool retry_range_locking)
{
+ int ret;
+
if (inode1 < inode2) {
swap(inode1, inode2);
swap(loff1, loff2);
}
- lock_extent_range(inode1, loff1, len);
- lock_extent_range(inode2, loff2, len);
+ ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+ if (ret)
+ return ret;
+ ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+ if (ret)
+ unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+ loff1 + len - 1);
+ return ret;
}
struct cmp_pages {
for (i = 0; i < cmp->num_pages; i++) {
pg = cmp->src_pages[i];
- if (pg)
+ if (pg) {
+ unlock_page(pg);
page_cache_release(pg);
+ }
pg = cmp->dst_pages[i];
- if (pg)
+ if (pg) {
+ unlock_page(pg);
page_cache_release(pg);
+ }
}
kfree(cmp->src_pages);
kfree(cmp->dst_pages);
src_page = cmp->src_pages[i];
dst_page = cmp->dst_pages[i];
+ ASSERT(PageLocked(src_page));
+ ASSERT(PageLocked(dst_page));
addr = kmap_atomic(src_page);
dst_addr = kmap_atomic(dst_page);
flush_dcache_page(dst_page);
if (memcmp(addr, dst_addr, cmp_len))
- ret = BTRFS_SAME_DATA_DIFFERS;
+ ret = -EBADE;
kunmap_atomic(addr);
kunmap_atomic(dst_addr);
return 0;
if (same_inode) {
- mutex_lock(&src->i_mutex);
+ inode_lock(src);
ret = extent_same_check_offsets(src, loff, &len, olen);
if (ret)
goto out_unlock;
}
+ again:
ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
if (ret)
goto out_unlock;
if (same_inode)
- lock_extent_range(src, same_lock_start, same_lock_len);
+ ret = lock_extent_range(src, same_lock_start, same_lock_len,
+ false);
else
- btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+ ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+ false);
+ /*
+ * If one of the inodes has dirty pages in the respective range or
+ * ordered extents, we need to flush dellaloc and wait for all ordered
+ * extents in the range. We must unlock the pages and the ranges in the
+ * io trees to avoid deadlocks when flushing delalloc (requires locking
+ * pages) and when waiting for ordered extents to complete (they require
+ * range locking).
+ */
+ if (ret == -EAGAIN) {
+ /*
+ * Ranges in the io trees already unlocked. Now unlock all
+ * pages before waiting for all IO to complete.
+ */
+ btrfs_cmp_data_free(&cmp);
+ if (same_inode) {
+ btrfs_wait_ordered_range(src, same_lock_start,
+ same_lock_len);
+ } else {
+ btrfs_wait_ordered_range(src, loff, len);
+ btrfs_wait_ordered_range(dst, dst_loff, len);
+ }
+ goto again;
+ }
+ ASSERT(ret == 0);
+ if (WARN_ON(ret)) {
+ /* ranges in the io trees already unlocked */
+ btrfs_cmp_data_free(&cmp);
+ return ret;
+ }
/* pass original length for comparison so we stay within i_size */
ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
btrfs_cmp_data_free(&cmp);
out_unlock:
if (same_inode)
- mutex_unlock(&src->i_mutex);
+ inode_unlock(src);
else
btrfs_double_inode_unlock(src, dst);
#define BTRFS_MAX_DEDUPE_LEN SZ_16M
-static long btrfs_ioctl_file_extent_same(struct file *file,
- struct btrfs_ioctl_same_args __user *argp)
+ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
+ struct file *dst_file, u64 dst_loff)
{
- struct btrfs_ioctl_same_args *same = NULL;
- struct btrfs_ioctl_same_extent_info *info;
- struct inode *src = file_inode(file);
- u64 off;
- u64 len;
- int i;
- int ret;
- unsigned long size;
+ 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;
- bool is_admin = capable(CAP_SYS_ADMIN);
- u16 count;
-
- if (!(file->f_mode & FMODE_READ))
- return -EINVAL;
-
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- if (get_user(count, &argp->dest_count)) {
- ret = -EFAULT;
- goto out;
- }
-
- size = offsetof(struct btrfs_ioctl_same_args __user, info[count]);
-
- same = memdup_user(argp, size);
-
- if (IS_ERR(same)) {
- ret = PTR_ERR(same);
- same = NULL;
- goto out;
- }
+ ssize_t res;
- off = same->logical_offset;
- len = same->length;
-
- /*
- * Limit the total length we will dedupe for each operation.
- * This is intended to bound the total time spent in this
- * ioctl to something sane.
- */
- if (len > BTRFS_MAX_DEDUPE_LEN)
- len = BTRFS_MAX_DEDUPE_LEN;
+ if (olen > BTRFS_MAX_DEDUPE_LEN)
+ olen = BTRFS_MAX_DEDUPE_LEN;
if (WARN_ON_ONCE(bs < PAGE_CACHE_SIZE)) {
/*
* result, btrfs_cmp_data() won't correctly handle
* this situation without an update.
