summaryrefslogtreecommitdiff
path: root/fs/btrfs/ioctl.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/ioctl.c')
-rw-r--r--fs/btrfs/ioctl.c286
1 files changed, 163 insertions, 123 deletions
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fa1b78cf25f6..fd172a93d11a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -86,6 +86,19 @@ struct btrfs_ioctl_received_subvol_args_32 {
struct btrfs_ioctl_received_subvol_args_32)
#endif
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+struct btrfs_ioctl_send_args_32 {
+ __s64 send_fd; /* in */
+ __u64 clone_sources_count; /* in */
+ compat_uptr_t clone_sources; /* in */
+ __u64 parent_root; /* in */
+ __u64 flags; /* in */
+ __u64 reserved[4]; /* in */
+} __attribute__ ((__packed__));
+
+#define BTRFS_IOC_SEND_32 _IOW(BTRFS_IOCTL_MAGIC, 38, \
+ struct btrfs_ioctl_send_args_32)
+#endif
static int btrfs_clone(struct inode *src, struct inode *inode,
u64 off, u64 olen, u64 olen_aligned, u64 destoff,
@@ -156,37 +169,6 @@ void btrfs_update_iflags(struct inode *inode)
new_fl);
}
-/*
- * Inherit flags from the parent inode.
- *
- * Currently only the compression flags and the cow flags are inherited.
- */
-void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
-{
- unsigned int flags;
-
- if (!dir)
- return;
-
- flags = BTRFS_I(dir)->flags;
-
- if (flags & BTRFS_INODE_NOCOMPRESS) {
- BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS;
- BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
- } else if (flags & BTRFS_INODE_COMPRESS) {
- BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
- BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
- }
-
- if (flags & BTRFS_INODE_NODATACOW) {
- BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
- if (S_ISREG(inode->i_mode))
- BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
- }
-
- btrfs_update_iflags(inode);
-}
-
static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
{
struct btrfs_inode *ip = BTRFS_I(file_inode(file));
@@ -327,8 +309,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
comp = "lzo";
- else
+ else if (fs_info->compress_type == BTRFS_COMPRESS_ZLIB)
comp = "zlib";
+ else
+ comp = "zstd";
ret = btrfs_set_prop(inode, "btrfs.compression",
comp, strlen(comp), 0);
if (ret)
@@ -638,23 +622,6 @@ fail_free:
return ret;
}
-static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
-{
- s64 writers;
- DEFINE_WAIT(wait);
-
- do {
- prepare_to_wait(&root->subv_writers->wait, &wait,
- TASK_UNINTERRUPTIBLE);
-
- writers = percpu_counter_sum(&root->subv_writers->counter);
- if (writers)
- schedule();
-
- finish_wait(&root->subv_writers->wait, &wait);
- } while (writers);
-}
-
static int create_snapshot(struct btrfs_root *root, struct inode *dir,
struct dentry *dentry,
u64 *async_transid, bool readonly,
@@ -681,9 +648,11 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
goto free_pending;
}
- atomic_inc(&root->will_be_snapshoted);
+ atomic_inc(&root->will_be_snapshotted);
smp_mb__after_atomic();
- btrfs_wait_for_no_snapshoting_writes(root);
+ /* wait for no snapshot writes */
+ wait_event(root->subv_writers->wait,
+ percpu_counter_sum(&root->subv_writers->counter) == 0);
ret = btrfs_start_delalloc_inodes(root, 0);
if (ret)
@@ -754,8 +723,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
fail:
btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
dec_and_free:
- if (atomic_dec_and_test(&root->will_be_snapshoted))
- wake_up_atomic_t(&root->will_be_snapshoted);
+ if (atomic_dec_and_test(&root->will_be_snapshotted))
+ wake_up_atomic_t(&root->will_be_snapshotted);
free_pending:
kfree(pending_snapshot->root_item);
btrfs_free_path(pending_snapshot->path);
@@ -1248,6 +1217,7 @@ again:
unlock_page(pages[i]);
put_page(pages[i]);
}
+ btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return i_done;
out:
@@ -1258,6 +1228,7 @@ out:
btrfs_delalloc_release_space(inode, data_reserved,
start_index << PAGE_SHIFT,
page_cnt << PAGE_SHIFT);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return ret;
@@ -1286,6 +1257,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
unsigned long cluster = max_cluster;
u64 new_align = ~((u64)SZ_128K - 1);
struct page **pages = NULL;
+ bool do_compress = range->flags & BTRFS_DEFRAG_RANGE_COMPRESS;
if (isize == 0)
return 0;
@@ -1293,7 +1265,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (range->start >= isize)
return -EINVAL;
- if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
+ if (do_compress) {
if (range->compress_type > BTRFS_COMPRESS_TYPES)
return -EINVAL;
if (range->compress_type)
@@ -1304,20 +1276,19 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
extent_thresh = SZ_256K;
/*
- * if we were not given a file, allocate a readahead
- * context
+ * If we were not given a file, allocate a readahead context. As
+ * readahead is just an optimization, defrag will work without it so
+ * we don't error out.
*/
if (!file) {
- ra = kzalloc(sizeof(*ra), GFP_NOFS);
- if (!ra)
- return -ENOMEM;
- file_ra_state_init(ra, inode->i_mapping);
+ ra = kzalloc(sizeof(*ra), GFP_KERNEL);
+ if (ra)
+ file_ra_state_init(ra, inode->i_mapping);
} else {
ra = &file->f_ra;
}
- pages = kmalloc_array(max_cluster, sizeof(struct page *),
- GFP_NOFS);
+ pages = kmalloc_array(max_cluster, sizeof(struct page *), GFP_KERNEL);
if (!pages) {
ret = -ENOMEM;
goto out_ra;
@@ -1373,8 +1344,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT,
extent_thresh, &last_len, &skip,
- &defrag_end, range->flags &
- BTRFS_DEFRAG_RANGE_COMPRESS)) {
+ &defrag_end, do_compress)){
unsigned long next;
/*
* the should_defrag function tells us how much to skip
@@ -1395,14 +1365,15 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (i + cluster > ra_index) {
ra_index = max(i, ra_index);
- btrfs_force_ra(inode->i_mapping, ra, file, ra_index,
- cluster);
+ if (ra)
+ page_cache_sync_readahead(inode->i_mapping, ra,
+ file, ra_index, cluster);
ra_index += cluster;
}
inode_lock(inode);
- if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
- BTRFS_I(inode)->force_compress = compress_type;
+ if (do_compress)
+ BTRFS_I(inode)->defrag_compress = compress_type;
ret = cluster_pages_for_defrag(inode, pages, i, cluster);
if (ret < 0) {
inode_unlock(inode);
@@ -1449,31 +1420,18 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
filemap_flush(inode->i_mapping);
}
- if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
- /* the filemap_flush will queue IO into the worker threads, but
- * we have to make sure the IO is actually started and that
- * ordered extents get created before we return
- */
- atomic_inc(&fs_info->async_submit_draining);
- while (atomic_read(&fs_info->nr_async_submits) ||
- atomic_read(&fs_info->async_delalloc_pages)) {
- wait_event(fs_info->async_submit_wait,
- (atomic_read(&fs_info->nr_async_submits) == 0 &&
- atomic_read(&fs_info->async_delalloc_pages) == 0));
- }
- atomic_dec(&fs_info->async_submit_draining);
- }
-
if (range->compress_type == BTRFS_COMPRESS_LZO) {
btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+ } else if (range->compress_type == BTRFS_COMPRESS_ZSTD) {
+ btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
}
ret = defrag_count;
out_ra:
- if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
+ if (do_compress) {
inode_lock(inode);
- BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
+ BTRFS_I(inode)->defrag_compress = BTRFS_COMPRESS_NONE;
inode_unlock(inode);
}
if (!file)
@@ -1600,8 +1558,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
goto out_free;
}
- new_size = div_u64(new_size, fs_info->sectorsize);
- new_size *= fs_info->sectorsize;
+ new_size = round_down(new_size, fs_info->sectorsize);
btrfs_info_in_rcu(fs_info, "new size for %s is %llu",
rcu_str_deref(device->name), new_size);
@@ -1870,8 +1827,13 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
ret = btrfs_update_root(trans, fs_info->tree_root,
&root->root_key, &root->root_item);
+ if (ret < 0) {
+ btrfs_end_transaction(trans);
+ goto out_reset;
+ }
+
+ ret = btrfs_commit_transaction(trans);
- btrfs_commit_transaction(trans);
out_reset:
if (ret)
btrfs_set_root_flags(&root->root_item, root_flags);
@@ -2201,16 +2163,13 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
buf_size = args.buf_size;
- if (buf_size < sizeof(struct btrfs_ioctl_search_header))
- return -EOVERFLOW;
-
/* limit result size to 16MB */
if (buf_size > buf_limit)
buf_size = buf_limit;
inode = file_inode(file);
ret = search_ioctl(inode, &args.key, &buf_size,
- (char *)(&uarg->buf[0]));
+ (char __user *)(&uarg->buf[0]));
if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key)))
ret = -EFAULT;
else if (ret == -EOVERFLOW &&
@@ -2804,9 +2763,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
}
mutex_unlock(&fs_devices->device_list_mutex);
- fi_args->nodesize = fs_info->super_copy->nodesize;
- fi_args->sectorsize = fs_info->super_copy->sectorsize;
- fi_args->clone_alignment = fs_info->super_copy->sectorsize;
+ fi_args->nodesize = fs_info->nodesize;
+ fi_args->sectorsize = fs_info->sectorsize;
+ fi_args->clone_alignment = fs_info->sectorsize;
if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
ret = -EFAULT;
@@ -3063,7 +3022,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
out:
if (ret)
btrfs_cmp_data_free(cmp);
- return 0;
+ return ret;
}
static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp)
@@ -3737,7 +3696,7 @@ process_slot:
if (disko) {
inode_add_bytes(inode, datal);
ret = btrfs_inc_extent_ref(trans,
- fs_info,
+ root,
disko, diskl, 0,
root->root_key.objectid,
btrfs_ino(BTRFS_I(inode)),
@@ -3998,15 +3957,35 @@ static long btrfs_ioctl_trans_start(struct file *file)
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
+ struct btrfs_file_private *private;
int ret;
+ static bool warned = false;
ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out;
+ if (!warned) {
+ btrfs_warn(fs_info,
+ "Userspace transaction mechanism is considered "
+ "deprecated and slated to be removed in 4.17. "
+ "If you have a valid use case please "
+ "speak up on the mailing list");
+ WARN_ON(1);
+ warned = true;
+ }
+
ret = -EINPROGRESS;
- if (file->private_data)
+ private = file->private_data;
+ if (private && private->trans)
goto out;
+ if (!private) {
+ private = kzalloc(sizeof(struct btrfs_file_private),
+ GFP_KERNEL);
+ if (!private)
+ return -ENOMEM;
+ file->private_data = private;
+ }
ret = -EROFS;
if (btrfs_root_readonly(root))
@@ -4023,7 +4002,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
if (IS_ERR(trans))
goto out_drop;
- file->private_data = trans;
+ private->trans = trans;
return 0;
out_drop:
@@ -4072,6 +4051,10 @@ 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)) {
+ ret = -ENOENT;
+ goto out;
+ }
path = btrfs_alloc_path();
if (!path) {
@@ -4136,10 +4119,12 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_space_info *dest_orig;
struct btrfs_ioctl_space_info __user *user_dest;
struct btrfs_space_info *info;
- u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
- BTRFS_BLOCK_GROUP_SYSTEM,
- BTRFS_BLOCK_GROUP_METADATA,
- BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
+ static const u64 types[] = {
+ BTRFS_BLOCK_GROUP_DATA,
+ BTRFS_BLOCK_GROUP_SYSTEM,
+ BTRFS_BLOCK_GROUP_METADATA,
+ BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA
+ };
int num_types = 4;
int alloc_size;
int ret = 0;
@@ -4278,14 +4263,13 @@ long btrfs_ioctl_trans_end(struct file *file)
{
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_trans_handle *trans;
+ struct btrfs_file_private *private = file->private_data;
- trans = file->private_data;
- if (!trans)
+ if (!private || !private->trans)
return -EINVAL;
- file->private_data = NULL;
- btrfs_end_transaction(trans);
+ btrfs_end_transaction(private->trans);
+ private->trans = NULL;
atomic_dec(&root->fs_info->open_ioctl_trans);
@@ -4438,7 +4422,7 @@ static long btrfs_ioctl_dev_replace(struct btrfs_fs_info *fs_info,
switch (p->cmd) {
case BTRFS_IOCTL_DEV_REPLACE_CMD_START:
- if (fs_info->sb->s_flags & MS_RDONLY) {
+ if (sb_rdonly(fs_info->sb)) {
ret = -EROFS;
goto out;
}
@@ -4512,8 +4496,8 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
ipath->fspath->val[i] = rel_ptr;
}
- ret = copy_to_user((void *)(unsigned long)ipa->fspath,
- (void *)(unsigned long)ipath->fspath, size);
+ ret = copy_to_user((void __user *)(unsigned long)ipa->fspath,
+ ipath->fspath, size);
if (ret) {
ret = -EFAULT;
goto out;
@@ -4548,13 +4532,14 @@ static int build_ino_list(u64 inum, u64 offset, u64 root, void *ctx)
}
static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
- void __user *arg)
+ void __user *arg, int version)
{
int ret = 0;
int size;
struct btrfs_ioctl_logical_ino_args *loi;
struct btrfs_data_container *inodes = NULL;
struct btrfs_path *path = NULL;
+ bool ignore_offset;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -4563,13 +4548,30 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
if (IS_ERR(loi))
return PTR_ERR(loi);
+ if (version == 1) {
+ ignore_offset = false;
+ size = min_t(u32, loi->size, SZ_64K);
+ } else {
+ /* All reserved bits must be 0 for now */
+ if (memchr_inv(loi->reserved, 0, sizeof(loi->reserved))) {
+ ret = -EINVAL;
+ goto out_loi;
+ }
+ /* Only accept flags we have defined so far */
+ if (loi->flags & ~(BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET)) {
+ ret = -EINVAL;
+ goto out_loi;
+ }
+ ignore_offset = loi->flags & BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET;
+ size = min_t(u32, loi->size, SZ_16M);
+ }
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
goto out;
}
- size = min_t(u32, loi->size, SZ_64K);
inodes = init_data_container(size);
if (IS_ERR(inodes)) {
ret = PTR_ERR(inodes);
@@ -4578,20 +4580,21 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
}
ret = iterate_inodes_from_logical(loi->logical, fs_info, path,
- build_ino_list, inodes);
+ build_ino_list, inodes, ignore_offset);
if (ret == -EINVAL)
ret = -ENOENT;
if (ret < 0)
goto out;
- ret = copy_to_user((void *)(unsigned long)loi->inodes,
- (void *)(unsigned long)inodes, size);
+ ret = copy_to_user((void __user *)(unsigned long)loi->inodes, inodes,
+ size);
if (ret)
ret = -EFAULT;
out:
btrfs_free_path(path);
kvfree(inodes);
+out_loi:
kfree(loi);
return ret;
@@ -5168,15 +5171,11 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
root->root_key.objectid);
if (ret < 0 && ret != -EEXIST) {
btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
goto out;
}
}
ret = btrfs_commit_transaction(trans);
- if (ret < 0) {
- btrfs_abort_transaction(trans, ret);
- goto out;
- }
-
out:
up_write(&fs_info->subvol_sem);
mnt_drop_write_file(file);
@@ -5498,6 +5497,41 @@ out_drop_write:
return ret;
}
+static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat)
+{
+ struct btrfs_ioctl_send_args *arg;
+ int ret;
+
+ if (compat) {
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+ struct btrfs_ioctl_send_args_32 args32;
+
+ ret = copy_from_user(&args32, argp, sizeof(args32));
+ if (ret)
+ return -EFAULT;
+ arg = kzalloc(sizeof(*arg), GFP_KERNEL);
+ if (!arg)
+ return -ENOMEM;
+ arg->send_fd = args32.send_fd;
+ arg->clone_sources_count = args32.clone_sources_count;
+ arg->clone_sources = compat_ptr(args32.clone_sources);
+ arg->parent_root = args32.parent_root;
+ arg->flags = args32.flags;
+ memcpy(arg->reserved, args32.reserved,
+ sizeof(args32.reserved));
+#else
+ return -ENOTTY;
+#endif
+ } else {
+ arg = memdup_user(argp, sizeof(*arg));
+ if (IS_ERR(arg))
+ return PTR_ERR(arg);
+ }
+ ret = btrfs_ioctl_send(file, arg);
+ kfree(arg);
+ return ret;
+}
+
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
@@ -5562,7 +5596,9 @@ long btrfs_ioctl(struct file *file, unsigned int
case BTRFS_IOC_INO_PATHS:
return btrfs_ioctl_ino_to_path(root, argp);
case BTRFS_IOC_LOGICAL_INO:
- return btrfs_ioctl_logical_to_ino(fs_info, argp);
+ return btrfs_ioctl_logical_to_ino(fs_info, argp, 1);
+ case BTRFS_IOC_LOGICAL_INO_V2:
+ return btrfs_ioctl_logical_to_ino(fs_info, argp, 2);
case BTRFS_IOC_SPACE_INFO:
return btrfs_ioctl_space_info(fs_info, argp);
case BTRFS_IOC_SYNC: {
@@ -5603,7 +5639,11 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_set_received_subvol_32(file, argp);
#endif
case BTRFS_IOC_SEND:
- return btrfs_ioctl_send(file, argp);
+ return _btrfs_ioctl_send(file, argp, false);
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+ case BTRFS_IOC_SEND_32:
+ return _btrfs_ioctl_send(file, argp, true);
+#endif
case BTRFS_IOC_GET_DEV_STATS:
return btrfs_ioctl_get_dev_stats(fs_info, argp);
case BTRFS_IOC_QUOTA_CTL:
generated by cgit (git 2.34.1) at 2024-06-14 20:46:27 +0000