#include <linux/ima.h>
/**
- * inode_change_ok - check if attribute changes to an inode are allowed
- * @inode: inode to check
+ * setattr_prepare - check if attribute changes to a dentry are allowed
+ * @dentry: dentry to check
* @attr: attributes to change
*
* Check if we are allowed to change the attributes contained in @attr
- * in the given inode. This includes the normal unix access permission
- * checks, as well as checks for rlimits and others.
+ * in the given dentry. This includes the normal unix access permission
+ * checks, as well as checks for rlimits and others. The function also clears
+ * SGID bit from mode if user is not allowed to set it. Also file capabilities
+ * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set.
*
* Should be called as the first thing in ->setattr implementations,
* possibly after taking additional locks.
*/
- int inode_change_ok(const struct inode *inode, struct iattr *attr)
+ int setattr_prepare(struct dentry *dentry, struct iattr *attr)
{
+ struct inode *inode = d_inode(dentry);
unsigned int ia_valid = attr->ia_valid;
/*
/* If force is set do it anyway. */
if (ia_valid & ATTR_FORCE)
- return 0;
+ goto kill_priv;
/* Make sure a caller can chown. */
if ((ia_valid & ATTR_UID) &&
return -EPERM;
}
+ kill_priv:
+ /* User has permission for the change */
+ if (ia_valid & ATTR_KILL_PRIV) {
+ int error;
+
+ error = security_inode_killpriv(dentry);
+ if (error)
+ return error;
+ }
+
return 0;
}
- EXPORT_SYMBOL(inode_change_ok);
+ EXPORT_SYMBOL(setattr_prepare);
/**
* inode_newsize_ok - may this inode be truncated to a given size
return -EPERM;
}
+ /*
+ * If utimes(2) and friends are called with times == NULL (or both
+ * times are UTIME_NOW), then we need to check for write permission
+ */
+ if (ia_valid & ATTR_TOUCH) {
+ if (IS_IMMUTABLE(inode))
+ return -EPERM;
+
+ if (!inode_owner_or_capable(inode)) {
+ error = inode_permission(inode, MAY_WRITE);
+ if (error)
+ return error;
+ }
+ }
+
if ((ia_valid & ATTR_MODE)) {
umode_t amode = attr->ia_mode;
/* Flag setting protected by i_mutex */
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_PRIV) {
- attr->ia_valid &= ~ATTR_KILL_PRIV;
- ia_valid &= ~ATTR_KILL_PRIV;
error = security_inode_need_killpriv(dentry);
- if (error > 0)
- error = security_inode_killpriv(dentry);
- if (error)
+ if (error < 0)
return error;
+ if (error == 0)
+ ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV;
}
/*
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
goto free_pages_out;
}
}
lock_extent(io_tree, async_extent->start,
async_extent->start + async_extent->ram_size - 1);
- ret = btrfs_reserve_extent(root,
+ ret = btrfs_reserve_extent(root, async_extent->ram_size,
async_extent->compressed_size,
async_extent->compressed_size,
0, alloc_hint, &ins, 1, 1);
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
-
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
*nr_written = *nr_written +
(end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
unsigned long op;
cur_alloc_size = disk_num_bytes;
- ret = btrfs_reserve_extent(root, cur_alloc_size,
+ ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
extent_clear_unlock_delalloc(inode, cur_offset,
cur_offset + num_bytes - 1,
locked_page, EXTENT_LOCKED |
- EXTENT_DELALLOC, PAGE_UNLOCK |
- PAGE_SET_PRIVATE2);
+ EXTENT_DELALLOC |
+ EXTENT_CLEAR_DATA_RESV,
+ PAGE_UNLOCK | PAGE_SET_PRIVATE2);
+
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
return;
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list && !(state->state & EXTENT_NORESERVE))
+ && do_list && !(state->state & EXTENT_NORESERVE)
+ && (*bits & (EXTENT_DO_ACCOUNTING |
+ EXTENT_CLEAR_DATA_RESV)))
btrfs_free_reserved_data_space_noquota(inode,
state->start, len);
found_key.offset = 0;
inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
ret = PTR_ERR_OR_ZERO(inode);
- if (ret && ret != -ESTALE)
+ if (ret && ret != -ENOENT)
goto out;
- if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ if (ret == -ENOENT && root == root->fs_info->tree_root) {
struct btrfs_root *dead_root;
struct btrfs_fs_info *fs_info = root->fs_info;
int is_dead_root = 0;
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
*/
- if (ret == -ESTALE) {
+ if (ret == -ENOENT) {
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
/*
* read an inode from the btree into the in-memory inode
*/
-static void btrfs_read_locked_inode(struct inode *inode)
+static int btrfs_read_locked_inode(struct inode *inode)
{
struct btrfs_path *path;
struct extent_buffer *leaf;
filled = true;
path = btrfs_alloc_path();
- if (!path)
+ if (!path) {
+ ret = -ENOMEM;
goto make_bad;
+ }
memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
- if (ret)
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
goto make_bad;
+ }
leaf = path->nodes[0];
}
btrfs_update_iflags(inode);
- return;
+ return 0;
make_bad:
btrfs_free_path(path);
make_bad_inode(inode);
+ return ret;
}
/*
int err = 0;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_trans_handle *trans;
+ u64 last_unlink_trans;
if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
return -ENOTEMPTY;
if (err)
goto out;
+ last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
+
/* now the directory is empty */
err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
dentry->d_name.name, dentry->d_name.len);
- if (!err)
+ if (!err) {
btrfs_i_size_write(inode, 0);
+ /*
+ * Propagate the last_unlink_trans value of the deleted dir to
+ * its parent directory. This is to prevent an unrecoverable
+ * log tree in the case we do something like this:
+ * 1) create dir foo
+ * 2) create snapshot under dir foo
+ * 3) delete the snapshot
+ * 4) rmdir foo
+ * 5) mkdir foo
+ * 6) fsync foo or some file inside foo
+ */
+ if (last_unlink_trans >= trans->transid)
+ BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
+ }
out:
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root);
if (btrfs_root_readonly(root))
return -EROFS;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
- btrfs_read_locked_inode(inode);
+ int ret;
+
+ ret = btrfs_read_locked_inode(inode);
if (!is_bad_inode(inode)) {
inode_tree_add(inode);
unlock_new_inode(inode);
} else {
unlock_new_inode(inode);
iput(inode);
- inode = ERR_PTR(-ESTALE);
+ ASSERT(ret < 0);
+ inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
}
}
int ret;
alloc_hint = get_extent_allocation_hint(inode, start, len);
- ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
+ ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0,
alloc_hint, &ins, 1, 1);
if (ret)
return ERR_PTR(ret);
ret = PTR_ERR(em2);
goto unlock_err;
}
+ /*
+ * For inode marked NODATACOW or extent marked PREALLOC,
+ * use the existing or preallocated extent, so does not
+ * need to adjust btrfs_space_info's bytes_may_use.
+ */
+ btrfs_free_reserved_data_space_noquota(inode,
+ start, len);
goto unlock;
}
}
i_size_write(inode, start + len);
adjust_dio_outstanding_extents(inode, dio_data, len);
- btrfs_free_reserved_data_space(inode, start, len);
WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
dio_data->unsubmitted_oe_range_end = start + len;
u64 last_alloc = (u64)-1;
int ret = 0;
bool own_trans = true;
+ u64 end = start + num_bytes - 1;
if (trans)
own_trans = false;
* sized chunks.
*/
cur_bytes = min(cur_bytes, last_alloc);
- ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
- *alloc_hint, &ins, 1, 0);
+ ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes,
+ min_size, 0, *alloc_hint, &ins, 1, 0);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
if (own_trans)
btrfs_end_transaction(trans, root);
}
+ if (cur_offset < end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ end - cur_offset + 1);
return ret;
}
}
-/* Inspired by filemap_check_errors() */
-int btrfs_inode_check_errors(struct inode *inode)
-{
- int ret = 0;
-
- if (test_bit(AS_ENOSPC, &inode->i_mapping->flags) &&
- test_and_clear_bit(AS_ENOSPC, &inode->i_mapping->flags))
- ret = -ENOSPC;
- if (test_bit(AS_EIO, &inode->i_mapping->flags) &&
- test_and_clear_bit(AS_EIO, &inode->i_mapping->flags))
- ret = -EIO;
-
- return ret;
-}
-
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
cifs_dbg(FYI, "Update attributes: %s inode 0x%p count %d dentry: 0x%p d_time %ld jiffies %ld\n",
full_path, inode, inode->i_count.counter,
- dentry, dentry->d_time, jiffies);
+ dentry, cifs_get_time(dentry), jiffies);
if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
attrs->ia_valid |= ATTR_FORCE;
- rc = inode_change_ok(inode, attrs);
+ rc = setattr_prepare(direntry, attrs);
if (rc < 0)
goto out;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
attrs->ia_valid |= ATTR_FORCE;
- rc = inode_change_ok(inode, attrs);
+ rc = setattr_prepare(direntry, attrs);
if (rc < 0) {
free_xid(xid);
return rc;
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
struct inode *inode = d_inode(dentry);
int err;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
{
struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
- int ret;
if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- ret = fscrypt_process_policy(inode, &policy);
- mnt_drop_write_file(filp);
- return ret;
+ return fscrypt_process_policy(filp, &policy);
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
if (unlikely(f2fs_readonly(src->i_sb)))
return -EROFS;
- if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
- return -EISDIR;
+ if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
+ return -EINVAL;
if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
return -EOPNOTSUPP;
inode_lock(src);
- if (src != dst)
- inode_lock(dst);
+ if (src != dst) {
+ if (!inode_trylock(dst)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ }
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
out_unlock:
if (src != dst)
inode_unlock(dst);
+out:
inode_unlock(src);
return ret;
}
req->out.args[0].size = count;
}
-static void fuse_release_user_pages(struct fuse_req *req, int write)
+static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty)
{
unsigned i;
for (i = 0; i < req->num_pages; i++) {
struct page *page = req->pages[i];
- if (write)
+ if (should_dirty)
set_page_dirty_lock(page);
put_page(page);
}
loff_t *ppos, int flags)
{
int write = flags & FUSE_DIO_WRITE;
+ bool should_dirty = !write && iter_is_iovec(iter);
int cuse = flags & FUSE_DIO_CUSE;
struct file *file = io->file;
struct inode *inode = file->f_mapping->host;
nres = fuse_send_read(req, io, pos, nbytes, owner);
if (!io->async)
- fuse_release_user_pages(req, !write);
+ fuse_release_user_pages(req, should_dirty);
if (req->out.h.error) {
err = req->out.h.error;
break;
attr.ia_file = file;
attr.ia_valid |= ATTR_FILE;
- fuse_do_setattr(inode, &attr, file);
+ fuse_do_setattr(file_dentry(file), &attr, file);
}
static inline loff_t fuse_round_up(loff_t off)
if (!(attr->ia_valid & OCFS2_VALID_ATTRS))
return 0;
- status = inode_change_ok(inode, attr);
+ status = setattr_prepare(dentry, attr);
if (status)
return status;
u64 start, u64 len)
{
int ret = 0;
- u64 tmpend, end = start + len;
+ u64 tmpend = 0;
+ u64 end = start + len;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
unsigned int csize = osb->s_clustersize;
handle_t *handle;
}
/*
- * We want to get the byte offset of the end of the 1st cluster.
+ * If start is on a cluster boundary and end is somewhere in another
+ * cluster, we have not COWed the cluster starting at start, unless
+ * end is also within the same cluster. So, in this case, we skip this
+ * first call to ocfs2_zero_range_for_truncate() truncate and move on
+ * to the next one.
*/
- tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
- if (tmpend > end)
- tmpend = end;
+ if ((start & (csize - 1)) != 0) {
+ /*
+ * We want to get the byte offset of the end of the 1st
+ * cluster.
+ */
+ tmpend = (u64)osb->s_clustersize +
+ (start & ~(osb->s_clustersize - 1));
+ if (tmpend > end)
+ tmpend = end;
- trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
- (unsigned long long)tmpend);
+ trace_ocfs2_zero_partial_clusters_range1(
+ (unsigned long long)start,
+ (unsigned long long)tmpend);
- ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
- if (ret)
- mlog_errno(ret);
+ ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+ tmpend);
+ if (ret)
+ mlog_errno(ret);
+ }
if (tmpend < end) {
/*
struct iov_iter *iter)
{
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_direct_IO: %s\n",
- iocb->ki_filp->f_path.dentry->d_name.name);
+ "orangefs_direct_IO: %pD\n",
+ iocb->ki_filp);
return -EINVAL;
}
struct inode *inode = dentry->d_inode;
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_setattr: called on %s\n",
- dentry->d_name.name);
+ "orangefs_setattr: called on %pd\n",
+ dentry);
- ret = inode_change_ok(inode, iattr);
+ ret = setattr_prepare(dentry, iattr);
if (ret)
goto out;
struct orangefs_inode_s *orangefs_inode = NULL;
gossip_debug(GOSSIP_INODE_DEBUG,
- "orangefs_getattr: called on %s\n",
- dentry->d_name.name);
+ "orangefs_getattr: called on %pd\n",
+ dentry);
ret = orangefs_inode_getattr(inode, 0, 0);
if (ret == 0) {
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/posix_acl.h>
#include "overlayfs.h"
static int ovl_copy_up_truncate(struct dentry *dentry)
* inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
* check for a swapfile (which this won't be anyway).
*/
- err = inode_change_ok(dentry->d_inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
return err;
}
-static bool ovl_is_private_xattr(const char *name)
+bool ovl_is_private_xattr(const char *name)
{
-#define OVL_XATTR_PRE_NAME OVL_XATTR_PREFIX "."
- return strncmp(name, OVL_XATTR_PRE_NAME,
- sizeof(OVL_XATTR_PRE_NAME) - 1) == 0;
+ return strncmp(name, OVL_XATTR_PREFIX,
+ sizeof(OVL_XATTR_PREFIX) - 1) == 0;
}
-int ovl_setxattr(struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags)
{
int err;
- struct dentry *upperdentry;
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
const struct cred *old_cred;
err = ovl_want_write(dentry);
if (err)
goto out;
+ if (!value && !OVL_TYPE_UPPER(type)) {
+ err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+ if (err < 0)
+ goto out_drop_write;
+ }
+
err = ovl_copy_up(dentry);
if (err)
goto out_drop_write;
- upperdentry = ovl_dentry_upper(dentry);
+ if (!OVL_TYPE_UPPER(type))
+ ovl_path_upper(dentry, &realpath);
+
old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_setxattr(upperdentry, name, value, size, flags);
+ if (value)
+ err = vfs_setxattr(realpath.dentry, name, value, size, flags);
+ else {
+ WARN_ON(flags != XATTR_REPLACE);
+ err = vfs_removexattr(realpath.dentry, name);
+ }
revert_creds(old_cred);
out_drop_write:
return err;
}
-ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size)
+int ovl_xattr_get(struct dentry *dentry, const char *name,
+ void *value, size_t size)
{
struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
const struct cred *old_cred;
- if (ovl_is_private_xattr(name))
- return -ENODATA;
-
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_getxattr(realdentry, name, value, size);
revert_creds(old_cred);
{
struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
- int off;
+ size_t len;
+ char *s;
const struct cred *old_cred;
old_cred = ovl_override_creds(dentry->d_sb);
return res;
/* filter out private xattrs */
- for (off = 0; off < res;) {
- char *s = list + off;
- size_t slen = strlen(s) + 1;
+ for (s = list, len = res; len;) {
+ size_t slen = strnlen(s, len) + 1;
- BUG_ON(off + slen > res);
+ /* underlying fs providing us with an broken xattr list? */
+ if (WARN_ON(slen > len))
+ return -EIO;
+ len -= slen;
if (ovl_is_private_xattr(s)) {
res -= slen;
- memmove(s, s + slen, res - off);
+ memmove(s, s + slen, len);
} else {
- off += slen;
+ s += slen;
}
}
return res;
}
-int ovl_removexattr(struct dentry *dentry, const char *name)
-{
- int err;
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
- const struct cred *old_cred;
-
- err = ovl_want_write(dentry);
- if (err)
- goto out;
-
- err = -ENODATA;
- if (ovl_is_private_xattr(name))
- goto out_drop_write;
-
- if (!OVL_TYPE_UPPER(type)) {
- err = vfs_getxattr(realpath.dentry, name, NULL, 0);
- if (err < 0)
- goto out_drop_write;
-
- err = ovl_copy_up(dentry);
- if (err)
- goto out_drop_write;
-
- ovl_path_upper(dentry, &realpath);
- }
-
- old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_removexattr(realpath.dentry, name);
- revert_creds(old_cred);
-out_drop_write:
- ovl_drop_write(dentry);
-out:
- return err;
-}
-
struct posix_acl *ovl_get_acl(struct inode *inode, int type)
{
struct inode *realinode = ovl_inode_real(inode, NULL);
const struct cred *old_cred;
struct posix_acl *acl;
- if (!IS_POSIXACL(realinode))
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
return NULL;
if (!realinode->i_op->get_acl)
return NULL;
old_cred = ovl_override_creds(inode->i_sb);
- acl = realinode->i_op->get_acl(realinode, type);
+ acl = get_acl(realinode, type);
revert_creds(old_cred);
return acl;
.permission = ovl_permission,
.getattr = ovl_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
.readlink = ovl_readlink,
.getattr = ovl_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.update_time = ovl_update_time,
};
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_flags |= S_NOCMTIME;
+#ifdef CONFIG_FS_POSIX_ACL
+ inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
+#endif
mode &= S_IFMT;
switch (mode) {
if (IS_ERR(p))
return PTR_ERR(p);
+ ret = -ENOMEM;
clone = posix_acl_clone(p, GFP_NOFS);
if (!clone)
- goto no_mem;
+ goto err_release;
ret = posix_acl_create_masq(clone, mode);
if (ret < 0)
- goto no_mem_clone;
+ goto err_release_clone;
if (ret == 0)
posix_acl_release(clone);
return 0;
-no_mem_clone:
+err_release_clone:
posix_acl_release(clone);
-no_mem:
+err_release:
posix_acl_release(p);
- return -ENOMEM;
+ return ret;
}
EXPORT_SYMBOL_GPL(posix_acl_create);
+ /**
+ * posix_acl_update_mode - update mode in set_acl
+ *
+ * Update the file mode when setting an ACL: compute the new file permission
+ * bits based on the ACL. In addition, if the ACL is equivalent to the new
+ * file mode, set *acl to NULL to indicate that no ACL should be set.
+ *
+ * As with chmod, clear the setgit bit if the caller is not in the owning group
+ * or capable of CAP_FSETID (see inode_change_ok).
+ *
+ * Called from set_acl inode operations.
+ */
+ int posix_acl_update_mode(struct inode *inode, umode_t *mode_p,
+ struct posix_acl **acl)
+ {
+ umode_t mode = inode->i_mode;
+ int error;
+
+ error = posix_acl_equiv_mode(*acl, &mode);
+ if (error < 0)
+ return error;
+ if (error == 0)
+ *acl = NULL;
+ if (!in_group_p(inode->i_gid) &&
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID))
+ mode &= ~S_ISGID;
+ *mode_p = mode;
+ return 0;
+ }
+ EXPORT_SYMBOL(posix_acl_update_mode);
+
/*
* Fix up the uids and gids in posix acl extended attributes in place.
*/
struct user_namespace *to, struct user_namespace *from,
void *value, size_t size)
{
- posix_acl_xattr_header *header = (posix_acl_xattr_header *)value;
- posix_acl_xattr_entry *entry = (posix_acl_xattr_entry *)(header+1), *end;
+ struct posix_acl_xattr_header *header = value;
+ struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
int count;
kuid_t uid;
kgid_t gid;
if (!value)
return;
- if (size < sizeof(posix_acl_xattr_header))
+ if (size < sizeof(struct posix_acl_xattr_header))
return;
if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
return;
posix_acl_from_xattr(struct user_namespace *user_ns,
const void *value, size_t size)
{
- posix_acl_xattr_header *header = (posix_acl_xattr_header *)value;
- posix_acl_xattr_entry *entry = (posix_acl_xattr_entry *)(header+1), *end;
+ const struct posix_acl_xattr_header *header = value;
+ const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end;
int count;
struct posix_acl *acl;
struct posix_acl_entry *acl_e;
if (!value)
return NULL;
- if (size < sizeof(posix_acl_xattr_header))
+ if (size < sizeof(struct posix_acl_xattr_header))
return ERR_PTR(-EINVAL);
if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
return ERR_PTR(-EOPNOTSUPP);
posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
void *buffer, size_t size)
{
- posix_acl_xattr_header *ext_acl = (posix_acl_xattr_header *)buffer;
- posix_acl_xattr_entry *ext_entry;
+ struct posix_acl_xattr_header *ext_acl = buffer;
+ struct posix_acl_xattr_entry *ext_entry;
int real_size, n;
real_size = posix_acl_xattr_size(acl->a_count);
if (real_size > size)
return -ERANGE;
- ext_entry = ext_acl->a_entries;
+ ext_entry = (void *)(ext_acl + 1);
ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
for (n=0; n < acl->a_count; n++, ext_entry++) {
.llseek = generic_file_llseek,
};
-static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task)
-{
- struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
- if (mm && !IS_ERR(mm)) {
- unsigned int nwords = 0;
- do {
- nwords += 2;
- } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
- seq_write(m, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0]));
- mmput(mm);
- return 0;
- } else
- return PTR_ERR(mm);
-}
-
-
#ifdef CONFIG_KALLSYMS
/*
* Provides a wchan file via kallsyms in a proper one-value-per-file format.
if (attr->ia_valid & ATTR_MODE)
return -EPERM;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
.release = mem_release,
};
+static int auxv_open(struct inode *inode, struct file *file)
+{
+ return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
+}
+
+static ssize_t auxv_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct mm_struct *mm = file->private_data;
+ unsigned int nwords = 0;
+ do {
+ nwords += 2;
+ } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
+ return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv,
+ nwords * sizeof(mm->saved_auxv[0]));
+}
+
+static const struct file_operations proc_auxv_operations = {
+ .open = auxv_open,
+ .read = auxv_read,
+ .llseek = generic_file_llseek,
+ .release = mem_release,
+};
+
static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
{
struct task_struct *task;
- struct mm_struct *mm;
struct file *exe_file;
task = get_proc_task(d_inode(dentry));
if (!task)
return -ENOENT;
- mm = get_task_mm(task);
+ exe_file = get_task_exe_file(task);
put_task_struct(task);
- if (!mm)
- return -ENOENT;
- exe_file = get_mm_exe_file(mm);
- mmput(mm);
if (exe_file) {
*exe_path = exe_file->f_path;
path_get(&exe_file->f_path);
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
#endif
REG("environ", S_IRUSR, proc_environ_operations),
- ONE("auxv", S_IRUSR, proc_pid_auxv),
+ REG("auxv", S_IRUSR, proc_auxv_operations),
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
ONE("limits", S_IRUGO, proc_pid_limits),
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
#endif
REG("environ", S_IRUSR, proc_environ_operations),
- ONE("auxv", S_IRUSR, proc_pid_auxv),
+ REG("auxv", S_IRUSR, proc_auxv_operations),
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
ONE("limits", S_IRUGO, proc_pid_limits),
newattrs.ia_valid |= ATTR_MTIME_SET;
}
/*
- * Tell inode_change_ok(), that this is an explicit time
+ * Tell setattr_prepare(), that this is an explicit time
* update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET
* were used.
*/
newattrs.ia_valid |= ATTR_TIMES_SET;
} else {
- /*
- * If times is NULL (or both times are UTIME_NOW),
- * then we need to check permissions, because
- * setattr_prepare() won't do it.
- */
- error = -EPERM;
- if (IS_IMMUTABLE(inode))
- goto mnt_drop_write_and_out;
-
- error = -EACCES;
- if (!inode_owner_or_capable(inode)) {
- error = inode_permission(inode, MAY_WRITE);
- if (error)
- goto mnt_drop_write_and_out;
- }
+ newattrs.ia_valid |= ATTR_TOUCH;
}
retry_deleg:
inode_lock(inode);
goto retry_deleg;
}
-mnt_drop_write_and_out:
mnt_drop_write(path->mnt);
out:
return error;
* page is inserted into the pagecache when we have to serve a write
* fault on a hole. It should never be dirtied and can simply be
* dropped from the pagecache once we get real data for the page.
+ *
+ * XXX: This is racy against mmap, and there's nothing we can do about
+ * it. dax_do_io() should really do this invalidation internally as
+ * it will know if we've allocated over a holei for this specific IO and
+ * if so it needs to update the mapping tree and invalidate existing
+ * PTEs over the newly allocated range. Remove this invalidation when
+ * dax_do_io() is fixed up.
*/
if (mapping->nrpages) {
- ret = invalidate_inode_pages2(mapping);
+ loff_t end = iocb->ki_pos + iov_iter_count(from) - 1;
+
+ ret = invalidate_inode_pages2_range(mapping,
+ iocb->ki_pos >> PAGE_SHIFT,
+ end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
}
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
- error = xfs_setattr_size(ip, &iattr);
+ error = xfs_vn_setattr_size(file_dentry(file), &iattr);
if (error)
goto out_unlock;
}
inode->i_mtime = iattr->ia_mtime;
}
+ static int
+ xfs_vn_change_ok(
+ struct dentry *dentry,
+ struct iattr *iattr)
+ {
+ struct xfs_mount *mp = XFS_I(d_inode(dentry))->i_mount;
+
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ return -EROFS;
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ return setattr_prepare(dentry, iattr);
+ }
+
+ /*
+ * Set non-size attributes of an inode.
+ *
+ * Caution: The caller of this function is responsible for calling
+ * setattr_prepare() or otherwise verifying the change is fine.
+ */
int
xfs_setattr_nonsize(
struct xfs_inode *ip,
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
- trace_xfs_setattr(ip);
-
- /* If acls are being inherited, we already have this checked */
- if (!(flags & XFS_ATTR_NOACL)) {
- if (mp->m_flags & XFS_MOUNT_RDONLY)
- return -EROFS;
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
-
- error = inode_change_ok(inode, iattr);
- if (error)
- return error;
- }
-
ASSERT((mask & ATTR_SIZE) == 0);
/*
return error;
}
+ int
+ xfs_vn_setattr_nonsize(
+ struct dentry *dentry,
+ struct iattr *iattr)
+ {
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ int error;
+
+ trace_xfs_setattr(ip);
+
+ error = xfs_vn_change_ok(dentry, iattr);
+ if (error)
+ return error;
+ return xfs_setattr_nonsize(ip, iattr, 0);
+ }
+
/*
* Truncate file. Must have write permission and not be a directory.
+ *
+ * Caution: The caller of this function is responsible for calling
+ * setattr_prepare() or otherwise verifying the change is fine.
*/
int
xfs_setattr_size(
uint lock_flags = 0;
bool did_zeroing = false;
- trace_xfs_setattr(ip);
-
- if (mp->m_flags & XFS_MOUNT_RDONLY)
- return -EROFS;
-
- if (XFS_FORCED_SHUTDOWN(mp))
- return -EIO;
-
- error = inode_change_ok(inode, iattr);
- if (error)
- return error;
-
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
goto out_unlock;
}
+ int
+ xfs_vn_setattr_size(
+ struct dentry *dentry,
+ struct iattr *iattr)
+ {
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ int error;
+
+ trace_xfs_setattr(ip);
+
+ error = xfs_vn_change_ok(dentry, iattr);
+ if (error)
+ return error;
+ return xfs_setattr_size(ip, iattr);
+ }
+
STATIC int
xfs_vn_setattr(
struct dentry *dentry,
struct iattr *iattr)
{
- struct xfs_inode *ip = XFS_I(d_inode(dentry));
int error;
if (iattr->ia_valid & ATTR_SIZE) {
- uint iolock = XFS_IOLOCK_EXCL;
+ struct xfs_inode *ip = XFS_I(d_inode(dentry));
+ uint iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, iolock);
error = xfs_break_layouts(d_inode(dentry), &iolock, true);
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
- error = xfs_setattr_size(ip, iattr);
+ error = xfs_vn_setattr_size(dentry, iattr);
}
xfs_iunlock(ip, iolock);
} else {
- error = xfs_setattr_nonsize(ip, iattr, 0);
+ error = xfs_vn_setattr_nonsize(dentry, iattr);
}
return error;
int error;
xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED);
- error = iomap_fiemap(inode, fieinfo, start, length, &xfs_iomap_ops);
+ if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+ fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
+ error = iomap_fiemap(inode, fieinfo, start, length,
+ &xfs_xattr_iomap_ops);
+ } else {
+ error = iomap_fiemap(inode, fieinfo, start, length,
+ &xfs_iomap_ops);
+ }
xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
return error;
extern struct files_stat_struct files_stat;
extern unsigned long get_max_files(void);
-extern int sysctl_nr_open;
+extern unsigned int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
extern int sysctl_protected_symlinks;
#define ATTR_KILL_PRIV (1 << 14)
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
+#define ATTR_TOUCH (1 << 17)
/*
* Whiteout is represented by a char device. The following constants define the
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
+#define ACL_DONT_CACHE ((void *)(-3))
static inline struct posix_acl *
uncached_acl_sentinel(struct task_struct *task)
extern void send_sigio(struct fown_struct *fown, int fd, int band);
+/*
+ * Return the inode to use for locking
+ *
+ * For overlayfs this should be the overlay inode, not the real inode returned
+ * by file_inode(). For any other fs file_inode(filp) and locks_inode(filp) are
+ * equal.
+ */
+static inline struct inode *locks_inode(const struct file *f)
+{
+ return f->f_path.dentry->d_inode;
+}
+
#ifdef CONFIG_FILE_LOCKING
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
- return locks_lock_inode_wait(file_inode(filp), fl);
+ return locks_lock_inode_wait(locks_inode(filp), fl);
}
struct fasync_struct {
S_VERSION = 8,
};
-extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
static inline void file_accessed(struct file *file)
{
static inline int locks_verify_locked(struct file *file)
{
- if (mandatory_lock(file_inode(file)))
+ if (mandatory_lock(locks_inode(file)))
return locks_mandatory_locked(file);
return 0;
}
#define buffer_migrate_page NULL
#endif
- extern int inode_change_ok(const struct inode *, struct iattr *);
+ extern int setattr_prepare(struct dentry *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
#include <linux/bug.h>
#include <linux/slab.h>
#include <linux/rcupdate.h>
-
-#define ACL_UNDEFINED_ID (-1)
-
-/* a_type field in acl_user_posix_entry_t */
-#define ACL_TYPE_ACCESS (0x8000)
-#define ACL_TYPE_DEFAULT (0x4000)
-
-/* e_tag entry in struct posix_acl_entry */
-#define ACL_USER_OBJ (0x01)
-#define ACL_USER (0x02)
-#define ACL_GROUP_OBJ (0x04)
-#define ACL_GROUP (0x08)
-#define ACL_MASK (0x10)
-#define ACL_OTHER (0x20)
-
-/* permissions in the e_perm field */
-#define ACL_READ (0x04)
-#define ACL_WRITE (0x02)
-#define ACL_EXECUTE (0x01)
-//#define ACL_ADD (0x08)
-//#define ACL_DELETE (0x10)
+#include <uapi/linux/posix_acl.h>
struct posix_acl_entry {
short e_tag;
extern int posix_acl_chmod(struct inode *, umode_t);
extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **,
struct posix_acl **);
+ extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **);
extern int simple_set_acl(struct inode *, struct posix_acl *, int);
extern int simple_acl_create(struct inode *, struct inode *);
info->alloced -= pages;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
-
+ shmem_unacct_blocks(info->flags, pages);
return false;
}
percpu_counter_add(&sbinfo->used_blocks, pages);
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks, pages);
+ shmem_unacct_blocks(info->flags, pages);
}
/*
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
return addr;
sb = shm_mnt->mnt_sb;
}
- if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER)
+ if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER)
return addr;
}
struct kobj_attribute shmem_enabled_attr =
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
bool shmem_huge_enabled(struct vm_area_struct *vma)
{
struct inode *inode = file_inode(vma->vm_file);
return false;
}
}
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
#else /* !CONFIG_SHMEM */