*/
- ret = -EINVAL;
- goto out;
- }
-
- ret = -EISDIR;
- if (S_ISDIR(src->i_mode))
- goto out;
-
- ret = -EACCES;
- if (!S_ISREG(src->i_mode))
- goto out;
-
- /* pre-format output fields to sane values */
- for (i = 0; i < count; i++) {
- same->info[i].bytes_deduped = 0ULL;
- same->info[i].status = 0;
- }
-
- for (i = 0, info = same->info; i < count; i++, info++) {
- struct inode *dst;
- struct fd dst_file = fdget(info->fd);
- if (!dst_file.file) {
- info->status = -EBADF;
- continue;
- }
- dst = file_inode(dst_file.file);
-
- if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) {
- info->status = -EINVAL;
- } else if (file->f_path.mnt != dst_file.file->f_path.mnt) {
- info->status = -EXDEV;
- } else if (S_ISDIR(dst->i_mode)) {
- info->status = -EISDIR;
- } else if (!S_ISREG(dst->i_mode)) {
- info->status = -EACCES;
- } else {
- info->status = btrfs_extent_same(src, off, len, dst,
- info->logical_offset);
- if (info->status == 0)
- info->bytes_deduped += len;
- }
- fdput(dst_file);
+ return -EINVAL;
}
- ret = copy_to_user(argp, same, size);
- if (ret)
- ret = -EFAULT;
-
-out:
- mnt_drop_write_file(file);
- kfree(same);
- return ret;
+ res = btrfs_extent_same(src, loff, olen, dst, dst_loff);
+ if (res)
+ return res;
+ return olen;
}
static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
return ret;
}
-static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
- u64 off, u64 olen, u64 destoff)
+static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
+ u64 off, u64 olen, u64 destoff)
{
struct inode *inode = file_inode(file);
+ struct inode *src = file_inode(file_src);
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct fd src_file;
- struct inode *src;
int ret;
u64 len = olen;
u64 bs = root->fs_info->sb->s_blocksize;
- int same_inode = 0;
+ int same_inode = src == inode;
/*
* TODO:
* be either compressed or non-compressed.
*/
- /* the destination must be opened for writing */
- if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
- return -EINVAL;
-
if (btrfs_root_readonly(root))
return -EROFS;
- ret = mnt_want_write_file(file);
- if (ret)
- return ret;
-
- src_file = fdget(srcfd);
- if (!src_file.file) {
- ret = -EBADF;
- goto out_drop_write;
- }
-
- ret = -EXDEV;
- if (src_file.file->f_path.mnt != file->f_path.mnt)
- goto out_fput;
-
- src = file_inode(src_file.file);
-
- ret = -EINVAL;
- if (src == inode)
- same_inode = 1;
-
- /* the src must be open for reading */
- if (!(src_file.file->f_mode & FMODE_READ))
- goto out_fput;
+ if (file_src->f_path.mnt != file->f_path.mnt ||
+ src->i_sb != inode->i_sb)
+ return -EXDEV;
/* don't make the dst file partly checksummed */
if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
- goto out_fput;
+ return -EINVAL;
- ret = -EISDIR;
if (S_ISDIR(src->i_mode) || S_ISDIR(inode->i_mode))
- goto out_fput;
-
- ret = -EXDEV;
- if (src->i_sb != inode->i_sb)
- goto out_fput;
+ return -EISDIR;
if (!same_inode) {
btrfs_double_inode_lock(src, inode);
} else {
- mutex_lock(&src->i_mutex);
+ inode_lock(src);
}
/* determine range to clone */
u64 lock_start = min_t(u64, off, destoff);
u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
- lock_extent_range(src, lock_start, lock_len);
+ ret = lock_extent_range(src, lock_start, lock_len, true);
} else {
- btrfs_double_extent_lock(src, off, inode, destoff, len);
+ ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+ true);
+ }
+ ASSERT(ret == 0);
+ if (WARN_ON(ret)) {
+ /* ranges in the io trees already unlocked */
+ goto out_unlock;
}
ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
if (!same_inode)
btrfs_double_inode_unlock(src, inode);
else
- mutex_unlock(&src->i_mutex);
-out_fput:
- fdput(src_file);
-out_drop_write:
- mnt_drop_write_file(file);
+ inode_unlock(src);
return ret;
}
-static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
+ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ size_t len, unsigned int flags)
{
- struct btrfs_ioctl_clone_range_args args;
+ ssize_t ret;
- if (copy_from_user(&args, argp, sizeof(args)))
- return -EFAULT;
- return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
- args.src_length, args.dest_offset);
+ ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out);
+ if (ret == 0)
+ ret = len;
+ return ret;
+}
+
+int btrfs_clone_file_range(struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff, u64 len)
+{
+ return btrfs_clone_files(dst_file, src_file, off, len, destoff);
}
/*
return btrfs_ioctl_dev_info(root, argp);
case BTRFS_IOC_BALANCE:
return btrfs_ioctl_balance(file, NULL);
- case BTRFS_IOC_CLONE:
- return btrfs_ioctl_clone(file, arg, 0, 0, 0);
- case BTRFS_IOC_CLONE_RANGE:
- return btrfs_ioctl_clone_range(file, argp);
case BTRFS_IOC_TRANS_START:
return btrfs_ioctl_trans_start(file);
case BTRFS_IOC_TRANS_END:
return btrfs_ioctl_get_fslabel(file, argp);
case BTRFS_IOC_SET_FSLABEL:
return btrfs_ioctl_set_fslabel(file, argp);
- case BTRFS_IOC_FILE_EXTENT_SAME:
- return btrfs_ioctl_file_extent_same(file, argp);
case BTRFS_IOC_GET_SUPPORTED_FEATURES:
return btrfs_ioctl_get_supported_features(file, argp);
case BTRFS_IOC_GET_FEATURES: